diff options
Diffstat (limited to 'arch')
860 files changed, 13822 insertions, 11848 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index a1124481d910..af14a567b493 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -481,9 +481,6 @@ config HAVE_STACKPROTECTOR An arch should select this symbol if: - it has implemented a stack canary (e.g. __stack_chk_guard) -config CC_HAS_STACKPROTECTOR_NONE - def_bool $(cc-option,-fno-stack-protector) - config STACKPROTECTOR bool "Stack Protector buffer overflow detection" depends on HAVE_STACKPROTECTOR @@ -975,6 +972,9 @@ config HAVE_SPARSE_SYSCALL_NR entries at 4000, 5000 and 6000 locations. This option turns on syscall related optimizations for a given architecture. +config ARCH_HAS_VDSO_DATA + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/alpha/include/asm/core_apecs.h b/arch/alpha/include/asm/core_apecs.h index 0a07055bc0fe..2d9726fc02ef 100644 --- a/arch/alpha/include/asm/core_apecs.h +++ b/arch/alpha/include/asm/core_apecs.h @@ -384,7 +384,7 @@ struct el_apecs_procdata } \ } while (0) -__EXTERN_INLINE unsigned int apecs_ioread8(void __iomem *xaddr) +__EXTERN_INLINE unsigned int apecs_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -420,7 +420,7 @@ __EXTERN_INLINE void apecs_iowrite8(u8 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int apecs_ioread16(void __iomem *xaddr) +__EXTERN_INLINE unsigned int apecs_ioread16(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -456,7 +456,7 @@ __EXTERN_INLINE void apecs_iowrite16(u16 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int apecs_ioread32(void __iomem *xaddr) +__EXTERN_INLINE unsigned int apecs_ioread32(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; if (addr < APECS_DENSE_MEM) diff --git a/arch/alpha/include/asm/core_cia.h b/arch/alpha/include/asm/core_cia.h index c706a7f2b061..cb22991f6761 100644 --- a/arch/alpha/include/asm/core_cia.h +++ b/arch/alpha/include/asm/core_cia.h @@ -342,7 +342,7 @@ struct el_CIA_sysdata_mcheck { #define vuip volatile unsigned int __force * #define vulp volatile unsigned long __force * -__EXTERN_INLINE unsigned int cia_ioread8(void __iomem *xaddr) +__EXTERN_INLINE unsigned int cia_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -374,7 +374,7 @@ __EXTERN_INLINE void cia_iowrite8(u8 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int cia_ioread16(void __iomem *xaddr) +__EXTERN_INLINE unsigned int cia_ioread16(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -404,7 +404,7 @@ __EXTERN_INLINE void cia_iowrite16(u16 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int cia_ioread32(void __iomem *xaddr) +__EXTERN_INLINE unsigned int cia_ioread32(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; if (addr < CIA_DENSE_MEM) diff --git a/arch/alpha/include/asm/core_lca.h b/arch/alpha/include/asm/core_lca.h index 84d5e5b84f4f..ec86314418cb 100644 --- a/arch/alpha/include/asm/core_lca.h +++ b/arch/alpha/include/asm/core_lca.h @@ -230,7 +230,7 @@ union el_lca { } while (0) -__EXTERN_INLINE unsigned int lca_ioread8(void __iomem *xaddr) +__EXTERN_INLINE unsigned int lca_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -266,7 +266,7 @@ __EXTERN_INLINE void lca_iowrite8(u8 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int lca_ioread16(void __iomem *xaddr) +__EXTERN_INLINE unsigned int lca_ioread16(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; unsigned long result, base_and_type; @@ -302,7 +302,7 @@ __EXTERN_INLINE void lca_iowrite16(u16 b, void __iomem *xaddr) *(vuip) ((addr << 5) + base_and_type) = w; } -__EXTERN_INLINE unsigned int lca_ioread32(void __iomem *xaddr) +__EXTERN_INLINE unsigned int lca_ioread32(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; if (addr < LCA_DENSE_MEM) diff --git a/arch/alpha/include/asm/core_marvel.h b/arch/alpha/include/asm/core_marvel.h index cc6fd92d5fa9..b266e02e284b 100644 --- a/arch/alpha/include/asm/core_marvel.h +++ b/arch/alpha/include/asm/core_marvel.h @@ -332,10 +332,10 @@ struct io7 { #define vucp volatile unsigned char __force * #define vusp volatile unsigned short __force * -extern unsigned int marvel_ioread8(void __iomem *); +extern unsigned int marvel_ioread8(const void __iomem *); extern void marvel_iowrite8(u8 b, void __iomem *); -__EXTERN_INLINE unsigned int marvel_ioread16(void __iomem *addr) +__EXTERN_INLINE unsigned int marvel_ioread16(const void __iomem *addr) { return __kernel_ldwu(*(vusp)addr); } diff --git a/arch/alpha/include/asm/core_mcpcia.h b/arch/alpha/include/asm/core_mcpcia.h index b30dc128210d..cb24d1bd6141 100644 --- a/arch/alpha/include/asm/core_mcpcia.h +++ b/arch/alpha/include/asm/core_mcpcia.h @@ -267,7 +267,7 @@ extern inline int __mcpcia_is_mmio(unsigned long addr) return (addr & 0x80000000UL) == 0; } -__EXTERN_INLINE unsigned int mcpcia_ioread8(void __iomem *xaddr) +__EXTERN_INLINE unsigned int mcpcia_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; @@ -291,7 +291,7 @@ __EXTERN_INLINE void mcpcia_iowrite8(u8 b, void __iomem *xaddr) *(vuip) ((addr << 5) + hose + 0x00) = w; } -__EXTERN_INLINE unsigned int mcpcia_ioread16(void __iomem *xaddr) +__EXTERN_INLINE unsigned int mcpcia_ioread16(const void __iomem *xaddr) { unsigned long addr = (unsigned long)xaddr & MCPCIA_MEM_MASK; unsigned long hose = (unsigned long)xaddr & ~MCPCIA_MEM_MASK; @@ -315,7 +315,7 @@ __EXTERN_INLINE void mcpcia_iowrite16(u16 b, void __iomem *xaddr) *(vuip) ((addr << 5) + hose + 0x08) = w; } -__EXTERN_INLINE unsigned int mcpcia_ioread32(void __iomem *xaddr) +__EXTERN_INLINE unsigned int mcpcia_ioread32(const void __iomem *xaddr) { unsigned long addr = (unsigned long)xaddr; diff --git a/arch/alpha/include/asm/core_t2.h b/arch/alpha/include/asm/core_t2.h index e0b33d09e93a..12bb7addc789 100644 --- a/arch/alpha/include/asm/core_t2.h +++ b/arch/alpha/include/asm/core_t2.h @@ -572,7 +572,7 @@ __EXTERN_INLINE int t2_is_mmio(const volatile void __iomem *addr) it doesn't make sense to merge the pio and mmio routines. */ #define IOPORT(OS, NS) \ -__EXTERN_INLINE unsigned int t2_ioread##NS(void __iomem *xaddr) \ +__EXTERN_INLINE unsigned int t2_ioread##NS(const void __iomem *xaddr) \ { \ if (t2_is_mmio(xaddr)) \ return t2_read##OS(xaddr); \ diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h index a4d0c19f1e79..1f6a909d1fa5 100644 --- a/arch/alpha/include/asm/io.h +++ b/arch/alpha/include/asm/io.h @@ -150,9 +150,9 @@ static inline void generic_##NAME(TYPE b, QUAL void __iomem *addr) \ alpha_mv.mv_##NAME(b, addr); \ } -REMAP1(unsigned int, ioread8, /**/) -REMAP1(unsigned int, ioread16, /**/) -REMAP1(unsigned int, ioread32, /**/) +REMAP1(unsigned int, ioread8, const) +REMAP1(unsigned int, ioread16, const) +REMAP1(unsigned int, ioread32, const) REMAP1(u8, readb, const volatile) REMAP1(u16, readw, const volatile) REMAP1(u32, readl, const volatile) @@ -307,7 +307,7 @@ static inline int __is_mmio(const volatile void __iomem *addr) */ #if IO_CONCAT(__IO_PREFIX,trivial_io_bw) -extern inline unsigned int ioread8(void __iomem *addr) +extern inline unsigned int ioread8(const void __iomem *addr) { unsigned int ret; mb(); @@ -316,7 +316,7 @@ extern inline unsigned int ioread8(void __iomem *addr) return ret; } -extern inline unsigned int ioread16(void __iomem *addr) +extern inline unsigned int ioread16(const void __iomem *addr) { unsigned int ret; mb(); @@ -359,7 +359,7 @@ extern inline void outw(u16 b, unsigned long port) #endif #if IO_CONCAT(__IO_PREFIX,trivial_io_lq) -extern inline unsigned int ioread32(void __iomem *addr) +extern inline unsigned int ioread32(const void __iomem *addr) { unsigned int ret; mb(); @@ -489,10 +489,10 @@ extern inline void writeq(u64 b, volatile void __iomem *addr) } #endif -#define ioread16be(p) be16_to_cpu(ioread16(p)) -#define ioread32be(p) be32_to_cpu(ioread32(p)) -#define iowrite16be(v,p) iowrite16(cpu_to_be16(v), (p)) -#define iowrite32be(v,p) iowrite32(cpu_to_be32(v), (p)) +#define ioread16be(p) swab16(ioread16(p)) +#define ioread32be(p) swab32(ioread32(p)) +#define iowrite16be(v,p) iowrite16(swab16(v), (p)) +#define iowrite32be(v,p) iowrite32(swab32(v), (p)) #define inb_p inb #define inw_p inw diff --git a/arch/alpha/include/asm/io_trivial.h b/arch/alpha/include/asm/io_trivial.h index ba3d8f0cfe0c..a1a29cbe02fa 100644 --- a/arch/alpha/include/asm/io_trivial.h +++ b/arch/alpha/include/asm/io_trivial.h @@ -7,15 +7,15 @@ #if IO_CONCAT(__IO_PREFIX,trivial_io_bw) __EXTERN_INLINE unsigned int -IO_CONCAT(__IO_PREFIX,ioread8)(void __iomem *a) +IO_CONCAT(__IO_PREFIX,ioread8)(const void __iomem *a) { - return __kernel_ldbu(*(volatile u8 __force *)a); + return __kernel_ldbu(*(const volatile u8 __force *)a); } __EXTERN_INLINE unsigned int -IO_CONCAT(__IO_PREFIX,ioread16)(void __iomem *a) +IO_CONCAT(__IO_PREFIX,ioread16)(const void __iomem *a) { - return __kernel_ldwu(*(volatile u16 __force *)a); + return __kernel_ldwu(*(const volatile u16 __force *)a); } __EXTERN_INLINE void @@ -33,9 +33,9 @@ IO_CONCAT(__IO_PREFIX,iowrite16)(u16 b, void __iomem *a) #if IO_CONCAT(__IO_PREFIX,trivial_io_lq) __EXTERN_INLINE unsigned int -IO_CONCAT(__IO_PREFIX,ioread32)(void __iomem *a) +IO_CONCAT(__IO_PREFIX,ioread32)(const void __iomem *a) { - return *(volatile u32 __force *)a; + return *(const volatile u32 __force *)a; } __EXTERN_INLINE void @@ -73,14 +73,14 @@ IO_CONCAT(__IO_PREFIX,writew)(u16 b, volatile void __iomem *a) __EXTERN_INLINE u8 IO_CONCAT(__IO_PREFIX,readb)(const volatile void __iomem *a) { - void __iomem *addr = (void __iomem *)a; + const void __iomem *addr = (const void __iomem *)a; return IO_CONCAT(__IO_PREFIX,ioread8)(addr); } __EXTERN_INLINE u16 IO_CONCAT(__IO_PREFIX,readw)(const volatile void __iomem *a) { - void __iomem *addr = (void __iomem *)a; + const void __iomem *addr = (const void __iomem *)a; return IO_CONCAT(__IO_PREFIX,ioread16)(addr); } diff --git a/arch/alpha/include/asm/jensen.h b/arch/alpha/include/asm/jensen.h index 436dc905b6ad..916895155a88 100644 --- a/arch/alpha/include/asm/jensen.h +++ b/arch/alpha/include/asm/jensen.h @@ -305,7 +305,7 @@ __EXTERN_INLINE int jensen_is_mmio(const volatile void __iomem *addr) that it doesn't make sense to merge them. */ #define IOPORT(OS, NS) \ -__EXTERN_INLINE unsigned int jensen_ioread##NS(void __iomem *xaddr) \ +__EXTERN_INLINE unsigned int jensen_ioread##NS(const void __iomem *xaddr) \ { \ if (jensen_is_mmio(xaddr)) \ return jensen_read##OS(xaddr - 0x100000000ul); \ diff --git a/arch/alpha/include/asm/machvec.h b/arch/alpha/include/asm/machvec.h index a6b73c6d10ee..a4e96e2bec74 100644 --- a/arch/alpha/include/asm/machvec.h +++ b/arch/alpha/include/asm/machvec.h @@ -46,9 +46,9 @@ struct alpha_machine_vector void (*mv_pci_tbi)(struct pci_controller *hose, dma_addr_t start, dma_addr_t end); - unsigned int (*mv_ioread8)(void __iomem *); - unsigned int (*mv_ioread16)(void __iomem *); - unsigned int (*mv_ioread32)(void __iomem *); + unsigned int (*mv_ioread8)(const void __iomem *); + unsigned int (*mv_ioread16)(const void __iomem *); + unsigned int (*mv_ioread32)(const void __iomem *); void (*mv_iowrite8)(u8, void __iomem *); void (*mv_iowrite16)(u16, void __iomem *); diff --git a/arch/alpha/include/asm/pgalloc.h b/arch/alpha/include/asm/pgalloc.h index a1a29f60934c..9c6a24fe493d 100644 --- a/arch/alpha/include/asm/pgalloc.h +++ b/arch/alpha/include/asm/pgalloc.h @@ -5,7 +5,7 @@ #include <linux/mm.h> #include <linux/mmzone.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> /* * Allocate and free page tables. The xxx_kernel() versions are @@ -34,23 +34,4 @@ pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern pgd_t *pgd_alloc(struct mm_struct *mm); -static inline void -pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long)pgd); -} - -static inline pmd_t * -pmd_alloc_one(struct mm_struct *mm, unsigned long address) -{ - pmd_t *ret = (pmd_t *)__get_free_page(GFP_PGTABLE_USER); - return ret; -} - -static inline void -pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_page((unsigned long)pmd); -} - #endif /* _ALPHA_PGALLOC_H */ diff --git a/arch/alpha/include/asm/tlbflush.h b/arch/alpha/include/asm/tlbflush.h index f8b492408f51..94dc37cf873a 100644 --- a/arch/alpha/include/asm/tlbflush.h +++ b/arch/alpha/include/asm/tlbflush.h @@ -5,7 +5,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <asm/compiler.h> -#include <asm/pgalloc.h> #ifndef __EXTERN_INLINE #define __EXTERN_INLINE extern inline diff --git a/arch/alpha/include/asm/uaccess.h b/arch/alpha/include/asm/uaccess.h index 1fe2b56cb861..1b6f25efa247 100644 --- a/arch/alpha/include/asm/uaccess.h +++ b/arch/alpha/include/asm/uaccess.h @@ -20,7 +20,7 @@ #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) /* * Is a address valid? This does a straightforward calculation rather diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index a9fd133a7fb2..72af1e72d833 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -302,7 +302,6 @@ irongate_init_arch(void) #include <linux/agp_backend.h> #include <linux/agpgart.h> #include <linux/export.h> -#include <asm/pgalloc.h> #define GET_PAGE_DIR_OFF(addr) (addr >> 22) #define GET_PAGE_DIR_IDX(addr) (GET_PAGE_DIR_OFF(addr)) diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 1db9d0eb2922..4485b77f8658 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -23,7 +23,6 @@ #include <asm/ptrace.h> #include <asm/smp.h> #include <asm/gct.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/vga.h> @@ -807,7 +806,7 @@ void __iomem *marvel_ioportmap (unsigned long addr) } unsigned int -marvel_ioread8(void __iomem *xaddr) +marvel_ioread8(const void __iomem *xaddr) { unsigned long addr = (unsigned long) xaddr; if (__marvel_is_port_kbd(addr)) diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 2a2820fb1be6..77f5d68ed04b 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -20,7 +20,6 @@ #include <asm/ptrace.h> #include <asm/smp.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/vga.h> diff --git a/arch/alpha/kernel/io.c b/arch/alpha/kernel/io.c index 938de13adfbf..838586abb1e0 100644 --- a/arch/alpha/kernel/io.c +++ b/arch/alpha/kernel/io.c @@ -14,7 +14,7 @@ "generic", which bumps through the machine vector. */ unsigned int -ioread8(void __iomem *addr) +ioread8(const void __iomem *addr) { unsigned int ret; mb(); @@ -23,7 +23,7 @@ ioread8(void __iomem *addr) return ret; } -unsigned int ioread16(void __iomem *addr) +unsigned int ioread16(const void __iomem *addr) { unsigned int ret; mb(); @@ -32,7 +32,7 @@ unsigned int ioread16(void __iomem *addr) return ret; } -unsigned int ioread32(void __iomem *addr) +unsigned int ioread32(const void __iomem *addr) { unsigned int ret; mb(); @@ -257,7 +257,7 @@ EXPORT_SYMBOL(readq_relaxed); /* * Read COUNT 8-bit bytes from port PORT into memory starting at SRC. */ -void ioread8_rep(void __iomem *port, void *dst, unsigned long count) +void ioread8_rep(const void __iomem *port, void *dst, unsigned long count) { while ((unsigned long)dst & 0x3) { if (!count) @@ -300,7 +300,7 @@ EXPORT_SYMBOL(insb); * the interfaces seems to be slow: just using the inlined version * of the inw() breaks things. */ -void ioread16_rep(void __iomem *port, void *dst, unsigned long count) +void ioread16_rep(const void __iomem *port, void *dst, unsigned long count) { if (unlikely((unsigned long)dst & 0x3)) { if (!count) @@ -340,7 +340,7 @@ EXPORT_SYMBOL(insw); * but the interfaces seems to be slow: just using the inlined version * of the inl() breaks things. */ -void ioread32_rep(void __iomem *port, void *dst, unsigned long count) +void ioread32_rep(const void __iomem *port, void *dst, unsigned long count) { if (unlikely((unsigned long)dst & 0x3)) { while (count--) { diff --git a/arch/alpha/kernel/machvec_impl.h b/arch/alpha/kernel/machvec_impl.h index 38f045ec5cd2..393d5d6ca5d2 100644 --- a/arch/alpha/kernel/machvec_impl.h +++ b/arch/alpha/kernel/machvec_impl.h @@ -7,8 +7,6 @@ * This file has goodies to help simplify instantiation of machine vectors. */ -#include <asm/pgalloc.h> - /* Whee. These systems don't have an HAE: IRONGATE, MARVEL, POLARIS, TSUNAMI, TITAN, WILDFIRE Fix things up for the GENERIC kernel by defining the HAE address diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 631cc17410d1..f4dd9f3f3001 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -36,7 +36,6 @@ #include <asm/io.h> #include <asm/irq.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index a28fb211881d..ec8bed9e7b75 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -249,7 +249,7 @@ 316 common mlockall sys_mlockall 317 common munlockall sys_munlockall 318 common sysinfo sys_sysinfo -319 common _sysctl sys_sysctl +319 common _sysctl sys_ni_syscall # 320 was sys_idle 321 common oldumount sys_oldumount 322 common swapon sys_swapon diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index c2303a8c2b9f..09172f017efc 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -25,6 +25,7 @@ #include <linux/interrupt.h> #include <linux/extable.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *); @@ -116,6 +117,7 @@ do_page_fault(unsigned long address, unsigned long mmcsr, #endif if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -148,7 +150,7 @@ retry: /* If for any reason at all we couldn't handle the fault, make sure we exit gracefully rather than endlessly redo the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -164,10 +166,6 @@ retry: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 5ad6087de1d6..0636e254a22f 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -17,7 +17,6 @@ #include <linux/module.h> #include <asm/hwrpb.h> -#include <asm/pgalloc.h> #include <asm/sections.h> pg_data_t node_data[MAX_NUMNODES]; diff --git a/arch/arc/include/asm/segment.h b/arch/arc/include/asm/segment.h index 6a2a5be5026d..871f8ab11bfd 100644 --- a/arch/arc/include/asm/segment.h +++ b/arch/arc/include/asm/segment.h @@ -14,8 +14,7 @@ typedef unsigned long mm_segment_t; #define KERNEL_DS MAKE_MM_SEG(0) #define USER_DS MAKE_MM_SEG(TASK_SIZE) - -#define segment_eq(a, b) ((a) == (b)) +#define uaccess_kernel() (get_fs() == KERNEL_DS) #endif /* __ASSEMBLY__ */ #endif /* __ASMARC_SEGMENT_H */ diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index 105420c23c8b..efeba1fe7252 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -91,7 +91,7 @@ fault: goto fail; mmap_read_lock(current->mm); - ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr, + ret = fixup_user_fault(current->mm, (unsigned long) uaddr, FAULT_FLAG_WRITE, NULL); mmap_read_unlock(current->mm); @@ -296,11 +296,6 @@ void flush_thread(void) { } -int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) -{ - return 0; -} - int elf_check_arch(const struct elf32_hdr *x) { unsigned int eflags; diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 72f5405a7ec5..f5657cb68e4f 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -13,7 +13,6 @@ #include <linux/kdebug.h> #include <linux/perf_event.h> #include <linux/mm_types.h> -#include <asm/pgalloc.h> #include <asm/mmu.h> /* @@ -106,6 +105,7 @@ void do_page_fault(unsigned long address, struct pt_regs *regs) if (write) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -131,7 +131,7 @@ retry: goto bad_area; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -156,22 +156,9 @@ bad_area: * Major/minor page fault accounting * (in case of retry we only land here once) */ - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - - if (likely(!(fault & VM_FAULT_ERROR))) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } - + if (likely(!(fault & VM_FAULT_ERROR))) /* Normal return path: fault Handled Gracefully */ return; - } if (!user_mode(regs)) goto no_context; diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index e7bdc2ac1c87..f886ac69d8ad 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -14,7 +14,6 @@ #include <linux/module.h> #include <linux/highmem.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/sections.h> #include <asm/arcregs.h> diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 00602a6fba04..b1147b7f2c8d 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -84,9 +84,8 @@ endif # -fstack-protector-strong triggers protection checks in this code, # but it is being used too early to link to meaningful stack_chk logic. -nossp-flags-$(CONFIG_CC_HAS_STACKPROTECTOR_NONE) := -fno-stack-protector $(foreach o, $(libfdt_objs) atags_to_fdt.o, \ - $(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt $(nossp-flags-y))) + $(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt -fno-stack-protector)) # These were previously generated C files. When you are building the kernel # with O=, make sure to remove the stale files in the output tree. Otherwise, @@ -103,13 +102,9 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -ifeq ($(CONFIG_FUNCTION_TRACER),y) -ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) -endif - ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \ -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN) +ccflags-remove-$(CONFIG_FUNCTION_TRACER) += -pg asflags-y := -DZIMAGE # Supply kernel BSS size to the decompressor via a linker symbol. diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi index 45de2ff6a777..b88d0caa4b2d 100644 --- a/arch/arm/boot/dts/am33xx-l4.dtsi +++ b/arch/arm/boot/dts/am33xx-l4.dtsi @@ -290,7 +290,7 @@ am33xx_pinmux: pinmux@800 { compatible = "pinctrl-single"; reg = <0x800 0x238>; - #pinctrl-cells = <1>; + #pinctrl-cells = <2>; pinctrl-single,register-width = <32>; pinctrl-single,function-mask = <0x7f>; }; diff --git a/arch/arm/configs/am200epdkit_defconfig b/arch/arm/configs/am200epdkit_defconfig index f56ac394caf1..4e49d6cb2f62 100644 --- a/arch/arm/configs/am200epdkit_defconfig +++ b/arch/arm/configs/am200epdkit_defconfig @@ -3,7 +3,6 @@ CONFIG_LOCALVERSION="gum" CONFIG_SYSVIPC=y CONFIG_SYSFS_DEPRECATED_V2=y CONFIG_EXPERT=y -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig index bd7b7f945e01..81665b7abf83 100644 --- a/arch/arm/configs/ezx_defconfig +++ b/arch/arm/configs/ezx_defconfig @@ -236,8 +236,6 @@ CONFIG_MEDIA_TUNER_CUSTOMISE=y # CONFIG_MEDIA_TUNER_MXL5007T is not set # CONFIG_MEDIA_TUNER_MC44S803 is not set # CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_MT9M111=y CONFIG_VIDEO_PXA27x=y # CONFIG_V4L_USB_DRIVERS is not set CONFIG_RADIO_TEA5764=y diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig index 05c5515fa871..ae15a2a33802 100644 --- a/arch/arm/configs/imote2_defconfig +++ b/arch/arm/configs/imote2_defconfig @@ -217,8 +217,6 @@ CONFIG_MEDIA_TUNER_CUSTOMISE=y # CONFIG_MEDIA_TUNER_MXL5007T is not set # CONFIG_MEDIA_TUNER_MC44S803 is not set # CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_MT9M111=y CONFIG_VIDEO_PXA27x=y # CONFIG_V4L_USB_DRIVERS is not set # CONFIG_RADIO_ADAPTERS is not set diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 3df90fc38398..f5f1111f2118 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -110,7 +110,6 @@ CONFIG_REGULATOR_MC13892=y CONFIG_MEDIA_SUPPORT=y CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_V4L_PLATFORM_DRIVERS=y -CONFIG_SOC_CAMERA=y CONFIG_V4L_MEM2MEM_DRIVERS=y CONFIG_VIDEO_CODA=y CONFIG_FB=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index cb335478ac37..82d3ffb18e70 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -272,7 +272,6 @@ CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m CONFIG_V4L_PLATFORM_DRIVERS=y CONFIG_VIDEO_MUX=y -CONFIG_SOC_CAMERA=y CONFIG_V4L_MEM2MEM_DRIVERS=y CONFIG_VIDEO_CODA=m CONFIG_VIDEO_IMX_PXP=y diff --git a/arch/arm/configs/pxa_defconfig b/arch/arm/configs/pxa_defconfig index 1dc7e9d7a294..d7b9eaf4783c 100644 --- a/arch/arm/configs/pxa_defconfig +++ b/arch/arm/configs/pxa_defconfig @@ -447,11 +447,8 @@ CONFIG_VIDEO_V4L2_SUBDEV_API=y CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m CONFIG_V4L_PLATFORM_DRIVERS=y -CONFIG_SOC_CAMERA=m -CONFIG_SOC_CAMERA_PLATFORM=m CONFIG_VIDEO_PXA27x=m CONFIG_V4L_MEM2MEM_DRIVERS=y -CONFIG_SOC_CAMERA_MT9M111=m CONFIG_DRM=m CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y diff --git a/arch/arm/configs/sama5_defconfig b/arch/arm/configs/sama5_defconfig index 7b7e333157fe..037d3a718a60 100644 --- a/arch/arm/configs/sama5_defconfig +++ b/arch/arm/configs/sama5_defconfig @@ -155,9 +155,7 @@ CONFIG_REGULATOR_PWM=m CONFIG_MEDIA_SUPPORT=y CONFIG_MEDIA_CAMERA_SUPPORT=y CONFIG_V4L_PLATFORM_DRIVERS=y -CONFIG_SOC_CAMERA=y CONFIG_VIDEO_ATMEL_ISI=y -CONFIG_SOC_CAMERA_OV2640=m CONFIG_DRM=y CONFIG_DRM_ATMEL_HLCDC=y CONFIG_DRM_PANEL_SIMPLE=y diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h index c675bc0d5aa8..be666f58bf7a 100644 --- a/arch/arm/include/asm/device.h +++ b/arch/arm/include/asm/device.h @@ -9,9 +9,6 @@ struct dev_archdata { #ifdef CONFIG_DMABOUNCE struct dmabounce_device_info *dmabounce; #endif -#ifdef CONFIG_IOMMU_API - void *iommu; /* private IOMMU data */ -#endif #ifdef CONFIG_ARM_DMA_USE_IOMMU struct dma_iommu_mapping *mapping; #endif diff --git a/arch/arm/include/asm/pgalloc.h b/arch/arm/include/asm/pgalloc.h index 069da393110c..15f4674715f8 100644 --- a/arch/arm/include/asm/pgalloc.h +++ b/arch/arm/include/asm/pgalloc.h @@ -22,17 +22,6 @@ #ifdef CONFIG_ARM_LPAE -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pmd_t *)get_zeroed_page(GFP_KERNEL); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - free_page((unsigned long)pmd); -} - static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) { set_pud(pud, __pud(__pa(pmd) | PMD_TYPE_TABLE)); @@ -76,6 +65,7 @@ static inline void clean_pte_table(pte_t *pte) #define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL #define __HAVE_ARCH_PTE_ALLOC_ONE +#define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> static inline pte_t * diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h index 4d4e7b6aabff..9415222b49ad 100644 --- a/arch/arm/include/asm/tlb.h +++ b/arch/arm/include/asm/tlb.h @@ -27,7 +27,6 @@ #else /* !CONFIG_MMU */ #include <linux/swap.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> static inline void __tlb_remove_table(void *_table) diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index b5fdd30252f8..a13d90206472 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -76,7 +76,7 @@ static inline void set_fs(mm_segment_t fs) modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER); } -#define segment_eq(a, b) ((a) == (b)) +#define uaccess_kernel() (get_fs() == KERNEL_DS) /* * We use 33-bit arithmetic here. Success returns zero, failure returns @@ -267,7 +267,7 @@ extern int __put_user_8(void *, unsigned long long); */ #define USER_DS KERNEL_DS -#define segment_eq(a, b) (1) +#define uaccess_kernel() (true) #define __addr_ok(addr) ((void)(addr), 1) #define __range_ok(addr, size) ((void)(addr), 0) #define get_fs() (KERNEL_DS) diff --git a/arch/arm/include/asm/vdso/gettimeofday.h b/arch/arm/include/asm/vdso/gettimeofday.h index 1b207cf07697..2134cbd5469f 100644 --- a/arch/arm/include/asm/vdso/gettimeofday.h +++ b/arch/arm/include/asm/vdso/gettimeofday.h @@ -113,7 +113,8 @@ static inline bool arm_vdso_hres_capable(void) } #define __arch_vdso_hres_capable arm_vdso_hres_capable -static __always_inline u64 __arch_get_hw_counter(int clock_mode) +static __always_inline u64 __arch_get_hw_counter(int clock_mode, + const struct vdso_data *vd) { #ifdef CONFIG_ARM_ARCH_TIMER u64 cycle_now; diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 974b6c64d3e6..5d84ad333f05 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -11,7 +11,6 @@ #include <linux/irq.h> #include <linux/memblock.h> #include <linux/of_fdt.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/fncpy.h> diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 3395be186c7d..8e6ace03e960 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -281,21 +281,6 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs) return 1; } -/* - * fill in the fpe structure for a core dump... - */ -int dump_fpu (struct pt_regs *regs, struct user_fp *fp) -{ - struct thread_info *thread = current_thread_info(); - int used_math = thread->used_cp[1] | thread->used_cp[2]; - - if (used_math) - memcpy(fp, &thread->fpstate.soft, sizeof (*fp)); - - return used_math != 0; -} -EXPORT_SYMBOL(dump_fpu); - unsigned long get_wchan(struct task_struct *p) { struct stackframe frame; diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index ab2568996ddb..c9dc912b83f0 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -713,7 +713,9 @@ struct page *get_signal_page(void) /* Defer to generic check */ asmlinkage void addr_limit_check_failed(void) { +#ifdef CONFIG_MMU addr_limit_user_check(); +#endif } #ifdef CONFIG_DEBUG_RSEQ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 9a6432557871..5d9da61eff62 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -37,7 +37,6 @@ #include <asm/idmap.h> #include <asm/topology.h> #include <asm/mmu_context.h> -#include <asm/pgalloc.h> #include <asm/procinfo.h> #include <asm/processor.h> #include <asm/sections.h> diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c index d2c9338d74e8..24bd20564be7 100644 --- a/arch/arm/kernel/suspend.c +++ b/arch/arm/kernel/suspend.c @@ -7,7 +7,6 @@ #include <asm/bugs.h> #include <asm/cacheflush.h> #include <asm/idmap.h> -#include <asm/pgalloc.h> #include <asm/memory.h> #include <asm/smp_plat.h> #include <asm/suspend.h> diff --git a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c index c0350bc20941..3da4c0920198 100644 --- a/arch/arm/mach-imx/mach-imx27_visstrim_m10.c +++ b/arch/arm/mach-imx/mach-imx27_visstrim_m10.c @@ -19,7 +19,6 @@ #include <linux/dma-mapping.h> #include <linux/leds.h> #include <linux/platform_data/asoc-mx27vis.h> -#include <media/soc_camera.h> #include <sound/tlv320aic32x4.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -191,34 +190,6 @@ static const struct gpio visstrim_m10_gpios[] __initconst = { }; /* Camera */ -static int visstrim_camera_power(struct device *dev, int on) -{ - gpio_set_value(TVP5150_PWDN, on); - - return 0; -}; - -static int visstrim_camera_reset(struct device *dev) -{ - gpio_set_value(TVP5150_RSTN, 0); - ndelay(500); - gpio_set_value(TVP5150_RSTN, 1); - - return 0; -}; - -static struct i2c_board_info visstrim_i2c_camera = { - I2C_BOARD_INFO("tvp5150", 0x5d), -}; - -static struct soc_camera_link iclink_tvp5150 = { - .bus_id = 0, - .board_info = &visstrim_i2c_camera, - .i2c_adapter_id = 0, - .power = visstrim_camera_power, - .reset = visstrim_camera_reset, -}; - static struct mx2_camera_platform_data visstrim_camera = { .flags = MX2_CAMERA_CCIR | MX2_CAMERA_CCIR_INTERLACE | MX2_CAMERA_PCLK_SAMPLE_RISING, @@ -549,8 +520,6 @@ static void __init visstrim_m10_late_init(void) imx_add_platform_device("mx27vis", 0, NULL, 0, &snd_mx27vis_pdata, sizeof(snd_mx27vis_pdata)); - platform_device_register_resndata(NULL, "soc-camera-pdrv", 0, NULL, 0, - &iclink_tvp5150, sizeof(iclink_tvp5150)); gpio_led_register_device(0, &visstrim_m10_led_data); diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index 8d32894ecd2e..2ee527c00284 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -29,8 +29,6 @@ #include <linux/io.h> #include <linux/platform_data/gpio-omap.h> -#include <media/soc_camera.h> - #include <asm/serial.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> @@ -40,7 +38,6 @@ #include <mach/mux.h> #include <mach/hardware.h> -#include "camera.h" #include <mach/usb.h> #include "ams-delta-fiq.h" @@ -459,12 +456,6 @@ static struct gpiod_lookup_table leds_gpio_table = { }, }; -static struct i2c_board_info ams_delta_camera_board_info[] = { - { - I2C_BOARD_INFO("ov6650", 0x60), - }, -}; - #ifdef CONFIG_LEDS_TRIGGERS DEFINE_LED_TRIGGER(ams_delta_camera_led_trigger); @@ -483,27 +474,6 @@ static int ams_delta_camera_power(struct device *dev, int power) #define ams_delta_camera_power NULL #endif -static struct soc_camera_link ams_delta_iclink = { - .bus_id = 0, /* OMAP1 SoC camera bus */ - .i2c_adapter_id = 1, - .board_info = &ams_delta_camera_board_info[0], - .module_name = "ov6650", - .power = ams_delta_camera_power, -}; - -static struct platform_device ams_delta_camera_device = { - .name = "soc-camera-pdrv", - .id = 0, - .dev = { - .platform_data = &ams_delta_iclink, - }, -}; - -static struct omap1_cam_platform_data ams_delta_camera_platform_data = { - .camexclk_khz = 12000, /* default 12MHz clock, no extra DPLL */ - .lclk_khz_max = 1334, /* results in 5fps CIF, 10fps QCIF */ -}; - static struct platform_device ams_delta_audio_device = { .name = "ams-delta-audio", .id = -1, @@ -598,7 +568,6 @@ static struct platform_device *ams_delta_devices[] __initdata = { &latch1_gpio_device, &latch2_gpio_device, &ams_delta_kp_device, - &ams_delta_camera_device, &ams_delta_audio_device, &ams_delta_serio_device, &ams_delta_nand_device, @@ -750,7 +719,6 @@ static void __init ams_delta_init(void) omap_register_i2c_bus(1, 100, NULL, 0); omap1_usb_init(&ams_delta_usb_config); - omap1_set_camera_info(&ams_delta_camera_platform_data); #ifdef CONFIG_LEDS_TRIGGERS led_trigger_register_simple("ams_delta_camera", &ams_delta_camera_led_trigger); diff --git a/arch/arm/mach-omap1/camera.h b/arch/arm/mach-omap1/camera.h deleted file mode 100644 index 8018f410d024..000000000000 --- a/arch/arm/mach-omap1/camera.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_ARCH_CAMERA_H_ -#define __ASM_ARCH_CAMERA_H_ - -#include <linux/platform_data/media/omap1_camera.h> - -void omap1_camera_init(void *); - -static inline void omap1_set_camera_info(struct omap1_cam_platform_data *info) -{ - omap1_camera_init(info); -} - -#endif /* __ASM_ARCH_CAMERA_H_ */ diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c index 3c4900ac72fc..eb0f09edb3d1 100644 --- a/arch/arm/mach-omap1/devices.c +++ b/arch/arm/mach-omap1/devices.c @@ -21,7 +21,6 @@ #include <mach/mux.h> #include <mach/omap7xx.h> -#include "camera.h" #include <mach/hardware.h> #include "common.h" @@ -258,48 +257,6 @@ static inline void omap_init_spi100k(void) } #endif - -#define OMAP1_CAMERA_BASE 0xfffb6800 -#define OMAP1_CAMERA_IOSIZE 0x1c - -static struct resource omap1_camera_resources[] = { - [0] = { - .start = OMAP1_CAMERA_BASE, - .end = OMAP1_CAMERA_BASE + OMAP1_CAMERA_IOSIZE - 1, - .flags = IORESOURCE_MEM, - }, - [1] = { - .start = INT_CAMERA, - .flags = IORESOURCE_IRQ, - }, -}; - -static u64 omap1_camera_dma_mask = DMA_BIT_MASK(32); - -static struct platform_device omap1_camera_device = { - .name = "omap1-camera", - .id = 0, /* This is used to put cameras on this interface */ - .dev = { - .dma_mask = &omap1_camera_dma_mask, - .coherent_dma_mask = DMA_BIT_MASK(32), - }, - .num_resources = ARRAY_SIZE(omap1_camera_resources), - .resource = omap1_camera_resources, -}; - -void __init omap1_camera_init(void *info) -{ - struct platform_device *dev = &omap1_camera_device; - int ret; - - dev->dev.platform_data = info; - - ret = platform_device_register(dev); - if (ret) - dev_err(&dev->dev, "unable to register device: %d\n", ret); -} - - /*-------------------------------------------------------------------------*/ static inline void omap_init_sti(void) {} diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c index 67fa28532a3a..9fba98c2313a 100644 --- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c +++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c @@ -42,7 +42,6 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/smp_scu.h> -#include <asm/pgalloc.h> #include <asm/suspend.h> #include <asm/virt.h> #include <asm/hardware/cache-l2x0.h> diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c index 4df443943579..b4a5fe02a0af 100644 --- a/arch/arm/mach-pxa/palmz72.c +++ b/arch/arm/mach-pxa/palmz72.c @@ -47,8 +47,6 @@ #include "pm.h" #include <linux/platform_data/media/camera-pxa.h> -#include <media/soc_camera.h> - #include "generic.h" #include "devices.h" @@ -272,115 +270,6 @@ static int __init palmz72_pm_init(void) device_initcall(palmz72_pm_init); #endif -/****************************************************************************** - * SoC Camera - ******************************************************************************/ -#if defined(CONFIG_SOC_CAMERA_OV9640) || \ - defined(CONFIG_SOC_CAMERA_OV9640_MODULE) -static struct pxacamera_platform_data palmz72_pxacamera_platform_data = { - .flags = PXA_CAMERA_MASTER | PXA_CAMERA_DATAWIDTH_8 | - PXA_CAMERA_PCLK_EN | PXA_CAMERA_MCLK_EN, - .mclk_10khz = 2600, -}; - -/* Board I2C devices. */ -static struct i2c_board_info palmz72_i2c_device[] = { - { - I2C_BOARD_INFO("ov9640", 0x30), - } -}; - -static int palmz72_camera_power(struct device *dev, int power) -{ - gpio_set_value(GPIO_NR_PALMZ72_CAM_PWDN, !power); - mdelay(50); - return 0; -} - -static int palmz72_camera_reset(struct device *dev) -{ - gpio_set_value(GPIO_NR_PALMZ72_CAM_RESET, 1); - mdelay(50); - gpio_set_value(GPIO_NR_PALMZ72_CAM_RESET, 0); - mdelay(50); - return 0; -} - -static struct soc_camera_link palmz72_iclink = { - .bus_id = 0, /* Match id in pxa27x_device_camera in device.c */ - .board_info = &palmz72_i2c_device[0], - .i2c_adapter_id = 0, - .module_name = "ov96xx", - .power = &palmz72_camera_power, - .reset = &palmz72_camera_reset, - .flags = SOCAM_DATAWIDTH_8, -}; - -static struct gpiod_lookup_table palmz72_i2c_gpiod_table = { - .dev_id = "i2c-gpio.0", - .table = { - GPIO_LOOKUP_IDX("gpio-pxa", 118, NULL, 0, - GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), - GPIO_LOOKUP_IDX("gpio-pxa", 117, NULL, 1, - GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN), - }, -}; - -static struct i2c_gpio_platform_data palmz72_i2c_bus_data = { - .udelay = 10, - .timeout = 100, -}; - -static struct platform_device palmz72_i2c_bus_device = { - .name = "i2c-gpio", - .id = 0, /* we use this as a replacement for i2c-pxa */ - .dev = { - .platform_data = &palmz72_i2c_bus_data, - } -}; - -static struct platform_device palmz72_camera = { - .name = "soc-camera-pdrv", - .id = -1, - .dev = { - .platform_data = &palmz72_iclink, - }, -}; - -/* Here we request the camera GPIOs and configure them. We power up the camera - * module, deassert the reset pin, but put it into powerdown (low to no power - * consumption) mode. This allows us to later bring the module up fast. */ -static struct gpio palmz72_camera_gpios[] = { - { GPIO_NR_PALMZ72_CAM_POWER, GPIOF_INIT_HIGH,"Camera DVDD" }, - { GPIO_NR_PALMZ72_CAM_RESET, GPIOF_INIT_LOW, "Camera RESET" }, - { GPIO_NR_PALMZ72_CAM_PWDN, GPIOF_INIT_LOW, "Camera PWDN" }, -}; - -static inline void __init palmz72_cam_gpio_init(void) -{ - int ret; - - ret = gpio_request_array(ARRAY_AND_SIZE(palmz72_camera_gpios)); - if (!ret) - gpio_free_array(ARRAY_AND_SIZE(palmz72_camera_gpios)); - else - printk(KERN_ERR "Camera GPIO init failed!\n"); - - return; -} - -static void __init palmz72_camera_init(void) -{ - palmz72_cam_gpio_init(); - pxa_set_camera_info(&palmz72_pxacamera_platform_data); - gpiod_add_lookup_table(&palmz72_i2c_gpiod_table); - platform_device_register(&palmz72_i2c_bus_device); - platform_device_register(&palmz72_camera); -} -#else -static inline void palmz72_camera_init(void) {} -#endif - static struct gpiod_lookup_table palmz72_mci_gpio_table = { .dev_id = "pxa2xx-mci.0", .table = { @@ -416,7 +305,6 @@ static void __init palmz72_init(void) palm27x_pmic_init(); palmz72_kpc_init(); palmz72_leds_init(); - palmz72_camera_init(); } MACHINE_START(PALMZ72, "Palm Zire72") diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c index bf613f88d70b..8dfcc366d0fe 100644 --- a/arch/arm/mach-pxa/pcm990-baseboard.c +++ b/arch/arm/mach-pxa/pcm990-baseboard.c @@ -24,10 +24,6 @@ #include <linux/pwm.h> #include <linux/pwm_backlight.h> -#include <media/i2c/mt9v022.h> -#include <media/soc_camera.h> - -#include <linux/platform_data/media/camera-pxa.h> #include <asm/mach/map.h> #include "pxa27x.h" #include <mach/audio.h> @@ -375,149 +371,6 @@ static struct pxaohci_platform_data pcm990_ohci_platform_data = { }; /* - * PXA27x Camera specific stuff - */ -#if defined(CONFIG_VIDEO_PXA27x) || defined(CONFIG_VIDEO_PXA27x_MODULE) -static unsigned long pcm990_camera_pin_config[] = { - /* CIF */ - GPIO98_CIF_DD_0, - GPIO105_CIF_DD_1, - GPIO104_CIF_DD_2, - GPIO103_CIF_DD_3, - GPIO95_CIF_DD_4, - GPIO94_CIF_DD_5, - GPIO93_CIF_DD_6, - GPIO108_CIF_DD_7, - GPIO107_CIF_DD_8, - GPIO106_CIF_DD_9, - GPIO42_CIF_MCLK, - GPIO45_CIF_PCLK, - GPIO43_CIF_FV, - GPIO44_CIF_LV, -}; - -/* - * CICR4: PCLK_EN: Pixel clock is supplied by the sensor - * MCLK_EN: Master clock is generated by PXA - * PCP: Data sampled on the falling edge of pixel clock - */ -struct pxacamera_platform_data pcm990_pxacamera_platform_data = { - .flags = PXA_CAMERA_MASTER | PXA_CAMERA_DATAWIDTH_8 | PXA_CAMERA_DATAWIDTH_10 | - PXA_CAMERA_PCLK_EN | PXA_CAMERA_MCLK_EN/* | PXA_CAMERA_PCP*/, - .mclk_10khz = 1000, -}; - -#include <linux/platform_data/pca953x.h> - -static struct pca953x_platform_data pca9536_data = { - .gpio_base = PXA_NR_BUILTIN_GPIO, -}; - -static int gpio_bus_switch = -EINVAL; - -static int pcm990_camera_set_bus_param(struct soc_camera_link *link, - unsigned long flags) -{ - if (gpio_bus_switch < 0) { - if (flags == SOCAM_DATAWIDTH_10) - return 0; - else - return -EINVAL; - } - - if (flags & SOCAM_DATAWIDTH_8) - gpio_set_value_cansleep(gpio_bus_switch, 1); - else - gpio_set_value_cansleep(gpio_bus_switch, 0); - - return 0; -} - -static unsigned long pcm990_camera_query_bus_param(struct soc_camera_link *link) -{ - int ret; - - if (gpio_bus_switch < 0) { - ret = gpio_request(PXA_NR_BUILTIN_GPIO, "camera"); - if (!ret) { - gpio_bus_switch = PXA_NR_BUILTIN_GPIO; - gpio_direction_output(gpio_bus_switch, 0); - } - } - - if (gpio_bus_switch >= 0) - return SOCAM_DATAWIDTH_8 | SOCAM_DATAWIDTH_10; - else - return SOCAM_DATAWIDTH_10; -} - -static void pcm990_camera_free_bus(struct soc_camera_link *link) -{ - if (gpio_bus_switch < 0) - return; - - gpio_free(gpio_bus_switch); - gpio_bus_switch = -EINVAL; -} - -/* Board I2C devices. */ -static struct i2c_board_info __initdata pcm990_i2c_devices[] = { - { - /* Must initialize before the camera(s) */ - I2C_BOARD_INFO("pca9536", 0x41), - .platform_data = &pca9536_data, - }, -}; - -static struct mt9v022_platform_data mt9v022_pdata = { - .y_skip_top = 1, -}; - -static struct i2c_board_info pcm990_camera_i2c[] = { - { - I2C_BOARD_INFO("mt9v022", 0x48), - }, { - I2C_BOARD_INFO("mt9m001", 0x5d), - }, -}; - -static struct soc_camera_link iclink[] = { - { - .bus_id = 0, /* Must match with the camera ID */ - .board_info = &pcm990_camera_i2c[0], - .priv = &mt9v022_pdata, - .i2c_adapter_id = 0, - .query_bus_param = pcm990_camera_query_bus_param, - .set_bus_param = pcm990_camera_set_bus_param, - .free_bus = pcm990_camera_free_bus, - }, { - .bus_id = 0, /* Must match with the camera ID */ - .board_info = &pcm990_camera_i2c[1], - .i2c_adapter_id = 0, - .query_bus_param = pcm990_camera_query_bus_param, - .set_bus_param = pcm990_camera_set_bus_param, - .free_bus = pcm990_camera_free_bus, - }, -}; - -static struct platform_device pcm990_camera[] = { - { - .name = "soc-camera-pdrv", - .id = 0, - .dev = { - .platform_data = &iclink[0], - }, - }, { - .name = "soc-camera-pdrv", - .id = 1, - .dev = { - .platform_data = &iclink[1], - }, - }, -}; -#endif /* CONFIG_VIDEO_PXA27x ||CONFIG_VIDEO_PXA27x_MODULE */ - -/* * system init for baseboard usage. Will be called by pcm027 init. * * Add platform devices present on this baseboard and init @@ -551,15 +404,5 @@ void __init pcm990_baseboard_init(void) pxa_set_i2c_info(NULL); pxa_set_ac97_info(NULL); -#if defined(CONFIG_VIDEO_PXA27x) || defined(CONFIG_VIDEO_PXA27x_MODULE) - pxa2xx_mfp_config(ARRAY_AND_SIZE(pcm990_camera_pin_config)); - pxa_set_camera_info(&pcm990_pxacamera_platform_data); - - i2c_register_board_info(0, ARRAY_AND_SIZE(pcm990_i2c_devices)); - - platform_device_register(&pcm990_camera[0]); - platform_device_register(&pcm990_camera[1]); -#endif - printk(KERN_INFO "PCM-990 Evaluation baseboard initialized\n"); } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index c6550eddfce1..efa402025031 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -202,7 +202,8 @@ static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma) static vm_fault_t __kprobes __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr, - unsigned int flags, struct task_struct *tsk) + unsigned int flags, struct task_struct *tsk, + struct pt_regs *regs) { struct vm_area_struct *vma; vm_fault_t fault; @@ -224,7 +225,7 @@ good_area: goto out; } - return handle_mm_fault(vma, addr & PAGE_MASK, flags); + return handle_mm_fault(vma, addr & PAGE_MASK, flags, regs); check_stack: /* Don't allow expansion below FIRST_USER_ADDRESS */ @@ -266,6 +267,8 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -290,7 +293,7 @@ retry: #endif } - fault = __do_page_fault(mm, addr, fsr, flags, tsk); + fault = __do_page_fault(mm, addr, fsr, flags, tsk, regs); /* If we need to retry but a fatal signal is pending, handle the * signal first. We do not need to release the mmap_lock because @@ -302,23 +305,7 @@ retry: return 0; } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ - - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c index a1e5aace897a..dd7a0277c5c0 100644 --- a/arch/arm/mm/hugetlbpage.c +++ b/arch/arm/mm/hugetlbpage.c @@ -17,7 +17,6 @@ #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> /* * On ARM, huge pages are backed by pmd's rather than pte's, so we do a lot diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 01e18e43b174..000c1b48e973 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -243,13 +243,8 @@ void __init bootmem_init(void) (phys_addr_t)max_low_pfn << PAGE_SHIFT); /* - * Sparsemem tries to allocate bootmem in memory_present(), - * so must be done after the fixed reservations - */ - memblocks_present(); - - /* - * sparse_init() needs the bootmem allocator up and running. + * sparse_init() tries to allocate memory from memblock, so must be + * done after the fixed reservations */ sparse_init(); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index cc3c9a6a1113..c36f977b2ccb 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -29,6 +29,7 @@ #include <asm/traps.h> #include <asm/procinfo.h> #include <asm/memory.h> +#include <asm/pgalloc.h> #include <asm/mach/arch.h> #include <asm/mach/map.h> diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 7e8ee4adf269..171077cbf419 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -162,7 +162,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index d40e9e5fc52b..396797ffe2b1 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/cpu.h> +#include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> #include <linux/gfp.h> #include <linux/highmem.h> @@ -42,15 +43,18 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order) static bool hypercall_cflush = false; /* buffers in highmem or foreign pages cannot cross page boundaries */ -static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op) +static void dma_cache_maint(struct device *dev, dma_addr_t handle, + size_t size, u32 op) { struct gnttab_cache_flush cflush; - cflush.a.dev_bus_addr = handle & XEN_PAGE_MASK; cflush.offset = xen_offset_in_page(handle); cflush.op = op; + handle &= XEN_PAGE_MASK; do { + cflush.a.dev_bus_addr = dma_to_phys(dev, handle); + if (size + cflush.offset > XEN_PAGE_SIZE) cflush.length = XEN_PAGE_SIZE - cflush.offset; else @@ -59,7 +63,7 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op) HYPERVISOR_grant_table_op(GNTTABOP_cache_flush, &cflush, 1); cflush.offset = 0; - cflush.a.dev_bus_addr += cflush.length; + handle += cflush.length; size -= cflush.length; } while (size); } @@ -71,24 +75,20 @@ static void dma_cache_maint(dma_addr_t handle, size_t size, u32 op) * pfn_valid returns true the pages is local and we can use the native * dma-direct functions, otherwise we call the Xen specific version. */ -void xen_dma_sync_for_cpu(dma_addr_t handle, phys_addr_t paddr, size_t size, - enum dma_data_direction dir) +void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) { - if (pfn_valid(PFN_DOWN(handle))) - arch_sync_dma_for_cpu(paddr, size, dir); - else if (dir != DMA_TO_DEVICE) - dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL); + if (dir != DMA_TO_DEVICE) + dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL); } -void xen_dma_sync_for_device(dma_addr_t handle, phys_addr_t paddr, size_t size, - enum dma_data_direction dir) +void xen_dma_sync_for_device(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir) { - if (pfn_valid(PFN_DOWN(handle))) - arch_sync_dma_for_device(paddr, size, dir); - else if (dir == DMA_FROM_DEVICE) - dma_cache_maint(handle, size, GNTTAB_CACHE_INVAL); + if (dir == DMA_FROM_DEVICE) + dma_cache_maint(dev, handle, size, GNTTAB_CACHE_INVAL); else - dma_cache_maint(handle, size, GNTTAB_CACHE_CLEAN); + dma_cache_maint(dev, handle, size, GNTTAB_CACHE_CLEAN); } bool xen_arch_need_swiotlb(struct device *dev, @@ -96,7 +96,7 @@ bool xen_arch_need_swiotlb(struct device *dev, dma_addr_t dev_addr) { unsigned int xen_pfn = XEN_PFN_DOWN(phys); - unsigned int bfn = XEN_PFN_DOWN(dev_addr); + unsigned int bfn = XEN_PFN_DOWN(dma_to_phys(dev, dev_addr)); /* * The swiotlb buffer should be used if diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index e11b4ea06127..6d232837cbee 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1182,22 +1182,6 @@ config HARDEN_BRANCH_PREDICTOR If unsure, say Y. -config HARDEN_EL2_VECTORS - bool "Harden EL2 vector mapping against system register leak" if EXPERT - default y - help - Speculation attacks against some high-performance processors can - be used to leak privileged information such as the vector base - register, resulting in a potential defeat of the EL2 layout - randomization. - - This config option will map the vectors to a fixed location, - independent of the EL2 code mapping, so that revealing VBAR_EL2 - to an attacker does not give away any extra information. This - only gets enabled on affected CPUs. - - If unsure, say Y. - config ARM64_SSBD bool "Speculative Store Bypass Disable" if EXPERT default y @@ -1520,7 +1504,6 @@ menu "ARMv8.3 architectural features" config ARM64_PTR_AUTH bool "Enable support for pointer authentication" default y - depends on !KVM || ARM64_VHE depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC # Modern compilers insert a .note.gnu.property section note for PAC # which is only understood by binutils starting with version 2.33.1. @@ -1547,8 +1530,7 @@ config ARM64_PTR_AUTH The feature is detected at runtime. If the feature is not present in hardware it will not be advertised to userspace/KVM guest nor will it - be enabled. However, KVM guest also require VHE mode and hence - CONFIG_ARM64_VHE=y option to use this feature. + be enabled. If the feature is present on the boot CPU but not on a late CPU, then the late CPU will be parked. Also, if the boot CPU does not have diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h index 12b778d55342..996498751318 100644 --- a/arch/arm64/include/asm/device.h +++ b/arch/arm64/include/asm/device.h @@ -6,9 +6,6 @@ #define __ASM_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* private IOMMU data */ -#endif }; struct pdev_archdata { diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index f987b8a8f325..4335800201c9 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -28,10 +28,9 @@ * compile time, but to set the physical address only * in the boot process. * - * These 'compile-time allocated' memory buffers are - * page-sized. Use set_fixmap(idx,phys) to associate - * physical memory with fixmap indices. - * + * Each enum increment in these 'compile-time allocated' + * memory buffers is page-sized. Use set_fixmap(idx,phys) + * to associate physical memory with a fixmap index. */ enum fixed_addresses { FIX_HOLE, diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 352aaebf4198..fb1a922b31ba 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -42,33 +42,81 @@ #include <linux/mm.h> -/* Translate a kernel address of @sym into its equivalent linear mapping */ -#define kvm_ksym_ref(sym) \ +/* + * Translate name of a symbol defined in nVHE hyp to the name seen + * by kernel proper. All nVHE symbols are prefixed by the build system + * to avoid clashes with the VHE variants. + */ +#define kvm_nvhe_sym(sym) __kvm_nvhe_##sym + +#define DECLARE_KVM_VHE_SYM(sym) extern char sym[] +#define DECLARE_KVM_NVHE_SYM(sym) extern char kvm_nvhe_sym(sym)[] + +/* + * Define a pair of symbols sharing the same name but one defined in + * VHE and the other in nVHE hyp implementations. + */ +#define DECLARE_KVM_HYP_SYM(sym) \ + DECLARE_KVM_VHE_SYM(sym); \ + DECLARE_KVM_NVHE_SYM(sym) + +#define CHOOSE_VHE_SYM(sym) sym +#define CHOOSE_NVHE_SYM(sym) kvm_nvhe_sym(sym) + +#ifndef __KVM_NVHE_HYPERVISOR__ +/* + * BIG FAT WARNINGS: + * + * - Don't be tempted to change the following is_kernel_in_hyp_mode() + * to has_vhe(). has_vhe() is implemented as a *final* capability, + * while this is used early at boot time, when the capabilities are + * not final yet.... + * + * - Don't let the nVHE hypervisor have access to this, as it will + * pick the *wrong* symbol (yes, it runs at EL2...). + */ +#define CHOOSE_HYP_SYM(sym) (is_kernel_in_hyp_mode() ? CHOOSE_VHE_SYM(sym) \ + : CHOOSE_NVHE_SYM(sym)) +#else +/* The nVHE hypervisor shouldn't even try to access anything */ +extern void *__nvhe_undefined_symbol; +#define CHOOSE_HYP_SYM(sym) __nvhe_undefined_symbol +#endif + +/* Translate a kernel address @ptr into its equivalent linear mapping */ +#define kvm_ksym_ref(ptr) \ ({ \ - void *val = &sym; \ + void *val = (ptr); \ if (!is_kernel_in_hyp_mode()) \ - val = lm_alias(&sym); \ + val = lm_alias((ptr)); \ val; \ }) +#define kvm_ksym_ref_nvhe(sym) kvm_ksym_ref(kvm_nvhe_sym(sym)) struct kvm; struct kvm_vcpu; +struct kvm_s2_mmu; -extern char __kvm_hyp_init[]; -extern char __kvm_hyp_init_end[]; +DECLARE_KVM_NVHE_SYM(__kvm_hyp_init); +DECLARE_KVM_HYP_SYM(__kvm_hyp_vector); +#define __kvm_hyp_init CHOOSE_NVHE_SYM(__kvm_hyp_init) +#define __kvm_hyp_vector CHOOSE_HYP_SYM(__kvm_hyp_vector) -extern char __kvm_hyp_vector[]; +#ifdef CONFIG_KVM_INDIRECT_VECTORS +extern atomic_t arm64_el2_vector_last_slot; +DECLARE_KVM_HYP_SYM(__bp_harden_hyp_vecs); +#define __bp_harden_hyp_vecs CHOOSE_HYP_SYM(__bp_harden_hyp_vecs) +#endif extern void __kvm_flush_vm_context(void); -extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); -extern void __kvm_tlb_flush_vmid(struct kvm *kvm); -extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); +extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa, + int level); +extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu); +extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu); extern void __kvm_timer_set_cntvoff(u64 cntvoff); -extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu); - -extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu); +extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); extern void __kvm_enable_ssbs(void); @@ -143,7 +191,6 @@ extern char __smccc_workaround_1_smc[__SMCCC_WORKAROUND_1_SMC_SZ]; .macro get_vcpu_ptr vcpu, ctxt get_host_ctxt \ctxt, \vcpu ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] - kern_hyp_va \vcpu .endm #endif diff --git a/arch/arm64/include/asm/kvm_coproc.h b/arch/arm64/include/asm/kvm_coproc.h index 454373704b8a..d6bb40122fdb 100644 --- a/arch/arm64/include/asm/kvm_coproc.h +++ b/arch/arm64/include/asm/kvm_coproc.h @@ -19,14 +19,6 @@ struct kvm_sys_reg_table { size_t num; }; -struct kvm_sys_reg_target_table { - struct kvm_sys_reg_table table64; - struct kvm_sys_reg_table table32; -}; - -void kvm_register_target_sys_reg_table(unsigned int target, - struct kvm_sys_reg_target_table *table); - int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 4d0f8ea600ba..49a55be2b9a2 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -124,33 +124,12 @@ static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) static __always_inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) { - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; -} - -static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu) -{ - return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1; -} - -static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.sysregs_loaded_on_cpu) - return read_sysreg_el1(SYS_ELR); - else - return *__vcpu_elr_el1(vcpu); -} - -static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v) -{ - if (vcpu->arch.sysregs_loaded_on_cpu) - write_sysreg_el1(v, SYS_ELR); - else - *__vcpu_elr_el1(vcpu) = v; + return (unsigned long *)&vcpu_gp_regs(vcpu)->pc; } static __always_inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { - return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate; + return (unsigned long *)&vcpu_gp_regs(vcpu)->pstate; } static __always_inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu) @@ -179,14 +158,14 @@ static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) static __always_inline unsigned long vcpu_get_reg(const struct kvm_vcpu *vcpu, u8 reg_num) { - return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs.regs[reg_num]; + return (reg_num == 31) ? 0 : vcpu_gp_regs(vcpu)->regs[reg_num]; } static __always_inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, unsigned long val) { if (reg_num != 31) - vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val; + vcpu_gp_regs(vcpu)->regs[reg_num] = val; } static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) @@ -197,7 +176,7 @@ static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) if (vcpu->arch.sysregs_loaded_on_cpu) return read_sysreg_el1(SYS_SPSR); else - return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1]; + return __vcpu_sys_reg(vcpu, SPSR_EL1); } static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) @@ -210,7 +189,7 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) if (vcpu->arch.sysregs_loaded_on_cpu) write_sysreg_el1(v, SYS_SPSR); else - vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v; + __vcpu_sys_reg(vcpu, SPSR_EL1) = v; } /* @@ -259,14 +238,14 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) return mode != PSR_MODE_EL0t; } -static __always_inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu) +static __always_inline u32 kvm_vcpu_get_esr(const struct kvm_vcpu *vcpu) { return vcpu->arch.fault.esr_el2; } static __always_inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); if (esr & ESR_ELx_CV) return (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT; @@ -291,64 +270,64 @@ static inline u64 kvm_vcpu_get_disr(const struct kvm_vcpu *vcpu) static inline u32 kvm_vcpu_hvc_get_imm(const struct kvm_vcpu *vcpu) { - return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_xVC_IMM_MASK; + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_xVC_IMM_MASK; } static __always_inline bool kvm_vcpu_dabt_isvalid(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_ISV); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_ISV); } static inline unsigned long kvm_vcpu_dabt_iss_nisv_sanitized(const struct kvm_vcpu *vcpu) { - return kvm_vcpu_get_hsr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC); + return kvm_vcpu_get_esr(vcpu) & (ESR_ELx_CM | ESR_ELx_WNR | ESR_ELx_FSC); } static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SSE); } static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_SF); } static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu) { - return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; + return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT; } static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_S1PTW); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW); } static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WNR) || + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) || kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */ } static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_CM); } static __always_inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu) { - return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); + return 1 << ((kvm_vcpu_get_esr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT); } /* This one is not specific to Data Abort */ static __always_inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) { - return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_IL); + return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_IL); } static __always_inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { - return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); + return ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); } static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) @@ -358,15 +337,15 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) { - return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC; + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC; } static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu) { - return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE; + return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE; } -static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) +static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case FSC_SEA: @@ -387,7 +366,7 @@ static __always_inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu) static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); return ESR_ELx_SYS64_ISS_RT(esr); } @@ -516,14 +495,14 @@ static __always_inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_i * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ -static __always_inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) +static __always_inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); - vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); + vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, SYS_SPSR); + write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f81151ad3d3c..65568b23868a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -66,19 +66,34 @@ struct kvm_vmid { u32 vmid; }; -struct kvm_arch { +struct kvm_s2_mmu { struct kvm_vmid vmid; - /* stage2 entry level table */ - pgd_t *pgd; - phys_addr_t pgd_phys; - - /* VTCR_EL2 value for this VM */ - u64 vtcr; + /* + * stage2 entry level table + * + * Two kvm_s2_mmu structures in the same VM can point to the same + * pgd here. This happens when running a guest using a + * translation regime that isn't affected by its own stage-2 + * translation, such as a non-VHE hypervisor running at vEL2, or + * for vEL1/EL0 with vHCR_EL2.VM == 0. In that case, we use the + * canonical stage-2 page tables. + */ + pgd_t *pgd; + phys_addr_t pgd_phys; /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; + struct kvm *kvm; +}; + +struct kvm_arch { + struct kvm_s2_mmu mmu; + + /* VTCR_EL2 value for this VM */ + u64 vtcr; + /* The maximum number of vCPUs depends on the used GIC model */ int max_vcpus; @@ -159,6 +174,16 @@ enum vcpu_sysreg { APGAKEYLO_EL1, APGAKEYHI_EL1, + ELR_EL1, + SP_EL1, + SPSR_EL1, + + CNTVOFF_EL2, + CNTV_CVAL_EL0, + CNTV_CTL_EL0, + CNTP_CVAL_EL0, + CNTP_CTL_EL0, + /* 32bit specific registers. Keep them at the end of the range */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ @@ -210,7 +235,15 @@ enum vcpu_sysreg { #define NR_COPRO_REGS (NR_SYS_REGS * 2) struct kvm_cpu_context { - struct kvm_regs gp_regs; + struct user_pt_regs regs; /* sp = sp_el0 */ + + u64 spsr_abt; + u64 spsr_und; + u64 spsr_irq; + u64 spsr_fiq; + + struct user_fpsimd_state fp_regs; + union { u64 sys_regs[NR_SYS_REGS]; u32 copro[NR_COPRO_REGS]; @@ -243,6 +276,9 @@ struct kvm_vcpu_arch { void *sve_state; unsigned int sve_max_vl; + /* Stage 2 paging state used by the hardware on next switch */ + struct kvm_s2_mmu *hw_mmu; + /* HYP configuration */ u64 hcr_el2; u32 mdcr_el2; @@ -327,7 +363,7 @@ struct kvm_vcpu_arch { struct vcpu_reset_state reset_state; /* True when deferrable sysregs are loaded on the physical CPU, - * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ + * see kvm_vcpu_load_sysregs_vhe and kvm_vcpu_put_sysregs_vhe. */ bool sysregs_loaded_on_cpu; /* Guest PV state */ @@ -378,15 +414,20 @@ struct kvm_vcpu_arch { #define vcpu_has_ptrauth(vcpu) false #endif -#define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) +#define vcpu_gp_regs(v) (&(v)->arch.ctxt.regs) /* - * Only use __vcpu_sys_reg if you know you want the memory backed version of a - * register, and not the one most recently accessed by a running VCPU. For - * example, for userspace access or for system registers that are never context - * switched, but only emulated. + * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the + * memory backed version of a register, and not the one most recently + * accessed by a running VCPU. For example, for userspace access or + * for system registers that are never context switched, but only + * emulated. */ -#define __vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)]) +#define __ctxt_sys_reg(c,r) (&(c)->sys_regs[(r)]) + +#define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) + +#define __vcpu_sys_reg(v,r) (ctxt_sys_reg(&(v)->arch.ctxt, (r))) u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); @@ -442,6 +483,18 @@ void kvm_arm_resume_guest(struct kvm *kvm); u64 __kvm_call_hyp(void *hypfn, ...); +#define kvm_call_hyp_nvhe(f, ...) \ + do { \ + DECLARE_KVM_NVHE_SYM(f); \ + __kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__); \ + } while(0) + +#define kvm_call_hyp_nvhe_ret(f, ...) \ + ({ \ + DECLARE_KVM_NVHE_SYM(f); \ + __kvm_call_hyp(kvm_ksym_ref_nvhe(f), ##__VA_ARGS__); \ + }) + /* * The couple of isb() below are there to guarantee the same behaviour * on VHE as on !VHE, where the eret to EL1 acts as a context @@ -453,7 +506,7 @@ u64 __kvm_call_hyp(void *hypfn, ...); f(__VA_ARGS__); \ isb(); \ } else { \ - __kvm_call_hyp(kvm_ksym_ref(f), ##__VA_ARGS__); \ + kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ } while(0) @@ -465,8 +518,7 @@ u64 __kvm_call_hyp(void *hypfn, ...); ret = f(__VA_ARGS__); \ isb(); \ } else { \ - ret = __kvm_call_hyp(kvm_ksym_ref(f), \ - ##__VA_ARGS__); \ + ret = kvm_call_hyp_nvhe_ret(f, ##__VA_ARGS__); \ } \ \ ret; \ @@ -518,7 +570,7 @@ DECLARE_PER_CPU(kvm_host_data_t, kvm_host_data); static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ - cpu_ctxt->sys_regs[MPIDR_EL1] = read_cpuid_mpidr(); + ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } static inline bool kvm_arch_requires_vhe(void) @@ -619,8 +671,8 @@ static inline int kvm_arm_have_ssbd(void) } } -void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu); -void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu); +void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu); +void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu); int kvm_set_ipa_limit(void); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index ce3080834bfa..46689e7db46c 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -12,8 +12,6 @@ #include <asm/alternative.h> #include <asm/sysreg.h> -#define __hyp_text __section(.hyp.text) notrace __noscs - #define read_sysreg_elx(r,nvh,vh) \ ({ \ u64 reg; \ @@ -63,17 +61,20 @@ void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if); void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if); int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu); +#ifdef __KVM_NVHE_HYPERVISOR__ void __timer_enable_traps(struct kvm_vcpu *vcpu); void __timer_disable_traps(struct kvm_vcpu *vcpu); +#endif +#ifdef __KVM_NVHE_HYPERVISOR__ void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt); void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt); +#else void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt); void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt); -void __sysreg32_save_state(struct kvm_vcpu *vcpu); -void __sysreg32_restore_state(struct kvm_vcpu *vcpu); +#endif void __debug_switch_to_guest(struct kvm_vcpu *vcpu); void __debug_switch_to_host(struct kvm_vcpu *vcpu); @@ -81,11 +82,17 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu); void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); +#ifndef __KVM_NVHE_HYPERVISOR__ void activate_traps_vhe_load(struct kvm_vcpu *vcpu); void deactivate_traps_vhe_put(void); +#endif u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt); + +void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt); +#ifdef __KVM_NVHE_HYPERVISOR__ void __noreturn __hyp_do_panic(unsigned long, ...); +#endif #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 40be8f6c7351..189839c3706a 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -134,8 +134,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void free_hyp_pgds(void); void stage2_unmap_vm(struct kvm *kvm); -int kvm_alloc_stage2_pgd(struct kvm *kvm); -void kvm_free_stage2_pgd(struct kvm *kvm); +int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu); +void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu); int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, phys_addr_t pa, unsigned long size, bool writable); @@ -577,13 +577,13 @@ static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm) return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm)); } -static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) +static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu) { - struct kvm_vmid *vmid = &kvm->arch.vmid; + struct kvm_vmid *vmid = &mmu->vmid; u64 vmid_field, baddr; u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0; - baddr = kvm->arch.pgd_phys; + baddr = mmu->pgd_phys; vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT; return kvm_phys_to_vttbr(baddr) | vmid_field | cnp; } @@ -592,10 +592,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm *kvm) * Must be called from hyp code running at EL2 with an updated VTTBR * and interrupts disabled. */ -static __always_inline void __load_guest_stage2(struct kvm *kvm) +static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu) { - write_sysreg(kvm->arch.vtcr, vtcr_el2); - write_sysreg(kvm_get_vttbr(kvm), vttbr_el2); + write_sysreg(kern_hyp_va(mmu->kvm)->arch.vtcr, vtcr_el2); + write_sysreg(kvm_get_vttbr(mmu), vttbr_el2); /* * ARM errata 1165522 and 1530923 require the actual execution of the diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h index 6301813dcace..0ddf98c3ba9f 100644 --- a/arch/arm64/include/asm/kvm_ptrauth.h +++ b/arch/arm64/include/asm/kvm_ptrauth.h @@ -61,44 +61,36 @@ /* * Both ptrauth_switch_to_guest and ptrauth_switch_to_host macros will - * check for the presence of one of the cpufeature flag - * ARM64_HAS_ADDRESS_AUTH_ARCH or ARM64_HAS_ADDRESS_AUTH_IMP_DEF and + * check for the presence ARM64_HAS_ADDRESS_AUTH, which is defined as + * (ARM64_HAS_ADDRESS_AUTH_ARCH || ARM64_HAS_ADDRESS_AUTH_IMP_DEF) and * then proceed ahead with the save/restore of Pointer Authentication - * key registers. + * key registers if enabled for the guest. */ .macro ptrauth_switch_to_guest g_ctxt, reg1, reg2, reg3 -alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH - b 1000f +alternative_if_not ARM64_HAS_ADDRESS_AUTH + b .L__skip_switch\@ alternative_else_nop_endif -alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF - b 1001f -alternative_else_nop_endif -1000: - ldr \reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)] + mrs \reg1, hcr_el2 and \reg1, \reg1, #(HCR_API | HCR_APK) - cbz \reg1, 1001f + cbz \reg1, .L__skip_switch\@ add \reg1, \g_ctxt, #CPU_APIAKEYLO_EL1 ptrauth_restore_state \reg1, \reg2, \reg3 -1001: +.L__skip_switch\@: .endm .macro ptrauth_switch_to_host g_ctxt, h_ctxt, reg1, reg2, reg3 -alternative_if ARM64_HAS_ADDRESS_AUTH_ARCH - b 2000f -alternative_else_nop_endif -alternative_if_not ARM64_HAS_ADDRESS_AUTH_IMP_DEF - b 2001f +alternative_if_not ARM64_HAS_ADDRESS_AUTH + b .L__skip_switch\@ alternative_else_nop_endif -2000: - ldr \reg1, [\g_ctxt, #(VCPU_HCR_EL2 - VCPU_CONTEXT)] + mrs \reg1, hcr_el2 and \reg1, \reg1, #(HCR_API | HCR_APK) - cbz \reg1, 2001f + cbz \reg1, .L__skip_switch\@ add \reg1, \g_ctxt, #CPU_APIAKEYLO_EL1 ptrauth_save_state \reg1, \reg2, \reg3 add \reg1, \h_ctxt, #CPU_APIAKEYLO_EL1 ptrauth_restore_state \reg1, \reg2, \reg3 isb -2001: +.L__skip_switch\@: .endm #else /* !CONFIG_ARM64_PTR_AUTH */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 8444df000181..a7a5ecaa2e83 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -45,13 +45,6 @@ struct bp_hardening_data { bp_hardening_cb_t fn; }; -#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) || \ - defined(CONFIG_HARDEN_EL2_VECTORS)) - -extern char __bp_harden_hyp_vecs[]; -extern atomic_t arm64_el2_vector_last_slot; -#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */ - #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 58e93583ddb6..3c6a7f5988b1 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -13,37 +13,13 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#define __HAVE_ARCH_PGD_FREE +#include <asm-generic/pgalloc.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) #if CONFIG_PGTABLE_LEVELS > 2 -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - gfp_t gfp = GFP_PGTABLE_USER; - struct page *page; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - - page = alloc_page(gfp); - if (!page) - return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_page(page); - return NULL; - } - return page_address(page); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp) -{ - BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1)); - pgtable_pmd_page_dtor(virt_to_page(pmdp)); - free_page((unsigned long)pmdp); -} - static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) { set_pud(pudp, __pud(__phys_to_pud_val(pmdp) | prot)); @@ -62,17 +38,6 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) #if CONFIG_PGTABLE_LEVELS > 3 -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pud_t *)__get_free_page(GFP_PGTABLE_USER); -} - -static inline void pud_free(struct mm_struct *mm, pud_t *pudp) -{ - BUG_ON((unsigned long)pudp & (PAGE_SIZE-1)); - free_page((unsigned long)pudp); -} - static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index a0c8a0b65259..0eadbf933e35 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -46,7 +46,12 @@ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); * Logical CPU mapping. */ extern u64 __cpu_logical_map[NR_CPUS]; -#define cpu_logical_map(cpu) __cpu_logical_map[cpu] +extern u64 cpu_logical_map(int cpu); + +static inline void set_cpu_logical_map(int cpu, u64 hwid) +{ + __cpu_logical_map[cpu] = hwid; +} struct seq_file; diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 8d7c466f809b..991dd5f031e4 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -50,7 +50,7 @@ static inline void set_fs(mm_segment_t fs) CONFIG_ARM64_UAO)); } -#define segment_eq(a, b) ((a) == (b)) +#define uaccess_kernel() (get_fs() == KERNEL_DS) /* * Test whether a block of memory is a valid user space address. diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 17e81bd9a2d3..734860ac7cf9 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -308,8 +308,8 @@ __SYSCALL(__NR_writev, compat_sys_writev) __SYSCALL(__NR_getsid, sys_getsid) #define __NR_fdatasync 148 __SYSCALL(__NR_fdatasync, sys_fdatasync) -#define __NR__sysctl 149 -__SYSCALL(__NR__sysctl, compat_sys_sysctl) + /* 149 was sys_sysctl */ +__SYSCALL(149, sys_ni_syscall) #define __NR_mlock 150 __SYSCALL(__NR_mlock, sys_mlock) #define __NR_munlock 151 diff --git a/arch/arm64/include/asm/vdso/compat_gettimeofday.h b/arch/arm64/include/asm/vdso/compat_gettimeofday.h index 75cbae60455b..7508b0ac1d21 100644 --- a/arch/arm64/include/asm/vdso/compat_gettimeofday.h +++ b/arch/arm64/include/asm/vdso/compat_gettimeofday.h @@ -103,7 +103,8 @@ int clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) return ret; } -static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) { u64 res; diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 9c29ad3049f8..631ab1281633 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -64,7 +64,8 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } -static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) { u64 res; diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 5051b388c654..09977acc007d 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -85,10 +85,17 @@ static inline bool is_kernel_in_hyp_mode(void) static __always_inline bool has_vhe(void) { - if (cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN)) + /* + * The following macros are defined for code specic to VHE/nVHE. + * If has_vhe() is inlined into those compilation units, it can + * be determined statically. Otherwise fall back to caps. + */ + if (__is_defined(__KVM_VHE_HYPERVISOR__)) return true; - - return false; + else if (__is_defined(__KVM_NVHE_HYPERVISOR__)) + return false; + else + return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN); } #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 0577e2142284..7d32fc959b1a 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -102,13 +102,12 @@ int main(void) DEFINE(VCPU_FAULT_DISR, offsetof(struct kvm_vcpu, arch.fault.disr_el1)); DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags)); DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2)); - DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); + DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_cpu_context, regs)); DEFINE(CPU_APIAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1])); DEFINE(CPU_APIBKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1])); DEFINE(CPU_APDAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1])); DEFINE(CPU_APDBKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APDBKEYLO_EL1])); DEFINE(CPU_APGAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APGAKEYLO_EL1])); - DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs)); DEFINE(HOST_CONTEXT_VCPU, offsetof(struct kvm_cpu_context, __hyp_running_vcpu)); DEFINE(HOST_DATA_CONTEXT, offsetof(struct kvm_host_data, host_ctxt)); #endif diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 79728bfb5351..6bd1d3ad037a 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -632,7 +632,7 @@ has_neoverse_n1_erratum_1542419(const struct arm64_cpu_capabilities *entry, return is_midr_in_range(midr, &range) && has_dic; } -#if defined(CONFIG_HARDEN_EL2_VECTORS) +#ifdef CONFIG_RANDOMIZE_BASE static const struct midr_range ca57_a72[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), @@ -891,7 +891,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, .matches = check_branch_predictor, }, -#ifdef CONFIG_HARDEN_EL2_VECTORS +#ifdef CONFIG_RANDOMIZE_BASE { .desc = "EL2 vector hardening", .capability = ARM64_HARDEN_EL2_VECTORS, diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index be0a63ffed23..9e897c500237 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -51,4 +51,58 @@ __efistub__ctype = _ctype; #endif +#ifdef CONFIG_KVM + +/* + * KVM nVHE code has its own symbol namespace prefixed with __kvm_nvhe_, to + * separate it from the kernel proper. The following symbols are legally + * accessed by it, therefore provide aliases to make them linkable. + * Do not include symbols which may not be safely accessed under hypervisor + * memory mappings. + */ + +#define KVM_NVHE_ALIAS(sym) __kvm_nvhe_##sym = sym; + +/* Alternative callbacks for init-time patching of nVHE hyp code. */ +KVM_NVHE_ALIAS(arm64_enable_wa2_handling); +KVM_NVHE_ALIAS(kvm_patch_vector_branch); +KVM_NVHE_ALIAS(kvm_update_va_mask); + +/* Global kernel state accessed by nVHE hyp code. */ +KVM_NVHE_ALIAS(arm64_ssbd_callback_required); +KVM_NVHE_ALIAS(kvm_host_data); +KVM_NVHE_ALIAS(kvm_vgic_global_state); + +/* Kernel constant needed to compute idmap addresses. */ +KVM_NVHE_ALIAS(kimage_voffset); + +/* Kernel symbols used to call panic() from nVHE hyp code (via ERET). */ +KVM_NVHE_ALIAS(__hyp_panic_string); +KVM_NVHE_ALIAS(panic); + +/* Vectors installed by hyp-init on reset HVC. */ +KVM_NVHE_ALIAS(__hyp_stub_vectors); + +/* IDMAP TCR_EL1.T0SZ as computed by the EL1 init code */ +KVM_NVHE_ALIAS(idmap_t0sz); + +/* Kernel symbol used by icache_is_vpipt(). */ +KVM_NVHE_ALIAS(__icache_flags); + +/* Kernel symbols needed for cpus_have_final/const_caps checks. */ +KVM_NVHE_ALIAS(arm64_const_caps_ready); +KVM_NVHE_ALIAS(cpu_hwcap_keys); +KVM_NVHE_ALIAS(cpu_hwcaps); + +/* Static keys which are set if a vGIC trap should be handled in hyp. */ +KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); +KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); + +/* Static key checked in pmr_sync(). */ +#ifdef CONFIG_ARM64_PSEUDO_NMI +KVM_NVHE_ALIAS(gic_pmr_sync); +#endif + +#endif /* CONFIG_KVM */ + #endif /* __ARM64_KERNEL_IMAGE_VARS_H */ diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index dab88260b137..7689f2031c0c 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -180,7 +180,7 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, /* * We didn't take an exception to get here, set PAN. UAO will be cleared - * by sdei_event_handler()s set_fs(USER_DS) call. + * by sdei_event_handler()s force_uaccess_begin() call. */ __uaccess_enable_hw_pan(); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index c793276ec7ad..77c4c9bad1b8 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -85,7 +85,7 @@ u64 __cacheline_aligned boot_args[4]; void __init smp_setup_processor_id(void) { u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK; - cpu_logical_map(0) = mpidr; + set_cpu_logical_map(0, mpidr); /* * clear __my_cpu_offset on boot CPU to avoid hang caused by @@ -276,7 +276,13 @@ arch_initcall(reserve_memblock_reserved_regions); u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; -void __init setup_arch(char **cmdline_p) +u64 cpu_logical_map(int cpu) +{ + return __cpu_logical_map[cpu]; +} +EXPORT_SYMBOL_GPL(cpu_logical_map); + +void __init __no_sanitize_address setup_arch(char **cmdline_p) { init_mm.start_code = (unsigned long) _text; init_mm.end_code = (unsigned long) _etext; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index e43a8ff19f0f..03957a1ae6c0 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -43,7 +43,6 @@ #include <asm/kvm_mmu.h> #include <asm/mmu_context.h> #include <asm/numa.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/smp_plat.h> #include <asm/sections.h> @@ -567,7 +566,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) return; /* map the logical cpu id to cpu MPIDR */ - cpu_logical_map(cpu_count) = hwid; + set_cpu_logical_map(cpu_count, hwid); cpu_madt_gicc[cpu_count] = *processor; @@ -681,7 +680,7 @@ static void __init of_parse_and_init_cpus(void) goto next; pr_debug("cpu logical map 0x%llx\n", hwid); - cpu_logical_map(cpu_count) = hwid; + set_cpu_logical_map(cpu_count, hwid); early_map_cpu_to_node(cpu_count, of_node_to_nid(dn)); next: @@ -722,7 +721,7 @@ void __init smp_init_cpus(void) for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) - cpu_logical_map(i) = INVALID_HWID; + set_cpu_logical_map(i, INVALID_HWID); } } } diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 13489aff4440..318c8f2df245 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -58,7 +58,7 @@ config KVM_ARM_PMU virtual machines. config KVM_INDIRECT_VECTORS - def_bool HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS + def_bool HARDEN_BRANCH_PREDICTOR || RANDOMIZE_BASE endif # KVM diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 8d3d9513cbfe..99977c1972cc 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -13,8 +13,8 @@ obj-$(CONFIG_KVM) += hyp/ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ $(KVM)/vfio.o $(KVM)/irqchip.o \ arm.o mmu.o mmio.o psci.o perf.o hypercalls.o pvtime.o \ - inject_fault.o regmap.o va_layout.o hyp.o hyp-init.o handle_exit.o \ - guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o \ + inject_fault.o regmap.o va_layout.o hyp.o handle_exit.o \ + guest.o debug.o reset.o sys_regs.o \ vgic-sys-reg-v3.o fpsimd.o pmu.o \ aarch32.o arch_timer.o \ vgic/vgic.o vgic/vgic-init.o \ diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index a1fe0ea3254e..32ba6fbc3814 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -51,6 +51,93 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, struct arch_timer_context *timer, enum kvm_arch_timer_regs treg); +u32 timer_get_ctl(struct arch_timer_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + return __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); + case TIMER_PTIMER: + return __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); + default: + WARN_ON(1); + return 0; + } +} + +u64 timer_get_cval(struct arch_timer_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + return __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + case TIMER_PTIMER: + return __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + default: + WARN_ON(1); + return 0; + } +} + +static u64 timer_get_offset(struct arch_timer_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + return __vcpu_sys_reg(vcpu, CNTVOFF_EL2); + default: + return 0; + } +} + +static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + __vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl; + break; + case TIMER_PTIMER: + __vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl; + break; + default: + WARN_ON(1); + } +} + +static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval; + break; + case TIMER_PTIMER: + __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval; + break; + default: + WARN_ON(1); + } +} + +static void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + + switch(arch_timer_ctx_index(ctxt)) { + case TIMER_VTIMER: + __vcpu_sys_reg(vcpu, CNTVOFF_EL2) = offset; + break; + default: + WARN(offset, "timer %ld\n", arch_timer_ctx_index(ctxt)); + } +} + u64 kvm_phys_timer_read(void) { return timecounter->cc->read(timecounter->cc); @@ -124,8 +211,8 @@ static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx) { u64 cval, now; - cval = timer_ctx->cnt_cval; - now = kvm_phys_timer_read() - timer_ctx->cntvoff; + cval = timer_get_cval(timer_ctx); + now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); if (now < cval) { u64 ns; @@ -144,8 +231,8 @@ static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx) { WARN_ON(timer_ctx && timer_ctx->loaded); return timer_ctx && - !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) && - (timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE); + ((timer_get_ctl(timer_ctx) & + (ARCH_TIMER_CTRL_IT_MASK | ARCH_TIMER_CTRL_ENABLE)) == ARCH_TIMER_CTRL_ENABLE); } /* @@ -256,8 +343,8 @@ static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx) if (!kvm_timer_irq_can_fire(timer_ctx)) return false; - cval = timer_ctx->cnt_cval; - now = kvm_phys_timer_read() - timer_ctx->cntvoff; + cval = timer_get_cval(timer_ctx); + now = kvm_phys_timer_read() - timer_get_offset(timer_ctx); return cval <= now; } @@ -350,8 +437,8 @@ static void timer_save_state(struct arch_timer_context *ctx) switch (index) { case TIMER_VTIMER: - ctx->cnt_ctl = read_sysreg_el0(SYS_CNTV_CTL); - ctx->cnt_cval = read_sysreg_el0(SYS_CNTV_CVAL); + timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTV_CTL)); + timer_set_cval(ctx, read_sysreg_el0(SYS_CNTV_CVAL)); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTV_CTL); @@ -359,8 +446,8 @@ static void timer_save_state(struct arch_timer_context *ctx) break; case TIMER_PTIMER: - ctx->cnt_ctl = read_sysreg_el0(SYS_CNTP_CTL); - ctx->cnt_cval = read_sysreg_el0(SYS_CNTP_CVAL); + timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); + timer_set_cval(ctx, read_sysreg_el0(SYS_CNTP_CVAL)); /* Disable the timer */ write_sysreg_el0(0, SYS_CNTP_CTL); @@ -429,14 +516,14 @@ static void timer_restore_state(struct arch_timer_context *ctx) switch (index) { case TIMER_VTIMER: - write_sysreg_el0(ctx->cnt_cval, SYS_CNTV_CVAL); + write_sysreg_el0(timer_get_cval(ctx), SYS_CNTV_CVAL); isb(); - write_sysreg_el0(ctx->cnt_ctl, SYS_CNTV_CTL); + write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTV_CTL); break; case TIMER_PTIMER: - write_sysreg_el0(ctx->cnt_cval, SYS_CNTP_CVAL); + write_sysreg_el0(timer_get_cval(ctx), SYS_CNTP_CVAL); isb(); - write_sysreg_el0(ctx->cnt_ctl, SYS_CNTP_CTL); + write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); break; case NR_KVM_TIMERS: BUG(); @@ -528,7 +615,7 @@ void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu) kvm_timer_vcpu_load_nogic(vcpu); } - set_cntvoff(map.direct_vtimer->cntvoff); + set_cntvoff(timer_get_offset(map.direct_vtimer)); kvm_timer_unblocking(vcpu); @@ -615,7 +702,7 @@ static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu) } } -void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu) +void kvm_timer_sync_user(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); @@ -639,8 +726,8 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) * resets the timer to be disabled and unmasked and is compliant with * the ARMv7 architecture. */ - vcpu_vtimer(vcpu)->cnt_ctl = 0; - vcpu_ptimer(vcpu)->cnt_ctl = 0; + timer_set_ctl(vcpu_vtimer(vcpu), 0); + timer_set_ctl(vcpu_ptimer(vcpu), 0); if (timer->enabled) { kvm_timer_update_irq(vcpu, false, vcpu_vtimer(vcpu)); @@ -668,13 +755,13 @@ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, tmp, kvm) - vcpu_vtimer(tmp)->cntvoff = cntvoff; + timer_set_offset(vcpu_vtimer(tmp), cntvoff); /* * When called from the vcpu create path, the CPU being created is not * included in the loop above, so we just set it here as well. */ - vcpu_vtimer(vcpu)->cntvoff = cntvoff; + timer_set_offset(vcpu_vtimer(vcpu), cntvoff); mutex_unlock(&kvm->lock); } @@ -684,9 +771,12 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) struct arch_timer_context *vtimer = vcpu_vtimer(vcpu); struct arch_timer_context *ptimer = vcpu_ptimer(vcpu); + vtimer->vcpu = vcpu; + ptimer->vcpu = vcpu; + /* Synchronize cntvoff across all vtimers of a VM. */ update_vtimer_cntvoff(vcpu, kvm_phys_timer_read()); - ptimer->cntvoff = 0; + timer_set_offset(ptimer, 0); hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); timer->bg_timer.function = kvm_bg_timer_expire; @@ -704,9 +794,6 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) vtimer->host_timer_irq_flags = host_vtimer_irq_flags; ptimer->host_timer_irq_flags = host_ptimer_irq_flags; - - vtimer->vcpu = vcpu; - ptimer->vcpu = vcpu; } static void kvm_timer_init_interrupt(void *info) @@ -756,10 +843,12 @@ static u64 read_timer_ctl(struct arch_timer_context *timer) * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit * regardless of ENABLE bit for our implementation convenience. */ + u32 ctl = timer_get_ctl(timer); + if (!kvm_timer_compute_delta(timer)) - return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT; - else - return timer->cnt_ctl; + ctl |= ARCH_TIMER_CTRL_IT_STAT; + + return ctl; } u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid) @@ -795,8 +884,8 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, switch (treg) { case TIMER_REG_TVAL: - val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff; - val &= lower_32_bits(val); + val = timer_get_cval(timer) - kvm_phys_timer_read() + timer_get_offset(timer); + val = lower_32_bits(val); break; case TIMER_REG_CTL: @@ -804,11 +893,11 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu, break; case TIMER_REG_CVAL: - val = timer->cnt_cval; + val = timer_get_cval(timer); break; case TIMER_REG_CNT: - val = kvm_phys_timer_read() - timer->cntvoff; + val = kvm_phys_timer_read() - timer_get_offset(timer); break; default: @@ -842,15 +931,15 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu, { switch (treg) { case TIMER_REG_TVAL: - timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + (s32)val; + timer_set_cval(timer, kvm_phys_timer_read() - timer_get_offset(timer) + (s32)val); break; case TIMER_REG_CTL: - timer->cnt_ctl = val & ~ARCH_TIMER_CTRL_IT_STAT; + timer_set_ctl(timer, val & ~ARCH_TIMER_CTRL_IT_STAT); break; case TIMER_REG_CVAL: - timer->cnt_cval = val; + timer_set_cval(timer, val); break; default: diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 73e12869afe3..691d21e4c717 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -106,22 +106,15 @@ static int kvm_arm_default_max_vcpus(void) */ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { - int ret, cpu; + int ret; ret = kvm_arm_setup_stage2(kvm, type); if (ret) return ret; - kvm->arch.last_vcpu_ran = alloc_percpu(typeof(*kvm->arch.last_vcpu_ran)); - if (!kvm->arch.last_vcpu_ran) - return -ENOMEM; - - for_each_possible_cpu(cpu) - *per_cpu_ptr(kvm->arch.last_vcpu_ran, cpu) = -1; - - ret = kvm_alloc_stage2_pgd(kvm); + ret = kvm_init_stage2_mmu(kvm, &kvm->arch.mmu); if (ret) - goto out_fail_alloc; + return ret; ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP); if (ret) @@ -129,18 +122,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_vgic_early_init(kvm); - /* Mark the initial VMID generation invalid */ - kvm->arch.vmid.vmid_gen = 0; - /* The maximum number of VCPUs is limited by the host's GIC model */ kvm->arch.max_vcpus = kvm_arm_default_max_vcpus(); return ret; out_free_stage2_pgd: - kvm_free_stage2_pgd(kvm); -out_fail_alloc: - free_percpu(kvm->arch.last_vcpu_ran); - kvm->arch.last_vcpu_ran = NULL; + kvm_free_stage2_pgd(&kvm->arch.mmu); return ret; } @@ -160,9 +147,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_vgic_destroy(kvm); - free_percpu(kvm->arch.last_vcpu_ran); - kvm->arch.last_vcpu_ran = NULL; - for (i = 0; i < KVM_MAX_VCPUS; ++i) { if (kvm->vcpus[i]) { kvm_vcpu_destroy(kvm->vcpus[i]); @@ -281,6 +265,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_arm_pvtime_vcpu_init(&vcpu->arch); + vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu; + err = kvm_vgic_vcpu_init(vcpu); if (err) return err; @@ -336,16 +322,18 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { + struct kvm_s2_mmu *mmu; int *last_ran; - last_ran = this_cpu_ptr(vcpu->kvm->arch.last_vcpu_ran); + mmu = vcpu->arch.hw_mmu; + last_ran = this_cpu_ptr(mmu->last_vcpu_ran); /* * We might get preempted before the vCPU actually runs, but * over-invalidation doesn't affect correctness. */ if (*last_ran != vcpu->vcpu_id) { - kvm_call_hyp(__kvm_tlb_flush_local_vmid, vcpu); + kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu); *last_ran = vcpu->vcpu_id; } @@ -353,7 +341,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); - kvm_vcpu_load_sysregs(vcpu); + if (has_vhe()) + kvm_vcpu_load_sysregs_vhe(vcpu); kvm_arch_vcpu_load_fp(vcpu); kvm_vcpu_pmu_restore_guest(vcpu); if (kvm_arm_is_pvtime_enabled(&vcpu->arch)) @@ -371,7 +360,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_put_fp(vcpu); - kvm_vcpu_put_sysregs(vcpu); + if (has_vhe()) + kvm_vcpu_put_sysregs_vhe(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); kvm_vcpu_pmu_restore_host(vcpu); @@ -468,7 +458,6 @@ static bool need_new_vmid_gen(struct kvm_vmid *vmid) /** * update_vmid - Update the vmid with a valid VMID for the current generation - * @kvm: The guest that struct vmid belongs to * @vmid: The stage-2 VMID information struct */ static void update_vmid(struct kvm_vmid *vmid) @@ -680,7 +669,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ cond_resched(); - update_vmid(&vcpu->kvm->arch.vmid); + update_vmid(&vcpu->arch.hw_mmu->vmid); check_vcpu_requests(vcpu); @@ -729,13 +718,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) */ smp_store_mb(vcpu->mode, IN_GUEST_MODE); - if (ret <= 0 || need_new_vmid_gen(&vcpu->kvm->arch.vmid) || + if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) || kvm_request_pending(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; isb(); /* Ensure work in x_flush_hwstate is committed */ kvm_pmu_sync_hwstate(vcpu); if (static_branch_unlikely(&userspace_irqchip_in_use)) - kvm_timer_sync_hwstate(vcpu); + kvm_timer_sync_user(vcpu); kvm_vgic_sync_hwstate(vcpu); local_irq_enable(); preempt_enable(); @@ -750,11 +739,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) trace_kvm_entry(*vcpu_pc(vcpu)); guest_enter_irqoff(); - if (has_vhe()) { - ret = kvm_vcpu_run_vhe(vcpu); - } else { - ret = kvm_call_hyp_ret(__kvm_vcpu_run_nvhe, vcpu); - } + ret = kvm_call_hyp_ret(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; vcpu->stat.exits++; @@ -784,7 +769,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * timer virtual interrupt state. */ if (static_branch_unlikely(&userspace_irqchip_in_use)) - kvm_timer_sync_hwstate(vcpu); + kvm_timer_sync_user(vcpu); kvm_arch_vcpu_ctxsync_fp(vcpu); @@ -1287,7 +1272,7 @@ static void cpu_init_hyp_mode(void) * so that we can use adr_l to access per-cpu variables in EL2. */ tpidr_el2 = ((unsigned long)this_cpu_ptr(&kvm_host_data) - - (unsigned long)kvm_ksym_ref(kvm_host_data)); + (unsigned long)kvm_ksym_ref(&kvm_host_data)); pgd_ptr = kvm_mmu_get_httbr(); hyp_stack_ptr = __this_cpu_read(kvm_arm_hyp_stack_page) + PAGE_SIZE; @@ -1308,7 +1293,7 @@ static void cpu_init_hyp_mode(void) */ if (this_cpu_has_cap(ARM64_SSBS) && arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) { - kvm_call_hyp(__kvm_enable_ssbs); + kvm_call_hyp_nvhe(__kvm_enable_ssbs); } } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index e329a36b2bee..3e081d556e81 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -85,7 +85,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled()); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { - fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs, + fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, vcpu->arch.sve_max_vl); @@ -109,12 +109,10 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { - u64 *guest_zcr = &vcpu->arch.ctxt.sys_regs[ZCR_EL1]; - fpsimd_save_and_flush_cpu_state(); if (guest_has_sve) - *guest_zcr = read_sysreg_s(SYS_ZCR_EL12); + __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_s(SYS_ZCR_EL12); } else if (host_has_sve) { /* * The FPSIMD/SVE state in the CPU has not been touched, and we diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index aea43ec60f37..dfb5218137ca 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -101,19 +101,69 @@ static int core_reg_size_from_offset(const struct kvm_vcpu *vcpu, u64 off) return size; } -static int validate_core_offset(const struct kvm_vcpu *vcpu, - const struct kvm_one_reg *reg) +static void *core_reg_addr(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { u64 off = core_reg_offset_from_id(reg->id); int size = core_reg_size_from_offset(vcpu, off); if (size < 0) - return -EINVAL; + return NULL; if (KVM_REG_SIZE(reg->id) != size) - return -EINVAL; + return NULL; - return 0; + switch (off) { + case KVM_REG_ARM_CORE_REG(regs.regs[0]) ... + KVM_REG_ARM_CORE_REG(regs.regs[30]): + off -= KVM_REG_ARM_CORE_REG(regs.regs[0]); + off /= 2; + return &vcpu->arch.ctxt.regs.regs[off]; + + case KVM_REG_ARM_CORE_REG(regs.sp): + return &vcpu->arch.ctxt.regs.sp; + + case KVM_REG_ARM_CORE_REG(regs.pc): + return &vcpu->arch.ctxt.regs.pc; + + case KVM_REG_ARM_CORE_REG(regs.pstate): + return &vcpu->arch.ctxt.regs.pstate; + + case KVM_REG_ARM_CORE_REG(sp_el1): + return __ctxt_sys_reg(&vcpu->arch.ctxt, SP_EL1); + + case KVM_REG_ARM_CORE_REG(elr_el1): + return __ctxt_sys_reg(&vcpu->arch.ctxt, ELR_EL1); + + case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_EL1]): + return __ctxt_sys_reg(&vcpu->arch.ctxt, SPSR_EL1); + + case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_ABT]): + return &vcpu->arch.ctxt.spsr_abt; + + case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_UND]): + return &vcpu->arch.ctxt.spsr_und; + + case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_IRQ]): + return &vcpu->arch.ctxt.spsr_irq; + + case KVM_REG_ARM_CORE_REG(spsr[KVM_SPSR_FIQ]): + return &vcpu->arch.ctxt.spsr_fiq; + + case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ... + KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]): + off -= KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]); + off /= 4; + return &vcpu->arch.ctxt.fp_regs.vregs[off]; + + case KVM_REG_ARM_CORE_REG(fp_regs.fpsr): + return &vcpu->arch.ctxt.fp_regs.fpsr; + + case KVM_REG_ARM_CORE_REG(fp_regs.fpcr): + return &vcpu->arch.ctxt.fp_regs.fpcr; + + default: + return NULL; + } } static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) @@ -125,8 +175,8 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) * off the index in the "array". */ __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; - struct kvm_regs *regs = vcpu_gp_regs(vcpu); - int nr_regs = sizeof(*regs) / sizeof(__u32); + int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); + void *addr; u32 off; /* Our ID is an index into the kvm_regs struct. */ @@ -135,10 +185,11 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; - if (validate_core_offset(vcpu, reg)) + addr = core_reg_addr(vcpu, reg); + if (!addr) return -EINVAL; - if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id))) + if (copy_to_user(uaddr, addr, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; @@ -147,10 +198,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { __u32 __user *uaddr = (__u32 __user *)(unsigned long)reg->addr; - struct kvm_regs *regs = vcpu_gp_regs(vcpu); - int nr_regs = sizeof(*regs) / sizeof(__u32); + int nr_regs = sizeof(struct kvm_regs) / sizeof(__u32); __uint128_t tmp; - void *valp = &tmp; + void *valp = &tmp, *addr; u64 off; int err = 0; @@ -160,7 +210,8 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs) return -ENOENT; - if (validate_core_offset(vcpu, reg)) + addr = core_reg_addr(vcpu, reg); + if (!addr) return -EINVAL; if (KVM_REG_SIZE(reg->id) > sizeof(tmp)) @@ -198,7 +249,7 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } } - memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + memcpy(addr, valp, KVM_REG_SIZE(reg->id)); if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { int i; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 1df3beafd73f..fe6c7d79309d 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -89,7 +89,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) */ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) { + if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_WFx_ISS_WFE) { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true); vcpu->stat.wfe_exit_stat++; kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu)); @@ -119,13 +119,13 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu) static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) { struct kvm_run *run = vcpu->run; - u32 hsr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); int ret = 0; run->exit_reason = KVM_EXIT_DEBUG; - run->debug.arch.hsr = hsr; + run->debug.arch.hsr = esr; - switch (ESR_ELx_EC(hsr)) { + switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_WATCHPT_LOW: run->debug.arch.far = vcpu->arch.fault.far_el2; /* fall through */ @@ -135,8 +135,8 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) case ESR_ELx_EC_BRK64: break; default: - kvm_err("%s: un-handled case hsr: %#08x\n", - __func__, (unsigned int) hsr); + kvm_err("%s: un-handled case esr: %#08x\n", + __func__, (unsigned int) esr); ret = -1; break; } @@ -146,10 +146,10 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu) static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu) { - u32 hsr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); - kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n", - hsr, esr_get_class_string(hsr)); + kvm_pr_unimpl("Unknown exception class: esr: %#08x -- %s\n", + esr, esr_get_class_string(esr)); kvm_inject_undefined(vcpu); return 1; @@ -200,10 +200,10 @@ static exit_handle_fn arm_exit_handlers[] = { static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) { - u32 hsr = kvm_vcpu_get_hsr(vcpu); - u8 hsr_ec = ESR_ELx_EC(hsr); + u32 esr = kvm_vcpu_get_esr(vcpu); + u8 esr_ec = ESR_ELx_EC(esr); - return arm_exit_handlers[hsr_ec]; + return arm_exit_handlers[esr_ec]; } /* @@ -242,15 +242,15 @@ int handle_exit(struct kvm_vcpu *vcpu, int exception_index) struct kvm_run *run = vcpu->run; if (ARM_SERROR_PENDING(exception_index)) { - u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); + u8 esr_ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); /* * HVC/SMC already have an adjusted PC, which we need * to correct in order to return to after having * injected the SError. */ - if (hsr_ec == ESR_ELx_EC_HVC32 || hsr_ec == ESR_ELx_EC_HVC64 || - hsr_ec == ESR_ELx_EC_SMC32 || hsr_ec == ESR_ELx_EC_SMC64) { + if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64 || + esr_ec == ESR_ELx_EC_SMC32 || esr_ec == ESR_ELx_EC_SMC64) { u32 adj = kvm_vcpu_trap_il_is32bit(vcpu) ? 4 : 2; *vcpu_pc(vcpu) -= adj; } @@ -307,5 +307,5 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index) exception_index = ARM_EXCEPTION_CODE(exception_index); if (exception_index == ARM_EXCEPTION_EL1_SERROR) - kvm_handle_guest_serror(vcpu, kvm_vcpu_get_hsr(vcpu)); + kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu)); } diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 8c9880783839..f54f0e89a71c 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -3,18 +3,12 @@ # Makefile for Kernel-based Virtual Machine module, HYP part # -ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \ - $(DISABLE_STACKLEAK_PLUGIN) - -obj-$(CONFIG_KVM) += hyp.o - -hyp-y := vgic-v3-sr.o timer-sr.o aarch32.o vgic-v2-cpuif-proxy.o sysreg-sr.o \ - debug-sr.o entry.o switch.o fpsimd.o tlb.o hyp-entry.o - -# KVM code is run at a different exception code with a different map, so -# compiler instrumentation that inserts callbacks or checks into the code may -# cause crashes. Just disable it. -GCOV_PROFILE := n -KASAN_SANITIZE := n -UBSAN_SANITIZE := n -KCOV_INSTRUMENT := n +incdir := $(srctree)/$(src)/include +subdir-asflags-y := -I$(incdir) +subdir-ccflags-y := -I$(incdir) \ + -fno-stack-protector \ + -DDISABLE_BRANCH_PROFILING \ + $(DISABLE_STACKLEAK_PLUGIN) + +obj-$(CONFIG_KVM) += vhe/ nvhe/ +obj-$(CONFIG_KVM_INDIRECT_VECTORS) += smccc_wa.o diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c index 25c0e47d57cb..ae56d8a4b382 100644 --- a/arch/arm64/kvm/hyp/aarch32.c +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -44,14 +44,14 @@ static const unsigned short cc_map[16] = { /* * Check if a trapped instruction should have been executed or not. */ -bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu) +bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) { unsigned long cpsr; u32 cpsr_cond; int cond; /* Top two bits non-zero? Unconditional. */ - if (kvm_vcpu_get_hsr(vcpu) >> 30) + if (kvm_vcpu_get_esr(vcpu) >> 30) return true; /* Is condition field valid? */ @@ -93,7 +93,7 @@ bool __hyp_text kvm_condition_valid32(const struct kvm_vcpu *vcpu) * * IT[7:0] -> CPSR[26:25],CPSR[15:10] */ -static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) +static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) { unsigned long itbits, cond; unsigned long cpsr = *vcpu_cpsr(vcpu); @@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) * kvm_skip_instr - skip a trapped instruction and proceed to the next * @vcpu: The vcpu pointer */ -void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) +void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { u32 pc = *vcpu_pc(vcpu); bool is_thumb; diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 90186cf6473e..ee32a7743389 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -16,12 +16,10 @@ #include <asm/kvm_mmu.h> #include <asm/kvm_ptrauth.h> -#define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) -#define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) +#define CPU_XREG_OFFSET(x) (CPU_USER_PT_REGS + 8*x) #define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8) .text - .pushsection .hyp.text, "ax" /* * We treat x18 as callee-saved as the host may use it as a platform diff --git a/arch/arm64/kvm/hyp/fpsimd.S b/arch/arm64/kvm/hyp/fpsimd.S index 5b8ff517ff10..01f114aa47b0 100644 --- a/arch/arm64/kvm/hyp/fpsimd.S +++ b/arch/arm64/kvm/hyp/fpsimd.S @@ -9,7 +9,6 @@ #include <asm/fpsimdmacros.h> .text - .pushsection .hyp.text, "ax" SYM_FUNC_START(__fpsimd_save_state) fpsimd_save x0, 1 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index 9c5cfb04170e..689fccbc9de7 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -16,7 +16,6 @@ #include <asm/mmu.h> .text - .pushsection .hyp.text, "ax" .macro do_el2_call /* @@ -40,6 +39,7 @@ el1_sync: // Guest trapped into EL2 ccmp x0, #ESR_ELx_EC_HVC32, #4, ne b.ne el1_trap +#ifdef __KVM_NVHE_HYPERVISOR__ mrs x1, vttbr_el2 // If vttbr is valid, the guest cbnz x1, el1_hvc_guest // called HVC @@ -74,6 +74,7 @@ el1_sync: // Guest trapped into EL2 eret sb +#endif /* __KVM_NVHE_HYPERVISOR__ */ el1_hvc_guest: /* @@ -180,6 +181,7 @@ el2_error: eret sb +#ifdef __KVM_NVHE_HYPERVISOR__ SYM_FUNC_START(__hyp_do_panic) mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ PSR_MODE_EL1h) @@ -189,6 +191,7 @@ SYM_FUNC_START(__hyp_do_panic) eret sb SYM_FUNC_END(__hyp_do_panic) +#endif SYM_CODE_START(__hyp_panic) get_host_ctxt x0, x1 @@ -318,20 +321,4 @@ SYM_CODE_START(__bp_harden_hyp_vecs) 1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ .org 1b SYM_CODE_END(__bp_harden_hyp_vecs) - - .popsection - -SYM_CODE_START(__smccc_workaround_1_smc) - esb - sub sp, sp, #(8 * 4) - stp x2, x3, [sp, #(8 * 0)] - stp x0, x1, [sp, #(8 * 2)] - mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 - smc #0 - ldp x2, x3, [sp, #(8 * 0)] - ldp x0, x1, [sp, #(8 * 2)] - add sp, sp, #(8 * 4) -1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ - .org 1b -SYM_CODE_END(__smccc_workaround_1_smc) #endif diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h index e95af204fec7..0297dc63988c 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h @@ -4,6 +4,9 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ +#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__ +#define __ARM64_KVM_HYP_DEBUG_SR_H__ + #include <linux/compiler.h> #include <linux/kvm_host.h> @@ -85,53 +88,8 @@ default: write_debug(ptr[0], reg, 0); \ } -static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1) -{ - u64 reg; - - /* Clear pmscr in case of early return */ - *pmscr_el1 = 0; - - /* SPE present on this CPU? */ - if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1), - ID_AA64DFR0_PMSVER_SHIFT)) - return; - - /* Yes; is it owned by EL3? */ - reg = read_sysreg_s(SYS_PMBIDR_EL1); - if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) - return; - - /* No; is the host actually using the thing? */ - reg = read_sysreg_s(SYS_PMBLIMITR_EL1); - if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT))) - return; - - /* Yes; save the control register and disable data generation */ - *pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1); - write_sysreg_s(0, SYS_PMSCR_EL1); - isb(); - - /* Now drain all buffered data to memory */ - psb_csync(); - dsb(nsh); -} - -static void __hyp_text __debug_restore_spe_nvhe(u64 pmscr_el1) -{ - if (!pmscr_el1) - return; - - /* The host page table is installed, but not yet synchronised */ - isb(); - - /* Re-enable data generation */ - write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1); -} - -static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu, - struct kvm_guest_debug_arch *dbg, - struct kvm_cpu_context *ctxt) +static void __debug_save_state(struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) { u64 aa64dfr0; int brps, wrps; @@ -145,12 +103,11 @@ static void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu, save_debug(dbg->dbg_wcr, dbgwcr, wrps); save_debug(dbg->dbg_wvr, dbgwvr, wrps); - ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1); + ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1); } -static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu, - struct kvm_guest_debug_arch *dbg, - struct kvm_cpu_context *ctxt) +static void __debug_restore_state(struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) { u64 aa64dfr0; int brps, wrps; @@ -165,23 +122,16 @@ static void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu, restore_debug(dbg->dbg_wcr, dbgwcr, wrps); restore_debug(dbg->dbg_wvr, dbgwvr, wrps); - write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1); + write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1); } -void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu) +static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - /* - * Non-VHE: Disable and flush SPE data generation - * VHE: The vcpu can run, but it can't hide. - */ - if (!has_vhe()) - __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1); - if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; @@ -190,20 +140,17 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu) host_dbg = &vcpu->arch.host_debug_state.regs; guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); - __debug_save_state(vcpu, host_dbg, host_ctxt); - __debug_restore_state(vcpu, guest_dbg, guest_ctxt); + __debug_save_state(host_dbg, host_ctxt); + __debug_restore_state(guest_dbg, guest_ctxt); } -void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu) +static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; struct kvm_guest_debug_arch *host_dbg; struct kvm_guest_debug_arch *guest_dbg; - if (!has_vhe()) - __debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1); - if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; @@ -212,13 +159,10 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu) host_dbg = &vcpu->arch.host_debug_state.regs; guest_dbg = kern_hyp_va(vcpu->arch.debug_ptr); - __debug_save_state(vcpu, guest_dbg, guest_ctxt); - __debug_restore_state(vcpu, host_dbg, host_ctxt); + __debug_save_state(guest_dbg, guest_ctxt); + __debug_restore_state(host_dbg, host_ctxt); vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY; } -u32 __hyp_text __kvm_get_mdcr_el2(void) -{ - return read_sysreg(mdcr_el2); -} +#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */ diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h new file mode 100644 index 000000000000..426ef65601dd --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -0,0 +1,511 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_SWITCH_H__ +#define __ARM64_KVM_HYP_SWITCH_H__ + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/thread_info.h> + +extern const char __hyp_panic_string[]; + +/* Check whether the FP regs were dirtied while in the host-side run loop: */ +static inline bool update_fp_enabled(struct kvm_vcpu *vcpu) +{ + /* + * When the system doesn't support FP/SIMD, we cannot rely on + * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an + * abort on the very first access to FP and thus we should never + * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always + * trap the accesses. + */ + if (!system_supports_fpsimd() || + vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_FP_HOST); + + return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED); +} + +/* Save the 32-bit only FPSIMD system register state */ +static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + __vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2); +} + +static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) +{ + /* + * We are about to set CPTR_EL2.TFP to trap all floating point + * register accesses to EL2, however, the ARM ARM clearly states that + * traps are only taken to EL2 if the operation would not otherwise + * trap to EL1. Therefore, always make sure that for 32-bit guests, + * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. + * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to + * it will cause an exception. + */ + if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) { + write_sysreg(1 << 30, fpexc32_el2); + isb(); + } +} + +static inline void __activate_traps_common(struct kvm_vcpu *vcpu) +{ + /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ + write_sysreg(1 << 15, hstr_el2); + + /* + * Make sure we trap PMU access from EL0 to EL2. Also sanitize + * PMSELR_EL0 to make sure it never contains the cycle + * counter, which could make a PMXEVCNTR_EL0 access UNDEF at + * EL1 instead of being trapped to EL2. + */ + write_sysreg(0, pmselr_el0); + write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); +} + +static inline void __deactivate_traps_common(void) +{ + write_sysreg(0, hstr_el2); + write_sysreg(0, pmuserenr_el0); +} + +static inline void ___activate_traps(struct kvm_vcpu *vcpu) +{ + u64 hcr = vcpu->arch.hcr_el2; + + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + hcr |= HCR_TVM; + + write_sysreg(hcr, hcr_el2); + + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) + write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); +} + +static inline void ___deactivate_traps(struct kvm_vcpu *vcpu) +{ + /* + * If we pended a virtual abort, preserve it until it gets + * cleared. See D1.14.3 (Virtual Interrupts) for details, but + * the crucial bit is "On taking a vSError interrupt, + * HCR_EL2.VSE is cleared to 0." + */ + if (vcpu->arch.hcr_el2 & HCR_VSE) { + vcpu->arch.hcr_el2 &= ~HCR_VSE; + vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE; + } +} + +static inline void __activate_vm(struct kvm_s2_mmu *mmu) +{ + __load_guest_stage2(mmu); +} + +static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) +{ + u64 par, tmp; + + /* + * Resolve the IPA the hard way using the guest VA. + * + * Stage-1 translation already validated the memory access + * rights. As such, we can use the EL1 translation regime, and + * don't have to distinguish between EL0 and EL1 access. + * + * We do need to save/restore PAR_EL1 though, as we haven't + * saved the guest context yet, and we may return early... + */ + par = read_sysreg(par_el1); + asm volatile("at s1e1r, %0" : : "r" (far)); + isb(); + + tmp = read_sysreg(par_el1); + write_sysreg(par, par_el1); + + if (unlikely(tmp & SYS_PAR_EL1_F)) + return false; /* Translation failed, back to guest */ + + /* Convert PAR to HPFAR format */ + *hpfar = PAR_TO_HPFAR(tmp); + return true; +} + +static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) +{ + u8 ec; + u64 esr; + u64 hpfar, far; + + esr = vcpu->arch.fault.esr_el2; + ec = ESR_ELx_EC(esr); + + if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW) + return true; + + far = read_sysreg_el2(SYS_FAR); + + /* + * The HPFAR can be invalid if the stage 2 fault did not + * happen during a stage 1 page table walk (the ESR_EL2.S1PTW + * bit is clear) and one of the two following cases are true: + * 1. The fault was due to a permission fault + * 2. The processor carries errata 834220 + * + * Therefore, for all non S1PTW faults where we either have a + * permission fault or the errata workaround is enabled, we + * resolve the IPA using the AT instruction. + */ + if (!(esr & ESR_ELx_S1PTW) && + (cpus_have_final_cap(ARM64_WORKAROUND_834220) || + (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + if (!__translate_far_to_hpfar(far, &hpfar)) + return false; + } else { + hpfar = read_sysreg(hpfar_el2); + } + + vcpu->arch.fault.far_el2 = far; + vcpu->arch.fault.hpfar_el2 = hpfar; + return true; +} + +/* Check for an FPSIMD/SVE trap and handle as appropriate */ +static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) +{ + bool vhe, sve_guest, sve_host; + u8 esr_ec; + + if (!system_supports_fpsimd()) + return false; + + /* + * Currently system_supports_sve() currently implies has_vhe(), + * so the check is redundant. However, has_vhe() can be determined + * statically and helps the compiler remove dead code. + */ + if (has_vhe() && system_supports_sve()) { + sve_guest = vcpu_has_sve(vcpu); + sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE; + vhe = true; + } else { + sve_guest = false; + sve_host = false; + vhe = has_vhe(); + } + + esr_ec = kvm_vcpu_trap_get_class(vcpu); + if (esr_ec != ESR_ELx_EC_FP_ASIMD && + esr_ec != ESR_ELx_EC_SVE) + return false; + + /* Don't handle SVE traps for non-SVE vcpus here: */ + if (!sve_guest) + if (esr_ec != ESR_ELx_EC_FP_ASIMD) + return false; + + /* Valid trap. Switch the context: */ + + if (vhe) { + u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN; + + if (sve_guest) + reg |= CPACR_EL1_ZEN; + + write_sysreg(reg, cpacr_el1); + } else { + write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP, + cptr_el2); + } + + isb(); + + if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { + /* + * In the SVE case, VHE is assumed: it is enforced by + * Kconfig and kvm_arch_init(). + */ + if (sve_host) { + struct thread_struct *thread = container_of( + vcpu->arch.host_fpsimd_state, + struct thread_struct, uw.fpsimd_state); + + sve_save_state(sve_pffr(thread), + &vcpu->arch.host_fpsimd_state->fpsr); + } else { + __fpsimd_save_state(vcpu->arch.host_fpsimd_state); + } + + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + } + + if (sve_guest) { + sve_load_state(vcpu_sve_pffr(vcpu), + &vcpu->arch.ctxt.fp_regs.fpsr, + sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1); + write_sysreg_s(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR_EL12); + } else { + __fpsimd_restore_state(&vcpu->arch.ctxt.fp_regs); + } + + /* Skip restoring fpexc32 for AArch64 guests */ + if (!(read_sysreg(hcr_el2) & HCR_RW)) + write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2); + + vcpu->arch.flags |= KVM_ARM64_FP_ENABLED; + + return true; +} + +static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + /* + * The normal sysreg handling code expects to see the traps, + * let's not do anything here. + */ + if (vcpu->arch.hcr_el2 & HCR_TVM) + return false; + + switch (sysreg) { + case SYS_SCTLR_EL1: + write_sysreg_el1(val, SYS_SCTLR); + break; + case SYS_TTBR0_EL1: + write_sysreg_el1(val, SYS_TTBR0); + break; + case SYS_TTBR1_EL1: + write_sysreg_el1(val, SYS_TTBR1); + break; + case SYS_TCR_EL1: + write_sysreg_el1(val, SYS_TCR); + break; + case SYS_ESR_EL1: + write_sysreg_el1(val, SYS_ESR); + break; + case SYS_FAR_EL1: + write_sysreg_el1(val, SYS_FAR); + break; + case SYS_AFSR0_EL1: + write_sysreg_el1(val, SYS_AFSR0); + break; + case SYS_AFSR1_EL1: + write_sysreg_el1(val, SYS_AFSR1); + break; + case SYS_MAIR_EL1: + write_sysreg_el1(val, SYS_MAIR); + break; + case SYS_AMAIR_EL1: + write_sysreg_el1(val, SYS_AMAIR); + break; + case SYS_CONTEXTIDR_EL1: + write_sysreg_el1(val, SYS_CONTEXTIDR); + break; + default: + return false; + } + + __kvm_skip_instr(vcpu); + return true; +} + +static inline bool esr_is_ptrauth_trap(u32 esr) +{ + u32 ec = ESR_ELx_EC(esr); + + if (ec == ESR_ELx_EC_PAC) + return true; + + if (ec != ESR_ELx_EC_SYS64) + return false; + + switch (esr_sys64_to_sysreg(esr)) { + case SYS_APIAKEYLO_EL1: + case SYS_APIAKEYHI_EL1: + case SYS_APIBKEYLO_EL1: + case SYS_APIBKEYHI_EL1: + case SYS_APDAKEYLO_EL1: + case SYS_APDAKEYHI_EL1: + case SYS_APDBKEYLO_EL1: + case SYS_APDBKEYHI_EL1: + case SYS_APGAKEYLO_EL1: + case SYS_APGAKEYHI_EL1: + return true; + } + + return false; +} + +#define __ptrauth_save_key(ctxt, key) \ + do { \ + u64 __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \ +} while(0) + +static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *ctxt; + u64 val; + + if (!vcpu_has_ptrauth(vcpu) || + !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu))) + return false; + + ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + __ptrauth_save_key(ctxt, APIA); + __ptrauth_save_key(ctxt, APIB); + __ptrauth_save_key(ctxt, APDA); + __ptrauth_save_key(ctxt, APDB); + __ptrauth_save_key(ctxt, APGA); + + vcpu_ptrauth_enable(vcpu); + + val = read_sysreg(hcr_el2); + val |= (HCR_API | HCR_APK); + write_sysreg(val, hcr_el2); + + return true; +} + +/* + * Return true when we were able to fixup the guest exit and should return to + * the guest, false when we should restore the host state and return to the + * main run loop. + */ +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) + vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); + + /* + * We're using the raw exception code in order to only process + * the trap if no SError is pending. We will come back to the + * same PC once the SError has been injected, and replay the + * trapping instruction. + */ + if (*exit_code != ARM_EXCEPTION_TRAP) + goto exit; + + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && + handle_tx2_tvm(vcpu)) + return true; + + /* + * We trap the first access to the FP/SIMD to save the host context + * and restore the guest context lazily. + * If FP/SIMD is not implemented, handle the trap and inject an + * undefined instruction exception to the guest. + * Similarly for trapped SVE accesses. + */ + if (__hyp_handle_fpsimd(vcpu)) + return true; + + if (__hyp_handle_ptrauth(vcpu)) + return true; + + if (!__populate_fault_info(vcpu)) + return true; + + if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { + bool valid; + + valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW && + kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && + kvm_vcpu_dabt_isvalid(vcpu) && + !kvm_vcpu_abt_issea(vcpu) && + !kvm_vcpu_dabt_iss1tw(vcpu); + + if (valid) { + int ret = __vgic_v2_perform_cpuif_access(vcpu); + + if (ret == 1) + return true; + + /* Promote an illegal access to an SError.*/ + if (ret == -1) + *exit_code = ARM_EXCEPTION_EL1_SERROR; + + goto exit; + } + } + + if (static_branch_unlikely(&vgic_v3_cpuif_trap) && + (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 || + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) { + int ret = __vgic_v3_perform_cpuif_access(vcpu); + + if (ret == 1) + return true; + } + +exit: + /* Return to the host kernel and handle the exit */ + return false; +} + +static inline bool __needs_ssbd_off(struct kvm_vcpu *vcpu) +{ + if (!cpus_have_final_cap(ARM64_SSBD)) + return false; + + return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG); +} + +static inline void __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * The host runs with the workaround always present. If the + * guest wants it disabled, so be it... + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL); +#endif +} + +static inline void __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) +{ +#ifdef CONFIG_ARM64_SSBD + /* + * If the guest has disabled the workaround, bring it back on. + */ + if (__needs_ssbd_off(vcpu) && + __hyp_this_cpu_read(arm64_ssbd_callback_required)) + arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL); +#endif +} + +#endif /* __ARM64_KVM_HYP_SWITCH_H__ */ diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h new file mode 100644 index 000000000000..7a986030145f --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -0,0 +1,193 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__ +#define __ARM64_KVM_HYP_SYSREG_SR_H__ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) +{ + ctxt_sys_reg(ctxt, MDSCR_EL1) = read_sysreg(mdscr_el1); +} + +static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt) +{ + ctxt_sys_reg(ctxt, TPIDR_EL0) = read_sysreg(tpidr_el0); + ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0); +} + +static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) +{ + ctxt_sys_reg(ctxt, CSSELR_EL1) = read_sysreg(csselr_el1); + ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR); + ctxt_sys_reg(ctxt, CPACR_EL1) = read_sysreg_el1(SYS_CPACR); + ctxt_sys_reg(ctxt, TTBR0_EL1) = read_sysreg_el1(SYS_TTBR0); + ctxt_sys_reg(ctxt, TTBR1_EL1) = read_sysreg_el1(SYS_TTBR1); + ctxt_sys_reg(ctxt, TCR_EL1) = read_sysreg_el1(SYS_TCR); + ctxt_sys_reg(ctxt, ESR_EL1) = read_sysreg_el1(SYS_ESR); + ctxt_sys_reg(ctxt, AFSR0_EL1) = read_sysreg_el1(SYS_AFSR0); + ctxt_sys_reg(ctxt, AFSR1_EL1) = read_sysreg_el1(SYS_AFSR1); + ctxt_sys_reg(ctxt, FAR_EL1) = read_sysreg_el1(SYS_FAR); + ctxt_sys_reg(ctxt, MAIR_EL1) = read_sysreg_el1(SYS_MAIR); + ctxt_sys_reg(ctxt, VBAR_EL1) = read_sysreg_el1(SYS_VBAR); + ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR); + ctxt_sys_reg(ctxt, AMAIR_EL1) = read_sysreg_el1(SYS_AMAIR); + ctxt_sys_reg(ctxt, CNTKCTL_EL1) = read_sysreg_el1(SYS_CNTKCTL); + ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg(par_el1); + ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1); + + ctxt_sys_reg(ctxt, SP_EL1) = read_sysreg(sp_el1); + ctxt_sys_reg(ctxt, ELR_EL1) = read_sysreg_el1(SYS_ELR); + ctxt_sys_reg(ctxt, SPSR_EL1) = read_sysreg_el1(SYS_SPSR); +} + +static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) +{ + ctxt->regs.pc = read_sysreg_el2(SYS_ELR); + ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); + + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2); +} + +static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(ctxt_sys_reg(ctxt, MDSCR_EL1), mdscr_el1); +} + +static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0), tpidr_el0); + write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0), tpidrro_el0); +} + +static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(ctxt_sys_reg(ctxt, MPIDR_EL1), vmpidr_el2); + write_sysreg(ctxt_sys_reg(ctxt, CSSELR_EL1), csselr_el1); + + if (has_vhe() || + !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } else if (!ctxt->__hyp_running_vcpu) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with nVHE's __activate_traps(). + */ + write_sysreg_el1((ctxt_sys_reg(ctxt, TCR_EL1) | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + + write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1), SYS_CPACR); + write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1), SYS_TTBR0); + write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1), SYS_TTBR1); + write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1), SYS_ESR); + write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1), SYS_AFSR0); + write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1), SYS_AFSR1); + write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL1), SYS_FAR); + write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL1), SYS_MAIR); + write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL1), SYS_VBAR); + write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR); + write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1), SYS_AMAIR); + write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL); + write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1), par_el1); + write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1), tpidr_el1); + + if (!has_vhe() && + cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with nVHE's __deactivate_traps(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } + + write_sysreg(ctxt_sys_reg(ctxt, SP_EL1), sp_el1); + write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1), SYS_ELR); + write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1), SYS_SPSR); +} + +static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) +{ + u64 pstate = ctxt->regs.pstate; + u64 mode = pstate & PSR_AA32_MODE_MASK; + + /* + * Safety check to ensure we're setting the CPU up to enter the guest + * in a less privileged mode. + * + * If we are attempting a return to EL2 or higher in AArch64 state, + * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that + * we'll take an illegal exception state exception immediately after + * the ERET to the guest. Attempts to return to AArch32 Hyp will + * result in an illegal exception return because EL2's execution state + * is determined by SCR_EL3.RW. + */ + if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t) + pstate = PSR_MODE_EL2h | PSR_IL_BIT; + + write_sysreg_el2(ctxt->regs.pc, SYS_ELR); + write_sysreg_el2(pstate, SYS_SPSR); + + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + write_sysreg_s(ctxt_sys_reg(ctxt, DISR_EL1), SYS_VDISR_EL2); +} + +static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + vcpu->arch.ctxt.spsr_abt = read_sysreg(spsr_abt); + vcpu->arch.ctxt.spsr_und = read_sysreg(spsr_und); + vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq); + vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq); + + __vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2); + __vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2); + + if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) + __vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2); +} + +static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + write_sysreg(vcpu->arch.ctxt.spsr_abt, spsr_abt); + write_sysreg(vcpu->arch.ctxt.spsr_und, spsr_und); + write_sysreg(vcpu->arch.ctxt.spsr_irq, spsr_irq); + write_sysreg(vcpu->arch.ctxt.spsr_fiq, spsr_fiq); + + write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2); + write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2); + + if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) + write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2); +} + +#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile new file mode 100644 index 000000000000..aef76487edc2 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -0,0 +1,62 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part +# + +asflags-y := -D__KVM_NVHE_HYPERVISOR__ +ccflags-y := -D__KVM_NVHE_HYPERVISOR__ + +obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o +obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ + ../fpsimd.o ../hyp-entry.o + +obj-y := $(patsubst %.o,%.hyp.o,$(obj-y)) +extra-y := $(patsubst %.hyp.o,%.hyp.tmp.o,$(obj-y)) + +$(obj)/%.hyp.tmp.o: $(src)/%.c FORCE + $(call if_changed_rule,cc_o_c) +$(obj)/%.hyp.tmp.o: $(src)/%.S FORCE + $(call if_changed_rule,as_o_S) +$(obj)/%.hyp.o: $(obj)/%.hyp.tmp.o FORCE + $(call if_changed,hypcopy) + +# Disable reordering functions by GCC (enabled at -O2). +# This pass puts functions into '.text.*' sections to aid the linker +# in optimizing ELF layout. See HYPCOPY comment below for more info. +ccflags-y += $(call cc-option,-fno-reorder-functions) + +# The HYPCOPY command uses `objcopy` to prefix all ELF symbol names +# and relevant ELF section names to avoid clashes with VHE code/data. +# +# Hyp code is assumed to be in the '.text' section of the input object +# files (with the exception of specialized sections such as +# '.hyp.idmap.text'). This assumption may be broken by a compiler that +# divides code into sections like '.text.unlikely' so as to optimize +# ELF layout. HYPCOPY checks that no such sections exist in the input +# using `objdump`, otherwise they would be linked together with other +# kernel code and not memory-mapped correctly at runtime. +quiet_cmd_hypcopy = HYPCOPY $@ + cmd_hypcopy = \ + if $(OBJDUMP) -h $< | grep -F '.text.'; then \ + echo "$@: function reordering not supported in nVHE hyp code" >&2; \ + /bin/false; \ + fi; \ + $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ \ + --rename-section=.text=.hyp.text \ + $< $@ + +# Remove ftrace and Shadow Call Stack CFLAGS. +# This is equivalent to the 'notrace' and '__noscs' annotations. +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) + +# KVM nVHE code is run at a different exception code with a different map, so +# compiler instrumentation that inserts callbacks or checks into the code may +# cause crashes. Just disable it. +GCOV_PROFILE := n +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +# Skip objtool checking for this directory because nVHE code is compiled with +# non-standard build rules. +OBJECT_FILES_NON_STANDARD := y diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c new file mode 100644 index 000000000000..91a711aa8382 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/debug-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/debug-monitors.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +static void __debug_save_spe(u64 *pmscr_el1) +{ + u64 reg; + + /* Clear pmscr in case of early return */ + *pmscr_el1 = 0; + + /* SPE present on this CPU? */ + if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1), + ID_AA64DFR0_PMSVER_SHIFT)) + return; + + /* Yes; is it owned by EL3? */ + reg = read_sysreg_s(SYS_PMBIDR_EL1); + if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) + return; + + /* No; is the host actually using the thing? */ + reg = read_sysreg_s(SYS_PMBLIMITR_EL1); + if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT))) + return; + + /* Yes; save the control register and disable data generation */ + *pmscr_el1 = read_sysreg_s(SYS_PMSCR_EL1); + write_sysreg_s(0, SYS_PMSCR_EL1); + isb(); + + /* Now drain all buffered data to memory */ + psb_csync(); + dsb(nsh); +} + +static void __debug_restore_spe(u64 pmscr_el1) +{ + if (!pmscr_el1) + return; + + /* The host page table is installed, but not yet synchronised */ + isb(); + + /* Re-enable data generation */ + write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1); +} + +void __debug_switch_to_guest(struct kvm_vcpu *vcpu) +{ + /* Disable and flush SPE data generation */ + __debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1); + __debug_switch_to_guest_common(vcpu); +} + +void __debug_switch_to_host(struct kvm_vcpu *vcpu) +{ + __debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1); + __debug_switch_to_host_common(vcpu); +} + +u32 __kvm_get_mdcr_el2(void) +{ + return read_sysreg(mdcr_el2); +} diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 86971fe26f3d..d9434e90c06d 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -105,6 +105,11 @@ alternative_else_nop_endif */ mov_q x4, (SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A)) CPU_BE( orr x4, x4, #SCTLR_ELx_EE) +alternative_if ARM64_HAS_ADDRESS_AUTH + mov_q x5, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \ + SCTLR_ELx_ENDA | SCTLR_ELx_ENDB) + orr x4, x4, x5 +alternative_else_nop_endif msr sctlr_el2, x4 isb diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c new file mode 100644 index 000000000000..341be2f2f312 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/switch.h> +#include <hyp/sysreg-sr.h> + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/thread_info.h> + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + ___activate_traps(vcpu); + __activate_traps_common(vcpu); + + val = CPTR_EL2_DEFAULT; + val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM; + if (!update_fp_enabled(vcpu)) { + val |= CPTR_EL2_TFP; + __activate_traps_fpsimd32(vcpu); + } + + write_sysreg(val, cptr_el2); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } +} + +static void __deactivate_traps(struct kvm_vcpu *vcpu) +{ + u64 mdcr_el2; + + ___deactivate_traps(vcpu); + + mdcr_el2 = read_sysreg(mdcr_el2); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + + __deactivate_traps_common(); + + mdcr_el2 &= MDCR_EL2_HPMN_MASK; + mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; + + write_sysreg(mdcr_el2, mdcr_el2); + write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); + write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); +} + +static void __deactivate_vm(struct kvm_vcpu *vcpu) +{ + write_sysreg(0, vttbr_el2); +} + +/* Save VGICv3 state on non-VHE systems */ +static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu) +{ + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { + __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); + } +} + +/* Restore VGICv3 state on non_VEH systems */ +static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) +{ + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { + __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); + } +} + +/** + * Disable host events, enable guest events + */ +static bool __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt) +{ + struct kvm_host_data *host; + struct kvm_pmu_events *pmu; + + host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); + pmu = &host->pmu_events; + + if (pmu->events_host) + write_sysreg(pmu->events_host, pmcntenclr_el0); + + if (pmu->events_guest) + write_sysreg(pmu->events_guest, pmcntenset_el0); + + return (pmu->events_host || pmu->events_guest); +} + +/** + * Disable guest events, enable host events + */ +static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) +{ + struct kvm_host_data *host; + struct kvm_pmu_events *pmu; + + host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); + pmu = &host->pmu_events; + + if (pmu->events_guest) + write_sysreg(pmu->events_guest, pmcntenclr_el0); + + if (pmu->events_host) + write_sysreg(pmu->events_host, pmcntenset_el0); +} + +/* Switch to the guest for legacy non-VHE systems */ +int __kvm_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + bool pmu_switch_needed; + u64 exit_code; + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + */ + if (system_uses_irq_prio_masking()) { + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + pmr_sync(); + } + + vcpu = kern_hyp_va(vcpu); + + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + host_ctxt->__hyp_running_vcpu = vcpu; + guest_ctxt = &vcpu->arch.ctxt; + + pmu_switch_needed = __pmu_switch_to_guest(host_ctxt); + + __sysreg_save_state_nvhe(host_ctxt); + + /* + * We must restore the 32-bit state before the sysregs, thanks + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. + */ + __sysreg32_restore_state(vcpu); + __sysreg_restore_state_nvhe(guest_ctxt); + + __activate_vm(kern_hyp_va(vcpu->arch.hw_mmu)); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + + __debug_switch_to_guest(vcpu); + + __set_guest_arch_workaround_state(vcpu); + + do { + /* Jump in the fire! */ + exit_code = __guest_enter(vcpu, host_ctxt); + + /* And we're baaack! */ + } while (fixup_guest_exit(vcpu, &exit_code)); + + __set_host_arch_workaround_state(vcpu); + + __sysreg_save_state_nvhe(guest_ctxt); + __sysreg32_save_state(vcpu); + __timer_disable_traps(vcpu); + __hyp_vgic_save_state(vcpu); + + __deactivate_traps(vcpu); + __deactivate_vm(vcpu); + + __sysreg_restore_state_nvhe(host_ctxt); + + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) + __fpsimd_save_fpexc32(vcpu); + + /* + * This must come after restoring the host sysregs, since a non-VHE + * system may enable SPE here and make use of the TTBRs. + */ + __debug_switch_to_host(vcpu); + + if (pmu_switch_needed) + __pmu_switch_to_host(host_ctxt); + + /* Returning to host will clear PSR.I, remask PMR if needed */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQOFF); + + return exit_code; +} + +void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) +{ + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); + u64 par = read_sysreg(par_el1); + struct kvm_vcpu *vcpu = host_ctxt->__hyp_running_vcpu; + unsigned long str_va; + + if (read_sysreg(vttbr_el2)) { + __timer_disable_traps(vcpu); + __deactivate_traps(vcpu); + __deactivate_vm(vcpu); + __sysreg_restore_state_nvhe(host_ctxt); + } + + /* + * Force the panic string to be loaded from the literal pool, + * making sure it is a kernel address and not a PC-relative + * reference. + */ + asm volatile("ldr %0, =%1" : "=r" (str_va) : "S" (__hyp_panic_string)); + + __hyp_do_panic(str_va, + spsr, elr, + read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR), + read_sysreg(hpfar_el2), par, vcpu); + unreachable(); +} diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c new file mode 100644 index 000000000000..88a25fc8fcd3 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/sysreg-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +/* + * Non-VHE: Both host and guest must save everything. + */ + +void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_el1_state(ctxt); + __sysreg_save_common_state(ctxt); + __sysreg_save_user_state(ctxt); + __sysreg_save_el2_return_state(ctxt); +} + +void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_restore_el1_state(ctxt); + __sysreg_restore_common_state(ctxt); + __sysreg_restore_user_state(ctxt); + __sysreg_restore_el2_return_state(ctxt); +} + +void __kvm_enable_ssbs(void) +{ + u64 tmp; + + asm volatile( + "mrs %0, sctlr_el2\n" + "orr %0, %0, %1\n" + "msr sctlr_el2, %0" + : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS)); +} diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c index fb5c0be33223..9072e71693ba 100644 --- a/arch/arm64/kvm/hyp/timer-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c @@ -10,7 +10,7 @@ #include <asm/kvm_hyp.h> -void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff) +void __kvm_timer_set_cntvoff(u64 cntvoff) { write_sysreg(cntvoff, cntvoff_el2); } @@ -19,7 +19,7 @@ void __hyp_text __kvm_timer_set_cntvoff(u64 cntvoff) * Should only be called on non-VHE systems. * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). */ -void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu) +void __timer_disable_traps(struct kvm_vcpu *vcpu) { u64 val; @@ -33,7 +33,7 @@ void __hyp_text __timer_disable_traps(struct kvm_vcpu *vcpu) * Should only be called on non-VHE systems. * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). */ -void __hyp_text __timer_enable_traps(struct kvm_vcpu *vcpu) +void __timer_enable_traps(struct kvm_vcpu *vcpu) { u64 val; diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c new file mode 100644 index 000000000000..69eae608d670 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/tlbflush.h> + +struct tlb_inv_context { + u64 tcr; +}; + +static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, + struct tlb_inv_context *cxt) +{ + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a host Stage-1 walk while we have the guest's + * VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the S1 MMU is enabled, so we can + * simply set the EPD bits to avoid any further TLB fill. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + } + + __load_guest_stage2(mmu); +} + +static void __tlb_switch_to_host(struct tlb_inv_context *cxt) +{ + write_sysreg(0, vttbr_el2); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + /* Ensure write of the host VMID */ + isb(); + /* Restore the host's TCR_EL1 */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + } +} + +void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + mmu = kern_hyp_va(mmu); + __tlb_switch_to_guest(mmu, &cxt); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + ipa >>= 12; + __tlbi_level(ipas2e1is, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(ish); + __tlbi(vmalle1is); + dsb(ish); + isb(); + + /* + * If the host is running at EL1 and we have a VPIPT I-cache, + * then we must perform I-cache maintenance at EL2 in order for + * it to have an effect on the guest. Since the guest cannot hit + * I-cache lines allocated with a different VMID, we don't need + * to worry about junk out of guest reset (we nuke the I-cache on + * VMID rollover), but we do need to be careful when remapping + * executable pages for the same guest. This can happen when KSM + * takes a CoW fault on an executable page, copies the page into + * a page that was previously mapped in the guest and then needs + * to invalidate the guest view of the I-cache for that page + * from EL1. To solve this, we invalidate the entire I-cache when + * unmapping a page from a guest if we have a VPIPT I-cache but + * the host is running at EL1. As above, we could do better if + * we had the VA. + * + * The moral of this story is: if you have a VPIPT I-cache, then + * you should be running with VHE enabled. + */ + if (icache_is_vpipt()) + __flush_icache_all(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + mmu = kern_hyp_va(mmu); + __tlb_switch_to_guest(mmu, &cxt); + + __tlbi(vmalls12e1is); + dsb(ish); + isb(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + mmu = kern_hyp_va(mmu); + __tlb_switch_to_guest(mmu, &cxt); + + __tlbi(vmalle1); + dsb(nsh); + isb(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_flush_vm_context(void) +{ + dsb(ishst); + __tlbi(alle1is); + + /* + * VIPT and PIPT caches are not affected by VMID, so no maintenance + * is necessary across a VMID rollover. + * + * VPIPT caches constrain lookup and maintenance to the active VMID, + * so we need to invalidate lines with a stale VMID to avoid an ABA + * race after multiple rollovers. + * + */ + if (icache_is_vpipt()) + asm volatile("ic ialluis"); + + dsb(ish); +} diff --git a/arch/arm64/kvm/hyp/smccc_wa.S b/arch/arm64/kvm/hyp/smccc_wa.S new file mode 100644 index 000000000000..b0441dbdf68b --- /dev/null +++ b/arch/arm64/kvm/hyp/smccc_wa.S @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015-2018 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/arm-smccc.h> +#include <linux/linkage.h> + +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + + /* + * This is not executed directly and is instead copied into the vectors + * by install_bp_hardening_cb(). + */ + .data + .pushsection .rodata + .global __smccc_workaround_1_smc +SYM_DATA_START(__smccc_workaround_1_smc) + esb + sub sp, sp, #(8 * 4) + stp x2, x3, [sp, #(8 * 0)] + stp x0, x1, [sp, #(8 * 2)] + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + smc #0 + ldp x2, x3, [sp, #(8 * 0)] + ldp x0, x1, [sp, #(8 * 2)] + add sp, sp, #(8 * 4) +1: .org __smccc_workaround_1_smc + __SMCCC_WORKAROUND_1_SMC_SZ + .org 1b +SYM_DATA_END(__smccc_workaround_1_smc) diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c deleted file mode 100644 index db1c4487d95d..000000000000 --- a/arch/arm64/kvm/hyp/switch.c +++ /dev/null @@ -1,936 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/arm-smccc.h> -#include <linux/kvm_host.h> -#include <linux/types.h> -#include <linux/jump_label.h> -#include <uapi/linux/psci.h> - -#include <kvm/arm_psci.h> - -#include <asm/barrier.h> -#include <asm/cpufeature.h> -#include <asm/kprobes.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> -#include <asm/fpsimd.h> -#include <asm/debug-monitors.h> -#include <asm/processor.h> -#include <asm/thread_info.h> - -/* Check whether the FP regs were dirtied while in the host-side run loop: */ -static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu) -{ - /* - * When the system doesn't support FP/SIMD, we cannot rely on - * the _TIF_FOREIGN_FPSTATE flag. However, we always inject an - * abort on the very first access to FP and thus we should never - * see KVM_ARM64_FP_ENABLED. For added safety, make sure we always - * trap the accesses. - */ - if (!system_supports_fpsimd() || - vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) - vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | - KVM_ARM64_FP_HOST); - - return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED); -} - -/* Save the 32-bit only FPSIMD system register state */ -static void __hyp_text __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu) -{ - if (!vcpu_el1_is_32bit(vcpu)) - return; - - vcpu->arch.ctxt.sys_regs[FPEXC32_EL2] = read_sysreg(fpexc32_el2); -} - -static void __hyp_text __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) -{ - /* - * We are about to set CPTR_EL2.TFP to trap all floating point - * register accesses to EL2, however, the ARM ARM clearly states that - * traps are only taken to EL2 if the operation would not otherwise - * trap to EL1. Therefore, always make sure that for 32-bit guests, - * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. - * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to - * it will cause an exception. - */ - if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) { - write_sysreg(1 << 30, fpexc32_el2); - isb(); - } -} - -static void __hyp_text __activate_traps_common(struct kvm_vcpu *vcpu) -{ - /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ - write_sysreg(1 << 15, hstr_el2); - - /* - * Make sure we trap PMU access from EL0 to EL2. Also sanitize - * PMSELR_EL0 to make sure it never contains the cycle - * counter, which could make a PMXEVCNTR_EL0 access UNDEF at - * EL1 instead of being trapped to EL2. - */ - write_sysreg(0, pmselr_el0); - write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); - write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); -} - -static void __hyp_text __deactivate_traps_common(void) -{ - write_sysreg(0, hstr_el2); - write_sysreg(0, pmuserenr_el0); -} - -static void activate_traps_vhe(struct kvm_vcpu *vcpu) -{ - u64 val; - - val = read_sysreg(cpacr_el1); - val |= CPACR_EL1_TTA; - val &= ~CPACR_EL1_ZEN; - - /* - * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to - * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2, - * except for some missing controls, such as TAM. - * In this case, CPTR_EL2.TAM has the same position with or without - * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM - * shift value for trapping the AMU accesses. - */ - - val |= CPTR_EL2_TAM; - - if (update_fp_enabled(vcpu)) { - if (vcpu_has_sve(vcpu)) - val |= CPACR_EL1_ZEN; - } else { - val &= ~CPACR_EL1_FPEN; - __activate_traps_fpsimd32(vcpu); - } - - write_sysreg(val, cpacr_el1); - - write_sysreg(kvm_get_hyp_vector(), vbar_el1); -} -NOKPROBE_SYMBOL(activate_traps_vhe); - -static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) -{ - u64 val; - - __activate_traps_common(vcpu); - - val = CPTR_EL2_DEFAULT; - val |= CPTR_EL2_TTA | CPTR_EL2_TZ | CPTR_EL2_TAM; - if (!update_fp_enabled(vcpu)) { - val |= CPTR_EL2_TFP; - __activate_traps_fpsimd32(vcpu); - } - - write_sysreg(val, cptr_el2); - - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; - - isb(); - /* - * At this stage, and thanks to the above isb(), S2 is - * configured and enabled. We can now restore the guest's S1 - * configuration: SCTLR, and only then TCR. - */ - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); - isb(); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); - } -} - -static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) -{ - u64 hcr = vcpu->arch.hcr_el2; - - if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) - hcr |= HCR_TVM; - - write_sysreg(hcr, hcr_el2); - - if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) - write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); - - if (has_vhe()) - activate_traps_vhe(vcpu); - else - __activate_traps_nvhe(vcpu); -} - -static void deactivate_traps_vhe(void) -{ - extern char vectors[]; /* kernel exception vectors */ - write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); - - /* - * ARM errata 1165522 and 1530923 require the actual execution of the - * above before we can switch to the EL2/EL0 translation regime used by - * the host. - */ - asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - - write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); - write_sysreg(vectors, vbar_el1); -} -NOKPROBE_SYMBOL(deactivate_traps_vhe); - -static void __hyp_text __deactivate_traps_nvhe(void) -{ - u64 mdcr_el2 = read_sysreg(mdcr_el2); - - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - u64 val; - - /* - * Set the TCR and SCTLR registers in the exact opposite - * sequence as __activate_traps_nvhe (first prevent walks, - * then force the MMU on). A generous sprinkling of isb() - * ensure that things happen in this exact order. - */ - val = read_sysreg_el1(SYS_TCR); - write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); - isb(); - val = read_sysreg_el1(SYS_SCTLR); - write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); - isb(); - } - - __deactivate_traps_common(); - - mdcr_el2 &= MDCR_EL2_HPMN_MASK; - mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; - - write_sysreg(mdcr_el2, mdcr_el2); - write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); - write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); -} - -static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) -{ - /* - * If we pended a virtual abort, preserve it until it gets - * cleared. See D1.14.3 (Virtual Interrupts) for details, but - * the crucial bit is "On taking a vSError interrupt, - * HCR_EL2.VSE is cleared to 0." - */ - if (vcpu->arch.hcr_el2 & HCR_VSE) { - vcpu->arch.hcr_el2 &= ~HCR_VSE; - vcpu->arch.hcr_el2 |= read_sysreg(hcr_el2) & HCR_VSE; - } - - if (has_vhe()) - deactivate_traps_vhe(); - else - __deactivate_traps_nvhe(); -} - -void activate_traps_vhe_load(struct kvm_vcpu *vcpu) -{ - __activate_traps_common(vcpu); -} - -void deactivate_traps_vhe_put(void) -{ - u64 mdcr_el2 = read_sysreg(mdcr_el2); - - mdcr_el2 &= MDCR_EL2_HPMN_MASK | - MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT | - MDCR_EL2_TPMS; - - write_sysreg(mdcr_el2, mdcr_el2); - - __deactivate_traps_common(); -} - -static void __hyp_text __activate_vm(struct kvm *kvm) -{ - __load_guest_stage2(kvm); -} - -static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) -{ - write_sysreg(0, vttbr_el2); -} - -/* Save VGICv3 state on non-VHE systems */ -static void __hyp_text __hyp_vgic_save_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); - __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); - } -} - -/* Restore VGICv3 state on non_VEH systems */ -static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) -{ - if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { - __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); - __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); - } -} - -static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) -{ - u64 par, tmp; - - /* - * Resolve the IPA the hard way using the guest VA. - * - * Stage-1 translation already validated the memory access - * rights. As such, we can use the EL1 translation regime, and - * don't have to distinguish between EL0 and EL1 access. - * - * We do need to save/restore PAR_EL1 though, as we haven't - * saved the guest context yet, and we may return early... - */ - par = read_sysreg(par_el1); - asm volatile("at s1e1r, %0" : : "r" (far)); - isb(); - - tmp = read_sysreg(par_el1); - write_sysreg(par, par_el1); - - if (unlikely(tmp & SYS_PAR_EL1_F)) - return false; /* Translation failed, back to guest */ - - /* Convert PAR to HPFAR format */ - *hpfar = PAR_TO_HPFAR(tmp); - return true; -} - -static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) -{ - u8 ec; - u64 esr; - u64 hpfar, far; - - esr = vcpu->arch.fault.esr_el2; - ec = ESR_ELx_EC(esr); - - if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW) - return true; - - far = read_sysreg_el2(SYS_FAR); - - /* - * The HPFAR can be invalid if the stage 2 fault did not - * happen during a stage 1 page table walk (the ESR_EL2.S1PTW - * bit is clear) and one of the two following cases are true: - * 1. The fault was due to a permission fault - * 2. The processor carries errata 834220 - * - * Therefore, for all non S1PTW faults where we either have a - * permission fault or the errata workaround is enabled, we - * resolve the IPA using the AT instruction. - */ - if (!(esr & ESR_ELx_S1PTW) && - (cpus_have_final_cap(ARM64_WORKAROUND_834220) || - (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { - if (!__translate_far_to_hpfar(far, &hpfar)) - return false; - } else { - hpfar = read_sysreg(hpfar_el2); - } - - vcpu->arch.fault.far_el2 = far; - vcpu->arch.fault.hpfar_el2 = hpfar; - return true; -} - -/* Check for an FPSIMD/SVE trap and handle as appropriate */ -static bool __hyp_text __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) -{ - bool vhe, sve_guest, sve_host; - u8 hsr_ec; - - if (!system_supports_fpsimd()) - return false; - - if (system_supports_sve()) { - sve_guest = vcpu_has_sve(vcpu); - sve_host = vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE; - vhe = true; - } else { - sve_guest = false; - sve_host = false; - vhe = has_vhe(); - } - - hsr_ec = kvm_vcpu_trap_get_class(vcpu); - if (hsr_ec != ESR_ELx_EC_FP_ASIMD && - hsr_ec != ESR_ELx_EC_SVE) - return false; - - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest) - if (hsr_ec != ESR_ELx_EC_FP_ASIMD) - return false; - - /* Valid trap. Switch the context: */ - - if (vhe) { - u64 reg = read_sysreg(cpacr_el1) | CPACR_EL1_FPEN; - - if (sve_guest) - reg |= CPACR_EL1_ZEN; - - write_sysreg(reg, cpacr_el1); - } else { - write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP, - cptr_el2); - } - - isb(); - - if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { - /* - * In the SVE case, VHE is assumed: it is enforced by - * Kconfig and kvm_arch_init(). - */ - if (sve_host) { - struct thread_struct *thread = container_of( - vcpu->arch.host_fpsimd_state, - struct thread_struct, uw.fpsimd_state); - - sve_save_state(sve_pffr(thread), - &vcpu->arch.host_fpsimd_state->fpsr); - } else { - __fpsimd_save_state(vcpu->arch.host_fpsimd_state); - } - - vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; - } - - if (sve_guest) { - sve_load_state(vcpu_sve_pffr(vcpu), - &vcpu->arch.ctxt.gp_regs.fp_regs.fpsr, - sve_vq_from_vl(vcpu->arch.sve_max_vl) - 1); - write_sysreg_s(vcpu->arch.ctxt.sys_regs[ZCR_EL1], SYS_ZCR_EL12); - } else { - __fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs); - } - - /* Skip restoring fpexc32 for AArch64 guests */ - if (!(read_sysreg(hcr_el2) & HCR_RW)) - write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2], - fpexc32_el2); - - vcpu->arch.flags |= KVM_ARM64_FP_ENABLED; - - return true; -} - -static bool __hyp_text handle_tx2_tvm(struct kvm_vcpu *vcpu) -{ - u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_hsr(vcpu)); - int rt = kvm_vcpu_sys_get_rt(vcpu); - u64 val = vcpu_get_reg(vcpu, rt); - - /* - * The normal sysreg handling code expects to see the traps, - * let's not do anything here. - */ - if (vcpu->arch.hcr_el2 & HCR_TVM) - return false; - - switch (sysreg) { - case SYS_SCTLR_EL1: - write_sysreg_el1(val, SYS_SCTLR); - break; - case SYS_TTBR0_EL1: - write_sysreg_el1(val, SYS_TTBR0); - break; - case SYS_TTBR1_EL1: - write_sysreg_el1(val, SYS_TTBR1); - break; - case SYS_TCR_EL1: - write_sysreg_el1(val, SYS_TCR); - break; - case SYS_ESR_EL1: - write_sysreg_el1(val, SYS_ESR); - break; - case SYS_FAR_EL1: - write_sysreg_el1(val, SYS_FAR); - break; - case SYS_AFSR0_EL1: - write_sysreg_el1(val, SYS_AFSR0); - break; - case SYS_AFSR1_EL1: - write_sysreg_el1(val, SYS_AFSR1); - break; - case SYS_MAIR_EL1: - write_sysreg_el1(val, SYS_MAIR); - break; - case SYS_AMAIR_EL1: - write_sysreg_el1(val, SYS_AMAIR); - break; - case SYS_CONTEXTIDR_EL1: - write_sysreg_el1(val, SYS_CONTEXTIDR); - break; - default: - return false; - } - - __kvm_skip_instr(vcpu); - return true; -} - -static bool __hyp_text esr_is_ptrauth_trap(u32 esr) -{ - u32 ec = ESR_ELx_EC(esr); - - if (ec == ESR_ELx_EC_PAC) - return true; - - if (ec != ESR_ELx_EC_SYS64) - return false; - - switch (esr_sys64_to_sysreg(esr)) { - case SYS_APIAKEYLO_EL1: - case SYS_APIAKEYHI_EL1: - case SYS_APIBKEYLO_EL1: - case SYS_APIBKEYHI_EL1: - case SYS_APDAKEYLO_EL1: - case SYS_APDAKEYHI_EL1: - case SYS_APDBKEYLO_EL1: - case SYS_APDBKEYHI_EL1: - case SYS_APGAKEYLO_EL1: - case SYS_APGAKEYHI_EL1: - return true; - } - - return false; -} - -#define __ptrauth_save_key(regs, key) \ -({ \ - regs[key ## KEYLO_EL1] = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ - regs[key ## KEYHI_EL1] = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ -}) - -static bool __hyp_text __hyp_handle_ptrauth(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *ctxt; - u64 val; - - if (!vcpu_has_ptrauth(vcpu) || - !esr_is_ptrauth_trap(kvm_vcpu_get_hsr(vcpu))) - return false; - - ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; - __ptrauth_save_key(ctxt->sys_regs, APIA); - __ptrauth_save_key(ctxt->sys_regs, APIB); - __ptrauth_save_key(ctxt->sys_regs, APDA); - __ptrauth_save_key(ctxt->sys_regs, APDB); - __ptrauth_save_key(ctxt->sys_regs, APGA); - - vcpu_ptrauth_enable(vcpu); - - val = read_sysreg(hcr_el2); - val |= (HCR_API | HCR_APK); - write_sysreg(val, hcr_el2); - - return true; -} - -/* - * Return true when we were able to fixup the guest exit and should return to - * the guest, false when we should restore the host state and return to the - * main run loop. - */ -static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) -{ - if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) - vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); - - /* - * We're using the raw exception code in order to only process - * the trap if no SError is pending. We will come back to the - * same PC once the SError has been injected, and replay the - * trapping instruction. - */ - if (*exit_code != ARM_EXCEPTION_TRAP) - goto exit; - - if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && - handle_tx2_tvm(vcpu)) - return true; - - /* - * We trap the first access to the FP/SIMD to save the host context - * and restore the guest context lazily. - * If FP/SIMD is not implemented, handle the trap and inject an - * undefined instruction exception to the guest. - * Similarly for trapped SVE accesses. - */ - if (__hyp_handle_fpsimd(vcpu)) - return true; - - if (__hyp_handle_ptrauth(vcpu)) - return true; - - if (!__populate_fault_info(vcpu)) - return true; - - if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { - bool valid; - - valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW && - kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && - kvm_vcpu_dabt_isvalid(vcpu) && - !kvm_vcpu_dabt_isextabt(vcpu) && - !kvm_vcpu_dabt_iss1tw(vcpu); - - if (valid) { - int ret = __vgic_v2_perform_cpuif_access(vcpu); - - if (ret == 1) - return true; - - /* Promote an illegal access to an SError.*/ - if (ret == -1) - *exit_code = ARM_EXCEPTION_EL1_SERROR; - - goto exit; - } - } - - if (static_branch_unlikely(&vgic_v3_cpuif_trap) && - (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 || - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) { - int ret = __vgic_v3_perform_cpuif_access(vcpu); - - if (ret == 1) - return true; - } - -exit: - /* Return to the host kernel and handle the exit */ - return false; -} - -static inline bool __hyp_text __needs_ssbd_off(struct kvm_vcpu *vcpu) -{ - if (!cpus_have_final_cap(ARM64_SSBD)) - return false; - - return !(vcpu->arch.workaround_flags & VCPU_WORKAROUND_2_FLAG); -} - -static void __hyp_text __set_guest_arch_workaround_state(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_ARM64_SSBD - /* - * The host runs with the workaround always present. If the - * guest wants it disabled, so be it... - */ - if (__needs_ssbd_off(vcpu) && - __hyp_this_cpu_read(arm64_ssbd_callback_required)) - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 0, NULL); -#endif -} - -static void __hyp_text __set_host_arch_workaround_state(struct kvm_vcpu *vcpu) -{ -#ifdef CONFIG_ARM64_SSBD - /* - * If the guest has disabled the workaround, bring it back on. - */ - if (__needs_ssbd_off(vcpu) && - __hyp_this_cpu_read(arm64_ssbd_callback_required)) - arm_smccc_1_1_smc(ARM_SMCCC_ARCH_WORKAROUND_2, 1, NULL); -#endif -} - -/** - * Disable host events, enable guest events - */ -static bool __hyp_text __pmu_switch_to_guest(struct kvm_cpu_context *host_ctxt) -{ - struct kvm_host_data *host; - struct kvm_pmu_events *pmu; - - host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); - pmu = &host->pmu_events; - - if (pmu->events_host) - write_sysreg(pmu->events_host, pmcntenclr_el0); - - if (pmu->events_guest) - write_sysreg(pmu->events_guest, pmcntenset_el0); - - return (pmu->events_host || pmu->events_guest); -} - -/** - * Disable guest events, enable host events - */ -static void __hyp_text __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) -{ - struct kvm_host_data *host; - struct kvm_pmu_events *pmu; - - host = container_of(host_ctxt, struct kvm_host_data, host_ctxt); - pmu = &host->pmu_events; - - if (pmu->events_guest) - write_sysreg(pmu->events_guest, pmcntenclr_el0); - - if (pmu->events_host) - write_sysreg(pmu->events_host, pmcntenset_el0); -} - -/* Switch to the guest for VHE systems running in EL2 */ -static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *host_ctxt; - struct kvm_cpu_context *guest_ctxt; - u64 exit_code; - - host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; - host_ctxt->__hyp_running_vcpu = vcpu; - guest_ctxt = &vcpu->arch.ctxt; - - sysreg_save_host_state_vhe(host_ctxt); - - /* - * ARM erratum 1165522 requires us to configure both stage 1 and - * stage 2 translation for the guest context before we clear - * HCR_EL2.TGE. - * - * We have already configured the guest's stage 1 translation in - * kvm_vcpu_load_sysregs above. We must now call __activate_vm - * before __activate_traps, because __activate_vm configures - * stage 2 translation, and __activate_traps clear HCR_EL2.TGE - * (among other things). - */ - __activate_vm(vcpu->kvm); - __activate_traps(vcpu); - - sysreg_restore_guest_state_vhe(guest_ctxt); - __debug_switch_to_guest(vcpu); - - __set_guest_arch_workaround_state(vcpu); - - do { - /* Jump in the fire! */ - exit_code = __guest_enter(vcpu, host_ctxt); - - /* And we're baaack! */ - } while (fixup_guest_exit(vcpu, &exit_code)); - - __set_host_arch_workaround_state(vcpu); - - sysreg_save_guest_state_vhe(guest_ctxt); - - __deactivate_traps(vcpu); - - sysreg_restore_host_state_vhe(host_ctxt); - - if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) - __fpsimd_save_fpexc32(vcpu); - - __debug_switch_to_host(vcpu); - - return exit_code; -} -NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); - -int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) -{ - int ret; - - local_daif_mask(); - - /* - * Having IRQs masked via PMR when entering the guest means the GIC - * will not signal the CPU of interrupts of lower priority, and the - * only way to get out will be via guest exceptions. - * Naturally, we want to avoid this. - * - * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a - * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. - */ - pmr_sync(); - - ret = __kvm_vcpu_run_vhe(vcpu); - - /* - * local_daif_restore() takes care to properly restore PSTATE.DAIF - * and the GIC PMR if the host is using IRQ priorities. - */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - /* - * When we exit from the guest we change a number of CPU configuration - * parameters, such as traps. Make sure these changes take effect - * before running the host or additional guests. - */ - isb(); - - return ret; -} - -/* Switch to the guest for legacy non-VHE systems */ -int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *host_ctxt; - struct kvm_cpu_context *guest_ctxt; - bool pmu_switch_needed; - u64 exit_code; - - /* - * Having IRQs masked via PMR when entering the guest means the GIC - * will not signal the CPU of interrupts of lower priority, and the - * only way to get out will be via guest exceptions. - * Naturally, we want to avoid this. - */ - if (system_uses_irq_prio_masking()) { - gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - pmr_sync(); - } - - vcpu = kern_hyp_va(vcpu); - - host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; - host_ctxt->__hyp_running_vcpu = vcpu; - guest_ctxt = &vcpu->arch.ctxt; - - pmu_switch_needed = __pmu_switch_to_guest(host_ctxt); - - __sysreg_save_state_nvhe(host_ctxt); - - /* - * We must restore the 32-bit state before the sysregs, thanks - * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). - * - * Also, and in order to be able to deal with erratum #1319537 (A57) - * and #1319367 (A72), we must ensure that all VM-related sysreg are - * restored before we enable S2 translation. - */ - __sysreg32_restore_state(vcpu); - __sysreg_restore_state_nvhe(guest_ctxt); - - __activate_vm(kern_hyp_va(vcpu->kvm)); - __activate_traps(vcpu); - - __hyp_vgic_restore_state(vcpu); - __timer_enable_traps(vcpu); - - __debug_switch_to_guest(vcpu); - - __set_guest_arch_workaround_state(vcpu); - - do { - /* Jump in the fire! */ - exit_code = __guest_enter(vcpu, host_ctxt); - - /* And we're baaack! */ - } while (fixup_guest_exit(vcpu, &exit_code)); - - __set_host_arch_workaround_state(vcpu); - - __sysreg_save_state_nvhe(guest_ctxt); - __sysreg32_save_state(vcpu); - __timer_disable_traps(vcpu); - __hyp_vgic_save_state(vcpu); - - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - - __sysreg_restore_state_nvhe(host_ctxt); - - if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) - __fpsimd_save_fpexc32(vcpu); - - /* - * This must come after restoring the host sysregs, since a non-VHE - * system may enable SPE here and make use of the TTBRs. - */ - __debug_switch_to_host(vcpu); - - if (pmu_switch_needed) - __pmu_switch_to_host(host_ctxt); - - /* Returning to host will clear PSR.I, remask PMR if needed */ - if (system_uses_irq_prio_masking()) - gic_write_pmr(GIC_PRIO_IRQOFF); - - return exit_code; -} - -static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n"; - -static void __hyp_text __hyp_call_panic_nvhe(u64 spsr, u64 elr, u64 par, - struct kvm_cpu_context *__host_ctxt) -{ - struct kvm_vcpu *vcpu; - unsigned long str_va; - - vcpu = __host_ctxt->__hyp_running_vcpu; - - if (read_sysreg(vttbr_el2)) { - __timer_disable_traps(vcpu); - __deactivate_traps(vcpu); - __deactivate_vm(vcpu); - __sysreg_restore_state_nvhe(__host_ctxt); - } - - /* - * Force the panic string to be loaded from the literal pool, - * making sure it is a kernel address and not a PC-relative - * reference. - */ - asm volatile("ldr %0, =__hyp_panic_string" : "=r" (str_va)); - - __hyp_do_panic(str_va, - spsr, elr, - read_sysreg(esr_el2), read_sysreg_el2(SYS_FAR), - read_sysreg(hpfar_el2), par, vcpu); -} - -static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, - struct kvm_cpu_context *host_ctxt) -{ - struct kvm_vcpu *vcpu; - vcpu = host_ctxt->__hyp_running_vcpu; - - __deactivate_traps(vcpu); - sysreg_restore_host_state_vhe(host_ctxt); - - panic(__hyp_panic_string, - spsr, elr, - read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), - read_sysreg(hpfar_el2), par, vcpu); -} -NOKPROBE_SYMBOL(__hyp_call_panic_vhe); - -void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) -{ - u64 spsr = read_sysreg_el2(SYS_SPSR); - u64 elr = read_sysreg_el2(SYS_ELR); - u64 par = read_sysreg(par_el1); - - if (!has_vhe()) - __hyp_call_panic_nvhe(spsr, elr, par, host_ctxt); - else - __hyp_call_panic_vhe(spsr, elr, par, host_ctxt); - - unreachable(); -} diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c deleted file mode 100644 index cc7e957f5b2c..000000000000 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ /dev/null @@ -1,333 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012-2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/compiler.h> -#include <linux/kvm_host.h> - -#include <asm/kprobes.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_hyp.h> - -/* - * Non-VHE: Both host and guest must save everything. - * - * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and - * pstate, which are handled as part of the el2 return state) on every - * switch (sp_el0 is being dealt with in the assembly code). - * tpidr_el0 and tpidrro_el0 only need to be switched when going - * to host userspace or a different VCPU. EL1 registers only need to be - * switched when potentially going to run a different VCPU. The latter two - * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. - */ - -static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) -{ - ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); -} - -static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) -{ - ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0); - ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0); -} - -static void __hyp_text __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) -{ - ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1); - ctxt->sys_regs[SCTLR_EL1] = read_sysreg_el1(SYS_SCTLR); - ctxt->sys_regs[CPACR_EL1] = read_sysreg_el1(SYS_CPACR); - ctxt->sys_regs[TTBR0_EL1] = read_sysreg_el1(SYS_TTBR0); - ctxt->sys_regs[TTBR1_EL1] = read_sysreg_el1(SYS_TTBR1); - ctxt->sys_regs[TCR_EL1] = read_sysreg_el1(SYS_TCR); - ctxt->sys_regs[ESR_EL1] = read_sysreg_el1(SYS_ESR); - ctxt->sys_regs[AFSR0_EL1] = read_sysreg_el1(SYS_AFSR0); - ctxt->sys_regs[AFSR1_EL1] = read_sysreg_el1(SYS_AFSR1); - ctxt->sys_regs[FAR_EL1] = read_sysreg_el1(SYS_FAR); - ctxt->sys_regs[MAIR_EL1] = read_sysreg_el1(SYS_MAIR); - ctxt->sys_regs[VBAR_EL1] = read_sysreg_el1(SYS_VBAR); - ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg_el1(SYS_CONTEXTIDR); - ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(SYS_AMAIR); - ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(SYS_CNTKCTL); - ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1); - ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); - - ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1); - ctxt->gp_regs.elr_el1 = read_sysreg_el1(SYS_ELR); - ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg_el1(SYS_SPSR); -} - -static void __hyp_text __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) -{ - ctxt->gp_regs.regs.pc = read_sysreg_el2(SYS_ELR); - ctxt->gp_regs.regs.pstate = read_sysreg_el2(SYS_SPSR); - - if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) - ctxt->sys_regs[DISR_EL1] = read_sysreg_s(SYS_VDISR_EL2); -} - -void __hyp_text __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_save_el1_state(ctxt); - __sysreg_save_common_state(ctxt); - __sysreg_save_user_state(ctxt); - __sysreg_save_el2_return_state(ctxt); -} - -void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_save_common_state(ctxt); -} -NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); - -void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_save_common_state(ctxt); - __sysreg_save_el2_return_state(ctxt); -} -NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); - -static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) -{ - write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); -} - -static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) -{ - write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); - write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); -} - -static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt) -{ - write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); - write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); - - if (has_vhe() || - !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); - } else if (!ctxt->__hyp_running_vcpu) { - /* - * Must only be done for guest registers, hence the context - * test. We're coming from the host, so SCTLR.M is already - * set. Pairs with __activate_traps_nvhe(). - */ - write_sysreg_el1((ctxt->sys_regs[TCR_EL1] | - TCR_EPD1_MASK | TCR_EPD0_MASK), - SYS_TCR); - isb(); - } - - write_sysreg_el1(ctxt->sys_regs[CPACR_EL1], SYS_CPACR); - write_sysreg_el1(ctxt->sys_regs[TTBR0_EL1], SYS_TTBR0); - write_sysreg_el1(ctxt->sys_regs[TTBR1_EL1], SYS_TTBR1); - write_sysreg_el1(ctxt->sys_regs[ESR_EL1], SYS_ESR); - write_sysreg_el1(ctxt->sys_regs[AFSR0_EL1], SYS_AFSR0); - write_sysreg_el1(ctxt->sys_regs[AFSR1_EL1], SYS_AFSR1); - write_sysreg_el1(ctxt->sys_regs[FAR_EL1], SYS_FAR); - write_sysreg_el1(ctxt->sys_regs[MAIR_EL1], SYS_MAIR); - write_sysreg_el1(ctxt->sys_regs[VBAR_EL1], SYS_VBAR); - write_sysreg_el1(ctxt->sys_regs[CONTEXTIDR_EL1],SYS_CONTEXTIDR); - write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], SYS_AMAIR); - write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], SYS_CNTKCTL); - write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); - write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); - - if (!has_vhe() && - cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) && - ctxt->__hyp_running_vcpu) { - /* - * Must only be done for host registers, hence the context - * test. Pairs with __deactivate_traps_nvhe(). - */ - isb(); - /* - * At this stage, and thanks to the above isb(), S2 is - * deconfigured and disabled. We can now restore the host's - * S1 configuration: SCTLR, and only then TCR. - */ - write_sysreg_el1(ctxt->sys_regs[SCTLR_EL1], SYS_SCTLR); - isb(); - write_sysreg_el1(ctxt->sys_regs[TCR_EL1], SYS_TCR); - } - - write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); - write_sysreg_el1(ctxt->gp_regs.elr_el1, SYS_ELR); - write_sysreg_el1(ctxt->gp_regs.spsr[KVM_SPSR_EL1],SYS_SPSR); -} - -static void __hyp_text -__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) -{ - u64 pstate = ctxt->gp_regs.regs.pstate; - u64 mode = pstate & PSR_AA32_MODE_MASK; - - /* - * Safety check to ensure we're setting the CPU up to enter the guest - * in a less privileged mode. - * - * If we are attempting a return to EL2 or higher in AArch64 state, - * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that - * we'll take an illegal exception state exception immediately after - * the ERET to the guest. Attempts to return to AArch32 Hyp will - * result in an illegal exception return because EL2's execution state - * is determined by SCR_EL3.RW. - */ - if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t) - pstate = PSR_MODE_EL2h | PSR_IL_BIT; - - write_sysreg_el2(ctxt->gp_regs.regs.pc, SYS_ELR); - write_sysreg_el2(pstate, SYS_SPSR); - - if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) - write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2); -} - -void __hyp_text __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_restore_el1_state(ctxt); - __sysreg_restore_common_state(ctxt); - __sysreg_restore_user_state(ctxt); - __sysreg_restore_el2_return_state(ctxt); -} - -void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_restore_common_state(ctxt); -} -NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); - -void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) -{ - __sysreg_restore_common_state(ctxt); - __sysreg_restore_el2_return_state(ctxt); -} -NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); - -void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) -{ - u64 *spsr, *sysreg; - - if (!vcpu_el1_is_32bit(vcpu)) - return; - - spsr = vcpu->arch.ctxt.gp_regs.spsr; - sysreg = vcpu->arch.ctxt.sys_regs; - - spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt); - spsr[KVM_SPSR_UND] = read_sysreg(spsr_und); - spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq); - spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq); - - sysreg[DACR32_EL2] = read_sysreg(dacr32_el2); - sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2); - - if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) - sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2); -} - -void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu) -{ - u64 *spsr, *sysreg; - - if (!vcpu_el1_is_32bit(vcpu)) - return; - - spsr = vcpu->arch.ctxt.gp_regs.spsr; - sysreg = vcpu->arch.ctxt.sys_regs; - - write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt); - write_sysreg(spsr[KVM_SPSR_UND], spsr_und); - write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq); - write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq); - - write_sysreg(sysreg[DACR32_EL2], dacr32_el2); - write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2); - - if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) - write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2); -} - -/** - * kvm_vcpu_load_sysregs - Load guest system registers to the physical CPU - * - * @vcpu: The VCPU pointer - * - * Load system registers that do not affect the host's execution, for - * example EL1 system registers on a VHE system where the host kernel - * runs at EL2. This function is called from KVM's vcpu_load() function - * and loading system register state early avoids having to load them on - * every entry to the VM. - */ -void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; - struct kvm_cpu_context *host_ctxt; - - if (!has_vhe()) - return; - - host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; - __sysreg_save_user_state(host_ctxt); - - /* - * Load guest EL1 and user state - * - * We must restore the 32-bit state before the sysregs, thanks - * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). - */ - __sysreg32_restore_state(vcpu); - __sysreg_restore_user_state(guest_ctxt); - __sysreg_restore_el1_state(guest_ctxt); - - vcpu->arch.sysregs_loaded_on_cpu = true; - - activate_traps_vhe_load(vcpu); -} - -/** - * kvm_vcpu_put_sysregs - Restore host system registers to the physical CPU - * - * @vcpu: The VCPU pointer - * - * Save guest system registers that do not affect the host's execution, for - * example EL1 system registers on a VHE system where the host kernel - * runs at EL2. This function is called from KVM's vcpu_put() function - * and deferring saving system register state until we're no longer running the - * VCPU avoids having to save them on every exit from the VM. - */ -void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) -{ - struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; - struct kvm_cpu_context *host_ctxt; - - if (!has_vhe()) - return; - - host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; - deactivate_traps_vhe_put(); - - __sysreg_save_el1_state(guest_ctxt); - __sysreg_save_user_state(guest_ctxt); - __sysreg32_save_state(vcpu); - - /* Restore host user state */ - __sysreg_restore_user_state(host_ctxt); - - vcpu->arch.sysregs_loaded_on_cpu = false; -} - -void __hyp_text __kvm_enable_ssbs(void) -{ - u64 tmp; - - asm volatile( - "mrs %0, sctlr_el2\n" - "orr %0, %0, %1\n" - "msr sctlr_el2, %0" - : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS)); -} diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c deleted file mode 100644 index d063a576d511..000000000000 --- a/arch/arm64/kvm/hyp/tlb.c +++ /dev/null @@ -1,242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2015 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#include <linux/irqflags.h> - -#include <asm/kvm_hyp.h> -#include <asm/kvm_mmu.h> -#include <asm/tlbflush.h> - -struct tlb_inv_context { - unsigned long flags; - u64 tcr; - u64 sctlr; -}; - -static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - u64 val; - - local_irq_save(cxt->flags); - - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - /* - * For CPUs that are affected by ARM errata 1165522 or 1530923, - * we cannot trust stage-1 to be in a correct state at that - * point. Since we do not want to force a full load of the - * vcpu state, we prevent the EL1 page-table walker to - * allocate new TLBs. This is done by setting the EPD bits - * in the TCR_EL1 register. We also need to prevent it to - * allocate IPA->PA walks, so we enable the S1 MMU... - */ - val = cxt->tcr = read_sysreg_el1(SYS_TCR); - val |= TCR_EPD1_MASK | TCR_EPD0_MASK; - write_sysreg_el1(val, SYS_TCR); - val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); - val |= SCTLR_ELx_M; - write_sysreg_el1(val, SYS_SCTLR); - } - - /* - * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and - * most TLB operations target EL2/EL0. In order to affect the - * guest TLBs (EL1/EL0), we need to change one of these two - * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so - * let's flip TGE before executing the TLB operation. - * - * ARM erratum 1165522 requires some special handling (again), - * as we need to make sure both stages of translation are in - * place before clearing TGE. __load_guest_stage2() already - * has an ISB in order to deal with this. - */ - __load_guest_stage2(kvm); - val = read_sysreg(hcr_el2); - val &= ~HCR_TGE; - write_sysreg(val, hcr_el2); - isb(); -} - -static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - u64 val; - - /* - * For CPUs that are affected by ARM 1319367, we need to - * avoid a host Stage-1 walk while we have the guest's - * VMID set in the VTTBR in order to invalidate TLBs. - * We're guaranteed that the S1 MMU is enabled, so we can - * simply set the EPD bits to avoid any further TLB fill. - */ - val = cxt->tcr = read_sysreg_el1(SYS_TCR); - val |= TCR_EPD1_MASK | TCR_EPD0_MASK; - write_sysreg_el1(val, SYS_TCR); - isb(); - } - - /* __load_guest_stage2() includes an ISB for the workaround. */ - __load_guest_stage2(kvm); - asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); -} - -static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - if (has_vhe()) - __tlb_switch_to_guest_vhe(kvm, cxt); - else - __tlb_switch_to_guest_nvhe(kvm, cxt); -} - -static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - /* - * We're done with the TLB operation, let's restore the host's - * view of HCR_EL2. - */ - write_sysreg(0, vttbr_el2); - write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); - isb(); - - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - /* Restore the registers to what they were */ - write_sysreg_el1(cxt->tcr, SYS_TCR); - write_sysreg_el1(cxt->sctlr, SYS_SCTLR); - } - - local_irq_restore(cxt->flags); -} - -static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - write_sysreg(0, vttbr_el2); - - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { - /* Ensure write of the host VMID */ - isb(); - /* Restore the host's TCR_EL1 */ - write_sysreg_el1(cxt->tcr, SYS_TCR); - } -} - -static void __hyp_text __tlb_switch_to_host(struct kvm *kvm, - struct tlb_inv_context *cxt) -{ - if (has_vhe()) - __tlb_switch_to_host_vhe(kvm, cxt); - else - __tlb_switch_to_host_nvhe(kvm, cxt); -} - -void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) -{ - struct tlb_inv_context cxt; - - dsb(ishst); - - /* Switch to requested VMID */ - kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest(kvm, &cxt); - - /* - * We could do so much better if we had the VA as well. - * Instead, we invalidate Stage-2 for this IPA, and the - * whole of Stage-1. Weep... - */ - ipa >>= 12; - __tlbi(ipas2e1is, ipa); - - /* - * We have to ensure completion of the invalidation at Stage-2, - * since a table walk on another CPU could refill a TLB with a - * complete (S1 + S2) walk based on the old Stage-2 mapping if - * the Stage-1 invalidation happened first. - */ - dsb(ish); - __tlbi(vmalle1is); - dsb(ish); - isb(); - - /* - * If the host is running at EL1 and we have a VPIPT I-cache, - * then we must perform I-cache maintenance at EL2 in order for - * it to have an effect on the guest. Since the guest cannot hit - * I-cache lines allocated with a different VMID, we don't need - * to worry about junk out of guest reset (we nuke the I-cache on - * VMID rollover), but we do need to be careful when remapping - * executable pages for the same guest. This can happen when KSM - * takes a CoW fault on an executable page, copies the page into - * a page that was previously mapped in the guest and then needs - * to invalidate the guest view of the I-cache for that page - * from EL1. To solve this, we invalidate the entire I-cache when - * unmapping a page from a guest if we have a VPIPT I-cache but - * the host is running at EL1. As above, we could do better if - * we had the VA. - * - * The moral of this story is: if you have a VPIPT I-cache, then - * you should be running with VHE enabled. - */ - if (!has_vhe() && icache_is_vpipt()) - __flush_icache_all(); - - __tlb_switch_to_host(kvm, &cxt); -} - -void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) -{ - struct tlb_inv_context cxt; - - dsb(ishst); - - /* Switch to requested VMID */ - kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest(kvm, &cxt); - - __tlbi(vmalls12e1is); - dsb(ish); - isb(); - - __tlb_switch_to_host(kvm, &cxt); -} - -void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) -{ - struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); - struct tlb_inv_context cxt; - - /* Switch to requested VMID */ - __tlb_switch_to_guest(kvm, &cxt); - - __tlbi(vmalle1); - dsb(nsh); - isb(); - - __tlb_switch_to_host(kvm, &cxt); -} - -void __hyp_text __kvm_flush_vm_context(void) -{ - dsb(ishst); - __tlbi(alle1is); - - /* - * VIPT and PIPT caches are not affected by VMID, so no maintenance - * is necessary across a VMID rollover. - * - * VPIPT caches constrain lookup and maintenance to the active VMID, - * so we need to invalidate lines with a stale VMID to avoid an ABA - * race after multiple rollovers. - * - */ - if (icache_is_vpipt()) - asm volatile("ic ialluis"); - - dsb(ish); -} diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 4f3a087e36d5..bd1bab551d48 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -13,7 +13,7 @@ #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> -static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) +static bool __is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT); @@ -32,7 +32,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) * 0: Not a GICV access * -1: Illegal GICV access successfully performed */ -int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) +int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) { struct kvm *kvm = kern_hyp_va(vcpu->kvm); struct vgic_dist *vgic = &kvm->arch.vgic; diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 10ed539835c1..5a0073511efb 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -16,7 +16,7 @@ #define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1) #define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5)) -static u64 __hyp_text __gic_v3_get_lr(unsigned int lr) +static u64 __gic_v3_get_lr(unsigned int lr) { switch (lr & 0xf) { case 0: @@ -56,7 +56,7 @@ static u64 __hyp_text __gic_v3_get_lr(unsigned int lr) unreachable(); } -static void __hyp_text __gic_v3_set_lr(u64 val, int lr) +static void __gic_v3_set_lr(u64 val, int lr) { switch (lr & 0xf) { case 0: @@ -110,7 +110,7 @@ static void __hyp_text __gic_v3_set_lr(u64 val, int lr) } } -static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n) +static void __vgic_v3_write_ap0rn(u32 val, int n) { switch (n) { case 0: @@ -128,7 +128,7 @@ static void __hyp_text __vgic_v3_write_ap0rn(u32 val, int n) } } -static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n) +static void __vgic_v3_write_ap1rn(u32 val, int n) { switch (n) { case 0: @@ -146,7 +146,7 @@ static void __hyp_text __vgic_v3_write_ap1rn(u32 val, int n) } } -static u32 __hyp_text __vgic_v3_read_ap0rn(int n) +static u32 __vgic_v3_read_ap0rn(int n) { u32 val; @@ -170,7 +170,7 @@ static u32 __hyp_text __vgic_v3_read_ap0rn(int n) return val; } -static u32 __hyp_text __vgic_v3_read_ap1rn(int n) +static u32 __vgic_v3_read_ap1rn(int n) { u32 val; @@ -194,7 +194,7 @@ static u32 __hyp_text __vgic_v3_read_ap1rn(int n) return val; } -void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; @@ -229,7 +229,7 @@ void __hyp_text __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) } } -void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; int i; @@ -255,7 +255,7 @@ void __hyp_text __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) } } -void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) { /* * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a @@ -302,7 +302,7 @@ void __hyp_text __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); } -void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) { u64 val; @@ -328,7 +328,7 @@ void __hyp_text __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) write_gicreg(0, ICH_HCR_EL2); } -void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; @@ -361,7 +361,7 @@ void __hyp_text __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) } } -void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) +void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; @@ -394,7 +394,7 @@ void __hyp_text __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) } } -void __hyp_text __vgic_v3_init_lrs(void) +void __vgic_v3_init_lrs(void) { int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2)); int i; @@ -403,30 +403,30 @@ void __hyp_text __vgic_v3_init_lrs(void) __gic_v3_set_lr(0, i); } -u64 __hyp_text __vgic_v3_get_ich_vtr_el2(void) +u64 __vgic_v3_get_ich_vtr_el2(void) { return read_gicreg(ICH_VTR_EL2); } -u64 __hyp_text __vgic_v3_read_vmcr(void) +u64 __vgic_v3_read_vmcr(void) { return read_gicreg(ICH_VMCR_EL2); } -void __hyp_text __vgic_v3_write_vmcr(u32 vmcr) +void __vgic_v3_write_vmcr(u32 vmcr) { write_gicreg(vmcr, ICH_VMCR_EL2); } -static int __hyp_text __vgic_v3_bpr_min(void) +static int __vgic_v3_bpr_min(void) { /* See Pseudocode for VPriorityGroup */ return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2)); } -static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu) +static int __vgic_v3_get_group(struct kvm_vcpu *vcpu) { - u32 esr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; return crm != 8; @@ -434,9 +434,8 @@ static int __hyp_text __vgic_v3_get_group(struct kvm_vcpu *vcpu) #define GICv3_IDLE_PRIORITY 0xff -static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, - u32 vmcr, - u64 *lr_val) +static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr, + u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; u8 priority = GICv3_IDLE_PRIORITY; @@ -474,8 +473,8 @@ static int __hyp_text __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, return lr; } -static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, - int intid, u64 *lr_val) +static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid, + u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; int i; @@ -494,7 +493,7 @@ static int __hyp_text __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, return -1; } -static int __hyp_text __vgic_v3_get_highest_active_priority(void) +static int __vgic_v3_get_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; @@ -526,12 +525,12 @@ static int __hyp_text __vgic_v3_get_highest_active_priority(void) return GICv3_IDLE_PRIORITY; } -static unsigned int __hyp_text __vgic_v3_get_bpr0(u32 vmcr) +static unsigned int __vgic_v3_get_bpr0(u32 vmcr) { return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; } -static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr) +static unsigned int __vgic_v3_get_bpr1(u32 vmcr) { unsigned int bpr; @@ -550,7 +549,7 @@ static unsigned int __hyp_text __vgic_v3_get_bpr1(u32 vmcr) * Convert a priority to a preemption level, taking the relevant BPR * into account by zeroing the sub-priority bits. */ -static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) +static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) { unsigned int bpr; @@ -568,7 +567,7 @@ static u8 __hyp_text __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) * matter what the guest does with its BPR, we can always set/get the * same value of a priority. */ -static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) +static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) { u8 pre, ap; u32 val; @@ -587,7 +586,7 @@ static void __hyp_text __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) } } -static int __hyp_text __vgic_v3_clear_highest_active_priority(void) +static int __vgic_v3_clear_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; @@ -625,7 +624,7 @@ static int __hyp_text __vgic_v3_clear_highest_active_priority(void) return GICv3_IDLE_PRIORITY; } -static void __hyp_text __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; u8 lr_prio, pmr; @@ -661,7 +660,7 @@ spurious: vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS); } -static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val) +static void __vgic_v3_clear_active_lr(int lr, u64 lr_val) { lr_val &= ~ICH_LR_ACTIVE_BIT; if (lr_val & ICH_LR_HW) { @@ -674,7 +673,7 @@ static void __hyp_text __vgic_v3_clear_active_lr(int lr, u64 lr_val) __gic_v3_set_lr(lr_val, lr); } -static void __hyp_text __vgic_v3_bump_eoicount(void) +static void __vgic_v3_bump_eoicount(void) { u32 hcr; @@ -683,8 +682,7 @@ static void __hyp_text __vgic_v3_bump_eoicount(void) write_gicreg(hcr, ICH_HCR_EL2); } -static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; @@ -707,7 +705,7 @@ static void __hyp_text __vgic_v3_write_dir(struct kvm_vcpu *vcpu, __vgic_v3_clear_active_lr(lr, lr_val); } -static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; @@ -744,17 +742,17 @@ static void __hyp_text __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int __vgic_v3_clear_active_lr(lr, lr_val); } -static void __hyp_text __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK)); } -static void __hyp_text __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK)); } -static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); @@ -766,7 +764,7 @@ static void __hyp_text __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, __vgic_v3_write_vmcr(vmcr); } -static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); @@ -778,17 +776,17 @@ static void __hyp_text __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, __vgic_v3_write_vmcr(vmcr); } -static void __hyp_text __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr)); } -static void __hyp_text __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr)); } -static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min() - 1; @@ -805,7 +803,7 @@ static void __hyp_text __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int __vgic_v3_write_vmcr(vmcr); } -static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min(); @@ -825,7 +823,7 @@ static void __hyp_text __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int __vgic_v3_write_vmcr(vmcr); } -static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val; @@ -837,7 +835,7 @@ static void __hyp_text __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n vcpu_set_reg(vcpu, rt, val); } -static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val = vcpu_get_reg(vcpu, rt); @@ -847,56 +845,49 @@ static void __hyp_text __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int __vgic_v3_write_ap1rn(val, n); } -static void __hyp_text __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, +static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 0); } -static void __hyp_text __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, +static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 1); } -static void __hyp_text __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 2); } -static void __hyp_text __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 3); } -static void __hyp_text __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 0); } -static void __hyp_text __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 1); } -static void __hyp_text __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 2); } -static void __hyp_text __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 3); } -static void __hyp_text __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; int lr, lr_grp, grp; @@ -915,16 +906,14 @@ spurious: vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); } -static void __hyp_text __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vmcr &= ICH_VMCR_PMR_MASK; vmcr >>= ICH_VMCR_PMR_SHIFT; vcpu_set_reg(vcpu, rt, vmcr); } -static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); @@ -936,15 +925,13 @@ static void __hyp_text __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, write_gicreg(vmcr, ICH_VMCR_EL2); } -static void __hyp_text __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = __vgic_v3_get_highest_active_priority(); vcpu_set_reg(vcpu, rt, val); } -static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vtr, val; @@ -965,8 +952,7 @@ static void __hyp_text __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, vcpu_set_reg(vcpu, rt, val); } -static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, - u32 vmcr, int rt) +static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); @@ -983,7 +969,7 @@ static void __hyp_text __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, write_gicreg(vmcr, ICH_VMCR_EL2); } -int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) +int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) { int rt; u32 esr; @@ -992,7 +978,7 @@ int __hyp_text __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) bool is_read; u32 sysreg; - esr = kvm_vcpu_get_hsr(vcpu); + esr = kvm_vcpu_get_esr(vcpu); if (vcpu_mode_is_32bit(vcpu)) { if (!kvm_condition_valid(vcpu)) { __kvm_skip_instr(vcpu); diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile new file mode 100644 index 000000000000..461e97c375cc --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part +# + +asflags-y := -D__KVM_VHE_HYPERVISOR__ +ccflags-y := -D__KVM_VHE_HYPERVISOR__ + +obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o +obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ + ../fpsimd.o ../hyp-entry.o diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c new file mode 100644 index 000000000000..f1e2e5a00933 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/debug-sr.h> + +#include <linux/kvm_host.h> + +#include <asm/kvm_hyp.h> + +void __debug_switch_to_guest(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_guest_common(vcpu); +} + +void __debug_switch_to_host(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_host_common(vcpu); +} + +u32 __kvm_get_mdcr_el2(void) +{ + return read_sysreg(mdcr_el2); +} diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c new file mode 100644 index 000000000000..c52d714e0d75 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/switch.h> + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/thread_info.h> + +const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n"; + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + ___activate_traps(vcpu); + + val = read_sysreg(cpacr_el1); + val |= CPACR_EL1_TTA; + val &= ~CPACR_EL1_ZEN; + + /* + * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to + * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2, + * except for some missing controls, such as TAM. + * In this case, CPTR_EL2.TAM has the same position with or without + * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM + * shift value for trapping the AMU accesses. + */ + + val |= CPTR_EL2_TAM; + + if (update_fp_enabled(vcpu)) { + if (vcpu_has_sve(vcpu)) + val |= CPACR_EL1_ZEN; + } else { + val &= ~CPACR_EL1_FPEN; + __activate_traps_fpsimd32(vcpu); + } + + write_sysreg(val, cpacr_el1); + + write_sysreg(kvm_get_hyp_vector(), vbar_el1); +} +NOKPROBE_SYMBOL(__activate_traps); + +static void __deactivate_traps(struct kvm_vcpu *vcpu) +{ + extern char vectors[]; /* kernel exception vectors */ + + ___deactivate_traps(vcpu); + + write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + + /* + * ARM errata 1165522 and 1530923 require the actual execution of the + * above before we can switch to the EL2/EL0 translation regime used by + * the host. + */ + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); + + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); + write_sysreg(vectors, vbar_el1); +} +NOKPROBE_SYMBOL(__deactivate_traps); + +void activate_traps_vhe_load(struct kvm_vcpu *vcpu) +{ + __activate_traps_common(vcpu); +} + +void deactivate_traps_vhe_put(void) +{ + u64 mdcr_el2 = read_sysreg(mdcr_el2); + + mdcr_el2 &= MDCR_EL2_HPMN_MASK | + MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT | + MDCR_EL2_TPMS; + + write_sysreg(mdcr_el2, mdcr_el2); + + __deactivate_traps_common(); +} + +/* Switch to the guest for VHE systems running in EL2 */ +static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + u64 exit_code; + + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + host_ctxt->__hyp_running_vcpu = vcpu; + guest_ctxt = &vcpu->arch.ctxt; + + sysreg_save_host_state_vhe(host_ctxt); + + /* + * ARM erratum 1165522 requires us to configure both stage 1 and + * stage 2 translation for the guest context before we clear + * HCR_EL2.TGE. + * + * We have already configured the guest's stage 1 translation in + * kvm_vcpu_load_sysregs_vhe above. We must now call __activate_vm + * before __activate_traps, because __activate_vm configures + * stage 2 translation, and __activate_traps clear HCR_EL2.TGE + * (among other things). + */ + __activate_vm(vcpu->arch.hw_mmu); + __activate_traps(vcpu); + + sysreg_restore_guest_state_vhe(guest_ctxt); + __debug_switch_to_guest(vcpu); + + __set_guest_arch_workaround_state(vcpu); + + do { + /* Jump in the fire! */ + exit_code = __guest_enter(vcpu, host_ctxt); + + /* And we're baaack! */ + } while (fixup_guest_exit(vcpu, &exit_code)); + + __set_host_arch_workaround_state(vcpu); + + sysreg_save_guest_state_vhe(guest_ctxt); + + __deactivate_traps(vcpu); + + sysreg_restore_host_state_vhe(host_ctxt); + + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) + __fpsimd_save_fpexc32(vcpu); + + __debug_switch_to_host(vcpu); + + return exit_code; +} +NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); + +int __kvm_vcpu_run(struct kvm_vcpu *vcpu) +{ + int ret; + + local_daif_mask(); + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. + */ + pmr_sync(); + + ret = __kvm_vcpu_run_vhe(vcpu); + + /* + * local_daif_restore() takes care to properly restore PSTATE.DAIF + * and the GIC PMR if the host is using IRQ priorities. + */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + /* + * When we exit from the guest we change a number of CPU configuration + * parameters, such as traps. Make sure these changes take effect + * before running the host or additional guests. + */ + isb(); + + return ret; +} + +static void __hyp_call_panic(u64 spsr, u64 elr, u64 par, + struct kvm_cpu_context *host_ctxt) +{ + struct kvm_vcpu *vcpu; + vcpu = host_ctxt->__hyp_running_vcpu; + + __deactivate_traps(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); + + panic(__hyp_panic_string, + spsr, elr, + read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), + read_sysreg(hpfar_el2), par, vcpu); +} +NOKPROBE_SYMBOL(__hyp_call_panic); + +void __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) +{ + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); + u64 par = read_sysreg(par_el1); + + __hyp_call_panic(spsr, elr, par, host_ctxt); + unreachable(); +} diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c new file mode 100644 index 000000000000..996471e4c138 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/sysreg-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +/* + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). + * tpidr_el0 and tpidrro_el0 only need to be switched when going + * to host userspace or a different VCPU. EL1 registers only need to be + * switched when potentially going to run a different VCPU. The latter two + * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. + */ + +void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_common_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); + +void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_common_state(ctxt); + __sysreg_save_el2_return_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); + +void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_restore_common_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); + +void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_restore_common_state(ctxt); + __sysreg_restore_el2_return_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); + +/** + * kvm_vcpu_load_sysregs_vhe - Load guest system registers to the physical CPU + * + * @vcpu: The VCPU pointer + * + * Load system registers that do not affect the host's execution, for + * example EL1 system registers on a VHE system where the host kernel + * runs at EL2. This function is called from KVM's vcpu_load() function + * and loading system register state early avoids having to load them on + * every entry to the VM. + */ +void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; + struct kvm_cpu_context *host_ctxt; + + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + __sysreg_save_user_state(host_ctxt); + + /* + * Load guest EL1 and user state + * + * We must restore the 32-bit state before the sysregs, thanks + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + */ + __sysreg32_restore_state(vcpu); + __sysreg_restore_user_state(guest_ctxt); + __sysreg_restore_el1_state(guest_ctxt); + + vcpu->arch.sysregs_loaded_on_cpu = true; + + activate_traps_vhe_load(vcpu); +} + +/** + * kvm_vcpu_put_sysregs_vhe - Restore host system registers to the physical CPU + * + * @vcpu: The VCPU pointer + * + * Save guest system registers that do not affect the host's execution, for + * example EL1 system registers on a VHE system where the host kernel + * runs at EL2. This function is called from KVM's vcpu_put() function + * and deferring saving system register state until we're no longer running the + * VCPU avoids having to save them on every exit from the VM. + */ +void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; + struct kvm_cpu_context *host_ctxt; + + host_ctxt = &__hyp_this_cpu_ptr(kvm_host_data)->host_ctxt; + deactivate_traps_vhe_put(); + + __sysreg_save_el1_state(guest_ctxt); + __sysreg_save_user_state(guest_ctxt); + __sysreg32_save_state(vcpu); + + /* Restore host user state */ + __sysreg_restore_user_state(host_ctxt); + + vcpu->arch.sysregs_loaded_on_cpu = false; +} diff --git a/arch/arm64/kvm/hyp/vhe/timer-sr.c b/arch/arm64/kvm/hyp/vhe/timer-sr.c new file mode 100644 index 000000000000..4cda674a8be6 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/timer-sr.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <asm/kvm_hyp.h> + +void __kvm_timer_set_cntvoff(u64 cntvoff) +{ + write_sysreg(cntvoff, cntvoff_el2); +} diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c new file mode 100644 index 000000000000..fd7895945bbc --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/irqflags.h> + +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/tlbflush.h> + +struct tlb_inv_context { + unsigned long flags; + u64 tcr; + u64 sctlr; +}; + +static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, + struct tlb_inv_context *cxt) +{ + u64 val; + + local_irq_save(cxt->flags); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + /* + * For CPUs that are affected by ARM errata 1165522 or 1530923, + * we cannot trust stage-1 to be in a correct state at that + * point. Since we do not want to force a full load of the + * vcpu state, we prevent the EL1 page-table walker to + * allocate new TLBs. This is done by setting the EPD bits + * in the TCR_EL1 register. We also need to prevent it to + * allocate IPA->PA walks, so we enable the S1 MMU... + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); + val |= SCTLR_ELx_M; + write_sysreg_el1(val, SYS_SCTLR); + } + + /* + * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and + * most TLB operations target EL2/EL0. In order to affect the + * guest TLBs (EL1/EL0), we need to change one of these two + * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so + * let's flip TGE before executing the TLB operation. + * + * ARM erratum 1165522 requires some special handling (again), + * as we need to make sure both stages of translation are in + * place before clearing TGE. __load_guest_stage2() already + * has an ISB in order to deal with this. + */ + __load_guest_stage2(mmu); + val = read_sysreg(hcr_el2); + val &= ~HCR_TGE; + write_sysreg(val, hcr_el2); + isb(); +} + +static void __tlb_switch_to_host(struct tlb_inv_context *cxt) +{ + /* + * We're done with the TLB operation, let's restore the host's + * view of HCR_EL2. + */ + write_sysreg(0, vttbr_el2); + write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + isb(); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + /* Restore the registers to what they were */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + write_sysreg_el1(cxt->sctlr, SYS_SCTLR); + } + + local_irq_restore(cxt->flags); +} + +void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + __tlb_switch_to_guest(mmu, &cxt); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + ipa >>= 12; + __tlbi_level(ipas2e1is, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(ish); + __tlbi(vmalle1is); + dsb(ish); + isb(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + __tlb_switch_to_guest(mmu, &cxt); + + __tlbi(vmalls12e1is); + dsb(ish); + isb(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + __tlb_switch_to_guest(mmu, &cxt); + + __tlbi(vmalle1); + dsb(nsh); + isb(); + + __tlb_switch_to_host(&cxt); +} + +void __kvm_flush_vm_context(void) +{ + dsb(ishst); + __tlbi(alle1is); + + /* + * VIPT and PIPT caches are not affected by VMID, so no maintenance + * is necessary across a VMID rollover. + * + * VPIPT caches constrain lookup and maintenance to the active VMID, + * so we need to invalidate lines with a stale VMID to avoid an ABA + * race after multiple rollovers. + * + */ + if (icache_is_vpipt()) + asm volatile("ic ialluis"); + + dsb(ish); +} diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index e21fdd93027a..ebfdfc27b2bd 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -64,7 +64,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, case PSR_MODE_EL1h: vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1); sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); - vcpu_write_elr_el1(vcpu, *vcpu_pc(vcpu)); + vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); break; default: /* Don't do that */ diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 158fbe682611..6a2826f1bf5e 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -146,12 +146,6 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) return -ENOSYS; } - /* Page table accesses IO mem: tell guest to fix its TTBR */ - if (kvm_vcpu_dabt_iss1tw(vcpu)) { - kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); - return 1; - } - /* * Prepare MMIO operation. First decode the syndrome data we get * from the CPU. Then try if some in-kernel emulation feels diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 7a7ddc4558a7..0121ef2c7c8d 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -55,12 +55,13 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot) */ void kvm_flush_remote_tlbs(struct kvm *kvm) { - kvm_call_hyp(__kvm_tlb_flush_vmid, kvm); + kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu); } -static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +static void kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa, + int level) { - kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa); + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ipa, level); } /* @@ -90,74 +91,80 @@ static bool kvm_is_device_pfn(unsigned long pfn) /** * stage2_dissolve_pmd() - clear and flush huge PMD entry - * @kvm: pointer to kvm structure. + * @mmu: pointer to mmu structure to operate on * @addr: IPA * @pmd: pmd pointer for IPA * * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. */ -static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd) +static void stage2_dissolve_pmd(struct kvm_s2_mmu *mmu, phys_addr_t addr, pmd_t *pmd) { if (!pmd_thp_or_huge(*pmd)) return; pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL); put_page(virt_to_page(pmd)); } /** * stage2_dissolve_pud() - clear and flush huge PUD entry - * @kvm: pointer to kvm structure. + * @mmu: pointer to mmu structure to operate on * @addr: IPA * @pud: pud pointer for IPA * * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. */ -static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp) +static void stage2_dissolve_pud(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t *pudp) { + struct kvm *kvm = mmu->kvm; + if (!stage2_pud_huge(kvm, *pudp)) return; stage2_pud_clear(kvm, pudp); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL); put_page(virt_to_page(pudp)); } -static void clear_stage2_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr) +static void clear_stage2_pgd_entry(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; p4d_t *p4d_table __maybe_unused = stage2_p4d_offset(kvm, pgd, 0UL); stage2_pgd_clear(kvm, pgd); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT); stage2_p4d_free(kvm, p4d_table); put_page(virt_to_page(pgd)); } -static void clear_stage2_p4d_entry(struct kvm *kvm, p4d_t *p4d, phys_addr_t addr) +static void clear_stage2_p4d_entry(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; pud_t *pud_table __maybe_unused = stage2_pud_offset(kvm, p4d, 0); stage2_p4d_clear(kvm, p4d); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT); stage2_pud_free(kvm, pud_table); put_page(virt_to_page(p4d)); } -static void clear_stage2_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) +static void clear_stage2_pud_entry(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; pmd_t *pmd_table __maybe_unused = stage2_pmd_offset(kvm, pud, 0); + VM_BUG_ON(stage2_pud_huge(kvm, *pud)); stage2_pud_clear(kvm, pud); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT); stage2_pmd_free(kvm, pmd_table); put_page(virt_to_page(pud)); } -static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) +static void clear_stage2_pmd_entry(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr) { pte_t *pte_table = pte_offset_kernel(pmd, 0); VM_BUG_ON(pmd_thp_or_huge(*pmd)); pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_NO_LEVEL_HINT); free_page((unsigned long)pte_table); put_page(virt_to_page(pmd)); } @@ -223,7 +230,7 @@ static inline void kvm_pgd_populate(pgd_t *pgdp, p4d_t *p4dp) * we then fully enforce cacheability of RAM, no matter what the guest * does. */ -static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd, +static void unmap_stage2_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { phys_addr_t start_addr = addr; @@ -235,7 +242,7 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd, pte_t old_pte = *pte; kvm_set_pte(pte, __pte(0)); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL); /* No need to invalidate the cache for device mappings */ if (!kvm_is_device_pfn(pte_pfn(old_pte))) @@ -245,13 +252,14 @@ static void unmap_stage2_ptes(struct kvm *kvm, pmd_t *pmd, } } while (pte++, addr += PAGE_SIZE, addr != end); - if (stage2_pte_table_empty(kvm, start_pte)) - clear_stage2_pmd_entry(kvm, pmd, start_addr); + if (stage2_pte_table_empty(mmu->kvm, start_pte)) + clear_stage2_pmd_entry(mmu, pmd, start_addr); } -static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud, +static void unmap_stage2_pmds(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; phys_addr_t next, start_addr = addr; pmd_t *pmd, *start_pmd; @@ -263,24 +271,25 @@ static void unmap_stage2_pmds(struct kvm *kvm, pud_t *pud, pmd_t old_pmd = *pmd; pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL); kvm_flush_dcache_pmd(old_pmd); put_page(virt_to_page(pmd)); } else { - unmap_stage2_ptes(kvm, pmd, addr, next); + unmap_stage2_ptes(mmu, pmd, addr, next); } } } while (pmd++, addr = next, addr != end); if (stage2_pmd_table_empty(kvm, start_pmd)) - clear_stage2_pud_entry(kvm, pud, start_addr); + clear_stage2_pud_entry(mmu, pud, start_addr); } -static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d, +static void unmap_stage2_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; phys_addr_t next, start_addr = addr; pud_t *pud, *start_pud; @@ -292,22 +301,23 @@ static void unmap_stage2_puds(struct kvm *kvm, p4d_t *p4d, pud_t old_pud = *pud; stage2_pud_clear(kvm, pud); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL); kvm_flush_dcache_pud(old_pud); put_page(virt_to_page(pud)); } else { - unmap_stage2_pmds(kvm, pud, addr, next); + unmap_stage2_pmds(mmu, pud, addr, next); } } } while (pud++, addr = next, addr != end); if (stage2_pud_table_empty(kvm, start_pud)) - clear_stage2_p4d_entry(kvm, p4d, start_addr); + clear_stage2_p4d_entry(mmu, p4d, start_addr); } -static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd, +static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; phys_addr_t next, start_addr = addr; p4d_t *p4d, *start_p4d; @@ -315,11 +325,11 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd, do { next = stage2_p4d_addr_end(kvm, addr, end); if (!stage2_p4d_none(kvm, *p4d)) - unmap_stage2_puds(kvm, p4d, addr, next); + unmap_stage2_puds(mmu, p4d, addr, next); } while (p4d++, addr = next, addr != end); if (stage2_p4d_table_empty(kvm, start_p4d)) - clear_stage2_pgd_entry(kvm, pgd, start_addr); + clear_stage2_pgd_entry(mmu, pgd, start_addr); } /** @@ -333,8 +343,9 @@ static void unmap_stage2_p4ds(struct kvm *kvm, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) +static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) { + struct kvm *kvm = mmu->kvm; pgd_t *pgd; phys_addr_t addr = start, end = start + size; phys_addr_t next; @@ -342,18 +353,18 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) assert_spin_locked(&kvm->mmu_lock); WARN_ON(size & ~PAGE_MASK); - pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + pgd = mmu->pgd + stage2_pgd_index(kvm, addr); do { /* * Make sure the page table is still active, as another thread * could have possibly freed the page table, while we released * the lock. */ - if (!READ_ONCE(kvm->arch.pgd)) + if (!READ_ONCE(mmu->pgd)) break; next = stage2_pgd_addr_end(kvm, addr, end); if (!stage2_pgd_none(kvm, *pgd)) - unmap_stage2_p4ds(kvm, pgd, addr, next); + unmap_stage2_p4ds(mmu, pgd, addr, next); /* * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. @@ -363,7 +374,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size) } while (pgd++, addr = next, addr != end); } -static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, +static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { pte_t *pte; @@ -375,9 +386,10 @@ static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd, } while (pte++, addr += PAGE_SIZE, addr != end); } -static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, +static void stage2_flush_pmds(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; pmd_t *pmd; phys_addr_t next; @@ -388,14 +400,15 @@ static void stage2_flush_pmds(struct kvm *kvm, pud_t *pud, if (pmd_thp_or_huge(*pmd)) kvm_flush_dcache_pmd(*pmd); else - stage2_flush_ptes(kvm, pmd, addr, next); + stage2_flush_ptes(mmu, pmd, addr, next); } } while (pmd++, addr = next, addr != end); } -static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d, +static void stage2_flush_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; pud_t *pud; phys_addr_t next; @@ -406,14 +419,15 @@ static void stage2_flush_puds(struct kvm *kvm, p4d_t *p4d, if (stage2_pud_huge(kvm, *pud)) kvm_flush_dcache_pud(*pud); else - stage2_flush_pmds(kvm, pud, addr, next); + stage2_flush_pmds(mmu, pud, addr, next); } } while (pud++, addr = next, addr != end); } -static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd, +static void stage2_flush_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; p4d_t *p4d; phys_addr_t next; @@ -421,23 +435,24 @@ static void stage2_flush_p4ds(struct kvm *kvm, pgd_t *pgd, do { next = stage2_p4d_addr_end(kvm, addr, end); if (!stage2_p4d_none(kvm, *p4d)) - stage2_flush_puds(kvm, p4d, addr, next); + stage2_flush_puds(mmu, p4d, addr, next); } while (p4d++, addr = next, addr != end); } static void stage2_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) { + struct kvm_s2_mmu *mmu = &kvm->arch.mmu; phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT; phys_addr_t end = addr + PAGE_SIZE * memslot->npages; phys_addr_t next; pgd_t *pgd; - pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + pgd = mmu->pgd + stage2_pgd_index(kvm, addr); do { next = stage2_pgd_addr_end(kvm, addr, end); if (!stage2_pgd_none(kvm, *pgd)) - stage2_flush_p4ds(kvm, pgd, addr, next); + stage2_flush_p4ds(mmu, pgd, addr, next); if (next != end) cond_resched_lock(&kvm->mmu_lock); @@ -964,21 +979,23 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, } /** - * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. - * @kvm: The KVM struct pointer for the VM. + * kvm_init_stage2_mmu - Initialise a S2 MMU strucrure + * @kvm: The pointer to the KVM structure + * @mmu: The pointer to the s2 MMU structure * * Allocates only the stage-2 HW PGD level table(s) of size defined by - * stage2_pgd_size(kvm). + * stage2_pgd_size(mmu->kvm). * * Note we don't need locking here as this is only called when the VM is * created, which can only be done once. */ -int kvm_alloc_stage2_pgd(struct kvm *kvm) +int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu) { phys_addr_t pgd_phys; pgd_t *pgd; + int cpu; - if (kvm->arch.pgd != NULL) { + if (mmu->pgd != NULL) { kvm_err("kvm_arch already initialized?\n"); return -EINVAL; } @@ -992,8 +1009,20 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) if (WARN_ON(pgd_phys & ~kvm_vttbr_baddr_mask(kvm))) return -EINVAL; - kvm->arch.pgd = pgd; - kvm->arch.pgd_phys = pgd_phys; + mmu->last_vcpu_ran = alloc_percpu(typeof(*mmu->last_vcpu_ran)); + if (!mmu->last_vcpu_ran) { + free_pages_exact(pgd, stage2_pgd_size(kvm)); + return -ENOMEM; + } + + for_each_possible_cpu(cpu) + *per_cpu_ptr(mmu->last_vcpu_ran, cpu) = -1; + + mmu->kvm = kvm; + mmu->pgd = pgd; + mmu->pgd_phys = pgd_phys; + mmu->vmid.vmid_gen = 0; + return 0; } @@ -1032,7 +1061,7 @@ static void stage2_unmap_memslot(struct kvm *kvm, if (!(vma->vm_flags & VM_PFNMAP)) { gpa_t gpa = addr + (vm_start - memslot->userspace_addr); - unmap_stage2_range(kvm, gpa, vm_end - vm_start); + unmap_stage2_range(&kvm->arch.mmu, gpa, vm_end - vm_start); } hva = vm_end; } while (hva < reg_end); @@ -1064,39 +1093,34 @@ void stage2_unmap_vm(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } -/** - * kvm_free_stage2_pgd - free all stage-2 tables - * @kvm: The KVM struct pointer for the VM. - * - * Walks the level-1 page table pointed to by kvm->arch.pgd and frees all - * underlying level-2 and level-3 tables before freeing the actual level-1 table - * and setting the struct pointer to NULL. - */ -void kvm_free_stage2_pgd(struct kvm *kvm) +void kvm_free_stage2_pgd(struct kvm_s2_mmu *mmu) { + struct kvm *kvm = mmu->kvm; void *pgd = NULL; spin_lock(&kvm->mmu_lock); - if (kvm->arch.pgd) { - unmap_stage2_range(kvm, 0, kvm_phys_size(kvm)); - pgd = READ_ONCE(kvm->arch.pgd); - kvm->arch.pgd = NULL; - kvm->arch.pgd_phys = 0; + if (mmu->pgd) { + unmap_stage2_range(mmu, 0, kvm_phys_size(kvm)); + pgd = READ_ONCE(mmu->pgd); + mmu->pgd = NULL; } spin_unlock(&kvm->mmu_lock); /* Free the HW pgd, one page at a time */ - if (pgd) + if (pgd) { free_pages_exact(pgd, stage2_pgd_size(kvm)); + free_percpu(mmu->last_vcpu_ran); + } } -static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static p4d_t *stage2_get_p4d(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; pgd_t *pgd; p4d_t *p4d; - pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + pgd = mmu->pgd + stage2_pgd_index(kvm, addr); if (stage2_pgd_none(kvm, *pgd)) { if (!cache) return NULL; @@ -1108,13 +1132,14 @@ static p4d_t *stage2_get_p4d(struct kvm *kvm, struct kvm_mmu_memory_cache *cache return stage2_p4d_offset(kvm, pgd, addr); } -static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static pud_t *stage2_get_pud(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; p4d_t *p4d; pud_t *pud; - p4d = stage2_get_p4d(kvm, cache, addr); + p4d = stage2_get_p4d(mmu, cache, addr); if (stage2_p4d_none(kvm, *p4d)) { if (!cache) return NULL; @@ -1126,13 +1151,14 @@ static pud_t *stage2_get_pud(struct kvm *kvm, struct kvm_mmu_memory_cache *cache return stage2_pud_offset(kvm, p4d, addr); } -static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static pmd_t *stage2_get_pmd(struct kvm_s2_mmu *mmu, struct kvm_mmu_memory_cache *cache, phys_addr_t addr) { + struct kvm *kvm = mmu->kvm; pud_t *pud; pmd_t *pmd; - pud = stage2_get_pud(kvm, cache, addr); + pud = stage2_get_pud(mmu, cache, addr); if (!pud || stage2_pud_huge(kvm, *pud)) return NULL; @@ -1147,13 +1173,14 @@ static pmd_t *stage2_get_pmd(struct kvm *kvm, struct kvm_mmu_memory_cache *cache return stage2_pmd_offset(kvm, pud, addr); } -static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache - *cache, phys_addr_t addr, const pmd_t *new_pmd) +static int stage2_set_pmd_huge(struct kvm_s2_mmu *mmu, + struct kvm_mmu_memory_cache *cache, + phys_addr_t addr, const pmd_t *new_pmd) { pmd_t *pmd, old_pmd; retry: - pmd = stage2_get_pmd(kvm, cache, addr); + pmd = stage2_get_pmd(mmu, cache, addr); VM_BUG_ON(!pmd); old_pmd = *pmd; @@ -1186,7 +1213,7 @@ retry: * get handled accordingly. */ if (!pmd_thp_or_huge(old_pmd)) { - unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE); + unmap_stage2_range(mmu, addr & S2_PMD_MASK, S2_PMD_SIZE); goto retry; } /* @@ -1202,7 +1229,7 @@ retry: */ WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd)); pmd_clear(pmd); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PMD_LEVEL); } else { get_page(virt_to_page(pmd)); } @@ -1211,13 +1238,15 @@ retry: return 0; } -static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static int stage2_set_pud_huge(struct kvm_s2_mmu *mmu, + struct kvm_mmu_memory_cache *cache, phys_addr_t addr, const pud_t *new_pudp) { + struct kvm *kvm = mmu->kvm; pud_t *pudp, old_pud; retry: - pudp = stage2_get_pud(kvm, cache, addr); + pudp = stage2_get_pud(mmu, cache, addr); VM_BUG_ON(!pudp); old_pud = *pudp; @@ -1236,13 +1265,13 @@ retry: * the range for this block and retry. */ if (!stage2_pud_huge(kvm, old_pud)) { - unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE); + unmap_stage2_range(mmu, addr & S2_PUD_MASK, S2_PUD_SIZE); goto retry; } WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp)); stage2_pud_clear(kvm, pudp); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PUD_LEVEL); } else { get_page(virt_to_page(pudp)); } @@ -1257,9 +1286,10 @@ retry: * leaf-entry is returned in the appropriate level variable - pudpp, * pmdpp, ptepp. */ -static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, +static bool stage2_get_leaf_entry(struct kvm_s2_mmu *mmu, phys_addr_t addr, pud_t **pudpp, pmd_t **pmdpp, pte_t **ptepp) { + struct kvm *kvm = mmu->kvm; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; @@ -1268,7 +1298,7 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, *pmdpp = NULL; *ptepp = NULL; - pudp = stage2_get_pud(kvm, NULL, addr); + pudp = stage2_get_pud(mmu, NULL, addr); if (!pudp || stage2_pud_none(kvm, *pudp) || !stage2_pud_present(kvm, *pudp)) return false; @@ -1294,14 +1324,14 @@ static bool stage2_get_leaf_entry(struct kvm *kvm, phys_addr_t addr, return true; } -static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz) +static bool stage2_is_exec(struct kvm_s2_mmu *mmu, phys_addr_t addr, unsigned long sz) { pud_t *pudp; pmd_t *pmdp; pte_t *ptep; bool found; - found = stage2_get_leaf_entry(kvm, addr, &pudp, &pmdp, &ptep); + found = stage2_get_leaf_entry(mmu, addr, &pudp, &pmdp, &ptep); if (!found) return false; @@ -1313,10 +1343,12 @@ static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz) return sz == PAGE_SIZE && kvm_s2pte_exec(ptep); } -static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, +static int stage2_set_pte(struct kvm_s2_mmu *mmu, + struct kvm_mmu_memory_cache *cache, phys_addr_t addr, const pte_t *new_pte, unsigned long flags) { + struct kvm *kvm = mmu->kvm; pud_t *pud; pmd_t *pmd; pte_t *pte, old_pte; @@ -1326,7 +1358,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, VM_BUG_ON(logging_active && !cache); /* Create stage-2 page table mapping - Levels 0 and 1 */ - pud = stage2_get_pud(kvm, cache, addr); + pud = stage2_get_pud(mmu, cache, addr); if (!pud) { /* * Ignore calls from kvm_set_spte_hva for unallocated @@ -1340,7 +1372,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, * on to allocate page. */ if (logging_active) - stage2_dissolve_pud(kvm, addr, pud); + stage2_dissolve_pud(mmu, addr, pud); if (stage2_pud_none(kvm, *pud)) { if (!cache) @@ -1364,7 +1396,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, * allocate page. */ if (logging_active) - stage2_dissolve_pmd(kvm, addr, pmd); + stage2_dissolve_pmd(mmu, addr, pmd); /* Create stage-2 page mappings - Level 2 */ if (pmd_none(*pmd)) { @@ -1388,7 +1420,7 @@ static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache, return 0; kvm_set_pte(pte, __pte(0)); - kvm_tlb_flush_vmid_ipa(kvm, addr); + kvm_tlb_flush_vmid_ipa(mmu, addr, S2_PTE_LEVEL); } else { get_page(virt_to_page(pte)); } @@ -1453,8 +1485,8 @@ int kvm_phys_addr_ioremap(struct kvm *kvm, phys_addr_t guest_ipa, if (ret) goto out; spin_lock(&kvm->mmu_lock); - ret = stage2_set_pte(kvm, &cache, addr, &pte, - KVM_S2PTE_FLAG_IS_IOMAP); + ret = stage2_set_pte(&kvm->arch.mmu, &cache, addr, &pte, + KVM_S2PTE_FLAG_IS_IOMAP); spin_unlock(&kvm->mmu_lock); if (ret) goto out; @@ -1493,9 +1525,10 @@ static void stage2_wp_ptes(pmd_t *pmd, phys_addr_t addr, phys_addr_t end) * @addr: range start address * @end: range end address */ -static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud, +static void stage2_wp_pmds(struct kvm_s2_mmu *mmu, pud_t *pud, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; pmd_t *pmd; phys_addr_t next; @@ -1516,13 +1549,14 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud, /** * stage2_wp_puds - write protect P4D range - * @pgd: pointer to pgd entry + * @p4d: pointer to p4d entry * @addr: range start address * @end: range end address */ -static void stage2_wp_puds(struct kvm *kvm, p4d_t *p4d, +static void stage2_wp_puds(struct kvm_s2_mmu *mmu, p4d_t *p4d, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; pud_t *pud; phys_addr_t next; @@ -1534,7 +1568,7 @@ static void stage2_wp_puds(struct kvm *kvm, p4d_t *p4d, if (!kvm_s2pud_readonly(pud)) kvm_set_s2pud_readonly(pud); } else { - stage2_wp_pmds(kvm, pud, addr, next); + stage2_wp_pmds(mmu, pud, addr, next); } } } while (pud++, addr = next, addr != end); @@ -1546,9 +1580,10 @@ static void stage2_wp_puds(struct kvm *kvm, p4d_t *p4d, * @addr: range start address * @end: range end address */ -static void stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd, +static void stage2_wp_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; p4d_t *p4d; phys_addr_t next; @@ -1556,7 +1591,7 @@ static void stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd, do { next = stage2_p4d_addr_end(kvm, addr, end); if (!stage2_p4d_none(kvm, *p4d)) - stage2_wp_puds(kvm, p4d, addr, next); + stage2_wp_puds(mmu, p4d, addr, next); } while (p4d++, addr = next, addr != end); } @@ -1566,12 +1601,13 @@ static void stage2_wp_p4ds(struct kvm *kvm, pgd_t *pgd, * @addr: Start address of range * @end: End address of range */ -static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) +static void stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end) { + struct kvm *kvm = mmu->kvm; pgd_t *pgd; phys_addr_t next; - pgd = kvm->arch.pgd + stage2_pgd_index(kvm, addr); + pgd = mmu->pgd + stage2_pgd_index(kvm, addr); do { /* * Release kvm_mmu_lock periodically if the memory region is @@ -1583,11 +1619,11 @@ static void stage2_wp_range(struct kvm *kvm, phys_addr_t addr, phys_addr_t end) * the lock. */ cond_resched_lock(&kvm->mmu_lock); - if (!READ_ONCE(kvm->arch.pgd)) + if (!READ_ONCE(mmu->pgd)) break; next = stage2_pgd_addr_end(kvm, addr, end); if (stage2_pgd_present(kvm, *pgd)) - stage2_wp_p4ds(kvm, pgd, addr, next); + stage2_wp_p4ds(mmu, pgd, addr, next); } while (pgd++, addr = next, addr != end); } @@ -1617,7 +1653,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot) end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); - stage2_wp_range(kvm, start, end); + stage2_wp_range(&kvm->arch.mmu, start, end); spin_unlock(&kvm->mmu_lock); kvm_flush_remote_tlbs(kvm); } @@ -1641,7 +1677,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; - stage2_wp_range(kvm, start, end); + stage2_wp_range(&kvm->arch.mmu, start, end); } /* @@ -1804,6 +1840,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, pgprot_t mem_type = PAGE_S2; bool logging_active = memslot_is_logging(memslot); unsigned long vma_pagesize, flags = 0; + struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu; write_fault = kvm_is_write_fault(vcpu); exec_fault = kvm_vcpu_trap_is_iabt(vcpu); @@ -1925,7 +1962,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, */ needs_exec = exec_fault || (fault_status == FSC_PERM && - stage2_is_exec(kvm, fault_ipa, vma_pagesize)); + stage2_is_exec(mmu, fault_ipa, vma_pagesize)); if (vma_pagesize == PUD_SIZE) { pud_t new_pud = kvm_pfn_pud(pfn, mem_type); @@ -1937,7 +1974,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (needs_exec) new_pud = kvm_s2pud_mkexec(new_pud); - ret = stage2_set_pud_huge(kvm, memcache, fault_ipa, &new_pud); + ret = stage2_set_pud_huge(mmu, memcache, fault_ipa, &new_pud); } else if (vma_pagesize == PMD_SIZE) { pmd_t new_pmd = kvm_pfn_pmd(pfn, mem_type); @@ -1949,7 +1986,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (needs_exec) new_pmd = kvm_s2pmd_mkexec(new_pmd); - ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd); + ret = stage2_set_pmd_huge(mmu, memcache, fault_ipa, &new_pmd); } else { pte_t new_pte = kvm_pfn_pte(pfn, mem_type); @@ -1961,7 +1998,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (needs_exec) new_pte = kvm_s2pte_mkexec(new_pte); - ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags); + ret = stage2_set_pte(mmu, memcache, fault_ipa, &new_pte, flags); } out_unlock: @@ -1990,7 +2027,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) spin_lock(&vcpu->kvm->mmu_lock); - if (!stage2_get_leaf_entry(vcpu->kvm, fault_ipa, &pud, &pmd, &pte)) + if (!stage2_get_leaf_entry(vcpu->arch.hw_mmu, fault_ipa, &pud, &pmd, &pte)) goto out; if (pud) { /* HugeTLB */ @@ -2040,21 +2077,18 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) is_iabt = kvm_vcpu_trap_is_iabt(vcpu); /* Synchronous External Abort? */ - if (kvm_vcpu_dabt_isextabt(vcpu)) { + if (kvm_vcpu_abt_issea(vcpu)) { /* * For RAS the host kernel may handle this abort. * There is no need to pass the error into the guest. */ - if (!kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_hsr(vcpu))) - return 1; - - if (unlikely(!is_iabt)) { + if (kvm_handle_guest_sea(fault_ipa, kvm_vcpu_get_esr(vcpu))) kvm_inject_vabt(vcpu); - return 1; - } + + return 1; } - trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_hsr(vcpu), + trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu), kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ @@ -2063,7 +2097,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), - (unsigned long)kvm_vcpu_get_hsr(vcpu)); + (unsigned long)kvm_vcpu_get_esr(vcpu)); return -EFAULT; } @@ -2074,12 +2108,23 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); write_fault = kvm_is_write_fault(vcpu); if (kvm_is_error_hva(hva) || (write_fault && !writable)) { + /* + * The guest has put either its instructions or its page-tables + * somewhere it shouldn't have. Userspace won't be able to do + * anything about this (there's no syndrome for a start), so + * re-inject the abort back into the guest. + */ if (is_iabt) { - /* Prefetch Abort on I/O address */ ret = -ENOEXEC; goto out; } + if (kvm_vcpu_dabt_iss1tw(vcpu)) { + kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu)); + ret = 1; + goto out_unlock; + } + /* * Check for a cache maintenance operation. Since we * ended-up here, we know it is outside of any memory @@ -2090,7 +2135,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) * So let's assume that the guest is just being * cautious, and skip the instruction. */ - if (kvm_vcpu_dabt_is_cm(vcpu)) { + if (kvm_is_error_hva(hva) && kvm_vcpu_dabt_is_cm(vcpu)) { kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); ret = 1; goto out_unlock; @@ -2163,14 +2208,14 @@ static int handle_hva_to_gpa(struct kvm *kvm, static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(kvm, gpa, size); + unmap_stage2_range(&kvm->arch.mmu, gpa, size); return 0; } int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { - if (!kvm->arch.pgd) + if (!kvm->arch.mmu.pgd) return 0; trace_kvm_unmap_hva_range(start, end); @@ -2190,7 +2235,7 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data * therefore stage2_set_pte() never needs to clear out a huge PMD * through this calling path. */ - stage2_set_pte(kvm, NULL, gpa, pte, 0); + stage2_set_pte(&kvm->arch.mmu, NULL, gpa, pte, 0); return 0; } @@ -2201,7 +2246,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) kvm_pfn_t pfn = pte_pfn(pte); pte_t stage2_pte; - if (!kvm->arch.pgd) + if (!kvm->arch.mmu.pgd) return 0; trace_kvm_set_spte_hva(hva); @@ -2224,7 +2269,7 @@ static int kvm_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) pte_t *pte; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); - if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte)) + if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte)) return 0; if (pud) @@ -2242,7 +2287,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void * pte_t *pte; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); - if (!stage2_get_leaf_entry(kvm, gpa, &pud, &pmd, &pte)) + if (!stage2_get_leaf_entry(&kvm->arch.mmu, gpa, &pud, &pmd, &pte)) return 0; if (pud) @@ -2255,7 +2300,7 @@ static int kvm_test_age_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void * int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) { - if (!kvm->arch.pgd) + if (!kvm->arch.mmu.pgd) return 0; trace_kvm_age_hva(start, end); return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL); @@ -2263,7 +2308,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) { - if (!kvm->arch.pgd) + if (!kvm->arch.mmu.pgd) return 0; trace_kvm_test_age_hva(hva); return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE, @@ -2476,7 +2521,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, spin_lock(&kvm->mmu_lock); if (ret) - unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size); + unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size); else stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -2495,7 +2540,7 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) void kvm_arch_flush_shadow_all(struct kvm *kvm) { - kvm_free_stage2_pgd(kvm); + kvm_free_stage2_pgd(&kvm->arch.mmu); } void kvm_arch_flush_shadow_memslot(struct kvm *kvm, @@ -2505,7 +2550,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, phys_addr_t size = slot->npages << PAGE_SHIFT; spin_lock(&kvm->mmu_lock); - unmap_stage2_range(kvm, gpa, size); + unmap_stage2_range(&kvm->arch.mmu, gpa, size); spin_unlock(&kvm->mmu_lock); } diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c index a900181e3867..accc1d5fba61 100644 --- a/arch/arm64/kvm/regmap.c +++ b/arch/arm64/kvm/regmap.c @@ -100,7 +100,7 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = { */ unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num) { - unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs; + unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.regs; unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK; switch (mode) { @@ -147,8 +147,20 @@ unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu) { int spsr_idx = vcpu_spsr32_mode(vcpu); - if (!vcpu->arch.sysregs_loaded_on_cpu) - return vcpu_gp_regs(vcpu)->spsr[spsr_idx]; + if (!vcpu->arch.sysregs_loaded_on_cpu) { + switch (spsr_idx) { + case KVM_SPSR_SVC: + return __vcpu_sys_reg(vcpu, SPSR_EL1); + case KVM_SPSR_ABT: + return vcpu->arch.ctxt.spsr_abt; + case KVM_SPSR_UND: + return vcpu->arch.ctxt.spsr_und; + case KVM_SPSR_IRQ: + return vcpu->arch.ctxt.spsr_irq; + case KVM_SPSR_FIQ: + return vcpu->arch.ctxt.spsr_fiq; + } + } switch (spsr_idx) { case KVM_SPSR_SVC: @@ -171,7 +183,24 @@ void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v) int spsr_idx = vcpu_spsr32_mode(vcpu); if (!vcpu->arch.sysregs_loaded_on_cpu) { - vcpu_gp_regs(vcpu)->spsr[spsr_idx] = v; + switch (spsr_idx) { + case KVM_SPSR_SVC: + __vcpu_sys_reg(vcpu, SPSR_EL1) = v; + break; + case KVM_SPSR_ABT: + vcpu->arch.ctxt.spsr_abt = v; + break; + case KVM_SPSR_UND: + vcpu->arch.ctxt.spsr_und = v; + break; + case KVM_SPSR_IRQ: + vcpu->arch.ctxt.spsr_irq = v; + break; + case KVM_SPSR_FIQ: + vcpu->arch.ctxt.spsr_fiq = v; + break; + } + return; } diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 6ed36be51b4b..ee33875c5c2a 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -42,6 +42,11 @@ static u32 kvm_ipa_limit; #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) +static bool system_has_full_ptr_auth(void) +{ + return system_supports_address_auth() && system_supports_generic_auth(); +} + /** * kvm_arch_vm_ioctl_check_extension * @@ -80,8 +85,7 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: - r = has_vhe() && system_supports_address_auth() && - system_supports_generic_auth(); + r = system_has_full_ptr_auth(); break; default: r = 0; @@ -205,19 +209,14 @@ static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) static int kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) { - /* Support ptrauth only if the system supports these capabilities. */ - if (!has_vhe()) - return -EINVAL; - - if (!system_supports_address_auth() || - !system_supports_generic_auth()) - return -EINVAL; /* * For now make sure that both address/generic pointer authentication - * features are requested by the userspace together. + * features are requested by the userspace together and the system + * supports these capabilities. */ if (!test_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, vcpu->arch.features) || - !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features)) + !test_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, vcpu->arch.features) || + !system_has_full_ptr_auth()) return -EINVAL; vcpu->arch.flags |= KVM_ARM64_GUEST_HAS_PTRAUTH; @@ -292,7 +291,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset core registers */ memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); - vcpu_gp_regs(vcpu)->regs.pstate = pstate; + vcpu_gp_regs(vcpu)->pstate = pstate; /* Reset system registers */ kvm_reset_sys_regs(vcpu); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 138961d7ebe3..077293b5115f 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -94,6 +94,7 @@ static bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; + case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break; case PAR_EL1: *val = read_sysreg_s(SYS_PAR_EL1); break; case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; @@ -133,6 +134,7 @@ static bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; + case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; @@ -242,6 +244,25 @@ static bool access_vm_reg(struct kvm_vcpu *vcpu, return true; } +static bool access_actlr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) + return ignore_write(vcpu, p); + + p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1); + + if (p->is_aarch32) { + if (r->Op2 & 2) + p->regval = upper_32_bits(p->regval); + else + p->regval = lower_32_bits(p->regval); + } + + return true; +} + /* * Trap handler for the GICv3 SGI generation system register. * Forward the request to the VGIC emulation. @@ -615,6 +636,12 @@ static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) vcpu_write_sys_reg(vcpu, amair, AMAIR_EL1); } +static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) +{ + u64 actlr = read_sysreg(actlr_el1); + vcpu_write_sys_reg(vcpu, actlr, ACTLR_EL1); +} + static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 mpidr; @@ -1518,6 +1545,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_UNALLOCATED(7,7), { SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 }, + { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 }, { SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility }, { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 }, @@ -1957,6 +1985,8 @@ static const struct sys_reg_desc cp14_64_regs[] = { static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn( 0), CRm( 0), Op2( 1), access_ctr }, { Op1( 0), CRn( 1), CRm( 0), Op2( 0), access_vm_reg, NULL, c1_SCTLR }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 1), access_actlr }, + { Op1( 0), CRn( 1), CRm( 0), Op2( 3), access_actlr }, { Op1( 0), CRn( 2), CRm( 0), Op2( 0), access_vm_reg, NULL, c2_TTBR0 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 1), access_vm_reg, NULL, c2_TTBR1 }, { Op1( 0), CRn( 2), CRm( 0), Op2( 2), access_vm_reg, NULL, c2_TTBCR }, @@ -2109,36 +2139,6 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n, return 0; } -/* Target specific emulation tables */ -static struct kvm_sys_reg_target_table *target_tables[KVM_ARM_NUM_TARGETS]; - -void kvm_register_target_sys_reg_table(unsigned int target, - struct kvm_sys_reg_target_table *table) -{ - if (check_sysreg_table(table->table64.table, table->table64.num, false) || - check_sysreg_table(table->table32.table, table->table32.num, true)) - return; - - target_tables[target] = table; -} - -/* Get specific register table for this target. */ -static const struct sys_reg_desc *get_target_table(unsigned target, - bool mode_is_64, - size_t *num) -{ - struct kvm_sys_reg_target_table *table; - - table = target_tables[target]; - if (mode_is_64) { - *num = table->table64.num; - return table->table64.table; - } else { - *num = table->table32.num; - return table->table32.table; - } -} - static int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; @@ -2220,10 +2220,10 @@ static int emulate_cp(struct kvm_vcpu *vcpu, static void unhandled_cp_access(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { - u8 hsr_ec = kvm_vcpu_trap_get_class(vcpu); + u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); int cp = -1; - switch(hsr_ec) { + switch (esr_ec) { case ESR_ELx_EC_CP15_32: case ESR_ELx_EC_CP15_64: cp = 15; @@ -2249,22 +2249,20 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu, */ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, const struct sys_reg_desc *global, - size_t nr_global, - const struct sys_reg_desc *target_specific, - size_t nr_specific) + size_t nr_global) { struct sys_reg_params params; - u32 hsr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); - int Rt2 = (hsr >> 10) & 0x1f; + int Rt2 = (esr >> 10) & 0x1f; params.is_aarch32 = true; params.is_32bit = false; - params.CRm = (hsr >> 1) & 0xf; - params.is_write = ((hsr & 1) == 0); + params.CRm = (esr >> 1) & 0xf; + params.is_write = ((esr & 1) == 0); params.Op0 = 0; - params.Op1 = (hsr >> 16) & 0xf; + params.Op1 = (esr >> 16) & 0xf; params.Op2 = 0; params.CRn = 0; @@ -2278,14 +2276,11 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, } /* - * Try to emulate the coprocessor access using the target - * specific table first, and using the global table afterwards. - * If either of the tables contains a handler, handle the + * If the table contains a handler, handle the * potential register operation in the case of a read and return * with success. */ - if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific) || - !emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { /* Split up the value between registers for the read side */ if (!params.is_write) { vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval)); @@ -2306,26 +2301,23 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu, */ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, const struct sys_reg_desc *global, - size_t nr_global, - const struct sys_reg_desc *target_specific, - size_t nr_specific) + size_t nr_global) { struct sys_reg_params params; - u32 hsr = kvm_vcpu_get_hsr(vcpu); + u32 esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); params.is_aarch32 = true; params.is_32bit = true; - params.CRm = (hsr >> 1) & 0xf; + params.CRm = (esr >> 1) & 0xf; params.regval = vcpu_get_reg(vcpu, Rt); - params.is_write = ((hsr & 1) == 0); - params.CRn = (hsr >> 10) & 0xf; + params.is_write = ((esr & 1) == 0); + params.CRn = (esr >> 10) & 0xf; params.Op0 = 0; - params.Op1 = (hsr >> 14) & 0x7; - params.Op2 = (hsr >> 17) & 0x7; + params.Op1 = (esr >> 14) & 0x7; + params.Op2 = (esr >> 17) & 0x7; - if (!emulate_cp(vcpu, ¶ms, target_specific, nr_specific) || - !emulate_cp(vcpu, ¶ms, global, nr_global)) { + if (!emulate_cp(vcpu, ¶ms, global, nr_global)) { if (!params.is_write) vcpu_set_reg(vcpu, Rt, params.regval); return 1; @@ -2337,38 +2329,22 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu, int kvm_handle_cp15_64(struct kvm_vcpu *vcpu) { - const struct sys_reg_desc *target_specific; - size_t num; - - target_specific = get_target_table(vcpu->arch.target, false, &num); - return kvm_handle_cp_64(vcpu, - cp15_64_regs, ARRAY_SIZE(cp15_64_regs), - target_specific, num); + return kvm_handle_cp_64(vcpu, cp15_64_regs, ARRAY_SIZE(cp15_64_regs)); } int kvm_handle_cp15_32(struct kvm_vcpu *vcpu) { - const struct sys_reg_desc *target_specific; - size_t num; - - target_specific = get_target_table(vcpu->arch.target, false, &num); - return kvm_handle_cp_32(vcpu, - cp15_regs, ARRAY_SIZE(cp15_regs), - target_specific, num); + return kvm_handle_cp_32(vcpu, cp15_regs, ARRAY_SIZE(cp15_regs)); } int kvm_handle_cp14_64(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_64(vcpu, - cp14_64_regs, ARRAY_SIZE(cp14_64_regs), - NULL, 0); + return kvm_handle_cp_64(vcpu, cp14_64_regs, ARRAY_SIZE(cp14_64_regs)); } int kvm_handle_cp14_32(struct kvm_vcpu *vcpu) { - return kvm_handle_cp_32(vcpu, - cp14_regs, ARRAY_SIZE(cp14_regs), - NULL, 0); + return kvm_handle_cp_32(vcpu, cp14_regs, ARRAY_SIZE(cp14_regs)); } static bool is_imp_def_sys_reg(struct sys_reg_params *params) @@ -2380,15 +2356,9 @@ static bool is_imp_def_sys_reg(struct sys_reg_params *params) static int emulate_sys_reg(struct kvm_vcpu *vcpu, struct sys_reg_params *params) { - size_t num; - const struct sys_reg_desc *table, *r; + const struct sys_reg_desc *r; - table = get_target_table(vcpu->arch.target, true, &num); - - /* Search target-specific then generic table. */ - r = find_reg(params, table, num); - if (!r) - r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); if (likely(r)) { perform_access(vcpu, params, r); @@ -2403,14 +2373,20 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, return 1; } -static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *table, size_t num) +/** + * kvm_reset_sys_regs - sets system registers to reset value + * @vcpu: The VCPU pointer + * + * This function finds the right table above and sets the registers on the + * virtual CPU struct to their architecturally defined reset values. + */ +void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) { unsigned long i; - for (i = 0; i < num; i++) - if (table[i].reset) - table[i].reset(vcpu, &table[i]); + for (i = 0; i < ARRAY_SIZE(sys_reg_descs); i++) + if (sys_reg_descs[i].reset) + sys_reg_descs[i].reset(vcpu, &sys_reg_descs[i]); } /** @@ -2420,7 +2396,7 @@ static void reset_sys_reg_descs(struct kvm_vcpu *vcpu, int kvm_handle_sys_reg(struct kvm_vcpu *vcpu) { struct sys_reg_params params; - unsigned long esr = kvm_vcpu_get_hsr(vcpu); + unsigned long esr = kvm_vcpu_get_esr(vcpu); int Rt = kvm_vcpu_sys_get_rt(vcpu); int ret; @@ -2491,8 +2467,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id, static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, u64 id) { - size_t num; - const struct sys_reg_desc *table, *r; + const struct sys_reg_desc *r; struct sys_reg_params params; /* We only do sys_reg for now. */ @@ -2502,10 +2477,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu, if (!index_to_params(id, ¶ms)) return NULL; - table = get_target_table(vcpu->arch.target, true, &num); - r = find_reg(¶ms, table, num); - if (!r) - r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); + r = find_reg(¶ms, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); /* Not saved in the sys_reg array and not otherwise accessible? */ if (r && !(r->reg || r->get_user)) @@ -2805,35 +2777,17 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu, /* Assumed ordered tables, see kvm_sys_reg_table_init. */ static int walk_sys_regs(struct kvm_vcpu *vcpu, u64 __user *uind) { - const struct sys_reg_desc *i1, *i2, *end1, *end2; + const struct sys_reg_desc *i2, *end2; unsigned int total = 0; - size_t num; int err; - /* We check for duplicates here, to allow arch-specific overrides. */ - i1 = get_target_table(vcpu->arch.target, true, &num); - end1 = i1 + num; i2 = sys_reg_descs; end2 = sys_reg_descs + ARRAY_SIZE(sys_reg_descs); - BUG_ON(i1 == end1 || i2 == end2); - - /* Walk carefully, as both tables may refer to the same register. */ - while (i1 || i2) { - int cmp = cmp_sys_reg(i1, i2); - /* target-specific overrides generic entry. */ - if (cmp <= 0) - err = walk_one_sys_reg(vcpu, i1, &uind, &total); - else - err = walk_one_sys_reg(vcpu, i2, &uind, &total); - + while (i2 != end2) { + err = walk_one_sys_reg(vcpu, i2++, &uind, &total); if (err) return err; - - if (cmp <= 0 && ++i1 == end1) - i1 = NULL; - if (cmp >= 0 && ++i2 == end2) - i2 = NULL; } return total; } @@ -2900,22 +2854,3 @@ void kvm_sys_reg_table_init(void) /* Clear all higher bits. */ cache_levels &= (1 << (i*3))-1; } - -/** - * kvm_reset_sys_regs - sets system registers to reset value - * @vcpu: The VCPU pointer - * - * This function finds the right table above and sets the registers on the - * virtual CPU struct to their architecturally defined reset values. - */ -void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) -{ - size_t num; - const struct sys_reg_desc *table; - - /* Generic chip reset first (so target could override). */ - reset_sys_reg_descs(vcpu, sys_reg_descs, ARRAY_SIZE(sys_reg_descs)); - - table = get_target_table(vcpu->arch.target, true, &num); - reset_sys_reg_descs(vcpu, table, num); -} diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c deleted file mode 100644 index aa9d356451eb..000000000000 --- a/arch/arm64/kvm/sys_regs_generic_v8.c +++ /dev/null @@ -1,96 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * Based on arch/arm/kvm/coproc_a15.c: - * Copyright (C) 2012 - Virtual Open Systems and Columbia University - * Authors: Rusty Russell <rusty@rustcorp.au> - * Christoffer Dall <c.dall@virtualopensystems.com> - */ -#include <linux/kvm_host.h> -#include <asm/cputype.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_emulate.h> -#include <asm/kvm_coproc.h> -#include <asm/sysreg.h> -#include <linux/init.h> - -#include "sys_regs.h" - -static bool access_actlr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) -{ - if (p->is_write) - return ignore_write(vcpu, p); - - p->regval = vcpu_read_sys_reg(vcpu, ACTLR_EL1); - - if (p->is_aarch32) { - if (r->Op2 & 2) - p->regval = upper_32_bits(p->regval); - else - p->regval = lower_32_bits(p->regval); - } - - return true; -} - -static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) -{ - __vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1); -} - -/* - * Implementation specific sys-reg registers. - * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 - */ -static const struct sys_reg_desc genericv8_sys_regs[] = { - { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 }, -}; - -static const struct sys_reg_desc genericv8_cp15_regs[] = { - /* ACTLR */ - { Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001), - access_actlr }, - { Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b011), - access_actlr }, -}; - -static struct kvm_sys_reg_target_table genericv8_target_table = { - .table64 = { - .table = genericv8_sys_regs, - .num = ARRAY_SIZE(genericv8_sys_regs), - }, - .table32 = { - .table = genericv8_cp15_regs, - .num = ARRAY_SIZE(genericv8_cp15_regs), - }, -}; - -static int __init sys_reg_genericv8_init(void) -{ - unsigned int i; - - for (i = 1; i < ARRAY_SIZE(genericv8_sys_regs); i++) - BUG_ON(cmp_sys_reg(&genericv8_sys_regs[i-1], - &genericv8_sys_regs[i]) >= 0); - - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_AEM_V8, - &genericv8_target_table); - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_FOUNDATION_V8, - &genericv8_target_table); - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A53, - &genericv8_target_table); - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_CORTEX_A57, - &genericv8_target_table); - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_XGENE_POTENZA, - &genericv8_target_table); - kvm_register_target_sys_reg_table(KVM_ARM_TARGET_GENERIC_V8, - &genericv8_target_table); - - return 0; -} -late_initcall(sys_reg_genericv8_init); diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h index 4c71270cc097..4691053c5ee4 100644 --- a/arch/arm64/kvm/trace_arm.h +++ b/arch/arm64/kvm/trace_arm.h @@ -301,8 +301,8 @@ TRACE_EVENT(kvm_timer_save_state, ), TP_fast_assign( - __entry->ctl = ctx->cnt_ctl; - __entry->cval = ctx->cnt_cval; + __entry->ctl = timer_get_ctl(ctx); + __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), @@ -323,8 +323,8 @@ TRACE_EVENT(kvm_timer_restore_state, ), TP_fast_assign( - __entry->ctl = ctx->cnt_ctl; - __entry->cval = ctx->cnt_cval; + __entry->ctl = timer_get_ctl(ctx); + __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index a4f48c1ac28c..e0404bcab019 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -48,7 +48,7 @@ __init void kvm_compute_layout(void) va_mask = GENMASK_ULL(tag_lsb - 1, 0); tag_val = hyp_va_msb; - if (tag_lsb != (vabits_actual - 1)) { + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && tag_lsb != (vabits_actual - 1)) { /* We have some free bits to insert a random tag. */ tag_val |= get_random_long() & GENMASK_ULL(vabits_actual - 2, tag_lsb); } diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c index d8cdfea5cc96..79f8899b234c 100644 --- a/arch/arm64/kvm/vgic/vgic-irqfd.c +++ b/arch/arm64/kvm/vgic/vgic-irqfd.c @@ -100,19 +100,33 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, /** * kvm_arch_set_irq_inatomic: fast-path for irqfd injection - * - * Currently only direct MSI injection is supported. */ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) { - if (e->type == KVM_IRQ_ROUTING_MSI && vgic_has_its(kvm) && level) { + if (!level) + return -EWOULDBLOCK; + + switch (e->type) { + case KVM_IRQ_ROUTING_MSI: { struct kvm_msi msi; + if (!vgic_has_its(kvm)) + break; + kvm_populate_msi(e, &msi); - if (!vgic_its_inject_cached_translation(kvm, &msi)) - return 0; + return vgic_its_inject_cached_translation(kvm, &msi); + } + + case KVM_IRQ_ROUTING_IRQCHIP: + /* + * Injecting SPIs is always possible in atomic context + * as long as the damn vgic is initialized. + */ + if (unlikely(!vgic_initialized(kvm))) + break; + return vgic_irqfd_set_irq(e, kvm, irq_source_id, 1, line_status); } return -EWOULDBLOCK; diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index c012a52b19f5..40cbaca81333 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -757,9 +757,8 @@ int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi) db = (u64)msi->address_hi << 32 | msi->address_lo; irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data); - if (!irq) - return -1; + return -EWOULDBLOCK; raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index d2339a2b9fb9..5c786b915cd3 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -389,7 +389,7 @@ u64 vgic_sanitise_outer_cacheability(u64 field) case GIC_BASER_CACHE_nC: return field; default: - return GIC_BASER_CACHE_nC; + return GIC_BASER_CACHE_SameAsInner; } } diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 8afb238ff335..f07333e86c2f 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -404,7 +404,8 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADACCESS 0x020000 static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, - unsigned int mm_flags, unsigned long vm_flags) + unsigned int mm_flags, unsigned long vm_flags, + struct pt_regs *regs) { struct vm_area_struct *vma = find_vma(mm, addr); @@ -428,7 +429,7 @@ static vm_fault_t __do_page_fault(struct mm_struct *mm, unsigned long addr, */ if (!(vma->vm_flags & vm_flags)) return VM_FAULT_BADACCESS; - return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags); + return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags, regs); } static bool is_el0_instruction_abort(unsigned int esr) @@ -450,7 +451,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, { const struct fault_info *inf; struct mm_struct *mm = current->mm; - vm_fault_t fault, major = 0; + vm_fault_t fault; unsigned long vm_flags = VM_ACCESS_FLAGS; unsigned int mm_flags = FAULT_FLAG_DEFAULT; @@ -516,8 +517,7 @@ retry: #endif } - fault = __do_page_fault(mm, addr, mm_flags, vm_flags); - major |= fault & VM_FAULT_MAJOR; + fault = __do_page_fault(mm, addr, mm_flags, vm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -538,25 +538,8 @@ retry: * Handle the "normal" (no error) case first. */ if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP | - VM_FAULT_BADACCESS)))) { - /* - * Major/minor page fault accounting is only done - * once. If we go through a retry, it is extremely - * likely that the page will be found in page cache at - * that point. - */ - if (major) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, - addr); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, - addr); - } - + VM_FAULT_BADACCESS)))) return 0; - } /* * If we are in kernel mode at this point, we have no context to diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index aa421bf4956e..55ecf6de9ff7 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -17,7 +17,6 @@ #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> /* * HugeTLB Support Matrix diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index f8c19c6c8e71..481d22c32a2e 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -430,11 +430,9 @@ void __init bootmem_init(void) #endif /* - * Sparsemem tries to allocate bootmem in memory_present(), so must be - * done after the fixed reservations. + * sparse_init() tries to allocate memory from memblock, so must be + * done after the fixed reservations */ - memblocks_present(); - sparse_init(); zone_sizes_init(min, max); diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index 9be71bee902c..b5e83c46b23e 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -16,7 +16,6 @@ #include <asm/fixmap.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> static void __iomem *__ioremap_caller(phys_addr_t phys_addr, size_t size, pgprot_t prot, void *caller) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1df25f26571d..75df62fea1b6 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -35,6 +35,7 @@ #include <asm/mmu_context.h> #include <asm/ptdump.h> #include <asm/tlbflush.h> +#include <asm/pgalloc.h> #define NO_BLOCK_MAPPINGS BIT(0) #define NO_CONT_MAPPINGS BIT(1) @@ -760,15 +761,20 @@ int kern_addr_valid(unsigned long addr) } #ifdef CONFIG_MEMORY_HOTPLUG -static void free_hotplug_page_range(struct page *page, size_t size) +static void free_hotplug_page_range(struct page *page, size_t size, + struct vmem_altmap *altmap) { - WARN_ON(PageReserved(page)); - free_pages((unsigned long)page_address(page), get_order(size)); + if (altmap) { + vmem_altmap_free(altmap, size >> PAGE_SHIFT); + } else { + WARN_ON(PageReserved(page)); + free_pages((unsigned long)page_address(page), get_order(size)); + } } static void free_hotplug_pgtable_page(struct page *page) { - free_hotplug_page_range(page, PAGE_SIZE); + free_hotplug_page_range(page, PAGE_SIZE, NULL); } static bool pgtable_range_aligned(unsigned long start, unsigned long end, @@ -791,7 +797,8 @@ static bool pgtable_range_aligned(unsigned long start, unsigned long end, } static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr, - unsigned long end, bool free_mapped) + unsigned long end, bool free_mapped, + struct vmem_altmap *altmap) { pte_t *ptep, pte; @@ -805,12 +812,14 @@ static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr, pte_clear(&init_mm, addr, ptep); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) - free_hotplug_page_range(pte_page(pte), PAGE_SIZE); + free_hotplug_page_range(pte_page(pte), + PAGE_SIZE, altmap); } while (addr += PAGE_SIZE, addr < end); } static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, - unsigned long end, bool free_mapped) + unsigned long end, bool free_mapped, + struct vmem_altmap *altmap) { unsigned long next; pmd_t *pmdp, pmd; @@ -833,16 +842,17 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr, flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) free_hotplug_page_range(pmd_page(pmd), - PMD_SIZE); + PMD_SIZE, altmap); continue; } WARN_ON(!pmd_table(pmd)); - unmap_hotplug_pte_range(pmdp, addr, next, free_mapped); + unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, - unsigned long end, bool free_mapped) + unsigned long end, bool free_mapped, + struct vmem_altmap *altmap) { unsigned long next; pud_t *pudp, pud; @@ -865,16 +875,17 @@ static void unmap_hotplug_pud_range(p4d_t *p4dp, unsigned long addr, flush_tlb_kernel_range(addr, addr + PAGE_SIZE); if (free_mapped) free_hotplug_page_range(pud_page(pud), - PUD_SIZE); + PUD_SIZE, altmap); continue; } WARN_ON(!pud_table(pud)); - unmap_hotplug_pmd_range(pudp, addr, next, free_mapped); + unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr, - unsigned long end, bool free_mapped) + unsigned long end, bool free_mapped, + struct vmem_altmap *altmap) { unsigned long next; p4d_t *p4dp, p4d; @@ -887,16 +898,24 @@ static void unmap_hotplug_p4d_range(pgd_t *pgdp, unsigned long addr, continue; WARN_ON(!p4d_present(p4d)); - unmap_hotplug_pud_range(p4dp, addr, next, free_mapped); + unmap_hotplug_pud_range(p4dp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } static void unmap_hotplug_range(unsigned long addr, unsigned long end, - bool free_mapped) + bool free_mapped, struct vmem_altmap *altmap) { unsigned long next; pgd_t *pgdp, pgd; + /* + * altmap can only be used as vmemmap mapping backing memory. + * In case the backing memory itself is not being freed, then + * altmap is irrelevant. Warn about this inconsistency when + * encountered. + */ + WARN_ON(!free_mapped && altmap); + do { next = pgd_addr_end(addr, end); pgdp = pgd_offset_k(addr); @@ -905,7 +924,7 @@ static void unmap_hotplug_range(unsigned long addr, unsigned long end, continue; WARN_ON(!pgd_present(pgd)); - unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped); + unmap_hotplug_p4d_range(pgdp, addr, next, free_mapped, altmap); } while (addr = next, addr < end); } @@ -1069,7 +1088,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end, int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - return vmemmap_populate_basepages(start, end, node); + return vmemmap_populate_basepages(start, end, node, altmap); } #else /* !ARM64_SWAPPER_USES_SECTION_MAPS */ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, @@ -1101,7 +1120,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, if (pmd_none(READ_ONCE(*pmdp))) { void *p = NULL; - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (!p) return -ENOMEM; @@ -1119,7 +1138,7 @@ void vmemmap_free(unsigned long start, unsigned long end, #ifdef CONFIG_MEMORY_HOTPLUG WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); - unmap_hotplug_range(start, end, true); + unmap_hotplug_range(start, end, true, altmap); free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END); #endif } @@ -1410,7 +1429,7 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) WARN_ON(pgdir != init_mm.pgd); WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END)); - unmap_hotplug_range(start, end, false); + unmap_hotplug_range(start, end, false, NULL); free_empty_tables(start, end, PAGE_OFFSET, PAGE_END); } diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index aafcee3e3f7e..73f8b49d485c 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -461,13 +461,3 @@ void __init arm64_numa_init(void) numa_init(dummy_numa_init); } - -/* - * We hope that we will be hotplugging memory on nodes we already know about, - * such that acpi_get_node() succeeds and we never fall back to this... - */ -int memory_add_physaddr_to_nid(u64 addr) -{ - pr_warn("Unknown node for memory at 0x%llx, assuming node 0\n", addr); - return 0; -} diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h index c7c1ed27e348..d58d8146b729 100644 --- a/arch/csky/include/asm/pgalloc.h +++ b/arch/csky/include/asm/pgalloc.h @@ -9,7 +9,7 @@ #include <linux/sched.h> #define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) @@ -42,11 +42,6 @@ static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) return pte; } -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_pages((unsigned long)pgd, PGD_ORDER); -} - static inline pgd_t *pgd_alloc(struct mm_struct *mm) { pgd_t *ret; diff --git a/arch/csky/include/asm/segment.h b/arch/csky/include/asm/segment.h index db2640d5f575..79ede9b1a646 100644 --- a/arch/csky/include/asm/segment.h +++ b/arch/csky/include/asm/segment.h @@ -13,6 +13,6 @@ typedef struct { #define USER_DS ((mm_segment_t) { 0x80000000UL }) #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #endif /* __ASM_CSKY_SEGMENT_H */ diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index e7425e6b0419..041d0de6a1b6 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -23,7 +23,6 @@ #include <asm/traps.h> #include <asm/sections.h> #include <asm/mmu_context.h> -#include <asm/pgalloc.h> #ifdef CONFIG_CPU_HAS_FPU #include <abi/fpu.h> #endif diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index b1dce9f2f04d..081b178b41b1 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -150,7 +150,8 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0); + fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0, + regs); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -160,16 +161,6 @@ good_area: goto bad_area; BUG(); } - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, - address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, - address); - } - mmap_read_unlock(mm); return; diff --git a/arch/h8300/include/asm/segment.h b/arch/h8300/include/asm/segment.h index a407978f9f9f..37950725d9b9 100644 --- a/arch/h8300/include/asm/segment.h +++ b/arch/h8300/include/asm/segment.h @@ -33,7 +33,7 @@ static inline mm_segment_t get_fs(void) return USER_DS; } -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #endif /* __ASSEMBLY__ */ diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index cc9be514a676..f0c47e6a7427 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -11,7 +11,7 @@ #include <asm/mem-layout.h> #include <asm/atomic.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> extern unsigned long long kmap_generation; @@ -41,11 +41,6 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; } -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long) pgd); -} - static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) { diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index d294e71d11d8..dfd322c5ce83 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -154,15 +154,6 @@ unsigned long get_wchan(struct task_struct *p) } /* - * Required placeholder. - */ -int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) -{ - return 0; -} - - -/* * Called on the exit path of event entry; see vm_entry.S * * Interrupts will already be disabled. diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index cd3808f96b93..ef32c5a84ff3 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -18,6 +18,7 @@ #include <linux/signal.h> #include <linux/extable.h> #include <linux/hardirq.h> +#include <linux/perf_event.h> /* * Decode of hardware exception sends us to one of several @@ -53,6 +54,8 @@ void do_page_fault(unsigned long address, long cause, struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -88,7 +91,7 @@ good_area: break; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -96,10 +99,6 @@ good_area: /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/ia64/include/asm/device.h b/arch/ia64/include/asm/device.h index 3eb397415381..918b198cd5bb 100644 --- a/arch/ia64/include/asm/device.h +++ b/arch/ia64/include/asm/device.h @@ -6,9 +6,6 @@ #define _ASM_IA64_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* hook for IOMMU specific extension */ -#endif }; struct pdev_archdata { diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h index c70bb9c11f52..6629301a2620 100644 --- a/arch/ia64/include/asm/elf.h +++ b/arch/ia64/include/asm/elf.h @@ -179,8 +179,6 @@ extern void ia64_init_addr_space (void); #define ELF_AR_SSD_OFFSET (56 * sizeof(elf_greg_t)) #define ELF_AR_END_OFFSET (57 * sizeof(elf_greg_t)) -typedef unsigned long elf_fpxregset_t; - typedef unsigned long elf_greg_t; typedef elf_greg_t elf_gregset_t[ELF_NGREG]; diff --git a/arch/ia64/include/asm/pgalloc.h b/arch/ia64/include/asm/pgalloc.h index 2a3050345099..9601cfe83c94 100644 --- a/arch/ia64/include/asm/pgalloc.h +++ b/arch/ia64/include/asm/pgalloc.h @@ -29,11 +29,6 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) return (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); } -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long)pgd); -} - #if CONFIG_PGTABLE_LEVELS == 4 static inline void p4d_populate(struct mm_struct *mm, p4d_t * p4d_entry, pud_t * pud) @@ -41,15 +36,6 @@ p4d_populate(struct mm_struct *mm, p4d_t * p4d_entry, pud_t * pud) p4d_val(*p4d_entry) = __pa(pud); } -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pud_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); -} - -static inline void pud_free(struct mm_struct *mm, pud_t *pud) -{ - free_page((unsigned long)pud); -} #define __pud_free_tlb(tlb, pud, address) pud_free((tlb)->mm, pud) #endif /* CONFIG_PGTABLE_LEVELS == 4 */ @@ -59,16 +45,6 @@ pud_populate(struct mm_struct *mm, pud_t * pud_entry, pmd_t * pmd) pud_val(*pud_entry) = __pa(pmd); } -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pmd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_page((unsigned long)pmd); -} - #define __pmd_free_tlb(tlb, pmd, address) pmd_free((tlb)->mm, pmd) static inline void diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h index 7847ae40a181..aa92234c0142 100644 --- a/arch/ia64/include/asm/smp.h +++ b/arch/ia64/include/asm/smp.h @@ -18,7 +18,6 @@ #include <linux/bitops.h> #include <linux/irqreturn.h> -#include <asm/io.h> #include <asm/param.h> #include <asm/processor.h> #include <asm/ptrace.h> @@ -44,11 +43,6 @@ ia64_get_lid (void) #ifdef CONFIG_SMP -#define XTP_OFFSET 0x1e0008 - -#define SMP_IRQ_REDIRECTION (1 << 0) -#define SMP_IPI_REDIRECTION (1 << 1) - #define raw_smp_processor_id() (current_thread_info()->cpu) extern struct smp_boot_data { @@ -62,7 +56,6 @@ extern cpumask_t cpu_core_map[NR_CPUS]; DECLARE_PER_CPU_SHARED_ALIGNED(cpumask_t, cpu_sibling_map); extern int smp_num_siblings; extern void __iomem *ipi_base_addr; -extern unsigned char smp_int_redirect; extern volatile int ia64_cpu_to_sapicid[]; #define cpu_physical_id(i) ia64_cpu_to_sapicid[i] @@ -84,34 +77,6 @@ cpu_logical_id (int cpuid) return i; } -/* - * XTP control functions: - * min_xtp : route all interrupts to this CPU - * normal_xtp: nominal XTP value - * max_xtp : never deliver interrupts to this CPU. - */ - -static inline void -min_xtp (void) -{ - if (smp_int_redirect & SMP_IRQ_REDIRECTION) - writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */ -} - -static inline void -normal_xtp (void) -{ - if (smp_int_redirect & SMP_IRQ_REDIRECTION) - writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */ -} - -static inline void -max_xtp (void) -{ - if (smp_int_redirect & SMP_IRQ_REDIRECTION) - writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */ -} - /* Upping and downing of CPUs */ extern int __cpu_disable (void); extern void __cpu_die (unsigned int cpu); diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h index f1f257d632b3..8d9da6f08a62 100644 --- a/arch/ia64/include/asm/tlb.h +++ b/arch/ia64/include/asm/tlb.h @@ -42,7 +42,6 @@ #include <linux/pagemap.h> #include <linux/swap.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/tlbflush.h> diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 8aa473a4b0f4..179243c3dfc7 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -50,7 +50,7 @@ #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) /* * When accessing user memory, we need to make sure the entire area really is in diff --git a/arch/ia64/include/asm/xtp.h b/arch/ia64/include/asm/xtp.h new file mode 100644 index 000000000000..5bf1d70ad860 --- /dev/null +++ b/arch/ia64/include/asm/xtp.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_IA64_XTP_H +#define _ASM_IA64_XTP_H + +#include <asm/io.h> + +#ifdef CONFIG_SMP + +#define XTP_OFFSET 0x1e0008 + +#define SMP_IRQ_REDIRECTION (1 << 0) +#define SMP_IPI_REDIRECTION (1 << 1) + +extern unsigned char smp_int_redirect; + +/* + * XTP control functions: + * min_xtp : route all interrupts to this CPU + * normal_xtp: nominal XTP value + * max_xtp : never deliver interrupts to this CPU. + */ + +static inline void +min_xtp (void) +{ + if (smp_int_redirect & SMP_IRQ_REDIRECTION) + writeb(0x00, ipi_base_addr + XTP_OFFSET); /* XTP to min */ +} + +static inline void +normal_xtp (void) +{ + if (smp_int_redirect & SMP_IRQ_REDIRECTION) + writeb(0x08, ipi_base_addr + XTP_OFFSET); /* XTP normal */ +} + +static inline void +max_xtp (void) +{ + if (smp_int_redirect & SMP_IRQ_REDIRECTION) + writeb(0x0f, ipi_base_addr + XTP_OFFSET); /* Set XTP to max */ +} + +#endif /* CONFIG_SMP */ + +#endif /* _ASM_IA64_XTP_Hy */ diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index fad4db20ce65..35adcf89035a 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -95,6 +95,7 @@ #include <asm/iosapic.h> #include <asm/processor.h> #include <asm/ptrace.h> +#include <asm/xtp.h> #undef DEBUG_INTERRUPT_ROUTING diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c index 0a8e5e585edc..ecef17c7c35b 100644 --- a/arch/ia64/kernel/irq.c +++ b/arch/ia64/kernel/irq.c @@ -25,6 +25,7 @@ #include <linux/kernel_stat.h> #include <asm/mca.h> +#include <asm/xtp.h> /* * 'what should we do if we get a hw irq event on an illegal vector'. diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index 7a4de9d994c5..f19cb97c0098 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -40,7 +40,6 @@ #include <asm/elf.h> #include <asm/irq.h> #include <asm/kexec.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/sal.h> #include <asm/switch_to.h> @@ -48,6 +47,7 @@ #include <linux/uaccess.h> #include <asm/unwind.h> #include <asm/user.h> +#include <asm/xtp.h> #include "entry.h" @@ -532,51 +532,17 @@ do_copy_task_regs (struct task_struct *task, struct unw_frame_info *info, void * } void -do_dump_task_fpu (struct task_struct *task, struct unw_frame_info *info, void *arg) -{ - elf_fpreg_t *dst = arg; - int i; - - memset(dst, 0, sizeof(elf_fpregset_t)); /* don't leak any "random" bits */ - - if (unw_unwind_to_user(info) < 0) - return; - - /* f0 is 0.0, f1 is 1.0 */ - - for (i = 2; i < 32; ++i) - unw_get_fr(info, i, dst + i); - - ia64_flush_fph(task); - if ((task->thread.flags & IA64_THREAD_FPH_VALID) != 0) - memcpy(dst + 32, task->thread.fph, 96*16); -} - -void do_copy_regs (struct unw_frame_info *info, void *arg) { do_copy_task_regs(current, info, arg); } void -do_dump_fpu (struct unw_frame_info *info, void *arg) -{ - do_dump_task_fpu(current, info, arg); -} - -void ia64_elf_core_copy_regs (struct pt_regs *pt, elf_gregset_t dst) { unw_init_running(do_copy_regs, dst); } -int -dump_fpu (struct pt_regs *pt, elf_fpregset_t dst) -{ - unw_init_running(do_dump_fpu, dst); - return 1; /* f0-f31 are always valid so we always return 1 */ -} - /* * Flush thread state. This is called when a thread does an execve(). */ diff --git a/arch/ia64/kernel/sal.c b/arch/ia64/kernel/sal.c index c455ece977ad..e4f0705c0282 100644 --- a/arch/ia64/kernel/sal.c +++ b/arch/ia64/kernel/sal.c @@ -18,6 +18,7 @@ #include <asm/page.h> #include <asm/sal.h> #include <asm/pal.h> +#include <asm/xtp.h> __cacheline_aligned DEFINE_SPINLOCK(sal_lock); unsigned long sal_platform_features; diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index d2d440fe855b..dd595fbd8006 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -65,6 +65,7 @@ #include <asm/tlbflush.h> #include <asm/unistd.h> #include <asm/uv/uv.h> +#include <asm/xtp.h> #if defined(CONFIG_SMP) && (IA64_CPU_SIZE > PAGE_SIZE) # error "struct cpuinfo_ia64 too big!" diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c index bbfd421e6deb..7b7b64eb3129 100644 --- a/arch/ia64/kernel/smp.c +++ b/arch/ia64/kernel/smp.c @@ -39,13 +39,13 @@ #include <asm/io.h> #include <asm/irq.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/sal.h> #include <asm/tlbflush.h> #include <asm/unistd.h> #include <asm/mca.h> +#include <asm/xtp.h> /* * Note: alignment of 4 entries/cacheline was empirically determined diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 016683b743c2..c29c600d7967 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -49,7 +49,6 @@ #include <asm/irq.h> #include <asm/mca.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/sal.h> diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index ced9c83e47c9..f52a41f4c340 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -135,7 +135,7 @@ 123 common writev sys_writev 124 common pread64 sys_pread64 125 common pwrite64 sys_pwrite64 -126 common _sysctl sys_sysctl +126 common _sysctl sys_ni_syscall 127 common mmap sys_mmap 128 common munmap sys_munmap 129 common mlock sys_mlock diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index d7d31c718d2d..e30e360beef8 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -21,7 +21,6 @@ #include <linux/swap.h> #include <asm/meminit.h> -#include <asm/pgalloc.h> #include <asm/sections.h> #include <asm/mca.h> diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index da810ca234da..dbe829fc5298 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -24,7 +24,6 @@ #include <linux/efi.h> #include <linux/nodemask.h> #include <linux/slab.h> -#include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/meminit.h> #include <asm/numa.h> @@ -601,7 +600,6 @@ void __init paging_init(void) max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT; - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); #ifdef CONFIG_VIRTUAL_MEM_MAP @@ -656,7 +654,7 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat) int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - return vmemmap_populate_basepages(start, end, node); + return vmemmap_populate_basepages(start, end, node, NULL); } void vmemmap_free(unsigned long start, unsigned long end, diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 3a4dec334cc5..cd9766d2b6e0 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -14,6 +14,7 @@ #include <linux/kdebug.h> #include <linux/prefetch.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/processor.h> #include <asm/exception.h> @@ -105,6 +106,8 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re flags |= FAULT_FLAG_USER; if (mask & VM_WRITE) flags |= FAULT_FLAG_WRITE; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -143,7 +146,7 @@ retry: * sure we exit gracefully rather than endlessly redo the * fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -166,10 +169,6 @@ retry: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c index 32352a73df0c..b331f94d20ac 100644 --- a/arch/ia64/mm/hugetlbpage.c +++ b/arch/ia64/mm/hugetlbpage.c @@ -18,7 +18,6 @@ #include <linux/sysctl.h> #include <linux/log2.h> #include <asm/mman.h> -#include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/tlbflush.h> diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 5e1015eb6d0d..f34964271101 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -106,7 +106,5 @@ int memory_add_physaddr_to_nid(u64 addr) return 0; return nid; } - -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif #endif diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 71c19918e387..135b5135cace 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -27,7 +27,6 @@ #include <asm/delay.h> #include <asm/mmu_context.h> -#include <asm/pgalloc.h> #include <asm/pal.h> #include <asm/tlbflush.h> #include <asm/dma.h> diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 6663f1741798..6f2f38d05772 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -16,6 +16,7 @@ config M68K select HAVE_DEBUG_BUGVERBOSE select GENERIC_IRQ_SHOW select GENERIC_ATOMIC64 + select NO_DMA if !MMU && !COLDFIRE select HAVE_UID16 select VIRT_TO_BUS select ARCH_HAVE_NMI_SAFE_CMPXCHG if RMW_INSNS @@ -59,9 +60,6 @@ config TIME_LOW_RES config NO_IOPORT_MAP def_bool y -config NO_DMA - def_bool (MMU && SUN3) || (!MMU && !COLDFIRE) - config ZONE_DMA bool default y diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine index a82651d58af4..17e8c3a292d7 100644 --- a/arch/m68k/Kconfig.machine +++ b/arch/m68k/Kconfig.machine @@ -126,6 +126,7 @@ config SUN3 depends on MMU depends on !MMU_MOTOROLA select MMU_SUN3 if MMU + select NO_DMA select M68020 help This option enables support for the Sun 3 series of workstations diff --git a/arch/m68k/coldfire/stmark2.c b/arch/m68k/coldfire/stmark2.c index a8d2b3d172f9..8b5af9c83244 100644 --- a/arch/m68k/coldfire/stmark2.c +++ b/arch/m68k/coldfire/stmark2.c @@ -13,6 +13,7 @@ #include <linux/spi/spi.h> #include <linux/spi/spi-fsl-dspi.h> #include <linux/spi/flash.h> +#include <linux/dma-mapping.h> #include <asm/mcfsim.h> /* @@ -78,6 +79,8 @@ static struct resource dspi_spi0_resource[] = { }, }; +static u64 stmark2_dspi_mask = DMA_BIT_MASK(32); + /* SPI controller, id = bus number */ static struct platform_device dspi_spi0_device = { .name = "fsl-dspi", @@ -86,6 +89,8 @@ static struct platform_device dspi_spi0_device = { .resource = dspi_spi0_resource, .dev = { .platform_data = &dspi_spi0_info, + .dma_mask = &stmark2_dspi_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/m68k/configs/stmark2_defconfig b/arch/m68k/configs/stmark2_defconfig index 2b746f55f419..d92306472fce 100644 --- a/arch/m68k/configs/stmark2_defconfig +++ b/arch/m68k/configs/stmark2_defconfig @@ -1,38 +1,33 @@ CONFIG_LOCALVERSION="stmark2-001" CONFIG_DEFAULT_HOSTNAME="stmark2" CONFIG_SYSVIPC=y -# CONFIG_FHANDLE is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_BLK_DEV_INITRD=y -# CONFIG_RD_BZIP2 is not set -# CONFIG_RD_LZMA is not set -# CONFIG_RD_XZ is not set -# CONFIG_RD_LZO is not set -# CONFIG_RD_LZ4 is not set CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_FHANDLE is not set # CONFIG_AIO is not set # CONFIG_ADVISE_SYSCALLS is not set # CONFIG_MEMBARRIER is not set CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set -# CONFIG_BLK_DEV_BSG is not set -CONFIG_BLK_CMDLINE_PARSER=y -# CONFIG_MMU is not set +CONFIG_COLDFIRE=y CONFIG_M5441x=y CONFIG_CLOCK_FREQ=240000000 CONFIG_STMARK2=y +CONFIG_UBOOT=y CONFIG_RAMBASE=0x40000000 CONFIG_RAMSIZE=0x8000000 CONFIG_VECTORBASE=0x40000000 CONFIG_KERNELBASE=0x40001000 +# CONFIG_BLK_DEV_BSG is not set +CONFIG_BLK_CMDLINE_PARSER=y CONFIG_BINFMT_FLAT=y +CONFIG_BINFMT_ZFLAT=y CONFIG_BINFMT_MISC=y -# CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y -CONFIG_FW_LOADER_USER_HELPER_FALLBACK=y # CONFIG_ALLOW_DEV_COREDUMP is not set CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y @@ -65,24 +60,36 @@ CONFIG_DEBUG_GPIO=y CONFIG_GPIO_SYSFS=y CONFIG_GPIO_GENERIC_PLATFORM=y # CONFIG_HWMON is not set -# CONFIG_RC_CORE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set +CONFIG_MMC=y +CONFIG_MMC_DEBUG=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_SDHCI_ESDHC_MCF=y +CONFIG_DMADEVICES=y +CONFIG_MCF_EDMA=y +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y # CONFIG_FILE_LOCKING is not set # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set +CONFIG_OVERLAY_FS=y CONFIG_FSCACHE=y # CONFIG_PROC_SYSCTL is not set +CONFIG_CRAMFS=y +CONFIG_SQUASHFS=y +CONFIG_ROMFS_FS=y +CONFIG_CRYPTO_ANSI_CPRNG=y +# CONFIG_CRYPTO_HW is not set CONFIG_PRINTK_TIME=y +# CONFIG_DEBUG_BUGVERBOSE is not set # CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_SLUB_DEBUG_ON=y CONFIG_PANIC_ON_OOPS=y # CONFIG_SCHED_DEBUG is not set -# CONFIG_DEBUG_BUGVERBOSE is not set -CONFIG_BOOTPARAM=y -CONFIG_BOOTPARAM_STRING="console=ttyS0,115200 root=/dev/ram0 rw rootfstype=ramfs rdinit=/bin/init devtmpfs.mount=1" -CONFIG_CRYPTO=y -# CONFIG_CRYPTO_ECHAINIV is not set -CONFIG_CRYPTO_ANSI_CPRNG=y -# CONFIG_CRYPTO_HW is not set -CONFIG_CRC16=y diff --git a/arch/m68k/include/asm/adb_iop.h b/arch/m68k/include/asm/adb_iop.h index 195d7fb1268c..6aecd020e2fc 100644 --- a/arch/m68k/include/asm/adb_iop.h +++ b/arch/m68k/include/asm/adb_iop.h @@ -29,6 +29,7 @@ #define ADB_IOP_EXPLICIT 0x80 /* nonzero if explicit command */ #define ADB_IOP_AUTOPOLL 0x40 /* auto/SRQ polling enabled */ +#define ADB_IOP_SET_AUTOPOLL 0x20 /* set autopoll device list */ #define ADB_IOP_SRQ 0x04 /* SRQ detected */ #define ADB_IOP_TIMEOUT 0x02 /* nonzero if timeout */ diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h index 38e1d7acc44d..3a3bdcfcd375 100644 --- a/arch/m68k/include/asm/cmpxchg.h +++ b/arch/m68k/include/asm/cmpxchg.h @@ -129,14 +129,6 @@ static inline unsigned long __cmpxchg(volatile void *p, unsigned long old, #else -/* - * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make - * them available. - */ -#define cmpxchg_local(ptr, o, n) \ - ((__typeof__(*(ptr)))__cmpxchg_local_generic((ptr), (unsigned long)(o),\ - (unsigned long)(n), sizeof(*(ptr)))) - #include <asm-generic/cmpxchg.h> #endif diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h index 0498192e1d98..2c96e8480173 100644 --- a/arch/m68k/include/asm/io_no.h +++ b/arch/m68k/include/asm/io_no.h @@ -14,15 +14,15 @@ * that behavior here first before we include asm-generic/io.h. */ #define __raw_readb(addr) \ - ({ unsigned char __v = (*(volatile unsigned char *) (addr)); __v; }) + ({ u8 __v = (*(__force volatile u8 *) (addr)); __v; }) #define __raw_readw(addr) \ - ({ unsigned short __v = (*(volatile unsigned short *) (addr)); __v; }) + ({ u16 __v = (*(__force volatile u16 *) (addr)); __v; }) #define __raw_readl(addr) \ - ({ unsigned int __v = (*(volatile unsigned int *) (addr)); __v; }) + ({ u32 __v = (*(__force volatile u32 *) (addr)); __v; }) -#define __raw_writeb(b, addr) (void)((*(volatile unsigned char *) (addr)) = (b)) -#define __raw_writew(b, addr) (void)((*(volatile unsigned short *) (addr)) = (b)) -#define __raw_writel(b, addr) (void)((*(volatile unsigned int *) (addr)) = (b)) +#define __raw_writeb(b, addr) (void)((*(__force volatile u8 *) (addr)) = (b)) +#define __raw_writew(b, addr) (void)((*(__force volatile u16 *) (addr)) = (b)) +#define __raw_writel(b, addr) (void)((*(__force volatile u32 *) (addr)) = (b)) #if defined(CONFIG_COLDFIRE) /* @@ -67,7 +67,7 @@ static inline u16 readw(const volatile void __iomem *addr) { if (cf_internalio(addr)) return __raw_readw(addr); - return __le16_to_cpu(__raw_readw(addr)); + return swab16(__raw_readw(addr)); } #define readl readl @@ -75,7 +75,7 @@ static inline u32 readl(const volatile void __iomem *addr) { if (cf_internalio(addr)) return __raw_readl(addr); - return __le32_to_cpu(__raw_readl(addr)); + return swab32(__raw_readl(addr)); } #define writew writew @@ -84,7 +84,7 @@ static inline void writew(u16 value, volatile void __iomem *addr) if (cf_internalio(addr)) __raw_writew(value, addr); else - __raw_writew(__cpu_to_le16(value), addr); + __raw_writew(swab16(value), addr); } #define writel writel @@ -93,7 +93,7 @@ static inline void writel(u32 value, volatile void __iomem *addr) if (cf_internalio(addr)) __raw_writel(value, addr); else - __raw_writel(__cpu_to_le32(value), addr); + __raw_writel(swab32(value), addr); } #else diff --git a/arch/m68k/include/asm/m53xxacr.h b/arch/m68k/include/asm/m53xxacr.h index 9138a624c5c8..692f90e7fecc 100644 --- a/arch/m68k/include/asm/m53xxacr.h +++ b/arch/m68k/include/asm/m53xxacr.h @@ -89,9 +89,9 @@ * coherency though in all cases. And for copyback caches we will need * to push cached data as well. */ -#define CACHE_INIT CACR_CINVA -#define CACHE_INVALIDATE CACR_CINVA -#define CACHE_INVALIDATED CACR_CINVA +#define CACHE_INIT (CACHE_MODE + CACR_CINVA - CACR_EC) +#define CACHE_INVALIDATE (CACHE_MODE + CACR_CINVA) +#define CACHE_INVALIDATED (CACHE_MODE + CACR_CINVA) #define ACR0_MODE ((CONFIG_RAMBASE & 0xff000000) + \ (0x000f0000) + \ diff --git a/arch/m68k/include/asm/mmu_context.h b/arch/m68k/include/asm/mmu_context.h index cac9f289d1f6..993fd7e37069 100644 --- a/arch/m68k/include/asm/mmu_context.h +++ b/arch/m68k/include/asm/mmu_context.h @@ -222,7 +222,7 @@ static inline void activate_mm(struct mm_struct *prev_mm, #include <asm/setup.h> #include <asm/page.h> -#include <asm/pgalloc.h> +#include <asm/cacheflush.h> static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h index c6686559e9b7..2b5e68a71ef7 100644 --- a/arch/m68k/include/asm/segment.h +++ b/arch/m68k/include/asm/segment.h @@ -52,7 +52,7 @@ static inline void set_fs(mm_segment_t val) #define set_fs(x) (current_thread_info()->addr_limit = (x)) #endif -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #endif /* __ASSEMBLY__ */ diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h index 11b95dadf7c0..000f64869b91 100644 --- a/arch/m68k/include/asm/sun3_pgalloc.h +++ b/arch/m68k/include/asm/sun3_pgalloc.h @@ -13,7 +13,7 @@ #include <asm/tlb.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> extern const char bad_pmd_string[]; @@ -40,11 +40,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t page */ #define pmd_free(mm, x) do { } while (0) -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long) pgd); -} - static inline pgd_t * pgd_alloc(struct mm_struct *mm) { pgd_t *new_pgd; diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h index 191e75a6bb24..5337bc2c262f 100644 --- a/arch/m68k/include/asm/tlbflush.h +++ b/arch/m68k/include/asm/tlbflush.h @@ -85,10 +85,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) { if (vma->vm_mm == current->active_mm) { - mm_segment_t old_fs = get_fs(); - set_fs(USER_DS); + mm_segment_t old_fs = force_uaccess_begin(); + __flush_tlb_one(addr); - set_fs(old_fs); + force_uaccess_end(old_fs); } } diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c index 871a0e11da34..b1ca3522eccc 100644 --- a/arch/m68k/kernel/dma.c +++ b/arch/m68k/kernel/dma.c @@ -15,7 +15,7 @@ #include <linux/vmalloc.h> #include <linux/export.h> -#include <asm/pgalloc.h> +#include <asm/cacheflush.h> #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE) void arch_dma_prep_coherent(struct page *page, size_t size) diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 1a4822de7292..81fc799d8392 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index df6fc782754f..546e81935fe8 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -35,10 +35,9 @@ #include <asm/fpu.h> #include <linux/uaccess.h> #include <asm/traps.h> -#include <asm/pgalloc.h> #include <asm/machdep.h> #include <asm/siginfo.h> - +#include <asm/tlbflush.h> static const char *vec_names[] = { [VEC_RESETSP] = "RESET SP", diff --git a/arch/m68k/mm/cache.c b/arch/m68k/mm/cache.c index 5ecb3310e874..b486c0889eec 100644 --- a/arch/m68k/mm/cache.c +++ b/arch/m68k/mm/cache.c @@ -8,7 +8,7 @@ */ #include <linux/module.h> -#include <asm/pgalloc.h> +#include <asm/cacheflush.h> #include <asm/traps.h> diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index a94a814ad6ad..795f483b1050 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -12,10 +12,10 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/setup.h> #include <asm/traps.h> -#include <asm/pgalloc.h> extern void die_if_kernel(char *, struct pt_regs *, long); @@ -85,6 +85,8 @@ int do_page_fault(struct pt_regs *regs, unsigned long address, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); @@ -135,7 +137,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); pr_debug("handle_mm_fault returns %x\n", fault); if (fault_signal_pending(fault, regs)) @@ -151,16 +153,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/m68k/mm/kmap.c b/arch/m68k/mm/kmap.c index 14d31d216cef..1269d513b221 100644 --- a/arch/m68k/mm/kmap.c +++ b/arch/m68k/mm/kmap.c @@ -19,8 +19,8 @@ #include <asm/setup.h> #include <asm/segment.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/io.h> +#include <asm/tlbflush.h> #undef DEBUG diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 7d04210d34f0..2b9cb4a62281 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -20,6 +20,7 @@ #include <asm/mmu_context.h> #include <asm/mcf_pgalloc.h> #include <asm/tlbflush.h> +#include <asm/pgalloc.h> #define KMAPAREA(x) ((x >= VMALLOC_START) && (x < KMAP_END)) @@ -39,7 +40,6 @@ void __init paging_init(void) unsigned long address, size; unsigned long next_pgtable, bootmem_end; unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; - enum zone_type zone; int i; empty_zero_page = (void *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); @@ -214,11 +214,6 @@ void __init cf_mmu_context_init(void) /* * Steal a context from a task that has one at the moment. - * This is only used on 8xx and 4xx and we presently assume that - * they don't do SMP. If they do then thicfpgalloc.hs will have to check - * whether the MM we steal is in use. - * We also assume that this is only used on systems that don't - * use an MMU hash table - this is true for 8xx and 4xx. * This isn't an LRU system, it just frees up each context in * turn (sort-of pseudo-random replacement :). This would be the * place to implement an LRU scheme if anyone was motivated to do it. diff --git a/arch/m68k/mm/memory.c b/arch/m68k/mm/memory.c index 65e0c4071912..fe75aecfb238 100644 --- a/arch/m68k/mm/memory.c +++ b/arch/m68k/mm/memory.c @@ -17,7 +17,6 @@ #include <asm/setup.h> #include <asm/segment.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/traps.h> #include <asm/machdep.h> diff --git a/arch/m68k/sun3x/dvma.c b/arch/m68k/sun3x/dvma.c index fef52d222d46..08bb92113026 100644 --- a/arch/m68k/sun3x/dvma.c +++ b/arch/m68k/sun3x/dvma.c @@ -22,7 +22,7 @@ #include <asm/dvma.h> #include <asm/io.h> #include <asm/page.h> -#include <asm/pgalloc.h> +#include <asm/tlbflush.h> /* IOMMU support */ diff --git a/arch/microblaze/include/asm/pgalloc.h b/arch/microblaze/include/asm/pgalloc.h index ebb6b7939bb8..8839ce00ea05 100644 --- a/arch/microblaze/include/asm/pgalloc.h +++ b/arch/microblaze/include/asm/pgalloc.h @@ -28,12 +28,6 @@ static inline pgd_t *get_pgd(void) return (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO, 0); } -static inline void free_pgd(pgd_t *pgd) -{ - free_page((unsigned long)pgd); -} - -#define pgd_free(mm, pgd) free_pgd(pgd) #define pgd_alloc(mm) get_pgd() #define pmd_pgtable(pmd) pmd_page(pmd) diff --git a/arch/microblaze/include/asm/tlbflush.h b/arch/microblaze/include/asm/tlbflush.h index 6f8f5c77a050..1200e2bf14bb 100644 --- a/arch/microblaze/include/asm/tlbflush.h +++ b/arch/microblaze/include/asm/tlbflush.h @@ -15,7 +15,6 @@ #include <asm/processor.h> /* For TASK_SIZE */ #include <asm/mmu.h> #include <asm/page.h> -#include <asm/pgalloc.h> extern void _tlbie(unsigned long address); extern void _tlbia(void); diff --git a/arch/microblaze/include/asm/uaccess.h b/arch/microblaze/include/asm/uaccess.h index 6723c56ec378..304b04ffea2f 100644 --- a/arch/microblaze/include/asm/uaccess.h +++ b/arch/microblaze/include/asm/uaccess.h @@ -41,7 +41,7 @@ # define get_fs() (current_thread_info()->addr_limit) # define set_fs(val) (current_thread_info()->addr_limit = (val)) -# define segment_eq(a, b) ((a).seg == (b).seg) +# define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #ifndef CONFIG_MMU diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 6cabeab9e2ba..a9e46e525cd0 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -18,7 +18,6 @@ #include <linux/tick.h> #include <linux/bitops.h> #include <linux/ptrace.h> -#include <asm/pgalloc.h> #include <linux/uaccess.h> /* for USER_DS macros */ #include <asm/cacheflush.h> diff --git a/arch/microblaze/kernel/signal.c b/arch/microblaze/kernel/signal.c index bdd6d0c86e16..65bf5fd8d473 100644 --- a/arch/microblaze/kernel/signal.c +++ b/arch/microblaze/kernel/signal.c @@ -35,7 +35,6 @@ #include <asm/entry.h> #include <asm/ucontext.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <linux/syscalls.h> #include <asm/cacheflush.h> #include <asm/syscalls.h> diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index a3f4be8e7238..b4e263916f41 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index a2bfe587b491..b3fed2cecf84 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -28,6 +28,7 @@ #include <linux/mman.h> #include <linux/mm.h> #include <linux/interrupt.h> +#include <linux/perf_event.h> #include <asm/page.h> #include <asm/mmu.h> @@ -121,6 +122,8 @@ void do_page_fault(struct pt_regs *regs, unsigned long address, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + /* When running in the kernel we expect faults to occur only to * addresses in user space. All other faults represent errors in the * kernel and should generate an OOPS. Unfortunately, in the case of an @@ -214,7 +217,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -230,10 +233,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (unlikely(fault & VM_FAULT_MAJOR)) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 521b59ba716c..0880a003573d 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -172,9 +172,6 @@ void __init setup_memory(void) &memblock.memory, 0); } - /* XXX need to clip this if using highmem? */ - sparse_memory_present_with_active_regions(0); - paging_init(); } diff --git a/arch/mips/configs/cu1000-neo_defconfig b/arch/mips/configs/cu1000-neo_defconfig index 6b471cdb16cf..e924c817f73d 100644 --- a/arch/mips/configs/cu1000-neo_defconfig +++ b/arch/mips/configs/cu1000-neo_defconfig @@ -17,7 +17,6 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y CONFIG_CC_OPTIMIZE_FOR_SIZE=y -CONFIG_SYSCTL_SYSCALL=y CONFIG_KALLSYMS_ALL=y CONFIG_EMBEDDED=y # CONFIG_VM_EVENT_COUNTERS is not set diff --git a/arch/mips/include/asm/pgalloc.h b/arch/mips/include/asm/pgalloc.h index fa77cb71f303..8b18424b3120 100644 --- a/arch/mips/include/asm/pgalloc.h +++ b/arch/mips/include/asm/pgalloc.h @@ -13,7 +13,9 @@ #include <linux/mm.h> #include <linux/sched.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#define __HAVE_ARCH_PMD_ALLOC_ONE +#define __HAVE_ARCH_PUD_ALLOC_ONE +#include <asm-generic/pgalloc.h> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) @@ -47,11 +49,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) extern void pgd_init(unsigned long page); extern pgd_t *pgd_alloc(struct mm_struct *mm); -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_pages((unsigned long)pgd, PGD_ORDER); -} - #define __pte_free_tlb(tlb,pte,address) \ do { \ pgtable_pte_page_dtor(pte); \ @@ -70,11 +67,6 @@ static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) return pmd; } -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_pages((unsigned long)pmd, PMD_ORDER); -} - #define __pmd_free_tlb(tlb, x, addr) pmd_free((tlb)->mm, x) #endif @@ -91,11 +83,6 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address) return pud; } -static inline void pud_free(struct mm_struct *mm, pud_t *pud) -{ - free_pages((unsigned long)pud, PUD_ORDER); -} - static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) { set_p4d(p4d, __p4d((unsigned long)pud)); diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h index 62b298c50905..61fc01f177a6 100644 --- a/arch/mips/include/asm/uaccess.h +++ b/arch/mips/include/asm/uaccess.h @@ -72,7 +72,7 @@ extern u64 __ua_limit; #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) /* * eva_kernel_access() - determine whether kernel memory access on an EVA system diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h index c63ddcaea54c..2203e2d0ae2a 100644 --- a/arch/mips/include/asm/vdso/gettimeofday.h +++ b/arch/mips/include/asm/vdso/gettimeofday.h @@ -167,7 +167,8 @@ static __always_inline u64 read_gic_count(const struct vdso_data *data) #endif -static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) { #ifdef CONFIG_CSRC_R4K if (clock_mode == VDSO_CLOCKMODE_R4K) @@ -175,7 +176,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) #endif #ifdef CONFIG_CLKSRC_MIPS_GIC if (clock_mode == VDSO_CLOCKMODE_GIC) - return read_gic_count(get_vdso_data()); + return read_gic_count(vd); #endif /* * Core checks mode already. So this raced against a concurrent diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 588b21245e00..bf5f5acab0a8 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -371,14 +371,6 @@ static void __init bootmem_init(void) #endif } - - /* - * In any case the added to the memblock memory regions - * (highmem/lowmem, available/reserved, etc) are considered - * as present, so inform sparsemem about them. - */ - memblocks_present(); - /* * Reserve initrd memory if needed. */ diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 6b4ee92e3aed..f9df9edb67a4 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -159,7 +159,7 @@ 149 n32 munlockall sys_munlockall 150 n32 vhangup sys_vhangup 151 n32 pivot_root sys_pivot_root -152 n32 _sysctl compat_sys_sysctl +152 n32 _sysctl sys_ni_syscall 153 n32 prctl sys_prctl 154 n32 adjtimex sys_adjtimex_time32 155 n32 setrlimit compat_sys_setrlimit diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index 391acbf425a0..557f9954a2b9 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -159,7 +159,7 @@ 149 n64 munlockall sys_munlockall 150 n64 vhangup sys_vhangup 151 n64 pivot_root sys_pivot_root -152 n64 _sysctl sys_sysctl +152 n64 _sysctl sys_ni_syscall 153 n64 prctl sys_prctl 154 n64 adjtimex sys_adjtimex 155 n64 setrlimit sys_setrlimit diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 5727c5187508..195b43cf27c8 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -164,7 +164,7 @@ 150 o32 unused150 sys_ni_syscall 151 o32 getsid sys_getsid 152 o32 fdatasync sys_fdatasync -153 o32 _sysctl sys_sysctl compat_sys_sysctl +153 o32 _sysctl sys_ni_syscall 154 o32 mlock sys_mlock 155 o32 munlock sys_munlock 156 o32 mlockall sys_mlockall diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c index 0adce604fa44..126a5f3f4e4c 100644 --- a/arch/mips/kernel/unaligned.c +++ b/arch/mips/kernel/unaligned.c @@ -191,17 +191,16 @@ static void emulate_load_store_insn(struct pt_regs *regs, * memory, so we need to "switch" the address limit to * user space, so that address check can work properly. */ - seg = get_fs(); - set_fs(USER_DS); + seg = force_uaccess_begin(); switch (insn.spec3_format.func) { case lhe_op: if (!access_ok(addr, 2)) { - set_fs(seg); + force_uaccess_end(seg); goto sigbus; } LoadHWE(addr, value, res); if (res) { - set_fs(seg); + force_uaccess_end(seg); goto fault; } compute_return_epc(regs); @@ -209,12 +208,12 @@ static void emulate_load_store_insn(struct pt_regs *regs, break; case lwe_op: if (!access_ok(addr, 4)) { - set_fs(seg); + force_uaccess_end(seg); goto sigbus; } LoadWE(addr, value, res); if (res) { - set_fs(seg); + force_uaccess_end(seg); goto fault; } compute_return_epc(regs); @@ -222,12 +221,12 @@ static void emulate_load_store_insn(struct pt_regs *regs, break; case lhue_op: if (!access_ok(addr, 2)) { - set_fs(seg); + force_uaccess_end(seg); goto sigbus; } LoadHWUE(addr, value, res); if (res) { - set_fs(seg); + force_uaccess_end(seg); goto fault; } compute_return_epc(regs); @@ -235,35 +234,35 @@ static void emulate_load_store_insn(struct pt_regs *regs, break; case she_op: if (!access_ok(addr, 2)) { - set_fs(seg); + force_uaccess_end(seg); goto sigbus; } compute_return_epc(regs); value = regs->regs[insn.spec3_format.rt]; StoreHWE(addr, value, res); if (res) { - set_fs(seg); + force_uaccess_end(seg); goto fault; } break; case swe_op: if (!access_ok(addr, 4)) { - set_fs(seg); + force_uaccess_end(seg); goto sigbus; } compute_return_epc(regs); value = regs->regs[insn.spec3_format.rt]; StoreWE(addr, value, res); if (res) { - set_fs(seg); + force_uaccess_end(seg); goto fault; } break; default: - set_fs(seg); + force_uaccess_end(seg); goto sigill; } - set_fs(seg); + force_uaccess_end(seg); } #endif break; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 703782355318..d70c4f8e14e2 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1935,7 +1935,7 @@ enum emulation_result kvm_mips_emulate_load(union mips_instruction inst, case lwu_op: vcpu->mmio_needed = 1; /* unsigned */ - /* fall through */ + fallthrough; #endif case lw_op: run->mmio.len = 4; diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index 3932f767e938..c299e5d6d69c 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -29,7 +29,9 @@ #include <linux/kvm_host.h> #include "interrupt.h" +#ifdef CONFIG_CPU_LOONGSON64 #include "loongson_regs.h" +#endif #include "trace.h" @@ -1142,7 +1144,6 @@ static enum emulation_result kvm_vz_gpsi_cache(union mips_instruction inst, #ifdef CONFIG_CPU_LOONGSON64 static enum emulation_result kvm_vz_gpsi_lwc2(union mips_instruction inst, u32 *opc, u32 cause, - struct kvm_run *run, struct kvm_vcpu *vcpu) { unsigned int rs, rd; @@ -1240,7 +1241,7 @@ static enum emulation_result kvm_trap_vz_handle_gpsi(u32 cause, u32 *opc, #endif #ifdef CONFIG_CPU_LOONGSON64 case lwc2_op: - er = kvm_vz_gpsi_lwc2(inst, opc, cause, run, vcpu); + er = kvm_vz_gpsi_lwc2(inst, opc, cause, vcpu); break; #endif case spec3_op: diff --git a/arch/mips/loongson64/numa.c b/arch/mips/loongson64/numa.c index 901f5be5ee76..ea8bb1bc667e 100644 --- a/arch/mips/loongson64/numa.c +++ b/arch/mips/loongson64/numa.c @@ -220,7 +220,6 @@ static __init void prom_meminit(void) cpumask_clear(&__node_cpumask[node]); } } - memblocks_present(); max_low_pfn = PHYS_PFN(memblock_end_of_DRAM()); for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) { diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index 01b168a90434..7c871b14e74a 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -96,6 +96,8 @@ static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -152,12 +154,11 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) goto out_of_memory; @@ -168,15 +169,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - tsk->maj_flt++; - } else { - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - tsk->min_flt++; - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 1213215ea965..d411e0a90a5b 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -402,8 +402,6 @@ void __init prom_meminit(void) } __node_data[node] = &null_node; } - - memblocks_present(); } void __init prom_free_prom_memory(void) diff --git a/arch/mips/sgi-ip32/ip32-memory.c b/arch/mips/sgi-ip32/ip32-memory.c index be1b2cfc4c3e..62b956cc2d1d 100644 --- a/arch/mips/sgi-ip32/ip32-memory.c +++ b/arch/mips/sgi-ip32/ip32-memory.c @@ -14,7 +14,6 @@ #include <asm/ip32/crime.h> #include <asm/bootinfo.h> #include <asm/page.h> -#include <asm/pgalloc.h> extern void crime_init(void); diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 2e64c7600eea..57fe83235281 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -35,8 +35,7 @@ cflags-vdso := $(ccflags-vdso) \ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \ - $(call cc-option, -fno-asynchronous-unwind-tables) \ - $(call cc-option, -fno-stack-protector) + $(call cc-option, -fno-asynchronous-unwind-tables) aflags-vdso := $(ccflags-vdso) \ -D__ASSEMBLY__ -Wa,-gdwarf-2 diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 3a9219f53ee0..010ba5f1d7dd 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -44,7 +44,7 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a) == (b)) +#define uaccess_kernel() (get_fs() == KERNEL_DS) #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size)) diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c index e85bbbadc0e7..e01ad5d17224 100644 --- a/arch/nds32/kernel/process.c +++ b/arch/nds32/kernel/process.c @@ -121,7 +121,7 @@ void show_regs(struct pt_regs *regs) regs->uregs[3], regs->uregs[2], regs->uregs[1], regs->uregs[0]); pr_info(" IRQs o%s Segment %s\n", interrupts_enabled(regs) ? "n" : "ff", - segment_eq(get_fs(), KERNEL_DS)? "kernel" : "user"); + uaccess_kernel() ? "kernel" : "user"); } EXPORT_SYMBOL(show_regs); diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c index c8b9061a2ee3..1eb7ded6992b 100644 --- a/arch/nds32/mm/alignment.c +++ b/arch/nds32/mm/alignment.c @@ -512,7 +512,7 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs) { unsigned long inst; int ret = -EFAULT; - mm_segment_t seg = get_fs(); + mm_segment_t seg; inst = get_inst(regs->ipc); @@ -520,13 +520,12 @@ int do_unaligned_access(unsigned long addr, struct pt_regs *regs) "Faulting addr: 0x%08lx, pc: 0x%08lx [inst: 0x%08lx ]\n", addr, regs->ipc, inst); - set_fs(USER_DS); - + seg = force_uaccess_begin(); if (inst & NDS32_16BIT_INSTRUCTION) ret = do_16((inst >> 16) & 0xffff, regs); else ret = do_32(inst, regs); - set_fs(seg); + force_uaccess_end(seg); return ret; } diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 8fb73f6401a0..f02524eb6d56 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -121,6 +121,8 @@ void do_page_fault(unsigned long entry, unsigned long addr, if (unlikely(faulthandler_disabled() || !mm)) goto no_context; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + /* * As per x86, we may deadlock here. However, since the kernel only * validly references user space from well defined areas of the code, @@ -206,7 +208,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, addr, flags); + fault = handle_mm_fault(vma, addr, flags, regs); /* * If we need to retry but a fatal signal is pending, handle the @@ -228,22 +230,7 @@ good_area: goto bad_area; } - /* - * Major/minor page fault accounting is only done on the initial - * attempt. If we go through a retry, it is extremely likely that the - * page will be found in page cache at that point. - */ - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/nds32/mm/mm-nds32.c b/arch/nds32/mm/mm-nds32.c index 8503bee882d1..55bec50ccc03 100644 --- a/arch/nds32/mm/mm-nds32.c +++ b/arch/nds32/mm/mm-nds32.c @@ -2,6 +2,8 @@ // Copyright (C) 2005-2017 Andes Technology Corporation #include <linux/init_task.h> + +#define __HAVE_ARCH_PGD_FREE #include <asm/pgalloc.h> #define FIRST_KERNEL_PGD_NR (USER_PTRS_PER_PGD) diff --git a/arch/nios2/include/asm/pgalloc.h b/arch/nios2/include/asm/pgalloc.h index 0b146d773c85..e6600d2a5ae0 100644 --- a/arch/nios2/include/asm/pgalloc.h +++ b/arch/nios2/include/asm/pgalloc.h @@ -12,7 +12,7 @@ #include <linux/mm.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) @@ -34,11 +34,6 @@ extern void pmd_init(unsigned long page, unsigned long pagetable); extern pgd_t *pgd_alloc(struct mm_struct *mm); -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_pages((unsigned long)pgd, PGD_ORDER); -} - #define __pte_free_tlb(tlb, pte, addr) \ do { \ pgtable_pte_page_dtor(pte); \ diff --git a/arch/nios2/include/asm/uaccess.h b/arch/nios2/include/asm/uaccess.h index e83f831a76f9..a741abbed6fb 100644 --- a/arch/nios2/include/asm/uaccess.h +++ b/arch/nios2/include/asm/uaccess.h @@ -30,7 +30,7 @@ #define get_fs() (current_thread_info()->addr_limit) #define set_fs(seg) (current_thread_info()->addr_limit = (seg)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define __access_ok(addr, len) \ (((signed long)(((long)get_fs().seg) & \ diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 0a42ab8e4c32..88a4ec03edab 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -252,14 +252,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->sp = sp; } -#include <linux/elfcore.h> - -/* Fill in the FPU structure for a core dump. */ -int dump_fpu(struct pt_regs *regs, elf_fpregset_t *r) -{ - return 0; /* Nios2 has no FPU and thus no FPU registers */ -} - asmlinkage int nios2_clone(unsigned long clone_flags, unsigned long newsp, int __user *parent_tidptr, int __user *child_tidptr, unsigned long tls) diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 4112ef0e247e..9476feecf512 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/extable.h> #include <linux/uaccess.h> +#include <linux/perf_event.h> #include <asm/mmu_context.h> #include <asm/traps.h> @@ -83,6 +84,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long cause, if (user_mode(regs)) flags |= FAULT_FLAG_USER; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + if (!mmap_read_trylock(mm)) { if (!user_mode(regs) && !search_exception_tables(regs->ea)) goto bad_area_nosemaphore; @@ -131,7 +134,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -146,16 +149,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index db02fb2077d9..7d6b4a77b379 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -14,6 +14,8 @@ #ifndef __ASM_OPENRISC_IO_H #define __ASM_OPENRISC_IO_H +#include <linux/types.h> + /* * PCI: can we really do 0 here if we have no port IO? */ @@ -25,9 +27,12 @@ #define PIO_OFFSET 0 #define PIO_MASK 0 -#include <asm-generic/io.h> - +#define ioremap ioremap void __iomem *ioremap(phys_addr_t offset, unsigned long size); + +#define iounmap iounmap extern void iounmap(void *addr); +#include <asm-generic/io.h> + #endif diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h index da12a4c38c4b..88820299ecc4 100644 --- a/arch/openrisc/include/asm/pgalloc.h +++ b/arch/openrisc/include/asm/pgalloc.h @@ -20,6 +20,9 @@ #include <linux/mm.h> #include <linux/memblock.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#include <asm-generic/pgalloc.h> + extern int mem_init_done; #define pmd_populate_kernel(mm, pmd, pte) \ @@ -61,38 +64,8 @@ extern inline pgd_t *pgd_alloc(struct mm_struct *mm) } #endif -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long)pgd); -} - extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm); -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - pte = alloc_pages(GFP_KERNEL, 0); - if (!pte) - return NULL; - clear_page(page_address(pte)); - if (!pgtable_pte_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_pte_page_dtor(pte); - __free_page(pte); -} - #define __pte_free_tlb(tlb, pte, addr) \ do { \ pgtable_pte_page_dtor(pte); \ diff --git a/arch/openrisc/include/asm/tlbflush.h b/arch/openrisc/include/asm/tlbflush.h index 4a4639c65cbb..185dcd3731ed 100644 --- a/arch/openrisc/include/asm/tlbflush.h +++ b/arch/openrisc/include/asm/tlbflush.h @@ -17,7 +17,6 @@ #include <linux/mm.h> #include <asm/processor.h> -#include <asm/pgalloc.h> #include <asm/current.h> #include <linux/sched.h> diff --git a/arch/openrisc/include/asm/uaccess.h b/arch/openrisc/include/asm/uaccess.h index 17c24f14615f..f0390211236b 100644 --- a/arch/openrisc/include/asm/uaccess.h +++ b/arch/openrisc/include/asm/uaccess.h @@ -43,21 +43,22 @@ #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) -#define segment_eq(a, b) ((a) == (b)) +#define uaccess_kernel() (get_fs() == KERNEL_DS) /* Ensure that the range from addr to addr+size is all within the process' * address space */ -#define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs()-size)) +static inline int __range_ok(unsigned long addr, unsigned long size) +{ + const mm_segment_t fs = get_fs(); -/* Ensure that addr is below task's addr_limit */ -#define __addr_ok(addr) ((unsigned long) addr < get_fs()) + return size <= fs && addr <= (fs - size); +} #define access_ok(addr, size) \ ({ \ - unsigned long __ao_addr = (unsigned long)(addr); \ - unsigned long __ao_size = (unsigned long)(size); \ - __range_ok(__ao_addr, __ao_size); \ + __chk_user_ptr(addr); \ + __range_ok((unsigned long)(addr), (size)); \ }) /* @@ -100,7 +101,7 @@ extern long __put_user_bad(void); #define __put_user_check(x, ptr, size) \ ({ \ long __pu_err = -EFAULT; \ - __typeof__(*(ptr)) *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ if (access_ok(__pu_addr, size)) \ __put_user_size((x), __pu_addr, (size), __pu_err); \ __pu_err; \ @@ -173,7 +174,7 @@ struct __large_struct { #define __get_user_check(x, ptr, size) \ ({ \ long __gu_err = -EFAULT, __gu_val = 0; \ - const __typeof__(*(ptr)) * __gu_addr = (ptr); \ + const __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ if (access_ok(__gu_addr, size)) \ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ @@ -241,17 +242,17 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long size) return __copy_tofrom_user(to, (__force const void *)from, size); } static inline unsigned long -raw_copy_to_user(void *to, const void __user *from, unsigned long size) +raw_copy_to_user(void __user *to, const void *from, unsigned long size) { return __copy_tofrom_user((__force void *)to, from, size); } #define INLINE_COPY_FROM_USER #define INLINE_COPY_TO_USER -extern unsigned long __clear_user(void *addr, unsigned long size); +extern unsigned long __clear_user(void __user *addr, unsigned long size); static inline __must_check unsigned long -clear_user(void *addr, unsigned long size) +clear_user(void __user *addr, unsigned long size) { if (likely(access_ok(addr, size))) size = __clear_user(addr, size); diff --git a/arch/openrisc/kernel/or32_ksyms.c b/arch/openrisc/kernel/or32_ksyms.c index 277ac7a55752..212e5f85004c 100644 --- a/arch/openrisc/kernel/or32_ksyms.c +++ b/arch/openrisc/kernel/or32_ksyms.c @@ -26,7 +26,6 @@ #include <asm/io.h> #include <asm/hardirq.h> #include <asm/delay.h> -#include <asm/pgalloc.h> #define DECLARE_EXPORT(name) extern void name(void); EXPORT_SYMBOL(name) diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index 848f74c2c47a..0ff391f00334 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -214,13 +214,6 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) regs->sp = sp; } -/* Fill in the fpu structure for a core dump. */ -int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu) -{ - /* TODO */ - return 0; -} - extern struct thread_info *_switch(struct thread_info *old_ti, struct thread_info *new_ti); extern int lwa_flag; diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 8aa438e1f51f..b18e775f8be3 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -292,13 +292,15 @@ void __init setup_arch(char **cmdline_p) init_mm.brk = (unsigned long)_end; #ifdef CONFIG_BLK_DEV_INITRD - initrd_start = (unsigned long)&__initrd_start; - initrd_end = (unsigned long)&__initrd_end; if (initrd_start == initrd_end) { + printk(KERN_INFO "Initial ramdisk not found\n"); initrd_start = 0; initrd_end = 0; + } else { + printk(KERN_INFO "Initial ramdisk at: 0x%p (%lu bytes)\n", + (void *)(initrd_start), initrd_end - initrd_start); + initrd_below_start_ok = 1; } - initrd_below_start_ok = 1; #endif /* setup memblock allocator */ diff --git a/arch/openrisc/kernel/signal.c b/arch/openrisc/kernel/signal.c index 4f0754874d78..97804f21a40c 100644 --- a/arch/openrisc/kernel/signal.c +++ b/arch/openrisc/kernel/signal.c @@ -68,7 +68,7 @@ static int restore_sigcontext(struct pt_regs *regs, asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs) { - struct rt_sigframe *frame = (struct rt_sigframe __user *)regs->sp; + struct rt_sigframe __user *frame = (struct rt_sigframe __user *)regs->sp; sigset_t set; /* @@ -76,7 +76,7 @@ asmlinkage long _sys_rt_sigreturn(struct pt_regs *regs) * then frame should be dword aligned here. If it's * not, then the user is trying to mess with us. */ - if (((long)frame) & 3) + if (((unsigned long)frame) & 3) goto badframe; if (!access_ok(frame, sizeof(*frame))) @@ -151,7 +151,7 @@ static inline void __user *get_sigframe(struct ksignal *ksig, static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { - struct rt_sigframe *frame; + struct rt_sigframe __user *frame; unsigned long return_ip; int err = 0; @@ -181,10 +181,10 @@ static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, l.ori r11,r0,__NR_sigreturn l.sys 1 */ - err |= __put_user(0xa960, (short *)(frame->retcode + 0)); - err |= __put_user(__NR_rt_sigreturn, (short *)(frame->retcode + 2)); - err |= __put_user(0x20000001, (unsigned long *)(frame->retcode + 4)); - err |= __put_user(0x15000000, (unsigned long *)(frame->retcode + 8)); + err |= __put_user(0xa960, (short __user *)(frame->retcode + 0)); + err |= __put_user(__NR_rt_sigreturn, (short __user *)(frame->retcode + 2)); + err |= __put_user(0x20000001, (unsigned long __user *)(frame->retcode + 4)); + err |= __put_user(0x15000000, (unsigned long __user *)(frame->retcode + 8)); if (err) return -EFAULT; diff --git a/arch/openrisc/kernel/smp.c b/arch/openrisc/kernel/smp.c index bd1e660bbc89..29c82ef2e207 100644 --- a/arch/openrisc/kernel/smp.c +++ b/arch/openrisc/kernel/smp.c @@ -219,30 +219,99 @@ static inline void ipi_flush_tlb_all(void *ignored) local_flush_tlb_all(); } +static inline void ipi_flush_tlb_mm(void *info) +{ + struct mm_struct *mm = (struct mm_struct *)info; + + local_flush_tlb_mm(mm); +} + +static void smp_flush_tlb_mm(struct cpumask *cmask, struct mm_struct *mm) +{ + unsigned int cpuid; + + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + + if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) { + /* local cpu is the only cpu present in cpumask */ + local_flush_tlb_mm(mm); + } else { + on_each_cpu_mask(cmask, ipi_flush_tlb_mm, mm, 1); + } + put_cpu(); +} + +struct flush_tlb_data { + unsigned long addr1; + unsigned long addr2; +}; + +static inline void ipi_flush_tlb_page(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_page(NULL, fd->addr1); +} + +static inline void ipi_flush_tlb_range(void *info) +{ + struct flush_tlb_data *fd = (struct flush_tlb_data *)info; + + local_flush_tlb_range(NULL, fd->addr1, fd->addr2); +} + +static void smp_flush_tlb_range(struct cpumask *cmask, unsigned long start, + unsigned long end) +{ + unsigned int cpuid; + + if (cpumask_empty(cmask)) + return; + + cpuid = get_cpu(); + + if (cpumask_any_but(cmask, cpuid) >= nr_cpu_ids) { + /* local cpu is the only cpu present in cpumask */ + if ((end - start) <= PAGE_SIZE) + local_flush_tlb_page(NULL, start); + else + local_flush_tlb_range(NULL, start, end); + } else { + struct flush_tlb_data fd; + + fd.addr1 = start; + fd.addr2 = end; + + if ((end - start) <= PAGE_SIZE) + on_each_cpu_mask(cmask, ipi_flush_tlb_page, &fd, 1); + else + on_each_cpu_mask(cmask, ipi_flush_tlb_range, &fd, 1); + } + put_cpu(); +} + void flush_tlb_all(void) { on_each_cpu(ipi_flush_tlb_all, NULL, 1); } -/* - * FIXME: implement proper functionality instead of flush_tlb_all. - * *But*, as things currently stands, the local_tlb_flush_* functions will - * all boil down to local_tlb_flush_all anyway. - */ void flush_tlb_mm(struct mm_struct *mm) { - on_each_cpu(ipi_flush_tlb_all, NULL, 1); + smp_flush_tlb_mm(mm_cpumask(mm), mm); } void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { - on_each_cpu(ipi_flush_tlb_all, NULL, 1); + smp_flush_tlb_range(mm_cpumask(vma->vm_mm), uaddr, uaddr + PAGE_SIZE); } void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - on_each_cpu(ipi_flush_tlb_all, NULL, 1); + smp_flush_tlb_range(mm_cpumask(vma->vm_mm), start, end); } /* Instruction cache invalidate - performed on each cpu */ diff --git a/arch/openrisc/kernel/stacktrace.c b/arch/openrisc/kernel/stacktrace.c index 43f140a28bc7..54d38809e22c 100644 --- a/arch/openrisc/kernel/stacktrace.c +++ b/arch/openrisc/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/sched.h> #include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <asm/processor.h> @@ -68,12 +69,25 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { unsigned long *sp = NULL; + if (!try_get_task_stack(tsk)) + return; + if (tsk == current) sp = (unsigned long *) &sp; - else - sp = (unsigned long *) KSTK_ESP(tsk); + else { + unsigned long ksp; + + /* Locate stack from kernel context */ + ksp = task_thread_info(tsk)->ksp; + ksp += STACK_FRAME_OVERHEAD; /* redzone */ + ksp += sizeof(struct pt_regs); + + sp = (unsigned long *) ksp; + } unwind_stack(trace, sp, save_stack_address_nosched); + + put_task_stack(tsk); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index 60449fd7f16f..22fbc5fb24b3 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -96,18 +96,6 @@ SECTIONS __init_end = .; - . = ALIGN(PAGE_SIZE); - .initrd : AT(ADDR(.initrd) - LOAD_OFFSET) - { - __initrd_start = .; - *(.initrd) - __initrd_end = .; - FILL (0); - . = ALIGN (PAGE_SIZE); - } - - __vmlinux_end = .; /* last address of the physical file */ - BSS_SECTION(0, 0, 0x20) _end = .; diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index d2224ccca294..ca97d9baab51 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -15,6 +15,7 @@ #include <linux/interrupt.h> #include <linux/extable.h> #include <linux/sched/signal.h> +#include <linux/perf_event.h> #include <linux/uaccess.h> #include <asm/siginfo.h> @@ -103,6 +104,8 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long address, if (in_interrupt() || !mm) goto no_context; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -159,7 +162,7 @@ good_area: * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -176,10 +179,6 @@ good_area: if (flags & FAULT_FLAG_ALLOW_RETRY) { /*RGD modeled on Cris */ - if (fault & VM_FAULT_MAJOR) - tsk->maj_flt++; - else - tsk->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/openrisc/mm/tlb.c b/arch/openrisc/mm/tlb.c index 4b680aed8f5f..2b6feabf6381 100644 --- a/arch/openrisc/mm/tlb.c +++ b/arch/openrisc/mm/tlb.c @@ -137,21 +137,28 @@ void local_flush_tlb_mm(struct mm_struct *mm) void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *next_tsk) { + unsigned int cpu; + + if (unlikely(prev == next)) + return; + + cpu = smp_processor_id(); + + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + cpumask_set_cpu(cpu, mm_cpumask(next)); + /* remember the pgd for the fault handlers * this is similar to the pgd register in some other CPU's. * we need our own copy of it because current and active_mm * might be invalid at points where we still need to derefer * the pgd. */ - current_pgd[smp_processor_id()] = next->pgd; + current_pgd[cpu] = next->pgd; /* We don't have context support implemented, so flush all * entries belonging to previous map */ - - if (prev != next) - local_flush_tlb_mm(prev); - + local_flush_tlb_mm(prev); } /* diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 03862320f779..21b375c67e53 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -34,13 +34,13 @@ extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned; /* Can't use raw_spin_lock_irq because of #include problems, so * this is the substitute */ #define _atomic_spin_lock_irqsave(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ + arch_spinlock_t *s = ATOMIC_HASH(l); \ local_irq_save(f); \ arch_spin_lock(s); \ } while(0) #define _atomic_spin_unlock_irqrestore(l,f) do { \ - arch_spinlock_t *s = ATOMIC_HASH(l); \ + arch_spinlock_t *s = ATOMIC_HASH(l); \ arch_spin_unlock(s); \ local_irq_restore(f); \ } while(0) @@ -85,7 +85,7 @@ static __inline__ void atomic_##op(int i, atomic_t *v) \ _atomic_spin_lock_irqsave(v, flags); \ v->counter c_op i; \ _atomic_spin_unlock_irqrestore(v, flags); \ -} \ +} #define ATOMIC_OP_RETURN(op, c_op) \ static __inline__ int atomic_##op##_return(int i, atomic_t *v) \ @@ -148,7 +148,7 @@ static __inline__ void atomic64_##op(s64 i, atomic64_t *v) \ _atomic_spin_lock_irqsave(v, flags); \ v->counter c_op i; \ _atomic_spin_unlock_irqrestore(v, flags); \ -} \ +} #define ATOMIC64_OP_RETURN(op, c_op) \ static __inline__ s64 atomic64_##op##_return(s64 i, atomic64_t *v) \ diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h index dbaaca84f27f..640d46edf32e 100644 --- a/arch/parisc/include/asm/barrier.h +++ b/arch/parisc/include/asm/barrier.h @@ -26,6 +26,67 @@ #define __smp_rmb() mb() #define __smp_wmb() mb() +#define __smp_store_release(p, v) \ +do { \ + typeof(p) __p = (p); \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (__force typeof(*p)) (v) }; \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("stb,ma %0,0(%1)" \ + : : "r"(*(__u8 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("sth,ma %0,0(%1)" \ + : : "r"(*(__u16 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("stw,ma %0,0(%1)" \ + : : "r"(*(__u32 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("std,ma %0,0(%1)" \ + : : "r"(*(__u64 *)__u.__c), "r"(__p) \ + : "memory"); \ + break; \ + } \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u; \ + typeof(p) __p = (p); \ + compiletime_assert_atomic_type(*p); \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile("ldb,ma 0(%1),%0" \ + : "=r"(*(__u8 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile("ldh,ma 0(%1),%0" \ + : "=r"(*(__u16 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile("ldw,ma 0(%1),%0" \ + : "=r"(*(__u32 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + case 8: \ + if (IS_ENABLED(CONFIG_64BIT)) \ + asm volatile("ldd,ma 0(%1),%0" \ + : "=r"(*(__u64 *)__u.__c) : "r"(__p) \ + : "memory"); \ + break; \ + } \ + __u.__val; \ +}) #include <asm-generic/barrier.h> #endif /* !__ASSEMBLY__ */ diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 301af07a04d4..3bd465a27791 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -305,9 +305,6 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; struct task_struct; -extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *); -#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs) - struct pt_regs; /* forward declaration... */ diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h index 116effe26143..45e20d38dc59 100644 --- a/arch/parisc/include/asm/io.h +++ b/arch/parisc/include/asm/io.h @@ -303,8 +303,8 @@ extern void outsl (unsigned long port, const void *src, unsigned long count); #define ioread64be ioread64be #define iowrite64 iowrite64 #define iowrite64be iowrite64be -extern u64 ioread64(void __iomem *addr); -extern u64 ioread64be(void __iomem *addr); +extern u64 ioread64(const void __iomem *addr); +extern u64 ioread64be(const void __iomem *addr); extern void iowrite64(u64 val, void __iomem *addr); extern void iowrite64be(u64 val, void __iomem *addr); diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h index 07b89c74abeb..cb5f2f730421 100644 --- a/arch/parisc/include/asm/mmu_context.h +++ b/arch/parisc/include/asm/mmu_context.h @@ -5,7 +5,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <linux/atomic.h> -#include <asm/pgalloc.h> #include <asm-generic/mm_hooks.h> static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h index 9ac74da256b8..cc7ecc2ef55d 100644 --- a/arch/parisc/include/asm/pgalloc.h +++ b/arch/parisc/include/asm/pgalloc.h @@ -10,7 +10,9 @@ #include <asm/cache.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#define __HAVE_ARCH_PMD_FREE +#define __HAVE_ARCH_PGD_FREE +#include <asm-generic/pgalloc.h> /* Allocate the top level pgd (page directory) * @@ -65,14 +67,6 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) (__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT))); } -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) -{ - pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL, PMD_ORDER); - if (pmd) - memset(pmd, 0, PAGE_SIZE<<PMD_ORDER); - return pmd; -} - static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) { diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h index 45537cd4d1d3..06b510f8172e 100644 --- a/arch/parisc/include/asm/timex.h +++ b/arch/parisc/include/asm/timex.h @@ -7,6 +7,7 @@ #ifndef _ASMPARISC_TIMEX_H #define _ASMPARISC_TIMEX_H +#include <asm/special_insns.h> #define CLOCK_TICK_RATE 1193180 /* Underlying HZ */ diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index ebbb9ffe038c..ed2cd4fb479b 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -14,7 +14,7 @@ #define KERNEL_DS ((mm_segment_t){0}) #define USER_DS ((mm_segment_t){1}) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c index 1eedfecc5137..b5e1d9f1b440 100644 --- a/arch/parisc/kernel/cache.c +++ b/arch/parisc/kernel/cache.c @@ -24,7 +24,6 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/sections.h> #include <asm/shmparam.h> diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 1df0f67ed667..4bab21c71055 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -64,7 +64,8 @@ void notrace __hot ftrace_function_trampoline(unsigned long parent, function_trace_op, regs); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (ftrace_graph_return != (trace_func_graph_ret_t) ftrace_stub || + if (dereference_function_descriptor(ftrace_graph_return) != + dereference_function_descriptor(ftrace_stub) || ftrace_graph_entry != ftrace_graph_entry_stub) { unsigned long *parent_rp; diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c index 4f1596bb1936..38c68e131bbe 100644 --- a/arch/parisc/kernel/pci-dma.c +++ b/arch/parisc/kernel/pci-dma.c @@ -32,7 +32,6 @@ #include <asm/dma.h> /* for DMA_CHUNK_SIZE */ #include <asm/io.h> #include <asm/page.h> /* get_order */ -#include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/tlbflush.h> /* for purge_tlb_*() macros */ diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index de6299ff1530..f196d96e2f9f 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -47,7 +47,6 @@ #include <asm/assembly.h> #include <asm/pdc.h> #include <asm/pdc_chassis.h> -#include <asm/pgalloc.h> #include <asm/unwind.h> #include <asm/sections.h> @@ -153,25 +152,6 @@ void release_thread(struct task_struct *dead_task) } /* - * Fill in the FPU structure for a core dump. - */ - -int dump_fpu (struct pt_regs * regs, elf_fpregset_t *r) -{ - if (regs == NULL) - return 0; - - memcpy(r, regs->fr, sizeof *r); - return 1; -} - -int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r) -{ - memcpy(r, tsk->thread.regs.fr, sizeof(*r)); - return 1; -} - -/* * Idle thread support * * Detect when running on QEMU with SeaBIOS PDC Firmware and let diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 02895a8f2c55..5df5d4cd5d4c 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -30,7 +30,6 @@ #include <asm/ucontext.h> #include <asm/rt_sigframe.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/asm-offsets.h> diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c index f8a842ddd82d..6271139d2213 100644 --- a/arch/parisc/kernel/smp.c +++ b/arch/parisc/kernel/smp.c @@ -39,7 +39,6 @@ #include <asm/irq.h> /* for CPU_IRQ_REGION and friends */ #include <asm/mmu_context.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/processor.h> #include <asm/ptrace.h> #include <asm/unistd.h> diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 292baabefade..def64d221cd4 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -163,7 +163,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl compat_sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index 0195aec657e2..ce400417d54e 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -43,13 +43,13 @@ #endif struct iomap_ops { - unsigned int (*read8)(void __iomem *); - unsigned int (*read16)(void __iomem *); - unsigned int (*read16be)(void __iomem *); - unsigned int (*read32)(void __iomem *); - unsigned int (*read32be)(void __iomem *); - u64 (*read64)(void __iomem *); - u64 (*read64be)(void __iomem *); + unsigned int (*read8)(const void __iomem *); + unsigned int (*read16)(const void __iomem *); + unsigned int (*read16be)(const void __iomem *); + unsigned int (*read32)(const void __iomem *); + unsigned int (*read32be)(const void __iomem *); + u64 (*read64)(const void __iomem *); + u64 (*read64be)(const void __iomem *); void (*write8)(u8, void __iomem *); void (*write16)(u16, void __iomem *); void (*write16be)(u16, void __iomem *); @@ -57,9 +57,9 @@ struct iomap_ops { void (*write32be)(u32, void __iomem *); void (*write64)(u64, void __iomem *); void (*write64be)(u64, void __iomem *); - void (*read8r)(void __iomem *, void *, unsigned long); - void (*read16r)(void __iomem *, void *, unsigned long); - void (*read32r)(void __iomem *, void *, unsigned long); + void (*read8r)(const void __iomem *, void *, unsigned long); + void (*read16r)(const void __iomem *, void *, unsigned long); + void (*read32r)(const void __iomem *, void *, unsigned long); void (*write8r)(void __iomem *, const void *, unsigned long); void (*write16r)(void __iomem *, const void *, unsigned long); void (*write32r)(void __iomem *, const void *, unsigned long); @@ -69,17 +69,17 @@ struct iomap_ops { #define ADDR2PORT(addr) ((unsigned long __force)(addr) & 0xffffff) -static unsigned int ioport_read8(void __iomem *addr) +static unsigned int ioport_read8(const void __iomem *addr) { return inb(ADDR2PORT(addr)); } -static unsigned int ioport_read16(void __iomem *addr) +static unsigned int ioport_read16(const void __iomem *addr) { return inw(ADDR2PORT(addr)); } -static unsigned int ioport_read32(void __iomem *addr) +static unsigned int ioport_read32(const void __iomem *addr) { return inl(ADDR2PORT(addr)); } @@ -99,17 +99,17 @@ static void ioport_write32(u32 datum, void __iomem *addr) outl(datum, ADDR2PORT(addr)); } -static void ioport_read8r(void __iomem *addr, void *dst, unsigned long count) +static void ioport_read8r(const void __iomem *addr, void *dst, unsigned long count) { insb(ADDR2PORT(addr), dst, count); } -static void ioport_read16r(void __iomem *addr, void *dst, unsigned long count) +static void ioport_read16r(const void __iomem *addr, void *dst, unsigned long count) { insw(ADDR2PORT(addr), dst, count); } -static void ioport_read32r(void __iomem *addr, void *dst, unsigned long count) +static void ioport_read32r(const void __iomem *addr, void *dst, unsigned long count) { insl(ADDR2PORT(addr), dst, count); } @@ -150,37 +150,37 @@ static const struct iomap_ops ioport_ops = { /* Legacy I/O memory ops */ -static unsigned int iomem_read8(void __iomem *addr) +static unsigned int iomem_read8(const void __iomem *addr) { return readb(addr); } -static unsigned int iomem_read16(void __iomem *addr) +static unsigned int iomem_read16(const void __iomem *addr) { return readw(addr); } -static unsigned int iomem_read16be(void __iomem *addr) +static unsigned int iomem_read16be(const void __iomem *addr) { return __raw_readw(addr); } -static unsigned int iomem_read32(void __iomem *addr) +static unsigned int iomem_read32(const void __iomem *addr) { return readl(addr); } -static unsigned int iomem_read32be(void __iomem *addr) +static unsigned int iomem_read32be(const void __iomem *addr) { return __raw_readl(addr); } -static u64 iomem_read64(void __iomem *addr) +static u64 iomem_read64(const void __iomem *addr) { return readq(addr); } -static u64 iomem_read64be(void __iomem *addr) +static u64 iomem_read64be(const void __iomem *addr) { return __raw_readq(addr); } @@ -220,7 +220,7 @@ static void iomem_write64be(u64 datum, void __iomem *addr) __raw_writel(datum, addr); } -static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count) +static void iomem_read8r(const void __iomem *addr, void *dst, unsigned long count) { while (count--) { *(u8 *)dst = __raw_readb(addr); @@ -228,7 +228,7 @@ static void iomem_read8r(void __iomem *addr, void *dst, unsigned long count) } } -static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count) +static void iomem_read16r(const void __iomem *addr, void *dst, unsigned long count) { while (count--) { *(u16 *)dst = __raw_readw(addr); @@ -236,7 +236,7 @@ static void iomem_read16r(void __iomem *addr, void *dst, unsigned long count) } } -static void iomem_read32r(void __iomem *addr, void *dst, unsigned long count) +static void iomem_read32r(const void __iomem *addr, void *dst, unsigned long count) { while (count--) { *(u32 *)dst = __raw_readl(addr); @@ -297,49 +297,49 @@ static const struct iomap_ops *iomap_ops[8] = { }; -unsigned int ioread8(void __iomem *addr) +unsigned int ioread8(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read8(addr); return *((u8 *)addr); } -unsigned int ioread16(void __iomem *addr) +unsigned int ioread16(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read16(addr); return le16_to_cpup((u16 *)addr); } -unsigned int ioread16be(void __iomem *addr) +unsigned int ioread16be(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read16be(addr); return *((u16 *)addr); } -unsigned int ioread32(void __iomem *addr) +unsigned int ioread32(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read32(addr); return le32_to_cpup((u32 *)addr); } -unsigned int ioread32be(void __iomem *addr) +unsigned int ioread32be(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read32be(addr); return *((u32 *)addr); } -u64 ioread64(void __iomem *addr) +u64 ioread64(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read64(addr); return le64_to_cpup((u64 *)addr); } -u64 ioread64be(void __iomem *addr) +u64 ioread64be(const void __iomem *addr) { if (unlikely(INDIRECT_ADDR(addr))) return iomap_ops[ADDR_TO_REGION(addr)]->read64be(addr); @@ -411,7 +411,7 @@ void iowrite64be(u64 datum, void __iomem *addr) /* Repeating interfaces */ -void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count) { if (unlikely(INDIRECT_ADDR(addr))) { iomap_ops[ADDR_TO_REGION(addr)]->read8r(addr, dst, count); @@ -423,7 +423,7 @@ void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) } } -void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count) { if (unlikely(INDIRECT_ADDR(addr))) { iomap_ops[ADDR_TO_REGION(addr)]->read16r(addr, dst, count); @@ -435,7 +435,7 @@ void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) } } -void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count) { if (unlikely(INDIRECT_ADDR(addr))) { iomap_ops[ADDR_TO_REGION(addr)]->read32r(addr, dst, count); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 66ac0719bd49..4bfe2da9fbe3 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -18,6 +18,7 @@ #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/hugetlb.h> +#include <linux/perf_event.h> #include <asm/traps.h> @@ -281,6 +282,7 @@ void do_page_fault(struct pt_regs *regs, unsigned long code, acc_type = parisc_acctyp(code, regs->iir); if (acc_type & VM_WRITE) flags |= FAULT_FLAG_WRITE; + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); retry: mmap_read_lock(mm); vma = find_vma_prev(mm, address, &prev_vma); @@ -302,7 +304,7 @@ good_area: * fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -323,10 +325,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { /* * No need to mmap_read_unlock(mm) as we would diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c index 0e1e212f1c96..d7ba014a7fbb 100644 --- a/arch/parisc/mm/hugetlbpage.c +++ b/arch/parisc/mm/hugetlbpage.c @@ -15,7 +15,6 @@ #include <linux/sysctl.h> #include <asm/mman.h> -#include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 39ea464c8bd9..4381b65ae1e0 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -689,11 +689,6 @@ void __init paging_init(void) flush_cache_all_local(); /* start with known state */ flush_tlb_all_local(NULL); - /* - * Mark all memblocks as present for sparsemem using - * memory_present() and then initialize sparsemem. - */ - memblocks_present(); sparse_init(); parisc_bootmem_free(); } diff --git a/arch/parisc/mm/ioremap.c b/arch/parisc/mm/ioremap.c index 6e7c005aa09b..345ff0b66499 100644 --- a/arch/parisc/mm/ioremap.c +++ b/arch/parisc/mm/ioremap.c @@ -11,7 +11,7 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/io.h> -#include <asm/pgalloc.h> +#include <linux/mm.h> /* * Generic mapping function (not visible outside): diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 29a057908173..1f48bbfb3ce9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -131,6 +131,7 @@ config PPC select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MEMBARRIER_CALLBACKS + select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 select ARCH_HAS_STRICT_KERNEL_RWX if (PPC32 && !HIBERNATION) select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST @@ -145,6 +146,8 @@ config PPC select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_CMPXCHG_LOCKREF if PPC64 + select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS + select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF @@ -491,6 +494,19 @@ config HOTPLUG_CPU Say N if you are unsure. +config PPC_QUEUED_SPINLOCKS + bool "Queued spinlocks" + depends on SMP + help + Say Y here to use queued spinlocks which give better scalability and + fairness on large SMP and NUMA systems without harming single threaded + performance. + + This option is currently experimental, the code is more complex and + less tested so it defaults to "N" for the moment. + + If unsure, say "N". + config ARCH_CPU_PROBE_RELEASE def_bool y depends on HOTPLUG_CPU @@ -834,13 +850,16 @@ config FORCE_MAX_ZONEORDER this in mind when choosing a value for this option. config PPC_SUBPAGE_PROT - bool "Support setting protections for 4k subpages" + bool "Support setting protections for 4k subpages (subpage_prot syscall)" + default n depends on PPC_BOOK3S_64 && PPC_64K_PAGES help - This option adds support for a system call to allow user programs + This option adds support for system call to allow user programs to set access permissions (read/write, readonly, or no access) on the 4k subpages of each 64k page. + If unsure, say N here. + config PPC_COPRO_BASE bool @@ -860,12 +879,8 @@ config PPC_DENORMALISATION Add support for handling denormalisation of single precision values. Useful for bare metal only. If unsure say Y here. -config CMDLINE_BOOL - bool "Default bootloader kernel arguments" - config CMDLINE - string "Initial kernel command string" if CMDLINE_BOOL - default "console=ttyS0,9600 console=tty0 root=/dev/sda2" if CMDLINE_BOOL + string "Initial kernel command string" default "" help On some platforms, there is currently no way for the boot loader to @@ -1199,6 +1214,7 @@ config TASK_SIZE_BOOL config TASK_SIZE hex "Size of user task space" if TASK_SIZE_BOOL default "0x80000000" if PPC_8xx + default "0xb0000000" if PPC_BOOK3S_32 && STRICT_KERNEL_RWX default "0xc0000000" endmenu diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index f310c32e88a4..3e8da9cf2eb9 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -246,7 +246,8 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # often slow when they are implemented at all KBUILD_CFLAGS += $(call cc-option,-mno-string) -cpu-as-$(CONFIG_4xx) += -Wa,-m405 +cpu-as-$(CONFIG_40x) += -Wa,-m405 +cpu-as-$(CONFIG_44x) += -Wa,-m440 cpu-as-$(CONFIG_ALTIVEC) += $(call as-option,-Wa$(comma)-maltivec) cpu-as-$(CONFIG_E200) += -Wa,-me200 cpu-as-$(CONFIG_E500) += -Wa,-me500 diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index 63d7456b9518..b88fd27a45f0 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -70,10 +70,10 @@ BOOTCFLAGS += -I$(objtree)/$(obj) -I$(srctree)/$(obj) DTC_FLAGS ?= -p 1024 $(obj)/4xx.o: BOOTCFLAGS += -mcpu=405 -$(obj)/ebony.o: BOOTCFLAGS += -mcpu=405 +$(obj)/ebony.o: BOOTCFLAGS += -mcpu=440 $(obj)/cuboot-hotfoot.o: BOOTCFLAGS += -mcpu=405 -$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405 -$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405 +$(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=440 +$(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=440 $(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-iss4xx.o: BOOTCFLAGS += -mcpu=405 $(obj)/treeboot-currituck.o: BOOTCFLAGS += -mcpu=405 @@ -117,7 +117,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c -src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c +src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S @@ -366,6 +366,8 @@ initrd-y := $(patsubst zImage%, zImage.initrd%, \ $(patsubst treeImage%, treeImage.initrd%, $(image-y))))) initrd-y := $(filter-out $(image-y), $(initrd-y)) targets += $(image-y) $(initrd-y) +targets += $(foreach x, dtbImage uImage cuImage simpleImage treeImage, \ + $(patsubst $(x).%, dts/%.dtb, $(filter $(x).%, $(image-y)))) $(addprefix $(obj)/, $(initrd-y)): $(obj)/ramdisk.image.gz diff --git a/arch/powerpc/boot/dts/akebono.dts b/arch/powerpc/boot/dts/akebono.dts index cd9d66041a3f..df18f8dc4642 100644 --- a/arch/powerpc/boot/dts/akebono.dts +++ b/arch/powerpc/boot/dts/akebono.dts @@ -248,7 +248,7 @@ }; }; - PCIE0: pciex@10100000000 { + PCIE0: pcie@10100000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -288,7 +288,7 @@ 0x0 0x0 0x0 0x4 &MPIC 48 0x2 /* int D */>; }; - PCIE1: pciex@20100000000 { + PCIE1: pcie@20100000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -328,7 +328,7 @@ 0x0 0x0 0x0 0x4 &MPIC 56 0x2 /* int D */>; }; - PCIE2: pciex@18100000000 { + PCIE2: pcie@18100000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -368,7 +368,7 @@ 0x0 0x0 0x0 0x4 &MPIC 64 0x2 /* int D */>; }; - PCIE3: pciex@28100000000 { + PCIE3: pcie@28100000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/bluestone.dts b/arch/powerpc/boot/dts/bluestone.dts index cc965a1816b6..aa1ae94cd776 100644 --- a/arch/powerpc/boot/dts/bluestone.dts +++ b/arch/powerpc/boot/dts/bluestone.dts @@ -325,7 +325,7 @@ }; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts index 0d6ac92d0f5e..c5fbb08e0a6e 100644 --- a/arch/powerpc/boot/dts/canyonlands.dts +++ b/arch/powerpc/boot/dts/canyonlands.dts @@ -461,7 +461,7 @@ interrupt-map = < 0x0 0x0 0x0 0x0 &UIC1 0x0 0x8 >; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -503,7 +503,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>; }; - PCIE1: pciex@d20000000 { + PCIE1: pcie@d20000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/currituck.dts b/arch/powerpc/boot/dts/currituck.dts index b6d87b9c2cef..aea8af810106 100644 --- a/arch/powerpc/boot/dts/currituck.dts +++ b/arch/powerpc/boot/dts/currituck.dts @@ -122,7 +122,7 @@ }; }; - PCIE0: pciex@10100000000 { // 4xGBIF1 + PCIE0: pcie@10100000000 { // 4xGBIF1 device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -160,7 +160,7 @@ 0x0 0x0 0x0 0x4 &MPIC 49 0x2 /* int D */>; }; - PCIE1: pciex@30100000000 { // 4xGBIF0 + PCIE1: pcie@30100000000 { // 4xGBIF0 device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -197,7 +197,7 @@ 0x0 0x0 0x0 0x4 &MPIC 41 0x2 /* int D */>; }; - PCIE2: pciex@38100000000 { // 2xGBIF0 + PCIE2: pcie@38100000000 { // 2xGBIF0 device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/fsl/p4080ds.dts b/arch/powerpc/boot/dts/fsl/p4080ds.dts index 65e20152e22f..969b32c4f2d5 100644 --- a/arch/powerpc/boot/dts/fsl/p4080ds.dts +++ b/arch/powerpc/boot/dts/fsl/p4080ds.dts @@ -125,11 +125,11 @@ i2c@118100 { eeprom@51 { - compatible = "atmel,24c256"; + compatible = "atmel,spd"; reg = <0x51>; }; eeprom@52 { - compatible = "atmel,24c256"; + compatible = "atmel,spd"; reg = <0x52>; }; rtc@68 { @@ -143,6 +143,45 @@ }; }; + i2c@118000 { + zl2006@21 { + compatible = "zl2006"; + reg = <0x21>; + }; + zl2006@22 { + compatible = "zl2006"; + reg = <0x22>; + }; + zl2006@23 { + compatible = "zl2006"; + reg = <0x23>; + }; + zl2006@24 { + compatible = "zl2006"; + reg = <0x24>; + }; + eeprom@50 { + compatible = "atmel,24c64"; + reg = <0x50>; + }; + eeprom@55 { + compatible = "atmel,24c64"; + reg = <0x55>; + }; + eeprom@56 { + compatible = "atmel,24c64"; + reg = <0x56>; + }; + eeprom@57 { + compatible = "atmel,24c02"; + reg = <0x57>; + }; + }; + + i2c@119100 { + /* 0x6E: ICS9FG108 */ + }; + usb0: usb@210000 { phy_type = "ulpi"; }; diff --git a/arch/powerpc/boot/dts/glacier.dts b/arch/powerpc/boot/dts/glacier.dts index a7a802f4ffdd..e84ff1afb58c 100644 --- a/arch/powerpc/boot/dts/glacier.dts +++ b/arch/powerpc/boot/dts/glacier.dts @@ -489,7 +489,7 @@ interrupt-map = < 0x0 0x0 0x0 0x0 &UIC1 0x0 0x8 >; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -531,7 +531,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>; }; - PCIE1: pciex@d20000000 { + PCIE1: pcie@d20000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/haleakala.dts b/arch/powerpc/boot/dts/haleakala.dts index cb16dad43c92..f81ce8786d59 100644 --- a/arch/powerpc/boot/dts/haleakala.dts +++ b/arch/powerpc/boot/dts/haleakala.dts @@ -237,7 +237,7 @@ }; }; - PCIE0: pciex@a0000000 { + PCIE0: pcie@a0000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/icon.dts b/arch/powerpc/boot/dts/icon.dts index 2e6e3a7b2604..fbaa60b8f87a 100644 --- a/arch/powerpc/boot/dts/icon.dts +++ b/arch/powerpc/boot/dts/icon.dts @@ -315,7 +315,7 @@ interrupt-map = <0x0 0x0 0x0 0x0 &UIC1 19 0x8>; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -356,7 +356,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>; }; - PCIE1: pciex@d20000000 { + PCIE1: pcie@d20000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/katmai.dts b/arch/powerpc/boot/dts/katmai.dts index 02629e119b87..a8f353229fb7 100644 --- a/arch/powerpc/boot/dts/katmai.dts +++ b/arch/powerpc/boot/dts/katmai.dts @@ -319,7 +319,7 @@ >; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -360,7 +360,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>; }; - PCIE1: pciex@d20000000 { + PCIE1: pcie@d20000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -401,7 +401,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0x7 0x4 /* swizzled int D */>; }; - PCIE2: pciex@d40000000 { + PCIE2: pcie@d40000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/kilauea.dts b/arch/powerpc/boot/dts/kilauea.dts index 2a3413221cc1..a709fb47a180 100644 --- a/arch/powerpc/boot/dts/kilauea.dts +++ b/arch/powerpc/boot/dts/kilauea.dts @@ -322,7 +322,7 @@ }; }; - PCIE0: pciex@a0000000 { + PCIE0: pcie@a0000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -363,7 +363,7 @@ 0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>; }; - PCIE1: pciex@c0000000 { + PCIE1: pcie@c0000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/makalu.dts b/arch/powerpc/boot/dts/makalu.dts index bf8fe1629392..c473cd911bca 100644 --- a/arch/powerpc/boot/dts/makalu.dts +++ b/arch/powerpc/boot/dts/makalu.dts @@ -268,7 +268,7 @@ }; }; - PCIE0: pciex@a0000000 { + PCIE0: pcie@a0000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -309,7 +309,7 @@ 0x0 0x0 0x0 0x4 &UIC2 0x3 0x4 /* swizzled int D */>; }; - PCIE1: pciex@c0000000 { + PCIE1: pcie@c0000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/dts/redwood.dts b/arch/powerpc/boot/dts/redwood.dts index f3e046fb49e2..f38035a1f4a1 100644 --- a/arch/powerpc/boot/dts/redwood.dts +++ b/arch/powerpc/boot/dts/redwood.dts @@ -235,7 +235,7 @@ has-new-stacr-staopc; }; }; - PCIE0: pciex@d00000000 { + PCIE0: pcie@d00000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -276,7 +276,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0x3 0x4 /* swizzled int D */>; }; - PCIE1: pciex@d20000000 { + PCIE1: pcie@d20000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; @@ -317,7 +317,7 @@ 0x0 0x0 0x0 0x4 &UIC3 0x7 0x4 /* swizzled int D */>; }; - PCIE2: pciex@d40000000 { + PCIE2: pcie@d40000000 { device_type = "pci"; #interrupt-cells = <1>; #size-cells = <2>; diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c index a9d209135975..cae31a6e8f02 100644 --- a/arch/powerpc/boot/main.c +++ b/arch/powerpc/boot/main.c @@ -104,7 +104,7 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen, { /* If we have an image attached to us, it overrides anything * supplied by the loader. */ - if (_initrd_end > _initrd_start) { + if (&_initrd_end > &_initrd_start) { printf("Attached initrd image at 0x%p-0x%p\n\r", _initrd_start, _initrd_end); initrd_addr = (unsigned long)_initrd_start; @@ -152,7 +152,7 @@ static void prep_esm_blob(struct addr_range vmlinux, void *chosen) unsigned long esm_blob_addr, esm_blob_size; /* Do we have an ESM (Enter Secure Mode) blob? */ - if (_esm_blob_end <= _esm_blob_start) + if (&_esm_blob_end <= &_esm_blob_start) return; printf("Attached ESM blob at 0x%p-0x%p\n\r", diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c index c52552a681c5..6e4efbdb6b7c 100644 --- a/arch/powerpc/boot/ps3.c +++ b/arch/powerpc/boot/ps3.c @@ -127,7 +127,7 @@ void platform_init(void) ps3_repository_read_rm_size(&rm_size); dt_fixup_memory(0, rm_size); - if (_initrd_end > _initrd_start) { + if (&_initrd_end > &_initrd_start) { setprop_val(chosen, "linux,initrd-start", (u32)(_initrd_start)); setprop_val(chosen, "linux,initrd-end", (u32)(_initrd_end)); } diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index 0bfa7e87e546..9a19e5905485 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -128,7 +128,7 @@ int serial_console_init(void) dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC_MPC52XX +#ifdef CONFIG_PPC_MPC52xx else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/configs/44x/akebono_defconfig b/arch/powerpc/configs/44x/akebono_defconfig index 7705a5c3f4ea..3894ba8f8ffc 100644 --- a/arch/powerpc/configs/44x/akebono_defconfig +++ b/arch/powerpc/configs/44x/akebono_defconfig @@ -19,8 +19,6 @@ CONFIG_HIGHMEM=y CONFIG_HZ_100=y CONFIG_IRQ_ALL_CPUS=y # CONFIG_COMPACTION is not set -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" # CONFIG_SUSPEND is not set CONFIG_NET=y CONFIG_PACKET=y @@ -58,7 +56,6 @@ CONFIG_BLK_DEV_SD=y # CONFIG_NET_VENDOR_DEC is not set # CONFIG_NET_VENDOR_DLINK is not set # CONFIG_NET_VENDOR_EMULEX is not set -# CONFIG_NET_VENDOR_EXAR is not set CONFIG_IBM_EMAC=y # CONFIG_NET_VENDOR_MARVELL is not set # CONFIG_NET_VENDOR_MELLANOX is not set diff --git a/arch/powerpc/configs/44x/arches_defconfig b/arch/powerpc/configs/44x/arches_defconfig index 82c6f49b8dcb..41d04e70d4fb 100644 --- a/arch/powerpc/configs/44x/arches_defconfig +++ b/arch/powerpc/configs/44x/arches_defconfig @@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_EBONY is not set CONFIG_ARCHES=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/bamboo_defconfig b/arch/powerpc/configs/44x/bamboo_defconfig index 679213214a75..acbce718eaa8 100644 --- a/arch/powerpc/configs/44x/bamboo_defconfig +++ b/arch/powerpc/configs/44x/bamboo_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set CONFIG_BAMBOO=y # CONFIG_EBONY is not set -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/bluestone_defconfig b/arch/powerpc/configs/44x/bluestone_defconfig index 8006a5728afd..37088f250c9e 100644 --- a/arch/powerpc/configs/44x/bluestone_defconfig +++ b/arch/powerpc/configs/44x/bluestone_defconfig @@ -11,8 +11,6 @@ CONFIG_EXPERT=y # CONFIG_COMPAT_BRK is not set CONFIG_BLUESTONE=y # CONFIG_EBONY is not set -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/canyonlands_defconfig b/arch/powerpc/configs/44x/canyonlands_defconfig index ccc14eb7a2f1..61776ade572b 100644 --- a/arch/powerpc/configs/44x/canyonlands_defconfig +++ b/arch/powerpc/configs/44x/canyonlands_defconfig @@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_EBONY is not set CONFIG_CANYONLANDS=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/currituck_defconfig b/arch/powerpc/configs/44x/currituck_defconfig index be76e066df01..34c86b3abecb 100644 --- a/arch/powerpc/configs/44x/currituck_defconfig +++ b/arch/powerpc/configs/44x/currituck_defconfig @@ -17,8 +17,6 @@ CONFIG_HIGHMEM=y CONFIG_HZ_100=y CONFIG_MATH_EMULATION=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" # CONFIG_SUSPEND is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/powerpc/configs/44x/eiger_defconfig b/arch/powerpc/configs/44x/eiger_defconfig index 1abaa63e067f..509300f400e2 100644 --- a/arch/powerpc/configs/44x/eiger_defconfig +++ b/arch/powerpc/configs/44x/eiger_defconfig @@ -10,8 +10,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_EBONY is not set CONFIG_EIGER=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_PCIEPORTBUS=y # CONFIG_PCIEASPM is not set CONFIG_NET=y diff --git a/arch/powerpc/configs/44x/fsp2_defconfig b/arch/powerpc/configs/44x/fsp2_defconfig index e67fc041ca3e..30845ce0885a 100644 --- a/arch/powerpc/configs/44x/fsp2_defconfig +++ b/arch/powerpc/configs/44x/fsp2_defconfig @@ -28,7 +28,6 @@ CONFIG_476FPE_ERR46=y CONFIG_SWIOTLB=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="ip=on rw" # CONFIG_SUSPEND is not set # CONFIG_PCI is not set diff --git a/arch/powerpc/configs/44x/icon_defconfig b/arch/powerpc/configs/44x/icon_defconfig index 7d7ff84c8200..930948a1da76 100644 --- a/arch/powerpc/configs/44x/icon_defconfig +++ b/arch/powerpc/configs/44x/icon_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_EBONY is not set CONFIG_ICON=y CONFIG_HIGHMEM=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_PCIEPORTBUS=y # CONFIG_PCIEASPM is not set CONFIG_NET=y diff --git a/arch/powerpc/configs/44x/iss476-smp_defconfig b/arch/powerpc/configs/44x/iss476-smp_defconfig index fb5c73a29bf4..2c3834eebca3 100644 --- a/arch/powerpc/configs/44x/iss476-smp_defconfig +++ b/arch/powerpc/configs/44x/iss476-smp_defconfig @@ -17,7 +17,6 @@ CONFIG_ISS4xx=y CONFIG_HZ_100=y CONFIG_MATH_EMULATION=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="root=/dev/issblk0" # CONFIG_PCI is not set CONFIG_ADVANCED_OPTIONS=y diff --git a/arch/powerpc/configs/44x/katmai_defconfig b/arch/powerpc/configs/44x/katmai_defconfig index c6dc1445fc04..1a0f1c3e0ee9 100644 --- a/arch/powerpc/configs/44x/katmai_defconfig +++ b/arch/powerpc/configs/44x/katmai_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_EBONY is not set CONFIG_KATMAI=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/rainier_defconfig b/arch/powerpc/configs/44x/rainier_defconfig index c83ad03182df..6dd67de06a0b 100644 --- a/arch/powerpc/configs/44x/rainier_defconfig +++ b/arch/powerpc/configs/44x/rainier_defconfig @@ -10,8 +10,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_EBONY is not set CONFIG_RAINIER=y CONFIG_MATH_EMULATION=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/redwood_defconfig b/arch/powerpc/configs/44x/redwood_defconfig index 640fe1d5af28..e28d76416537 100644 --- a/arch/powerpc/configs/44x/redwood_defconfig +++ b/arch/powerpc/configs/44x/redwood_defconfig @@ -10,8 +10,6 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_EBONY is not set CONFIG_REDWOOD=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_PCIEPORTBUS=y # CONFIG_PCIEASPM is not set CONFIG_NET=y diff --git a/arch/powerpc/configs/44x/sam440ep_defconfig b/arch/powerpc/configs/44x/sam440ep_defconfig index 22dc0dadf576..ef09786d49b9 100644 --- a/arch/powerpc/configs/44x/sam440ep_defconfig +++ b/arch/powerpc/configs/44x/sam440ep_defconfig @@ -12,8 +12,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_AMIGA_PARTITION=y # CONFIG_EBONY is not set CONFIG_SAM440EP=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/sequoia_defconfig b/arch/powerpc/configs/44x/sequoia_defconfig index 2c0973db8837..b4984eab43eb 100644 --- a/arch/powerpc/configs/44x/sequoia_defconfig +++ b/arch/powerpc/configs/44x/sequoia_defconfig @@ -11,8 +11,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_EBONY is not set CONFIG_SEQUOIA=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/taishan_defconfig b/arch/powerpc/configs/44x/taishan_defconfig index a2d355ca62b2..3ea5932ab852 100644 --- a/arch/powerpc/configs/44x/taishan_defconfig +++ b/arch/powerpc/configs/44x/taishan_defconfig @@ -9,8 +9,6 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_EBONY is not set CONFIG_TAISHAN=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y diff --git a/arch/powerpc/configs/44x/warp_defconfig b/arch/powerpc/configs/44x/warp_defconfig index af66c69c49fe..47252c2d7669 100644 --- a/arch/powerpc/configs/44x/warp_defconfig +++ b/arch/powerpc/configs/44x/warp_defconfig @@ -14,7 +14,6 @@ CONFIG_MODULE_UNLOAD=y CONFIG_WARP=y CONFIG_PPC4xx_GPIO=y CONFIG_HZ_1000=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="ip=on" # CONFIG_PCI is not set CONFIG_NET=y diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index b507df6ac69f..524db76f47b7 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -67,7 +67,6 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI=y CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_M25P80=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y CONFIG_MTD_RAW_NAND=y diff --git a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig index d50aca608736..3a6381aa9fdc 100644 --- a/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig +++ b/arch/powerpc/configs/85xx/xes_mpc85xx_defconfig @@ -51,9 +51,6 @@ CONFIG_NET_IPIP=y CONFIG_IP_MROUTE=y CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_MTD=y CONFIG_MTD_REDBOOT_PARTS=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/86xx-hw.config b/arch/powerpc/configs/86xx-hw.config index 151164cf8cb3..0cb24b33c88e 100644 --- a/arch/powerpc/configs/86xx-hw.config +++ b/arch/powerpc/configs/86xx-hw.config @@ -32,8 +32,6 @@ CONFIG_HW_RANDOM=y CONFIG_HZ_1000=y CONFIG_I2C_MPC=y CONFIG_I2C=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set CONFIG_INPUT_FF_MEMLESS=m # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSEDEV is not set diff --git a/arch/powerpc/configs/fsl-emb-nonhw.config b/arch/powerpc/configs/fsl-emb-nonhw.config index 3c7dad19a691..df37efed0aec 100644 --- a/arch/powerpc/configs/fsl-emb-nonhw.config +++ b/arch/powerpc/configs/fsl-emb-nonhw.config @@ -56,7 +56,6 @@ CONFIG_IKCONFIG=y CONFIG_INET_AH=y CONFIG_INET_ESP=y CONFIG_INET_IPCOMP=y -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_INET=y CONFIG_IP_ADVANCED_ROUTER=y CONFIG_IP_MROUTE=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index a68c7f3af10e..1c674c4c1d86 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -51,7 +51,6 @@ CONFIG_NF_CONNTRACK_FTP=m CONFIG_NF_CONNTRACK_IRC=m CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_BLK_DEV_LOOP=y diff --git a/arch/powerpc/configs/holly_defconfig b/arch/powerpc/configs/holly_defconfig index 067f433c8f5e..271daff47d1d 100644 --- a/arch/powerpc/configs/holly_defconfig +++ b/arch/powerpc/configs/holly_defconfig @@ -13,7 +13,6 @@ CONFIG_EMBEDDED6xx=y CONFIG_PPC_HOLLY=y CONFIG_GEN_RTC=y CONFIG_BINFMT_MISC=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=ttyS0,115200" # CONFIG_SECCOMP is not set CONFIG_NET=y diff --git a/arch/powerpc/configs/linkstation_defconfig b/arch/powerpc/configs/linkstation_defconfig index ea59f3d146df..d4be64f190ff 100644 --- a/arch/powerpc/configs/linkstation_defconfig +++ b/arch/powerpc/configs/linkstation_defconfig @@ -37,7 +37,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NETFILTER_XT_MATCH_MAC=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m diff --git a/arch/powerpc/configs/mpc512x_defconfig b/arch/powerpc/configs/mpc512x_defconfig index e39346b3dc3b..e75d3f3060c9 100644 --- a/arch/powerpc/configs/mpc512x_defconfig +++ b/arch/powerpc/configs/mpc512x_defconfig @@ -47,7 +47,6 @@ CONFIG_MTD_UBI=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=1 CONFIG_BLK_DEV_RAM_SIZE=8192 -CONFIG_BLK_DEV_RAM_DAX=y CONFIG_EEPROM_AT24=y CONFIG_EEPROM_AT25=y CONFIG_SCSI=y diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index be125729635c..95d43f8a3869 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -19,7 +19,6 @@ CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y -CONFIG_SBC834x=y CONFIG_ASP834x=y CONFIG_QE_GPIO=y CONFIG_MATH_EMULATION=y diff --git a/arch/powerpc/configs/mvme5100_defconfig b/arch/powerpc/configs/mvme5100_defconfig index 0a0d046fc445..1fed6be95d53 100644 --- a/arch/powerpc/configs/mvme5100_defconfig +++ b/arch/powerpc/configs/mvme5100_defconfig @@ -20,10 +20,9 @@ CONFIG_EMBEDDED6xx=y CONFIG_MVME5100=y CONFIG_KVM_GUEST=y CONFIG_HZ_100=y +CONFIG_CMDLINE="console=ttyS0,9600 ip=dhcp root=/dev/nfs" # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set # CONFIG_COMPACTION is not set -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="console=ttyS0,9600 ip=dhcp root=/dev/nfs" CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -46,7 +45,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NETFILTER_XT_MATCH_MAC=m CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m CONFIG_NETFILTER_XT_MATCH_STATE=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_FILTER=m CONFIG_IP_NF_TARGET_REJECT=m diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 08b7f4cef243..af9af03059e4 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -58,7 +58,6 @@ CONFIG_BLK_DEV_RAM_SIZE=16384 CONFIG_EEPROM_LEGACY=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y -CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 05e325ca3fbd..665a8d7cded0 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -75,7 +75,6 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -90,13 +89,6 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_IP_DCCP=m -CONFIG_IRDA=m -CONFIG_IRLAN=m -CONFIG_IRNET=m -CONFIG_IRCOMM=m -CONFIG_IRDA_CACHE_LAST_LSAP=y -CONFIG_IRDA_FAST_RR=y -CONFIG_IRTTY_SIR=m CONFIG_BT=m CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 2de9aadf0f50..cf30fc24413b 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -64,7 +64,6 @@ CONFIG_HWPOISON_INJECT=m CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_PPC_64K_PAGES=y -CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y CONFIG_PM=y CONFIG_HOTPLUG_PCI=y @@ -246,7 +245,6 @@ CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_INFINIBAND_MTHCA=m -CONFIG_INFINIBAND_CXGB3=m CONFIG_INFINIBAND_CXGB4=m CONFIG_MLX4_INFINIBAND=m CONFIG_INFINIBAND_IPOIB=m diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig index 25f6c91e843a..7e48693775f4 100644 --- a/arch/powerpc/configs/ppc40x_defconfig +++ b/arch/powerpc/configs/ppc40x_defconfig @@ -20,9 +20,6 @@ CONFIG_INET=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_INET_XFRM_MODE_TRANSPORT is not set -# CONFIG_INET_XFRM_MODE_TUNNEL is not set -# CONFIG_INET_XFRM_MODE_BEET is not set CONFIG_CONNECTOR=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index 8d7e3e98856d..48759656a067 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -268,7 +268,6 @@ CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_INFINIBAND_MTHCA=m -CONFIG_INFINIBAND_CXGB3=m CONFIG_INFINIBAND_CXGB4=m CONFIG_MLX4_INFINIBAND=m CONFIG_INFINIBAND_IPOIB=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index feb5d47d8d1e..5e6f92ba3210 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -53,7 +53,6 @@ CONFIG_MPC836x_MDS=y CONFIG_MPC836x_RDK=y CONFIG_MPC837x_MDS=y CONFIG_MPC837x_RDB=y -CONFIG_SBC834x=y CONFIG_ASP834x=y CONFIG_PPC_86xx=y CONFIG_MPC8641_HPCN=y @@ -187,7 +186,6 @@ CONFIG_NETFILTER_XT_MATCH_STRING=m CONFIG_NETFILTER_XT_MATCH_TCPMSS=m CONFIG_NETFILTER_XT_MATCH_TIME=m CONFIG_NETFILTER_XT_MATCH_U32=m -CONFIG_NF_CONNTRACK_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m CONFIG_IP_NF_MATCH_ECN=m @@ -203,7 +201,6 @@ CONFIG_IP_NF_SECURITY=m CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m -CONFIG_NF_CONNTRACK_IPV6=m CONFIG_IP6_NF_IPTABLES=m CONFIG_IP6_NF_MATCH_AH=m CONFIG_IP6_NF_MATCH_EUI64=m @@ -241,7 +238,6 @@ CONFIG_BRIDGE_EBT_SNAT=m CONFIG_BRIDGE_EBT_LOG=m CONFIG_BRIDGE_EBT_NFLOG=m CONFIG_IP_DCCP=m -CONFIG_NET_DCCPPROBE=m CONFIG_TIPC=m CONFIG_ATM=m CONFIG_ATM_CLIP=m @@ -251,7 +247,6 @@ CONFIG_BRIDGE=m CONFIG_VLAN_8021Q=m CONFIG_DECNET=m CONFIG_DECNET_ROUTER=y -CONFIG_IPX=m CONFIG_ATALK=m CONFIG_DEV_APPLETALK=m CONFIG_IPDDP=m @@ -297,26 +292,6 @@ CONFIG_NET_ACT_NAT=m CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m -CONFIG_IRDA=m -CONFIG_IRLAN=m -CONFIG_IRNET=m -CONFIG_IRCOMM=m -CONFIG_IRDA_CACHE_LAST_LSAP=y -CONFIG_IRDA_FAST_RR=y -CONFIG_IRTTY_SIR=m -CONFIG_KINGSUN_DONGLE=m -CONFIG_KSDAZZLE_DONGLE=m -CONFIG_KS959_DONGLE=m -CONFIG_USB_IRDA=m -CONFIG_SIGMATEL_FIR=m -CONFIG_NSC_FIR=m -CONFIG_WINBOND_FIR=m -CONFIG_TOSHIBA_FIR=m -CONFIG_SMC_IRCC_FIR=m -CONFIG_ALI_FIR=m -CONFIG_VLSI_FIR=m -CONFIG_VIA_FIR=m -CONFIG_MCS_FIR=m CONFIG_BT=m CONFIG_BT_RFCOMM=m CONFIG_BT_RFCOMM_TTY=y @@ -332,7 +307,6 @@ CONFIG_BT_HCIBFUSB=m CONFIG_BT_HCIDTL1=m CONFIG_BT_HCIBT3C=m CONFIG_BT_HCIBLUECARD=m -CONFIG_BT_HCIBTUART=m CONFIG_BT_HCIVHCI=m CONFIG_CFG80211=m CONFIG_MAC80211=m @@ -366,7 +340,6 @@ CONFIG_EEPROM_93CX6=m CONFIG_RAID_ATTRS=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m @@ -663,7 +636,6 @@ CONFIG_I2C_MPC=m CONFIG_I2C_PCA_PLATFORM=m CONFIG_I2C_SIMTEC=m CONFIG_I2C_PARPORT=m -CONFIG_I2C_PARPORT_LIGHT=m CONFIG_I2C_TINY_USB=m CONFIG_I2C_PCA_ISA=m CONFIG_I2C_STUB=m @@ -676,7 +648,6 @@ CONFIG_W1_SLAVE_THERM=m CONFIG_W1_SLAVE_SMEM=m CONFIG_W1_SLAVE_DS2433=m CONFIG_W1_SLAVE_DS2433_CRC=y -CONFIG_W1_SLAVE_DS2760=m CONFIG_APM_POWER=m CONFIG_BATTERY_PMU=m CONFIG_HWMON=m @@ -1065,15 +1036,6 @@ CONFIG_CIFS_UPCALL=y CONFIG_CIFS_XATTR=y CONFIG_CIFS_POSIX=y CONFIG_CIFS_DFS_UPCALL=y -CONFIG_NCP_FS=m -CONFIG_NCPFS_PACKET_SIGNING=y -CONFIG_NCPFS_IOCTL_LOCKING=y -CONFIG_NCPFS_STRONG=y -CONFIG_NCPFS_NFS_NS=y -CONFIG_NCPFS_OS2_NS=y -CONFIG_NCPFS_SMALLDOS=y -CONFIG_NCPFS_NLS=y -CONFIG_NCPFS_EXTRAS=y CONFIG_CODA_FS=m CONFIG_9P_FS=m CONFIG_NLS_DEFAULT="utf8" @@ -1117,7 +1079,6 @@ CONFIG_NLS_KOI8_U=m CONFIG_DEBUG_INFO=y CONFIG_UNUSED_SYMBOLS=y CONFIG_HEADERS_INSTALL=y -CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_OBJECTS=y diff --git a/arch/powerpc/configs/ps3_defconfig b/arch/powerpc/configs/ps3_defconfig index 81b55c880fc3..142f1321fa58 100644 --- a/arch/powerpc/configs/ps3_defconfig +++ b/arch/powerpc/configs/ps3_defconfig @@ -34,8 +34,6 @@ CONFIG_KEXEC=y # CONFIG_SPARSEMEM_VMEMMAP is not set # CONFIG_COMPACTION is not set CONFIG_SCHED_SMT=y -CONFIG_CMDLINE_BOOL=y -CONFIG_CMDLINE="" CONFIG_PM=y CONFIG_PM_DEBUG=y # CONFIG_SECCOMP is not set diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index dfa4a726333b..d5dece981c02 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -57,7 +57,6 @@ CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_PPC_64K_PAGES=y -CONFIG_PPC_SUBPAGE_PROT=y CONFIG_SCHED_SMT=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_RPA=m @@ -94,6 +93,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_VIRTIO_BLK=m +CONFIG_BLK_DEV_NVME=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y @@ -224,7 +224,6 @@ CONFIG_INFINIBAND=m CONFIG_INFINIBAND_USER_MAD=m CONFIG_INFINIBAND_USER_ACCESS=m CONFIG_INFINIBAND_MTHCA=m -CONFIG_INFINIBAND_CXGB3=m CONFIG_INFINIBAND_CXGB4=m CONFIG_MLX4_INFINIBAND=m CONFIG_INFINIBAND_IPOIB=m diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index ad6739ac63dc..b806a5d3a695 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -45,7 +45,6 @@ CONFIG_IRQ_ALL_CPUS=y CONFIG_NUMA=y CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=tty0 console=hvc0 ipr.fast_reboot=1 quiet" # CONFIG_SECCOMP is not set # CONFIG_PPC_MEM_KEYS is not set diff --git a/arch/powerpc/configs/storcenter_defconfig b/arch/powerpc/configs/storcenter_defconfig index b964084e4056..47dcfaddc1ac 100644 --- a/arch/powerpc/configs/storcenter_defconfig +++ b/arch/powerpc/configs/storcenter_defconfig @@ -12,7 +12,6 @@ CONFIG_EMBEDDED6xx=y CONFIG_STORCENTER=y CONFIG_HZ_100=y CONFIG_BINFMT_MISC=y -CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=ttyS0,115200" # CONFIG_SECCOMP is not set CONFIG_NET=y diff --git a/arch/powerpc/crypto/crc32-vpmsum_core.S b/arch/powerpc/crypto/crc32-vpmsum_core.S index c3524eba4d0d..a16a717c809c 100644 --- a/arch/powerpc/crypto/crc32-vpmsum_core.S +++ b/arch/powerpc/crypto/crc32-vpmsum_core.S @@ -19,7 +19,7 @@ * We then use fixed point Barrett reduction to compute a mod n over GF(2) * for n = CRC using POWER8 instructions. We use x = 32. * - * http://en.wikipedia.org/wiki/Barrett_reduction + * https://en.wikipedia.org/wiki/Barrett_reduction * * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM */ diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 2d444d09b553..90cd5c53af66 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -7,5 +7,6 @@ generic-y += export.h generic-y += kvm_types.h generic-y += local64.h generic-y += mcs_spinlock.h +generic-y += qrwlock.h generic-y += vtime.h generic-y += early_ioremap.h diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 7d81e86a1e5d..de14b1a34d56 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -98,7 +98,7 @@ unsigned long __init early_init(unsigned long dt_ptr); void __init machine_init(u64 dt_ptr); #endif long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs); -notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs); +notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs, long scv); notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr); notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr); @@ -144,13 +144,13 @@ void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ -extern s32 patch__call_flush_count_cache; +extern s32 patch__call_flush_branch_caches; extern s32 patch__flush_count_cache_return; extern s32 patch__flush_link_stack_return; extern s32 patch__call_kvm_flush_link_stack; extern s32 patch__memset_nocache, patch__memcpy_nocache; -extern long flush_count_cache; +extern long flush_branch_caches; extern long kvm_flush_link_stack; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 0311c3c42960..8a55eb8cc97b 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -191,6 +191,34 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v) #define atomic_xchg(v, new) (xchg(&((v)->counter), new)) #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new)) +/* + * Don't want to override the generic atomic_try_cmpxchg_acquire, because + * we add a lock hint to the lwarx, which may not be wanted for the + * _acquire case (and is not used by the other _acquire variants so it + * would be a surprise). + */ +static __always_inline bool +atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new) +{ + int r, o = *old; + + __asm__ __volatile__ ( +"1:\t" PPC_LWARX(%0,0,%2,1) " # atomic_try_cmpxchg_acquire \n" +" cmpw 0,%0,%3 \n" +" bne- 2f \n" +" stwcx. %4,0,%2 \n" +" bne- 1b \n" +"\t" PPC_ACQUIRE_BARRIER " \n" +"2: \n" + : "=&r" (r), "+m" (v->counter) + : "r" (&v->counter), "r" (o), "r" (new) + : "cr0", "memory"); + + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} + /** * atomic_fetch_add_unless - add unless the number is a given value * @v: pointer of type atomic_t diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 123adcefd40f..f53c42380832 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -7,6 +7,10 @@ #include <asm/asm-const.h> +#ifndef __ASSEMBLY__ +#include <asm/ppc-opcode.h> +#endif + /* * Memory barrier. * The sync instruction guarantees that all memory accesses initiated @@ -76,6 +80,22 @@ do { \ ___p1; \ }) +#ifdef CONFIG_PPC64 +#define smp_cond_load_relaxed(ptr, cond_expr) ({ \ + typeof(ptr) __PTR = (ptr); \ + __unqual_scalar_typeof(*ptr) VAL; \ + VAL = READ_ONCE(*__PTR); \ + if (unlikely(!(cond_expr))) { \ + spin_begin(); \ + do { \ + VAL = READ_ONCE(*__PTR); \ + } while (!(cond_expr)); \ + spin_end(); \ + } \ + (typeof(*ptr))VAL; \ +}) +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #define NOSPEC_BARRIER_SLOT nop #elif defined(CONFIG_PPC_FSL_BOOK3E) @@ -97,6 +117,15 @@ do { \ #define barrier_nospec() #endif /* CONFIG_PPC_BARRIER_NOSPEC */ +/* + * pmem_wmb() ensures that all stores for which the modification + * are written to persistent storage by preceding dcbfps/dcbstps + * instructions have updated persistent storage before any data + * access or data transfer caused by subsequent instructions is + * initiated. + */ +#define pmem_wmb() __asm__ __volatile__(PPC_PHWSYNC ::: "memory") + #include <asm-generic/barrier.h> #endif /* _ASM_POWERPC_BARRIER_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 224912432821..36443cda8dcf 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -184,17 +184,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); */ #define VMALLOC_OFFSET (0x1000000) /* 16M */ -/* - * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules - * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear - * memory shall not share segments. - */ -#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES) -#define VMALLOC_START ((ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \ - ~(VMALLOC_OFFSET - 1)) -#else #define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))) -#endif #ifdef CONFIG_KASAN_VMALLOC #define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT) @@ -202,6 +192,11 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot); #define VMALLOC_END ioremap_bot #endif +#ifdef CONFIG_STRICT_KERNEL_RWX +#define MODULES_END ALIGN_DOWN(PAGE_OFFSET, SZ_256M) +#define MODULES_VADDR (MODULES_END - SZ_256M) +#endif + #ifndef __ASSEMBLY__ #include <linux/sched.h> #include <linux/threads.h> diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 3f9ae3585ab9..082b98808701 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -34,11 +34,11 @@ #define H_PUD_TABLE_SIZE (sizeof(pud_t) << H_PUD_INDEX_SIZE) #define H_PGD_TABLE_SIZE (sizeof(pgd_t) << H_PGD_INDEX_SIZE) -#define H_PAGE_F_GIX_SHIFT 53 -#define H_PAGE_F_SECOND _RPAGE_RPN44 /* HPTE is in 2ndary HPTEG */ -#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) -#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ -#define H_PAGE_HASHPTE _RPAGE_RSV2 /* software: PTE & hash are busy */ +#define H_PAGE_F_GIX_SHIFT _PAGE_PA_MAX +#define H_PAGE_F_SECOND _RPAGE_PKEY_BIT0 /* HPTE is in 2ndary HPTEG */ +#define H_PAGE_F_GIX (_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41) +#define H_PAGE_BUSY _RPAGE_RSV1 +#define H_PAGE_HASHPTE _RPAGE_PKEY_BIT4 /* PTE flags to conserve for HPTE identification */ #define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \ @@ -57,11 +57,12 @@ #define H_PMD_FRAG_NR (PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT) /* memory key bits, only 8 keys supported */ -#define H_PTE_PKEY_BIT0 0 -#define H_PTE_PKEY_BIT1 0 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#define H_PTE_PKEY_BIT4 0 +#define H_PTE_PKEY_BIT3 0 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT1 + /* * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range() diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 0729c034e56f..f20de1149ebe 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -32,15 +32,15 @@ */ #define H_PAGE_COMBO _RPAGE_RPN0 /* this is a combo 4k page */ #define H_PAGE_4K_PFN _RPAGE_RPN1 /* PFN is for a single 4k page */ -#define H_PAGE_BUSY _RPAGE_RPN44 /* software: PTE & hash are busy */ +#define H_PAGE_BUSY _RPAGE_RSV1 /* software: PTE & hash are busy */ #define H_PAGE_HASHPTE _RPAGE_RPN43 /* PTE has associated HPTE */ /* memory key bits. */ -#define H_PTE_PKEY_BIT0 _RPAGE_RSV1 -#define H_PTE_PKEY_BIT1 _RPAGE_RSV2 -#define H_PTE_PKEY_BIT2 _RPAGE_RSV3 -#define H_PTE_PKEY_BIT3 _RPAGE_RSV4 -#define H_PTE_PKEY_BIT4 _RPAGE_RSV5 +#define H_PTE_PKEY_BIT4 _RPAGE_PKEY_BIT4 +#define H_PTE_PKEY_BIT3 _RPAGE_PKEY_BIT3 +#define H_PTE_PKEY_BIT2 _RPAGE_PKEY_BIT2 +#define H_PTE_PKEY_BIT1 _RPAGE_PKEY_BIT1 +#define H_PTE_PKEY_BIT0 _RPAGE_PKEY_BIT0 /* * We need to differentiate between explicit huge page and THP huge diff --git a/arch/powerpc/include/asm/book3s/64/hash-pkey.h b/arch/powerpc/include/asm/book3s/64/hash-pkey.h new file mode 100644 index 000000000000..795010897e5d --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/hash-pkey.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H +#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H + +static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT1 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT3 : 0x0UL) | + ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL)); +} + +static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL)); +} + +static inline u16 hash__pte_to_pkey_bits(u64 pteflags) +{ + return (((pteflags & H_PTE_PKEY_BIT4) ? 0x10 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT3) ? 0x8 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT1) ? 0x2 : 0x0UL) | + ((pteflags & H_PTE_PKEY_BIT0) ? 0x1 : 0x0UL)); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/kexec.h b/arch/powerpc/include/asm/book3s/64/kexec.h new file mode 100644 index 000000000000..6b5c3a248ba2 --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/kexec.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_ +#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_ + + +#define reset_sprs reset_sprs +static inline void reset_sprs(void) +{ + if (cpu_has_feature(CPU_FTR_ARCH_206)) { + mtspr(SPRN_AMR, 0); + mtspr(SPRN_UAMOR, 0); + } + + if (cpu_has_feature(CPU_FTR_ARCH_207S)) { + mtspr(SPRN_IAMR, 0); + } + + /* Do we need isync()? We are going via a kexec reset */ + isync(); +} + +#endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 3fa1b962dc27..93d18da5e7ec 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -86,8 +86,8 @@ #define HPTE_R_PP0 ASM_CONST(0x8000000000000000) #define HPTE_R_TS ASM_CONST(0x4000000000000000) #define HPTE_R_KEY_HI ASM_CONST(0x3000000000000000) -#define HPTE_R_KEY_BIT0 ASM_CONST(0x2000000000000000) -#define HPTE_R_KEY_BIT1 ASM_CONST(0x1000000000000000) +#define HPTE_R_KEY_BIT4 ASM_CONST(0x2000000000000000) +#define HPTE_R_KEY_BIT3 ASM_CONST(0x1000000000000000) #define HPTE_R_RPN_SHIFT 12 #define HPTE_R_RPN ASM_CONST(0x0ffffffffffff000) #define HPTE_R_RPN_3_0 ASM_CONST(0x01fffffffffff000) @@ -103,8 +103,8 @@ #define HPTE_R_R ASM_CONST(0x0000000000000100) #define HPTE_R_KEY_LO ASM_CONST(0x0000000000000e00) #define HPTE_R_KEY_BIT2 ASM_CONST(0x0000000000000800) -#define HPTE_R_KEY_BIT3 ASM_CONST(0x0000000000000400) -#define HPTE_R_KEY_BIT4 ASM_CONST(0x0000000000000200) +#define HPTE_R_KEY_BIT1 ASM_CONST(0x0000000000000400) +#define HPTE_R_KEY_BIT0 ASM_CONST(0x0000000000000200) #define HPTE_R_KEY (HPTE_R_KEY_LO | HPTE_R_KEY_HI) #define HPTE_V_1TB_SEG ASM_CONST(0x4000000000000000) @@ -793,7 +793,7 @@ static inline unsigned long get_vsid(unsigned long context, unsigned long ea, } /* - * For kernel space, we use context ids as below + * For kernel space, we use context ids as * below. Range is 512TB per context. * * 0x00001 - [ 0xc000000000000000 - 0xc001ffffffffffff] diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 5393a535240c..55442d45c597 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -82,6 +82,11 @@ extern unsigned int mmu_pid_bits; /* Base PID to allocate from */ extern unsigned int mmu_base_pid; +/* + * memory block size used with radix translation. + */ +extern unsigned int __ro_after_init radix_mem_block_size; + #define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) #define PRTB_ENTRIES (1ul << mmu_pid_bits) @@ -209,6 +214,12 @@ extern int mmu_io_psize; void mmu_early_init_devtree(void); void hash__early_init_devtree(void); void radix__early_init_devtree(void); +#ifdef CONFIG_PPC_MEM_KEYS +void pkey_early_init_devtree(void); +#else +static inline void pkey_early_init_devtree(void) {} +#endif + extern void hash__early_init_mmu(void); extern void radix__early_init_mmu(void); static inline void __init early_init_mmu(void) diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 69c5b051734f..e1af0b394ceb 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -107,9 +107,23 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) return pud; } +static inline void __pud_free(pud_t *pud) +{ + struct page *page = virt_to_page(pud); + + /* + * Early pud pages allocated via memblock allocator + * can't be directly freed to slab + */ + if (PageReserved(page)) + free_reserved_page(page); + else + kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); +} + static inline void pud_free(struct mm_struct *mm, pud_t *pud) { - kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud); + return __pud_free(pud); } static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 25c3cb8272c0..6de56c3b33c4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -20,9 +20,13 @@ #define _PAGE_RW (_PAGE_READ | _PAGE_WRITE) #define _PAGE_RWX (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) #define _PAGE_PRIVILEGED 0x00008 /* kernel access only */ -#define _PAGE_SAO 0x00010 /* Strong access order */ + +#define _PAGE_CACHE_CTL 0x00030 /* Bits for the folowing cache modes */ + /* No bits set is normal cacheable memory */ + /* 0x00010 unused, is SAO bit on radix POWER9 */ #define _PAGE_NON_IDEMPOTENT 0x00020 /* non idempotent memory */ #define _PAGE_TOLERANT 0x00030 /* tolerant memory, cache inhibited */ + #define _PAGE_DIRTY 0x00080 /* C: page changed */ #define _PAGE_ACCESSED 0x00100 /* R: page referenced */ /* @@ -32,11 +36,13 @@ #define _RPAGE_SW1 0x00800 #define _RPAGE_SW2 0x00400 #define _RPAGE_SW3 0x00200 -#define _RPAGE_RSV1 0x1000000000000000UL -#define _RPAGE_RSV2 0x0800000000000000UL -#define _RPAGE_RSV3 0x0400000000000000UL -#define _RPAGE_RSV4 0x0200000000000000UL -#define _RPAGE_RSV5 0x00040UL +#define _RPAGE_RSV1 0x00040UL + +#define _RPAGE_PKEY_BIT4 0x1000000000000000UL +#define _RPAGE_PKEY_BIT3 0x0800000000000000UL +#define _RPAGE_PKEY_BIT2 0x0400000000000000UL +#define _RPAGE_PKEY_BIT1 0x0200000000000000UL +#define _RPAGE_PKEY_BIT0 0x0100000000000000UL #define _PAGE_PTE 0x4000000000000000UL /* distinguishes PTEs from pointers */ #define _PAGE_PRESENT 0x8000000000000000UL /* pte contains a translation */ @@ -58,13 +64,12 @@ */ #define _RPAGE_RPN0 0x01000 #define _RPAGE_RPN1 0x02000 -#define _RPAGE_RPN44 0x0100000000000000UL #define _RPAGE_RPN43 0x0080000000000000UL #define _RPAGE_RPN42 0x0040000000000000UL #define _RPAGE_RPN41 0x0020000000000000UL /* Max physical address bit as per radix table */ -#define _RPAGE_PA_MAX 57 +#define _RPAGE_PA_MAX 56 /* * Max physical address bit we will use for now. @@ -125,8 +130,6 @@ _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE | \ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP) -#define H_PTE_PKEY (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \ - H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4) /* * We define 2 sets of base prot bits, one for basic pages (ie, * cacheable kernel and user pages) and one for non cacheable @@ -825,8 +828,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, return hash__set_pte_at(mm, addr, ptep, pte, percpu); } -#define _PAGE_CACHE_CTL (_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT) - #define pgprot_noncached pgprot_noncached static inline pgprot_t pgprot_noncached(pgprot_t prot) { diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h new file mode 100644 index 000000000000..b7d9f4267bcd --- /dev/null +++ b/arch/powerpc/include/asm/book3s/64/pkeys.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _ASM_POWERPC_BOOK3S_64_PKEYS_H +#define _ASM_POWERPC_BOOK3S_64_PKEYS_H + +#include <asm/book3s/64/hash-pkey.h> + +extern u64 __ro_after_init default_uamor; + +static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) +{ + if (!mmu_has_feature(MMU_FTR_PKEY)) + return 0x0UL; + + if (radix_enabled()) + BUG(); + return hash__vmflag_to_pte_pkey_bits(vm_flags); +} + +static inline u16 pte_to_pkey_bits(u64 pteflags) +{ + if (radix_enabled()) + BUG(); + return hash__pte_to_pkey_bits(pteflags); +} + +#endif /*_ASM_POWERPC_KEYS_H */ diff --git a/arch/powerpc/include/asm/book3s/64/radix-4k.h b/arch/powerpc/include/asm/book3s/64/radix-4k.h index d5f5ab73dc7f..035ceecd6d67 100644 --- a/arch/powerpc/include/asm/book3s/64/radix-4k.h +++ b/arch/powerpc/include/asm/book3s/64/radix-4k.h @@ -11,7 +11,7 @@ #define RADIX_PGD_INDEX_SIZE 13 // size: 8B << 13 = 64KB, maps 2^13 x 512GB = 4PB /* - * One fragment per per page + * One fragment per page */ #define RADIX_PTE_FRAG_SIZE_SHIFT (RADIX_PTE_INDEX_SIZE + 3) #define RADIX_PTE_FRAG_NR (PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT) diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h index ca8db193ae38..94439e0cefc9 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h @@ -2,10 +2,25 @@ #ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H #define _ASM_POWERPC_TLBFLUSH_RADIX_H +#include <asm/hvcall.h> + struct vm_area_struct; struct mm_struct; struct mmu_gather; +static inline u64 psize_to_rpti_pgsize(unsigned long psize) +{ + if (psize == MMU_PAGE_4K) + return H_RPTI_PAGE_4K; + if (psize == MMU_PAGE_64K) + return H_RPTI_PAGE_64K; + if (psize == MMU_PAGE_2M) + return H_RPTI_PAGE_2M; + if (psize == MMU_PAGE_1G) + return H_RPTI_PAGE_1G; + return H_RPTI_PAGE_ALL; +} + static inline int mmu_get_ap(int psize) { return mmu_psize_defs[psize].ap; diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index de600b915a3c..54764c6e922d 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -6,6 +6,7 @@ #include <linux/mm.h> #include <asm/cputable.h> +#include <asm/cpu_has_feature.h> #ifdef CONFIG_PPC_BOOK3S_64 /* diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index bac2252c839e..fdddb822d564 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -191,14 +191,14 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_SPURR LONG_ASM_CONST(0x0000000001000000) #define CPU_FTR_DSCR LONG_ASM_CONST(0x0000000002000000) #define CPU_FTR_VSX LONG_ASM_CONST(0x0000000004000000) -#define CPU_FTR_SAO LONG_ASM_CONST(0x0000000008000000) +// Free LONG_ASM_CONST(0x0000000008000000) #define CPU_FTR_CP_USE_DCBTZ LONG_ASM_CONST(0x0000000010000000) #define CPU_FTR_UNALIGNED_LD_STD LONG_ASM_CONST(0x0000000020000000) #define CPU_FTR_ASYM_SMT LONG_ASM_CONST(0x0000000040000000) #define CPU_FTR_STCX_CHECKS_ADDRESS LONG_ASM_CONST(0x0000000080000000) #define CPU_FTR_POPCNTB LONG_ASM_CONST(0x0000000100000000) #define CPU_FTR_POPCNTD LONG_ASM_CONST(0x0000000200000000) -#define CPU_FTR_PKEY LONG_ASM_CONST(0x0000000400000000) +/* LONG_ASM_CONST(0x0000000400000000) Free */ #define CPU_FTR_VMX_COPY LONG_ASM_CONST(0x0000000800000000) #define CPU_FTR_TM LONG_ASM_CONST(0x0000001000000000) #define CPU_FTR_CFAR LONG_ASM_CONST(0x0000002000000000) @@ -214,6 +214,7 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_P9_TLBIE_ERAT_BUG LONG_ASM_CONST(0x0001000000000000) #define CPU_FTR_P9_RADIX_PREFETCH_BUG LONG_ASM_CONST(0x0002000000000000) #define CPU_FTR_ARCH_31 LONG_ASM_CONST(0x0004000000000000) +#define CPU_FTR_DAWR1 LONG_ASM_CONST(0x0008000000000000) #ifndef __ASSEMBLY__ @@ -435,32 +436,32 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO | CPU_FTR_ASYM_SMT | \ + CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | \ - CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX | CPU_FTR_PKEY) + CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX ) #define CPU_FTRS_POWER8 (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO | \ + CPU_FTR_DSCR | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \ - CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_PKEY) + CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP ) #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG) #define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\ CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO | \ + CPU_FTR_DSCR | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ - CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ - CPU_FTR_P9_TLBIE_STQ_BUG | CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR) + CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_P9_TLBIE_STQ_BUG | \ + CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR) #define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG) #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \ CPU_FTR_P9_RADIX_PREFETCH_BUG | \ @@ -473,12 +474,12 @@ static inline void cpu_feature_keys_init(void) { } CPU_FTR_MMCRA | CPU_FTR_SMT | \ CPU_FTR_COHERENT_ICACHE | \ CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \ - CPU_FTR_DSCR | CPU_FTR_SAO | \ + CPU_FTR_DSCR | \ CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \ CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \ CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \ - CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \ - CPU_FTR_ARCH_31) + CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31 | \ + CPU_FTR_DAWR | CPU_FTR_DAWR1) #define CPU_FTRS_CELL (CPU_FTR_LWSYNC | \ CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \ CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \ @@ -628,9 +629,10 @@ enum { /* * Maximum number of hw breakpoint supported on powerpc. Number of - * breakpoints supported by actual hw might be less than this. + * breakpoints supported by actual hw might be less than this, which + * is decided at run time in nr_wp_slots(). */ -#define HBP_NUM_MAX 1 +#define HBP_NUM_MAX 2 #endif /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 0fccd5ea1e9a..ed75d1c318e3 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -36,6 +36,8 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct) return mulhdu((__force u64) ct, __cputime_usec_factor); } +#define cputime_to_nsecs(cputime) tb_to_ns((__force u64)cputime) + /* * PPC64 uses PACA which is task independent for storing accounting data while * PPC32 uses struct thread_info, therefore at task switch the accounting data @@ -65,7 +67,7 @@ static inline void arch_vtime_task_switch(struct task_struct *prev) /* * account_cpu_user_entry/exit runs "unreconciled", so can't trace, - * can't use use get_paca() + * can't use get_paca() */ static notrace inline void account_cpu_user_entry(void) { diff --git a/arch/powerpc/include/asm/crashdump-ppc64.h b/arch/powerpc/include/asm/crashdump-ppc64.h new file mode 100644 index 000000000000..68d9717cc5ee --- /dev/null +++ b/arch/powerpc/include/asm/crashdump-ppc64.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_CRASHDUMP_PPC64_H +#define _ASM_POWERPC_CRASHDUMP_PPC64_H + +/* + * Backup region - first 64KB of System RAM + * + * If ever the below macros are to be changed, please be judicious. + * The implicit assumptions are: + * - start, end & size are less than UINT32_MAX. + * - start & size are at least 8 byte aligned. + * + * For implementation details: arch/powerpc/purgatory/trampoline_64.S + */ +#define BACKUP_SRC_START 0 +#define BACKUP_SRC_END 0xffff +#define BACKUP_SRC_SIZE (BACKUP_SRC_END - BACKUP_SRC_START + 1) + +#endif /* __ASM_POWERPC_CRASHDUMP_PPC64_H */ diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h index 4ce6808deed3..3e9da22a2779 100644 --- a/arch/powerpc/include/asm/dbell.h +++ b/arch/powerpc/include/asm/dbell.h @@ -11,8 +11,10 @@ #include <linux/smp.h> #include <linux/threads.h> +#include <asm/cputhreads.h> #include <asm/ppc-opcode.h> #include <asm/feature-fixups.h> +#include <asm/kvm_ppc.h> #define PPC_DBELL_MSG_BRDCAST (0x04000000) #define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36)) @@ -87,9 +89,6 @@ static inline void ppc_msgsync(void) #endif /* CONFIG_PPC_BOOK3S */ -extern void doorbell_global_ipi(int cpu); -extern void doorbell_core_ipi(int cpu); -extern int doorbell_try_core_ipi(int cpu); extern void doorbell_exception(struct pt_regs *regs); static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) @@ -100,4 +99,63 @@ static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag) _ppc_msgsnd(msg); } +#ifdef CONFIG_SMP + +/* + * Doorbells must only be used if CPU_FTR_DBELL is available. + * msgsnd is used in HV, and msgsndp is used in !HV. + * + * These should be used by platform code that is aware of restrictions. + * Other arch code should use ->cause_ipi. + * + * doorbell_global_ipi() sends a dbell to any target CPU. + * Must be used only by architectures that address msgsnd target + * by PIR/get_hard_smp_processor_id. + */ +static inline void doorbell_global_ipi(int cpu) +{ + u32 tag = get_hard_smp_processor_id(cpu); + + kvmppc_set_host_ipi(cpu); + /* Order previous accesses vs. msgsnd, which is treated as a store */ + ppc_msgsnd_sync(); + ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); +} + +/* + * doorbell_core_ipi() sends a dbell to a target CPU in the same core. + * Must be used only by architectures that address msgsnd target + * by TIR/cpu_thread_in_core. + */ +static inline void doorbell_core_ipi(int cpu) +{ + u32 tag = cpu_thread_in_core(cpu); + + kvmppc_set_host_ipi(cpu); + /* Order previous accesses vs. msgsnd, which is treated as a store */ + ppc_msgsnd_sync(); + ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); +} + +/* + * Attempt to cause a core doorbell if destination is on the same core. + * Returns 1 on success, 0 on failure. + */ +static inline int doorbell_try_core_ipi(int cpu) +{ + int this_cpu = get_cpu(); + int ret = 0; + + if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) { + doorbell_core_ipi(cpu); + ret = 1; + } + + put_cpu(); + + return ret; +} + +#endif /* CONFIG_SMP */ + #endif /* _ASM_POWERPC_DBELL_H */ diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h index 452402215e12..219559d65864 100644 --- a/arch/powerpc/include/asm/device.h +++ b/arch/powerpc/include/asm/device.h @@ -29,9 +29,6 @@ struct dev_archdata { struct iommu_table *iommu_table_base; #endif -#ifdef CONFIG_IOMMU_API - void *iommu_domain; -#endif #ifdef CONFIG_PPC64 struct pci_dn *pci_data; #endif @@ -44,6 +41,9 @@ struct dev_archdata { #ifdef CONFIG_CXL_BASE struct cxl_context *cxl_ctx; #endif +#ifdef CONFIG_PCI_IOV + void *iov_data; +#endif }; struct pdev_archdata { diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 414d209f45bb..17ccc6474ab6 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -90,13 +90,14 @@ static inline bool drmem_lmb_reserved(struct drmem_lmb *lmb) } u64 drmem_lmb_memory_max(void); -void __init walk_drmem_lmbs(struct device_node *dn, - void (*func)(struct drmem_lmb *, const __be32 **)); +int walk_drmem_lmbs(struct device_node *dn, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)); int drmem_update_dt(void); #ifdef CONFIG_PPC_PSERIES -void __init walk_drmem_lmbs_early(unsigned long node, - void (*func)(struct drmem_lmb *, const __be32 **)); +int __init +walk_drmem_lmbs_early(unsigned long node, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)); #endif static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index 964a54292b36..d5f369bcd130 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -133,7 +133,6 @@ static inline bool eeh_pe_passed(struct eeh_pe *pe) struct eeh_dev { int mode; /* EEH mode */ - int class_code; /* Class code of the device */ int bdfn; /* bdfn of device (for cfg ops) */ struct pci_controller *controller; int pe_config_addr; /* PE config address */ @@ -148,7 +147,10 @@ struct eeh_dev { struct pci_dn *pdn; /* Associated PCI device node */ struct pci_dev *pdev; /* Associated PCI device */ bool in_error; /* Error flag for edev */ + + /* VF specific properties */ struct pci_dev *physfn; /* Associated SRIOV PF */ + int vf_index; /* Index of this VF */ }; /* "fmt" must be a simple literal string */ @@ -217,18 +219,17 @@ struct eeh_ops { int (*init)(void); struct eeh_dev *(*probe)(struct pci_dev *pdev); int (*set_option)(struct eeh_pe *pe, int option); - int (*get_pe_addr)(struct eeh_pe *pe); int (*get_state)(struct eeh_pe *pe, int *delay); int (*reset)(struct eeh_pe *pe, int option); int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len); int (*configure_bridge)(struct eeh_pe *pe); int (*err_inject)(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); - int (*read_config)(struct pci_dn *pdn, int where, int size, u32 *val); - int (*write_config)(struct pci_dn *pdn, int where, int size, u32 val); + int (*read_config)(struct eeh_dev *edev, int where, int size, u32 *val); + int (*write_config)(struct eeh_dev *edev, int where, int size, u32 val); int (*next_error)(struct eeh_pe **pe); - int (*restore_config)(struct pci_dn *pdn); - int (*notify_resume)(struct pci_dn *pdn); + int (*restore_config)(struct eeh_dev *edev); + int (*notify_resume)(struct eeh_dev *edev); }; extern int eeh_subsystem_flags; @@ -282,8 +283,8 @@ struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root); struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no, int config_addr); -int eeh_add_to_parent_pe(struct eeh_dev *edev); -int eeh_rmv_from_parent_pe(struct eeh_dev *edev); +int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent); +int eeh_pe_tree_remove(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); void *eeh_pe_traverse(struct eeh_pe *root, eeh_pe_traverse_func fn, void *flag); @@ -293,8 +294,6 @@ void eeh_pe_restore_bars(struct eeh_pe *pe); const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); -struct eeh_dev *eeh_dev_init(struct pci_dn *pdn); -void eeh_dev_phb_init_dynamic(struct pci_controller *phb); void eeh_show_enabled(void); int __init eeh_ops_register(struct eeh_ops *ops); int __exit eeh_ops_unregister(const char *name); @@ -314,7 +313,6 @@ int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed); int eeh_pe_configure(struct eeh_pe *pe); int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func, unsigned long addr, unsigned long mask); -int eeh_restore_vf_config(struct pci_dn *pdn); /** * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure. @@ -340,11 +338,6 @@ static inline bool eeh_enabled(void) static inline void eeh_show_enabled(void) { } -static inline void *eeh_dev_init(struct pci_dn *pdn, void *data) -{ - return NULL; -} - static inline void eeh_dev_phb_init_dynamic(struct pci_controller *phb) { } static inline int eeh_check_failure(const volatile void __iomem *token) @@ -362,6 +355,7 @@ static inline void eeh_remove_device(struct pci_dev *dev) { } #define EEH_POSSIBLE_ERROR(val, type) (0) #define EEH_IO_ERROR_VALUE(size) (-1UL) +static inline int eeh_phb_pe_create(struct pci_controller *phb) { return 0; } #endif /* CONFIG_EEH */ #if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_EEH) diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index 57c229a86f08..53ed2ca40151 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -53,8 +53,6 @@ static inline void ppc_elf_core_copy_regs(elf_gregset_t elf_regs, } #define ELF_CORE_COPY_REGS(gregs, regs) ppc_elf_core_copy_regs(gregs, regs); -typedef elf_vrregset_t elf_fpxregset_t; - /* ELF_HWCAP yields a mask that user programs can use to figure out what instruction set this cpu supports. This could be done in userspace, but it's not easy, and we've already done it here. */ diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index d3a7e36f1402..c99ba08a408d 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -37,7 +37,7 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -/* A "hypercall" is an "sc 1" instruction. This header file file provides C +/* A "hypercall" is an "sc 1" instruction. This header file provides C * wrapper functions for the ePAPR hypervisor interface. It is inteded * for use by Linux device drivers and other operating systems. * @@ -246,7 +246,7 @@ static inline unsigned int ev_int_get_mask(unsigned int interrupt, * ev_int_eoi - signal the end of interrupt processing * @interrupt: the interrupt number * - * This function signals the end of processing for the the specified + * This function signals the end of processing for the specified * interrupt, which must be the interrupt currently in service. By * definition, this is also the highest-priority interrupt. * diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index 54a98ef7d7fe..40cdcb2fb057 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -66,14 +66,7 @@ #define EX_TLB_SRR0 (10 * 8) #define EX_TLB_SRR1 (11 * 8) #define EX_TLB_R7 (12 * 8) -#ifdef CONFIG_BOOK3E_MMU_TLB_STATS -#define EX_TLB_R8 (13 * 8) -#define EX_TLB_R9 (14 * 8) -#define EX_TLB_LR (15 * 8) -#define EX_TLB_SIZE (16 * 8) -#else #define EX_TLB_SIZE (13 * 8) -#endif #define START_EXCEPTION(label) \ .globl exc_##label##_book3e; \ @@ -110,8 +103,7 @@ exc_##label##_book3e: std r11,EX_TLB_R12(r12); \ mtspr SPRN_SPRG_TLB_EXFRAME,r14; \ std r15,EX_TLB_SRR1(r12); \ - std r16,EX_TLB_SRR0(r12); \ - TLB_MISS_PROLOG_STATS + std r16,EX_TLB_SRR0(r12); /* And these are the matching epilogs that restores things * @@ -143,7 +135,6 @@ exc_##label##_book3e: mtspr SPRN_SRR0,r15; \ ld r15,EX_TLB_R15(r12); \ mtspr SPRN_SRR1,r16; \ - TLB_MISS_RESTORE_STATS \ ld r16,EX_TLB_R16(r12); \ ld r12,EX_TLB_R12(r12); \ @@ -158,53 +149,15 @@ exc_##label##_book3e: addi r11,r13,PACA_EXTLB; \ TLB_MISS_RESTORE(r11) -#ifdef CONFIG_BOOK3E_MMU_TLB_STATS -#define TLB_MISS_PROLOG_STATS \ - mflr r10; \ - std r8,EX_TLB_R8(r12); \ - std r9,EX_TLB_R9(r12); \ - std r10,EX_TLB_LR(r12); -#define TLB_MISS_RESTORE_STATS \ - ld r16,EX_TLB_LR(r12); \ - ld r9,EX_TLB_R9(r12); \ - ld r8,EX_TLB_R8(r12); \ - mtlr r16; -#define TLB_MISS_STATS_D(name) \ - addi r9,r13,MMSTAT_DSTATS+name; \ - bl tlb_stat_inc; -#define TLB_MISS_STATS_I(name) \ - addi r9,r13,MMSTAT_ISTATS+name; \ - bl tlb_stat_inc; -#define TLB_MISS_STATS_X(name) \ - ld r8,PACA_EXTLB+EX_TLB_ESR(r13); \ - cmpdi cr2,r8,-1; \ - beq cr2,61f; \ - addi r9,r13,MMSTAT_DSTATS+name; \ - b 62f; \ -61: addi r9,r13,MMSTAT_ISTATS+name; \ -62: bl tlb_stat_inc; -#define TLB_MISS_STATS_SAVE_INFO \ - std r14,EX_TLB_ESR(r12); /* save ESR */ -#define TLB_MISS_STATS_SAVE_INFO_BOLTED \ - std r14,PACA_EXTLB+EX_TLB_ESR(r13); /* save ESR */ -#else -#define TLB_MISS_PROLOG_STATS -#define TLB_MISS_RESTORE_STATS -#define TLB_MISS_PROLOG_STATS_BOLTED -#define TLB_MISS_RESTORE_STATS_BOLTED -#define TLB_MISS_STATS_D(name) -#define TLB_MISS_STATS_I(name) -#define TLB_MISS_STATS_X(name) -#define TLB_MISS_STATS_Y(name) -#define TLB_MISS_STATS_SAVE_INFO -#define TLB_MISS_STATS_SAVE_INFO_BOLTED -#endif - #define SET_IVOR(vector_number, vector_offset) \ LOAD_REG_ADDR(r3,interrupt_base_book3e);\ ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; - +/* + * powerpc relies on return from interrupt/syscall being context synchronising + * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional + * synchronisation instructions. + */ #define RFI_TO_KERNEL \ rfi diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 47bd4ea0837d..ebe95aa04d53 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -68,6 +68,14 @@ * * The nop instructions allow us to insert one or more instructions to flush the * L1-D cache when returning to userspace or a guest. + * + * powerpc relies on return from interrupt/syscall being context synchronising + * (which hrfid, rfid, and rfscv are) to support ARCH_HAS_MEMBARRIER_SYNC_CORE + * without additional synchronisation instructions. + * + * soft-masked interrupt replay does not include a context-synchronising rfid, + * but those always return to kernel, the sync is only required when returning + * to user. */ #define RFI_FLUSH_SLOT \ RFI_FLUSH_FIXUP_SECTION; \ @@ -123,6 +131,12 @@ hrfid; \ b hrfi_flush_fallback +#define RFSCV_TO_USER \ + STF_EXIT_BARRIER_SLOT; \ + RFI_FLUSH_SLOT; \ + RFSCV; \ + b rfscv_flush_fallback + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_EXCEPTION_H */ diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 6003c2e533a0..0b295bdb201e 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -52,6 +52,7 @@ #define FW_FEATURE_PAPR_SCM ASM_CONST(0x0000002000000000) #define FW_FEATURE_ULTRAVISOR ASM_CONST(0x0000004000000000) #define FW_FEATURE_STUFF_TCE ASM_CONST(0x0000008000000000) +#define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000) #ifndef __ASSEMBLY__ @@ -71,7 +72,8 @@ enum { FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN | FW_FEATURE_HPT_RESIZE | FW_FEATURE_DRMEM_V2 | FW_FEATURE_DRC_INFO | FW_FEATURE_BLOCK_REMOVE | - FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR, + FW_FEATURE_PAPR_SCM | FW_FEATURE_ULTRAVISOR | + FW_FEATURE_RPT_INVALIDATE, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, @@ -132,6 +134,12 @@ extern int ibm_nmi_interlock_token; extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup; +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) +bool is_kvm_guest(void); +#else +static inline bool is_kvm_guest(void) { return false; } +#endif + #ifdef CONFIG_PPC_PSERIES void pseries_probe_fw_features(void); #else diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h index 29188810ba30..925cf89cbf4b 100644 --- a/arch/powerpc/include/asm/fixmap.h +++ b/arch/powerpc/include/asm/fixmap.h @@ -52,7 +52,7 @@ enum fixed_addresses { FIX_HOLE, /* reserve the top 128K for early debugging purposes */ FIX_EARLY_DEBUG_TOP = FIX_HOLE, - FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+((128*1024)/PAGE_SIZE)-1, + FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128, PAGE_SIZE)/PAGE_SIZE)-1, #ifdef CONFIG_HIGHMEM FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, diff --git a/arch/powerpc/include/asm/hardirq.h b/arch/powerpc/include/asm/hardirq.h index f1e9067bd5ac..f133b5930ae1 100644 --- a/arch/powerpc/include/asm/hardirq.h +++ b/arch/powerpc/include/asm/hardirq.h @@ -13,7 +13,6 @@ typedef struct { unsigned int pmu_irqs; unsigned int mce_exceptions; unsigned int spurious_irqs; - unsigned int hmi_exceptions; unsigned int sreset_irqs; #ifdef CONFIG_PPC_WATCHDOG unsigned int soft_nmi_irqs; diff --git a/arch/powerpc/include/asm/head-64.h b/arch/powerpc/include/asm/head-64.h index 2dabcf668292..4cb9efa2eb21 100644 --- a/arch/powerpc/include/asm/head-64.h +++ b/arch/powerpc/include/asm/head-64.h @@ -128,7 +128,7 @@ name: .if ((start) % (size) != 0); \ .error "Fixed section exception vector misalignment"; \ .endif; \ - .if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100); \ + .if ((size) != 0x20) && ((size) != 0x80) && ((size) != 0x100) && ((size) != 0x1000); \ .error "Fixed section exception vector bad size"; \ .endif; \ .if (start) < sname##_start; \ diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 551a9d4d3958..013165e62618 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -57,6 +57,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty); +void gigantic_hugetlb_cma_reserve(void) __init; #include <asm-generic/hugetlb.h> #else /* ! CONFIG_HUGETLB_PAGE */ @@ -71,6 +72,12 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, { return NULL; } + + +static inline void __init gigantic_hugetlb_cma_reserve(void) +{ +} + #endif /* CONFIG_HUGETLB_PAGE */ #endif /* _ASM_POWERPC_HUGETLB_H */ diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index e90c073e437e..fbb377055471 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -237,7 +237,7 @@ #define H_CREATE_RPT 0x1A4 #define H_REMOVE_RPT 0x1A8 #define H_REGISTER_RPAGES 0x1AC -#define H_DISABLE_AND_GETC 0x1B0 +#define H_DISABLE_AND_GET 0x1B0 #define H_ERROR_DATA 0x1B4 #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC @@ -305,7 +305,8 @@ #define H_SCM_UNBIND_ALL 0x3FC #define H_SCM_HEALTH 0x400 #define H_SCM_PERFORMANCE_STATS 0x418 -#define MAX_HCALL_OPCODE H_SCM_PERFORMANCE_STATS +#define H_RPT_INVALIDATE 0x448 +#define MAX_HCALL_OPCODE H_RPT_INVALIDATE /* Scope args for H_SCM_UNBIND_ALL */ #define H_UNBIND_SCOPE_ALL (0x1) @@ -354,9 +355,10 @@ /* Values for 2nd argument to H_SET_MODE */ #define H_SET_MODE_RESOURCE_SET_CIABR 1 -#define H_SET_MODE_RESOURCE_SET_DAWR 2 +#define H_SET_MODE_RESOURCE_SET_DAWR0 2 #define H_SET_MODE_RESOURCE_ADDR_TRANS_MODE 3 #define H_SET_MODE_RESOURCE_LE 4 +#define H_SET_MODE_RESOURCE_SET_DAWR1 5 /* Values for argument to H_SIGNAL_SYS_RESET */ #define H_SIGNAL_SYS_RESET_ALL -1 @@ -389,6 +391,37 @@ #define PROC_TABLE_RADIX 0x04 #define PROC_TABLE_GTSE 0x01 +/* + * Defines for + * H_RPT_INVALIDATE - Invalidate RPT translation lookaside information. + */ + +/* Type of translation to invalidate (type) */ +#define H_RPTI_TYPE_NESTED 0x0001 /* Invalidate nested guest partition-scope */ +#define H_RPTI_TYPE_TLB 0x0002 /* Invalidate TLB */ +#define H_RPTI_TYPE_PWC 0x0004 /* Invalidate Page Walk Cache */ +/* Invalidate Process Table Entries if H_RPTI_TYPE_NESTED is clear */ +#define H_RPTI_TYPE_PRT 0x0008 +/* Invalidate Partition Table Entries if H_RPTI_TYPE_NESTED is set */ +#define H_RPTI_TYPE_PAT 0x0008 +#define H_RPTI_TYPE_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ + H_RPTI_TYPE_PRT) +#define H_RPTI_TYPE_NESTED_ALL (H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | \ + H_RPTI_TYPE_PAT) + +/* Invalidation targets (target) */ +#define H_RPTI_TARGET_CMMU 0x01 /* All virtual processors in the partition */ +#define H_RPTI_TARGET_CMMU_LOCAL 0x02 /* Current virtual processor */ +/* All nest/accelerator agents in use by the partition */ +#define H_RPTI_TARGET_NMMU 0x04 + +/* Page size mask (page sizes) */ +#define H_RPTI_PAGE_4K 0x01 +#define H_RPTI_PAGE_64K 0x02 +#define H_RPTI_PAGE_2M 0x04 +#define H_RPTI_PAGE_1G 0x08 +#define H_RPTI_PAGE_ALL (-1UL) + #ifndef __ASSEMBLY__ #include <linux/types.h> diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index cb424799da0d..db206a7f38e2 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -9,6 +9,8 @@ #ifndef _PPC_BOOK3S_64_HW_BREAKPOINT_H #define _PPC_BOOK3S_64_HW_BREAKPOINT_H +#include <asm/cpu_has_feature.h> + #ifdef __KERNEL__ struct arch_hw_breakpoint { unsigned long address; @@ -17,7 +19,7 @@ struct arch_hw_breakpoint { u16 hw_len; /* length programmed in hw */ }; -/* Note: Don't change the the first 6 bits below as they are in the same order +/* Note: Don't change the first 6 bits below as they are in the same order * as the dabr and dabrx. */ #define HW_BRK_TYPE_READ 0x01 @@ -46,7 +48,7 @@ struct arch_hw_breakpoint { static inline int nr_wp_slots(void) { - return HBP_NUM_MAX; + return cpu_has_feature(CPU_FTR_DAWR1) ? 2 : 1; } #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/powerpc/include/asm/hydra.h b/arch/powerpc/include/asm/hydra.h index b3b0f2d020f0..ae02eb53d6ef 100644 --- a/arch/powerpc/include/asm/hydra.h +++ b/arch/powerpc/include/asm/hydra.h @@ -10,7 +10,7 @@ * * © Copyright 1995 Apple Computer, Inc. All rights reserved. * - * It's available online from http://www.cpu.lu/~mlan/ftp/MacTech.pdf + * It's available online from https://www.cpu.lu/~mlan/ftp/MacTech.pdf * You can obtain paper copies of this book from computer bookstores or by * writing Morgan Kaufmann Publishers, Inc., 340 Pine Street, Sixth Floor, San * Francisco, CA 94104. Reference ISBN 1-55860-393-X. diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4da4fcba0684..4f897993b710 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -99,6 +99,11 @@ struct trace_imc_data { */ #define IMC_TRACE_RECORD_TB1_MASK 0x3ffffffffffULL +/* + * Bit 0:1 in third DW of IMC trace record + * specifies the MSR[HV PR] values. + */ +#define IMC_TRACE_RECORD_VAL_HVPR(x) ((x) >> 62) /* * Device tree parser code detects IMC pmu support and diff --git a/arch/powerpc/include/asm/inst.h b/arch/powerpc/include/asm/inst.h index 45f3ec868258..cc73c1267572 100644 --- a/arch/powerpc/include/asm/inst.h +++ b/arch/powerpc/include/asm/inst.h @@ -122,6 +122,25 @@ static inline u64 ppc_inst_as_u64(struct ppc_inst x) #endif } +#define PPC_INST_STR_LEN sizeof("00000000 00000000") + +static inline char *__ppc_inst_as_str(char str[PPC_INST_STR_LEN], struct ppc_inst x) +{ + if (ppc_inst_prefixed(x)) + sprintf(str, "%08x %08x", ppc_inst_val(x), ppc_inst_suffix(x)); + else + sprintf(str, "%08x", ppc_inst_val(x)); + + return str; +} + +#define ppc_inst_as_str(x) \ +({ \ + char __str[PPC_INST_STR_LEN]; \ + __ppc_inst_as_str(__str, x); \ + __str; \ +}) + int probe_user_read_inst(struct ppc_inst *inst, struct ppc_inst __user *nip); diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index be85c7005fb1..d635b96c7ea6 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -27,10 +27,12 @@ #ifdef CONFIG_KASAN void kasan_early_init(void); +void kasan_mmu_init(void); void kasan_init(void); void kasan_late_init(void); #else static inline void kasan_init(void) { } +static inline void kasan_mmu_init(void) { } static inline void kasan_late_init(void) { } #endif diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index c68476818753..55d6ede30c19 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -100,15 +100,26 @@ void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_co #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_elf64_ops; -#ifdef CONFIG_IMA_KEXEC #define ARCH_HAS_KIMAGE_ARCH struct kimage_arch { + struct crash_mem *exclude_ranges; + + unsigned long backup_start; + void *backup_buf; + + unsigned long elfcorehdr_addr; + unsigned long elf_headers_sz; + void *elf_headers; + +#ifdef CONFIG_IMA_KEXEC phys_addr_t ima_buffer_addr; size_t ima_buffer_size; -}; #endif +}; +char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len); int setup_purgatory(struct kimage *image, const void *slave_code, const void *fdt, unsigned long kernel_load_addr, unsigned long fdt_load_addr); @@ -116,6 +127,20 @@ int setup_new_fdt(const struct kimage *image, void *fdt, unsigned long initrd_load_addr, unsigned long initrd_len, const char *cmdline); int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size); + +#ifdef CONFIG_PPC64 +struct kexec_buf; + +int load_crashdump_segments_ppc64(struct kimage *image, + struct kexec_buf *kbuf); +int setup_purgatory_ppc64(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr); +int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, + unsigned long initrd_len, const char *cmdline); +#endif /* CONFIG_PPC64 */ + #endif /* CONFIG_KEXEC_FILE */ #else /* !CONFIG_KEXEC_CORE */ @@ -150,6 +175,18 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) } #endif /* CONFIG_KEXEC_CORE */ + +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/kexec.h> +#endif + +#ifndef reset_sprs +#define reset_sprs reset_sprs +static inline void reset_sprs(void) +{ +} +#endif + #endif /* ! __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_KEXEC_H */ diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h new file mode 100644 index 000000000000..7a90000f8d15 --- /dev/null +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_POWERPC_KEXEC_RANGES_H +#define _ASM_POWERPC_KEXEC_RANGES_H + +#define MEM_RANGE_CHUNK_SZ 2048 /* Memory ranges size chunk */ + +void sort_memory_ranges(struct crash_mem *mrngs, bool merge); +struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); +int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); +int add_tce_mem_ranges(struct crash_mem **mem_ranges); +int add_initrd_mem_range(struct crash_mem **mem_ranges); +#ifdef CONFIG_PPC_BOOK3S_64 +int add_htab_mem_range(struct crash_mem **mem_ranges); +#else +static inline int add_htab_mem_range(struct crash_mem **mem_ranges) +{ + return 0; +} +#endif +int add_kernel_mem_range(struct crash_mem **mem_ranges); +int add_rtas_mem_range(struct crash_mem **mem_ranges); +int add_opal_mem_range(struct crash_mem **mem_ranges); +int add_reserved_mem_ranges(struct crash_mem **mem_ranges); + +#endif /* _ASM_POWERPC_KEXEC_RANGES_H */ diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h index 45704f2716e2..078f4648ea27 100644 --- a/arch/powerpc/include/asm/kvm_book3s_asm.h +++ b/arch/powerpc/include/asm/kvm_book3s_asm.h @@ -119,7 +119,7 @@ struct kvmppc_host_state { void __iomem *xive_tima_virt; u32 saved_xirr; u64 dabr; - u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */ + u64 host_mmcr[10]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER, MMCR3, SIER2/3 */ u32 host_pmc[8]; u64 host_purr; u64 host_spurr; diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h index 9cb7d8be2366..0a6319448cb6 100644 --- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h +++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h @@ -23,6 +23,10 @@ int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn); unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm); void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, struct kvm *kvm, bool skip_page_out); +int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new); +void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old); #else static inline int kvmppc_uvmem_init(void) { @@ -82,5 +86,15 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn) static inline void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, struct kvm *kvm, bool skip_page_out) { } + +static inline int kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *new) +{ + return H_UNSUPPORTED; +} + +static inline void kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *old) { } + #endif /* CONFIG_PPC_UV */ #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h index 310ba48d13f0..0c3401b2e19e 100644 --- a/arch/powerpc/include/asm/kvm_booke.h +++ b/arch/powerpc/include/asm/kvm_booke.h @@ -89,10 +89,12 @@ static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu) return vcpu->arch.regs.nip; } +#ifdef CONFIG_BOOKE static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { return vcpu->arch.fault_dear; } +#endif static inline bool kvmppc_supports_magic_page(struct kvm_vcpu *vcpu) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 7e2d061d0445..e020d269416d 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -637,12 +637,14 @@ struct kvm_vcpu_arch { u32 ccr1; u32 dbsr; - u64 mmcr[5]; + u64 mmcr[4]; /* MMCR0, MMCR1, MMCR2, MMCR3 */ + u64 mmcra; + u64 mmcrs; u32 pmc[8]; u32 spmc[2]; u64 siar; u64 sdar; - u64 sier; + u64 sier[3]; #ifdef CONFIG_PPC_TRANSACTIONAL_MEM u64 tfhar; u64 texasr; diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h index 9c1f6b4b9bbf..744612054c94 100644 --- a/arch/powerpc/include/asm/kvm_para.h +++ b/arch/powerpc/include/asm/kvm_para.h @@ -8,35 +8,15 @@ #ifndef __POWERPC_KVM_PARA_H__ #define __POWERPC_KVM_PARA_H__ -#include <uapi/asm/kvm_para.h> - -#ifdef CONFIG_KVM_GUEST - -#include <linux/of.h> - -static inline int kvm_para_available(void) -{ - struct device_node *hyper_node; - - hyper_node = of_find_node_by_path("/hypervisor"); - if (!hyper_node) - return 0; +#include <asm/firmware.h> - if (!of_device_is_compatible(hyper_node, "linux,kvm")) - return 0; - - return 1; -} - -#else +#include <uapi/asm/kvm_para.h> static inline int kvm_para_available(void) { - return 0; + return IS_ENABLED(CONFIG_KVM_GUEST) && is_kvm_guest(); } -#endif - static inline unsigned int kvm_arch_para_features(void) { unsigned long r; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index ccf66b3a4c1d..0a056c64c317 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -59,7 +59,7 @@ enum xlate_readwrite { }; extern int kvmppc_vcpu_run(struct kvm_vcpu *vcpu); -extern int __kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu); +extern int __kvmppc_vcpu_run(struct kvm_vcpu *vcpu); extern void kvmppc_handler_highmem(void); extern void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu); diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 7bcb64444a39..a90b892f0bfe 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -131,7 +131,7 @@ struct machdep_calls { unsigned long dabrx); /* Set DAWR for this platform, leave empty for default implementation */ - int (*set_dawr)(unsigned long dawr, + int (*set_dawr)(int nr, unsigned long dawr, unsigned long dawrx); #ifdef CONFIG_PPC32 /* XXX for now */ diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 376a395daf32..adf2cda67f9a 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -86,6 +86,7 @@ enum MCE_TlbErrorType { enum MCE_UserErrorType { MCE_USER_ERROR_INDETERMINATE = 0, MCE_USER_ERROR_TLBIE = 1, + MCE_USER_ERROR_SCV = 2, }; enum MCE_RaErrorType { @@ -220,6 +221,8 @@ extern void machine_check_print_event_info(struct machine_check_event *evt, unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr); extern void mce_common_process_ue(struct pt_regs *regs, struct mce_error_info *mce_err); +int mce_register_notifier(struct notifier_block *nb); +int mce_unregister_notifier(struct notifier_block *nb); #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h index d610c2e07b28..7c07728af300 100644 --- a/arch/powerpc/include/asm/mman.h +++ b/arch/powerpc/include/asm/mman.h @@ -13,42 +13,20 @@ #include <linux/pkeys.h> #include <asm/cpu_has_feature.h> -/* - * This file is included by linux/mman.h, so we can't use cacl_vm_prot_bits() - * here. How important is the optimization? - */ +#ifdef CONFIG_PPC_MEM_KEYS static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { -#ifdef CONFIG_PPC_MEM_KEYS - return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey)); -#else - return ((prot & PROT_SAO) ? VM_SAO : 0); -#endif + return pkey_to_vmflag_bits(pkey); } #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags) { -#ifdef CONFIG_PPC_MEM_KEYS - return (vm_flags & VM_SAO) ? - __pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) : - __pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags)); -#else - return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0); -#endif + return __pgprot(vmflag_to_pte_pkey_bits(vm_flags)); } #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags) - -static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) -{ - if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO)) - return false; - if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO)) - return false; - return true; -} -#define arch_validate_prot arch_validate_prot +#endif #endif /* CONFIG_PPC64 */ #endif /* _ASM_POWERPC_MMAN_H */ diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index f4ac25d4df05..255a1837e9f7 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -29,6 +29,19 @@ */ /* + * Support for KUEP feature. + */ +#define MMU_FTR_KUEP ASM_CONST(0x00000400) + +/* + * Support for memory protection keys. + */ +#define MMU_FTR_PKEY ASM_CONST(0x00000800) + +/* Guest Translation Shootdown Enable */ +#define MMU_FTR_GTSE ASM_CONST(0x00001000) + +/* * Support for 68 bit VA space. We added that from ISA 2.05 */ #define MMU_FTR_68_BIT_VA ASM_CONST(0x00002000) @@ -173,10 +186,18 @@ enum { #endif #ifdef CONFIG_PPC_RADIX_MMU MMU_FTR_TYPE_RADIX | + MMU_FTR_GTSE | #ifdef CONFIG_PPC_KUAP MMU_FTR_RADIX_KUAP | #endif /* CONFIG_PPC_KUAP */ #endif /* CONFIG_PPC_RADIX_MMU */ +#ifdef CONFIG_PPC_MEM_KEYS + MMU_FTR_PKEY | +#endif +#ifdef CONFIG_PPC_KUEP + MMU_FTR_KUEP | +#endif /* CONFIG_PPC_KUAP */ + 0, }; @@ -356,6 +377,8 @@ extern void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); static inline void mmu_early_init_devtree(void) { } +static inline void pkey_early_init_devtree(void) {} + extern void *abatron_pteptrs[2]; #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 1a474f6b1992..7f3658a97384 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -218,8 +218,6 @@ static inline void inc_mm_active_cpus(struct mm_struct *mm) { } static inline void dec_mm_active_cpus(struct mm_struct *mm) { } static inline void mm_context_add_copro(struct mm_struct *mm) { } static inline void mm_context_remove_copro(struct mm_struct *mm) { } -static inline void mm_context_add_vas_windows(struct mm_struct *mm) { } -static inline void mm_context_remove_vas_windows(struct mm_struct *mm) { } #endif diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b0afbdd07740..b9e134d0f03a 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -249,6 +249,18 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p return old; } + +#ifdef CONFIG_PPC_16K_PAGES +#define __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_basic_t val = READ_ONCE(ptep->pte); + pte_t pte = {val, val, val, val}; + + return pte; +} +#endif /* CONFIG_PPC_16K_PAGES */ + #else static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) @@ -284,16 +296,6 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return __pte(pte_update(mm, addr, ptep, ~0, 0, 0)); } -#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) -#define __HAVE_ARCH_PTEP_GET -static inline pte_t ptep_get(pte_t *ptep) -{ - pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0}; - - return pte; -} -#endif - #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 6cb8aa357191..59ee9fa4ae09 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -82,8 +82,6 @@ */ #include <asm/nohash/pte-book3e.h> -#define _PAGE_SAO 0 - #define PTE_RPN_MASK (~((1UL << PTE_RPN_SHIFT) - 1)) /* diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 84b2564cf5a4..9454d29ff4b4 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -225,6 +225,7 @@ struct paca_struct { u16 in_mce; u8 hmi_event_available; /* HMI event is available */ u8 hmi_p9_special_emu; /* HMI P9 special emulation */ + u32 hmi_irqs; /* HMI irq stat */ #endif u8 ftrace_enabled; /* Hard disable ftrace */ diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index a63fe6f3a0ff..254687258f42 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -255,8 +255,10 @@ static inline bool pfn_valid(unsigned long pfn) */ #ifdef CONFIG_PPC_BOOK3E_64 #define is_kernel_addr(x) ((x) >= 0x8000000000000000ul) -#else +#elif defined(CONFIG_PPC_BOOK3S_64) #define is_kernel_addr(x) ((x) >= PAGE_OFFSET) +#else +#define is_kernel_addr(x) ((x) >= TASK_SIZE) #endif #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/paravirt.h b/arch/powerpc/include/asm/paravirt.h new file mode 100644 index 000000000000..9362c94fe3aa --- /dev/null +++ b/arch/powerpc/include/asm/paravirt.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_PARAVIRT_H +#define _ASM_POWERPC_PARAVIRT_H + +#include <linux/jump_label.h> +#include <asm/smp.h> +#ifdef CONFIG_PPC64 +#include <asm/paca.h> +#include <asm/hvcall.h> +#endif + +#ifdef CONFIG_PPC_SPLPAR +DECLARE_STATIC_KEY_FALSE(shared_processor); + +static inline bool is_shared_processor(void) +{ + return static_branch_unlikely(&shared_processor); +} + +/* If bit 0 is set, the cpu has been preempted */ +static inline u32 yield_count_of(int cpu) +{ + __be32 yield_count = READ_ONCE(lppaca_of(cpu).yield_count); + return be32_to_cpu(yield_count); +} + +static inline void yield_to_preempted(int cpu, u32 yield_count) +{ + plpar_hcall_norets(H_CONFER, get_hard_smp_processor_id(cpu), yield_count); +} + +static inline void prod_cpu(int cpu) +{ + plpar_hcall_norets(H_PROD, get_hard_smp_processor_id(cpu)); +} + +static inline void yield_to_any(void) +{ + plpar_hcall_norets(H_CONFER, -1, 0); +} +#else +static inline bool is_shared_processor(void) +{ + return false; +} + +static inline u32 yield_count_of(int cpu) +{ + return 0; +} + +extern void ___bad_yield_to_preempted(void); +static inline void yield_to_preempted(int cpu, u32 yield_count) +{ + ___bad_yield_to_preempted(); /* This would be a bug */ +} + +extern void ___bad_yield_to_any(void); +static inline void yield_to_any(void) +{ + ___bad_yield_to_any(); /* This would be a bug */ +} + +extern void ___bad_prod_cpu(void); +static inline void prod_cpu(int cpu) +{ + ___bad_prod_cpu(); /* This would be a bug */ +} + +#endif + +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + if (!is_shared_processor()) + return false; + if (yield_count_of(cpu) & 1) + return true; + return false; +} + +static inline bool pv_is_native_spin_unlock(void) +{ + return !is_shared_processor(); +} + +#endif /* _ASM_POWERPC_PARAVIRT_H */ diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h index b92e81b256e5..d2a2a14e56f9 100644 --- a/arch/powerpc/include/asm/pci-bridge.h +++ b/arch/powerpc/include/asm/pci-bridge.h @@ -202,7 +202,6 @@ struct pci_dn { #define IODA_INVALID_PE 0xFFFFFFFF unsigned int pe_number; #ifdef CONFIG_PCI_IOV - int vf_index; /* VF index in the PF */ u16 vfs_expanded; /* number of VFs IOV BAR expanded */ u16 num_vfs; /* number of VFs enabled*/ unsigned int *pe_num_map; /* PE# for the first VF PE or array */ diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index eed3954082fa..1e8b2e1ec1db 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -12,6 +12,8 @@ #ifdef CONFIG_PPC_PERF_CTRS #include <asm/perf_event_server.h> +#else +static inline bool is_sier_available(void) { return false; } #endif #ifdef CONFIG_FSL_EMB_PERF_EVENT diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 3e9703f44c7c..86c9eb064b22 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -17,6 +17,13 @@ struct perf_event; +struct mmcr_regs { + unsigned long mmcr0; + unsigned long mmcr1; + unsigned long mmcr2; + unsigned long mmcra; + unsigned long mmcr3; +}; /* * This struct provides the constants and functions needed to * describe the PMU on a particular POWER-family CPU. @@ -28,7 +35,7 @@ struct power_pmu { unsigned long add_fields; unsigned long test_adder; int (*compute_mmcr)(u64 events[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], + unsigned int hwc[], struct mmcr_regs *mmcr, struct perf_event *pevents[]); int (*get_constraint)(u64 event_id, unsigned long *mskp, unsigned long *valp); @@ -41,13 +48,13 @@ struct power_pmu { unsigned long group_constraint_val; u64 (*bhrb_filter_map)(u64 branch_sample_type); void (*config_bhrb)(u64 pmu_bhrb_filter); - void (*disable_pmc)(unsigned int pmc, unsigned long mmcr[]); + void (*disable_pmc)(unsigned int pmc, struct mmcr_regs *mmcr); int (*limited_pmc_event)(u64 event_id); u32 flags; const struct attribute_group **attr_groups; int n_generic; int *generic_events; - int (*cache_events)[PERF_COUNT_HW_CACHE_MAX] + u64 (*cache_events)[PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX]; @@ -69,6 +76,7 @@ struct power_pmu { #define PPMU_HAS_SIER 0x00000040 /* Has SIER */ #define PPMU_ARCH_207S 0x00000080 /* PMC is architecture v2.07S */ #define PPMU_NO_SIAR 0x00000100 /* Do not use SIAR */ +#define PPMU_ARCH_31 0x00000200 /* Has MMCR3, SIER2 and SIER3 */ /* * Values for flags to get_alternatives() diff --git a/arch/powerpc/include/asm/pkeys.h b/arch/powerpc/include/asm/pkeys.h index 2fe6cae14d10..a7951049e129 100644 --- a/arch/powerpc/include/asm/pkeys.h +++ b/arch/powerpc/include/asm/pkeys.h @@ -11,9 +11,7 @@ #include <linux/jump_label.h> #include <asm/firmware.h> -DECLARE_STATIC_KEY_TRUE(pkey_disabled); -extern int pkeys_total; /* total pkeys as per device tree */ -extern u32 initial_allocation_mask; /* bits set for the initially allocated keys */ +extern int num_pkey; extern u32 reserved_allocation_mask; /* bits set for reserved keys */ #define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | \ @@ -25,48 +23,28 @@ extern u32 reserved_allocation_mask; /* bits set for reserved keys */ PKEY_DISABLE_WRITE | \ PKEY_DISABLE_EXECUTE) +#ifdef CONFIG_PPC_BOOK3S_64 +#include <asm/book3s/64/pkeys.h> +#else +#error "Not supported" +#endif + + static inline u64 pkey_to_vmflag_bits(u16 pkey) { return (((u64)pkey << VM_PKEY_SHIFT) & ARCH_VM_PKEY_FLAGS); } -static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) -{ - if (static_branch_likely(&pkey_disabled)) - return 0x0UL; - - return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT4 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT3 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT1 : 0x0UL) | - ((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT0 : 0x0UL)); -} - static inline int vma_pkey(struct vm_area_struct *vma) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return 0; return (vma->vm_flags & ARCH_VM_PKEY_FLAGS) >> VM_PKEY_SHIFT; } -#define arch_max_pkey() pkeys_total - -static inline u64 pte_to_hpte_pkey_bits(u64 pteflags) +static inline int arch_max_pkey(void) { - return (((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL)); -} - -static inline u16 pte_to_pkey_bits(u64 pteflags) -{ - return (((pteflags & H_PTE_PKEY_BIT0) ? 0x10 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT1) ? 0x8 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT3) ? 0x2 : 0x0UL) | - ((pteflags & H_PTE_PKEY_BIT4) ? 0x1 : 0x0UL)); + return num_pkey; } #define pkey_alloc_mask(pkey) (0x1 << pkey) @@ -114,9 +92,8 @@ static inline int mm_pkey_alloc(struct mm_struct *mm) u32 all_pkeys_mask = (u32)(~(0x0)); int ret; - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -1; - /* * Are we out of pkeys? We must handle this specially because ffz() * behavior is undefined if there are no zeros. @@ -132,7 +109,7 @@ static inline int mm_pkey_alloc(struct mm_struct *mm) static inline int mm_pkey_free(struct mm_struct *mm, int pkey) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -1; if (!mm_pkey_is_allocated(mm, pkey)) @@ -147,21 +124,13 @@ static inline int mm_pkey_free(struct mm_struct *mm, int pkey) * Try to dedicate one of the protection keys to be used as an * execute-only protection key. */ -extern int __execute_only_pkey(struct mm_struct *mm); -static inline int execute_only_pkey(struct mm_struct *mm) -{ - if (static_branch_likely(&pkey_disabled)) - return -1; - - return __execute_only_pkey(mm); -} - +extern int execute_only_pkey(struct mm_struct *mm); extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey); static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return 0; /* @@ -179,7 +148,7 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return -EINVAL; /* @@ -196,7 +165,7 @@ static inline int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, static inline bool arch_pkeys_enabled(void) { - return !static_branch_likely(&pkey_disabled); + return mmu_has_feature(MMU_FTR_PKEY); } extern void pkey_mm_init(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 4497c8afb573..ece84a430701 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -312,7 +312,12 @@ static inline long plpar_set_ciabr(unsigned long ciabr) static inline long plpar_set_watchpoint0(unsigned long dawr0, unsigned long dawrx0) { - return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR, dawr0, dawrx0); + return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR0, dawr0, dawrx0); +} + +static inline long plpar_set_watchpoint1(unsigned long dawr1, unsigned long dawrx1) +{ + return plpar_set_mode(0, H_SET_MODE_RESOURCE_SET_DAWR1, dawr1, dawrx1); } static inline long plpar_signal_sys_reset(long cpu) @@ -334,6 +339,51 @@ static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) return rc; } +/* + * Wrapper to H_RPT_INVALIDATE hcall that handles return values appropriately + * + * - Returns H_SUCCESS on success + * - For H_BUSY return value, we retry the hcall. + * - For any other hcall failures, attempt a full flush once before + * resorting to BUG(). + * + * Note: This hcall is expected to fail only very rarely. The correct + * error recovery of killing the process/guest will be eventually + * needed. + */ +static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type, + u64 page_sizes, u64 start, u64 end) +{ + long rc; + unsigned long all; + + while (true) { + rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target, type, + page_sizes, start, end); + if (rc == H_BUSY) { + cpu_relax(); + continue; + } else if (rc == H_SUCCESS) + return rc; + + /* Flush request failed, try with a full flush once */ + if (type & H_RPTI_TYPE_NESTED) + all = H_RPTI_TYPE_NESTED | H_RPTI_TYPE_NESTED_ALL; + else + all = H_RPTI_TYPE_ALL; +retry: + rc = plpar_hcall_norets(H_RPT_INVALIDATE, pid, target, + all, page_sizes, 0, -1UL); + if (rc == H_BUSY) { + cpu_relax(); + goto retry; + } else if (rc == H_SUCCESS) + return rc; + + BUG(); + } +} + #else /* !CONFIG_PPC_PSERIES */ static inline long plpar_set_ciabr(unsigned long ciabr) @@ -346,6 +396,13 @@ static inline long plpar_pte_read_4(unsigned long flags, unsigned long ptex, { return 0; } + +static inline long pseries_rpt_invalidate(u32 pid, u64 target, u64 type, + u64 page_sizes, u64 start, u64 end) +{ + return 0; +} + #endif /* CONFIG_PPC_PSERIES */ #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h index 7de82647e761..ee79d2cd9fb6 100644 --- a/arch/powerpc/include/asm/pnv-ocxl.h +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -9,28 +9,26 @@ #define PNV_OCXL_TL_BITS_PER_RATE 4 #define PNV_OCXL_TL_RATE_BUF_SIZE ((PNV_OCXL_TL_MAX_TEMPLATE+1) * PNV_OCXL_TL_BITS_PER_RATE / 8) -extern int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, - u16 *supported); -extern int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count); +int pnv_ocxl_get_actag(struct pci_dev *dev, u16 *base, u16 *enabled, u16 *supported); +int pnv_ocxl_get_pasid_count(struct pci_dev *dev, int *count); -extern int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap, +int pnv_ocxl_get_tl_cap(struct pci_dev *dev, long *cap, char *rate_buf, int rate_buf_size); -extern int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap, - uint64_t rate_buf_phys, int rate_buf_size); - -extern int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq); -extern void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar, - void __iomem *tfc, void __iomem *pe_handle); -extern int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr, - void __iomem **dar, void __iomem **tfc, - void __iomem **pe_handle); - -extern int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, - void **platform_data); -extern void pnv_ocxl_spa_release(void *platform_data); -extern int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); - -extern int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); -extern void pnv_ocxl_free_xive_irq(u32 irq); +int pnv_ocxl_set_tl_conf(struct pci_dev *dev, long cap, + uint64_t rate_buf_phys, int rate_buf_size); + +int pnv_ocxl_get_xsl_irq(struct pci_dev *dev, int *hwirq); +void pnv_ocxl_unmap_xsl_regs(void __iomem *dsisr, void __iomem *dar, + void __iomem *tfc, void __iomem *pe_handle); +int pnv_ocxl_map_xsl_regs(struct pci_dev *dev, void __iomem **dsisr, + void __iomem **dar, void __iomem **tfc, + void __iomem **pe_handle); + +int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **platform_data); +void pnv_ocxl_spa_release(void *platform_data); +int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); + +int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); +void pnv_ocxl_free_xive_irq(u32 irq); #endif /* _ASM_PNV_OCXL_H */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 2a39c716c343..a6e3700c4566 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -76,6 +76,19 @@ #define __REGA0_R30 30 #define __REGA0_R31 31 +#define IMM_L(i) ((uintptr_t)(i) & 0xffff) +#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc) + +/* + * 16-bit immediate helper macros: HA() is for use with sign-extending instrs + * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the + * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). + */ +#define IMM_H(i) ((uintptr_t)(i)>>16) +#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ + (((uintptr_t)(i) & 0x8000) >> 15)) + + /* opcode and xopcode for instructions */ #define OP_TRAP 3 #define OP_TRAP_64 2 @@ -195,56 +208,28 @@ #define OP_LQ 56 /* sorted alphabetically */ -#define PPC_INST_BHRBE 0x7c00025c -#define PPC_INST_CLRBHRB 0x7c00035c +#define PPC_INST_BCCTR_FLUSH 0x4c400420 #define PPC_INST_COPY 0x7c20060c -#define PPC_INST_CP_ABORT 0x7c00068c -#define PPC_INST_DARN 0x7c0005e6 #define PPC_INST_DCBA 0x7c0005ec #define PPC_INST_DCBA_MASK 0xfc0007fe -#define PPC_INST_DCBAL 0x7c2005ec -#define PPC_INST_DCBZL 0x7c2007ec -#define PPC_INST_ICBT 0x7c00002c -#define PPC_INST_ICSWX 0x7c00032d -#define PPC_INST_ICSWEPX 0x7c00076d #define PPC_INST_ISEL 0x7c00001e #define PPC_INST_ISEL_MASK 0xfc00003e -#define PPC_INST_LDARX 0x7c0000a8 -#define PPC_INST_STDCX 0x7c0001ad -#define PPC_INST_LQARX 0x7c000228 -#define PPC_INST_STQCX 0x7c00016d #define PPC_INST_LSWI 0x7c0004aa #define PPC_INST_LSWX 0x7c00042a -#define PPC_INST_LWARX 0x7c000028 -#define PPC_INST_STWCX 0x7c00012d #define PPC_INST_LWSYNC 0x7c2004ac #define PPC_INST_SYNC 0x7c0004ac #define PPC_INST_SYNC_MASK 0xfc0007fe #define PPC_INST_ISYNC 0x4c00012c -#define PPC_INST_LXVD2X 0x7c000698 #define PPC_INST_MCRXR 0x7c000400 #define PPC_INST_MCRXR_MASK 0xfc0007fe #define PPC_INST_MFSPR_PVR 0x7c1f42a6 #define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe -#define PPC_INST_MFTMR 0x7c0002dc -#define PPC_INST_MSGSND 0x7c00019c -#define PPC_INST_MSGCLR 0x7c0001dc -#define PPC_INST_MSGSYNC 0x7c0006ec -#define PPC_INST_MSGSNDP 0x7c00011c -#define PPC_INST_MSGCLRP 0x7c00015c #define PPC_INST_MTMSRD 0x7c000164 -#define PPC_INST_MTTMR 0x7c0003dc #define PPC_INST_NOP 0x60000000 -#define PPC_INST_PASTE 0x7c20070d #define PPC_INST_POPCNTB 0x7c0000f4 #define PPC_INST_POPCNTB_MASK 0xfc0007fe -#define PPC_INST_POPCNTD 0x7c0003f4 -#define PPC_INST_POPCNTW 0x7c0002f4 #define PPC_INST_RFEBB 0x4c000124 -#define PPC_INST_RFCI 0x4c000066 -#define PPC_INST_RFDI 0x4c00004e #define PPC_INST_RFID 0x4c000024 -#define PPC_INST_RFMCI 0x4c00004c #define PPC_INST_MFSPR 0x7c0002a6 #define PPC_INST_MFSPR_DSCR 0x7c1102a6 #define PPC_INST_MFSPR_DSCR_MASK 0xfc1ffffe @@ -254,131 +239,43 @@ #define PPC_INST_MFSPR_DSCR_USER_MASK 0xfc1ffffe #define PPC_INST_MTSPR_DSCR_USER 0x7c0303a6 #define PPC_INST_MTSPR_DSCR_USER_MASK 0xfc1ffffe -#define PPC_INST_MFVSRD 0x7c000066 -#define PPC_INST_MTVSRD 0x7c000166 #define PPC_INST_SC 0x44000002 -#define PPC_INST_SLBFEE 0x7c0007a7 -#define PPC_INST_SLBIA 0x7c0003e4 - #define PPC_INST_STRING 0x7c00042a #define PPC_INST_STRING_MASK 0xfc0007fe #define PPC_INST_STRING_GEN_MASK 0xfc00067e - #define PPC_INST_STSWI 0x7c0005aa #define PPC_INST_STSWX 0x7c00052a -#define PPC_INST_STXVD2X 0x7c000798 -#define PPC_INST_TLBIE 0x7c000264 -#define PPC_INST_TLBIEL 0x7c000224 -#define PPC_INST_TLBILX 0x7c000024 -#define PPC_INST_WAIT 0x7c00007c -#define PPC_INST_TLBIVAX 0x7c000624 -#define PPC_INST_TLBSRX_DOT 0x7c0006a5 -#define PPC_INST_VPMSUMW 0x10000488 -#define PPC_INST_VPMSUMD 0x100004c8 -#define PPC_INST_VPERMXOR 0x1000002d -#define PPC_INST_XXLOR 0xf0000490 -#define PPC_INST_XXSWAPD 0xf0000250 -#define PPC_INST_XVCPSGNDP 0xf0000780 #define PPC_INST_TRECHKPT 0x7c0007dd #define PPC_INST_TRECLAIM 0x7c00075d -#define PPC_INST_TABORT 0x7c00071d #define PPC_INST_TSR 0x7c0005dd - -#define PPC_INST_NAP 0x4c000364 -#define PPC_INST_SLEEP 0x4c0003a4 -#define PPC_INST_WINKLE 0x4c0003e4 - -#define PPC_INST_STOP 0x4c0002e4 - -/* A2 specific instructions */ -#define PPC_INST_ERATWE 0x7c0001a6 -#define PPC_INST_ERATRE 0x7c000166 -#define PPC_INST_ERATILX 0x7c000066 -#define PPC_INST_ERATIVAX 0x7c000666 -#define PPC_INST_ERATSX 0x7c000126 -#define PPC_INST_ERATSX_DOT 0x7c000127 - -/* Misc instructions for BPF compiler */ -#define PPC_INST_LBZ 0x88000000 #define PPC_INST_LD 0xe8000000 -#define PPC_INST_LDX 0x7c00002a -#define PPC_INST_LHZ 0xa0000000 -#define PPC_INST_LWZ 0x80000000 -#define PPC_INST_LHBRX 0x7c00062c -#define PPC_INST_LDBRX 0x7c000428 -#define PPC_INST_STB 0x98000000 -#define PPC_INST_STH 0xb0000000 #define PPC_INST_STD 0xf8000000 -#define PPC_INST_STDX 0x7c00012a -#define PPC_INST_STDU 0xf8000001 -#define PPC_INST_STW 0x90000000 -#define PPC_INST_STWU 0x94000000 #define PPC_INST_MFLR 0x7c0802a6 -#define PPC_INST_MTLR 0x7c0803a6 #define PPC_INST_MTCTR 0x7c0903a6 -#define PPC_INST_CMPWI 0x2c000000 -#define PPC_INST_CMPDI 0x2c200000 -#define PPC_INST_CMPW 0x7c000000 -#define PPC_INST_CMPD 0x7c200000 -#define PPC_INST_CMPLW 0x7c000040 -#define PPC_INST_CMPLD 0x7c200040 -#define PPC_INST_CMPLWI 0x28000000 -#define PPC_INST_CMPLDI 0x28200000 #define PPC_INST_ADDI 0x38000000 #define PPC_INST_ADDIS 0x3c000000 #define PPC_INST_ADD 0x7c000214 -#define PPC_INST_ADDC 0x7c000014 -#define PPC_INST_SUB 0x7c000050 #define PPC_INST_BLR 0x4e800020 -#define PPC_INST_BLRL 0x4e800021 #define PPC_INST_BCTR 0x4e800420 -#define PPC_INST_MULLD 0x7c0001d2 -#define PPC_INST_MULLW 0x7c0001d6 -#define PPC_INST_MULHWU 0x7c000016 -#define PPC_INST_MULLI 0x1c000000 -#define PPC_INST_MADDHD 0x10000030 -#define PPC_INST_MADDHDU 0x10000031 -#define PPC_INST_MADDLD 0x10000033 -#define PPC_INST_DIVWU 0x7c000396 +#define PPC_INST_BCTRL 0x4e800421 #define PPC_INST_DIVD 0x7c0003d2 -#define PPC_INST_DIVDU 0x7c000392 -#define PPC_INST_RLWINM 0x54000000 -#define PPC_INST_RLWINM_DOT 0x54000001 -#define PPC_INST_RLWIMI 0x50000000 -#define PPC_INST_RLDICL 0x78000000 #define PPC_INST_RLDICR 0x78000004 -#define PPC_INST_SLW 0x7c000030 -#define PPC_INST_SLD 0x7c000036 -#define PPC_INST_SRW 0x7c000430 -#define PPC_INST_SRAW 0x7c000630 -#define PPC_INST_SRAWI 0x7c000670 -#define PPC_INST_SRD 0x7c000436 -#define PPC_INST_SRAD 0x7c000634 -#define PPC_INST_SRADI 0x7c000674 -#define PPC_INST_AND 0x7c000038 -#define PPC_INST_ANDDOT 0x7c000039 -#define PPC_INST_OR 0x7c000378 -#define PPC_INST_XOR 0x7c000278 -#define PPC_INST_ANDI 0x70000000 #define PPC_INST_ORI 0x60000000 #define PPC_INST_ORIS 0x64000000 -#define PPC_INST_XORI 0x68000000 -#define PPC_INST_XORIS 0x6c000000 -#define PPC_INST_NEG 0x7c0000d0 -#define PPC_INST_EXTSW 0x7c0007b4 #define PPC_INST_BRANCH 0x48000000 #define PPC_INST_BRANCH_COND 0x40800000 -#define PPC_INST_LBZCIX 0x7c0006aa -#define PPC_INST_STBCIX 0x7c0007aa -#define PPC_INST_LWZX 0x7c00002e -#define PPC_INST_LFSX 0x7c00042e -#define PPC_INST_STFSX 0x7c00052e -#define PPC_INST_LFDX 0x7c0004ae -#define PPC_INST_STFDX 0x7c0005ae -#define PPC_INST_LVX 0x7c0000ce -#define PPC_INST_STVX 0x7c0001ce -#define PPC_INST_VCMPEQUD 0x100000c7 -#define PPC_INST_VCMPEQUB 0x10000006 + +/* Prefixes */ +#define PPC_INST_LFS 0xc0000000 +#define PPC_INST_STFS 0xd0000000 +#define PPC_INST_LFD 0xc8000000 +#define PPC_INST_STFD 0xd8000000 +#define PPC_PREFIX_MLS 0x06000000 +#define PPC_PREFIX_8LS 0x04000000 + +/* Prefixed instructions */ +#define PPC_INST_PLD 0xe4000000 +#define PPC_INST_PSTD 0xf4000000 /* macros to insert fields into opcodes */ #define ___PPC_RA(a) (((a) & 0x1f) << 16) @@ -411,6 +308,7 @@ #define __PPC_CT(t) (((t) & 0x0f) << 21) #define __PPC_SPR(r) ((((r) & 0x1f) << 16) | ((((r) >> 5) & 0x1f) << 11)) #define __PPC_RC21 (0x1 << 10) +#define __PPC_PRFX_R(r) (((r) & 0x1) << 20) /* * Both low and high 16 bits are added as SIGNED additions, so if low 16 bits @@ -431,175 +329,278 @@ #define __PPC_EH(eh) 0 #endif +/* Base instruction encoding */ +#define PPC_RAW_CP_ABORT (0x7c00068c) +#define PPC_RAW_COPY(a, b) (PPC_INST_COPY | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DARN(t, l) (0x7c0005e6 | ___PPC_RT(t) | (((l) & 0x3) << 16)) +#define PPC_RAW_DCBAL(a, b) (0x7c2005ec | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_DCBZL(a, b) (0x7c2007ec | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_LQARX(t, a, b, eh) (0x7c000228 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_LDARX(t, a, b, eh) (0x7c0000a8 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_LWARX(t, a, b, eh) (0x7c000028 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | __PPC_EH(eh)) +#define PPC_RAW_PHWSYNC (0x7c8004ac) +#define PPC_RAW_PLWSYNC (0x7ca004ac) +#define PPC_RAW_STQCX(t, a, b) (0x7c00016d | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MADDHD(t, a, b, c) (0x10000030 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MADDHDU(t, a, b, c) (0x10000031 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MADDLD(t, a, b, c) (0x10000033 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | ___PPC_RC(c)) +#define PPC_RAW_MSGSND(b) (0x7c00019c | ___PPC_RB(b)) +#define PPC_RAW_MSGSYNC (0x7c0006ec) +#define PPC_RAW_MSGCLR(b) (0x7c0001dc | ___PPC_RB(b)) +#define PPC_RAW_MSGSNDP(b) (0x7c00011c | ___PPC_RB(b)) +#define PPC_RAW_MSGCLRP(b) (0x7c00015c | ___PPC_RB(b)) +#define PPC_RAW_PASTE(a, b) (0x7c20070d | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_POPCNTB(a, s) (PPC_INST_POPCNTB | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_POPCNTD(a, s) (0x7c0003f4 | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_POPCNTW(a, s) (0x7c0002f4 | __PPC_RA(a) | __PPC_RS(s)) +#define PPC_RAW_RFCI (0x4c000066) +#define PPC_RAW_RFDI (0x4c00004e) +#define PPC_RAW_RFMCI (0x4c00004c) +#define PPC_RAW_TLBILX(t, a, b) (0x7c000024 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_WAIT(w) (0x7c00007c | __PPC_WC(w)) +#define PPC_RAW_TLBIE(lp, a) (0x7c000264 | ___PPC_RB(a) | ___PPC_RS(lp)) +#define PPC_RAW_TLBIE_5(rb, rs, ric, prs, r) \ + (0x7c000264 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r)) +#define PPC_RAW_TLBIEL(rb, rs, ric, prs, r) \ + (0x7c000224 | ___PPC_RB(rb) | ___PPC_RS(rs) | ___PPC_RIC(ric) | ___PPC_PRS(prs) | ___PPC_R(r)) +#define PPC_RAW_TLBSRX_DOT(a, b) (0x7c0006a5 | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_TLBIVAX(a, b) (0x7c000624 | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATWE(s, a, w) (0x7c0001a6 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_RAW_ERATRE(s, a, w) (0x7c000166 | __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) +#define PPC_RAW_ERATILX(t, a, b) (0x7c000066 | __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATIVAX(s, a, b) (0x7c000666 | __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATSX(t, a, w) (0x7c000126 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_ERATSX_DOT(t, a, w) (0x7c000127 | __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | __PPC_RT(t) | __PPC_RB(b)) +#define __PPC_RAW_SLBFEE_DOT(t, b) (0x7c0007a7 | ___PPC_RT(t) | ___PPC_RB(b)) +#define PPC_RAW_ICBT(c, a, b) (0x7c00002c | __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_RAW_LBZCIX(t, a, b) (0x7c0006aa | __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_STBCIX(s, a, b) (0x7c0007aa | __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) +#define PPC_RAW_DCBFPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (4 << 21)) +#define PPC_RAW_DCBSTPS(a, b) (0x7c0000ac | ___PPC_RA(a) | ___PPC_RB(b) | (6 << 21)) +/* + * Define what the VSX XX1 form instructions will look like, then add + * the 128 bit load store instructions based on that. + */ +#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) +#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) +#define PPC_RAW_STXVD2X(s, a, b) (0x7c000798 | VSX_XX1((s), a, b)) +#define PPC_RAW_LXVD2X(s, a, b) (0x7c000698 | VSX_XX1((s), a, b)) +#define PPC_RAW_MFVRD(a, t) (0x7c000066 | VSX_XX1((t) + 32, a, R0)) +#define PPC_RAW_MTVRD(t, a) (0x7c000166 | VSX_XX1((t) + 32, a, R0)) +#define PPC_RAW_VPMSUMW(t, a, b) (0x10000488 | VSX_XX3((t), a, b)) +#define PPC_RAW_VPMSUMD(t, a, b) (0x100004c8 | VSX_XX3((t), a, b)) +#define PPC_RAW_XXLOR(t, a, b) (0xf0000490 | VSX_XX3((t), a, b)) +#define PPC_RAW_XXSWAPD(t, a) (0xf0000250 | VSX_XX3((t), a, a)) +#define PPC_RAW_XVCPSGNDP(t, a, b) ((0xf0000780 | VSX_XX3((t), (a), (b)))) +#define PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc) \ + ((0x1000002d | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6))) +#define PPC_RAW_NAP (0x4c000364) +#define PPC_RAW_SLEEP (0x4c0003a4) +#define PPC_RAW_WINKLE (0x4c0003e4) +#define PPC_RAW_STOP (0x4c0002e4) +#define PPC_RAW_CLRBHRB (0x7c00035c) +#define PPC_RAW_MFBHRBE(r, n) (0x7c00025c | __PPC_RT(r) | (((n) & 0x3ff) << 11)) +#define PPC_RAW_TRECHKPT (PPC_INST_TRECHKPT) +#define PPC_RAW_TRECLAIM(r) (PPC_INST_TRECLAIM | __PPC_RA(r)) +#define PPC_RAW_TABORT(r) (0x7c00071d | __PPC_RA(r)) +#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6)) +#define PPC_RAW_MTTMR(tmr, r) (0x7c0003dc | TMRN(tmr) | ___PPC_RS(r)) +#define PPC_RAW_MFTMR(tmr, r) (0x7c0002dc | TMRN(tmr) | ___PPC_RT(r)) +#define PPC_RAW_ICSWX(s, a, b) (0x7c00032d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ICSWEPX(s, a, b) (0x7c00076d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SLBIA(IH) (0x7c0003e4 | (((IH) & 0x7) << 21)) +#define PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb) \ + (0x100000c7 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21) +#define PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb) \ + (0x10000006 | ___PPC_RT(vrt) | ___PPC_RA(vra) | ___PPC_RB(vrb) | __PPC_RC21) +#define PPC_RAW_LD(r, base, i) (PPC_INST_LD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_DS(i)) +#define PPC_RAW_LWZ(r, base, i) (0x80000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LWZX(t, a, b) (0x7c00002e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STD(r, base, i) (PPC_INST_STD | ___PPC_RS(r) | ___PPC_RA(base) | IMM_DS(i)) +#define PPC_RAW_STDCX(s, a, b) (0x7c0001ad | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LFSX(t, a, b) (0x7c00042e | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STFSX(s, a, b) (0x7c00052e | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LFDX(t, a, b) (0x7c0004ae | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STFDX(s, a, b) (0x7c0005ae | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_LVX(t, a, b) (0x7c0000ce | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_STVX(s, a, b) (0x7c0001ce | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADD(t, a, b) (PPC_INST_ADD | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADD_DOT(t, a, b) (PPC_INST_ADD | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_ADDC(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_ADDC_DOT(t, a, b) (0x7c000014 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_NOP() (PPC_INST_NOP) +#define PPC_RAW_BLR() (PPC_INST_BLR) +#define PPC_RAW_BLRL() (0x4e800021) +#define PPC_RAW_MTLR(r) (0x7c0803a6 | ___PPC_RT(r)) +#define PPC_RAW_BCTR() (PPC_INST_BCTR) +#define PPC_RAW_MTCTR(r) (PPC_INST_MTCTR | ___PPC_RT(r)) +#define PPC_RAW_ADDI(d, a, i) (PPC_INST_ADDI | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_LI(r, i) PPC_RAW_ADDI(r, 0, i) +#define PPC_RAW_ADDIS(d, a, i) (PPC_INST_ADDIS | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_LIS(r, i) PPC_RAW_ADDIS(r, 0, i) +#define PPC_RAW_STDX(r, base, b) (0x7c00012a | ___PPC_RS(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_STDU(r, base, i) (0xf8000001 | ___PPC_RS(r) | ___PPC_RA(base) | ((i) & 0xfffc)) +#define PPC_RAW_STW(r, base, i) (0x90000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STWU(r, base, i) (0x94000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STH(r, base, i) (0xb0000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_STB(r, base, i) (0x98000000 | ___PPC_RS(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LBZ(r, base, i) (0x88000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LDX(r, base, b) (0x7c00002a | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LHZ(r, base, i) (0xa0000000 | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) +#define PPC_RAW_LHBRX(r, base, b) (0x7c00062c | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_LDBRX(r, base, b) (0x7c000428 | ___PPC_RT(r) | ___PPC_RA(base) | ___PPC_RB(b)) +#define PPC_RAW_STWCX(s, a, b) (0x7c00012d | ___PPC_RS(s) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPWI(a, i) (0x2c000000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPDI(a, i) (0x2c200000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPW(a, b) (0x7c000000 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPD(a, b) (0x7c200000 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPLWI(a, i) (0x28000000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPLDI(a, i) (0x28200000 | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_CMPLW(a, b) (0x7c000040 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_CMPLD(a, b) (0x7c200040 | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_SUB(d, a, b) (0x7c000050 | ___PPC_RT(d) | ___PPC_RB(a) | ___PPC_RA(b)) +#define PPC_RAW_MULD(d, a, b) (0x7c0001d2 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULW(d, a, b) (0x7c0001d6 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULHWU(d, a, b) (0x7c000016 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_MULI(d, a, i) (0x1c000000 | ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) +#define PPC_RAW_DIVWU(d, a, b) (0x7c000396 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDU(d, a, b) (0x7c000392 | ___PPC_RT(d) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDE(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDE_DOT(t, a, b) (0x7c000352 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_DIVDEU(t, a, b) (0x7c000312 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b)) +#define PPC_RAW_DIVDEU_DOT(t, a, b) (0x7c000312 | ___PPC_RT(t) | ___PPC_RA(a) | ___PPC_RB(b) | 0x1) +#define PPC_RAW_AND(d, a, b) (0x7c000038 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_ANDI(d, a, i) (0x70000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_AND_DOT(d, a, b) (0x7c000039 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_OR(d, a, b) (0x7c000378 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_MR(d, a) PPC_RAW_OR(d, a, a) +#define PPC_RAW_ORI(d, a, i) (PPC_INST_ORI | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_ORIS(d, a, i) (PPC_INST_ORIS | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_XOR(d, a, b) (0x7c000278 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(b)) +#define PPC_RAW_XORI(d, a, i) (0x68000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_XORIS(d, a, i) (0x6c000000 | ___PPC_RA(d) | ___PPC_RS(a) | IMM_L(i)) +#define PPC_RAW_EXTSW(d, a) (0x7c0007b4 | ___PPC_RA(d) | ___PPC_RS(a)) +#define PPC_RAW_SLW(d, a, s) (0x7c000030 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SLD(d, a, s) (0x7c000036 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRW(d, a, s) (0x7c000430 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAW(d, a, s) (0x7c000630 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAWI(d, a, i) (0x7c000670 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i)) +#define PPC_RAW_SRD(d, a, s) (0x7c000436 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRAD(d, a, s) (0x7c000634 | ___PPC_RA(d) | ___PPC_RS(a) | ___PPC_RB(s)) +#define PPC_RAW_SRADI(d, a, i) (0x7c000674 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i)) +#define PPC_RAW_RLWINM(d, a, i, mb, me) (0x54000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLWINM_DOT(d, a, i, mb, me) \ + (0x54000001 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLWIMI(d, a, i, mb, me) (0x50000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH(i) | __PPC_MB(mb) | __PPC_ME(me)) +#define PPC_RAW_RLDICL(d, a, i, mb) (0x78000000 | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_MB64(mb)) +#define PPC_RAW_RLDICR(d, a, i, me) (PPC_INST_RLDICR | ___PPC_RA(d) | ___PPC_RS(a) | __PPC_SH64(i) | __PPC_ME64(me)) + +/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ +#define PPC_RAW_SLWI(d, a, i) PPC_RAW_RLWINM(d, a, i, 0, 31-(i)) +/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ +#define PPC_RAW_SRWI(d, a, i) PPC_RAW_RLWINM(d, a, 32-(i), i, 31) +/* sldi = rldicr Rx, Ry, n, 63-n */ +#define PPC_RAW_SLDI(d, a, i) PPC_RAW_RLDICR(d, a, i, 63-(i)) +/* sldi = rldicl Rx, Ry, 64-n, n */ +#define PPC_RAW_SRDI(d, a, i) PPC_RAW_RLDICL(d, a, 64-(i), i) + +#define PPC_RAW_NEG(d, a) (0x7c0000d0 | ___PPC_RT(d) | ___PPC_RA(a)) + /* Deal with instructions that older assemblers aren't aware of */ -#define PPC_CP_ABORT stringify_in_c(.long PPC_INST_CP_ABORT) -#define PPC_COPY(a, b) stringify_in_c(.long PPC_INST_COPY | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_DARN(t, l) stringify_in_c(.long PPC_INST_DARN | \ - ___PPC_RT(t) | \ - (((l) & 0x3) << 16)) -#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_INST_DCBAL | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_INST_DCBZL | \ - __PPC_RA(a) | __PPC_RB(b)) -#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LQARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LDARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_INST_LWARX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | __PPC_EH(eh)) -#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_INST_STQCX | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHD | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_INST_MADDHDU | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_INST_MADDLD | \ - ___PPC_RT(t) | ___PPC_RA(a) | \ - ___PPC_RB(b) | ___PPC_RC(c)) -#define PPC_MSGSND(b) stringify_in_c(.long PPC_INST_MSGSND | \ - ___PPC_RB(b)) -#define PPC_MSGSYNC stringify_in_c(.long PPC_INST_MSGSYNC) -#define PPC_MSGCLR(b) stringify_in_c(.long PPC_INST_MSGCLR | \ - ___PPC_RB(b)) -#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_INST_MSGSNDP | \ - ___PPC_RB(b)) -#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_INST_MSGCLRP | \ - ___PPC_RB(b)) -#define PPC_PASTE(a, b) stringify_in_c(.long PPC_INST_PASTE | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_INST_POPCNTB | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_INST_POPCNTD | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_INST_POPCNTW | \ - __PPC_RA(a) | __PPC_RS(s)) -#define PPC_RFCI stringify_in_c(.long PPC_INST_RFCI) -#define PPC_RFDI stringify_in_c(.long PPC_INST_RFDI) -#define PPC_RFMCI stringify_in_c(.long PPC_INST_RFMCI) -#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_INST_TLBILX | \ - __PPC_T_TLB(t) | __PPC_RA0(a) | __PPC_RB(b)) +#define PPC_BCCTR_FLUSH stringify_in_c(.long PPC_INST_BCCTR_FLUSH) +#define PPC_CP_ABORT stringify_in_c(.long PPC_RAW_CP_ABORT) +#define PPC_COPY(a, b) stringify_in_c(.long PPC_RAW_COPY(a, b)) +#define PPC_DARN(t, l) stringify_in_c(.long PPC_RAW_DARN(t, l)) +#define PPC_DCBAL(a, b) stringify_in_c(.long PPC_RAW_DCBAL(a, b)) +#define PPC_DCBZL(a, b) stringify_in_c(.long PPC_RAW_DCBZL(a, b)) +#define PPC_DIVDE(t, a, b) stringify_in_c(.long PPC_RAW_DIVDE(t, a, b)) +#define PPC_DIVDEU(t, a, b) stringify_in_c(.long PPC_RAW_DIVDEU(t, a, b)) +#define PPC_LQARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LQARX(t, a, b, eh)) +#define PPC_LDARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LDARX(t, a, b, eh)) +#define PPC_LWARX(t, a, b, eh) stringify_in_c(.long PPC_RAW_LWARX(t, a, b, eh)) +#define PPC_STQCX(t, a, b) stringify_in_c(.long PPC_RAW_STQCX(t, a, b)) +#define PPC_MADDHD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHD(t, a, b, c)) +#define PPC_MADDHDU(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDHDU(t, a, b, c)) +#define PPC_MADDLD(t, a, b, c) stringify_in_c(.long PPC_RAW_MADDLD(t, a, b, c)) +#define PPC_MSGSND(b) stringify_in_c(.long PPC_RAW_MSGSND(b)) +#define PPC_MSGSYNC stringify_in_c(.long PPC_RAW_MSGSYNC) +#define PPC_MSGCLR(b) stringify_in_c(.long PPC_RAW_MSGCLR(b)) +#define PPC_MSGSNDP(b) stringify_in_c(.long PPC_RAW_MSGSNDP(b)) +#define PPC_MSGCLRP(b) stringify_in_c(.long PPC_RAW_MSGCLRP(b)) +#define PPC_PASTE(a, b) stringify_in_c(.long PPC_RAW_PASTE(a, b)) +#define PPC_POPCNTB(a, s) stringify_in_c(.long PPC_RAW_POPCNTB(a, s)) +#define PPC_POPCNTD(a, s) stringify_in_c(.long PPC_RAW_POPCNTD(a, s)) +#define PPC_POPCNTW(a, s) stringify_in_c(.long PPC_RAW_POPCNTW(a, s)) +#define PPC_RFCI stringify_in_c(.long PPC_RAW_RFCI) +#define PPC_RFDI stringify_in_c(.long PPC_RAW_RFDI) +#define PPC_RFMCI stringify_in_c(.long PPC_RAW_RFMCI) +#define PPC_TLBILX(t, a, b) stringify_in_c(.long PPC_RAW_TLBILX(t, a, b)) #define PPC_TLBILX_ALL(a, b) PPC_TLBILX(0, a, b) #define PPC_TLBILX_PID(a, b) PPC_TLBILX(1, a, b) #define PPC_TLBILX_VA(a, b) PPC_TLBILX(3, a, b) -#define PPC_WAIT(w) stringify_in_c(.long PPC_INST_WAIT | \ - __PPC_WC(w)) -#define PPC_TLBIE(lp,a) stringify_in_c(.long PPC_INST_TLBIE | \ - ___PPC_RB(a) | ___PPC_RS(lp)) -#define PPC_TLBIE_5(rb,rs,ric,prs,r) \ - stringify_in_c(.long PPC_INST_TLBIE | \ - ___PPC_RB(rb) | ___PPC_RS(rs) | \ - ___PPC_RIC(ric) | ___PPC_PRS(prs) | \ - ___PPC_R(r)) +#define PPC_WAIT(w) stringify_in_c(.long PPC_RAW_WAIT(w)) +#define PPC_TLBIE(lp, a) stringify_in_c(.long PPC_RAW_TLBIE(lp, a)) +#define PPC_TLBIE_5(rb, rs, ric, prs, r) \ + stringify_in_c(.long PPC_RAW_TLBIE_5(rb, rs, ric, prs, r)) #define PPC_TLBIEL(rb,rs,ric,prs,r) \ - stringify_in_c(.long PPC_INST_TLBIEL | \ - ___PPC_RB(rb) | ___PPC_RS(rs) | \ - ___PPC_RIC(ric) | ___PPC_PRS(prs) | \ - ___PPC_R(r)) -#define PPC_TLBSRX_DOT(a,b) stringify_in_c(.long PPC_INST_TLBSRX_DOT | \ - __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_TLBIVAX(a,b) stringify_in_c(.long PPC_INST_TLBIVAX | \ - __PPC_RA0(a) | __PPC_RB(b)) - -#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_INST_ERATWE | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) -#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_INST_ERATRE | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_WS(w)) -#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_INST_ERATILX | \ - __PPC_T_TLB(t) | __PPC_RA0(a) | \ - __PPC_RB(b)) -#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_INST_ERATIVAX | \ - __PPC_RS(s) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_INST_ERATSX | \ - __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_INST_ERATSX_DOT | \ - __PPC_RS(t) | __PPC_RA0(a) | __PPC_RB(b)) -#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ - __PPC_RT(t) | __PPC_RB(b)) -#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_INST_SLBFEE | \ - ___PPC_RT(t) | ___PPC_RB(b)) -#define PPC_ICBT(c,a,b) stringify_in_c(.long PPC_INST_ICBT | \ - __PPC_CT(c) | __PPC_RA0(a) | __PPC_RB(b)) + stringify_in_c(.long PPC_RAW_TLBIEL(rb, rs, ric, prs, r)) +#define PPC_TLBSRX_DOT(a, b) stringify_in_c(.long PPC_RAW_TLBSRX_DOT(a, b)) +#define PPC_TLBIVAX(a, b) stringify_in_c(.long PPC_RAW_TLBIVAX(a, b)) + +#define PPC_ERATWE(s, a, w) stringify_in_c(.long PPC_RAW_ERATWE(s, a, w)) +#define PPC_ERATRE(s, a, w) stringify_in_c(.long PPC_RAW_ERATRE(a, a, w)) +#define PPC_ERATILX(t, a, b) stringify_in_c(.long PPC_RAW_ERATILX(t, a, b)) +#define PPC_ERATIVAX(s, a, b) stringify_in_c(.long PPC_RAW_ERATIVAX(s, a, b)) +#define PPC_ERATSX(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX(t, a, w)) +#define PPC_ERATSX_DOT(t, a, w) stringify_in_c(.long PPC_RAW_ERATSX_DOT(t, a, w)) +#define PPC_SLBFEE_DOT(t, b) stringify_in_c(.long PPC_RAW_SLBFEE_DOT(t, b)) +#define __PPC_SLBFEE_DOT(t, b) stringify_in_c(.long __PPC_RAW_SLBFEE_DOT(t, b)) +#define PPC_ICBT(c, a, b) stringify_in_c(.long PPC_RAW_ICBT(c, a, b)) /* PASemi instructions */ -#define LBZCIX(t,a,b) stringify_in_c(.long PPC_INST_LBZCIX | \ - __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)) -#define STBCIX(s,a,b) stringify_in_c(.long PPC_INST_STBCIX | \ - __PPC_RS(s) | __PPC_RA(a) | __PPC_RB(b)) - -/* - * Define what the VSX XX1 form instructions will look like, then add - * the 128 bit load store instructions based on that. - */ -#define VSX_XX1(s, a, b) (__PPC_XS(s) | __PPC_RA(a) | __PPC_RB(b)) -#define VSX_XX3(t, a, b) (__PPC_XT(t) | __PPC_XA(a) | __PPC_XB(b)) -#define STXVD2X(s, a, b) stringify_in_c(.long PPC_INST_STXVD2X | \ - VSX_XX1((s), a, b)) -#define LXVD2X(s, a, b) stringify_in_c(.long PPC_INST_LXVD2X | \ - VSX_XX1((s), a, b)) -#define MFVRD(a, t) stringify_in_c(.long PPC_INST_MFVSRD | \ - VSX_XX1((t)+32, a, R0)) -#define MTVRD(t, a) stringify_in_c(.long PPC_INST_MTVSRD | \ - VSX_XX1((t)+32, a, R0)) -#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMW | \ - VSX_XX3((t), a, b)) -#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_INST_VPMSUMD | \ - VSX_XX3((t), a, b)) -#define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \ - VSX_XX3((t), a, b)) -#define XXSWAPD(t, a) stringify_in_c(.long PPC_INST_XXSWAPD | \ - VSX_XX3((t), a, a)) -#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_INST_XVCPSGNDP | \ - VSX_XX3((t), (a), (b)))) +#define LBZCIX(t, a, b) stringify_in_c(.long PPC_RAW_LBZCIX(t, a, b)) +#define STBCIX(s, a, b) stringify_in_c(.long PPC_RAW_STBCIX(s, a, b)) +#define PPC_DCBFPS(a, b) stringify_in_c(.long PPC_RAW_DCBFPS(a, b)) +#define PPC_DCBSTPS(a, b) stringify_in_c(.long PPC_RAW_DCBSTPS(a, b)) +#define PPC_PHWSYNC stringify_in_c(.long PPC_RAW_PHWSYNC) +#define PPC_PLWSYNC stringify_in_c(.long PPC_RAW_PLWSYNC) +#define STXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_STXVD2X(s, a, b)) +#define LXVD2X(s, a, b) stringify_in_c(.long PPC_RAW_LXVD2X(s, a, b)) +#define MFVRD(a, t) stringify_in_c(.long PPC_RAW_MFVRD(a, t)) +#define MTVRD(t, a) stringify_in_c(.long PPC_RAW_MTVRD(t, a)) +#define VPMSUMW(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMW(t, a, b)) +#define VPMSUMD(t, a, b) stringify_in_c(.long PPC_RAW_VPMSUMD(t, a, b)) +#define XXLOR(t, a, b) stringify_in_c(.long PPC_RAW_XXLOR(t, a, b)) +#define XXSWAPD(t, a) stringify_in_c(.long PPC_RAW_XXSWAPD(t, a)) +#define XVCPSGNDP(t, a, b) stringify_in_c(.long (PPC_RAW_XVCPSGNDP(t, a, b))) #define VPERMXOR(vrt, vra, vrb, vrc) \ - stringify_in_c(.long (PPC_INST_VPERMXOR | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | (((vrc) & 0x1f) << 6))) + stringify_in_c(.long (PPC_RAW_VPERMXOR(vrt, vra, vrb, vrc))) -#define PPC_NAP stringify_in_c(.long PPC_INST_NAP) -#define PPC_SLEEP stringify_in_c(.long PPC_INST_SLEEP) -#define PPC_WINKLE stringify_in_c(.long PPC_INST_WINKLE) +#define PPC_NAP stringify_in_c(.long PPC_RAW_NAP) +#define PPC_SLEEP stringify_in_c(.long PPC_RAW_SLEEP) +#define PPC_WINKLE stringify_in_c(.long PPC_RAW_WINKLE) -#define PPC_STOP stringify_in_c(.long PPC_INST_STOP) +#define PPC_STOP stringify_in_c(.long PPC_RAW_STOP) /* BHRB instructions */ -#define PPC_CLRBHRB stringify_in_c(.long PPC_INST_CLRBHRB) -#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_INST_BHRBE | \ - __PPC_RT(r) | \ - (((n) & 0x3ff) << 11)) +#define PPC_CLRBHRB stringify_in_c(.long PPC_RAW_CLRBHRB) +#define PPC_MFBHRBE(r, n) stringify_in_c(.long PPC_RAW_MFBHRBE(r, n)) /* Transactional memory instructions */ -#define TRECHKPT stringify_in_c(.long PPC_INST_TRECHKPT) -#define TRECLAIM(r) stringify_in_c(.long PPC_INST_TRECLAIM \ - | __PPC_RA(r)) -#define TABORT(r) stringify_in_c(.long PPC_INST_TABORT \ - | __PPC_RA(r)) +#define TRECHKPT stringify_in_c(.long PPC_RAW_TRECHKPT) +#define TRECLAIM(r) stringify_in_c(.long PPC_RAW_TRECLAIM(r)) +#define TABORT(r) stringify_in_c(.long PPC_RAW_TABORT(r)) /* book3e thread control instructions */ -#define TMRN(x) ((((x) & 0x1f) << 16) | (((x) & 0x3e0) << 6)) -#define MTTMR(tmr, r) stringify_in_c(.long PPC_INST_MTTMR | \ - TMRN(tmr) | ___PPC_RS(r)) -#define MFTMR(tmr, r) stringify_in_c(.long PPC_INST_MFTMR | \ - TMRN(tmr) | ___PPC_RT(r)) +#define MTTMR(tmr, r) stringify_in_c(.long PPC_RAW_MTTMR(tmr, r)) +#define MFTMR(tmr, r) stringify_in_c(.long PPC_RAW_MFTMR(tmr, r)) /* Coprocessor instructions */ -#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_INST_ICSWX | \ - ___PPC_RS(s) | \ - ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_INST_ICSWEPX | \ - ___PPC_RS(s) | \ - ___PPC_RA(a) | \ - ___PPC_RB(b)) - -#define PPC_SLBIA(IH) stringify_in_c(.long PPC_INST_SLBIA | \ - ((IH & 0x7) << 21)) +#define PPC_ICSWX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWX(s, a, b)) +#define PPC_ICSWEPX(s, a, b) stringify_in_c(.long PPC_RAW_ICSWEPX(s, a, b)) + +#define PPC_SLBIA(IH) stringify_in_c(.long PPC_RAW_SLBIA(IH)) /* * These may only be used on ISA v3.0 or later (aka. CPU_FTR_ARCH_300, radix @@ -611,12 +612,8 @@ #define PPC_RADIX_INVALIDATE_ERAT_USER PPC_SLBIA(3) #define PPC_RADIX_INVALIDATE_ERAT_GUEST PPC_SLBIA(6) -#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUD | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | __PPC_RC21) +#define VCMPEQUD_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUD_RC(vrt, vra, vrb)) -#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_INST_VCMPEQUB | \ - ___PPC_RT(vrt) | ___PPC_RA(vra) | \ - ___PPC_RB(vrb) | __PPC_RC21) +#define VCMPEQUB_RC(vrt, vra, vrb) stringify_in_c(.long PPC_RAW_VCMPEQUB_RC(vrt, vra, vrb)) #endif /* _ASM_POWERPC_PPC_OPCODE_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index 6b03dff61a05..b4cc6608131c 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -755,6 +755,8 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define N_SLINE 68 #define N_SO 100 +#define RFSCV .long 0x4c0000a4 + /* * Create an endian fixup trampoline * @@ -774,7 +776,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define FIXUP_ENDIAN #else /* - * This version may be used in in HV or non-HV context. + * This version may be used in HV or non-HV context. * MSR[EE] must be disabled. */ #define FIXUP_ENDIAN \ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 52a67835057a..ed0d633ab5aa 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -237,7 +237,6 @@ struct thread_struct { #ifdef CONFIG_PPC_MEM_KEYS unsigned long amr; unsigned long iamr; - unsigned long uamor; #endif #ifdef CONFIG_KVM_BOOK3S_32_HANDLER void* kvm_shadow_vcpu; /* KVM internal data */ @@ -272,6 +271,10 @@ struct thread_struct { unsigned mmcr0; unsigned used_ebb; + unsigned long mmcr3; + unsigned long sier2; + unsigned long sier3; + #endif }; diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index ac3970fff0d5..155a197c0aa1 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -222,9 +222,14 @@ static inline void set_trap(struct pt_regs *regs, unsigned long val) regs->trap = (regs->trap & TRAP_FLAGS_MASK) | (val & ~TRAP_FLAGS_MASK); } +static inline bool trap_is_scv(struct pt_regs *regs) +{ + return (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && TRAP(regs) == 0x3000); +} + static inline bool trap_is_syscall(struct pt_regs *regs) { - return TRAP(regs) == 0xc00; + return (trap_is_scv(regs) || TRAP(regs) == 0xc00); } static inline bool trap_norestart(struct pt_regs *regs) @@ -238,7 +243,7 @@ static inline void set_trap_norestart(struct pt_regs *regs) } #define arch_has_single_step() (1) -#ifndef CONFIG_BOOK3S_601 +#ifndef CONFIG_PPC_BOOK3S_601 #define arch_has_block_step() (true) #else #define arch_has_block_step() (false) diff --git a/arch/powerpc/include/asm/qspinlock.h b/arch/powerpc/include/asm/qspinlock.h new file mode 100644 index 000000000000..b752d34517b3 --- /dev/null +++ b/arch/powerpc/include/asm/qspinlock.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_QSPINLOCK_H +#define _ASM_POWERPC_QSPINLOCK_H + +#include <asm-generic/qspinlock_types.h> +#include <asm/paravirt.h> + +#define _Q_PENDING_LOOPS (1 << 9) /* not tuned */ + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_queued_spin_unlock(struct qspinlock *lock); + +static __always_inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + if (!is_shared_processor()) + native_queued_spin_lock_slowpath(lock, val); + else + __pv_queued_spin_lock_slowpath(lock, val); +} + +#define queued_spin_unlock queued_spin_unlock +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + if (!is_shared_processor()) + smp_store_release(&lock->locked, 0); + else + __pv_queued_spin_unlock(lock); +} + +#else +extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +#endif + +static __always_inline void queued_spin_lock(struct qspinlock *lock) +{ + u32 val = 0; + + if (likely(atomic_try_cmpxchg_lock(&lock->val, &val, _Q_LOCKED_VAL))) + return; + + queued_spin_lock_slowpath(lock, val); +} +#define queued_spin_lock queued_spin_lock + +#define smp_mb__after_spinlock() smp_mb() + +static __always_inline int queued_spin_is_locked(struct qspinlock *lock) +{ + /* + * This barrier was added to simple spinlocks by commit 51d7d5205d338, + * but it should now be possible to remove it, asm arm64 has done with + * commit c6f5d02b6a0f. + */ + smp_mb(); + return atomic_read(&lock->val); +} +#define queued_spin_is_locked queued_spin_is_locked + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define SPIN_THRESHOLD (1<<15) /* not tuned */ + +static __always_inline void pv_wait(u8 *ptr, u8 val) +{ + if (*ptr != val) + return; + yield_to_any(); + /* + * We could pass in a CPU here if waiting in the queue and yield to + * the previous CPU in the queue. + */ +} + +static __always_inline void pv_kick(int cpu) +{ + prod_cpu(cpu); +} + +extern void __pv_init_lock_hash(void); + +static inline void pv_spinlocks_init(void) +{ + __pv_init_lock_hash(); +} + +#endif + +#include <asm-generic/qspinlock.h> + +#endif /* _ASM_POWERPC_QSPINLOCK_H */ diff --git a/arch/powerpc/include/asm/qspinlock_paravirt.h b/arch/powerpc/include/asm/qspinlock_paravirt.h new file mode 100644 index 000000000000..6b60e7736a47 --- /dev/null +++ b/arch/powerpc/include/asm/qspinlock_paravirt.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_QSPINLOCK_PARAVIRT_H +#define _ASM_POWERPC_QSPINLOCK_PARAVIRT_H + +EXPORT_SYMBOL(__pv_queued_spin_unlock); + +#endif /* _ASM_POWERPC_QSPINLOCK_PARAVIRT_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 88e6c78100d9..88fb88491fe9 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -12,6 +12,7 @@ #ifdef __KERNEL__ #include <linux/stringify.h> +#include <linux/const.h> #include <asm/cputable.h> #include <asm/asm-const.h> #include <asm/feature-fixups.h> @@ -473,7 +474,8 @@ #ifndef SPRN_LPID #define SPRN_LPID 0x13F /* Logical Partition Identifier */ #endif -#define LPID_RSVD 0x3ff /* Reserved LPID for partn switching */ +#define LPID_RSVD_POWER7 0x3ff /* Reserved LPID for partn switching */ +#define LPID_RSVD 0xfff /* Reserved LPID for partn switching */ #define SPRN_HMER 0x150 /* Hypervisor maintenance exception reg */ #define HMER_DEBUG_TRIG (1ul << (63 - 17)) /* Debug trigger */ #define SPRN_HMEER 0x151 /* Hyp maintenance exception enable reg */ @@ -876,7 +878,9 @@ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 #define SPRN_MMCR2 785 +#define SPRN_MMCR3 754 #define SPRN_UMMCR2 769 +#define SPRN_UMMCR3 738 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -886,6 +890,7 @@ #define MMCRA_SLOT 0x07000000UL /* SLOT bits (37-39) */ #define MMCRA_SLOT_SHIFT 24 #define MMCRA_SAMPLE_ENABLE 0x00000001UL /* enable sampling */ +#define MMCRA_BHRB_DISABLE _UL(0x2000000000) // BHRB disable bit for ISA v3.1 #define POWER6_MMCRA_SDSYNC 0x0000080000000000ULL /* SDAR/SIAR synced */ #define POWER6_MMCRA_SIHV 0x0000040000000000ULL #define POWER6_MMCRA_SIPR 0x0000020000000000ULL @@ -918,6 +923,10 @@ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIER2 752 +#define SPRN_SIER3 753 +#define SPRN_USIER2 736 +#define SPRN_USIER3 737 #define SPRN_SIAR 796 #define SPRN_SDAR 797 #define SPRN_TACR 888 @@ -1354,6 +1363,7 @@ #define PVR_ARCH_206p 0x0f100003 #define PVR_ARCH_207 0x0f000004 #define PVR_ARCH_300 0x0f000005 +#define PVR_ARCH_31 0x0f000006 /* Macros for setting and retrieving special purpose registers */ #ifndef __ASSEMBLY__ @@ -1472,7 +1482,7 @@ static inline void update_power8_hid0(unsigned long hid0) { /* * The HID0 update on Power8 should at the very least be - * preceded by a a SYNC instruction followed by an ISYNC + * preceded by a SYNC instruction followed by an ISYNC * instruction */ asm volatile("sync; mtspr %0,%1; isync":: "i"(SPRN_HID0), "r"(hid0)); diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 014968f25f7e..55f9a154c95d 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -215,7 +215,6 @@ inline uint16_t pseries_errorlog_length(struct pseries_errorlog *sect) #define PSERIES_HP_ELOG_ACTION_ADD 1 #define PSERIES_HP_ELOG_ACTION_REMOVE 2 -#define PSERIES_HP_ELOG_ACTION_READD 3 #define PSERIES_HP_ELOG_ID_DRC_NAME 1 #define PSERIES_HP_ELOG_ID_DRC_INDEX 2 @@ -253,8 +252,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); -extern int rtas_online_cpus_mask(cpumask_var_t cpus); -extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(u64 handle); struct rtc_time; diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h index 7c05e95a5c44..fbb8fa32150f 100644 --- a/arch/powerpc/include/asm/security_features.h +++ b/arch/powerpc/include/asm/security_features.h @@ -63,6 +63,8 @@ static inline bool security_ftr_enabled(u64 feature) // bcctr 2,0,0 triggers a hardware assisted count cache flush #define SEC_FTR_BCCTR_FLUSH_ASSIST 0x0000000000000800ull +// bcctr 2,0,0 triggers a hardware assisted link stack flush +#define SEC_FTR_BCCTR_LINK_FLUSH_ASSIST 0x0000000000002000ull // Features indicating need for Spectre/Meltdown mitigations diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index 65676e2325b8..9efbddee2bca 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -30,12 +30,12 @@ void setup_panic(void); #define ARCH_PANIC_TIMEOUT 180 #ifdef CONFIG_PPC_PSERIES -extern void pseries_enable_reloc_on_exc(void); +extern bool pseries_enable_reloc_on_exc(void); extern void pseries_disable_reloc_on_exc(void); extern void pseries_big_endian_exceptions(void); extern void pseries_little_endian_exceptions(void); #else -static inline void pseries_enable_reloc_on_exc(void) {} +static inline bool pseries_enable_reloc_on_exc(void) { return false; } static inline void pseries_disable_reloc_on_exc(void) {} static inline void pseries_big_endian_exceptions(void) {} static inline void pseries_little_endian_exceptions(void) {} diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h new file mode 100644 index 000000000000..9c3c30534333 --- /dev/null +++ b/arch/powerpc/include/asm/simple_spinlock.h @@ -0,0 +1,288 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_H +#define _ASM_POWERPC_SIMPLE_SPINLOCK_H + +/* + * Simple spin lock operations. + * + * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM + * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM + * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM + * Rework to support virtual processors + * + * Type of int is used as a full 64b word is not necessary. + * + * (the type definitions are in asm/simple_spinlock_types.h) + */ +#include <linux/irqflags.h> +#include <asm/paravirt.h> +#include <asm/paca.h> +#include <asm/synch.h> +#include <asm/ppc-opcode.h> + +#ifdef CONFIG_PPC64 +/* use 0x800000yy when locked, where yy == CPU number */ +#ifdef __BIG_ENDIAN__ +#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) +#else +#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index)) +#endif +#else +#define LOCK_TOKEN 1 +#endif + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.slock == 0; +} + +static inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + smp_mb(); + return !arch_spin_value_unlocked(*lock); +} + +/* + * This returns the old value in the lock, so we succeeded + * in getting the lock if the return value is 0. + */ +static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) +{ + unsigned long tmp, token; + + token = LOCK_TOKEN; + __asm__ __volatile__( +"1: " PPC_LWARX(%0,0,%2,1) "\n\ + cmpwi 0,%0,0\n\ + bne- 2f\n\ + stwcx. %1,0,%2\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" + : "=&r" (tmp) + : "r" (token), "r" (&lock->slock) + : "cr0", "memory"); + + return tmp; +} + +static inline int arch_spin_trylock(arch_spinlock_t *lock) +{ + return __arch_spin_trylock(lock) == 0; +} + +/* + * On a system with shared processors (that is, where a physical + * processor is multiplexed between several virtual processors), + * there is no point spinning on a lock if the holder of the lock + * isn't currently scheduled on a physical processor. Instead + * we detect this situation and ask the hypervisor to give the + * rest of our timeslice to the lock holder. + * + * So that we can tell which virtual processor is holding a lock, + * we put 0x80000000 | smp_processor_id() in the lock when it is + * held. Conveniently, we have a word in the paca that holds this + * value. + */ + +#if defined(CONFIG_PPC_SPLPAR) +/* We only yield to the hypervisor if we are in shared processor mode */ +void splpar_spin_yield(arch_spinlock_t *lock); +void splpar_rw_yield(arch_rwlock_t *lock); +#else /* SPLPAR */ +static inline void splpar_spin_yield(arch_spinlock_t *lock) {}; +static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; +#endif + +static inline void spin_yield(arch_spinlock_t *lock) +{ + if (is_shared_processor()) + splpar_spin_yield(lock); + else + barrier(); +} + +static inline void rw_yield(arch_rwlock_t *lock) +{ + if (is_shared_processor()) + splpar_rw_yield(lock); + else + barrier(); +} + +static inline void arch_spin_lock(arch_spinlock_t *lock) +{ + while (1) { + if (likely(__arch_spin_trylock(lock) == 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_spin_yield(lock); + } while (unlikely(lock->slock != 0)); + HMT_medium(); + } +} + +static inline +void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) +{ + unsigned long flags_dis; + + while (1) { + if (likely(__arch_spin_trylock(lock) == 0)) + break; + local_save_flags(flags_dis); + local_irq_restore(flags); + do { + HMT_low(); + if (is_shared_processor()) + splpar_spin_yield(lock); + } while (unlikely(lock->slock != 0)); + HMT_medium(); + local_irq_restore(flags_dis); + } +} +#define arch_spin_lock_flags arch_spin_lock_flags + +static inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + __asm__ __volatile__("# arch_spin_unlock\n\t" + PPC_RELEASE_BARRIER: : :"memory"); + lock->slock = 0; +} + +/* + * Read-write spinlocks, allowing multiple readers + * but only one writer. + * + * NOTE! it is quite common to have readers in interrupts + * but no interrupt writers. For those circumstances we + * can "mix" irq-safe locks - any writer needs to get a + * irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ + +#ifdef CONFIG_PPC64 +#define __DO_SIGN_EXTEND "extsw %0,%0\n" +#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */ +#else +#define __DO_SIGN_EXTEND +#define WRLOCK_TOKEN (-1) +#endif + +/* + * This returns the old value in the lock + 1, + * so we got a read lock if the return value is > 0. + */ +static inline long __arch_read_trylock(arch_rwlock_t *rw) +{ + long tmp; + + __asm__ __volatile__( +"1: " PPC_LWARX(%0,0,%1,1) "\n" + __DO_SIGN_EXTEND +" addic. %0,%0,1\n\ + ble- 2f\n" +" stwcx. %0,0,%1\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" : "=&r" (tmp) + : "r" (&rw->lock) + : "cr0", "xer", "memory"); + + return tmp; +} + +/* + * This returns the old value in the lock, + * so we got the write lock if the return value is 0. + */ +static inline long __arch_write_trylock(arch_rwlock_t *rw) +{ + long tmp, token; + + token = WRLOCK_TOKEN; + __asm__ __volatile__( +"1: " PPC_LWARX(%0,0,%2,1) "\n\ + cmpwi 0,%0,0\n\ + bne- 2f\n" +" stwcx. %1,0,%2\n\ + bne- 1b\n" + PPC_ACQUIRE_BARRIER +"2:" : "=&r" (tmp) + : "r" (token), "r" (&rw->lock) + : "cr0", "memory"); + + return tmp; +} + +static inline void arch_read_lock(arch_rwlock_t *rw) +{ + while (1) { + if (likely(__arch_read_trylock(rw) > 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_rw_yield(rw); + } while (unlikely(rw->lock < 0)); + HMT_medium(); + } +} + +static inline void arch_write_lock(arch_rwlock_t *rw) +{ + while (1) { + if (likely(__arch_write_trylock(rw) == 0)) + break; + do { + HMT_low(); + if (is_shared_processor()) + splpar_rw_yield(rw); + } while (unlikely(rw->lock != 0)); + HMT_medium(); + } +} + +static inline int arch_read_trylock(arch_rwlock_t *rw) +{ + return __arch_read_trylock(rw) > 0; +} + +static inline int arch_write_trylock(arch_rwlock_t *rw) +{ + return __arch_write_trylock(rw) == 0; +} + +static inline void arch_read_unlock(arch_rwlock_t *rw) +{ + long tmp; + + __asm__ __volatile__( + "# read_unlock\n\t" + PPC_RELEASE_BARRIER +"1: lwarx %0,0,%1\n\ + addic %0,%0,-1\n" +" stwcx. %0,0,%1\n\ + bne- 1b" + : "=&r"(tmp) + : "r"(&rw->lock) + : "cr0", "xer", "memory"); +} + +static inline void arch_write_unlock(arch_rwlock_t *rw) +{ + __asm__ __volatile__("# write_unlock\n\t" + PPC_RELEASE_BARRIER: : :"memory"); + rw->lock = 0; +} + +#define arch_spin_relax(lock) spin_yield(lock) +#define arch_read_relax(lock) rw_yield(lock) +#define arch_write_relax(lock) rw_yield(lock) + +/* See include/linux/spinlock.h */ +#define smp_mb__after_spinlock() smp_mb() + +#endif /* _ASM_POWERPC_SIMPLE_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h new file mode 100644 index 000000000000..0f3cdd8faa95 --- /dev/null +++ b/arch/powerpc/include/asm/simple_spinlock_types.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H +#define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H + +#ifndef __LINUX_SPINLOCK_TYPES_H +# error "please don't include this file directly" +#endif + +typedef struct { + volatile unsigned int slock; +} arch_spinlock_t; + +#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } + +typedef struct { + volatile signed int lock; +} arch_rwlock_t; + +#define __ARCH_RW_LOCK_UNLOCKED { 0 } + +#endif /* _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H */ diff --git a/arch/powerpc/include/asm/smu.h b/arch/powerpc/include/asm/smu.h index 8dff086c0cab..4b30a0205c93 100644 --- a/arch/powerpc/include/asm/smu.h +++ b/arch/powerpc/include/asm/smu.h @@ -108,7 +108,7 @@ /* * i2c commands * - * To issue an i2c command, first is to send a parameter block to the + * To issue an i2c command, first is to send a parameter block to * the SMU. This is a command of type 0x9a with 9 bytes of header * eventually followed by data for a write: * diff --git a/arch/powerpc/include/asm/sparsemem.h b/arch/powerpc/include/asm/sparsemem.h index c89b32443cff..1e6fa371cc38 100644 --- a/arch/powerpc/include/asm/sparsemem.h +++ b/arch/powerpc/include/asm/sparsemem.h @@ -17,12 +17,6 @@ extern int create_section_mapping(unsigned long start, unsigned long end, int nid, pgprot_t prot); extern int remove_section_mapping(unsigned long start, unsigned long end); -#ifdef CONFIG_PPC_BOOK3S_64 -extern int resize_hpt_for_hotplug(unsigned long new_mem_size); -#else -static inline int resize_hpt_for_hotplug(unsigned long new_mem_size) { return 0; } -#endif - #ifdef CONFIG_NUMA extern int hot_add_scn_to_nid(unsigned long scn_addr); #else diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 2d620896cdae..6ec72282888d 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -3,312 +3,16 @@ #define __ASM_SPINLOCK_H #ifdef __KERNEL__ -/* - * Simple spin lock operations. - * - * Copyright (C) 2001-2004 Paul Mackerras <paulus@au.ibm.com>, IBM - * Copyright (C) 2001 Anton Blanchard <anton@au.ibm.com>, IBM - * Copyright (C) 2002 Dave Engebretsen <engebret@us.ibm.com>, IBM - * Rework to support virtual processors - * - * Type of int is used as a full 64b word is not necessary. - * - * (the type definitions are in asm/spinlock_types.h) - */ -#include <linux/jump_label.h> -#include <linux/irqflags.h> -#ifdef CONFIG_PPC64 -#include <asm/paca.h> -#include <asm/hvcall.h> -#endif -#include <asm/synch.h> -#include <asm/ppc-opcode.h> - -#ifdef CONFIG_PPC64 -/* use 0x800000yy when locked, where yy == CPU number */ -#ifdef __BIG_ENDIAN__ -#define LOCK_TOKEN (*(u32 *)(&get_paca()->lock_token)) -#else -#define LOCK_TOKEN (*(u32 *)(&get_paca()->paca_index)) -#endif +#ifdef CONFIG_PPC_QUEUED_SPINLOCKS +#include <asm/qspinlock.h> +#include <asm/qrwlock.h> #else -#define LOCK_TOKEN 1 +#include <asm/simple_spinlock.h> #endif -#ifdef CONFIG_PPC_PSERIES -DECLARE_STATIC_KEY_FALSE(shared_processor); - -#define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) -{ - if (!static_branch_unlikely(&shared_processor)) - return false; - return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1); -} -#endif - -static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) -{ - return lock.slock == 0; -} - -static inline int arch_spin_is_locked(arch_spinlock_t *lock) -{ - smp_mb(); - return !arch_spin_value_unlocked(*lock); -} - -/* - * This returns the old value in the lock, so we succeeded - * in getting the lock if the return value is 0. - */ -static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock) -{ - unsigned long tmp, token; - - token = LOCK_TOKEN; - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%2,1) "\n\ - cmpwi 0,%0,0\n\ - bne- 2f\n\ - stwcx. %1,0,%2\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" - : "=&r" (tmp) - : "r" (token), "r" (&lock->slock) - : "cr0", "memory"); - - return tmp; -} - -static inline int arch_spin_trylock(arch_spinlock_t *lock) -{ - return __arch_spin_trylock(lock) == 0; -} - -/* - * On a system with shared processors (that is, where a physical - * processor is multiplexed between several virtual processors), - * there is no point spinning on a lock if the holder of the lock - * isn't currently scheduled on a physical processor. Instead - * we detect this situation and ask the hypervisor to give the - * rest of our timeslice to the lock holder. - * - * So that we can tell which virtual processor is holding a lock, - * we put 0x80000000 | smp_processor_id() in the lock when it is - * held. Conveniently, we have a word in the paca that holds this - * value. - */ - -#if defined(CONFIG_PPC_SPLPAR) -/* We only yield to the hypervisor if we are in shared processor mode */ -void splpar_spin_yield(arch_spinlock_t *lock); -void splpar_rw_yield(arch_rwlock_t *lock); -#else /* SPLPAR */ -static inline void splpar_spin_yield(arch_spinlock_t *lock) {}; -static inline void splpar_rw_yield(arch_rwlock_t *lock) {}; -#endif - -static inline bool is_shared_processor(void) -{ -#ifdef CONFIG_PPC_SPLPAR - return static_branch_unlikely(&shared_processor); -#else - return false; -#endif -} - -static inline void spin_yield(arch_spinlock_t *lock) -{ - if (is_shared_processor()) - splpar_spin_yield(lock); - else - barrier(); -} - -static inline void rw_yield(arch_rwlock_t *lock) -{ - if (is_shared_processor()) - splpar_rw_yield(lock); - else - barrier(); -} - -static inline void arch_spin_lock(arch_spinlock_t *lock) -{ - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - } -} - -static inline -void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long flags_dis; - - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - local_save_flags(flags_dis); - local_irq_restore(flags); - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - local_irq_restore(flags_dis); - } -} -#define arch_spin_lock_flags arch_spin_lock_flags - -static inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __asm__ __volatile__("# arch_spin_unlock\n\t" - PPC_RELEASE_BARRIER: : :"memory"); - lock->slock = 0; -} - -/* - * Read-write spinlocks, allowing multiple readers - * but only one writer. - * - * NOTE! it is quite common to have readers in interrupts - * but no interrupt writers. For those circumstances we - * can "mix" irq-safe locks - any writer needs to get a - * irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ - -#ifdef CONFIG_PPC64 -#define __DO_SIGN_EXTEND "extsw %0,%0\n" -#define WRLOCK_TOKEN LOCK_TOKEN /* it's negative */ -#else -#define __DO_SIGN_EXTEND -#define WRLOCK_TOKEN (-1) +#ifndef CONFIG_PARAVIRT_SPINLOCKS +static inline void pv_spinlocks_init(void) { } #endif -/* - * This returns the old value in the lock + 1, - * so we got a read lock if the return value is > 0. - */ -static inline long __arch_read_trylock(arch_rwlock_t *rw) -{ - long tmp; - - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%1,1) "\n" - __DO_SIGN_EXTEND -" addic. %0,%0,1\n\ - ble- 2f\n" -" stwcx. %0,0,%1\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" : "=&r" (tmp) - : "r" (&rw->lock) - : "cr0", "xer", "memory"); - - return tmp; -} - -/* - * This returns the old value in the lock, - * so we got the write lock if the return value is 0. - */ -static inline long __arch_write_trylock(arch_rwlock_t *rw) -{ - long tmp, token; - - token = WRLOCK_TOKEN; - __asm__ __volatile__( -"1: " PPC_LWARX(%0,0,%2,1) "\n\ - cmpwi 0,%0,0\n\ - bne- 2f\n" -" stwcx. %1,0,%2\n\ - bne- 1b\n" - PPC_ACQUIRE_BARRIER -"2:" : "=&r" (tmp) - : "r" (token), "r" (&rw->lock) - : "cr0", "memory"); - - return tmp; -} - -static inline void arch_read_lock(arch_rwlock_t *rw) -{ - while (1) { - if (likely(__arch_read_trylock(rw) > 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_rw_yield(rw); - } while (unlikely(rw->lock < 0)); - HMT_medium(); - } -} - -static inline void arch_write_lock(arch_rwlock_t *rw) -{ - while (1) { - if (likely(__arch_write_trylock(rw) == 0)) - break; - do { - HMT_low(); - if (is_shared_processor()) - splpar_rw_yield(rw); - } while (unlikely(rw->lock != 0)); - HMT_medium(); - } -} - -static inline int arch_read_trylock(arch_rwlock_t *rw) -{ - return __arch_read_trylock(rw) > 0; -} - -static inline int arch_write_trylock(arch_rwlock_t *rw) -{ - return __arch_write_trylock(rw) == 0; -} - -static inline void arch_read_unlock(arch_rwlock_t *rw) -{ - long tmp; - - __asm__ __volatile__( - "# read_unlock\n\t" - PPC_RELEASE_BARRIER -"1: lwarx %0,0,%1\n\ - addic %0,%0,-1\n" -" stwcx. %0,0,%1\n\ - bne- 1b" - : "=&r"(tmp) - : "r"(&rw->lock) - : "cr0", "xer", "memory"); -} - -static inline void arch_write_unlock(arch_rwlock_t *rw) -{ - __asm__ __volatile__("# write_unlock\n\t" - PPC_RELEASE_BARRIER: : :"memory"); - rw->lock = 0; -} - -#define arch_spin_relax(lock) spin_yield(lock) -#define arch_read_relax(lock) rw_yield(lock) -#define arch_write_relax(lock) rw_yield(lock) - -/* See include/linux/spinlock.h */ -#define smp_mb__after_spinlock() smp_mb() - #endif /* __KERNEL__ */ #endif /* __ASM_SPINLOCK_H */ diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h index 87adaf13b7e8..c5d742f18021 100644 --- a/arch/powerpc/include/asm/spinlock_types.h +++ b/arch/powerpc/include/asm/spinlock_types.h @@ -6,16 +6,11 @@ # error "please don't include this file directly" #endif -typedef struct { - volatile unsigned int slock; -} arch_spinlock_t; - -#define __ARCH_SPIN_LOCK_UNLOCKED { 0 } - -typedef struct { - volatile signed int lock; -} arch_rwlock_t; - -#define __ARCH_RW_LOCK_UNLOCKED { 0 } +#ifdef CONFIG_PPC_QUEUED_SPINLOCKS +#include <asm-generic/qspinlock_types.h> +#include <asm-generic/qrwlock_types.h> +#else +#include <asm/simple_spinlock_types.h> +#endif #endif diff --git a/arch/powerpc/include/asm/sstep.h b/arch/powerpc/include/asm/sstep.h index 3b01c69a44aa..972ed0df154d 100644 --- a/arch/powerpc/include/asm/sstep.h +++ b/arch/powerpc/include/asm/sstep.h @@ -40,6 +40,7 @@ enum instruction_type { CACHEOP, BARRIER, SYSCALL, + SYSCALL_VECTORED_0, MFMSR, MTMSR, RFI, @@ -104,6 +105,12 @@ enum instruction_type { #define MKOP(t, f, s) ((t) | (f) | SIZE(s)) +/* Prefix instruction operands */ +#define GET_PREFIX_RA(i) (((i) >> 16) & 0x1f) +#define GET_PREFIX_R(i) ((i) & (1ul << 20)) + +extern s32 patch__exec_instr; + struct instruction_op { int type; int reg; diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h index b72692702f35..283552cd0e58 100644 --- a/arch/powerpc/include/asm/string.h +++ b/arch/powerpc/include/asm/string.h @@ -28,7 +28,7 @@ extern void * memcpy(void *,const void *,__kernel_size_t); extern void * memmove(void *,const void *,__kernel_size_t); extern int memcmp(const void *,const void *,__kernel_size_t); extern void * memchr(const void *,int,__kernel_size_t); -extern void * memcpy_flushcache(void *,const void *,__kernel_size_t); +void memcpy_flushcache(void *dest, const void *src, size_t size); void *__memset(void *s, int c, __kernel_size_t count); void *__memcpy(void *to, const void *from, __kernel_size_t n); diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index b287cfc2dd85..cb326720a8a1 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -39,7 +39,6 @@ struct div_result { }; /* Accessor functions for the timebase (RTC on 601) registers. */ -/* If one day CONFIG_POWER is added just define __USE_RTC as 1 */ #define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index d2d2c4bd8435..6047402b0a4d 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -17,7 +17,7 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_BOOK3S_601)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) return 0; return mftb(); diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 862985cf5180..fbc6f3002f23 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -12,7 +12,6 @@ #ifndef __powerpc64__ #include <linux/pgtable.h> #endif -#include <asm/pgalloc.h> #ifndef __powerpc64__ #include <asm/page.h> #include <asm/mmu.h> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 2db7ba789720..f0b6300e7dd3 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -43,7 +43,6 @@ extern void __init dump_numa_cpu_topology(void); extern int sysfs_add_device_to_node(struct device *dev, int nid); extern void sysfs_remove_device_from_node(struct device *dev, int nid); -extern int numa_update_cpu_topology(bool cpus_locked); static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) { @@ -78,11 +77,6 @@ static inline void sysfs_remove_device_from_node(struct device *dev, { } -static inline int numa_update_cpu_topology(bool cpus_locked) -{ - return 0; -} - static inline void update_numa_cpu_lookup_table(unsigned int cpu, int node) {} static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) @@ -93,32 +87,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) #endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) -extern int start_topology_update(void); -extern int stop_topology_update(void); -extern int prrn_is_enabled(void); extern int find_and_online_cpu_nid(int cpu); -extern int timed_topology_update(int nsecs); #else -static inline int start_topology_update(void) -{ - return 0; -} -static inline int stop_topology_update(void) -{ - return 0; -} -static inline int prrn_is_enabled(void) -{ - return 0; -} static inline int find_and_online_cpu_nid(int cpu) { return 0; } -static inline int timed_topology_update(int nsecs) -{ - return 0; -} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ @@ -141,7 +115,6 @@ int get_physical_package_id(int cpu); #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) -int dlpar_cpu_readd(int cpu); #endif #endif diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 64c04ab09112..00699903f1ef 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -38,8 +38,7 @@ static inline void set_fs(mm_segment_t fs) set_thread_flag(TIF_FSCHECK); } -#define segment_eq(a, b) ((a).seg == (b).seg) - +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define user_addr_max() (get_fs().seg) #ifdef __powerpc64__ diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h index d08ea11b271c..309b4d65b74f 100644 --- a/arch/powerpc/include/asm/xive.h +++ b/arch/powerpc/include/asm/xive.h @@ -155,7 +155,6 @@ static inline void xive_smp_probe(void) { } static inline int xive_smp_prepare_cpu(unsigned int cpu) { return -EINVAL; } static inline void xive_smp_setup_cpu(void) { } static inline void xive_smp_disable_cpu(void) { } -static inline void xive_kexec_teardown_cpu(int secondary) { } static inline void xive_shutdown(void) { } static inline void xive_flush_interrupt(void) { } diff --git a/arch/powerpc/include/uapi/asm/kvm.h b/arch/powerpc/include/uapi/asm/kvm.h index 264e266a85bf..c3af3f324c5a 100644 --- a/arch/powerpc/include/uapi/asm/kvm.h +++ b/arch/powerpc/include/uapi/asm/kvm.h @@ -640,6 +640,11 @@ struct kvm_ppc_cpu_char { #define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf) #define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0) +/* POWER10 registers */ +#define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1) +#define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2) +#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index c0c737215b00..3a700351feca 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -11,7 +11,7 @@ #include <asm-generic/mman-common.h> -#define PROT_SAO 0x10 /* Strong Access Ordering */ +#define PROT_SAO 0x10 /* Unsupported since v5.9 */ #define MAP_RENAME MAP_ANONYMOUS /* In SunOS terminology */ #define MAP_NORESERVE 0x40 /* don't reserve swap pages */ diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h index 9ccecc1d6840..50ef95e2f5b1 100644 --- a/arch/powerpc/include/uapi/asm/papr_pdsm.h +++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h @@ -72,6 +72,11 @@ #define PAPR_PDSM_DIMM_CRITICAL 2 #define PAPR_PDSM_DIMM_FATAL 3 +/* struct nd_papr_pdsm_health.extension_flags field flags */ + +/* Indicate that the 'dimm_fuel_gauge' field is valid */ +#define PDSM_DIMM_HEALTH_RUN_GAUGE_VALID 1 + /* * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH * Various flags indicate the health status of the dimm. @@ -84,6 +89,7 @@ * dimm_locked : Contents of the dimm cant be modified until CEC reboot * dimm_encrypted : Contents of dimm are encrypted. * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX + * dimm_fuel_gauge : Life remaining of DIMM as a percentage from 0-100 */ struct nd_papr_pdsm_health { union { @@ -96,6 +102,9 @@ struct nd_papr_pdsm_health { __u8 dimm_locked; __u8 dimm_encrypted; __u16 dimm_health; + + /* Extension flag PDSM_DIMM_HEALTH_RUN_GAUGE_VALID */ + __u16 dimm_fuel_gauge; }; __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; }; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 244542ae2a91..cbf41fb4ee89 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -16,7 +16,7 @@ CFLAGS_prom_init.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) -CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_prom_init.o += -fno-stack-protector CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_prom_init.o += -ffreestanding @@ -45,11 +45,10 @@ obj-y := cputable.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o + of_platform.o prom_parse.o firmware.o obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ - paca.o nvram_64.o firmware.o note.o \ - syscall_64.o + paca.o nvram_64.o note.o syscall_64.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o @@ -71,7 +70,7 @@ obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o obj-$(CONFIG_RTAS_PROC) += rtas-proc.o obj-$(CONFIG_PPC_DT_CPU_FTRS) += dt_cpu_ftrs.o -obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ +obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_cache.o \ eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o obj-$(CONFIG_CRASH_DUMP) += crash_dump.o diff --git a/arch/powerpc/kernel/align.c b/arch/powerpc/kernel/align.c index 1f1ce8b86d5b..c7797eb958c7 100644 --- a/arch/powerpc/kernel/align.c +++ b/arch/powerpc/kernel/align.c @@ -178,11 +178,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __get_user_inatomic(temp.v[1], p++); ret |= __get_user_inatomic(temp.v[2], p++); ret |= __get_user_inatomic(temp.v[3], p++); - /* fall through */ + fallthrough; case 4: ret |= __get_user_inatomic(temp.v[4], p++); ret |= __get_user_inatomic(temp.v[5], p++); - /* fall through */ + fallthrough; case 2: ret |= __get_user_inatomic(temp.v[6], p++); ret |= __get_user_inatomic(temp.v[7], p++); @@ -263,11 +263,11 @@ static int emulate_spe(struct pt_regs *regs, unsigned int reg, ret |= __put_user_inatomic(data.v[1], p++); ret |= __put_user_inatomic(data.v[2], p++); ret |= __put_user_inatomic(data.v[3], p++); - /* fall through */ + fallthrough; case 4: ret |= __put_user_inatomic(data.v[4], p++); ret |= __put_user_inatomic(data.v[5], p++); - /* fall through */ + fallthrough; case 2: ret |= __put_user_inatomic(data.v[6], p++); ret |= __put_user_inatomic(data.v[7], p++); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6657dc6b2336..8711c2164b45 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -559,6 +559,8 @@ int main(void) OFFSET(VCPU_IRQ_PENDING, kvm_vcpu, arch.irq_pending); OFFSET(VCPU_DBELL_REQ, kvm_vcpu, arch.doorbell_request); OFFSET(VCPU_MMCR, kvm_vcpu, arch.mmcr); + OFFSET(VCPU_MMCRA, kvm_vcpu, arch.mmcra); + OFFSET(VCPU_MMCRS, kvm_vcpu, arch.mmcrs); OFFSET(VCPU_PMC, kvm_vcpu, arch.pmc); OFFSET(VCPU_SPMC, kvm_vcpu, arch.spmc); OFFSET(VCPU_SIAR, kvm_vcpu, arch.siar); @@ -696,6 +698,9 @@ int main(void) HSTATE_FIELD(HSTATE_SDAR, host_mmcr[4]); HSTATE_FIELD(HSTATE_MMCR2, host_mmcr[5]); HSTATE_FIELD(HSTATE_SIER, host_mmcr[6]); + HSTATE_FIELD(HSTATE_MMCR3, host_mmcr[7]); + HSTATE_FIELD(HSTATE_SIER2, host_mmcr[8]); + HSTATE_FIELD(HSTATE_SIER3, host_mmcr[9]); HSTATE_FIELD(HSTATE_PMC1, host_pmc[0]); HSTATE_FIELD(HSTATE_PMC2, host_pmc[1]); HSTATE_FIELD(HSTATE_PMC3, host_pmc[2]); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index 470336277c67..65ab9fcebd31 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -7,6 +7,8 @@ * Author: Nathan Lynch */ +#define pr_fmt(fmt) "cacheinfo: " fmt + #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/kernel.h> @@ -166,7 +168,7 @@ static void release_cache_debugcheck(struct cache *cache) list_for_each_entry(iter, &cache_list, list) WARN_ONCE(iter->next_local == cache, - "cache for %pOF(%s) refers to cache for %pOF(%s)\n", + "cache for %pOFP(%s) refers to cache for %pOFP(%s)\n", iter->ofnode, cache_type_string(iter), cache->ofnode, @@ -178,7 +180,7 @@ static void release_cache(struct cache *cache) if (!cache) return; - pr_debug("freeing L%d %s cache for %pOF\n", cache->level, + pr_debug("freeing L%d %s cache for %pOFP\n", cache->level, cache_type_string(cache), cache->ofnode); release_cache_debugcheck(cache); @@ -193,7 +195,7 @@ static void cache_cpu_set(struct cache *cache, int cpu) while (next) { WARN_ONCE(cpumask_test_cpu(cpu, &next->shared_cpu_map), - "CPU %i already accounted in %pOF(%s)\n", + "CPU %i already accounted in %pOFP(%s)\n", cpu, next->ofnode, cache_type_string(next)); cpumask_set_cpu(cpu, &next->shared_cpu_map); @@ -352,7 +354,7 @@ static int cache_is_unified_d(const struct device_node *np) static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level) { - pr_debug("creating L%d ucache for %pOF\n", level, node); + pr_debug("creating L%d ucache for %pOFP\n", level, node); return new_cache(cache_is_unified_d(node), level, node); } @@ -362,7 +364,7 @@ static struct cache *cache_do_one_devnode_split(struct device_node *node, { struct cache *dcache, *icache; - pr_debug("creating L%d dcache and icache for %pOF\n", level, + pr_debug("creating L%d dcache and icache for %pOFP\n", level, node); dcache = new_cache(CACHE_TYPE_DATA, level, node); @@ -418,12 +420,27 @@ static void link_cache_lists(struct cache *smaller, struct cache *bigger) } smaller->next_local = bigger; + + /* + * The cache->next_local list sorts by level ascending: + * L1d -> L1i -> L2 -> L3 ... + */ + WARN_ONCE((smaller->level == 1 && bigger->level > 2) || + (smaller->level > 1 && bigger->level != smaller->level + 1), + "linking L%i cache %pOFP to L%i cache %pOFP; skipped a level?\n", + smaller->level, smaller->ofnode, bigger->level, bigger->ofnode); } static void do_subsidiary_caches_debugcheck(struct cache *cache) { - WARN_ON_ONCE(cache->level != 1); - WARN_ON_ONCE(!of_node_is_type(cache->ofnode, "cpu")); + WARN_ONCE(cache->level != 1, + "instantiating cache chain from L%d %s cache for " + "%pOFP instead of an L1\n", cache->level, + cache_type_string(cache), cache->ofnode); + WARN_ONCE(!of_node_is_type(cache->ofnode, "cpu"), + "instantiating cache chain from node %pOFP of type '%s' " + "instead of a cpu node\n", cache->ofnode, + of_node_get_device_type(cache->ofnode)); } static void do_subsidiary_caches(struct cache *cache) @@ -647,12 +664,13 @@ static const struct cpumask *get_big_core_shared_cpu_map(int cpu, struct cache * return &cache->shared_cpu_map; } -static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +static ssize_t +show_shared_cpumap(struct kobject *k, struct kobj_attribute *attr, char *buf, bool list) { struct cache_index_dir *index; struct cache *cache; const struct cpumask *mask; - int ret, cpu; + int cpu; index = kobj_to_cache_index_dir(k); cache = index->cache; @@ -664,16 +682,25 @@ static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *att mask = &cache->shared_cpu_map; } - ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n", - cpumask_pr_args(mask)); - buf[ret++] = '\n'; - buf[ret] = '\0'; - return ret; + return cpumap_print_to_pagebuf(list, buf, mask); +} + +static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + return show_shared_cpumap(k, attr, buf, false); +} + +static ssize_t shared_cpu_list_show(struct kobject *k, struct kobj_attribute *attr, char *buf) +{ + return show_shared_cpumap(k, attr, buf, true); } static struct kobj_attribute cache_shared_cpu_map_attr = __ATTR(shared_cpu_map, 0444, shared_cpu_map_show, NULL); +static struct kobj_attribute cache_shared_cpu_list_attr = + __ATTR(shared_cpu_list, 0444, shared_cpu_list_show, NULL); + /* Attributes which should always be created -- the kobject/sysfs core * does this automatically via kobj_type->default_attrs. This is the * minimum data required to uniquely identify a cache. @@ -682,6 +709,7 @@ static struct attribute *cache_index_default_attrs[] = { &cache_type_attr.attr, &cache_level_attr.attr, &cache_shared_cpu_map_attr.attr, + &cache_shared_cpu_list_attr.attr, NULL, }; @@ -733,13 +761,13 @@ static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir) rc = attr->show(&dir->kobj, attr, buf); if (rc <= 0) { pr_debug("not creating %s attribute for " - "%pOF(%s) (rc = %zd)\n", + "%pOFP(%s) (rc = %zd)\n", attr->attr.name, cache->ofnode, cache_type, rc); continue; } if (sysfs_create_file(&dir->kobj, &attr->attr)) - pr_debug("could not create %s attribute for %pOF(%s)\n", + pr_debug("could not create %s attribute for %pOFP(%s)\n", attr->attr.name, cache->ofnode, cache_type); } @@ -855,7 +883,7 @@ static void cache_cpu_clear(struct cache *cache, int cpu) struct cache *next = cache->next_local; WARN_ONCE(!cpumask_test_cpu(cpu, &cache->shared_cpu_map), - "CPU %i not accounted in %pOF(%s)\n", + "CPU %i not accounted in %pOFP(%s)\n", cpu, cache->ofnode, cache_type_string(cache)); diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index efdcfa714106..704e8b9501ee 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -94,13 +94,15 @@ _GLOBAL(__restore_cpu_power8) _GLOBAL(__setup_cpu_power10) mflr r11 bl __init_FSCR_power10 + bl __init_PMU + bl __init_PMU_ISA31 b 1f _GLOBAL(__setup_cpu_power9) mflr r11 - bl __init_FSCR -1: bl __init_PMU - bl __init_hvmode_206 + bl __init_FSCR_power9 + bl __init_PMU +1: bl __init_hvmode_206 mtlr r11 beqlr li r0,0 @@ -124,13 +126,15 @@ _GLOBAL(__setup_cpu_power9) _GLOBAL(__restore_cpu_power10) mflr r11 bl __init_FSCR_power10 + bl __init_PMU + bl __init_PMU_ISA31 b 1f _GLOBAL(__restore_cpu_power9) mflr r11 - bl __init_FSCR -1: bl __init_PMU - mfmsr r3 + bl __init_FSCR_power9 + bl __init_PMU +1: mfmsr r3 rldicl. r0,r3,4,63 mtlr r11 beqlr @@ -198,6 +202,12 @@ __init_FSCR_power10: mtspr SPRN_FSCR, r3 // fall through +__init_FSCR_power9: + mfspr r3, SPRN_FSCR + ori r3, r3, FSCR_SCV + mtspr SPRN_FSCR, r3 + // fall through + __init_FSCR: mfspr r3,SPRN_FSCR ori r3,r3,FSCR_TAR|FSCR_EBB @@ -233,3 +243,10 @@ __init_PMU_ISA207: li r5,0 mtspr SPRN_MMCRS,r5 blr + +__init_PMU_ISA31: + li r5,0 + mtspr SPRN_MMCR3,r5 + LOAD_REG_IMMEDIATE(r5, MMCRA_BHRB_DISABLE) + mtspr SPRN_MMCRA,r5 + blr diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index b4066354f073..3d406a9626e8 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -120,7 +120,8 @@ extern void __restore_cpu_e6500(void); #define COMMON_USER2_POWER9 (COMMON_USER2_POWER8 | \ PPC_FEATURE2_ARCH_3_00 | \ PPC_FEATURE2_HAS_IEEE128 | \ - PPC_FEATURE2_DARN ) + PPC_FEATURE2_DARN | \ + PPC_FEATURE2_SCV) #define COMMON_USER_POWER10 COMMON_USER_POWER9 #define COMMON_USER2_POWER10 (COMMON_USER2_POWER9 | \ PPC_FEATURE2_ARCH_3_1 | \ diff --git a/arch/powerpc/kernel/dawr.c b/arch/powerpc/kernel/dawr.c index 500f52fa4711..cdc2dccb987d 100644 --- a/arch/powerpc/kernel/dawr.c +++ b/arch/powerpc/kernel/dawr.c @@ -37,7 +37,7 @@ int set_dawr(int nr, struct arch_hw_breakpoint *brk) dawrx |= (mrd & 0x3f) << (63 - 53); if (ppc_md.set_dawr) - return ppc_md.set_dawr(dawr, dawrx); + return ppc_md.set_dawr(nr, dawr, dawrx); if (nr == 0) { mtspr(SPRN_DAWR0, dawr); diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f17ff1200eaa..52680cf07c9d 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -18,61 +18,6 @@ #ifdef CONFIG_SMP -/* - * Doorbells must only be used if CPU_FTR_DBELL is available. - * msgsnd is used in HV, and msgsndp is used in !HV. - * - * These should be used by platform code that is aware of restrictions. - * Other arch code should use ->cause_ipi. - * - * doorbell_global_ipi() sends a dbell to any target CPU. - * Must be used only by architectures that address msgsnd target - * by PIR/get_hard_smp_processor_id. - */ -void doorbell_global_ipi(int cpu) -{ - u32 tag = get_hard_smp_processor_id(cpu); - - kvmppc_set_host_ipi(cpu); - /* Order previous accesses vs. msgsnd, which is treated as a store */ - ppc_msgsnd_sync(); - ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); -} - -/* - * doorbell_core_ipi() sends a dbell to a target CPU in the same core. - * Must be used only by architectures that address msgsnd target - * by TIR/cpu_thread_in_core. - */ -void doorbell_core_ipi(int cpu) -{ - u32 tag = cpu_thread_in_core(cpu); - - kvmppc_set_host_ipi(cpu); - /* Order previous accesses vs. msgsnd, which is treated as a store */ - ppc_msgsnd_sync(); - ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag); -} - -/* - * Attempt to cause a core doorbell if destination is on the same core. - * Returns 1 on success, 0 on failure. - */ -int doorbell_try_core_ipi(int cpu) -{ - int this_cpu = get_cpu(); - int ret = 0; - - if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) { - doorbell_core_ipi(cpu); - ret = 1; - } - - put_cpu(); - - return ret; -} - void doorbell_exception(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 3a409517c031..6f8c0c6b937a 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -24,7 +24,6 @@ /* Device-tree visible constants follow */ -#define ISA_V2_07B 2070 #define ISA_V3_0B 3000 #define ISA_V3_1 3100 @@ -67,6 +66,7 @@ struct dt_cpu_feature { extern long __machine_check_early_realmode_p8(struct pt_regs *regs); extern long __machine_check_early_realmode_p9(struct pt_regs *regs); +extern long __machine_check_early_realmode_p10(struct pt_regs *regs); static int hv_mode; @@ -337,6 +337,7 @@ static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f) #ifdef CONFIG_PPC_RADIX_MMU cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; + cur_cpu_spec->mmu_features |= MMU_FTR_GTSE; cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; return 1; @@ -450,6 +451,39 @@ static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f) return 1; } +static void init_pmu_power10(void) +{ + init_pmu_power9(); + + mtspr(SPRN_MMCR3, 0); + mtspr(SPRN_MMCRA, MMCRA_BHRB_DISABLE); +} + +static int __init feat_enable_pmu_power10(struct dt_cpu_feature *f) +{ + hfscr_pmu_enable(); + + init_pmu_power10(); + init_pmu_registers = init_pmu_power10; + + cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT; + + cur_cpu_spec->num_pmcs = 6; + cur_cpu_spec->pmc_type = PPC_PMC_IBM; + cur_cpu_spec->oprofile_cpu_type = "ppc64/power10"; + + return 1; +} + +static int __init feat_enable_mce_power10(struct dt_cpu_feature *f) +{ + cur_cpu_spec->platform = "power10"; + cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p10; + + return 1; +} + static int __init feat_enable_tm(struct dt_cpu_feature *f) { #ifdef CONFIG_PPC_TRANSACTIONAL_MEM @@ -587,6 +621,7 @@ static struct dt_cpu_feature_match __initdata {"little-endian", feat_enable_le, CPU_FTR_REAL_LE}, {"smt", feat_enable_smt, 0}, {"interrupt-facilities", feat_enable, 0}, + {"system-call-vectored", feat_enable, 0}, {"timer-facilities", feat_enable, 0}, {"timer-facilities-v3", feat_enable, 0}, {"debug-facilities", feat_enable, 0}, @@ -622,7 +657,7 @@ static struct dt_cpu_feature_match __initdata {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, {"processor-utilization-of-resources-register", feat_enable_purr, 0}, {"no-execute", feat_enable, 0}, - {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, + /* strong-access-ordering is unused */ {"cache-inhibited-large-page", feat_enable_large_ci, 0}, {"coprocessor-icswx", feat_enable, 0}, {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0}, @@ -638,7 +673,9 @@ static struct dt_cpu_feature_match __initdata {"group-start-register", feat_enable, 0}, {"pc-relative-addressing", feat_enable, 0}, {"machine-check-power9", feat_enable_mce_power9, 0}, + {"machine-check-power10", feat_enable_mce_power10, 0}, {"performance-monitor-power9", feat_enable_pmu_power9, 0}, + {"performance-monitor-power10", feat_enable_pmu_power10, 0}, {"event-based-branch-v3", feat_enable, 0}, {"random-number-generator", feat_enable, 0}, {"system-call-vectored", feat_disable, 0}, @@ -649,6 +686,7 @@ static struct dt_cpu_feature_match __initdata {"wait-v3", feat_enable, 0}, {"prefix-instructions", feat_enable, 0}, {"matrix-multiply-assist", feat_enable_mma, 0}, + {"debug-facilities-v31", feat_enable, CPU_FTR_DAWR1}, }; static bool __initdata using_dt_cpu_ftrs; @@ -674,12 +712,12 @@ static void __init cpufeatures_setup_start(u32 isa) { pr_info("setup for ISA %d\n", isa); - if (isa >= 3000) { + if (isa >= ISA_V3_0B) { cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300; cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00; } - if (isa >= 3100) { + if (isa >= ISA_V3_1) { cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_31; cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_1; } @@ -776,12 +814,6 @@ static __init void cpufeatures_cpu_quirks(void) } update_tlbie_feature_flag(version); - /* - * PKEY was not in the initial base or feature node - * specification, but it should become optional in the next - * cpu feature version sequence. - */ - cur_cpu_spec->cpu_features |= CPU_FTR_PKEY; } static void __init cpufeatures_setup_finished(void) diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index d407981dec76..94682382fc8c 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -167,39 +167,33 @@ void eeh_show_enabled(void) */ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); u32 cfg; int cap, i; int n = 0, l = 0; char buffer[128]; - if (!pdn) { - pr_warn("EEH: Note: No error log for absent device.\n"); - return 0; - } - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", - pdn->phb->global_number, pdn->busno, - PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + edev->pe->phb->global_number, edev->bdfn >> 8, + PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn)); pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", - pdn->phb->global_number, pdn->busno, - PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); + edev->pe->phb->global_number, edev->bdfn >> 8, + PCI_SLOT(edev->bdfn), PCI_FUNC(edev->bdfn)); - eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg); + eeh_ops->read_config(edev, PCI_VENDOR_ID, 4, &cfg); n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg); pr_warn("EEH: PCI device/vendor: %08x\n", cfg); - eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg); + eeh_ops->read_config(edev, PCI_COMMAND, 4, &cfg); n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg); pr_warn("EEH: PCI cmd/status register: %08x\n", cfg); /* Gather bridge-specific registers */ if (edev->mode & EEH_DEV_BRIDGE) { - eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg); + eeh_ops->read_config(edev, PCI_SEC_STATUS, 2, &cfg); n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg); pr_warn("EEH: Bridge secondary status: %04x\n", cfg); - eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg); + eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &cfg); n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg); pr_warn("EEH: Bridge control: %04x\n", cfg); } @@ -207,11 +201,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) /* Dump out the PCI-X command and status regs */ cap = edev->pcix_cap; if (cap) { - eeh_ops->read_config(pdn, cap, 4, &cfg); + eeh_ops->read_config(edev, cap, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg); pr_warn("EEH: PCI-X cmd: %08x\n", cfg); - eeh_ops->read_config(pdn, cap+4, 4, &cfg); + eeh_ops->read_config(edev, cap+4, 4, &cfg); n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg); pr_warn("EEH: PCI-X status: %08x\n", cfg); } @@ -223,7 +217,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) pr_warn("EEH: PCI-E capabilities and status follow:\n"); for (i=0; i<=8; i++) { - eeh_ops->read_config(pdn, cap+4*i, 4, &cfg); + eeh_ops->read_config(edev, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); if ((i % 4) == 0) { @@ -250,7 +244,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) pr_warn("EEH: PCI-E AER capability register set follows:\n"); for (i=0; i<=13; i++) { - eeh_ops->read_config(pdn, cap+4*i, 4, &cfg); + eeh_ops->read_config(edev, cap+4*i, 4, &cfg); n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg); if ((i % 4) == 0) { @@ -726,7 +720,6 @@ static void eeh_disable_and_save_dev_state(struct eeh_dev *edev, static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); struct pci_dev *pdev = eeh_dev_to_pci_dev(edev); struct pci_dev *dev = userdata; @@ -734,73 +727,14 @@ static void eeh_restore_dev_state(struct eeh_dev *edev, void *userdata) return; /* Apply customization from firmware */ - if (pdn && eeh_ops->restore_config) - eeh_ops->restore_config(pdn); + if (eeh_ops->restore_config) + eeh_ops->restore_config(edev); /* The caller should restore state for the specified device */ if (pdev != dev) pci_restore_state(pdev); } -int eeh_restore_vf_config(struct pci_dn *pdn) -{ - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - u32 devctl, cmd, cap2, aer_capctl; - int old_mps; - - if (edev->pcie_cap) { - /* Restore MPS */ - old_mps = (ffs(pdn->mps) - 8) << 5; - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, - 2, &devctl); - devctl &= ~PCI_EXP_DEVCTL_PAYLOAD; - devctl |= old_mps; - eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, - 2, devctl); - - /* Disable Completion Timeout if possible */ - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP2, - 4, &cap2); - if (cap2 & PCI_EXP_DEVCAP2_COMP_TMOUT_DIS) { - eeh_ops->read_config(pdn, - edev->pcie_cap + PCI_EXP_DEVCTL2, - 4, &cap2); - cap2 |= PCI_EXP_DEVCTL2_COMP_TMOUT_DIS; - eeh_ops->write_config(pdn, - edev->pcie_cap + PCI_EXP_DEVCTL2, - 4, cap2); - } - } - - /* Enable SERR and parity checking */ - eeh_ops->read_config(pdn, PCI_COMMAND, 2, &cmd); - cmd |= (PCI_COMMAND_PARITY | PCI_COMMAND_SERR); - eeh_ops->write_config(pdn, PCI_COMMAND, 2, cmd); - - /* Enable report various errors */ - if (edev->pcie_cap) { - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, - 2, &devctl); - devctl &= ~PCI_EXP_DEVCTL_CERE; - devctl |= (PCI_EXP_DEVCTL_NFERE | - PCI_EXP_DEVCTL_FERE | - PCI_EXP_DEVCTL_URRE); - eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, - 2, devctl); - } - - /* Enable ECRC generation and check */ - if (edev->pcie_cap && edev->aer_cap) { - eeh_ops->read_config(pdn, edev->aer_cap + PCI_ERR_CAP, - 4, &aer_capctl); - aer_capctl |= (PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE); - eeh_ops->write_config(pdn, edev->aer_cap + PCI_ERR_CAP, - 4, aer_capctl); - } - - return 0; -} - /** * pcibios_set_pcie_reset_state - Set PCI-E reset state * @dev: pci device struct @@ -977,15 +911,13 @@ int eeh_pe_reset_full(struct eeh_pe *pe, bool include_passed) */ void eeh_save_bars(struct eeh_dev *edev) { - struct pci_dn *pdn; int i; - pdn = eeh_dev_to_pdn(edev); - if (!pdn) + if (!edev) return; for (i = 0; i < 16; i++) - eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]); + eeh_ops->read_config(edev, i * 4, 4, &edev->config_space[i]); /* * For PCI bridges including root port, we need enable bus @@ -1096,7 +1028,7 @@ static int eeh_init(void) /* Initialize PHB PEs */ list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - eeh_dev_phb_init_dynamic(hose); + eeh_phb_pe_create(hose); eeh_addr_cache_init(); @@ -1175,7 +1107,7 @@ void eeh_probe_device(struct pci_dev *dev) * FIXME: HEY MA, LOOK AT ME, NO LOCKING! */ if (edev->pdev && edev->pdev != dev) { - eeh_rmv_from_parent_pe(edev); + eeh_pe_tree_remove(edev); eeh_addr_cache_rmv_dev(edev->pdev); eeh_sysfs_remove_device(edev->pdev); @@ -1254,7 +1186,7 @@ void eeh_remove_device(struct pci_dev *dev) edev->in_error = false; dev->dev.archdata.edev = NULL; if (!(edev->pe->state & EEH_PE_KEEP)) - eeh_rmv_from_parent_pe(edev); + eeh_pe_tree_remove(edev); else edev->mode |= EEH_DEV_DISCONNECTED; } diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c deleted file mode 100644 index 7370185c7a05..000000000000 --- a/arch/powerpc/kernel/eeh_dev.c +++ /dev/null @@ -1,67 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * The file intends to implement dynamic creation of EEH device, which will - * be bound with OF node and PCI device simutaneously. The EEH devices would - * be foundamental information for EEH core components to work proerly. Besides, - * We have to support multiple situations where dynamic creation of EEH device - * is required: - * - * 1) Before PCI emunation starts, we need create EEH devices according to the - * PCI sensitive OF nodes. - * 2) When PCI emunation is done, we need do the binding between PCI device and - * the associated EEH device. - * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device - * will be created while PCI sensitive OF node is detected from DR. - * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If - * PHB is newly inserted, we also need create EEH devices accordingly. - * - * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012. - */ - -#include <linux/export.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/string.h> - -#include <asm/pci-bridge.h> -#include <asm/ppc-pci.h> - -/** - * eeh_dev_init - Create EEH device according to OF node - * @pdn: PCI device node - * - * It will create EEH device according to the given OF node. The function - * might be called by PCI emunation, DR, PHB hotplug. - */ -struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) -{ - struct eeh_dev *edev; - - /* Allocate EEH device */ - edev = kzalloc(sizeof(*edev), GFP_KERNEL); - if (!edev) - return NULL; - - /* Associate EEH device with OF node */ - pdn->edev = edev; - edev->pdn = pdn; - edev->bdfn = (pdn->busno << 8) | pdn->devfn; - edev->controller = pdn->phb; - - return edev; -} - -/** - * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB - * @phb: PHB - * - * Scan the PHB OF node and its child association, then create the - * EEH devices accordingly - */ -void eeh_dev_phb_init_dynamic(struct pci_controller *phb) -{ - /* EEH PE for PHB */ - eeh_phb_pe_create(phb); -} diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 7b048cee767c..3eff6a4888e7 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -214,7 +214,7 @@ static void eeh_dev_save_state(struct eeh_dev *edev, void *userdata) pci_save_state(pdev); } -static void eeh_set_channel_state(struct eeh_pe *root, enum pci_channel_state s) +static void eeh_set_channel_state(struct eeh_pe *root, pci_channel_state_t s) { struct eeh_pe *pe; struct eeh_dev *edev, *tmp; @@ -425,8 +425,8 @@ static enum pci_ers_result eeh_report_resume(struct eeh_dev *edev, pci_uevent_ers(edev->pdev, PCI_ERS_RESULT_RECOVERED); #ifdef CONFIG_PCI_IOV - if (eeh_ops->notify_resume && eeh_dev_to_pdn(edev)) - eeh_ops->notify_resume(eeh_dev_to_pdn(edev)); + if (eeh_ops->notify_resume) + eeh_ops->notify_resume(edev); #endif return PCI_ERS_RESULT_NONE; } @@ -477,7 +477,7 @@ static void *eeh_add_virt_device(struct eeh_dev *edev) } #ifdef CONFIG_PCI_IOV - pci_iov_add_virtfn(edev->physfn, eeh_dev_to_pdn(edev)->vf_index); + pci_iov_add_virtfn(edev->physfn, edev->vf_index); #endif return NULL; } @@ -521,9 +521,7 @@ static void eeh_rmv_device(struct eeh_dev *edev, void *userdata) if (edev->physfn) { #ifdef CONFIG_PCI_IOV - struct pci_dn *pdn = eeh_dev_to_pdn(edev); - - pci_iov_remove_virtfn(edev->physfn, pdn->vf_index); + pci_iov_remove_virtfn(edev->physfn, edev->vf_index); edev->pdev = NULL; #endif if (rmv_data) @@ -544,7 +542,7 @@ static void *eeh_pe_detach_dev(struct eeh_pe *pe, void *userdata) continue; edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED); - eeh_rmv_from_parent_pe(edev); + eeh_pe_tree_remove(edev); } return NULL; diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index 177852e39a25..d2aaaa73fdd5 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -319,56 +319,22 @@ struct eeh_pe *eeh_pe_get(struct pci_controller *phb, } /** - * eeh_pe_get_parent - Retrieve the parent PE + * eeh_pe_tree_insert - Add EEH device to parent PE * @edev: EEH device + * @new_pe_parent: PE to create additional PEs under * - * The whole PEs existing in the system are organized as hierarchy - * tree. The function is used to retrieve the parent PE according - * to the parent EEH device. - */ -static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev) -{ - struct eeh_dev *parent; - struct pci_dn *pdn = eeh_dev_to_pdn(edev); - - /* - * It might have the case for the indirect parent - * EEH device already having associated PE, but - * the direct parent EEH device doesn't have yet. - */ - if (edev->physfn) - pdn = pci_get_pdn(edev->physfn); - else - pdn = pdn ? pdn->parent : NULL; - while (pdn) { - /* We're poking out of PCI territory */ - parent = pdn_to_eeh_dev(pdn); - if (!parent) - return NULL; - - if (parent->pe) - return parent->pe; - - pdn = pdn->parent; - } - - return NULL; -} - -/** - * eeh_add_to_parent_pe - Add EEH device to parent PE - * @edev: EEH device + * Add EEH device to the PE in edev->pe_config_addr. If a PE already + * exists with that address then @edev is added to that PE. Otherwise + * a new PE is created and inserted into the PE tree as a child of + * @new_pe_parent. * - * Add EEH device to the parent PE. If the parent PE already - * exists, the PE type will be changed to EEH_PE_BUS. Otherwise, - * we have to create new PE to hold the EEH device and the new - * PE will be linked to its parent PE as well. + * If @new_pe_parent is NULL then the new PE will be inserted under + * directly under the the PHB. */ -int eeh_add_to_parent_pe(struct eeh_dev *edev) +int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) { + struct pci_controller *hose = edev->controller; struct eeh_pe *pe, *parent; - struct pci_dn *pdn = eeh_dev_to_pdn(edev); - int config_addr = (pdn->busno << 8) | (pdn->devfn); /* Check if the PE number is valid */ if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { @@ -382,7 +348,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) * PE should be composed of PCI bus and its subordinate * components. */ - pe = eeh_pe_get(pdn->phb, edev->pe_config_addr, config_addr); + pe = eeh_pe_get(hose, edev->pe_config_addr, edev->bdfn); if (pe) { if (pe->type & EEH_PE_INVALID) { list_add_tail(&edev->entry, &pe->edevs); @@ -399,8 +365,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) parent = parent->parent; } - eeh_edev_dbg(edev, - "Added to device PE (parent: PE#%x)\n", + eeh_edev_dbg(edev, "Added to existing PE (parent: PE#%x)\n", pe->parent->addr); } else { /* Mark the PE as type of PCI bus */ @@ -416,15 +381,15 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) /* Create a new EEH PE */ if (edev->physfn) - pe = eeh_pe_alloc(pdn->phb, EEH_PE_VF); + pe = eeh_pe_alloc(hose, EEH_PE_VF); else - pe = eeh_pe_alloc(pdn->phb, EEH_PE_DEVICE); + pe = eeh_pe_alloc(hose, EEH_PE_DEVICE); if (!pe) { pr_err("%s: out of memory!\n", __func__); return -ENOMEM; } pe->addr = edev->pe_config_addr; - pe->config_addr = config_addr; + pe->config_addr = edev->bdfn; /* * Put the new EEH PE into hierarchy tree. If the parent @@ -432,34 +397,35 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) * to PHB directly. Otherwise, we have to associate the * PE with its parent. */ - parent = eeh_pe_get_parent(edev); - if (!parent) { - parent = eeh_phb_pe_get(pdn->phb); - if (!parent) { + if (!new_pe_parent) { + new_pe_parent = eeh_phb_pe_get(hose); + if (!new_pe_parent) { pr_err("%s: No PHB PE is found (PHB Domain=%d)\n", - __func__, pdn->phb->global_number); + __func__, hose->global_number); edev->pe = NULL; kfree(pe); return -EEXIST; } } - pe->parent = parent; + + /* link new PE into the tree */ + pe->parent = new_pe_parent; + list_add_tail(&pe->child, &new_pe_parent->child_list); /* * Put the newly created PE into the child list and * link the EEH device accordingly. */ - list_add_tail(&pe->child, &parent->child_list); list_add_tail(&edev->entry, &pe->edevs); edev->pe = pe; - eeh_edev_dbg(edev, "Added to device PE (parent: PE#%x)\n", - pe->parent->addr); + eeh_edev_dbg(edev, "Added to new (parent: PE#%x)\n", + new_pe_parent->addr); return 0; } /** - * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE + * eeh_pe_tree_remove - Remove one EEH device from the associated PE * @edev: EEH device * * The PE hierarchy tree might be changed when doing PCI hotplug. @@ -467,7 +433,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev) * during EEH recovery. So we have to call the function remove the * corresponding PE accordingly if necessary. */ -int eeh_rmv_from_parent_pe(struct eeh_dev *edev) +int eeh_pe_tree_remove(struct eeh_dev *edev) { struct eeh_pe *pe, *parent, *child; bool keep, recover; @@ -698,7 +664,6 @@ void eeh_pe_state_clear(struct eeh_pe *root, int state, bool include_passed) */ static void eeh_bridge_check_link(struct eeh_dev *edev) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); int cap; uint32_t val; int timeout = 0; @@ -714,32 +679,32 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) /* Check slot status */ cap = edev->pcie_cap; - eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_SLTSTA, 2, &val); if (!(val & PCI_EXP_SLTSTA_PDS)) { eeh_edev_dbg(edev, "No card in the slot (0x%04x) !\n", val); return; } /* Check power status if we have the capability */ - eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_SLTCAP, 2, &val); if (val & PCI_EXP_SLTCAP_PCP) { - eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_SLTCTL, 2, &val); if (val & PCI_EXP_SLTCTL_PCC) { eeh_edev_dbg(edev, "In power-off state, power it on ...\n"); val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC); val |= (0x0100 & PCI_EXP_SLTCTL_PIC); - eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val); + eeh_ops->write_config(edev, cap + PCI_EXP_SLTCTL, 2, val); msleep(2 * 1000); } } /* Enable link */ - eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_LNKCTL, 2, &val); val &= ~PCI_EXP_LNKCTL_LD; - eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val); + eeh_ops->write_config(edev, cap + PCI_EXP_LNKCTL, 2, val); /* Check link */ - eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_LNKCAP, 4, &val); if (!(val & PCI_EXP_LNKCAP_DLLLARC)) { eeh_edev_dbg(edev, "No link reporting capability (0x%08x) \n", val); msleep(1000); @@ -752,7 +717,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) msleep(20); timeout += 20; - eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val); + eeh_ops->read_config(edev, cap + PCI_EXP_LNKSTA, 2, &val); if (val & PCI_EXP_LNKSTA_DLLLA) break; } @@ -769,7 +734,6 @@ static void eeh_bridge_check_link(struct eeh_dev *edev) static void eeh_restore_bridge_bars(struct eeh_dev *edev) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); int i; /* @@ -777,20 +741,20 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev) * Bus numbers and windows: 0x18 - 0x30 */ for (i = 4; i < 13; i++) - eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]); + eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]); /* Rom: 0x38 */ - eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]); + eeh_ops->write_config(edev, 14*4, 4, edev->config_space[14]); /* Cache line & Latency timer: 0xC 0xD */ - eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1, + eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1, SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1, - SAVED_BYTE(PCI_LATENCY_TIMER)); + eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1, + SAVED_BYTE(PCI_LATENCY_TIMER)); /* Max latency, min grant, interrupt ping and line: 0x3C */ - eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]); + eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]); /* PCI Command: 0x4 */ - eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1] | + eeh_ops->write_config(edev, PCI_COMMAND, 4, edev->config_space[1] | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); /* Check the PCIe link is ready */ @@ -799,28 +763,27 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev) static void eeh_restore_device_bars(struct eeh_dev *edev) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); int i; u32 cmd; for (i = 4; i < 10; i++) - eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]); + eeh_ops->write_config(edev, i*4, 4, edev->config_space[i]); /* 12 == Expansion ROM Address */ - eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]); + eeh_ops->write_config(edev, 12*4, 4, edev->config_space[12]); - eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1, + eeh_ops->write_config(edev, PCI_CACHE_LINE_SIZE, 1, SAVED_BYTE(PCI_CACHE_LINE_SIZE)); - eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1, + eeh_ops->write_config(edev, PCI_LATENCY_TIMER, 1, SAVED_BYTE(PCI_LATENCY_TIMER)); /* max latency, min grant, interrupt pin and line */ - eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]); + eeh_ops->write_config(edev, 15*4, 4, edev->config_space[15]); /* * Restore PERR & SERR bits, some devices require it, * don't touch the other command bits */ - eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd); + eeh_ops->read_config(edev, PCI_COMMAND, 4, &cmd); if (edev->config_space[1] & PCI_COMMAND_PARITY) cmd |= PCI_COMMAND_PARITY; else @@ -829,7 +792,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev) cmd |= PCI_COMMAND_SERR; else cmd &= ~PCI_COMMAND_SERR; - eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd); + eeh_ops->write_config(edev, PCI_COMMAND, 4, cmd); } /** @@ -843,16 +806,14 @@ static void eeh_restore_device_bars(struct eeh_dev *edev) */ static void eeh_restore_one_device_bars(struct eeh_dev *edev, void *flag) { - struct pci_dn *pdn = eeh_dev_to_pdn(edev); - /* Do special restore for bridges */ if (edev->mode & EEH_DEV_BRIDGE) eeh_restore_bridge_bars(edev); else eeh_restore_device_bars(edev); - if (eeh_ops->restore_config && pdn) - eeh_ops->restore_config(pdn); + if (eeh_ops->restore_config) + eeh_ops->restore_config(edev); } /** diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c index 4fb0f1e1017a..429620da73ba 100644 --- a/arch/powerpc/kernel/eeh_sysfs.c +++ b/arch/powerpc/kernel/eeh_sysfs.c @@ -99,7 +99,7 @@ static ssize_t eeh_notify_resume_store(struct device *dev, if (!edev || !edev->pe || !eeh_ops->notify_resume) return -ENODEV; - if (eeh_ops->notify_resume(pci_get_pdn(pdev))) + if (eeh_ops->notify_resume(edev)) return -EIO; return count; diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 217ebdf5b00b..f4d0af8e1136 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -36,6 +36,12 @@ #include "head_32.h" /* + * powerpc relies on return from interrupt/syscall being context synchronising + * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional + * synchronisation instructions. + */ + +/* * Align to 4k in order to ensure that all functions modyfing srr0/srr1 * fit into one page in order to not encounter a TLB miss between the * modification of srr0/srr1 and the associated rfi. diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 9d49338e0c85..33a42e42c56f 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -64,15 +64,173 @@ exception_marker: .section ".text" .align 7 +#ifdef CONFIG_PPC_BOOK3S +.macro system_call_vectored name trapnr + .globl system_call_vectored_\name +system_call_vectored_\name: +_ASM_NOKPROBE_SYMBOL(system_call_vectored_\name) +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +BEGIN_FTR_SECTION + extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ + bne .Ltabort_syscall +END_FTR_SECTION_IFSET(CPU_FTR_TM) +#endif + INTERRUPT_TO_KERNEL + mr r10,r1 + ld r1,PACAKSAVE(r13) + std r10,0(r1) + std r11,_NIP(r1) + std r12,_MSR(r1) + std r0,GPR0(r1) + std r10,GPR1(r1) + std r2,GPR2(r1) + ld r2,PACATOC(r13) + mfcr r12 + li r11,0 + /* Can we avoid saving r3-r8 in common case? */ + std r3,GPR3(r1) + std r4,GPR4(r1) + std r5,GPR5(r1) + std r6,GPR6(r1) + std r7,GPR7(r1) + std r8,GPR8(r1) + /* Zero r9-r12, this should only be required when restoring all GPRs */ + std r11,GPR9(r1) + std r11,GPR10(r1) + std r11,GPR11(r1) + std r11,GPR12(r1) + std r9,GPR13(r1) + SAVE_NVGPRS(r1) + std r11,_XER(r1) + std r11,_LINK(r1) + std r11,_CTR(r1) + + li r11,\trapnr + std r11,_TRAP(r1) + std r12,_CCR(r1) + std r3,ORIG_GPR3(r1) + addi r10,r1,STACK_FRAME_OVERHEAD + ld r11,exception_marker@toc(r2) + std r11,-16(r10) /* "regshere" marker */ + + /* + * RECONCILE_IRQ_STATE without calling trace_hardirqs_off(), which + * would clobber syscall parameters. Also we always enter with IRQs + * enabled and nothing pending. system_call_exception() will call + * trace_hardirqs_off(). + * + * scv enters with MSR[EE]=1, so don't set PACA_IRQ_HARD_DIS. The + * entry vector already sets PACAIRQSOFTMASK to IRQS_ALL_DISABLED. + */ + + /* Calling convention has r9 = orig r0, r10 = regs */ + mr r9,r0 + bl system_call_exception + +.Lsyscall_vectored_\name\()_exit: + addi r4,r1,STACK_FRAME_OVERHEAD + li r5,1 /* scv */ + bl syscall_exit_prepare + + ld r2,_CCR(r1) + ld r4,_NIP(r1) + ld r5,_MSR(r1) + +BEGIN_FTR_SECTION + stdcx. r0,0,r1 /* to clear the reservation */ +END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS) + +BEGIN_FTR_SECTION + HMT_MEDIUM_LOW +END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) + + cmpdi r3,0 + bne .Lsyscall_vectored_\name\()_restore_regs + + /* rfscv returns with LR->NIA and CTR->MSR */ + mtlr r4 + mtctr r5 + + /* Could zero these as per ABI, but we may consider a stricter ABI + * which preserves these if libc implementations can benefit, so + * restore them for now until further measurement is done. */ + ld r0,GPR0(r1) + ld r4,GPR4(r1) + ld r5,GPR5(r1) + ld r6,GPR6(r1) + ld r7,GPR7(r1) + ld r8,GPR8(r1) + /* Zero volatile regs that may contain sensitive kernel data */ + li r9,0 + li r10,0 + li r11,0 + li r12,0 + mtspr SPRN_XER,r0 + + /* + * We don't need to restore AMR on the way back to userspace for KUAP. + * The value of AMR only matters while we're in the kernel. + */ + mtcr r2 + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r13,GPR13(r1) + ld r1,GPR1(r1) + RFSCV_TO_USER + b . /* prevent speculative execution */ + +.Lsyscall_vectored_\name\()_restore_regs: + li r3,0 + mtmsrd r3,1 + mtspr SPRN_SRR0,r4 + mtspr SPRN_SRR1,r5 + + ld r3,_CTR(r1) + ld r4,_LINK(r1) + ld r5,_XER(r1) + + REST_NVGPRS(r1) + ld r0,GPR0(r1) + mtcr r2 + mtctr r3 + mtlr r4 + mtspr SPRN_XER,r5 + REST_10GPRS(2, r1) + REST_2GPRS(12, r1) + ld r1,GPR1(r1) + RFI_TO_USER +.endm + +system_call_vectored common 0x3000 +/* + * We instantiate another entry copy for the SIGILL variant, with TRAP=0x7ff0 + * which is tested by system_call_exception when r0 is -1 (as set by vector + * entry code). + */ +system_call_vectored sigill 0x7ff0 + + +/* + * Entered via kernel return set up by kernel/sstep.c, must match entry regs + */ + .globl system_call_vectored_emulate +system_call_vectored_emulate: +_ASM_NOKPROBE_SYMBOL(system_call_vectored_emulate) + li r10,IRQS_ALL_DISABLED + stb r10,PACAIRQSOFTMASK(r13) + b system_call_vectored_common +#endif + + .balign IFETCH_ALIGN_BYTES .globl system_call_common system_call_common: +_ASM_NOKPROBE_SYMBOL(system_call_common) #ifdef CONFIG_PPC_TRANSACTIONAL_MEM BEGIN_FTR_SECTION extrdi. r10, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif -_ASM_NOKPROBE_SYMBOL(system_call_common) mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) @@ -138,6 +296,7 @@ END_BTB_FLUSH_SECTION .Lsyscall_exit: addi r4,r1,STACK_FRAME_OVERHEAD + li r5,0 /* !scv */ bl syscall_exit_prepare ld r2,_CCR(r1) @@ -224,21 +383,29 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) b . /* prevent speculative execution */ #endif +#ifdef CONFIG_PPC_BOOK3S +_GLOBAL(ret_from_fork_scv) + bl schedule_tail + REST_NVGPRS(r1) + li r3,0 /* fork() return value */ + b .Lsyscall_vectored_common_exit +#endif + _GLOBAL(ret_from_fork) bl schedule_tail REST_NVGPRS(r1) - li r3,0 + li r3,0 /* fork() return value */ b .Lsyscall_exit _GLOBAL(ret_from_kernel_thread) bl schedule_tail REST_NVGPRS(r1) - mtlr r14 + mtctr r14 mr r3,r15 #ifdef PPC64_ELF_ABI_v2 mr r12,r14 #endif - blrl + bctrl li r3,0 b .Lsyscall_exit @@ -259,10 +426,7 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs); #define FLUSH_COUNT_CACHE \ 1: nop; \ - patch_site 1b, patch__call_flush_count_cache - - -#define BCCTR_FLUSH .long 0x4c400420 + patch_site 1b, patch__call_flush_branch_caches .macro nops number .rept \number @@ -271,8 +435,8 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs); .endm .balign 32 -.global flush_count_cache -flush_count_cache: +.global flush_branch_caches +flush_branch_caches: /* Save LR into r9 */ mflr r9 @@ -294,7 +458,7 @@ flush_count_cache: li r9,0x7fff mtctr r9 - BCCTR_FLUSH + PPC_BCCTR_FLUSH 2: nop patch_site 2b patch__flush_count_cache_return @@ -303,7 +467,7 @@ flush_count_cache: .rept 278 .balign 32 - BCCTR_FLUSH + PPC_BCCTR_FLUSH nops 7 .endr @@ -357,7 +521,7 @@ _GLOBAL(_switch) * kernel/sched/core.c). * * Uncacheable stores in the case of involuntary preemption must - * be taken care of. The smp_mb__before_spin_lock() in __schedule() + * be taken care of. The smp_mb__after_spinlock() in __schedule() * is implemented as hwsync on powerpc, which orders MMIO too. So * long as there is an hwsync in the context switch path, it will * be executed on the source CPU after the task has performed diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 446e54c3f71e..f7d748b88705 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -508,8 +508,24 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real) .macro __GEN_COMMON_BODY name .if IMASK + .if ! ISTACK + .error "No support for masked interrupt to use custom stack" + .endif + + /* If coming from user, skip soft-mask tests. */ + andi. r10,r12,MSR_PR + bne 2f + + /* Kernel code running below __end_interrupts is implicitly + * soft-masked */ + LOAD_HANDLER(r10, __end_interrupts) + cmpld r11,r10 + li r10,IMASK + blt- 1f + + /* Test the soft mask state against our interrupt's bit */ lbz r10,PACAIRQSOFTMASK(r13) - andi. r10,r10,IMASK +1: andi. r10,r10,IMASK /* Associate vector numbers with bits in paca->irq_happened */ .if IVEC == 0x500 || IVEC == 0xea0 li r10,PACA_IRQ_EE @@ -540,7 +556,7 @@ DEFINE_FIXED_SYMBOL(\name\()_common_real) .if ISTACK andi. r10,r12,MSR_PR /* See if coming from user */ - mr r10,r1 /* Save r1 */ +2: mr r10,r1 /* Save r1 */ subi r1,r1,INT_FRAME_SIZE /* alloc frame on kernel stack */ beq- 100f ld r1,PACAKSAVE(r13) /* kernel stack to use */ @@ -740,6 +756,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) * guarantee they will be delivered virtually. Some conditions (see the ISA) * cause exceptions to be delivered in real mode. * + * The scv instructions are a special case. They get a 0x3000 offset applied. + * scv exceptions have unique reentrancy properties, see below. + * * It's impossible to receive interrupts below 0x300 via AIL. * * KVM: None of the virtual exceptions are from the guest. Anything that @@ -749,8 +768,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) * We layout physical memory as follows: * 0x0000 - 0x00ff : Secondary processor spin code * 0x0100 - 0x18ff : Real mode pSeries interrupt vectors - * 0x1900 - 0x3fff : Real mode trampolines - * 0x4000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors + * 0x1900 - 0x2fff : Real mode trampolines + * 0x3000 - 0x58ff : Relon (IR=1,DR=1) mode pSeries interrupt vectors * 0x5900 - 0x6fff : Relon mode trampolines * 0x7000 - 0x7fff : FWNMI data area * 0x8000 - .... : Common interrupt handlers, remaining early @@ -761,8 +780,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP) * vectors there. */ OPEN_FIXED_SECTION(real_vectors, 0x0100, 0x1900) -OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x4000) -OPEN_FIXED_SECTION(virt_vectors, 0x4000, 0x5900) +OPEN_FIXED_SECTION(real_trampolines, 0x1900, 0x3000) +OPEN_FIXED_SECTION(virt_vectors, 0x3000, 0x5900) OPEN_FIXED_SECTION(virt_trampolines, 0x5900, 0x7000) #ifdef CONFIG_PPC_POWERNV @@ -798,6 +817,77 @@ USE_FIXED_SECTION(real_vectors) .globl __start_interrupts __start_interrupts: +/** + * Interrupt 0x3000 - System Call Vectored Interrupt (syscall). + * This is a synchronous interrupt invoked with the "scv" instruction. The + * system call does not alter the HV bit, so it is directed to the OS. + * + * Handling: + * scv instructions enter the kernel without changing EE, RI, ME, or HV. + * In particular, this means we can take a maskable interrupt at any point + * in the scv handler, which is unlike any other interrupt. This is solved + * by treating the instruction addresses below __end_interrupts as being + * soft-masked. + * + * AIL-0 mode scv exceptions go to 0x17000-0x17fff, but we set AIL-3 and + * ensure scv is never executed with relocation off, which means AIL-0 + * should never happen. + * + * Before leaving the below __end_interrupts text, at least of the following + * must be true: + * - MSR[PR]=1 (i.e., return to userspace) + * - MSR_EE|MSR_RI is set (no reentrant exceptions) + * - Standard kernel environment is set up (stack, paca, etc) + * + * Call convention: + * + * syscall register convention is in Documentation/powerpc/syscall64-abi.rst + */ +EXC_VIRT_BEGIN(system_call_vectored, 0x3000, 0x1000) + /* SCV 0 */ + mr r9,r13 + GET_PACA(r13) + mflr r11 + mfctr r12 + li r10,IRQS_ALL_DISABLED + stb r10,PACAIRQSOFTMASK(r13) +#ifdef CONFIG_RELOCATABLE + b system_call_vectored_tramp +#else + b system_call_vectored_common +#endif + nop + + /* SCV 1 - 127 */ + .rept 127 + mr r9,r13 + GET_PACA(r13) + mflr r11 + mfctr r12 + li r10,IRQS_ALL_DISABLED + stb r10,PACAIRQSOFTMASK(r13) + li r0,-1 /* cause failure */ +#ifdef CONFIG_RELOCATABLE + b system_call_vectored_sigill_tramp +#else + b system_call_vectored_sigill +#endif + .endr +EXC_VIRT_END(system_call_vectored, 0x3000, 0x1000) + +#ifdef CONFIG_RELOCATABLE +TRAMP_VIRT_BEGIN(system_call_vectored_tramp) + __LOAD_HANDLER(r10, system_call_vectored_common) + mtctr r10 + bctr + +TRAMP_VIRT_BEGIN(system_call_vectored_sigill_tramp) + __LOAD_HANDLER(r10, system_call_vectored_sigill) + mtctr r10 + bctr +#endif + + /* No virt vectors corresponding with 0x0..0x100 */ EXC_VIRT_NONE(0x4000, 0x100) @@ -2838,7 +2928,8 @@ masked_interrupt: ld r10,PACA_EXGEN+EX_R10(r13) ld r11,PACA_EXGEN+EX_R11(r13) ld r12,PACA_EXGEN+EX_R12(r13) - /* returns to kernel where r13 must be set up, so don't restore it */ + ld r13,PACA_EXGEN+EX_R13(r13) + /* May return to masked low address where r13 is not set up */ .if \hsrr HRFI_TO_KERNEL .else @@ -2946,6 +3037,47 @@ TRAMP_REAL_BEGIN(hrfi_flush_fallback) GET_SCRATCH0(r13); hrfid +TRAMP_REAL_BEGIN(rfscv_flush_fallback) + /* system call volatile */ + mr r7,r13 + GET_PACA(r13); + mr r8,r1 + ld r1,PACAKSAVE(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SIZE(r13) + srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */ + mtctr r11 + DCBT_BOOK3S_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync + + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ +1: + ld r11,(0x80 + 8)*0(r10) + ld r11,(0x80 + 8)*1(r10) + ld r11,(0x80 + 8)*2(r10) + ld r11,(0x80 + 8)*3(r10) + ld r11,(0x80 + 8)*4(r10) + ld r11,(0x80 + 8)*5(r10) + ld r11,(0x80 + 8)*6(r10) + ld r11,(0x80 + 8)*7(r10) + addi r10,r10,0x80*8 + bdnz 1b + + mtctr r9 + li r9,0 + li r10,0 + li r11,0 + mr r1,r8 + mr r13,r7 + RFSCV + USE_TEXT_SECTION() MASKED_INTERRUPT MASKED_INTERRUPT hsrr=1 @@ -2997,6 +3129,10 @@ EXC_COMMON_BEGIN(ppc64_runlatch_on_trampoline) USE_FIXED_SECTION(virt_trampolines) /* + * All code below __end_interrupts is treated as soft-masked. If + * any code runs here with MSR[EE]=1, it must then cope with pending + * soft interrupt being raised (i.e., by ensuring it is replayed). + * * The __end_interrupts marker must be past the out-of-line (OOL) * handlers, so that they are copied to real address 0x100 when running * a relocatable kernel. This ensures they can be reached from the short diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 78ab9a6ee6ac..10ebb4bf71ad 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -32,6 +32,14 @@ #include <asm/fadump-internal.h> #include <asm/setup.h> +/* + * The CPU who acquired the lock to trigger the fadump crash should + * wait for other CPUs to enter. + * + * The timeout is in milliseconds. + */ +#define CRASH_TIMEOUT 500 + static struct fw_dump fw_dump; static void __init fadump_reserve_crash_area(u64 base); @@ -39,7 +47,10 @@ static void __init fadump_reserve_crash_area(u64 base); struct kobject *fadump_kobj; #ifndef CONFIG_PRESERVE_FA_DUMP + +static atomic_t cpus_in_fadump; static DEFINE_MUTEX(fadump_mutex); + struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false }; #define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */ @@ -668,8 +679,11 @@ early_param("fadump_reserve_mem", early_fadump_reserve_mem); void crash_fadump(struct pt_regs *regs, const char *str) { + unsigned int msecs; struct fadump_crash_info_header *fdh = NULL; int old_cpu, this_cpu; + /* Do not include first CPU */ + unsigned int ncpus = num_online_cpus() - 1; if (!should_fadump_crash()) return; @@ -685,6 +699,8 @@ void crash_fadump(struct pt_regs *regs, const char *str) old_cpu = cmpxchg(&crashing_cpu, -1, this_cpu); if (old_cpu != -1) { + atomic_inc(&cpus_in_fadump); + /* * We can't loop here indefinitely. Wait as long as fadump * is in force. If we race with fadump un-registration this @@ -708,6 +724,16 @@ void crash_fadump(struct pt_regs *regs, const char *str) fdh->online_mask = *cpu_online_mask; + /* + * If we came in via system reset, wait a while for the secondary + * CPUs to enter. + */ + if (TRAP(&(fdh->regs)) == 0x100) { + msecs = CRASH_TIMEOUT; + while ((atomic_read(&cpus_in_fadump) < ncpus) && (--msecs > 0)) + mdelay(1); + } + fw_dump.ops->fadump_trigger(fdh, str); } diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index cc4a5e3f51f1..fe48d319d490 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -11,8 +11,27 @@ #include <linux/export.h> #include <linux/cache.h> +#include <linux/of.h> #include <asm/firmware.h> +#ifdef CONFIG_PPC64 unsigned long powerpc_firmware_features __read_mostly; EXPORT_SYMBOL_GPL(powerpc_firmware_features); +#endif + +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) +bool is_kvm_guest(void) +{ + struct device_node *hyper_node; + + hyper_node = of_find_node_by_path("/hypervisor"); + if (!hyper_node) + return 0; + + if (!of_device_is_compatible(hyper_node, "linux,kvm")) + return 0; + + return 1; +} +#endif diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index cac22cb97a8c..4ae39db70044 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -107,9 +107,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX) or r12,r12,r4 std r12,_MSR(r1) #endif - /* Don't care if r4 overflows, this is desired behaviour */ - lbz r4,THREAD_LOAD_FP(r5) - addi r4,r4,1 + li r4,1 stb r4,THREAD_LOAD_FP(r5) addi r10,r5,THREAD_FPSTATE lfd fr0,FPSTATE_FPSCR(r10) diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 705c042309d8..f3ab94d73936 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -474,7 +474,7 @@ InstructionTLBMiss: /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_IMISS #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) - lis r1,PAGE_OFFSET@h /* check if kernel address */ + lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 #endif mfspr r2, SPRN_SPRG_PGDIR @@ -484,7 +484,7 @@ InstructionTLBMiss: li r1,_PAGE_PRESENT | _PAGE_EXEC #endif #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) - bge- 112f + bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ #endif @@ -541,7 +541,7 @@ DataLoadTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_DMISS - lis r1,PAGE_OFFSET@h /* check if kernel address */ + lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR #ifdef CONFIG_SWAP @@ -549,7 +549,7 @@ DataLoadTLBMiss: #else li r1, _PAGE_PRESENT #endif - bge- 112f + bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ 112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ @@ -621,7 +621,7 @@ DataStoreTLBMiss: */ /* Get PTE (linux-style) and check access */ mfspr r3,SPRN_DMISS - lis r1,PAGE_OFFSET@h /* check if kernel address */ + lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR #ifdef CONFIG_SWAP @@ -629,7 +629,7 @@ DataStoreTLBMiss: #else li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT #endif - bge- 112f + bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ 112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */ @@ -673,6 +673,10 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_NEED_DTLB_SW_LRU) #define altivec_assist_exception unknown_exception #endif +#ifndef CONFIG_TAU_INT +#define TAUException unknown_exception +#endif + EXCEPTION(0x1300, Trap_13, instruction_breakpoint_exception, EXC_XFER_STD) EXCEPTION(0x1400, SMI, SMIException, EXC_XFER_STD) EXCEPTION(0x1500, Trap_15, unknown_exception, EXC_XFER_STD) diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 926bfa73586a..5b282d9965a5 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -620,7 +620,7 @@ start_here: ori r6, r6, swapper_pg_dir@l lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* Must match your Abatron config file */ + stw r5, 0xf0(0) /* Must match your Abatron config file */ tophys(r5,r5) stw r6, 0(r5) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 0000daf0e1da..1f4a1efa0074 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -418,8 +418,9 @@ static int hw_breakpoint_validate_len(struct arch_hw_breakpoint *hw) if (dawr_enabled()) { max_len = DAWR_MAX_LEN; - /* DAWR region can't cross 512 bytes boundary */ - if (ALIGN(start_addr, SZ_512M) != ALIGN(end_addr - 1, SZ_512M)) + /* DAWR region can't cross 512 bytes boundary on p10 predecessors */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && + (ALIGN_DOWN(start_addr, SZ_512) != ALIGN_DOWN(end_addr - 1, SZ_512))) return -EINVAL; } else if (IS_ENABLED(CONFIG_PPC_8xx)) { /* 8xx can setup a range without limitation */ @@ -498,11 +499,11 @@ static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info return ((info->address <= dar) && (dar - info->address < info->len)); } -static bool dar_user_range_overlaps(unsigned long dar, int size, - struct arch_hw_breakpoint *info) +static bool ea_user_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) { - return ((dar < info->address + info->len) && - (dar + size > info->address)); + return ((ea < info->address + info->len) && + (ea + size > info->address)); } static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) @@ -515,20 +516,22 @@ static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) return ((hw_start_addr <= dar) && (hw_end_addr > dar)); } -static bool dar_hw_range_overlaps(unsigned long dar, int size, - struct arch_hw_breakpoint *info) +static bool ea_hw_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) { unsigned long hw_start_addr, hw_end_addr; hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); - return ((dar < hw_end_addr) && (dar + size > hw_start_addr)); + return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); } /* * If hw has multiple DAWR registers, we also need to check all * dawrx constraint bits to confirm this is _really_ a valid event. + * If type is UNKNOWN, but privilege level matches, consider it as + * a positive match. */ static bool check_dawrx_constraints(struct pt_regs *regs, int type, struct arch_hw_breakpoint *info) @@ -536,7 +539,12 @@ static bool check_dawrx_constraints(struct pt_regs *regs, int type, if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ)) return false; - if (OP_IS_STORE(type) && !(info->type & HW_BRK_TYPE_WRITE)) + /* + * The Cache Management instructions other than dcbz never + * cause a match. i.e. if type is CACHEOP, the instruction + * is dcbz, and dcbz is treated as Store. + */ + if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE)) return false; if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL)) @@ -553,7 +561,8 @@ static bool check_dawrx_constraints(struct pt_regs *regs, int type, * including extraneous exception. Otherwise return false. */ static bool check_constraints(struct pt_regs *regs, struct ppc_inst instr, - int type, int size, struct arch_hw_breakpoint *info) + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info) { bool in_user_range = dar_in_user_range(regs->dar, info); bool dawrx_constraints; @@ -569,22 +578,27 @@ static bool check_constraints(struct pt_regs *regs, struct ppc_inst instr, } if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) { - if (in_user_range) - return true; + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; - if (dar_in_hw_range(regs->dar, info)) { - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - return true; - } - return false; + return true; } dawrx_constraints = check_dawrx_constraints(regs, type, info); - if (dar_user_range_overlaps(regs->dar, size, info)) + if (type == UNKNOWN) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; + + return dawrx_constraints; + } + + if (ea_user_range_overlaps(ea, size, info)) return dawrx_constraints; - if (dar_hw_range_overlaps(regs->dar, size, info)) { + if (ea_hw_range_overlaps(ea, size, info)) { if (dawrx_constraints) { info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; return true; @@ -593,8 +607,17 @@ static bool check_constraints(struct pt_regs *regs, struct ppc_inst instr, return false; } +static int cache_op_size(void) +{ +#ifdef __powerpc64__ + return ppc64_caches.l1d.block_size; +#else + return L1_CACHE_BYTES; +#endif +} + static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, - int *type, int *size, bool *larx_stcx) + int *type, int *size, unsigned long *ea) { struct instruction_op op; @@ -602,16 +625,23 @@ static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, return; analyse_instr(&op, regs, *instr); - - /* - * Set size = 8 if analyse_instr() fails. If it's a userspace - * watchpoint(valid or extraneous), we can notify user about it. - * If it's a kernel watchpoint, instruction emulation will fail - * in stepping_handler() and watchpoint will be disabled. - */ *type = GETTYPE(op.type); - *size = !(*type == UNKNOWN) ? GETSIZE(op.type) : 8; - *larx_stcx = (*type == LARX || *type == STCX); + *ea = op.ea; +#ifdef __powerpc64__ + if (!(regs->msr & MSR_64BIT)) + *ea &= 0xffffffffUL; +#endif + + *size = GETSIZE(op.type); + if (*type == CACHEOP) { + *size = cache_op_size(); + *ea &= ~(*size - 1); + } +} + +static bool is_larx_stcx_instr(int type) +{ + return type == LARX || type == STCX; } /* @@ -678,7 +708,7 @@ int hw_breakpoint_handler(struct die_args *args) struct ppc_inst instr = ppc_inst(0); int type = 0; int size = 0; - bool larx_stcx = false; + unsigned long ea; /* Disable breakpoints during exception handling */ hw_breakpoint_disable(); @@ -692,7 +722,7 @@ int hw_breakpoint_handler(struct die_args *args) rcu_read_lock(); if (!IS_ENABLED(CONFIG_PPC_8xx)) - get_instr_detail(regs, &instr, &type, &size, &larx_stcx); + get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { bp[i] = __this_cpu_read(bp_per_reg[i]); @@ -702,7 +732,7 @@ int hw_breakpoint_handler(struct die_args *args) info[i] = counter_arch_bp(bp[i]); info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (check_constraints(regs, instr, type, size, info[i])) { + if (check_constraints(regs, instr, ea, type, size, info[i])) { if (!IS_ENABLED(CONFIG_PPC_8xx) && ppc_inst_equal(instr, ppc_inst(0))) { handler_error(bp[i], info[i]); @@ -744,7 +774,7 @@ int hw_breakpoint_handler(struct die_args *args) } if (!IS_ENABLED(CONFIG_PPC_8xx)) { - if (larx_stcx) { + if (is_larx_stcx_instr(type)) { for (i = 0; i < nr_wp_slots(); i++) { if (!hit[i]) continue; diff --git a/arch/powerpc/kernel/iomap.c b/arch/powerpc/kernel/iomap.c index 5ac84efc6ede..9fe4fb3b08aa 100644 --- a/arch/powerpc/kernel/iomap.c +++ b/arch/powerpc/kernel/iomap.c @@ -15,23 +15,23 @@ * Here comes the ppc64 implementation of the IOMAP * interfaces. */ -unsigned int ioread8(void __iomem *addr) +unsigned int ioread8(const void __iomem *addr) { return readb(addr); } -unsigned int ioread16(void __iomem *addr) +unsigned int ioread16(const void __iomem *addr) { return readw(addr); } -unsigned int ioread16be(void __iomem *addr) +unsigned int ioread16be(const void __iomem *addr) { return readw_be(addr); } -unsigned int ioread32(void __iomem *addr) +unsigned int ioread32(const void __iomem *addr) { return readl(addr); } -unsigned int ioread32be(void __iomem *addr) +unsigned int ioread32be(const void __iomem *addr) { return readl_be(addr); } @@ -41,27 +41,27 @@ EXPORT_SYMBOL(ioread16be); EXPORT_SYMBOL(ioread32); EXPORT_SYMBOL(ioread32be); #ifdef __powerpc64__ -u64 ioread64(void __iomem *addr) +u64 ioread64(const void __iomem *addr) { return readq(addr); } -u64 ioread64_lo_hi(void __iomem *addr) +u64 ioread64_lo_hi(const void __iomem *addr) { return readq(addr); } -u64 ioread64_hi_lo(void __iomem *addr) +u64 ioread64_hi_lo(const void __iomem *addr) { return readq(addr); } -u64 ioread64be(void __iomem *addr) +u64 ioread64be(const void __iomem *addr) { return readq_be(addr); } -u64 ioread64be_lo_hi(void __iomem *addr) +u64 ioread64be_lo_hi(const void __iomem *addr) { return readq_be(addr); } -u64 ioread64be_hi_lo(void __iomem *addr) +u64 ioread64be_hi_lo(const void __iomem *addr) { return readq_be(addr); } @@ -139,15 +139,15 @@ EXPORT_SYMBOL(iowrite64be_hi_lo); * FIXME! We could make these do EEH handling if we really * wanted. Not clear if we do. */ -void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count) { readsb(addr, dst, count); } -void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count) { readsw(addr, dst, count); } -void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count) { readsl(addr, dst, count); } diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 05b1cc0e009e..bf21ebd36190 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -621,13 +621,14 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_printf(p, "%10u ", per_cpu(irq_stat, j).mce_exceptions); seq_printf(p, " Machine check exceptions\n"); +#ifdef CONFIG_PPC_BOOK3S_64 if (cpu_has_feature(CPU_FTR_HVMODE)) { seq_printf(p, "%*s: ", prec, "HMI"); for_each_online_cpu(j) - seq_printf(p, "%10u ", - per_cpu(irq_stat, j).hmi_exceptions); + seq_printf(p, "%10u ", paca_ptrs[j]->hmi_irqs); seq_printf(p, " Hypervisor Maintenance Interrupts\n"); } +#endif seq_printf(p, "%*s: ", prec, "NMI"); for_each_online_cpu(j) @@ -665,7 +666,9 @@ u64 arch_irq_stat_cpu(unsigned int cpu) sum += per_cpu(irq_stat, cpu).mce_exceptions; sum += per_cpu(irq_stat, cpu).spurious_irqs; sum += per_cpu(irq_stat, cpu).timer_irqs_others; - sum += per_cpu(irq_stat, cpu).hmi_exceptions; +#ifdef CONFIG_PPC_BOOK3S_64 + sum += paca_ptrs[cpu]->hmi_irqs; +#endif sum += per_cpu(irq_stat, cpu).sreset_irqs; #ifdef CONFIG_PPC_WATCHDOG sum += per_cpu(irq_stat, cpu).soft_nmi_irqs; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 9cc792a3a6a9..6ab9b4d037c3 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -244,7 +244,7 @@ static int try_to_emulate(struct kprobe *p, struct pt_regs *regs) * So, we should never get here... but, its still * good to catch them, just in case... */ - printk("Can't step on instruction %x\n", ppc_inst_val(insn)); + printk("Can't step on instruction %s\n", ppc_inst_as_str(insn)); BUG(); } else { /* diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index fd90c0eda229..ada59f6c4298 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -49,6 +49,20 @@ static struct irq_work mce_ue_event_irq_work = { DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); +static BLOCKING_NOTIFIER_HEAD(mce_notifier_list); + +int mce_register_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&mce_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(mce_register_notifier); + +int mce_unregister_notifier(struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&mce_notifier_list, nb); +} +EXPORT_SYMBOL_GPL(mce_unregister_notifier); + static void mce_set_error_info(struct machine_check_event *mce, struct mce_error_info *mce_err) { @@ -278,6 +292,7 @@ static void machine_process_ue_event(struct work_struct *work) while (__this_cpu_read(mce_ue_count) > 0) { index = __this_cpu_read(mce_ue_count) - 1; evt = this_cpu_ptr(&mce_ue_event_queue[index]); + blocking_notifier_call_chain(&mce_notifier_list, 0, evt); #ifdef CONFIG_MEMORY_FAILURE /* * This should probably queued elsewhere, but @@ -370,6 +385,7 @@ void machine_check_print_event_info(struct machine_check_event *evt, static const char *mc_user_types[] = { "Indeterminate", "tlbie(l) invalid", + "scv invalid", }; static const char *mc_ra_types[] = { "Indeterminate", @@ -711,7 +727,7 @@ long hmi_exception_realmode(struct pt_regs *regs) { int ret; - __this_cpu_inc(irq_stat.hmi_exceptions); + local_paca->hmi_irqs++; ret = hmi_handle_debugtrig(regs); if (ret >= 0) diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index c3b522bff9b4..b7e173754a2e 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -243,6 +243,45 @@ static const struct mce_ierror_table mce_p9_ierror_table[] = { MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, { 0, 0, 0, 0, 0, 0, 0 } }; +static const struct mce_ierror_table mce_p10_ierror_table[] = { +{ 0x00000000081c0000, 0x0000000000040000, true, + MCE_ERROR_TYPE_UE, MCE_UE_ERROR_IFETCH, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x0000000000080000, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x00000000000c0000, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000000081c0000, 0x0000000000100000, true, + MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000000081c0000, 0x0000000000140000, true, + MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000000081c0000, 0x0000000000180000, true, + MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x00000000001c0000, true, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH_FOREIGN, MCE_ECLASS_SOFTWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x0000000008080000, true, + MCE_ERROR_TYPE_USER,MCE_USER_ERROR_SCV, MCE_ECLASS_SOFTWARE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000000081c0000, 0x00000000080c0000, true, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_IFETCH, MCE_ECLASS_SOFTWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x0000000008100000, true, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH, MCE_ECLASS_SOFTWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000000081c0000, 0x0000000008140000, false, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_STORE, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_FATAL, false }, /* ASYNC is fatal */ +{ 0x00000000081c0000, 0x00000000081c0000, true, MCE_ECLASS_HARDWARE, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_IFETCH_FOREIGN, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0, 0, 0, 0, 0, 0, 0 } }; + struct mce_derror_table { unsigned long dsisr_value; bool dar_valid; /* dar is a valid indicator of faulting address */ @@ -361,6 +400,46 @@ static const struct mce_derror_table mce_p9_derror_table[] = { MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, { 0, false, 0, 0, 0, 0, 0 } }; +static const struct mce_derror_table mce_p10_derror_table[] = { +{ 0x00008000, false, + MCE_ERROR_TYPE_UE, MCE_UE_ERROR_LOAD_STORE, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00004000, true, + MCE_ERROR_TYPE_UE, MCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE, + MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000800, true, + MCE_ERROR_TYPE_ERAT, MCE_ERAT_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000400, true, + MCE_ERROR_TYPE_TLB, MCE_TLB_ERROR_MULTIHIT, MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000200, false, + MCE_ERROR_TYPE_USER, MCE_USER_ERROR_TLBIE, MCE_ECLASS_SOFTWARE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000080, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_MULTIHIT, /* Before PARITY */ + MCE_ECLASS_SOFT_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_WARNING, true }, +{ 0x00000100, true, + MCE_ERROR_TYPE_SLB, MCE_SLB_ERROR_PARITY, MCE_ECLASS_HARD_INDETERMINATE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000040, true, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000020, false, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE, + MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000010, false, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN, + MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0x00000008, false, + MCE_ERROR_TYPE_RA, MCE_RA_ERROR_LOAD_STORE_FOREIGN, MCE_ECLASS_HARDWARE, + MCE_INITIATOR_CPU, MCE_SEV_SEVERE, true }, +{ 0, false, 0, 0, 0, 0, 0 } }; + static int mce_find_instr_ea_and_phys(struct pt_regs *regs, uint64_t *addr, uint64_t *phys_addr) { @@ -657,3 +736,8 @@ long __machine_check_early_realmode_p9(struct pt_regs *regs) return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table); } + +long __machine_check_early_realmode_p10(struct pt_regs *regs) +{ + return mce_handle_error(regs, mce_p10_derror_table, mce_p10_ierror_table); +} diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 1864605eca29..7bb46ad98207 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -413,20 +413,6 @@ _GLOBAL(kexec_sequence) li r0,0 std r0,16(r1) -BEGIN_FTR_SECTION - /* - * This is the best time to turn AMR/IAMR off. - * key 0 is used in radix for supervisor<->user - * protection, but on hash key 0 is reserved - * ideally we want to enter with a clean state. - * NOTE, we rely on r0 being 0 from above. - */ - mtspr SPRN_IAMR,r0 -BEGIN_FTR_SECTION_NESTED(42) - mtspr SPRN_AMOR,r0 -END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42) -END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) - /* save regs for local vars on new stack. * yes, we won't go back, but ... */ diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c index df649acb5631..a211b0253cdb 100644 --- a/arch/powerpc/kernel/module.c +++ b/arch/powerpc/kernel/module.c @@ -86,3 +86,14 @@ int module_finalize(const Elf_Ehdr *hdr, return 0; } + +#ifdef MODULES_VADDR +void *module_alloc(unsigned long size) +{ + BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR); + + return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL, + PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c index 71a3f97dc988..f89376ff633e 100644 --- a/arch/powerpc/kernel/of_platform.c +++ b/arch/powerpc/kernel/of_platform.c @@ -62,8 +62,8 @@ static int of_pci_phb_probe(struct platform_device *dev) /* Init pci_dn data structures */ pci_devs_phb_init_dynamic(phb); - /* Create EEH PEs for the PHB */ - eeh_dev_phb_init_dynamic(phb); + /* Create EEH PE for the PHB */ + eeh_phb_pe_create(phb); /* Scan the bus */ pcibios_scan_phb(phb); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 74da65aacbc9..0ad15768d762 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -57,8 +57,8 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align, #define LPPACA_SIZE 0x400 -static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align, - unsigned long limit, int cpu) +static void *__init alloc_shared_lppaca(unsigned long size, unsigned long limit, + int cpu) { size_t shared_lppaca_total_size = PAGE_ALIGN(nr_cpu_ids * LPPACA_SIZE); static unsigned long shared_lppaca_size; @@ -68,6 +68,13 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align, if (!shared_lppaca) { memblock_set_bottom_up(true); + /* + * See Documentation/powerpc/ultravisor.rst for more details. + * + * UV/HV data sharing is in PAGE_SIZE granularity. In order to + * minimize the number of pages shared, align the allocation to + * PAGE_SIZE. + */ shared_lppaca = memblock_alloc_try_nid(shared_lppaca_total_size, PAGE_SIZE, MEMBLOCK_LOW_LIMIT, @@ -122,7 +129,7 @@ static struct lppaca * __init new_lppaca(int cpu, unsigned long limit) return NULL; if (is_secure_guest()) - lp = alloc_shared_lppaca(LPPACA_SIZE, 0x400, limit, cpu); + lp = alloc_shared_lppaca(LPPACA_SIZE, limit, cpu); else lp = alloc_paca_data(LPPACA_SIZE, 0x400, limit, cpu); diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c index 4e654df55969..e99b7c547d7e 100644 --- a/arch/powerpc/kernel/pci_dn.c +++ b/arch/powerpc/kernel/pci_dn.c @@ -124,9 +124,28 @@ struct pci_dn *pci_get_pdn(struct pci_dev *pdev) return NULL; } +#ifdef CONFIG_EEH +static struct eeh_dev *eeh_dev_init(struct pci_dn *pdn) +{ + struct eeh_dev *edev; + + /* Allocate EEH device */ + edev = kzalloc(sizeof(*edev), GFP_KERNEL); + if (!edev) + return NULL; + + /* Associate EEH device with OF node */ + pdn->edev = edev; + edev->pdn = pdn; + edev->bdfn = (pdn->busno << 8) | pdn->devfn; + edev->controller = pdn->phb; + + return edev; +} +#endif /* CONFIG_EEH */ + #ifdef CONFIG_PCI_IOV static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent, - int vf_index, int busno, int devfn) { struct pci_dn *pdn; @@ -143,7 +162,6 @@ static struct pci_dn *add_one_sriov_vf_pdn(struct pci_dn *parent, pdn->parent = parent; pdn->busno = busno; pdn->devfn = devfn; - pdn->vf_index = vf_index; pdn->pe_number = IODA_INVALID_PE; INIT_LIST_HEAD(&pdn->child_list); INIT_LIST_HEAD(&pdn->list); @@ -174,7 +192,7 @@ struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev) for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) { struct eeh_dev *edev __maybe_unused; - pdn = add_one_sriov_vf_pdn(parent, i, + pdn = add_one_sriov_vf_pdn(parent, pci_iov_virtfn_bus(pdev, i), pci_iov_virtfn_devfn(pdev, i)); if (!pdn) { @@ -187,7 +205,10 @@ struct pci_dn *add_sriov_vf_pdns(struct pci_dev *pdev) /* Create the EEH device for the VF */ edev = eeh_dev_init(pdn); BUG_ON(!edev); + + /* FIXME: these should probably be populated by the EEH probe */ edev->physfn = pdev; + edev->vf_index = i; #endif /* CONFIG_EEH */ } return pci_get_pdn(pdev); @@ -242,7 +263,7 @@ void remove_sriov_vf_pdns(struct pci_dev *pdev) * have a configured PE. */ if (edev->pe) - eeh_rmv_from_parent_pe(edev); + eeh_pe_tree_remove(edev); pdn->edev = NULL; kfree(edev); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 794b754deec2..016bd831908e 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -471,49 +471,58 @@ EXPORT_SYMBOL(giveup_all); #ifdef CONFIG_PPC_BOOK3S_64 #ifdef CONFIG_PPC_FPU -static int restore_fp(struct task_struct *tsk) +static bool should_restore_fp(void) { - if (tsk->thread.load_fp) { - load_fp_state(¤t->thread.fp_state); + if (current->thread.load_fp) { current->thread.load_fp++; - return 1; + return true; } - return 0; + return false; +} + +static void do_restore_fp(void) +{ + load_fp_state(¤t->thread.fp_state); } #else -static int restore_fp(struct task_struct *tsk) { return 0; } +static bool should_restore_fp(void) { return false; } +static void do_restore_fp(void) { } #endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC -#define loadvec(thr) ((thr).load_vec) -static int restore_altivec(struct task_struct *tsk) +static bool should_restore_altivec(void) { - if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) { - load_vr_state(&tsk->thread.vr_state); - tsk->thread.used_vr = 1; - tsk->thread.load_vec++; - - return 1; + if (cpu_has_feature(CPU_FTR_ALTIVEC) && (current->thread.load_vec)) { + current->thread.load_vec++; + return true; } - return 0; + return false; +} + +static void do_restore_altivec(void) +{ + load_vr_state(¤t->thread.vr_state); + current->thread.used_vr = 1; } #else -#define loadvec(thr) 0 -static inline int restore_altivec(struct task_struct *tsk) { return 0; } +static bool should_restore_altivec(void) { return false; } +static void do_restore_altivec(void) { } #endif /* CONFIG_ALTIVEC */ #ifdef CONFIG_VSX -static int restore_vsx(struct task_struct *tsk) +static bool should_restore_vsx(void) { - if (cpu_has_feature(CPU_FTR_VSX)) { - tsk->thread.used_vsr = 1; - return 1; - } - - return 0; + if (cpu_has_feature(CPU_FTR_VSX)) + return true; + return false; +} +static void do_restore_vsx(void) +{ + current->thread.used_vsr = 1; } #else -static inline int restore_vsx(struct task_struct *tsk) { return 0; } +static bool should_restore_vsx(void) { return false; } +static void do_restore_vsx(void) { } #endif /* CONFIG_VSX */ /* @@ -529,32 +538,42 @@ static inline int restore_vsx(struct task_struct *tsk) { return 0; } void notrace restore_math(struct pt_regs *regs) { unsigned long msr; - - if (!MSR_TM_ACTIVE(regs->msr) && - !current->thread.load_fp && !loadvec(current->thread)) - return; + unsigned long new_msr = 0; msr = regs->msr; - msr_check_and_set(msr_all_available); /* - * Only reload if the bit is not set in the user MSR, the bit BEING set - * indicates that the registers are hot + * new_msr tracks the facilities that are to be restored. Only reload + * if the bit is not set in the user MSR (if it is set, the registers + * are live for the user thread). */ - if ((!(msr & MSR_FP)) && restore_fp(current)) - msr |= MSR_FP | current->thread.fpexc_mode; + if ((!(msr & MSR_FP)) && should_restore_fp()) + new_msr |= MSR_FP | current->thread.fpexc_mode; - if ((!(msr & MSR_VEC)) && restore_altivec(current)) - msr |= MSR_VEC; + if ((!(msr & MSR_VEC)) && should_restore_altivec()) + new_msr |= MSR_VEC; - if ((msr & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC) && - restore_vsx(current)) { - msr |= MSR_VSX; + if ((!(msr & MSR_VSX)) && should_restore_vsx()) { + if (((msr | new_msr) & (MSR_FP | MSR_VEC)) == (MSR_FP | MSR_VEC)) + new_msr |= MSR_VSX; } - msr_check_and_clear(msr_all_available); + if (new_msr) { + msr_check_and_set(new_msr); + + if (new_msr & MSR_FP) + do_restore_fp(); + + if (new_msr & MSR_VEC) + do_restore_altivec(); + + if (new_msr & MSR_VSX) + do_restore_vsx(); - regs->msr = msr; + msr_check_and_clear(new_msr); + + regs->msr |= new_msr; + } } #endif @@ -1599,6 +1618,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, { struct pt_regs *childregs, *kregs; extern void ret_from_fork(void); + extern void ret_from_fork_scv(void); extern void ret_from_kernel_thread(void); void (*f)(void); unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE; @@ -1635,7 +1655,9 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, if (usp) childregs->gpr[1] = usp; p->thread.regs = childregs; - childregs->gpr[3] = 0; /* Result from fork() */ + /* 64s sets this in ret_from_fork */ + if (!IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + childregs->gpr[3] = 0; /* Result from fork() */ if (clone_flags & CLONE_SETTLS) { if (!is_32bit_task()) childregs->gpr[13] = tls; @@ -1643,7 +1665,10 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, childregs->gpr[2] = tls; } - f = ret_from_fork; + if (trap_is_scv(regs)) + f = ret_from_fork_scv; + else + f = ret_from_fork; } childregs->msr &= ~(MSR_FP|MSR_VEC|MSR_VSX); sp -= STACK_FRAME_OVERHEAD; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9cc49f265c86..d8a2fb87ba0c 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -163,7 +163,7 @@ static struct ibm_pa_feature { { .pabyte = 0, .pabit = 6, .cpu_features = CPU_FTR_NOEXECUTE }, { .pabyte = 1, .pabit = 2, .mmu_features = MMU_FTR_CI_LARGE_PAGE }, #ifdef CONFIG_PPC_RADIX_MMU - { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX }, + { .pabyte = 40, .pabit = 0, .mmu_features = MMU_FTR_TYPE_RADIX | MMU_FTR_GTSE }, #endif { .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN }, { .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE, @@ -175,6 +175,8 @@ static struct ibm_pa_feature { */ { .pabyte = 22, .pabit = 0, .cpu_features = CPU_FTR_TM_COMP, .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP }, + + { .pabyte = 64, .pabit = 0, .cpu_features = CPU_FTR_DAWR1 }, }; static void __init scan_features(unsigned long node, const unsigned char *ftrs, @@ -468,8 +470,9 @@ static bool validate_mem_limit(u64 base, u64 *size) * This contains a list of memory blocks along with NUMA affinity * information. */ -static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, - const __be32 **usm) +static int __init early_init_drmem_lmb(struct drmem_lmb *lmb, + const __be32 **usm, + void *data) { u64 base, size; int is_kexec_kdump = 0, rngs; @@ -484,7 +487,7 @@ static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, */ if ((lmb->flags & DRCONF_MEM_RESERVED) || !(lmb->flags & DRCONF_MEM_ASSIGNED)) - return; + return 0; if (*usm) is_kexec_kdump = 1; @@ -499,7 +502,7 @@ static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, */ rngs = dt_mem_next_cell(dt_root_size_cells, usm); if (!rngs) /* there are no (base, size) duple */ - return; + return 0; } do { @@ -524,6 +527,8 @@ static void __init early_init_drmem_lmb(struct drmem_lmb *lmb, if (lmb->flags & DRCONF_MEM_HOTREMOVABLE) memblock_mark_hotplug(base, size); } while (--rngs); + + return 0; } #endif /* CONFIG_PPC_PSERIES */ @@ -534,7 +539,7 @@ static int __init early_init_dt_scan_memory_ppc(unsigned long node, #ifdef CONFIG_PPC_PSERIES if (depth == 1 && strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) { - walk_drmem_lmbs_early(node, early_init_drmem_lmb); + walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb); return 0; } #endif @@ -815,6 +820,11 @@ void __init early_init_devtree(void *params) /* Now try to figure out if we are running on LPAR and so on */ pseries_probe_fw_features(); + /* + * Initialize pkey features and default AMR/IAMR values + */ + pkey_early_init_devtree(); + #ifdef CONFIG_PPC_PS3 /* Identify PS3 firmware */ if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3")) diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 90c604d00b7d..ae7ec9903191 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -169,6 +169,7 @@ static unsigned long __prombss prom_tce_alloc_end; #ifdef CONFIG_PPC_PSERIES static bool __prombss prom_radix_disable; +static bool __prombss prom_radix_gtse_disable; static bool __prombss prom_xive_disable; #endif @@ -823,6 +824,12 @@ static void __init early_cmdline_parse(void) if (prom_radix_disable) prom_debug("Radix disabled from cmdline\n"); + opt = prom_strstr(prom_cmd_line, "radix_hcall_invalidate=on"); + if (opt) { + prom_radix_gtse_disable = true; + prom_debug("Radix GTSE disabled from cmdline\n"); + } + opt = prom_strstr(prom_cmd_line, "xive=off"); if (opt) { prom_xive_disable = true; @@ -1285,10 +1292,8 @@ static void __init prom_parse_platform_support(u8 index, u8 val, prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support); break; case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */ - if (val & OV5_FEAT(OV5_RADIX_GTSE)) { - prom_debug("Radix - GTSE supported\n"); - support->radix_gtse = true; - } + if (val & OV5_FEAT(OV5_RADIX_GTSE)) + support->radix_gtse = !prom_radix_gtse_disable; break; case OV5_INDX(OV5_XIVE_SUPPORT): /* Interrupt mode */ prom_parse_xive_model(val & OV5_FEAT(OV5_XIVE_SUPPORT), @@ -1336,12 +1341,15 @@ static void __init prom_check_platform_support(void) } } - if (supported.radix_mmu && supported.radix_gtse && - IS_ENABLED(CONFIG_PPC_RADIX_MMU)) { - /* Radix preferred - but we require GTSE for now */ - prom_debug("Asking for radix with GTSE\n"); + if (supported.radix_mmu && IS_ENABLED(CONFIG_PPC_RADIX_MMU)) { + /* Radix preferred - Check if GTSE is also supported */ + prom_debug("Asking for radix\n"); ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX); - ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE); + if (supported.radix_gtse) + ibm_architecture_vec.vec5.radix_ext = + OV5_FEAT(OV5_RADIX_GTSE); + else + prom_debug("Radix GTSE isn't supported\n"); } else if (supported.hash_mmu) { /* Default to hash mmu (if we can) */ prom_debug("Asking for hash\n"); @@ -3262,7 +3270,7 @@ static int enter_secure_mode(unsigned long kbase, unsigned long fdt) /* * Call the Ultravisor to transfer us to secure memory if we have an ESM blob. */ -static void setup_secure_guest(unsigned long kbase, unsigned long fdt) +static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt) { int ret; @@ -3292,7 +3300,7 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt) } } #else -static void setup_secure_guest(unsigned long kbase, unsigned long fdt) +static void __init setup_secure_guest(unsigned long kbase, unsigned long fdt) { } #endif /* CONFIG_PPC_SVM */ diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 13208a9a02ca..7e6478e7ed07 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -471,12 +471,12 @@ static int pkey_get(struct task_struct *target, const struct user_regset *regset struct membuf to) { BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr)); - BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor)); if (!arch_pkeys_enabled()) return -ENODEV; - return membuf_write(&to, &target->thread.amr, ELF_NPKEY * sizeof(unsigned long)); + membuf_write(&to, &target->thread.amr, 2 * sizeof(unsigned long)); + return membuf_store(&to, default_uamor); } static int pkey_set(struct task_struct *target, const struct user_regset *regset, @@ -498,9 +498,17 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset if (ret) return ret; - /* UAMOR determines which bits of the AMR can be set from userspace. */ - target->thread.amr = (new_amr & target->thread.uamor) | - (target->thread.amr & ~target->thread.uamor); + /* + * UAMOR determines which bits of the AMR can be set from userspace. + * UAMOR value 0b11 indicates that the AMR value can be modified + * from userspace. If the kernel is using a specific key, we avoid + * userspace modifying the AMR value for that key by masking them + * via UAMOR 0b00. + * + * Pick the AMR values for the keys that kernel is using. This + * will be indicated by the ~default_uamor bits. + */ + target->thread.amr = (new_amr & default_uamor) | (target->thread.amr & ~default_uamor); return 0; } diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index a09eba03f180..806d554ce357 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -843,96 +843,6 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } -enum rtas_cpu_state { - DOWN, - UP, -}; - -#ifndef CONFIG_SMP -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - if (!cpumask_empty(cpus)) { - cpumask_clear(cpus); - return -EINVAL; - } else - return 0; -} -#else -/* On return cpumask will be altered to indicate CPUs changed. - * CPUs with states changed will be set in the mask, - * CPUs with status unchanged will be unset in the mask. */ -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - int cpu; - int cpuret = 0; - int ret = 0; - - if (cpumask_empty(cpus)) - return 0; - - for_each_cpu(cpu, cpus) { - struct device *dev = get_cpu_device(cpu); - - switch (state) { - case DOWN: - cpuret = device_offline(dev); - break; - case UP: - cpuret = device_online(dev); - break; - } - if (cpuret < 0) { - pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", - __func__, - ((state == UP) ? "up" : "down"), - cpu, cpuret); - if (!ret) - ret = cpuret; - if (state == UP) { - /* clear bits for unchanged cpus, return */ - cpumask_shift_right(cpus, cpus, cpu); - cpumask_shift_left(cpus, cpus, cpu); - break; - } else { - /* clear bit for unchanged cpu, continue */ - cpumask_clear_cpu(cpu, cpus); - } - } - cond_resched(); - } - - return ret; -} -#endif - -int rtas_online_cpus_mask(cpumask_var_t cpus) -{ - int ret; - - ret = rtas_cpu_state_change_mask(UP, cpus); - - if (ret) { - cpumask_var_t tmp_mask; - - if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL)) - return ret; - - /* Use tmp_mask to preserve cpus mask from first failure */ - cpumask_copy(tmp_mask, cpus); - rtas_offline_cpus_mask(tmp_mask); - free_cpumask_var(tmp_mask); - } - - return ret; -} - -int rtas_offline_cpus_mask(cpumask_var_t cpus) -{ - return rtas_cpu_state_change_mask(DOWN, cpus); -} - int rtas_ibm_suspend_me(u64 handle) { long state; @@ -940,8 +850,6 @@ int rtas_ibm_suspend_me(u64 handle) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); - cpumask_var_t offline_mask; - int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -962,9 +870,6 @@ int rtas_ibm_suspend_me(u64 handle) return -EIO; } - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); @@ -973,24 +878,8 @@ int rtas_ibm_suspend_me(u64 handle) lock_device_hotplug(); - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); - cpuret = rtas_online_cpus_mask(offline_mask); - if (cpuret) { - pr_err("%s: Could not bring present CPUs online.\n", __func__); - atomic_set(&data.error, cpuret); - goto out; - } - cpu_hotplug_disable(); - /* Check if we raced with a CPU-Offline Operation */ - if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { - pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); - atomic_set(&data.error, -EAGAIN); - goto out_hotplug_enable; - } - /* Call function on all CPUs. One of us will make the * rtas call */ @@ -1001,18 +890,11 @@ int rtas_ibm_suspend_me(u64 handle) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); -out_hotplug_enable: - cpu_hotplug_enable(); - /* Take down CPUs not online prior to suspend */ - cpuret = rtas_offline_cpus_mask(offline_mask); - if (cpuret) - pr_warn("%s: Could not restore CPUs to offline state.\n", - __func__); + cpu_hotplug_enable(); -out: unlock_device_hotplug(); - free_cpumask_var(offline_mask); + return atomic_read(&data.error); } diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c index 89b798f8f656..8561dfb33f24 100644 --- a/arch/powerpc/kernel/rtasd.c +++ b/arch/powerpc/kernel/rtasd.c @@ -273,37 +273,15 @@ void pSeries_log_error(char *buf, unsigned int err_type, int fatal) } } -#ifdef CONFIG_PPC_PSERIES -static void handle_prrn_event(s32 scope) -{ - /* - * For PRRN, we must pass the negative of the scope value in - * the RTAS event. - */ - pseries_devicetree_update(-scope); - numa_update_cpu_topology(false); -} - static void handle_rtas_event(const struct rtas_error_log *log) { - if (rtas_error_type(log) != RTAS_TYPE_PRRN || !prrn_is_enabled()) + if (!machine_is(pseries)) return; - /* For PRRN Events the extended log length is used to denote - * the scope for calling rtas update-nodes. - */ - handle_prrn_event(rtas_error_extended_log_length(log)); + if (rtas_error_type(log) == RTAS_TYPE_PRRN) + pr_info_ratelimited("Platform resource reassignment ignored.\n"); } -#else - -static void handle_rtas_event(const struct rtas_error_log *log) -{ - return; -} - -#endif - static int rtas_log_open(struct inode * inode, struct file * file) { return 0; diff --git a/arch/powerpc/kernel/secure_boot.c b/arch/powerpc/kernel/secure_boot.c index 4b982324d368..f9af305d9579 100644 --- a/arch/powerpc/kernel/secure_boot.c +++ b/arch/powerpc/kernel/secure_boot.c @@ -23,12 +23,19 @@ bool is_ppc_secureboot_enabled(void) { struct device_node *node; bool enabled = false; + u32 secureboot; node = get_ppc_fw_sb_node(); enabled = of_property_read_bool(node, "os-secureboot-enforcing"); - of_node_put(node); + if (enabled) + goto out; + + if (!of_property_read_u32(of_root, "ibm,secure-boot", &secureboot)) + enabled = (secureboot > 1); + +out: pr_info("Secure boot mode %s\n", enabled ? "enabled" : "disabled"); return enabled; @@ -38,12 +45,19 @@ bool is_ppc_trustedboot_enabled(void) { struct device_node *node; bool enabled = false; + u32 trustedboot; node = get_ppc_fw_sb_node(); enabled = of_property_read_bool(node, "trusted-enabled"); - of_node_put(node); + if (enabled) + goto out; + + if (!of_property_read_u32(of_root, "ibm,trusted-boot", &trustedboot)) + enabled = (trustedboot > 0); + +out: pr_info("Trusted boot mode %s\n", enabled ? "enabled" : "disabled"); return enabled; diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index d86701ce116b..c9876aab3142 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -21,13 +21,13 @@ u64 powerpc_security_features __read_mostly = SEC_FTR_DEFAULT; -enum count_cache_flush_type { - COUNT_CACHE_FLUSH_NONE = 0x1, - COUNT_CACHE_FLUSH_SW = 0x2, - COUNT_CACHE_FLUSH_HW = 0x4, +enum branch_cache_flush_type { + BRANCH_CACHE_FLUSH_NONE = 0x1, + BRANCH_CACHE_FLUSH_SW = 0x2, + BRANCH_CACHE_FLUSH_HW = 0x4, }; -static enum count_cache_flush_type count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; -static bool link_stack_flush_enabled; +static enum branch_cache_flush_type count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE; +static enum branch_cache_flush_type link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE; bool barrier_nospec_enabled; static bool no_nospec; @@ -219,24 +219,25 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c if (ccd) seq_buf_printf(&s, "Indirect branch cache disabled"); - if (link_stack_flush_enabled) - seq_buf_printf(&s, ", Software link stack flush"); - - } else if (count_cache_flush_type != COUNT_CACHE_FLUSH_NONE) { + } else if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) { seq_buf_printf(&s, "Mitigation: Software count cache flush"); - if (count_cache_flush_type == COUNT_CACHE_FLUSH_HW) + if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW) seq_buf_printf(&s, " (hardware accelerated)"); - if (link_stack_flush_enabled) - seq_buf_printf(&s, ", Software link stack flush"); - } else if (btb_flush_enabled) { seq_buf_printf(&s, "Mitigation: Branch predictor state flush"); } else { seq_buf_printf(&s, "Vulnerable"); } + if (bcs || ccd || count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) { + if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE) + seq_buf_printf(&s, ", Software link stack flush"); + if (link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) + seq_buf_printf(&s, " (hardware accelerated)"); + } + seq_buf_printf(&s, "\n"); return s.len; @@ -427,61 +428,79 @@ static __init int stf_barrier_debugfs_init(void) device_initcall(stf_barrier_debugfs_init); #endif /* CONFIG_DEBUG_FS */ -static void no_count_cache_flush(void) +static void update_branch_cache_flush(void) { - count_cache_flush_type = COUNT_CACHE_FLUSH_NONE; - pr_info("count-cache-flush: software flush disabled.\n"); -} - -static void toggle_count_cache_flush(bool enable) -{ - if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE) && - !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) - enable = false; - - if (!enable) { - patch_instruction_site(&patch__call_flush_count_cache, - ppc_inst(PPC_INST_NOP)); #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + // This controls the branch from guest_exit_cont to kvm_flush_link_stack + if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { patch_instruction_site(&patch__call_kvm_flush_link_stack, ppc_inst(PPC_INST_NOP)); -#endif - pr_info("link-stack-flush: software flush disabled.\n"); - link_stack_flush_enabled = false; - no_count_cache_flush(); - return; + } else { + // Could use HW flush, but that could also flush count cache + patch_branch_site(&patch__call_kvm_flush_link_stack, + (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); } - - // This enables the branch from _switch to flush_count_cache - patch_branch_site(&patch__call_flush_count_cache, - (u64)&flush_count_cache, BRANCH_SET_LINK); - -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE - // This enables the branch from guest_exit_cont to kvm_flush_link_stack - patch_branch_site(&patch__call_kvm_flush_link_stack, - (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); #endif - pr_info("link-stack-flush: software flush enabled.\n"); - link_stack_flush_enabled = true; + // This controls the branch from _switch to flush_branch_caches + if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE && + link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { + patch_instruction_site(&patch__call_flush_branch_caches, + ppc_inst(PPC_INST_NOP)); + } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW && + link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) { + patch_instruction_site(&patch__call_flush_branch_caches, + ppc_inst(PPC_INST_BCCTR_FLUSH)); + } else { + patch_branch_site(&patch__call_flush_branch_caches, + (u64)&flush_branch_caches, BRANCH_SET_LINK); + + // If we just need to flush the link stack, early return + if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) { + patch_instruction_site(&patch__flush_link_stack_return, + ppc_inst(PPC_INST_BLR)); + + // If we have flush instruction, early return + } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW) { + patch_instruction_site(&patch__flush_count_cache_return, + ppc_inst(PPC_INST_BLR)); + } + } +} - // If we just need to flush the link stack, patch an early return - if (!security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { - patch_instruction_site(&patch__flush_link_stack_return, - ppc_inst(PPC_INST_BLR)); - no_count_cache_flush(); - return; +static void toggle_branch_cache_flush(bool enable) +{ + if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) { + if (count_cache_flush_type != BRANCH_CACHE_FLUSH_NONE) + count_cache_flush_type = BRANCH_CACHE_FLUSH_NONE; + + pr_info("count-cache-flush: flush disabled.\n"); + } else { + if (security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { + count_cache_flush_type = BRANCH_CACHE_FLUSH_HW; + pr_info("count-cache-flush: hardware flush enabled.\n"); + } else { + count_cache_flush_type = BRANCH_CACHE_FLUSH_SW; + pr_info("count-cache-flush: software flush enabled.\n"); + } } - if (!security_ftr_enabled(SEC_FTR_BCCTR_FLUSH_ASSIST)) { - count_cache_flush_type = COUNT_CACHE_FLUSH_SW; - pr_info("count-cache-flush: full software flush sequence enabled.\n"); - return; + if (!enable || !security_ftr_enabled(SEC_FTR_FLUSH_LINK_STACK)) { + if (link_stack_flush_type != BRANCH_CACHE_FLUSH_NONE) + link_stack_flush_type = BRANCH_CACHE_FLUSH_NONE; + + pr_info("link-stack-flush: flush disabled.\n"); + } else { + if (security_ftr_enabled(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST)) { + link_stack_flush_type = BRANCH_CACHE_FLUSH_HW; + pr_info("link-stack-flush: hardware flush enabled.\n"); + } else { + link_stack_flush_type = BRANCH_CACHE_FLUSH_SW; + pr_info("link-stack-flush: software flush enabled.\n"); + } } - patch_instruction_site(&patch__flush_count_cache_return, ppc_inst(PPC_INST_BLR)); - count_cache_flush_type = COUNT_CACHE_FLUSH_HW; - pr_info("count-cache-flush: hardware assisted flush sequence enabled\n"); + update_branch_cache_flush(); } void setup_count_cache_flush(void) @@ -505,7 +524,7 @@ void setup_count_cache_flush(void) security_ftr_enabled(SEC_FTR_FLUSH_COUNT_CACHE)) security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); - toggle_count_cache_flush(enable); + toggle_branch_cache_flush(enable); } #ifdef CONFIG_DEBUG_FS @@ -520,14 +539,14 @@ static int count_cache_flush_set(void *data, u64 val) else return -EINVAL; - toggle_count_cache_flush(enable); + toggle_branch_cache_flush(enable); return 0; } static int count_cache_flush_get(void *data, u64 *val) { - if (count_cache_flush_type == COUNT_CACHE_FLUSH_NONE) + if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) *val = 0; else *val = 1; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9d3faac53295..b198b0ff25bc 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -928,6 +928,9 @@ void __init setup_arch(char **cmdline_p) /* Reserve large chunks of memory for use by CMA for KVM. */ kvm_cma_reserve(); + /* Reserve large chunks of memory for us by CMA for hugetlb */ + gigantic_hugetlb_cma_reserve(); + klp_init_thread_info(&init_task); init_mm.start_code = (unsigned long)_stext; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 0ba1ed77dc68..6be430107c6f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -196,7 +196,10 @@ static void __init configure_exceptions(void) /* Under a PAPR hypervisor, we need hypercalls */ if (firmware_has_feature(FW_FEATURE_SET_MODE)) { /* Enable AIL if possible */ - pseries_enable_reloc_on_exc(); + if (!pseries_enable_reloc_on_exc()) { + init_task.thread.fscr &= ~FSCR_SCV; + cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV; + } /* * Tell the hypervisor that we want our exceptions to diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c index b4143b6ff093..d15a98c758b8 100644 --- a/arch/powerpc/kernel/signal.c +++ b/arch/powerpc/kernel/signal.c @@ -205,8 +205,14 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, return; /* error signalled ? */ - if (!(regs->ccr & 0x10000000)) + if (trap_is_scv(regs)) { + /* 32-bit compat mode sign extend? */ + if (!IS_ERR_VALUE(ret)) + return; + ret = -ret; + } else if (!(regs->ccr & 0x10000000)) { return; + } switch (ret) { case ERESTART_RESTARTBLOCK: @@ -239,9 +245,14 @@ static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka, regs->nip -= 4; regs->result = 0; } else { - regs->result = -EINTR; - regs->gpr[3] = EINTR; - regs->ccr |= 0x10000000; + if (trap_is_scv(regs)) { + regs->result = -EINTR; + regs->gpr[3] = -EINTR; + } else { + regs->result = -EINTR; + regs->gpr[3] = EINTR; + regs->ccr |= 0x10000000; + } } } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 1415c16ab628..96950f189b5a 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -102,22 +102,18 @@ static inline int save_general_regs(struct pt_regs *regs, struct mcontext __user *frame) { elf_greg_t64 *gregs = (elf_greg_t64 *)regs; - int i; - /* Force usr to alway see softe as 1 (interrupts enabled) */ - elf_greg_t64 softe = 0x1; + int val, i; WARN_ON(!FULL_REGS(regs)); for (i = 0; i <= PT_RESULT; i ++) { - if (i == 14 && !FULL_REGS(regs)) - i = 32; - if ( i == PT_SOFTE) { - if(__put_user((unsigned int)softe, &frame->mc_gregs[i])) - return -EFAULT; - else - continue; - } - if (__put_user((unsigned int)gregs[i], &frame->mc_gregs[i])) + /* Force usr to alway see softe as 1 (interrupts enabled) */ + if (i == PT_SOFTE) + val = 1; + else + val = gregs[i]; + + if (__put_user(val, &frame->mc_gregs[i])) return -EFAULT; } return 0; diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 55e5f76554da..bfc939360bad 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -21,6 +21,7 @@ #include <linux/ptrace.h> #include <linux/ratelimit.h> #include <linux/syscalls.h> +#include <linux/pagemap.h> #include <asm/sigcontext.h> #include <asm/ucontext.h> @@ -39,8 +40,8 @@ #define GP_REGS_SIZE min(sizeof(elf_gregset_t), sizeof(struct pt_regs)) #define FP_REGS_SIZE sizeof(elf_fpregset_t) -#define TRAMP_TRACEBACK 3 -#define TRAMP_SIZE 6 +#define TRAMP_TRACEBACK 4 +#define TRAMP_SIZE 7 /* * When we have signals to deliver, we set up on the user stack, @@ -600,13 +601,15 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) int i; long err = 0; + /* bctrl # call the handler */ + err |= __put_user(PPC_INST_BCTRL, &tramp[0]); /* addi r1, r1, __SIGNAL_FRAMESIZE # Pop the dummy stackframe */ err |= __put_user(PPC_INST_ADDI | __PPC_RT(R1) | __PPC_RA(R1) | - (__SIGNAL_FRAMESIZE & 0xffff), &tramp[0]); + (__SIGNAL_FRAMESIZE & 0xffff), &tramp[1]); /* li r0, __NR_[rt_]sigreturn| */ - err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[1]); + err |= __put_user(PPC_INST_ADDI | (syscall & 0xffff), &tramp[2]); /* sc */ - err |= __put_user(PPC_INST_SC, &tramp[2]); + err |= __put_user(PPC_INST_SC, &tramp[3]); /* Minimal traceback info */ for (i=TRAMP_TRACEBACK; i < TRAMP_SIZE ;i++) @@ -632,7 +635,6 @@ static long setup_trampoline(unsigned int syscall, unsigned int __user *tramp) SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, struct ucontext __user *, new_ctx, long, ctx_size) { - unsigned char tmp; sigset_t set; unsigned long new_msr = 0; int ctx_has_vsx_region = 0; @@ -667,9 +669,8 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, } if (new_ctx == NULL) return 0; - if (!access_ok(new_ctx, ctx_size) - || __get_user(tmp, (u8 __user *) new_ctx) - || __get_user(tmp, (u8 __user *) new_ctx + ctx_size - 1)) + if (!access_ok(new_ctx, ctx_size) || + fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) return -EFAULT; /* @@ -864,12 +865,12 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, /* Set up to return from userspace. */ if (vdso64_rt_sigtramp && tsk->mm->context.vdso_base) { - regs->link = tsk->mm->context.vdso_base + vdso64_rt_sigtramp; + regs->nip = tsk->mm->context.vdso_base + vdso64_rt_sigtramp; } else { err |= setup_trampoline(__NR_rt_sigreturn, &frame->tramp[0]); if (err) goto badframe; - regs->link = (unsigned long) &frame->tramp[0]; + regs->nip = (unsigned long) &frame->tramp[0]; } /* Allocate a dummy caller frame for the signal handler. */ @@ -878,8 +879,8 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, /* Set up "regs" so we "return" to the signal handler. */ if (is_elf2_task()) { - regs->nip = (unsigned long) ksig->ka.sa.sa_handler; - regs->gpr[12] = regs->nip; + regs->ctr = (unsigned long) ksig->ka.sa.sa_handler; + regs->gpr[12] = regs->ctr; } else { /* Handler is *really* a pointer to the function descriptor for * the signal routine. The first entry in the function @@ -889,7 +890,7 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, func_descr_t __user *funct_desc_ptr = (func_descr_t __user *) ksig->ka.sa.sa_handler; - err |= get_user(regs->nip, &funct_desc_ptr->entry); + err |= get_user(regs->ctr, &funct_desc_ptr->entry); err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); } diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 73199470c265..8261999c7d52 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -59,6 +59,7 @@ #include <asm/asm-prototypes.h> #include <asm/cpu_has_feature.h> #include <asm/ftrace.h> +#include <asm/kup.h> #ifdef DEBUG #include <asm/udbg.h> diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index 79edba3ab312..8e50818aa50b 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -60,6 +60,11 @@ notrace long system_call_exception(long r3, long r4, long r5, local_irq_enable(); if (unlikely(current_thread_info()->flags & _TIF_SYSCALL_DOTRACE)) { + if (unlikely(regs->trap == 0x7ff0)) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } /* * We use the return value of do_syscall_trace_enter() as the * syscall number. If the syscall was rejected for any reason @@ -78,6 +83,11 @@ notrace long system_call_exception(long r3, long r4, long r5, r8 = regs->gpr[8]; } else if (unlikely(r0 >= NR_syscalls)) { + if (unlikely(regs->trap == 0x7ff0)) { + /* Unsupported scv vector */ + _exception(SIGILL, regs, ILL_ILLOPC, regs->nip); + return regs->gpr[3]; + } return -ENOSYS; } @@ -105,16 +115,20 @@ notrace long system_call_exception(long r3, long r4, long r5, * local irqs must be disabled. Returns false if the caller must re-enable * them, check for new work, and try again. */ -static notrace inline bool prep_irq_for_enabled_exit(void) +static notrace inline bool prep_irq_for_enabled_exit(bool clear_ri) { /* This must be done with RI=1 because tracing may touch vmaps */ trace_hardirqs_on(); /* This pattern matches prep_irq_for_idle */ - __hard_EE_RI_disable(); + if (clear_ri) + __hard_EE_RI_disable(); + else + __hard_irq_disable(); if (unlikely(lazy_irq_pending_nocheck())) { /* Took an interrupt, may have more exit work to do. */ - __hard_RI_enable(); + if (clear_ri) + __hard_RI_enable(); trace_hardirqs_off(); local_paca->irq_happened |= PACA_IRQ_HARD_DIS; @@ -136,7 +150,8 @@ static notrace inline bool prep_irq_for_enabled_exit(void) * because RI=0 and soft mask state is "unreconciled", so it is marked notrace. */ notrace unsigned long syscall_exit_prepare(unsigned long r3, - struct pt_regs *regs) + struct pt_regs *regs, + long scv) { unsigned long *ti_flagsp = ¤t_thread_info()->flags; unsigned long ti_flags; @@ -151,7 +166,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3, ti_flags = *ti_flagsp; - if (unlikely(r3 >= (unsigned long)-MAX_ERRNO)) { + if (unlikely(r3 >= (unsigned long)-MAX_ERRNO) && !scv) { if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) { r3 = -r3; regs->ccr |= 0x10000000; /* Set SO bit in CR */ @@ -206,12 +221,20 @@ again: else if (cpu_has_feature(CPU_FTR_ALTIVEC)) mathflags |= MSR_VEC; + /* + * If userspace MSR has all available FP bits set, + * then they are live and no need to restore. If not, + * it means the regs were given up and restore_math + * may decide to restore them (to avoid taking an FP + * fault). + */ if ((regs->msr & mathflags) != mathflags) restore_math(regs); } } - if (unlikely(!prep_irq_for_enabled_exit())) { + /* scv need not set RI=0 because SRRs are not used */ + if (unlikely(!prep_irq_for_enabled_exit(!scv))) { local_irq_enable(); goto again; } @@ -277,12 +300,13 @@ again: else if (cpu_has_feature(CPU_FTR_ALTIVEC)) mathflags |= MSR_VEC; + /* See above restore_math comment */ if ((regs->msr & mathflags) != mathflags) restore_math(regs); } } - if (unlikely(!prep_irq_for_enabled_exit())) { + if (unlikely(!prep_irq_for_enabled_exit(true))) { local_irq_enable(); local_irq_disable(); goto again; @@ -345,7 +369,7 @@ again: } } - if (unlikely(!prep_irq_for_enabled_exit())) { + if (unlikely(!prep_irq_for_enabled_exit(true))) { /* * Can't local_irq_restore to replay if we were in * interrupt context. Must replay directly. diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index be9f74546068..c2d737ff2e7b 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -197,7 +197,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 nospu _sysctl sys_sysctl compat_sys_sysctl +149 nospu _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 571b3259697e..46b4ebc33db7 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -622,8 +622,10 @@ SYSFS_PMCSETUP(pmc7, SPRN_PMC7); SYSFS_PMCSETUP(pmc8, SPRN_PMC8); SYSFS_PMCSETUP(mmcra, SPRN_MMCRA); +SYSFS_PMCSETUP(mmcr3, SPRN_MMCR3); static DEVICE_ATTR(mmcra, 0600, show_mmcra, store_mmcra); +static DEVICE_ATTR(mmcr3, 0600, show_mmcr3, store_mmcr3); #endif /* HAS_PPC_PMC56 */ @@ -886,6 +888,9 @@ static int register_cpu_online(unsigned int cpu) #ifdef CONFIG_PMU_SYSFS if (cpu_has_feature(CPU_FTR_MMCRA)) device_create_file(s, &dev_attr_mmcra); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + device_create_file(s, &dev_attr_mmcr3); #endif /* CONFIG_PMU_SYSFS */ if (cpu_has_feature(CPU_FTR_PURR)) { @@ -980,6 +985,9 @@ static int unregister_cpu_online(unsigned int cpu) #ifdef CONFIG_PMU_SYSFS if (cpu_has_feature(CPU_FTR_MMCRA)) device_remove_file(s, &dev_attr_mmcra); + + if (cpu_has_feature(CPU_FTR_ARCH_31)) + device_remove_file(s, &dev_attr_mmcr3); #endif /* CONFIG_PMU_SYSFS */ if (cpu_has_feature(CPU_FTR_PURR)) { diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index c1fede6ec934..42761ebec9f7 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -73,8 +73,8 @@ ftrace_modify_code(unsigned long ip, struct ppc_inst old, struct ppc_inst new) /* Make sure it is what we expect it to be */ if (!ppc_inst_equal(replaced, old)) { - pr_err("%p: replaced (%#x) != old (%#x)", - (void *)ip, ppc_inst_val(replaced), ppc_inst_val(old)); + pr_err("%p: replaced (%s) != old (%s)", + (void *)ip, ppc_inst_as_str(replaced), ppc_inst_as_str(old)); return -EINVAL; } @@ -137,7 +137,7 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op)); + pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); return -EINVAL; } @@ -172,8 +172,8 @@ __ftrace_make_nop(struct module *mod, /* We expect either a mflr r0, or a std r0, LRSAVE(r1) */ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_MFLR)) && !ppc_inst_equal(op, ppc_inst(PPC_INST_STD_LR))) { - pr_err("Unexpected instruction %08x around bl _mcount\n", - ppc_inst_val(op)); + pr_err("Unexpected instruction %s around bl _mcount\n", + ppc_inst_as_str(op)); return -EINVAL; } #else @@ -203,7 +203,7 @@ __ftrace_make_nop(struct module *mod, } if (!ppc_inst_equal(op, ppc_inst(PPC_INST_LD_TOC))) { - pr_err("Expected %08x found %08x\n", PPC_INST_LD_TOC, ppc_inst_val(op)); + pr_err("Expected %08x found %s\n", PPC_INST_LD_TOC, ppc_inst_as_str(op)); return -EINVAL; } #endif /* CONFIG_MPROFILE_KERNEL */ @@ -231,7 +231,7 @@ __ftrace_make_nop(struct module *mod, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op)); + pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); return -EINVAL; } @@ -406,7 +406,7 @@ static int __ftrace_make_nop_kernel(struct dyn_ftrace *rec, unsigned long addr) /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op)); + pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); return -EINVAL; } @@ -533,8 +533,8 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return -EFAULT; if (!expected_nop_sequence(ip, op[0], op[1])) { - pr_err("Unexpected call sequence at %p: %x %x\n", - ip, ppc_inst_val(op[0]), ppc_inst_val(op[1])); + pr_err("Unexpected call sequence at %p: %s %s\n", + ip, ppc_inst_as_str(op[0]), ppc_inst_as_str(op[1])); return -EINVAL; } @@ -597,7 +597,7 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) /* It should be pointing to a nop */ if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) { - pr_err("Expected NOP but have %x\n", ppc_inst_val(op)); + pr_err("Expected NOP but have %s\n", ppc_inst_as_str(op)); return -EINVAL; } @@ -654,7 +654,7 @@ static int __ftrace_make_call_kernel(struct dyn_ftrace *rec, unsigned long addr) } if (!ppc_inst_equal(op, ppc_inst(PPC_INST_NOP))) { - pr_err("Unexpected call sequence at %p: %x\n", ip, ppc_inst_val(op)); + pr_err("Unexpected call sequence at %p: %s\n", ip, ppc_inst_as_str(op)); return -EINVAL; } @@ -733,7 +733,7 @@ __ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, /* Make sure that that this is still a 24bit jump */ if (!is_bl_op(op)) { - pr_err("Not expected bl: opcode is %x\n", ppc_inst_val(op)); + pr_err("Not expected bl: opcode is %s\n", ppc_inst_as_str(op)); return -EINVAL; } diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 97413a385720..d1ebe152f210 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -2060,14 +2060,6 @@ void DebugException(struct pt_regs *regs, unsigned long debug_status) NOKPROBE_SYMBOL(DebugException); #endif /* CONFIG_PPC_ADV_DEBUG_REGS */ -#if !defined(CONFIG_TAU_INT) -void TAUException(struct pt_regs *regs) -{ - printk("TAU trap at PC: %lx, MSR: %lx, vector=%lx %s\n", - regs->nip, regs->msr, regs->trap, print_tainted()); -} -#endif /* CONFIG_INT_TAU */ - #ifdef CONFIG_ALTIVEC void altivec_assist_exception(struct pt_regs *regs) { diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index e0f4ba45b6cc..8dad44262e75 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -677,7 +677,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index e147bbdc12cd..87ab1152d5ce 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -50,7 +50,7 @@ $(obj-vdso32): %.o: %.S FORCE # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) + cmd_vdso32ld = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 5206c2eb2a1d..4c985467a668 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -111,6 +111,7 @@ SECTIONS *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) + *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index 32ebb3522ea1..38c317f25141 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -34,7 +34,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) $(call cc-ldoption, -Wl$(comma)--orphan-handling=warn) # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S index 526f5ba2593e..cab14324242b 100644 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ b/arch/powerpc/kernel/vdso64/cacheflush.S @@ -8,6 +8,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> +#include <asm/vdso_datapage.h> #include <asm/asm-offsets.h> .text @@ -24,14 +25,12 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) .cfi_startproc mflr r12 .cfi_register lr,r12 - mr r11,r3 - bl V_LOCAL_FUNC(__get_datapage) + get_datapage r10, r0 mtlr r12 - mr r10,r3 lwz r7,CFG_DCACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 /* ensure we get enough */ lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) @@ -48,7 +47,7 @@ V_FUNCTION_BEGIN(__kernel_sync_dicache) lwz r7,CFG_ICACHE_BLOCKSZ(r10) addi r5,r7,-1 - andc r6,r11,r5 /* round low to line bdy */ + andc r6,r3,r5 /* round low to line bdy */ subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S index dc84f5ae3802..067247d3efb9 100644 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ b/arch/powerpc/kernel/vdso64/datapage.S @@ -10,35 +10,13 @@ #include <asm/asm-offsets.h> #include <asm/unistd.h> #include <asm/vdso.h> +#include <asm/vdso_datapage.h> .text .global __kernel_datapage_offset; __kernel_datapage_offset: .long 0 -V_FUNCTION_BEGIN(__get_datapage) - .cfi_startproc - /* We don't want that exposed or overridable as we want other objects - * to be able to bl directly to here - */ - .protected __get_datapage - .hidden __get_datapage - - mflr r0 - .cfi_register lr,r0 - - bcl 20,31,data_page_branch -data_page_branch: - mflr r3 - mtlr r0 - addi r3, r3, __kernel_datapage_offset-data_page_branch - lwz r0,0(r3) - .cfi_restore lr - add r3,r0,r3 - blr - .cfi_endproc -V_FUNCTION_END(__get_datapage) - /* * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; * @@ -53,7 +31,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr r4,r3 - bl V_LOCAL_FUNC(__get_datapage) + get_datapage r3, r0 mtlr r12 addi r3,r3,CFG_SYSCALL_MAP64 cmpldi cr0,r4,0 @@ -75,7 +53,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - bl V_LOCAL_FUNC(__get_datapage) + get_datapage r3, r0 ld r3,CFG_TB_TICKS_PER_SEC(r3) mtlr r12 crclr cr0*4+so diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S index 1c9a04703250..20f8be40c653 100644 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ b/arch/powerpc/kernel/vdso64/gettimeofday.S @@ -9,6 +9,7 @@ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/vdso.h> +#include <asm/vdso_datapage.h> #include <asm/asm-offsets.h> #include <asm/unistd.h> @@ -26,7 +27,7 @@ V_FUNCTION_BEGIN(__kernel_gettimeofday) mr r11,r3 /* r11 holds tv */ mr r10,r4 /* r10 holds tz */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + get_datapage r3, r0 cmpldi r11,0 /* check if tv is NULL */ beq 2f lis r7,1000000@ha /* load up USEC_PER_SEC */ @@ -71,7 +72,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime) mflr r12 /* r12 saves lr */ .cfi_register lr,r12 mr r11,r4 /* r11 saves tp */ - bl V_LOCAL_FUNC(__get_datapage) /* get data page */ + get_datapage r3, r0 lis r7,NSEC_PER_SEC@h /* want nanoseconds */ ori r7,r7,NSEC_PER_SEC@l beq cr5,70f @@ -188,7 +189,7 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) mflr r12 .cfi_register lr,r12 - bl V_LOCAL_FUNC(__get_datapage) + get_datapage r3, r0 lwz r5, CLOCK_HRTIMER_RES(r3) mtlr r12 li r3,0 @@ -221,7 +222,7 @@ V_FUNCTION_BEGIN(__kernel_time) .cfi_register lr,r12 mr r11,r3 /* r11 holds t */ - bl V_LOCAL_FUNC(__get_datapage) + get_datapage r3, r0 ld r4,STAMP_XTIME_SEC(r3) diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index a8cc0409d7d2..bbf68cd01088 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -6,6 +6,7 @@ * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. * Copyright (C) 2004 Alan Modra (amodra@au.ibm.com)), IBM Corp. */ +#include <asm/cache.h> /* IFETCH_ALIGN_BYTES */ #include <asm/processor.h> #include <asm/ppc_asm.h> #include <asm/unistd.h> @@ -14,21 +15,17 @@ .text -/* The nop here is a hack. The dwarf2 unwind routines subtract 1 from - the return address to get an address in the middle of the presumed - call instruction. Since we don't have a call here, we artificially - extend the range covered by the unwind info by padding before the - real start. */ - nop .balign 8 + .balign IFETCH_ALIGN_BYTES V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) -.Lsigrt_start = . - 4 +.Lsigrt_start: + bctrl /* call the handler */ addi r1, r1, __SIGNAL_FRAMESIZE li r0,__NR_rt_sigreturn sc .Lsigrt_end: V_FUNCTION_END(__kernel_sigtramp_rt64) -/* The ".balign 8" above and the following zeros mimic the old stack +/* The .balign 8 above and the following zeros mimic the old stack trampoline layout. The last magic value is the ucontext pointer, chosen in such a way that older libgcc unwind code returns a zero for a sigcontext pointer. */ diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 256fb9720298..4e3a8d4ee614 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -30,7 +30,7 @@ SECTIONS . = ALIGN(16); .text : { *(.text .stub .text.* .gnu.linkonce.t.* __ftr_alt_*) - *(.sfpr .glink) + *(.sfpr) } :text PROVIDE(__etext = .); PROVIDE(_etext = .); @@ -111,6 +111,7 @@ SECTIONS *(.branch_lt) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) + *(.glink .iplt .plt .rela*) } } diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S index efc5b52f95d2..801dc28fdcca 100644 --- a/arch/powerpc/kernel/vector.S +++ b/arch/powerpc/kernel/vector.S @@ -76,9 +76,7 @@ _GLOBAL(load_up_altivec) oris r12,r12,MSR_VEC@h std r12,_MSR(r1) #endif - /* Don't care if r4 overflows, this is desired behaviour */ - lbz r4,THREAD_LOAD_VEC(r5) - addi r4,r4,1 + li r4,1 stb r4,THREAD_LOAD_VEC(r5) addi r6,r5,THREAD_VRSTATE li r4,1 diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile index 86380c69f5ce..4aff6846c772 100644 --- a/arch/powerpc/kexec/Makefile +++ b/arch/powerpc/kexec/Makefile @@ -7,7 +7,7 @@ obj-y += core.o crash.o core_$(BITS).o obj-$(CONFIG_PPC32) += relocate_32.o -obj-$(CONFIG_KEXEC_FILE) += file_load.o elf_$(BITS).o +obj-$(CONFIG_KEXEC_FILE) += file_load.o ranges.o file_load_$(BITS).o elf_$(BITS).o ifdef CONFIG_HAVE_IMA_KEXEC ifdef CONFIG_IMA diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index b4184092172a..8a449b2d8715 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -152,6 +152,8 @@ static void kexec_smp_down(void *arg) if (ppc_md.kexec_cpu_down) ppc_md.kexec_cpu_down(0, 1); + reset_sprs(); + kexec_smp_wait(); /* NOTREACHED */ } diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c index 3072fd6dbe94..d0e459bb2f05 100644 --- a/arch/powerpc/kexec/elf_64.c +++ b/arch/powerpc/kexec/elf_64.c @@ -35,6 +35,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, void *fdt; const void *slave_code; struct elfhdr ehdr; + char *modified_cmdline = NULL; struct kexec_elf_info elf_info; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ppc64_rma_size }; @@ -46,6 +47,14 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, if (ret) goto out; + if (image->type == KEXEC_TYPE_CRASH) { + /* min & max buffer values for kdump case */ + kbuf.buf_min = pbuf.buf_min = crashk_res.start; + kbuf.buf_max = pbuf.buf_max = + ((crashk_res.end < ppc64_rma_size) ? + crashk_res.end : (ppc64_rma_size - 1)); + } + ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr); if (ret) goto out; @@ -60,6 +69,25 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); + /* Load additional segments needed for panic kernel */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = load_crashdump_segments_ppc64(image, &kbuf); + if (ret) { + pr_err("Failed to load kdump kernel segments\n"); + goto out; + } + + /* Setup cmdline for kdump kernel case */ + modified_cmdline = setup_kdump_cmdline(image, cmdline, + cmdline_len); + if (!modified_cmdline) { + pr_err("Setting up cmdline for kdump kernel failed\n"); + ret = -EINVAL; + goto out; + } + cmdline = modified_cmdline; + } + if (initrd != NULL) { kbuf.buffer = initrd; kbuf.bufsz = kbuf.memsz = initrd_len; @@ -88,7 +116,8 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, goto out; } - ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline); + ret = setup_new_fdt_ppc64(image, fdt, initrd_load_addr, + initrd_len, cmdline); if (ret) goto out; @@ -107,12 +136,13 @@ static void *elf64_load(struct kimage *image, char *kernel_buf, pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr); slave_code = elf_info.buffer + elf_info.proghdrs[0].p_offset; - ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr, - fdt_load_addr); + ret = setup_purgatory_ppc64(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr); if (ret) pr_err("Error setting up the purgatory.\n"); out: + kfree(modified_cmdline); kexec_free_elf_info(&elf_info); /* Make kimage_file_post_load_cleanup free the fdt buffer for us. */ diff --git a/arch/powerpc/kexec/file_load.c b/arch/powerpc/kexec/file_load.c index 143c91724617..9a232bc36c8f 100644 --- a/arch/powerpc/kexec/file_load.c +++ b/arch/powerpc/kexec/file_load.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ppc64 code to implement the kexec_file_load syscall + * powerpc code to implement the kexec_file_load syscall * * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) * Copyright (C) 2004 IBM Corp. @@ -18,23 +18,45 @@ #include <linux/kexec.h> #include <linux/of_fdt.h> #include <linux/libfdt.h> +#include <asm/setup.h> #include <asm/ima.h> -#define SLAVE_CODE_SIZE 256 +#define SLAVE_CODE_SIZE 256 /* First 0x100 bytes */ -const struct kexec_file_ops * const kexec_file_loaders[] = { - &kexec_elf64_ops, - NULL -}; - -int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, - unsigned long buf_len) +/** + * setup_kdump_cmdline - Prepend "elfcorehdr=<addr> " to command line + * of kdump kernel for exporting the core. + * @image: Kexec image + * @cmdline: Command line parameters to update. + * @cmdline_len: Length of the cmdline parameters. + * + * kdump segment must be setup before calling this function. + * + * Returns new cmdline buffer for kdump kernel on success, NULL otherwise. + */ +char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len) { - /* We don't support crash kernels yet. */ - if (image->type == KEXEC_TYPE_CRASH) - return -EOPNOTSUPP; + int elfcorehdr_strlen; + char *cmdline_ptr; + + cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!cmdline_ptr) + return NULL; + + elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", + image->arch.elfcorehdr_addr); + + if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { + pr_err("Appending elfcorehdr=<addr> exceeds cmdline size\n"); + kfree(cmdline_ptr); + return NULL; + } - return kexec_image_probe_default(image, buf, buf_len); + memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); + // Ensure it's nul terminated + cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; + return cmdline_ptr; } /** @@ -236,6 +258,20 @@ int setup_new_fdt(const struct kimage *image, void *fdt, } } + if (image->type == KEXEC_TYPE_CRASH) { + /* + * Avoid elfcorehdr from being stomped on in kdump kernel by + * setting up memory reserve map. + */ + ret = fdt_add_mem_rsv(fdt, image->arch.elfcorehdr_addr, + image->arch.elf_headers_sz); + if (ret) { + pr_err("Error reserving elfcorehdr memory: %s\n", + fdt_strerror(ret)); + goto err; + } + } + ret = setup_ima_buffer(image, fdt, chosen_node); if (ret) { pr_err("Error setting up the new device tree.\n"); diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c new file mode 100644 index 000000000000..53bb71e3a2e1 --- /dev/null +++ b/arch/powerpc/kexec/file_load_64.c @@ -0,0 +1,1119 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ppc64 code to implement the kexec_file_load syscall + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2004,2005 Milton D Miller II, IBM Corporation + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2020 IBM Corporation + * + * Based on kexec-tools' kexec-ppc64.c, kexec-elf-rel-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Hari Bathini, IBM Corporation. + */ + +#include <linux/kexec.h> +#include <linux/of_fdt.h> +#include <linux/libfdt.h> +#include <linux/of_device.h> +#include <linux/memblock.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <asm/drmem.h> +#include <asm/kexec_ranges.h> +#include <asm/crashdump-ppc64.h> + +struct umem_info { + u64 *buf; /* data buffer for usable-memory property */ + u32 size; /* size allocated for the data buffer */ + u32 max_entries; /* maximum no. of entries */ + u32 idx; /* index of current entry */ + + /* usable memory ranges to look up */ + unsigned int nr_ranges; + const struct crash_mem_range *ranges; +}; + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_elf64_ops, + NULL +}; + +/** + * get_exclude_memory_ranges - Get exclude memory ranges. This list includes + * regions like opal/rtas, tce-table, initrd, + * kernel, htab which should be avoided while + * setting up kexec load segments. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_exclude_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_initrd_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_htab_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_kernel_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); + if (ret) + goto out; + + /* exclude memory ranges should be sorted for easy lookup */ + sort_memory_ranges(*mem_ranges, true); +out: + if (ret) + pr_err("Failed to setup exclude memory ranges\n"); + return ret; +} + +/** + * get_usable_memory_ranges - Get usable memory ranges. This list includes + * regions like crashkernel, opal/rtas & tce-table, + * that kdump kernel could use. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_usable_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + /* + * Early boot failure observed on guests when low memory (first memory + * block?) is not added to usable memory. So, add [0, crashk_res.end] + * instead of [crashk_res.start, crashk_res.end] to workaround it. + * Also, crashed kernel's memory must be added to reserve map to + * avoid kdump kernel from using it. + */ + ret = add_mem_range(mem_ranges, 0, crashk_res.end + 1); + if (ret) + goto out; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup usable memory ranges\n"); + return ret; +} + +/** + * get_crash_memory_ranges - Get crash memory ranges. This list includes + * first/crashing kernel's memory regions that + * would be exported via an elfcore. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_crash_memory_ranges(struct crash_mem **mem_ranges) +{ + struct memblock_region *reg; + struct crash_mem *tmem; + int ret; + + for_each_memblock(memory, reg) { + u64 base, size; + + base = (u64)reg->base; + size = (u64)reg->size; + + /* Skip backup memory region, which needs a separate entry */ + if (base == BACKUP_SRC_START) { + if (size > BACKUP_SRC_SIZE) { + base = BACKUP_SRC_END + 1; + size -= BACKUP_SRC_SIZE; + } else + continue; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + goto out; + + /* Try merging adjacent ranges before reallocation attempt */ + if ((*mem_ranges)->nr_ranges == (*mem_ranges)->max_nr_ranges) + sort_memory_ranges(*mem_ranges, true); + } + + /* Reallocate memory ranges if there is no space to split ranges */ + tmem = *mem_ranges; + if (tmem && (tmem->nr_ranges == tmem->max_nr_ranges)) { + tmem = realloc_mem_ranges(mem_ranges); + if (!tmem) + goto out; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(tmem, crashk_res.start, crashk_res.end); + if (ret) + goto out; + + /* + * FIXME: For now, stay in parity with kexec-tools but if RTAS/OPAL + * regions are exported to save their context at the time of + * crash, they should actually be backed up just like the + * first 64K bytes of memory. + */ + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_opal_mem_range(mem_ranges); + if (ret) + goto out; + + /* create a separate program header for the backup region */ + ret = add_mem_range(mem_ranges, BACKUP_SRC_START, BACKUP_SRC_SIZE); + if (ret) + goto out; + + sort_memory_ranges(*mem_ranges, false); +out: + if (ret) + pr_err("Failed to setup crash memory ranges\n"); + return ret; +} + +/** + * get_reserved_memory_ranges - Get reserve memory ranges. This list includes + * memory regions that should be added to the + * memory reserve map to ensure the region is + * protected from any mischief. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +static int get_reserved_memory_ranges(struct crash_mem **mem_ranges) +{ + int ret; + + ret = add_rtas_mem_range(mem_ranges); + if (ret) + goto out; + + ret = add_tce_mem_ranges(mem_ranges); + if (ret) + goto out; + + ret = add_reserved_mem_ranges(mem_ranges); +out: + if (ret) + pr_err("Failed to setup reserved memory ranges\n"); + return ret; +} + +/** + * __locate_mem_hole_top_down - Looks top down for a large enough memory hole + * in the memory regions between buf_min & buf_max + * for the buffer. If found, sets kbuf->mem. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * + * Returns 0 on success, negative errno on error. + */ +static int __locate_mem_hole_top_down(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max) +{ + int ret = -EADDRNOTAVAIL; + phys_addr_t start, end; + u64 i; + + for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + /* + * memblock uses [start, end) convention while it is + * [start, end] here. Fix the off-by-one to have the + * same convention. + */ + end -= 1; + + if (start > buf_max) + continue; + + /* Memory hole not found */ + if (end < buf_min) + break; + + /* Adjust memory region based on the given range */ + if (start < buf_min) + start = buf_min; + if (end > buf_max) + end = buf_max; + + start = ALIGN(start, kbuf->buf_align); + if (start < end && (end - start + 1) >= kbuf->memsz) { + /* Suitable memory range found. Set kbuf->mem */ + kbuf->mem = ALIGN_DOWN(end - kbuf->memsz + 1, + kbuf->buf_align); + ret = 0; + break; + } + } + + return ret; +} + +/** + * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a + * suitable buffer with top down approach. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * @emem: Exclude memory ranges. + * + * Returns 0 on success, negative errno on error. + */ +static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max, + const struct crash_mem *emem) +{ + int i, ret = 0, err = -EADDRNOTAVAIL; + u64 start, end, tmin, tmax; + + tmax = buf_max; + for (i = (emem->nr_ranges - 1); i >= 0; i--) { + start = emem->ranges[i].start; + end = emem->ranges[i].end; + + if (start > tmax) + continue; + + if (end < tmax) { + tmin = (end < buf_min ? buf_min : end + 1); + ret = __locate_mem_hole_top_down(kbuf, tmin, tmax); + if (!ret) + return 0; + } + + tmax = start - 1; + + if (tmax < buf_min) { + ret = err; + break; + } + ret = 0; + } + + if (!ret) { + tmin = buf_min; + ret = __locate_mem_hole_top_down(kbuf, tmin, tmax); + } + return ret; +} + +/** + * __locate_mem_hole_bottom_up - Looks bottom up for a large enough memory hole + * in the memory regions between buf_min & buf_max + * for the buffer. If found, sets kbuf->mem. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * + * Returns 0 on success, negative errno on error. + */ +static int __locate_mem_hole_bottom_up(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max) +{ + int ret = -EADDRNOTAVAIL; + phys_addr_t start, end; + u64 i; + + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + /* + * memblock uses [start, end) convention while it is + * [start, end] here. Fix the off-by-one to have the + * same convention. + */ + end -= 1; + + if (end < buf_min) + continue; + + /* Memory hole not found */ + if (start > buf_max) + break; + + /* Adjust memory region based on the given range */ + if (start < buf_min) + start = buf_min; + if (end > buf_max) + end = buf_max; + + start = ALIGN(start, kbuf->buf_align); + if (start < end && (end - start + 1) >= kbuf->memsz) { + /* Suitable memory range found. Set kbuf->mem */ + kbuf->mem = start; + ret = 0; + break; + } + } + + return ret; +} + +/** + * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a + * suitable buffer with bottom up approach. + * @kbuf: Buffer contents and memory parameters. + * @buf_min: Minimum address for the buffer. + * @buf_max: Maximum address for the buffer. + * @emem: Exclude memory ranges. + * + * Returns 0 on success, negative errno on error. + */ +static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf, + u64 buf_min, u64 buf_max, + const struct crash_mem *emem) +{ + int i, ret = 0, err = -EADDRNOTAVAIL; + u64 start, end, tmin, tmax; + + tmin = buf_min; + for (i = 0; i < emem->nr_ranges; i++) { + start = emem->ranges[i].start; + end = emem->ranges[i].end; + + if (end < tmin) + continue; + + if (start > tmin) { + tmax = (start > buf_max ? buf_max : start - 1); + ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax); + if (!ret) + return 0; + } + + tmin = end + 1; + + if (tmin > buf_max) { + ret = err; + break; + } + ret = 0; + } + + if (!ret) { + tmax = buf_max; + ret = __locate_mem_hole_bottom_up(kbuf, tmin, tmax); + } + return ret; +} + +/** + * check_realloc_usable_mem - Reallocate buffer if it can't accommodate entries + * @um_info: Usable memory buffer and ranges info. + * @cnt: No. of entries to accommodate. + * + * Frees up the old buffer if memory reallocation fails. + * + * Returns buffer on success, NULL on error. + */ +static u64 *check_realloc_usable_mem(struct umem_info *um_info, int cnt) +{ + u32 new_size; + u64 *tbuf; + + if ((um_info->idx + cnt) <= um_info->max_entries) + return um_info->buf; + + new_size = um_info->size + MEM_RANGE_CHUNK_SZ; + tbuf = krealloc(um_info->buf, new_size, GFP_KERNEL); + if (tbuf) { + um_info->buf = tbuf; + um_info->size = new_size; + um_info->max_entries = (um_info->size / sizeof(u64)); + } + + return tbuf; +} + +/** + * add_usable_mem - Add the usable memory ranges within the given memory range + * to the buffer + * @um_info: Usable memory buffer and ranges info. + * @base: Base address of memory range to look for. + * @end: End address of memory range to look for. + * + * Returns 0 on success, negative errno on error. + */ +static int add_usable_mem(struct umem_info *um_info, u64 base, u64 end) +{ + u64 loc_base, loc_end; + bool add; + int i; + + for (i = 0; i < um_info->nr_ranges; i++) { + add = false; + loc_base = um_info->ranges[i].start; + loc_end = um_info->ranges[i].end; + if (loc_base >= base && loc_end <= end) + add = true; + else if (base < loc_end && end > loc_base) { + if (loc_base < base) + loc_base = base; + if (loc_end > end) + loc_end = end; + add = true; + } + + if (add) { + if (!check_realloc_usable_mem(um_info, 2)) + return -ENOMEM; + + um_info->buf[um_info->idx++] = cpu_to_be64(loc_base); + um_info->buf[um_info->idx++] = + cpu_to_be64(loc_end - loc_base + 1); + } + } + + return 0; +} + +/** + * kdump_setup_usable_lmb - This is a callback function that gets called by + * walk_drmem_lmbs for every LMB to set its + * usable memory ranges. + * @lmb: LMB info. + * @usm: linux,drconf-usable-memory property value. + * @data: Pointer to usable memory buffer and ranges info. + * + * Returns 0 on success, negative errno on error. + */ +static int kdump_setup_usable_lmb(struct drmem_lmb *lmb, const __be32 **usm, + void *data) +{ + struct umem_info *um_info; + int tmp_idx, ret; + u64 base, end; + + /* + * kdump load isn't supported on kernels already booted with + * linux,drconf-usable-memory property. + */ + if (*usm) { + pr_err("linux,drconf-usable-memory property already exists!"); + return -EINVAL; + } + + um_info = data; + tmp_idx = um_info->idx; + if (!check_realloc_usable_mem(um_info, 1)) + return -ENOMEM; + + um_info->idx++; + base = lmb->base_addr; + end = base + drmem_lmb_size() - 1; + ret = add_usable_mem(um_info, base, end); + if (!ret) { + /* + * Update the no. of ranges added. Two entries (base & size) + * for every range added. + */ + um_info->buf[tmp_idx] = + cpu_to_be64((um_info->idx - tmp_idx - 1) / 2); + } + + return ret; +} + +#define NODE_PATH_LEN 256 +/** + * add_usable_mem_property - Add usable memory property for the given + * memory node. + * @fdt: Flattened device tree for the kdump kernel. + * @dn: Memory node. + * @um_info: Usable memory buffer and ranges info. + * + * Returns 0 on success, negative errno on error. + */ +static int add_usable_mem_property(void *fdt, struct device_node *dn, + struct umem_info *um_info) +{ + int n_mem_addr_cells, n_mem_size_cells, node; + char path[NODE_PATH_LEN]; + int i, len, ranges, ret; + const __be32 *prop; + u64 base, end; + + of_node_get(dn); + + if (snprintf(path, NODE_PATH_LEN, "%pOF", dn) > (NODE_PATH_LEN - 1)) { + pr_err("Buffer (%d) too small for memory node: %pOF\n", + NODE_PATH_LEN, dn); + return -EOVERFLOW; + } + pr_debug("Memory node path: %s\n", path); + + /* Now that we know the path, find its offset in kdump kernel's fdt */ + node = fdt_path_offset(fdt, path); + if (node < 0) { + pr_err("Malformed device tree: error reading %s\n", path); + ret = -EINVAL; + goto out; + } + + /* Get the address & size cells */ + n_mem_addr_cells = of_n_addr_cells(dn); + n_mem_size_cells = of_n_size_cells(dn); + pr_debug("address cells: %d, size cells: %d\n", n_mem_addr_cells, + n_mem_size_cells); + + um_info->idx = 0; + if (!check_realloc_usable_mem(um_info, 2)) { + ret = -ENOMEM; + goto out; + } + + prop = of_get_property(dn, "reg", &len); + if (!prop || len <= 0) { + ret = 0; + goto out; + } + + /* + * "reg" property represents sequence of (addr,size) tuples + * each representing a memory range. + */ + ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells); + + for (i = 0; i < ranges; i++) { + base = of_read_number(prop, n_mem_addr_cells); + prop += n_mem_addr_cells; + end = base + of_read_number(prop, n_mem_size_cells) - 1; + prop += n_mem_size_cells; + + ret = add_usable_mem(um_info, base, end); + if (ret) + goto out; + } + + /* + * No kdump kernel usable memory found in this memory node. + * Write (0,0) tuple in linux,usable-memory property for + * this region to be ignored. + */ + if (um_info->idx == 0) { + um_info->buf[0] = 0; + um_info->buf[1] = 0; + um_info->idx = 2; + } + + ret = fdt_setprop(fdt, node, "linux,usable-memory", um_info->buf, + (um_info->idx * sizeof(u64))); + +out: + of_node_put(dn); + return ret; +} + + +/** + * update_usable_mem_fdt - Updates kdump kernel's fdt with linux,usable-memory + * and linux,drconf-usable-memory DT properties as + * appropriate to restrict its memory usage. + * @fdt: Flattened device tree for the kdump kernel. + * @usable_mem: Usable memory ranges for kdump kernel. + * + * Returns 0 on success, negative errno on error. + */ +static int update_usable_mem_fdt(void *fdt, struct crash_mem *usable_mem) +{ + struct umem_info um_info; + struct device_node *dn; + int node, ret = 0; + + if (!usable_mem) { + pr_err("Usable memory ranges for kdump kernel not found\n"); + return -ENOENT; + } + + node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory"); + if (node == -FDT_ERR_NOTFOUND) + pr_debug("No dynamic reconfiguration memory found\n"); + else if (node < 0) { + pr_err("Malformed device tree: error reading /ibm,dynamic-reconfiguration-memory.\n"); + return -EINVAL; + } + + um_info.buf = NULL; + um_info.size = 0; + um_info.max_entries = 0; + um_info.idx = 0; + /* Memory ranges to look up */ + um_info.ranges = &(usable_mem->ranges[0]); + um_info.nr_ranges = usable_mem->nr_ranges; + + dn = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); + if (dn) { + ret = walk_drmem_lmbs(dn, &um_info, kdump_setup_usable_lmb); + of_node_put(dn); + + if (ret) { + pr_err("Could not setup linux,drconf-usable-memory property for kdump\n"); + goto out; + } + + ret = fdt_setprop(fdt, node, "linux,drconf-usable-memory", + um_info.buf, (um_info.idx * sizeof(u64))); + if (ret) { + pr_err("Failed to update fdt with linux,drconf-usable-memory property"); + goto out; + } + } + + /* + * Walk through each memory node and set linux,usable-memory property + * for the corresponding node in kdump kernel's fdt. + */ + for_each_node_by_type(dn, "memory") { + ret = add_usable_mem_property(fdt, dn, &um_info); + if (ret) { + pr_err("Failed to set linux,usable-memory property for %s node", + dn->full_name); + goto out; + } + } + +out: + kfree(um_info.buf); + return ret; +} + +/** + * load_backup_segment - Locate a memory hole to place the backup region. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +static int load_backup_segment(struct kimage *image, struct kexec_buf *kbuf) +{ + void *buf; + int ret; + + /* + * Setup a source buffer for backup segment. + * + * A source buffer has no meaning for backup region as data will + * be copied from backup source, after crash, in the purgatory. + * But as load segment code doesn't recognize such segments, + * setup a dummy source buffer to keep it happy for now. + */ + buf = vzalloc(BACKUP_SRC_SIZE); + if (!buf) + return -ENOMEM; + + kbuf->buffer = buf; + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf->bufsz = kbuf->memsz = BACKUP_SRC_SIZE; + kbuf->top_down = false; + + ret = kexec_add_buffer(kbuf); + if (ret) { + vfree(buf); + return ret; + } + + image->arch.backup_buf = buf; + image->arch.backup_start = kbuf->mem; + return 0; +} + +/** + * update_backup_region_phdr - Update backup region's offset for the core to + * export the region appropriately. + * @image: Kexec image. + * @ehdr: ELF core header. + * + * Assumes an exclusive program header is setup for the backup region + * in the ELF headers + * + * Returns nothing. + */ +static void update_backup_region_phdr(struct kimage *image, Elf64_Ehdr *ehdr) +{ + Elf64_Phdr *phdr; + unsigned int i; + + phdr = (Elf64_Phdr *)(ehdr + 1); + for (i = 0; i < ehdr->e_phnum; i++) { + if (phdr->p_paddr == BACKUP_SRC_START) { + phdr->p_offset = image->arch.backup_start; + pr_debug("Backup region offset updated to 0x%lx\n", + image->arch.backup_start); + return; + } + } +} + +/** + * load_elfcorehdr_segment - Setup crash memory ranges and initialize elfcorehdr + * segment needed to load kdump kernel. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +static int load_elfcorehdr_segment(struct kimage *image, struct kexec_buf *kbuf) +{ + struct crash_mem *cmem = NULL; + unsigned long headers_sz; + void *headers = NULL; + int ret; + + ret = get_crash_memory_ranges(&cmem); + if (ret) + goto out; + + /* Setup elfcorehdr segment */ + ret = crash_prepare_elf64_headers(cmem, false, &headers, &headers_sz); + if (ret) { + pr_err("Failed to prepare elf headers for the core\n"); + goto out; + } + + /* Fix the offset for backup region in the ELF header */ + update_backup_region_phdr(image, headers); + + kbuf->buffer = headers; + kbuf->mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf->bufsz = kbuf->memsz = headers_sz; + kbuf->top_down = false; + + ret = kexec_add_buffer(kbuf); + if (ret) { + vfree(headers); + goto out; + } + + image->arch.elfcorehdr_addr = kbuf->mem; + image->arch.elf_headers_sz = headers_sz; + image->arch.elf_headers = headers; +out: + kfree(cmem); + return ret; +} + +/** + * load_crashdump_segments_ppc64 - Initialize the additional segements needed + * to load kdump kernel. + * @image: Kexec image. + * @kbuf: Buffer contents and memory parameters. + * + * Returns 0 on success, negative errno on error. + */ +int load_crashdump_segments_ppc64(struct kimage *image, + struct kexec_buf *kbuf) +{ + int ret; + + /* Load backup segment - first 64K bytes of the crashing kernel */ + ret = load_backup_segment(image, kbuf); + if (ret) { + pr_err("Failed to load backup segment\n"); + return ret; + } + pr_debug("Loaded the backup region at 0x%lx\n", kbuf->mem); + + /* Load elfcorehdr segment - to export crashing kernel's vmcore */ + ret = load_elfcorehdr_segment(image, kbuf); + if (ret) { + pr_err("Failed to load elfcorehdr segment\n"); + return ret; + } + pr_debug("Loaded elf core header at 0x%lx, bufsz=0x%lx memsz=0x%lx\n", + image->arch.elfcorehdr_addr, kbuf->bufsz, kbuf->memsz); + + return 0; +} + +/** + * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global + * variables and call setup_purgatory() to initialize + * common global variable. + * @image: kexec image. + * @slave_code: Slave code for the purgatory. + * @fdt: Flattened device tree for the next kernel. + * @kernel_load_addr: Address where the kernel is loaded. + * @fdt_load_addr: Address where the flattened device tree is loaded. + * + * Returns 0 on success, negative errno on error. + */ +int setup_purgatory_ppc64(struct kimage *image, const void *slave_code, + const void *fdt, unsigned long kernel_load_addr, + unsigned long fdt_load_addr) +{ + struct device_node *dn = NULL; + int ret; + + ret = setup_purgatory(image, slave_code, fdt, kernel_load_addr, + fdt_load_addr); + if (ret) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + u32 my_run_at_load = 1; + + /* + * Tell relocatable kernel to run at load address + * via the word meant for that at 0x5c. + */ + ret = kexec_purgatory_get_set_symbol(image, "run_at_load", + &my_run_at_load, + sizeof(my_run_at_load), + false); + if (ret) + goto out; + } + + /* Tell purgatory where to look for backup region */ + ret = kexec_purgatory_get_set_symbol(image, "backup_start", + &image->arch.backup_start, + sizeof(image->arch.backup_start), + false); + if (ret) + goto out; + + /* Setup OPAL base & entry values */ + dn = of_find_node_by_path("/ibm,opal"); + if (dn) { + u64 val; + + of_property_read_u64(dn, "opal-base-address", &val); + ret = kexec_purgatory_get_set_symbol(image, "opal_base", &val, + sizeof(val), false); + if (ret) + goto out; + + of_property_read_u64(dn, "opal-entry-address", &val); + ret = kexec_purgatory_get_set_symbol(image, "opal_entry", &val, + sizeof(val), false); + } +out: + if (ret) + pr_err("Failed to setup purgatory symbols"); + of_node_put(dn); + return ret; +} + +/** + * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel + * being loaded. + * @image: kexec image being loaded. + * @fdt: Flattened device tree for the next kernel. + * @initrd_load_addr: Address where the next initrd will be loaded. + * @initrd_len: Size of the next initrd, or 0 if there will be none. + * @cmdline: Command line for the next kernel, or NULL if there will + * be none. + * + * Returns 0 on success, negative errno on error. + */ +int setup_new_fdt_ppc64(const struct kimage *image, void *fdt, + unsigned long initrd_load_addr, + unsigned long initrd_len, const char *cmdline) +{ + struct crash_mem *umem = NULL, *rmem = NULL; + int i, nr_ranges, ret; + + ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline); + if (ret) + goto out; + + /* + * Restrict memory usage for kdump kernel by setting up + * usable memory ranges and memory reserve map. + */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = get_usable_memory_ranges(&umem); + if (ret) + goto out; + + ret = update_usable_mem_fdt(fdt, umem); + if (ret) { + pr_err("Error setting up usable-memory property for kdump kernel\n"); + goto out; + } + + /* + * Ensure we don't touch crashed kernel's memory except the + * first 64K of RAM, which will be backed up. + */ + ret = fdt_add_mem_rsv(fdt, BACKUP_SRC_END + 1, + crashk_res.start - BACKUP_SRC_SIZE); + if (ret) { + pr_err("Error reserving crash memory: %s\n", + fdt_strerror(ret)); + goto out; + } + + /* Ensure backup region is not used by kdump/capture kernel */ + ret = fdt_add_mem_rsv(fdt, image->arch.backup_start, + BACKUP_SRC_SIZE); + if (ret) { + pr_err("Error reserving memory for backup: %s\n", + fdt_strerror(ret)); + goto out; + } + } + + /* Update memory reserve map */ + ret = get_reserved_memory_ranges(&rmem); + if (ret) + goto out; + + nr_ranges = rmem ? rmem->nr_ranges : 0; + for (i = 0; i < nr_ranges; i++) { + u64 base, size; + + base = rmem->ranges[i].start; + size = rmem->ranges[i].end - base + 1; + ret = fdt_add_mem_rsv(fdt, base, size); + if (ret) { + pr_err("Error updating memory reserve map: %s\n", + fdt_strerror(ret)); + goto out; + } + } + +out: + kfree(rmem); + kfree(umem); + return ret; +} + +/** + * arch_kexec_locate_mem_hole - Skip special memory regions like rtas, opal, + * tce-table, reserved-ranges & such (exclude + * memory ranges) as they can't be used for kexec + * segment buffer. Sets kbuf->mem when a suitable + * memory hole is found. + * @kbuf: Buffer contents and memory parameters. + * + * Assumes minimum of PAGE_SIZE alignment for kbuf->memsz & kbuf->buf_align. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf) +{ + struct crash_mem **emem; + u64 buf_min, buf_max; + int ret; + + /* Look up the exclude ranges list while locating the memory hole */ + emem = &(kbuf->image->arch.exclude_ranges); + if (!(*emem) || ((*emem)->nr_ranges == 0)) { + pr_warn("No exclude range list. Using the default locate mem hole method\n"); + return kexec_locate_mem_hole(kbuf); + } + + buf_min = kbuf->buf_min; + buf_max = kbuf->buf_max; + /* Segments for kdump kernel should be within crashkernel region */ + if (kbuf->image->type == KEXEC_TYPE_CRASH) { + buf_min = (buf_min < crashk_res.start ? + crashk_res.start : buf_min); + buf_max = (buf_max > crashk_res.end ? + crashk_res.end : buf_max); + } + + if (buf_min > buf_max) { + pr_err("Invalid buffer min and/or max values\n"); + return -EINVAL; + } + + if (kbuf->top_down) + ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max, + *emem); + else + ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max, + *emem); + + /* Add the buffer allocated to the exclude list for the next lookup */ + if (!ret) { + add_mem_range(emem, kbuf->mem, kbuf->memsz); + sort_memory_ranges(*emem, true); + } else { + pr_err("Failed to locate memory buffer of size %lu\n", + kbuf->memsz); + } + return ret; +} + +/** + * arch_kexec_kernel_image_probe - Does additional handling needed to setup + * kexec segments. + * @image: kexec image being loaded. + * @buf: Buffer pointing to elf data. + * @buf_len: Length of the buffer. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len) +{ + int ret; + + /* Get exclude memory ranges needed for setting up kexec segments */ + ret = get_exclude_memory_ranges(&(image->arch.exclude_ranges)); + if (ret) { + pr_err("Failed to setup exclude memory ranges for buffer lookup\n"); + return ret; + } + + return kexec_image_probe_default(image, buf, buf_len); +} + +/** + * arch_kimage_file_post_load_cleanup - Frees up all the allocations done + * while loading the image. + * @image: kexec image being loaded. + * + * Returns 0 on success, negative errno on error. + */ +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + kfree(image->arch.exclude_ranges); + image->arch.exclude_ranges = NULL; + + vfree(image->arch.backup_buf); + image->arch.backup_buf = NULL; + + vfree(image->arch.elf_headers); + image->arch.elf_headers = NULL; + image->arch.elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} diff --git a/arch/powerpc/kexec/ranges.c b/arch/powerpc/kexec/ranges.c new file mode 100644 index 000000000000..6b81c852feab --- /dev/null +++ b/arch/powerpc/kexec/ranges.c @@ -0,0 +1,412 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * powerpc code to implement the kexec_file_load syscall + * + * Copyright (C) 2004 Adam Litke (agl@us.ibm.com) + * Copyright (C) 2004 IBM Corp. + * Copyright (C) 2004,2005 Milton D Miller II, IBM Corporation + * Copyright (C) 2005 R Sharada (sharada@in.ibm.com) + * Copyright (C) 2006 Mohan Kumar M (mohan@in.ibm.com) + * Copyright (C) 2020 IBM Corporation + * + * Based on kexec-tools' kexec-ppc64.c, fs2dt.c. + * Heavily modified for the kernel by + * Hari Bathini, IBM Corporation. + */ + +#define pr_fmt(fmt) "kexec ranges: " fmt + +#include <linux/sort.h> +#include <linux/kexec.h> +#include <linux/of_device.h> +#include <linux/slab.h> +#include <asm/sections.h> +#include <asm/kexec_ranges.h> + +/** + * get_max_nr_ranges - Get the max no. of ranges crash_mem structure + * could hold, given the size allocated for it. + * @size: Allocation size of crash_mem structure. + * + * Returns the maximum no. of ranges. + */ +static inline unsigned int get_max_nr_ranges(size_t size) +{ + return ((size - sizeof(struct crash_mem)) / + sizeof(struct crash_mem_range)); +} + +/** + * get_mem_rngs_size - Get the allocated size of mem_rngs based on + * max_nr_ranges and chunk size. + * @mem_rngs: Memory ranges. + * + * Returns the maximum size of @mem_rngs. + */ +static inline size_t get_mem_rngs_size(struct crash_mem *mem_rngs) +{ + size_t size; + + if (!mem_rngs) + return 0; + + size = (sizeof(struct crash_mem) + + (mem_rngs->max_nr_ranges * sizeof(struct crash_mem_range))); + + /* + * Memory is allocated in size multiple of MEM_RANGE_CHUNK_SZ. + * So, align to get the actual length. + */ + return ALIGN(size, MEM_RANGE_CHUNK_SZ); +} + +/** + * __add_mem_range - add a memory range to memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * @base: Base address of the range to add. + * @size: Size of the memory range to add. + * + * (Re)allocates memory, if needed. + * + * Returns 0 on success, negative errno on error. + */ +static int __add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) +{ + struct crash_mem *mem_rngs = *mem_ranges; + + if (!mem_rngs || (mem_rngs->nr_ranges == mem_rngs->max_nr_ranges)) { + mem_rngs = realloc_mem_ranges(mem_ranges); + if (!mem_rngs) + return -ENOMEM; + } + + mem_rngs->ranges[mem_rngs->nr_ranges].start = base; + mem_rngs->ranges[mem_rngs->nr_ranges].end = base + size - 1; + pr_debug("Added memory range [%#016llx - %#016llx] at index %d\n", + base, base + size - 1, mem_rngs->nr_ranges); + mem_rngs->nr_ranges++; + return 0; +} + +/** + * __merge_memory_ranges - Merges the given memory ranges list. + * @mem_rngs: Range list to merge. + * + * Assumes a sorted range list. + * + * Returns nothing. + */ +static void __merge_memory_ranges(struct crash_mem *mem_rngs) +{ + struct crash_mem_range *ranges; + int i, idx; + + if (!mem_rngs) + return; + + idx = 0; + ranges = &(mem_rngs->ranges[0]); + for (i = 1; i < mem_rngs->nr_ranges; i++) { + if (ranges[i].start <= (ranges[i-1].end + 1)) + ranges[idx].end = ranges[i].end; + else { + idx++; + if (i == idx) + continue; + + ranges[idx] = ranges[i]; + } + } + mem_rngs->nr_ranges = idx + 1; +} + +/* cmp_func_t callback to sort ranges with sort() */ +static int rngcmp(const void *_x, const void *_y) +{ + const struct crash_mem_range *x = _x, *y = _y; + + if (x->start > y->start) + return 1; + if (x->start < y->start) + return -1; + return 0; +} + +/** + * sort_memory_ranges - Sorts the given memory ranges list. + * @mem_rngs: Range list to sort. + * @merge: If true, merge the list after sorting. + * + * Returns nothing. + */ +void sort_memory_ranges(struct crash_mem *mem_rngs, bool merge) +{ + int i; + + if (!mem_rngs) + return; + + /* Sort the ranges in-place */ + sort(&(mem_rngs->ranges[0]), mem_rngs->nr_ranges, + sizeof(mem_rngs->ranges[0]), rngcmp, NULL); + + if (merge) + __merge_memory_ranges(mem_rngs); + + /* For debugging purpose */ + pr_debug("Memory ranges:\n"); + for (i = 0; i < mem_rngs->nr_ranges; i++) { + pr_debug("\t[%03d][%#016llx - %#016llx]\n", i, + mem_rngs->ranges[i].start, + mem_rngs->ranges[i].end); + } +} + +/** + * realloc_mem_ranges - reallocate mem_ranges with size incremented + * by MEM_RANGE_CHUNK_SZ. Frees up the old memory, + * if memory allocation fails. + * @mem_ranges: Memory ranges to reallocate. + * + * Returns pointer to reallocated memory on success, NULL otherwise. + */ +struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges) +{ + struct crash_mem *mem_rngs = *mem_ranges; + unsigned int nr_ranges; + size_t size; + + size = get_mem_rngs_size(mem_rngs); + nr_ranges = mem_rngs ? mem_rngs->nr_ranges : 0; + + size += MEM_RANGE_CHUNK_SZ; + mem_rngs = krealloc(*mem_ranges, size, GFP_KERNEL); + if (!mem_rngs) { + kfree(*mem_ranges); + *mem_ranges = NULL; + return NULL; + } + + mem_rngs->nr_ranges = nr_ranges; + mem_rngs->max_nr_ranges = get_max_nr_ranges(size); + *mem_ranges = mem_rngs; + + return mem_rngs; +} + +/** + * add_mem_range - Updates existing memory range, if there is an overlap. + * Else, adds a new memory range. + * @mem_ranges: Range list to add the memory range to. + * @base: Base address of the range to add. + * @size: Size of the memory range to add. + * + * (Re)allocates memory, if needed. + * + * Returns 0 on success, negative errno on error. + */ +int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size) +{ + struct crash_mem *mem_rngs = *mem_ranges; + u64 mstart, mend, end; + unsigned int i; + + if (!size) + return 0; + + end = base + size - 1; + + if (!mem_rngs || !(mem_rngs->nr_ranges)) + return __add_mem_range(mem_ranges, base, size); + + for (i = 0; i < mem_rngs->nr_ranges; i++) { + mstart = mem_rngs->ranges[i].start; + mend = mem_rngs->ranges[i].end; + if (base < mend && end > mstart) { + if (base < mstart) + mem_rngs->ranges[i].start = base; + if (end > mend) + mem_rngs->ranges[i].end = end; + return 0; + } + } + + return __add_mem_range(mem_ranges, base, size); +} + +/** + * add_tce_mem_ranges - Adds tce-table range to the given memory ranges list. + * @mem_ranges: Range list to add the memory range(s) to. + * + * Returns 0 on success, negative errno on error. + */ +int add_tce_mem_ranges(struct crash_mem **mem_ranges) +{ + struct device_node *dn = NULL; + int ret = 0; + + for_each_node_by_type(dn, "pci") { + u64 base; + u32 size; + + ret = of_property_read_u64(dn, "linux,tce-base", &base); + ret |= of_property_read_u32(dn, "linux,tce-size", &size); + if (ret) { + /* + * It is ok to have pci nodes without tce. So, ignore + * property does not exist error. + */ + if (ret == -EINVAL) { + ret = 0; + continue; + } + break; + } + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + break; + } + + of_node_put(dn); + return ret; +} + +/** + * add_initrd_mem_range - Adds initrd range to the given memory ranges list, + * if the initrd was retained. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_initrd_mem_range(struct crash_mem **mem_ranges) +{ + u64 base, end; + int ret; + + /* This range means something, only if initrd was retained */ + if (!strstr(saved_command_line, "retain_initrd")) + return 0; + + ret = of_property_read_u64(of_chosen, "linux,initrd-start", &base); + ret |= of_property_read_u64(of_chosen, "linux,initrd-end", &end); + if (!ret) + ret = add_mem_range(mem_ranges, base, end - base + 1); + + return ret; +} + +#ifdef CONFIG_PPC_BOOK3S_64 +/** + * add_htab_mem_range - Adds htab range to the given memory ranges list, + * if it exists + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_htab_mem_range(struct crash_mem **mem_ranges) +{ + if (!htab_address) + return 0; + + return add_mem_range(mem_ranges, __pa(htab_address), htab_size_bytes); +} +#endif + +/** + * add_kernel_mem_range - Adds kernel text region to the given + * memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_kernel_mem_range(struct crash_mem **mem_ranges) +{ + return add_mem_range(mem_ranges, 0, __pa(_end)); +} + +/** + * add_rtas_mem_range - Adds RTAS region to the given memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_rtas_mem_range(struct crash_mem **mem_ranges) +{ + struct device_node *dn; + u32 base, size; + int ret = 0; + + dn = of_find_node_by_path("/rtas"); + if (!dn) + return 0; + + ret = of_property_read_u32(dn, "linux,rtas-base", &base); + ret |= of_property_read_u32(dn, "rtas-size", &size); + if (!ret) + ret = add_mem_range(mem_ranges, base, size); + + of_node_put(dn); + return ret; +} + +/** + * add_opal_mem_range - Adds OPAL region to the given memory ranges list. + * @mem_ranges: Range list to add the memory range to. + * + * Returns 0 on success, negative errno on error. + */ +int add_opal_mem_range(struct crash_mem **mem_ranges) +{ + struct device_node *dn; + u64 base, size; + int ret; + + dn = of_find_node_by_path("/ibm,opal"); + if (!dn) + return 0; + + ret = of_property_read_u64(dn, "opal-base-address", &base); + ret |= of_property_read_u64(dn, "opal-runtime-size", &size); + if (!ret) + ret = add_mem_range(mem_ranges, base, size); + + of_node_put(dn); + return ret; +} + +/** + * add_reserved_mem_ranges - Adds "/reserved-ranges" regions exported by f/w + * to the given memory ranges list. + * @mem_ranges: Range list to add the memory ranges to. + * + * Returns 0 on success, negative errno on error. + */ +int add_reserved_mem_ranges(struct crash_mem **mem_ranges) +{ + int n_mem_addr_cells, n_mem_size_cells, i, len, cells, ret = 0; + const __be32 *prop; + + prop = of_get_property(of_root, "reserved-ranges", &len); + if (!prop) + return 0; + + n_mem_addr_cells = of_n_addr_cells(of_root); + n_mem_size_cells = of_n_size_cells(of_root); + cells = n_mem_addr_cells + n_mem_size_cells; + + /* Each reserved range is an (address,size) pair */ + for (i = 0; i < (len / (sizeof(u32) * cells)); i++) { + u64 base, size; + + base = of_read_number(prop + (i * cells), n_mem_addr_cells); + size = of_read_number(prop + (i * cells) + n_mem_addr_cells, + n_mem_size_cells); + + ret = add_mem_range(mem_ranges, base, size); + if (ret) + break; + } + + return ret; +} diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 7c5a1812a1c3..38ea396a23d6 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -260,11 +260,15 @@ int kvmppc_mmu_hv_init(void) if (!mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE)) return -EINVAL; - /* POWER7 has 10-bit LPIDs (12-bit in POWER8) */ host_lpid = 0; if (cpu_has_feature(CPU_FTR_HVMODE)) host_lpid = mfspr(SPRN_LPID); - rsvd_lpid = LPID_RSVD; + + /* POWER8 and above have 12-bit LPIDs (10-bit in POWER7) */ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + rsvd_lpid = LPID_RSVD; + else + rsvd_lpid = LPID_RSVD_POWER7; kvmppc_init_lpid(rsvd_lpid + 1); diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 777aa5625d5f..22a677b18695 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -161,7 +161,9 @@ int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr, return -EINVAL; /* Read the entry from guest memory */ addr = base + (index * sizeof(rpte)); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, addr, &rpte, sizeof(rpte)); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); if (ret) { if (pte_ret_p) *pte_ret_p = addr; @@ -237,7 +239,9 @@ int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr, /* Read the table to find the root of the radix tree */ ptbl = (table & PRTB_MASK) + (table_index * sizeof(entry)); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, ptbl, &entry, sizeof(entry)); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); if (ret) return ret; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index ebb04f331ad3..4ba06a2a306c 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -343,13 +343,18 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) vcpu->arch.pvr = pvr; } +/* Dummy value used in computing PCR value below */ +#define PCR_ARCH_31 (PCR_ARCH_300 << 1) + static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { unsigned long host_pcr_bit = 0, guest_pcr_bit = 0; struct kvmppc_vcore *vc = vcpu->arch.vcore; /* We can (emulate) our own architecture version and anything older */ - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_31)) + host_pcr_bit = PCR_ARCH_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) host_pcr_bit = PCR_ARCH_300; else if (cpu_has_feature(CPU_FTR_ARCH_207S)) host_pcr_bit = PCR_ARCH_207; @@ -375,6 +380,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; break; + case PVR_ARCH_31: + guest_pcr_bit = PCR_ARCH_31; + break; default: return -EINVAL; } @@ -765,7 +773,7 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags, return H_P3; vcpu->arch.ciabr = value1; return H_SUCCESS; - case H_SET_MODE_RESOURCE_SET_DAWR: + case H_SET_MODE_RESOURCE_SET_DAWR0: if (!kvmppc_power8_compatible(vcpu)) return H_P2; if (!ppc_breakpoint_available()) @@ -1680,10 +1688,22 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_UAMOR: *val = get_reg_val(id, vcpu->arch.uamor); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; *val = get_reg_val(id, vcpu->arch.mmcr[i]); break; + case KVM_REG_PPC_MMCR2: + *val = get_reg_val(id, vcpu->arch.mmcr[2]); + break; + case KVM_REG_PPC_MMCRA: + *val = get_reg_val(id, vcpu->arch.mmcra); + break; + case KVM_REG_PPC_MMCRS: + *val = get_reg_val(id, vcpu->arch.mmcrs); + break; + case KVM_REG_PPC_MMCR3: + *val = get_reg_val(id, vcpu->arch.mmcr[3]); + break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; *val = get_reg_val(id, vcpu->arch.pmc[i]); @@ -1699,7 +1719,13 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, *val = get_reg_val(id, vcpu->arch.sdar); break; case KVM_REG_PPC_SIER: - *val = get_reg_val(id, vcpu->arch.sier); + *val = get_reg_val(id, vcpu->arch.sier[0]); + break; + case KVM_REG_PPC_SIER2: + *val = get_reg_val(id, vcpu->arch.sier[1]); + break; + case KVM_REG_PPC_SIER3: + *val = get_reg_val(id, vcpu->arch.sier[2]); break; case KVM_REG_PPC_IAMR: *val = get_reg_val(id, vcpu->arch.iamr); @@ -1901,10 +1927,22 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, case KVM_REG_PPC_UAMOR: vcpu->arch.uamor = set_reg_val(id, *val); break; - case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS: + case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCR1: i = id - KVM_REG_PPC_MMCR0; vcpu->arch.mmcr[i] = set_reg_val(id, *val); break; + case KVM_REG_PPC_MMCR2: + vcpu->arch.mmcr[2] = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MMCRA: + vcpu->arch.mmcra = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MMCRS: + vcpu->arch.mmcrs = set_reg_val(id, *val); + break; + case KVM_REG_PPC_MMCR3: + *val = get_reg_val(id, vcpu->arch.mmcr[3]); + break; case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8: i = id - KVM_REG_PPC_PMC1; vcpu->arch.pmc[i] = set_reg_val(id, *val); @@ -1920,7 +1958,13 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id, vcpu->arch.sdar = set_reg_val(id, *val); break; case KVM_REG_PPC_SIER: - vcpu->arch.sier = set_reg_val(id, *val); + vcpu->arch.sier[0] = set_reg_val(id, *val); + break; + case KVM_REG_PPC_SIER2: + vcpu->arch.sier[1] = set_reg_val(id, *val); + break; + case KVM_REG_PPC_SIER3: + vcpu->arch.sier[2] = set_reg_val(id, *val); break; case KVM_REG_PPC_IAMR: vcpu->arch.iamr = set_reg_val(id, *val); @@ -2319,7 +2363,7 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) * to trap and then we emulate them. */ vcpu->arch.hfscr = HFSCR_TAR | HFSCR_EBB | HFSCR_PM | HFSCR_BHRB | - HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP; + HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX; if (cpu_has_feature(CPU_FTR_HVMODE)) { vcpu->arch.hfscr &= mfspr(SPRN_HFSCR); if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST)) @@ -4516,16 +4560,14 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, switch (change) { case KVM_MR_CREATE: - if (kvmppc_uvmem_slot_init(kvm, new)) - return; - uv_register_mem_slot(kvm->arch.lpid, - new->base_gfn << PAGE_SHIFT, - new->npages * PAGE_SIZE, - 0, new->id); + /* + * @TODO kvmppc_uvmem_memslot_create() can fail and + * return error. Fix this. + */ + kvmppc_uvmem_memslot_create(kvm, new); break; case KVM_MR_DELETE: - uv_unregister_mem_slot(kvm->arch.lpid, old->id); - kvmppc_uvmem_slot_free(kvm, old); + kvmppc_uvmem_memslot_delete(kvm, old); break; default: /* TODO: Handle KVM_MR_MOVE */ diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7cd3cf3d366b..073617ce83e0 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -113,7 +113,7 @@ void __init kvm_cma_reserve(void) selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT; if (selected_size) { - pr_debug("%s: reserving %ld MiB for global area\n", __func__, + pr_info("%s: reserving %ld MiB for global area\n", __func__, (unsigned long)selected_size / SZ_1M); align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; cma_declare_contiguous(0, selected_size, 0, align_size, diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S index 63fd81f3039d..59822cba454d 100644 --- a/arch/powerpc/kvm/book3s_hv_interrupts.S +++ b/arch/powerpc/kvm/book3s_hv_interrupts.S @@ -140,6 +140,14 @@ BEGIN_FTR_SECTION std r8, HSTATE_MMCR2(r13) std r9, HSTATE_SIER(r13) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +BEGIN_FTR_SECTION + mfspr r5, SPRN_MMCR3 + mfspr r6, SPRN_SIER2 + mfspr r7, SPRN_SIER3 + std r5, HSTATE_MMCR3(r13) + std r6, HSTATE_SIER2(r13) + std r7, HSTATE_SIER3(r13) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mfspr r3, SPRN_PMC1 mfspr r5, SPRN_PMC2 mfspr r6, SPRN_PMC3 diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index 2c849a65db77..6822d23a2da4 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -233,20 +233,21 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) /* copy parameters in */ hv_ptr = kvmppc_get_gpr(vcpu, 4); + regs_ptr = kvmppc_get_gpr(vcpu, 5); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_read_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); + sizeof(struct hv_guest_state)) || + kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_PARAMETER; + if (kvmppc_need_byteswap(vcpu)) byteswap_hv_regs(&l2_hv); if (l2_hv.version != HV_GUEST_STATE_VERSION) return H_P2; - regs_ptr = kvmppc_get_gpr(vcpu, 5); - err = kvm_vcpu_read_guest(vcpu, regs_ptr, &l2_regs, - sizeof(struct pt_regs)); - if (err) - return H_PARAMETER; if (kvmppc_need_byteswap(vcpu)) byteswap_pt_regs(&l2_regs); if (l2_hv.vcpu_token >= NR_CPUS) @@ -323,12 +324,12 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu) byteswap_hv_regs(&l2_hv); byteswap_pt_regs(&l2_regs); } + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); err = kvm_vcpu_write_guest(vcpu, hv_ptr, &l2_hv, - sizeof(struct hv_guest_state)); - if (err) - return H_AUTHORITY; - err = kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, + sizeof(struct hv_guest_state)) || + kvm_vcpu_write_guest(vcpu, regs_ptr, &l2_regs, sizeof(struct pt_regs)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (err) return H_AUTHORITY; @@ -508,12 +509,16 @@ long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu) goto not_found; /* Write what was loaded into our buffer back to the L1 guest */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; } else { /* Load the data to be stored from the L1 guest into our buf */ + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto not_found; @@ -548,9 +553,12 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp) ret = -EFAULT; ptbl_addr = (kvm->arch.l1_ptcr & PRTB_MASK) + (gp->l1_lpid << 4); - if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) + if (gp->l1_lpid < (1ul << ((kvm->arch.l1_ptcr & PRTS_MASK) + 8))) { + int srcu_idx = srcu_read_lock(&kvm->srcu); ret = kvm_read_guest(kvm, ptbl_addr, &ptbl_entry, sizeof(ptbl_entry)); + srcu_read_unlock(&kvm->srcu, srcu_idx); + } if (ret) { gp->l1_gr_to_hr = 0; gp->process_table = 0; diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c index 79f7d07ef674..6028628ea3ac 100644 --- a/arch/powerpc/kvm/book3s_hv_ras.c +++ b/arch/powerpc/kvm/book3s_hv_ras.c @@ -244,7 +244,7 @@ long kvmppc_realmode_hmi_handler(void) { bool resync_req; - __this_cpu_inc(irq_stat.hmi_exceptions); + local_paca->hmi_irqs++; if (hmi_handle_debugtrig(NULL) >= 0) return 1; diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 71943892c81c..799d6d0f4ead 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -3428,7 +3428,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) mtspr SPRN_PMC6, r9 ld r3, VCPU_MMCR(r4) ld r5, VCPU_MMCR + 8(r4) - ld r6, VCPU_MMCR + 16(r4) + ld r6, VCPU_MMCRA(r4) ld r7, VCPU_SIAR(r4) ld r8, VCPU_SDAR(r4) mtspr SPRN_MMCR1, r5 @@ -3436,14 +3436,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_PMAO_BUG) mtspr SPRN_SIAR, r7 mtspr SPRN_SDAR, r8 BEGIN_FTR_SECTION - ld r5, VCPU_MMCR + 24(r4) + ld r5, VCPU_MMCR + 24(r4) + ld r6, VCPU_SIER + 8(r4) + ld r7, VCPU_SIER + 16(r4) + mtspr SPRN_MMCR3, r5 + mtspr SPRN_SIER2, r6 + mtspr SPRN_SIER3, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) +BEGIN_FTR_SECTION + ld r5, VCPU_MMCR + 16(r4) ld r6, VCPU_SIER(r4) mtspr SPRN_MMCR2, r5 mtspr SPRN_SIER, r6 BEGIN_FTR_SECTION_NESTED(96) lwz r7, VCPU_PMC + 24(r4) lwz r8, VCPU_PMC + 28(r4) - ld r9, VCPU_MMCR + 32(r4) + ld r9, VCPU_MMCRS(r4) mtspr SPRN_SPMC1, r7 mtspr SPRN_SPMC2, r8 mtspr SPRN_MMCRS, r9 @@ -3496,6 +3504,14 @@ BEGIN_FTR_SECTION mtspr SPRN_MMCR2, r8 mtspr SPRN_SIER, r9 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +BEGIN_FTR_SECTION + ld r5, HSTATE_MMCR3(r13) + ld r6, HSTATE_SIER2(r13) + ld r7, HSTATE_SIER3(r13) + mtspr SPRN_MMCR3, r5 + mtspr SPRN_SIER2, r6 + mtspr SPRN_SIER3, r7 +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) mtspr SPRN_MMCR0, r3 isync mtlr r0 @@ -3551,10 +3567,18 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mfspr r8, SPRN_SDAR std r4, VCPU_MMCR(r9) std r5, VCPU_MMCR + 8(r9) - std r6, VCPU_MMCR + 16(r9) + std r6, VCPU_MMCRA(r9) BEGIN_FTR_SECTION - std r10, VCPU_MMCR + 24(r9) + std r10, VCPU_MMCR + 16(r9) END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) +BEGIN_FTR_SECTION + mfspr r5, SPRN_MMCR3 + mfspr r6, SPRN_SIER2 + mfspr r7, SPRN_SIER3 + std r5, VCPU_MMCR + 24(r9) + std r6, VCPU_SIER + 8(r9) + std r7, VCPU_SIER + 16(r9) +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) std r7, VCPU_SIAR(r9) std r8, VCPU_SDAR(r9) mfspr r3, SPRN_PMC1 @@ -3578,7 +3602,7 @@ BEGIN_FTR_SECTION_NESTED(96) mfspr r8, SPRN_MMCRS stw r6, VCPU_PMC + 24(r9) stw r7, VCPU_PMC + 28(r9) - std r8, VCPU_MMCR + 32(r9) + std r8, VCPU_MMCRS(r9) lis r4, 0x8000 mtspr SPRN_MMCRS, r4 END_FTR_SECTION_NESTED(CPU_FTR_ARCH_300, 0, 96) diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 6850bd04bcb9..7705d5557239 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -93,12 +93,133 @@ #include <asm/ultravisor.h> #include <asm/mman.h> #include <asm/kvm_ppc.h> +#include <asm/kvm_book3s_uvmem.h> static struct dev_pagemap kvmppc_uvmem_pgmap; static unsigned long *kvmppc_uvmem_bitmap; static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock); -#define KVMPPC_UVMEM_PFN (1UL << 63) +/* + * States of a GFN + * --------------- + * The GFN can be in one of the following states. + * + * (a) Secure - The GFN is secure. The GFN is associated with + * a Secure VM, the contents of the GFN is not accessible + * to the Hypervisor. This GFN can be backed by a secure-PFN, + * or can be backed by a normal-PFN with contents encrypted. + * The former is true when the GFN is paged-in into the + * ultravisor. The latter is true when the GFN is paged-out + * of the ultravisor. + * + * (b) Shared - The GFN is shared. The GFN is associated with a + * a secure VM. The contents of the GFN is accessible to + * Hypervisor. This GFN is backed by a normal-PFN and its + * content is un-encrypted. + * + * (c) Normal - The GFN is a normal. The GFN is associated with + * a normal VM. The contents of the GFN is accesible to + * the Hypervisor. Its content is never encrypted. + * + * States of a VM. + * --------------- + * + * Normal VM: A VM whose contents are always accessible to + * the hypervisor. All its GFNs are normal-GFNs. + * + * Secure VM: A VM whose contents are not accessible to the + * hypervisor without the VM's consent. Its GFNs are + * either Shared-GFN or Secure-GFNs. + * + * Transient VM: A Normal VM that is transitioning to secure VM. + * The transition starts on successful return of + * H_SVM_INIT_START, and ends on successful return + * of H_SVM_INIT_DONE. This transient VM, can have GFNs + * in any of the three states; i.e Secure-GFN, Shared-GFN, + * and Normal-GFN. The VM never executes in this state + * in supervisor-mode. + * + * Memory slot State. + * ----------------------------- + * The state of a memory slot mirrors the state of the + * VM the memory slot is associated with. + * + * VM State transition. + * -------------------- + * + * A VM always starts in Normal Mode. + * + * H_SVM_INIT_START moves the VM into transient state. During this + * time the Ultravisor may request some of its GFNs to be shared or + * secured. So its GFNs can be in one of the three GFN states. + * + * H_SVM_INIT_DONE moves the VM entirely from transient state to + * secure-state. At this point any left-over normal-GFNs are + * transitioned to Secure-GFN. + * + * H_SVM_INIT_ABORT moves the transient VM back to normal VM. + * All its GFNs are moved to Normal-GFNs. + * + * UV_TERMINATE transitions the secure-VM back to normal-VM. All + * the secure-GFN and shared-GFNs are tranistioned to normal-GFN + * Note: The contents of the normal-GFN is undefined at this point. + * + * GFN state implementation: + * ------------------------- + * + * Secure GFN is associated with a secure-PFN; also called uvmem_pfn, + * when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag + * set, and contains the value of the secure-PFN. + * It is associated with a normal-PFN; also called mem_pfn, when + * the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set. + * The value of the normal-PFN is not tracked. + * + * Shared GFN is associated with a normal-PFN. Its pfn[] has + * KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN + * is not tracked. + * + * Normal GFN is associated with normal-PFN. Its pfn[] has + * no flag set. The value of the normal-PFN is not tracked. + * + * Life cycle of a GFN + * -------------------- + * + * -------------------------------------------------------------- + * | | Share | Unshare | SVM |H_SVM_INIT_DONE| + * | |operation |operation | abort/ | | + * | | | | terminate | | + * ------------------------------------------------------------- + * | | | | | | + * | Secure | Shared | Secure |Normal |Secure | + * | | | | | | + * | Shared | Shared | Secure |Normal |Shared | + * | | | | | | + * | Normal | Shared | Secure |Normal |Secure | + * -------------------------------------------------------------- + * + * Life cycle of a VM + * -------------------- + * + * -------------------------------------------------------------------- + * | | start | H_SVM_ |H_SVM_ |H_SVM_ |UV_SVM_ | + * | | VM |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE | + * | | | | | | | + * --------- ---------------------------------------------------------- + * | | | | | | | + * | Normal | Normal | Transient|Error |Error |Normal | + * | | | | | | | + * | Secure | Error | Error |Error |Error |Normal | + * | | | | | | | + * |Transient| N/A | Error |Secure |Normal |Normal | + * -------------------------------------------------------------------- + */ + +#define KVMPPC_GFN_UVMEM_PFN (1UL << 63) +#define KVMPPC_GFN_MEM_PFN (1UL << 62) +#define KVMPPC_GFN_SHARED (1UL << 61) +#define KVMPPC_GFN_SECURE (KVMPPC_GFN_UVMEM_PFN | KVMPPC_GFN_MEM_PFN) +#define KVMPPC_GFN_FLAG_MASK (KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED) +#define KVMPPC_GFN_PFN_MASK (~KVMPPC_GFN_FLAG_MASK) struct kvmppc_uvmem_slot { struct list_head list; @@ -106,11 +227,11 @@ struct kvmppc_uvmem_slot { unsigned long base_pfn; unsigned long *pfns; }; - struct kvmppc_uvmem_page_pvt { struct kvm *kvm; unsigned long gpa; bool skip_page_out; + bool remove_gfn; }; bool kvmppc_uvmem_available(void) @@ -163,8 +284,8 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) mutex_unlock(&kvm->arch.uvmem_lock); } -static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, - struct kvm *kvm) +static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm, + unsigned long flag, unsigned long uvmem_pfn) { struct kvmppc_uvmem_slot *p; @@ -172,24 +293,41 @@ static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn, if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { unsigned long index = gfn - p->base_pfn; - p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN; + if (flag == KVMPPC_GFN_UVMEM_PFN) + p->pfns[index] = uvmem_pfn | flag; + else + p->pfns[index] = flag; return; } } } -static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm) +/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */ +static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn, + unsigned long uvmem_pfn, struct kvm *kvm) { - struct kvmppc_uvmem_slot *p; + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn); +} - list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) { - if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { - p->pfns[gfn - p->base_pfn] = 0; - return; - } - } +/* mark the GFN as secure-GFN associated with a memory-PFN. */ +static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0); +} + +/* mark the GFN as a shared GFN. */ +static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0); +} + +/* mark the GFN as a non-existent GFN. */ +static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm) +{ + kvmppc_mark_gfn(gfn, kvm, 0, 0); } +/* return true, if the GFN is a secure-GFN backed by a secure-PFN */ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, unsigned long *uvmem_pfn) { @@ -199,10 +337,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) { unsigned long index = gfn - p->base_pfn; - if (p->pfns[index] & KVMPPC_UVMEM_PFN) { + if (p->pfns[index] & KVMPPC_GFN_UVMEM_PFN) { if (uvmem_pfn) *uvmem_pfn = p->pfns[index] & - ~KVMPPC_UVMEM_PFN; + KVMPPC_GFN_PFN_MASK; return true; } else return false; @@ -211,10 +349,114 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, return false; } +/* + * starting from *gfn search for the next available GFN that is not yet + * transitioned to a secure GFN. return the value of that GFN in *gfn. If a + * GFN is found, return true, else return false + * + * Must be called with kvm->arch.uvmem_lock held. + */ +static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot, + struct kvm *kvm, unsigned long *gfn) +{ + struct kvmppc_uvmem_slot *p; + bool ret = false; + unsigned long i; + + list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) + if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns) + break; + if (!p) + return ret; + /* + * The code below assumes, one to one correspondence between + * kvmppc_uvmem_slot and memslot. + */ + for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) { + unsigned long index = i - p->base_pfn; + + if (!(p->pfns[index] & KVMPPC_GFN_FLAG_MASK)) { + *gfn = i; + ret = true; + break; + } + } + return ret; +} + +static int kvmppc_memslot_page_merge(struct kvm *kvm, + const struct kvm_memory_slot *memslot, bool merge) +{ + unsigned long gfn = memslot->base_gfn; + unsigned long end, start = gfn_to_hva(kvm, gfn); + int ret = 0; + struct vm_area_struct *vma; + int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE; + + if (kvm_is_error_hva(start)) + return H_STATE; + + end = start + (memslot->npages << PAGE_SHIFT); + + mmap_write_lock(kvm->mm); + do { + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma) { + ret = H_STATE; + break; + } + ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, + merge_flag, &vma->vm_flags); + if (ret) { + ret = H_STATE; + break; + } + start = vma->vm_end; + } while (end > vma->vm_end); + + mmap_write_unlock(kvm->mm); + return ret; +} + +static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); + kvmppc_uvmem_slot_free(kvm, memslot); + kvmppc_memslot_page_merge(kvm, memslot, true); +} + +static int __kvmppc_uvmem_memslot_create(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + int ret = H_PARAMETER; + + if (kvmppc_memslot_page_merge(kvm, memslot, false)) + return ret; + + if (kvmppc_uvmem_slot_init(kvm, memslot)) + goto out1; + + ret = uv_register_mem_slot(kvm->arch.lpid, + memslot->base_gfn << PAGE_SHIFT, + memslot->npages * PAGE_SIZE, + 0, memslot->id); + if (ret < 0) { + ret = H_PARAMETER; + goto out; + } + return 0; +out: + kvmppc_uvmem_slot_free(kvm, memslot); +out1: + kvmppc_memslot_page_merge(kvm, memslot, true); + return ret; +} + unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) { struct kvm_memslots *slots; - struct kvm_memory_slot *memslot; + struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; int srcu_idx; @@ -232,35 +474,117 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) return H_AUTHORITY; srcu_idx = srcu_read_lock(&kvm->srcu); + + /* register the memslot */ slots = kvm_memslots(kvm); kvm_for_each_memslot(memslot, slots) { - if (kvmppc_uvmem_slot_init(kvm, memslot)) { - ret = H_PARAMETER; - goto out; - } - ret = uv_register_mem_slot(kvm->arch.lpid, - memslot->base_gfn << PAGE_SHIFT, - memslot->npages * PAGE_SIZE, - 0, memslot->id); - if (ret < 0) { - kvmppc_uvmem_slot_free(kvm, memslot); - ret = H_PARAMETER; - goto out; + ret = __kvmppc_uvmem_memslot_create(kvm, memslot); + if (ret) + break; + } + + if (ret) { + slots = kvm_memslots(kvm); + kvm_for_each_memslot(m, slots) { + if (m == memslot) + break; + __kvmppc_uvmem_memslot_delete(kvm, memslot); } } -out: + srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } -unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +/* + * Provision a new page on HV side and copy over the contents + * from secure memory using UV_PAGE_OUT uvcall. + * Caller must held kvm->arch.uvmem_lock. + */ +static int __kvmppc_svm_page_out(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) { - if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) - return H_UNSUPPORTED; + unsigned long src_pfn, dst_pfn = 0; + struct migrate_vma mig; + struct page *dpage, *spage; + struct kvmppc_uvmem_page_pvt *pvt; + unsigned long pfn; + int ret = U_SUCCESS; - kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; - pr_info("LPID %d went secure\n", kvm->arch.lpid); - return H_SUCCESS; + memset(&mig, 0, sizeof(mig)); + mig.vma = vma; + mig.start = start; + mig.end = end; + mig.src = &src_pfn; + mig.dst = &dst_pfn; + mig.pgmap_owner = &kvmppc_uvmem_pgmap; + mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; + + /* The requested page is already paged-out, nothing to do */ + if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) + return ret; + + ret = migrate_vma_setup(&mig); + if (ret) + return -1; + + spage = migrate_pfn_to_page(*mig.src); + if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) + goto out_finalize; + + if (!is_zone_device_page(spage)) + goto out_finalize; + + dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); + if (!dpage) { + ret = -1; + goto out_finalize; + } + + lock_page(dpage); + pvt = spage->zone_device_data; + pfn = page_to_pfn(dpage); + + /* + * This function is used in two cases: + * - When HV touches a secure page, for which we do UV_PAGE_OUT + * - When a secure page is converted to shared page, we *get* + * the page to essentially unmap the device page. In this + * case we skip page-out. + */ + if (!pvt->skip_page_out) + ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + + if (ret == U_SUCCESS) + *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + else { + unlock_page(dpage); + __free_page(dpage); + goto out_finalize; + } + + migrate_vma_pages(&mig); + +out_finalize: + migrate_vma_finalize(&mig); + return ret; +} + +static inline int kvmppc_svm_page_out(struct vm_area_struct *vma, + unsigned long start, unsigned long end, + unsigned long page_shift, + struct kvm *kvm, unsigned long gpa) +{ + int ret; + + mutex_lock(&kvm->arch.uvmem_lock); + ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa); + mutex_unlock(&kvm->arch.uvmem_lock); + + return ret; } /* @@ -271,33 +595,53 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) * fault on them, do fault time migration to replace the device PTEs in * QEMU page table with normal PTEs from newly allocated pages. */ -void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free, +void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, struct kvm *kvm, bool skip_page_out) { int i; struct kvmppc_uvmem_page_pvt *pvt; - unsigned long pfn, uvmem_pfn; - unsigned long gfn = free->base_gfn; + struct page *uvmem_page; + struct vm_area_struct *vma = NULL; + unsigned long uvmem_pfn, gfn; + unsigned long addr; - for (i = free->npages; i; --i, ++gfn) { - struct page *uvmem_page; + mmap_read_lock(kvm->mm); + + addr = slot->userspace_addr; + + gfn = slot->base_gfn; + for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) { + + /* Fetch the VMA if addr is not in the latest fetched one */ + if (!vma || addr >= vma->vm_end) { + vma = find_vma_intersection(kvm->mm, addr, addr+1); + if (!vma) { + pr_err("Can't find VMA for gfn:0x%lx\n", gfn); + break; + } + } mutex_lock(&kvm->arch.uvmem_lock); - if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { - mutex_unlock(&kvm->arch.uvmem_lock); - continue; + + if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) { + uvmem_page = pfn_to_page(uvmem_pfn); + pvt = uvmem_page->zone_device_data; + pvt->skip_page_out = skip_page_out; + pvt->remove_gfn = true; + + if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE, + PAGE_SHIFT, kvm, pvt->gpa)) + pr_err("Can't page out gpa:0x%lx addr:0x%lx\n", + pvt->gpa, addr); + } else { + /* Remove the shared flag if any */ + kvmppc_gfn_remove(gfn, kvm); } - uvmem_page = pfn_to_page(uvmem_pfn); - pvt = uvmem_page->zone_device_data; - pvt->skip_page_out = skip_page_out; mutex_unlock(&kvm->arch.uvmem_lock); - - pfn = gfn_to_pfn(kvm, gfn); - if (is_error_noslot_pfn(pfn)) - continue; - kvm_release_pfn_clean(pfn); } + + mmap_read_unlock(kvm->mm); } unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) @@ -360,7 +704,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm) goto out_clear; uvmem_pfn = bit + pfn_first; - kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); + kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm); pvt->gpa = gpa; pvt->kvm = kvm; @@ -379,13 +723,14 @@ out: } /* - * Alloc a PFN from private device memory pool and copy page from normal - * memory to secure memory using UV_PAGE_IN uvcall. + * Alloc a PFN from private device memory pool. If @pagein is true, + * copy page from normal memory to secure memory using UV_PAGE_IN uvcall. */ -static int -kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long gpa, struct kvm *kvm, - unsigned long page_shift, bool *downgrade) +static int kvmppc_svm_page_in(struct vm_area_struct *vma, + unsigned long start, + unsigned long end, unsigned long gpa, struct kvm *kvm, + unsigned long page_shift, + bool pagein) { unsigned long src_pfn, dst_pfn = 0; struct migrate_vma mig; @@ -402,18 +747,6 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, mig.dst = &dst_pfn; mig.flags = MIGRATE_VMA_SELECT_SYSTEM; - /* - * We come here with mmap_lock write lock held just for - * ksm_madvise(), otherwise we only need read mmap_lock. - * Hence downgrade to read lock once ksm_madvise() is done. - */ - ret = ksm_madvise(vma, vma->vm_start, vma->vm_end, - MADV_UNMERGEABLE, &vma->vm_flags); - mmap_write_downgrade(kvm->mm); - *downgrade = true; - if (ret) - return ret; - ret = migrate_vma_setup(&mig); if (ret) return ret; @@ -429,11 +762,16 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start, goto out_finalize; } - pfn = *mig.src >> MIGRATE_PFN_SHIFT; - spage = migrate_pfn_to_page(*mig.src); - if (spage) - uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, - page_shift); + if (pagein) { + pfn = *mig.src >> MIGRATE_PFN_SHIFT; + spage = migrate_pfn_to_page(*mig.src); + if (spage) { + ret = uv_page_in(kvm->arch.lpid, pfn << page_shift, + gpa, 0, page_shift); + if (ret) + goto out_finalize; + } + } *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; migrate_vma_pages(&mig); @@ -442,6 +780,80 @@ out_finalize: return ret; } +static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm, + const struct kvm_memory_slot *memslot) +{ + unsigned long gfn = memslot->base_gfn; + struct vm_area_struct *vma; + unsigned long start, end; + int ret = 0; + + mmap_read_lock(kvm->mm); + mutex_lock(&kvm->arch.uvmem_lock); + while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) { + ret = H_STATE; + start = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(start)) + break; + + end = start + (1UL << PAGE_SHIFT); + vma = find_vma_intersection(kvm->mm, start, end); + if (!vma || vma->vm_start > start || vma->vm_end < end) + break; + + ret = kvmppc_svm_page_in(vma, start, end, + (gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false); + if (ret) { + ret = H_STATE; + break; + } + + /* relinquish the cpu if needed */ + cond_resched(); + } + mutex_unlock(&kvm->arch.uvmem_lock); + mmap_read_unlock(kvm->mm); + return ret; +} + +unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; + int srcu_idx; + long ret = H_SUCCESS; + + if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) + return H_UNSUPPORTED; + + /* migrate any unmoved normal pfn to device pfns*/ + srcu_idx = srcu_read_lock(&kvm->srcu); + slots = kvm_memslots(kvm); + kvm_for_each_memslot(memslot, slots) { + ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); + if (ret) { + /* + * The pages will remain transitioned. + * Its the callers responsibility to + * terminate the VM, which will undo + * all state of the VM. Till then + * this VM is in a erroneous state. + * Its KVMPPC_SECURE_INIT_DONE will + * remain unset. + */ + ret = H_STATE; + goto out; + } + } + + kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE; + pr_info("LPID %d went secure\n", kvm->arch.lpid); + +out: + srcu_read_unlock(&kvm->srcu, srcu_idx); + return ret; +} + /* * Shares the page with HV, thus making it a normal page. * @@ -451,8 +863,8 @@ out_finalize: * In the former case, uses dev_pagemap_ops.migrate_to_ram handler * to unmap the device page from QEMU's page tables. */ -static unsigned long -kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) +static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa, + unsigned long page_shift) { int ret = H_PARAMETER; @@ -469,6 +881,11 @@ kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift) uvmem_page = pfn_to_page(uvmem_pfn); pvt = uvmem_page->zone_device_data; pvt->skip_page_out = true; + /* + * do not drop the GFN. It is a valid GFN + * that is transitioned to a shared GFN. + */ + pvt->remove_gfn = false; } retry: @@ -482,12 +899,16 @@ retry: uvmem_page = pfn_to_page(uvmem_pfn); pvt = uvmem_page->zone_device_data; pvt->skip_page_out = true; + pvt->remove_gfn = false; /* it continues to be a valid GFN */ kvm_release_pfn_clean(pfn); goto retry; } - if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift)) + if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, + page_shift)) { + kvmppc_gfn_shared(gfn, kvm); ret = H_SUCCESS; + } kvm_release_pfn_clean(pfn); mutex_unlock(&kvm->arch.uvmem_lock); out: @@ -501,11 +922,10 @@ out: * H_PAGE_IN_SHARED flag makes the page shared which means that the same * memory in is visible from both UV and HV. */ -unsigned long -kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, - unsigned long flags, unsigned long page_shift) +unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, + unsigned long flags, + unsigned long page_shift) { - bool downgrade = false; unsigned long start, end; struct vm_area_struct *vma; int srcu_idx; @@ -526,7 +946,7 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, ret = H_PARAMETER; srcu_idx = srcu_read_lock(&kvm->srcu); - mmap_write_lock(kvm->mm); + mmap_read_lock(kvm->mm); start = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(start)) @@ -542,97 +962,20 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa, if (!vma || vma->vm_start > start || vma->vm_end < end) goto out_unlock; - if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, - &downgrade)) - ret = H_SUCCESS; + if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift, + true)) + goto out_unlock; + + ret = H_SUCCESS; + out_unlock: mutex_unlock(&kvm->arch.uvmem_lock); out: - if (downgrade) - mmap_read_unlock(kvm->mm); - else - mmap_write_unlock(kvm->mm); + mmap_read_unlock(kvm->mm); srcu_read_unlock(&kvm->srcu, srcu_idx); return ret; } -/* - * Provision a new page on HV side and copy over the contents - * from secure memory using UV_PAGE_OUT uvcall. - */ -static int -kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start, - unsigned long end, unsigned long page_shift, - struct kvm *kvm, unsigned long gpa) -{ - unsigned long src_pfn, dst_pfn = 0; - struct migrate_vma mig; - struct page *dpage, *spage; - struct kvmppc_uvmem_page_pvt *pvt; - unsigned long pfn; - int ret = U_SUCCESS; - - memset(&mig, 0, sizeof(mig)); - mig.vma = vma; - mig.start = start; - mig.end = end; - mig.src = &src_pfn; - mig.dst = &dst_pfn; - mig.pgmap_owner = &kvmppc_uvmem_pgmap; - mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; - - mutex_lock(&kvm->arch.uvmem_lock); - /* The requested page is already paged-out, nothing to do */ - if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL)) - goto out; - - ret = migrate_vma_setup(&mig); - if (ret) - goto out; - - spage = migrate_pfn_to_page(*mig.src); - if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE)) - goto out_finalize; - - if (!is_zone_device_page(spage)) - goto out_finalize; - - dpage = alloc_page_vma(GFP_HIGHUSER, vma, start); - if (!dpage) { - ret = -1; - goto out_finalize; - } - - lock_page(dpage); - pvt = spage->zone_device_data; - pfn = page_to_pfn(dpage); - - /* - * This function is used in two cases: - * - When HV touches a secure page, for which we do UV_PAGE_OUT - * - When a secure page is converted to shared page, we *get* - * the page to essentially unmap the device page. In this - * case we skip page-out. - */ - if (!pvt->skip_page_out) - ret = uv_page_out(kvm->arch.lpid, pfn << page_shift, - gpa, 0, page_shift); - - if (ret == U_SUCCESS) - *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; - else { - unlock_page(dpage); - __free_page(dpage); - goto out_finalize; - } - - migrate_vma_pages(&mig); -out_finalize: - migrate_vma_finalize(&mig); -out: - mutex_unlock(&kvm->arch.uvmem_lock); - return ret; -} /* * Fault handler callback that gets called when HV touches any page that @@ -657,7 +1000,8 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf) /* * Release the device PFN back to the pool * - * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT. + * Gets called when secure GFN tranistions from a secure-PFN + * to a normal PFN during H_SVM_PAGE_OUT. * Gets called with kvm->arch.uvmem_lock held. */ static void kvmppc_uvmem_page_free(struct page *page) @@ -672,7 +1016,10 @@ static void kvmppc_uvmem_page_free(struct page *page) pvt = page->zone_device_data; page->zone_device_data = NULL; - kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + if (pvt->remove_gfn) + kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm); + else + kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm); kfree(pvt); } @@ -744,6 +1091,21 @@ out: return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT; } +int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new) +{ + int ret = __kvmppc_uvmem_memslot_create(kvm, new); + + if (!ret) + ret = kvmppc_uv_migrate_mem_slot(kvm, new); + + return ret; +} + +void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old) +{ + __kvmppc_uvmem_memslot_delete(kvm, old); +} + static u64 kvmppc_get_secmem_size(void) { struct device_node *np; diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index f7ad99d972ce..25a3679fb590 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -26,7 +26,7 @@ #define FUNC(name) name #define GET_SHADOW_VCPU(reg) lwz reg, (THREAD + THREAD_KVM_SVCPU)(r2) -#endif /* CONFIG_PPC_BOOK3S_XX */ +#endif /* CONFIG_PPC_BOOK3S_64 */ #define VCPU_LOAD_NVGPRS(vcpu) \ PPC_LL r14, VCPU_GPR(R14)(vcpu); \ @@ -55,8 +55,7 @@ ****************************************************************************/ /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) @@ -68,8 +67,8 @@ kvm_start_entry: /* Save host state to the stack */ PPC_STLU r1, -SWITCH_FRAME_SIZE(r1) - /* Save r3 (kvm_run) and r4 (vcpu) */ - SAVE_2GPRS(3, r1) + /* Save r3 (vcpu) */ + SAVE_GPR(3, r1) /* Save non-volatile registers (r14 - r31) */ SAVE_NVGPRS(r1) @@ -82,47 +81,46 @@ kvm_start_entry: PPC_STL r0, _LINK(r1) /* Load non-volatile guest state from the vcpu */ - VCPU_LOAD_NVGPRS(r4) + VCPU_LOAD_NVGPRS(r3) kvm_start_lightweight: /* Copy registers into shadow vcpu so we can access them in real mode */ - mr r3, r4 bl FUNC(kvmppc_copy_to_svcpu) nop - REST_GPR(4, r1) + REST_GPR(3, r1) #ifdef CONFIG_PPC_BOOK3S_64 /* Get the dcbz32 flag */ - PPC_LL r3, VCPU_HFLAGS(r4) - rldicl r3, r3, 0, 63 /* r3 &= 1 */ - stb r3, HSTATE_RESTORE_HID5(r13) + PPC_LL r0, VCPU_HFLAGS(r3) + rldicl r0, r0, 0, 63 /* r3 &= 1 */ + stb r0, HSTATE_RESTORE_HID5(r13) /* Load up guest SPRG3 value, since it's user readable */ - lwz r3, VCPU_SHAREDBE(r4) - cmpwi r3, 0 - ld r5, VCPU_SHARED(r4) + lbz r4, VCPU_SHAREDBE(r3) + cmpwi r4, 0 + ld r5, VCPU_SHARED(r3) beq sprg3_little_endian sprg3_big_endian: #ifdef __BIG_ENDIAN__ - ld r3, VCPU_SHARED_SPRG3(r5) + ld r4, VCPU_SHARED_SPRG3(r5) #else addi r5, r5, VCPU_SHARED_SPRG3 - ldbrx r3, 0, r5 + ldbrx r4, 0, r5 #endif b after_sprg3_load sprg3_little_endian: #ifdef __LITTLE_ENDIAN__ - ld r3, VCPU_SHARED_SPRG3(r5) + ld r4, VCPU_SHARED_SPRG3(r5) #else addi r5, r5, VCPU_SHARED_SPRG3 - ldbrx r3, 0, r5 + ldbrx r4, 0, r5 #endif after_sprg3_load: - mtspr SPRN_SPRG3, r3 + mtspr SPRN_SPRG3, r4 #endif /* CONFIG_PPC_BOOK3S_64 */ - PPC_LL r4, VCPU_SHADOW_MSR(r4) /* get shadow_msr */ + PPC_LL r4, VCPU_SHADOW_MSR(r3) /* get shadow_msr */ /* Jump to segment patching handler and into our guest */ bl FUNC(kvmppc_entry_trampoline) @@ -146,7 +144,7 @@ after_sprg3_load: * */ - PPC_LL r3, GPR4(r1) /* vcpu pointer */ + PPC_LL r3, GPR3(r1) /* vcpu pointer */ /* * kvmppc_copy_from_svcpu can clobber volatile registers, save @@ -169,7 +167,7 @@ after_sprg3_load: #endif /* CONFIG_PPC_BOOK3S_64 */ /* R7 = vcpu */ - PPC_LL r7, GPR4(r1) + PPC_LL r7, GPR3(r1) PPC_STL r14, VCPU_GPR(R14)(r7) PPC_STL r15, VCPU_GPR(R15)(r7) @@ -190,11 +188,11 @@ after_sprg3_load: PPC_STL r30, VCPU_GPR(R30)(r7) PPC_STL r31, VCPU_GPR(R31)(r7) - /* Pass the exit number as 3rd argument to kvmppc_handle_exit */ - lwz r5, VCPU_TRAP(r7) + /* Pass the exit number as 2nd argument to kvmppc_handle_exit */ + lwz r4, VCPU_TRAP(r7) - /* Restore r3 (kvm_run) and r4 (vcpu) */ - REST_2GPRS(3, r1) + /* Restore r3 (vcpu) */ + REST_GPR(3, r1) bl FUNC(kvmppc_handle_exit_pr) /* If RESUME_GUEST, get back in the loop */ @@ -223,11 +221,11 @@ kvm_loop_heavyweight: PPC_LL r4, _LINK(r1) PPC_STL r4, (PPC_LR_STKOFF + SWITCH_FRAME_SIZE)(r1) - /* Load vcpu and cpu_run */ - REST_2GPRS(3, r1) + /* Load vcpu */ + REST_GPR(3, r1) /* Load non-volatile guest state from the vcpu */ - VCPU_LOAD_NVGPRS(r4) + VCPU_LOAD_NVGPRS(r3) /* Jump back into the beginning of this function */ b kvm_start_lightweight @@ -235,7 +233,7 @@ kvm_loop_heavyweight: kvm_loop_lightweight: /* We'll need the vcpu pointer */ - REST_GPR(4, r1) + REST_GPR(3, r1) /* Jump back into the beginning of this function */ b kvm_start_lightweight diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index ed12dfbf9bb5..88fac22fbf09 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1151,9 +1151,9 @@ static int kvmppc_exit_pr_progint(struct kvm_vcpu *vcpu, unsigned int exit_nr) return r; } -int kvmppc_handle_exit_pr(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +int kvmppc_handle_exit_pr(struct kvm_vcpu *vcpu, unsigned int exit_nr) { + struct kvm_run *run = vcpu->run; int r = RESUME_HOST; int s; @@ -1826,12 +1826,11 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu) static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; int ret; /* Check if we can run the vcpu at all */ if (!vcpu->arch.sane) { - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; ret = -EINVAL; goto out; } @@ -1858,7 +1857,7 @@ static int kvmppc_vcpu_run_pr(struct kvm_vcpu *vcpu) kvmppc_fix_ee_before_entry(); - ret = __kvmppc_vcpu_run(run, vcpu); + ret = __kvmppc_vcpu_run(vcpu); kvmppc_clear_debug(vcpu); diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c index 26b25994c969..c5e677508d3b 100644 --- a/arch/powerpc/kvm/book3s_rtas.c +++ b/arch/powerpc/kvm/book3s_rtas.c @@ -229,7 +229,9 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu) */ args_phys = kvmppc_get_gpr(vcpu, 4) & KVM_PAM; + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); rc = kvm_read_guest(vcpu->kvm, args_phys, &args, sizeof(args)); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (rc) goto fail; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index c0d62a917e20..3e1c9f08e302 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -731,12 +731,11 @@ int kvmppc_core_check_requests(struct kvm_vcpu *vcpu) int kvmppc_vcpu_run(struct kvm_vcpu *vcpu) { - struct kvm_run *run = vcpu->run; int ret, s; struct debug_reg debug; if (!vcpu->arch.sane) { - run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; return -EINVAL; } @@ -778,7 +777,7 @@ int kvmppc_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.pgdir = vcpu->kvm->mm->pgd; kvmppc_fix_ee_before_entry(); - ret = __kvmppc_vcpu_run(run, vcpu); + ret = __kvmppc_vcpu_run(vcpu); /* No need for guest_exit. It's done in handle_exit. We also get here with interrupts enabled. */ @@ -982,9 +981,9 @@ static int kvmppc_resume_inst_load(struct kvm_vcpu *vcpu, * * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV) */ -int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, - unsigned int exit_nr) +int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) { + struct kvm_run *run = vcpu->run; int r = RESUME_HOST; int s; int idx; diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S index 2e56ab5a5f55..6fa82efe833b 100644 --- a/arch/powerpc/kvm/booke_interrupts.S +++ b/arch/powerpc/kvm/booke_interrupts.S @@ -237,7 +237,7 @@ _GLOBAL(kvmppc_resume_host) /* Switch to kernel stack and jump to handler. */ LOAD_REG_ADDR(r3, kvmppc_handle_exit) mtctr r3 - lwz r3, HOST_RUN(r1) + mr r3, r4 lwz r2, HOST_R2(r1) mr r14, r4 /* Save vcpu pointer. */ @@ -337,15 +337,14 @@ heavyweight_exit: /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) stwu r1, -HOST_STACK_SIZE(r1) - stw r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */ + stw r1, VCPU_HOST_STACK(r3) /* Save stack pointer to vcpu. */ /* Save host state to stack. */ - stw r3, HOST_RUN(r1) + mr r4, r3 mflr r3 stw r3, HOST_STACK_LR(r1) mfcr r5 diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S index c577ba4b3169..8262c14fc9e6 100644 --- a/arch/powerpc/kvm/bookehv_interrupts.S +++ b/arch/powerpc/kvm/bookehv_interrupts.S @@ -434,9 +434,10 @@ _GLOBAL(kvmppc_resume_host) #endif /* Switch to kernel stack and jump to handler. */ - PPC_LL r3, HOST_RUN(r1) + mr r3, r4 mr r5, r14 /* intno */ mr r14, r4 /* Save vcpu pointer. */ + mr r4, r5 bl kvmppc_handle_exit /* Restore vcpu pointer and the nonvolatiles we used. */ @@ -525,15 +526,14 @@ heavyweight_exit: blr /* Registers: - * r3: kvm_run pointer - * r4: vcpu pointer + * r3: vcpu pointer */ _GLOBAL(__kvmppc_vcpu_run) stwu r1, -HOST_STACK_SIZE(r1) - PPC_STL r1, VCPU_HOST_STACK(r4) /* Save stack pointer to vcpu. */ + PPC_STL r1, VCPU_HOST_STACK(r3) /* Save stack pointer to vcpu. */ /* Save host state to stack. */ - PPC_STL r3, HOST_RUN(r1) + mr r4, r3 mflr r3 mfcr r5 PPC_STL r3, HOST_STACK_LR(r1) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index aaa7b62f2f82..13999123b735 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -403,7 +403,10 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, return EMULATE_DONE; } - if (kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size)) + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (rc) return EMULATE_DO_MMIO; return EMULATE_DONE; diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 4a61a971c34e..830a126e095d 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -89,7 +89,7 @@ {H_CREATE_RPT, "H_CREATE_RPT"}, \ {H_REMOVE_RPT, "H_REMOVE_RPT"}, \ {H_REGISTER_RPAGES, "H_REGISTER_RPAGES"}, \ - {H_DISABLE_AND_GETC, "H_DISABLE_AND_GETC"}, \ + {H_DISABLE_AND_GET, "H_DISABLE_AND_GET"}, \ {H_ERROR_DATA, "H_ERROR_DATA"}, \ {H_GET_HCA_INFO, "H_GET_HCA_INFO"}, \ {H_GET_PERF_COUNT, "H_GET_PERF_COUNT"}, \ diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile index 5e994cda8e40..d66a645503eb 100644 --- a/arch/powerpc/lib/Makefile +++ b/arch/powerpc/lib/Makefile @@ -41,7 +41,10 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \ obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \ memcpy_64.o memcpy_mcsafe_64.o +ifndef CONFIG_PPC_QUEUED_SPINLOCKS obj64-$(CONFIG_SMP) += locks.o +endif + obj64-$(CONFIG_ALTIVEC) += vmx-helper.o obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o \ test_emulate_step_exec_instr.o diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 0a051dfeb177..8c3934ea6220 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -93,7 +93,7 @@ static int map_patch_area(void *addr, unsigned long text_poke_addr) unsigned long pfn; int err; - if (is_vmalloc_addr(addr)) + if (is_vmalloc_or_module_addr(addr)) pfn = vmalloc_to_pfn(addr); else pfn = __pa_symbol(addr) >> PAGE_SHIFT; diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c index 6440d5943c00..04165b7a163f 100644 --- a/arch/powerpc/lib/locks.c +++ b/arch/powerpc/lib/locks.c @@ -27,14 +27,14 @@ void splpar_spin_yield(arch_spinlock_t *lock) return; holder_cpu = lock_value & 0xffff; BUG_ON(holder_cpu >= NR_CPUS); - yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); + + yield_count = yield_count_of(holder_cpu); if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ rmb(); if (lock->slock != lock_value) return; /* something has changed */ - plpar_hcall_norets(H_CONFER, - get_hard_smp_processor_id(holder_cpu), yield_count); + yield_to_preempted(holder_cpu, yield_count); } EXPORT_SYMBOL_GPL(splpar_spin_yield); @@ -53,13 +53,13 @@ void splpar_rw_yield(arch_rwlock_t *rw) return; /* no write lock at present */ holder_cpu = lock_value & 0xffff; BUG_ON(holder_cpu >= NR_CPUS); - yield_count = be32_to_cpu(lppaca_of(holder_cpu).yield_count); + + yield_count = yield_count_of(holder_cpu); if ((yield_count & 1) == 0) return; /* virtual cpu is currently running */ rmb(); if (rw->lock != lock_value) return; /* something has changed */ - plpar_hcall_norets(H_CONFER, - get_hard_smp_processor_id(holder_cpu), yield_count); + yield_to_preempted(holder_cpu, yield_count); } #endif diff --git a/arch/powerpc/lib/pmem.c b/arch/powerpc/lib/pmem.c index 0666a8d29596..1550e0d2513a 100644 --- a/arch/powerpc/lib/pmem.c +++ b/arch/powerpc/lib/pmem.c @@ -9,20 +9,56 @@ #include <asm/cacheflush.h> +static inline void __clean_pmem_range(unsigned long start, unsigned long stop) +{ + unsigned long shift = l1_dcache_shift(); + unsigned long bytes = l1_dcache_bytes(); + void *addr = (void *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); + unsigned long i; + + for (i = 0; i < size >> shift; i++, addr += bytes) + asm volatile(PPC_DCBSTPS(%0, %1): :"i"(0), "r"(addr): "memory"); +} + +static inline void __flush_pmem_range(unsigned long start, unsigned long stop) +{ + unsigned long shift = l1_dcache_shift(); + unsigned long bytes = l1_dcache_bytes(); + void *addr = (void *)(start & ~(bytes - 1)); + unsigned long size = stop - (unsigned long)addr + (bytes - 1); + unsigned long i; + + for (i = 0; i < size >> shift; i++, addr += bytes) + asm volatile(PPC_DCBFPS(%0, %1): :"i"(0), "r"(addr): "memory"); +} + +static inline void clean_pmem_range(unsigned long start, unsigned long stop) +{ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return __clean_pmem_range(start, stop); +} + +static inline void flush_pmem_range(unsigned long start, unsigned long stop) +{ + if (cpu_has_feature(CPU_FTR_ARCH_207S)) + return __flush_pmem_range(start, stop); +} + /* * CONFIG_ARCH_HAS_PMEM_API symbols */ void arch_wb_cache_pmem(void *addr, size_t size) { unsigned long start = (unsigned long) addr; - flush_dcache_range(start, start + size); + clean_pmem_range(start, start + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { unsigned long start = (unsigned long) addr; - flush_dcache_range(start, start + size); + flush_pmem_range(start, start + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); @@ -35,19 +71,17 @@ long __copy_from_user_flushcache(void *dest, const void __user *src, unsigned long copied, start = (unsigned long) dest; copied = __copy_from_user(dest, src, size); - flush_dcache_range(start, start + size); + clean_pmem_range(start, start + size); return copied; } -void *memcpy_flushcache(void *dest, const void *src, size_t size) +void memcpy_flushcache(void *dest, const void *src, size_t size) { unsigned long start = (unsigned long) dest; memcpy(dest, src, size); - flush_dcache_range(start, start + size); - - return dest; + clean_pmem_range(start, start + size); } EXPORT_SYMBOL(memcpy_flushcache); diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5abe98216dc2..caee8cc77e19 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -16,6 +16,7 @@ #include <asm/disassemble.h> extern char system_call_common[]; +extern char system_call_vectored_emulate[]; #ifdef CONFIG_PPC64 /* Bits in SRR1 that are copied from MSR */ @@ -200,8 +201,8 @@ static nokprobe_inline unsigned long mlsd_8lsd_ea(unsigned int instr, unsigned int dd; unsigned long ea, d0, d1, d; - prefix_r = instr & (1ul << 20); - ra = (suffix >> 16) & 0x1f; + prefix_r = GET_PREFIX_R(instr); + ra = GET_PREFIX_RA(suffix); d0 = instr & 0x3ffff; d1 = suffix & 0xffff; @@ -1236,6 +1237,9 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, case 17: /* sc */ if ((word & 0xfe2) == 2) op->type = SYSCALL; + else if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && + (word & 0xfe3) == 1) + op->type = SYSCALL_VECTORED_0; else op->type = UNKNOWN; return 0; @@ -1339,8 +1343,8 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, switch (opcode) { #ifdef __powerpc64__ case 1: - prefix_r = word & (1ul << 20); - ra = (suffix >> 16) & 0x1f; + prefix_r = GET_PREFIX_R(word); + ra = GET_PREFIX_RA(suffix); rd = (suffix >> 21) & 0x1f; op->reg = rd; op->val = regs->gpr[rd]; @@ -1802,7 +1806,18 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, op->val = (int) regs->gpr[ra] / (int) regs->gpr[rb]; goto arith_done; - +#ifdef __powerpc64__ + case 425: /* divde[.] */ + asm volatile(PPC_DIVDE(%0, %1, %2) : + "=r" (op->val) : "r" (regs->gpr[ra]), + "r" (regs->gpr[rb])); + goto arith_done; + case 393: /* divdeu[.] */ + asm volatile(PPC_DIVDEU(%0, %1, %2) : + "=r" (op->val) : "r" (regs->gpr[ra]), + "r" (regs->gpr[rb])); + goto arith_done; +#endif case 755: /* darn */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) return -1; @@ -2715,8 +2730,8 @@ int analyse_instr(struct instruction_op *op, const struct pt_regs *regs, } break; case 1: /* Prefixed instructions */ - prefix_r = word & (1ul << 20); - ra = (suffix >> 16) & 0x1f; + prefix_r = GET_PREFIX_R(word); + ra = GET_PREFIX_RA(suffix); op->update_reg = ra; rd = (suffix >> 21) & 0x1f; op->reg = rd; @@ -3378,6 +3393,18 @@ int emulate_step(struct pt_regs *regs, struct ppc_inst instr) regs->msr = MSR_KERNEL; return 1; +#ifdef CONFIG_PPC_BOOK3S_64 + case SYSCALL_VECTORED_0: /* scv 0 */ + regs->gpr[9] = regs->gpr[13]; + regs->gpr[10] = MSR_KERNEL; + regs->gpr[11] = regs->nip + 4; + regs->gpr[12] = regs->msr & MSR_MASK; + regs->gpr[13] = (unsigned long) get_paca(); + regs->nip = (unsigned long) &system_call_vectored_emulate; + regs->msr = MSR_KERNEL; + return 1; +#endif + case RFI: return -1; #endif diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c index 46af80279ebc..0a201b771477 100644 --- a/arch/powerpc/lib/test_emulate_step.c +++ b/arch/powerpc/lib/test_emulate_step.c @@ -8,59 +8,51 @@ #define pr_fmt(fmt) "emulate_step_test: " fmt #include <linux/ptrace.h> +#include <asm/cpu_has_feature.h> #include <asm/sstep.h> #include <asm/ppc-opcode.h> #include <asm/code-patching.h> #include <asm/inst.h> -#define IMM_L(i) ((uintptr_t)(i) & 0xffff) -#define IMM_DS(i) ((uintptr_t)(i) & 0xfffc) - -/* - * Defined with TEST_ prefix so it does not conflict with other - * definitions. - */ -#define TEST_LD(r, base, i) ppc_inst(PPC_INST_LD | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_DS(i)) -#define TEST_LWZ(r, base, i) ppc_inst(PPC_INST_LWZ | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define TEST_LWZX(t, a, b) ppc_inst(PPC_INST_LWZX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_STD(r, base, i) ppc_inst(PPC_INST_STD | ___PPC_RS(r) | \ - ___PPC_RA(base) | IMM_DS(i)) -#define TEST_LDARX(t, a, b, eh) ppc_inst(PPC_INST_LDARX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b) | \ - __PPC_EH(eh)) -#define TEST_STDCX(s, a, b) ppc_inst(PPC_INST_STDCX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_LFSX(t, a, b) ppc_inst(PPC_INST_LFSX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_STFSX(s, a, b) ppc_inst(PPC_INST_STFSX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_LFDX(t, a, b) ppc_inst(PPC_INST_LFDX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_STFDX(s, a, b) ppc_inst(PPC_INST_STFDX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_LVX(t, a, b) ppc_inst(PPC_INST_LVX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_STVX(s, a, b) ppc_inst(PPC_INST_STVX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_LXVD2X(s, a, b) ppc_inst(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b)) -#define TEST_STXVD2X(s, a, b) ppc_inst(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b)) -#define TEST_ADD(t, a, b) ppc_inst(PPC_INST_ADD | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_ADD_DOT(t, a, b) ppc_inst(PPC_INST_ADD | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b) | 0x1) -#define TEST_ADDC(t, a, b) ppc_inst(PPC_INST_ADDC | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define TEST_ADDC_DOT(t, a, b) ppc_inst(PPC_INST_ADDC | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b) | 0x1) - #define MAX_SUBTESTS 16 #define IGNORE_GPR(n) (0x1UL << (n)) #define IGNORE_XER (0x1UL << 32) #define IGNORE_CCR (0x1UL << 33) +#define NEGATIVE_TEST (0x1UL << 63) + +#define TEST_PLD(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_PLD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PLWZ(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_RAW_LWZ(r, base, i)) + +#define TEST_PSTD(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_8LS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_PSTD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PLFS(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_LFS | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PSTFS(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_STFS | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PLFD(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_LFD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PSTFD(r, base, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_INST_STFD | ___PPC_RT(r) | ___PPC_RA(base) | IMM_L(i)) + +#define TEST_PADDI(t, a, i, pr) \ + ppc_inst_prefix(PPC_PREFIX_MLS | __PPC_PRFX_R(pr) | IMM_H(i), \ + PPC_RAW_ADDI(t, a, i)) + static void __init init_pt_regs(struct pt_regs *regs) { @@ -105,7 +97,7 @@ static void __init test_ld(void) regs.gpr[3] = (unsigned long) &a; /* ld r5, 0(r3) */ - stepped = emulate_step(®s, TEST_LD(5, 3, 0)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LD(5, 3, 0))); if (stepped == 1 && regs.gpr[5] == a) show_result("ld", "PASS"); @@ -113,6 +105,29 @@ static void __init test_ld(void) show_result("ld", "FAIL"); } +static void __init test_pld(void) +{ + struct pt_regs regs; + unsigned long a = 0x23; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("pld", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long)&a; + + /* pld r5, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PLD(5, 3, 0, 0)); + + if (stepped == 1 && regs.gpr[5] == a) + show_result("pld", "PASS"); + else + show_result("pld", "FAIL"); +} + static void __init test_lwz(void) { struct pt_regs regs; @@ -123,7 +138,7 @@ static void __init test_lwz(void) regs.gpr[3] = (unsigned long) &a; /* lwz r5, 0(r3) */ - stepped = emulate_step(®s, TEST_LWZ(5, 3, 0)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LWZ(5, 3, 0))); if (stepped == 1 && regs.gpr[5] == a) show_result("lwz", "PASS"); @@ -131,6 +146,30 @@ static void __init test_lwz(void) show_result("lwz", "FAIL"); } +static void __init test_plwz(void) +{ + struct pt_regs regs; + unsigned int a = 0x4545; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("plwz", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long)&a; + + /* plwz r5, 0(r3), 0 */ + + stepped = emulate_step(®s, TEST_PLWZ(5, 3, 0, 0)); + + if (stepped == 1 && regs.gpr[5] == a) + show_result("plwz", "PASS"); + else + show_result("plwz", "FAIL"); +} + static void __init test_lwzx(void) { struct pt_regs regs; @@ -143,7 +182,7 @@ static void __init test_lwzx(void) regs.gpr[5] = 0x8765; /* lwzx r5, r3, r4 */ - stepped = emulate_step(®s, TEST_LWZX(5, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LWZX(5, 3, 4))); if (stepped == 1 && regs.gpr[5] == a[2]) show_result("lwzx", "PASS"); else @@ -161,13 +200,36 @@ static void __init test_std(void) regs.gpr[5] = 0x5678; /* std r5, 0(r3) */ - stepped = emulate_step(®s, TEST_STD(5, 3, 0)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STD(5, 3, 0))); if (stepped == 1 && regs.gpr[5] == a) show_result("std", "PASS"); else show_result("std", "FAIL"); } +static void __init test_pstd(void) +{ + struct pt_regs regs; + unsigned long a = 0x1234; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("pstd", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + regs.gpr[3] = (unsigned long)&a; + regs.gpr[5] = 0x5678; + + /* pstd r5, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PSTD(5, 3, 0, 0)); + if (stepped == 1 || regs.gpr[5] == a) + show_result("pstd", "PASS"); + else + show_result("pstd", "FAIL"); +} + static void __init test_ldarx_stdcx(void) { struct pt_regs regs; @@ -186,7 +248,7 @@ static void __init test_ldarx_stdcx(void) regs.gpr[5] = 0x5678; /* ldarx r5, r3, r4, 0 */ - stepped = emulate_step(®s, TEST_LDARX(5, 3, 4, 0)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LDARX(5, 3, 4, 0))); /* * Don't touch 'a' here. Touching 'a' can do Load/store @@ -204,7 +266,7 @@ static void __init test_ldarx_stdcx(void) regs.gpr[5] = 0x9ABC; /* stdcx. r5, r3, r4 */ - stepped = emulate_step(®s, TEST_STDCX(5, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STDCX(5, 3, 4))); /* * Two possible scenarios that indicates successful emulation @@ -244,7 +306,7 @@ static void __init test_lfsx_stfsx(void) regs.gpr[4] = 0; /* lfsx frt10, r3, r4 */ - stepped = emulate_step(®s, TEST_LFSX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LFSX(10, 3, 4))); if (stepped == 1) show_result("lfsx", "PASS"); @@ -257,7 +319,7 @@ static void __init test_lfsx_stfsx(void) c.a = 678.91; /* stfsx frs10, r3, r4 */ - stepped = emulate_step(®s, TEST_STFSX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STFSX(10, 3, 4))); if (stepped == 1 && c.b == cached_b) show_result("stfsx", "PASS"); @@ -265,6 +327,53 @@ static void __init test_lfsx_stfsx(void) show_result("stfsx", "FAIL"); } +static void __init test_plfs_pstfs(void) +{ + struct pt_regs regs; + union { + float a; + int b; + } c; + int cached_b; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("pld", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + + + /*** plfs ***/ + + c.a = 123.45; + cached_b = c.b; + + regs.gpr[3] = (unsigned long)&c.a; + + /* plfs frt10, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PLFS(10, 3, 0, 0)); + + if (stepped == 1) + show_result("plfs", "PASS"); + else + show_result("plfs", "FAIL"); + + + /*** pstfs ***/ + + c.a = 678.91; + + /* pstfs frs10, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PSTFS(10, 3, 0, 0)); + + if (stepped == 1 && c.b == cached_b) + show_result("pstfs", "PASS"); + else + show_result("pstfs", "FAIL"); +} + static void __init test_lfdx_stfdx(void) { struct pt_regs regs; @@ -287,7 +396,7 @@ static void __init test_lfdx_stfdx(void) regs.gpr[4] = 0; /* lfdx frt10, r3, r4 */ - stepped = emulate_step(®s, TEST_LFDX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LFDX(10, 3, 4))); if (stepped == 1) show_result("lfdx", "PASS"); @@ -300,13 +409,60 @@ static void __init test_lfdx_stfdx(void) c.a = 987654.32; /* stfdx frs10, r3, r4 */ - stepped = emulate_step(®s, TEST_STFDX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STFDX(10, 3, 4))); if (stepped == 1 && c.b == cached_b) show_result("stfdx", "PASS"); else show_result("stfdx", "FAIL"); } + +static void __init test_plfd_pstfd(void) +{ + struct pt_regs regs; + union { + double a; + long b; + } c; + long cached_b; + int stepped = -1; + + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + show_result("pld", "SKIP (!CPU_FTR_ARCH_31)"); + return; + } + + init_pt_regs(®s); + + + /*** plfd ***/ + + c.a = 123456.78; + cached_b = c.b; + + regs.gpr[3] = (unsigned long)&c.a; + + /* plfd frt10, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PLFD(10, 3, 0, 0)); + + if (stepped == 1) + show_result("plfd", "PASS"); + else + show_result("plfd", "FAIL"); + + + /*** pstfd ***/ + + c.a = 987654.32; + + /* pstfd frs10, 0(r3), 0 */ + stepped = emulate_step(®s, TEST_PSTFD(10, 3, 0, 0)); + + if (stepped == 1 && c.b == cached_b) + show_result("pstfd", "PASS"); + else + show_result("pstfd", "FAIL"); +} #else static void __init test_lfsx_stfsx(void) { @@ -314,11 +470,23 @@ static void __init test_lfsx_stfsx(void) show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)"); } +static void __init test_plfs_pstfs(void) +{ + show_result("plfs", "SKIP (CONFIG_PPC_FPU is not set)"); + show_result("pstfs", "SKIP (CONFIG_PPC_FPU is not set)"); +} + static void __init test_lfdx_stfdx(void) { show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)"); show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)"); } + +static void __init test_plfd_pstfd(void) +{ + show_result("plfd", "SKIP (CONFIG_PPC_FPU is not set)"); + show_result("pstfd", "SKIP (CONFIG_PPC_FPU is not set)"); +} #endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC @@ -346,7 +514,7 @@ static void __init test_lvx_stvx(void) regs.gpr[4] = 0; /* lvx vrt10, r3, r4 */ - stepped = emulate_step(®s, TEST_LVX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LVX(10, 3, 4))); if (stepped == 1) show_result("lvx", "PASS"); @@ -362,7 +530,7 @@ static void __init test_lvx_stvx(void) c.b[3] = 498532; /* stvx vrs10, r3, r4 */ - stepped = emulate_step(®s, TEST_STVX(10, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STVX(10, 3, 4))); if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] && cached_b[2] == c.b[2] && cached_b[3] == c.b[3]) @@ -403,7 +571,7 @@ static void __init test_lxvd2x_stxvd2x(void) regs.gpr[4] = 0; /* lxvd2x vsr39, r3, r4 */ - stepped = emulate_step(®s, TEST_LXVD2X(39, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_LXVD2X(39, R3, R4))); if (stepped == 1 && cpu_has_feature(CPU_FTR_VSX)) { show_result("lxvd2x", "PASS"); @@ -423,7 +591,7 @@ static void __init test_lxvd2x_stxvd2x(void) c.b[3] = 4; /* stxvd2x vsr39, r3, r4 */ - stepped = emulate_step(®s, TEST_STXVD2X(39, 3, 4)); + stepped = emulate_step(®s, ppc_inst(PPC_RAW_STXVD2X(39, R3, R4))); if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] && cached_b[2] == c.b[2] && cached_b[3] == c.b[3] && @@ -447,18 +615,24 @@ static void __init test_lxvd2x_stxvd2x(void) static void __init run_tests_load_store(void) { test_ld(); + test_pld(); test_lwz(); + test_plwz(); test_lwzx(); test_std(); + test_pstd(); test_ldarx_stdcx(); test_lfsx_stfsx(); + test_plfs_pstfs(); test_lfdx_stfdx(); + test_plfd_pstfd(); test_lvx_stvx(); test_lxvd2x_stxvd2x(); } struct compute_test { char *mnemonic; + unsigned long cpu_feature; struct { char *descr; unsigned long flags; @@ -467,6 +641,11 @@ struct compute_test { } subtests[MAX_SUBTESTS + 1]; }; +/* Extreme values for si0||si1 (the MLS:D-form 34 bit immediate field) */ +#define SI_MIN BIT(33) +#define SI_MAX (BIT(33) - 1) +#define SI_UMAX (BIT(34) - 1) + static struct compute_test compute_tests[] = { { .mnemonic = "nop", @@ -485,7 +664,7 @@ static struct compute_test compute_tests[] = { .subtests = { { .descr = "RA = LONG_MIN, RB = LONG_MIN", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MIN, @@ -493,7 +672,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN, RB = LONG_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MAX, @@ -501,7 +680,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MAX, RB = LONG_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = LONG_MAX, .gpr[22] = LONG_MAX, @@ -509,7 +688,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = ULONG_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = ULONG_MAX, @@ -517,7 +696,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = 0x1", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = 0x1, @@ -525,7 +704,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MIN", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MIN, @@ -533,7 +712,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MAX, @@ -541,7 +720,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MAX, RB = INT_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = INT_MAX, .gpr[22] = INT_MAX, @@ -549,7 +728,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = UINT_MAX", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = UINT_MAX, @@ -557,7 +736,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = 0x1", - .instr = TEST_ADD(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = 0x1, @@ -571,7 +750,7 @@ static struct compute_test compute_tests[] = { { .descr = "RA = LONG_MIN, RB = LONG_MIN", .flags = IGNORE_CCR, - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MIN, @@ -579,7 +758,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN, RB = LONG_MAX", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MAX, @@ -588,7 +767,7 @@ static struct compute_test compute_tests[] = { { .descr = "RA = LONG_MAX, RB = LONG_MAX", .flags = IGNORE_CCR, - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MAX, .gpr[22] = LONG_MAX, @@ -596,7 +775,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = ULONG_MAX", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = ULONG_MAX, @@ -604,7 +783,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = 0x1", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = 0x1, @@ -612,7 +791,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MIN", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MIN, @@ -620,7 +799,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MAX", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MAX, @@ -628,7 +807,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MAX, RB = INT_MAX", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MAX, .gpr[22] = INT_MAX, @@ -636,7 +815,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = UINT_MAX", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = UINT_MAX, @@ -644,7 +823,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = 0x1", - .instr = TEST_ADD_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADD_DOT(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = 0x1, @@ -657,7 +836,7 @@ static struct compute_test compute_tests[] = { .subtests = { { .descr = "RA = LONG_MIN, RB = LONG_MIN", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MIN, @@ -665,7 +844,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN, RB = LONG_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MAX, @@ -673,7 +852,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MAX, RB = LONG_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = LONG_MAX, .gpr[22] = LONG_MAX, @@ -681,7 +860,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = ULONG_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = ULONG_MAX, @@ -689,7 +868,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = 0x1", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = 0x1, @@ -697,7 +876,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MIN", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MIN, @@ -705,7 +884,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MAX, @@ -713,7 +892,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MAX, RB = INT_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = INT_MAX, .gpr[22] = INT_MAX, @@ -721,7 +900,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = UINT_MAX", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = UINT_MAX, @@ -729,7 +908,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = 0x1", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = 0x1, @@ -737,7 +916,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN", - .instr = TEST_ADDC(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN | (uint)INT_MIN, .gpr[22] = LONG_MIN | (uint)INT_MIN, @@ -751,7 +930,7 @@ static struct compute_test compute_tests[] = { { .descr = "RA = LONG_MIN, RB = LONG_MIN", .flags = IGNORE_CCR, - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MIN, @@ -759,7 +938,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN, RB = LONG_MAX", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN, .gpr[22] = LONG_MAX, @@ -768,7 +947,7 @@ static struct compute_test compute_tests[] = { { .descr = "RA = LONG_MAX, RB = LONG_MAX", .flags = IGNORE_CCR, - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MAX, .gpr[22] = LONG_MAX, @@ -776,7 +955,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = ULONG_MAX", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = ULONG_MAX, @@ -784,7 +963,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = ULONG_MAX, RB = 0x1", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = ULONG_MAX, .gpr[22] = 0x1, @@ -792,7 +971,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MIN", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MIN, @@ -800,7 +979,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MIN, RB = INT_MAX", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MIN, .gpr[22] = INT_MAX, @@ -808,7 +987,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = INT_MAX, RB = INT_MAX", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = INT_MAX, .gpr[22] = INT_MAX, @@ -816,7 +995,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = UINT_MAX", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = UINT_MAX, @@ -824,7 +1003,7 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = UINT_MAX, RB = 0x1", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = UINT_MAX, .gpr[22] = 0x1, @@ -832,31 +1011,320 @@ static struct compute_test compute_tests[] = { }, { .descr = "RA = LONG_MIN | INT_MIN, RB = LONG_MIN | INT_MIN", - .instr = TEST_ADDC_DOT(20, 21, 22), + .instr = ppc_inst(PPC_RAW_ADDC_DOT(20, 21, 22)), .regs = { .gpr[21] = LONG_MIN | (uint)INT_MIN, .gpr[22] = LONG_MIN | (uint)INT_MIN, } } } + }, + { + .mnemonic = "divde", + .subtests = { + { + .descr = "RA = LONG_MIN, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDE(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = 1L, RB = 0", + .instr = ppc_inst(PPC_RAW_DIVDE(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = 1L, + .gpr[22] = 0, + } + }, + { + .descr = "RA = LONG_MIN, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDE(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MAX, + } + } + } + }, + { + .mnemonic = "divde.", + .subtests = { + { + .descr = "RA = LONG_MIN, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDE_DOT(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = 1L, RB = 0", + .instr = ppc_inst(PPC_RAW_DIVDE_DOT(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = 1L, + .gpr[22] = 0, + } + }, + { + .descr = "RA = LONG_MIN, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDE_DOT(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MAX, + } + } + } + }, + { + .mnemonic = "divdeu", + .subtests = { + { + .descr = "RA = LONG_MIN, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDEU(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = 1L, RB = 0", + .instr = ppc_inst(PPC_RAW_DIVDEU(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = 1L, + .gpr[22] = 0, + } + }, + { + .descr = "RA = LONG_MIN, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDEU(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MAX, + } + }, + { + .descr = "RA = LONG_MAX - 1, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDEU(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MAX - 1, + .gpr[22] = LONG_MAX, + } + }, + { + .descr = "RA = LONG_MIN + 1, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDEU(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = LONG_MIN + 1, + .gpr[22] = LONG_MIN, + } + } + } + }, + { + .mnemonic = "divdeu.", + .subtests = { + { + .descr = "RA = LONG_MIN, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDEU_DOT(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = 1L, RB = 0", + .instr = ppc_inst(PPC_RAW_DIVDEU_DOT(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = 1L, + .gpr[22] = 0, + } + }, + { + .descr = "RA = LONG_MIN, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDEU_DOT(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MIN, + .gpr[22] = LONG_MAX, + } + }, + { + .descr = "RA = LONG_MAX - 1, RB = LONG_MAX", + .instr = ppc_inst(PPC_RAW_DIVDEU_DOT(20, 21, 22)), + .regs = { + .gpr[21] = LONG_MAX - 1, + .gpr[22] = LONG_MAX, + } + }, + { + .descr = "RA = LONG_MIN + 1, RB = LONG_MIN", + .instr = ppc_inst(PPC_RAW_DIVDEU_DOT(20, 21, 22)), + .flags = IGNORE_GPR(20), + .regs = { + .gpr[21] = LONG_MIN + 1, + .gpr[22] = LONG_MIN, + } + } + } + }, + { + .mnemonic = "paddi", + .cpu_feature = CPU_FTR_ARCH_31, + .subtests = { + { + .descr = "RA = LONG_MIN, SI = SI_MIN, R = 0", + .instr = TEST_PADDI(21, 22, SI_MIN, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = LONG_MIN, SI = SI_MAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_MAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = LONG_MIN, + } + }, + { + .descr = "RA = LONG_MAX, SI = SI_MAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_MAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = LONG_MAX, + } + }, + { + .descr = "RA = ULONG_MAX, SI = SI_UMAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_UMAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = ULONG_MAX, + } + }, + { + .descr = "RA = ULONG_MAX, SI = 0x1, R = 0", + .instr = TEST_PADDI(21, 22, 0x1, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = ULONG_MAX, + } + }, + { + .descr = "RA = INT_MIN, SI = SI_MIN, R = 0", + .instr = TEST_PADDI(21, 22, SI_MIN, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = INT_MIN, + } + }, + { + .descr = "RA = INT_MIN, SI = SI_MAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_MAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = INT_MIN, + } + }, + { + .descr = "RA = INT_MAX, SI = SI_MAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_MAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = INT_MAX, + } + }, + { + .descr = "RA = UINT_MAX, SI = 0x1, R = 0", + .instr = TEST_PADDI(21, 22, 0x1, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = UINT_MAX, + } + }, + { + .descr = "RA = UINT_MAX, SI = SI_MAX, R = 0", + .instr = TEST_PADDI(21, 22, SI_MAX, 0), + .regs = { + .gpr[21] = 0, + .gpr[22] = UINT_MAX, + } + }, + { + .descr = "RA is r0, SI = SI_MIN, R = 0", + .instr = TEST_PADDI(21, 0, SI_MIN, 0), + .regs = { + .gpr[21] = 0x0, + } + }, + { + .descr = "RA = 0, SI = SI_MIN, R = 0", + .instr = TEST_PADDI(21, 22, SI_MIN, 0), + .regs = { + .gpr[21] = 0x0, + .gpr[22] = 0x0, + } + }, + { + .descr = "RA is r0, SI = 0, R = 1", + .instr = TEST_PADDI(21, 0, 0, 1), + .regs = { + .gpr[21] = 0, + } + }, + { + .descr = "RA is r0, SI = SI_MIN, R = 1", + .instr = TEST_PADDI(21, 0, SI_MIN, 1), + .regs = { + .gpr[21] = 0, + } + }, + /* Invalid instruction form with R = 1 and RA != 0 */ + { + .descr = "RA = R22(0), SI = 0, R = 1", + .instr = TEST_PADDI(21, 22, 0, 1), + .flags = NEGATIVE_TEST, + .regs = { + .gpr[21] = 0, + .gpr[22] = 0, + } + } + } } }; static int __init emulate_compute_instr(struct pt_regs *regs, - struct ppc_inst instr) + struct ppc_inst instr, + bool negative) { + int analysed; struct instruction_op op; if (!regs || !ppc_inst_val(instr)) return -EINVAL; - if (analyse_instr(&op, regs, instr) != 1 || - GETTYPE(op.type) != COMPUTE) { - pr_info("emulation failed, instruction = 0x%08x\n", ppc_inst_val(instr)); + regs->nip = patch_site_addr(&patch__exec_instr); + + analysed = analyse_instr(&op, regs, instr); + if (analysed != 1 || GETTYPE(op.type) != COMPUTE) { + if (negative) + return -EFAULT; + pr_info("emulation failed, instruction = %s\n", ppc_inst_as_str(instr)); return -EFAULT; } - - emulate_update_regs(regs, &op); + if (analysed == 1 && negative) + pr_info("negative test failed, instruction = %s\n", ppc_inst_as_str(instr)); + if (!negative) + emulate_update_regs(regs, &op); return 0; } @@ -864,7 +1332,6 @@ static int __init execute_compute_instr(struct pt_regs *regs, struct ppc_inst instr) { extern int exec_instr(struct pt_regs *regs); - extern s32 patch__exec_instr; if (!regs || !ppc_inst_val(instr)) return -EINVAL; @@ -872,7 +1339,7 @@ static int __init execute_compute_instr(struct pt_regs *regs, /* Patch the NOP with the actual instruction */ patch_instruction_site(&patch__exec_instr, instr); if (exec_instr(regs)) { - pr_info("execution failed, instruction = 0x%08x\n", ppc_inst_val(instr)); + pr_info("execution failed, instruction = %s\n", ppc_inst_as_str(instr)); return -EFAULT; } @@ -894,15 +1361,21 @@ static void __init run_tests_compute(void) struct pt_regs *regs, exp, got; unsigned int i, j, k; struct ppc_inst instr; - bool ignore_gpr, ignore_xer, ignore_ccr, passed; + bool ignore_gpr, ignore_xer, ignore_ccr, passed, rc, negative; for (i = 0; i < ARRAY_SIZE(compute_tests); i++) { test = &compute_tests[i]; + if (test->cpu_feature && !early_cpu_has_feature(test->cpu_feature)) { + show_result(test->mnemonic, "SKIP (!CPU_FTR)"); + continue; + } + for (j = 0; j < MAX_SUBTESTS && test->subtests[j].descr; j++) { instr = test->subtests[j].instr; flags = test->subtests[j].flags; regs = &test->subtests[j].regs; + negative = flags & NEGATIVE_TEST; ignore_xer = flags & IGNORE_XER; ignore_ccr = flags & IGNORE_CCR; passed = true; @@ -917,8 +1390,12 @@ static void __init run_tests_compute(void) exp.msr = MSR_KERNEL; got.msr = MSR_KERNEL; - if (emulate_compute_instr(&got, instr) || - execute_compute_instr(&exp, instr)) { + rc = emulate_compute_instr(&got, instr, negative) != 0; + if (negative) { + /* skip executing instruction */ + passed = rc; + goto print; + } else if (rc || execute_compute_instr(&exp, instr)) { passed = false; goto print; } diff --git a/arch/powerpc/lib/test_emulate_step_exec_instr.S b/arch/powerpc/lib/test_emulate_step_exec_instr.S index 1580f34f4f4f..9ef941d958d8 100644 --- a/arch/powerpc/lib/test_emulate_step_exec_instr.S +++ b/arch/powerpc/lib/test_emulate_step_exec_instr.S @@ -80,7 +80,9 @@ _GLOBAL(exec_instr) REST_NVGPRS(r31) /* Placeholder for the test instruction */ + .balign 64 1: nop + nop patch_site 1b patch__exec_instr /* diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index 923ad8f374eb..1690d369688b 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -62,7 +62,7 @@ _GLOBAL(hash_page) isync #endif /* Get PTE (linux-style) and check access */ - lis r0,KERNELBASE@h /* check if kernel address */ + lis r0, TASK_SIZE@h /* check if kernel address */ cmplw 0,r4,r0 ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */ mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */ diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 03b6ba54460e..c0162911f6cb 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -187,6 +187,17 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return __mmu_mapin_ram(border, top); } +static bool is_module_segment(unsigned long addr) +{ + if (!IS_ENABLED(CONFIG_MODULES)) + return false; + if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M)) + return false; + if (addr >= ALIGN(VMALLOC_END, SZ_256M)) + return false; + return true; +} + void mmu_mark_initmem_nx(void) { int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; @@ -223,9 +234,9 @@ void mmu_mark_initmem_nx(void) for (i = TASK_SIZE >> 28; i < 16; i++) { /* Do not set NX on VM space for modules */ - if (IS_ENABLED(CONFIG_MODULES) && - (VMALLOC_START & 0xf0000000) == i << 28) - break; + if (is_module_segment(i << 28)) + continue; + mtsrin(mfsrin(i << 28) | 0x10000000, i << 28); } } diff --git a/arch/powerpc/mm/book3s64/hash_hugetlbpage.c b/arch/powerpc/mm/book3s64/hash_hugetlbpage.c index 25acb9c5ee1b..964467b3a776 100644 --- a/arch/powerpc/mm/book3s64/hash_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hash_hugetlbpage.c @@ -10,7 +10,6 @@ #include <linux/mm.h> #include <linux/hugetlb.h> -#include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/machdep.h> diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c index 2a99167afbaf..fd9c7f91b092 100644 --- a/arch/powerpc/mm/book3s64/hash_pgtable.c +++ b/arch/powerpc/mm/book3s64/hash_pgtable.c @@ -9,7 +9,6 @@ #include <linux/mm_types.h> #include <linux/mm.h> -#include <asm/pgalloc.h> #include <asm/sections.h> #include <asm/mmu.h> #include <asm/tlb.h> diff --git a/arch/powerpc/mm/book3s64/hash_tlb.c b/arch/powerpc/mm/book3s64/hash_tlb.c index 0fbf3dc9f2c2..eb0bccaf221e 100644 --- a/arch/powerpc/mm/book3s64/hash_tlb.c +++ b/arch/powerpc/mm/book3s64/hash_tlb.c @@ -21,7 +21,6 @@ #include <linux/mm.h> #include <linux/percpu.h> #include <linux/hardirq.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/bug.h> diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 9b9f92ad0e7a..1da9dbba9217 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -232,8 +232,6 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= HPTE_R_I; else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT) rflags |= (HPTE_R_I | HPTE_R_G); - else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO) - rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M); else /* * Add memory coherence if cache inhibited is not set @@ -596,7 +594,7 @@ static void __init htab_scan_page_sizes(void) } #ifdef CONFIG_HUGETLB_PAGE - if (!hugetlb_disabled) { + if (!hugetlb_disabled && !early_radix_enabled() ) { /* Reserve 16G huge page memory sections for huge pages */ of_scan_flat_dt(htab_dt_scan_hugepage_blocks, NULL); } @@ -663,11 +661,10 @@ static void __init htab_init_page_sizes(void) * Pick a size for the linear mapping. Currently, we only * support 16M, 1M and 4K which is the default */ - if (IS_ENABLED(STRICT_KERNEL_RWX) && + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && (unsigned long)_stext % 0x1000000) { if (mmu_psize_defs[MMU_PAGE_16M].shift) - pr_warn("Kernel not 16M aligned, " - "disabling 16M linear map alignment"); + pr_warn("Kernel not 16M aligned, disabling 16M linear map alignment\n"); aligned = false; } @@ -788,7 +785,7 @@ static unsigned long __init htab_get_table_size(void) } #ifdef CONFIG_MEMORY_HOTPLUG -int resize_hpt_for_hotplug(unsigned long new_mem_size) +static int resize_hpt_for_hotplug(unsigned long new_mem_size) { unsigned target_hpt_shift; @@ -822,6 +819,8 @@ int hash__create_section_mapping(unsigned long start, unsigned long end, return -1; } + resize_hpt_for_hotplug(memblock_phys_mem_size()); + rc = htab_bolt_mapping(start, end, __pa(start), pgprot_val(prot), mmu_linear_psize, mmu_kernel_ssize); @@ -839,6 +838,10 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end) int rc = htab_remove_mapping(start, end, mmu_linear_psize, mmu_kernel_ssize); WARN_ON(rc < 0); + + if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC) + pr_warn("Hash collision while resizing HPT\n"); + return rc; } #endif /* CONFIG_MEMORY_HOTPLUG */ @@ -1111,6 +1114,9 @@ void hash__early_init_mmu_secondary(void) if (cpu_has_feature(CPU_FTR_ARCH_206) && cpu_has_feature(CPU_FTR_HVMODE)) tlbiel_all(); + + if (IS_ENABLED(CONFIG_PPC_MEM_KEYS) && mmu_has_feature(MMU_FTR_PKEY)) + mtspr(SPRN_UAMOR, default_uamor); } #endif /* CONFIG_SMP */ @@ -1731,10 +1737,6 @@ unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift, return gslot; } -/* - * WARNING: This is called from hash_low_64.S, if you change this prototype, - * do not forget to update the assembly call site ! - */ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize, unsigned long flags) { diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index c58ad1049909..e18ae50a275c 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -15,6 +15,7 @@ #include <asm/powernv.h> #include <asm/firmware.h> #include <asm/ultravisor.h> +#include <asm/kexec.h> #include <mm/mmu_decl.h> #include <trace/events/thp.h> @@ -165,6 +166,8 @@ void mmu_cleanup_all(void) radix__mmu_cleanup_all(); else if (mmu_hash_ops.hpte_clear_all) mmu_hash_ops.hpte_clear_all(); + + reset_sprs(); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -339,6 +342,9 @@ void pmd_fragment_free(unsigned long *pmd) { struct page *page = virt_to_page(pmd); + if (PageReserved(page)) + return free_reserved_page(page); + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); if (atomic_dec_and_test(&page->pt_frag_refcount)) { pgtable_pmd_page_dtor(page); @@ -356,7 +362,7 @@ static inline void pgtable_free(void *table, int index) pmd_fragment_free(table); break; case PUD_INDEX: - kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table); + __pud_free(table); break; #if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE) /* 16M hugepd directory at pud level */ diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index d174106bab67..b1d091a97611 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -10,58 +10,97 @@ #include <asm/mmu.h> #include <asm/setup.h> #include <linux/pkeys.h> -#include <linux/of_device.h> +#include <linux/of_fdt.h> -DEFINE_STATIC_KEY_TRUE(pkey_disabled); -int pkeys_total; /* Total pkeys as per device tree */ -u32 initial_allocation_mask; /* Bits set for the initially allocated keys */ -u32 reserved_allocation_mask; /* Bits set for reserved keys */ -static bool pkey_execute_disable_supported; -static bool pkeys_devtree_defined; /* property exported by device tree */ -static u64 pkey_amr_mask; /* Bits in AMR not to be touched */ -static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ -static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ +int num_pkey; /* Max number of pkeys supported */ +/* + * Keys marked in the reservation list cannot be allocated by userspace + */ +u32 reserved_allocation_mask __ro_after_init; + +/* Bits set for the initially allocated keys */ +static u32 initial_allocation_mask __ro_after_init; + +/* + * Even if we allocate keys with sys_pkey_alloc(), we need to make sure + * other thread still find the access denied using the same keys. + */ +static u64 default_amr = ~0x0UL; +static u64 default_iamr = 0x5555555555555555UL; +u64 default_uamor __ro_after_init; +/* + * Key used to implement PROT_EXEC mmap. Denies READ/WRITE + * We pick key 2 because 0 is special key and 1 is reserved as per ISA. + */ static int execute_only_key = 2; +static bool pkey_execute_disable_supported; + #define AMR_BITS_PER_PKEY 2 #define AMR_RD_BIT 0x1UL #define AMR_WR_BIT 0x2UL #define IAMR_EX_BIT 0x1UL -#define PKEY_REG_BITS (sizeof(u64)*8) +#define PKEY_REG_BITS (sizeof(u64) * 8) #define pkeyshift(pkey) (PKEY_REG_BITS - ((pkey+1) * AMR_BITS_PER_PKEY)) -static void scan_pkey_feature(void) +static int __init dt_scan_storage_keys(unsigned long node, + const char *uname, int depth, + void *data) { - u32 vals[2]; - struct device_node *cpu; + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *prop; + int *pkeys_total = (int *) data; - cpu = of_find_node_by_type(NULL, "cpu"); - if (!cpu) - return; + /* We are scanning "cpu" nodes only */ + if (type == NULL || strcmp(type, "cpu") != 0) + return 0; - if (of_property_read_u32_array(cpu, - "ibm,processor-storage-keys", vals, 2)) - return; + prop = of_get_flat_dt_prop(node, "ibm,processor-storage-keys", NULL); + if (!prop) + return 0; + *pkeys_total = be32_to_cpu(prop[0]); + return 1; +} + +static int scan_pkey_feature(void) +{ + int ret; + int pkeys_total = 0; /* - * Since any pkey can be used for data or execute, we will just treat - * all keys as equal and track them as one entity. + * Pkey is not supported with Radix translation. */ - pkeys_total = vals[0]; - pkeys_devtree_defined = true; -} + if (early_radix_enabled()) + return 0; -static inline bool pkey_mmu_enabled(void) -{ - if (firmware_has_feature(FW_FEATURE_LPAR)) - return pkeys_total; - else - return cpu_has_feature(CPU_FTR_PKEY); + ret = of_scan_flat_dt(dt_scan_storage_keys, &pkeys_total); + if (ret == 0) { + /* + * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device + * tree. We make this exception since some version of skiboot forgot to + * expose this property on power8/9. + */ + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + unsigned long pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E || + PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9) + pkeys_total = 32; + } + } + + /* + * Adjust the upper limit, based on the number of bits supported by + * arch-neutral code. + */ + pkeys_total = min_t(int, pkeys_total, + ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) + 1)); + return pkeys_total; } -static int pkey_initialize(void) +void __init pkey_early_init_devtree(void) { - int os_reserved, i; + int pkeys_total, i; /* * We define PKEY_DISABLE_EXECUTE in addition to the arch-neutral @@ -79,32 +118,21 @@ static int pkey_initialize(void) __builtin_popcountl(ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT) != (sizeof(u64) * BITS_PER_BYTE)); - /* scan the device tree for pkey feature */ - scan_pkey_feature(); - /* - * Let's assume 32 pkeys on P8 bare metal, if its not defined by device - * tree. We make this exception since skiboot forgot to expose this - * property on power8. + * Only P7 and above supports SPRN_AMR update with MSR[PR] = 1 */ - if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) && - cpu_has_feature(CPU_FTRS_POWER8)) - pkeys_total = 32; + if (!early_cpu_has_feature(CPU_FTR_ARCH_206)) + return; - /* - * Adjust the upper limit, based on the number of bits supported by - * arch-neutral code. - */ - pkeys_total = min_t(int, pkeys_total, - ((ARCH_VM_PKEY_FLAGS >> VM_PKEY_SHIFT)+1)); + /* scan the device tree for pkey feature */ + pkeys_total = scan_pkey_feature(); + if (!pkeys_total) + goto out; - if (!pkey_mmu_enabled() || radix_enabled() || !pkeys_total) - static_branch_enable(&pkey_disabled); - else - static_branch_disable(&pkey_disabled); + /* Allow all keys to be modified by default */ + default_uamor = ~0x0UL; - if (static_branch_likely(&pkey_disabled)) - return 0; + cur_cpu_spec->mmu_features |= MMU_FTR_PKEY; /* * The device tree cannot be relied to indicate support for @@ -118,53 +146,86 @@ static int pkey_initialize(void) #ifdef CONFIG_PPC_4K_PAGES /* * The OS can manage only 8 pkeys due to its inability to represent them - * in the Linux 4K PTE. + * in the Linux 4K PTE. Mark all other keys reserved. */ - os_reserved = pkeys_total - 8; + num_pkey = min(8, pkeys_total); #else - os_reserved = 0; + num_pkey = pkeys_total; #endif - /* Bits are in LE format. */ - reserved_allocation_mask = (0x1 << 1) | (0x1 << execute_only_key); - - /* register mask is in BE format */ - pkey_amr_mask = ~0x0ul; - pkey_amr_mask &= ~(0x3ul << pkeyshift(0)); - - pkey_iamr_mask = ~0x0ul; - pkey_iamr_mask &= ~(0x3ul << pkeyshift(0)); - pkey_iamr_mask &= ~(0x3ul << pkeyshift(execute_only_key)); - - pkey_uamor_mask = ~0x0ul; - pkey_uamor_mask &= ~(0x3ul << pkeyshift(0)); - pkey_uamor_mask &= ~(0x3ul << pkeyshift(execute_only_key)); - - /* mark the rest of the keys as reserved and hence unavailable */ - for (i = (pkeys_total - os_reserved); i < pkeys_total; i++) { - reserved_allocation_mask |= (0x1 << i); - pkey_uamor_mask &= ~(0x3ul << pkeyshift(i)); - } - initial_allocation_mask = reserved_allocation_mask | (0x1 << 0); - if (unlikely((pkeys_total - os_reserved) <= execute_only_key)) { + if (unlikely(num_pkey <= execute_only_key) || !pkey_execute_disable_supported) { /* * Insufficient number of keys to support * execute only key. Mark it unavailable. - * Any AMR, UAMOR, IAMR bit set for - * this key is irrelevant since this key - * can never be allocated. */ execute_only_key = -1; + } else { + /* + * Mark the execute_only_pkey as not available for + * user allocation via pkey_alloc. + */ + reserved_allocation_mask |= (0x1 << execute_only_key); + + /* + * Deny READ/WRITE for execute_only_key. + * Allow execute in IAMR. + */ + default_amr |= (0x3ul << pkeyshift(execute_only_key)); + default_iamr &= ~(0x1ul << pkeyshift(execute_only_key)); + + /* + * Clear the uamor bits for this key. + */ + default_uamor &= ~(0x3ul << pkeyshift(execute_only_key)); } - return 0; -} + /* + * Allow access for only key 0. And prevent any other modification. + */ + default_amr &= ~(0x3ul << pkeyshift(0)); + default_iamr &= ~(0x1ul << pkeyshift(0)); + default_uamor &= ~(0x3ul << pkeyshift(0)); + /* + * key 0 is special in that we want to consider it an allocated + * key which is preallocated. We don't allow changing AMR bits + * w.r.t key 0. But one can pkey_free(key0) + */ + initial_allocation_mask |= (0x1 << 0); -arch_initcall(pkey_initialize); + /* + * key 1 is recommended not to be used. PowerISA(3.0) page 1015, + * programming note. + */ + reserved_allocation_mask |= (0x1 << 1); + default_uamor &= ~(0x3ul << pkeyshift(1)); + + /* + * Prevent the usage of OS reserved keys. Update UAMOR + * for those keys. Also mark the rest of the bits in the + * 32 bit mask as reserved. + */ + for (i = num_pkey; i < 32 ; i++) { + reserved_allocation_mask |= (0x1 << i); + default_uamor &= ~(0x3ul << pkeyshift(i)); + } + /* + * Prevent the allocation of reserved keys too. + */ + initial_allocation_mask |= reserved_allocation_mask; + + pr_info("Enabling pkeys with max key count %d\n", num_pkey); +out: + /* + * Setup uamor on boot cpu + */ + mtspr(SPRN_UAMOR, default_uamor); + + return; +} void pkey_mm_init(struct mm_struct *mm) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return; mm_pkey_allocation_map(mm) = initial_allocation_mask; mm->context.execute_only_pkey = execute_only_key; @@ -196,30 +257,6 @@ static inline void write_iamr(u64 value) mtspr(SPRN_IAMR, value); } -static inline u64 read_uamor(void) -{ - return mfspr(SPRN_UAMOR); -} - -static inline void write_uamor(u64 value) -{ - mtspr(SPRN_UAMOR, value); -} - -static bool is_pkey_enabled(int pkey) -{ - u64 uamor = read_uamor(); - u64 pkey_bits = 0x3ul << pkeyshift(pkey); - u64 uamor_pkey_bits = (uamor & pkey_bits); - - /* - * Both the bits in UAMOR corresponding to the key should be set or - * reset. - */ - WARN_ON(uamor_pkey_bits && (uamor_pkey_bits != pkey_bits)); - return !!(uamor_pkey_bits); -} - static inline void init_amr(int pkey, u8 init_bits) { u64 new_amr_bits = (((u64)init_bits & 0x3UL) << pkeyshift(pkey)); @@ -245,8 +282,18 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, { u64 new_amr_bits = 0x0ul; u64 new_iamr_bits = 0x0ul; + u64 pkey_bits, uamor_pkey_bits; - if (!is_pkey_enabled(pkey)) + /* + * Check whether the key is disabled by UAMOR. + */ + pkey_bits = 0x3ul << pkeyshift(pkey); + uamor_pkey_bits = (default_uamor & pkey_bits); + + /* + * Both the bits in UAMOR corresponding to the key should be set + */ + if (uamor_pkey_bits != pkey_bits) return -EINVAL; if (init_val & PKEY_DISABLE_EXECUTE) { @@ -268,7 +315,7 @@ int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey, void thread_pkey_regs_save(struct thread_struct *thread) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return; /* @@ -276,38 +323,33 @@ void thread_pkey_regs_save(struct thread_struct *thread) */ thread->amr = read_amr(); thread->iamr = read_iamr(); - thread->uamor = read_uamor(); } void thread_pkey_regs_restore(struct thread_struct *new_thread, struct thread_struct *old_thread) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return; if (old_thread->amr != new_thread->amr) write_amr(new_thread->amr); if (old_thread->iamr != new_thread->iamr) write_iamr(new_thread->iamr); - if (old_thread->uamor != new_thread->uamor) - write_uamor(new_thread->uamor); } void thread_pkey_regs_init(struct thread_struct *thread) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return; - thread->amr = pkey_amr_mask; - thread->iamr = pkey_iamr_mask; - thread->uamor = pkey_uamor_mask; + thread->amr = default_amr; + thread->iamr = default_iamr; - write_uamor(pkey_uamor_mask); - write_amr(pkey_amr_mask); - write_iamr(pkey_iamr_mask); + write_amr(default_amr); + write_iamr(default_iamr); } -int __execute_only_pkey(struct mm_struct *mm) +int execute_only_pkey(struct mm_struct *mm) { return mm->context.execute_only_pkey; } @@ -366,7 +408,7 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) bool arch_pte_access_permitted(u64 pte, bool write, bool execute) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return true; return pkey_access_permitted(pte_to_pkey_bits(pte), write, execute); @@ -383,7 +425,7 @@ bool arch_pte_access_permitted(u64 pte, bool write, bool execute) bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, bool execute, bool foreign) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return true; /* * Do not enforce our key-permissions on a foreign vma. @@ -396,7 +438,7 @@ bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write, void arch_dup_pkeys(struct mm_struct *oldmm, struct mm_struct *mm) { - if (static_branch_likely(&pkey_disabled)) + if (!mmu_has_feature(MMU_FTR_PKEY)) return; /* Duplicate the oldmm pkey state in mm: */ diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c index c812b401b66c..cb91071eef52 100644 --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c @@ -2,7 +2,6 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/security.h> -#include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/machdep.h> #include <asm/mman.h> diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index bb00e0cba119..28c784976bed 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -15,7 +15,7 @@ #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/string_helpers.h> -#include <linux/stop_machine.h> +#include <linux/memory.h> #include <asm/pgalloc.h> #include <asm/mmu_context.h> @@ -34,6 +34,7 @@ unsigned int mmu_pid_bits; unsigned int mmu_base_pid; +unsigned int radix_mem_block_size __ro_after_init; static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) @@ -56,6 +57,13 @@ static __ref void *early_alloc_pgtable(unsigned long size, int nid, return ptr; } +/* + * When allocating pud or pmd pointers, we allocate a complete page + * of PAGE_SIZE rather than PUD_TABLE_SIZE or PMD_TABLE_SIZE. This + * is to ensure that the page obtained from the memblock allocator + * can be completely used as page table page and can be freed + * correctly when the page table entries are removed. + */ static int early_map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t flags, unsigned int map_page_size, @@ -72,8 +80,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa, pgdp = pgd_offset_k(ea); p4dp = p4d_offset(pgdp, ea); if (p4d_none(*p4dp)) { - pudp = early_alloc_pgtable(PUD_TABLE_SIZE, nid, - region_start, region_end); + pudp = early_alloc_pgtable(PAGE_SIZE, nid, + region_start, region_end); p4d_populate(&init_mm, p4dp, pudp); } pudp = pud_offset(p4dp, ea); @@ -82,8 +90,8 @@ static int early_map_kernel_page(unsigned long ea, unsigned long pa, goto set_the_pte; } if (pud_none(*pudp)) { - pmdp = early_alloc_pgtable(PMD_TABLE_SIZE, nid, - region_start, region_end); + pmdp = early_alloc_pgtable(PAGE_SIZE, nid, region_start, + region_end); pud_populate(&init_mm, pudp, pmdp); } pmdp = pmd_offset(pudp, ea); @@ -259,6 +267,7 @@ static unsigned long next_boundary(unsigned long addr, unsigned long end) static int __meminit create_physical_mapping(unsigned long start, unsigned long end, + unsigned long max_mapping_size, int nid, pgprot_t _prot) { unsigned long vaddr, addr, mapping_size = 0; @@ -272,6 +281,8 @@ static int __meminit create_physical_mapping(unsigned long start, int rc; gap = next_boundary(addr, end) - addr; + if (gap > max_mapping_size) + gap = max_mapping_size; previous_size = mapping_size; prev_exec = exec; @@ -322,8 +333,9 @@ static void __init radix_init_pgtable(void) /* We don't support slb for radix */ mmu_slb_size = 0; + /* - * Create the linear mapping, using standard page size for now + * Create the linear mapping */ for_each_memblock(memory, reg) { /* @@ -339,6 +351,7 @@ static void __init radix_init_pgtable(void) WARN_ON(create_physical_mapping(reg->base, reg->base + reg->size, + radix_mem_block_size, -1, PAGE_KERNEL)); } @@ -479,6 +492,57 @@ static int __init radix_dt_scan_page_sizes(unsigned long node, return 1; } +#ifdef CONFIG_MEMORY_HOTPLUG +static int __init probe_memory_block_size(unsigned long node, const char *uname, int + depth, void *data) +{ + unsigned long *mem_block_size = (unsigned long *)data; + const __be64 *prop; + int len; + + if (depth != 1) + return 0; + + if (strcmp(uname, "ibm,dynamic-reconfiguration-memory")) + return 0; + + prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); + if (!prop || len < sizeof(__be64)) + /* + * Nothing in the device tree + */ + *mem_block_size = MIN_MEMORY_BLOCK_SIZE; + else + *mem_block_size = be64_to_cpup(prop); + return 1; +} + +static unsigned long radix_memory_block_size(void) +{ + unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE; + + /* + * OPAL firmware feature is set by now. Hence we are ok + * to test OPAL feature. + */ + if (firmware_has_feature(FW_FEATURE_OPAL)) + mem_block_size = 1UL * 1024 * 1024 * 1024; + else + of_scan_flat_dt(probe_memory_block_size, &mem_block_size); + + return mem_block_size; +} + +#else /* CONFIG_MEMORY_HOTPLUG */ + +static unsigned long radix_memory_block_size(void) +{ + return 1UL * 1024 * 1024 * 1024; +} + +#endif /* CONFIG_MEMORY_HOTPLUG */ + + void __init radix__early_init_devtree(void) { int rc; @@ -487,17 +551,27 @@ void __init radix__early_init_devtree(void) * Try to find the available page sizes in the device-tree */ rc = of_scan_flat_dt(radix_dt_scan_page_sizes, NULL); - if (rc != 0) /* Found */ - goto found; + if (!rc) { + /* + * No page size details found in device tree. + * Let's assume we have page 4k and 64k support + */ + mmu_psize_defs[MMU_PAGE_4K].shift = 12; + mmu_psize_defs[MMU_PAGE_4K].ap = 0x0; + + mmu_psize_defs[MMU_PAGE_64K].shift = 16; + mmu_psize_defs[MMU_PAGE_64K].ap = 0x5; + } + /* - * let's assume we have page 4k and 64k support + * Max mapping size used when mapping pages. We don't use + * ppc_md.memory_block_size() here because this get called + * early and we don't have machine probe called yet. Also + * the pseries implementation only check for ibm,lmb-size. + * All hypervisor supporting radix do expose that device + * tree node. */ - mmu_psize_defs[MMU_PAGE_4K].shift = 12; - mmu_psize_defs[MMU_PAGE_4K].ap = 0x0; - - mmu_psize_defs[MMU_PAGE_64K].shift = 16; - mmu_psize_defs[MMU_PAGE_64K].ap = 0x5; -found: + radix_mem_block_size = radix_memory_block_size(); return; } @@ -519,8 +593,10 @@ void setup_kuep(bool disabled) if (disabled || !early_radix_enabled()) return; - if (smp_processor_id() == boot_cpuid) + if (smp_processor_id() == boot_cpuid) { pr_info("Activating Kernel Userspace Execution Prevention\n"); + cur_cpu_spec->mmu_features |= MMU_FTR_KUEP; + } /* * Radix always uses key0 of the IAMR to determine if an access is @@ -544,6 +620,10 @@ void setup_kuap(bool disabled) /* Make sure userspace can't change the AMR */ mtspr(SPRN_UAMOR, 0); + + /* + * Set the default kernel AMR values on all cpus. + */ mtspr(SPRN_AMR, AMR_KUAP_BLOCKED); isync(); } @@ -700,30 +780,19 @@ static void free_pmd_table(pmd_t *pmd_start, pud_t *pud) pud_clear(pud); } -struct change_mapping_params { - pte_t *pte; - unsigned long start; - unsigned long end; - unsigned long aligned_start; - unsigned long aligned_end; -}; - -static int __meminit stop_machine_change_mapping(void *data) +static void free_pud_table(pud_t *pud_start, p4d_t *p4d) { - struct change_mapping_params *params = - (struct change_mapping_params *)data; + pud_t *pud; + int i; - if (!data) - return -1; + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } - spin_unlock(&init_mm.page_table_lock); - pte_clear(&init_mm, params->aligned_start, params->pte); - create_physical_mapping(__pa(params->aligned_start), - __pa(params->start), -1, PAGE_KERNEL); - create_physical_mapping(__pa(params->end), __pa(params->aligned_end), - -1, PAGE_KERNEL); - spin_lock(&init_mm.page_table_lock); - return 0; + pud_free(&init_mm, pud_start); + p4d_clear(p4d); } static void remove_pte_table(pte_t *pte_start, unsigned long addr, @@ -754,53 +823,7 @@ static void remove_pte_table(pte_t *pte_start, unsigned long addr, } } -/* - * clear the pte and potentially split the mapping helper - */ -static void __meminit split_kernel_mapping(unsigned long addr, unsigned long end, - unsigned long size, pte_t *pte) -{ - unsigned long mask = ~(size - 1); - unsigned long aligned_start = addr & mask; - unsigned long aligned_end = addr + size; - struct change_mapping_params params; - bool split_region = false; - - if ((end - addr) < size) { - /* - * We're going to clear the PTE, but not flushed - * the mapping, time to remap and flush. The - * effects if visible outside the processor or - * if we are running in code close to the - * mapping we cleared, we are in trouble. - */ - if (overlaps_kernel_text(aligned_start, addr) || - overlaps_kernel_text(end, aligned_end)) { - /* - * Hack, just return, don't pte_clear - */ - WARN_ONCE(1, "Linear mapping %lx->%lx overlaps kernel " - "text, not splitting\n", addr, end); - return; - } - split_region = true; - } - - if (split_region) { - params.pte = pte; - params.start = addr; - params.end = end; - params.aligned_start = addr & ~(size - 1); - params.aligned_end = min_t(unsigned long, aligned_end, - (unsigned long)__va(memblock_end_of_DRAM())); - stop_machine(stop_machine_change_mapping, ¶ms, NULL); - return; - } - - pte_clear(&init_mm, addr, pte); -} - -static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, +static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end) { unsigned long next; @@ -815,7 +838,12 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, continue; if (pmd_is_leaf(*pmd)) { - split_kernel_mapping(addr, end, PMD_SIZE, (pte_t *)pmd); + if (!IS_ALIGNED(addr, PMD_SIZE) || + !IS_ALIGNED(next, PMD_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, (pte_t *)pmd); continue; } @@ -825,7 +853,7 @@ static void remove_pmd_table(pmd_t *pmd_start, unsigned long addr, } } -static void remove_pud_table(pud_t *pud_start, unsigned long addr, +static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end) { unsigned long next; @@ -840,7 +868,12 @@ static void remove_pud_table(pud_t *pud_start, unsigned long addr, continue; if (pud_is_leaf(*pud)) { - split_kernel_mapping(addr, end, PUD_SIZE, (pte_t *)pud); + if (!IS_ALIGNED(addr, PUD_SIZE) || + !IS_ALIGNED(next, PUD_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + pte_clear(&init_mm, addr, (pte_t *)pud); continue; } @@ -868,12 +901,19 @@ static void __meminit remove_pagetable(unsigned long start, unsigned long end) continue; if (p4d_is_leaf(*p4d)) { - split_kernel_mapping(addr, end, P4D_SIZE, (pte_t *)p4d); + if (!IS_ALIGNED(addr, P4D_SIZE) || + !IS_ALIGNED(next, P4D_SIZE)) { + WARN_ONCE(1, "%s: unaligned range\n", __func__); + continue; + } + + pte_clear(&init_mm, addr, (pte_t *)pgd); continue; } pud_base = (pud_t *)p4d_page_vaddr(*p4d); remove_pud_table(pud_base, addr, next); + free_pud_table(pud_base, p4d); } spin_unlock(&init_mm.page_table_lock); @@ -889,7 +929,8 @@ int __meminit radix__create_section_mapping(unsigned long start, return -1; } - return create_physical_mapping(__pa(start), __pa(end), nid, prot); + return create_physical_mapping(__pa(start), __pa(end), + radix_mem_block_size, nid, prot); } int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end) diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index b5cc9b23cf02..0d233763441f 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -16,6 +16,7 @@ #include <asm/tlbflush.h> #include <asm/trace.h> #include <asm/cputhreads.h> +#include <asm/plpar_wrappers.h> #define RIC_FLUSH_TLB 0 #define RIC_FLUSH_PWC 1 @@ -694,7 +695,14 @@ void radix__flush_tlb_mm(struct mm_struct *mm) goto local; } - if (cputlb_use_tlbie()) { + if (!mmu_has_feature(MMU_FTR_GTSE)) { + unsigned long tgt = H_RPTI_TARGET_CMMU; + + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, + H_RPTI_PAGE_ALL, 0, -1UL); + } else if (cputlb_use_tlbie()) { if (mm_needs_flush_escalation(mm)) _tlbie_pid(pid, RIC_FLUSH_ALL); else @@ -727,7 +735,16 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm) goto local; } } - if (cputlb_use_tlbie()) + if (!mmu_has_feature(MMU_FTR_GTSE)) { + unsigned long tgt = H_RPTI_TARGET_CMMU; + unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | + H_RPTI_TYPE_PRT; + + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, type, + H_RPTI_PAGE_ALL, 0, -1UL); + } else if (cputlb_use_tlbie()) _tlbie_pid(pid, RIC_FLUSH_ALL); else _tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL); @@ -760,7 +777,19 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr, exit_flush_lazy_tlbs(mm); goto local; } - if (cputlb_use_tlbie()) + if (!mmu_has_feature(MMU_FTR_GTSE)) { + unsigned long tgt, pg_sizes, size; + + tgt = H_RPTI_TARGET_CMMU; + pg_sizes = psize_to_rpti_pgsize(psize); + size = 1UL << mmu_psize_to_shift(psize); + + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, + pg_sizes, vmaddr, + vmaddr + size); + } else if (cputlb_use_tlbie()) _tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB); else _tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB); @@ -810,7 +839,14 @@ static inline void _tlbiel_kernel_broadcast(void) */ void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end) { - if (cputlb_use_tlbie()) + if (!mmu_has_feature(MMU_FTR_GTSE)) { + unsigned long tgt = H_RPTI_TARGET_CMMU | H_RPTI_TARGET_NMMU; + unsigned long type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | + H_RPTI_TYPE_PRT; + + pseries_rpt_invalidate(0, tgt, type, H_RPTI_PAGE_ALL, + start, end); + } else if (cputlb_use_tlbie()) _tlbie_pid(0, RIC_FLUSH_ALL); else _tlbiel_kernel_broadcast(); @@ -864,7 +900,17 @@ is_local: nr_pages > tlb_local_single_page_flush_ceiling); } - if (full) { + if (!mmu_has_feature(MMU_FTR_GTSE) && !local) { + unsigned long tgt = H_RPTI_TARGET_CMMU; + unsigned long pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize); + + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + pg_sizes |= psize_to_rpti_pgsize(MMU_PAGE_2M); + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, H_RPTI_TYPE_TLB, pg_sizes, + start, end); + } else if (full) { if (local) { _tlbiel_pid(pid, RIC_FLUSH_TLB); } else { @@ -1046,7 +1092,17 @@ is_local: nr_pages > tlb_local_single_page_flush_ceiling); } - if (full) { + if (!mmu_has_feature(MMU_FTR_GTSE) && !local) { + unsigned long tgt = H_RPTI_TARGET_CMMU; + unsigned long type = H_RPTI_TYPE_TLB; + unsigned long pg_sizes = psize_to_rpti_pgsize(psize); + + if (also_pwc) + type |= H_RPTI_TYPE_PWC; + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, type, pg_sizes, start, end); + } else if (full) { if (local) { _tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB); } else { @@ -1111,7 +1167,19 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr) exit_flush_lazy_tlbs(mm); goto local; } - if (cputlb_use_tlbie()) + if (!mmu_has_feature(MMU_FTR_GTSE)) { + unsigned long tgt, type, pg_sizes; + + tgt = H_RPTI_TARGET_CMMU; + type = H_RPTI_TYPE_TLB | H_RPTI_TYPE_PWC | + H_RPTI_TYPE_PRT; + pg_sizes = psize_to_rpti_pgsize(mmu_virtual_psize); + + if (atomic_read(&mm->context.copros) > 0) + tgt |= H_RPTI_TARGET_NMMU; + pseries_rpt_invalidate(pid, tgt, type, pg_sizes, + addr, end); + } else if (cputlb_use_tlbie()) _tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true); else _tlbiel_va_range_multicast(mm, diff --git a/arch/powerpc/mm/copro_fault.c b/arch/powerpc/mm/copro_fault.c index b83abbead4a2..8acd00178956 100644 --- a/arch/powerpc/mm/copro_fault.c +++ b/arch/powerpc/mm/copro_fault.c @@ -64,7 +64,7 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, } ret = 0; - *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0); + *flt = handle_mm_fault(vma, ea, is_write ? FAULT_FLAG_WRITE : 0, NULL); if (unlikely(*flt & VM_FAULT_ERROR)) { if (*flt & VM_FAULT_OOM) { ret = -ENOMEM; @@ -76,11 +76,6 @@ int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea, BUG(); } - if (*flt & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; - out_unlock: mmap_read_unlock(mm); return ret; diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 59327cefbc6a..b2eeea39684c 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -14,6 +14,8 @@ #include <asm/prom.h> #include <asm/drmem.h> +static int n_root_addr_cells, n_root_size_cells; + static struct drmem_lmb_info __drmem_info; struct drmem_lmb_info *drmem_info = &__drmem_info; @@ -189,12 +191,13 @@ int drmem_update_dt(void) return rc; } -static void __init read_drconf_v1_cell(struct drmem_lmb *lmb, +static void read_drconf_v1_cell(struct drmem_lmb *lmb, const __be32 **prop) { const __be32 *p = *prop; - lmb->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p); + lmb->base_addr = of_read_number(p, n_root_addr_cells); + p += n_root_addr_cells; lmb->drc_index = of_read_number(p++, 1); p++; /* skip reserved field */ @@ -205,29 +208,33 @@ static void __init read_drconf_v1_cell(struct drmem_lmb *lmb, *prop = p; } -static void __init __walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, - void (*func)(struct drmem_lmb *, const __be32 **)) +static int +__walk_drmem_v1_lmbs(const __be32 *prop, const __be32 *usm, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)) { struct drmem_lmb lmb; u32 i, n_lmbs; + int ret = 0; n_lmbs = of_read_number(prop++, 1); - if (n_lmbs == 0) - return; - for (i = 0; i < n_lmbs; i++) { read_drconf_v1_cell(&lmb, &prop); - func(&lmb, &usm); + ret = func(&lmb, &usm, data); + if (ret) + break; } + + return ret; } -static void __init read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell, +static void read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell, const __be32 **prop) { const __be32 *p = *prop; dr_cell->seq_lmbs = of_read_number(p++, 1); - dr_cell->base_addr = dt_mem_next_cell(dt_root_addr_cells, &p); + dr_cell->base_addr = of_read_number(p, n_root_addr_cells); + p += n_root_addr_cells; dr_cell->drc_index = of_read_number(p++, 1); dr_cell->aa_index = of_read_number(p++, 1); dr_cell->flags = of_read_number(p++, 1); @@ -235,17 +242,16 @@ static void __init read_drconf_v2_cell(struct of_drconf_cell_v2 *dr_cell, *prop = p; } -static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, - void (*func)(struct drmem_lmb *, const __be32 **)) +static int +__walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)) { struct of_drconf_cell_v2 dr_cell; struct drmem_lmb lmb; u32 i, j, lmb_sets; + int ret = 0; lmb_sets = of_read_number(prop++, 1); - if (lmb_sets == 0) - return; - for (i = 0; i < lmb_sets; i++) { read_drconf_v2_cell(&dr_cell, &prop); @@ -259,21 +265,29 @@ static void __init __walk_drmem_v2_lmbs(const __be32 *prop, const __be32 *usm, lmb.aa_index = dr_cell.aa_index; lmb.flags = dr_cell.flags; - func(&lmb, &usm); + ret = func(&lmb, &usm, data); + if (ret) + break; } } + + return ret; } #ifdef CONFIG_PPC_PSERIES -void __init walk_drmem_lmbs_early(unsigned long node, - void (*func)(struct drmem_lmb *, const __be32 **)) +int __init walk_drmem_lmbs_early(unsigned long node, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)) { const __be32 *prop, *usm; - int len; + int len, ret = -ENODEV; prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); if (!prop || len < dt_root_size_cells * sizeof(__be32)) - return; + return ret; + + /* Get the address & size cells */ + n_root_addr_cells = dt_root_addr_cells; + n_root_size_cells = dt_root_size_cells; drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop); @@ -281,20 +295,21 @@ void __init walk_drmem_lmbs_early(unsigned long node, prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory", &len); if (prop) { - __walk_drmem_v1_lmbs(prop, usm, func); + ret = __walk_drmem_v1_lmbs(prop, usm, data, func); } else { prop = of_get_flat_dt_prop(node, "ibm,dynamic-memory-v2", &len); if (prop) - __walk_drmem_v2_lmbs(prop, usm, func); + ret = __walk_drmem_v2_lmbs(prop, usm, data, func); } memblock_dump_all(); + return ret; } #endif -static int __init init_drmem_lmb_size(struct device_node *dn) +static int init_drmem_lmb_size(struct device_node *dn) { const __be32 *prop; int len; @@ -303,12 +318,12 @@ static int __init init_drmem_lmb_size(struct device_node *dn) return 0; prop = of_get_property(dn, "ibm,lmb-size", &len); - if (!prop || len < dt_root_size_cells * sizeof(__be32)) { + if (!prop || len < n_root_size_cells * sizeof(__be32)) { pr_info("Could not determine LMB size\n"); return -1; } - drmem_info->lmb_size = dt_mem_next_cell(dt_root_size_cells, &prop); + drmem_info->lmb_size = of_read_number(prop, n_root_size_cells); return 0; } @@ -329,24 +344,36 @@ static const __be32 *of_get_usable_memory(struct device_node *dn) return prop; } -void __init walk_drmem_lmbs(struct device_node *dn, - void (*func)(struct drmem_lmb *, const __be32 **)) +int walk_drmem_lmbs(struct device_node *dn, void *data, + int (*func)(struct drmem_lmb *, const __be32 **, void *)) { const __be32 *prop, *usm; + int ret = -ENODEV; + + if (!of_root) + return ret; + + /* Get the address & size cells */ + of_node_get(of_root); + n_root_addr_cells = of_n_addr_cells(of_root); + n_root_size_cells = of_n_size_cells(of_root); + of_node_put(of_root); if (init_drmem_lmb_size(dn)) - return; + return ret; usm = of_get_usable_memory(dn); prop = of_get_property(dn, "ibm,dynamic-memory", NULL); if (prop) { - __walk_drmem_v1_lmbs(prop, usm, func); + ret = __walk_drmem_v1_lmbs(prop, usm, data, func); } else { prop = of_get_property(dn, "ibm,dynamic-memory-v2", NULL); if (prop) - __walk_drmem_v2_lmbs(prop, usm, func); + ret = __walk_drmem_v2_lmbs(prop, usm, data, func); } + + return ret; } static void __init init_drmem_v1_lmbs(const __be32 *prop) diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 641fc5f3d7dd..0add963a849b 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -42,39 +42,7 @@ #include <asm/kup.h> #include <asm/inst.h> -/* - * Check whether the instruction inst is a store using - * an update addressing form which will update r1. - */ -static bool store_updates_sp(struct ppc_inst inst) -{ - /* check for 1 in the rA field */ - if (((ppc_inst_val(inst) >> 16) & 0x1f) != 1) - return false; - /* check major opcode */ - switch (ppc_inst_primary_opcode(inst)) { - case OP_STWU: - case OP_STBU: - case OP_STHU: - case OP_STFSU: - case OP_STFDU: - return true; - case OP_STD: /* std or stdu */ - return (ppc_inst_val(inst) & 3) == 1; - case OP_31: - /* check minor opcode */ - switch ((ppc_inst_val(inst) >> 1) & 0x3ff) { - case OP_31_XOP_STDUX: - case OP_31_XOP_STWUX: - case OP_31_XOP_STBUX: - case OP_31_XOP_STHUX: - case OP_31_XOP_STFSUX: - case OP_31_XOP_STFDUX: - return true; - } - } - return false; -} + /* * do_page_fault error handling helpers */ @@ -267,54 +235,6 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, return false; } -static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, - struct vm_area_struct *vma, unsigned int flags, - bool *must_retry) -{ - /* - * N.B. The POWER/Open ABI allows programs to access up to - * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB - * below the stack pointer (r1) before decrementing it. - * The exec code can write slightly over 640kB to the stack - * before setting the user r1. Thus we allow the stack to - * expand to 1MB without further checks. - */ - if (address + 0x100000 < vma->vm_end) { - struct ppc_inst __user *nip = (struct ppc_inst __user *)regs->nip; - /* get user regs even if this fault is in kernel mode */ - struct pt_regs *uregs = current->thread.regs; - if (uregs == NULL) - return true; - - /* - * A user-mode access to an address a long way below - * the stack pointer is only valid if the instruction - * is one which would update the stack pointer to the - * address accessed if the instruction completed, - * i.e. either stwu rs,n(r1) or stwux rs,r1,rb - * (or the byte, halfword, float or double forms). - * - * If we don't check this then any write to the area - * between the last mapped region and the stack will - * expand the stack rather than segfaulting. - */ - if (address + 2048 >= uregs->gpr[1]) - return false; - - if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && - access_ok(nip, sizeof(*nip))) { - struct ppc_inst inst; - - if (!probe_user_read_inst(&inst, nip)) - return !store_updates_sp(inst); - *must_retry = true; - } - return true; - } - return false; -} - #ifdef CONFIG_PPC_MEM_KEYS static bool access_pkey_error(bool is_write, bool is_exec, bool is_pkey, struct vm_area_struct *vma) @@ -480,7 +400,6 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address, int is_user = user_mode(regs); int is_write = page_fault_is_write(error_code); vm_fault_t fault, major = 0; - bool must_retry = false; bool kprobe_fault = kprobe_page_fault(regs, 11); if (unlikely(debugger_fault_handler(regs) || kprobe_fault)) @@ -569,30 +488,15 @@ retry: vma = find_vma(mm, address); if (unlikely(!vma)) return bad_area(regs, address); - if (likely(vma->vm_start <= address)) - goto good_area; - if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) - return bad_area(regs, address); - /* The stack is being expanded, check if it's valid */ - if (unlikely(bad_stack_expansion(regs, address, vma, flags, - &must_retry))) { - if (!must_retry) + if (unlikely(vma->vm_start > address)) { + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) return bad_area(regs, address); - mmap_read_unlock(mm); - if (fault_in_pages_readable((const char __user *)regs->nip, - sizeof(unsigned int))) - return bad_area_nosemaphore(regs, address); - goto retry; + if (unlikely(expand_stack(vma, address))) + return bad_area(regs, address); } - /* Try to expand it */ - if (unlikely(expand_stack(vma, address))) - return bad_area(regs, address); - -good_area: - #ifdef CONFIG_PPC_MEM_KEYS if (unlikely(access_pkey_error(is_write, is_exec, (error_code & DSISR_KEYFAULT), vma))) @@ -607,7 +511,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); major |= fault & VM_FAULT_MAJOR; @@ -633,14 +537,9 @@ good_area: /* * Major/minor page fault accounting. */ - if (major) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); + if (major) cmo_account_page_fault(); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } + return 0; } NOKPROBE_SYMBOL(__do_page_fault); diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index e9bfbccd975d..26292544630f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -684,3 +684,21 @@ void flush_dcache_icache_hugepage(struct page *page) } } } + +void __init gigantic_hugetlb_cma_reserve(void) +{ + unsigned long order = 0; + + if (radix_enabled()) + order = PUD_SHIFT - PAGE_SHIFT; + else if (!firmware_has_feature(FW_FEATURE_LPAR) && mmu_psize_defs[MMU_PAGE_16G].shift) + /* + * For pseries we do use ibm,expected#pages for reserving 16G pages. + */ + order = mmu_psize_to_shift(MMU_PAGE_16G) - PAGE_SHIFT; + + if (order) { + VM_WARN_ON(order < MAX_ORDER); + hugetlb_cma_reserve(order); + } +} diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 5a5469eb3174..02c7db4087cb 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -29,7 +29,6 @@ #include <linux/slab.h> #include <linux/hugetlb.h> -#include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/io.h> #include <asm/mmu.h> @@ -171,6 +170,8 @@ void __init MMU_init(void) btext_unmap(); #endif + kasan_mmu_init(); + setup_kup(); /* Shortly after that, the entire linear mapping will be available */ diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index bc73abf0bc25..02e127fa5777 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -225,12 +225,12 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, * fall back to system memory if the altmap allocation fail. */ if (altmap && !altmap_cross_boundary(altmap, start, page_size)) { - p = altmap_alloc_block_buf(page_size, altmap); + p = vmemmap_alloc_block_buf(page_size, node, altmap); if (!p) pr_debug("altmap block allocation failed, falling back to system memory"); } if (!p) - p = vmemmap_alloc_block_buf(page_size, node); + p = vmemmap_alloc_block_buf(page_size, node, NULL); if (!p) return -ENOMEM; @@ -406,13 +406,15 @@ static void __init early_check_vec5(void) } if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] & OV5_FEAT(OV5_RADIX_GTSE))) { - pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n"); - } + cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE; + } else + cur_cpu_spec->mmu_features |= MMU_FTR_GTSE; /* Do radix anyway - the hypervisor said we had to */ cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; } else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) { /* Hypervisor only supports hash - disable radix */ cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX; + cur_cpu_spec->mmu_features &= ~MMU_FTR_GTSE; } } diff --git a/arch/powerpc/mm/kasan/8xx.c b/arch/powerpc/mm/kasan/8xx.c index 569d98a41881..2784224054f8 100644 --- a/arch/powerpc/mm/kasan/8xx.c +++ b/arch/powerpc/mm/kasan/8xx.c @@ -5,7 +5,6 @@ #include <linux/kasan.h> #include <linux/memblock.h> #include <linux/hugetlb.h> -#include <asm/pgalloc.h> static int __init kasan_init_shadow_8M(unsigned long k_start, unsigned long k_end, void *block) diff --git a/arch/powerpc/mm/kasan/book3s_32.c b/arch/powerpc/mm/kasan/book3s_32.c index a32b4640b9de..202bd260a009 100644 --- a/arch/powerpc/mm/kasan/book3s_32.c +++ b/arch/powerpc/mm/kasan/book3s_32.c @@ -4,7 +4,6 @@ #include <linux/kasan.h> #include <linux/memblock.h> -#include <asm/pgalloc.h> #include <mm/mmu_decl.h> int __init kasan_init_region(void *start, size_t size) diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 0760e1e754e4..fb294046e00e 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -115,16 +115,35 @@ static void __init kasan_unmap_early_shadow_vmalloc(void) unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END); kasan_update_early_region(k_start, k_end, __pte(0)); + +#ifdef MODULES_VADDR + k_start = (unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR); + k_end = (unsigned long)kasan_mem_to_shadow((void *)MODULES_END); + kasan_update_early_region(k_start, k_end, __pte(0)); +#endif } -static void __init kasan_mmu_init(void) +void __init kasan_mmu_init(void) { int ret; + + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || + IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } +} + +void __init kasan_init(void) +{ struct memblock_region *reg; for_each_memblock(memory, reg) { phys_addr_t base = reg->base; phys_addr_t top = min(base + reg->size, total_lowmem); + int ret; if (base >= top) continue; @@ -134,20 +153,6 @@ static void __init kasan_mmu_init(void) panic("kasan: kasan_init_region() failed"); } - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || - IS_ENABLED(CONFIG_KASAN_VMALLOC)) { - ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); - - if (ret) - panic("kasan: kasan_init_shadow_page_tables() failed"); - } - -} - -void __init kasan_init(void) -{ - kasan_mmu_init(); - kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c2c11eb8dcfc..42e25874f5a8 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -34,7 +34,6 @@ #include <linux/dma-direct.h> #include <linux/kprobes.h> -#include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/io.h> #include <asm/mmu_context.h> @@ -127,8 +126,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, unsigned long nr_pages = size >> PAGE_SHIFT; int rc; - resize_hpt_for_hotplug(memblock_phys_mem_size()); - start = (unsigned long)__va(start); rc = create_section_mapping(start, start + size, nid, params->pgprot); @@ -161,9 +158,6 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, * hit that section of memory */ vm_unmap_aliases(); - - if (resize_hpt_for_hotplug(memblock_phys_mem_size()) == -ENOSPC) - pr_warn("Hash collision while resizing HPT\n"); } #endif @@ -184,8 +178,6 @@ void __init mem_topology_setup(void) void __init initmem_init(void) { - /* XXX need to clip this if using highmem? */ - sparse_memory_present_with_active_regions(0); sparse_init(); } diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c index 13e74bc39ba5..95751c322f6c 100644 --- a/arch/powerpc/mm/nohash/40x.c +++ b/arch/powerpc/mm/nohash/40x.c @@ -32,7 +32,6 @@ #include <linux/highmem.h> #include <linux/memblock.h> -#include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/io.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index 92e8929cbe3e..d2b37146ae6c 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -13,7 +13,6 @@ #include <asm/fixmap.h> #include <asm/code-patching.h> #include <asm/inst.h> -#include <asm/pgalloc.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_booke.c index c06dfbb771f4..0c294827d6e5 100644 --- a/arch/powerpc/mm/nohash/fsl_booke.c +++ b/arch/powerpc/mm/nohash/fsl_booke.c @@ -37,7 +37,6 @@ #include <linux/highmem.h> #include <linux/memblock.h> -#include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/io.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index bce0e5349978..4c74e8a5482b 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -15,7 +15,6 @@ #include <linux/libfdt.h> #include <linux/crash_core.h> #include <asm/cacheflush.h> -#include <asm/pgalloc.h> #include <asm/prom.h> #include <asm/kdump.h> #include <mm/mmu_decl.h> diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 696f568253a0..14514585db98 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -34,6 +34,7 @@ #include <linux/of_fdt.h> #include <linux/hugetlb.h> +#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/code-patching.h> diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index d5e2704d0096..bf24451f3e71 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -71,7 +71,6 @@ START_BTB_FLUSH_SECTION END_BTB_FLUSH_SECTION std r7,EX_TLB_R7(r12) #endif - TLB_MISS_PROLOG_STATS .endm .macro tlb_epilog_bolted @@ -85,7 +84,6 @@ END_BTB_FLUSH_SECTION mtcr r14 ld r14,EX_TLB_R14(r12) ld r15,EX_TLB_R15(r12) - TLB_MISS_RESTORE_STATS ld r16,EX_TLB_R16(r12) mfspr r12,SPRN_SPRG_GEN_SCRATCH .endm @@ -128,7 +126,6 @@ END_BTB_FLUSH_SECTION ori r10,r10,_PAGE_PRESENT oris r11,r10,_PAGE_ACCESSED@h - TLB_MISS_STATS_SAVE_INFO_BOLTED bne tlb_miss_kernel_bolted tlb_miss_common_bolted: @@ -209,7 +206,6 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_USE_TLBRSRV) tlbwe tlb_miss_done_bolted: - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) tlb_epilog_bolted rfi @@ -229,11 +225,9 @@ tlb_miss_fault_bolted: andi. r10,r11,_PAGE_EXEC|_PAGE_BAP_SX bne itlb_miss_fault_bolted dtlb_miss_fault_bolted: - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) tlb_epilog_bolted b exc_data_storage_book3e itlb_miss_fault_bolted: - TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) tlb_epilog_bolted b exc_instruction_storage_book3e @@ -243,7 +237,6 @@ itlb_miss_fault_bolted: rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 srdi r15,r16,60 /* get region */ - TLB_MISS_STATS_SAVE_INFO_BOLTED bne- itlb_miss_fault_bolted li r11,_PAGE_PRESENT|_PAGE_EXEC /* Base perm */ @@ -276,7 +269,6 @@ itlb_miss_fault_bolted: srdi. r15,r16,60 /* get region */ ori r16,r16,1 - TLB_MISS_STATS_SAVE_INFO_BOLTED bne tlb_miss_kernel_e6500 /* user/kernel test */ b tlb_miss_common_e6500 @@ -288,7 +280,6 @@ itlb_miss_fault_bolted: srdi. r15,r16,60 /* get region */ rldicr r16,r16,0,62 - TLB_MISS_STATS_SAVE_INFO_BOLTED bne tlb_miss_kernel_e6500 /* user vs kernel check */ /* @@ -460,7 +451,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SMT) .endm tlb_unlock_e6500 - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) tlb_epilog_bolted rfi @@ -519,11 +509,9 @@ tlb_miss_fault_e6500: andi. r16,r16,1 bne itlb_miss_fault_e6500 dtlb_miss_fault_e6500: - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) tlb_epilog_bolted b exc_data_storage_book3e itlb_miss_fault_e6500: - TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) tlb_epilog_bolted b exc_instruction_storage_book3e #endif /* CONFIG_PPC_FSL_BOOK3E */ @@ -548,7 +536,6 @@ itlb_miss_fault_e6500: mfspr r16,SPRN_DEAR /* get faulting address */ srdi r15,r16,60 /* get region */ cmpldi cr0,r15,0xc /* linear mapping ? */ - TLB_MISS_STATS_SAVE_INFO beq tlb_load_linear /* yes -> go to linear map load */ /* The page tables are mapped virtually linear. At this point, though, @@ -600,7 +587,6 @@ itlb_miss_fault_e6500: /* We got a crappy address, just fault with whatever DEAR and ESR * are here */ - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e @@ -624,7 +610,6 @@ itlb_miss_fault_e6500: */ srdi r15,r16,60 /* get region */ cmpldi cr0,r15,0xc /* linear mapping ? */ - TLB_MISS_STATS_SAVE_INFO beq tlb_load_linear /* yes -> go to linear map load */ /* We do the user/kernel test for the PID here along with the RW test @@ -646,7 +631,6 @@ itlb_miss_fault_e6500: beq+ normal_tlb_miss /* We got a crappy address, just fault */ - TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) TLB_MISS_EPILOG_ERROR b exc_instruction_storage_book3e @@ -745,7 +729,6 @@ normal_tlb_miss_done: * level 0 and just going back to userland. They are only needed * if you are going to take an access fault */ - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_NORM_OK) TLB_MISS_EPILOG_SUCCESS rfi @@ -757,11 +740,9 @@ normal_tlb_miss_access_fault: ld r15,EX_TLB_ESR(r12) mtspr SPRN_DEAR,r14 mtspr SPRN_ESR,r15 - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e -1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) - TLB_MISS_EPILOG_ERROR +1: TLB_MISS_EPILOG_ERROR b exc_instruction_storage_book3e @@ -899,7 +880,6 @@ virt_page_table_tlb_miss_done: 1: END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_TLBRSRV) /* Return to caller, normal case */ - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK); TLB_MISS_EPILOG_SUCCESS rfi @@ -935,18 +915,15 @@ virt_page_table_tlb_miss_fault: beq 1f mtspr SPRN_DEAR,r15 mtspr SPRN_ESR,r16 - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT); TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e -1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT); - TLB_MISS_EPILOG_ERROR +1: TLB_MISS_EPILOG_ERROR b exc_instruction_storage_book3e virt_page_table_tlb_miss_whacko_fault: /* The linear fault will restart everything so ESR and DEAR will * not have been clobbered, let's just fault with what we have */ - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_FAULT); TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e @@ -971,7 +948,6 @@ virt_page_table_tlb_miss_whacko_fault: mfspr r16,SPRN_DEAR /* get faulting address */ srdi r11,r16,60 /* get region */ cmpldi cr0,r11,0xc /* linear mapping ? */ - TLB_MISS_STATS_SAVE_INFO beq tlb_load_linear /* yes -> go to linear map load */ /* We do the user/kernel test for the PID here along with the RW test @@ -991,7 +967,6 @@ virt_page_table_tlb_miss_whacko_fault: /* We got a crappy address, just fault with whatever DEAR and ESR * are here */ - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_NORM_FAULT) TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e @@ -1015,7 +990,6 @@ virt_page_table_tlb_miss_whacko_fault: */ srdi r11,r16,60 /* get region */ cmpldi cr0,r11,0xc /* linear mapping ? */ - TLB_MISS_STATS_SAVE_INFO beq tlb_load_linear /* yes -> go to linear map load */ /* We do the user/kernel test for the PID here along with the RW test @@ -1033,7 +1007,6 @@ virt_page_table_tlb_miss_whacko_fault: beq+ htw_tlb_miss /* We got a crappy address, just fault */ - TLB_MISS_STATS_I(MMSTAT_TLB_MISS_NORM_FAULT) TLB_MISS_EPILOG_ERROR b exc_instruction_storage_book3e @@ -1130,7 +1103,6 @@ htw_tlb_miss_done: * level 0 and just going back to userland. They are only needed * if you are going to take an access fault */ - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_PT_OK) TLB_MISS_EPILOG_SUCCESS rfi @@ -1142,11 +1114,9 @@ htw_tlb_miss_fault: beq 1f mtspr SPRN_DEAR,r16 mtspr SPRN_ESR,r14 - TLB_MISS_STATS_D(MMSTAT_TLB_MISS_PT_FAULT) TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e -1: TLB_MISS_STATS_I(MMSTAT_TLB_MISS_PT_FAULT) - TLB_MISS_EPILOG_ERROR +1: TLB_MISS_EPILOG_ERROR b exc_instruction_storage_book3e /* @@ -1221,7 +1191,6 @@ tlb_load_linear_done: * We do that because we can't resume a fault within a TLB * miss handler, due to MAS and TLB reservation being clobbered. */ - TLB_MISS_STATS_X(MMSTAT_TLB_MISS_LINEAR) TLB_MISS_EPILOG_ERROR rfi @@ -1233,13 +1202,3 @@ tlb_load_linear_fault: b exc_data_storage_book3e 1: TLB_MISS_EPILOG_ERROR_SPECIAL b exc_instruction_storage_book3e - - -#ifdef CONFIG_BOOK3E_MMU_TLB_STATS -.tlb_stat_inc: -1: ldarx r8,0,r9 - addi r8,r8,1 - stdcx. r8,0,r9 - bne- 1b - blr -#endif diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 9fcf2d195830..1f61fa2148b5 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -221,7 +221,8 @@ static void initialize_distance_lookup_table(int nid, } } -/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa +/* + * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA * info is found. */ static int associativity_to_nid(const __be32 *associativity) @@ -235,7 +236,7 @@ static int associativity_to_nid(const __be32 *associativity) nid = of_read_number(&associativity[min_common_depth], 1); /* POWER4 LPAR uses 0xffff as invalid node */ - if (nid == 0xffff || nid >= MAX_NUMNODES) + if (nid == 0xffff || nid >= nr_node_ids) nid = NUMA_NO_NODE; if (nid > 0 && @@ -448,7 +449,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb) index = lmb->aa_index * aa.array_sz + min_common_depth - 1; nid = of_read_number(&aa.arrays[index], 1); - if (nid == 0xffff || nid >= MAX_NUMNODES) + if (nid == 0xffff || nid >= nr_node_ids) nid = default_nid; if (nid > 0) { @@ -644,8 +645,9 @@ static inline int __init read_usm_ranges(const __be32 **usm) * Extract NUMA information from the ibm,dynamic-reconfiguration-memory * node. This assumes n_mem_{addr,size}_cells have been set. */ -static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, - const __be32 **usm) +static int __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, + const __be32 **usm, + void *data) { unsigned int ranges, is_kexec_kdump = 0; unsigned long base, size, sz; @@ -657,7 +659,7 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, */ if ((lmb->flags & DRCONF_MEM_RESERVED) || !(lmb->flags & DRCONF_MEM_ASSIGNED)) - return; + return 0; if (*usm) is_kexec_kdump = 1; @@ -669,7 +671,7 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, if (is_kexec_kdump) { ranges = read_usm_ranges(usm); if (!ranges) /* there are no (base, size) duple */ - return; + return 0; } do { @@ -686,6 +688,8 @@ static void __init numa_setup_drmem_lmb(struct drmem_lmb *lmb, if (sz) memblock_set_node(base, sz, &memblock.memory, nid); } while (--ranges); + + return 0; } static int __init parse_numa_properties(void) @@ -787,7 +791,7 @@ new_range: */ memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (memory) { - walk_drmem_lmbs(memory, numa_setup_drmem_lmb); + walk_drmem_lmbs(memory, NULL, numa_setup_drmem_lmb); of_node_put(memory); } @@ -949,7 +953,6 @@ void __init initmem_init(void) get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); setup_node_data(nid, start_pfn, end_pfn); - sparse_memory_present_with_active_regions(nid); } sparse_init(); @@ -984,28 +987,6 @@ static int __init early_numa(char *p) } early_param("numa", early_numa); -/* - * The platform can inform us through one of several mechanisms - * (post-migration device tree updates, PRRN or VPHN) that the NUMA - * assignment of a resource has changed. This controls whether we act - * on that. Disabled by default. - */ -static bool topology_updates_enabled; - -static int __init early_topology_updates(char *p) -{ - if (!p) - return 0; - - if (!strcmp(p, "on")) { - pr_warn("Caution: enabling topology updates\n"); - topology_updates_enabled = true; - } - - return 0; -} -early_param("topology_updates", early_topology_updates); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Find the node associated with a hot added memory section for @@ -1144,98 +1125,9 @@ u64 memory_hotplug_max(void) /* Virtual Processor Home Node (VPHN) support */ #ifdef CONFIG_PPC_SPLPAR -struct topology_update_data { - struct topology_update_data *next; - unsigned int cpu; - int old_nid; - int new_nid; -}; - -#define TOPOLOGY_DEF_TIMER_SECS 60 - -static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS]; -static cpumask_t cpu_associativity_changes_mask; -static int vphn_enabled; -static int prrn_enabled; -static void reset_topology_timer(void); -static int topology_timer_secs = 1; static int topology_inited; /* - * Change polling interval for associativity changes. - */ -int timed_topology_update(int nsecs) -{ - if (vphn_enabled) { - if (nsecs > 0) - topology_timer_secs = nsecs; - else - topology_timer_secs = TOPOLOGY_DEF_TIMER_SECS; - - reset_topology_timer(); - } - - return 0; -} - -/* - * Store the current values of the associativity change counters in the - * hypervisor. - */ -static void setup_cpu_associativity_change_counters(void) -{ - int cpu; - - /* The VPHN feature supports a maximum of 8 reference points */ - BUILD_BUG_ON(MAX_DISTANCE_REF_POINTS > 8); - - for_each_possible_cpu(cpu) { - int i; - u8 *counts = vphn_cpu_change_counts[cpu]; - volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts; - - for (i = 0; i < distance_ref_points_depth; i++) - counts[i] = hypervisor_counts[i]; - } -} - -/* - * The hypervisor maintains a set of 8 associativity change counters in - * the VPA of each cpu that correspond to the associativity levels in the - * ibm,associativity-reference-points property. When an associativity - * level changes, the corresponding counter is incremented. - * - * Set a bit in cpu_associativity_changes_mask for each cpu whose home - * node associativity levels have changed. - * - * Returns the number of cpus with unhandled associativity changes. - */ -static int update_cpu_associativity_changes_mask(void) -{ - int cpu; - cpumask_t *changes = &cpu_associativity_changes_mask; - - for_each_possible_cpu(cpu) { - int i, changed = 0; - u8 *counts = vphn_cpu_change_counts[cpu]; - volatile u8 *hypervisor_counts = lppaca_of(cpu).vphn_assoc_counts; - - for (i = 0; i < distance_ref_points_depth; i++) { - if (hypervisor_counts[i] != counts[i]) { - counts[i] = hypervisor_counts[i]; - changed = 1; - } - } - if (changed) { - cpumask_or(changes, changes, cpu_sibling_mask(cpu)); - cpu = cpu_last_thread_sibling(cpu); - } - } - - return cpumask_weight(changes); -} - -/* * Retrieve the new associativity information for a virtual processor's * home node. */ @@ -1250,7 +1142,6 @@ static long vphn_get_associativity(unsigned long cpu, switch (rc) { case H_SUCCESS: dbg("VPHN hcall succeeded. Reset polling...\n"); - timed_topology_update(0); goto out; case H_FUNCTION: @@ -1269,8 +1160,6 @@ static long vphn_get_associativity(unsigned long cpu, , rc); break; } - - stop_topology_update(); out: return rc; } @@ -1314,380 +1203,8 @@ int find_and_online_cpu_nid(int cpu) return new_nid; } -/* - * Update the CPU maps and sysfs entries for a single CPU when its NUMA - * characteristics change. This function doesn't perform any locking and is - * only safe to call from stop_machine(). - */ -static int update_cpu_topology(void *data) -{ - struct topology_update_data *update; - unsigned long cpu; - - if (!data) - return -EINVAL; - - cpu = smp_processor_id(); - - for (update = data; update; update = update->next) { - int new_nid = update->new_nid; - if (cpu != update->cpu) - continue; - - unmap_cpu_from_node(cpu); - map_cpu_to_node(cpu, new_nid); - set_cpu_numa_node(cpu, new_nid); - set_cpu_numa_mem(cpu, local_memory_node(new_nid)); - vdso_getcpu_init(); - } - - return 0; -} - -static int update_lookup_table(void *data) -{ - struct topology_update_data *update; - - if (!data) - return -EINVAL; - - /* - * Upon topology update, the numa-cpu lookup table needs to be updated - * for all threads in the core, including offline CPUs, to ensure that - * future hotplug operations respect the cpu-to-node associativity - * properly. - */ - for (update = data; update; update = update->next) { - int nid, base, j; - - nid = update->new_nid; - base = cpu_first_thread_sibling(update->cpu); - - for (j = 0; j < threads_per_core; j++) { - update_numa_cpu_lookup_table(base + j, nid); - } - } - - return 0; -} - -/* - * Update the node maps and sysfs entries for each cpu whose home node - * has changed. Returns 1 when the topology has changed, and 0 otherwise. - * - * cpus_locked says whether we already hold cpu_hotplug_lock. - */ -int numa_update_cpu_topology(bool cpus_locked) -{ - unsigned int cpu, sibling, changed = 0; - struct topology_update_data *updates, *ud; - cpumask_t updated_cpus; - struct device *dev; - int weight, new_nid, i = 0; - - if (!prrn_enabled && !vphn_enabled && topology_inited) - return 0; - - weight = cpumask_weight(&cpu_associativity_changes_mask); - if (!weight) - return 0; - - updates = kcalloc(weight, sizeof(*updates), GFP_KERNEL); - if (!updates) - return 0; - - cpumask_clear(&updated_cpus); - - for_each_cpu(cpu, &cpu_associativity_changes_mask) { - /* - * If siblings aren't flagged for changes, updates list - * will be too short. Skip on this update and set for next - * update. - */ - if (!cpumask_subset(cpu_sibling_mask(cpu), - &cpu_associativity_changes_mask)) { - pr_info("Sibling bits not set for associativity " - "change, cpu%d\n", cpu); - cpumask_or(&cpu_associativity_changes_mask, - &cpu_associativity_changes_mask, - cpu_sibling_mask(cpu)); - cpu = cpu_last_thread_sibling(cpu); - continue; - } - - new_nid = find_and_online_cpu_nid(cpu); - - if (new_nid == numa_cpu_lookup_table[cpu]) { - cpumask_andnot(&cpu_associativity_changes_mask, - &cpu_associativity_changes_mask, - cpu_sibling_mask(cpu)); - dbg("Assoc chg gives same node %d for cpu%d\n", - new_nid, cpu); - cpu = cpu_last_thread_sibling(cpu); - continue; - } - - for_each_cpu(sibling, cpu_sibling_mask(cpu)) { - ud = &updates[i++]; - ud->next = &updates[i]; - ud->cpu = sibling; - ud->new_nid = new_nid; - ud->old_nid = numa_cpu_lookup_table[sibling]; - cpumask_set_cpu(sibling, &updated_cpus); - } - cpu = cpu_last_thread_sibling(cpu); - } - - /* - * Prevent processing of 'updates' from overflowing array - * where last entry filled in a 'next' pointer. - */ - if (i) - updates[i-1].next = NULL; - - pr_debug("Topology update for the following CPUs:\n"); - if (cpumask_weight(&updated_cpus)) { - for (ud = &updates[0]; ud; ud = ud->next) { - pr_debug("cpu %d moving from node %d " - "to %d\n", ud->cpu, - ud->old_nid, ud->new_nid); - } - } - - /* - * In cases where we have nothing to update (because the updates list - * is too short or because the new topology is same as the old one), - * skip invoking update_cpu_topology() via stop-machine(). This is - * necessary (and not just a fast-path optimization) since stop-machine - * can end up electing a random CPU to run update_cpu_topology(), and - * thus trick us into setting up incorrect cpu-node mappings (since - * 'updates' is kzalloc()'ed). - * - * And for the similar reason, we will skip all the following updating. - */ - if (!cpumask_weight(&updated_cpus)) - goto out; - - if (cpus_locked) - stop_machine_cpuslocked(update_cpu_topology, &updates[0], - &updated_cpus); - else - stop_machine(update_cpu_topology, &updates[0], &updated_cpus); - - /* - * Update the numa-cpu lookup table with the new mappings, even for - * offline CPUs. It is best to perform this update from the stop- - * machine context. - */ - if (cpus_locked) - stop_machine_cpuslocked(update_lookup_table, &updates[0], - cpumask_of(raw_smp_processor_id())); - else - stop_machine(update_lookup_table, &updates[0], - cpumask_of(raw_smp_processor_id())); - - for (ud = &updates[0]; ud; ud = ud->next) { - unregister_cpu_under_node(ud->cpu, ud->old_nid); - register_cpu_under_node(ud->cpu, ud->new_nid); - - dev = get_cpu_device(ud->cpu); - if (dev) - kobject_uevent(&dev->kobj, KOBJ_CHANGE); - cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask); - changed = 1; - } - -out: - kfree(updates); - return changed; -} - -int arch_update_cpu_topology(void) -{ - return numa_update_cpu_topology(true); -} - -static void topology_work_fn(struct work_struct *work) -{ - rebuild_sched_domains(); -} -static DECLARE_WORK(topology_work, topology_work_fn); - -static void topology_schedule_update(void) -{ - schedule_work(&topology_work); -} - -static void topology_timer_fn(struct timer_list *unused) -{ - if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask)) - topology_schedule_update(); - else if (vphn_enabled) { - if (update_cpu_associativity_changes_mask() > 0) - topology_schedule_update(); - reset_topology_timer(); - } -} -static struct timer_list topology_timer; - -static void reset_topology_timer(void) -{ - if (vphn_enabled) - mod_timer(&topology_timer, jiffies + topology_timer_secs * HZ); -} - -#ifdef CONFIG_SMP - -static int dt_update_callback(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct of_reconfig_data *update = data; - int rc = NOTIFY_DONE; - - switch (action) { - case OF_RECONFIG_UPDATE_PROPERTY: - if (of_node_is_type(update->dn, "cpu") && - !of_prop_cmp(update->prop->name, "ibm,associativity")) { - u32 core_id; - of_property_read_u32(update->dn, "reg", &core_id); - rc = dlpar_cpu_readd(core_id); - rc = NOTIFY_OK; - } - break; - } - - return rc; -} - -static struct notifier_block dt_update_nb = { - .notifier_call = dt_update_callback, -}; - -#endif - -/* - * Start polling for associativity changes. - */ -int start_topology_update(void) -{ - int rc = 0; - - if (!topology_updates_enabled) - return 0; - - if (firmware_has_feature(FW_FEATURE_PRRN)) { - if (!prrn_enabled) { - prrn_enabled = 1; -#ifdef CONFIG_SMP - rc = of_reconfig_notifier_register(&dt_update_nb); -#endif - } - } - if (firmware_has_feature(FW_FEATURE_VPHN) && - lppaca_shared_proc(get_lppaca())) { - if (!vphn_enabled) { - vphn_enabled = 1; - setup_cpu_associativity_change_counters(); - timer_setup(&topology_timer, topology_timer_fn, - TIMER_DEFERRABLE); - reset_topology_timer(); - } - } - - pr_info("Starting topology update%s%s\n", - (prrn_enabled ? " prrn_enabled" : ""), - (vphn_enabled ? " vphn_enabled" : "")); - - return rc; -} - -/* - * Disable polling for VPHN associativity changes. - */ -int stop_topology_update(void) -{ - int rc = 0; - - if (!topology_updates_enabled) - return 0; - - if (prrn_enabled) { - prrn_enabled = 0; -#ifdef CONFIG_SMP - rc = of_reconfig_notifier_unregister(&dt_update_nb); -#endif - } - if (vphn_enabled) { - vphn_enabled = 0; - rc = del_timer_sync(&topology_timer); - } - - pr_info("Stopping topology update\n"); - - return rc; -} - -int prrn_is_enabled(void) -{ - return prrn_enabled; -} - -static int topology_read(struct seq_file *file, void *v) -{ - if (vphn_enabled || prrn_enabled) - seq_puts(file, "on\n"); - else - seq_puts(file, "off\n"); - - return 0; -} - -static int topology_open(struct inode *inode, struct file *file) -{ - return single_open(file, topology_read, NULL); -} - -static ssize_t topology_write(struct file *file, const char __user *buf, - size_t count, loff_t *off) -{ - char kbuf[4]; /* "on" or "off" plus null. */ - int read_len; - - read_len = count < 3 ? count : 3; - if (copy_from_user(kbuf, buf, read_len)) - return -EINVAL; - - kbuf[read_len] = '\0'; - - if (!strncmp(kbuf, "on", 2)) { - topology_updates_enabled = true; - start_topology_update(); - } else if (!strncmp(kbuf, "off", 3)) { - stop_topology_update(); - topology_updates_enabled = false; - } else - return -EINVAL; - - return count; -} - -static const struct proc_ops topology_proc_ops = { - .proc_read = seq_read, - .proc_write = topology_write, - .proc_open = topology_open, - .proc_release = single_release, -}; - static int topology_update_init(void) { - start_topology_update(); - - if (vphn_enabled) - topology_schedule_update(); - - if (!proc_create("powerpc/topology_updates", 0644, NULL, &topology_proc_ops)) - return -ENOMEM; - topology_inited = 1; return 0; } diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c index ee4bd6d38602..97ae4935da79 100644 --- a/arch/powerpc/mm/pgtable-frag.c +++ b/arch/powerpc/mm/pgtable-frag.c @@ -110,6 +110,9 @@ void pte_fragment_free(unsigned long *table, int kernel) { struct page *page = virt_to_page(table); + if (PageReserved(page)) + return free_reserved_page(page); + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); if (atomic_dec_and_test(&page->pt_frag_refcount)) { if (!kernel) diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 1136257c3a99..9c0547d77af3 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -23,7 +23,6 @@ #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/hugetlb.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <asm/hugetlb.h> diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index bb43a8c04bee..cc6e2f94517f 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -31,7 +31,6 @@ #include <linux/slab.h> #include <linux/hugetlb.h> -#include <asm/pgalloc.h> #include <asm/page.h> #include <asm/prom.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index a2c33efc7ce8..ad6df9a2e7c8 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -17,10 +17,10 @@ #include <linux/seq_file.h> #include <linux/const.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/plpar_wrappers.h> #include <linux/memblock.h> #include <asm/firmware.h> +#include <asm/pgalloc.h> struct pg_state { struct seq_file *seq; @@ -258,7 +258,7 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 * for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); - if (lpar_rc != H_SUCCESS) + if (lpar_rc) continue; for (j = 0; j < 4; j++) { if (HPTE_V_COMPARE(ptes[j].v, want_v) && diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c index de6e05ef871c..aca354fb670b 100644 --- a/arch/powerpc/mm/ptdump/ptdump.c +++ b/arch/powerpc/mm/ptdump/ptdump.c @@ -21,7 +21,6 @@ #include <asm/fixmap.h> #include <linux/const.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/hugetlb.h> #include <mm/mmu_decl.h> @@ -74,6 +73,10 @@ struct addr_marker { static struct addr_marker address_markers[] = { { 0, "Start of kernel VM" }, +#ifdef MODULES_VADDR + { 0, "modules start" }, + { 0, "modules end" }, +#endif { 0, "vmalloc() Area" }, { 0, "vmalloc() End" }, #ifdef CONFIG_PPC64 @@ -195,6 +198,24 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr) st->wx_pages += (addr - st->start_address) / PAGE_SIZE; } +static void note_page_update_state(struct pg_state *st, unsigned long addr, + unsigned int level, u64 val, unsigned long page_size) +{ + u64 flag = val & pg_level[level].mask; + u64 pa = val & PTE_RPN_MASK; + + st->level = level; + st->current_flags = flag; + st->start_address = addr; + st->start_pa = pa; + st->page_size = page_size; + + while (addr >= st->marker[1].start_address) { + st->marker++; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } +} + static void note_page(struct pg_state *st, unsigned long addr, unsigned int level, u64 val, unsigned long page_size) { @@ -203,13 +224,8 @@ static void note_page(struct pg_state *st, unsigned long addr, /* At first no level is set */ if (!st->level) { - st->level = level; - st->current_flags = flag; - st->start_address = addr; - st->start_pa = pa; - st->last_pa = pa; - st->page_size = page_size; pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + note_page_update_state(st, addr, level, val, page_size); /* * Dump the section of virtual memory when: * - the PTE flags from one entry to the next differs. @@ -241,19 +257,9 @@ static void note_page(struct pg_state *st, unsigned long addr, * Address indicates we have passed the end of the * current section of virtual memory */ - while (addr >= st->marker[1].start_address) { - st->marker++; - pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); - } - st->start_address = addr; - st->start_pa = pa; - st->last_pa = pa; - st->page_size = page_size; - st->current_flags = flag; - st->level = level; - } else { - st->last_pa = pa; + note_page_update_state(st, addr, level, val, page_size); } + st->last_pa = pa; } static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) @@ -348,7 +354,15 @@ static void populate_markers(void) { int i = 0; +#ifdef CONFIG_PPC64 address_markers[i++].start_address = PAGE_OFFSET; +#else + address_markers[i++].start_address = TASK_SIZE; +#endif +#ifdef MODULES_VADDR + address_markers[i++].start_address = MODULES_VADDR; + address_markers[i++].start_address = MODULES_END; +#endif address_markers[i++].start_address = VMALLOC_START; address_markers[i++].start_address = VMALLOC_END; #ifdef CONFIG_PPC64 @@ -385,7 +399,7 @@ static int ptdump_show(struct seq_file *m, void *v) struct pg_state st = { .seq = m, .marker = address_markers, - .start_address = PAGE_OFFSET, + .start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE, }; #ifdef CONFIG_PPC64 @@ -429,7 +443,7 @@ void ptdump_check_wx(void) .seq = NULL, .marker = address_markers, .check_wx = true, - .start_address = PAGE_OFFSET, + .start_address = IS_ENABLED(CONFIG_PPC64) ? PAGE_OFFSET : TASK_SIZE, }; #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index 55d4377ccfae..d0a67a1bbaf1 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -11,6 +11,7 @@ #ifndef __ASSEMBLY__ #include <asm/types.h> +#include <asm/ppc-opcode.h> #ifdef PPC64_ELF_ABI_v1 #define FUNCTION_DESCR_SIZE 24 @@ -18,167 +19,10 @@ #define FUNCTION_DESCR_SIZE 0 #endif -/* - * 16-bit immediate helper macros: HA() is for use with sign-extending instrs - * (e.g. LD, ADDI). If the bottom 16 bits is "-ve", add another bit into the - * top half to negate the effect (i.e. 0xffff + 1 = 0x(1)0000). - */ -#define IMM_H(i) ((uintptr_t)(i)>>16) -#define IMM_HA(i) (((uintptr_t)(i)>>16) + \ - (((uintptr_t)(i) & 0x8000) >> 15)) -#define IMM_L(i) ((uintptr_t)(i) & 0xffff) - #define PLANT_INSTR(d, idx, instr) \ do { if (d) { (d)[idx] = instr; } idx++; } while (0) #define EMIT(instr) PLANT_INSTR(image, ctx->idx, instr) -#define PPC_NOP() EMIT(PPC_INST_NOP) -#define PPC_BLR() EMIT(PPC_INST_BLR) -#define PPC_BLRL() EMIT(PPC_INST_BLRL) -#define PPC_MTLR(r) EMIT(PPC_INST_MTLR | ___PPC_RT(r)) -#define PPC_BCTR() EMIT(PPC_INST_BCTR) -#define PPC_MTCTR(r) EMIT(PPC_INST_MTCTR | ___PPC_RT(r)) -#define PPC_ADDI(d, a, i) EMIT(PPC_INST_ADDI | ___PPC_RT(d) | \ - ___PPC_RA(a) | IMM_L(i)) -#define PPC_MR(d, a) PPC_OR(d, a, a) -#define PPC_LI(r, i) PPC_ADDI(r, 0, i) -#define PPC_ADDIS(d, a, i) EMIT(PPC_INST_ADDIS | \ - ___PPC_RT(d) | ___PPC_RA(a) | IMM_L(i)) -#define PPC_LIS(r, i) PPC_ADDIS(r, 0, i) -#define PPC_STD(r, base, i) EMIT(PPC_INST_STD | ___PPC_RS(r) | \ - ___PPC_RA(base) | ((i) & 0xfffc)) -#define PPC_STDX(r, base, b) EMIT(PPC_INST_STDX | ___PPC_RS(r) | \ - ___PPC_RA(base) | ___PPC_RB(b)) -#define PPC_STDU(r, base, i) EMIT(PPC_INST_STDU | ___PPC_RS(r) | \ - ___PPC_RA(base) | ((i) & 0xfffc)) -#define PPC_STW(r, base, i) EMIT(PPC_INST_STW | ___PPC_RS(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_STWU(r, base, i) EMIT(PPC_INST_STWU | ___PPC_RS(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_STH(r, base, i) EMIT(PPC_INST_STH | ___PPC_RS(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_STB(r, base, i) EMIT(PPC_INST_STB | ___PPC_RS(r) | \ - ___PPC_RA(base) | IMM_L(i)) - -#define PPC_LBZ(r, base, i) EMIT(PPC_INST_LBZ | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_LD(r, base, i) EMIT(PPC_INST_LD | ___PPC_RT(r) | \ - ___PPC_RA(base) | ((i) & 0xfffc)) -#define PPC_LDX(r, base, b) EMIT(PPC_INST_LDX | ___PPC_RT(r) | \ - ___PPC_RA(base) | ___PPC_RB(b)) -#define PPC_LWZ(r, base, i) EMIT(PPC_INST_LWZ | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_LHZ(r, base, i) EMIT(PPC_INST_LHZ | ___PPC_RT(r) | \ - ___PPC_RA(base) | IMM_L(i)) -#define PPC_LHBRX(r, base, b) EMIT(PPC_INST_LHBRX | ___PPC_RT(r) | \ - ___PPC_RA(base) | ___PPC_RB(b)) -#define PPC_LDBRX(r, base, b) EMIT(PPC_INST_LDBRX | ___PPC_RT(r) | \ - ___PPC_RA(base) | ___PPC_RB(b)) - -#define PPC_BPF_LDARX(t, a, b, eh) EMIT(PPC_INST_LDARX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b) | \ - __PPC_EH(eh)) -#define PPC_BPF_LWARX(t, a, b, eh) EMIT(PPC_INST_LWARX | ___PPC_RT(t) | \ - ___PPC_RA(a) | ___PPC_RB(b) | \ - __PPC_EH(eh)) -#define PPC_BPF_STWCX(s, a, b) EMIT(PPC_INST_STWCX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_BPF_STDCX(s, a, b) EMIT(PPC_INST_STDCX | ___PPC_RS(s) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_CMPWI(a, i) EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i)) -#define PPC_CMPDI(a, i) EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i)) -#define PPC_CMPW(a, b) EMIT(PPC_INST_CMPW | ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_CMPD(a, b) EMIT(PPC_INST_CMPD | ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_CMPLWI(a, i) EMIT(PPC_INST_CMPLWI | ___PPC_RA(a) | IMM_L(i)) -#define PPC_CMPLDI(a, i) EMIT(PPC_INST_CMPLDI | ___PPC_RA(a) | IMM_L(i)) -#define PPC_CMPLW(a, b) EMIT(PPC_INST_CMPLW | ___PPC_RA(a) | \ - ___PPC_RB(b)) -#define PPC_CMPLD(a, b) EMIT(PPC_INST_CMPLD | ___PPC_RA(a) | \ - ___PPC_RB(b)) - -#define PPC_SUB(d, a, b) EMIT(PPC_INST_SUB | ___PPC_RT(d) | \ - ___PPC_RB(a) | ___PPC_RA(b)) -#define PPC_ADD(d, a, b) EMIT(PPC_INST_ADD | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_MULD(d, a, b) EMIT(PPC_INST_MULLD | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_MULW(d, a, b) EMIT(PPC_INST_MULLW | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_MULHWU(d, a, b) EMIT(PPC_INST_MULHWU | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_MULI(d, a, i) EMIT(PPC_INST_MULLI | ___PPC_RT(d) | \ - ___PPC_RA(a) | IMM_L(i)) -#define PPC_DIVWU(d, a, b) EMIT(PPC_INST_DIVWU | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_DIVDU(d, a, b) EMIT(PPC_INST_DIVDU | ___PPC_RT(d) | \ - ___PPC_RA(a) | ___PPC_RB(b)) -#define PPC_AND(d, a, b) EMIT(PPC_INST_AND | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(b)) -#define PPC_ANDI(d, a, i) EMIT(PPC_INST_ANDI | ___PPC_RA(d) | \ - ___PPC_RS(a) | IMM_L(i)) -#define PPC_AND_DOT(d, a, b) EMIT(PPC_INST_ANDDOT | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(b)) -#define PPC_OR(d, a, b) EMIT(PPC_INST_OR | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(b)) -#define PPC_MR(d, a) PPC_OR(d, a, a) -#define PPC_ORI(d, a, i) EMIT(PPC_INST_ORI | ___PPC_RA(d) | \ - ___PPC_RS(a) | IMM_L(i)) -#define PPC_ORIS(d, a, i) EMIT(PPC_INST_ORIS | ___PPC_RA(d) | \ - ___PPC_RS(a) | IMM_L(i)) -#define PPC_XOR(d, a, b) EMIT(PPC_INST_XOR | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(b)) -#define PPC_XORI(d, a, i) EMIT(PPC_INST_XORI | ___PPC_RA(d) | \ - ___PPC_RS(a) | IMM_L(i)) -#define PPC_XORIS(d, a, i) EMIT(PPC_INST_XORIS | ___PPC_RA(d) | \ - ___PPC_RS(a) | IMM_L(i)) -#define PPC_EXTSW(d, a) EMIT(PPC_INST_EXTSW | ___PPC_RA(d) | \ - ___PPC_RS(a)) -#define PPC_SLW(d, a, s) EMIT(PPC_INST_SLW | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SLD(d, a, s) EMIT(PPC_INST_SLD | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SRW(d, a, s) EMIT(PPC_INST_SRW | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SRAW(d, a, s) EMIT(PPC_INST_SRAW | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SRAWI(d, a, i) EMIT(PPC_INST_SRAWI | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i)) -#define PPC_SRD(d, a, s) EMIT(PPC_INST_SRD | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SRAD(d, a, s) EMIT(PPC_INST_SRAD | ___PPC_RA(d) | \ - ___PPC_RS(a) | ___PPC_RB(s)) -#define PPC_SRADI(d, a, i) EMIT(PPC_INST_SRADI | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH64(i)) -#define PPC_RLWINM(d, a, i, mb, me) EMIT(PPC_INST_RLWINM | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i) | \ - __PPC_MB(mb) | __PPC_ME(me)) -#define PPC_RLWINM_DOT(d, a, i, mb, me) EMIT(PPC_INST_RLWINM_DOT | \ - ___PPC_RA(d) | ___PPC_RS(a) | \ - __PPC_SH(i) | __PPC_MB(mb) | \ - __PPC_ME(me)) -#define PPC_RLWIMI(d, a, i, mb, me) EMIT(PPC_INST_RLWIMI | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH(i) | \ - __PPC_MB(mb) | __PPC_ME(me)) -#define PPC_RLDICL(d, a, i, mb) EMIT(PPC_INST_RLDICL | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH64(i) | \ - __PPC_MB64(mb)) -#define PPC_RLDICR(d, a, i, me) EMIT(PPC_INST_RLDICR | ___PPC_RA(d) | \ - ___PPC_RS(a) | __PPC_SH64(i) | \ - __PPC_ME64(me)) - -/* slwi = rlwinm Rx, Ry, n, 0, 31-n */ -#define PPC_SLWI(d, a, i) PPC_RLWINM(d, a, i, 0, 31-(i)) -/* srwi = rlwinm Rx, Ry, 32-n, n, 31 */ -#define PPC_SRWI(d, a, i) PPC_RLWINM(d, a, 32-(i), i, 31) -/* sldi = rldicr Rx, Ry, n, 63-n */ -#define PPC_SLDI(d, a, i) PPC_RLDICR(d, a, i, 63-(i)) -/* sldi = rldicl Rx, Ry, 64-n, n */ -#define PPC_SRDI(d, a, i) PPC_RLDICL(d, a, 64-(i), i) - -#define PPC_NEG(d, a) EMIT(PPC_INST_NEG | ___PPC_RT(d) | ___PPC_RA(a)) - /* Long jump; (unconditional 'branch') */ #define PPC_JMP(dest) EMIT(PPC_INST_BRANCH | \ (((dest) - (ctx->idx * 4)) & 0x03fffffc)) @@ -191,11 +35,11 @@ #define PPC_LI32(d, i) do { \ if ((int)(uintptr_t)(i) >= -32768 && \ (int)(uintptr_t)(i) < 32768) \ - PPC_LI(d, i); \ + EMIT(PPC_RAW_LI(d, i)); \ else { \ - PPC_LIS(d, IMM_H(i)); \ + EMIT(PPC_RAW_LIS(d, IMM_H(i))); \ if (IMM_L(i)) \ - PPC_ORI(d, d, IMM_L(i)); \ + EMIT(PPC_RAW_ORI(d, d, IMM_L(i))); \ } } while(0) #define PPC_LI64(d, i) do { \ @@ -204,19 +48,21 @@ PPC_LI32(d, i); \ else { \ if (!((uintptr_t)(i) & 0xffff800000000000ULL)) \ - PPC_LI(d, ((uintptr_t)(i) >> 32) & 0xffff); \ + EMIT(PPC_RAW_LI(d, ((uintptr_t)(i) >> 32) & \ + 0xffff)); \ else { \ - PPC_LIS(d, ((uintptr_t)(i) >> 48)); \ + EMIT(PPC_RAW_LIS(d, ((uintptr_t)(i) >> 48))); \ if ((uintptr_t)(i) & 0x0000ffff00000000ULL) \ - PPC_ORI(d, d, \ - ((uintptr_t)(i) >> 32) & 0xffff); \ + EMIT(PPC_RAW_ORI(d, d, \ + ((uintptr_t)(i) >> 32) & 0xffff)); \ } \ - PPC_SLDI(d, d, 32); \ + EMIT(PPC_RAW_SLDI(d, d, 32)); \ if ((uintptr_t)(i) & 0x00000000ffff0000ULL) \ - PPC_ORIS(d, d, \ - ((uintptr_t)(i) >> 16) & 0xffff); \ + EMIT(PPC_RAW_ORIS(d, d, \ + ((uintptr_t)(i) >> 16) & 0xffff)); \ if ((uintptr_t)(i) & 0x000000000000ffffULL) \ - PPC_ORI(d, d, (uintptr_t)(i) & 0xffff); \ + EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) & \ + 0xffff)); \ } } while (0) #ifdef CONFIG_PPC64 @@ -240,7 +86,7 @@ static inline bool is_nearbranch(int offset) #define PPC_BCC(cond, dest) do { \ if (is_nearbranch((dest) - (ctx->idx * 4))) { \ PPC_BCC_SHORT(cond, dest); \ - PPC_NOP(); \ + EMIT(PPC_RAW_NOP()); \ } else { \ /* Flip the 'T or F' bit to invert comparison */ \ PPC_BCC_SHORT(cond ^ COND_CMP_TRUE, (ctx->idx+2)*4); \ diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h index 4ec2a9f14f84..448dfd4d98e1 100644 --- a/arch/powerpc/net/bpf_jit32.h +++ b/arch/powerpc/net/bpf_jit32.h @@ -72,21 +72,21 @@ DECLARE_LOAD_FUNC(sk_load_half); DECLARE_LOAD_FUNC(sk_load_byte); DECLARE_LOAD_FUNC(sk_load_byte_msh); -#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LBZ(r, base, i); \ - else { PPC_ADDIS(r, base, IMM_HA(i)); \ - PPC_LBZ(r, r, IMM_L(i)); } } while(0) +#define PPC_LBZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LBZ(r, base, i)); \ + else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \ + EMIT(PPC_RAW_LBZ(r, r, IMM_L(i))); } } while(0) -#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) PPC_LD(r, base, i); \ - else { PPC_ADDIS(r, base, IMM_HA(i)); \ - PPC_LD(r, r, IMM_L(i)); } } while(0) +#define PPC_LD_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LD(r, base, i)); \ + else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \ + EMIT(PPC_RAW_LD(r, r, IMM_L(i))); } } while(0) -#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LWZ(r, base, i); \ - else { PPC_ADDIS(r, base, IMM_HA(i)); \ - PPC_LWZ(r, r, IMM_L(i)); } } while(0) +#define PPC_LWZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LWZ(r, base, i)); \ + else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \ + EMIT(PPC_RAW_LWZ(r, r, IMM_L(i))); } } while(0) -#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) PPC_LHZ(r, base, i); \ - else { PPC_ADDIS(r, base, IMM_HA(i)); \ - PPC_LHZ(r, r, IMM_L(i)); } } while(0) +#define PPC_LHZ_OFFS(r, base, i) do { if ((i) < 32768) EMIT(PPC_RAW_LHZ(r, base, i)); \ + else { EMIT(PPC_RAW_ADDIS(r, base, IMM_HA(i))); \ + EMIT(PPC_RAW_LHZ(r, r, IMM_L(i))); } } while(0) #ifdef CONFIG_PPC64 #define PPC_LL_OFFS(r, base, i) do { PPC_LD_OFFS(r, base, i); } while(0) @@ -107,20 +107,20 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh); } while(0) #endif #else -#define PPC_BPF_LOAD_CPU(r) do { PPC_LI(r, 0); } while(0) +#define PPC_BPF_LOAD_CPU(r) do { EMIT(PPC_RAW_LI(r, 0)); } while(0) #endif #define PPC_LHBRX_OFFS(r, base, i) \ - do { PPC_LI32(r, i); PPC_LHBRX(r, r, base); } while(0) + do { PPC_LI32(r, i); EMIT(PPC_RAW_LHBRX(r, r, base)); } while(0) #ifdef __LITTLE_ENDIAN__ #define PPC_NTOHS_OFFS(r, base, i) PPC_LHBRX_OFFS(r, base, i) #else #define PPC_NTOHS_OFFS(r, base, i) PPC_LHZ_OFFS(r, base, i) #endif -#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0) -#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0) +#define PPC_BPF_LL(r, base, i) do { EMIT(PPC_RAW_LWZ(r, base, i)); } while(0) +#define PPC_BPF_STL(r, base, i) do { EMIT(PPC_RAW_STW(r, base, i)); } while(0) +#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STWU(r, base, i)); } while(0) #define SEEN_DATAREF 0x10000 /* might call external helpers */ #define SEEN_XREG 0x20000 /* X reg is used */ diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index cf3a7e337f02..2e33c6673ff9 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -70,19 +70,21 @@ static const int b2p[] = { */ #define PPC_BPF_LL(r, base, i) do { \ if ((i) % 4) { \ - PPC_LI(b2p[TMP_REG_2], (i)); \ - PPC_LDX(r, base, b2p[TMP_REG_2]); \ + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\ + EMIT(PPC_RAW_LDX(r, base, \ + b2p[TMP_REG_2])); \ } else \ - PPC_LD(r, base, i); \ + EMIT(PPC_RAW_LD(r, base, i)); \ } while(0) #define PPC_BPF_STL(r, base, i) do { \ if ((i) % 4) { \ - PPC_LI(b2p[TMP_REG_2], (i)); \ - PPC_STDX(r, base, b2p[TMP_REG_2]); \ + EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\ + EMIT(PPC_RAW_STDX(r, base, \ + b2p[TMP_REG_2])); \ } else \ - PPC_STD(r, base, i); \ + EMIT(PPC_RAW_STD(r, base, i)); \ } while(0) -#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0) +#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STDU(r, base, i)); } while(0) #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 0acc9d5fb19e..16d09b36fe06 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -61,7 +61,7 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, PPC_LWZ_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, data_len)); PPC_LWZ_OFFS(r_HL, r_skb, offsetof(struct sk_buff, len)); - PPC_SUB(r_HL, r_HL, r_scratch1); + EMIT(PPC_RAW_SUB(r_HL, r_HL, r_scratch1)); PPC_LL_OFFS(r_D, r_skb, offsetof(struct sk_buff, data)); } @@ -70,12 +70,12 @@ static void bpf_jit_build_prologue(struct bpf_prog *fp, u32 *image, * TODO: Could also detect whether first instr. sets X and * avoid this (as below, with A). */ - PPC_LI(r_X, 0); + EMIT(PPC_RAW_LI(r_X, 0)); } /* make sure we dont leak kernel information to user */ if (bpf_needs_clear_a(&filter[0])) - PPC_LI(r_A, 0); + EMIT(PPC_RAW_LI(r_A, 0)); } static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) @@ -83,10 +83,10 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) int i; if (ctx->seen & (SEEN_MEM | SEEN_DATAREF)) { - PPC_ADDI(1, 1, BPF_PPC_STACKFRAME); + EMIT(PPC_RAW_ADDI(1, 1, BPF_PPC_STACKFRAME)); if (ctx->seen & SEEN_DATAREF) { PPC_BPF_LL(0, 1, PPC_LR_STKOFF); - PPC_MTLR(0); + EMIT(PPC_RAW_MTLR(0)); PPC_BPF_LL(r_D, 1, -(REG_SZ*(32-r_D))); PPC_BPF_LL(r_HL, 1, -(REG_SZ*(32-r_HL))); } @@ -100,7 +100,7 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) } /* The RETs have left a return value in R3. */ - PPC_BLR(); + EMIT(PPC_RAW_BLR()); } #define CHOOSE_LOAD_FUNC(K, func) \ @@ -134,124 +134,124 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, /*** ALU ops ***/ case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */ ctx->seen |= SEEN_XREG; - PPC_ADD(r_A, r_A, r_X); + EMIT(PPC_RAW_ADD(r_A, r_A, r_X)); break; case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */ if (!K) break; - PPC_ADDI(r_A, r_A, IMM_L(K)); + EMIT(PPC_RAW_ADDI(r_A, r_A, IMM_L(K))); if (K >= 32768) - PPC_ADDIS(r_A, r_A, IMM_HA(K)); + EMIT(PPC_RAW_ADDIS(r_A, r_A, IMM_HA(K))); break; case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */ ctx->seen |= SEEN_XREG; - PPC_SUB(r_A, r_A, r_X); + EMIT(PPC_RAW_SUB(r_A, r_A, r_X)); break; case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ if (!K) break; - PPC_ADDI(r_A, r_A, IMM_L(-K)); + EMIT(PPC_RAW_ADDI(r_A, r_A, IMM_L(-K))); if (K >= 32768) - PPC_ADDIS(r_A, r_A, IMM_HA(-K)); + EMIT(PPC_RAW_ADDIS(r_A, r_A, IMM_HA(-K))); break; case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */ ctx->seen |= SEEN_XREG; - PPC_MULW(r_A, r_A, r_X); + EMIT(PPC_RAW_MULW(r_A, r_A, r_X)); break; case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ if (K < 32768) - PPC_MULI(r_A, r_A, K); + EMIT(PPC_RAW_MULI(r_A, r_A, K)); else { PPC_LI32(r_scratch1, K); - PPC_MULW(r_A, r_A, r_scratch1); + EMIT(PPC_RAW_MULW(r_A, r_A, r_scratch1)); } break; case BPF_ALU | BPF_MOD | BPF_X: /* A %= X; */ case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */ ctx->seen |= SEEN_XREG; - PPC_CMPWI(r_X, 0); + EMIT(PPC_RAW_CMPWI(r_X, 0)); if (ctx->pc_ret0 != -1) { PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); } else { PPC_BCC_SHORT(COND_NE, (ctx->idx*4)+12); - PPC_LI(r_ret, 0); + EMIT(PPC_RAW_LI(r_ret, 0)); PPC_JMP(exit_addr); } if (code == (BPF_ALU | BPF_MOD | BPF_X)) { - PPC_DIVWU(r_scratch1, r_A, r_X); - PPC_MULW(r_scratch1, r_X, r_scratch1); - PPC_SUB(r_A, r_A, r_scratch1); + EMIT(PPC_RAW_DIVWU(r_scratch1, r_A, r_X)); + EMIT(PPC_RAW_MULW(r_scratch1, r_X, r_scratch1)); + EMIT(PPC_RAW_SUB(r_A, r_A, r_scratch1)); } else { - PPC_DIVWU(r_A, r_A, r_X); + EMIT(PPC_RAW_DIVWU(r_A, r_A, r_X)); } break; case BPF_ALU | BPF_MOD | BPF_K: /* A %= K; */ PPC_LI32(r_scratch2, K); - PPC_DIVWU(r_scratch1, r_A, r_scratch2); - PPC_MULW(r_scratch1, r_scratch2, r_scratch1); - PPC_SUB(r_A, r_A, r_scratch1); + EMIT(PPC_RAW_DIVWU(r_scratch1, r_A, r_scratch2)); + EMIT(PPC_RAW_MULW(r_scratch1, r_scratch2, r_scratch1)); + EMIT(PPC_RAW_SUB(r_A, r_A, r_scratch1)); break; case BPF_ALU | BPF_DIV | BPF_K: /* A /= K */ if (K == 1) break; PPC_LI32(r_scratch1, K); - PPC_DIVWU(r_A, r_A, r_scratch1); + EMIT(PPC_RAW_DIVWU(r_A, r_A, r_scratch1)); break; case BPF_ALU | BPF_AND | BPF_X: ctx->seen |= SEEN_XREG; - PPC_AND(r_A, r_A, r_X); + EMIT(PPC_RAW_AND(r_A, r_A, r_X)); break; case BPF_ALU | BPF_AND | BPF_K: if (!IMM_H(K)) - PPC_ANDI(r_A, r_A, K); + EMIT(PPC_RAW_ANDI(r_A, r_A, K)); else { PPC_LI32(r_scratch1, K); - PPC_AND(r_A, r_A, r_scratch1); + EMIT(PPC_RAW_AND(r_A, r_A, r_scratch1)); } break; case BPF_ALU | BPF_OR | BPF_X: ctx->seen |= SEEN_XREG; - PPC_OR(r_A, r_A, r_X); + EMIT(PPC_RAW_OR(r_A, r_A, r_X)); break; case BPF_ALU | BPF_OR | BPF_K: if (IMM_L(K)) - PPC_ORI(r_A, r_A, IMM_L(K)); + EMIT(PPC_RAW_ORI(r_A, r_A, IMM_L(K))); if (K >= 65536) - PPC_ORIS(r_A, r_A, IMM_H(K)); + EMIT(PPC_RAW_ORIS(r_A, r_A, IMM_H(K))); break; case BPF_ANC | SKF_AD_ALU_XOR_X: case BPF_ALU | BPF_XOR | BPF_X: /* A ^= X */ ctx->seen |= SEEN_XREG; - PPC_XOR(r_A, r_A, r_X); + EMIT(PPC_RAW_XOR(r_A, r_A, r_X)); break; case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ if (IMM_L(K)) - PPC_XORI(r_A, r_A, IMM_L(K)); + EMIT(PPC_RAW_XORI(r_A, r_A, IMM_L(K))); if (K >= 65536) - PPC_XORIS(r_A, r_A, IMM_H(K)); + EMIT(PPC_RAW_XORIS(r_A, r_A, IMM_H(K))); break; case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X; */ ctx->seen |= SEEN_XREG; - PPC_SLW(r_A, r_A, r_X); + EMIT(PPC_RAW_SLW(r_A, r_A, r_X)); break; case BPF_ALU | BPF_LSH | BPF_K: if (K == 0) break; else - PPC_SLWI(r_A, r_A, K); + EMIT(PPC_RAW_SLWI(r_A, r_A, K)); break; case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X; */ ctx->seen |= SEEN_XREG; - PPC_SRW(r_A, r_A, r_X); + EMIT(PPC_RAW_SRW(r_A, r_A, r_X)); break; case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K; */ if (K == 0) break; else - PPC_SRWI(r_A, r_A, K); + EMIT(PPC_RAW_SRWI(r_A, r_A, K)); break; case BPF_ALU | BPF_NEG: - PPC_NEG(r_A, r_A); + EMIT(PPC_RAW_NEG(r_A, r_A)); break; case BPF_RET | BPF_K: PPC_LI32(r_ret, K); @@ -277,24 +277,24 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, if (ctx->seen) PPC_JMP(exit_addr); else - PPC_BLR(); + EMIT(PPC_RAW_BLR()); } break; case BPF_RET | BPF_A: - PPC_MR(r_ret, r_A); + EMIT(PPC_RAW_MR(r_ret, r_A)); if (i != flen - 1) { if (ctx->seen) PPC_JMP(exit_addr); else - PPC_BLR(); + EMIT(PPC_RAW_BLR()); } break; case BPF_MISC | BPF_TAX: /* X = A */ - PPC_MR(r_X, r_A); + EMIT(PPC_RAW_MR(r_X, r_A)); break; case BPF_MISC | BPF_TXA: /* A = X */ ctx->seen |= SEEN_XREG; - PPC_MR(r_A, r_X); + EMIT(PPC_RAW_MR(r_A, r_X)); break; /*** Constant loads/M[] access ***/ @@ -305,19 +305,19 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, PPC_LI32(r_X, K); break; case BPF_LD | BPF_MEM: /* A = mem[K] */ - PPC_MR(r_A, r_M + (K & 0xf)); + EMIT(PPC_RAW_MR(r_A, r_M + (K & 0xf))); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; case BPF_LDX | BPF_MEM: /* X = mem[K] */ - PPC_MR(r_X, r_M + (K & 0xf)); + EMIT(PPC_RAW_MR(r_X, r_M + (K & 0xf))); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; case BPF_ST: /* mem[K] = A */ - PPC_MR(r_M + (K & 0xf), r_A); + EMIT(PPC_RAW_MR(r_M + (K & 0xf), r_A)); ctx->seen |= SEEN_MEM | (1<<(K & 0xf)); break; case BPF_STX: /* mem[K] = X */ - PPC_MR(r_M + (K & 0xf), r_X); + EMIT(PPC_RAW_MR(r_M + (K & 0xf), r_X)); ctx->seen |= SEEN_XREG | SEEN_MEM | (1<<(K & 0xf)); break; case BPF_LD | BPF_W | BPF_LEN: /* A = skb->len; */ @@ -346,13 +346,13 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, type) != 2); PPC_LL_OFFS(r_scratch1, r_skb, offsetof(struct sk_buff, dev)); - PPC_CMPDI(r_scratch1, 0); + EMIT(PPC_RAW_CMPDI(r_scratch1, 0)); if (ctx->pc_ret0 != -1) { PPC_BCC(COND_EQ, addrs[ctx->pc_ret0]); } else { /* Exit, returning 0; first pass hits here. */ PPC_BCC_SHORT(COND_NE, ctx->idx * 4 + 12); - PPC_LI(r_ret, 0); + EMIT(PPC_RAW_LI(r_ret, 0)); PPC_JMP(exit_addr); } if (code == (BPF_ANC | SKF_AD_IFINDEX)) { @@ -383,9 +383,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: PPC_LBZ_OFFS(r_A, r_skb, PKT_VLAN_PRESENT_OFFSET()); if (PKT_VLAN_PRESENT_BIT) - PPC_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT); + EMIT(PPC_RAW_SRWI(r_A, r_A, PKT_VLAN_PRESENT_BIT)); if (PKT_VLAN_PRESENT_BIT < 7) - PPC_ANDI(r_A, r_A, 1); + EMIT(PPC_RAW_ANDI(r_A, r_A, 1)); break; case BPF_ANC | SKF_AD_QUEUE: BUILD_BUG_ON(sizeof_field(struct sk_buff, @@ -395,8 +395,8 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, break; case BPF_ANC | SKF_AD_PKTTYPE: PPC_LBZ_OFFS(r_A, r_skb, PKT_TYPE_OFFSET()); - PPC_ANDI(r_A, r_A, PKT_TYPE_MAX); - PPC_SRWI(r_A, r_A, 5); + EMIT(PPC_RAW_ANDI(r_A, r_A, PKT_TYPE_MAX)); + EMIT(PPC_RAW_SRWI(r_A, r_A, 5)); break; case BPF_ANC | SKF_AD_CPU: PPC_BPF_LOAD_CPU(r_A); @@ -414,9 +414,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, /* Load from [K]. */ ctx->seen |= SEEN_DATAREF; PPC_FUNC_ADDR(r_scratch1, func); - PPC_MTLR(r_scratch1); + EMIT(PPC_RAW_MTLR(r_scratch1)); PPC_LI32(r_addr, K); - PPC_BLRL(); + EMIT(PPC_RAW_BLRL()); /* * Helper returns 'lt' condition on error, and an * appropriate return value in r3 @@ -440,11 +440,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, */ ctx->seen |= SEEN_DATAREF | SEEN_XREG; PPC_FUNC_ADDR(r_scratch1, func); - PPC_MTLR(r_scratch1); - PPC_ADDI(r_addr, r_X, IMM_L(K)); + EMIT(PPC_RAW_MTLR(r_scratch1)); + EMIT(PPC_RAW_ADDI(r_addr, r_X, IMM_L(K))); if (K >= 32768) - PPC_ADDIS(r_addr, r_addr, IMM_HA(K)); - PPC_BLRL(); + EMIT(PPC_RAW_ADDIS(r_addr, r_addr, IMM_HA(K))); + EMIT(PPC_RAW_BLRL()); /* If error, cr0.LT set */ PPC_BCC(COND_LT, exit_addr); break; @@ -489,30 +489,30 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JEQ | BPF_X: ctx->seen |= SEEN_XREG; - PPC_CMPLW(r_A, r_X); + EMIT(PPC_RAW_CMPLW(r_A, r_X)); break; case BPF_JMP | BPF_JSET | BPF_X: ctx->seen |= SEEN_XREG; - PPC_AND_DOT(r_scratch1, r_A, r_X); + EMIT(PPC_RAW_AND_DOT(r_scratch1, r_A, r_X)); break; case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGE | BPF_K: if (K < 32768) - PPC_CMPLWI(r_A, K); + EMIT(PPC_RAW_CMPLWI(r_A, K)); else { PPC_LI32(r_scratch1, K); - PPC_CMPLW(r_A, r_scratch1); + EMIT(PPC_RAW_CMPLW(r_A, r_scratch1)); } break; case BPF_JMP | BPF_JSET | BPF_K: if (K < 32768) /* PPC_ANDI is /only/ dot-form */ - PPC_ANDI(r_scratch1, r_A, K); + EMIT(PPC_RAW_ANDI(r_scratch1, r_A, K)); else { PPC_LI32(r_scratch1, K); - PPC_AND_DOT(r_scratch1, r_A, - r_scratch1); + EMIT(PPC_RAW_AND_DOT(r_scratch1, r_A, + r_scratch1)); } break; } diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index be3517ef0574..022103c6a201 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -95,12 +95,12 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) * invoked through a tail call. */ if (ctx->seen & SEEN_TAILCALL) { - PPC_LI(b2p[TMP_REG_1], 0); + EMIT(PPC_RAW_LI(b2p[TMP_REG_1], 0)); /* this goes in the redzone */ PPC_BPF_STL(b2p[TMP_REG_1], 1, -(BPF_PPC_STACK_SAVE + 8)); } else { - PPC_NOP(); - PPC_NOP(); + EMIT(PPC_RAW_NOP()); + EMIT(PPC_RAW_NOP()); } #define BPF_TAILCALL_PROLOGUE_SIZE 8 @@ -129,8 +129,8 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) /* Setup frame pointer to point to the bpf stack area */ if (bpf_is_seen_register(ctx, BPF_REG_FP)) - PPC_ADDI(b2p[BPF_REG_FP], 1, - STACK_FRAME_MIN_SIZE + ctx->stack_size); + EMIT(PPC_RAW_ADDI(b2p[BPF_REG_FP], 1, + STACK_FRAME_MIN_SIZE + ctx->stack_size)); } static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx) @@ -144,10 +144,10 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx /* Tear down our stack frame */ if (bpf_has_stack_frame(ctx)) { - PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size); + EMIT(PPC_RAW_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size)); if (ctx->seen & SEEN_FUNC) { PPC_BPF_LL(0, 1, PPC_LR_STKOFF); - PPC_MTLR(0); + EMIT(PPC_RAW_MTLR(0)); } } } @@ -157,9 +157,9 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) bpf_jit_emit_common_epilogue(image, ctx); /* Move result to r3 */ - PPC_MR(3, b2p[BPF_REG_0]); + EMIT(PPC_RAW_MR(3, b2p[BPF_REG_0])); - PPC_BLR(); + EMIT(PPC_RAW_BLR()); } static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, @@ -171,7 +171,7 @@ static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, /* Load actual entry point from function descriptor */ PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); /* ... and move it to LR */ - PPC_MTLR(b2p[TMP_REG_1]); + EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1])); /* * Load TOC from function descriptor at offset 8. * We can clobber r2 since we get called through a @@ -182,9 +182,9 @@ static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, #else /* We can clobber r12 */ PPC_FUNC_ADDR(12, func); - PPC_MTLR(12); + EMIT(PPC_RAW_MTLR(12)); #endif - PPC_BLRL(); + EMIT(PPC_RAW_BLRL()); } static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, @@ -206,7 +206,7 @@ static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, * that PPC_LI64() can emit. */ for (i = ctx->idx - ctx_idx; i < 5; i++) - PPC_NOP(); + EMIT(PPC_RAW_NOP()); #ifdef PPC64_ELF_ABI_v1 /* @@ -220,8 +220,8 @@ static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, PPC_BPF_LL(12, 12, 0); #endif - PPC_MTLR(12); - PPC_BLRL(); + EMIT(PPC_RAW_MTLR(12)); + EMIT(PPC_RAW_BLRL()); } static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) @@ -239,9 +239,9 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * if (index >= array->map.max_entries) * goto out; */ - PPC_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries)); - PPC_RLWINM(b2p_index, b2p_index, 0, 0, 31); - PPC_CMPLW(b2p_index, b2p[TMP_REG_1]); + EMIT(PPC_RAW_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries))); + EMIT(PPC_RAW_RLWINM(b2p_index, b2p_index, 0, 0, 31)); + EMIT(PPC_RAW_CMPLW(b2p_index, b2p[TMP_REG_1])); PPC_BCC(COND_GE, out); /* @@ -249,42 +249,42 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 * goto out; */ PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); - PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT); + EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT)); PPC_BCC(COND_GT, out); /* * tail_call_cnt++; */ - PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], 1)); PPC_BPF_STL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); /* prog = array->ptrs[index]; */ - PPC_MULI(b2p[TMP_REG_1], b2p_index, 8); - PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array); + EMIT(PPC_RAW_MULI(b2p[TMP_REG_1], b2p_index, 8)); + EMIT(PPC_RAW_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array)); PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs)); /* * if (prog == NULL) * goto out; */ - PPC_CMPLDI(b2p[TMP_REG_1], 0); + EMIT(PPC_RAW_CMPLDI(b2p[TMP_REG_1], 0)); PPC_BCC(COND_EQ, out); /* goto *(prog->bpf_func + prologue_size); */ PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func)); #ifdef PPC64_ELF_ABI_v1 /* skip past the function descriptor */ - PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], - FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], + FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE)); #else - PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE)); #endif - PPC_MTCTR(b2p[TMP_REG_1]); + EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1])); /* tear down stack, restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); - PPC_BCTR(); + EMIT(PPC_RAW_BCTR()); /* out: */ } @@ -340,11 +340,11 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, */ case BPF_ALU | BPF_ADD | BPF_X: /* (u32) dst += (u32) src */ case BPF_ALU64 | BPF_ADD | BPF_X: /* dst += src */ - PPC_ADD(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_SUB | BPF_X: /* (u32) dst -= (u32) src */ case BPF_ALU64 | BPF_SUB | BPF_X: /* dst -= src */ - PPC_SUB(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_ADD | BPF_K: /* (u32) dst += (u32) imm */ case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ @@ -354,53 +354,53 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, imm = -imm; if (imm) { if (imm >= -32768 && imm < 32768) - PPC_ADDI(dst_reg, dst_reg, IMM_L(imm)); + EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); else { PPC_LI32(b2p[TMP_REG_1], imm); - PPC_ADD(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); } } goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */ case BPF_ALU64 | BPF_MUL | BPF_X: /* dst *= src */ if (BPF_CLASS(code) == BPF_ALU) - PPC_MULW(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_MULW(dst_reg, dst_reg, src_reg)); else - PPC_MULD(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_MULD(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_K: /* (u32) dst *= (u32) imm */ case BPF_ALU64 | BPF_MUL | BPF_K: /* dst *= imm */ if (imm >= -32768 && imm < 32768) - PPC_MULI(dst_reg, dst_reg, IMM_L(imm)); + EMIT(PPC_RAW_MULI(dst_reg, dst_reg, IMM_L(imm))); else { PPC_LI32(b2p[TMP_REG_1], imm); if (BPF_CLASS(code) == BPF_ALU) - PPC_MULW(dst_reg, dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_MULW(dst_reg, dst_reg, + b2p[TMP_REG_1])); else - PPC_MULD(dst_reg, dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_MULD(dst_reg, dst_reg, + b2p[TMP_REG_1])); } goto bpf_alu32_trunc; case BPF_ALU | BPF_DIV | BPF_X: /* (u32) dst /= (u32) src */ case BPF_ALU | BPF_MOD | BPF_X: /* (u32) dst %= (u32) src */ if (BPF_OP(code) == BPF_MOD) { - PPC_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg); - PPC_MULW(b2p[TMP_REG_1], src_reg, - b2p[TMP_REG_1]); - PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_DIVWU(b2p[TMP_REG_1], dst_reg, src_reg)); + EMIT(PPC_RAW_MULW(b2p[TMP_REG_1], src_reg, + b2p[TMP_REG_1])); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); } else - PPC_DIVWU(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU64 | BPF_DIV | BPF_X: /* dst /= src */ case BPF_ALU64 | BPF_MOD | BPF_X: /* dst %= src */ if (BPF_OP(code) == BPF_MOD) { - PPC_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg); - PPC_MULD(b2p[TMP_REG_1], src_reg, - b2p[TMP_REG_1]); - PPC_SUB(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_DIVDU(b2p[TMP_REG_1], dst_reg, src_reg)); + EMIT(PPC_RAW_MULD(b2p[TMP_REG_1], src_reg, + b2p[TMP_REG_1])); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); } else - PPC_DIVDU(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg)); break; case BPF_ALU | BPF_MOD | BPF_K: /* (u32) dst %= (u32) imm */ case BPF_ALU | BPF_DIV | BPF_K: /* (u32) dst /= (u32) imm */ @@ -415,35 +415,37 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, switch (BPF_CLASS(code)) { case BPF_ALU: if (BPF_OP(code) == BPF_MOD) { - PPC_DIVWU(b2p[TMP_REG_2], dst_reg, - b2p[TMP_REG_1]); - PPC_MULW(b2p[TMP_REG_1], + EMIT(PPC_RAW_DIVWU(b2p[TMP_REG_2], + dst_reg, + b2p[TMP_REG_1])); + EMIT(PPC_RAW_MULW(b2p[TMP_REG_1], b2p[TMP_REG_1], - b2p[TMP_REG_2]); - PPC_SUB(dst_reg, dst_reg, - b2p[TMP_REG_1]); + b2p[TMP_REG_2])); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, + b2p[TMP_REG_1])); } else - PPC_DIVWU(dst_reg, dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, + b2p[TMP_REG_1])); break; case BPF_ALU64: if (BPF_OP(code) == BPF_MOD) { - PPC_DIVDU(b2p[TMP_REG_2], dst_reg, - b2p[TMP_REG_1]); - PPC_MULD(b2p[TMP_REG_1], + EMIT(PPC_RAW_DIVDU(b2p[TMP_REG_2], + dst_reg, + b2p[TMP_REG_1])); + EMIT(PPC_RAW_MULD(b2p[TMP_REG_1], b2p[TMP_REG_1], - b2p[TMP_REG_2]); - PPC_SUB(dst_reg, dst_reg, - b2p[TMP_REG_1]); + b2p[TMP_REG_2])); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, + b2p[TMP_REG_1])); } else - PPC_DIVDU(dst_reg, dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, + b2p[TMP_REG_1])); break; } goto bpf_alu32_trunc; case BPF_ALU | BPF_NEG: /* (u32) dst = -dst */ case BPF_ALU64 | BPF_NEG: /* dst = -dst */ - PPC_NEG(dst_reg, dst_reg); + EMIT(PPC_RAW_NEG(dst_reg, dst_reg)); goto bpf_alu32_trunc; /* @@ -451,101 +453,101 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, */ case BPF_ALU | BPF_AND | BPF_X: /* (u32) dst = dst & src */ case BPF_ALU64 | BPF_AND | BPF_X: /* dst = dst & src */ - PPC_AND(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_AND(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_AND | BPF_K: /* (u32) dst = dst & imm */ case BPF_ALU64 | BPF_AND | BPF_K: /* dst = dst & imm */ if (!IMM_H(imm)) - PPC_ANDI(dst_reg, dst_reg, IMM_L(imm)); + EMIT(PPC_RAW_ANDI(dst_reg, dst_reg, IMM_L(imm))); else { /* Sign-extended */ PPC_LI32(b2p[TMP_REG_1], imm); - PPC_AND(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_AND(dst_reg, dst_reg, b2p[TMP_REG_1])); } goto bpf_alu32_trunc; case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */ case BPF_ALU64 | BPF_OR | BPF_X: /* dst = dst | src */ - PPC_OR(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_OR | BPF_K:/* dst = (u32) dst | (u32) imm */ case BPF_ALU64 | BPF_OR | BPF_K:/* dst = dst | imm */ if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) { /* Sign-extended */ PPC_LI32(b2p[TMP_REG_1], imm); - PPC_OR(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_1])); } else { if (IMM_L(imm)) - PPC_ORI(dst_reg, dst_reg, IMM_L(imm)); + EMIT(PPC_RAW_ORI(dst_reg, dst_reg, IMM_L(imm))); if (IMM_H(imm)) - PPC_ORIS(dst_reg, dst_reg, IMM_H(imm)); + EMIT(PPC_RAW_ORIS(dst_reg, dst_reg, IMM_H(imm))); } goto bpf_alu32_trunc; case BPF_ALU | BPF_XOR | BPF_X: /* (u32) dst ^= src */ case BPF_ALU64 | BPF_XOR | BPF_X: /* dst ^= src */ - PPC_XOR(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_XOR(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_XOR | BPF_K: /* (u32) dst ^= (u32) imm */ case BPF_ALU64 | BPF_XOR | BPF_K: /* dst ^= imm */ if (imm < 0 && BPF_CLASS(code) == BPF_ALU64) { /* Sign-extended */ PPC_LI32(b2p[TMP_REG_1], imm); - PPC_XOR(dst_reg, dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_XOR(dst_reg, dst_reg, b2p[TMP_REG_1])); } else { if (IMM_L(imm)) - PPC_XORI(dst_reg, dst_reg, IMM_L(imm)); + EMIT(PPC_RAW_XORI(dst_reg, dst_reg, IMM_L(imm))); if (IMM_H(imm)) - PPC_XORIS(dst_reg, dst_reg, IMM_H(imm)); + EMIT(PPC_RAW_XORIS(dst_reg, dst_reg, IMM_H(imm))); } goto bpf_alu32_trunc; case BPF_ALU | BPF_LSH | BPF_X: /* (u32) dst <<= (u32) src */ /* slw clears top 32 bits */ - PPC_SLW(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SLW(dst_reg, dst_reg, src_reg)); /* skip zero extension move, but set address map. */ if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; case BPF_ALU64 | BPF_LSH | BPF_X: /* dst <<= src; */ - PPC_SLD(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SLD(dst_reg, dst_reg, src_reg)); break; case BPF_ALU | BPF_LSH | BPF_K: /* (u32) dst <<== (u32) imm */ /* with imm 0, we still need to clear top 32 bits */ - PPC_SLWI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SLWI(dst_reg, dst_reg, imm)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; case BPF_ALU64 | BPF_LSH | BPF_K: /* dst <<== imm */ if (imm != 0) - PPC_SLDI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, imm)); break; case BPF_ALU | BPF_RSH | BPF_X: /* (u32) dst >>= (u32) src */ - PPC_SRW(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SRW(dst_reg, dst_reg, src_reg)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; case BPF_ALU64 | BPF_RSH | BPF_X: /* dst >>= src */ - PPC_SRD(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SRD(dst_reg, dst_reg, src_reg)); break; case BPF_ALU | BPF_RSH | BPF_K: /* (u32) dst >>= (u32) imm */ - PPC_SRWI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SRWI(dst_reg, dst_reg, imm)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; case BPF_ALU64 | BPF_RSH | BPF_K: /* dst >>= imm */ if (imm != 0) - PPC_SRDI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SRDI(dst_reg, dst_reg, imm)); break; case BPF_ALU | BPF_ARSH | BPF_X: /* (s32) dst >>= src */ - PPC_SRAW(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SRAW(dst_reg, dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU64 | BPF_ARSH | BPF_X: /* (s64) dst >>= src */ - PPC_SRAD(dst_reg, dst_reg, src_reg); + EMIT(PPC_RAW_SRAD(dst_reg, dst_reg, src_reg)); break; case BPF_ALU | BPF_ARSH | BPF_K: /* (s32) dst >>= imm */ - PPC_SRAWI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SRAWI(dst_reg, dst_reg, imm)); goto bpf_alu32_trunc; case BPF_ALU64 | BPF_ARSH | BPF_K: /* (s64) dst >>= imm */ if (imm != 0) - PPC_SRADI(dst_reg, dst_reg, imm); + EMIT(PPC_RAW_SRADI(dst_reg, dst_reg, imm)); break; /* @@ -555,10 +557,10 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */ if (imm == 1) { /* special mov32 for zext */ - PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31); + EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31)); break; } - PPC_MR(dst_reg, src_reg); + EMIT(PPC_RAW_MR(dst_reg, src_reg)); goto bpf_alu32_trunc; case BPF_ALU | BPF_MOV | BPF_K: /* (u32) dst = imm */ case BPF_ALU64 | BPF_MOV | BPF_K: /* dst = (s64) imm */ @@ -572,7 +574,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, bpf_alu32_trunc: /* Truncate to 32-bits */ if (BPF_CLASS(code) == BPF_ALU && !fp->aux->verifier_zext) - PPC_RLWINM(dst_reg, dst_reg, 0, 0, 31); + EMIT(PPC_RAW_RLWINM(dst_reg, dst_reg, 0, 0, 31)); break; /* @@ -590,11 +592,11 @@ bpf_alu32_trunc: switch (imm) { case 16: /* Rotate 8 bits left & mask with 0x0000ff00 */ - PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23); + EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23)); /* Rotate 8 bits right & insert LSB to reg */ - PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31); + EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31)); /* Move result back to dst_reg */ - PPC_MR(dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 32: /* @@ -602,12 +604,12 @@ bpf_alu32_trunc: * 2 bytes are already in their final position * -- byte 2 and 4 (of bytes 1, 2, 3 and 4) */ - PPC_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31); + EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31)); /* Rotate 24 bits and insert byte 1 */ - PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7); + EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7)); /* Rotate 24 bits and insert byte 3 */ - PPC_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23); - PPC_MR(dst_reg, b2p[TMP_REG_1]); + EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23)); + EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); break; case 64: /* @@ -619,8 +621,8 @@ bpf_alu32_trunc: * same across all passes */ PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); - PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx)); - PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); + EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); break; } break; @@ -629,14 +631,14 @@ emit_clear: switch (imm) { case 16: /* zero-extend 16 bits into 64 bits */ - PPC_RLDICL(dst_reg, dst_reg, 0, 48); + EMIT(PPC_RAW_RLDICL(dst_reg, dst_reg, 0, 48)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; case 32: if (!fp->aux->verifier_zext) /* zero-extend 32 bits into 64 bits */ - PPC_RLDICL(dst_reg, dst_reg, 0, 32); + EMIT(PPC_RAW_RLDICL(dst_reg, dst_reg, 0, 32)); break; case 64: /* nop */ @@ -650,18 +652,18 @@ emit_clear: case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */ case BPF_ST | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = imm */ if (BPF_CLASS(code) == BPF_ST) { - PPC_LI(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm)); src_reg = b2p[TMP_REG_1]; } - PPC_STB(src_reg, dst_reg, off); + EMIT(PPC_RAW_STB(src_reg, dst_reg, off)); break; case BPF_STX | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = src */ case BPF_ST | BPF_MEM | BPF_H: /* (u16 *)(dst + off) = imm */ if (BPF_CLASS(code) == BPF_ST) { - PPC_LI(b2p[TMP_REG_1], imm); + EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm)); src_reg = b2p[TMP_REG_1]; } - PPC_STH(src_reg, dst_reg, off); + EMIT(PPC_RAW_STH(src_reg, dst_reg, off)); break; case BPF_STX | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = src */ case BPF_ST | BPF_MEM | BPF_W: /* *(u32 *)(dst + off) = imm */ @@ -669,7 +671,7 @@ emit_clear: PPC_LI32(b2p[TMP_REG_1], imm); src_reg = b2p[TMP_REG_1]; } - PPC_STW(src_reg, dst_reg, off); + EMIT(PPC_RAW_STW(src_reg, dst_reg, off)); break; case BPF_STX | BPF_MEM | BPF_DW: /* (u64 *)(dst + off) = src */ case BPF_ST | BPF_MEM | BPF_DW: /* *(u64 *)(dst + off) = imm */ @@ -686,24 +688,24 @@ emit_clear: /* *(u32 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_W: /* Get EA into TMP_REG_1 */ - PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ - PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); + EMIT(PPC_RAW_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0)); /* add value from src_reg into this */ - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); + EMIT(PPC_RAW_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg)); /* store result back */ - PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); + EMIT(PPC_RAW_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1])); /* we're done if this succeeded */ PPC_BCC_SHORT(COND_NE, tmp_idx); break; /* *(u64 *)(dst + off) += src */ case BPF_STX | BPF_XADD | BPF_DW: - PPC_ADDI(b2p[TMP_REG_1], dst_reg, off); + EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); tmp_idx = ctx->idx * 4; - PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0); - PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg); - PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]); + EMIT(PPC_RAW_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0)); + EMIT(PPC_RAW_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg)); + EMIT(PPC_RAW_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1])); PPC_BCC_SHORT(COND_NE, tmp_idx); break; @@ -712,19 +714,19 @@ emit_clear: */ /* dst = *(u8 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_B: - PPC_LBZ(dst_reg, src_reg, off); + EMIT(PPC_RAW_LBZ(dst_reg, src_reg, off)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; /* dst = *(u16 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_H: - PPC_LHZ(dst_reg, src_reg, off); + EMIT(PPC_RAW_LHZ(dst_reg, src_reg, off)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; /* dst = *(u32 *)(ul) (src + off) */ case BPF_LDX | BPF_MEM | BPF_W: - PPC_LWZ(dst_reg, src_reg, off); + EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); if (insn_is_zext(&insn[i + 1])) addrs[++i] = ctx->idx * 4; break; @@ -775,7 +777,7 @@ emit_clear: else bpf_jit_emit_func_call_rel(image, ctx, func_addr); /* move return value from r3 to BPF_REG_0 */ - PPC_MR(b2p[BPF_REG_0], 3); + EMIT(PPC_RAW_MR(b2p[BPF_REG_0], 3)); break; /* @@ -860,9 +862,9 @@ cond_branch: case BPF_JMP32 | BPF_JNE | BPF_X: /* unsigned comparison */ if (BPF_CLASS(code) == BPF_JMP32) - PPC_CMPLW(dst_reg, src_reg); + EMIT(PPC_RAW_CMPLW(dst_reg, src_reg)); else - PPC_CMPLD(dst_reg, src_reg); + EMIT(PPC_RAW_CMPLD(dst_reg, src_reg)); break; case BPF_JMP | BPF_JSGT | BPF_X: case BPF_JMP | BPF_JSLT | BPF_X: @@ -874,21 +876,21 @@ cond_branch: case BPF_JMP32 | BPF_JSLE | BPF_X: /* signed comparison */ if (BPF_CLASS(code) == BPF_JMP32) - PPC_CMPW(dst_reg, src_reg); + EMIT(PPC_RAW_CMPW(dst_reg, src_reg)); else - PPC_CMPD(dst_reg, src_reg); + EMIT(PPC_RAW_CMPD(dst_reg, src_reg)); break; case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: if (BPF_CLASS(code) == BPF_JMP) { - PPC_AND_DOT(b2p[TMP_REG_1], dst_reg, - src_reg); + EMIT(PPC_RAW_AND_DOT(b2p[TMP_REG_1], dst_reg, + src_reg)); } else { int tmp_reg = b2p[TMP_REG_1]; - PPC_AND(tmp_reg, dst_reg, src_reg); - PPC_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0, - 31); + EMIT(PPC_RAW_AND(tmp_reg, dst_reg, src_reg)); + EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0, + 31)); } break; case BPF_JMP | BPF_JNE | BPF_K: @@ -912,19 +914,19 @@ cond_branch: */ if (imm >= 0 && imm < 32768) { if (is_jmp32) - PPC_CMPLWI(dst_reg, imm); + EMIT(PPC_RAW_CMPLWI(dst_reg, imm)); else - PPC_CMPLDI(dst_reg, imm); + EMIT(PPC_RAW_CMPLDI(dst_reg, imm)); } else { /* sign-extending load */ PPC_LI32(b2p[TMP_REG_1], imm); /* ... but unsigned comparison */ if (is_jmp32) - PPC_CMPLW(dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_CMPLW(dst_reg, + b2p[TMP_REG_1])); else - PPC_CMPLD(dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_CMPLD(dst_reg, + b2p[TMP_REG_1])); } break; } @@ -945,17 +947,17 @@ cond_branch: */ if (imm >= -32768 && imm < 32768) { if (is_jmp32) - PPC_CMPWI(dst_reg, imm); + EMIT(PPC_RAW_CMPWI(dst_reg, imm)); else - PPC_CMPDI(dst_reg, imm); + EMIT(PPC_RAW_CMPDI(dst_reg, imm)); } else { PPC_LI32(b2p[TMP_REG_1], imm); if (is_jmp32) - PPC_CMPW(dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_CMPW(dst_reg, + b2p[TMP_REG_1])); else - PPC_CMPD(dst_reg, - b2p[TMP_REG_1]); + EMIT(PPC_RAW_CMPD(dst_reg, + b2p[TMP_REG_1])); } break; } @@ -964,19 +966,19 @@ cond_branch: /* andi does not sign-extend the immediate */ if (imm >= 0 && imm < 32768) /* PPC_ANDI is _only/always_ dot-form */ - PPC_ANDI(b2p[TMP_REG_1], dst_reg, imm); + EMIT(PPC_RAW_ANDI(b2p[TMP_REG_1], dst_reg, imm)); else { int tmp_reg = b2p[TMP_REG_1]; PPC_LI32(tmp_reg, imm); if (BPF_CLASS(code) == BPF_JMP) { - PPC_AND_DOT(tmp_reg, dst_reg, - tmp_reg); + EMIT(PPC_RAW_AND_DOT(tmp_reg, dst_reg, + tmp_reg)); } else { - PPC_AND(tmp_reg, dst_reg, - tmp_reg); - PPC_RLWINM_DOT(tmp_reg, tmp_reg, - 0, 0, 31); + EMIT(PPC_RAW_AND(tmp_reg, dst_reg, + tmp_reg)); + EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg, + 0, 0, 31)); } } break; diff --git a/arch/powerpc/perf/Makefile b/arch/powerpc/perf/Makefile index 53d614e98537..c02854dea2b2 100644 --- a/arch/powerpc/perf/Makefile +++ b/arch/powerpc/perf/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_PPC_PERF_CTRS) += core-book3s.o bhrb.o obj64-$(CONFIG_PPC_PERF_CTRS) += ppc970-pmu.o power5-pmu.o \ power5+-pmu.o power6-pmu.o power7-pmu.o \ isa207-common.o power8-pmu.o power9-pmu.o \ - generic-compat-pmu.o + generic-compat-pmu.o power10-pmu.o obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o obj-$(CONFIG_PPC_POWERNV) += imc-pmu.o diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h index 7a2cb9e1181a..ae24d4a00da6 100644 --- a/arch/powerpc/perf/callchain.h +++ b/arch/powerpc/perf/callchain.h @@ -2,7 +2,7 @@ #ifndef _POWERPC_PERF_CALLCHAIN_H #define _POWERPC_PERF_CALLCHAIN_H -int read_user_stack_slow(void __user *ptr, void *buf, int nb); +int read_user_stack_slow(const void __user *ptr, void *buf, int nb); void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry, @@ -16,4 +16,27 @@ static inline bool invalid_user_sp(unsigned long sp) return (!sp || (sp & mask) || (sp > top)); } +/* + * On 32-bit we just access the address and let hash_page create a + * HPTE if necessary, so there is no need to fall back to reading + * the page tables. Since this is called at interrupt level, + * do_page_fault() won't treat a DSI as a page fault. + */ +static inline int __read_user_stack(const void __user *ptr, void *ret, + size_t size) +{ + unsigned long addr = (unsigned long)ptr; + int rc; + + if (addr > TASK_SIZE - size || (addr & (size - 1))) + return -EFAULT; + + rc = copy_from_user_nofault(ret, ptr, size); + + if (IS_ENABLED(CONFIG_PPC64) && rc) + return read_user_stack_slow(ptr, ret, size); + + return rc; +} + #endif /* _POWERPC_PERF_CALLCHAIN_H */ diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index 542e68b8eae0..64e4013d8060 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -30,26 +30,9 @@ #endif /* CONFIG_PPC64 */ -/* - * On 32-bit we just access the address and let hash_page create a - * HPTE if necessary, so there is no need to fall back to reading - * the page tables. Since this is called at interrupt level, - * do_page_fault() won't treat a DSI as a page fault. - */ -static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) +static int read_user_stack_32(const unsigned int __user *ptr, unsigned int *ret) { - int rc; - - if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned int) || - ((unsigned long)ptr & 3)) - return -EFAULT; - - rc = copy_from_user_nofault(ret, ptr, sizeof(*ret)); - - if (IS_ENABLED(CONFIG_PPC64) && rc) - return read_user_stack_slow(ptr, ret, 4); - - return rc; + return __read_user_stack(ptr, ret, sizeof(*ret)); } /* diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index fa2a1b83b9b0..fed90e827f3a 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -23,7 +23,7 @@ * interrupt context, so if the access faults, we read the page tables * to find which page (if any) is mapped and access it directly. */ -int read_user_stack_slow(void __user *ptr, void *buf, int nb) +int read_user_stack_slow(const void __user *ptr, void *buf, int nb) { unsigned long addr = (unsigned long) ptr; @@ -44,16 +44,9 @@ int read_user_stack_slow(void __user *ptr, void *buf, int nb) return -EFAULT; } -static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) +static int read_user_stack_64(const unsigned long __user *ptr, unsigned long *ret) { - if ((unsigned long)ptr > TASK_SIZE - sizeof(unsigned long) || - ((unsigned long)ptr & 7)) - return -EFAULT; - - if (!copy_from_user_nofault(ret, ptr, sizeof(*ret))) - return 0; - - return read_user_stack_slow(ptr, ret, 8); + return __read_user_stack(ptr, ret, sizeof(*ret)); } /* diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 01d70280d287..78fe34986594 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -37,12 +37,7 @@ struct cpu_hw_events { struct perf_event *event[MAX_HWEVENTS]; u64 events[MAX_HWEVENTS]; unsigned int flags[MAX_HWEVENTS]; - /* - * The order of the MMCR array is: - * - 64-bit, MMCR0, MMCR1, MMCRA, MMCR2 - * - 32-bit, MMCR0, MMCR1, MMCR2 - */ - unsigned long mmcr[4]; + struct mmcr_regs mmcr; struct perf_event *limited_counter[MAX_LIMITED_HWCOUNTERS]; u8 limited_hwidx[MAX_LIMITED_HWCOUNTERS]; u64 alternatives[MAX_HWEVENTS][MAX_EVENT_ALTERNATIVES]; @@ -77,6 +72,11 @@ static unsigned int freeze_events_kernel = MMCR0_FCS; /* * 32-bit doesn't have MMCRA but does have an MMCR2, * and a few other names are different. + * Also 32-bit doesn't have MMCR3, SIER2 and SIER3. + * Define them as zero knowing that any code path accessing + * these registers (via mtspr/mfspr) are done under ppmu flag + * check for PPMU_ARCH_31 and we will not enter that code path + * for 32-bit. */ #ifdef CONFIG_PPC32 @@ -90,7 +90,11 @@ static unsigned int freeze_events_kernel = MMCR0_FCS; #define MMCR0_PMCC_U6 0 #define SPRN_MMCRA SPRN_MMCR2 +#define SPRN_MMCR3 0 +#define SPRN_SIER2 0 +#define SPRN_SIER3 0 #define MMCRA_SAMPLE_ENABLE 0 +#define MMCRA_BHRB_DISABLE 0 static inline unsigned long perf_ip_adjust(struct pt_regs *regs) { @@ -121,7 +125,7 @@ static void ebb_event_add(struct perf_event *event) { } static void ebb_switch_out(unsigned long mmcr0) { } static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw) { - return cpuhw->mmcr[0]; + return cpuhw->mmcr.mmcr0; } static inline void power_pmu_bhrb_enable(struct perf_event *event) {} @@ -466,8 +470,11 @@ static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events * * addresses at this point. Check the privileges before * exporting it to userspace (avoid exposure of regions * where we could have speculative execution) + * Incase of ISA v3.1, BHRB will capture only user-space + * addresses, hence include a check before filtering code */ - if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0) + if (!(ppmu->flags & PPMU_ARCH_31) && + is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0) continue; /* Branches are read most recent first (ie. mfbhrb 0 is @@ -586,11 +593,16 @@ static void ebb_switch_out(unsigned long mmcr0) current->thread.sdar = mfspr(SPRN_SDAR); current->thread.mmcr0 = mmcr0 & MMCR0_USER_MASK; current->thread.mmcr2 = mfspr(SPRN_MMCR2) & MMCR2_USER_MASK; + if (ppmu->flags & PPMU_ARCH_31) { + current->thread.mmcr3 = mfspr(SPRN_MMCR3); + current->thread.sier2 = mfspr(SPRN_SIER2); + current->thread.sier3 = mfspr(SPRN_SIER3); + } } static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw) { - unsigned long mmcr0 = cpuhw->mmcr[0]; + unsigned long mmcr0 = cpuhw->mmcr.mmcr0; if (!ebb) goto out; @@ -624,7 +636,13 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw) * unfreeze counters, it should not set exclude_xxx in its events and * instead manage the MMCR2 entirely by itself. */ - mtspr(SPRN_MMCR2, cpuhw->mmcr[3] | current->thread.mmcr2); + mtspr(SPRN_MMCR2, cpuhw->mmcr.mmcr2 | current->thread.mmcr2); + + if (ppmu->flags & PPMU_ARCH_31) { + mtspr(SPRN_MMCR3, current->thread.mmcr3); + mtspr(SPRN_SIER2, current->thread.sier2); + mtspr(SPRN_SIER3, current->thread.sier3); + } out: return mmcr0; } @@ -845,6 +863,11 @@ void perf_event_print_debug(void) pr_info("EBBRR: %016lx BESCR: %016lx\n", mfspr(SPRN_EBBRR), mfspr(SPRN_BESCR)); } + + if (ppmu->flags & PPMU_ARCH_31) { + pr_info("MMCR3: %016lx SIER2: %016lx SIER3: %016lx\n", + mfspr(SPRN_MMCR3), mfspr(SPRN_SIER2), mfspr(SPRN_SIER3)); + } #endif pr_info("SIAR: %016lx SDAR: %016lx SIER: %016lx\n", mfspr(SPRN_SIAR), sdar, sier); @@ -1196,7 +1219,7 @@ static void write_mmcr0(struct cpu_hw_events *cpuhw, unsigned long mmcr0) static void power_pmu_disable(struct pmu *pmu) { struct cpu_hw_events *cpuhw; - unsigned long flags, mmcr0, val; + unsigned long flags, mmcr0, val, mmcra; if (!ppmu) return; @@ -1229,12 +1252,24 @@ static void power_pmu_disable(struct pmu *pmu) mb(); isync(); + val = mmcra = cpuhw->mmcr.mmcra; + /* * Disable instruction sampling if it was enabled */ - if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { - mtspr(SPRN_MMCRA, - cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); + if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) + val &= ~MMCRA_SAMPLE_ENABLE; + + /* Disable BHRB via mmcra (BHRBRD) for p10 */ + if (ppmu->flags & PPMU_ARCH_31) + val |= MMCRA_BHRB_DISABLE; + + /* + * Write SPRN_MMCRA if mmcra has either disabled + * instruction sampling or BHRB. + */ + if (val != mmcra) { + mtspr(SPRN_MMCRA, mmcra); mb(); isync(); } @@ -1308,18 +1343,20 @@ static void power_pmu_enable(struct pmu *pmu) * (possibly updated for removal of events). */ if (!cpuhw->n_added) { - mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); - mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); + mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr.mmcr1); + if (ppmu->flags & PPMU_ARCH_31) + mtspr(SPRN_MMCR3, cpuhw->mmcr.mmcr3); goto out_enable; } /* * Clear all MMCR settings and recompute them for the new set of events. */ - memset(cpuhw->mmcr, 0, sizeof(cpuhw->mmcr)); + memset(&cpuhw->mmcr, 0, sizeof(cpuhw->mmcr)); if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_events, hwc_index, - cpuhw->mmcr, cpuhw->event)) { + &cpuhw->mmcr, cpuhw->event)) { /* shouldn't ever get here */ printk(KERN_ERR "oops compute_mmcr failed\n"); goto out; @@ -1333,11 +1370,11 @@ static void power_pmu_enable(struct pmu *pmu) */ event = cpuhw->event[0]; if (event->attr.exclude_user) - cpuhw->mmcr[0] |= MMCR0_FCP; + cpuhw->mmcr.mmcr0 |= MMCR0_FCP; if (event->attr.exclude_kernel) - cpuhw->mmcr[0] |= freeze_events_kernel; + cpuhw->mmcr.mmcr0 |= freeze_events_kernel; if (event->attr.exclude_hv) - cpuhw->mmcr[0] |= MMCR0_FCHV; + cpuhw->mmcr.mmcr0 |= MMCR0_FCHV; } /* @@ -1346,12 +1383,15 @@ static void power_pmu_enable(struct pmu *pmu) * Then unfreeze the events. */ ppc_set_pmu_inuse(1); - mtspr(SPRN_MMCRA, cpuhw->mmcr[2] & ~MMCRA_SAMPLE_ENABLE); - mtspr(SPRN_MMCR1, cpuhw->mmcr[1]); - mtspr(SPRN_MMCR0, (cpuhw->mmcr[0] & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) + mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra & ~MMCRA_SAMPLE_ENABLE); + mtspr(SPRN_MMCR1, cpuhw->mmcr.mmcr1); + mtspr(SPRN_MMCR0, (cpuhw->mmcr.mmcr0 & ~(MMCR0_PMC1CE | MMCR0_PMCjCE)) | MMCR0_FC); if (ppmu->flags & PPMU_ARCH_207S) - mtspr(SPRN_MMCR2, cpuhw->mmcr[3]); + mtspr(SPRN_MMCR2, cpuhw->mmcr.mmcr2); + + if (ppmu->flags & PPMU_ARCH_31) + mtspr(SPRN_MMCR3, cpuhw->mmcr.mmcr3); /* * Read off any pre-existing events that need to move @@ -1402,7 +1442,7 @@ static void power_pmu_enable(struct pmu *pmu) perf_event_update_userpage(event); } cpuhw->n_limited = n_lim; - cpuhw->mmcr[0] |= MMCR0_PMXE | MMCR0_FCECE; + cpuhw->mmcr.mmcr0 |= MMCR0_PMXE | MMCR0_FCECE; out_enable: pmao_restore_workaround(ebb); @@ -1418,9 +1458,9 @@ static void power_pmu_enable(struct pmu *pmu) /* * Enable instruction sampling if necessary */ - if (cpuhw->mmcr[2] & MMCRA_SAMPLE_ENABLE) { + if (cpuhw->mmcr.mmcra & MMCRA_SAMPLE_ENABLE) { mb(); - mtspr(SPRN_MMCRA, cpuhw->mmcr[2]); + mtspr(SPRN_MMCRA, cpuhw->mmcr.mmcra); } out: @@ -1550,7 +1590,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) cpuhw->flags[i-1] = cpuhw->flags[i]; } --cpuhw->n_events; - ppmu->disable_pmc(event->hw.idx - 1, cpuhw->mmcr); + ppmu->disable_pmc(event->hw.idx - 1, &cpuhw->mmcr); if (event->hw.idx) { write_pmc(event->hw.idx, 0); event->hw.idx = 0; @@ -1571,7 +1611,7 @@ static void power_pmu_del(struct perf_event *event, int ef_flags) } if (cpuhw->n_events == 0) { /* disable exceptions if no events are running */ - cpuhw->mmcr[0] &= ~(MMCR0_PMXE | MMCR0_FCECE); + cpuhw->mmcr.mmcr0 &= ~(MMCR0_PMXE | MMCR0_FCECE); } if (has_branch_stack(event)) @@ -1795,7 +1835,7 @@ static void hw_perf_event_destroy(struct perf_event *event) static int hw_perf_cache_event(u64 config, u64 *eventp) { unsigned long type, op, result; - int ev; + u64 ev; if (!ppmu->cache_events) return -EINVAL; @@ -2246,7 +2286,7 @@ static void __perf_event_interrupt(struct pt_regs *regs) * XXX might want to use MSR.PM to keep the events frozen until * we get back out of this interrupt. */ - write_mmcr0(cpuhw, cpuhw->mmcr[0]); + write_mmcr0(cpuhw, cpuhw->mmcr.mmcr0); if (nmi) nmi_exit(); @@ -2268,7 +2308,7 @@ static int power_pmu_prepare_cpu(unsigned int cpu) if (ppmu) { memset(cpuhw, 0, sizeof(*cpuhw)); - cpuhw->mmcr[0] = MMCR0_FC; + cpuhw->mmcr.mmcr0 = MMCR0_FC; } return 0; } @@ -2314,6 +2354,8 @@ static int __init init_ppc64_pmu(void) return 0; else if (!init_power9_pmu()) return 0; + else if (!init_power10_pmu()) + return 0; else if (!init_ppc970_pmu()) return 0; else diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c index 5e5a54d5588e..eb8a6aaf4cc1 100644 --- a/arch/powerpc/perf/generic-compat-pmu.c +++ b/arch/powerpc/perf/generic-compat-pmu.c @@ -101,7 +101,7 @@ static int compat_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 generic_compat_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [ C(L1D) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0, diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index db213eb7cb02..cdb7bfbd157e 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -31,6 +31,8 @@ static int interface_version; /* Whether we have to aggregate result data for some domains. */ static bool aggregate_result_elements; +static cpumask_t hv_24x7_cpumask; + static bool domain_is_valid(unsigned domain) { switch (domain) { @@ -446,6 +448,12 @@ static ssize_t device_show_string(struct device *dev, return sprintf(buf, "%s\n", (char *)d->var); } +static ssize_t cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &hv_24x7_cpumask); +} + static ssize_t sockets_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -1113,6 +1121,7 @@ static DEVICE_ATTR_RO(domains); static DEVICE_ATTR_RO(sockets); static DEVICE_ATTR_RO(chipspersocket); static DEVICE_ATTR_RO(coresperchip); +static DEVICE_ATTR_RO(cpumask); static struct bin_attribute *if_bin_attrs[] = { &bin_attr_catalog, @@ -1126,6 +1135,7 @@ static struct attribute *if_attrs[] = { &dev_attr_sockets.attr, &dev_attr_chipspersocket.attr, &dev_attr_coresperchip.attr, + &dev_attr_cpumask.attr, NULL, }; @@ -1641,6 +1651,45 @@ static struct pmu h_24x7_pmu = { .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; +static int ppc_hv_24x7_cpu_online(unsigned int cpu) +{ + if (cpumask_empty(&hv_24x7_cpumask)) + cpumask_set_cpu(cpu, &hv_24x7_cpumask); + + return 0; +} + +static int ppc_hv_24x7_cpu_offline(unsigned int cpu) +{ + int target; + + /* Check if exiting cpu is used for collecting 24x7 events */ + if (!cpumask_test_and_clear_cpu(cpu, &hv_24x7_cpumask)) + return 0; + + /* Find a new cpu to collect 24x7 events */ + target = cpumask_last(cpu_active_mask); + + if (target < 0 || target >= nr_cpu_ids) { + pr_err("hv_24x7: CPU hotplug init failed\n"); + return -1; + } + + /* Migrate 24x7 events to the new target */ + cpumask_set_cpu(target, &hv_24x7_cpumask); + perf_pmu_migrate_context(&h_24x7_pmu, cpu, target); + + return 0; +} + +static int hv_24x7_cpu_hotplug_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE, + "perf/powerpc/hv_24x7:online", + ppc_hv_24x7_cpu_online, + ppc_hv_24x7_cpu_offline); +} + static int hv_24x7_init(void) { int r; @@ -1685,6 +1734,11 @@ static int hv_24x7_init(void) if (r) return r; + /* init cpuhotplug */ + r = hv_24x7_cpu_hotplug_init(); + if (r) + return r; + r = perf_pmu_register(&h_24x7_pmu, h_24x7_pmu.name, -1); if (r) return r; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 0edcfd0b491d..a45d694a5d5d 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1288,11 +1288,30 @@ static int trace_imc_prepare_sample(struct trace_imc_data *mem, header->size = sizeof(*header) + event->header_size; header->misc = 0; - if (is_kernel_addr(data->ip)) - header->misc |= PERF_RECORD_MISC_KERNEL; - else - header->misc |= PERF_RECORD_MISC_USER; - + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + switch (IMC_TRACE_RECORD_VAL_HVPR(mem->val)) { + case 0:/* when MSR HV and PR not set in the trace-record */ + header->misc |= PERF_RECORD_MISC_GUEST_KERNEL; + break; + case 1: /* MSR HV is 0 and PR is 1 */ + header->misc |= PERF_RECORD_MISC_GUEST_USER; + break; + case 2: /* MSR HV is 1 and PR is 0 */ + header->misc |= PERF_RECORD_MISC_HYPERVISOR; + break; + case 3: /* MSR HV is 1 and PR is 1 */ + header->misc |= PERF_RECORD_MISC_USER; + break; + default: + pr_info("IMC: Unable to set the flag based on MSR bits\n"); + break; + } + } else { + if (is_kernel_addr(data->ip)) + header->misc |= PERF_RECORD_MISC_KERNEL; + else + header->misc |= PERF_RECORD_MISC_USER; + } perf_event_header__init_id(header, data, event); return 0; diff --git a/arch/powerpc/perf/internal.h b/arch/powerpc/perf/internal.h index f755c64da137..80bbf72bfec2 100644 --- a/arch/powerpc/perf/internal.h +++ b/arch/powerpc/perf/internal.h @@ -9,4 +9,5 @@ extern int init_power6_pmu(void); extern int init_power7_pmu(void); extern int init_power8_pmu(void); extern int init_power9_pmu(void); +extern int init_power10_pmu(void); extern int init_generic_compat_pmu(void); diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 4c86da5eb28a..964437adec18 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -55,7 +55,9 @@ static bool is_event_valid(u64 event) { u64 valid_mask = EVENT_VALID_MASK; - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (cpu_has_feature(CPU_FTR_ARCH_31)) + valid_mask = p10_EVENT_VALID_MASK; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) valid_mask = p9_EVENT_VALID_MASK; return !(event & ~valid_mask); @@ -69,6 +71,14 @@ static inline bool is_event_marked(u64 event) return false; } +static unsigned long sdar_mod_val(u64 event) +{ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + return p10_SDAR_MODE(event); + + return p9_SDAR_MODE(event); +} + static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) { /* @@ -79,7 +89,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) * MMCRA[SDAR_MODE] will be programmed as "0b01" for continous sampling * mode and will be un-changed when setting MMCRA[63] (Marked events). * - * Incase of Power9: + * Incase of Power9/power10: * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'), * or if group already have any marked events. * For rest @@ -90,8 +100,8 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra) if (cpu_has_feature(CPU_FTR_ARCH_300)) { if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE)) *mmcra &= MMCRA_SDAR_MODE_NO_UPDATES; - else if (p9_SDAR_MODE(event)) - *mmcra |= p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT; + else if (sdar_mod_val(event)) + *mmcra |= sdar_mod_val(event) << MMCRA_SDAR_MODE_SHIFT; else *mmcra |= MMCRA_SDAR_MODE_DCACHE; } else @@ -134,7 +144,11 @@ static bool is_thresh_cmp_valid(u64 event) /* * Check the mantissa upper two bits are not zero, unless the * exponent is also zero. See the THRESH_CMP_MANTISSA doc. + * Power10: thresh_cmp is replaced by l2_l3 event select. */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + return false; + cmp = (event >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; exp = cmp >> 7; @@ -251,7 +265,12 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) pmc = (event >> EVENT_PMC_SHIFT) & EVENT_PMC_MASK; unit = (event >> EVENT_UNIT_SHIFT) & EVENT_UNIT_MASK; - cache = (event >> EVENT_CACHE_SEL_SHIFT) & EVENT_CACHE_SEL_MASK; + if (cpu_has_feature(CPU_FTR_ARCH_31)) + cache = (event >> EVENT_CACHE_SEL_SHIFT) & + p10_EVENT_CACHE_SEL_MASK; + else + cache = (event >> EVENT_CACHE_SEL_SHIFT) & + EVENT_CACHE_SEL_MASK; ebb = (event >> EVENT_EBB_SHIFT) & EVENT_EBB_MASK; if (pmc) { @@ -283,7 +302,10 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } if (unit >= 6 && unit <= 9) { - if (cpu_has_feature(CPU_FTR_ARCH_300)) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) { + mask |= CNST_L2L3_GROUP_MASK; + value |= CNST_L2L3_GROUP_VAL(event >> p10_L2L3_EVENT_SHIFT); + } else if (cpu_has_feature(CPU_FTR_ARCH_300)) { mask |= CNST_CACHE_GROUP_MASK; value |= CNST_CACHE_GROUP_VAL(event & 0xff); @@ -363,10 +385,11 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } int isa207_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], + unsigned int hwc[], struct mmcr_regs *mmcr, struct perf_event *pevents[]) { unsigned long mmcra, mmcr1, mmcr2, unit, combine, psel, cache, val; + unsigned long mmcr3; unsigned int pmc, pmc_inuse; int i; @@ -379,7 +402,14 @@ int isa207_compute_mmcr(u64 event[], int n_ev, pmc_inuse |= 1 << pmc; } - mmcra = mmcr1 = mmcr2 = 0; + mmcra = mmcr1 = mmcr2 = mmcr3 = 0; + + /* + * Disable bhrb unless explicitly requested + * by setting MMCRA (BHRBRD) bit. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + mmcra |= MMCRA_BHRB_DISABLE; /* Second pass: assign PMCs, set all MMCR1 fields */ for (i = 0; i < n_ev; ++i) { @@ -438,8 +468,17 @@ int isa207_compute_mmcr(u64 event[], int n_ev, mmcra |= val << MMCRA_THR_CTL_SHIFT; val = (event[i] >> EVENT_THR_SEL_SHIFT) & EVENT_THR_SEL_MASK; mmcra |= val << MMCRA_THR_SEL_SHIFT; - val = (event[i] >> EVENT_THR_CMP_SHIFT) & EVENT_THR_CMP_MASK; - mmcra |= thresh_cmp_val(val); + if (!cpu_has_feature(CPU_FTR_ARCH_31)) { + val = (event[i] >> EVENT_THR_CMP_SHIFT) & + EVENT_THR_CMP_MASK; + mmcra |= thresh_cmp_val(val); + } + } + + if (cpu_has_feature(CPU_FTR_ARCH_31) && (unit == 6)) { + val = (event[i] >> p10_L2L3_EVENT_SHIFT) & + p10_EVENT_L2L3_SEL_MASK; + mmcr2 |= val << p10_L2L3_SEL_SHIFT; } if (event[i] & EVENT_WANTS_BHRB) { @@ -447,6 +486,11 @@ int isa207_compute_mmcr(u64 event[], int n_ev, mmcra |= val << MMCRA_IFM_SHIFT; } + /* set MMCRA (BHRBRD) to 0 if there is user request for BHRB */ + if (cpu_has_feature(CPU_FTR_ARCH_31) && + (has_branch_stack(pevents[i]) || (event[i] & EVENT_WANTS_BHRB))) + mmcra &= ~MMCRA_BHRB_DISABLE; + if (pevents[i]->attr.exclude_user) mmcr2 |= MMCR2_FCP(pmc); @@ -460,34 +504,43 @@ int isa207_compute_mmcr(u64 event[], int n_ev, mmcr2 |= MMCR2_FCS(pmc); } + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + if (pmc <= 4) { + val = (event[i] >> p10_EVENT_MMCR3_SHIFT) & + p10_EVENT_MMCR3_MASK; + mmcr3 |= val << MMCR3_SHIFT(pmc); + } + } + hwc[i] = pmc - 1; } /* Return MMCRx values */ - mmcr[0] = 0; + mmcr->mmcr0 = 0; /* pmc_inuse is 1-based */ if (pmc_inuse & 2) - mmcr[0] = MMCR0_PMC1CE; + mmcr->mmcr0 = MMCR0_PMC1CE; if (pmc_inuse & 0x7c) - mmcr[0] |= MMCR0_PMCjCE; + mmcr->mmcr0 |= MMCR0_PMCjCE; /* If we're not using PMC 5 or 6, freeze them */ if (!(pmc_inuse & 0x60)) - mmcr[0] |= MMCR0_FC56; + mmcr->mmcr0 |= MMCR0_FC56; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; - mmcr[3] = mmcr2; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; + mmcr->mmcr2 = mmcr2; + mmcr->mmcr3 = mmcr3; return 0; } -void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +void isa207_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { if (pmc <= 3) - mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1)); + mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SHIFT(pmc + 1)); } static int find_alternative(u64 event, const unsigned int ev_alt[][MAX_ALT], int size) diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 63fd4f3f6013..044de65e96b9 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -87,6 +87,31 @@ EVENT_LINUX_MASK | \ EVENT_PSEL_MASK)) +/* Contants to support power10 raw encoding format */ +#define p10_SDAR_MODE_SHIFT 22 +#define p10_SDAR_MODE_MASK 0x3ull +#define p10_SDAR_MODE(v) (((v) >> p10_SDAR_MODE_SHIFT) & \ + p10_SDAR_MODE_MASK) +#define p10_EVENT_L2L3_SEL_MASK 0x1f +#define p10_L2L3_SEL_SHIFT 3 +#define p10_L2L3_EVENT_SHIFT 40 +#define p10_EVENT_THRESH_MASK 0xffffull +#define p10_EVENT_CACHE_SEL_MASK 0x3ull +#define p10_EVENT_MMCR3_MASK 0x7fffull +#define p10_EVENT_MMCR3_SHIFT 45 + +#define p10_EVENT_VALID_MASK \ + ((p10_SDAR_MODE_MASK << p10_SDAR_MODE_SHIFT | \ + (p10_EVENT_THRESH_MASK << EVENT_THRESH_SHIFT) | \ + (EVENT_SAMPLE_MASK << EVENT_SAMPLE_SHIFT) | \ + (p10_EVENT_CACHE_SEL_MASK << EVENT_CACHE_SEL_SHIFT) | \ + (EVENT_PMC_MASK << EVENT_PMC_SHIFT) | \ + (EVENT_UNIT_MASK << EVENT_UNIT_SHIFT) | \ + (p9_EVENT_COMBINE_MASK << p9_EVENT_COMBINE_SHIFT) | \ + (p10_EVENT_MMCR3_MASK << p10_EVENT_MMCR3_SHIFT) | \ + (EVENT_MARKED_MASK << EVENT_MARKED_SHIFT) | \ + EVENT_LINUX_MASK | \ + EVENT_PSEL_MASK)) /* * Layout of constraint bits: * @@ -135,6 +160,9 @@ #define CNST_CACHE_PMC4_VAL (1ull << 54) #define CNST_CACHE_PMC4_MASK CNST_CACHE_PMC4_VAL +#define CNST_L2L3_GROUP_VAL(v) (((v) & 0x1full) << 55) +#define CNST_L2L3_GROUP_MASK CNST_L2L3_GROUP_VAL(0x1f) + /* * For NC we are counting up to 4 events. This requires three bits, and we need * the fifth event to overflow and set the 4th bit. To achieve that we bias the @@ -191,7 +219,7 @@ #define MMCRA_THR_CTR_EXP(v) (((v) >> MMCRA_THR_CTR_EXP_SHIFT) &\ MMCRA_THR_CTR_EXP_MASK) -/* MMCR1 Threshold Compare bit constant for power9 */ +/* MMCRA Threshold Compare bit constant for power9 */ #define p9_MMCRA_THR_CMP_SHIFT 45 /* Bits in MMCR2 for PowerISA v2.07 */ @@ -202,6 +230,9 @@ #define MAX_ALT 2 #define MAX_PMU_COUNTERS 6 +/* Bits in MMCR3 for PowerISA v3.10 */ +#define MMCR3_SHIFT(pmc) (49 - (15 * ((pmc) - 1))) + #define ISA207_SIER_TYPE_SHIFT 15 #define ISA207_SIER_TYPE_MASK (0x7ull << ISA207_SIER_TYPE_SHIFT) @@ -217,9 +248,9 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp); int isa207_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], + unsigned int hwc[], struct mmcr_regs *mmcr, struct perf_event *pevents[]); -void isa207_disable_pmc(unsigned int pmc, unsigned long mmcr[]); +void isa207_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr); int isa207_get_alternatives(u64 event, u64 alt[], int size, unsigned int flags, const unsigned int ev_alt[][MAX_ALT]); void isa207_get_mem_data_src(union perf_mem_data_src *dsrc, u32 flags, diff --git a/arch/powerpc/perf/mpc7450-pmu.c b/arch/powerpc/perf/mpc7450-pmu.c index 4d5ef92511d1..1919e9df9165 100644 --- a/arch/powerpc/perf/mpc7450-pmu.c +++ b/arch/powerpc/perf/mpc7450-pmu.c @@ -257,7 +257,7 @@ static const u32 pmcsel_mask[N_COUNTER] = { * Compute MMCR0/1/2 values for a set of events. */ static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], - unsigned long mmcr[], + struct mmcr_regs *mmcr, struct perf_event *pevents[]) { u8 event_index[N_CLASSES][N_COUNTER]; @@ -321,9 +321,16 @@ static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], mmcr0 |= MMCR0_PMCnCE; /* Return MMCRx values */ - mmcr[0] = mmcr0; - mmcr[1] = mmcr1; - mmcr[2] = mmcr2; + mmcr->mmcr0 = mmcr0; + mmcr->mmcr1 = mmcr1; + mmcr->mmcr2 = mmcr2; + /* + * 32-bit doesn't have an MMCRA and uses SPRN_MMCR2 to define + * SPRN_MMCRA. So assign mmcra of cpu_hw_events with `mmcr2` + * value to ensure that any write to this SPRN_MMCRA will + * use mmcr2 value. + */ + mmcr->mmcra = mmcr2; return 0; } @@ -331,12 +338,12 @@ static int mpc7450_compute_mmcr(u64 event[], int n_ev, unsigned int hwc[], * Disable counting by a PMC. * Note that the pmc argument is 0-based here, not 1-based. */ -static void mpc7450_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void mpc7450_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { if (pmc <= 1) - mmcr[0] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); + mmcr->mmcr0 &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); else - mmcr[1] &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); + mmcr->mmcr1 &= ~(pmcsel_mask[pmc] << pmcsel_shift[pmc]); } static int mpc7450_generic_events[] = { @@ -354,7 +361,7 @@ static int mpc7450_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0, 0x225 }, [C(OP_WRITE)] = { 0, 0x227 }, diff --git a/arch/powerpc/perf/power10-events-list.h b/arch/powerpc/perf/power10-events-list.h new file mode 100644 index 000000000000..60c1b8111082 --- /dev/null +++ b/arch/powerpc/perf/power10-events-list.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Performance counter support for POWER10 processors. + * + * Copyright 2020 Madhavan Srinivasan, IBM Corporation. + * Copyright 2020 Athira Rajeev, IBM Corporation. + */ + +/* + * Power10 event codes. + */ +EVENT(PM_RUN_CYC, 0x600f4); +EVENT(PM_DISP_STALL_CYC, 0x100f8); +EVENT(PM_EXEC_STALL, 0x30008); +EVENT(PM_RUN_INST_CMPL, 0x500fa); +EVENT(PM_BR_CMPL, 0x4d05e); +EVENT(PM_BR_MPRED_CMPL, 0x400f6); + +/* All L1 D cache load references counted at finish, gated by reject */ +EVENT(PM_LD_REF_L1, 0x100fc); +/* Load Missed L1 */ +EVENT(PM_LD_MISS_L1, 0x3e054); +/* Store Missed L1 */ +EVENT(PM_ST_MISS_L1, 0x300f0); +/* L1 cache data prefetches */ +EVENT(PM_LD_PREFETCH_CACHE_LINE_MISS, 0x1002c); +/* Demand iCache Miss */ +EVENT(PM_L1_ICACHE_MISS, 0x200fc); +/* Instruction fetches from L1 */ +EVENT(PM_INST_FROM_L1, 0x04080); +/* Instruction Demand sectors wriittent into IL1 */ +EVENT(PM_INST_FROM_L1MISS, 0x03f00000001c040); +/* Instruction prefetch written into IL1 */ +EVENT(PM_IC_PREF_REQ, 0x040a0); +/* The data cache was reloaded from local core's L3 due to a demand load */ +EVENT(PM_DATA_FROM_L3, 0x01340000001c040); +/* Demand LD - L3 Miss (not L2 hit and not L3 hit) */ +EVENT(PM_DATA_FROM_L3MISS, 0x300fe); +/* Data PTEG reload */ +EVENT(PM_DTLB_MISS, 0x300fc); +/* ITLB Reloaded */ +EVENT(PM_ITLB_MISS, 0x400fc); + +EVENT(PM_RUN_CYC_ALT, 0x0001e); +EVENT(PM_RUN_INST_CMPL_ALT, 0x00002); + +/* + * Memory Access Events + * + * Primary PMU event used here is PM_MRK_INST_CMPL (0x401e0) + * To enable capturing of memory profiling, these MMCRA bits + * needs to be programmed and corresponding raw event format + * encoding. + * + * MMCRA bits encoding needed are + * SM (Sampling Mode) + * EM (Eligibility for Random Sampling) + * TECE (Threshold Event Counter Event) + * TS (Threshold Start Event) + * TE (Threshold End Event) + * + * Corresponding Raw Encoding bits: + * sample [EM,SM] + * thresh_sel (TECE) + * thresh start (TS) + * thresh end (TE) + */ + +EVENT(MEM_LOADS, 0x34340401e0); +EVENT(MEM_STORES, 0x343c0401e0); diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c new file mode 100644 index 000000000000..f7cff7f36a1c --- /dev/null +++ b/arch/powerpc/perf/power10-pmu.c @@ -0,0 +1,419 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Performance counter support for POWER10 processors. + * + * Copyright 2020 Madhavan Srinivasan, IBM Corporation. + * Copyright 2020 Athira Rajeev, IBM Corporation. + */ + +#define pr_fmt(fmt) "power10-pmu: " fmt + +#include "isa207-common.h" +#include "internal.h" + +/* + * Raw event encoding for Power10: + * + * 60 56 52 48 44 40 36 32 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * | | [ ] [ src_match ] [ src_mask ] | [ ] [ l2l3_sel ] [ thresh_ctl ] + * | | | | | | + * | | *- IFM (Linux) | | thresh start/stop -* + * | *- BHRB (Linux) | src_sel + * *- EBB (Linux) *invert_bit + * + * 28 24 20 16 12 8 4 0 + * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | + * [ ] [ sample ] [ ] [ ] [ pmc ] [unit ] [ ] m [ pmcxsel ] + * | | | | | | + * | | | | | *- mark + * | | | *- L1/L2/L3 cache_sel | + * | | sdar_mode | + * | *- sampling mode for marked events *- combine + * | + * *- thresh_sel + * + * Below uses IBM bit numbering. + * + * MMCR1[x:y] = unit (PMCxUNIT) + * MMCR1[24] = pmc1combine[0] + * MMCR1[25] = pmc1combine[1] + * MMCR1[26] = pmc2combine[0] + * MMCR1[27] = pmc2combine[1] + * MMCR1[28] = pmc3combine[0] + * MMCR1[29] = pmc3combine[1] + * MMCR1[30] = pmc4combine[0] + * MMCR1[31] = pmc4combine[1] + * + * if pmc == 3 and unit == 0 and pmcxsel[0:6] == 0b0101011 + * MMCR1[20:27] = thresh_ctl + * else if pmc == 4 and unit == 0xf and pmcxsel[0:6] == 0b0101001 + * MMCR1[20:27] = thresh_ctl + * else + * MMCRA[48:55] = thresh_ctl (THRESH START/END) + * + * if thresh_sel: + * MMCRA[45:47] = thresh_sel + * + * if l2l3_sel: + * MMCR2[56:60] = l2l3_sel[0:4] + * + * MMCR1[16] = cache_sel[0] + * MMCR1[17] = cache_sel[1] + * + * if mark: + * MMCRA[63] = 1 (SAMPLE_ENABLE) + * MMCRA[57:59] = sample[0:2] (RAND_SAMP_ELIG) + * MMCRA[61:62] = sample[3:4] (RAND_SAMP_MODE) + * + * if EBB and BHRB: + * MMCRA[32:33] = IFM + * + * MMCRA[SDAR_MODE] = sdar_mode[0:1] + */ + +/* + * Some power10 event codes. + */ +#define EVENT(_name, _code) enum{_name = _code} + +#include "power10-events-list.h" + +#undef EVENT + +/* MMCRA IFM bits - POWER10 */ +#define POWER10_MMCRA_IFM1 0x0000000040000000UL +#define POWER10_MMCRA_IFM2 0x0000000080000000UL +#define POWER10_MMCRA_IFM3 0x00000000C0000000UL +#define POWER10_MMCRA_BHRB_MASK 0x00000000C0000000UL + +/* Table of alternatives, sorted by column 0 */ +static const unsigned int power10_event_alternatives[][MAX_ALT] = { + { PM_RUN_CYC_ALT, PM_RUN_CYC }, + { PM_RUN_INST_CMPL_ALT, PM_RUN_INST_CMPL }, +}; + +static int power10_get_alternatives(u64 event, unsigned int flags, u64 alt[]) +{ + int num_alt = 0; + + num_alt = isa207_get_alternatives(event, alt, + ARRAY_SIZE(power10_event_alternatives), flags, + power10_event_alternatives); + + return num_alt; +} + +GENERIC_EVENT_ATTR(cpu-cycles, PM_RUN_CYC); +GENERIC_EVENT_ATTR(instructions, PM_RUN_INST_CMPL); +GENERIC_EVENT_ATTR(branch-instructions, PM_BR_CMPL); +GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED_CMPL); +GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); +GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1); +GENERIC_EVENT_ATTR(mem-loads, MEM_LOADS); +GENERIC_EVENT_ATTR(mem-stores, MEM_STORES); + +CACHE_EVENT_ATTR(L1-dcache-load-misses, PM_LD_MISS_L1); +CACHE_EVENT_ATTR(L1-dcache-loads, PM_LD_REF_L1); +CACHE_EVENT_ATTR(L1-dcache-prefetches, PM_LD_PREFETCH_CACHE_LINE_MISS); +CACHE_EVENT_ATTR(L1-dcache-store-misses, PM_ST_MISS_L1); +CACHE_EVENT_ATTR(L1-icache-load-misses, PM_L1_ICACHE_MISS); +CACHE_EVENT_ATTR(L1-icache-loads, PM_INST_FROM_L1); +CACHE_EVENT_ATTR(L1-icache-prefetches, PM_IC_PREF_REQ); +CACHE_EVENT_ATTR(LLC-load-misses, PM_DATA_FROM_L3MISS); +CACHE_EVENT_ATTR(LLC-loads, PM_DATA_FROM_L3); +CACHE_EVENT_ATTR(branch-load-misses, PM_BR_MPRED_CMPL); +CACHE_EVENT_ATTR(branch-loads, PM_BR_CMPL); +CACHE_EVENT_ATTR(dTLB-load-misses, PM_DTLB_MISS); +CACHE_EVENT_ATTR(iTLB-load-misses, PM_ITLB_MISS); + +static struct attribute *power10_events_attr[] = { + GENERIC_EVENT_PTR(PM_RUN_CYC), + GENERIC_EVENT_PTR(PM_RUN_INST_CMPL), + GENERIC_EVENT_PTR(PM_BR_CMPL), + GENERIC_EVENT_PTR(PM_BR_MPRED_CMPL), + GENERIC_EVENT_PTR(PM_LD_REF_L1), + GENERIC_EVENT_PTR(PM_LD_MISS_L1), + GENERIC_EVENT_PTR(MEM_LOADS), + GENERIC_EVENT_PTR(MEM_STORES), + CACHE_EVENT_PTR(PM_LD_MISS_L1), + CACHE_EVENT_PTR(PM_LD_REF_L1), + CACHE_EVENT_PTR(PM_LD_PREFETCH_CACHE_LINE_MISS), + CACHE_EVENT_PTR(PM_ST_MISS_L1), + CACHE_EVENT_PTR(PM_L1_ICACHE_MISS), + CACHE_EVENT_PTR(PM_INST_FROM_L1), + CACHE_EVENT_PTR(PM_IC_PREF_REQ), + CACHE_EVENT_PTR(PM_DATA_FROM_L3MISS), + CACHE_EVENT_PTR(PM_DATA_FROM_L3), + CACHE_EVENT_PTR(PM_BR_MPRED_CMPL), + CACHE_EVENT_PTR(PM_BR_CMPL), + CACHE_EVENT_PTR(PM_DTLB_MISS), + CACHE_EVENT_PTR(PM_ITLB_MISS), + NULL +}; + +static struct attribute_group power10_pmu_events_group = { + .name = "events", + .attrs = power10_events_attr, +}; + +PMU_FORMAT_ATTR(event, "config:0-59"); +PMU_FORMAT_ATTR(pmcxsel, "config:0-7"); +PMU_FORMAT_ATTR(mark, "config:8"); +PMU_FORMAT_ATTR(combine, "config:10-11"); +PMU_FORMAT_ATTR(unit, "config:12-15"); +PMU_FORMAT_ATTR(pmc, "config:16-19"); +PMU_FORMAT_ATTR(cache_sel, "config:20-21"); +PMU_FORMAT_ATTR(sdar_mode, "config:22-23"); +PMU_FORMAT_ATTR(sample_mode, "config:24-28"); +PMU_FORMAT_ATTR(thresh_sel, "config:29-31"); +PMU_FORMAT_ATTR(thresh_stop, "config:32-35"); +PMU_FORMAT_ATTR(thresh_start, "config:36-39"); +PMU_FORMAT_ATTR(l2l3_sel, "config:40-44"); +PMU_FORMAT_ATTR(src_sel, "config:45-46"); +PMU_FORMAT_ATTR(invert_bit, "config:47"); +PMU_FORMAT_ATTR(src_mask, "config:48-53"); +PMU_FORMAT_ATTR(src_match, "config:54-59"); + +static struct attribute *power10_pmu_format_attr[] = { + &format_attr_event.attr, + &format_attr_pmcxsel.attr, + &format_attr_mark.attr, + &format_attr_combine.attr, + &format_attr_unit.attr, + &format_attr_pmc.attr, + &format_attr_cache_sel.attr, + &format_attr_sdar_mode.attr, + &format_attr_sample_mode.attr, + &format_attr_thresh_sel.attr, + &format_attr_thresh_stop.attr, + &format_attr_thresh_start.attr, + &format_attr_l2l3_sel.attr, + &format_attr_src_sel.attr, + &format_attr_invert_bit.attr, + &format_attr_src_mask.attr, + &format_attr_src_match.attr, + NULL, +}; + +static struct attribute_group power10_pmu_format_group = { + .name = "format", + .attrs = power10_pmu_format_attr, +}; + +static const struct attribute_group *power10_pmu_attr_groups[] = { + &power10_pmu_format_group, + &power10_pmu_events_group, + NULL, +}; + +static int power10_generic_events[] = { + [PERF_COUNT_HW_CPU_CYCLES] = PM_RUN_CYC, + [PERF_COUNT_HW_INSTRUCTIONS] = PM_RUN_INST_CMPL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = PM_BR_CMPL, + [PERF_COUNT_HW_BRANCH_MISSES] = PM_BR_MPRED_CMPL, + [PERF_COUNT_HW_CACHE_REFERENCES] = PM_LD_REF_L1, + [PERF_COUNT_HW_CACHE_MISSES] = PM_LD_MISS_L1, +}; + +static u64 power10_bhrb_filter_map(u64 branch_sample_type) +{ + u64 pmu_bhrb_filter = 0; + + /* BHRB and regular PMU events share the same privilege state + * filter configuration. BHRB is always recorded along with a + * regular PMU event. As the privilege state filter is handled + * in the basic PMC configuration of the accompanying regular + * PMU event, we ignore any separate BHRB specific request. + */ + + /* No branch filter requested */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY) + return pmu_bhrb_filter; + + /* Invalid branch filter options - HW does not support */ + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_RETURN) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_IND_CALL) { + pmu_bhrb_filter |= POWER10_MMCRA_IFM2; + return pmu_bhrb_filter; + } + + if (branch_sample_type & PERF_SAMPLE_BRANCH_COND) { + pmu_bhrb_filter |= POWER10_MMCRA_IFM3; + return pmu_bhrb_filter; + } + + if (branch_sample_type & PERF_SAMPLE_BRANCH_CALL) + return -1; + + if (branch_sample_type & PERF_SAMPLE_BRANCH_ANY_CALL) { + pmu_bhrb_filter |= POWER10_MMCRA_IFM1; + return pmu_bhrb_filter; + } + + /* Every thing else is unsupported */ + return -1; +} + +static void power10_config_bhrb(u64 pmu_bhrb_filter) +{ + pmu_bhrb_filter &= POWER10_MMCRA_BHRB_MASK; + + /* Enable BHRB filter in PMU */ + mtspr(SPRN_MMCRA, (mfspr(SPRN_MMCRA) | pmu_bhrb_filter)); +} + +#define C(x) PERF_COUNT_HW_CACHE_##x + +/* + * Table of generalized cache-related events. + * 0 means not supported, -1 means nonsensical, other values + * are event codes. + */ +static u64 power10_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { + [C(L1D)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PM_LD_REF_L1, + [C(RESULT_MISS)] = PM_LD_MISS_L1, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = PM_ST_MISS_L1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = PM_LD_PREFETCH_CACHE_LINE_MISS, + [C(RESULT_MISS)] = 0, + }, + }, + [C(L1I)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PM_INST_FROM_L1, + [C(RESULT_MISS)] = PM_L1_ICACHE_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = PM_INST_FROM_L1MISS, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = PM_IC_PREF_REQ, + [C(RESULT_MISS)] = 0, + }, + }, + [C(LL)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PM_DATA_FROM_L3, + [C(RESULT_MISS)] = PM_DATA_FROM_L3MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = 0, + }, + }, + [C(DTLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = PM_DTLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(ITLB)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = 0, + [C(RESULT_MISS)] = PM_ITLB_MISS, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(BPU)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = PM_BR_CMPL, + [C(RESULT_MISS)] = PM_BR_MPRED_CMPL, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, + [C(NODE)] = { + [C(OP_READ)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = -1, + [C(RESULT_MISS)] = -1, + }, + }, +}; + +#undef C + +static struct power_pmu power10_pmu = { + .name = "POWER10", + .n_counter = MAX_PMU_COUNTERS, + .add_fields = ISA207_ADD_FIELDS, + .test_adder = ISA207_TEST_ADDER, + .group_constraint_mask = CNST_CACHE_PMC4_MASK, + .group_constraint_val = CNST_CACHE_PMC4_VAL, + .compute_mmcr = isa207_compute_mmcr, + .config_bhrb = power10_config_bhrb, + .bhrb_filter_map = power10_bhrb_filter_map, + .get_constraint = isa207_get_constraint, + .get_alternatives = power10_get_alternatives, + .get_mem_data_src = isa207_get_mem_data_src, + .get_mem_weight = isa207_get_mem_weight, + .disable_pmc = isa207_disable_pmc, + .flags = PPMU_HAS_SIER | PPMU_ARCH_207S | + PPMU_ARCH_31, + .n_generic = ARRAY_SIZE(power10_generic_events), + .generic_events = power10_generic_events, + .cache_events = &power10_cache_events, + .attr_groups = power10_pmu_attr_groups, + .bhrb_nr = 32, +}; + +int init_power10_pmu(void) +{ + int rc; + + /* Comes from cpu_specs[] */ + if (!cur_cpu_spec->oprofile_cpu_type || + strcmp(cur_cpu_spec->oprofile_cpu_type, "ppc64/power10")) + return -ENODEV; + + rc = register_power_pmu(&power10_pmu); + if (rc) + return rc; + + /* Tell userspace that EBB is supported */ + cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_EBB; + + return 0; +} diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index f8574547fc6b..a62b2cd7914f 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -448,7 +448,8 @@ static int power5p_marked_instr_event(u64 event) } static int power5p_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]) + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[]) { unsigned long mmcr1 = 0; unsigned long mmcra = 0; @@ -586,20 +587,20 @@ static int power5p_compute_mmcr(u64 event[], int n_ev, } /* Return MMCRx values */ - mmcr[0] = 0; + mmcr->mmcr0 = 0; if (pmc_inuse & 1) - mmcr[0] = MMCR0_PMC1CE; + mmcr->mmcr0 = MMCR0_PMC1CE; if (pmc_inuse & 0x3e) - mmcr[0] |= MMCR0_PMCjCE; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; + mmcr->mmcr0 |= MMCR0_PMCjCE; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; return 0; } -static void power5p_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void power5p_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { if (pmc <= 3) - mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); + mmcr->mmcr1 &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); } static int power5p_generic_events[] = { @@ -618,7 +619,7 @@ static int power5p_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0x1c10a8, 0x3c1088 }, [C(OP_WRITE)] = { 0x2c10a8, 0xc10c3 }, diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index da52ecab7c9a..8732b587cf71 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -379,7 +379,8 @@ static int power5_marked_instr_event(u64 event) } static int power5_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]) + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[]) { unsigned long mmcr1 = 0; unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; @@ -528,20 +529,20 @@ static int power5_compute_mmcr(u64 event[], int n_ev, } /* Return MMCRx values */ - mmcr[0] = 0; + mmcr->mmcr0 = 0; if (pmc_inuse & 1) - mmcr[0] = MMCR0_PMC1CE; + mmcr->mmcr0 = MMCR0_PMC1CE; if (pmc_inuse & 0x3e) - mmcr[0] |= MMCR0_PMCjCE; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; + mmcr->mmcr0 |= MMCR0_PMCjCE; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; return 0; } -static void power5_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void power5_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { if (pmc <= 3) - mmcr[1] &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); + mmcr->mmcr1 &= ~(0x7fUL << MMCR1_PMCSEL_SH(pmc)); } static int power5_generic_events[] = { @@ -560,7 +561,7 @@ static int power5_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0x4c1090, 0x3c1088 }, [C(OP_WRITE)] = { 0x3c1090, 0xc10c3 }, diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c index 3929cacf72ed..0e318cf87129 100644 --- a/arch/powerpc/perf/power6-pmu.c +++ b/arch/powerpc/perf/power6-pmu.c @@ -171,7 +171,7 @@ static int power6_marked_instr_event(u64 event) * Assign PMC numbers and compute MMCR1 value for a set of events */ static int p6_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]) + unsigned int hwc[], struct mmcr_regs *mmcr, struct perf_event *pevents[]) { unsigned long mmcr1 = 0; unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; @@ -243,13 +243,13 @@ static int p6_compute_mmcr(u64 event[], int n_ev, if (pmc < 4) mmcr1 |= (unsigned long)psel << MMCR1_PMCSEL_SH(pmc); } - mmcr[0] = 0; + mmcr->mmcr0 = 0; if (pmc_inuse & 1) - mmcr[0] = MMCR0_PMC1CE; + mmcr->mmcr0 = MMCR0_PMC1CE; if (pmc_inuse & 0xe) - mmcr[0] |= MMCR0_PMCjCE; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; + mmcr->mmcr0 |= MMCR0_PMCjCE; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; return 0; } @@ -457,11 +457,11 @@ static int p6_get_alternatives(u64 event, unsigned int flags, u64 alt[]) return nalt; } -static void p6_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void p6_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { /* Set PMCxSEL to 0 to disable PMCx */ if (pmc <= 3) - mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); + mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); } static int power6_generic_events[] = { @@ -481,7 +481,7 @@ static int power6_generic_events[] = { * are event codes. * The "DTLB" and "ITLB" events relate to the DERAT and IERAT. */ -static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0x280030, 0x80080 }, [C(OP_WRITE)] = { 0x180032, 0x80088 }, diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index a137813a3076..5e0bf09cf077 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -242,7 +242,8 @@ static int power7_marked_instr_event(u64 event) } static int power7_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]) + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[]) { unsigned long mmcr1 = 0; unsigned long mmcra = MMCRA_SDAR_DCACHE_MISS | MMCRA_SDAR_ERAT_MISS; @@ -298,20 +299,20 @@ static int power7_compute_mmcr(u64 event[], int n_ev, } /* Return MMCRx values */ - mmcr[0] = 0; + mmcr->mmcr0 = 0; if (pmc_inuse & 1) - mmcr[0] = MMCR0_PMC1CE; + mmcr->mmcr0 = MMCR0_PMC1CE; if (pmc_inuse & 0x3e) - mmcr[0] |= MMCR0_PMCjCE; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; + mmcr->mmcr0 |= MMCR0_PMCjCE; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; return 0; } -static void power7_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void power7_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { if (pmc <= 3) - mmcr[1] &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); + mmcr->mmcr1 &= ~(0xffUL << MMCR1_PMCSEL_SH(pmc)); } static int power7_generic_events[] = { @@ -332,7 +333,7 @@ static int power7_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0xc880, 0x400f0 }, [C(OP_WRITE)] = { 0, 0x300f0 }, diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index 3a5fcc20ff31..5282e8415ddf 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -253,7 +253,7 @@ static void power8_config_bhrb(u64 pmu_bhrb_filter) * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power8_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [ C(L1D) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 08c3ef796198..05dae38b969a 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -310,7 +310,7 @@ static void power9_config_bhrb(u64 pmu_bhrb_filter) * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [ C(L1D) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = PM_LD_REF_L1, diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c index 4035d93d87ab..d35223fb112c 100644 --- a/arch/powerpc/perf/ppc970-pmu.c +++ b/arch/powerpc/perf/ppc970-pmu.c @@ -253,7 +253,8 @@ static int p970_get_alternatives(u64 event, unsigned int flags, u64 alt[]) } static int p970_compute_mmcr(u64 event[], int n_ev, - unsigned int hwc[], unsigned long mmcr[], struct perf_event *pevents[]) + unsigned int hwc[], struct mmcr_regs *mmcr, + struct perf_event *pevents[]) { unsigned long mmcr0 = 0, mmcr1 = 0, mmcra = 0; unsigned int pmc, unit, byte, psel; @@ -393,27 +394,26 @@ static int p970_compute_mmcr(u64 event[], int n_ev, mmcra |= 0x2000; /* mark only one IOP per PPC instruction */ /* Return MMCRx values */ - mmcr[0] = mmcr0; - mmcr[1] = mmcr1; - mmcr[2] = mmcra; + mmcr->mmcr0 = mmcr0; + mmcr->mmcr1 = mmcr1; + mmcr->mmcra = mmcra; return 0; } -static void p970_disable_pmc(unsigned int pmc, unsigned long mmcr[]) +static void p970_disable_pmc(unsigned int pmc, struct mmcr_regs *mmcr) { - int shift, i; + int shift; + /* + * Setting the PMCxSEL field to 0x08 disables PMC x. + */ if (pmc <= 1) { shift = MMCR0_PMC1SEL_SH - 7 * pmc; - i = 0; + mmcr->mmcr0 = (mmcr->mmcr0 & ~(0x1fUL << shift)) | (0x08UL << shift); } else { shift = MMCR1_PMC3SEL_SH - 5 * (pmc - 2); - i = 1; + mmcr->mmcr1 = (mmcr->mmcr1 & ~(0x1fUL << shift)) | (0x08UL << shift); } - /* - * Setting the PMCxSEL field to 0x08 disables PMC x. - */ - mmcr[i] = (mmcr[i] & ~(0x1fUL << shift)) | (0x08UL << shift); } static int ppc970_generic_events[] = { @@ -432,7 +432,7 @@ static int ppc970_generic_events[] = { * 0 means not supported, -1 means nonsensical, other values * are event codes. */ -static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { +static u64 ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { [C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */ [C(OP_READ)] = { 0x8810, 0x3810 }, [C(OP_WRITE)] = { 0x7810, 0x813 }, diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S index 70083649c9ea..11475c58ea43 100644 --- a/arch/powerpc/platforms/52xx/lite5200_sleep.S +++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S @@ -56,7 +56,7 @@ lite5200_low_power: /* * save stuff BDI overwrites * 0xf0 (0xe0->0x100 gets overwritten when BDI connected; - * even when CONFIG_BDI* is disabled and MMU XLAT commented; heisenbug?)) + * even when CONFIG_BDI_SWITCH is disabled and MMU XLAT commented; heisenbug?)) * WARNING: self-refresh doesn't seem to work when BDI2000 is connected, * possibly because BDI sets SDRAM registers before wakeup code does */ diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig index fa3d29dcb57e..b77cbb0a50e1 100644 --- a/arch/powerpc/platforms/85xx/Kconfig +++ b/arch/powerpc/platforms/85xx/Kconfig @@ -160,7 +160,7 @@ config XES_MPC85xx computers from Extreme Engineering Solutions (X-ES) based on Freescale MPC85xx processors. Manufacturer: Extreme Engineering Solutions, Inc. - URL: <http://www.xes-inc.com/> + URL: <https://www.xes-inc.com/> config STX_GP3 bool "Silicon Turnkey Express GP3" diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 0f7c8241912b..f2ff359041ee 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -44,6 +44,7 @@ config SPU_FS tristate "SPU file system" default m depends on PPC_CELL + depends on COREDUMP select SPU_BASE help The SPU file system is used to access Synergistic Processing diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c index 3b75e8f60609..026c181a98c5 100644 --- a/arch/powerpc/platforms/cell/spufs/coredump.c +++ b/arch/powerpc/platforms/cell/spufs/coredump.c @@ -66,13 +66,20 @@ static int match_context(const void *v, struct file *file, unsigned fd) */ static struct spu_context *coredump_next_context(int *fd) { + struct spu_context *ctx; struct file *file; int n = iterate_fd(current->files, *fd, match_context, NULL); if (!n) return NULL; *fd = n - 1; + + rcu_read_lock(); file = fcheck(*fd); - return SPUFS_I(file_inode(file))->i_ctx; + ctx = SPUFS_I(file_inode(file))->i_ctx; + get_spu_context(ctx); + rcu_read_unlock(); + + return ctx; } int spufs_coredump_extra_notes_size(void) @@ -83,17 +90,23 @@ int spufs_coredump_extra_notes_size(void) fd = 0; while ((ctx = coredump_next_context(&fd)) != NULL) { rc = spu_acquire_saved(ctx); - if (rc) + if (rc) { + put_spu_context(ctx); break; + } + rc = spufs_ctx_note_size(ctx, fd); spu_release_saved(ctx); - if (rc < 0) + if (rc < 0) { + put_spu_context(ctx); break; + } size += rc; /* start searching the next fd next time */ fd++; + put_spu_context(ctx); } return size; @@ -105,7 +118,7 @@ static int spufs_arch_write_note(struct spu_context *ctx, int i, size_t sz = spufs_coredump_read[i].size; char fullname[80]; struct elf_note en; - size_t ret; + int ret; sprintf(fullname, "SPU/%d/%s", dfd, spufs_coredump_read[i].name); en.n_namesz = strlen(fullname) + 1; diff --git a/arch/powerpc/platforms/pasemi/misc.c b/arch/powerpc/platforms/pasemi/misc.c index 1cd4ca14b08d..1bf65d02d3ba 100644 --- a/arch/powerpc/platforms/pasemi/misc.c +++ b/arch/powerpc/platforms/pasemi/misc.c @@ -56,8 +56,7 @@ static int __init pasemi_register_i2c_devices(void) if (!adap_node) continue; - node = NULL; - while ((node = of_get_next_child(adap_node, node))) { + for_each_child_of_node(adap_node, node) { struct i2c_board_info info = {}; const u32 *addr; int len; diff --git a/arch/powerpc/platforms/powermac/Makefile b/arch/powerpc/platforms/powermac/Makefile index f4247ade71ca..cf85f0662d0d 100644 --- a/arch/powerpc/platforms/powermac/Makefile +++ b/arch/powerpc/platforms/powermac/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS_bootx_init.o += -fPIC -CFLAGS_bootx_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_bootx_init.o += -fno-stack-protector KASAN_SANITIZE_bootx_init.o := n diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index 181caa3f6717..5c77b9a24c0e 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -1465,7 +1465,7 @@ static long g5_i2s_enable(struct device_node *node, long param, long value) case 2: if (macio->type == macio_shasta) break; - /* fall through */ + fallthrough; default: return -ENODEV; } diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index bf4be4b53b44..f77a59b5c2e1 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -629,8 +629,7 @@ static void __init kw_i2c_probe(void) for (i = 0; i < chans; i++) kw_i2c_add(host, np, np, i); } else { - for (child = NULL; - (child = of_get_next_child(np, child)) != NULL;) { + for_each_child_of_node(np, child) { const u32 *reg = of_get_property(child, "reg", NULL); if (reg == NULL) @@ -1193,8 +1192,7 @@ static void pmac_i2c_devscan(void (*callback)(struct device_node *dev, * platform function instance */ list_for_each_entry(bus, &pmac_i2c_busses, link) { - for (np = NULL; - (np = of_get_next_child(bus->busnode, np)) != NULL;) { + for_each_child_of_node(bus->busnode, np) { struct whitelist_ent *p; /* If multibus, check if device is on that bus */ if (bus->flags & pmac_i2c_multibus) diff --git a/arch/powerpc/platforms/powermac/pfunc_base.c b/arch/powerpc/platforms/powermac/pfunc_base.c index 62311e84a423..f5422506d4b0 100644 --- a/arch/powerpc/platforms/powermac/pfunc_base.c +++ b/arch/powerpc/platforms/powermac/pfunc_base.c @@ -114,7 +114,7 @@ static void macio_gpio_init_one(struct macio_chip *macio) * Ok, got one, we dont need anything special to track them down, so * we just create them all */ - for (gp = NULL; (gp = of_get_next_child(gparent, gp)) != NULL;) { + for_each_child_of_node(gparent, gp) { const u32 *reg = of_get_property(gp, "reg", NULL); unsigned long offset; if (reg == NULL) @@ -133,7 +133,7 @@ static void macio_gpio_init_one(struct macio_chip *macio) macio->of_node); /* And now we run all the init ones */ - for (gp = NULL; (gp = of_get_next_child(gparent, gp)) != NULL;) + for_each_child_of_node(gparent, gp) pmf_do_functions(gp, NULL, 0, PMF_FLAGS_ON_INIT, NULL); /* Note: We do not at this point implement the "at sleep" or "at wake" diff --git a/arch/powerpc/platforms/powermac/udbg_scc.c b/arch/powerpc/platforms/powermac/udbg_scc.c index 6b61a18e8db3..f286bdfe8346 100644 --- a/arch/powerpc/platforms/powermac/udbg_scc.c +++ b/arch/powerpc/platforms/powermac/udbg_scc.c @@ -80,7 +80,7 @@ void udbg_scc_init(int force_scc) path = of_get_property(of_chosen, "linux,stdout-path", NULL); if (path != NULL) stdout = of_find_node_by_path(path); - for (ch = NULL; (ch = of_get_next_child(escc, ch)) != NULL;) { + for_each_child_of_node(escc, ch) { if (ch == stdout) ch_def = of_node_get(ch); if (of_node_name_eq(ch, "ch-a")) diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile index fe3f0fb5aeca..2eb6ae150d1f 100644 --- a/arch/powerpc/platforms/powernv/Makefile +++ b/arch/powerpc/platforms/powernv/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_FA_DUMP) += opal-fadump.o obj-$(CONFIG_PRESERVE_FA_DUMP) += opal-fadump.o obj-$(CONFIG_OPAL_CORE) += opal-core.o obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o +obj-$(CONFIG_PCI_IOV) += pci-sriov.o obj-$(CONFIG_CXL_BASE) += pci-cxl.o obj-$(CONFIG_EEH) += eeh-powernv.o obj-$(CONFIG_MEMORY_FAILURE) += opal-memory-errors.o diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 79409e005fcd..9af8c3b98853 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -338,6 +338,28 @@ static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap) return 0; } +static struct eeh_pe *pnv_eeh_get_upstream_pe(struct pci_dev *pdev) +{ + struct pci_controller *hose = pdev->bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pci_dev *parent = pdev->bus->self; + +#ifdef CONFIG_PCI_IOV + /* for VFs we use the PF's PE as the upstream PE */ + if (pdev->is_virtfn) + parent = pdev->physfn; +#endif + + /* otherwise use the PE of our parent bridge */ + if (parent) { + struct pnv_ioda_pe *ioda_pe = pnv_ioda_get_pe(parent); + + return eeh_pe_get(phb->hose, ioda_pe->pe_number, 0); + } + + return NULL; +} + /** * pnv_eeh_probe - Do probe on PCI device * @pdev: pci_dev to probe @@ -350,6 +372,7 @@ static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev) struct pci_controller *hose = pdn->phb; struct pnv_phb *phb = hose->private_data; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); + struct eeh_pe *upstream_pe; uint32_t pcie_flags; int ret; int config_addr = (pdn->busno << 8) | (pdn->devfn); @@ -372,19 +395,18 @@ static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev) } /* Skip for PCI-ISA bridge */ - if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA) + if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA) return NULL; eeh_edev_dbg(edev, "Probing device\n"); /* Initialize eeh device */ - edev->class_code = pdn->class_code; edev->mode &= 0xFFFFFF00; edev->pcix_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); edev->pcie_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_EXP); edev->af_cap = pnv_eeh_find_cap(pdn, PCI_CAP_ID_AF); edev->aer_cap = pnv_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); - if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { + if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; if (edev->pcie_cap) { pnv_pci_cfg_read(pdn, edev->pcie_cap + PCI_EXP_FLAGS, @@ -399,8 +421,10 @@ static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev) edev->pe_config_addr = phb->ioda.pe_rmap[config_addr]; + upstream_pe = pnv_eeh_get_upstream_pe(pdev); + /* Create PE */ - ret = eeh_add_to_parent_pe(edev); + ret = eeh_pe_tree_insert(edev, upstream_pe); if (ret) { eeh_edev_warn(edev, "Failed to add device to PE (code %d)\n", ret); return NULL; @@ -535,18 +559,6 @@ static int pnv_eeh_set_option(struct eeh_pe *pe, int option) return 0; } -/** - * pnv_eeh_get_pe_addr - Retrieve PE address - * @pe: EEH PE - * - * Retrieve the PE address according to the given tranditional - * PCI BDF (Bus/Device/Function) address. - */ -static int pnv_eeh_get_pe_addr(struct eeh_pe *pe) -{ - return pe->addr; -} - static void pnv_eeh_get_phb_diag(struct eeh_pe *pe) { struct pnv_phb *phb = pe->phb->private_data; @@ -850,32 +862,32 @@ static int __pnv_eeh_bridge_reset(struct pci_dev *dev, int option) case EEH_RESET_HOT: /* Don't report linkDown event */ if (aer) { - eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + eeh_ops->read_config(edev, aer + PCI_ERR_UNCOR_MASK, 4, &ctrl); ctrl |= PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + eeh_ops->write_config(edev, aer + PCI_ERR_UNCOR_MASK, 4, ctrl); } - eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl |= PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + eeh_ops->write_config(edev, PCI_BRIDGE_CONTROL, 2, ctrl); msleep(EEH_PE_RST_HOLD_TIME); break; case EEH_RESET_DEACTIVATE: - eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &ctrl); + eeh_ops->read_config(edev, PCI_BRIDGE_CONTROL, 2, &ctrl); ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; - eeh_ops->write_config(pdn, PCI_BRIDGE_CONTROL, 2, ctrl); + eeh_ops->write_config(edev, PCI_BRIDGE_CONTROL, 2, ctrl); msleep(EEH_PE_RST_SETTLE_TIME); /* Continue reporting linkDown event */ if (aer) { - eeh_ops->read_config(pdn, aer + PCI_ERR_UNCOR_MASK, + eeh_ops->read_config(edev, aer + PCI_ERR_UNCOR_MASK, 4, &ctrl); ctrl &= ~PCI_ERR_UNC_SURPDN; - eeh_ops->write_config(pdn, aer + PCI_ERR_UNCOR_MASK, + eeh_ops->write_config(edev, aer + PCI_ERR_UNCOR_MASK, 4, ctrl); } @@ -944,11 +956,12 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev) static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type, int pos, u16 mask) { + struct eeh_dev *edev = pdn->edev; int i, status = 0; /* Wait for Transaction Pending bit to be cleared */ for (i = 0; i < 4; i++) { - eeh_ops->read_config(pdn, pos, 2, &status); + eeh_ops->read_config(edev, pos, 2, &status); if (!(status & mask)) return; @@ -969,7 +982,7 @@ static int pnv_eeh_do_flr(struct pci_dn *pdn, int option) if (WARN_ON(!edev->pcie_cap)) return -ENOTTY; - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCAP, 4, ®); + eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCAP, 4, ®); if (!(reg & PCI_EXP_DEVCAP_FLR)) return -ENOTTY; @@ -979,18 +992,18 @@ static int pnv_eeh_do_flr(struct pci_dn *pdn, int option) pnv_eeh_wait_for_pending(pdn, "", edev->pcie_cap + PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_TRPND); - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL, 4, ®); reg |= PCI_EXP_DEVCTL_BCR_FLR; - eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + eeh_ops->write_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL, 4, reg); msleep(EEH_PE_RST_HOLD_TIME); break; case EEH_RESET_DEACTIVATE: - eeh_ops->read_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + eeh_ops->read_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL, 4, ®); reg &= ~PCI_EXP_DEVCTL_BCR_FLR; - eeh_ops->write_config(pdn, edev->pcie_cap + PCI_EXP_DEVCTL, + eeh_ops->write_config(edev, edev->pcie_cap + PCI_EXP_DEVCTL, 4, reg); msleep(EEH_PE_RST_SETTLE_TIME); break; @@ -1007,7 +1020,7 @@ static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option) if (WARN_ON(!edev->af_cap)) return -ENOTTY; - eeh_ops->read_config(pdn, edev->af_cap + PCI_AF_CAP, 1, &cap); + eeh_ops->read_config(edev, edev->af_cap + PCI_AF_CAP, 1, &cap); if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR)) return -ENOTTY; @@ -1022,12 +1035,12 @@ static int pnv_eeh_do_af_flr(struct pci_dn *pdn, int option) pnv_eeh_wait_for_pending(pdn, "AF", edev->af_cap + PCI_AF_CTRL, PCI_AF_STATUS_TP << 8); - eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, + eeh_ops->write_config(edev, edev->af_cap + PCI_AF_CTRL, 1, PCI_AF_CTRL_FLR); msleep(EEH_PE_RST_HOLD_TIME); break; case EEH_RESET_DEACTIVATE: - eeh_ops->write_config(pdn, edev->af_cap + PCI_AF_CTRL, 1, 0); + eeh_ops->write_config(edev, edev->af_cap + PCI_AF_CTRL, 1, 0); msleep(EEH_PE_RST_SETTLE_TIME); break; } @@ -1261,9 +1274,11 @@ static inline bool pnv_eeh_cfg_blocked(struct pci_dn *pdn) return false; } -static int pnv_eeh_read_config(struct pci_dn *pdn, +static int pnv_eeh_read_config(struct eeh_dev *edev, int where, int size, u32 *val) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + if (!pdn) return PCIBIOS_DEVICE_NOT_FOUND; @@ -1275,9 +1290,11 @@ static int pnv_eeh_read_config(struct pci_dn *pdn, return pnv_pci_cfg_read(pdn, where, size, val); } -static int pnv_eeh_write_config(struct pci_dn *pdn, +static int pnv_eeh_write_config(struct eeh_dev *edev, int where, int size, u32 val) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + if (!pdn) return PCIBIOS_DEVICE_NOT_FOUND; @@ -1631,34 +1648,24 @@ static int pnv_eeh_next_error(struct eeh_pe **pe) return ret; } -static int pnv_eeh_restore_config(struct pci_dn *pdn) +static int pnv_eeh_restore_config(struct eeh_dev *edev) { - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); struct pnv_phb *phb; s64 ret = 0; - int config_addr = (pdn->busno << 8) | (pdn->devfn); if (!edev) return -EEXIST; - /* - * We have to restore the PCI config space after reset since the - * firmware can't see SRIOV VFs. - * - * FIXME: The MPS, error routing rules, timeout setting are worthy - * to be exported by firmware in extendible way. - */ - if (edev->physfn) { - ret = eeh_restore_vf_config(pdn); - } else { - phb = pdn->phb->private_data; - ret = opal_pci_reinit(phb->opal_id, - OPAL_REINIT_PCI_DEV, config_addr); - } + if (edev->physfn) + return 0; + + phb = edev->controller->private_data; + ret = opal_pci_reinit(phb->opal_id, + OPAL_REINIT_PCI_DEV, edev->bdfn); if (ret) { pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", - __func__, config_addr, ret); + __func__, edev->bdfn, ret); return -EIO; } @@ -1670,7 +1677,6 @@ static struct eeh_ops pnv_eeh_ops = { .init = pnv_eeh_init, .probe = pnv_eeh_probe, .set_option = pnv_eeh_set_option, - .get_pe_addr = pnv_eeh_get_pe_addr, .get_state = pnv_eeh_get_state, .reset = pnv_eeh_reset, .get_log = pnv_eeh_get_log, diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 2dd467383a88..77513a80cef9 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -48,7 +48,7 @@ static bool default_stop_found; * First stop state levels when SPR and TB loss can occur. */ static u64 pnv_first_tb_loss_level = MAX_STOP_STATE + 1; -static u64 pnv_first_spr_loss_level = MAX_STOP_STATE + 1; +static u64 deep_spr_loss_state = MAX_STOP_STATE + 1; /* * psscr value and mask of the deepest stop idle state. @@ -73,9 +73,6 @@ static int pnv_save_sprs_for_deep_states(void) */ uint64_t lpcr_val = mfspr(SPRN_LPCR); uint64_t hid0_val = mfspr(SPRN_HID0); - uint64_t hid1_val = mfspr(SPRN_HID1); - uint64_t hid4_val = mfspr(SPRN_HID4); - uint64_t hid5_val = mfspr(SPRN_HID5); uint64_t hmeer_val = mfspr(SPRN_HMEER); uint64_t msr_val = MSR_IDLE; uint64_t psscr_val = pnv_deepest_stop_psscr_val; @@ -117,6 +114,9 @@ static int pnv_save_sprs_for_deep_states(void) /* Only p8 needs to set extra HID regiters */ if (!cpu_has_feature(CPU_FTR_ARCH_300)) { + uint64_t hid1_val = mfspr(SPRN_HID1); + uint64_t hid4_val = mfspr(SPRN_HID4); + uint64_t hid5_val = mfspr(SPRN_HID5); rc = opal_slw_set_reg(pir, SPRN_HID1, hid1_val); if (rc != 0) @@ -611,6 +611,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) unsigned long srr1; unsigned long pls; unsigned long mmcr0 = 0; + unsigned long mmcra = 0; struct p9_sprs sprs = {}; /* avoid false used-uninitialised */ bool sprs_saved = false; @@ -657,7 +658,22 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) */ mmcr0 = mfspr(SPRN_MMCR0); } - if ((psscr & PSSCR_RL_MASK) >= pnv_first_spr_loss_level) { + + if (cpu_has_feature(CPU_FTR_ARCH_31)) { + /* + * POWER10 uses MMCRA (BHRBRD) as BHRB disable bit. + * If the user hasn't asked for the BHRB to be + * written, the value of MMCRA[BHRBRD] is 1. + * On wakeup from stop, MMCRA[BHRBD] will be 0, + * since it is previleged resource and will be lost. + * Thus, if we do not save and restore the MMCRA[BHRBD], + * hardware will be needlessly writing to the BHRB + * in problem mode. + */ + mmcra = mfspr(SPRN_MMCRA); + } + + if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) { sprs.lpcr = mfspr(SPRN_LPCR); sprs.hfscr = mfspr(SPRN_HFSCR); sprs.fscr = mfspr(SPRN_FSCR); @@ -700,8 +716,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR)); if ((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS) { - unsigned long mmcra; - /* * We don't need an isync after the mtsprs here because the * upcoming mtmsrd is execution synchronizing. @@ -721,6 +735,10 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mtspr(SPRN_MMCR0, mmcr0); } + /* Reload MMCRA to restore BHRB disable bit for POWER10 */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + mtspr(SPRN_MMCRA, mmcra); + /* * DD2.2 and earlier need to set then clear bit 60 in MMCRA * to ensure the PMU starts running. @@ -741,7 +759,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) * just always test PSSCR for SPR/TB state loss. */ pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT; - if (likely(pls < pnv_first_spr_loss_level)) { + if (likely(pls < deep_spr_loss_state)) { if (sprs_saved) atomic_stop_thread_idle(); goto out; @@ -1088,7 +1106,7 @@ static void __init pnv_power9_idle_init(void) * the deepest loss-less (OPAL_PM_STOP_INST_FAST) stop state. */ pnv_first_tb_loss_level = MAX_STOP_STATE + 1; - pnv_first_spr_loss_level = MAX_STOP_STATE + 1; + deep_spr_loss_state = MAX_STOP_STATE + 1; for (i = 0; i < nr_pnv_idle_states; i++) { int err; struct pnv_idle_states_t *state = &pnv_idle_states[i]; @@ -1099,8 +1117,8 @@ static void __init pnv_power9_idle_init(void) pnv_first_tb_loss_level = psscr_rl; if ((state->flags & OPAL_PM_LOSE_FULL_CONTEXT) && - (pnv_first_spr_loss_level > psscr_rl)) - pnv_first_spr_loss_level = psscr_rl; + (deep_spr_loss_state > psscr_rl)) + deep_spr_loss_state = psscr_rl; /* * The idle code does not deal with TB loss occurring @@ -1111,8 +1129,8 @@ static void __init pnv_power9_idle_init(void) * compatibility. */ if ((state->flags & OPAL_PM_TIMEBASE_STOP) && - (pnv_first_spr_loss_level > psscr_rl)) - pnv_first_spr_loss_level = psscr_rl; + (deep_spr_loss_state > psscr_rl)) + deep_spr_loss_state = psscr_rl; err = validate_psscr_val_mask(&state->psscr_val, &state->psscr_mask, @@ -1158,7 +1176,7 @@ static void __init pnv_power9_idle_init(void) } pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n", - pnv_first_spr_loss_level); + deep_spr_loss_state); pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n", pnv_first_tb_loss_level); @@ -1205,7 +1223,7 @@ static void __init pnv_probe_idle_states(void) return; } - if (cpu_has_feature(CPU_FTR_ARCH_300)) + if (pvr_version_is(PVR_POWER9)) pnv_power9_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c index 1656e8965d6b..c094fdf5825c 100644 --- a/arch/powerpc/platforms/powernv/opal-async.c +++ b/arch/powerpc/platforms/powernv/opal-async.c @@ -104,7 +104,7 @@ static int __opal_async_release_token(int token) */ case ASYNC_TOKEN_DISPATCHED: opal_async_tokens[token].state = ASYNC_TOKEN_ABANDONED; - /* Fall through */ + fallthrough; default: rc = 1; } diff --git a/arch/powerpc/platforms/powernv/pci-ioda-tce.c b/arch/powerpc/platforms/powernv/pci-ioda-tce.c index f923359d8afc..5218f5da2737 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda-tce.c +++ b/arch/powerpc/platforms/powernv/pci-ioda-tce.c @@ -166,7 +166,7 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, if (!ptce) { ptce = pnv_tce(tbl, false, idx, alloc); if (!ptce) - return alloc ? H_HARDWARE : H_TOO_HARD; + return -ENOMEM; } if (newtce & TCE_PCI_WRITE) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 73a63efcf855..c9c25fb0783c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -115,32 +115,13 @@ static int __init pci_reset_phbs_setup(char *str) early_param("ppc_pci_reset_phbs", pci_reset_phbs_setup); -static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) -{ - /* - * WARNING: We cannot rely on the resource flags. The Linux PCI - * allocation code sometimes decides to put a 64-bit prefetchable - * BAR in the 32-bit window, so we have to compare the addresses. - * - * For simplicity we only test resource start. - */ - return (r->start >= phb->ioda.m64_base && - r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); -} - -static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags) -{ - unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH); - - return (resource_flags & flags) == flags; -} - static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) { s64 rc; phb->ioda.pe_array[pe_no].phb = phb; phb->ioda.pe_array[pe_no].pe_number = pe_no; + phb->ioda.pe_array[pe_no].dma_setup_done = false; /* * Clear the PE frozen state as it might be put into frozen state @@ -164,26 +145,48 @@ static void pnv_ioda_reserve_pe(struct pnv_phb *phb, int pe_no) return; } + mutex_lock(&phb->ioda.pe_alloc_mutex); if (test_and_set_bit(pe_no, phb->ioda.pe_alloc)) pr_debug("%s: PE %x was reserved on PHB#%x\n", __func__, pe_no, phb->hose->global_number); + mutex_unlock(&phb->ioda.pe_alloc_mutex); pnv_ioda_init_pe(phb, pe_no); } -static struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb) +struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb, int count) { - long pe; + struct pnv_ioda_pe *ret = NULL; + int run = 0, pe, i; + + mutex_lock(&phb->ioda.pe_alloc_mutex); + /* scan backwards for a run of @count cleared bits */ for (pe = phb->ioda.total_pe_num - 1; pe >= 0; pe--) { - if (!test_and_set_bit(pe, phb->ioda.pe_alloc)) - return pnv_ioda_init_pe(phb, pe); + if (test_bit(pe, phb->ioda.pe_alloc)) { + run = 0; + continue; + } + + run++; + if (run == count) + break; + } + if (run != count) + goto out; + + for (i = pe; i < pe + count; i++) { + set_bit(i, phb->ioda.pe_alloc); + pnv_ioda_init_pe(phb, i); } + ret = &phb->ioda.pe_array[pe]; - return NULL; +out: + mutex_unlock(&phb->ioda.pe_alloc_mutex); + return ret; } -static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) +void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) { struct pnv_phb *phb = pe->phb; unsigned int pe_num = pe->pe_number; @@ -192,7 +195,10 @@ static void pnv_ioda_free_pe(struct pnv_ioda_pe *pe) WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */ kfree(pe->npucomp); memset(pe, 0, sizeof(struct pnv_ioda_pe)); + + mutex_lock(&phb->ioda.pe_alloc_mutex); clear_bit(pe_num, phb->ioda.pe_alloc); + mutex_unlock(&phb->ioda.pe_alloc_mutex); } /* The default M64 BAR is shared by all PEs */ @@ -252,8 +258,7 @@ fail: static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev, unsigned long *pe_bitmap) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct resource *r; resource_size_t base, sgsz, start, end; int segno, i; @@ -311,6 +316,28 @@ static int pnv_ioda1_init_m64(struct pnv_phb *phb) } } + for (index = 0; index < phb->ioda.total_pe_num; index++) { + int64_t rc; + + /* + * P7IOC supports M64DT, which helps mapping M64 segment + * to one particular PE#. However, PHB3 has fixed mapping + * between M64 segment and PE#. In order to have same logic + * for P7IOC and PHB3, we enforce fixed mapping between M64 + * segment and PE# on P7IOC. + */ + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + index, OPAL_M64_WINDOW_TYPE, + index / PNV_IODA1_M64_SEGS, + index % PNV_IODA1_M64_SEGS); + if (rc != OPAL_SUCCESS) { + pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n", + __func__, rc, phb->hose->global_number, + index); + goto fail; + } + } + /* * Exclude the segments for reserved and root bus PE, which * are first or last two PEs. @@ -351,8 +378,7 @@ static void pnv_ioda_reserve_m64_pe(struct pci_bus *bus, static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(bus); struct pnv_ioda_pe *master_pe, *pe; unsigned long size, *pe_alloc; int i; @@ -403,26 +429,6 @@ static struct pnv_ioda_pe *pnv_ioda_pick_m64_pe(struct pci_bus *bus, bool all) pe->master = master_pe; list_add_tail(&pe->list, &master_pe->slaves); } - - /* - * P7IOC supports M64DT, which helps mapping M64 segment - * to one particular PE#. However, PHB3 has fixed mapping - * between M64 segment and PE#. In order to have same logic - * for P7IOC and PHB3, we enforce fixed mapping between M64 - * segment and PE# on P7IOC. - */ - if (phb->type == PNV_PHB_IODA1) { - int64_t rc; - - rc = opal_pci_map_pe_mmio_window(phb->opal_id, - pe->pe_number, OPAL_M64_WINDOW_TYPE, - pe->pe_number / PNV_IODA1_M64_SEGS, - pe->pe_number % PNV_IODA1_M64_SEGS); - if (rc != OPAL_SUCCESS) - pr_warn("%s: Error %lld mapping M64 for PHB#%x-PE#%x\n", - __func__, rc, phb->hose->global_number, - pe->pe_number); - } } kfree(pe_alloc); @@ -673,8 +679,7 @@ struct pnv_ioda_pe *pnv_pci_bdfn_to_pe(struct pnv_phb *phb, u16 bdfn) struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus); struct pci_dn *pdn = pci_get_pdn(dev); if (!pdn) @@ -816,7 +821,7 @@ static void pnv_ioda_unset_peltv(struct pnv_phb *phb, pe_warn(pe, "OPAL error %lld remove self from PELTV\n", rc); } -static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) +int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; uint8_t bcomp, dcomp, fcomp; @@ -887,7 +892,7 @@ static int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) return 0; } -static int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) +int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { struct pci_dev *parent; uint8_t bcomp, dcomp, fcomp; @@ -982,95 +987,9 @@ out: return 0; } -#ifdef CONFIG_PCI_IOV -static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) -{ - struct pci_dn *pdn = pci_get_pdn(dev); - int i; - struct resource *res, res2; - resource_size_t size; - u16 num_vfs; - - if (!dev->is_physfn) - return -EINVAL; - - /* - * "offset" is in VFs. The M64 windows are sized so that when they - * are segmented, each segment is the same size as the IOV BAR. - * Each segment is in a separate PE, and the high order bits of the - * address are the PE number. Therefore, each VF's BAR is in a - * separate PE, and changing the IOV BAR start address changes the - * range of PEs the VFs are in. - */ - num_vfs = pdn->num_vfs; - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; - if (!res->flags || !res->parent) - continue; - - /* - * The actual IOV BAR range is determined by the start address - * and the actual size for num_vfs VFs BAR. This check is to - * make sure that after shifting, the range will not overlap - * with another device. - */ - size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); - res2.flags = res->flags; - res2.start = res->start + (size * offset); - res2.end = res2.start + (size * num_vfs) - 1; - - if (res2.end > res->end) { - dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n", - i, &res2, res, num_vfs, offset); - return -EBUSY; - } - } - - /* - * Since M64 BAR shares segments among all possible 256 PEs, - * we have to shift the beginning of PF IOV BAR to make it start from - * the segment which belongs to the PE number assigned to the first VF. - * This creates a "hole" in the /proc/iomem which could be used for - * allocating other resources so we reserve this area below and - * release when IOV is released. - */ - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; - if (!res->flags || !res->parent) - continue; - - size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); - res2 = *res; - res->start += size * offset; - - dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n", - i, &res2, res, (offset > 0) ? "En" : "Dis", - num_vfs, offset); - - if (offset < 0) { - devm_release_resource(&dev->dev, &pdn->holes[i]); - memset(&pdn->holes[i], 0, sizeof(pdn->holes[i])); - } - - pci_update_resource(dev, i + PCI_IOV_RESOURCES); - - if (offset > 0) { - pdn->holes[i].start = res2.start; - pdn->holes[i].end = res2.start + size * offset - 1; - pdn->holes[i].flags = IORESOURCE_BUS; - pdn->holes[i].name = "pnv_iov_reserved"; - devm_request_resource(&dev->dev, res->parent, - &pdn->holes[i]); - } - } - return 0; -} -#endif /* CONFIG_PCI_IOV */ - static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus); struct pci_dn *pdn = pci_get_pdn(dev); struct pnv_ioda_pe *pe; @@ -1082,7 +1001,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) if (pdn->pe_number != IODA_INVALID_PE) return NULL; - pe = pnv_ioda_alloc_pe(phb); + pe = pnv_ioda_alloc_pe(phb, 1); if (!pe) { pr_warn("%s: Not enough PE# available, disabling device\n", pci_name(dev)); @@ -1129,8 +1048,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev) */ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(bus); struct pnv_ioda_pe *pe = NULL; unsigned int pe_num; @@ -1154,7 +1072,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all) /* The PE number isn't pinned by M64 */ if (!pe) - pe = pnv_ioda_alloc_pe(phb); + pe = pnv_ioda_alloc_pe(phb, 1); if (!pe) { pr_warn("%s: Not enough PE# available for PCI bus %04x:%02x\n", @@ -1196,8 +1114,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev) struct pnv_ioda_pe *pe; struct pci_dev *gpu_pdev; struct pci_dn *npu_pdn; - struct pci_controller *hose = pci_bus_to_host(npu_pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(npu_pdev->bus); /* * Intentionally leak a reference on the npu device (for @@ -1297,446 +1214,12 @@ static void pnv_pci_ioda_setup_nvlink(void) #endif } -#ifdef CONFIG_PCI_IOV -static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pci_dn *pdn; - int i, j; - int m64_bars; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - - if (pdn->m64_single_mode) - m64_bars = num_vfs; - else - m64_bars = 1; - - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) - for (j = 0; j < m64_bars; j++) { - if (pdn->m64_map[j][i] == IODA_INVALID_M64) - continue; - opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 0); - clear_bit(pdn->m64_map[j][i], &phb->ioda.m64_bar_alloc); - pdn->m64_map[j][i] = IODA_INVALID_M64; - } - - kfree(pdn->m64_map); - return 0; -} - -static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pci_dn *pdn; - unsigned int win; - struct resource *res; - int i, j; - int64_t rc; - int total_vfs; - resource_size_t size, start; - int pe_num; - int m64_bars; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - total_vfs = pci_sriov_get_totalvfs(pdev); - - if (pdn->m64_single_mode) - m64_bars = num_vfs; - else - m64_bars = 1; - - pdn->m64_map = kmalloc_array(m64_bars, - sizeof(*pdn->m64_map), - GFP_KERNEL); - if (!pdn->m64_map) - return -ENOMEM; - /* Initialize the m64_map to IODA_INVALID_M64 */ - for (i = 0; i < m64_bars ; i++) - for (j = 0; j < PCI_SRIOV_NUM_BARS; j++) - pdn->m64_map[i][j] = IODA_INVALID_M64; - - - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &pdev->resource[i + PCI_IOV_RESOURCES]; - if (!res->flags || !res->parent) - continue; - - for (j = 0; j < m64_bars; j++) { - do { - win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, - phb->ioda.m64_bar_idx + 1, 0); - - if (win >= phb->ioda.m64_bar_idx + 1) - goto m64_failed; - } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); - - pdn->m64_map[j][i] = win; - - if (pdn->m64_single_mode) { - size = pci_iov_resource_size(pdev, - PCI_IOV_RESOURCES + i); - start = res->start + size * j; - } else { - size = resource_size(res); - start = res->start; - } - - /* Map the M64 here */ - if (pdn->m64_single_mode) { - pe_num = pdn->pe_num_map[j]; - rc = opal_pci_map_pe_mmio_window(phb->opal_id, - pe_num, OPAL_M64_WINDOW_TYPE, - pdn->m64_map[j][i], 0); - } - - rc = opal_pci_set_phb_mem_window(phb->opal_id, - OPAL_M64_WINDOW_TYPE, - pdn->m64_map[j][i], - start, - 0, /* unused */ - size); - - - if (rc != OPAL_SUCCESS) { - dev_err(&pdev->dev, "Failed to map M64 window #%d: %lld\n", - win, rc); - goto m64_failed; - } - - if (pdn->m64_single_mode) - rc = opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 2); - else - rc = opal_pci_phb_mmio_enable(phb->opal_id, - OPAL_M64_WINDOW_TYPE, pdn->m64_map[j][i], 1); - - if (rc != OPAL_SUCCESS) { - dev_err(&pdev->dev, "Failed to enable M64 window #%d: %llx\n", - win, rc); - goto m64_failed; - } - } - } - return 0; - -m64_failed: - pnv_pci_vf_release_m64(pdev, num_vfs); - return -EBUSY; -} - -static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, - int num); - -static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe) -{ - struct iommu_table *tbl; - int64_t rc; - - tbl = pe->table_group.tables[0]; - rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); - if (rc) - pe_warn(pe, "OPAL error %lld release DMA window\n", rc); - - pnv_pci_ioda2_set_bypass(pe, false); - if (pe->table_group.group) { - iommu_group_put(pe->table_group.group); - BUG_ON(pe->table_group.group); - } - iommu_tce_table_put(tbl); -} - -static void pnv_ioda_release_vf_PE(struct pci_dev *pdev) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe, *pe_n; - struct pci_dn *pdn; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - - if (!pdev->is_physfn) - return; - - list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { - if (pe->parent_dev != pdev) - continue; - - pnv_pci_ioda2_release_dma_pe(pdev, pe); - - /* Remove from list */ - mutex_lock(&phb->ioda.pe_list_mutex); - list_del(&pe->list); - mutex_unlock(&phb->ioda.pe_list_mutex); - - pnv_ioda_deconfigure_pe(phb, pe); - - pnv_ioda_free_pe(pe); - } -} - -void pnv_pci_sriov_disable(struct pci_dev *pdev) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe; - struct pci_dn *pdn; - u16 num_vfs, i; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - num_vfs = pdn->num_vfs; - - /* Release VF PEs */ - pnv_ioda_release_vf_PE(pdev); - - if (phb->type == PNV_PHB_IODA2) { - if (!pdn->m64_single_mode) - pnv_pci_vf_resource_shift(pdev, -*pdn->pe_num_map); - - /* Release M64 windows */ - pnv_pci_vf_release_m64(pdev, num_vfs); - - /* Release PE numbers */ - if (pdn->m64_single_mode) { - for (i = 0; i < num_vfs; i++) { - if (pdn->pe_num_map[i] == IODA_INVALID_PE) - continue; - - pe = &phb->ioda.pe_array[pdn->pe_num_map[i]]; - pnv_ioda_free_pe(pe); - } - } else - bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); - /* Releasing pe_num_map */ - kfree(pdn->pe_num_map); - } -} - -static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, +static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); -static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe; - int pe_num; - u16 vf_index; - struct pci_dn *pdn; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - - if (!pdev->is_physfn) - return; - - /* Reserve PE for each VF */ - for (vf_index = 0; vf_index < num_vfs; vf_index++) { - int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index); - int vf_bus = pci_iov_virtfn_bus(pdev, vf_index); - struct pci_dn *vf_pdn; - - if (pdn->m64_single_mode) - pe_num = pdn->pe_num_map[vf_index]; - else - pe_num = *pdn->pe_num_map + vf_index; - - pe = &phb->ioda.pe_array[pe_num]; - pe->pe_number = pe_num; - pe->phb = phb; - pe->flags = PNV_IODA_PE_VF; - pe->pbus = NULL; - pe->parent_dev = pdev; - pe->mve_number = -1; - pe->rid = (vf_bus << 8) | vf_devfn; - - pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n", - hose->global_number, pdev->bus->number, - PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num); - - if (pnv_ioda_configure_pe(phb, pe)) { - /* XXX What do we do here ? */ - pnv_ioda_free_pe(pe); - pe->pdev = NULL; - continue; - } - - /* Put PE to the list */ - mutex_lock(&phb->ioda.pe_list_mutex); - list_add_tail(&pe->list, &phb->ioda.pe_list); - mutex_unlock(&phb->ioda.pe_list_mutex); - - /* associate this pe to it's pdn */ - list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) { - if (vf_pdn->busno == vf_bus && - vf_pdn->devfn == vf_devfn) { - vf_pdn->pe_number = pe_num; - break; - } - } - - pnv_pci_ioda2_setup_dma_pe(phb, pe); - } -} - -int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) -{ - struct pci_bus *bus; - struct pci_controller *hose; - struct pnv_phb *phb; - struct pnv_ioda_pe *pe; - struct pci_dn *pdn; - int ret; - u16 i; - - bus = pdev->bus; - hose = pci_bus_to_host(bus); - phb = hose->private_data; - pdn = pci_get_pdn(pdev); - - if (phb->type == PNV_PHB_IODA2) { - if (!pdn->vfs_expanded) { - dev_info(&pdev->dev, "don't support this SRIOV device" - " with non 64bit-prefetchable IOV BAR\n"); - return -ENOSPC; - } - - /* - * When M64 BARs functions in Single PE mode, the number of VFs - * could be enabled must be less than the number of M64 BARs. - */ - if (pdn->m64_single_mode && num_vfs > phb->ioda.m64_bar_idx) { - dev_info(&pdev->dev, "Not enough M64 BAR for VFs\n"); - return -EBUSY; - } - - /* Allocating pe_num_map */ - if (pdn->m64_single_mode) - pdn->pe_num_map = kmalloc_array(num_vfs, - sizeof(*pdn->pe_num_map), - GFP_KERNEL); - else - pdn->pe_num_map = kmalloc(sizeof(*pdn->pe_num_map), GFP_KERNEL); - - if (!pdn->pe_num_map) - return -ENOMEM; - - if (pdn->m64_single_mode) - for (i = 0; i < num_vfs; i++) - pdn->pe_num_map[i] = IODA_INVALID_PE; - - /* Calculate available PE for required VFs */ - if (pdn->m64_single_mode) { - for (i = 0; i < num_vfs; i++) { - pe = pnv_ioda_alloc_pe(phb); - if (!pe) { - ret = -EBUSY; - goto m64_failed; - } - - pdn->pe_num_map[i] = pe->pe_number; - } - } else { - mutex_lock(&phb->ioda.pe_alloc_mutex); - *pdn->pe_num_map = bitmap_find_next_zero_area( - phb->ioda.pe_alloc, phb->ioda.total_pe_num, - 0, num_vfs, 0); - if (*pdn->pe_num_map >= phb->ioda.total_pe_num) { - mutex_unlock(&phb->ioda.pe_alloc_mutex); - dev_info(&pdev->dev, "Failed to enable VF%d\n", num_vfs); - kfree(pdn->pe_num_map); - return -EBUSY; - } - bitmap_set(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); - mutex_unlock(&phb->ioda.pe_alloc_mutex); - } - pdn->num_vfs = num_vfs; - - /* Assign M64 window accordingly */ - ret = pnv_pci_vf_assign_m64(pdev, num_vfs); - if (ret) { - dev_info(&pdev->dev, "Not enough M64 window resources\n"); - goto m64_failed; - } - - /* - * When using one M64 BAR to map one IOV BAR, we need to shift - * the IOV BAR according to the PE# allocated to the VFs. - * Otherwise, the PE# for the VF will conflict with others. - */ - if (!pdn->m64_single_mode) { - ret = pnv_pci_vf_resource_shift(pdev, *pdn->pe_num_map); - if (ret) - goto m64_failed; - } - } - - /* Setup VF PEs */ - pnv_ioda_setup_vf_PE(pdev, num_vfs); - - return 0; - -m64_failed: - if (pdn->m64_single_mode) { - for (i = 0; i < num_vfs; i++) { - if (pdn->pe_num_map[i] == IODA_INVALID_PE) - continue; - - pe = &phb->ioda.pe_array[pdn->pe_num_map[i]]; - pnv_ioda_free_pe(pe); - } - } else - bitmap_clear(phb->ioda.pe_alloc, *pdn->pe_num_map, num_vfs); - - /* Releasing pe_num_map */ - kfree(pdn->pe_num_map); - - return ret; -} - -int pnv_pcibios_sriov_disable(struct pci_dev *pdev) -{ - pnv_pci_sriov_disable(pdev); - - /* Release PCI data */ - remove_sriov_vf_pdns(pdev); - return 0; -} - -int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) -{ - /* Allocate PCI data */ - add_sriov_vf_pdns(pdev); - - return pnv_pci_sriov_enable(pdev, num_vfs); -} -#endif /* CONFIG_PCI_IOV */ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *pe; @@ -1762,6 +1245,24 @@ static void pnv_pci_ioda_dma_dev_setup(struct pci_dev *pdev) pci_info(pdev, "Added to existing PE#%x\n", pe->pe_number); } + /* + * We assume that bridges *probably* don't need to do any DMA so we can + * skip allocating a TCE table, etc unless we get a non-bridge device. + */ + if (!pe->dma_setup_done && !pci_is_bridge(pdev)) { + switch (phb->type) { + case PNV_PHB_IODA1: + pnv_pci_ioda1_setup_dma_pe(phb, pe); + break; + case PNV_PHB_IODA2: + pnv_pci_ioda2_setup_dma_pe(phb, pe); + break; + default: + pr_warn("%s: No DMA for PHB#%x (type %d)\n", + __func__, phb->hose->global_number, phb->type); + } + } + if (pdn) pdn->pe_number = pe->pe_number; pe->device_count++; @@ -1847,8 +1348,7 @@ err: static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev, u64 dma_mask) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *pe; @@ -1885,19 +1385,6 @@ static bool pnv_pci_ioda_iommu_bypass_supported(struct pci_dev *pdev, return false; } -static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) -{ - struct pci_dev *dev; - - list_for_each_entry(dev, &bus->devices, bus_list) { - set_iommu_table_base(&dev->dev, pe->table_group.tables[0]); - dev->dev.archdata.dma_offset = pe->tce_bypass_base; - - if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) - pnv_ioda_setup_bus_dma(pe, dev->subordinate); - } -} - static inline __be64 __iomem *pnv_ioda_get_inval_reg(struct pnv_phb *phb, bool real_mode) { @@ -2285,6 +1772,7 @@ found: pe->table_group.tce32_size = tbl->it_size << tbl->it_page_shift; iommu_init_table(tbl, phb->hose->node, 0, 0); + pe->dma_setup_done = true; return; fail: /* XXX Failure: Try to fallback to 64-bit only ? */ @@ -2474,7 +1962,6 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe) return 0; } -#if defined(CONFIG_IOMMU_API) || defined(CONFIG_PCI_IOV) static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, int num) { @@ -2498,7 +1985,6 @@ static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group, return ret; } -#endif #ifdef CONFIG_IOMMU_API unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift, @@ -2547,6 +2033,19 @@ static long pnv_pci_ioda2_create_table_userspace( return ret; } +static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe, struct pci_bus *bus) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + set_iommu_table_base(&dev->dev, pe->table_group.tables[0]); + dev->dev.archdata.dma_offset = pe->tce_bypass_base; + + if ((pe->flags & PNV_IODA_PE_BUS_ALL) && dev->subordinate) + pnv_ioda_setup_bus_dma(pe, dev->subordinate); + } +} + static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group) { struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, @@ -2583,14 +2082,11 @@ static struct iommu_table_group_ops pnv_pci_ioda2_ops = { }; #endif -static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, - struct pnv_ioda_pe *pe) +void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, + struct pnv_ioda_pe *pe) { int64_t rc; - if (!pnv_pci_ioda_pe_dma_weight(pe)) - return; - /* TVE #1 is selected by PCI address bit 59 */ pe->tce_bypass_base = 1ull << 59; @@ -2615,6 +2111,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, iommu_register_group(&pe->table_group, phb->hose->global_number, pe->pe_number); #endif + pe->dma_setup_done = true; } int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq) @@ -2763,118 +2260,6 @@ static void pnv_pci_init_ioda_msis(struct pnv_phb *phb) count, phb->msi_base); } -#ifdef CONFIG_PCI_IOV -static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) -{ - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; - const resource_size_t gate = phb->ioda.m64_segsize >> 2; - struct resource *res; - int i; - resource_size_t size, total_vf_bar_sz; - struct pci_dn *pdn; - int mul, total_vfs; - - pdn = pci_get_pdn(pdev); - pdn->vfs_expanded = 0; - pdn->m64_single_mode = false; - - total_vfs = pci_sriov_get_totalvfs(pdev); - mul = phb->ioda.total_pe_num; - total_vf_bar_sz = 0; - - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &pdev->resource[i + PCI_IOV_RESOURCES]; - if (!res->flags || res->parent) - continue; - if (!pnv_pci_is_m64_flags(res->flags)) { - dev_warn(&pdev->dev, "Don't support SR-IOV with" - " non M64 VF BAR%d: %pR. \n", - i, res); - goto truncate_iov; - } - - total_vf_bar_sz += pci_iov_resource_size(pdev, - i + PCI_IOV_RESOURCES); - - /* - * If bigger than quarter of M64 segment size, just round up - * power of two. - * - * Generally, one M64 BAR maps one IOV BAR. To avoid conflict - * with other devices, IOV BAR size is expanded to be - * (total_pe * VF_BAR_size). When VF_BAR_size is half of M64 - * segment size , the expanded size would equal to half of the - * whole M64 space size, which will exhaust the M64 Space and - * limit the system flexibility. This is a design decision to - * set the boundary to quarter of the M64 segment size. - */ - if (total_vf_bar_sz > gate) { - mul = roundup_pow_of_two(total_vfs); - dev_info(&pdev->dev, - "VF BAR Total IOV size %llx > %llx, roundup to %d VFs\n", - total_vf_bar_sz, gate, mul); - pdn->m64_single_mode = true; - break; - } - } - - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &pdev->resource[i + PCI_IOV_RESOURCES]; - if (!res->flags || res->parent) - continue; - - size = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); - /* - * On PHB3, the minimum size alignment of M64 BAR in single - * mode is 32MB. - */ - if (pdn->m64_single_mode && (size < SZ_32M)) - goto truncate_iov; - dev_dbg(&pdev->dev, " Fixing VF BAR%d: %pR to\n", i, res); - res->end = res->start + size * mul - 1; - dev_dbg(&pdev->dev, " %pR\n", res); - dev_info(&pdev->dev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", - i, res, mul); - } - pdn->vfs_expanded = mul; - - return; - -truncate_iov: - /* To save MMIO space, IOV BAR is truncated. */ - for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &pdev->resource[i + PCI_IOV_RESOURCES]; - res->flags = 0; - res->end = res->start - 1; - } -} - -static void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev) -{ - if (WARN_ON(pci_dev_is_added(pdev))) - return; - - if (pdev->is_virtfn) { - struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev); - - /* - * VF PEs are single-device PEs so their pdev pointer needs to - * be set. The pdev doesn't exist when the PE is allocated (in - * (pcibios_sriov_enable()) so we fix it up here. - */ - pe->pdev = pdev; - WARN_ON(!(pe->flags & PNV_IODA_PE_VF)); - } else if (pdev->is_physfn) { - /* - * For PFs adjust their allocated IOV resources to match what - * the PHB can support using it's M64 BAR table. - */ - pnv_pci_ioda_fixup_iov_resources(pdev); - } -} -#endif /* CONFIG_PCI_IOV */ - static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, struct resource *res) { @@ -3101,10 +2486,9 @@ static void pnv_pci_ioda_fixup(void) static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, unsigned long type) { - struct pci_dev *bridge; - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(bus); int num_pci_bridges = 0; + struct pci_dev *bridge; bridge = bus->self; while (bridge) { @@ -3190,8 +2574,6 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus, static void pnv_pci_configure_bus(struct pci_bus *bus) { - struct pci_controller *hose = pci_bus_to_host(bus); - struct pnv_phb *phb = hose->private_data; struct pci_dev *bridge = bus->self; struct pnv_ioda_pe *pe; bool all = (bridge && pci_pcie_type(bridge) == PCI_EXP_TYPE_PCI_BRIDGE); @@ -3215,17 +2597,6 @@ static void pnv_pci_configure_bus(struct pci_bus *bus) return; pnv_ioda_setup_pe_seg(pe); - switch (phb->type) { - case PNV_PHB_IODA1: - pnv_pci_ioda1_setup_dma_pe(phb, pe); - break; - case PNV_PHB_IODA2: - pnv_pci_ioda2_setup_dma_pe(phb, pe); - break; - default: - pr_warn("%s: No DMA for PHB#%x (type %d)\n", - __func__, phb->hose->global_number, phb->type); - } } static resource_size_t pnv_pci_default_alignment(void) @@ -3233,49 +2604,12 @@ static resource_size_t pnv_pci_default_alignment(void) return PAGE_SIZE; } -#ifdef CONFIG_PCI_IOV -static resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, - int resno) -{ - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; - struct pci_dn *pdn = pci_get_pdn(pdev); - resource_size_t align; - - /* - * On PowerNV platform, IOV BAR is mapped by M64 BAR to enable the - * SR-IOV. While from hardware perspective, the range mapped by M64 - * BAR should be size aligned. - * - * When IOV BAR is mapped with M64 BAR in Single PE mode, the extra - * powernv-specific hardware restriction is gone. But if just use the - * VF BAR size as the alignment, PF BAR / VF BAR may be allocated with - * in one segment of M64 #15, which introduces the PE conflict between - * PF and VF. Based on this, the minimum alignment of an IOV BAR is - * m64_segsize. - * - * This function returns the total IOV BAR size if M64 BAR is in - * Shared PE mode or just VF BAR size if not. - * If the M64 BAR is in Single PE mode, return the VF BAR size or - * M64 segment size if IOV BAR size is less. - */ - align = pci_iov_resource_size(pdev, resno); - if (!pdn->vfs_expanded) - return align; - if (pdn->m64_single_mode) - return max(align, (resource_size_t)phb->ioda.m64_segsize); - - return pdn->vfs_expanded * align; -} -#endif /* CONFIG_PCI_IOV */ - /* Prevent enabling devices for which we couldn't properly * assign a PE */ static bool pnv_pci_enable_device_hook(struct pci_dev *dev) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus); struct pci_dn *pdn; /* The function is probably called while the PEs have @@ -3346,11 +2680,10 @@ static long pnv_pci_ioda1_unset_window(struct iommu_table_group *table_group, static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe) { - unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe); struct iommu_table *tbl = pe->table_group.tables[0]; int64_t rc; - if (!weight) + if (!pe->dma_setup_done) return; rc = pnv_pci_ioda1_unset_window(&pe->table_group, 0); @@ -3367,22 +2700,17 @@ static void pnv_pci_ioda1_release_pe_dma(struct pnv_ioda_pe *pe) iommu_tce_table_put(tbl); } -static void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) +void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe) { struct iommu_table *tbl = pe->table_group.tables[0]; - unsigned int weight = pnv_pci_ioda_pe_dma_weight(pe); -#ifdef CONFIG_IOMMU_API int64_t rc; -#endif - if (!weight) + if (pe->dma_setup_done) return; -#ifdef CONFIG_IOMMU_API rc = pnv_pci_ioda2_unset_window(&pe->table_group, 0); if (rc) pe_warn(pe, "OPAL error %lld release DMA window\n", rc); -#endif pnv_pci_ioda2_set_bypass(pe, false); if (pe->table_group.group) { @@ -3405,14 +2733,8 @@ static void pnv_ioda_free_pe_seg(struct pnv_ioda_pe *pe, if (map[idx] != pe->pe_number) continue; - if (win == OPAL_M64_WINDOW_TYPE) - rc = opal_pci_map_pe_mmio_window(phb->opal_id, - phb->ioda.reserved_pe_idx, win, - idx / PNV_IODA1_M64_SEGS, - idx % PNV_IODA1_M64_SEGS); - else - rc = opal_pci_map_pe_mmio_window(phb->opal_id, - phb->ioda.reserved_pe_idx, win, 0, idx); + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + phb->ioda.reserved_pe_idx, win, 0, idx); if (rc != OPAL_SUCCESS) pe_warn(pe, "Error %lld unmapping (%d) segment#%d\n", @@ -3431,8 +2753,7 @@ static void pnv_ioda_release_pe_seg(struct pnv_ioda_pe *pe) phb->ioda.io_segmap); pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE, phb->ioda.m32_segmap); - pnv_ioda_free_pe_seg(pe, OPAL_M64_WINDOW_TYPE, - phb->ioda.m64_segmap); + /* M64 is pre-configured by pnv_ioda1_init_m64() */ } else if (phb->type == PNV_PHB_IODA2) { pnv_ioda_free_pe_seg(pe, OPAL_M32_WINDOW_TYPE, phb->ioda.m32_segmap); @@ -3488,17 +2809,27 @@ static void pnv_ioda_release_pe(struct pnv_ioda_pe *pe) static void pnv_pci_release_device(struct pci_dev *pdev) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct pci_dn *pdn = pci_get_pdn(pdev); struct pnv_ioda_pe *pe; + /* The VF PE state is torn down when sriov_disable() is called */ if (pdev->is_virtfn) return; if (!pdn || pdn->pe_number == IODA_INVALID_PE) return; +#ifdef CONFIG_PCI_IOV + /* + * FIXME: Try move this to sriov_disable(). It's here since we allocate + * the iov state at probe time since we need to fiddle with the IOV + * resources. + */ + if (pdev->is_physfn) + kfree(pdev->dev.archdata.iov_data); +#endif + /* * PCI hotplug can happen as part of EEH error recovery. The @pdn * isn't removed and added afterwards in this scenario. We should @@ -3534,8 +2865,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static void pnv_pci_ioda_dma_bus_setup(struct pci_bus *bus) { - struct pci_controller *hose = bus->sysdata; - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(bus); struct pnv_ioda_pe *pe; list_for_each_entry(pe, &phb->ioda.pe_list, list) { @@ -3760,7 +3090,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, pnv_ioda_reserve_pe(phb, phb->ioda.root_pe_idx); } else { /* otherwise just allocate one */ - root_pe = pnv_ioda_alloc_pe(phb); + root_pe = pnv_ioda_alloc_pe(phb, 1); phb->ioda.root_pe_idx = root_pe->pe_number; } @@ -3873,8 +3203,7 @@ void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np) static void pnv_npu2_opencapi_cfg_size_fixup(struct pci_dev *dev) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus); if (!machine_is(powernv)) return; diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c new file mode 100644 index 000000000000..c4434f20f42f --- /dev/null +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -0,0 +1,766 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/kernel.h> +#include <linux/ioport.h> +#include <linux/bitmap.h> +#include <linux/pci.h> + +#include <asm/opal.h> + +#include "pci.h" + +/* for pci_dev_is_added() */ +#include "../../../../drivers/pci/pci.h" + +/* + * The majority of the complexity in supporting SR-IOV on PowerNV comes from + * the need to put the MMIO space for each VF into a separate PE. Internally + * the PHB maps MMIO addresses to a specific PE using the "Memory BAR Table". + * The MBT historically only applied to the 64bit MMIO window of the PHB + * so it's common to see it referred to as the "M64BT". + * + * An MBT entry stores the mapped range as an <base>,<mask> pair. This forces + * the address range that we want to map to be power-of-two sized and aligned. + * For conventional PCI devices this isn't really an issue since PCI device BARs + * have the same requirement. + * + * For a SR-IOV BAR things are a little more awkward since size and alignment + * are not coupled. The alignment is set based on the the per-VF BAR size, but + * the total BAR area is: number-of-vfs * per-vf-size. The number of VFs + * isn't necessarily a power of two, so neither is the total size. To fix that + * we need to finesse (read: hack) the Linux BAR allocator so that it will + * allocate the SR-IOV BARs in a way that lets us map them using the MBT. + * + * The changes to size and alignment that we need to do depend on the "mode" + * of MBT entry that we use. We only support SR-IOV on PHB3 (IODA2) and above, + * so as a baseline we can assume that we have the following BAR modes + * available: + * + * NB: $PE_COUNT is the number of PEs that the PHB supports. + * + * a) A segmented BAR that splits the mapped range into $PE_COUNT equally sized + * segments. The n'th segment is mapped to the n'th PE. + * b) An un-segmented BAR that maps the whole address range to a specific PE. + * + * + * We prefer to use mode a) since it only requires one MBT entry per SR-IOV BAR + * For comparison b) requires one entry per-VF per-BAR, or: + * (num-vfs * num-sriov-bars) in total. To use a) we need the size of each segment + * to equal the size of the per-VF BAR area. So: + * + * new_size = per-vf-size * number-of-PEs + * + * The alignment for the SR-IOV BAR also needs to be changed from per-vf-size + * to "new_size", calculated above. Implementing this is a convoluted process + * which requires several hooks in the PCI core: + * + * 1. In pcibios_add_device() we call pnv_pci_ioda_fixup_iov(). + * + * At this point the device has been probed and the device's BARs are sized, + * but no resource allocations have been done. The SR-IOV BARs are sized + * based on the maximum number of VFs supported by the device and we need + * to increase that to new_size. + * + * 2. Later, when Linux actually assigns resources it tries to make the resource + * allocations for each PCI bus as compact as possible. As a part of that it + * sorts the BARs on a bus by their required alignment, which is calculated + * using pci_resource_alignment(). + * + * For IOV resources this goes: + * pci_resource_alignment() + * pci_sriov_resource_alignment() + * pcibios_sriov_resource_alignment() + * pnv_pci_iov_resource_alignment() + * + * Our hook overrides the default alignment, equal to the per-vf-size, with + * new_size computed above. + * + * 3. When userspace enables VFs for a device: + * + * sriov_enable() + * pcibios_sriov_enable() + * pnv_pcibios_sriov_enable() + * + * This is where we actually allocate PE numbers for each VF and setup the + * MBT mapping for each SR-IOV BAR. In steps 1) and 2) we setup an "arena" + * where each MBT segment is equal in size to the VF BAR so we can shift + * around the actual SR-IOV BAR location within this arena. We need this + * ability because the PE space is shared by all devices on the same PHB. + * When using mode a) described above segment 0 in maps to PE#0 which might + * be already being used by another device on the PHB. + * + * As a result we need allocate a contigious range of PE numbers, then shift + * the address programmed into the SR-IOV BAR of the PF so that the address + * of VF0 matches up with the segment corresponding to the first allocated + * PE number. This is handled in pnv_pci_vf_resource_shift(). + * + * Once all that is done we return to the PCI core which then enables VFs, + * scans them and creates pci_devs for each. The init process for a VF is + * largely the same as a normal device, but the VF is inserted into the IODA + * PE that we allocated for it rather than the PE associated with the bus. + * + * 4. When userspace disables VFs we unwind the above in + * pnv_pcibios_sriov_disable(). Fortunately this is relatively simple since + * we don't need to validate anything, just tear down the mappings and + * move SR-IOV resource back to its "proper" location. + * + * That's how mode a) works. In theory mode b) (single PE mapping) is less work + * since we can map each individual VF with a separate BAR. However, there's a + * few limitations: + * + * 1) For IODA2 mode b) has a minimum alignment requirement of 32MB. This makes + * it only usable for devices with very large per-VF BARs. Such devices are + * similar to Big Foot. They definitely exist, but I've never seen one. + * + * 2) The number of MBT entries that we have is limited. PHB3 and PHB4 only + * 16 total and some are needed for. Most SR-IOV capable network cards can support + * more than 16 VFs on each port. + * + * We use b) when using a) would use more than 1/4 of the entire 64 bit MMIO + * window of the PHB. + * + * + * + * PHB4 (IODA3) added a few new features that would be useful for SR-IOV. It + * allowed the MBT to map 32bit MMIO space in addition to 64bit which allows + * us to support SR-IOV BARs in the 32bit MMIO window. This is useful since + * the Linux BAR allocation will place any BAR marked as non-prefetchable into + * the non-prefetchable bridge window, which is 32bit only. It also added two + * new modes: + * + * c) A segmented BAR similar to a), but each segment can be individually + * mapped to any PE. This is matches how the 32bit MMIO window worked on + * IODA1&2. + * + * d) A segmented BAR with 8, 64, or 128 segments. This works similarly to a), + * but with fewer segments and configurable base PE. + * + * i.e. The n'th segment maps to the (n + base)'th PE. + * + * The base PE is also required to be a multiple of the window size. + * + * Unfortunately, the OPAL API doesn't currently (as of skiboot v6.6) allow us + * to exploit any of the IODA3 features. + */ + +static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) +{ + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); + struct resource *res; + int i; + resource_size_t vf_bar_sz; + struct pnv_iov_data *iov; + int mul; + + iov = kzalloc(sizeof(*iov), GFP_KERNEL); + if (!iov) + goto disable_iov; + pdev->dev.archdata.iov_data = iov; + mul = phb->ioda.total_pe_num; + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || res->parent) + continue; + if (!pnv_pci_is_m64_flags(res->flags)) { + dev_warn(&pdev->dev, "Don't support SR-IOV with non M64 VF BAR%d: %pR. \n", + i, res); + goto disable_iov; + } + + vf_bar_sz = pci_iov_resource_size(pdev, i + PCI_IOV_RESOURCES); + + /* + * Generally, one segmented M64 BAR maps one IOV BAR. However, + * if a VF BAR is too large we end up wasting a lot of space. + * If each VF needs more than 1/4 of the default m64 segment + * then each VF BAR should be mapped in single-PE mode to reduce + * the amount of space required. This does however limit the + * number of VFs we can support. + * + * The 1/4 limit is arbitrary and can be tweaked. + */ + if (vf_bar_sz > (phb->ioda.m64_segsize >> 2)) { + /* + * On PHB3, the minimum size alignment of M64 BAR in + * single mode is 32MB. If this VF BAR is smaller than + * 32MB, but still too large for a segmented window + * then we can't map it and need to disable SR-IOV for + * this device. + */ + if (vf_bar_sz < SZ_32M) { + pci_err(pdev, "VF BAR%d: %pR can't be mapped in single PE mode\n", + i, res); + goto disable_iov; + } + + iov->m64_single_mode[i] = true; + continue; + } + + /* + * This BAR can be mapped with one segmented window, so adjust + * te resource size to accommodate. + */ + pci_dbg(pdev, " Fixing VF BAR%d: %pR to\n", i, res); + res->end = res->start + vf_bar_sz * mul - 1; + pci_dbg(pdev, " %pR\n", res); + + pci_info(pdev, "VF BAR%d: %pR (expanded to %d VFs for PE alignment)", + i, res, mul); + + iov->need_shift = true; + } + + return; + +disable_iov: + /* Save ourselves some MMIO space by disabling the unusable BARs */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + res->flags = 0; + res->end = res->start - 1; + } + + pdev->dev.archdata.iov_data = NULL; + kfree(iov); +} + +void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev) +{ + if (WARN_ON(pci_dev_is_added(pdev))) + return; + + if (pdev->is_virtfn) { + struct pnv_ioda_pe *pe = pnv_ioda_get_pe(pdev); + + /* + * VF PEs are single-device PEs so their pdev pointer needs to + * be set. The pdev doesn't exist when the PE is allocated (in + * (pcibios_sriov_enable()) so we fix it up here. + */ + pe->pdev = pdev; + WARN_ON(!(pe->flags & PNV_IODA_PE_VF)); + } else if (pdev->is_physfn) { + /* + * For PFs adjust their allocated IOV resources to match what + * the PHB can support using it's M64 BAR table. + */ + pnv_pci_ioda_fixup_iov_resources(pdev); + } +} + +resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, + int resno) +{ + resource_size_t align = pci_iov_resource_size(pdev, resno); + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); + struct pnv_iov_data *iov = pnv_iov_get(pdev); + + /* + * iov can be null if we have an SR-IOV device with IOV BAR that can't + * be placed in the m64 space (i.e. The BAR is 32bit or non-prefetch). + * In that case we don't allow VFs to be enabled since one of their + * BARs would not be placed in the correct PE. + */ + if (!iov) + return align; + + /* + * If we're using single mode then we can just use the native VF BAR + * alignment. We validated that it's possible to use a single PE + * window above when we did the fixup. + */ + if (iov->m64_single_mode[resno - PCI_IOV_RESOURCES]) + return align; + + /* + * On PowerNV platform, IOV BAR is mapped by M64 BAR to enable the + * SR-IOV. While from hardware perspective, the range mapped by M64 + * BAR should be size aligned. + * + * This function returns the total IOV BAR size if M64 BAR is in + * Shared PE mode or just VF BAR size if not. + * If the M64 BAR is in Single PE mode, return the VF BAR size or + * M64 segment size if IOV BAR size is less. + */ + return phb->ioda.total_pe_num * align; +} + +static int pnv_pci_vf_release_m64(struct pci_dev *pdev, u16 num_vfs) +{ + struct pnv_iov_data *iov; + struct pnv_phb *phb; + int window_id; + + phb = pci_bus_to_pnvhb(pdev->bus); + iov = pnv_iov_get(pdev); + + for_each_set_bit(window_id, iov->used_m64_bar_mask, MAX_M64_BARS) { + opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + window_id, + 0); + + clear_bit(window_id, &phb->ioda.m64_bar_alloc); + } + + return 0; +} + + +/* + * PHB3 and beyond support segmented windows. The window's address range + * is subdivided into phb->ioda.total_pe_num segments and there's a 1-1 + * mapping between PEs and segments. + */ +static int64_t pnv_ioda_map_m64_segmented(struct pnv_phb *phb, + int window_id, + resource_size_t start, + resource_size_t size) +{ + int64_t rc; + + rc = opal_pci_set_phb_mem_window(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + window_id, + start, + 0, /* unused */ + size); + if (rc) + goto out; + + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + window_id, + OPAL_ENABLE_M64_SPLIT); +out: + if (rc) + pr_err("Failed to map M64 window #%d: %lld\n", window_id, rc); + + return rc; +} + +static int64_t pnv_ioda_map_m64_single(struct pnv_phb *phb, + int pe_num, + int window_id, + resource_size_t start, + resource_size_t size) +{ + int64_t rc; + + /* + * The API for setting up m64 mmio windows seems to have been designed + * with P7-IOC in mind. For that chip each M64 BAR (window) had a fixed + * split of 8 equally sized segments each of which could individually + * assigned to a PE. + * + * The problem with this is that the API doesn't have any way to + * communicate the number of segments we want on a BAR. This wasn't + * a problem for p7-ioc since you didn't have a choice, but the + * single PE windows added in PHB3 don't map cleanly to this API. + * + * As a result we've got this slightly awkward process where we + * call opal_pci_map_pe_mmio_window() to put the single in single + * PE mode, and set the PE for the window before setting the address + * bounds. We need to do it this way because the single PE windows + * for PHB3 have different alignment requirements on PHB3. + */ + rc = opal_pci_map_pe_mmio_window(phb->opal_id, + pe_num, + OPAL_M64_WINDOW_TYPE, + window_id, + 0); + if (rc) + goto out; + + /* + * NB: In single PE mode the window needs to be aligned to 32MB + */ + rc = opal_pci_set_phb_mem_window(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + window_id, + start, + 0, /* ignored by FW, m64 is 1-1 */ + size); + if (rc) + goto out; + + /* + * Now actually enable it. We specified the BAR should be in "non-split" + * mode so FW will validate that the BAR is in single PE mode. + */ + rc = opal_pci_phb_mmio_enable(phb->opal_id, + OPAL_M64_WINDOW_TYPE, + window_id, + OPAL_ENABLE_M64_NON_SPLIT); +out: + if (rc) + pr_err("Error mapping single PE BAR\n"); + + return rc; +} + +static int pnv_pci_alloc_m64_bar(struct pnv_phb *phb, struct pnv_iov_data *iov) +{ + int win; + + do { + win = find_next_zero_bit(&phb->ioda.m64_bar_alloc, + phb->ioda.m64_bar_idx + 1, 0); + + if (win >= phb->ioda.m64_bar_idx + 1) + return -1; + } while (test_and_set_bit(win, &phb->ioda.m64_bar_alloc)); + + set_bit(win, iov->used_m64_bar_mask); + + return win; +} + +static int pnv_pci_vf_assign_m64(struct pci_dev *pdev, u16 num_vfs) +{ + struct pnv_iov_data *iov; + struct pnv_phb *phb; + unsigned int win; + struct resource *res; + int i, j; + int64_t rc; + resource_size_t size, start; + int base_pe_num; + + phb = pci_bus_to_pnvhb(pdev->bus); + iov = pnv_iov_get(pdev); + + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &pdev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + + /* don't need single mode? map everything in one go! */ + if (!iov->m64_single_mode[i]) { + win = pnv_pci_alloc_m64_bar(phb, iov); + if (win < 0) + goto m64_failed; + + size = resource_size(res); + start = res->start; + + rc = pnv_ioda_map_m64_segmented(phb, win, start, size); + if (rc) + goto m64_failed; + + continue; + } + + /* otherwise map each VF with single PE BARs */ + size = pci_iov_resource_size(pdev, PCI_IOV_RESOURCES + i); + base_pe_num = iov->vf_pe_arr[0].pe_number; + + for (j = 0; j < num_vfs; j++) { + win = pnv_pci_alloc_m64_bar(phb, iov); + if (win < 0) + goto m64_failed; + + start = res->start + size * j; + rc = pnv_ioda_map_m64_single(phb, win, + base_pe_num + j, + start, + size); + if (rc) + goto m64_failed; + } + } + return 0; + +m64_failed: + pnv_pci_vf_release_m64(pdev, num_vfs); + return -EBUSY; +} + +static void pnv_ioda_release_vf_PE(struct pci_dev *pdev) +{ + struct pnv_phb *phb; + struct pnv_ioda_pe *pe, *pe_n; + + phb = pci_bus_to_pnvhb(pdev->bus); + + if (!pdev->is_physfn) + return; + + /* FIXME: Use pnv_ioda_release_pe()? */ + list_for_each_entry_safe(pe, pe_n, &phb->ioda.pe_list, list) { + if (pe->parent_dev != pdev) + continue; + + pnv_pci_ioda2_release_pe_dma(pe); + + /* Remove from list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_del(&pe->list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + pnv_ioda_deconfigure_pe(phb, pe); + + pnv_ioda_free_pe(pe); + } +} + +static int pnv_pci_vf_resource_shift(struct pci_dev *dev, int offset) +{ + struct resource *res, res2; + struct pnv_iov_data *iov; + resource_size_t size; + u16 num_vfs; + int i; + + if (!dev->is_physfn) + return -EINVAL; + iov = pnv_iov_get(dev); + + /* + * "offset" is in VFs. The M64 windows are sized so that when they + * are segmented, each segment is the same size as the IOV BAR. + * Each segment is in a separate PE, and the high order bits of the + * address are the PE number. Therefore, each VF's BAR is in a + * separate PE, and changing the IOV BAR start address changes the + * range of PEs the VFs are in. + */ + num_vfs = iov->num_vfs; + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + if (iov->m64_single_mode[i]) + continue; + + /* + * The actual IOV BAR range is determined by the start address + * and the actual size for num_vfs VFs BAR. This check is to + * make sure that after shifting, the range will not overlap + * with another device. + */ + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2.flags = res->flags; + res2.start = res->start + (size * offset); + res2.end = res2.start + (size * num_vfs) - 1; + + if (res2.end > res->end) { + dev_err(&dev->dev, "VF BAR%d: %pR would extend past %pR (trying to enable %d VFs shifted by %d)\n", + i, &res2, res, num_vfs, offset); + return -EBUSY; + } + } + + /* + * Since M64 BAR shares segments among all possible 256 PEs, + * we have to shift the beginning of PF IOV BAR to make it start from + * the segment which belongs to the PE number assigned to the first VF. + * This creates a "hole" in the /proc/iomem which could be used for + * allocating other resources so we reserve this area below and + * release when IOV is released. + */ + for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + res = &dev->resource[i + PCI_IOV_RESOURCES]; + if (!res->flags || !res->parent) + continue; + if (iov->m64_single_mode[i]) + continue; + + size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + res2 = *res; + res->start += size * offset; + + dev_info(&dev->dev, "VF BAR%d: %pR shifted to %pR (%sabling %d VFs shifted by %d)\n", + i, &res2, res, (offset > 0) ? "En" : "Dis", + num_vfs, offset); + + if (offset < 0) { + devm_release_resource(&dev->dev, &iov->holes[i]); + memset(&iov->holes[i], 0, sizeof(iov->holes[i])); + } + + pci_update_resource(dev, i + PCI_IOV_RESOURCES); + + if (offset > 0) { + iov->holes[i].start = res2.start; + iov->holes[i].end = res2.start + size * offset - 1; + iov->holes[i].flags = IORESOURCE_BUS; + iov->holes[i].name = "pnv_iov_reserved"; + devm_request_resource(&dev->dev, res->parent, + &iov->holes[i]); + } + } + return 0; +} + +static void pnv_pci_sriov_disable(struct pci_dev *pdev) +{ + u16 num_vfs, base_pe; + struct pnv_iov_data *iov; + + iov = pnv_iov_get(pdev); + num_vfs = iov->num_vfs; + base_pe = iov->vf_pe_arr[0].pe_number; + + if (WARN_ON(!iov)) + return; + + /* Release VF PEs */ + pnv_ioda_release_vf_PE(pdev); + + /* Un-shift the IOV BARs if we need to */ + if (iov->need_shift) + pnv_pci_vf_resource_shift(pdev, -base_pe); + + /* Release M64 windows */ + pnv_pci_vf_release_m64(pdev, num_vfs); +} + +static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) +{ + struct pnv_phb *phb; + struct pnv_ioda_pe *pe; + int pe_num; + u16 vf_index; + struct pnv_iov_data *iov; + struct pci_dn *pdn; + + if (!pdev->is_physfn) + return; + + phb = pci_bus_to_pnvhb(pdev->bus); + pdn = pci_get_pdn(pdev); + iov = pnv_iov_get(pdev); + + /* Reserve PE for each VF */ + for (vf_index = 0; vf_index < num_vfs; vf_index++) { + int vf_devfn = pci_iov_virtfn_devfn(pdev, vf_index); + int vf_bus = pci_iov_virtfn_bus(pdev, vf_index); + struct pci_dn *vf_pdn; + + pe = &iov->vf_pe_arr[vf_index]; + pe->phb = phb; + pe->flags = PNV_IODA_PE_VF; + pe->pbus = NULL; + pe->parent_dev = pdev; + pe->mve_number = -1; + pe->rid = (vf_bus << 8) | vf_devfn; + + pe_num = pe->pe_number; + pe_info(pe, "VF %04d:%02d:%02d.%d associated with PE#%x\n", + pci_domain_nr(pdev->bus), pdev->bus->number, + PCI_SLOT(vf_devfn), PCI_FUNC(vf_devfn), pe_num); + + if (pnv_ioda_configure_pe(phb, pe)) { + /* XXX What do we do here ? */ + pnv_ioda_free_pe(pe); + pe->pdev = NULL; + continue; + } + + /* Put PE to the list */ + mutex_lock(&phb->ioda.pe_list_mutex); + list_add_tail(&pe->list, &phb->ioda.pe_list); + mutex_unlock(&phb->ioda.pe_list_mutex); + + /* associate this pe to it's pdn */ + list_for_each_entry(vf_pdn, &pdn->parent->child_list, list) { + if (vf_pdn->busno == vf_bus && + vf_pdn->devfn == vf_devfn) { + vf_pdn->pe_number = pe_num; + break; + } + } + + pnv_pci_ioda2_setup_dma_pe(phb, pe); + } +} + +static int pnv_pci_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + struct pnv_ioda_pe *base_pe; + struct pnv_iov_data *iov; + struct pnv_phb *phb; + int ret; + u16 i; + + phb = pci_bus_to_pnvhb(pdev->bus); + iov = pnv_iov_get(pdev); + + /* + * There's a calls to IODA2 PE setup code littered throughout. We could + * probably fix that, but we'd still have problems due to the + * restriction inherent on IODA1 PHBs. + * + * NB: We class IODA3 as IODA2 since they're very similar. + */ + if (phb->type != PNV_PHB_IODA2) { + pci_err(pdev, "SR-IOV is not supported on this PHB\n"); + return -ENXIO; + } + + if (!iov) { + dev_info(&pdev->dev, "don't support this SRIOV device with non 64bit-prefetchable IOV BAR\n"); + return -ENOSPC; + } + + /* allocate a contigious block of PEs for our VFs */ + base_pe = pnv_ioda_alloc_pe(phb, num_vfs); + if (!base_pe) { + pci_err(pdev, "Unable to allocate PEs for %d VFs\n", num_vfs); + return -EBUSY; + } + + iov->vf_pe_arr = base_pe; + iov->num_vfs = num_vfs; + + /* Assign M64 window accordingly */ + ret = pnv_pci_vf_assign_m64(pdev, num_vfs); + if (ret) { + dev_info(&pdev->dev, "Not enough M64 window resources\n"); + goto m64_failed; + } + + /* + * When using one M64 BAR to map one IOV BAR, we need to shift + * the IOV BAR according to the PE# allocated to the VFs. + * Otherwise, the PE# for the VF will conflict with others. + */ + if (iov->need_shift) { + ret = pnv_pci_vf_resource_shift(pdev, base_pe->pe_number); + if (ret) + goto shift_failed; + } + + /* Setup VF PEs */ + pnv_ioda_setup_vf_PE(pdev, num_vfs); + + return 0; + +shift_failed: + pnv_pci_vf_release_m64(pdev, num_vfs); + +m64_failed: + for (i = 0; i < num_vfs; i++) + pnv_ioda_free_pe(&iov->vf_pe_arr[i]); + + return ret; +} + +int pnv_pcibios_sriov_disable(struct pci_dev *pdev) +{ + pnv_pci_sriov_disable(pdev); + + /* Release PCI data */ + remove_sriov_vf_pdns(pdev); + return 0; +} + +int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs) +{ + /* Allocate PCI data */ + add_sriov_vf_pdns(pdev); + + return pnv_pci_sriov_enable(pdev, num_vfs); +} diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 091fe1cf386b..9b9bca169275 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -162,8 +162,7 @@ EXPORT_SYMBOL_GPL(pnv_pci_set_power_state); int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct msi_desc *entry; struct msi_msg msg; int hwirq; @@ -211,8 +210,7 @@ int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) void pnv_teardown_msi_irqs(struct pci_dev *pdev) { - struct pci_controller *hose = pci_bus_to_host(pdev->bus); - struct pnv_phb *phb = hose->private_data; + struct pnv_phb *phb = pci_bus_to_pnvhb(pdev->bus); struct msi_desc *entry; irq_hw_number_t hwirq; @@ -824,10 +822,9 @@ EXPORT_SYMBOL(pnv_pci_get_phb_node); int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable) { - __be64 val; - struct pci_controller *hose; - struct pnv_phb *phb; + struct pnv_phb *phb = pci_bus_to_pnvhb(dev->bus); u64 tunnel_bar; + __be64 val; int rc; if (!opal_check_token(OPAL_PCI_GET_PBCQ_TUNNEL_BAR)) @@ -835,9 +832,6 @@ int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable) if (!opal_check_token(OPAL_PCI_SET_PBCQ_TUNNEL_BAR)) return -ENXIO; - hose = pci_bus_to_host(dev->bus); - phb = hose->private_data; - mutex_lock(&tunnel_mutex); rc = opal_pci_get_pbcq_tunnel_bar(phb->opal_id, &val); if (rc != OPAL_SUCCESS) { diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 51c254f2f3cb..739a0b3b72e1 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -87,7 +87,14 @@ struct pnv_ioda_pe { bool tce_bypass_enabled; uint64_t tce_bypass_base; - /* MSIs. MVE index is identical for for 32 and 64 bit MSI + /* + * Used to track whether we've done DMA setup for this PE or not. We + * want to defer allocating TCE tables, etc until we've added a + * non-bridge device to the PE. + */ + bool dma_setup_done; + + /* MSIs. MVE index is identical for 32 and 64 bit MSI * and -1 if not supported. (It's actually identical to the * PE number) */ @@ -147,6 +154,7 @@ struct pnv_phb { unsigned long m64_size; unsigned long m64_segsize; unsigned long m64_base; +#define MAX_M64_BARS 64 unsigned long m64_bar_alloc; /* IO ports */ @@ -187,6 +195,89 @@ struct pnv_phb { u8 *diag_data; }; + +/* IODA PE management */ + +static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) +{ + /* + * WARNING: We cannot rely on the resource flags. The Linux PCI + * allocation code sometimes decides to put a 64-bit prefetchable + * BAR in the 32-bit window, so we have to compare the addresses. + * + * For simplicity we only test resource start. + */ + return (r->start >= phb->ioda.m64_base && + r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); +} + +static inline bool pnv_pci_is_m64_flags(unsigned long resource_flags) +{ + unsigned long flags = (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH); + + return (resource_flags & flags) == flags; +} + +int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); +int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); + +void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe); +void pnv_pci_ioda2_release_pe_dma(struct pnv_ioda_pe *pe); + +struct pnv_ioda_pe *pnv_ioda_alloc_pe(struct pnv_phb *phb, int count); +void pnv_ioda_free_pe(struct pnv_ioda_pe *pe); + +#ifdef CONFIG_PCI_IOV +/* + * For SR-IOV we want to put each VF's MMIO resource in to a separate PE. + * This requires a bit of acrobatics with the MMIO -> PE configuration + * and this structure is used to keep track of it all. + */ +struct pnv_iov_data { + /* number of VFs enabled */ + u16 num_vfs; + + /* pointer to the array of VF PEs. num_vfs long*/ + struct pnv_ioda_pe *vf_pe_arr; + + /* Did we map the VF BAR with single-PE IODA BARs? */ + bool m64_single_mode[PCI_SRIOV_NUM_BARS]; + + /* + * True if we're using any segmented windows. In that case we need + * shift the start of the IOV resource the segment corresponding to + * the allocated PE. + */ + bool need_shift; + + /* + * Bit mask used to track which m64 windows are used to map the + * SR-IOV BARs for this device. + */ + DECLARE_BITMAP(used_m64_bar_mask, MAX_M64_BARS); + + /* + * If we map the SR-IOV BARs with a segmented window then + * parts of that window will be "claimed" by other PEs. + * + * "holes" here is used to reserve the leading portion + * of the window that is used by other (non VF) PEs. + */ + struct resource holes[PCI_SRIOV_NUM_BARS]; +}; + +static inline struct pnv_iov_data *pnv_iov_get(struct pci_dev *pdev) +{ + return pdev->dev.archdata.iov_data; +} + +void pnv_pci_ioda_fixup_iov(struct pci_dev *pdev); +resource_size_t pnv_pci_iov_resource_alignment(struct pci_dev *pdev, int resno); + +int pnv_pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs); +int pnv_pcibios_sriov_disable(struct pci_dev *pdev); +#endif /* CONFIG_PCI_IOV */ + extern struct pci_ops pnv_pci_ops; void pnv_pci_dump_phb_diag_data(struct pci_controller *hose, @@ -260,4 +351,14 @@ extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl, extern unsigned long pnv_ioda_parse_tce_sizes(struct pnv_phb *phb); +static inline struct pnv_phb *pci_bus_to_pnvhb(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + + if (hose) + return hose->private_data; + + return NULL; +} + #endif /* __POWERNV_PCI_H */ diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 3bc188da82ba..7fcb88623081 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -399,7 +399,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static unsigned long pnv_memory_block_size(void) { - return 256UL * 1024 * 1024; + /* + * We map the kernel linear region with 1GB large pages on radix. For + * memory hot unplug to work our memory block size must be at least + * this size. + */ + if (radix_enabled()) + return radix_mem_block_size; + else + return 256UL * 1024 * 1024; } #endif diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig index 24c18362e5ea..5e037df2a3a1 100644 --- a/arch/powerpc/platforms/pseries/Kconfig +++ b/arch/powerpc/platforms/pseries/Kconfig @@ -25,15 +25,22 @@ config PPC_PSERIES select SWIOTLB default y +config PARAVIRT_SPINLOCKS + bool + config PPC_SPLPAR - depends on PPC_PSERIES bool "Support for shared-processor logical partitions" + depends on PPC_PSERIES + select PARAVIRT_SPINLOCKS if PPC_QUEUED_SPINLOCKS + default y help Enabling this option will make the kernel run more efficiently on logically-partitioned pSeries systems which use shared processors, that is, which share physical processors between two or more partitions. + Say Y if you are unsure. + config DTL bool "Dispatch Trace Log" depends on PPC_SPLPAR && DEBUG_FS diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c index 9dba7e880885..45a3a3022a85 100644 --- a/arch/powerpc/platforms/pseries/cmm.c +++ b/arch/powerpc/platforms/pseries/cmm.c @@ -26,7 +26,6 @@ #include <asm/firmware.h> #include <asm/hvcall.h> #include <asm/mmu.h> -#include <asm/pgalloc.h> #include <linux/uaccess.h> #include <linux/memory.h> #include <asm/plpar_wrappers.h> diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ace117f99d94..cb2d9a970b7b 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -24,6 +24,7 @@ #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/spinlock.h> +#include <linux/crash_dump.h> #include <asm/eeh.h> #include <asm/eeh_event.h> @@ -32,6 +33,8 @@ #include <asm/ppc-pci.h> #include <asm/rtas.h> +static int pseries_eeh_get_pe_addr(struct pci_dn *pdn); + /* RTAS tokens */ static int ibm_set_eeh_option; static int ibm_set_slot_reset; @@ -52,8 +55,6 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) dev_dbg(&pdev->dev, "EEH: Setting up device\n"); #ifdef CONFIG_PCI_IOV if (pdev->is_virtfn) { - struct pci_dn *physfn_pdn; - pdn->device_id = pdev->device; pdn->vendor_id = pdev->vendor; pdn->class_code = pdev->class; @@ -63,23 +64,172 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) * completion from platform. */ pdn->last_allow_rc = 0; - physfn_pdn = pci_get_pdn(pdev->physfn); - pdn->pe_number = physfn_pdn->pe_num_map[pdn->vf_index]; } #endif pseries_eeh_init_edev(pdn); #ifdef CONFIG_PCI_IOV if (pdev->is_virtfn) { + /* + * FIXME: This really should be handled by choosing the right + * parent PE in in pseries_eeh_init_edev(). + */ + struct eeh_pe *physfn_pe = pci_dev_to_eeh_dev(pdev->physfn)->pe; struct eeh_dev *edev = pdn_to_eeh_dev(pdn); edev->pe_config_addr = (pdn->busno << 16) | (pdn->devfn << 8); - eeh_rmv_from_parent_pe(edev); /* Remove as it is adding to bus pe */ - eeh_add_to_parent_pe(edev); /* Add as VF PE type */ + eeh_pe_tree_remove(edev); /* Remove as it is adding to bus pe */ + eeh_pe_tree_insert(edev, physfn_pe); /* Add as VF PE type */ } #endif eeh_probe_device(pdev); } + +/** + * pseries_eeh_get_config_addr - Retrieve config address + * + * Retrieve the assocated config address. Actually, there're 2 RTAS + * function calls dedicated for the purpose. We need implement + * it through the new function and then the old one. Besides, + * you should make sure the config address is figured out from + * FDT node before calling the function. + * + * It's notable that zero'ed return value means invalid PE config + * address. + */ +static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr) +{ + int ret = 0; + int rets[3]; + + if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { + /* + * First of all, we need to make sure there has one PE + * associated with the device. Otherwise, PE address is + * meaningless. + */ + ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 1); + if (ret || (rets[0] == 0)) + return 0; + + /* Retrieve the associated PE config address */ + ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 0); + if (ret) { + pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", + __func__, phb->global_number, config_addr); + return 0; + } + + return rets[0]; + } + + if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { + ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), 0); + if (ret) { + pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", + __func__, phb->global_number, config_addr); + return 0; + } + + return rets[0]; + } + + return ret; +} + +/** + * pseries_eeh_phb_reset - Reset the specified PHB + * @phb: PCI controller + * @config_adddr: the associated config address + * @option: reset option + * + * Reset the specified PHB/PE + */ +static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, int option) +{ + int ret; + + /* Reset PE through RTAS call */ + ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), option); + + /* If fundamental-reset not supported, try hot-reset */ + if (option == EEH_RESET_FUNDAMENTAL && + ret == -8) { + option = EEH_RESET_HOT; + ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid), option); + } + + /* We need reset hold or settlement delay */ + if (option == EEH_RESET_FUNDAMENTAL || + option == EEH_RESET_HOT) + msleep(EEH_PE_RST_HOLD_TIME); + else + msleep(EEH_PE_RST_SETTLE_TIME); + + return ret; +} + +/** + * pseries_eeh_phb_configure_bridge - Configure PCI bridges in the indicated PE + * @phb: PCI controller + * @config_adddr: the associated config address + * + * The function will be called to reconfigure the bridges included + * in the specified PE so that the mulfunctional PE would be recovered + * again. + */ +static int pseries_eeh_phb_configure_bridge(struct pci_controller *phb, int config_addr) +{ + int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; + + while (max_wait > 0) { + ret = rtas_call(ibm_configure_pe, 3, 1, NULL, + config_addr, BUID_HI(phb->buid), + BUID_LO(phb->buid)); + + if (!ret) + return ret; + if (ret < 0) + break; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + + pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n", + __func__, phb->global_number, config_addr, ret); + /* PAPR defines -3 as "Parameter Error" for this function: */ + if (ret == -3) + return -EINVAL; + else + return -EIO; +} + /* * Buffer for reporting slot-error-detail rtas calls. Its here * in BSS, and not dynamically alloced, so that it ends up in @@ -96,6 +246,10 @@ static int eeh_error_buf_size; */ static int pseries_eeh_init(void) { + struct pci_controller *phb; + struct pci_dn *pdn; + int addr, config_addr; + /* figure out EEH RTAS function call tokens */ ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); @@ -148,6 +302,22 @@ static int pseries_eeh_init(void) /* Set EEH machine dependent code */ ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; + if (is_kdump_kernel() || reset_devices) { + pr_info("Issue PHB reset ...\n"); + list_for_each_entry(phb, &hose_list, list_node) { + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); + addr = (pdn->busno << 16) | (pdn->devfn << 8); + config_addr = pseries_eeh_get_config_addr(phb, addr); + /* invalid PE config addr */ + if (config_addr == 0) + continue; + + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); + pseries_eeh_phb_configure_bridge(phb, config_addr); + } + } + return 0; } @@ -221,6 +391,43 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap) } /** + * pseries_eeh_pe_get_parent - Retrieve the parent PE + * @edev: EEH device + * + * The whole PEs existing in the system are organized as hierarchy + * tree. The function is used to retrieve the parent PE according + * to the parent EEH device. + */ +static struct eeh_pe *pseries_eeh_pe_get_parent(struct eeh_dev *edev) +{ + struct eeh_dev *parent; + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + + /* + * It might have the case for the indirect parent + * EEH device already having associated PE, but + * the direct parent EEH device doesn't have yet. + */ + if (edev->physfn) + pdn = pci_get_pdn(edev->physfn); + else + pdn = pdn ? pdn->parent : NULL; + while (pdn) { + /* We're poking out of PCI territory */ + parent = pdn_to_eeh_dev(pdn); + if (!parent) + return NULL; + + if (parent->pe) + return parent->pe; + + pdn = pdn->parent; + } + + return NULL; +} + +/** * pseries_eeh_init_edev - initialise the eeh_dev and eeh_pe for a pci_dn * * @pdn: PCI device node @@ -275,12 +482,11 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) * correctly reflects that current device is root port * or PCIe switch downstream port. */ - edev->class_code = pdn->class_code; edev->pcix_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_PCIX); edev->pcie_cap = pseries_eeh_find_cap(pdn, PCI_CAP_ID_EXP); edev->aer_cap = pseries_eeh_find_ecap(pdn, PCI_EXT_CAP_ID_ERR); edev->mode &= 0xFFFFFF00; - if ((edev->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { + if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_PCI) { edev->mode |= EEH_DEV_BRIDGE; if (edev->pcie_cap) { rtas_read_config(pdn, edev->pcie_cap + PCI_EXP_FLAGS, @@ -304,8 +510,10 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) if (ret) { eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret); } else { + struct eeh_pe *parent; + /* Retrieve PE address */ - edev->pe_config_addr = eeh_ops->get_pe_addr(&pe); + edev->pe_config_addr = pseries_eeh_get_pe_addr(pdn); pe.addr = edev->pe_config_addr; /* Some older systems (Power4) allow the ibm,set-eeh-option @@ -316,16 +524,19 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) enable = 1; - if (enable) { + /* + * This device doesn't support EEH, but it may have an + * EEH parent. In this case any error on the device will + * freeze the PE of it's upstream bridge, so added it to + * the upstream PE. + */ + parent = pseries_eeh_pe_get_parent(edev); + if (parent && !enable) + edev->pe_config_addr = parent->addr; + + if (enable || parent) { eeh_add_flag(EEH_ENABLED); - eeh_add_to_parent_pe(edev); - } else if (pdn->parent && pdn_to_eeh_dev(pdn->parent) && - (pdn_to_eeh_dev(pdn->parent))->pe) { - /* This device doesn't support EEH, but it may have an - * EEH parent, in which case we mark it as supported. - */ - edev->pe_config_addr = pdn_to_eeh_dev(pdn->parent)->pe_config_addr; - eeh_add_to_parent_pe(edev); + eeh_pe_tree_insert(edev, parent); } eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n", (enable ? "enabled" : "unsupported"), ret); @@ -435,8 +646,10 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) * It's notable that zero'ed return value means invalid PE config * address. */ -static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) +static int pseries_eeh_get_pe_addr(struct pci_dn *pdn) { + int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); + unsigned long buid = pdn->phb->buid; int ret = 0; int rets[3]; @@ -447,18 +660,16 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) * meaningless. */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 1); + config_addr, BUID_HI(buid), BUID_LO(buid), 1); if (ret || (rets[0] == 0)) return 0; /* Retrieve the associated PE config address */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 0); + config_addr, BUID_HI(buid), BUID_LO(buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pe->phb->global_number, pe->config_addr); + __func__, pdn->phb->global_number, config_addr); return 0; } @@ -467,11 +678,10 @@ static int pseries_eeh_get_pe_addr(struct eeh_pe *pe) if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, - pe->config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), 0); + config_addr, BUID_HI(buid), BUID_LO(buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pe->phb->global_number, pe->config_addr); + __func__, pdn->phb->global_number, config_addr); return 0; } @@ -569,35 +779,13 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) static int pseries_eeh_reset(struct eeh_pe *pe, int option) { int config_addr; - int ret; /* Figure out PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Reset PE through RTAS call */ - ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), option); - - /* If fundamental-reset not supported, try hot-reset */ - if (option == EEH_RESET_FUNDAMENTAL && - ret == -8) { - option = EEH_RESET_HOT; - ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid), option); - } - - /* We need reset hold or settlement delay */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) - msleep(EEH_PE_RST_HOLD_TIME); - else - msleep(EEH_PE_RST_SETTLE_TIME); - - return ret; + return pseries_eeh_phb_reset(pe->phb, config_addr, option); } /** @@ -641,108 +829,49 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u * pseries_eeh_configure_bridge - Configure PCI bridges in the indicated PE * @pe: EEH PE * - * The function will be called to reconfigure the bridges included - * in the specified PE so that the mulfunctional PE would be recovered - * again. */ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; - int ret; - /* Waiting 0.2s maximum before skipping configuration */ - int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - while (max_wait > 0) { - ret = rtas_call(ibm_configure_pe, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - - if (!ret) - return ret; - if (ret < 0) - break; - - /* - * If RTAS returns a delay value that's above 100ms, cut it - * down to 100ms in case firmware made a mistake. For more - * on how these delay values work see rtas_busy_delay_time - */ - if (ret > RTAS_EXTENDED_DELAY_MIN+2 && - ret <= RTAS_EXTENDED_DELAY_MAX) - ret = RTAS_EXTENDED_DELAY_MIN+2; - - max_wait -= rtas_busy_delay_time(ret); - - if (max_wait < 0) - break; - - rtas_busy_delay(ret); - } - - pr_warn("%s: Unable to configure bridge PHB#%x-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); - /* PAPR defines -3 as "Parameter Error" for this function: */ - if (ret == -3) - return -EINVAL; - else - return -EIO; + return pseries_eeh_phb_configure_bridge(pe->phb, config_addr); } /** * pseries_eeh_read_config - Read PCI config space - * @pdn: PCI device node - * @where: PCI address + * @edev: EEH device handle + * @where: PCI config space offset * @size: size to read * @val: return value * * Read config space from the speicifed device */ -static int pseries_eeh_read_config(struct pci_dn *pdn, int where, int size, u32 *val) +static int pseries_eeh_read_config(struct eeh_dev *edev, int where, int size, u32 *val) { + struct pci_dn *pdn = eeh_dev_to_pdn(edev); + return rtas_read_config(pdn, where, size, val); } /** * pseries_eeh_write_config - Write PCI config space - * @pdn: PCI device node - * @where: PCI address + * @edev: EEH device handle + * @where: PCI config space offset * @size: size to write * @val: value to be written * * Write config space to the specified device */ -static int pseries_eeh_write_config(struct pci_dn *pdn, int where, int size, u32 val) +static int pseries_eeh_write_config(struct eeh_dev *edev, int where, int size, u32 val) { - return rtas_write_config(pdn, where, size, val); -} + struct pci_dn *pdn = eeh_dev_to_pdn(edev); -static int pseries_eeh_restore_config(struct pci_dn *pdn) -{ - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - s64 ret = 0; - - if (!edev) - return -EEXIST; - - /* - * FIXME: The MPS, error routing rules, timeout setting are worthy - * to be exported by firmware in extendible way. - */ - if (edev->physfn) - ret = eeh_restore_vf_config(pdn); - - if (ret) { - pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n", - __func__, edev->pe_config_addr, ret); - return -EIO; - } - - return ret; + return rtas_write_config(pdn, where, size, val); } #ifdef CONFIG_PCI_IOV @@ -772,8 +901,8 @@ int pseries_send_allow_unfreeze(struct pci_dn *pdn, static int pseries_call_allow_unfreeze(struct eeh_dev *edev) { + int cur_vfs = 0, rc = 0, vf_index, bus, devfn, vf_pe_num; struct pci_dn *pdn, *tmp, *parent, *physfn_pdn; - int cur_vfs = 0, rc = 0, vf_index, bus, devfn; u16 *vf_pe_array; vf_pe_array = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL); @@ -806,8 +935,10 @@ static int pseries_call_allow_unfreeze(struct eeh_dev *edev) } } else { pdn = pci_get_pdn(edev->pdev); - vf_pe_array[0] = cpu_to_be16(pdn->pe_number); physfn_pdn = pci_get_pdn(edev->physfn); + + vf_pe_num = physfn_pdn->pe_num_map[edev->vf_index]; + vf_pe_array[0] = cpu_to_be16(vf_pe_num); rc = pseries_send_allow_unfreeze(physfn_pdn, vf_pe_array, 1); pdn->last_allow_rc = rc; @@ -818,10 +949,8 @@ static int pseries_call_allow_unfreeze(struct eeh_dev *edev) return rc; } -static int pseries_notify_resume(struct pci_dn *pdn) +static int pseries_notify_resume(struct eeh_dev *edev) { - struct eeh_dev *edev = pdn_to_eeh_dev(pdn); - if (!edev) return -EEXIST; @@ -841,7 +970,6 @@ static struct eeh_ops pseries_eeh_ops = { .init = pseries_eeh_init, .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, - .get_pe_addr = pseries_eeh_get_pe_addr, .get_state = pseries_eeh_get_state, .reset = pseries_eeh_reset, .get_log = pseries_eeh_get_log, @@ -850,7 +978,7 @@ static struct eeh_ops pseries_eeh_ops = { .read_config = pseries_eeh_read_config, .write_config = pseries_eeh_write_config, .next_error = NULL, - .restore_config = pseries_eeh_restore_config, + .restore_config = NULL, /* NB: configure_bridge() does this */ #ifdef CONFIG_PCI_IOV .notify_resume = pseries_notify_resume #endif diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index 3e49cc23a97a..4c7b7f5a2ebc 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -65,6 +65,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_HPT_RESIZE, "hcall-hpt-resize"}, {FW_FEATURE_BLOCK_REMOVE, "hcall-block-remove"}, {FW_FEATURE_PAPR_SCM, "hcall-scm"}, + {FW_FEATURE_RPT_INVALIDATE, "hcall-rpt-invalidate"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 3e8cbfe7a80f..c6e0d8abf75e 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -35,54 +35,10 @@ #include <asm/topology.h> #include "pseries.h" -#include "offline_states.h" /* This version can't take the spinlock, because it never returns */ static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE; -static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) = - CPU_STATE_OFFLINE; -static DEFINE_PER_CPU(enum cpu_state_vals, current_state) = CPU_STATE_OFFLINE; - -static enum cpu_state_vals default_offline_state = CPU_STATE_OFFLINE; - -static bool cede_offline_enabled __read_mostly = true; - -/* - * Enable/disable cede_offline when available. - */ -static int __init setup_cede_offline(char *str) -{ - return (kstrtobool(str, &cede_offline_enabled) == 0); -} - -__setup("cede_offline=", setup_cede_offline); - -enum cpu_state_vals get_cpu_current_state(int cpu) -{ - return per_cpu(current_state, cpu); -} - -void set_cpu_current_state(int cpu, enum cpu_state_vals state) -{ - per_cpu(current_state, cpu) = state; -} - -enum cpu_state_vals get_preferred_offline_state(int cpu) -{ - return per_cpu(preferred_offline_state, cpu); -} - -void set_preferred_offline_state(int cpu, enum cpu_state_vals state) -{ - per_cpu(preferred_offline_state, cpu) = state; -} - -void set_default_offline_state(int cpu) -{ - per_cpu(preferred_offline_state, cpu) = default_offline_state; -} - static void rtas_stop_self(void) { static struct rtas_args args; @@ -101,9 +57,7 @@ static void rtas_stop_self(void) static void pseries_mach_cpu_die(void) { - unsigned int cpu = smp_processor_id(); unsigned int hwcpu = hard_smp_processor_id(); - u8 cede_latency_hint = 0; local_irq_disable(); idle_task_exit(); @@ -112,49 +66,6 @@ static void pseries_mach_cpu_die(void) else xics_teardown_cpu(); - if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - set_cpu_current_state(cpu, CPU_STATE_INACTIVE); - if (ppc_md.suspend_disable_cpu) - ppc_md.suspend_disable_cpu(); - - cede_latency_hint = 2; - - get_lppaca()->idle = 1; - if (!lppaca_shared_proc(get_lppaca())) - get_lppaca()->donate_dedicated_cpu = 1; - - while (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - while (!prep_irq_for_idle()) { - local_irq_enable(); - local_irq_disable(); - } - - extended_cede_processor(cede_latency_hint); - } - - local_irq_disable(); - - if (!lppaca_shared_proc(get_lppaca())) - get_lppaca()->donate_dedicated_cpu = 0; - get_lppaca()->idle = 0; - - if (get_preferred_offline_state(cpu) == CPU_STATE_ONLINE) { - unregister_slb_shadow(hwcpu); - - hard_irq_disable(); - /* - * Call to start_secondary_resume() will not return. - * Kernel stack will be reset and start_secondary() - * will be called to continue the online operation. - */ - start_secondary_resume(); - } - } - - /* Requested state is CPU_STATE_OFFLINE at this point */ - WARN_ON(get_preferred_offline_state(cpu) != CPU_STATE_OFFLINE); - - set_cpu_current_state(cpu, CPU_STATE_OFFLINE); unregister_slb_shadow(hwcpu); rtas_stop_self(); @@ -200,24 +111,13 @@ static void pseries_cpu_die(unsigned int cpu) int cpu_status = 1; unsigned int pcpu = get_hard_smp_processor_id(cpu); - if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { - cpu_status = 1; - for (tries = 0; tries < 5000; tries++) { - if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) { - cpu_status = 0; - break; - } - msleep(1); - } - } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { + for (tries = 0; tries < 25; tries++) { + cpu_status = smp_query_cpu_stopped(pcpu); + if (cpu_status == QCSS_STOPPED || + cpu_status == QCSS_HARDWARE_ERROR) + break; + cpu_relax(); - for (tries = 0; tries < 25; tries++) { - cpu_status = smp_query_cpu_stopped(pcpu); - if (cpu_status == QCSS_STOPPED || - cpu_status == QCSS_HARDWARE_ERROR) - break; - cpu_relax(); - } } if (cpu_status != 0) { @@ -359,28 +259,14 @@ static int dlpar_offline_cpu(struct device_node *dn) if (get_hard_smp_processor_id(cpu) != thread) continue; - if (get_cpu_current_state(cpu) == CPU_STATE_OFFLINE) + if (!cpu_online(cpu)) break; - if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { - set_preferred_offline_state(cpu, - CPU_STATE_OFFLINE); - cpu_maps_update_done(); - timed_topology_update(1); - rc = device_offline(get_cpu_device(cpu)); - if (rc) - goto out; - cpu_maps_update_begin(); - break; - } - - /* - * The cpu is in CPU_STATE_INACTIVE. - * Upgrade it's state to CPU_STATE_OFFLINE. - */ - set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); - WARN_ON(plpar_hcall_norets(H_PROD, thread) != H_SUCCESS); - __cpu_die(cpu); + cpu_maps_update_done(); + rc = device_offline(get_cpu_device(cpu)); + if (rc) + goto out; + cpu_maps_update_begin(); break; } if (cpu == num_possible_cpus()) { @@ -414,10 +300,7 @@ static int dlpar_online_cpu(struct device_node *dn) for_each_present_cpu(cpu) { if (get_hard_smp_processor_id(cpu) != thread) continue; - BUG_ON(get_cpu_current_state(cpu) - != CPU_STATE_OFFLINE); cpu_maps_update_done(); - timed_topology_update(1); find_and_online_cpu_nid(cpu); rc = device_online(get_cpu_device(cpu)); if (rc) { @@ -854,7 +737,6 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) parent = of_find_node_by_path("/cpus"); if (!parent) { pr_warn("Could not find CPU root node in device tree\n"); - kfree(cpu_drcs); return -1; } @@ -896,25 +778,6 @@ static int dlpar_cpu_add_by_count(u32 cpus_to_add) return rc; } -int dlpar_cpu_readd(int cpu) -{ - struct device_node *dn; - struct device *dev; - u32 drc_index; - int rc; - - dev = get_cpu_device(cpu); - dn = dev->of_node; - - rc = of_property_read_u32(dn, "ibm,my-drc-index", &drc_index); - - rc = dlpar_cpu_remove_by_index(drc_index); - if (!rc) - rc = dlpar_cpu_add(drc_index); - - return rc; -} - int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) { u32 count, drc_index; @@ -1013,27 +876,8 @@ static struct notifier_block pseries_smp_nb = { .notifier_call = pseries_smp_notifier, }; -#define MAX_CEDE_LATENCY_LEVELS 4 -#define CEDE_LATENCY_PARAM_LENGTH 10 -#define CEDE_LATENCY_PARAM_MAX_LENGTH \ - (MAX_CEDE_LATENCY_LEVELS * CEDE_LATENCY_PARAM_LENGTH * sizeof(char)) -#define CEDE_LATENCY_TOKEN 45 - -static char cede_parameters[CEDE_LATENCY_PARAM_MAX_LENGTH]; - -static int parse_cede_parameters(void) -{ - memset(cede_parameters, 0, CEDE_LATENCY_PARAM_MAX_LENGTH); - return rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1, - NULL, - CEDE_LATENCY_TOKEN, - __pa(cede_parameters), - CEDE_LATENCY_PARAM_MAX_LENGTH); -} - static int __init pseries_cpu_hotplug_init(void) { - int cpu; int qcss_tok; #ifdef CONFIG_ARCH_CPU_PROBE_RELEASE @@ -1056,16 +900,8 @@ static int __init pseries_cpu_hotplug_init(void) smp_ops->cpu_die = pseries_cpu_die; /* Processors can be added/removed only on LPAR */ - if (firmware_has_feature(FW_FEATURE_LPAR)) { + if (firmware_has_feature(FW_FEATURE_LPAR)) of_reconfig_notifier_register(&pseries_smp_nb); - cpu_maps_update_begin(); - if (cede_offline_enabled && parse_cede_parameters() == 0) { - default_offline_state = CPU_STATE_INACTIVE; - for_each_online_cpu(cpu) - set_default_offline_state(cpu); - } - cpu_maps_update_done(); - } return 0; } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 5ace2f9a277e..5d545b78111f 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -22,12 +22,10 @@ #include <asm/drmem.h> #include "pseries.h" -static bool rtas_hp_event; - unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -487,40 +485,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index) return rc; } -static int dlpar_memory_readd_by_index(u32 drc_index) -{ - struct drmem_lmb *lmb; - int lmb_found; - int rc; - - pr_info("Attempting to update LMB, drc index %x\n", drc_index); - - lmb_found = 0; - for_each_drmem_lmb(lmb) { - if (lmb->drc_index == drc_index) { - lmb_found = 1; - rc = dlpar_remove_lmb(lmb); - if (!rc) { - rc = dlpar_add_lmb(lmb); - if (rc) - dlpar_release_drc(lmb->drc_index); - } - break; - } - } - - if (!lmb_found) - rc = -EINVAL; - - if (rc) - pr_info("Failed to update memory at %llx\n", - lmb->base_addr); - else - pr_info("Memory at %llx was updated\n", lmb->base_addr); - - return rc; -} - static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) { struct drmem_lmb *lmb, *start_lmb, *end_lmb; @@ -617,10 +581,6 @@ static int dlpar_memory_remove_by_index(u32 drc_index) { return -EOPNOTSUPP; } -static int dlpar_memory_readd_by_index(u32 drc_index) -{ - return -EOPNOTSUPP; -} static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) { @@ -903,21 +863,14 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) } break; - case PSERIES_HP_ELOG_ACTION_READD: - drc_index = hp_elog->_drc_u.drc_index; - rc = dlpar_memory_readd_by_index(drc_index); - break; default: pr_err("Invalid action (%d) specified\n", hp_elog->action); rc = -EINVAL; break; } - if (!rc) { - rtas_hp_event = true; + if (!rc) rc = drmem_update_dt(); - rtas_hp_event = false; - } unlock_device_hotplug(); return rc; @@ -953,60 +906,6 @@ static int pseries_add_mem_node(struct device_node *np) return (ret < 0) ? -EINVAL : 0; } -static int pseries_update_drconf_memory(struct of_reconfig_data *pr) -{ - struct of_drconf_cell_v1 *new_drmem, *old_drmem; - unsigned long memblock_size; - u32 entries; - __be32 *p; - int i, rc = -EINVAL; - - if (rtas_hp_event) - return 0; - - memblock_size = pseries_memory_block_size(); - if (!memblock_size) - return -EINVAL; - - if (!pr->old_prop) - return 0; - - p = (__be32 *) pr->old_prop->value; - if (!p) - return -EINVAL; - - /* The first int of the property is the number of lmb's described - * by the property. This is followed by an array of of_drconf_cell - * entries. Get the number of entries and skip to the array of - * of_drconf_cell's. - */ - entries = be32_to_cpu(*p++); - old_drmem = (struct of_drconf_cell_v1 *)p; - - p = (__be32 *)pr->prop->value; - p++; - new_drmem = (struct of_drconf_cell_v1 *)p; - - for (i = 0; i < entries; i++) { - if ((be32_to_cpu(old_drmem[i].flags) & DRCONF_MEM_ASSIGNED) && - (!(be32_to_cpu(new_drmem[i].flags) & DRCONF_MEM_ASSIGNED))) { - rc = pseries_remove_memblock( - be64_to_cpu(old_drmem[i].base_addr), - memblock_size); - break; - } else if ((!(be32_to_cpu(old_drmem[i].flags) & - DRCONF_MEM_ASSIGNED)) && - (be32_to_cpu(new_drmem[i].flags) & - DRCONF_MEM_ASSIGNED)) { - rc = memblock_add(be64_to_cpu(old_drmem[i].base_addr), - memblock_size); - rc = (rc < 0) ? -EINVAL : 0; - break; - } - } - return rc; -} - static int pseries_memory_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -1020,10 +919,6 @@ static int pseries_memory_notifier(struct notifier_block *nb, case OF_RECONFIG_DETACH_NODE: err = pseries_remove_mem_node(rd->dn); break; - case OF_RECONFIG_UPDATE_PROPERTY: - if (!strcmp(rd->prop->name, "ibm,dynamic-memory")) - err = pseries_update_drconf_memory(rd); - break; } return notifier_from_errno(err); } diff --git a/arch/powerpc/platforms/pseries/hvcserver.c b/arch/powerpc/platforms/pseries/hvcserver.c index 267139b13530..96e18d3b2fcf 100644 --- a/arch/powerpc/platforms/pseries/hvcserver.c +++ b/arch/powerpc/platforms/pseries/hvcserver.c @@ -45,7 +45,7 @@ static int hvcs_convert(long to_convert) case H_LONG_BUSY_ORDER_10_SEC: case H_LONG_BUSY_ORDER_100_SEC: return -EBUSY; - case H_FUNCTION: /* fall through */ + case H_FUNCTION: default: return -EPERM; } diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f71ff2c94efe..baf24eacd268 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1681,9 +1681,11 @@ static int pseries_lpar_register_process_table(unsigned long base, if (table_size) flags |= PROC_TABLE_NEW; - if (radix_enabled()) - flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE; - else + if (radix_enabled()) { + flags |= PROC_TABLE_RADIX; + if (mmu_has_feature(MMU_FTR_GTSE)) + flags |= PROC_TABLE_GTSE; + } else flags |= PROC_TABLE_HPT_SLB; for (;;) { rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base, diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 10d982997736..d6f4162478a5 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -6,6 +6,9 @@ * Copyright (C) 2010 IBM Corporation */ + +#define pr_fmt(fmt) "mobility: " fmt + #include <linux/cpu.h> #include <linux/kernel.h> #include <linux/kobject.h> @@ -64,6 +67,8 @@ static int delete_dt_node(__be32 phandle) if (!dn) return -ENOENT; + pr_debug("removing node %pOFfp\n", dn); + dlpar_detach_node(dn); of_node_put(dn); return 0; @@ -122,6 +127,7 @@ static int update_dt_property(struct device_node *dn, struct property **prop, } if (!more) { + pr_debug("updating node %pOF property %s\n", dn, name); of_update_property(dn, new_prop); *prop = NULL; } @@ -240,33 +246,12 @@ static int add_dt_node(__be32 parent_phandle, __be32 drc_index) if (rc) dlpar_free_cc_nodes(dn); + pr_debug("added node %pOFfp\n", dn); + of_node_put(parent_dn); return rc; } -static void prrn_update_node(__be32 phandle) -{ - struct pseries_hp_errorlog hp_elog; - struct device_node *dn; - - /* - * If a node is found from a the given phandle, the phandle does not - * represent the drc index of an LMB and we can ignore. - */ - dn = of_find_node_by_phandle(be32_to_cpu(phandle)); - if (dn) { - of_node_put(dn); - return; - } - - hp_elog.resource = PSERIES_HP_ELOG_RESOURCE_MEM; - hp_elog.action = PSERIES_HP_ELOG_ACTION_READD; - hp_elog.id_type = PSERIES_HP_ELOG_ID_DRC_INDEX; - hp_elog._drc_u.drc_index = phandle; - - handle_dlpar_errorlog(&hp_elog); -} - int pseries_devicetree_update(s32 scope) { char *rtas_buf; @@ -305,10 +290,6 @@ int pseries_devicetree_update(s32 scope) break; case UPDATE_DT_NODE: update_dt_node(phandle, scope); - - if (scope == PRRN_SCOPE) - prrn_update_node(phandle); - break; case ADD_DT_NODE: drc_index = *data++; @@ -388,8 +369,6 @@ static ssize_t migration_store(struct class *class, if (rc) return rc; - stop_topology_update(); - do { rc = rtas_ibm_suspend_me(streamid); if (rc == -EAGAIN) @@ -401,8 +380,6 @@ static ssize_t migration_store(struct class *class, post_mobility_fixup(); - start_topology_update(); - return count; } @@ -427,11 +404,11 @@ static int __init mobility_sysfs_init(void) rc = sysfs_create_file(mobility_kobj, &class_attr_migration.attr); if (rc) - pr_err("mobility: unable to create migration sysfs file (%d)\n", rc); + pr_err("unable to create migration sysfs file (%d)\n", rc); rc = sysfs_create_file(mobility_kobj, &class_attr_api_version.attr.attr); if (rc) - pr_err("mobility: unable to create api_version sysfs file (%d)\n", rc); + pr_err("unable to create api_version sysfs file (%d)\n", rc); return 0; } diff --git a/arch/powerpc/platforms/pseries/offline_states.h b/arch/powerpc/platforms/pseries/offline_states.h deleted file mode 100644 index 51414aee2862..000000000000 --- a/arch/powerpc/platforms/pseries/offline_states.h +++ /dev/null @@ -1,38 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _OFFLINE_STATES_H_ -#define _OFFLINE_STATES_H_ - -/* Cpu offline states go here */ -enum cpu_state_vals { - CPU_STATE_OFFLINE, - CPU_STATE_INACTIVE, - CPU_STATE_ONLINE, - CPU_MAX_OFFLINE_STATES -}; - -#ifdef CONFIG_HOTPLUG_CPU -extern enum cpu_state_vals get_cpu_current_state(int cpu); -extern void set_cpu_current_state(int cpu, enum cpu_state_vals state); -extern void set_preferred_offline_state(int cpu, enum cpu_state_vals state); -extern void set_default_offline_state(int cpu); -#else -static inline enum cpu_state_vals get_cpu_current_state(int cpu) -{ - return CPU_STATE_ONLINE; -} - -static inline void set_cpu_current_state(int cpu, enum cpu_state_vals state) -{ -} - -static inline void set_preferred_offline_state(int cpu, enum cpu_state_vals state) -{ -} - -static inline void set_default_offline_state(int cpu) -{ -} -#endif - -extern enum cpu_state_vals get_preferred_offline_state(int cpu); -#endif diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 9c569078a09f..f439f0dfea7d 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -13,9 +13,11 @@ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/seq_buf.h> +#include <linux/nd.h> #include <asm/plpar_wrappers.h> #include <asm/papr_pdsm.h> +#include <asm/mce.h> #define BIND_ANY_ADDR (~0ul) @@ -62,6 +64,26 @@ PAPR_PMEM_HEALTH_FATAL | \ PAPR_PMEM_HEALTH_UNHEALTHY) +#define PAPR_SCM_PERF_STATS_EYECATCHER __stringify(SCMSTATS) +#define PAPR_SCM_PERF_STATS_VERSION 0x1 + +/* Struct holding a single performance metric */ +struct papr_scm_perf_stat { + u8 stat_id[8]; + __be64 stat_val; +} __packed; + +/* Struct exchanged between kernel and PHYP for fetching drc perf stats */ +struct papr_scm_perf_stats { + u8 eye_catcher[8]; + /* Should be PAPR_SCM_PERF_STATS_VERSION */ + __be32 stats_version; + /* Number of stats following */ + __be32 num_statistics; + /* zero or more performance matrics */ + struct papr_scm_perf_stat scm_statistic[]; +} __packed; + /* private struct associated with each region */ struct papr_scm_priv { struct platform_device *pdev; @@ -80,6 +102,7 @@ struct papr_scm_priv { struct resource res; struct nd_region *region; struct nd_interleave_set nd_set; + struct list_head region_list; /* Protect dimm health data from concurrent read/writes */ struct mutex health_mutex; @@ -89,8 +112,14 @@ struct papr_scm_priv { /* Health information for the dimm */ u64 health_bitmap; + + /* length of the stat buffer as expected by phyp */ + size_t stat_buffer_len; }; +static LIST_HEAD(papr_nd_regions); +static DEFINE_MUTEX(papr_ndr_lock); + static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; @@ -195,6 +224,79 @@ err_out: } /* + * Query the Dimm performance stats from PHYP and copy them (if returned) to + * provided struct papr_scm_perf_stats instance 'stats' that can hold atleast + * (num_stats + header) bytes. + * - If buff_stats == NULL the return value is the size in byes of the buffer + * needed to hold all supported performance-statistics. + * - If buff_stats != NULL and num_stats == 0 then we copy all known + * performance-statistics to 'buff_stat' and expect to be large enough to + * hold them. + * - if buff_stats != NULL and num_stats > 0 then copy the requested + * performance-statistics to buff_stats. + */ +static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, + struct papr_scm_perf_stats *buff_stats, + unsigned int num_stats) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + size_t size; + s64 rc; + + /* Setup the out buffer */ + if (buff_stats) { + memcpy(buff_stats->eye_catcher, + PAPR_SCM_PERF_STATS_EYECATCHER, 8); + buff_stats->stats_version = + cpu_to_be32(PAPR_SCM_PERF_STATS_VERSION); + buff_stats->num_statistics = + cpu_to_be32(num_stats); + + /* + * Calculate the buffer size based on num-stats provided + * or use the prefetched max buffer length + */ + if (num_stats) + /* Calculate size from the num_stats */ + size = sizeof(struct papr_scm_perf_stats) + + num_stats * sizeof(struct papr_scm_perf_stat); + else + size = p->stat_buffer_len; + } else { + /* In case of no out buffer ignore the size */ + size = 0; + } + + /* Do the HCALL asking PHYP for info */ + rc = plpar_hcall(H_SCM_PERFORMANCE_STATS, ret, p->drc_index, + buff_stats ? virt_to_phys(buff_stats) : 0, + size); + + /* Check if the error was due to an unknown stat-id */ + if (rc == H_PARTIAL) { + dev_err(&p->pdev->dev, + "Unknown performance stats, Err:0x%016lX\n", ret[0]); + return -ENOENT; + } else if (rc != H_SUCCESS) { + dev_err(&p->pdev->dev, + "Failed to query performance stats, Err:%lld\n", rc); + return -EIO; + + } else if (!size) { + /* Handle case where stat buffer size was requested */ + dev_dbg(&p->pdev->dev, + "Performance stats size %ld\n", ret[0]); + return ret[0]; + } + + /* Successfully fetched the requested stats from phyp */ + dev_dbg(&p->pdev->dev, + "Performance stats returned %d stats\n", + be32_to_cpu(buff_stats->num_statistics)); + return 0; +} + +/* * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the * health information. */ @@ -416,6 +518,51 @@ static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf, return 0; } +static int papr_pdsm_fuel_gauge(struct papr_scm_priv *p, + union nd_pdsm_payload *payload) +{ + int rc, size; + u64 statval; + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + + /* Silently fail if fetching performance metrics isn't supported */ + if (!p->stat_buffer_len) + return 0; + + /* Allocate request buffer enough to hold single performance stat */ + size = sizeof(struct papr_scm_perf_stats) + + sizeof(struct papr_scm_perf_stat); + + stats = kzalloc(size, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + stat = &stats->scm_statistic[0]; + memcpy(&stat->stat_id, "MemLife ", sizeof(stat->stat_id)); + stat->stat_val = 0; + + /* Fetch the fuel gauge and populate it in payload */ + rc = drc_pmem_query_stats(p, stats, 1); + if (rc < 0) { + dev_dbg(&p->pdev->dev, "Err(%d) fetching fuel gauge\n", rc); + goto free_stats; + } + + statval = be64_to_cpu(stat->stat_val); + dev_dbg(&p->pdev->dev, + "Fetched fuel-gauge %llu", statval); + payload->health.extension_flags |= + PDSM_DIMM_HEALTH_RUN_GAUGE_VALID; + payload->health.dimm_fuel_gauge = statval; + + rc = sizeof(struct nd_papr_pdsm_health); + +free_stats: + kfree(stats); + return rc; +} + /* Fetch the DIMM health info and populate it in provided package. */ static int papr_pdsm_health(struct papr_scm_priv *p, union nd_pdsm_payload *payload) @@ -456,6 +603,10 @@ static int papr_pdsm_health(struct papr_scm_priv *p, /* struct populated hence can release the mutex now */ mutex_unlock(&p->health_mutex); + + /* Populate the fuel gauge meter in the payload */ + papr_pdsm_fuel_gauge(p, payload); + rc = sizeof(struct nd_papr_pdsm_health); out: @@ -631,6 +782,48 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } +static ssize_t perf_stats_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + int index, rc; + struct seq_buf s; + struct papr_scm_perf_stat *stat; + struct papr_scm_perf_stats *stats; + struct nvdimm *dimm = to_nvdimm(dev); + struct papr_scm_priv *p = nvdimm_provider_data(dimm); + + if (!p->stat_buffer_len) + return -ENOENT; + + /* Allocate the buffer for phyp where stats are written */ + stats = kzalloc(p->stat_buffer_len, GFP_KERNEL); + if (!stats) + return -ENOMEM; + + /* Ask phyp to return all dimm perf stats */ + rc = drc_pmem_query_stats(p, stats, 0); + if (rc) + goto free_stats; + /* + * Go through the returned output buffer and print stats and + * values. Since stat_id is essentially a char string of + * 8 bytes, simply use the string format specifier to print it. + */ + seq_buf_init(&s, buf, PAGE_SIZE); + for (index = 0, stat = stats->scm_statistic; + index < be32_to_cpu(stats->num_statistics); + ++index, ++stat) { + seq_buf_printf(&s, "%.8s = 0x%016llX\n", + stat->stat_id, + be64_to_cpu(stat->stat_val)); + } + +free_stats: + kfree(stats); + return rc ? rc : seq_buf_used(&s); +} +DEVICE_ATTR_RO(perf_stats); + static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -676,6 +869,7 @@ DEVICE_ATTR_RO(flags); /* papr_scm specific dimm attributes */ static struct attribute *papr_nd_attributes[] = { &dev_attr_flags.attr, + &dev_attr_perf_stats.attr, NULL, }; @@ -696,6 +890,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) struct nd_region_desc ndr_desc; unsigned long dimm_flags; int target_nid, online_nid; + ssize_t stat_size; p->bus_desc.ndctl = papr_scm_ndctl; p->bus_desc.module = THIS_MODULE; @@ -759,6 +954,20 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dev_info(dev, "Region registered with target node %d and online node %d", target_nid, online_nid); + mutex_lock(&papr_ndr_lock); + list_add_tail(&p->region_list, &papr_nd_regions); + mutex_unlock(&papr_ndr_lock); + + /* Try retriving the stat buffer and see if its supported */ + stat_size = drc_pmem_query_stats(p, NULL, 0); + if (stat_size > 0) { + p->stat_buffer_len = stat_size; + dev_dbg(&p->pdev->dev, "Max perf-stat size %lu-bytes\n", + p->stat_buffer_len); + } else { + dev_info(&p->pdev->dev, "Dimm performance stats unavailable\n"); + } + return 0; err: nvdimm_bus_unregister(p->bus); @@ -766,6 +975,68 @@ err: nvdimm_bus_unregister(p->bus); return -ENXIO; } +static void papr_scm_add_badblock(struct nd_region *region, + struct nvdimm_bus *bus, u64 phys_addr) +{ + u64 aligned_addr = ALIGN_DOWN(phys_addr, L1_CACHE_BYTES); + + if (nvdimm_bus_add_badrange(bus, aligned_addr, L1_CACHE_BYTES)) { + pr_err("Bad block registration for 0x%llx failed\n", phys_addr); + return; + } + + pr_debug("Add memory range (0x%llx - 0x%llx) as bad range\n", + aligned_addr, aligned_addr + L1_CACHE_BYTES); + + nvdimm_region_notify(region, NVDIMM_REVALIDATE_POISON); +} + +static int handle_mce_ue(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct machine_check_event *evt = data; + struct papr_scm_priv *p; + u64 phys_addr; + bool found = false; + + if (evt->error_type != MCE_ERROR_TYPE_UE) + return NOTIFY_DONE; + + if (list_empty(&papr_nd_regions)) + return NOTIFY_DONE; + + /* + * The physical address obtained here is PAGE_SIZE aligned, so get the + * exact address from the effective address + */ + phys_addr = evt->u.ue_error.physical_address + + (evt->u.ue_error.effective_address & ~PAGE_MASK); + + if (!evt->u.ue_error.physical_address_provided || + !is_zone_device_page(pfn_to_page(phys_addr >> PAGE_SHIFT))) + return NOTIFY_DONE; + + /* mce notifier is called from a process context, so mutex is safe */ + mutex_lock(&papr_ndr_lock); + list_for_each_entry(p, &papr_nd_regions, region_list) { + if (phys_addr >= p->res.start && phys_addr <= p->res.end) { + found = true; + break; + } + } + + if (found) + papr_scm_add_badblock(p->region, p->bus, phys_addr); + + mutex_unlock(&papr_ndr_lock); + + return found ? NOTIFY_OK : NOTIFY_DONE; +} + +static struct notifier_block mce_ue_nb = { + .notifier_call = handle_mce_ue +}; + static int papr_scm_probe(struct platform_device *pdev) { struct device_node *dn = pdev->dev.of_node; @@ -866,6 +1137,10 @@ static int papr_scm_remove(struct platform_device *pdev) { struct papr_scm_priv *p = platform_get_drvdata(pdev); + mutex_lock(&papr_ndr_lock); + list_del(&p->region_list); + mutex_unlock(&papr_ndr_lock); + nvdimm_bus_unregister(p->bus); drc_pmem_unbind(p); kfree(p->bus_desc.provider_name); @@ -876,6 +1151,7 @@ static int papr_scm_remove(struct platform_device *pdev) static const struct of_device_id papr_scm_match[] = { { .compatible = "ibm,pmemory" }, + { .compatible = "ibm,pmemory-v2" }, { }, }; @@ -888,7 +1164,25 @@ static struct platform_driver papr_scm_driver = { }, }; -module_platform_driver(papr_scm_driver); +static int __init papr_scm_init(void) +{ + int ret; + + ret = platform_driver_register(&papr_scm_driver); + if (!ret) + mce_register_notifier(&mce_ue_nb); + + return ret; +} +module_init(papr_scm_init); + +static void __exit papr_scm_exit(void) +{ + mce_unregister_notifier(&mce_ue_nb); + platform_driver_unregister(&papr_scm_driver); +} +module_exit(papr_scm_exit); + MODULE_DEVICE_TABLE(of, papr_scm_match); MODULE_LICENSE("GPL"); MODULE_AUTHOR("IBM Corporation"); diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index b3a38f5a6b68..f9ae17e8a0f4 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -34,7 +34,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pci_devs_phb_init_dynamic(phb); /* Create EEH devices for the PHB */ - eeh_dev_phb_init_dynamic(phb); + eeh_phb_pe_create(phb); if (dn->child) pseries_eeh_init_edev_recursive(PCI_DN(dn)); diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c index f860a897a9e0..e1dc5d3254df 100644 --- a/arch/powerpc/platforms/pseries/pmem.c +++ b/arch/powerpc/platforms/pseries/pmem.c @@ -24,7 +24,6 @@ #include <asm/topology.h> #include "pseries.h" -#include "offline_states.h" static struct device_node *pmem_node; @@ -147,6 +146,12 @@ const struct of_device_id drc_pmem_match[] = { static int pseries_pmem_init(void) { + /* + * Only supported on POWER8 and above. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_207S)) + return 0; + pmem_node = of_find_node_by_type(NULL, "ibm,persistent-memory"); if (!pmem_node) return 0; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 27094c872fd6..2f4ee0a90284 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -359,7 +359,7 @@ static void pseries_lpar_idle(void) * to ever be a problem in practice we can move this into a kernel thread to * finish off the process later in boot. */ -void pseries_enable_reloc_on_exc(void) +bool pseries_enable_reloc_on_exc(void) { long rc; unsigned int delay, total_delay = 0; @@ -370,11 +370,13 @@ void pseries_enable_reloc_on_exc(void) if (rc == H_P2) { pr_info("Relocation on exceptions not" " supported\n"); + return false; } else if (rc != H_SUCCESS) { pr_warn("Unable to enable relocation" " on exceptions: %ld\n", rc); + return false; } - break; + return true; } delay = get_longbusy_msecs(rc); @@ -383,7 +385,7 @@ void pseries_enable_reloc_on_exc(void) pr_warn("Warning: Giving up waiting to enable " "relocation on exceptions (%u msec)!\n", total_delay); - return; + return false; } mdelay(delay); @@ -746,6 +748,11 @@ static void __init pSeries_setup_arch(void) smp_init_pseries(); + if (radix_enabled() && !mmu_has_feature(MMU_FTR_GTSE)) + if (!firmware_has_feature(FW_FEATURE_RPT_INVALIDATE)) + panic("BUG: Radix support requires either GTSE or RPT_INVALIDATE\n"); + + /* openpic global configuration register (64-bit format). */ /* openpic Interrupt Source Unit pointer (64-bit format). */ /* python0 facility area (mmio) (64-bit format) REAL address. */ @@ -772,8 +779,10 @@ static void __init pSeries_setup_arch(void) if (firmware_has_feature(FW_FEATURE_LPAR)) { vpa_init(boot_cpuid); - if (lppaca_shared_proc(get_lppaca())) + if (lppaca_shared_proc(get_lppaca())) { static_branch_enable(&shared_processor); + pv_spinlocks_init(); + } ppc_md.power_save = pseries_lpar_idle; ppc_md.enable_pmcs = pseries_lpar_enable_pmcs; @@ -832,12 +841,15 @@ static int pseries_set_xdabr(unsigned long dabr, unsigned long dabrx) return plpar_hcall_norets(H_SET_XDABR, dabr, dabrx); } -static int pseries_set_dawr(unsigned long dawr, unsigned long dawrx) +static int pseries_set_dawr(int nr, unsigned long dawr, unsigned long dawrx) { /* PAPR says we can't set HYP */ dawrx &= ~DAWRX_HYP; - return plpar_set_watchpoint0(dawr, dawrx); + if (nr == 0) + return plpar_set_watchpoint0(dawr, dawrx); + else + return plpar_set_watchpoint1(dawr, dawrx); } #define CMO_CHARACTERISTICS_TOKEN 44 diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index 6891710833be..92922491a81c 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -44,8 +44,6 @@ #include <asm/svm.h> #include "pseries.h" -#include "offline_states.h" - /* * The Primary thread of each non-boot processor was started from the OF client @@ -108,10 +106,7 @@ static inline int smp_startup_cpu(unsigned int lcpu) /* Fixup atomic count: it exited inside IRQ handler. */ task_thread_info(paca_ptrs[lcpu]->__current)->preempt_count = 0; -#ifdef CONFIG_HOTPLUG_CPU - if (get_cpu_current_state(lcpu) == CPU_STATE_INACTIVE) - goto out; -#endif + /* * If the RTAS start-cpu token does not exist then presume the * cpu is already spinning. @@ -126,9 +121,6 @@ static inline int smp_startup_cpu(unsigned int lcpu) return 0; } -#ifdef CONFIG_HOTPLUG_CPU -out: -#endif return 1; } @@ -143,10 +135,6 @@ static void smp_setup_cpu(int cpu) vpa_init(cpu); cpumask_clear_cpu(cpu, of_spin_mask); -#ifdef CONFIG_HOTPLUG_CPU - set_cpu_current_state(cpu, CPU_STATE_ONLINE); - set_default_offline_state(cpu); -#endif } static int smp_pSeries_kick_cpu(int nr) @@ -163,20 +151,6 @@ static int smp_pSeries_kick_cpu(int nr) * the processor will continue on to secondary_start */ paca_ptrs[nr]->cpu_start = 1; -#ifdef CONFIG_HOTPLUG_CPU - set_preferred_offline_state(nr, CPU_STATE_ONLINE); - - if (get_cpu_current_state(nr) == CPU_STATE_INACTIVE) { - long rc; - unsigned long hcpuid; - - hcpuid = get_hard_smp_processor_id(nr); - rc = plpar_hcall_norets(H_PROD, hcpuid); - if (rc != H_SUCCESS) - printk(KERN_ERR "Error: Prod to wake up processor %d " - "Ret= %ld\n", nr, rc); - } -#endif return 0; } @@ -188,13 +162,16 @@ static int pseries_smp_prepare_cpu(int cpu) return 0; } -static void smp_pseries_cause_ipi(int cpu) +/* Cause IPI as setup by the interrupt controller (xics or xive) */ +static void (*ic_cause_ipi)(int cpu) __ro_after_init; + +/* Use msgsndp doorbells target is a sibling, else use interrupt controller */ +static void dbell_or_ic_cause_ipi(int cpu) { - /* POWER9 should not use this handler */ if (doorbell_try_core_ipi(cpu)) return; - icp_ops->cause_ipi(cpu); + ic_cause_ipi(cpu); } static int pseries_cause_nmi_ipi(int cpu) @@ -218,26 +195,49 @@ static int pseries_cause_nmi_ipi(int cpu) return 0; } -static __init void pSeries_smp_probe_xics(void) -{ - xics_smp_probe(); - - if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest()) - smp_ops->cause_ipi = smp_pseries_cause_ipi; - else - smp_ops->cause_ipi = icp_ops->cause_ipi; -} - static __init void pSeries_smp_probe(void) { if (xive_enabled()) - /* - * Don't use P9 doorbells when XIVE is enabled. IPIs - * using MMIOs should be faster - */ xive_smp_probe(); else - pSeries_smp_probe_xics(); + xics_smp_probe(); + + /* No doorbell facility, must use the interrupt controller for IPIs */ + if (!cpu_has_feature(CPU_FTR_DBELL)) + return; + + /* Doorbells can only be used for IPIs between SMT siblings */ + if (!cpu_has_feature(CPU_FTR_SMT)) + return; + + if (is_kvm_guest()) { + /* + * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp + * faults to the hypervisor which then reads the instruction + * from guest memory, which tends to be slower than using XIVE. + */ + if (xive_enabled()) + return; + + /* + * XICS hcalls aren't as fast, so we can use msgsndp (which + * also helps exercise KVM emulation), however KVM can't + * emulate secure guests because it can't read the instruction + * out of their memory. + */ + if (is_secure_guest()) + return; + } + + /* + * Under PowerVM, FSCR[MSGP] is enabled as guest vCPU siblings are + * gang scheduled on the same physical core, so doorbells are always + * faster than the interrupt controller, and they can be used by + * secure guests. + */ + + ic_cause_ipi = smp_ops->cause_ipi; + smp_ops->cause_ipi = dbell_or_ic_cause_ipi; } static struct smp_ops_t pseries_smp_ops = { diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 0a24a5a185f0..81e0ac58d620 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - stream_id = simple_strtoul(buf, NULL, 16); do { @@ -149,33 +145,14 @@ static ssize_t store_hibernate(struct device *dev, ssleep(1); } while (rc == -EAGAIN); - if (!rc) { - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, - cpu_online_mask); - rc = rtas_online_cpus_mask(offline_mask); - if (rc) { - pr_err("%s: Could not bring present CPUs online.\n", - __func__); - goto out; - } - - stop_topology_update(); + if (!rc) rc = pm_suspend(PM_SUSPEND_MEM); - start_topology_update(); - - /* Take down CPUs not online prior to suspend */ - if (!rtas_offline_cpus_mask(offline_mask)) - pr_warn("%s: Could not restore CPUs to offline " - "state.\n", __func__); - } stream_id = 0; if (!rc) rc = count; -out: - free_cpumask_var(offline_mask); + return rc; } diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile index 7c6d8b14f440..348f59581052 100644 --- a/arch/powerpc/purgatory/Makefile +++ b/arch/powerpc/purgatory/Makefile @@ -2,11 +2,11 @@ KASAN_SANITIZE := n -targets += trampoline.o purgatory.ro kexec-purgatory.c +targets += trampoline_$(BITS).o purgatory.ro kexec-purgatory.c LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -$(obj)/purgatory.ro: $(obj)/trampoline.o FORCE +$(obj)/purgatory.ro: $(obj)/trampoline_$(BITS).o FORCE $(call if_changed,ld) quiet_cmd_bin2c = BIN2C $@ diff --git a/arch/powerpc/purgatory/trampoline.S b/arch/powerpc/purgatory/trampoline_64.S index a5a83c3f53e6..d956b8a35fd1 100644 --- a/arch/powerpc/purgatory/trampoline.S +++ b/arch/powerpc/purgatory/trampoline_64.S @@ -10,6 +10,7 @@ */ #include <asm/asm-compat.h> +#include <asm/crashdump-ppc64.h> .machine ppc64 .balign 256 @@ -43,14 +44,39 @@ master: mr %r17,%r3 /* save cpu id to r17 */ mr %r15,%r4 /* save physical address in reg15 */ + /* Work out where we're running */ + bcl 20, 31, 0f +0: mflr %r18 + + /* + * Copy BACKUP_SRC_SIZE bytes from BACKUP_SRC_START to + * backup_start 8 bytes at a time. + * + * Use r3 = dest, r4 = src, r5 = size, r6 = count + */ + ld %r3, (backup_start - 0b)(%r18) + cmpdi %cr0, %r3, 0 + beq .Lskip_copy /* skip if there is no backup region */ + lis %r5, BACKUP_SRC_SIZE@h + ori %r5, %r5, BACKUP_SRC_SIZE@l + cmpdi %cr0, %r5, 0 + beq .Lskip_copy /* skip if copy size is zero */ + lis %r4, BACKUP_SRC_START@h + ori %r4, %r4, BACKUP_SRC_START@l + li %r6, 0 +.Lcopy_loop: + ldx %r0, %r6, %r4 + stdx %r0, %r6, %r3 + addi %r6, %r6, 8 + cmpld %cr0, %r6, %r5 + blt .Lcopy_loop + +.Lskip_copy: or %r3,%r3,%r3 /* ok now to high priority, lets boot */ lis %r6,0x1 mtctr %r6 /* delay a bit for slaves to catch up */ bdnz . /* before we overwrite 0-100 again */ - bl 0f /* Work out where we're running */ -0: mflr %r18 - /* load device-tree address */ ld %r3, (dt_offset - 0b)(%r18) mr %r16,%r3 /* save dt address in reg16 */ @@ -61,6 +87,10 @@ master: li %r4,28 STWX_BE %r17,%r3,%r4 /* Store my cpu as __be32 at byte 28 */ 1: + /* Load opal base and entry values in r8 & r9 respectively */ + ld %r8,(opal_base - 0b)(%r18) + ld %r9,(opal_entry - 0b)(%r18) + /* load the kernel address */ ld %r4,(kernel - 0b)(%r18) @@ -89,7 +119,6 @@ master: rfid /* update MSR and start kernel */ - .balign 8 .globl kernel kernel: @@ -102,6 +131,23 @@ dt_offset: .8byte 0x0 .size dt_offset, . - dt_offset + .balign 8 + .globl backup_start +backup_start: + .8byte 0x0 + .size backup_start, . - backup_start + + .balign 8 + .globl opal_base +opal_base: + .8byte 0x0 + .size opal_base, . - opal_base + + .balign 8 + .globl opal_entry +opal_entry: + .8byte 0x0 + .size opal_entry, . - opal_entry .data .balign 8 diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c index 71b881e554fc..cb58ec7ce77a 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -18,6 +18,7 @@ #include <linux/delay.h> #include <linux/cpumask.h> #include <linux/mm.h> +#include <linux/kmemleak.h> #include <asm/machdep.h> #include <asm/prom.h> @@ -647,6 +648,7 @@ static bool xive_native_provision_pages(void) pr_err("Failed to allocate provisioning page\n"); return false; } + kmemleak_ignore(p); opal_xive_donate_page(chip, __pa(p)); } return true; diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index f0551a2be9df..1e3674d7ea7b 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -768,7 +768,7 @@ static const u8 *get_vec5_feature(unsigned int index) return vec5 + index; } -static bool xive_spapr_disabled(void) +static bool __init xive_spapr_disabled(void) { const u8 *vec5_xive; diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 77114755dc6f..6e6a30aea3ed 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -31,7 +31,10 @@ grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]] grep -v '\<__start_initialization_multiplatform>' | grep -v -e 'b.\?.\?ctr' | grep -v -e 'b.\?.\?lr' | -sed 's/://' | +sed -e 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' \ + -e 's/\bbf.\?[[:space:]]*[[:digit:]][[:digit:]]*,/bne/' \ + -e 's/[[:space:]]0x/ /' \ + -e 's/://' | awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' ) diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile index 89c76ca35640..eb25d7554ffd 100644 --- a/arch/powerpc/xmon/Makefile +++ b/arch/powerpc/xmon/Makefile @@ -7,8 +7,7 @@ UBSAN_SANITIZE := n KASAN_SANITIZE := n # Disable ftrace for the entire directory -ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS)) +ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE) ifdef CONFIG_CC_IS_CLANG # clang stores addresses on the stack causing the frame size to blow diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 7efe4bc3ccf6..df7bca00f5ec 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -481,6 +481,13 @@ static inline int unrecoverable_excp(struct pt_regs *regs) #endif } +static void xmon_touch_watchdogs(void) +{ + touch_softlockup_watchdog_sync(); + rcu_cpu_stall_reset(); + touch_nmi_watchdog(); +} + static int xmon_core(struct pt_regs *regs, int fromipi) { int cmd = 0; @@ -718,7 +725,7 @@ static int xmon_core(struct pt_regs *regs, int fromipi) else insert_cpu_bpts(); - touch_nmi_watchdog(); + xmon_touch_watchdogs(); local_irq_restore(flags); return cmd != 'X' && cmd != EOF; @@ -1593,6 +1600,7 @@ const char *getvecname(unsigned long vec) case 0x1300: ret = "(Instruction Breakpoint)"; break; case 0x1500: ret = "(Denormalisation)"; break; case 0x1700: ret = "(Altivec Assist)"; break; + case 0x3000: ret = "(System Call Vectored)"; break; default: ret = ""; } return ret; @@ -1861,7 +1869,7 @@ static void cacheflush(void) catch_memory_errors = 1; sync(); - if (cmd != 'i') { + if (cmd != 'i' || IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { for (; nflush > 0; --nflush, adrs += L1_CACHE_BYTES) cflush((void *) adrs); } else { @@ -2022,6 +2030,18 @@ static void dump_300_sprs(void) #endif } +static void dump_310_sprs(void) +{ +#ifdef CONFIG_PPC64 + if (!cpu_has_feature(CPU_FTR_ARCH_31)) + return; + + printf("mmcr3 = %.16lx, sier2 = %.16lx, sier3 = %.16lx\n", + mfspr(SPRN_MMCR3), mfspr(SPRN_SIER2), mfspr(SPRN_SIER3)); + +#endif +} + static void dump_one_spr(int spr, bool show_unimplemented) { unsigned long val; @@ -2076,6 +2096,7 @@ static void super_regs(void) dump_206_sprs(); dump_207_sprs(); dump_300_sprs(); + dump_310_sprs(); return; } @@ -2934,11 +2955,10 @@ generic_inst_dump(unsigned long adr, long count, int praddr, int nr, dotted; unsigned long first_adr; struct ppc_inst inst, last_inst = ppc_inst(0); - unsigned char val[4]; dotted = 0; - for (first_adr = adr; count > 0; --count, adr += 4) { - nr = mread(adr, val, 4); + for (first_adr = adr; count > 0; --count, adr += ppc_inst_len(inst)) { + nr = mread_instr(adr, &inst); if (nr == 0) { if (praddr) { const char *x = fault_chars[fault_type]; @@ -2946,7 +2966,6 @@ generic_inst_dump(unsigned long adr, long count, int praddr, } break; } - inst = ppc_inst(GETWORD(val)); if (adr > first_adr && ppc_inst_equal(inst, last_inst)) { if (!dotted) { printf(" ...\n"); @@ -2957,9 +2976,12 @@ generic_inst_dump(unsigned long adr, long count, int praddr, dotted = 0; last_inst = inst; if (praddr) - printf(REG" %.8x", adr, ppc_inst_val(inst)); + printf(REG" %s", adr, ppc_inst_as_str(inst)); printf("\t"); - dump_func(ppc_inst_val(inst), adr); + if (!ppc_inst_prefixed(inst)) + dump_func(ppc_inst_val(inst), adr); + else + dump_func(ppc_inst_as_u64(inst), adr); printf("\n"); } return adr - first_adr; @@ -4256,7 +4278,7 @@ static int do_spu_cmd(void) subcmd = inchar(); if (isxdigit(subcmd) || subcmd == '\n') termch = subcmd; - /* fall through */ + fallthrough; case 'f': scanhex(&num); if (num >= XMON_NUM_SPUS || !spu_info[num].spu) { diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h index 3f601ee8233f..23b1544e0ca5 100644 --- a/arch/riscv/include/asm/pgalloc.h +++ b/arch/riscv/include/asm/pgalloc.h @@ -11,7 +11,7 @@ #include <asm/tlb.h> #ifdef CONFIG_MMU -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) @@ -55,24 +55,8 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; } -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long)pgd); -} - #ifndef __PAGETABLE_PMD_FOLDED -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - return (pmd_t *)__get_free_page( - GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_ZERO); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_page((unsigned long)pmd); -} - #define __pmd_free_tlb(tlb, pmd, addr) pmd_free((tlb)->mm, pmd) #endif /* __PAGETABLE_PMD_FOLDED */ diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 8ce9d607b53d..f56c66b3f5fe 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -8,6 +8,8 @@ #ifndef _ASM_RISCV_UACCESS_H #define _ASM_RISCV_UACCESS_H +#include <asm/pgtable.h> /* for TASK_SIZE */ + /* * User space memory access functions */ @@ -62,11 +64,9 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a).seg == (b).seg) - +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define user_addr_max() (get_fs().seg) - /** * access_ok: - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h index 3099362d9f26..f839f16e0d2a 100644 --- a/arch/riscv/include/asm/vdso/gettimeofday.h +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -60,7 +60,8 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return ret; } -static __always_inline u64 __arch_get_hw_counter(s32 clock_mode) +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) { /* * The purpose of csr_read(CSR_TIME) is to trap the system into diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index ae7b7fe24658..716d64e36f83 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -14,7 +14,6 @@ #include <linux/signal.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/ptrace.h> #include <asm/tlbflush.h> @@ -110,7 +109,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, addr, flags); + fault = handle_mm_fault(vma, addr, flags, regs); /* * If we need to retry but a fatal signal is pending, handle the @@ -128,21 +127,7 @@ good_area: BUG(); } - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, addr); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, addr); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 50bcd9f594d7..787c75f751a5 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -570,7 +570,6 @@ static void __init resource_init(void) void __init paging_init(void) { setup_vm_final(); - memblocks_present(); sparse_init(); setup_zero_page(); zone_sizes_init(); @@ -581,6 +580,6 @@ void __init paging_init(void) int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - return vmemmap_populate_basepages(start, end, node); + return vmemmap_populate_basepages(start, end, node, NULL); } #endif diff --git a/arch/s390/Kbuild b/arch/s390/Kbuild index e63940bb57cd..8b98c501142d 100644 --- a/arch/s390/Kbuild +++ b/arch/s390/Kbuild @@ -7,5 +7,4 @@ obj-$(CONFIG_S390_HYPFS_FS) += hypfs/ obj-$(CONFIG_APPLDATA_BASE) += appldata/ obj-y += net/ obj-$(CONFIG_PCI) += pci/ -obj-$(CONFIG_NUMA) += numa/ obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += purgatory/ diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8c0b52940165..3d86e12e8e3c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -126,7 +126,6 @@ config S390 select HAVE_ARCH_JUMP_LABEL_RELATIVE select HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_VMALLOC - select CLOCKSOURCE_VALIDATE_LAST_CYCLE select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_SOFT_DIRTY @@ -766,6 +765,7 @@ config VFIO_AP def_tristate n prompt "VFIO support for AP devices" depends on S390_AP_IOMMU && VFIO_MDEV_DEVICE && KVM + depends on ZCRYPT help This driver grants access to Adjunct Processor (AP) devices via the VFIO mediated device interface. diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 8dfa2cf1f05c..ba94b03c8b2f 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables -KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) +KBUILD_CFLAGS_DECOMPRESSOR += -ffreestanding KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index e1ae23911ccd..5057773f82e9 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -249,7 +249,7 @@ static void prng_tdes_deinstantiate(void) { pr_debug("The prng module stopped " "after running in triple DES mode\n"); - kzfree(prng_data); + kfree_sensitive(prng_data); } @@ -442,7 +442,7 @@ outfree: static void prng_sha512_deinstantiate(void) { pr_debug("The prng module stopped after running in SHA-512 mode\n"); - kzfree(prng_data); + kfree_sensitive(prng_data); } diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index cae473a7b6f7..11c5952e1afa 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -45,7 +45,11 @@ static inline int atomic_fetch_add(int i, atomic_t *v) static inline void atomic_add(int i, atomic_t *v) { #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES - if (__builtin_constant_p(i) && (i > -129) && (i < 128)) { + /* + * Order of conditions is important to circumvent gcc 10 bug: + * https://gcc.gnu.org/pipermail/gcc-patches/2020-July/549318.html + */ + if ((i > -129) && (i < 128) && __builtin_constant_p(i)) { __atomic_add_const(i, &v->counter); return; } @@ -112,7 +116,11 @@ static inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) static inline void atomic64_add(s64 i, atomic64_t *v) { #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES - if (__builtin_constant_p(i) && (i > -129) && (i < 128)) { + /* + * Order of conditions is important to circumvent gcc 10 bug: + * https://gcc.gnu.org/pipermail/gcc-patches/2020-July/549318.html + */ + if ((i > -129) && (i < 128) && __builtin_constant_p(i)) { __atomic64_add_const(i, (long *)&v->counter); return; } diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 17a26261f288..c1b82bcc017c 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -2,7 +2,7 @@ /* * S/390 debug facility * - * Copyright IBM Corp. 1999, 2000 + * Copyright IBM Corp. 1999, 2020 */ #ifndef DEBUG_H #define DEBUG_H @@ -26,19 +26,14 @@ #define DEBUG_DATA(entry) (char *)(entry + 1) /* data is stored behind */ /* the entry information */ -#define __DEBUG_FEATURE_VERSION 2 /* version of debug feature */ +#define __DEBUG_FEATURE_VERSION 3 /* version of debug feature */ struct __debug_entry { - union { - struct { - unsigned long clock : 52; - unsigned long exception : 1; - unsigned long level : 3; - unsigned long cpuid : 8; - } fields; - unsigned long stck; - } id; + unsigned long clock : 60; + unsigned long exception : 1; + unsigned long level : 3; void *caller; + unsigned short cpu; } __packed; typedef struct __debug_entry debug_entry_t; diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index aa406c05a350..954fa8ca6cbd 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -36,7 +36,6 @@ static inline bool __tlb_remove_page_size(struct mmu_gather *tlb, #define p4d_free_tlb p4d_free_tlb #define pud_free_tlb pud_free_tlb -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm-generic/tlb.h> diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 2204704840ea..acce6a08a1fa 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -5,7 +5,6 @@ #include <linux/mm.h> #include <linux/sched.h> #include <asm/processor.h> -#include <asm/pgalloc.h> /* * Flush all TLB entries on the local CPU. diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index fbb507504a3b..3a0ac0c7a9a3 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -86,12 +86,6 @@ static inline const struct cpumask *cpumask_of_node(int node) #define pcibus_to_node(bus) __pcibus_to_node(bus) -#define node_distance(a, b) __node_distance(a, b) -static inline int __node_distance(int a, int b) -{ - return 0; -} - #else /* !CONFIG_NUMA */ #define numa_node_id numa_node_id diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 324438889fe1..f09444d6aeab 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -32,7 +32,7 @@ #define USER_DS_SACF (3) #define get_fs() (current->thread.mm_segment) -#define segment_eq(a,b) (((a) & 2) == ((b) & 2)) +#define uaccess_kernel() ((get_fs() & 2) == KERNEL_DS) void set_fs(mm_segment_t fs); diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index a8f136943deb..efca70970761 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -49,6 +49,7 @@ CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE) obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o +obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_AUDIT) += audit.o compat-obj-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index beb4b44a11d1..b6619ae9a3e0 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -2,7 +2,7 @@ /* * S/390 debug facility * - * Copyright IBM Corp. 1999, 2012 + * Copyright IBM Corp. 1999, 2020 * * Author(s): Michael Holzheu (holzheu@de.ibm.com), * Holger Smolinski (Holger.Smolinski@de.ibm.com) @@ -433,7 +433,7 @@ static int debug_format_entry(file_private_info_t *p_info) act_entry = (debug_entry_t *) ((char *)id_snap->areas[p_info->act_area] [p_info->act_page] + p_info->act_entry); - if (act_entry->id.stck == 0LL) + if (act_entry->clock == 0LL) goto out; /* empty entry */ if (view->header_proc) len += view->header_proc(id_snap, view, p_info->act_area, @@ -829,12 +829,17 @@ static inline debug_entry_t *get_active_entry(debug_info_t *id) static inline void debug_finish_entry(debug_info_t *id, debug_entry_t *active, int level, int exception) { - active->id.stck = get_tod_clock_fast() - - *(unsigned long long *) &tod_clock_base[1]; - active->id.fields.cpuid = smp_processor_id(); + unsigned char clk[STORE_CLOCK_EXT_SIZE]; + unsigned long timestamp; + + get_tod_clock_ext(clk); + timestamp = *(unsigned long *) &clk[0] >> 4; + timestamp -= TOD_UNIX_EPOCH >> 12; + active->clock = timestamp; + active->cpu = smp_processor_id(); active->caller = __builtin_return_address(0); - active->id.fields.exception = exception; - active->id.fields.level = level; + active->exception = exception; + active->level = level; proceed_active_entry(id); if (exception) proceed_active_area(id); @@ -1398,25 +1403,24 @@ static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view, int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view, int area, debug_entry_t *entry, char *out_buf) { - unsigned long base, sec, usec; + unsigned long sec, usec; unsigned long caller; unsigned int level; char *except_str; int rc = 0; - level = entry->id.fields.level; - base = (*(unsigned long *) &tod_clock_base[0]) >> 4; - sec = (entry->id.stck >> 12) + base - (TOD_UNIX_EPOCH >> 12); + level = entry->level; + sec = entry->clock; usec = do_div(sec, USEC_PER_SEC); - if (entry->id.fields.exception) + if (entry->exception) except_str = "*"; else except_str = "-"; caller = (unsigned long) entry->caller; - rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %02i %pK ", + rc += sprintf(out_buf, "%02i %011ld:%06lu %1u %1s %04u %pK ", area, sec, usec, level, except_str, - entry->id.fields.cpuid, (void *)caller); + entry->cpu, (void *)caller); return rc; } EXPORT_SYMBOL(debug_dflt_header_fn); diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c index 93c6b8932fbd..d91989c7bd6a 100644 --- a/arch/s390/kernel/machine_kexec.c +++ b/arch/s390/kernel/machine_kexec.c @@ -16,7 +16,6 @@ #include <linux/debug_locks.h> #include <asm/cio.h> #include <asm/setup.h> -#include <asm/pgalloc.h> #include <asm/smp.h> #include <asm/ipl.h> #include <asm/diag.h> diff --git a/arch/s390/numa/numa.c b/arch/s390/kernel/numa.c index 51c5a9f6e525..51c5a9f6e525 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/kernel/numa.c diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index b06dec1267d0..ec801d3bbb37 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -160,24 +160,6 @@ asmlinkage void execve_tail(void) asm volatile("sfpc %0" : : "d" (0)); } -/* - * fill in the FPU structure for a core dump. - */ -int dump_fpu (struct pt_regs * regs, s390_fp_regs *fpregs) -{ - save_fpu_regs(); - fpregs->fpc = current->thread.fpu.fpc; - fpregs->pad = 0; - if (MACHINE_HAS_VX) - convert_vx_to_fp((freg_t *)&fpregs->fprs, - current->thread.fpu.vxrs); - else - memcpy(&fpregs->fprs, current->thread.fpu.fprs, - sizeof(fpregs->fprs)); - return 1; -} -EXPORT_SYMBOL(dump_fpu); - unsigned long get_wchan(struct task_struct *p) { struct unwind_state state; diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index a09b9e98936c..11d2f7d05f91 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -25,7 +25,6 @@ #include <linux/compat.h> #include <trace/syscall.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/switch_to.h> diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index f1fda4375526..10456bc936fb 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -138,7 +138,7 @@ 146 common writev sys_writev compat_sys_writev 147 common getsid sys_getsid sys_getsid 148 common fdatasync sys_fdatasync sys_fdatasync -149 common _sysctl sys_sysctl compat_sys_sysctl +149 common _sysctl - - 150 common mlock sys_mlock sys_mlock 151 common munlock sys_munlock sys_munlock 152 common mlockall sys_mlockall sys_mlockall diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 563429dece03..5b8ec1c447e1 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -10,7 +10,6 @@ #include <linux/kvm.h> #include <linux/kvm_host.h> -#include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/virtio-ccw.h> #include "kvm-s390.h" diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 1608fd99bbee..2f177298c663 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2768,7 +2768,7 @@ static struct page *get_map_page(struct kvm *kvm, u64 uaddr) struct page *page = NULL; mmap_read_lock(kvm->mm); - get_user_pages_remote(NULL, kvm->mm, uaddr, 1, FOLL_WRITE, + get_user_pages_remote(kvm->mm, uaddr, 1, FOLL_WRITE, &page, NULL, NULL); mmap_read_unlock(kvm->mm); return page; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 66da278a67fb..6b74b92c1a58 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1892,7 +1892,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args) r = set_guest_storage_key(current->mm, hva, keys[i], 0); if (r) { - r = fixup_user_fault(current, current->mm, hva, + r = fixup_user_fault(current->mm, hva, FAULT_FLAG_WRITE, &unlocked); if (r) break; diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 96ae368aa0a2..cd74989ce0b0 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -22,7 +22,6 @@ #include <asm/ebcdic.h> #include <asm/sysinfo.h> #include <asm/page-states.h> -#include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/io.h> #include <asm/ptrace.h> @@ -274,7 +273,7 @@ retry: rc = get_guest_storage_key(current->mm, vmaddr, &key); if (rc) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { mmap_read_unlock(current->mm); @@ -320,7 +319,7 @@ retry: mmap_read_lock(current->mm); rc = reset_guest_reference_bit(current->mm, vmaddr); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { mmap_read_unlock(current->mm); @@ -391,7 +390,7 @@ static int handle_sske(struct kvm_vcpu *vcpu) m3 & SSKE_MC); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } @@ -1095,7 +1094,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) rc = cond_set_guest_storage_key(current->mm, vmaddr, key, NULL, nq, mr, mc); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 63e330109b63..eb99e2f95ebe 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -9,7 +9,6 @@ #include <linux/kvm_host.h> #include <linux/pagemap.h> #include <linux/sched/signal.h> -#include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/uv.h> #include <asm/mman.h> diff --git a/arch/s390/lib/test_unwind.c b/arch/s390/lib/test_unwind.c index 32b7a30b2485..7c988994931f 100644 --- a/arch/s390/lib/test_unwind.c +++ b/arch/s390/lib/test_unwind.c @@ -9,6 +9,7 @@ #include <linux/kallsyms.h> #include <linux/kthread.h> #include <linux/module.h> +#include <linux/slab.h> #include <linux/string.h> #include <linux/kprobes.h> #include <linux/wait.h> @@ -63,6 +64,7 @@ static noinline int test_unwind(struct task_struct *task, struct pt_regs *regs, break; if (state.reliable && !addr) { pr_err("unwind state reliable but addr is 0\n"); + kfree(bt); return -EINVAL; } sprint_symbol(sym, addr); diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 5c15ae3daf71..1141c8d5c0d0 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -21,7 +21,6 @@ #include <linux/oom.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/diag.h> #ifdef CONFIG_CMM_IUCV diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index aebf9183bedd..4c8c063bce5b 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -476,7 +476,7 @@ retry: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) { fault = VM_FAULT_SIGNAL; if (flags & FAULT_FLAG_RETRY_NOWAIT) @@ -486,21 +486,7 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; - /* - * Major/minor page fault accounting is only done on the - * initial attempt. If we go through a retry, it is extremely - * likely that the page will be found in page cache at that point. - */ if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } if (fault & VM_FAULT_RETRY) { if (IS_ENABLED(CONFIG_PGSTE) && gmap && (flags & FAULT_FLAG_RETRY_NOWAIT)) { diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 190357ff86b3..373542ca1113 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -649,7 +649,7 @@ retry: rc = vmaddr; goto out_up; } - if (fixup_user_fault(current, gmap->mm, vmaddr, fault_flags, + if (fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked)) { rc = -EFAULT; goto out_up; @@ -879,7 +879,7 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr, BUG_ON(gmap_is_shadow(gmap)); fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0; - if (fixup_user_fault(current, mm, vmaddr, fault_flags, &unlocked)) + if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked)) return -EFAULT; if (unlocked) /* lost mmap_lock, caller has to retry __gmap_translate */ @@ -2485,23 +2485,36 @@ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4], } EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + + split_huge_pmd(vma, pmd, addr); + return 0; +} + +static const struct mm_walk_ops thp_split_walk_ops = { + .pmd_entry = thp_split_walk_pmd_entry, +}; + static inline void thp_split_mm(struct mm_struct *mm) { -#ifdef CONFIG_TRANSPARENT_HUGEPAGE struct vm_area_struct *vma; - unsigned long addr; for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { - for (addr = vma->vm_start; - addr < vma->vm_end; - addr += PAGE_SIZE) - follow_page(vma, addr, FOLL_SPLIT); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; + walk_page_vma(vma, &thp_split_walk_ops, NULL); } mm->def_flags |= VM_NOHUGEPAGE; -#endif } +#else +static inline void thp_split_mm(struct mm_struct *mm) +{ +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Remove all empty zero pages from the mapping for lazy refaulting diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 6dc7c3b60ef6..0d282081dc1f 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -115,7 +115,6 @@ void __init paging_init(void) __load_psw_mask(psw.mask); kasan_free_early_identity(); - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); zone_dma_bits = 31; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 1b78f630a9ca..e54f928503c5 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -17,7 +17,6 @@ #include <linux/random.h> #include <linux/compat.h> #include <linux/security.h> -#include <asm/pgalloc.h> #include <asm/elf.h> static unsigned long stack_maxrandom_size(void) diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 2e0cc19f4cd7..0d25f743b270 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -19,7 +19,6 @@ #include <linux/ksm.h> #include <linux/mman.h> -#include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> diff --git a/arch/s390/numa/Makefile b/arch/s390/numa/Makefile deleted file mode 100644 index c89d26f4f77d..000000000000 --- a/arch/s390/numa/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -obj-y += numa.o diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 9fc2b010e938..d20927128fce 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -1,75 +1,77 @@ # SPDX-License-Identifier: GPL-2.0 config SUPERH def_bool y + select ARCH_32BIT_OFF_T + select ARCH_HAVE_CUSTOM_GPIO_H + select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) select ARCH_HAS_BINFMT_FLAT if !MMU + select ARCH_HAS_GIGANTIC_PAGE + select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HIBERNATION_POSSIBLE if MMU select ARCH_MIGHT_HAVE_PC_PARPORT - select HAVE_PATA_PLATFORM + select ARCH_WANT_IPC_PARSE_VERSION select CLKDEV_LOOKUP + select CPU_NO_EFFICIENT_FFS select DMA_DECLARE_COHERENT - select HAVE_IDE if HAS_IOPORT_MAP - select HAVE_OPROFILE + select GENERIC_ATOMIC64 + select GENERIC_CLOCKEVENTS + select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST + select GENERIC_IDLE_POLL_SETUP + select GENERIC_IRQ_SHOW + select GENERIC_PCI_IOMAP if PCI + select GENERIC_SCHED_CLOCK + select GENERIC_STRNCPY_FROM_USER + select GENERIC_STRNLEN_USER + select GENERIC_SMP_IDLE_THREAD + select GUP_GET_PTE_LOW_HIGH if X2TLB + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_KGDB + select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_PERF_EVENTS + select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE - select HAVE_FAST_GUP if MMU - select ARCH_HAVE_CUSTOM_GPIO_H - select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A) - select ARCH_HAS_GCOV_PROFILE_ALL - select PERF_USE_VMALLOC select HAVE_DEBUG_KMEMLEAK - select HAVE_KERNEL_GZIP - select CPU_NO_EFFICIENT_FFS + select HAVE_DYNAMIC_FTRACE + select HAVE_FAST_GUP if MMU + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_TRACER + select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_HW_BREAKPOINT + select HAVE_IDE if HAS_IOPORT_MAP + select HAVE_IOREMAP_PROT if MMU && !X2TLB select HAVE_KERNEL_BZIP2 + select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZMA - select HAVE_KERNEL_XZ select HAVE_KERNEL_LZO + select HAVE_KERNEL_XZ + select HAVE_KPROBES + select HAVE_KRETPROBES + select HAVE_MIXED_BREAKPOINTS_REGS + select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER + select HAVE_NMI + select HAVE_OPROFILE + select HAVE_PATA_PLATFORM + select HAVE_PERF_EVENTS + select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_UID16 - select ARCH_WANT_IPC_PARSE_VERSION + select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS - select HAVE_REGS_AND_STACK_ACCESS_API - select MAY_HAVE_SPARSE_IRQ select IRQ_FORCED_THREADING - select RTC_LIB - select GENERIC_ATOMIC64 - select GENERIC_IRQ_SHOW - select GENERIC_SMP_IDLE_THREAD - select GENERIC_IDLE_POLL_SETUP - select GENERIC_CLOCKEVENTS - select GENERIC_CMOS_UPDATE if SH_SH03 || SH_DREAMCAST - select GENERIC_PCI_IOMAP if PCI - select GENERIC_SCHED_CLOCK - select GENERIC_STRNCPY_FROM_USER - select GENERIC_STRNLEN_USER - select HAVE_MOD_ARCH_SPECIFIC if DWARF_UNWINDER + select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA + select NEED_SG_DMA_LENGTH + select NO_DMA if !MMU && !DMA_COHERENT select NO_GENERIC_PCI_IOPORT_MAP if PCI - select OLD_SIGSUSPEND select OLD_SIGACTION + select OLD_SIGSUSPEND select PCI_DOMAINS if PCI - select HAVE_ARCH_AUDITSYSCALL - select HAVE_FUTEX_CMPXCHG if FUTEX - select HAVE_NMI - select NEED_SG_DMA_LENGTH - select ARCH_HAS_GIGANTIC_PAGE - select ARCH_32BIT_OFF_T - select GUP_GET_PTE_LOW_HIGH if X2TLB - select HAVE_KPROBES - select HAVE_KRETPROBES - select HAVE_IOREMAP_PROT if MMU && !X2TLB - select HAVE_FUNCTION_TRACER - select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_DYNAMIC_FTRACE - select ARCH_WANT_IPC_PARSE_VERSION - select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_ARCH_KGDB - select HAVE_HW_BREAKPOINT - select HAVE_MIXED_BREAKPOINTS_REGS select PERF_EVENTS - select ARCH_HIBERNATION_POSSIBLE if MMU + select PERF_USE_VMALLOC + select RTC_LIB select SPARSE_IRQ - select HAVE_STACKPROTECTOR help The SuperH is a RISC processor targeted for use in embedded systems and consumer electronics; it was also used in the Sega Dreamcast @@ -123,8 +125,8 @@ config ARCH_HAS_ILOG2_U64 config NO_IOPORT_MAP def_bool !PCI - depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN && \ - !SH_HP6XX && !SH_SOLUTION_ENGINE + depends on !SH_SH4202_MICRODEV && !SH_SHMIN && !SH_HP6XX && \ + !SH_SOLUTION_ENGINE config IO_TRAPPED bool @@ -136,8 +138,10 @@ config DMA_COHERENT bool config DMA_NONCOHERENT - def_bool !DMA_COHERENT + def_bool !NO_DMA && !DMA_COHERENT + select ARCH_HAS_DMA_PREP_COHERENT select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_DIRECT_REMAP config PGTABLE_LEVELS default 3 if X2TLB @@ -630,7 +634,7 @@ config SMP Y to "Enhanced Real Time Clock Support", below. See also <file:Documentation/admin-guide/lockup-watchdogs.rst> and the SMP-HOWTO - available at <http://www.tldp.org/docs.html#howto>. + available at <https://www.tldp.org/docs.html#howto>. If you don't know what to do here, say N. @@ -726,7 +730,6 @@ config ZERO_PAGE_OFFSET config BOOT_LINK_OFFSET hex default "0x00210000" if SH_SHMIN - default "0x00400000" if SH_CAYMAN default "0x00810000" if SH_7780_SOLUTION_ENGINE default "0x009e0000" if SH_TITAN default "0x01800000" if SH_SDK7780 diff --git a/arch/sh/Makefile b/arch/sh/Makefile index da9cf952f33c..2faebfd72eca 100644 --- a/arch/sh/Makefile +++ b/arch/sh/Makefile @@ -15,11 +15,7 @@ ifneq ($(SUBARCH),$(ARCH)) endif endif -ifeq ($(ARCH),sh) KBUILD_DEFCONFIG := shx3_defconfig -else -KBUILD_DEFCONFIG := cayman_defconfig -endif isa-y := any isa-$(CONFIG_SH_DSP) := sh @@ -143,7 +139,6 @@ machdir-$(CONFIG_SH_SH7763RDP) += mach-sh7763rdp machdir-$(CONFIG_SH_SH4202_MICRODEV) += mach-microdev machdir-$(CONFIG_SH_LANDISK) += mach-landisk machdir-$(CONFIG_SH_LBOX_RE2) += mach-lboxre2 -machdir-$(CONFIG_SH_CAYMAN) += mach-cayman machdir-$(CONFIG_SH_RSK) += mach-rsk ifneq ($(machdir-y),) diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index fb0ca0c1efe1..83bcb6d2daca 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -340,12 +340,6 @@ config SH_MAGIC_PANEL_R2 help Select Magic Panel R2 if configuring for Magic Panel R2. -config SH_CAYMAN - bool "Hitachi Cayman" - depends on CPU_SUBTYPE_SH5_101 || CPU_SUBTYPE_SH5_103 - select HAVE_PCI - select ARCH_MIGHT_HAVE_PC_SERIO - config SH_POLARIS bool "SMSC Polaris" select CPU_HAS_IPR_IRQ diff --git a/arch/sh/boards/board-sh2007.c b/arch/sh/boards/board-sh2007.c index ef9c87deeb08..6ea85e480851 100644 --- a/arch/sh/boards/board-sh2007.c +++ b/arch/sh/boards/board-sh2007.c @@ -126,14 +126,14 @@ static void __init sh2007_init_irq(void) */ static void __init sh2007_setup(char **cmdline_p) { - printk(KERN_INFO "SH-2007 Setup..."); + pr_info("SH-2007 Setup..."); /* setup wait control registers for area 5 */ __raw_writel(CS5BCR_D, CS5BCR); __raw_writel(CS5WCR_D, CS5WCR); __raw_writel(CS5PCR_D, CS5PCR); - printk(KERN_INFO " done.\n"); + pr_cont(" done.\n"); } /* diff --git a/arch/sh/boards/mach-cayman/Makefile b/arch/sh/boards/mach-cayman/Makefile deleted file mode 100644 index 775a4be57434..000000000000 --- a/arch/sh/boards/mach-cayman/Makefile +++ /dev/null @@ -1,5 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for the Hitachi Cayman specific parts of the kernel -# -obj-y := setup.o irq.o panic.o diff --git a/arch/sh/boards/mach-cayman/irq.c b/arch/sh/boards/mach-cayman/irq.c deleted file mode 100644 index 0305d0b51730..000000000000 --- a/arch/sh/boards/mach-cayman/irq.c +++ /dev/null @@ -1,148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * arch/sh/mach-cayman/irq.c - SH-5 Cayman Interrupt Support - * - * This file handles the board specific parts of the Cayman interrupt system - * - * Copyright (C) 2002 Stuart Menefy - */ -#include <linux/io.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/signal.h> -#include <cpu/irq.h> -#include <asm/page.h> - -/* Setup for the SMSC FDC37C935 / LAN91C100FD */ -#define SMSC_IRQ IRQ_IRL1 - -/* Setup for PCI Bus 2, which transmits interrupts via the EPLD */ -#define PCI2_IRQ IRQ_IRL3 - -unsigned long epld_virt; - -#define EPLD_BASE 0x04002000 -#define EPLD_STATUS_BASE (epld_virt + 0x10) -#define EPLD_MASK_BASE (epld_virt + 0x20) - -/* Note the SMSC SuperIO chip and SMSC LAN chip interrupts are all muxed onto - the same SH-5 interrupt */ - -static irqreturn_t cayman_interrupt_smsc(int irq, void *dev_id) -{ - printk(KERN_INFO "CAYMAN: spurious SMSC interrupt\n"); - return IRQ_NONE; -} - -static irqreturn_t cayman_interrupt_pci2(int irq, void *dev_id) -{ - printk(KERN_INFO "CAYMAN: spurious PCI interrupt, IRQ %d\n", irq); - return IRQ_NONE; -} - -static void enable_cayman_irq(struct irq_data *data) -{ - unsigned int irq = data->irq; - unsigned long flags; - unsigned long mask; - unsigned int reg; - unsigned char bit; - - irq -= START_EXT_IRQS; - reg = EPLD_MASK_BASE + ((irq / 8) << 2); - bit = 1<<(irq % 8); - local_irq_save(flags); - mask = __raw_readl(reg); - mask |= bit; - __raw_writel(mask, reg); - local_irq_restore(flags); -} - -static void disable_cayman_irq(struct irq_data *data) -{ - unsigned int irq = data->irq; - unsigned long flags; - unsigned long mask; - unsigned int reg; - unsigned char bit; - - irq -= START_EXT_IRQS; - reg = EPLD_MASK_BASE + ((irq / 8) << 2); - bit = 1<<(irq % 8); - local_irq_save(flags); - mask = __raw_readl(reg); - mask &= ~bit; - __raw_writel(mask, reg); - local_irq_restore(flags); -} - -struct irq_chip cayman_irq_type = { - .name = "Cayman-IRQ", - .irq_unmask = enable_cayman_irq, - .irq_mask = disable_cayman_irq, -}; - -int cayman_irq_demux(int evt) -{ - int irq = intc_evt_to_irq[evt]; - - if (irq == SMSC_IRQ) { - unsigned long status; - int i; - - status = __raw_readl(EPLD_STATUS_BASE) & - __raw_readl(EPLD_MASK_BASE) & 0xff; - if (status == 0) { - irq = -1; - } else { - for (i=0; i<8; i++) { - if (status & (1<<i)) - break; - } - irq = START_EXT_IRQS + i; - } - } - - if (irq == PCI2_IRQ) { - unsigned long status; - int i; - - status = __raw_readl(EPLD_STATUS_BASE + 3 * sizeof(u32)) & - __raw_readl(EPLD_MASK_BASE + 3 * sizeof(u32)) & 0xff; - if (status == 0) { - irq = -1; - } else { - for (i=0; i<8; i++) { - if (status & (1<<i)) - break; - } - irq = START_EXT_IRQS + (3 * 8) + i; - } - } - - return irq; -} - -void init_cayman_irq(void) -{ - int i; - - epld_virt = (unsigned long)ioremap(EPLD_BASE, 1024); - if (!epld_virt) { - printk(KERN_ERR "Cayman IRQ: Unable to remap EPLD\n"); - return; - } - - for (i = 0; i < NR_EXT_IRQS; i++) { - irq_set_chip_and_handler(START_EXT_IRQS + i, - &cayman_irq_type, handle_level_irq); - } - - /* Setup the SMSC interrupt */ - if (request_irq(SMSC_IRQ, cayman_interrupt_smsc, 0, "Cayman SMSC Mux", - NULL)) - pr_err("Failed to register Cayman SMSC Mux interrupt\n"); - if (request_irq(PCI2_IRQ, cayman_interrupt_pci2, 0, "Cayman PCI2 Mux", - NULL)) - pr_err("Failed to register Cayman PCI2 Mux interrupt\n"); -} diff --git a/arch/sh/boards/mach-cayman/panic.c b/arch/sh/boards/mach-cayman/panic.c deleted file mode 100644 index cfc46314e7d9..000000000000 --- a/arch/sh/boards/mach-cayman/panic.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (C) 2003 Richard Curnow, SuperH UK Limited - */ - -#include <linux/kernel.h> -#include <linux/io.h> -#include <cpu/registers.h> - -/* THIS IS A PHYSICAL ADDRESS */ -#define HDSP2534_ADDR (0x04002100) - -static void poor_mans_delay(void) -{ - int i; - - for (i = 0; i < 2500000; i++) - cpu_relax(); -} - -static void show_value(unsigned long x) -{ - int i; - unsigned nibble; - for (i = 0; i < 8; i++) { - nibble = ((x >> (i * 4)) & 0xf); - - __raw_writeb(nibble + ((nibble > 9) ? 55 : 48), - HDSP2534_ADDR + 0xe0 + ((7 - i) << 2)); - } -} - -void -panic_handler(unsigned long panicPC, unsigned long panicSSR, - unsigned long panicEXPEVT) -{ - while (1) { - /* This piece of code displays the PC on the LED display */ - show_value(panicPC); - poor_mans_delay(); - show_value(panicSSR); - poor_mans_delay(); - show_value(panicEXPEVT); - poor_mans_delay(); - } -} diff --git a/arch/sh/boards/mach-cayman/setup.c b/arch/sh/boards/mach-cayman/setup.c deleted file mode 100644 index 8ef76e288da0..000000000000 --- a/arch/sh/boards/mach-cayman/setup.c +++ /dev/null @@ -1,181 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * arch/sh/mach-cayman/setup.c - * - * SH5 Cayman support - * - * Copyright (C) 2002 David J. Mckay & Benedict Gaster - * Copyright (C) 2003 - 2007 Paul Mundt - */ -#include <linux/init.h> -#include <linux/io.h> -#include <linux/kernel.h> -#include <cpu/irq.h> - -/* - * Platform Dependent Interrupt Priorities. - */ - -/* Using defaults defined in irq.h */ -#define RES NO_PRIORITY /* Disabled */ -#define IR0 IRL0_PRIORITY /* IRLs */ -#define IR1 IRL1_PRIORITY -#define IR2 IRL2_PRIORITY -#define IR3 IRL3_PRIORITY -#define PCA INTA_PRIORITY /* PCI Ints */ -#define PCB INTB_PRIORITY -#define PCC INTC_PRIORITY -#define PCD INTD_PRIORITY -#define SER TOP_PRIORITY -#define ERR TOP_PRIORITY -#define PW0 TOP_PRIORITY -#define PW1 TOP_PRIORITY -#define PW2 TOP_PRIORITY -#define PW3 TOP_PRIORITY -#define DM0 NO_PRIORITY /* DMA Ints */ -#define DM1 NO_PRIORITY -#define DM2 NO_PRIORITY -#define DM3 NO_PRIORITY -#define DAE NO_PRIORITY -#define TU0 TIMER_PRIORITY /* TMU Ints */ -#define TU1 NO_PRIORITY -#define TU2 NO_PRIORITY -#define TI2 NO_PRIORITY -#define ATI NO_PRIORITY /* RTC Ints */ -#define PRI NO_PRIORITY -#define CUI RTC_PRIORITY -#define ERI SCIF_PRIORITY /* SCIF Ints */ -#define RXI SCIF_PRIORITY -#define BRI SCIF_PRIORITY -#define TXI SCIF_PRIORITY -#define ITI TOP_PRIORITY /* WDT Ints */ - -/* Setup for the SMSC FDC37C935 */ -#define SMSC_SUPERIO_BASE 0x04000000 -#define SMSC_CONFIG_PORT_ADDR 0x3f0 -#define SMSC_INDEX_PORT_ADDR SMSC_CONFIG_PORT_ADDR -#define SMSC_DATA_PORT_ADDR 0x3f1 - -#define SMSC_ENTER_CONFIG_KEY 0x55 -#define SMSC_EXIT_CONFIG_KEY 0xaa - -#define SMCS_LOGICAL_DEV_INDEX 0x07 -#define SMSC_DEVICE_ID_INDEX 0x20 -#define SMSC_DEVICE_REV_INDEX 0x21 -#define SMSC_ACTIVATE_INDEX 0x30 -#define SMSC_PRIMARY_BASE_INDEX 0x60 -#define SMSC_SECONDARY_BASE_INDEX 0x62 -#define SMSC_PRIMARY_INT_INDEX 0x70 -#define SMSC_SECONDARY_INT_INDEX 0x72 - -#define SMSC_IDE1_DEVICE 1 -#define SMSC_KEYBOARD_DEVICE 7 -#define SMSC_CONFIG_REGISTERS 8 - -#define SMSC_SUPERIO_READ_INDEXED(index) ({ \ - outb((index), SMSC_INDEX_PORT_ADDR); \ - inb(SMSC_DATA_PORT_ADDR); }) -#define SMSC_SUPERIO_WRITE_INDEXED(val, index) ({ \ - outb((index), SMSC_INDEX_PORT_ADDR); \ - outb((val), SMSC_DATA_PORT_ADDR); }) - -#define IDE1_PRIMARY_BASE 0x01f0 -#define IDE1_SECONDARY_BASE 0x03f6 - -unsigned long smsc_superio_virt; - -int platform_int_priority[NR_INTC_IRQS] = { - IR0, IR1, IR2, IR3, PCA, PCB, PCC, PCD, /* IRQ 0- 7 */ - RES, RES, RES, RES, SER, ERR, PW3, PW2, /* IRQ 8-15 */ - PW1, PW0, DM0, DM1, DM2, DM3, DAE, RES, /* IRQ 16-23 */ - RES, RES, RES, RES, RES, RES, RES, RES, /* IRQ 24-31 */ - TU0, TU1, TU2, TI2, ATI, PRI, CUI, ERI, /* IRQ 32-39 */ - RXI, BRI, TXI, RES, RES, RES, RES, RES, /* IRQ 40-47 */ - RES, RES, RES, RES, RES, RES, RES, RES, /* IRQ 48-55 */ - RES, RES, RES, RES, RES, RES, RES, ITI, /* IRQ 56-63 */ -}; - -static int __init smsc_superio_setup(void) -{ - unsigned char devid, devrev; - - smsc_superio_virt = (unsigned long)ioremap(SMSC_SUPERIO_BASE, 1024); - if (!smsc_superio_virt) { - panic("Unable to remap SMSC SuperIO\n"); - } - - /* Initially the chip is in run state */ - /* Put it into configuration state */ - outb(SMSC_ENTER_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR); - outb(SMSC_ENTER_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR); - - /* Read device ID info */ - devid = SMSC_SUPERIO_READ_INDEXED(SMSC_DEVICE_ID_INDEX); - devrev = SMSC_SUPERIO_READ_INDEXED(SMSC_DEVICE_REV_INDEX); - printk("SMSC SuperIO devid %02x rev %02x\n", devid, devrev); - - /* Select the keyboard device */ - SMSC_SUPERIO_WRITE_INDEXED(SMSC_KEYBOARD_DEVICE, SMCS_LOGICAL_DEV_INDEX); - - /* enable it */ - SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_ACTIVATE_INDEX); - - /* Select the interrupts */ - /* On a PC keyboard is IRQ1, mouse is IRQ12 */ - SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX); - SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX); - - /* - * Only IDE1 exists on the Cayman - */ - - /* Power it on */ - SMSC_SUPERIO_WRITE_INDEXED(1 << SMSC_IDE1_DEVICE, 0x22); - - SMSC_SUPERIO_WRITE_INDEXED(SMSC_IDE1_DEVICE, SMCS_LOGICAL_DEV_INDEX); - SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_ACTIVATE_INDEX); - - SMSC_SUPERIO_WRITE_INDEXED(IDE1_PRIMARY_BASE >> 8, - SMSC_PRIMARY_BASE_INDEX + 0); - SMSC_SUPERIO_WRITE_INDEXED(IDE1_PRIMARY_BASE & 0xff, - SMSC_PRIMARY_BASE_INDEX + 1); - - SMSC_SUPERIO_WRITE_INDEXED(IDE1_SECONDARY_BASE >> 8, - SMSC_SECONDARY_BASE_INDEX + 0); - SMSC_SUPERIO_WRITE_INDEXED(IDE1_SECONDARY_BASE & 0xff, - SMSC_SECONDARY_BASE_INDEX + 1); - - SMSC_SUPERIO_WRITE_INDEXED(14, SMSC_PRIMARY_INT_INDEX); - - SMSC_SUPERIO_WRITE_INDEXED(SMSC_CONFIG_REGISTERS, - SMCS_LOGICAL_DEV_INDEX); - - SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc2); /* GP42 = nIDE1_OE */ - SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */ - SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */ - SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */ - - /* Exit the configuration state */ - outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR); - - return 0; -} -device_initcall(smsc_superio_setup); - -static void __iomem *cayman_ioport_map(unsigned long port, unsigned int len) -{ - if (port < 0x400) { - extern unsigned long smsc_superio_virt; - return (void __iomem *)((port << 2) | smsc_superio_virt); - } - - return (void __iomem *)port; -} - -extern void init_cayman_irq(void); - -static struct sh_machine_vector mv_cayman __initmv = { - .mv_name = "Hitachi Cayman", - .mv_ioport_map = cayman_ioport_map, - .mv_init_irq = init_cayman_irq, -}; diff --git a/arch/sh/boards/mach-landisk/setup.c b/arch/sh/boards/mach-landisk/setup.c index 16b4d8b0bb85..2c44b94f82fb 100644 --- a/arch/sh/boards/mach-landisk/setup.c +++ b/arch/sh/boards/mach-landisk/setup.c @@ -82,6 +82,9 @@ device_initcall(landisk_devices_setup); static void __init landisk_setup(char **cmdline_p) { + /* I/O port identity mapping */ + __set_io_port_base(0); + /* LED ON */ __raw_writeb(__raw_readb(PA_LED) | 0x03, PA_LED); diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile index ad0e2403e56f..589d2d8a573d 100644 --- a/arch/sh/boot/compressed/Makefile +++ b/arch/sh/boot/compressed/Makefile @@ -28,10 +28,7 @@ IMAGE_OFFSET := $(shell /bin/bash -c 'printf "0x%08x" \ $(CONFIG_BOOT_LINK_OFFSET)]') endif -ifeq ($(CONFIG_MCOUNT),y) -ORIG_CFLAGS := $(KBUILD_CFLAGS) -KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS)) -endif +ccflags-remove-$(CONFIG_MCOUNT) += -pg LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \ -T $(obj)/../../kernel/vmlinux.lds diff --git a/arch/sh/configs/ap325rxa_defconfig b/arch/sh/configs/ap325rxa_defconfig index cc6e4ce53dac..5193b3e099b9 100644 --- a/arch/sh/configs/ap325rxa_defconfig +++ b/arch/sh/configs/ap325rxa_defconfig @@ -65,9 +65,6 @@ CONFIG_VIDEO_DEV=y # CONFIG_VIDEO_ALLOW_V4L1 is not set # CONFIG_MEDIA_TUNER_CUSTOMISE is not set CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_PLATFORM=y -CONFIG_SOC_CAMERA_OV772X=y CONFIG_VIDEO_SH_MOBILE_CEU=y # CONFIG_RADIO_ADAPTERS is not set CONFIG_FB=y diff --git a/arch/sh/configs/cayman_defconfig b/arch/sh/configs/cayman_defconfig deleted file mode 100644 index 911437c163c7..000000000000 --- a/arch/sh/configs/cayman_defconfig +++ /dev/null @@ -1,66 +0,0 @@ -CONFIG_POSIX_MQUEUE=y -CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_BLK_DEV_BSG is not set -CONFIG_FORCE_MAX_ZONEORDER=11 -CONFIG_MEMORY_START=0x80000000 -CONFIG_MEMORY_SIZE=0x00400000 -CONFIG_FLATMEM_MANUAL=y -CONFIG_CACHE_OFF=y -CONFIG_SH_PCLK_FREQ=50000000 -CONFIG_HEARTBEAT=y -CONFIG_PREEMPT=y -CONFIG_NET=y -CONFIG_PACKET=y -CONFIG_UNIX=y -CONFIG_INET=y -CONFIG_IP_PNP=y -# CONFIG_IPV6 is not set -# CONFIG_FW_LOADER is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_RAM=y -CONFIG_SCSI=y -CONFIG_BLK_DEV_SD=y -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_SPI_ATTRS=y -CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_SERIO is not set -CONFIG_HW_RANDOM=y -CONFIG_I2C=m -CONFIG_WATCHDOG=y -CONFIG_FB=y -CONFIG_FIRMWARE_EDID=y -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_SH_MOBILE_LCDC=m -CONFIG_FRAMEBUFFER_CONSOLE=y -CONFIG_FONTS=y -CONFIG_FONT_8x16=y -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set -# CONFIG_LOGO_LINUX_CLUT224 is not set -# CONFIG_LOGO_SUPERH_MONO is not set -# CONFIG_LOGO_SUPERH_VGA16 is not set -CONFIG_EXT2_FS=y -CONFIG_EXT3_FS=y -# CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_MINIX_FS=y -CONFIG_ROMFS_FS=y -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_SCHEDSTATS=y -CONFIG_FRAME_POINTER=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set diff --git a/arch/sh/configs/dreamcast_defconfig b/arch/sh/configs/dreamcast_defconfig index ae067e0b15e3..6a82c7b8ff32 100644 --- a/arch/sh/configs/dreamcast_defconfig +++ b/arch/sh/configs/dreamcast_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_MODULES=y diff --git a/arch/sh/configs/ecovec24_defconfig b/arch/sh/configs/ecovec24_defconfig index 2fb7db4957ce..03cb916819fa 100644 --- a/arch/sh/configs/ecovec24_defconfig +++ b/arch/sh/configs/ecovec24_defconfig @@ -72,9 +72,6 @@ CONFIG_MEDIA_SUPPORT=y CONFIG_VIDEO_DEV=y # CONFIG_MEDIA_TUNER_CUSTOMISE is not set CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_MT9T112=y -CONFIG_SOC_CAMERA_TW9910=y CONFIG_VIDEO_SH_MOBILE_CEU=y # CONFIG_V4L_USB_DRIVERS is not set CONFIG_FB=y diff --git a/arch/sh/configs/espt_defconfig b/arch/sh/configs/espt_defconfig index a5b865a75d22..9a988c347e9d 100644 --- a/arch/sh/configs/espt_defconfig +++ b/arch/sh/configs/espt_defconfig @@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_UTS_NS=y CONFIG_IPC_NS=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/hp6xx_defconfig b/arch/sh/configs/hp6xx_defconfig index a92db6694ce2..70e6605d7f7e 100644 --- a/arch/sh/configs/hp6xx_defconfig +++ b/arch/sh/configs/hp6xx_defconfig @@ -3,7 +3,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH7709=y diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index 567af752b1bb..ba6ec042606f 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -1,6 +1,5 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/lboxre2_defconfig b/arch/sh/configs/lboxre2_defconfig index 10f6d371ce2c..05e4ac6fed5f 100644 --- a/arch/sh/configs/lboxre2_defconfig +++ b/arch/sh/configs/lboxre2_defconfig @@ -1,6 +1,5 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index ed84d1303acf..c65667d00313 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -2,7 +2,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set CONFIG_CPU_SUBTYPE_SH4_202=y diff --git a/arch/sh/configs/migor_defconfig b/arch/sh/configs/migor_defconfig index 494a1675c226..a24cf8cd2cea 100644 --- a/arch/sh/configs/migor_defconfig +++ b/arch/sh/configs/migor_defconfig @@ -4,7 +4,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y @@ -62,9 +61,6 @@ CONFIG_VIDEO_DEV=y # CONFIG_VIDEO_ALLOW_V4L1 is not set # CONFIG_MEDIA_TUNER_CUSTOMISE is not set CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_TW9910=y -CONFIG_SOC_CAMERA_OV772X=y CONFIG_VIDEO_SH_MOBILE_CEU=y # CONFIG_RADIO_ADAPTERS is not set CONFIG_FB=y diff --git a/arch/sh/configs/r7780mp_defconfig b/arch/sh/configs/r7780mp_defconfig index c97ec60cff27..e922659fdadb 100644 --- a/arch/sh/configs/r7780mp_defconfig +++ b/arch/sh/configs/r7780mp_defconfig @@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set CONFIG_SLAB=y diff --git a/arch/sh/configs/r7785rp_defconfig b/arch/sh/configs/r7785rp_defconfig index 55fce65eb454..5978866358ec 100644 --- a/arch/sh/configs/r7785rp_defconfig +++ b/arch/sh/configs/r7785rp_defconfig @@ -7,7 +7,6 @@ CONFIG_RCU_TRACE=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/rts7751r2d1_defconfig b/arch/sh/configs/rts7751r2d1_defconfig index 6a3cfe08295f..fc9c22152b08 100644 --- a/arch/sh/configs/rts7751r2d1_defconfig +++ b/arch/sh/configs/rts7751r2d1_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/rts7751r2dplus_defconfig b/arch/sh/configs/rts7751r2dplus_defconfig index 2b3d7d280672..ff3fd6787fd6 100644 --- a/arch/sh/configs/rts7751r2dplus_defconfig +++ b/arch/sh/configs/rts7751r2dplus_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig index 21a43f14ffac..ff5bb4489922 100644 --- a/arch/sh/configs/se7206_defconfig +++ b/arch/sh/configs/se7206_defconfig @@ -18,7 +18,6 @@ CONFIG_USER_NS=y CONFIG_PID_NS=y CONFIG_BLK_DEV_INITRD=y # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_ALL=y # CONFIG_ELF_CORE is not set # CONFIG_COMPAT_BRK is not set diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig index 4e794e719a28..5d6c19338ebf 100644 --- a/arch/sh/configs/se7343_defconfig +++ b/arch/sh/configs/se7343_defconfig @@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set diff --git a/arch/sh/configs/se7619_defconfig b/arch/sh/configs/se7619_defconfig index 3264415a5931..71a672c30716 100644 --- a/arch/sh/configs/se7619_defconfig +++ b/arch/sh/configs/se7619_defconfig @@ -1,7 +1,6 @@ # CONFIG_LOCALVERSION_AUTO is not set CONFIG_LOG_BUF_SHIFT=14 # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set # CONFIG_ELF_CORE is not set diff --git a/arch/sh/configs/se7705_defconfig b/arch/sh/configs/se7705_defconfig index 4496b94b7d88..ed00a6eeadf5 100644 --- a/arch/sh/configs/se7705_defconfig +++ b/arch/sh/configs/se7705_defconfig @@ -2,7 +2,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y diff --git a/arch/sh/configs/se7724_defconfig b/arch/sh/configs/se7724_defconfig index 0e8d5cc1e107..a26f7f1841c7 100644 --- a/arch/sh/configs/se7724_defconfig +++ b/arch/sh/configs/se7724_defconfig @@ -70,8 +70,6 @@ CONFIG_VIDEO_DEV=y CONFIG_DVB_CORE=m # CONFIG_MEDIA_TUNER_CUSTOMISE is not set CONFIG_VIDEO_HELPER_CHIPS_AUTO=y -CONFIG_SOC_CAMERA=y -CONFIG_SOC_CAMERA_OV772X=y CONFIG_VIDEO_SH_MOBILE_CEU=y # CONFIG_RADIO_ADAPTERS is not set # CONFIG_DVB_FE_CUSTOMISE is not set diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index b23f67542728..3f1c13799d79 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -5,7 +5,6 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/se7751_defconfig b/arch/sh/configs/se7751_defconfig index 162343683937..4a024065bb75 100644 --- a/arch/sh/configs/se7751_defconfig +++ b/arch/sh/configs/se7751_defconfig @@ -3,7 +3,6 @@ CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/secureedge5410_defconfig b/arch/sh/configs/secureedge5410_defconfig index 360592d63a2f..8422599cfb04 100644 --- a/arch/sh/configs/secureedge5410_defconfig +++ b/arch/sh/configs/secureedge5410_defconfig @@ -1,7 +1,6 @@ # CONFIG_SWAP is not set CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_HOTPLUG is not set CONFIG_SLAB=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index 87db9a84b5ec..f0073ed39947 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -3,7 +3,6 @@ CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=m diff --git a/arch/sh/configs/sh7710voipgw_defconfig b/arch/sh/configs/sh7710voipgw_defconfig index 08426913c0e3..0d814770b07f 100644 --- a/arch/sh/configs/sh7710voipgw_defconfig +++ b/arch/sh/configs/sh7710voipgw_defconfig @@ -2,7 +2,6 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_FUTEX is not set # CONFIG_EPOLL is not set # CONFIG_SHMEM is not set diff --git a/arch/sh/configs/sh7757lcr_defconfig b/arch/sh/configs/sh7757lcr_defconfig index d0933a9b9799..a2700ab165af 100644 --- a/arch/sh/configs/sh7757lcr_defconfig +++ b/arch/sh/configs/sh7757lcr_defconfig @@ -8,7 +8,6 @@ CONFIG_TASK_XACCT=y CONFIG_TASK_IO_ACCOUNTING=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_KALLSYMS_ALL=y CONFIG_SLAB=y CONFIG_MODULES=y diff --git a/arch/sh/configs/sh7763rdp_defconfig b/arch/sh/configs/sh7763rdp_defconfig index d0a0aa74cecf..26c5fd02c87a 100644 --- a/arch/sh/configs/sh7763rdp_defconfig +++ b/arch/sh/configs/sh7763rdp_defconfig @@ -5,7 +5,6 @@ CONFIG_LOG_BUF_SHIFT=14 CONFIG_NAMESPACES=y CONFIG_UTS_NS=y CONFIG_IPC_NS=y -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_PROFILING=y CONFIG_OPROFILE=y diff --git a/arch/sh/configs/shmin_defconfig b/arch/sh/configs/shmin_defconfig index a27b129b93c5..c0b6f40d01cc 100644 --- a/arch/sh/configs/shmin_defconfig +++ b/arch/sh/configs/shmin_defconfig @@ -1,7 +1,6 @@ # CONFIG_SWAP is not set CONFIG_LOG_BUF_SHIFT=14 # CONFIG_UID16 is not set -# CONFIG_SYSCTL_SYSCALL is not set # CONFIG_KALLSYMS is not set # CONFIG_HOTPLUG is not set # CONFIG_BUG is not set diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig index 4ec961ace688..ba887f1351be 100644 --- a/arch/sh/configs/titan_defconfig +++ b/arch/sh/configs/titan_defconfig @@ -6,7 +6,6 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=16 CONFIG_BLK_DEV_INITRD=y # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -# CONFIG_SYSCTL_SYSCALL is not set CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y diff --git a/arch/sh/drivers/pci/Makefile b/arch/sh/drivers/pci/Makefile index a5c1e9066f83..d313fd3ce709 100644 --- a/arch/sh/drivers/pci/Makefile +++ b/arch/sh/drivers/pci/Makefile @@ -25,4 +25,3 @@ obj-$(CONFIG_SH_7780_SOLUTION_ENGINE) += fixups-sdk7780.o obj-$(CONFIG_SH_TITAN) += fixups-titan.o obj-$(CONFIG_SH_LANDISK) += fixups-landisk.o obj-$(CONFIG_SH_LBOX_RE2) += fixups-rts7751r2d.o -obj-$(CONFIG_SH_CAYMAN) += fixups-cayman.o diff --git a/arch/sh/drivers/pci/common.c b/arch/sh/drivers/pci/common.c index fe163ecd0719..2fd2b77e12ce 100644 --- a/arch/sh/drivers/pci/common.c +++ b/arch/sh/drivers/pci/common.c @@ -54,7 +54,7 @@ int __init pci_is_66mhz_capable(struct pci_channel *hose, int cap66 = -1; u16 stat; - printk(KERN_INFO "PCI: Checking 66MHz capabilities...\n"); + pr_info("PCI: Checking 66MHz capabilities...\n"); for (pci_devfn = 0; pci_devfn < 0xff; pci_devfn++) { if (PCI_FUNC(pci_devfn)) @@ -134,7 +134,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr, pcibios_report_status(PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_SIG_TARGET_ABORT | PCI_STATUS_REC_MASTER_ABORT, 1); - printk("\n"); + pr_cont("\n"); cmd |= PCI_STATUS_REC_TARGET_ABORT; } @@ -143,7 +143,7 @@ unsigned int pcibios_handle_status_errors(unsigned long addr, printk(KERN_DEBUG "PCI: parity error detected: "); pcibios_report_status(PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY, 1); - printk("\n"); + pr_cont("\n"); cmd |= PCI_STATUS_PARITY | PCI_STATUS_DETECTED_PARITY; diff --git a/arch/sh/drivers/pci/fixups-cayman.c b/arch/sh/drivers/pci/fixups-cayman.c deleted file mode 100644 index c797bfbe2e98..000000000000 --- a/arch/sh/drivers/pci/fixups-cayman.c +++ /dev/null @@ -1,78 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/pci.h> -#include <linux/types.h> -#include <cpu/irq.h> -#include "pci-sh5.h" - -int pcibios_map_platform_irq(const struct pci_dev *dev, u8 slot, u8 pin) -{ - int result = -1; - - /* The complication here is that the PCI IRQ lines from the Cayman's 2 - 5V slots get into the CPU via a different path from the IRQ lines - from the 3 3.3V slots. Thus, we have to detect whether the card's - interrupts go via the 5V or 3.3V path, i.e. the 'bridge swizzling' - at the point where we cross from 5V to 3.3V is not the normal case. - - The added complication is that we don't know that the 5V slots are - always bus 2, because a card containing a PCI-PCI bridge may be - plugged into a 3.3V slot, and this changes the bus numbering. - - Also, the Cayman has an intermediate PCI bus that goes a custom - expansion board header (and to the secondary bridge). This bus has - never been used in practice. - - The 1ary onboard PCI-PCI bridge is device 3 on bus 0 - The 2ary onboard PCI-PCI bridge is device 0 on the 2ary bus of - the 1ary bridge. - */ - - struct slot_pin { - int slot; - int pin; - } path[4]; - int i=0; - - while (dev->bus->number > 0) { - - slot = path[i].slot = PCI_SLOT(dev->devfn); - pin = path[i].pin = pci_swizzle_interrupt_pin(dev, pin); - dev = dev->bus->self; - i++; - if (i > 3) panic("PCI path to root bus too long!\n"); - } - - slot = PCI_SLOT(dev->devfn); - /* This is the slot on bus 0 through which the device is eventually - reachable. */ - - /* Now work back up. */ - if ((slot < 3) || (i == 0)) { - /* Bus 0 (incl. PCI-PCI bridge itself) : perform the final - swizzle now. */ - result = IRQ_INTA + pci_swizzle_interrupt_pin(dev, pin) - 1; - } else { - i--; - slot = path[i].slot; - pin = path[i].pin; - if (slot > 0) { - panic("PCI expansion bus device found - not handled!\n"); - } else { - if (i > 0) { - /* 5V slots */ - i--; - slot = path[i].slot; - pin = path[i].pin; - /* 'pin' was swizzled earlier wrt slot, don't do it again. */ - result = IRQ_P2INTA + (pin - 1); - } else { - /* IRQ for 2ary PCI-PCI bridge : unused */ - result = -1; - } - } - } - - return result; -} diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c index 287b3a68570c..9a624a6ee354 100644 --- a/arch/sh/drivers/pci/pci-sh7780.c +++ b/arch/sh/drivers/pci/pci-sh7780.c @@ -148,7 +148,7 @@ static irqreturn_t sh7780_pci_serr_irq(int irq, void *dev_id) printk(KERN_DEBUG "PCI: system error received: "); pcibios_report_status(PCI_STATUS_SIG_SYSTEM_ERROR, 1); - printk("\n"); + pr_cont("\n"); /* Deassert SERR */ __raw_writel(SH4_PCIINTM_SDIM, hose->reg_base + SH4_PCIINTM); @@ -179,7 +179,7 @@ static int __init sh7780_pci_setup_irqs(struct pci_channel *hose) ret = request_irq(hose->serr_irq, sh7780_pci_serr_irq, 0, "PCI SERR interrupt", hose); if (unlikely(ret)) { - printk(KERN_ERR "PCI: Failed hooking SERR IRQ\n"); + pr_err("PCI: Failed hooking SERR IRQ\n"); return ret; } @@ -250,7 +250,7 @@ static int __init sh7780_pci_init(void) const char *type; int ret, i; - printk(KERN_NOTICE "PCI: Starting initialization.\n"); + pr_notice("PCI: Starting initialization.\n"); chan->reg_base = 0xfe040000; @@ -270,7 +270,7 @@ static int __init sh7780_pci_init(void) id = __raw_readw(chan->reg_base + PCI_VENDOR_ID); if (id != PCI_VENDOR_ID_RENESAS) { - printk(KERN_ERR "PCI: Unknown vendor ID 0x%04x.\n", id); + pr_err("PCI: Unknown vendor ID 0x%04x.\n", id); return -ENODEV; } @@ -281,14 +281,13 @@ static int __init sh7780_pci_init(void) (id == PCI_DEVICE_ID_RENESAS_SH7785) ? "SH7785" : NULL; if (unlikely(!type)) { - printk(KERN_ERR "PCI: Found an unsupported Renesas host " - "controller, device id 0x%04x.\n", id); + pr_err("PCI: Found an unsupported Renesas host controller, device id 0x%04x.\n", + id); return -EINVAL; } - printk(KERN_NOTICE "PCI: Found a Renesas %s host " - "controller, revision %d.\n", type, - __raw_readb(chan->reg_base + PCI_REVISION_ID)); + pr_notice("PCI: Found a Renesas %s host controller, revision %d.\n", + type, __raw_readb(chan->reg_base + PCI_REVISION_ID)); /* * Now throw it in to register initialization mode and @@ -395,9 +394,9 @@ static int __init sh7780_pci_init(void) sh7780_pci66_init(chan); - printk(KERN_NOTICE "PCI: Running at %dMHz.\n", - (__raw_readw(chan->reg_base + PCI_STATUS) & PCI_STATUS_66MHZ) ? - 66 : 33); + pr_notice("PCI: Running at %dMHz.\n", + (__raw_readw(chan->reg_base + PCI_STATUS) & PCI_STATUS_66MHZ) + ? 66 : 33); return 0; diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index c7784e156964..6ab0b7377f66 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -120,8 +120,7 @@ int register_pci_controller(struct pci_channel *hose) * Do not panic here but later - this might happen before console init. */ if (!hose->io_map_base) { - printk(KERN_WARNING - "registering PCI controller with io_map_base unset\n"); + pr_warn("registering PCI controller with io_map_base unset\n"); } /* @@ -145,7 +144,7 @@ out: for (--i; i >= 0; i--) release_resource(&hose->resources[i]); - printk(KERN_WARNING "Skipping PCI bus scan due to resource conflict\n"); + pr_warn("Skipping PCI bus scan due to resource conflict\n"); return -1; } @@ -213,8 +212,8 @@ pcibios_bus_report_status_early(struct pci_channel *hose, pci_devfn, PCI_STATUS, status & status_mask); if (warn) - printk("(%02x:%02x: %04X) ", current_bus, - pci_devfn, status); + pr_cont("(%02x:%02x: %04X) ", current_bus, pci_devfn, + status); } } @@ -249,7 +248,7 @@ pcibios_bus_report_status(struct pci_bus *bus, unsigned int status_mask, pci_write_config_word(dev, PCI_STATUS, status & status_mask); if (warn) - printk("(%s: %04X) ", pci_name(dev), status); + pr_cont("(%s: %04X) ", pci_name(dev), status); } list_for_each_entry(dev, &bus->devices, bus_list) diff --git a/arch/sh/include/asm/adc.h b/arch/sh/include/asm/adc.h index 99ec66849559..feccfe639e38 100644 --- a/arch/sh/include/asm/adc.h +++ b/arch/sh/include/asm/adc.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_ADC_H #define __ASM_ADC_H -#ifdef __KERNEL__ /* * Copyright (C) 2004 Andriy Skulysh */ @@ -10,5 +9,4 @@ int adc_single(unsigned int channel); -#endif /* __KERNEL__ */ #endif /* __ASM_ADC_H */ diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h index 34bfbcddcce0..468fba333e89 100644 --- a/arch/sh/include/asm/addrspace.h +++ b/arch/sh/include/asm/addrspace.h @@ -7,8 +7,6 @@ #ifndef __ASM_SH_ADDRSPACE_H #define __ASM_SH_ADDRSPACE_H -#ifdef __KERNEL__ - #include <cpu/addrspace.h> /* If this CPU supports segmentation, hook up the helpers */ @@ -62,5 +60,4 @@ #define P3_ADDR_MAX P4SEG #endif -#endif /* __KERNEL__ */ #endif /* __ASM_SH_ADDRSPACE_H */ diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h index 445dd14c448a..450b5854d7c6 100644 --- a/arch/sh/include/asm/bitops.h +++ b/arch/sh/include/asm/bitops.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_BITOPS_H #define __ASM_SH_BITOPS_H -#ifdef __KERNEL__ - #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly #endif @@ -71,6 +69,4 @@ static inline unsigned long __ffs(unsigned long word) #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/fls64.h> -#endif /* __KERNEL__ */ - #endif /* __ASM_SH_BITOPS_H */ diff --git a/arch/sh/include/asm/cache.h b/arch/sh/include/asm/cache.h index 2408ac4873aa..a293343456af 100644 --- a/arch/sh/include/asm/cache.h +++ b/arch/sh/include/asm/cache.h @@ -8,7 +8,6 @@ */ #ifndef __ASM_SH_CACHE_H #define __ASM_SH_CACHE_H -#ifdef __KERNEL__ #include <linux/init.h> #include <cpu/cache.h> @@ -44,5 +43,4 @@ struct cache_info { unsigned long flags; }; #endif /* __ASSEMBLY__ */ -#endif /* __KERNEL__ */ #endif /* __ASM_SH_CACHE_H */ diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index fe7400079b97..4486a865ff62 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_CACHEFLUSH_H #define __ASM_SH_CACHEFLUSH_H -#ifdef __KERNEL__ - #include <linux/mm.h> /* @@ -109,5 +107,4 @@ static inline void *sh_cacheop_vaddr(void *vaddr) return vaddr; } -#endif /* __KERNEL__ */ #endif /* __ASM_SH_CACHEFLUSH_H */ diff --git a/arch/sh/include/asm/dma.h b/arch/sh/include/asm/dma.h index 4d5a21a891c0..17d23ae98c77 100644 --- a/arch/sh/include/asm/dma.h +++ b/arch/sh/include/asm/dma.h @@ -6,7 +6,6 @@ */ #ifndef __ASM_SH_DMA_H #define __ASM_SH_DMA_H -#ifdef __KERNEL__ #include <linux/spinlock.h> #include <linux/wait.h> @@ -144,5 +143,4 @@ extern int isa_dma_bridge_buggy; #define isa_dma_bridge_buggy (0) #endif -#endif /* __KERNEL__ */ #endif /* __ASM_SH_DMA_H */ diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h index 7661fb5d548a..2862d6d1cb64 100644 --- a/arch/sh/include/asm/elf.h +++ b/arch/sh/include/asm/elf.h @@ -90,7 +90,6 @@ typedef struct user_fpu_struct elf_fpregset_t; #endif #define ELF_ARCH EM_SH -#ifdef __KERNEL__ /* * This is used to ensure we don't load something for the wrong architecture. */ @@ -209,5 +208,4 @@ do { \ NEW_AUX_ENT(AT_L2_CACHESHAPE, l2_cache_shape); \ } while (0) -#endif /* __KERNEL__ */ #endif /* __ASM_SH_ELF_H */ diff --git a/arch/sh/include/asm/fpu.h b/arch/sh/include/asm/fpu.h index 43cfaf929aa7..04584be8986c 100644 --- a/arch/sh/include/asm/fpu.h +++ b/arch/sh/include/asm/fpu.h @@ -37,11 +37,6 @@ struct user_regset; extern int do_fpu_inst(unsigned short, struct pt_regs *); extern int init_fpu(struct task_struct *); -extern int fpregs_get(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf); - static inline void __unlazy_fpu(struct task_struct *tsk, struct pt_regs *regs) { if (task_thread_info(tsk)->status & TS_USEDFPU) { diff --git a/arch/sh/include/asm/freq.h b/arch/sh/include/asm/freq.h index 18133bf83738..87c23621b7ae 100644 --- a/arch/sh/include/asm/freq.h +++ b/arch/sh/include/asm/freq.h @@ -6,9 +6,7 @@ */ #ifndef __ASM_SH_FREQ_H #define __ASM_SH_FREQ_H -#ifdef __KERNEL__ #include <cpu/freq.h> -#endif /* __KERNEL__ */ #endif /* __ASM_SH_FREQ_H */ diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h index b39cda09fb95..b70f3fce6ed7 100644 --- a/arch/sh/include/asm/futex.h +++ b/arch/sh/include/asm/futex.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_FUTEX_H #define __ASM_SH_FUTEX_H -#ifdef __KERNEL__ - #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/errno.h> @@ -71,5 +69,4 @@ static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, return ret; } -#endif /* __KERNEL__ */ #endif /* __ASM_SH_FUTEX_H */ diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h index 26f0f9b4658b..6d5c6463bc07 100644 --- a/arch/sh/include/asm/io.h +++ b/arch/sh/include/asm/io.h @@ -17,13 +17,12 @@ #include <asm/cache.h> #include <asm/addrspace.h> #include <asm/machvec.h> +#include <asm/page.h> #include <linux/pgtable.h> #include <asm-generic/iomap.h> -#ifdef __KERNEL__ #define __IO_PREFIX generic #include <asm/io_generic.h> -#include <asm/io_trapped.h> #include <asm-generic/pci_iomap.h> #include <mach/mangle-port.h> @@ -243,125 +242,38 @@ unsigned long long poke_real_address_q(unsigned long long addr, #define phys_to_virt(address) (__va(address)) #endif -/* - * On 32-bit SH, we traditionally have the whole physical address space - * mapped at all times (as MIPS does), so "ioremap()" and "iounmap()" do - * not need to do anything but place the address in the proper segment. - * This is true for P1 and P2 addresses, as well as some P3 ones. - * However, most of the P3 addresses and newer cores using extended - * addressing need to map through page tables, so the ioremap() - * implementation becomes a bit more complicated. - * - * See arch/sh/mm/ioremap.c for additional notes on this. - * - * We cheat a bit and always return uncachable areas until we've fixed - * the drivers to handle caching properly. - * - * On the SH-5 the concept of segmentation in the 1:1 PXSEG sense simply - * doesn't exist, so everything must go through page tables. - */ #ifdef CONFIG_MMU +void iounmap(void __iomem *addr); void __iomem *__ioremap_caller(phys_addr_t offset, unsigned long size, pgprot_t prot, void *caller); -void iounmap(void __iomem *addr); - -static inline void __iomem * -__ioremap(phys_addr_t offset, unsigned long size, pgprot_t prot) -{ - return __ioremap_caller(offset, size, prot, __builtin_return_address(0)); -} - -static inline void __iomem * -__ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) -{ -#ifdef CONFIG_29BIT - phys_addr_t last_addr = offset + size - 1; - - /* - * For P1 and P2 space this is trivial, as everything is already - * mapped. Uncached access for P1 addresses are done through P2. - * In the P3 case or for addresses outside of the 29-bit space, - * mapping must be done by the PMB or by using page tables. - */ - if (likely(PXSEG(offset) < P3SEG && PXSEG(last_addr) < P3SEG)) { - u64 flags = pgprot_val(prot); - - /* - * Anything using the legacy PTEA space attributes needs - * to be kicked down to page table mappings. - */ - if (unlikely(flags & _PAGE_PCC_MASK)) - return NULL; - if (unlikely(flags & _PAGE_CACHABLE)) - return (void __iomem *)P1SEGADDR(offset); - - return (void __iomem *)P2SEGADDR(offset); - } - - /* P4 above the store queues are always mapped. */ - if (unlikely(offset >= P3_ADDR_MAX)) - return (void __iomem *)P4SEGADDR(offset); -#endif - - return NULL; -} - -static inline void __iomem * -__ioremap_mode(phys_addr_t offset, unsigned long size, pgprot_t prot) -{ - void __iomem *ret; - - ret = __ioremap_trapped(offset, size); - if (ret) - return ret; - - ret = __ioremap_29bit(offset, size, prot); - if (ret) - return ret; - - return __ioremap(offset, size, prot); -} -#else -#define __ioremap(offset, size, prot) ((void __iomem *)(offset)) -#define __ioremap_mode(offset, size, prot) ((void __iomem *)(offset)) -static inline void iounmap(void __iomem *addr) {} -#endif /* CONFIG_MMU */ static inline void __iomem *ioremap(phys_addr_t offset, unsigned long size) { - return __ioremap_mode(offset, size, PAGE_KERNEL_NOCACHE); + return __ioremap_caller(offset, size, PAGE_KERNEL_NOCACHE, + __builtin_return_address(0)); } static inline void __iomem * ioremap_cache(phys_addr_t offset, unsigned long size) { - return __ioremap_mode(offset, size, PAGE_KERNEL); + return __ioremap_caller(offset, size, PAGE_KERNEL, + __builtin_return_address(0)); } #define ioremap_cache ioremap_cache #ifdef CONFIG_HAVE_IOREMAP_PROT -static inline void __iomem * -ioremap_prot(phys_addr_t offset, unsigned long size, unsigned long flags) +static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, + unsigned long flags) { - return __ioremap_mode(offset, size, __pgprot(flags)); + return __ioremap_caller(offset, size, __pgprot(flags), + __builtin_return_address(0)); } -#endif +#endif /* CONFIG_HAVE_IOREMAP_PROT */ -#ifdef CONFIG_IOREMAP_FIXED -extern void __iomem *ioremap_fixed(phys_addr_t, unsigned long, pgprot_t); -extern int iounmap_fixed(void __iomem *); -extern void ioremap_fixed_init(void); -#else -static inline void __iomem * -ioremap_fixed(phys_addr_t phys_addr, unsigned long size, pgprot_t prot) -{ - BUG(); - return NULL; -} - -static inline void ioremap_fixed_init(void) { } -static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } -#endif +#else /* CONFIG_MMU */ +#define iounmap(addr) do { } while (0) +#define ioremap(offset, size) ((void __iomem *)(unsigned long)(offset)) +#endif /* CONFIG_MMU */ #define ioremap_uc ioremap @@ -380,6 +292,4 @@ static inline int iounmap_fixed(void __iomem *addr) { return -EINVAL; } int valid_phys_addr_range(phys_addr_t addr, size_t size); int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); -#endif /* __KERNEL__ */ - #endif /* __ASM_SH_IO_H */ diff --git a/arch/sh/include/asm/kdebug.h b/arch/sh/include/asm/kdebug.h index 960545306afa..de8693fabb1d 100644 --- a/arch/sh/include/asm/kdebug.h +++ b/arch/sh/include/asm/kdebug.h @@ -12,8 +12,7 @@ enum die_val { }; /* arch/sh/kernel/dumpstack.c */ -extern void printk_address(unsigned long address, int reliable, - const char *loglvl); +extern void printk_address(unsigned long address, int reliable); extern void dump_mem(const char *str, const char *loglvl, unsigned long bottom, unsigned long top); diff --git a/arch/sh/include/asm/mmu_context.h b/arch/sh/include/asm/mmu_context.h index 48e67d544d53..f664e51e8a15 100644 --- a/arch/sh/include/asm/mmu_context.h +++ b/arch/sh/include/asm/mmu_context.h @@ -8,7 +8,6 @@ #ifndef __ASM_SH_MMU_CONTEXT_H #define __ASM_SH_MMU_CONTEXT_H -#ifdef __KERNEL__ #include <cpu/mmu_context.h> #include <asm/tlbflush.h> #include <linux/uaccess.h> @@ -177,5 +176,4 @@ static inline void disable_mmu(void) #define disable_mmu() do { } while (0) #endif -#endif /* __KERNEL__ */ #endif /* __ASM_SH_MMU_CONTEXT_H */ diff --git a/arch/sh/include/asm/mmzone.h b/arch/sh/include/asm/mmzone.h index cbaee1d1b673..6552a088dc97 100644 --- a/arch/sh/include/asm/mmzone.h +++ b/arch/sh/include/asm/mmzone.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_MMZONE_H #define __ASM_SH_MMZONE_H -#ifdef __KERNEL__ - #ifdef CONFIG_NEED_MULTIPLE_NODES #include <linux/numa.h> @@ -44,5 +42,4 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, /* arch/sh/mm/init.c */ void __init allocate_pgdat(unsigned int nid); -#endif /* __KERNEL__ */ #endif /* __ASM_SH_MMZONE_H */ diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h index 10a36b1cf2ea..ad22e88c6657 100644 --- a/arch/sh/include/asm/pci.h +++ b/arch/sh/include/asm/pci.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_PCI_H #define __ASM_SH_PCI_H -#ifdef __KERNEL__ - /* Can be used to override the logic in pci_scan_bus for skipping already-configured bus numbers - to be used for buggy BIOSes or architectures with incomplete PCI setup by the loader */ @@ -96,6 +94,4 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) return channel ? 15 : 14; } -#endif /* __KERNEL__ */ #endif /* __ASM_SH_PCI_H */ - diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h index d770da3f8b6f..0e6b0be25e33 100644 --- a/arch/sh/include/asm/pgalloc.h +++ b/arch/sh/include/asm/pgalloc.h @@ -3,6 +3,10 @@ #define __ASM_SH_PGALLOC_H #include <asm/page.h> + +#define __HAVE_ARCH_PMD_ALLOC_ONE +#define __HAVE_ARCH_PMD_FREE +#define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> extern pgd_t *pgd_alloc(struct mm_struct *); diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index d44409413418..aa92cc933889 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -8,7 +8,6 @@ #ifndef __ASM_SH_PROCESSOR_32_H #define __ASM_SH_PROCESSOR_32_H -#ifdef __KERNEL__ #include <linux/compiler.h> #include <linux/linkage.h> @@ -203,5 +202,4 @@ static inline void prefetchw(const void *x) } #endif -#endif /* __KERNEL__ */ #endif /* __ASM_SH_PROCESSOR_32_H */ diff --git a/arch/sh/include/asm/segment.h b/arch/sh/include/asm/segment.h index 33d1d28057cb..02e54a3335d6 100644 --- a/arch/sh/include/asm/segment.h +++ b/arch/sh/include/asm/segment.h @@ -24,8 +24,7 @@ typedef struct { #define USER_DS KERNEL_DS #endif -#define segment_eq(a, b) ((a).seg == (b).seg) - +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define get_fs() (current_thread_info()->addr_limit) #define set_fs(x) (current_thread_info()->addr_limit = (x)) diff --git a/arch/sh/include/asm/smc37c93x.h b/arch/sh/include/asm/smc37c93x.h index f054c30a171a..891f2f8f2fd0 100644 --- a/arch/sh/include/asm/smc37c93x.h +++ b/arch/sh/include/asm/smc37c93x.h @@ -112,8 +112,8 @@ typedef struct uart_reg { #define FCR_RFRES 0x0200 /* Receiver FIFO reset */ #define FCR_TFRES 0x0400 /* Transmitter FIFO reset */ #define FCR_DMA 0x0800 /* DMA mode select */ -#define FCR_RTL 0x4000 /* Receiver triger (LSB) */ -#define FCR_RTM 0x8000 /* Receiver triger (MSB) */ +#define FCR_RTL 0x4000 /* Receiver trigger (LSB) */ +#define FCR_RTM 0x8000 /* Receiver trigger (MSB) */ /* Line Control Register */ diff --git a/arch/sh/include/asm/sparsemem.h b/arch/sh/include/asm/sparsemem.h index 4eb899751e45..4703cbe23844 100644 --- a/arch/sh/include/asm/sparsemem.h +++ b/arch/sh/include/asm/sparsemem.h @@ -2,16 +2,11 @@ #ifndef __ASM_SH_SPARSEMEM_H #define __ASM_SH_SPARSEMEM_H -#ifdef __KERNEL__ /* * SECTION_SIZE_BITS 2^N: how big each section will be - * MAX_PHYSADDR_BITS 2^N: how much physical address space we have - * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space + * MAX_PHYSMEM_BITS 2^N: how much physical address space we have */ #define SECTION_SIZE_BITS 26 -#define MAX_PHYSADDR_BITS 32 #define MAX_PHYSMEM_BITS 32 -#endif - #endif /* __ASM_SH_SPARSEMEM_H */ diff --git a/arch/sh/include/asm/stacktrace.h b/arch/sh/include/asm/stacktrace.h index 50c173c0b9f5..4f98cdc64ec5 100644 --- a/arch/sh/include/asm/stacktrace.h +++ b/arch/sh/include/asm/stacktrace.h @@ -12,8 +12,6 @@ struct stacktrace_ops { void (*address)(void *data, unsigned long address, int reliable); - /* On negative return stop dumping */ - int (*stack)(void *data, char *name); }; void dump_trace(struct task_struct *tsk, struct pt_regs *regs, diff --git a/arch/sh/include/asm/string_32.h b/arch/sh/include/asm/string_32.h index 3558b1d7123e..a276b193d3b4 100644 --- a/arch/sh/include/asm/string_32.h +++ b/arch/sh/include/asm/string_32.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_STRING_H #define __ASM_SH_STRING_H -#ifdef __KERNEL__ - /* * Copyright (C) 1999 Niibe Yutaka * But consider these trivial functions to be public domain. @@ -28,32 +26,6 @@ static inline char *strcpy(char *__dest, const char *__src) return __xdest; } -#define __HAVE_ARCH_STRNCPY -static inline char *strncpy(char *__dest, const char *__src, size_t __n) -{ - register char *__xdest = __dest; - unsigned long __dummy; - - if (__n == 0) - return __xdest; - - __asm__ __volatile__( - "1:\n" - "mov.b @%1+, %2\n\t" - "mov.b %2, @%0\n\t" - "cmp/eq #0, %2\n\t" - "bt/s 2f\n\t" - " cmp/eq %5,%1\n\t" - "bf/s 1b\n\t" - " add #1, %0\n" - "2:" - : "=r" (__dest), "=r" (__src), "=&z" (__dummy) - : "0" (__dest), "1" (__src), "r" (__src+__n) - : "memory", "t"); - - return __xdest; -} - #define __HAVE_ARCH_STRCMP static inline int strcmp(const char *__cs, const char *__ct) { @@ -127,6 +99,4 @@ extern void *memchr(const void *__s, int __c, size_t __n); #define __HAVE_ARCH_STRLEN extern size_t strlen(const char *); -#endif /* __KERNEL__ */ - #endif /* __ASM_SH_STRING_H */ diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h index 0b5b8e75edac..cb51a7528384 100644 --- a/arch/sh/include/asm/syscall_32.h +++ b/arch/sh/include/asm/syscall_32.h @@ -40,10 +40,7 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - if (error) - regs->regs[0] = -error; - else - regs->regs[0] = val; + regs->regs[0] = (long) error ?: val; } static inline void syscall_get_arguments(struct task_struct *task, diff --git a/arch/sh/include/asm/syscalls_32.h b/arch/sh/include/asm/syscalls_32.h index 9f9faf63b48c..5c555b864fe0 100644 --- a/arch/sh/include/asm/syscalls_32.h +++ b/arch/sh/include/asm/syscalls_32.h @@ -2,8 +2,6 @@ #ifndef __ASM_SH_SYSCALLS_32_H #define __ASM_SH_SYSCALLS_32_H -#ifdef __KERNEL__ - #include <linux/compiler.h> #include <linux/linkage.h> #include <linux/types.h> @@ -26,5 +24,4 @@ asmlinkage void do_syscall_trace_leave(struct pt_regs *regs); asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned int save_r0, unsigned long thread_info_flags); -#endif /* __KERNEL__ */ #endif /* __ASM_SH_SYSCALLS_32_H */ diff --git a/arch/sh/include/asm/thread_info.h b/arch/sh/include/asm/thread_info.h index 6404be69d5fa..243ea5150aa0 100644 --- a/arch/sh/include/asm/thread_info.h +++ b/arch/sh/include/asm/thread_info.h @@ -10,8 +10,6 @@ * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds and Dave Miller */ -#ifdef __KERNEL__ - #include <asm/page.h> /* @@ -170,7 +168,4 @@ static inline unsigned int get_thread_fault_code(void) } #endif /* !__ASSEMBLY__ */ - -#endif /* __KERNEL__ */ - #endif /* __ASM_SH_THREAD_INFO_H */ diff --git a/arch/sh/include/asm/uaccess_32.h b/arch/sh/include/asm/uaccess_32.h index 624cf55acc27..5d7ddc092afd 100644 --- a/arch/sh/include/asm/uaccess_32.h +++ b/arch/sh/include/asm/uaccess_32.h @@ -26,6 +26,9 @@ do { \ case 4: \ __get_user_asm(x, ptr, retval, "l"); \ break; \ + case 8: \ + __get_user_u64(x, ptr, retval); \ + break; \ default: \ __get_user_unknown(); \ break; \ @@ -66,6 +69,56 @@ do { \ extern void __get_user_unknown(void); +#if defined(CONFIG_CPU_LITTLE_ENDIAN) +#define __get_user_u64(x, addr, err) \ +({ \ +__asm__ __volatile__( \ + "1:\n\t" \ + "mov.l %2,%R1\n\t" \ + "mov.l %T2,%S1\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3:\n\t" \ + "mov #0,%R1\n\t" \ + "mov #0,%S1\n\t" \ + "mov.l 4f, %0\n\t" \ + "jmp @%0\n\t" \ + " mov %3, %0\n\t" \ + ".balign 4\n" \ + "4: .long 2b\n\t" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n\t" \ + ".long 1b, 3b\n\t" \ + ".long 1b + 2, 3b\n\t" \ + ".previous" \ + :"=&r" (err), "=&r" (x) \ + :"m" (__m(addr)), "i" (-EFAULT), "0" (err)); }) +#else +#define __get_user_u64(x, addr, err) \ +({ \ +__asm__ __volatile__( \ + "1:\n\t" \ + "mov.l %2,%S1\n\t" \ + "mov.l %T2,%R1\n\t" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3:\n\t" \ + "mov #0,%S1\n\t" \ + "mov #0,%R1\n\t" \ + "mov.l 4f, %0\n\t" \ + "jmp @%0\n\t" \ + " mov %3, %0\n\t" \ + ".balign 4\n" \ + "4: .long 2b\n\t" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n\t" \ + ".long 1b, 3b\n\t" \ + ".long 1b + 2, 3b\n\t" \ + ".previous" \ + :"=&r" (err), "=&r" (x) \ + :"m" (__m(addr)), "i" (-EFAULT), "0" (err)); }) +#endif + #define __put_user_size(x,ptr,size,retval) \ do { \ retval = 0; \ diff --git a/arch/sh/include/asm/watchdog.h b/arch/sh/include/asm/watchdog.h index cecd0fc507f9..b9ca4c99f046 100644 --- a/arch/sh/include/asm/watchdog.h +++ b/arch/sh/include/asm/watchdog.h @@ -8,7 +8,6 @@ */ #ifndef __ASM_SH_WATCHDOG_H #define __ASM_SH_WATCHDOG_H -#ifdef __KERNEL__ #include <linux/types.h> #include <linux/io.h> @@ -157,5 +156,4 @@ static inline void sh_wdt_write_csr(__u8 val) __raw_writew((WTCSR_HIGH << 8) | (__u16)val, WTCSR); } #endif /* CONFIG_CPU_SUBTYPE_SH7785 || CONFIG_CPU_SUBTYPE_SH7780 */ -#endif /* __KERNEL__ */ #endif /* __ASM_SH_WATCHDOG_H */ diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile index b0f5574b6228..aa0fbc9202b1 100644 --- a/arch/sh/kernel/Makefile +++ b/arch/sh/kernel/Makefile @@ -47,5 +47,3 @@ obj-$(CONFIG_DWARF_UNWINDER) += dwarf.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_callchain.o obj-$(CONFIG_DMA_NONCOHERENT) += dma-coherent.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o - -ccflags-y := -Werror diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c index 845543780cc5..08e1af63edd9 100644 --- a/arch/sh/kernel/disassemble.c +++ b/arch/sh/kernel/disassemble.c @@ -376,148 +376,148 @@ static void print_sh_insn(u32 memaddr, u16 insn) } ok: - printk("%-8s ", op->name); + pr_cont("%-8s ", op->name); lastsp = (op->arg[0] == A_END); disp_pc = 0; for (n = 0; n < 6 && op->arg[n] != A_END; n++) { if (n && op->arg[1] != A_END) - printk(", "); + pr_cont(", "); switch (op->arg[n]) { case A_IMM: - printk("#%d", (char)(imm)); + pr_cont("#%d", (char)(imm)); break; case A_R0: - printk("r0"); + pr_cont("r0"); break; case A_REG_N: - printk("r%d", rn); + pr_cont("r%d", rn); break; case A_INC_N: - printk("@r%d+", rn); + pr_cont("@r%d+", rn); break; case A_DEC_N: - printk("@-r%d", rn); + pr_cont("@-r%d", rn); break; case A_IND_N: - printk("@r%d", rn); + pr_cont("@r%d", rn); break; case A_DISP_REG_N: - printk("@(%d,r%d)", imm, rn); + pr_cont("@(%d,r%d)", imm, rn); break; case A_REG_M: - printk("r%d", rm); + pr_cont("r%d", rm); break; case A_INC_M: - printk("@r%d+", rm); + pr_cont("@r%d+", rm); break; case A_DEC_M: - printk("@-r%d", rm); + pr_cont("@-r%d", rm); break; case A_IND_M: - printk("@r%d", rm); + pr_cont("@r%d", rm); break; case A_DISP_REG_M: - printk("@(%d,r%d)", imm, rm); + pr_cont("@(%d,r%d)", imm, rm); break; case A_REG_B: - printk("r%d_bank", rb); + pr_cont("r%d_bank", rb); break; case A_DISP_PC: disp_pc = 1; disp_pc_addr = imm + 4 + (memaddr & relmask); - printk("%08x <%pS>", disp_pc_addr, - (void *)disp_pc_addr); + pr_cont("%08x <%pS>", disp_pc_addr, + (void *)disp_pc_addr); break; case A_IND_R0_REG_N: - printk("@(r0,r%d)", rn); + pr_cont("@(r0,r%d)", rn); break; case A_IND_R0_REG_M: - printk("@(r0,r%d)", rm); + pr_cont("@(r0,r%d)", rm); break; case A_DISP_GBR: - printk("@(%d,gbr)",imm); + pr_cont("@(%d,gbr)", imm); break; case A_R0_GBR: - printk("@(r0,gbr)"); + pr_cont("@(r0,gbr)"); break; case A_BDISP12: case A_BDISP8: - printk("%08x", imm + memaddr); + pr_cont("%08x", imm + memaddr); break; case A_SR: - printk("sr"); + pr_cont("sr"); break; case A_GBR: - printk("gbr"); + pr_cont("gbr"); break; case A_VBR: - printk("vbr"); + pr_cont("vbr"); break; case A_SSR: - printk("ssr"); + pr_cont("ssr"); break; case A_SPC: - printk("spc"); + pr_cont("spc"); break; case A_MACH: - printk("mach"); + pr_cont("mach"); break; case A_MACL: - printk("macl"); + pr_cont("macl"); break; case A_PR: - printk("pr"); + pr_cont("pr"); break; case A_SGR: - printk("sgr"); + pr_cont("sgr"); break; case A_DBR: - printk("dbr"); + pr_cont("dbr"); break; case FD_REG_N: case F_REG_N: - printk("fr%d", rn); + pr_cont("fr%d", rn); break; case F_REG_M: - printk("fr%d", rm); + pr_cont("fr%d", rm); break; case DX_REG_N: if (rn & 1) { - printk("xd%d", rn & ~1); + pr_cont("xd%d", rn & ~1); break; } /* else, fall through */ case D_REG_N: - printk("dr%d", rn); + pr_cont("dr%d", rn); break; case DX_REG_M: if (rm & 1) { - printk("xd%d", rm & ~1); + pr_cont("xd%d", rm & ~1); break; } /* else, fall through */ case D_REG_M: - printk("dr%d", rm); + pr_cont("dr%d", rm); break; case FPSCR_M: case FPSCR_N: - printk("fpscr"); + pr_cont("fpscr"); break; case FPUL_M: case FPUL_N: - printk("fpul"); + pr_cont("fpul"); break; case F_FR0: - printk("fr0"); + pr_cont("fr0"); break; case V_REG_N: - printk("fv%d", rn*4); + pr_cont("fv%d", rn*4); break; case V_REG_M: - printk("fv%d", rm*4); + pr_cont("fv%d", rm*4); break; case XMTRX_M4: - printk("xmtrx"); + pr_cont("xmtrx"); break; default: return; @@ -532,7 +532,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) else __get_user(val, (u32 *)disp_pc_addr); - printk(" ! %08x <%pS>", val, (void *)val); + pr_cont(" ! %08x <%pS>", val, (void *)val); } return; @@ -541,7 +541,7 @@ static void print_sh_insn(u32 memaddr, u16 insn) } - printk(".word 0x%x%x%x%x", nibs[0], nibs[1], nibs[2], nibs[3]); + pr_info(".word 0x%x%x%x%x", nibs[0], nibs[1], nibs[2], nibs[3]); } void show_code(struct pt_regs *regs) @@ -552,20 +552,21 @@ void show_code(struct pt_regs *regs) if (regs->pc & 0x1) return; - printk("Code:\n"); + pr_info("Code:\n"); for (i = -3 ; i < 6 ; i++) { unsigned short insn; if (__get_user(insn, pc + i)) { - printk(" (Bad address in pc)\n"); + pr_err(" (Bad address in pc)\n"); break; } - printk("%s%08lx: ", (i ? " ": "->"), (unsigned long)(pc + i)); + pr_info("%s%08lx: ", (i ? " " : "->"), + (unsigned long)(pc + i)); print_sh_insn((unsigned long)(pc + i), insn); - printk("\n"); + pr_cont("\n"); } - printk("\n"); + pr_info("\n"); } diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c index d4811691b93c..cd46a9825e3c 100644 --- a/arch/sh/kernel/dma-coherent.c +++ b/arch/sh/kernel/dma-coherent.c @@ -3,60 +3,13 @@ * Copyright (C) 2004 - 2007 Paul Mundt */ #include <linux/mm.h> -#include <linux/init.h> #include <linux/dma-noncoherent.h> -#include <linux/module.h> #include <asm/cacheflush.h> #include <asm/addrspace.h> -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t gfp, unsigned long attrs) +void arch_dma_prep_coherent(struct page *page, size_t size) { - void *ret, *ret_nocache; - int order = get_order(size); - - gfp |= __GFP_ZERO; - - ret = (void *)__get_free_pages(gfp, order); - if (!ret) - return NULL; - - /* - * Pages from the page allocator may have data present in - * cache. So flush the cache before using uncached memory. - */ - arch_sync_dma_for_device(virt_to_phys(ret), size, - DMA_BIDIRECTIONAL); - - ret_nocache = (void __force *)ioremap(virt_to_phys(ret), size); - if (!ret_nocache) { - free_pages((unsigned long)ret, order); - return NULL; - } - - split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order); - - *dma_handle = virt_to_phys(ret); - if (!WARN_ON(!dev)) - *dma_handle -= PFN_PHYS(dev->dma_pfn_offset); - - return ret_nocache; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - int order = get_order(size); - unsigned long pfn = (dma_handle >> PAGE_SHIFT); - int k; - - if (!WARN_ON(!dev)) - pfn += dev->dma_pfn_offset; - - for (k = 0; k < (1 << order); k++) - __free_pages(pfn_to_page(pfn + k), 0); - - iounmap(vaddr); + __flush_purge_region(page_address(page), size); } void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, diff --git a/arch/sh/kernel/dumpstack.c b/arch/sh/kernel/dumpstack.c index a13c045804ed..758a6c89e911 100644 --- a/arch/sh/kernel/dumpstack.c +++ b/arch/sh/kernel/dumpstack.c @@ -16,8 +16,8 @@ #include <asm/unwinder.h> #include <asm/stacktrace.h> -void dump_mem(const char *str, const char *loglvl, - unsigned long bottom, unsigned long top) +void dump_mem(const char *str, const char *loglvl, unsigned long bottom, + unsigned long top) { unsigned long p; int i; @@ -31,23 +31,23 @@ void dump_mem(const char *str, const char *loglvl, unsigned int val; if (p < bottom || p >= top) - printk("%s ", loglvl); + pr_cont(" "); else { if (__get_user(val, (unsigned int __user *)p)) { - printk("%s\n", loglvl); + pr_cont("\n"); return; } - printk("%s%08x ", loglvl, val); + pr_cont("%08x ", val); } } - printk("%s\n", loglvl); + pr_cont("\n"); } } -void printk_address(unsigned long address, int reliable, const char *loglvl) +void printk_address(unsigned long address, int reliable) { - printk("%s [<%p>] %s%pS\n", loglvl, (void *) address, - reliable ? "" : "? ", (void *) address); + pr_cont(" [<%px>] %s%pS\n", (void *) address, + reliable ? "" : "? ", (void *) address); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -107,22 +107,16 @@ stack_reader_dump(struct task_struct *task, struct pt_regs *regs, } } -static int print_trace_stack(void *data, char *name) -{ - printk("%s <%s> ", (char *)data, name); - return 0; -} - /* * Print one address/symbol entries per line. */ static void print_trace_address(void *data, unsigned long addr, int reliable) { - printk_address(addr, reliable, (char *)data); + printk("%s", (char *)data); + printk_address(addr, reliable); } static const struct stacktrace_ops print_trace_ops = { - .stack = print_trace_stack, .address = print_trace_address, }; @@ -136,7 +130,7 @@ void show_trace(struct task_struct *tsk, unsigned long *sp, unwind_stack(tsk, regs, sp, &print_trace_ops, (void *)loglvl); - printk("%s\n", loglvl); + pr_cont("\n"); if (!tsk) tsk = current; diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S index 9bac5bbb67f3..ad963104d22d 100644 --- a/arch/sh/kernel/entry-common.S +++ b/arch/sh/kernel/entry-common.S @@ -178,34 +178,6 @@ syscall_exit_work: bra resume_userspace nop - .align 2 -syscall_trace_entry: - ! Yes it is traced. - mov r15, r4 - mov.l 7f, r11 ! Call do_syscall_trace_enter which notifies - jsr @r11 ! superior (will chomp R[0-7]) - nop - mov.l r0, @(OFF_R0,r15) ! Save return value - ! Reload R0-R4 from kernel stack, where the - ! parent may have modified them using - ! ptrace(POKEUSR). (Note that R0-R2 are - ! reloaded from the kernel stack by syscall_call - ! below, so don't need to be reloaded here.) - ! This allows the parent to rewrite system calls - ! and args on the fly. - mov.l @(OFF_R4,r15), r4 ! arg0 - mov.l @(OFF_R5,r15), r5 - mov.l @(OFF_R6,r15), r6 - mov.l @(OFF_R7,r15), r7 ! arg3 - mov.l @(OFF_R3,r15), r3 ! syscall_nr - ! - mov.l 6f, r10 ! Number of syscalls - cmp/hs r10, r3 - bf syscall_call - mov #-ENOSYS, r0 - bra syscall_exit - mov.l r0, @(OFF_R0,r15) ! Return value - __restore_all: mov #OFF_SR, r0 mov.l @(r0,r15), r0 ! get status register @@ -388,6 +360,37 @@ syscall_exit: bf syscall_exit_work bra __restore_all nop + + .align 2 +syscall_trace_entry: + ! Yes it is traced. + mov r15, r4 + mov.l 7f, r11 ! Call do_syscall_trace_enter which notifies + jsr @r11 ! superior (will chomp R[0-7]) + nop + cmp/eq #-1, r0 + bt syscall_exit + mov.l r0, @(OFF_R0,r15) ! Save return value + ! Reload R0-R4 from kernel stack, where the + ! parent may have modified them using + ! ptrace(POKEUSR). (Note that R0-R2 are + ! reloaded from the kernel stack by syscall_call + ! below, so don't need to be reloaded here.) + ! This allows the parent to rewrite system calls + ! and args on the fly. + mov.l @(OFF_R4,r15), r4 ! arg0 + mov.l @(OFF_R5,r15), r5 + mov.l @(OFF_R6,r15), r6 + mov.l @(OFF_R7,r15), r7 ! arg3 + mov.l @(OFF_R3,r15), r3 ! syscall_nr + ! + mov.l 6f, r10 ! Number of syscalls + cmp/hs r10, r3 + bf syscall_call + mov #-ENOSYS, r0 + bra syscall_exit + mov.l r0, @(OFF_R0,r15) ! Return value + .align 2 #if !defined(CONFIG_CPU_SH2) 1: .long TRA diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index c20fc5487e05..0dc0f52f9bb8 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -14,7 +14,6 @@ #include <linux/irqflags.h> #include <linux/smp.h> #include <linux/atomic.h> -#include <asm/pgalloc.h> #include <asm/smp.h> #include <asm/bl_bit.h> diff --git a/arch/sh/kernel/io_trapped.c b/arch/sh/kernel/io_trapped.c index 037aab2708b7..004ad0130b10 100644 --- a/arch/sh/kernel/io_trapped.c +++ b/arch/sh/kernel/io_trapped.c @@ -102,7 +102,6 @@ int register_trapped_io(struct trapped_io *tiop) pr_warn("unable to install trapped io filter\n"); return -1; } -EXPORT_SYMBOL_GPL(register_trapped_io); void __iomem *match_trapped_io_handler(struct list_head *list, unsigned long offset, @@ -131,7 +130,6 @@ void __iomem *match_trapped_io_handler(struct list_head *list, spin_unlock_irqrestore(&trapped_lock, flags); return NULL; } -EXPORT_SYMBOL_GPL(match_trapped_io_handler); static struct trapped_io *lookup_tiop(unsigned long address) { diff --git a/arch/sh/kernel/iomap.c b/arch/sh/kernel/iomap.c index ef9e2c97cbb7..0a0dff4e66de 100644 --- a/arch/sh/kernel/iomap.c +++ b/arch/sh/kernel/iomap.c @@ -8,31 +8,31 @@ #include <linux/module.h> #include <linux/io.h> -unsigned int ioread8(void __iomem *addr) +unsigned int ioread8(const void __iomem *addr) { return readb(addr); } EXPORT_SYMBOL(ioread8); -unsigned int ioread16(void __iomem *addr) +unsigned int ioread16(const void __iomem *addr) { return readw(addr); } EXPORT_SYMBOL(ioread16); -unsigned int ioread16be(void __iomem *addr) +unsigned int ioread16be(const void __iomem *addr) { return be16_to_cpu(__raw_readw(addr)); } EXPORT_SYMBOL(ioread16be); -unsigned int ioread32(void __iomem *addr) +unsigned int ioread32(const void __iomem *addr) { return readl(addr); } EXPORT_SYMBOL(ioread32); -unsigned int ioread32be(void __iomem *addr) +unsigned int ioread32be(const void __iomem *addr) { return be32_to_cpu(__raw_readl(addr)); } @@ -74,7 +74,7 @@ EXPORT_SYMBOL(iowrite32be); * convert to CPU byte order. We write in "IO byte * order" (we also don't have IO barriers). */ -static inline void mmio_insb(void __iomem *addr, u8 *dst, int count) +static inline void mmio_insb(const void __iomem *addr, u8 *dst, int count) { while (--count >= 0) { u8 data = __raw_readb(addr); @@ -83,7 +83,7 @@ static inline void mmio_insb(void __iomem *addr, u8 *dst, int count) } } -static inline void mmio_insw(void __iomem *addr, u16 *dst, int count) +static inline void mmio_insw(const void __iomem *addr, u16 *dst, int count) { while (--count >= 0) { u16 data = __raw_readw(addr); @@ -92,7 +92,7 @@ static inline void mmio_insw(void __iomem *addr, u16 *dst, int count) } } -static inline void mmio_insl(void __iomem *addr, u32 *dst, int count) +static inline void mmio_insl(const void __iomem *addr, u32 *dst, int count) { while (--count >= 0) { u32 data = __raw_readl(addr); @@ -125,19 +125,19 @@ static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count) } } -void ioread8_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread8_rep(const void __iomem *addr, void *dst, unsigned long count) { mmio_insb(addr, dst, count); } EXPORT_SYMBOL(ioread8_rep); -void ioread16_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread16_rep(const void __iomem *addr, void *dst, unsigned long count) { mmio_insw(addr, dst, count); } EXPORT_SYMBOL(ioread16_rep); -void ioread32_rep(void __iomem *addr, void *dst, unsigned long count) +void ioread32_rep(const void __iomem *addr, void *dst, unsigned long count) { mmio_insl(addr, dst, count); } diff --git a/arch/sh/kernel/ioport.c b/arch/sh/kernel/ioport.c index 34f8cdbbcf0b..f39446a658bd 100644 --- a/arch/sh/kernel/ioport.c +++ b/arch/sh/kernel/ioport.c @@ -7,6 +7,7 @@ */ #include <linux/module.h> #include <linux/io.h> +#include <asm/io_trapped.h> unsigned long sh_io_port_base __read_mostly = -1; EXPORT_SYMBOL(sh_io_port_base); diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c index 4a98980b8a07..223c14f44af7 100644 --- a/arch/sh/kernel/machine_kexec.c +++ b/arch/sh/kernel/machine_kexec.c @@ -14,7 +14,6 @@ #include <linux/ftrace.h> #include <linux/suspend.h> #include <linux/memblock.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/io.h> #include <asm/cacheflush.h> diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c index beadbbdb4486..d606679a211e 100644 --- a/arch/sh/kernel/machvec.c +++ b/arch/sh/kernel/machvec.c @@ -15,6 +15,7 @@ #include <asm/setup.h> #include <asm/io.h> #include <asm/irq.h> +#include <asm/processor.h> #define MV_NAME_SIZE 32 @@ -64,10 +65,10 @@ static int __init early_parse_mv(char *from) mvp = get_mv_byname(mv_name); if (unlikely(!mvp)) { - printk("Available vectors:\n\n\t'%s', ", sh_mv.mv_name); + pr_info("Available vectors:\n\n\t'%s', ", sh_mv.mv_name); for_each_mv(mvp) - printk("'%s', ", mvp->mv_name); - printk("\n\n"); + pr_cont("'%s', ", mvp->mv_name); + pr_cont("\n\n"); panic("Failed to select machvec '%s' -- halting.\n", mv_name); } else @@ -104,7 +105,7 @@ void __init sh_mv_setup(void) sh_mv = *(struct sh_machine_vector *)&__machvec_start; } - printk(KERN_NOTICE "Booting machvec: %s\n", get_system_type()); + pr_notice("Booting machvec: %s\n", get_system_type()); /* * Manually walk the vec, fill in anything that the board hasn't yet diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c index 6281f2fdf9ca..c9d3aa18732d 100644 --- a/arch/sh/kernel/perf_callchain.c +++ b/arch/sh/kernel/perf_callchain.c @@ -11,11 +11,6 @@ #include <asm/unwinder.h> #include <asm/ptrace.h> -static int callchain_stack(void *data, char *name) -{ - return 0; -} - static void callchain_address(void *data, unsigned long addr, int reliable) { struct perf_callchain_entry_ctx *entry = data; @@ -25,7 +20,6 @@ static void callchain_address(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops callchain_ops = { - .stack = callchain_stack, .address = callchain_address, }; diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index cde0a66116d2..80a5d1c66a51 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -30,34 +30,30 @@ void show_regs(struct pt_regs * regs) { - printk("\n"); + pr_info("\n"); show_regs_print_info(KERN_DEFAULT); - printk("PC is at %pS\n", (void *)instruction_pointer(regs)); - printk("PR is at %pS\n", (void *)regs->pr); + pr_info("PC is at %pS\n", (void *)instruction_pointer(regs)); + pr_info("PR is at %pS\n", (void *)regs->pr); - printk("PC : %08lx SP : %08lx SR : %08lx ", - regs->pc, regs->regs[15], regs->sr); + pr_info("PC : %08lx SP : %08lx SR : %08lx ", regs->pc, + regs->regs[15], regs->sr); #ifdef CONFIG_MMU - printk("TEA : %08x\n", __raw_readl(MMU_TEA)); + pr_cont("TEA : %08x\n", __raw_readl(MMU_TEA)); #else - printk("\n"); + pr_cont("\n"); #endif - printk("R0 : %08lx R1 : %08lx R2 : %08lx R3 : %08lx\n", - regs->regs[0],regs->regs[1], - regs->regs[2],regs->regs[3]); - printk("R4 : %08lx R5 : %08lx R6 : %08lx R7 : %08lx\n", - regs->regs[4],regs->regs[5], - regs->regs[6],regs->regs[7]); - printk("R8 : %08lx R9 : %08lx R10 : %08lx R11 : %08lx\n", - regs->regs[8],regs->regs[9], - regs->regs[10],regs->regs[11]); - printk("R12 : %08lx R13 : %08lx R14 : %08lx\n", - regs->regs[12],regs->regs[13], - regs->regs[14]); - printk("MACH: %08lx MACL: %08lx GBR : %08lx PR : %08lx\n", - regs->mach, regs->macl, regs->gbr, regs->pr); + pr_info("R0 : %08lx R1 : %08lx R2 : %08lx R3 : %08lx\n", + regs->regs[0], regs->regs[1], regs->regs[2], regs->regs[3]); + pr_info("R4 : %08lx R5 : %08lx R6 : %08lx R7 : %08lx\n", + regs->regs[4], regs->regs[5], regs->regs[6], regs->regs[7]); + pr_info("R8 : %08lx R9 : %08lx R10 : %08lx R11 : %08lx\n", + regs->regs[8], regs->regs[9], regs->regs[10], regs->regs[11]); + pr_info("R12 : %08lx R13 : %08lx R14 : %08lx\n", + regs->regs[12], regs->regs[13], regs->regs[14]); + pr_info("MACH: %08lx MACL: %08lx GBR : %08lx PR : %08lx\n", + regs->mach, regs->macl, regs->gbr, regs->pr); show_trace(NULL, (unsigned long *)regs->regs[15], regs, KERN_DEFAULT); show_code(regs); @@ -93,24 +89,6 @@ void release_thread(struct task_struct *dead_task) /* do nothing */ } -/* Fill in the fpu structure for a core dump.. */ -int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu) -{ - int fpvalid = 0; - -#if defined(CONFIG_SH_FPU) - struct task_struct *tsk = current; - - fpvalid = !!tsk_used_math(tsk); - if (fpvalid) - fpvalid = !fpregs_get(tsk, NULL, - (struct membuf){fpu, sizeof(*fpu)}); -#endif - - return fpvalid; -} -EXPORT_SYMBOL(dump_fpu); - asmlinkage void ret_from_fork(void); asmlinkage void ret_from_kernel_thread(void); diff --git a/arch/sh/kernel/ptrace_32.c b/arch/sh/kernel/ptrace_32.c index 5c93bdb6c41a..b05bf92f9c32 100644 --- a/arch/sh/kernel/ptrace_32.c +++ b/arch/sh/kernel/ptrace_32.c @@ -165,7 +165,7 @@ static int genregs_set(struct task_struct *target, } #ifdef CONFIG_SH_FPU -int fpregs_get(struct task_struct *target, +static int fpregs_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { @@ -457,8 +457,6 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { long ret = 0; - secure_computing_strict(regs->regs[0]); - if (test_thread_flag(TIF_SYSCALL_TRACE) && tracehook_report_syscall_entry(regs)) /* @@ -468,6 +466,9 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) */ ret = -1L; + if (secure_computing() == -1) + return -1; + if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) trace_sys_enter(regs, regs->regs[0]); diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c index 2950b19ad077..daf0b53ee066 100644 --- a/arch/sh/kernel/stacktrace.c +++ b/arch/sh/kernel/stacktrace.c @@ -15,11 +15,6 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> -static int save_stack_stack(void *data, char *name) -{ - return 0; -} - /* * Save stack-backtrace addresses into a stack_trace buffer. */ @@ -40,7 +35,6 @@ static void save_stack_address(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops save_stack_ops = { - .stack = save_stack_stack, .address = save_stack_address, }; @@ -73,7 +67,6 @@ save_stack_address_nosched(void *data, unsigned long addr, int reliable) } static const struct stacktrace_ops save_stack_ops_nosched = { - .stack = save_stack_stack, .address = save_stack_address_nosched, }; diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index 96848db9659e..ae0a00beea5f 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -156,7 +156,7 @@ 146 common writev sys_writev 147 common getsid sys_getsid 148 common fdatasync sys_fdatasync -149 common _sysctl sys_sysctl +149 common _sysctl sys_ni_syscall 150 common mlock sys_mlock 151 common munlock sys_munlock 152 common mlockall sys_mlockall diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c index 058c6181bb30..b62ad0ba2395 100644 --- a/arch/sh/kernel/traps_32.c +++ b/arch/sh/kernel/traps_32.c @@ -482,8 +482,6 @@ asmlinkage void do_address_error(struct pt_regs *regs, error_code = lookup_exception_vector(); #endif - oldfs = get_fs(); - if (user_mode(regs)) { int si_code = BUS_ADRERR; unsigned int user_action; @@ -491,13 +489,13 @@ asmlinkage void do_address_error(struct pt_regs *regs, local_irq_enable(); inc_unaligned_user_access(); - set_fs(USER_DS); + oldfs = force_uaccess_begin(); if (copy_from_user(&instruction, (insn_size_t *)(regs->pc & ~1), sizeof(instruction))) { - set_fs(oldfs); + force_uaccess_end(oldfs); goto uspace_segv; } - set_fs(oldfs); + force_uaccess_end(oldfs); /* shout about userspace fixups */ unaligned_fixups_notify(current, instruction, regs); @@ -520,11 +518,11 @@ fixup: goto uspace_segv; } - set_fs(USER_DS); + oldfs = force_uaccess_begin(); tmp = handle_unaligned_access(instruction, regs, &user_mem_access, 0, address); - set_fs(oldfs); + force_uaccess_end(oldfs); if (tmp == 0) return; /* sorted */ diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile index d0abbe5e38b0..eb473d373ca4 100644 --- a/arch/sh/lib/Makefile +++ b/arch/sh/lib/Makefile @@ -30,5 +30,3 @@ memset-$(CONFIG_CPU_SH4) := memset-sh4.o lib-$(CONFIG_MMU) += copy_page.o __clear_user.o lib-$(CONFIG_MCOUNT) += mcount.o lib-y += $(memcpy-y) $(memset-y) $(udivsi3-y) - -ccflags-y := -Werror diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c index 540e670dbafc..dad8e6a54906 100644 --- a/arch/sh/lib/delay.c +++ b/arch/sh/lib/delay.c @@ -29,7 +29,6 @@ void __delay(unsigned long loops) : "0" (loops) : "t"); } -EXPORT_SYMBOL(__delay); inline void __const_udelay(unsigned long xloops) { diff --git a/arch/sh/mm/Makefile b/arch/sh/mm/Makefile index 487da0ff03b3..f69ddc70b146 100644 --- a/arch/sh/mm/Makefile +++ b/arch/sh/mm/Makefile @@ -43,5 +43,3 @@ obj-$(CONFIG_UNCACHED_MAPPING) += uncached.o obj-$(CONFIG_HAVE_SRAM_POOL) += sram.o GCOV_PROFILE_pmb.o := n - -ccflags-y := -Werror diff --git a/arch/sh/mm/cache-sh3.c b/arch/sh/mm/cache-sh3.c index 26f3bd43e850..bc595982d396 100644 --- a/arch/sh/mm/cache-sh3.c +++ b/arch/sh/mm/cache-sh3.c @@ -16,7 +16,6 @@ #include <asm/cache.h> #include <asm/io.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> diff --git a/arch/sh/mm/cache-sh7705.c b/arch/sh/mm/cache-sh7705.c index 48978293226c..4c67b3d88775 100644 --- a/arch/sh/mm/cache-sh7705.c +++ b/arch/sh/mm/cache-sh7705.c @@ -20,7 +20,6 @@ #include <asm/cache.h> #include <asm/io.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index 3169a343a5ab..0de206c1acfe 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -57,8 +57,6 @@ int __init platform_resource_setup_memory(struct platform_device *pdev, return -ENOMEM; } - memset(buf, 0, memsize); - r->flags = IORESOURCE_MEM; r->start = dma_handle; r->end = r->start + memsize - 1; diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index fbe1f2fe9a8c..88a1f453d73e 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -208,13 +208,12 @@ show_fault_oops(struct pt_regs *regs, unsigned long address) if (!oops_may_print()) return; - printk(KERN_ALERT "PC:"); pr_alert("BUG: unable to handle kernel %s at %08lx\n", address < PAGE_SIZE ? "NULL pointer dereference" : "paging request", address); pr_alert("PC:"); - printk_address(regs->pc, 1, KERN_ALERT); + printk_address(regs->pc, 1); show_pte(NULL, address); } @@ -482,22 +481,13 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (unlikely(fault & (VM_FAULT_RETRY | VM_FAULT_ERROR))) if (mm_fault_error(regs, error_code, address, fault)) return; if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, - regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, - regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c index acd5652a0de3..220d7bc43d2b 100644 --- a/arch/sh/mm/hugetlbpage.c +++ b/arch/sh/mm/hugetlbpage.c @@ -17,7 +17,6 @@ #include <linux/sysctl.h> #include <asm/mman.h> -#include <asm/pgalloc.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index a70ba0fdd0b3..4735176ab811 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -27,7 +27,9 @@ #include <asm/sections.h> #include <asm/setup.h> #include <asm/cache.h> +#include <asm/pgalloc.h> #include <linux/sizes.h> +#include "ioremap.h" pgd_t swapper_pg_dir[PTRS_PER_PGD]; @@ -240,12 +242,6 @@ static void __init do_init_bootmem(void) plat_mem_setup(); - for_each_memblock(memory, reg) { - int nid = memblock_get_region_node(reg); - - memory_present(nid, memblock_region_memory_base_pfn(reg), - memblock_region_memory_end_pfn(reg)); - } sparse_init(); } @@ -430,15 +426,6 @@ int arch_add_memory(int nid, u64 start, u64 size, return ret; } -#ifdef CONFIG_NUMA -int memory_add_physaddr_to_nid(u64 addr) -{ - /* Node 0 for now.. */ - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); -#endif - void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap) { diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c index f6d02246d665..21342581144d 100644 --- a/arch/sh/mm/ioremap.c +++ b/arch/sh/mm/ioremap.c @@ -18,12 +18,59 @@ #include <linux/mm.h> #include <linux/pci.h> #include <linux/io.h> +#include <asm/io_trapped.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <asm/addrspace.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/mmu.h> +#include "ioremap.h" + +/* + * On 32-bit SH, we traditionally have the whole physical address space mapped + * at all times (as MIPS does), so "ioremap()" and "iounmap()" do not need to do + * anything but place the address in the proper segment. This is true for P1 + * and P2 addresses, as well as some P3 ones. However, most of the P3 addresses + * and newer cores using extended addressing need to map through page tables, so + * the ioremap() implementation becomes a bit more complicated. + */ +#ifdef CONFIG_29BIT +static void __iomem * +__ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot) +{ + phys_addr_t last_addr = offset + size - 1; + + /* + * For P1 and P2 space this is trivial, as everything is already + * mapped. Uncached access for P1 addresses are done through P2. + * In the P3 case or for addresses outside of the 29-bit space, + * mapping must be done by the PMB or by using page tables. + */ + if (likely(PXSEG(offset) < P3SEG && PXSEG(last_addr) < P3SEG)) { + u64 flags = pgprot_val(prot); + + /* + * Anything using the legacy PTEA space attributes needs + * to be kicked down to page table mappings. + */ + if (unlikely(flags & _PAGE_PCC_MASK)) + return NULL; + if (unlikely(flags & _PAGE_CACHABLE)) + return (void __iomem *)P1SEGADDR(offset); + + return (void __iomem *)P2SEGADDR(offset); + } + + /* P4 above the store queues are always mapped. */ + if (unlikely(offset >= P3_ADDR_MAX)) + return (void __iomem *)P4SEGADDR(offset); + + return NULL; +} +#else +#define __ioremap_29bit(offset, size, prot) NULL +#endif /* CONFIG_29BIT */ /* * Remap an arbitrary physical address space into the kernel virtual @@ -42,6 +89,14 @@ __ioremap_caller(phys_addr_t phys_addr, unsigned long size, unsigned long offset, last_addr, addr, orig_addr; void __iomem *mapped; + mapped = __ioremap_trapped(phys_addr, size); + if (mapped) + return mapped; + + mapped = __ioremap_29bit(phys_addr, size, pgprot); + if (mapped) + return mapped; + /* Don't allow wraparound or zero size */ last_addr = phys_addr + size - 1; if (!size || last_addr < phys_addr) diff --git a/arch/sh/mm/ioremap.h b/arch/sh/mm/ioremap.h new file mode 100644 index 000000000000..f2544e721a35 --- /dev/null +++ b/arch/sh/mm/ioremap.h @@ -0,0 +1,23 @@ +#ifndef _SH_MM_IORMEMAP_H +#define _SH_MM_IORMEMAP_H 1 + +#ifdef CONFIG_IOREMAP_FIXED +void __iomem *ioremap_fixed(phys_addr_t, unsigned long, pgprot_t); +int iounmap_fixed(void __iomem *); +void ioremap_fixed_init(void); +#else +static inline void __iomem * +ioremap_fixed(phys_addr_t phys_addr, unsigned long size, pgprot_t prot) +{ + BUG(); + return NULL; +} +static inline void ioremap_fixed_init(void) +{ +} +static inline int iounmap_fixed(void __iomem *addr) +{ + return -EINVAL; +} +#endif /* CONFIG_IOREMAP_FIXED */ +#endif /* _SH_MM_IORMEMAP_H */ diff --git a/arch/sh/mm/ioremap_fixed.c b/arch/sh/mm/ioremap_fixed.c index 07e744d75fa0..136113bcac25 100644 --- a/arch/sh/mm/ioremap_fixed.c +++ b/arch/sh/mm/ioremap_fixed.c @@ -18,12 +18,12 @@ #include <linux/proc_fs.h> #include <asm/fixmap.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/addrspace.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/mmu.h> #include <asm/mmu_context.h> +#include "ioremap.h" struct ioremap_map { void __iomem *addr; diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c index f7e4439deb17..50f0dc1744d0 100644 --- a/arch/sh/mm/numa.c +++ b/arch/sh/mm/numa.c @@ -53,7 +53,4 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end) /* It's up */ node_set_online(nid); - - /* Kick sparsemem */ - sparse_memory_present_with_active_regions(nid); } diff --git a/arch/sh/mm/pgtable.c b/arch/sh/mm/pgtable.c index 5c8f9247c3c2..cf7ce4b57359 100644 --- a/arch/sh/mm/pgtable.c +++ b/arch/sh/mm/pgtable.c @@ -2,8 +2,6 @@ #include <linux/mm.h> #include <linux/slab.h> -#define PGALLOC_GFP GFP_KERNEL | __GFP_ZERO - static struct kmem_cache *pgd_cachep; #if PAGETABLE_LEVELS > 2 static struct kmem_cache *pmd_cachep; @@ -13,6 +11,7 @@ void pgd_ctor(void *x) { pgd_t *pgd = x; + memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t)); memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD, (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); @@ -32,7 +31,7 @@ void pgtable_cache_init(void) pgd_t *pgd_alloc(struct mm_struct *mm) { - return kmem_cache_alloc(pgd_cachep, PGALLOC_GFP); + return kmem_cache_alloc(pgd_cachep, GFP_KERNEL); } void pgd_free(struct mm_struct *mm, pgd_t *pgd) @@ -48,7 +47,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) { - return kmem_cache_alloc(pmd_cachep, PGALLOC_GFP); + return kmem_cache_alloc(pmd_cachep, GFP_KERNEL | __GFP_ZERO); } void pmd_free(struct mm_struct *mm, pmd_t *pmd) diff --git a/arch/sh/mm/tlb-sh3.c b/arch/sh/mm/tlb-sh3.c index 869243518bb3..fb400afc2a49 100644 --- a/arch/sh/mm/tlb-sh3.c +++ b/arch/sh/mm/tlb-sh3.c @@ -21,7 +21,6 @@ #include <asm/io.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> diff --git a/arch/sh/oprofile/backtrace.c b/arch/sh/oprofile/backtrace.c index f1205f92631d..cc16cf86cd92 100644 --- a/arch/sh/oprofile/backtrace.c +++ b/arch/sh/oprofile/backtrace.c @@ -19,12 +19,6 @@ #include <asm/sections.h> #include <asm/stacktrace.h> -static int backtrace_stack(void *data, char *name) -{ - /* Yes, we want all stacks */ - return 0; -} - static void backtrace_address(void *data, unsigned long addr, int reliable) { unsigned int *depth = data; @@ -34,7 +28,6 @@ static void backtrace_address(void *data, unsigned long addr, int reliable) } static struct stacktrace_ops backtrace_ops = { - .stack = backtrace_stack, .address = backtrace_address, }; diff --git a/arch/sh/tools/mach-types b/arch/sh/tools/mach-types index 569977e52c91..29e648855d50 100644 --- a/arch/sh/tools/mach-types +++ b/arch/sh/tools/mach-types @@ -46,7 +46,6 @@ X3PROTO SH_X3PROTO MAGICPANELR2 SH_MAGIC_PANEL_R2 R2D_PLUS RTS7751R2D_PLUS R2D_1 RTS7751R2D_1 -CAYMAN SH_CAYMAN SDK7780 SH_SDK7780 MIGOR SH_MIGOR RSK7201 SH_RSK7201 diff --git a/arch/sparc/include/asm/ide.h b/arch/sparc/include/asm/ide.h index 499aa2e6e276..904cc6cbc155 100644 --- a/arch/sparc/include/asm/ide.h +++ b/arch/sparc/include/asm/ide.h @@ -13,7 +13,6 @@ #include <asm/io.h> #ifdef CONFIG_SPARC64 -#include <asm/pgalloc.h> #include <asm/spitfire.h> #include <asm/cacheflush.h> #include <asm/page.h> diff --git a/arch/sparc/include/asm/sparsemem.h b/arch/sparc/include/asm/sparsemem.h index 1dd1b61432db..aa9a676bc341 100644 --- a/arch/sparc/include/asm/sparsemem.h +++ b/arch/sparc/include/asm/sparsemem.h @@ -7,7 +7,6 @@ #include <asm/page.h> #define SECTION_SIZE_BITS 30 -#define MAX_PHYSADDR_BITS MAX_PHYS_ADDRESS_BITS #define MAX_PHYSMEM_BITS MAX_PHYS_ADDRESS_BITS #endif /* !(__KERNEL__) */ diff --git a/arch/sparc/include/asm/timer_64.h b/arch/sparc/include/asm/timer_64.h index c7e4fb601a57..dcfad4613e18 100644 --- a/arch/sparc/include/asm/timer_64.h +++ b/arch/sparc/include/asm/timer_64.h @@ -7,6 +7,7 @@ #ifndef _SPARC64_TIMER_H #define _SPARC64_TIMER_H +#include <uapi/asm/asi.h> #include <linux/types.h> #include <linux/init.h> diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h index 6820d357581c..e841cae544c2 100644 --- a/arch/sparc/include/asm/tlb_64.h +++ b/arch/sparc/include/asm/tlb_64.h @@ -4,7 +4,6 @@ #include <linux/swap.h> #include <linux/pagemap.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index d6d8413eca83..0a2d3ebc4bb8 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -28,7 +28,7 @@ #define get_fs() (current->thread.current_ds) #define set_fs(val) ((current->thread.current_ds) = (val)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) /* We have there a nice not-mapped page at PAGE_OFFSET - PAGE_SIZE, so that this test * can be fairly lightweight. diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index bf9d330073b2..698cf69f74e9 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -32,7 +32,7 @@ #define get_fs() ((mm_segment_t){(current_thread_info()->current_ds)}) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define set_fs(val) \ do { \ diff --git a/arch/sparc/include/asm/vvar.h b/arch/sparc/include/asm/vvar.h index 0289503d1cb0..6eaf5cfcaae1 100644 --- a/arch/sparc/include/asm/vvar.h +++ b/arch/sparc/include/asm/vvar.h @@ -6,7 +6,8 @@ #define _ASM_SPARC_VVAR_DATA_H #include <asm/clocksource.h> -#include <linux/seqlock.h> +#include <asm/processor.h> +#include <asm/barrier.h> #include <linux/time.h> #include <linux/types.h> diff --git a/arch/sparc/kernel/leon_smp.c b/arch/sparc/kernel/leon_smp.c index 41829c024f92..1eed26d423fb 100644 --- a/arch/sparc/kernel/leon_smp.c +++ b/arch/sparc/kernel/leon_smp.c @@ -38,7 +38,6 @@ #include <asm/delay.h> #include <asm/irq.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/oplib.h> #include <asm/cpudata.h> #include <asm/asi.h> diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index bd123f1de2e7..adfcaeab3ddc 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -34,7 +34,6 @@ #include <asm/oplib.h> #include <linux/uaccess.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/delay.h> #include <asm/processor.h> #include <asm/psr.h> @@ -381,55 +380,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, return 0; } -/* - * fill in the fpu structure for a core dump. - */ -int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs) -{ - if (used_math()) { - memset(fpregs, 0, sizeof(*fpregs)); - fpregs->pr_q_entrysize = 8; - return 1; - } -#ifdef CONFIG_SMP - if (test_thread_flag(TIF_USEDFPU)) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - if (regs != NULL) { - regs->psr &= ~(PSR_EF); - clear_thread_flag(TIF_USEDFPU); - } - } -#else - if (current == last_task_used_math) { - put_psr(get_psr() | PSR_EF); - fpsave(¤t->thread.float_regs[0], ¤t->thread.fsr, - ¤t->thread.fpqueue[0], ¤t->thread.fpqdepth); - if (regs != NULL) { - regs->psr &= ~(PSR_EF); - last_task_used_math = NULL; - } - } -#endif - memcpy(&fpregs->pr_fr.pr_regs[0], - ¤t->thread.float_regs[0], - (sizeof(unsigned long) * 32)); - fpregs->pr_fsr = current->thread.fsr; - fpregs->pr_qcnt = current->thread.fpqdepth; - fpregs->pr_q_entrysize = 8; - fpregs->pr_en = 1; - if(fpregs->pr_qcnt != 0) { - memcpy(&fpregs->pr_q[0], - ¤t->thread.fpqueue[0], - sizeof(struct fpq) * fpregs->pr_qcnt); - } - /* Zero out the rest. */ - memset(&fpregs->pr_q[fpregs->pr_qcnt], 0, - sizeof(struct fpq) * (32 - fpregs->pr_qcnt)); - return 1; -} - unsigned long get_wchan(struct task_struct *task) { unsigned long pc, fp, bias = 0; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 04ef19b88632..a75093b993f9 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -666,72 +666,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } -typedef struct { - union { - unsigned int pr_regs[32]; - unsigned long pr_dregs[16]; - } pr_fr; - unsigned int __unused; - unsigned int pr_fsr; - unsigned char pr_qcnt; - unsigned char pr_q_entrysize; - unsigned char pr_en; - unsigned int pr_q[64]; -} elf_fpregset_t32; - -/* - * fill in the fpu structure for a core dump. - */ -int dump_fpu (struct pt_regs * regs, elf_fpregset_t * fpregs) -{ - unsigned long *kfpregs = current_thread_info()->fpregs; - unsigned long fprs = current_thread_info()->fpsaved[0]; - - if (test_thread_flag(TIF_32BIT)) { - elf_fpregset_t32 *fpregs32 = (elf_fpregset_t32 *)fpregs; - - if (fprs & FPRS_DL) - memcpy(&fpregs32->pr_fr.pr_regs[0], kfpregs, - sizeof(unsigned int) * 32); - else - memset(&fpregs32->pr_fr.pr_regs[0], 0, - sizeof(unsigned int) * 32); - fpregs32->pr_qcnt = 0; - fpregs32->pr_q_entrysize = 8; - memset(&fpregs32->pr_q[0], 0, - (sizeof(unsigned int) * 64)); - if (fprs & FPRS_FEF) { - fpregs32->pr_fsr = (unsigned int) current_thread_info()->xfsr[0]; - fpregs32->pr_en = 1; - } else { - fpregs32->pr_fsr = 0; - fpregs32->pr_en = 0; - } - } else { - if(fprs & FPRS_DL) - memcpy(&fpregs->pr_regs[0], kfpregs, - sizeof(unsigned int) * 32); - else - memset(&fpregs->pr_regs[0], 0, - sizeof(unsigned int) * 32); - if(fprs & FPRS_DU) - memcpy(&fpregs->pr_regs[16], kfpregs+16, - sizeof(unsigned int) * 32); - else - memset(&fpregs->pr_regs[16], 0, - sizeof(unsigned int) * 32); - if(fprs & FPRS_FEF) { - fpregs->pr_fsr = current_thread_info()->xfsr[0]; - fpregs->pr_gsr = current_thread_info()->gsr[0]; - } else { - fpregs->pr_fsr = fpregs->pr_gsr = 0; - } - fpregs->pr_fprs = fprs; - } - return 1; -} -EXPORT_SYMBOL(dump_fpu); - unsigned long get_wchan(struct task_struct *task) { unsigned long pc, fp, bias = 0; diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index 3b005b6c3e0f..f1f8c8ebe641 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -23,7 +23,6 @@ #include <linux/uaccess.h> #include <asm/ptrace.h> -#include <asm/pgalloc.h> #include <asm/cacheflush.h> /* flush_sig_insns */ #include <asm/switch_to.h> diff --git a/arch/sparc/kernel/smp_32.c b/arch/sparc/kernel/smp_32.c index 76ce290c67cf..50c127ab46d5 100644 --- a/arch/sparc/kernel/smp_32.c +++ b/arch/sparc/kernel/smp_32.c @@ -29,7 +29,6 @@ #include <asm/irq.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/oplib.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 0085e28bf019..e286e2badc8a 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -47,6 +47,7 @@ #include <linux/uaccess.h> #include <asm/starfire.h> #include <asm/tlb.h> +#include <asm/pgalloc.h> #include <asm/sections.h> #include <asm/prom.h> #include <asm/mdesc.h> diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c index 91b61f012d19..1079638986b5 100644 --- a/arch/sparc/kernel/sun4m_irq.c +++ b/arch/sparc/kernel/sun4m_irq.c @@ -16,7 +16,6 @@ #include <asm/timer.h> #include <asm/traps.h> -#include <asm/pgalloc.h> #include <asm/irq.h> #include <asm/io.h> #include <asm/cacheflush.h> diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 46024e80ee86..4af114e84f20 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -300,7 +300,7 @@ 249 64 nanosleep sys_nanosleep 250 32 mremap sys_mremap 250 64 mremap sys_64_mremap -251 common _sysctl sys_sysctl compat_sys_sysctl +251 common _sysctl sys_ni_syscall 252 common getsid sys_getsid 253 common fdatasync sys_fdatasync 254 32 nfsservctl sys_ni_syscall sys_nis_syscall diff --git a/arch/sparc/kernel/vdso.c b/arch/sparc/kernel/vdso.c index 58880662b271..0e27437eb97b 100644 --- a/arch/sparc/kernel/vdso.c +++ b/arch/sparc/kernel/vdso.c @@ -7,7 +7,6 @@ * a different vsyscall implementation for Linux/IA32 and for the name. */ -#include <linux/seqlock.h> #include <linux/time.h> #include <linux/timekeeper_internal.h> diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index cfef656eda0f..8071bfd72349 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -234,7 +234,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -250,15 +250,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, address); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; @@ -410,7 +401,7 @@ good_area: if (!(vma->vm_flags & (VM_READ | VM_EXEC))) goto bad_area; } - switch (handle_mm_fault(vma, address, flags)) { + switch (handle_mm_fault(vma, address, flags, NULL)) { case VM_FAULT_SIGBUS: case VM_FAULT_OOM: goto do_sigbus; diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index a3806614e4dc..0a6bcc85fba7 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -422,7 +422,7 @@ good_area: goto bad_area; } - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) goto exit_exception; @@ -438,15 +438,6 @@ good_area: } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) { - current->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, - 1, regs, address); - } else { - current->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, - 1, regs, address); - } if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c index d1fc9a7b7d78..8f2a2afb048a 100644 --- a/arch/sparc/mm/highmem.c +++ b/arch/sparc/mm/highmem.c @@ -29,7 +29,6 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> #include <asm/vaddrs.h> static pte_t *kmap_pte; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 02e6e5e0f106..fad6d3129904 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1610,7 +1610,6 @@ static unsigned long __init bootmem_init(unsigned long phys_base) /* XXX cpu notifier XXX */ - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); return end_pfn; diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c index bfcc04bfce54..430a47a1b6ae 100644 --- a/arch/sparc/mm/io-unit.c +++ b/arch/sparc/mm/io-unit.c @@ -15,7 +15,6 @@ #include <linux/of.h> #include <linux/of_device.h> -#include <asm/pgalloc.h> #include <asm/io.h> #include <asm/io-unit.h> #include <asm/mxcc.h> diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c index 35b002eb312e..3a388b1c5d4b 100644 --- a/arch/sparc/mm/iommu.c +++ b/arch/sparc/mm/iommu.c @@ -16,7 +16,6 @@ #include <linux/of.h> #include <linux/of_device.h> -#include <asm/pgalloc.h> #include <asm/io.h> #include <asm/mxcc.h> #include <asm/mbus.h> diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c index a32a16c18617..20ee14739333 100644 --- a/arch/sparc/mm/tlb.c +++ b/arch/sparc/mm/tlb.c @@ -10,7 +10,6 @@ #include <linux/swap.h> #include <linux/preempt.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> #include <asm/mmu_context.h> diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 708cb6304c2d..f44355e46f31 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -54,7 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE # optimize sibling calls. # CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \ - $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO @@ -93,7 +93,7 @@ KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -fpic -KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) +KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ef69be17ff70..eb51fec75948 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -14,6 +14,7 @@ config UML select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_BUGVERBOSE + select NO_DMA select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS @@ -167,9 +168,6 @@ config MMAPPER This driver allows a host file to be used as emulated IO memory inside UML. -config NO_DMA - def_bool y - config PGTABLE_LEVELS int default 3 if 3_LEVEL_PGTABLES diff --git a/arch/um/Makefile b/arch/um/Makefile index 3f27aa3ec0a6..1cea46ff9bb7 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -121,8 +121,7 @@ LINK-$(CONFIG_LD_SCRIPT_STATIC) += -static LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib $(call cc-option, -no-pie) CFLAGS_NO_HARDENING := $(call cc-option, -fno-PIC,) $(call cc-option, -fno-pic,) \ - $(call cc-option, -fno-stack-protector,) \ - $(call cc-option, -fno-stack-protector-all,) + -fno-stack-protector $(call cc-option, -fno-stack-protector-all) # Options used by linker script export LDS_START := $(START) diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 351aee52aca6..a6c4bb6c2c01 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -385,7 +385,7 @@ static irqreturn_t vu_req_interrupt(int irq, void *data) } break; case VHOST_USER_SLAVE_IOTLB_MSG: - /* not supported - VIRTIO_F_IOMMU_PLATFORM */ + /* not supported - VIRTIO_F_ACCESS_PLATFORM */ case VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG: /* not supported - VHOST_USER_PROTOCOL_F_HOST_NOTIFIER */ default: diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h index 881e76da1938..5393e13e07e0 100644 --- a/arch/um/include/asm/pgalloc.h +++ b/arch/um/include/asm/pgalloc.h @@ -10,7 +10,7 @@ #include <linux/mm.h> -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#include <asm-generic/pgalloc.h> #define pmd_populate_kernel(mm, pmd, pte) \ set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte))) @@ -25,7 +25,6 @@ * Allocate and free page tables. */ extern pgd_t *pgd_alloc(struct mm_struct *); -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); #define __pte_free_tlb(tlb,pte, address) \ do { \ @@ -34,12 +33,6 @@ do { \ } while (0) #ifdef CONFIG_3_LEVEL_PGTABLES - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - free_page((unsigned long)pmd); -} - #define __pmd_free_tlb(tlb,x, address) tlb_remove_page((tlb),virt_to_page(x)) #endif diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h index 36f452957cef..7e6a4180db9d 100644 --- a/arch/um/include/asm/pgtable-3level.h +++ b/arch/um/include/asm/pgtable-3level.h @@ -78,9 +78,6 @@ static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; } #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) #endif -struct mm_struct; -extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address); - static inline void pud_clear (pud_t *pud) { set_pud(pud, __pud(_PAGE_NEWPAGE)); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index c2ff76c8981e..9242dc91d751 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -196,23 +196,6 @@ pgd_t *pgd_alloc(struct mm_struct *mm) return pgd; } -void pgd_free(struct mm_struct *mm, pgd_t *pgd) -{ - free_page((unsigned long) pgd); -} - -#ifdef CONFIG_3_LEVEL_PGTABLES -pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address) -{ - pmd_t *pmd = (pmd_t *) __get_free_page(GFP_KERNEL); - - if (pmd) - memset(pmd, 0, PAGE_SIZE); - - return pmd; -} -#endif - void *uml_kmalloc(int size, int flags) { return kmalloc(size, flags); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 2b3afa354a90..ad12f78bda7e 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -71,7 +71,7 @@ good_area: do { vm_fault_t fault; - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, NULL); if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) goto out_nosemaphore; @@ -88,10 +88,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9a2849527dd7..7101ac64bb20 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -209,6 +209,7 @@ config X86 select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT + select HAVE_POSIX_CPU_TIMERS_TASK_WORK select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RELIABLE_STACKTRACE if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION select HAVE_FUNCTION_ARG_ACCESS_API diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1e634d7ee6eb..4346ffb2e39f 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -36,8 +36,8 @@ REALMODE_CFLAGS := $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse -REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding) -REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector) +REALMODE_CFLAGS += -ffreestanding +REALMODE_CFLAGS += -fno-stack-protector REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) export REALMODE_CFLAGS diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index c08714ae76ec..3962f592633d 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -35,8 +35,8 @@ cflags-$(CONFIG_X86_32) := -march=i386 cflags-$(CONFIG_X86_64) := -mcmodel=small KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse -KBUILD_CFLAGS += $(call cc-option,-ffreestanding) -KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector) +KBUILD_CFLAGS += -ffreestanding +KBUILD_CFLAGS += -fno-stack-protector KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) KBUILD_CFLAGS += $(call cc-disable-warning, gnu) KBUILD_CFLAGS += -Wno-pointer-sign diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 29b7d52143e9..df8c017e6161 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -449,8 +449,6 @@ .macro SWITCH_TO_KERNEL_STACK - ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV - BUG_IF_WRONG_CR3 SWITCH_TO_KERNEL_CR3 scratch_reg=%eax @@ -599,8 +597,6 @@ */ .macro SWITCH_TO_ENTRY_STACK - ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV - /* Bytes to copy */ movl $PTREGS_SIZE, %ecx @@ -872,17 +868,6 @@ SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) * will ignore all of the single-step traps generated in this range. */ -#ifdef CONFIG_XEN_PV -/* - * Xen doesn't set %esp to be precisely what the normal SYSENTER - * entry point expects, so fix it up before using the normal path. - */ -SYM_CODE_START(xen_sysenter_target) - addl $5*4, %esp /* remove xen-provided frame */ - jmp .Lsysenter_past_esp -SYM_CODE_END(xen_sysenter_target) -#endif - /* * 32-bit SYSENTER entry. * @@ -965,9 +950,8 @@ SYM_FUNC_START(entry_SYSENTER_32) movl %esp, %eax call do_SYSENTER_32 - /* XEN PV guests always use IRET path */ - ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ - "jmp .Lsyscall_32_done", X86_FEATURE_XENPV + testl %eax, %eax + jz .Lsyscall_32_done STACKLEAK_ERASE @@ -1165,95 +1149,6 @@ SYM_FUNC_END(entry_INT80_32) #endif .endm -#ifdef CONFIG_PARAVIRT -SYM_CODE_START(native_iret) - iret - _ASM_EXTABLE(native_iret, asm_iret_error) -SYM_CODE_END(native_iret) -#endif - -#ifdef CONFIG_XEN_PV -/* - * See comment in entry_64.S for further explanation - * - * Note: This is not an actual IDT entry point. It's a XEN specific entry - * point and therefore named to match the 64-bit trampoline counterpart. - */ -SYM_FUNC_START(xen_asm_exc_xen_hypervisor_callback) - /* - * Check to see if we got the event in the critical - * region in xen_iret_direct, after we've reenabled - * events and checked for pending events. This simulates - * iret instruction's behaviour where it delivers a - * pending interrupt when enabling interrupts: - */ - cmpl $xen_iret_start_crit, (%esp) - jb 1f - cmpl $xen_iret_end_crit, (%esp) - jae 1f - call xen_iret_crit_fixup -1: - pushl $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - ENCODE_FRAME_POINTER - - mov %esp, %eax - call xen_pv_evtchn_do_upcall - jmp handle_exception_return -SYM_FUNC_END(xen_asm_exc_xen_hypervisor_callback) - -/* - * Hypervisor uses this for application faults while it executes. - * We get here for two reasons: - * 1. Fault while reloading DS, ES, FS or GS - * 2. Fault while executing IRET - * Category 1 we fix up by reattempting the load, and zeroing the segment - * register if the load fails. - * Category 2 we fix up by jumping to do_iret_error. We cannot use the - * normal Linux return path in this case because if we use the IRET hypercall - * to pop the stack frame we end up in an infinite loop of failsafe callbacks. - * We distinguish between categories by maintaining a status value in EAX. - */ -SYM_FUNC_START(xen_failsafe_callback) - pushl %eax - movl $1, %eax -1: mov 4(%esp), %ds -2: mov 8(%esp), %es -3: mov 12(%esp), %fs -4: mov 16(%esp), %gs - /* EAX == 0 => Category 1 (Bad segment) - EAX != 0 => Category 2 (Bad IRET) */ - testl %eax, %eax - popl %eax - lea 16(%esp), %esp - jz 5f - jmp asm_iret_error -5: pushl $-1 /* orig_ax = -1 => not a system call */ - SAVE_ALL - ENCODE_FRAME_POINTER - jmp handle_exception_return - -.section .fixup, "ax" -6: xorl %eax, %eax - movl %eax, 4(%esp) - jmp 1b -7: xorl %eax, %eax - movl %eax, 8(%esp) - jmp 2b -8: xorl %eax, %eax - movl %eax, 12(%esp) - jmp 3b -9: xorl %eax, %eax - movl %eax, 16(%esp) - jmp 4b -.previous - _ASM_EXTABLE(1b, 6b) - _ASM_EXTABLE(2b, 7b) - _ASM_EXTABLE(3b, 8b) - _ASM_EXTABLE(4b, 9b) -SYM_FUNC_END(xen_failsafe_callback) -#endif /* CONFIG_XEN_PV */ - SYM_CODE_START_LOCAL_NOALIGN(handle_exception) /* the function address is in %gs's slot on the stack */ SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1 diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index e31a75262c9c..9d1102873666 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -160,7 +160,7 @@ 146 i386 writev sys_writev compat_sys_writev 147 i386 getsid sys_getsid 148 i386 fdatasync sys_fdatasync -149 i386 _sysctl sys_sysctl compat_sys_sysctl +149 i386 _sysctl sys_ni_syscall 150 i386 mlock sys_mlock 151 i386 munlock sys_munlock 152 i386 mlockall sys_mlockall diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 9d82078c949a..f30d6ae9a688 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -164,7 +164,7 @@ 153 common vhangup sys_vhangup 154 common modify_ldt sys_modify_ldt 155 common pivot_root sys_pivot_root -156 64 _sysctl sys_sysctl +156 64 _sysctl sys_ni_syscall 157 common prctl sys_prctl 158 common arch_prctl sys_arch_prctl 159 common adjtimex sys_adjtimex diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 04e65f0698f6..215376d975a2 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -82,7 +82,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE # optimize sibling calls. # CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ - $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO @@ -151,7 +151,7 @@ KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic -KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector) +KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S index e78047d119f6..2cbd39939dc6 100644 --- a/arch/x86/entry/vdso/vdso32/note.S +++ b/arch/x86/entry/vdso/vdso32/note.S @@ -16,33 +16,3 @@ ELFNOTE_START(Linux, 0, "a") ELFNOTE_END BUILD_SALT - -#ifdef CONFIG_XEN -/* - * Add a special note telling glibc's dynamic linker a fake hardware - * flavor that it will use to choose the search path for libraries in the - * same way it uses real hardware capabilities like "mmx". - * We supply "nosegneg" as the fake capability, to indicate that we - * do not like negative offsets in instructions using segment overrides, - * since we implement those inefficiently. This makes it possible to - * install libraries optimized to avoid those access patterns in someplace - * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file - * corresponding to the bits here is needed to make ldconfig work right. - * It should contain: - * hwcap 1 nosegneg - * to match the mapping of bit to name that we give here. - * - * At runtime, the fake hardware feature will be considered to be present - * if its bit is set in the mask word. So, we start with the mask 0, and - * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen. - */ - -#include "../../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */ - -ELFNOTE_START(GNU, 2, "a") - .long 1 /* ncaps */ -VDSO32_NOTE_MASK: /* Symbol used by arch/x86/xen/setup.c */ - .long 0 /* mask */ - .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */ -ELFNOTE_END -#endif diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 68b38820b10e..67b411f7e8c4 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -130,11 +130,17 @@ struct rapl_pmus { struct rapl_pmu *pmus[]; }; +enum rapl_unit_quirk { + RAPL_UNIT_QUIRK_NONE, + RAPL_UNIT_QUIRK_INTEL_HSW, + RAPL_UNIT_QUIRK_INTEL_SPR, +}; + struct rapl_model { struct perf_msr *rapl_msrs; unsigned long events; unsigned int msr_power_unit; - bool apply_quirk; + enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ @@ -612,14 +618,28 @@ static int rapl_check_hw_unit(struct rapl_model *rm) for (i = 0; i < NR_RAPL_DOMAINS; i++) rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + switch (rm->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2 * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ - if (rm->apply_quirk) + case RAPL_UNIT_QUIRK_INTEL_HSW: + rapl_hw_unit[PERF_RAPL_RAM] = 16; + break; + /* + * SPR shares the same DRAM domain energy unit as HSW, plus it + * also has a fixed energy unit for Psys domain. + */ + case RAPL_UNIT_QUIRK_INTEL_SPR: rapl_hw_unit[PERF_RAPL_RAM] = 16; + rapl_hw_unit[PERF_RAPL_PSYS] = 0; + break; + default: + break; + } + /* * Calculate the timer rate: @@ -665,7 +685,7 @@ static const struct attribute_group *rapl_attr_update[] = { &rapl_events_pkg_group, &rapl_events_ram_group, &rapl_events_gpu_group, - &rapl_events_gpu_group, + &rapl_events_psys_group, NULL, }; @@ -698,7 +718,6 @@ static struct rapl_model model_snb = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), - .apply_quirk = false, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; @@ -707,7 +726,6 @@ static struct rapl_model model_snbep = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), - .apply_quirk = false, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; @@ -717,7 +735,6 @@ static struct rapl_model model_hsw = { BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), - .apply_quirk = false, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; @@ -726,7 +743,7 @@ static struct rapl_model model_hsx = { .events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), - .apply_quirk = true, + .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; @@ -734,7 +751,7 @@ static struct rapl_model model_hsx = { static struct rapl_model model_knl = { .events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), - .apply_quirk = true, + .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; @@ -745,14 +762,22 @@ static struct rapl_model model_skl = { BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), - .apply_quirk = false, + .msr_power_unit = MSR_RAPL_POWER_UNIT, + .rapl_msrs = intel_rapl_msrs, +}; + +static struct rapl_model model_spr = { + .events = BIT(PERF_RAPL_PP0) | + BIT(PERF_RAPL_PKG) | + BIT(PERF_RAPL_RAM) | + BIT(PERF_RAPL_PSYS), + .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, .rapl_msrs = intel_rapl_msrs, }; static struct rapl_model model_amd_fam17h = { .events = BIT(PERF_RAPL_PKG), - .apply_quirk = false, .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, .rapl_msrs = amd_rapl_msrs, }; @@ -787,6 +812,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &model_hsx), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L, &model_skl), X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl), + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr), X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h), X86_MATCH_VENDOR_FAM(HYGON, 0x18, &model_amd_fam17h), {}, diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 385d3d172ee1..ca8a657edf59 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -30,7 +30,6 @@ #include <linux/sched/task_stack.h> #include <linux/uaccess.h> -#include <asm/pgalloc.h> #include <asm/cacheflush.h> #include <asm/user32.h> #include <asm/ia32.h> diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h index 49bd6cf3eec9..7c0a52ca2f4d 100644 --- a/arch/x86/include/asm/device.h +++ b/arch/x86/include/asm/device.h @@ -3,9 +3,6 @@ #define _ASM_X86_DEVICE_H struct dev_archdata { -#ifdef CONFIG_IOMMU_API - void *iommu; /* hook for IOMMU specific extension */ -#endif }; struct pdev_archdata { diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 452beed7892b..b9a5d488f1a5 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -21,8 +21,6 @@ typedef struct user_i387_struct elf_fpregset_t; #ifdef __i386__ -typedef struct user_fxsr_struct elf_fpxregset_t; - #define R_386_NONE 0 #define R_386_32 1 #define R_386_PC32 2 diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b9527a54db99..0f0dd645b594 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -26,9 +26,9 @@ #ifndef __ASSEMBLY__ #include <linux/kernel.h> -#include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> +#include <asm/pgtable_types.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 47562147e70b..d98016b83755 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -9,7 +9,6 @@ #include <trace/events/tlb.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/paravirt.h> #include <asm/debugreg.h> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 60b944dd2df1..4f77b8f22e54 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -8,6 +8,7 @@ #include <asm/io.h> #include <asm/hyperv-tlfs.h> #include <asm/nospec-branch.h> +#include <asm/paravirt.h> typedef int (*hyperv_fill_flush_list_func)( struct hv_guest_mapping_flush_list *flush, @@ -54,6 +55,17 @@ typedef int (*hyperv_fill_flush_list_func)( vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK); #define hv_get_raw_timer() rdtsc_ordered() +/* + * Reference to pv_ops must be inline so objtool + * detection of noinstr violations can work correctly. + */ +static __always_inline void hv_setup_sched_clock(void *sched_clock) +{ +#ifdef CONFIG_PARAVIRT + pv_ops.time.sched_clock = sched_clock; +#endif +} + void hyperv_vector_handler(struct pt_regs *regs); static inline void hv_enable_stimer0_percpu_irq(int irq) {} diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 29aa7859bdee..62ad61d6fefc 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -7,7 +7,8 @@ #include <linux/pagemap.h> #define __HAVE_ARCH_PTE_ALLOC_ONE -#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ +#define __HAVE_ARCH_PGD_FREE +#include <asm-generic/pgalloc.h> static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } @@ -86,30 +87,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, #define pmd_pgtable(pmd) pmd_page(pmd) #if CONFIG_PGTABLE_LEVELS > 2 -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - struct page *page; - gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO; - - if (mm == &init_mm) - gfp &= ~__GFP_ACCOUNT; - page = alloc_pages(gfp, 0); - if (!page) - return NULL; - if (!pgtable_pmd_page_ctor(page)) { - __free_pages(page, 0); - return NULL; - } - return (pmd_t *)page_address(page); -} - -static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) -{ - BUG_ON((unsigned long)pmd & (PAGE_SIZE-1)); - pgtable_pmd_page_dtor(virt_to_page(pmd)); - free_page((unsigned long)pmd); -} - extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, @@ -147,21 +124,6 @@ static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pu set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - gfp_t gfp = GFP_KERNEL_ACCOUNT; - - if (mm == &init_mm) - gfp &= ~__GFP_ACCOUNT; - return (pud_t *)get_zeroed_page(gfp); -} - -static inline void pud_free(struct mm_struct *mm, pud_t *pud) -{ - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); -} - extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 6e81788a30c1..28996fe19301 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -25,7 +25,7 @@ void entry_SYSENTER_compat(void); void __end_entry_SYSENTER_compat(void); void entry_SYSCALL_compat(void); void entry_INT80_compat(void); -#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +#ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); #endif #endif diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 6669164abadc..9646c300f128 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -301,7 +301,7 @@ static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; extern void early_ignore_irq(void); -#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) +#ifdef CONFIG_XEN_PV extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE]; #endif diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index e15f364efbcc..c0538f82c9a2 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -5,16 +5,6 @@ #include <linux/cpumask.h> #include <asm/percpu.h> -/* - * We need the APIC definitions automatically as part of 'smp.h' - */ -#ifdef CONFIG_X86_LOCAL_APIC -# include <asm/mpspec.h> -# include <asm/apic.h> -# ifdef CONFIG_X86_IO_APIC -# include <asm/io_apic.h> -# endif -#endif #include <asm/thread_info.h> #include <asm/cpumask.h> diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index b7b2624fba86..01a300a9700b 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -6,6 +6,7 @@ #define _ASM_X86_TSC_H #include <asm/processor.h> +#include <asm/cpufeature.h> /* * Standard way to access the cycle counter. diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 2f3e8f2a958f..ecefaffd15d4 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -33,7 +33,7 @@ static inline void set_fs(mm_segment_t fs) set_thread_flag(TIF_FSCHECK); } -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define user_addr_max() (current->thread.addr_limit.seg) /* diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index fb81fea99093..df01d7349d79 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -241,7 +241,8 @@ static u64 vread_hvclock(void) } #endif -static inline u64 __arch_get_hw_counter(s32 clock_mode) +static inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_data *vd) { if (likely(clock_mode == VDSO_CLOCKMODE_TSC)) return (u64)rdtsc_ordered(); diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index ba4c1b15908b..454b20815f35 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -82,7 +82,7 @@ struct xen_dm_op_buf; * - clobber the rest * * The result certainly isn't pretty, and it really shows up cpp's - * weakness as as macro language. Sorry. (But let's just give thanks + * weakness as a macro language. Sorry. (But let's just give thanks * there aren't more than 5 arguments...) */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c826cddae157..c3daf0aaa0ee 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -7,6 +7,7 @@ #include <linux/mutex.h> #include <linux/list.h> #include <linux/stringify.h> +#include <linux/highmem.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/memory.h> @@ -874,8 +875,6 @@ static void *__text_poke(void *addr, const void *opcode, size_t len) */ BUG_ON(!pages[0] || (cross_page_boundary && !pages[1])); - local_irq_save(flags); - /* * Map the page without the global bit, as TLB flushing is done with * flush_tlb_mm_range(), which is intended for non-global PTEs. @@ -892,6 +891,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len) */ VM_BUG_ON(!ptep); + local_irq_save(flags); + pte = mk_pte(pages[0], pgprot); set_pte_at(poking_mm, poking_addr, ptep, pte); @@ -941,8 +942,8 @@ static void *__text_poke(void *addr, const void *opcode, size_t len) */ BUG_ON(memcmp(addr, opcode, len)); - pte_unmap_unlock(ptep, ptl); local_irq_restore(flags); + pte_unmap_unlock(ptep, ptl); return addr; } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e0e2f020ec02..5f943b938167 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -40,13 +40,13 @@ #include <asm/irq_remapping.h> #include <asm/perf_event.h> #include <asm/x86_init.h> -#include <asm/pgalloc.h> #include <linux/atomic.h> #include <asm/mpspec.h> #include <asm/i8259.h> #include <asm/proto.h> #include <asm/traps.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/io_apic.h> #include <asm/desc.h> #include <asm/hpet.h> diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 98c9bb75d185..780c702969b7 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -10,6 +10,7 @@ * like self-ipi, etc... */ #include <linux/cpumask.h> +#include <linux/thread_info.h> #include <asm/apic.h> diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 38b5b51d42f6..98d015a4405a 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -9,6 +9,7 @@ #include <linux/smp.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include "local.h" diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index d1fc62a67320..34a992e275ef 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -9,6 +9,7 @@ * Bits copied from original nmi.c file * */ +#include <linux/thread_info.h> #include <asm/apic.h> #include <asm/nmi.h> diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 6ca0f91372fd..387154e39e08 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -2,6 +2,7 @@ #include <linux/cpumask.h> #include <linux/smp.h> +#include <asm/io_apic.h> #include "local.h" diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h index 04797f05ce94..a997d849509a 100644 --- a/arch/x86/kernel/apic/local.h +++ b/arch/x86/kernel/apic/local.h @@ -10,6 +10,7 @@ #include <linux/jump_label.h> +#include <asm/irq_vectors.h> #include <asm/apic.h> /* APIC flat 64 */ diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 67b33d67002f..7bda71def557 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -10,6 +10,7 @@ #include <linux/errno.h> #include <linux/smp.h> +#include <asm/io_apic.h> #include <asm/apic.h> #include <asm/acpi.h> diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c index 29f0e0984557..bd3835d6b535 100644 --- a/arch/x86/kernel/apic/probe_64.c +++ b/arch/x86/kernel/apic/probe_64.c @@ -8,6 +8,7 @@ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and * James Cleverdon. */ +#include <linux/thread_info.h> #include <asm/apic.h> #include "local.h" diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index dba6a83bc349..93792b457b81 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,8 +17,7 @@ KCOV_INSTRUMENT_perf_event.o := n KCSAN_SANITIZE_common.o := n # Make sure load_percpu_segment has no stackprotector -nostackp := $(call cc-option, -fno-stack-protector) -CFLAGS_common.o := $(nostackp) +CFLAGS_common.o := -fno-stack-protector obj-y := cacheinfo.o scattered.o topology.o obj-y += common.o diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index 1da9b1c9a2db..0b2c03943ac6 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -11,14 +11,15 @@ #include <linux/interrupt.h> #include <asm/apic.h> +#include <asm/cpufeatures.h> #include <asm/desc.h> #include <asm/hypervisor.h> #include <asm/idtentry.h> #include <asm/irq_regs.h> -static uint32_t __init acrn_detect(void) +static u32 __init acrn_detect(void) { - return hypervisor_cpuid_base("ACRNACRNACRN\0\0", 0); + return hypervisor_cpuid_base("ACRNACRNACRN", 0); } static void __init acrn_init_platform(void) @@ -29,12 +30,7 @@ static void __init acrn_init_platform(void) static bool acrn_x2apic_available(void) { - /* - * x2apic is not supported for now. Future enablement will have to check - * X86_FEATURE_X2APIC to determine whether x2apic is supported in the - * guest. - */ - return false; + return boot_cpu_has(X86_FEATURE_X2APIC); } static void (*acrn_intr_handler)(void); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index d4806eac9325..dcc3d943c68f 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -15,6 +15,7 @@ #include <asm/cpu.h> #include <asm/spec-ctrl.h> #include <asm/smp.h> +#include <asm/numa.h> #include <asm/pci-direct.h> #include <asm/delay.h> #include <asm/debugreg.h> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index f0b743a2fe9c..d3f0db463f96 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -31,6 +31,7 @@ #include <asm/intel-family.h> #include <asm/e820/api.h> #include <asm/hypervisor.h> +#include <asm/tlbflush.h> #include "cpu.h" @@ -1549,7 +1550,12 @@ static ssize_t l1tf_show_state(char *buf) static ssize_t itlb_multihit_show_state(char *buf) { - if (itlb_multihit_kvm_mitigation) + if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !boot_cpu_has(X86_FEATURE_VMX)) + return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + else if (!(cr4_read_shadow() & X86_CR4_VMXE)) + return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + else if (itlb_multihit_kvm_mitigation) return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); else return sprintf(buf, "KVM: Vulnerable\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 965474d78cef..c5d6f17d9b9d 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -45,6 +45,7 @@ #include <asm/mtrr.h> #include <asm/hwcap2.h> #include <linux/numa.h> +#include <asm/numa.h> #include <asm/asm.h> #include <asm/bugs.h> #include <asm/cpu.h> diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 4e28c1fc8749..ac6c30e5801d 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -10,6 +10,7 @@ #include <asm/cpu.h> #include <asm/smp.h> +#include <asm/numa.h> #include <asm/cacheinfo.h> #include <asm/spec-ctrl.h> #include <asm/delay.h> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b6b7b38dff5f..59a1e3ce3f14 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -23,6 +23,7 @@ #include <asm/cmdline.h> #include <asm/traps.h> #include <asm/resctrl.h> +#include <asm/numa.h> #ifdef CONFIG_X86_64 #include <linux/topology.h> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index af94f05a5c66..31125448b174 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -361,13 +361,6 @@ static void __init ms_hyperv_init_platform(void) #endif } -void hv_setup_sched_clock(void *sched_clock) -{ -#ifdef CONFIG_PARAVIRT - pv_ops.time.sched_clock = sched_clock; -#endif -} - const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .name = "Microsoft Hyper-V", .detect = ms_hyperv_platform, diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index fd87b59452a3..a8f3af257e26 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -230,7 +230,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem) int ret = 0; /* Exclude the low 1M because it is always reserved */ - ret = crash_exclude_mem_range(cmem, 0, 1<<20); + ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1); if (ret) return ret; diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 8d85e00bb40a..a0e8fc7d85f1 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -20,6 +20,7 @@ #include <asm/irqdomain.h> #include <asm/hpet.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/pci_x86.h> #include <asm/setup.h> #include <asm/i8259.h> diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 7a2bf884fede..038e19c0019e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -611,6 +611,10 @@ static void check_xstate_against_struct(int nr) * This essentially double-checks what the cpu told us about * how large the XSAVE buffer needs to be. We are recalculating * it to be safe. + * + * Dynamic XSAVE features allocate their own buffers and are not + * covered by these checks. Only the size of the buffer for task->fpu + * is checked here. */ static void do_extra_xstate_size_checks(void) { @@ -673,6 +677,33 @@ static unsigned int __init get_xsaves_size(void) return ebx; } +/* + * Get the total size of the enabled xstates without the dynamic supervisor + * features. + */ +static unsigned int __init get_xsaves_size_no_dynamic(void) +{ + u64 mask = xfeatures_mask_dynamic(); + unsigned int size; + + if (!mask) + return get_xsaves_size(); + + /* Disable dynamic features. */ + wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor()); + + /* + * Ask the hardware what size is required of the buffer. + * This is the size required for the task->fpu buffer. + */ + size = get_xsaves_size(); + + /* Re-enable dynamic features so XSAVES will work on them again. */ + wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask); + + return size; +} + static unsigned int __init get_xsave_size(void) { unsigned int eax, ebx, ecx, edx; @@ -710,7 +741,7 @@ static int __init init_xstate_size(void) xsave_size = get_xsave_size(); if (boot_cpu_has(X86_FEATURE_XSAVES)) - possible_xstate_size = get_xsaves_size(); + possible_xstate_size = get_xsaves_size_no_dynamic(); else possible_xstate_size = xsave_size; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 51504566b3a6..7edbd5ee5ed4 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -286,6 +286,7 @@ extern void ftrace_regs_caller_ret(void); extern void ftrace_caller_end(void); extern void ftrace_caller_op_ptr(void); extern void ftrace_regs_caller_op_ptr(void); +extern void ftrace_regs_caller_jmp(void); /* movq function_trace_op(%rip), %rdx */ /* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */ @@ -316,6 +317,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long end_offset; unsigned long op_offset; unsigned long call_offset; + unsigned long jmp_offset; unsigned long offset; unsigned long npages; unsigned long size; @@ -333,11 +335,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) end_offset = (unsigned long)ftrace_regs_caller_end; op_offset = (unsigned long)ftrace_regs_caller_op_ptr; call_offset = (unsigned long)ftrace_regs_call; + jmp_offset = (unsigned long)ftrace_regs_caller_jmp; } else { start_offset = (unsigned long)ftrace_caller; end_offset = (unsigned long)ftrace_caller_end; op_offset = (unsigned long)ftrace_caller_op_ptr; call_offset = (unsigned long)ftrace_call; + jmp_offset = 0; } size = end_offset - start_offset; @@ -367,10 +371,14 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) if (WARN_ON(ret < 0)) goto fail; + /* No need to test direct calls on created trampolines */ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { - ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller); - ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); - if (WARN_ON(ret < 0)) + /* NOP the jnz 1f; but make sure it's a 2 byte jnz */ + ip = trampoline + (jmp_offset - start_offset); + if (WARN_ON(*(char *)ip != 0x75)) + goto fail; + ret = copy_from_kernel_nofault(ip, ideal_nops[2], 2); + if (ret < 0) goto fail; } diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 083a3da7bb73..ac3d5f22fe64 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -241,22 +241,10 @@ SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) */ movq ORIG_RAX(%rsp), %rax testq %rax, %rax - jz 1f +SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL) + jnz 1f - /* Swap the flags with orig_rax */ - movq MCOUNT_REG_SIZE(%rsp), %rdi - movq %rdi, MCOUNT_REG_SIZE-8(%rsp) - movq %rax, MCOUNT_REG_SIZE(%rsp) - - restore_mcount_regs 8 - /* Restore flags */ - popfq - -SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL); - UNWIND_HINT_RET_OFFSET - jmp ftrace_epilogue - -1: restore_mcount_regs + restore_mcount_regs /* Restore flags */ popfq @@ -269,6 +257,17 @@ SYM_INNER_LABEL(ftrace_regs_caller_ret, SYM_L_GLOBAL); SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) jmp ftrace_epilogue + /* Swap the flags with orig_rax */ +1: movq MCOUNT_REG_SIZE(%rsp), %rdi + movq %rdi, MCOUNT_REG_SIZE-8(%rsp) + movq %rax, MCOUNT_REG_SIZE(%rsp) + + restore_mcount_regs 8 + /* Restore flags */ + popfq + UNWIND_HINT_RET_OFFSET + jmp ftrace_epilogue + SYM_FUNC_END(ftrace_regs_caller) diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index f66a6b90f954..7ed84c282233 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -134,38 +134,7 @@ SYM_CODE_START(startup_32) movl %eax,pa(initial_page_table+0xffc) #endif -#ifdef CONFIG_PARAVIRT - /* This is can only trip for a broken bootloader... */ - cmpw $0x207, pa(boot_params + BP_version) - jb .Ldefault_entry - - /* Paravirt-compatible boot parameters. Look to see what architecture - we're booting under. */ - movl pa(boot_params + BP_hardware_subarch), %eax - cmpl $num_subarch_entries, %eax - jae .Lbad_subarch - - movl pa(subarch_entries)(,%eax,4), %eax - subl $__PAGE_OFFSET, %eax - jmp *%eax - -.Lbad_subarch: -SYM_INNER_LABEL_ALIGN(xen_entry, SYM_L_WEAK) - /* Unknown implementation; there's really - nothing we can do at this point. */ - ud2a - - __INITDATA - -subarch_entries: - .long .Ldefault_entry /* normal x86/PC */ - .long xen_entry /* Xen hypervisor */ - .long .Ldefault_entry /* Moorestown MID */ -num_subarch_entries = (. - subarch_entries) / 4 -.previous -#else jmp .Ldefault_entry -#endif /* CONFIG_PARAVIRT */ SYM_CODE_END(startup_32) #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index dd73135d7cee..beb1bada1b0a 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -22,6 +22,8 @@ #include <asm/timer.h> #include <asm/hw_irq.h> #include <asm/desc.h> +#include <asm/io_apic.h> +#include <asm/acpi.h> #include <asm/apic.h> #include <asm/setup.h> #include <asm/i8259.h> diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 6eb8b50ea07e..4eb8f2d19a87 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -13,6 +13,8 @@ #include <linux/reboot.h> #include <linux/serial_8250.h> #include <asm/apic.h> +#include <asm/io_apic.h> +#include <asm/acpi.h> #include <asm/cpu.h> #include <asm/hypervisor.h> #include <asm/i8259.h> diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index afac7ccce72f..411af4aa7b51 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -19,10 +19,11 @@ #include <linux/smp.h> #include <linux/pci.h> +#include <asm/io_apic.h> +#include <asm/acpi.h> #include <asm/irqdomain.h> #include <asm/mtrr.h> #include <asm/mpspec.h> -#include <asm/pgalloc.h> #include <asm/io_apic.h> #include <asm/proto.h> #include <asm/bios_ebda.h> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index d6f946707270..9afefe325acb 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -390,7 +390,7 @@ unsigned long x86_fsgsbase_read_task(struct task_struct *task, */ mutex_lock(&task->mm->context.lock); ldt = task->mm->context.ldt; - if (unlikely(idx >= ldt->nr_entries)) + if (unlikely(!ldt || idx >= ldt->nr_entries)) base = 0; else base = get_desc_base(ldt->entries + idx); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b9a68d8e06d8..3511736fbc74 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -25,6 +25,7 @@ #include <xen/xen.h> #include <asm/apic.h> +#include <asm/numa.h> #include <asm/bios_ebda.h> #include <asm/bugs.h> #include <asm/cpu.h> diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index b8810ebbc8ae..0a2ec801b63f 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -31,6 +31,7 @@ #include <linux/init.h> #include <linux/smp.h> #include <linux/irq.h> +#include <asm/io_apic.h> #include <asm/cpu.h> static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 438fc554d48d..1f66d2d1e998 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -62,7 +62,6 @@ #ifdef CONFIG_X86_64 #include <asm/x86_init.h> -#include <asm/pgalloc.h> #include <asm/proto.h> #else #include <asm/processor-flags.h> diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c index 4fec6f3a1858..6555a857a1e6 100644 --- a/arch/x86/kernel/tsc_msr.c +++ b/arch/x86/kernel/tsc_msr.c @@ -7,6 +7,7 @@ */ #include <linux/kernel.h> +#include <linux/thread_info.h> #include <asm/apic.h> #include <asm/cpu_device_id.h> @@ -133,10 +134,15 @@ static const struct freq_desc freq_desc_ann = { .mask = 0x0f, }; -/* 24 MHz crystal? : 24 * 13 / 4 = 78 MHz */ +/* + * 24 MHz crystal? : 24 * 13 / 4 = 78 MHz + * Frequency step for Lightning Mountain SoC is fixed to 78 MHz, + * so all the frequency entries are 78000. + */ static const struct freq_desc freq_desc_lgm = { .use_msr_plat = true, - .freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }, + .freqs = { 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000, + 78000, 78000, 78000, 78000, 78000, 78000, 78000, 78000 }, .mask = 0x0f, }; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index fa873e3e6e90..3fd6eec202d7 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -370,7 +370,8 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_EDX, F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) + F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | + F(SERIALIZE) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index af9cdb426dd2..814d3aee5cef 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -900,6 +900,7 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages) kvm_request_apicv_update(vcpu->kvm, false, APICV_INHIBIT_REASON_HYPERV); synic->active = true; synic->dont_zero_synic_pages = dont_zero_synic_pages; + synic->control = HV_SYNIC_CONTROL_ENABLE; return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 12ea77f99ff3..599d73206299 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -820,22 +820,22 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) return 1; - if (cr0 & X86_CR0_PG) { #ifdef CONFIG_X86_64 - if (!is_paging(vcpu) && (vcpu->arch.efer & EFER_LME)) { - int cs_db, cs_l; + if ((vcpu->arch.efer & EFER_LME) && !is_paging(vcpu) && + (cr0 & X86_CR0_PG)) { + int cs_db, cs_l; - if (!is_pae(vcpu)) - return 1; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - if (cs_l) - return 1; - } else -#endif - if (is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + if (!is_pae(vcpu)) + return 1; + kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + if (cs_l) return 1; } +#endif + if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) && + is_pae(vcpu) && ((cr0 ^ old_cr0) & pdptr_bits) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu))) + return 1; if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) return 1; @@ -10667,11 +10667,17 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + int ret; irqfd->producer = prod; + kvm_arch_start_assignment(irqfd->kvm); + ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, + prod->irq, irqfd->gsi, 1); + + if (ret) + kvm_arch_end_assignment(irqfd->kvm); - return kvm_x86_ops.update_pi_irte(irqfd->kvm, - prod->irq, irqfd->gsi, 1); + return ret; } void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, @@ -10694,6 +10700,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); + + kvm_arch_end_assignment(irqfd->kvm); } int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 6110bce7237b..d46fff11f06f 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -24,7 +24,7 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_cmdline.o = -pg endif -CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector) +CFLAGS_cmdline.o := -fno-stack-protector endif inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index f7fd0e868c9c..5864219221ca 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -22,10 +22,9 @@ obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o mmap.o \ obj-y += pat/ # Make sure __phys_addr has no stackprotector -nostackp := $(call cc-option, -fno-stack-protector) -CFLAGS_physaddr.o := $(nostackp) -CFLAGS_setup_nx.o := $(nostackp) -CFLAGS_mem_encrypt_identity.o := $(nostackp) +CFLAGS_physaddr.o := -fno-stack-protector +CFLAGS_setup_nx.o := -fno-stack-protector +CFLAGS_mem_encrypt_identity.o := -fno-stack-protector CFLAGS_fault.o := -I $(srctree)/$(src)/../include/asm/trace diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 5e5edd2ec893..35f1498e9832 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -21,7 +21,6 @@ #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ -#include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ @@ -1140,7 +1139,7 @@ void do_user_addr_fault(struct pt_regs *regs, struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; - vm_fault_t fault, major = 0; + vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; @@ -1292,8 +1291,7 @@ good_area: * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ - fault = handle_mm_fault(vma, address, flags); - major |= fault & VM_FAULT_MAJOR; + fault = handle_mm_fault(vma, address, flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { @@ -1320,18 +1318,6 @@ good_area: return; } - /* - * Major/minor page fault accounting. If any of the events - * returned VM_FAULT_MAJOR, we account it as a major fault. - */ - if (major) { - tsk->maj_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); - } else { - tsk->min_flt++; - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - } - check_v8086_mode(regs, address, tsk); } NOKPROBE_SYMBOL(do_user_addr_fault); diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index cf5781142716..a0d023cb4292 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -17,7 +17,6 @@ #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> -#include <asm/pgalloc.h> #include <asm/elf.h> #if 0 /* This is just for testing */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8b4afad84f4a..7c055259de3a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -52,6 +52,7 @@ #include <asm/cpu_entry_area.h> #include <asm/init.h> #include <asm/pgtable_areas.h> +#include <asm/numa.h> #include "mm_internal.h" @@ -678,7 +679,6 @@ void __init initmem_init(void) #endif memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0); - sparse_memory_present_with_active_regions(0); #ifdef CONFIG_FLATMEM max_mapnr = IS_ENABLED(CONFIG_HIGHMEM) ? highend_pfn : max_low_pfn; @@ -718,7 +718,6 @@ void __init paging_init(void) * NOTE: at this point the bootmem allocator is fully available. */ olpc_dt_build_devicetree(); - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); zone_sizes_init(); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 449e071240e1..a4ac13cc3fdc 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -817,7 +817,6 @@ void __init initmem_init(void) void __init paging_init(void) { - sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); /* @@ -1453,6 +1452,15 @@ static unsigned long probe_memory_block_size(void) goto done; } + /* + * Use max block size to minimize overhead on bare metal, where + * alignment for memory hotplug isn't a concern. + */ + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) { + bz = MAX_BLOCK_SIZE; + goto done; + } + /* Find the largest allowed block size that aligns to memory end */ for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) { if (IS_ALIGNED(boot_mem_end, bz)) @@ -1510,10 +1518,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, if (pmd_none(*pmd)) { void *p; - if (altmap) - p = altmap_alloc_block_buf(PMD_SIZE, altmap); - else - p = vmemmap_alloc_block_buf(PMD_SIZE, node); + p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); if (p) { pte_t entry; @@ -1540,7 +1545,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start, vmemmap_verify((pte_t *)pmd, node, addr, next); continue; } - if (vmemmap_populate_basepages(addr, next, node)) + if (vmemmap_populate_basepages(addr, next, node, NULL)) return -ENOMEM; } return 0; @@ -1552,7 +1557,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, int err; if (end - start < PAGES_PER_SECTION * sizeof(struct page)) - err = vmemmap_populate_basepages(start, end, node); + err = vmemmap_populate_basepages(start, end, node, NULL); else if (boot_cpu_has(X86_FEATURE_PSE)) err = vmemmap_populate_hugepages(start, end, node, altmap); else if (altmap) { @@ -1560,7 +1565,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, __func__); err = -ENOMEM; } else - err = vmemmap_populate_basepages(start, end, node); + err = vmemmap_populate_basepages(start, end, node, NULL); if (!err) sync_global_pgds(start, end - 1); return err; diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index fb620fd9dae9..6e6b39710e5f 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -26,7 +26,6 @@ #include <linux/memblock.h> #include <linux/pgtable.h> -#include <asm/pgalloc.h> #include <asm/setup.h> #include <asm/kaslr.h> diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index b05f45e5e8e2..aa76ec2d359b 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -929,5 +929,4 @@ int memory_add_physaddr_to_nid(u64 start) nid = numa_meminfo.blk[0].nid; return nid; } -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); #endif diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 1953685c2ddf..c234634e26ba 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -11,7 +11,6 @@ #include <linux/spinlock.h> #include <asm/cpu_entry_area.h> -#include <asm/pgalloc.h> #include <asm/fixmap.h> #include <asm/e820/api.h> #include <asm/tlb.h> diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index a8a924b3c335..1aab92930569 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -34,7 +34,6 @@ #include <asm/vsyscall.h> #include <asm/cmdline.h> #include <asm/pti.h> -#include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/sections.h> diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 0c67a5a94de3..b8c9a5b87f37 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -557,12 +557,12 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_z * Device [8086:2fc0] * Erratum HSE43 * CONFIG_TDP_NOMINAL CSR Implemented at Incorrect Offset - * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html + * https://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v3-spec-update.html * * Devices [8086:6f60,6fa0,6fc0] * Erratum BDF2 * PCI BARs in the Home Agent Will Return Non-Zero Values During Enumeration - * http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html + * https://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html */ static void pci_invalid_bar(struct pci_dev *dev) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index e3f1ca316068..9f9aad42ccff 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -62,7 +62,7 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) #ifdef CONFIG_ACPI static int xen_register_pirq(u32 gsi, int triggering, bool set_pirq) { - int rc, pirq = -1, irq = -1; + int rc, pirq = -1, irq; struct physdev_map_pirq map_irq; int shareable = 0; char *name; diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index a6e5f2c1805d..a2f447dffea6 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -11,6 +11,7 @@ #include <linux/slab.h> #include <asm/efi.h> #include <linux/io.h> +#include <asm/pgalloc.h> #include <asm/uv/bios.h> #include <asm/uv/uv_hub.h> diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 37923d715741..6907b523e856 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -3,8 +3,7 @@ OBJECT_FILES_NON_STANDARD_hibernate_asm_$(BITS).o := y # __restore_processor_state() restores %gs after S3 resume and so should not # itself be stack-protected -nostackp := $(call cc-option, -fno-stack-protector) -CFLAGS_cpu.o := $(nostackp) +CFLAGS_cpu.o := -fno-stack-protector obj-$(CONFIG_PM_SLEEP) += cpu.o obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index d147f1b2c925..cd3914fc9f3d 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -98,7 +98,7 @@ static int get_e820_md5(struct e820_table *table, void *buf) if (crypto_shash_digest(desc, (u8 *)table, size, buf)) ret = -EINVAL; - kzfree(desc); + kfree_sensitive(desc); free_tfm: crypto_free_shash(tfm); diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 088bd764e0b7..95ea17a9d20c 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -32,9 +32,9 @@ KCOV_INSTRUMENT := n # make up the standalone purgatory.ro PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel -PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss +PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss -g0 PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING -PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector) +PURGATORY_CFLAGS += -fno-stack-protector # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not @@ -64,6 +64,9 @@ CFLAGS_sha256.o += $(PURGATORY_CFLAGS) CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_string.o += $(PURGATORY_CFLAGS) +AFLAGS_REMOVE_setup-x86_$(BITS).o += -Wa,-gdwarf-2 +AFLAGS_REMOVE_entry64.o += -Wa,-gdwarf-2 + $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE $(call if_changed,ld) diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 0caddd6acb22..5943387e3f35 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -42,7 +42,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE # optimize sibling calls. # CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ - $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \ + $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \ -fno-omit-frame-pointer -foptimize-sibling-calls $(vobjs): KBUILD_CFLAGS += $(CFL) diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 1aded63a95cb..218acbd5c7a0 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -19,6 +19,7 @@ config XEN_PV bool "Xen PV guest support" default y depends on XEN + depends on X86_64 select PARAVIRT_XXL select XEN_HAVE_PVMMU select XEN_HAVE_VPMU @@ -50,7 +51,7 @@ config XEN_PVHVM_SMP config XEN_512GB bool "Limit Xen pv-domain memory to 512GB" - depends on XEN_PV && X86_64 + depends on XEN_PV default y help Limit paravirtualized user domains to 512GB of RAM. diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 084de77a109e..fc5c5ba4aacb 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -OBJECT_FILES_NON_STANDARD_xen-asm_$(BITS).o := y +OBJECT_FILES_NON_STANDARD_xen-asm.o := y ifdef CONFIG_FUNCTION_TRACER # Do not profile debug and lowlevel utilities @@ -9,9 +9,8 @@ CFLAGS_REMOVE_irq.o = -pg endif # Make sure early boot has no stackprotector -nostackp := $(call cc-option, -fno-stack-protector) -CFLAGS_enlighten_pv.o := $(nostackp) -CFLAGS_mmu_pv.o := $(nostackp) +CFLAGS_enlighten_pv.o := -fno-stack-protector +CFLAGS_mmu_pv.o := -fno-stack-protector obj-y += enlighten.o obj-y += mmu.o @@ -34,7 +33,6 @@ obj-$(CONFIG_XEN_PV) += mmu_pv.o obj-$(CONFIG_XEN_PV) += irq.o obj-$(CONFIG_XEN_PV) += multicalls.o obj-$(CONFIG_XEN_PV) += xen-asm.o -obj-$(CONFIG_XEN_PV) += xen-asm_$(BITS).o obj-$(CONFIG_XEN_PVH) += enlighten_pvh.o diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 5e53bfbe5823..e82fd1910dae 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/init.h> +#include <linux/thread_info.h> #include <asm/x86_init.h> #include <asm/apic.h> +#include <asm/io_apic.h> #include <asm/xen/hypercall.h> #include <xen/xen.h> @@ -58,10 +60,6 @@ static u32 xen_apic_read(u32 reg) if (reg == APIC_LVR) return 0x14; -#ifdef CONFIG_X86_32 - if (reg == APIC_LDR) - return SET_APIC_LOGICAL_ID(1UL << smp_processor_id()); -#endif if (reg != APIC_ID) return 0; @@ -127,14 +125,6 @@ static int xen_phys_pkg_id(int initial_apic_id, int index_msb) return initial_apic_id >> index_msb; } -#ifdef CONFIG_X86_32 -static int xen_x86_32_early_logical_apicid(int cpu) -{ - /* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */ - return 1 << cpu; -} -#endif - static void xen_noop(void) { } @@ -197,11 +187,6 @@ static struct apic xen_pv_apic = { .icr_write = xen_apic_icr_write, .wait_icr_idle = xen_noop, .safe_wait_icr_idle = xen_safe_apic_wait_icr_idle, - -#ifdef CONFIG_X86_32 - /* generic_processor_info and setup_local_APIC. */ - .x86_32_early_logical_apicid = xen_x86_32_early_logical_apicid, -#endif }; static void __init xen_apic_check(void) diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 3e89b0067ff0..9e87ab010c82 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -11,6 +11,7 @@ #include <asm/cpu.h> #include <asm/smp.h> +#include <asm/io_apic.h> #include <asm/reboot.h> #include <asm/setup.h> #include <asm/idtentry.h> diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 2aab43a13a8c..22e741e0b10c 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -119,14 +119,6 @@ static void __init xen_banner(void) printk(KERN_INFO "Xen version: %d.%d%s%s\n", version >> 16, version & 0xffff, extra.extraversion, xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : ""); - -#ifdef CONFIG_X86_32 - pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n" - "Support for running as 32-bit PV-guest under Xen will soon be removed\n" - "from the Linux kernel!\n" - "Please use either a 64-bit kernel or switch to HVM or PVH mode!\n" - "WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"); -#endif } static void __init xen_pv_init_platform(void) @@ -353,15 +345,13 @@ static void set_aliased_prot(void *v, pgprot_t prot) pte_t *ptep; pte_t pte; unsigned long pfn; - struct page *page; unsigned char dummy; + void *va; ptep = lookup_address((unsigned long)v, &level); BUG_ON(ptep == NULL); pfn = pte_pfn(*ptep); - page = pfn_to_page(pfn); - pte = pfn_pte(pfn, prot); /* @@ -391,14 +381,10 @@ static void set_aliased_prot(void *v, pgprot_t prot) if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); - if (!PageHighMem(page)) { - void *av = __va(PFN_PHYS(pfn)); + va = __va(PFN_PHYS(pfn)); - if (av != v) - if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0)) - BUG(); - } else - kmap_flush_unused(); + if (va != v && HYPERVISOR_update_va_mapping((unsigned long)va, pte, 0)) + BUG(); preempt_enable(); } @@ -538,30 +524,12 @@ static void load_TLS_descriptor(struct thread_struct *t, static void xen_load_tls(struct thread_struct *t, unsigned int cpu) { /* - * XXX sleazy hack: If we're being called in a lazy-cpu zone - * and lazy gs handling is enabled, it means we're in a - * context switch, and %gs has just been saved. This means we - * can zero it out to prevent faults on exit from the - * hypervisor if the next process has no %gs. Either way, it - * has been saved, and the new value will get loaded properly. - * This will go away as soon as Xen has been modified to not - * save/restore %gs for normal hypercalls. - * - * On x86_64, this hack is not used for %gs, because gs points - * to KERNEL_GS_BASE (and uses it for PDA references), so we - * must not zero %gs on x86_64 - * - * For x86_64, we need to zero %fs, otherwise we may get an + * In lazy mode we need to zero %fs, otherwise we may get an * exception between the new %fs descriptor being loaded and * %fs being effectively cleared at __switch_to(). */ - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) { -#ifdef CONFIG_X86_32 - lazy_load_gs(0); -#else + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) loadsegment(fs, 0); -#endif - } xen_mc_batch(); @@ -572,13 +540,11 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu) xen_mc_issue(PARAVIRT_LAZY_CPU); } -#ifdef CONFIG_X86_64 static void xen_load_gs_index(unsigned int idx) { if (HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, idx)) BUG(); } -#endif static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, const void *ptr) @@ -597,7 +563,6 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, preempt_enable(); } -#ifdef CONFIG_X86_64 void noist_exc_debug(struct pt_regs *regs); DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) @@ -697,7 +662,6 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) return true; } -#endif static int cvt_gate_to_trap(int vector, const gate_desc *val, struct trap_info *info) @@ -710,10 +674,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, info->vector = vector; addr = gate_offset(val); -#ifdef CONFIG_X86_64 if (!get_trap_addr((void **)&addr, val->bits.ist)) return 0; -#endif /* CONFIG_X86_64 */ info->address = addr; info->cs = gate_segment(val); @@ -958,15 +920,12 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err) static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) { int ret; -#ifdef CONFIG_X86_64 unsigned int which; u64 base; -#endif ret = 0; switch (msr) { -#ifdef CONFIG_X86_64 case MSR_FS_BASE: which = SEGBASE_FS; goto set; case MSR_KERNEL_GS_BASE: which = SEGBASE_GS_USER; goto set; case MSR_GS_BASE: which = SEGBASE_GS_KERNEL; goto set; @@ -976,7 +935,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high) if (HYPERVISOR_set_segment_base(which, base) != 0) ret = -EIO; break; -#endif case MSR_STAR: case MSR_CSTAR: @@ -1058,9 +1016,7 @@ void __init xen_setup_vcpu_info_placement(void) static const struct pv_info xen_info __initconst = { .shared_kernel_pmd = 0, -#ifdef CONFIG_X86_64 .extra_user_64bit_cs = FLAT_USER_CS64, -#endif .name = "Xen", }; @@ -1086,18 +1042,14 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_pmc = xen_read_pmc, .iret = xen_iret, -#ifdef CONFIG_X86_64 .usergs_sysret64 = xen_sysret64, -#endif .load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, .load_gdt = xen_load_gdt, .load_idt = xen_load_idt, .load_tls = xen_load_tls, -#ifdef CONFIG_X86_64 .load_gs_index = xen_load_gs_index, -#endif .alloc_ldt = xen_alloc_ldt, .free_ldt = xen_free_ldt, @@ -1364,15 +1316,7 @@ asmlinkage __visible void __init xen_start_kernel(void) /* keep using Xen gdt for now; no urgent need to change it */ -#ifdef CONFIG_X86_32 - pv_info.kernel_rpl = 1; - if (xen_feature(XENFEAT_supervisor_mode_kernel)) - pv_info.kernel_rpl = 0; -#else pv_info.kernel_rpl = 0; -#endif - /* set the limit of our address space */ - xen_reserve_top(); /* * We used to do this in xen_arch_setup, but that is too late @@ -1384,12 +1328,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (rc != 0) xen_raw_printk("physdev_op failed %d\n", rc); -#ifdef CONFIG_X86_32 - /* set up basic CPUID stuff */ - cpu_detect(&new_cpu_data); - set_cpu_cap(&new_cpu_data, X86_FEATURE_FPU); - new_cpu_data.x86_capability[CPUID_1_EDX] = cpuid_edx(1); -#endif if (xen_start_info->mod_start) { if (xen_start_info->flags & SIF_MOD_START_PFN) @@ -1458,12 +1396,8 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_efi_init(&boot_params); /* Start the world */ -#ifdef CONFIG_X86_32 - i386_start_kernel(); -#else cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */ x86_64_start_reservations((char *)__pa_symbol(&boot_params)); -#endif } static int xen_cpu_up_prepare_pv(unsigned int cpu) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index a58d9c69807a..3273c985d3dd 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -86,19 +86,8 @@ #include "mmu.h" #include "debugfs.h" -#ifdef CONFIG_X86_32 -/* - * Identity map, in addition to plain kernel map. This needs to be - * large enough to allocate page table pages to allocate the rest. - * Each page can map 2MB. - */ -#define LEVEL1_IDENT_ENTRIES (PTRS_PER_PTE * 4) -static RESERVE_BRK_ARRAY(pte_t, level1_ident_pgt, LEVEL1_IDENT_ENTRIES); -#endif -#ifdef CONFIG_X86_64 /* l3 pud for userspace vsyscall mapping */ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; -#endif /* CONFIG_X86_64 */ /* * Protects atomic reservation decrease/increase against concurrent increases. @@ -280,10 +269,7 @@ static inline void __xen_set_pte(pte_t *ptep, pte_t pteval) if (!xen_batched_set_pte(ptep, pteval)) { /* * Could call native_set_pte() here and trap and - * emulate the PTE write but with 32-bit guests this - * needs two traps (one for each of the two 32-bit - * words in the PTE) so do one hypercall directly - * instead. + * emulate the PTE write, but a hypercall is much cheaper. */ struct mmu_update u; @@ -439,26 +425,6 @@ static void xen_set_pud(pud_t *ptr, pud_t val) xen_set_pud_hyper(ptr, val); } -#ifdef CONFIG_X86_PAE -static void xen_set_pte_atomic(pte_t *ptep, pte_t pte) -{ - trace_xen_mmu_set_pte_atomic(ptep, pte); - __xen_set_pte(ptep, pte); -} - -static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - trace_xen_mmu_pte_clear(mm, addr, ptep); - __xen_set_pte(ptep, native_make_pte(0)); -} - -static void xen_pmd_clear(pmd_t *pmdp) -{ - trace_xen_mmu_pmd_clear(pmdp); - set_pmd(pmdp, __pmd(0)); -} -#endif /* CONFIG_X86_PAE */ - __visible pmd_t xen_make_pmd(pmdval_t pmd) { pmd = pte_pfn_to_mfn(pmd); @@ -466,7 +432,6 @@ __visible pmd_t xen_make_pmd(pmdval_t pmd) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_pmd); -#ifdef CONFIG_X86_64 __visible pudval_t xen_pud_val(pud_t pud) { return pte_mfn_to_pfn(pud.pud); @@ -571,27 +536,27 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d) } PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d); #endif /* CONFIG_PGTABLE_LEVELS >= 5 */ -#endif /* CONFIG_X86_64 */ -static int xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int i, nr, flush = 0; + int i, nr; nr = last ? pmd_index(limit) + 1 : PTRS_PER_PMD; for (i = 0; i < nr; i++) { if (!pmd_none(pmd[i])) - flush |= (*func)(mm, pmd_page(pmd[i]), PT_PTE); + (*func)(mm, pmd_page(pmd[i]), PT_PTE); } - return flush; } -static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_pud_walk(struct mm_struct *mm, pud_t *pud, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int i, nr, flush = 0; + int i, nr; nr = last ? pud_index(limit) + 1 : PTRS_PER_PUD; for (i = 0; i < nr; i++) { @@ -602,29 +567,26 @@ static int xen_pud_walk(struct mm_struct *mm, pud_t *pud, pmd = pmd_offset(&pud[i], 0); if (PTRS_PER_PMD > 1) - flush |= (*func)(mm, virt_to_page(pmd), PT_PMD); - flush |= xen_pmd_walk(mm, pmd, func, - last && i == nr - 1, limit); + (*func)(mm, virt_to_page(pmd), PT_PMD); + xen_pmd_walk(mm, pmd, func, last && i == nr - 1, limit); } - return flush; } -static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, - int (*func)(struct mm_struct *mm, struct page *, enum pt_level), - bool last, unsigned long limit) +static void xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + bool last, unsigned long limit) { - int flush = 0; pud_t *pud; if (p4d_none(*p4d)) - return flush; + return; pud = pud_offset(p4d, 0); if (PTRS_PER_PUD > 1) - flush |= (*func)(mm, virt_to_page(pud), PT_PUD); - flush |= xen_pud_walk(mm, pud, func, last, limit); - return flush; + (*func)(mm, virt_to_page(pud), PT_PUD); + xen_pud_walk(mm, pud, func, last, limit); } /* @@ -636,32 +598,27 @@ static int xen_p4d_walk(struct mm_struct *mm, p4d_t *p4d, * will be STACK_TOP_MAX, but at boot we need to pin up to * FIXADDR_TOP. * - * For 32-bit the important bit is that we don't pin beyond there, - * because then we start getting into Xen's ptes. - * - * For 64-bit, we must skip the Xen hole in the middle of the address - * space, just after the big x86-64 virtual hole. + * We must skip the Xen hole in the middle of the address space, just after + * the big x86-64 virtual hole. */ -static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, - int (*func)(struct mm_struct *mm, struct page *, - enum pt_level), - unsigned long limit) +static void __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) { - int i, nr, flush = 0; + int i, nr; unsigned hole_low = 0, hole_high = 0; /* The limit is the last byte to be touched */ limit--; BUG_ON(limit >= FIXADDR_TOP); -#ifdef CONFIG_X86_64 /* * 64-bit has a great big hole in the middle of the address * space, which contains the Xen mappings. */ hole_low = pgd_index(GUARD_HOLE_BASE_ADDR); hole_high = pgd_index(GUARD_HOLE_END_ADDR); -#endif nr = pgd_index(limit) + 1; for (i = 0; i < nr; i++) { @@ -674,22 +631,20 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd, continue; p4d = p4d_offset(&pgd[i], 0); - flush |= xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); + xen_p4d_walk(mm, p4d, func, i == nr - 1, limit); } /* Do the top level last, so that the callbacks can use it as a cue to do final things like tlb flushes. */ - flush |= (*func)(mm, virt_to_page(pgd), PT_PGD); - - return flush; + (*func)(mm, virt_to_page(pgd), PT_PGD); } -static int xen_pgd_walk(struct mm_struct *mm, - int (*func)(struct mm_struct *mm, struct page *, - enum pt_level), - unsigned long limit) +static void xen_pgd_walk(struct mm_struct *mm, + void (*func)(struct mm_struct *mm, struct page *, + enum pt_level), + unsigned long limit) { - return __xen_pgd_walk(mm, mm->pgd, func, limit); + __xen_pgd_walk(mm, mm->pgd, func, limit); } /* If we're using split pte locks, then take the page's lock and @@ -722,26 +677,17 @@ static void xen_do_pin(unsigned level, unsigned long pfn) xen_extend_mmuext_op(&op); } -static int xen_pin_page(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void xen_pin_page(struct mm_struct *mm, struct page *page, + enum pt_level level) { unsigned pgfl = TestSetPagePinned(page); - int flush; - - if (pgfl) - flush = 0; /* already pinned */ - else if (PageHighMem(page)) - /* kmaps need flushing if we found an unpinned - highpage */ - flush = 1; - else { + + if (!pgfl) { void *pt = lowmem_page_address(page); unsigned long pfn = page_to_pfn(page); struct multicall_space mcs = __xen_mc_entry(0); spinlock_t *ptl; - flush = 0; - /* * We need to hold the pagetable lock between the time * we make the pagetable RO and when we actually pin @@ -778,8 +724,6 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page, xen_mc_callback(xen_pte_unlock, ptl); } } - - return flush; } /* This is called just after a mm has been created, but it has not @@ -787,39 +731,22 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page, read-only, and can be pinned. */ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd) { + pgd_t *user_pgd = xen_get_user_pgd(pgd); + trace_xen_mmu_pgd_pin(mm, pgd); xen_mc_batch(); - if (__xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT)) { - /* re-enable interrupts for flushing */ - xen_mc_issue(0); + __xen_pgd_walk(mm, pgd, xen_pin_page, USER_LIMIT); - kmap_flush_unused(); + xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd))); - xen_mc_batch(); + if (user_pgd) { + xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD); + xen_do_pin(MMUEXT_PIN_L4_TABLE, + PFN_DOWN(__pa(user_pgd))); } -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - xen_do_pin(MMUEXT_PIN_L4_TABLE, PFN_DOWN(__pa(pgd))); - - if (user_pgd) { - xen_pin_page(mm, virt_to_page(user_pgd), PT_PGD); - xen_do_pin(MMUEXT_PIN_L4_TABLE, - PFN_DOWN(__pa(user_pgd))); - } - } -#else /* CONFIG_X86_32 */ -#ifdef CONFIG_X86_PAE - /* Need to make sure unshared kernel PMD is pinnable */ - xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]), - PT_PMD); -#endif - xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd))); -#endif /* CONFIG_X86_64 */ xen_mc_issue(0); } @@ -854,11 +781,10 @@ void xen_mm_pin_all(void) spin_unlock(&pgd_lock); } -static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, + enum pt_level level) { SetPagePinned(page); - return 0; } /* @@ -870,18 +796,16 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, static void __init xen_after_bootmem(void) { static_branch_enable(&xen_struct_pages_ready); -#ifdef CONFIG_X86_64 SetPagePinned(virt_to_page(level3_user_vsyscall)); -#endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } -static int xen_unpin_page(struct mm_struct *mm, struct page *page, - enum pt_level level) +static void xen_unpin_page(struct mm_struct *mm, struct page *page, + enum pt_level level) { unsigned pgfl = TestClearPagePinned(page); - if (pgfl && !PageHighMem(page)) { + if (pgfl) { void *pt = lowmem_page_address(page); unsigned long pfn = page_to_pfn(page); spinlock_t *ptl = NULL; @@ -912,36 +836,24 @@ static int xen_unpin_page(struct mm_struct *mm, struct page *page, xen_mc_callback(xen_pte_unlock, ptl); } } - - return 0; /* never need to flush on unpin */ } /* Release a pagetables pages back as normal RW */ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd) { + pgd_t *user_pgd = xen_get_user_pgd(pgd); + trace_xen_mmu_pgd_unpin(mm, pgd); xen_mc_batch(); xen_do_pin(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(pgd); - - if (user_pgd) { - xen_do_pin(MMUEXT_UNPIN_TABLE, - PFN_DOWN(__pa(user_pgd))); - xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD); - } + if (user_pgd) { + xen_do_pin(MMUEXT_UNPIN_TABLE, + PFN_DOWN(__pa(user_pgd))); + xen_unpin_page(mm, virt_to_page(user_pgd), PT_PGD); } -#endif - -#ifdef CONFIG_X86_PAE - /* Need to make sure unshared kernel PMD is unpinned */ - xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]), - PT_PMD); -#endif __xen_pgd_walk(mm, pgd, xen_unpin_page, USER_LIMIT); @@ -1089,7 +1001,6 @@ static void __init pin_pagetable_pfn(unsigned cmd, unsigned long pfn) BUG(); } -#ifdef CONFIG_X86_64 static void __init xen_cleanhighmap(unsigned long vaddr, unsigned long vaddr_end) { @@ -1273,17 +1184,15 @@ static void __init xen_pagetable_cleanhighmap(void) xen_cleanhighmap(addr, roundup(addr + size, PMD_SIZE * 2)); xen_start_info->pt_base = (unsigned long)__va(__pa(xen_start_info->pt_base)); } -#endif static void __init xen_pagetable_p2m_setup(void) { xen_vmalloc_p2m_tree(); -#ifdef CONFIG_X86_64 xen_pagetable_p2m_free(); xen_pagetable_cleanhighmap(); -#endif + /* And revector! Bye bye old array */ xen_start_info->mfn_list = (unsigned long)xen_p2m_addr; } @@ -1420,6 +1329,8 @@ static void __xen_write_cr3(bool kernel, unsigned long cr3) } static void xen_write_cr3(unsigned long cr3) { + pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); + BUG_ON(preemptible()); xen_mc_batch(); /* disables interrupts */ @@ -1430,20 +1341,14 @@ static void xen_write_cr3(unsigned long cr3) __xen_write_cr3(true, cr3); -#ifdef CONFIG_X86_64 - { - pgd_t *user_pgd = xen_get_user_pgd(__va(cr3)); - if (user_pgd) - __xen_write_cr3(false, __pa(user_pgd)); - else - __xen_write_cr3(false, 0); - } -#endif + if (user_pgd) + __xen_write_cr3(false, __pa(user_pgd)); + else + __xen_write_cr3(false, 0); xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ } -#ifdef CONFIG_X86_64 /* * At the start of the day - when Xen launches a guest, it has already * built pagetables for the guest. We diligently look over them @@ -1478,49 +1383,39 @@ static void __init xen_write_cr3_init(unsigned long cr3) xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */ } -#endif static int xen_pgd_alloc(struct mm_struct *mm) { pgd_t *pgd = mm->pgd; - int ret = 0; + struct page *page = virt_to_page(pgd); + pgd_t *user_pgd; + int ret = -ENOMEM; BUG_ON(PagePinned(virt_to_page(pgd))); + BUG_ON(page->private != 0); -#ifdef CONFIG_X86_64 - { - struct page *page = virt_to_page(pgd); - pgd_t *user_pgd; + user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); + page->private = (unsigned long)user_pgd; - BUG_ON(page->private != 0); - - ret = -ENOMEM; - - user_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO); - page->private = (unsigned long)user_pgd; - - if (user_pgd != NULL) { + if (user_pgd != NULL) { #ifdef CONFIG_X86_VSYSCALL_EMULATION - user_pgd[pgd_index(VSYSCALL_ADDR)] = - __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); + user_pgd[pgd_index(VSYSCALL_ADDR)] = + __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); #endif - ret = 0; - } - - BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); + ret = 0; } -#endif + + BUG_ON(PagePinned(virt_to_page(xen_get_user_pgd(pgd)))); + return ret; } static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) { -#ifdef CONFIG_X86_64 pgd_t *user_pgd = xen_get_user_pgd(pgd); if (user_pgd) free_page((unsigned long)user_pgd); -#endif } /* @@ -1539,7 +1434,6 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) */ __visible pte_t xen_make_pte_init(pteval_t pte) { -#ifdef CONFIG_X86_64 unsigned long pfn; /* @@ -1553,7 +1447,7 @@ __visible pte_t xen_make_pte_init(pteval_t pte) pfn >= xen_start_info->first_p2m_pfn && pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames) pte &= ~_PAGE_RW; -#endif + pte = pte_pfn_to_mfn(pte); return native_make_pte(pte); } @@ -1561,13 +1455,6 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init); static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) { -#ifdef CONFIG_X86_32 - /* If there's an existing pte, then don't allow _PAGE_RW to be set */ - if (pte_mfn(pte) != INVALID_P2M_ENTRY - && pte_val_ma(*ptep) & _PAGE_PRESENT) - pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & - pte_val_ma(pte)); -#endif __xen_set_pte(ptep, pte); } @@ -1642,20 +1529,14 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, if (static_branch_likely(&xen_struct_pages_ready)) SetPagePinned(page); - if (!PageHighMem(page)) { - xen_mc_batch(); + xen_mc_batch(); - __set_pfn_prot(pfn, PAGE_KERNEL_RO); + __set_pfn_prot(pfn, PAGE_KERNEL_RO); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) - __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + __pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn); - xen_mc_issue(PARAVIRT_LAZY_MMU); - } else { - /* make sure there are no stray mappings of - this page */ - kmap_flush_unused(); - } + xen_mc_issue(PARAVIRT_LAZY_MMU); } } @@ -1678,16 +1559,15 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level) trace_xen_mmu_release_ptpage(pfn, level, pinned); if (pinned) { - if (!PageHighMem(page)) { - xen_mc_batch(); + xen_mc_batch(); - if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) - __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); + if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS) + __pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn); - __set_pfn_prot(pfn, PAGE_KERNEL); + __set_pfn_prot(pfn, PAGE_KERNEL); + + xen_mc_issue(PARAVIRT_LAZY_MMU); - xen_mc_issue(PARAVIRT_LAZY_MMU); - } ClearPagePinned(page); } } @@ -1702,7 +1582,6 @@ static void xen_release_pmd(unsigned long pfn) xen_release_ptpage(pfn, PT_PMD); } -#ifdef CONFIG_X86_64 static void xen_alloc_pud(struct mm_struct *mm, unsigned long pfn) { xen_alloc_ptpage(mm, pfn, PT_PUD); @@ -1712,20 +1591,6 @@ static void xen_release_pud(unsigned long pfn) { xen_release_ptpage(pfn, PT_PUD); } -#endif - -void __init xen_reserve_top(void) -{ -#ifdef CONFIG_X86_32 - unsigned long top = HYPERVISOR_VIRT_START; - struct xen_platform_parameters pp; - - if (HYPERVISOR_xen_version(XENVER_platform_parameters, &pp) == 0) - top = pp.virt_start; - - reserve_top_address(-top); -#endif /* CONFIG_X86_32 */ -} /* * Like __va(), but returns address in the kernel mapping (which is @@ -1733,11 +1598,7 @@ void __init xen_reserve_top(void) */ static void * __init __ka(phys_addr_t paddr) { -#ifdef CONFIG_X86_64 return (void *)(paddr + __START_KERNEL_map); -#else - return __va(paddr); -#endif } /* Convert a machine address to physical address */ @@ -1771,56 +1632,7 @@ static void __init set_page_prot(void *addr, pgprot_t prot) { return set_page_prot_flags(addr, prot, UVMF_NONE); } -#ifdef CONFIG_X86_32 -static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) -{ - unsigned pmdidx, pteidx; - unsigned ident_pte; - unsigned long pfn; - - level1_ident_pgt = extend_brk(sizeof(pte_t) * LEVEL1_IDENT_ENTRIES, - PAGE_SIZE); - - ident_pte = 0; - pfn = 0; - for (pmdidx = 0; pmdidx < PTRS_PER_PMD && pfn < max_pfn; pmdidx++) { - pte_t *pte_page; - - /* Reuse or allocate a page of ptes */ - if (pmd_present(pmd[pmdidx])) - pte_page = m2v(pmd[pmdidx].pmd); - else { - /* Check for free pte pages */ - if (ident_pte == LEVEL1_IDENT_ENTRIES) - break; - - pte_page = &level1_ident_pgt[ident_pte]; - ident_pte += PTRS_PER_PTE; - - pmd[pmdidx] = __pmd(__pa(pte_page) | _PAGE_TABLE); - } - - /* Install mappings */ - for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) { - pte_t pte; - if (pfn > max_pfn_mapped) - max_pfn_mapped = pfn; - - if (!pte_none(pte_page[pteidx])) - continue; - - pte = pfn_pte(pfn, PAGE_KERNEL_EXEC); - pte_page[pteidx] = pte; - } - } - - for (pteidx = 0; pteidx < ident_pte; pteidx += PTRS_PER_PTE) - set_page_prot(&level1_ident_pgt[pteidx], PAGE_KERNEL_RO); - - set_page_prot(pmd, PAGE_KERNEL_RO); -} -#endif void __init xen_setup_machphys_mapping(void) { struct xen_machphys_mapping mapping; @@ -1831,13 +1643,8 @@ void __init xen_setup_machphys_mapping(void) } else { machine_to_phys_nr = MACH2PHYS_NR_ENTRIES; } -#ifdef CONFIG_X86_32 - WARN_ON((machine_to_phys_mapping + (machine_to_phys_nr - 1)) - < machine_to_phys_mapping); -#endif } -#ifdef CONFIG_X86_64 static void __init convert_pfn_mfn(void *v) { pte_t *pte = v; @@ -2168,105 +1975,6 @@ void __init xen_relocate_p2m(void) xen_start_info->nr_p2m_frames = n_frames; } -#else /* !CONFIG_X86_64 */ -static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD); -static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD); -RESERVE_BRK(fixup_kernel_pmd, PAGE_SIZE); -RESERVE_BRK(fixup_kernel_pte, PAGE_SIZE); - -static void __init xen_write_cr3_init(unsigned long cr3) -{ - unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir)); - - BUG_ON(read_cr3_pa() != __pa(initial_page_table)); - BUG_ON(cr3 != __pa(swapper_pg_dir)); - - /* - * We are switching to swapper_pg_dir for the first time (from - * initial_page_table) and therefore need to mark that page - * read-only and then pin it. - * - * Xen disallows sharing of kernel PMDs for PAE - * guests. Therefore we must copy the kernel PMD from - * initial_page_table into a new kernel PMD to be used in - * swapper_pg_dir. - */ - swapper_kernel_pmd = - extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - copy_page(swapper_kernel_pmd, initial_kernel_pmd); - swapper_pg_dir[KERNEL_PGD_BOUNDARY] = - __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT); - set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO); - - set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO); - xen_write_cr3(cr3); - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, - PFN_DOWN(__pa(initial_page_table))); - set_page_prot(initial_page_table, PAGE_KERNEL); - set_page_prot(initial_kernel_pmd, PAGE_KERNEL); - - pv_ops.mmu.write_cr3 = &xen_write_cr3; -} - -/* - * For 32 bit domains xen_start_info->pt_base is the pgd address which might be - * not the first page table in the page table pool. - * Iterate through the initial page tables to find the real page table base. - */ -static phys_addr_t __init xen_find_pt_base(pmd_t *pmd) -{ - phys_addr_t pt_base, paddr; - unsigned pmdidx; - - pt_base = min(__pa(xen_start_info->pt_base), __pa(pmd)); - - for (pmdidx = 0; pmdidx < PTRS_PER_PMD; pmdidx++) - if (pmd_present(pmd[pmdidx]) && !pmd_large(pmd[pmdidx])) { - paddr = m2p(pmd[pmdidx].pmd); - pt_base = min(pt_base, paddr); - } - - return pt_base; -} - -void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) -{ - pmd_t *kernel_pmd; - - kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd); - - xen_pt_base = xen_find_pt_base(kernel_pmd); - xen_pt_size = xen_start_info->nr_pt_frames * PAGE_SIZE; - - initial_kernel_pmd = - extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE); - - max_pfn_mapped = PFN_DOWN(xen_pt_base + xen_pt_size + 512 * 1024); - - copy_page(initial_kernel_pmd, kernel_pmd); - - xen_map_identity_early(initial_kernel_pmd, max_pfn); - - copy_page(initial_page_table, pgd); - initial_page_table[KERNEL_PGD_BOUNDARY] = - __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT); - - set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO); - set_page_prot(initial_page_table, PAGE_KERNEL_RO); - set_page_prot(empty_zero_page, PAGE_KERNEL_RO); - - pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd))); - - pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, - PFN_DOWN(__pa(initial_page_table))); - xen_write_cr3(__pa(initial_page_table)); - - memblock_reserve(xen_pt_base, xen_pt_size); -} -#endif /* CONFIG_X86_64 */ - void __init xen_reserve_special_pages(void) { phys_addr_t paddr; @@ -2300,12 +2008,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: -#ifdef CONFIG_X86_32 - case FIX_WP_TEST: -# ifdef CONFIG_HIGHMEM - case FIX_KMAP_BEGIN ... FIX_KMAP_END: -# endif -#elif defined(CONFIG_X86_VSYSCALL_EMULATION) +#ifdef CONFIG_X86_VSYSCALL_EMULATION case VSYSCALL_PAGE: #endif /* All local page mappings */ @@ -2357,9 +2060,7 @@ static void __init xen_post_allocator_init(void) pv_ops.mmu.set_pte = xen_set_pte; pv_ops.mmu.set_pmd = xen_set_pmd; pv_ops.mmu.set_pud = xen_set_pud; -#ifdef CONFIG_X86_64 pv_ops.mmu.set_p4d = xen_set_p4d; -#endif /* This will work as long as patching hasn't happened yet (which it hasn't) */ @@ -2367,15 +2068,11 @@ static void __init xen_post_allocator_init(void) pv_ops.mmu.alloc_pmd = xen_alloc_pmd; pv_ops.mmu.release_pte = xen_release_pte; pv_ops.mmu.release_pmd = xen_release_pmd; -#ifdef CONFIG_X86_64 pv_ops.mmu.alloc_pud = xen_alloc_pud; pv_ops.mmu.release_pud = xen_release_pud; -#endif pv_ops.mmu.make_pte = PV_CALLEE_SAVE(xen_make_pte); -#ifdef CONFIG_X86_64 pv_ops.mmu.write_cr3 = &xen_write_cr3; -#endif } static void xen_leave_lazy_mmu(void) @@ -2420,17 +2117,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .make_pte = PV_CALLEE_SAVE(xen_make_pte_init), .make_pgd = PV_CALLEE_SAVE(xen_make_pgd), -#ifdef CONFIG_X86_PAE - .set_pte_atomic = xen_set_pte_atomic, - .pte_clear = xen_pte_clear, - .pmd_clear = xen_pmd_clear, -#endif /* CONFIG_X86_PAE */ .set_pud = xen_set_pud_hyper, .make_pmd = PV_CALLEE_SAVE(xen_make_pmd), .pmd_val = PV_CALLEE_SAVE(xen_pmd_val), -#ifdef CONFIG_X86_64 .pud_val = PV_CALLEE_SAVE(xen_pud_val), .make_pud = PV_CALLEE_SAVE(xen_make_pud), .set_p4d = xen_set_p4d_hyper, @@ -2442,7 +2133,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .p4d_val = PV_CALLEE_SAVE(xen_p4d_val), .make_p4d = PV_CALLEE_SAVE(xen_make_p4d), #endif -#endif /* CONFIG_X86_64 */ .activate_mm = xen_activate_mm, .dup_mmap = xen_dup_mmap, diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 0acba2c712ab..be4151f42611 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -379,12 +379,8 @@ static void __init xen_rebuild_p2m_list(unsigned long *p2m) if (type == P2M_TYPE_PFN || i < chunk) { /* Use initial p2m page contents. */ -#ifdef CONFIG_X86_64 mfns = alloc_p2m_page(); copy_page(mfns, xen_p2m_addr + pfn); -#else - mfns = xen_p2m_addr + pfn; -#endif ptep = populate_extra_pte((unsigned long)(p2m + pfn)); set_pte(ptep, pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL)); @@ -467,7 +463,7 @@ EXPORT_SYMBOL_GPL(get_phys_to_machine); * Allocate new pmd(s). It is checked whether the old pmd is still in place. * If not, nothing is changed. This is okay as the only reason for allocating * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual - * pmd. In case of PAE/x86-32 there are multiple pmds to allocate! + * pmd. */ static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *pte_pg) { diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 3566e37241d7..7eab14d56369 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -32,7 +32,6 @@ #include <xen/features.h> #include <xen/hvc-console.h> #include "xen-ops.h" -#include "vdso.h" #include "mmu.h" #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) @@ -545,13 +544,10 @@ static unsigned long __init xen_get_pages_limit(void) { unsigned long limit; -#ifdef CONFIG_X86_32 - limit = GB(64) / PAGE_SIZE; -#else limit = MAXMEM / PAGE_SIZE; if (!xen_initial_domain() && xen_512gb_limit) limit = GB(512) / PAGE_SIZE; -#endif + return limit; } @@ -722,17 +718,8 @@ static void __init xen_reserve_xen_mfnlist(void) if (!xen_is_e820_reserved(start, size)) return; -#ifdef CONFIG_X86_32 - /* - * Relocating the p2m on 32 bit system to an arbitrary virtual address - * is not supported, so just give up. - */ - xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n"); - BUG(); -#else xen_relocate_p2m(); memblock_free(start, size); -#endif } /** @@ -921,20 +908,6 @@ char * __init xen_memory_setup(void) return "Xen"; } -/* - * Set the bit indicating "nosegneg" library variants should be used. - * We only need to bother in pure 32-bit mode; compat 32-bit processes - * can have un-truncated segments, so wrapping around is allowed. - */ -static void __init fiddle_vdso(void) -{ -#ifdef CONFIG_X86_32 - u32 *mask = vdso_image_32.data + - vdso_image_32.sym_VDSO32_NOTE_MASK; - *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; -#endif -} - static int register_callback(unsigned type, const void *func) { struct callback_register callback = { @@ -951,11 +924,7 @@ void xen_enable_sysenter(void) int ret; unsigned sysenter_feature; -#ifdef CONFIG_X86_32 - sysenter_feature = X86_FEATURE_SEP; -#else sysenter_feature = X86_FEATURE_SYSENTER32; -#endif if (!boot_cpu_has(sysenter_feature)) return; @@ -967,7 +936,6 @@ void xen_enable_sysenter(void) void xen_enable_syscall(void) { -#ifdef CONFIG_X86_64 int ret; ret = register_callback(CALLBACKTYPE_syscall, xen_syscall_target); @@ -983,7 +951,6 @@ void xen_enable_syscall(void) if (ret != 0) setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } -#endif /* CONFIG_X86_64 */ } static void __init xen_pvmmu_arch_setup(void) @@ -1024,7 +991,6 @@ void __init xen_arch_setup(void) disable_cpuidle(); disable_cpufreq(); WARN_ON(xen_set_default_idle()); - fiddle_vdso(); #ifdef CONFIG_NUMA numa_off = 1; #endif diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f8d39440b292..f5e7db4f82ab 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <linux/thread_info.h> #include <asm/smp.h> #include <xen/events.h> diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 9ea598dcc132..c2ac319f11a4 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -29,6 +29,7 @@ #include <asm/idtentry.h> #include <asm/desc.h> #include <asm/cpu.h> +#include <asm/io_apic.h> #include <xen/interface/xen.h> #include <xen/interface/vcpu.h> @@ -210,15 +211,6 @@ static void __init xen_pv_smp_prepare_boot_cpu(void) * sure the old memory can be recycled. */ make_lowmem_page_readwrite(xen_initial_gdt); -#ifdef CONFIG_X86_32 - /* - * Xen starts us with XEN_FLAT_RING1_DS, but linux code - * expects __USER_DS - */ - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); -#endif - xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); @@ -299,10 +291,6 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) gdt = get_cpu_gdt_rw(cpu); -#ifdef CONFIG_X86_32 - ctxt->user_regs.fs = __KERNEL_PERCPU; - ctxt->user_regs.gs = __KERNEL_STACK_CANARY; -#endif memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt)); /* @@ -340,12 +328,7 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle) ctxt->kernel_ss = __KERNEL_DS; ctxt->kernel_sp = task_top_of_stack(idle); -#ifdef CONFIG_X86_32 - ctxt->event_callback_cs = __KERNEL_CS; - ctxt->failsafe_callback_cs = __KERNEL_CS; -#else ctxt->gs_base_kernel = per_cpu_offset(cpu); -#endif ctxt->event_callback_eip = (unsigned long)xen_asm_exc_xen_hypervisor_callback; ctxt->failsafe_callback_eip = diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c index 8303b58c79a9..cae9660f4c67 100644 --- a/arch/x86/xen/suspend_pv.c +++ b/arch/x86/xen/suspend_pv.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> -#include <asm/fixmap.h> - #include <asm/xen/hypercall.h> #include <asm/xen/page.h> +#include <asm/fixmap.h> + #include "xen-ops.h" void xen_pv_pre_suspend(void) diff --git a/arch/x86/xen/vdso.h b/arch/x86/xen/vdso.h deleted file mode 100644 index 873c54c488fe..000000000000 --- a/arch/x86/xen/vdso.h +++ /dev/null @@ -1,6 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Bit used for the pseudo-hwcap for non-negative segments. We use - bit 1 to avoid bugs in some versions of glibc when bit 0 is - used; the choice is otherwise arbitrary. */ -#define VDSO_NOTE_NONEGSEG_BIT 1 diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 508fe204520b..1cb0e84b9161 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -6,12 +6,18 @@ * operations here; the indirect forms are better handled in C. */ +#include <asm/errno.h> #include <asm/asm-offsets.h> #include <asm/percpu.h> #include <asm/processor-flags.h> -#include <asm/frame.h> +#include <asm/segment.h> +#include <asm/thread_info.h> #include <asm/asm.h> +#include <asm/frame.h> +#include <xen/interface/xen.h> + +#include <linux/init.h> #include <linux/linkage.h> /* @@ -76,11 +82,7 @@ SYM_FUNC_END(xen_save_fl_direct) */ SYM_FUNC_START(xen_restore_fl_direct) FRAME_BEGIN -#ifdef CONFIG_X86_64 testw $X86_EFLAGS_IF, %di -#else - testb $X86_EFLAGS_IF>>8, %ah -#endif setz PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask /* * Preempt here doesn't matter because that will deal with any @@ -104,15 +106,6 @@ SYM_FUNC_END(xen_restore_fl_direct) */ SYM_FUNC_START(check_events) FRAME_BEGIN -#ifdef CONFIG_X86_32 - push %eax - push %ecx - push %edx - call xen_force_evtchn_callback - pop %edx - pop %ecx - pop %eax -#else push %rax push %rcx push %rdx @@ -132,7 +125,6 @@ SYM_FUNC_START(check_events) pop %rdx pop %rcx pop %rax -#endif FRAME_END ret SYM_FUNC_END(check_events) @@ -151,3 +143,175 @@ SYM_FUNC_START(xen_read_cr2_direct) FRAME_END ret SYM_FUNC_END(xen_read_cr2_direct); + +.macro xen_pv_trap name +SYM_CODE_START(xen_\name) + pop %rcx + pop %r11 + jmp \name +SYM_CODE_END(xen_\name) +_ASM_NOKPROBE(xen_\name) +.endm + +xen_pv_trap asm_exc_divide_error +xen_pv_trap asm_xenpv_exc_debug +xen_pv_trap asm_exc_int3 +xen_pv_trap asm_xenpv_exc_nmi +xen_pv_trap asm_exc_overflow +xen_pv_trap asm_exc_bounds +xen_pv_trap asm_exc_invalid_op +xen_pv_trap asm_exc_device_not_available +xen_pv_trap asm_exc_double_fault +xen_pv_trap asm_exc_coproc_segment_overrun +xen_pv_trap asm_exc_invalid_tss +xen_pv_trap asm_exc_segment_not_present +xen_pv_trap asm_exc_stack_segment +xen_pv_trap asm_exc_general_protection +xen_pv_trap asm_exc_page_fault +xen_pv_trap asm_exc_spurious_interrupt_bug +xen_pv_trap asm_exc_coprocessor_error +xen_pv_trap asm_exc_alignment_check +#ifdef CONFIG_X86_MCE +xen_pv_trap asm_exc_machine_check +#endif /* CONFIG_X86_MCE */ +xen_pv_trap asm_exc_simd_coprocessor_error +#ifdef CONFIG_IA32_EMULATION +xen_pv_trap entry_INT80_compat +#endif +xen_pv_trap asm_exc_xen_hypervisor_callback + + __INIT +SYM_CODE_START(xen_early_idt_handler_array) + i = 0 + .rept NUM_EXCEPTION_VECTORS + pop %rcx + pop %r11 + jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE + i = i + 1 + .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc + .endr +SYM_CODE_END(xen_early_idt_handler_array) + __FINIT + +hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 +/* + * Xen64 iret frame: + * + * ss + * rsp + * rflags + * cs + * rip <-- standard iret frame + * + * flags + * + * rcx } + * r11 }<-- pushed by hypercall page + * rsp->rax } + */ +SYM_CODE_START(xen_iret) + pushq $0 + jmp hypercall_iret +SYM_CODE_END(xen_iret) + +SYM_CODE_START(xen_sysret64) + /* + * We're already on the usermode stack at this point, but + * still with the kernel gs, so we can easily switch back. + * + * tss.sp2 is scratch space. + */ + movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + + pushq $__USER_DS + pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) + pushq %r11 + pushq $__USER_CS + pushq %rcx + + pushq $VGCF_in_syscall + jmp hypercall_iret +SYM_CODE_END(xen_sysret64) + +/* + * Xen handles syscall callbacks much like ordinary exceptions, which + * means we have: + * - kernel gs + * - kernel rsp + * - an iret-like stack frame on the stack (including rcx and r11): + * ss + * rsp + * rflags + * cs + * rip + * r11 + * rsp->rcx + */ + +/* Normal 64-bit system call target */ +SYM_FUNC_START(xen_syscall_target) + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER_DS and __USER_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER_DS, 4*8(%rsp) + movq $__USER_CS, 1*8(%rsp) + + jmp entry_SYSCALL_64_after_hwframe +SYM_FUNC_END(xen_syscall_target) + +#ifdef CONFIG_IA32_EMULATION + +/* 32-bit compat syscall target */ +SYM_FUNC_START(xen_syscall32_target) + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSCALL_compat_after_hwframe +SYM_FUNC_END(xen_syscall32_target) + +/* 32-bit compat sysenter target */ +SYM_FUNC_START(xen_sysenter_target) + /* + * NB: Xen is polite and clears TF from EFLAGS for us. This means + * that we don't need to guard against single step exceptions here. + */ + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSENTER_compat_after_hwframe +SYM_FUNC_END(xen_sysenter_target) + +#else /* !CONFIG_IA32_EMULATION */ + +SYM_FUNC_START_ALIAS(xen_syscall32_target) +SYM_FUNC_START(xen_sysenter_target) + lea 16(%rsp), %rsp /* strip %rcx, %r11 */ + mov $-ENOSYS, %rax + pushq $0 + jmp hypercall_iret +SYM_FUNC_END(xen_sysenter_target) +SYM_FUNC_END_ALIAS(xen_syscall32_target) + +#endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S deleted file mode 100644 index 4757cec33abe..000000000000 --- a/arch/x86/xen/xen-asm_32.S +++ /dev/null @@ -1,185 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Asm versions of Xen pv-ops, suitable for direct use. - * - * We only bother with direct forms (ie, vcpu in pda) of the - * operations here; the indirect forms are better handled in C. - */ - -#include <asm/thread_info.h> -#include <asm/processor-flags.h> -#include <asm/segment.h> -#include <asm/asm.h> - -#include <xen/interface/xen.h> - -#include <linux/linkage.h> - -/* Pseudo-flag used for virtual NMI, which we don't implement yet */ -#define XEN_EFLAGS_NMI 0x80000000 - -/* - * This is run where a normal iret would be run, with the same stack setup: - * 8: eflags - * 4: cs - * esp-> 0: eip - * - * This attempts to make sure that any pending events are dealt with - * on return to usermode, but there is a small window in which an - * event can happen just before entering usermode. If the nested - * interrupt ends up setting one of the TIF_WORK_MASK pending work - * flags, they will not be tested again before returning to - * usermode. This means that a process can end up with pending work, - * which will be unprocessed until the process enters and leaves the - * kernel again, which could be an unbounded amount of time. This - * means that a pending signal or reschedule event could be - * indefinitely delayed. - * - * The fix is to notice a nested interrupt in the critical window, and - * if one occurs, then fold the nested interrupt into the current - * interrupt stack frame, and re-process it iteratively rather than - * recursively. This means that it will exit via the normal path, and - * all pending work will be dealt with appropriately. - * - * Because the nested interrupt handler needs to deal with the current - * stack state in whatever form its in, we keep things simple by only - * using a single register which is pushed/popped on the stack. - */ - -.macro POP_FS -1: - popw %fs -.pushsection .fixup, "ax" -2: movw $0, (%esp) - jmp 1b -.popsection - _ASM_EXTABLE(1b,2b) -.endm - -SYM_CODE_START(xen_iret) - /* test eflags for special cases */ - testl $(X86_EFLAGS_VM | XEN_EFLAGS_NMI), 8(%esp) - jnz hyper_iret - - push %eax - ESP_OFFSET=4 # bytes pushed onto stack - - /* Store vcpu_info pointer for easy access */ -#ifdef CONFIG_SMP - pushw %fs - movl $(__KERNEL_PERCPU), %eax - movl %eax, %fs - movl %fs:xen_vcpu, %eax - POP_FS -#else - movl %ss:xen_vcpu, %eax -#endif - - /* check IF state we're restoring */ - testb $X86_EFLAGS_IF>>8, 8+1+ESP_OFFSET(%esp) - - /* - * Maybe enable events. Once this happens we could get a - * recursive event, so the critical region starts immediately - * afterwards. However, if that happens we don't end up - * resuming the code, so we don't have to be worried about - * being preempted to another CPU. - */ - setz %ss:XEN_vcpu_info_mask(%eax) -xen_iret_start_crit: - - /* check for unmasked and pending */ - cmpw $0x0001, %ss:XEN_vcpu_info_pending(%eax) - - /* - * If there's something pending, mask events again so we can - * jump back into exc_xen_hypervisor_callback. Otherwise do not - * touch XEN_vcpu_info_mask. - */ - jne 1f - movb $1, %ss:XEN_vcpu_info_mask(%eax) - -1: popl %eax - - /* - * From this point on the registers are restored and the stack - * updated, so we don't need to worry about it if we're - * preempted - */ -iret_restore_end: - - /* - * Jump to hypervisor_callback after fixing up the stack. - * Events are masked, so jumping out of the critical region is - * OK. - */ - je xen_asm_exc_xen_hypervisor_callback - -1: iret -xen_iret_end_crit: - _ASM_EXTABLE(1b, asm_iret_error) - -hyper_iret: - /* put this out of line since its very rarely used */ - jmp hypercall_page + __HYPERVISOR_iret * 32 -SYM_CODE_END(xen_iret) - - .globl xen_iret_start_crit, xen_iret_end_crit - -/* - * This is called by xen_asm_exc_xen_hypervisor_callback in entry_32.S when it sees - * that the EIP at the time of interrupt was between - * xen_iret_start_crit and xen_iret_end_crit. - * - * The stack format at this point is: - * ---------------- - * ss : (ss/esp may be present if we came from usermode) - * esp : - * eflags } outer exception info - * cs } - * eip } - * ---------------- - * eax : outer eax if it hasn't been restored - * ---------------- - * eflags } - * cs } nested exception info - * eip } - * return address : (into xen_asm_exc_xen_hypervisor_callback) - * - * In order to deliver the nested exception properly, we need to discard the - * nested exception frame such that when we handle the exception, we do it - * in the context of the outer exception rather than starting a new one. - * - * The only caveat is that if the outer eax hasn't been restored yet (i.e. - * it's still on stack), we need to restore its value here. -*/ -.pushsection .noinstr.text, "ax" -SYM_CODE_START(xen_iret_crit_fixup) - /* - * Paranoia: Make sure we're really coming from kernel space. - * One could imagine a case where userspace jumps into the - * critical range address, but just before the CPU delivers a - * PF, it decides to deliver an interrupt instead. Unlikely? - * Definitely. Easy to avoid? Yes. - */ - testb $2, 2*4(%esp) /* nested CS */ - jnz 2f - - /* - * If eip is before iret_restore_end then stack - * hasn't been restored yet. - */ - cmpl $iret_restore_end, 1*4(%esp) - jae 1f - - movl 4*4(%esp), %eax /* load outer EAX */ - ret $4*4 /* discard nested EIP, CS, and EFLAGS as - * well as the just restored EAX */ - -1: - ret $3*4 /* discard nested EIP, CS, and EFLAGS */ - -2: - ret -SYM_CODE_END(xen_iret_crit_fixup) -.popsection diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S deleted file mode 100644 index aab1d99b2b48..000000000000 --- a/arch/x86/xen/xen-asm_64.S +++ /dev/null @@ -1,192 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Asm versions of Xen pv-ops, suitable for direct use. - * - * We only bother with direct forms (ie, vcpu in pda) of the - * operations here; the indirect forms are better handled in C. - */ - -#include <asm/errno.h> -#include <asm/percpu.h> -#include <asm/processor-flags.h> -#include <asm/segment.h> -#include <asm/asm-offsets.h> -#include <asm/thread_info.h> -#include <asm/asm.h> - -#include <xen/interface/xen.h> - -#include <linux/init.h> -#include <linux/linkage.h> - -.macro xen_pv_trap name -SYM_CODE_START(xen_\name) - pop %rcx - pop %r11 - jmp \name -SYM_CODE_END(xen_\name) -_ASM_NOKPROBE(xen_\name) -.endm - -xen_pv_trap asm_exc_divide_error -xen_pv_trap asm_xenpv_exc_debug -xen_pv_trap asm_exc_int3 -xen_pv_trap asm_xenpv_exc_nmi -xen_pv_trap asm_exc_overflow -xen_pv_trap asm_exc_bounds -xen_pv_trap asm_exc_invalid_op -xen_pv_trap asm_exc_device_not_available -xen_pv_trap asm_exc_double_fault -xen_pv_trap asm_exc_coproc_segment_overrun -xen_pv_trap asm_exc_invalid_tss -xen_pv_trap asm_exc_segment_not_present -xen_pv_trap asm_exc_stack_segment -xen_pv_trap asm_exc_general_protection -xen_pv_trap asm_exc_page_fault -xen_pv_trap asm_exc_spurious_interrupt_bug -xen_pv_trap asm_exc_coprocessor_error -xen_pv_trap asm_exc_alignment_check -#ifdef CONFIG_X86_MCE -xen_pv_trap asm_exc_machine_check -#endif /* CONFIG_X86_MCE */ -xen_pv_trap asm_exc_simd_coprocessor_error -#ifdef CONFIG_IA32_EMULATION -xen_pv_trap entry_INT80_compat -#endif -xen_pv_trap asm_exc_xen_hypervisor_callback - - __INIT -SYM_CODE_START(xen_early_idt_handler_array) - i = 0 - .rept NUM_EXCEPTION_VECTORS - pop %rcx - pop %r11 - jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE - i = i + 1 - .fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc - .endr -SYM_CODE_END(xen_early_idt_handler_array) - __FINIT - -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 -/* - * Xen64 iret frame: - * - * ss - * rsp - * rflags - * cs - * rip <-- standard iret frame - * - * flags - * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } - */ -SYM_CODE_START(xen_iret) - pushq $0 - jmp hypercall_iret -SYM_CODE_END(xen_iret) - -SYM_CODE_START(xen_sysret64) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back. - * - * tss.sp2 is scratch space. - */ - movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER_DS - pushq PER_CPU_VAR(cpu_tss_rw + TSS_sp2) - pushq %r11 - pushq $__USER_CS - pushq %rcx - - pushq $VGCF_in_syscall - jmp hypercall_iret -SYM_CODE_END(xen_sysret64) - -/* - * Xen handles syscall callbacks much like ordinary exceptions, which - * means we have: - * - kernel gs - * - kernel rsp - * - an iret-like stack frame on the stack (including rcx and r11): - * ss - * rsp - * rflags - * cs - * rip - * r11 - * rsp->rcx - */ - -/* Normal 64-bit system call target */ -SYM_FUNC_START(xen_syscall_target) - popq %rcx - popq %r11 - - /* - * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER_DS and __USER_CS, so - * report those values even though Xen will guess its own values. - */ - movq $__USER_DS, 4*8(%rsp) - movq $__USER_CS, 1*8(%rsp) - - jmp entry_SYSCALL_64_after_hwframe -SYM_FUNC_END(xen_syscall_target) - -#ifdef CONFIG_IA32_EMULATION - -/* 32-bit compat syscall target */ -SYM_FUNC_START(xen_syscall32_target) - popq %rcx - popq %r11 - - /* - * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so - * report those values even though Xen will guess its own values. - */ - movq $__USER32_DS, 4*8(%rsp) - movq $__USER32_CS, 1*8(%rsp) - - jmp entry_SYSCALL_compat_after_hwframe -SYM_FUNC_END(xen_syscall32_target) - -/* 32-bit compat sysenter target */ -SYM_FUNC_START(xen_sysenter_target) - /* - * NB: Xen is polite and clears TF from EFLAGS for us. This means - * that we don't need to guard against single step exceptions here. - */ - popq %rcx - popq %r11 - - /* - * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so - * report those values even though Xen will guess its own values. - */ - movq $__USER32_DS, 4*8(%rsp) - movq $__USER32_CS, 1*8(%rsp) - - jmp entry_SYSENTER_compat_after_hwframe -SYM_FUNC_END(xen_sysenter_target) - -#else /* !CONFIG_IA32_EMULATION */ - -SYM_FUNC_START_ALIAS(xen_syscall32_target) -SYM_FUNC_START(xen_sysenter_target) - lea 16(%rsp), %rsp /* strip %rcx, %r11 */ - mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret -SYM_FUNC_END(xen_sysenter_target) -SYM_FUNC_END_ALIAS(xen_syscall32_target) - -#endif /* CONFIG_IA32_EMULATION */ diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 1ba601df3a37..2d7c8f34f56c 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -35,13 +35,8 @@ SYM_CODE_START(startup_xen) rep __ASM_SIZE(stos) mov %_ASM_SI, xen_start_info -#ifdef CONFIG_X86_64 mov initial_stack(%rip), %rsp -#else - mov initial_stack, %esp -#endif -#ifdef CONFIG_X86_64 /* Set up %gs. * * The base of %gs always points to fixed_percpu_data. If the @@ -53,7 +48,6 @@ SYM_CODE_START(startup_xen) movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax cdq wrmsr -#endif call xen_start_kernel SYM_CODE_END(startup_xen) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 53b224fd6177..45d556f71858 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -33,7 +33,6 @@ void xen_setup_mfn_list_list(void); void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); -void xen_reserve_top(void); void __init xen_reserve_special_pages(void); void __init xen_pt_check_e820(void); diff --git a/arch/xtensa/boot/boot-elf/Makefile b/arch/xtensa/boot/boot-elf/Makefile index 0ebc9827f7e5..f7c775d53012 100644 --- a/arch/xtensa/boot/boot-elf/Makefile +++ b/arch/xtensa/boot/boot-elf/Makefile @@ -26,7 +26,7 @@ $(obj)/Image.o: $(obj)/../vmlinux.bin $(OBJS) $(OBJS) $@ $(obj)/../Image.elf: $(obj)/Image.o $(obj)/boot.lds - $(Q)$(LD) $(KBUILD_LDFLAGS) $(LDFLAGS_vmlinux) \ + $(Q)$(LD) $(KBUILD_LDFLAGS) \ -T $(obj)/boot.lds \ --build-id=none \ -o $@ $(obj)/Image.o diff --git a/arch/xtensa/include/asm/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h index 1d38f0e755ba..d3a22da4d2c9 100644 --- a/arch/xtensa/include/asm/pgalloc.h +++ b/arch/xtensa/include/asm/pgalloc.h @@ -8,9 +8,14 @@ #ifndef _XTENSA_PGALLOC_H #define _XTENSA_PGALLOC_H +#ifdef CONFIG_MMU #include <linux/highmem.h> #include <linux/slab.h> +#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL +#define __HAVE_ARCH_PTE_ALLOC_ONE +#include <asm-generic/pgalloc.h> + /* * Allocating and freeing a pmd is trivial: the 1-entry pmd is * inside the pgd, so has no extra memory associated with it. @@ -28,50 +33,37 @@ pgd_alloc(struct mm_struct *mm) return (pgd_t*) __get_free_pages(GFP_KERNEL | __GFP_ZERO, PGD_ORDER); } -static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) +static inline void ptes_clear(pte_t *ptep) { - free_page((unsigned long)pgd); + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) + pte_clear(NULL, 0, ptep + i); } static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) { pte_t *ptep; - int i; - ptep = (pte_t *)__get_free_page(GFP_KERNEL); + ptep = (pte_t *)__pte_alloc_one_kernel(mm); if (!ptep) return NULL; - for (i = 0; i < 1024; i++) - pte_clear(NULL, 0, ptep + i); + ptes_clear(ptep); return ptep; } static inline pgtable_t pte_alloc_one(struct mm_struct *mm) { - pte_t *pte; struct page *page; - pte = pte_alloc_one_kernel(mm); - if (!pte) + page = __pte_alloc_one(mm, GFP_PGTABLE_USER); + if (!page) return NULL; - page = virt_to_page(pte); - if (!pgtable_pte_page_ctor(page)) { - __free_page(page); - return NULL; - } + ptes_clear(page_address(page)); return page; } -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - -static inline void pte_free(struct mm_struct *mm, pgtable_t pte) -{ - pgtable_pte_page_dtor(pte); - __free_page(pte); -} #define pmd_pgtable(pmd) pmd_page(pmd) +#endif /* CONFIG_MMU */ #endif /* _XTENSA_PGALLOC_H */ diff --git a/arch/xtensa/include/asm/uaccess.h b/arch/xtensa/include/asm/uaccess.h index e57f0d0a88d8..b9758119feca 100644 --- a/arch/xtensa/include/asm/uaccess.h +++ b/arch/xtensa/include/asm/uaccess.h @@ -35,7 +35,7 @@ #define get_fs() (current->thread.current_ds) #define set_fs(val) (current->thread.current_ds = (val)) -#define segment_eq(a, b) ((a).seg == (b).seg) +#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) #define __kernel_ok (uaccess_kernel()) #define __user_ok(addr, size) \ diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index d216ccba42f7..6276e3c2d3fc 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -222,7 +222,7 @@ 204 common quotactl sys_quotactl # 205 was old nfsservctl 205 common nfsservctl sys_ni_syscall -206 common _sysctl sys_sysctl +206 common _sysctl sys_ni_syscall 207 common bdflush sys_bdflush 208 common uname sys_newuname 209 common sysinfo sys_sysinfo diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c index 24cf6972eace..415fe7faa37f 100644 --- a/arch/xtensa/kernel/xtensa_ksyms.c +++ b/arch/xtensa/kernel/xtensa_ksyms.c @@ -25,7 +25,6 @@ #include <asm/dma.h> #include <asm/io.h> #include <asm/page.h> -#include <asm/pgalloc.h> #include <asm/ftrace.h> #ifdef CONFIG_BLK_DEV_FD #include <asm/floppy.h> diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 2369433b734a..5835406b3cec 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -31,7 +31,6 @@ #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/page.h> -#include <asm/pgalloc.h> /* * Note: diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index c4decc73fd86..7666408ce12a 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -20,7 +20,6 @@ #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/hardirq.h> -#include <asm/pgalloc.h> DEFINE_PER_CPU(unsigned long, asid_cache) = ASID_USER_FIRST; void bad_page_fault(struct pt_regs*, unsigned long, int); @@ -73,6 +72,9 @@ void do_page_fault(struct pt_regs *regs) if (user_mode(regs)) flags |= FAULT_FLAG_USER; + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); + retry: mmap_read_lock(mm); vma = find_vma(mm, address); @@ -108,7 +110,7 @@ good_area: * make sure we exit gracefully rather than endlessly redo * the fault. */ - fault = handle_mm_fault(vma, address, flags); + fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) return; @@ -123,10 +125,6 @@ good_area: BUG(); } if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_MAJOR) - current->maj_flt++; - else - current->min_flt++; if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; @@ -140,12 +138,6 @@ good_area: } mmap_read_unlock(mm); - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); - if (flags & VM_FAULT_MAJOR) - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address); - else - perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address); - return; /* Something tried to access memory that isn't in our memory map.. |