diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-25 09:39:36 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-03-25 09:39:36 -0700 |
| commit | 1f1c153e406a7375ae0fc3d6000b64e7ba27cf8a (patch) | |
| tree | 65ef22de3c57d33702e38f89d7a8aa9f7bb79822 /arch | |
| parent | 9a8b3d5f71eb74b1b95927bd320b1070866a119a (diff) | |
| parent | fe2640bd7a62f1f7c3f55fbda31084085075bc30 (diff) | |
| download | linux-1f1c153e406a7375ae0fc3d6000b64e7ba27cf8a.tar.bz2 | |
Merge tag 'powerpc-5.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
"Livepatch support for 32-bit is probably the standout new feature,
otherwise mostly just lots of bits and pieces all over the board.
There's a series of commits cleaning up function descriptor handling,
which touches a few other arches as well as LKDTM. It has acks from
Arnd, Kees and Helge.
Summary:
- Enforce kernel RO, and implement STRICT_MODULE_RWX for 603.
- Add support for livepatch to 32-bit.
- Implement CONFIG_DYNAMIC_FTRACE_WITH_ARGS.
- Merge vdso64 and vdso32 into a single directory.
- Fix build errors with newer binutils.
- Add support for UADDR64 relocations, which are emitted by some
toolchains. This allows powerpc to build with the latest lld.
- Fix (another) potential userspace r13 corruption in transactional
memory handling.
- Cleanups of function descriptor handling & related fixes to LKDTM.
Thanks to Abdul Haleem, Alexey Kardashevskiy, Anders Roxell, Aneesh
Kumar K.V, Anton Blanchard, Arnd Bergmann, Athira Rajeev, Bhaskar
Chowdhury, Cédric Le Goater, Chen Jingwen, Christophe JAILLET,
Christophe Leroy, Corentin Labbe, Daniel Axtens, Daniel Henrique
Barboza, David Dai, Fabiano Rosas, Ganesh Goudar, Guo Zhengkui, Hangyu
Hua, Haren Myneni, Hari Bathini, Igor Zhbanov, Jakob Koschel, Jason
Wang, Jeremy Kerr, Joachim Wiberg, Jordan Niethe, Julia Lawall, Kajol
Jain, Kees Cook, Laurent Dufour, Madhavan Srinivasan, Mamatha Inamdar,
Maxime Bizon, Maxim Kiselev, Maxim Kochetkov, Michal Suchanek,
Nageswara R Sastry, Nathan Lynch, Naveen N. Rao, Nicholas Piggin,
Nour-eddine Taleb, Paul Menzel, Ping Fang, Pratik R. Sampat, Randy
Dunlap, Ritesh Harjani, Rohan McLure, Russell Currey, Sachin Sant,
Segher Boessenkool, Shivaprasad G Bhat, Sourabh Jain, Thierry Reding,
Tobias Waldekranz, Tyrel Datwyler, Vaibhav Jain, Vladimir Oltean,
Wedson Almeida Filho, and YueHaibing"
* tag 'powerpc-5.18-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (179 commits)
powerpc/pseries: Fix use after free in remove_phb_dynamic()
powerpc/time: improve decrementer clockevent processing
powerpc/time: Fix KVM host re-arming a timer beyond decrementer range
powerpc/tm: Fix more userspace r13 corruption
powerpc/xive: fix return value of __setup handler
powerpc/64: Add UADDR64 relocation support
powerpc: 8xx: fix a return value error in mpc8xx_pic_init
powerpc/ps3: remove unneeded semicolons
powerpc/64: Force inlining of prevent_user_access() and set_kuap()
powerpc/bitops: Force inlining of fls()
powerpc: declare unmodified attribute_group usages const
powerpc/spufs: Fix build warning when CONFIG_PROC_FS=n
powerpc/secvar: fix refcount leak in format_show()
powerpc/64e: Tie PPC_BOOK3E_64 to PPC_FSL_BOOK3E
powerpc: Move C prototypes out of asm-prototypes.h
powerpc/kexec: Declare kexec_paca static
powerpc/smp: Declare current_set static
powerpc: Cleanup asm-prototypes.c
powerpc/ftrace: Use STK_GOT in ftrace_mprofile.S
powerpc/ftrace: Regroup PPC64 specific operations in ftrace_mprofile.S
...
Diffstat (limited to 'arch')
206 files changed, 3057 insertions, 2170 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 9af3a597cc67..84bc1de02720 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -202,6 +202,9 @@ config HAVE_FUNCTION_ERROR_INJECTION config HAVE_NMI bool +config HAVE_FUNCTION_DESCRIPTORS + bool + config TRACE_IRQFLAGS_SUPPORT bool diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index b2317324827f..cb93769a9f2a 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -36,6 +36,7 @@ config IA64 select HAVE_SETUP_PER_CPU_AREA select TTY select HAVE_ARCH_TRACEHOOK + select HAVE_FUNCTION_DESCRIPTORS select HAVE_VIRT_CPU_ACCOUNTING select HUGETLB_PAGE_SIZE_VARIABLE if HUGETLB_PAGE select VIRT_TO_BUS diff --git a/arch/ia64/include/asm/elf.h b/arch/ia64/include/asm/elf.h index 6629301a2620..2ef5f9966ad1 100644 --- a/arch/ia64/include/asm/elf.h +++ b/arch/ia64/include/asm/elf.h @@ -226,7 +226,7 @@ struct got_entry { * Layout of the Function Descriptor */ struct fdesc { - uint64_t ip; + uint64_t addr; uint64_t gp; }; diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h index 3a033d2008b3..8e0875cf6071 100644 --- a/arch/ia64/include/asm/sections.h +++ b/arch/ia64/include/asm/sections.h @@ -9,6 +9,9 @@ #include <linux/elf.h> #include <linux/uaccess.h> + +typedef struct fdesc func_desc_t; + #include <asm-generic/sections.h> extern char __phys_per_cpu_start[]; @@ -27,25 +30,4 @@ extern char __start_gate_brl_fsys_bubble_down_patchlist[], __end_gate_brl_fsys_b extern char __start_unwind[], __end_unwind[]; extern char __start_ivt_text[], __end_ivt_text[]; -#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 - -#undef dereference_function_descriptor -static inline void *dereference_function_descriptor(void *ptr) -{ - struct fdesc *desc = ptr; - void *p; - - if (!get_kernel_nofault(p, (void *)&desc->ip)) - ptr = p; - return ptr; -} - -#undef dereference_kernel_function_descriptor -static inline void *dereference_kernel_function_descriptor(void *ptr) -{ - if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd) - return ptr; - return dereference_function_descriptor(ptr); -} - #endif /* _ASM_IA64_SECTIONS_H */ diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c index 360f36b0eb3f..8f62cf97f691 100644 --- a/arch/ia64/kernel/module.c +++ b/arch/ia64/kernel/module.c @@ -602,15 +602,15 @@ get_fdesc (struct module *mod, uint64_t value, int *okp) return value; /* Look for existing function descriptor. */ - while (fdesc->ip) { - if (fdesc->ip == value) + while (fdesc->addr) { + if (fdesc->addr == value) return (uint64_t)fdesc; if ((uint64_t) ++fdesc >= mod->arch.opd->sh_addr + mod->arch.opd->sh_size) BUG(); } /* Create new one */ - fdesc->ip = value; + fdesc->addr = value; fdesc->gp = mod->arch.gp; return (uint64_t) fdesc; } diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 00cb889bd9a6..90fc95bd55ca 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -72,6 +72,7 @@ config PARISC select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS select TRACE_IRQFLAGS_SUPPORT + select HAVE_FUNCTION_DESCRIPTORS if 64BIT help The PA-RISC microprocessor is designed by Hewlett-Packard and used diff --git a/arch/parisc/include/asm/sections.h b/arch/parisc/include/asm/sections.h index bb52aea0cb21..33df42b5cc6d 100644 --- a/arch/parisc/include/asm/sections.h +++ b/arch/parisc/include/asm/sections.h @@ -2,20 +2,14 @@ #ifndef _PARISC_SECTIONS_H #define _PARISC_SECTIONS_H +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +#include <asm/elf.h> +typedef Elf64_Fdesc func_desc_t; +#endif + /* nothing to see, move along */ #include <asm-generic/sections.h> extern char __alt_instructions[], __alt_instructions_end[]; -#ifdef CONFIG_64BIT - -#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 - -#undef dereference_function_descriptor -void *dereference_function_descriptor(void *); - -#undef dereference_kernel_function_descriptor -void *dereference_kernel_function_descriptor(void *); -#endif - #endif diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index ea3d83b6fb62..2030c77592d3 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -263,27 +263,6 @@ __get_wchan(struct task_struct *p) return 0; } -#ifdef CONFIG_64BIT -void *dereference_function_descriptor(void *ptr) -{ - Elf64_Fdesc *desc = ptr; - void *p; - - if (!get_kernel_nofault(p, (void *)&desc->addr)) - ptr = p; - return ptr; -} - -void *dereference_kernel_function_descriptor(void *ptr) -{ - if (ptr < (void *)__start_opd || - ptr >= (void *)__end_opd) - return ptr; - - return dereference_function_descriptor(ptr); -} -#endif - static inline unsigned long brk_rnd(void) { return (get_random_int() & BRK_RND_MASK) << PAGE_SHIFT; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 7e7387bd7d53..174edabb74fa 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -9,6 +9,10 @@ config 64BIT bool default y if PPC64 +config LIVEPATCH_64 + def_bool PPC64 + depends on LIVEPATCH + config MMU bool default y @@ -132,7 +136,7 @@ config PPC select ARCH_HAS_SET_MEMORY select ARCH_HAS_STRICT_KERNEL_RWX if (PPC_BOOK3S || PPC_8xx || 40x) && !HIBERNATION select ARCH_HAS_STRICT_KERNEL_RWX if FSL_BOOKE && !HIBERNATION && !RANDOMIZE_BASE - select ARCH_HAS_STRICT_MODULE_RWX if ARCH_HAS_STRICT_KERNEL_RWX && !PPC_BOOK3S_32 + select ARCH_HAS_STRICT_MODULE_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UACCESS_FLUSHCACHE select ARCH_HAS_UBSAN_SANITIZE_ALL @@ -198,11 +202,13 @@ config PPC select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_STACKOVERFLOW select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_ARGS if MPROFILE_KERNEL || PPC32 select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL || PPC32 select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU) select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_FUNCTION_DESCRIPTORS if PPC64 && !CPU_LITTLE_ENDIAN select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER @@ -222,7 +228,7 @@ config PPC select HAVE_KPROBES_ON_FTRACE select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION - select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS && PPC64 + select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) select HAVE_OPTPROBES diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 5f16ac1583c5..eb541e730d3c 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -171,7 +171,7 @@ else CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mtune=power7,$(call cc-option,-mtune=power5)) CFLAGS-$(CONFIG_GENERIC_CPU) += $(call cc-option,-mcpu=power5,-mcpu=power4) endif -else +else ifdef CONFIG_PPC_BOOK3E_64 CFLAGS-$(CONFIG_GENERIC_CPU) += -mcpu=powerpc64 endif @@ -213,7 +213,7 @@ CHECKFLAGS += -m$(BITS) -D__powerpc__ -D__powerpc$(BITS)__ ifdef CONFIG_CPU_BIG_ENDIAN CHECKFLAGS += -D__BIG_ENDIAN__ else -CHECKFLAGS += -D__LITTLE_ENDIAN__ +CHECKFLAGS += -D__LITTLE_ENDIAN__ -D_CALL_ELF=2 endif ifdef CONFIG_476FPE_ERR46 @@ -421,9 +421,9 @@ ifeq ($(KBUILD_EXTMOD),) prepare: vdso_prepare vdso_prepare: prepare0 $(if $(CONFIG_VDSO32),$(Q)$(MAKE) \ - $(build)=arch/powerpc/kernel/vdso32 include/generated/vdso32-offsets.h) + $(build)=arch/powerpc/kernel/vdso include/generated/vdso32-offsets.h) $(if $(CONFIG_PPC64),$(Q)$(MAKE) \ - $(build)=arch/powerpc/kernel/vdso64 include/generated/vdso64-offsets.h) + $(build)=arch/powerpc/kernel/vdso include/generated/vdso64-offsets.h) endif archprepare: checkbin diff --git a/arch/powerpc/boot/.gitignore b/arch/powerpc/boot/.gitignore index 1eee61b82341..a4716d138cfc 100644 --- a/arch/powerpc/boot/.gitignore +++ b/arch/powerpc/boot/.gitignore @@ -16,6 +16,7 @@ kernel-vmlinux.strip.c kernel-vmlinux.strip.gz mktree otheros.bld +otheros-too-big.bld uImage cuImage.* dtbImage.* diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts new file mode 100644 index 000000000000..73f8c998c64d --- /dev/null +++ b/arch/powerpc/boot/dts/fsl/t1040rdb-rev-a.dts @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * T1040RDB-REV-A Device Tree Source + * + * Copyright 2014 - 2015 Freescale Semiconductor Inc. + * + */ + +#include "t1040rdb.dts" + +/ { + model = "fsl,T1040RDB-REV-A"; + compatible = "fsl,T1040RDB-REV-A"; +}; + +&seville_port0 { + label = "ETH5"; +}; + +&seville_port2 { + label = "ETH7"; +}; + +&seville_port4 { + label = "ETH9"; +}; + +&seville_port6 { + label = "ETH11"; +}; diff --git a/arch/powerpc/boot/dts/fsl/t1040rdb.dts b/arch/powerpc/boot/dts/fsl/t1040rdb.dts index af0c8a6f5613..b6733e7e6580 100644 --- a/arch/powerpc/boot/dts/fsl/t1040rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1040rdb.dts @@ -119,7 +119,7 @@ managed = "in-band-status"; phy-handle = <&phy_qsgmii_0>; phy-mode = "qsgmii"; - label = "ETH5"; + label = "ETH3"; status = "okay"; }; @@ -135,7 +135,7 @@ managed = "in-band-status"; phy-handle = <&phy_qsgmii_2>; phy-mode = "qsgmii"; - label = "ETH7"; + label = "ETH5"; status = "okay"; }; @@ -151,7 +151,7 @@ managed = "in-band-status"; phy-handle = <&phy_qsgmii_4>; phy-mode = "qsgmii"; - label = "ETH9"; + label = "ETH7"; status = "okay"; }; @@ -167,7 +167,7 @@ managed = "in-band-status"; phy-handle = <&phy_qsgmii_6>; phy-mode = "qsgmii"; - label = "ETH11"; + label = "ETH9"; status = "okay"; }; diff --git a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi index 099a598c74c0..bfe1ed5be337 100644 --- a/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi +++ b/arch/powerpc/boot/dts/fsl/t104xrdb.dtsi @@ -139,12 +139,12 @@ fman@400000 { ethernet@e6000 { phy-handle = <&phy_rgmii_0>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-id"; }; ethernet@e8000 { phy-handle = <&phy_rgmii_1>; - phy-connection-type = "rgmii"; + phy-connection-type = "rgmii-id"; }; mdio0: mdio@fc000 { diff --git a/arch/powerpc/boot/dts/xpedite5200.dts b/arch/powerpc/boot/dts/xpedite5200.dts index 840ea84bbb59..74b346f2d43c 100644 --- a/arch/powerpc/boot/dts/xpedite5200.dts +++ b/arch/powerpc/boot/dts/xpedite5200.dts @@ -132,7 +132,7 @@ reg = <0x68>; }; - dtt@48 { + dtt@34 { compatible = "maxim,max1237"; reg = <0x34>; }; diff --git a/arch/powerpc/boot/dts/xpedite5200_xmon.dts b/arch/powerpc/boot/dts/xpedite5200_xmon.dts index 449fc1b5dc23..d491c7a8f979 100644 --- a/arch/powerpc/boot/dts/xpedite5200_xmon.dts +++ b/arch/powerpc/boot/dts/xpedite5200_xmon.dts @@ -136,7 +136,7 @@ reg = <0x68>; }; - dtt@48 { + dtt@34 { compatible = "maxim,max1237"; reg = <0x34>; }; diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 2b736d9fbb1b..2bc53c646ccd 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -21,6 +21,7 @@ #define PPC_STLCX stringify_in_c(stdcx.) #define PPC_CNTLZL stringify_in_c(cntlzd) #define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS) +#define PPC_SRL stringify_in_c(srd) #define PPC_LR_STKOFF 16 #define PPC_MIN_STKFRM 112 @@ -54,6 +55,7 @@ #define PPC_STLCX stringify_in_c(stwcx.) #define PPC_CNTLZL stringify_in_c(cntlzw) #define PPC_MTOCRF stringify_in_c(mtcrf) +#define PPC_SRL stringify_in_c(srw) #define PPC_LR_STKOFF 4 #define PPC_MIN_STKFRM 16 diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index 41b8a1e1144a..d995c65d18ab 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -19,22 +19,6 @@ #include <uapi/asm/ucontext.h> -/* SMP */ -extern struct task_struct *current_set[NR_CPUS]; -extern struct task_struct *secondary_current; -void start_secondary(void *unused); - -/* kexec */ -struct paca_struct; -struct kimage; -extern struct paca_struct kexec_paca; -void kexec_copy_flush(struct kimage *image); - -/* pseries hcall tracing */ -extern struct static_key hcall_tracepoint_key; -void __trace_hcall_entry(unsigned long opcode, unsigned long *args); -void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); - /* Ultravisor */ #if defined(CONFIG_PPC_POWERNV) || defined(CONFIG_PPC_SVM) long ucall_norets(unsigned long opcode, ...); @@ -50,49 +34,12 @@ int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3, int64_t a4, int64_t a5, int64_t a6, int64_t a7, int64_t opcode, uint64_t msr); -/* VMX copying */ -int enter_vmx_usercopy(void); -int exit_vmx_usercopy(void); -int enter_vmx_ops(void); -void *exit_vmx_ops(void *dest); - -/* signals, syscalls and interrupts */ -long sys_swapcontext(struct ucontext __user *old_ctx, - struct ucontext __user *new_ctx, - long ctx_size); -#ifdef CONFIG_PPC32 -long sys_debug_setcontext(struct ucontext __user *ctx, - int ndbg, struct sig_dbg_op __user *dbg); -int -ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, - struct __kernel_old_timeval __user *tvp); -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, long scv); -notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs); -notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs); -#ifdef CONFIG_PPC64 -unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *regs); -unsigned long interrupt_exit_user_restart(struct pt_regs *regs); -unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs); -#endif - -long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, - u32 len_high, u32 len_low); -long sys_switch_endian(void); - /* prom_init (OpenFirmware) */ unsigned long __init prom_init(unsigned long r3, unsigned long r4, unsigned long pp, unsigned long r6, unsigned long r7, unsigned long kbase); -/* setup */ -void __init early_setup(unsigned long dt_ptr); -void early_setup_secondary(void); - /* misc runtime */ extern u64 __bswapdi2(u64); extern s64 __lshrdi3(s64, int); @@ -103,11 +50,6 @@ extern int __ucmpdi2(u64, u64); /* tracing */ void _mcount(void); -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, - unsigned long sp); - -void pnv_power9_force_smt4_catch(void); -void pnv_power9_force_smt4_release(void); /* Transaction memory related */ void tm_enable(void); diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index ea5d27dda8cf..344fba3b16eb 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -287,7 +287,7 @@ static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr) * fls: find last (most-significant) bit set. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline int fls(unsigned int x) +static __always_inline int fls(unsigned int x) { int lz; @@ -305,7 +305,7 @@ static inline int fls(unsigned int x) * 32-bit fls calls. */ #ifdef CONFIG_PPC64 -static inline int fls64(__u64 x) +static __always_inline int fls64(__u64 x) { int lz; diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index 95e06f2a8e23..40041ac713d9 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -298,28 +298,35 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p unsigned long clr, unsigned long set, int huge) { pte_basic_t old; - unsigned long tmp; - __asm__ __volatile__( + if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) { + unsigned long tmp; + + asm volatile( #ifndef CONFIG_PTE_64BIT -"1: lwarx %0, 0, %3\n" -" andc %1, %0, %4\n" + "1: lwarx %0, 0, %3\n" + " andc %1, %0, %4\n" #else -"1: lwarx %L0, 0, %3\n" -" lwz %0, -4(%3)\n" -" andc %1, %L0, %4\n" + "1: lwarx %L0, 0, %3\n" + " lwz %0, -4(%3)\n" + " andc %1, %L0, %4\n" #endif -" or %1, %1, %5\n" -" stwcx. %1, 0, %3\n" -" bne- 1b" - : "=&r" (old), "=&r" (tmp), "=m" (*p) + " or %1, %1, %5\n" + " stwcx. %1, 0, %3\n" + " bne- 1b" + : "=&r" (old), "=&r" (tmp), "=m" (*p) #ifndef CONFIG_PTE_64BIT - : "r" (p), + : "r" (p), #else - : "b" ((unsigned long)(p) + 4), + : "b" ((unsigned long)(p) + 4), #endif - "r" (clr), "r" (set), "m" (*p) - : "cc" ); + "r" (clr), "r" (set), "m" (*p) + : "cc" ); + } else { + old = pte_val(*p); + + *p = __pte((old & ~(pte_basic_t)clr) | set); + } return old; } diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h index 69fcf63eec94..54cf46808157 100644 --- a/arch/powerpc/include/asm/book3s/64/kup.h +++ b/arch/powerpc/include/asm/book3s/64/kup.h @@ -328,7 +328,7 @@ static inline unsigned long get_kuap(void) return mfspr(SPRN_AMR); } -static inline void set_kuap(unsigned long value) +static __always_inline void set_kuap(unsigned long value) { if (!mmu_has_feature(MMU_FTR_BOOK3S_KUAP)) return; @@ -398,7 +398,7 @@ static __always_inline void allow_user_access(void __user *to, const void __user #endif /* !CONFIG_PPC_KUAP */ -static inline void prevent_user_access(unsigned long dir) +static __always_inline void prevent_user_access(unsigned long dir) { set_kuap(AMR_KUAP_BLOCKED); if (static_branch_unlikely(&uaccess_flush_key)) diff --git a/arch/powerpc/include/asm/bug.h b/arch/powerpc/include/asm/bug.h index 02c08d1492f8..ecbae1832de3 100644 --- a/arch/powerpc/include/asm/bug.h +++ b/arch/powerpc/include/asm/bug.h @@ -11,7 +11,7 @@ #ifdef __ASSEMBLY__ #include <asm/asm-offsets.h> #ifdef CONFIG_DEBUG_BUGVERBOSE -.macro EMIT_BUG_ENTRY addr,file,line,flags +.macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" 5001: .4byte \addr - 5001b, 5002f - 5001b .short \line, \flags @@ -22,7 +22,7 @@ .previous .endm #else -.macro EMIT_BUG_ENTRY addr,file,line,flags +.macro __EMIT_BUG_ENTRY addr,file,line,flags .section __bug_table,"aw" 5001: .4byte \addr - 5001b .short \flags @@ -33,7 +33,14 @@ .macro EMIT_WARN_ENTRY addr,file,line,flags EX_TABLE(\addr,\addr+4) - EMIT_BUG_ENTRY \addr,\file,\line,\flags + __EMIT_BUG_ENTRY \addr,\file,\line,\flags +.endm + +.macro EMIT_BUG_ENTRY addr,file,line,flags + .if \flags & 1 /* BUGFLAG_WARNING */ + .err /* Use EMIT_WARN_ENTRY for warnings */ + .endif + __EMIT_BUG_ENTRY \addr,\file,\line,\flags .endm #else /* !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/code-patching.h b/arch/powerpc/include/asm/code-patching.h index e26080539c31..409483b2d0ce 100644 --- a/arch/powerpc/include/asm/code-patching.h +++ b/arch/powerpc/include/asm/code-patching.h @@ -118,7 +118,7 @@ static inline unsigned long ppc_function_entry(void *func) * function's descriptor. The first entry in the descriptor is the * address of the function text. */ - return ((func_descr_t *)func)->entry; + return ((struct func_desc *)func)->addr; #else return (unsigned long)func; #endif diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h index b8425e3cfd81..971589a21bc0 100644 --- a/arch/powerpc/include/asm/elf.h +++ b/arch/powerpc/include/asm/elf.h @@ -176,4 +176,10 @@ do { \ /* Relocate the kernel image to @final_address */ void relocate(unsigned long final_address); +struct func_desc { + unsigned long addr; + unsigned long toc; + unsigned long env; +}; + #endif /* _ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/asm/epapr_hcalls.h b/arch/powerpc/include/asm/epapr_hcalls.h index c99ba08a408d..cdf3c6df5123 100644 --- a/arch/powerpc/include/asm/epapr_hcalls.h +++ b/arch/powerpc/include/asm/epapr_hcalls.h @@ -65,7 +65,7 @@ * but the gcc inline assembly syntax does not allow us to specify registers * on the clobber list that are also on the input/output list. Therefore, * the lists of clobbered registers depends on the number of register - * parmeters ("+r" and "=r") passed to the hypercall. + * parameters ("+r" and "=r") passed to the hypercall. * * Each assembly block should use one of the HCALL_CLOBBERSx macros. As a * general rule, 'x' is the number of parameters passed to the assembly diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 9b702d2b80fb..8dddd34b8ecf 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -54,6 +54,7 @@ #define FW_FEATURE_STUFF_TCE ASM_CONST(0x0000008000000000) #define FW_FEATURE_RPT_INVALIDATE ASM_CONST(0x0000010000000000) #define FW_FEATURE_FORM2_AFFINITY ASM_CONST(0x0000020000000000) +#define FW_FEATURE_ENERGY_SCALE_INFO ASM_CONST(0x0000040000000000) #ifndef __ASSEMBLY__ @@ -74,7 +75,8 @@ enum { 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_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY, + FW_FEATURE_RPT_INVALIDATE | FW_FEATURE_FORM2_AFFINITY | + FW_FEATURE_ENERGY_SCALE_INFO, FW_FEATURE_PSERIES_ALWAYS = 0, FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_ULTRAVISOR, FW_FEATURE_POWERNV_ALWAYS = 0, diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index debe8c4f7062..d83758acd1c7 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -10,44 +10,7 @@ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR -#ifdef __ASSEMBLY__ - -/* Based off of objdump output from glibc */ - -#define MCOUNT_SAVE_FRAME \ - stwu r1,-48(r1); \ - stw r3, 12(r1); \ - stw r4, 16(r1); \ - stw r5, 20(r1); \ - stw r6, 24(r1); \ - mflr r3; \ - lwz r4, 52(r1); \ - mfcr r5; \ - stw r7, 28(r1); \ - stw r8, 32(r1); \ - stw r9, 36(r1); \ - stw r10,40(r1); \ - stw r3, 44(r1); \ - stw r5, 8(r1) - -#define MCOUNT_RESTORE_FRAME \ - lwz r6, 8(r1); \ - lwz r0, 44(r1); \ - lwz r3, 12(r1); \ - mtctr r0; \ - lwz r4, 16(r1); \ - mtcr r6; \ - lwz r5, 20(r1); \ - lwz r6, 24(r1); \ - lwz r0, 52(r1); \ - lwz r7, 28(r1); \ - lwz r8, 32(r1); \ - mtlr r0; \ - lwz r9, 36(r1); \ - lwz r10,40(r1); \ - addi r1, r1, 48 - -#else /* !__ASSEMBLY__ */ +#ifndef __ASSEMBLY__ extern void _mcount(void); static inline unsigned long ftrace_call_adjust(unsigned long addr) @@ -56,9 +19,36 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, + unsigned long sp); + struct dyn_arch_ftrace { struct module *mod; }; + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +struct ftrace_regs { + struct pt_regs regs; +}; + +static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + /* We clear regs.msr in ftrace_call */ + return fregs->regs.msr ? &fregs->regs : NULL; +} + +static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, + unsigned long ip) +{ + regs_set_return_ip(&fregs->regs, ip); +} + +struct ftrace_ops; + +#define ftrace_graph_func ftrace_graph_func +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#endif #endif /* __ASSEMBLY__ */ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 962708fa1017..6a1a1ac5743b 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -15,7 +15,7 @@ extern bool hugetlb_disabled; -void __init hugetlbpage_init_default(void); +void __init hugetlbpage_init_defaultsize(void); int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len); @@ -76,6 +76,9 @@ static inline void __init gigantic_hugetlb_cma_reserve(void) { } +static inline void __init hugetlbpage_init_defaultsize(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 9bcf345cb208..d92a20a85395 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -323,7 +323,8 @@ #define H_SCM_PERFORMANCE_STATS 0x418 #define H_RPT_INVALIDATE 0x448 #define H_SCM_FLUSH 0x44C -#define MAX_HCALL_OPCODE H_SCM_FLUSH +#define H_GET_ENERGY_SCALE_INFO 0x450 +#define MAX_HCALL_OPCODE H_GET_ENERGY_SCALE_INFO /* Scope args for H_SCM_UNBIND_ALL */ #define H_UNBIND_SCOPE_ALL (0x1) @@ -500,6 +501,11 @@ long plpar_hcall_raw(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9(unsigned long opcode, unsigned long *retbuf, ...); long plpar_hcall9_raw(unsigned long opcode, unsigned long *retbuf, ...); +/* pseries hcall tracing */ +extern struct static_key hcall_tracepoint_key; +void __trace_hcall_entry(unsigned long opcode, unsigned long *args); +void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf); + struct hvcall_mpp_data { unsigned long entitled_mem; unsigned long mapped_mem; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index fc28f46d2f9d..f964ef5c57d8 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -123,9 +123,6 @@ static inline void nap_adjust_return(struct pt_regs *regs) #endif } -struct interrupt_state { -}; - static inline void booke_restore_dbcr0(void) { #ifdef CONFIG_PPC_ADV_DEBUG_REGS @@ -138,7 +135,7 @@ static inline void booke_restore_dbcr0(void) #endif } -static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrupt_state *state) +static inline void interrupt_enter_prepare(struct pt_regs *regs) { #ifdef CONFIG_PPC32 if (!arch_irq_disabled_regs(regs)) @@ -228,17 +225,17 @@ static inline void interrupt_enter_prepare(struct pt_regs *regs, struct interrup * However interrupt_nmi_exit_prepare does return directly to regs, because * NMIs do not do "exit work" or replay soft-masked interrupts. */ -static inline void interrupt_exit_prepare(struct pt_regs *regs, struct interrupt_state *state) +static inline void interrupt_exit_prepare(struct pt_regs *regs) { } -static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct interrupt_state *state) +static inline void interrupt_async_enter_prepare(struct pt_regs *regs) { #ifdef CONFIG_PPC64 /* Ensure interrupt_enter_prepare does not enable MSR[EE] */ local_paca->irq_happened |= PACA_IRQ_HARD_DIS; #endif - interrupt_enter_prepare(regs, state); + interrupt_enter_prepare(regs); #ifdef CONFIG_PPC_BOOK3S_64 /* * RI=1 is set by interrupt_enter_prepare, so this thread flags access @@ -251,7 +248,7 @@ static inline void interrupt_async_enter_prepare(struct pt_regs *regs, struct in irq_enter(); } -static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct interrupt_state *state) +static inline void interrupt_async_exit_prepare(struct pt_regs *regs) { /* * Adjust at exit so the main handler sees the true NIA. This must @@ -262,7 +259,7 @@ static inline void interrupt_async_exit_prepare(struct pt_regs *regs, struct int nap_adjust_return(regs); irq_exit(); - interrupt_exit_prepare(regs, state); + interrupt_exit_prepare(regs); } struct interrupt_nmi_state { @@ -447,13 +444,11 @@ static __always_inline void ____##func(struct pt_regs *regs); \ \ interrupt_handler void func(struct pt_regs *regs) \ { \ - struct interrupt_state state; \ - \ - interrupt_enter_prepare(regs, &state); \ + interrupt_enter_prepare(regs); \ \ ____##func (regs); \ \ - interrupt_exit_prepare(regs, &state); \ + interrupt_exit_prepare(regs); \ } \ NOKPROBE_SYMBOL(func); \ \ @@ -482,14 +477,13 @@ static __always_inline long ____##func(struct pt_regs *regs); \ \ interrupt_handler long func(struct pt_regs *regs) \ { \ - struct interrupt_state state; \ long ret; \ \ - interrupt_enter_prepare(regs, &state); \ + interrupt_enter_prepare(regs); \ \ ret = ____##func (regs); \ \ - interrupt_exit_prepare(regs, &state); \ + interrupt_exit_prepare(regs); \ \ return ret; \ } \ @@ -518,13 +512,11 @@ static __always_inline void ____##func(struct pt_regs *regs); \ \ interrupt_handler void func(struct pt_regs *regs) \ { \ - struct interrupt_state state; \ - \ - interrupt_async_enter_prepare(regs, &state); \ + interrupt_async_enter_prepare(regs); \ \ ____##func (regs); \ \ - interrupt_async_exit_prepare(regs, &state); \ + interrupt_async_exit_prepare(regs); \ } \ NOKPROBE_SYMBOL(func); \ \ @@ -612,7 +604,7 @@ DECLARE_INTERRUPT_HANDLER_RAW(do_slb_fault); DECLARE_INTERRUPT_HANDLER(do_bad_segment_interrupt); /* hash_utils.c */ -DECLARE_INTERRUPT_HANDLER_RAW(do_hash_fault); +DECLARE_INTERRUPT_HANDLER(do_hash_fault); /* fault.c */ DECLARE_INTERRUPT_HANDLER(do_page_fault); @@ -644,6 +636,17 @@ static inline void interrupt_cond_local_irq_enable(struct pt_regs *regs) local_irq_enable(); } +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, long scv); +notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs); +notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs); +#ifdef CONFIG_PPC64 +unsigned long syscall_exit_restart(unsigned long r3, struct pt_regs *regs); +unsigned long interrupt_exit_user_restart(struct pt_regs *regs); +unsigned long interrupt_exit_kernel_restart(struct pt_regs *regs); +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_INTERRUPT_H */ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index beba4979bff9..fee979d3a1aa 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -359,25 +359,37 @@ static inline void __raw_writeq_be(unsigned long v, volatile void __iomem *addr) */ static inline void __raw_rm_writeb(u8 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stbcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stbcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writew(u16 val, volatile void __iomem *paddr) { - __asm__ __volatile__("sthcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + sthcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writel(u32 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stwcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stwcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } static inline void __raw_rm_writeq(u64 val, volatile void __iomem *paddr) { - __asm__ __volatile__("stdcix %0,0,%1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + stdcix %0,0,%1; \ + .machine pop;" : : "r" (val), "r" (paddr) : "memory"); } @@ -389,7 +401,10 @@ static inline void __raw_rm_writeq_be(u64 val, volatile void __iomem *paddr) static inline u8 __raw_rm_readb(volatile void __iomem *paddr) { u8 ret; - __asm__ __volatile__("lbzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lbzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -397,7 +412,10 @@ static inline u8 __raw_rm_readb(volatile void __iomem *paddr) static inline u16 __raw_rm_readw(volatile void __iomem *paddr) { u16 ret; - __asm__ __volatile__("lhzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lhzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -405,7 +423,10 @@ static inline u16 __raw_rm_readw(volatile void __iomem *paddr) static inline u32 __raw_rm_readl(volatile void __iomem *paddr) { u32 ret; - __asm__ __volatile__("lwzcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + lwzcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } @@ -413,7 +434,10 @@ static inline u32 __raw_rm_readl(volatile void __iomem *paddr) static inline u64 __raw_rm_readq(volatile void __iomem *paddr) { u64 ret; - __asm__ __volatile__("ldcix %0,0, %1" + __asm__ __volatile__(".machine push; \ + .machine power6; \ + ldcix %0,0, %1; \ + .machine pop;" : "=r" (ret) : "r" (paddr) : "memory"); return ret; } diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 8ebdd23d987c..2aefe14e1442 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -96,6 +96,8 @@ static inline bool kdump_in_progress(void) void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer, unsigned long start_address) __noreturn; +void kexec_copy_flush(struct kimage *image); + #ifdef CONFIG_KEXEC_FILE extern const struct kexec_file_ops kexec_elf64_ops; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index d9bf60bf0816..faf301d0dec0 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -26,6 +26,8 @@ #include <asm/hvcall.h> #include <asm/mce.h> +#define __KVM_HAVE_ARCH_VCPU_DEBUGFS + #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS @@ -295,7 +297,6 @@ struct kvm_arch { bool dawr1_enabled; pgd_t *pgtable; u64 process_table; - struct dentry *debugfs_dir; struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */ #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE @@ -673,7 +674,6 @@ struct kvm_vcpu_arch { u64 timing_min_duration[__NUMBER_OF_KVM_EXIT_TYPES]; u64 timing_max_duration[__NUMBER_OF_KVM_EXIT_TYPES]; u64 timing_last_exit; - struct dentry *debugfs_exit_timing; #endif #ifdef CONFIG_PPC_BOOK3S @@ -831,8 +831,6 @@ struct kvm_vcpu_arch { struct kvmhv_tb_accumulator rm_exit; /* real-mode exit code */ struct kvmhv_tb_accumulator guest_time; /* guest execution */ struct kvmhv_tb_accumulator cede_time; /* time napping inside guest */ - - struct dentry *debugfs_dir; #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ }; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index a14dbcd1b8ce..c583d0c37f31 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -314,6 +314,8 @@ struct kvmppc_ops { int (*svm_off)(struct kvm *kvm); int (*enable_dawr1)(struct kvm *kvm); bool (*hash_v3_possible)(void); + int (*create_vm_debugfs)(struct kvm *kvm); + int (*create_vcpu_debugfs)(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry); }; extern struct kvmppc_ops *kvmppc_hv_ops; diff --git a/arch/powerpc/include/asm/livepatch.h b/arch/powerpc/include/asm/livepatch.h index 4fe018cc207b..6f10de6af6e3 100644 --- a/arch/powerpc/include/asm/livepatch.h +++ b/arch/powerpc/include/asm/livepatch.h @@ -14,21 +14,21 @@ #ifdef CONFIG_LIVEPATCH static inline void klp_arch_set_pc(struct ftrace_regs *fregs, unsigned long ip) { - struct pt_regs *regs = ftrace_get_regs(fregs); - - regs_set_return_ip(regs, ip); + ftrace_instruction_pointer_set(fregs, ip); } #define klp_get_ftrace_location klp_get_ftrace_location static inline unsigned long klp_get_ftrace_location(unsigned long faddr) { /* - * Live patch works only with -mprofile-kernel on PPC. In this case, - * the ftrace location is always within the first 16 bytes. + * Live patch works on PPC32 and only with -mprofile-kernel on PPC64. In + * both cases, the ftrace location is always within the first 16 bytes. */ return ftrace_location_range(faddr, faddr + 16); } +#endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_LIVEPATCH_64 static inline void klp_init_thread_info(struct task_struct *p) { /* + 1 to account for STACK_END_MAGIC */ @@ -36,6 +36,6 @@ static inline void klp_init_thread_info(struct task_struct *p) } #else static inline void klp_init_thread_info(struct task_struct *p) { } -#endif /* CONFIG_LIVEPATCH */ +#endif #endif /* _ASM_POWERPC_LIVEPATCH_H */ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index e821037f74f0..358d171ae8e0 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -10,11 +10,6 @@ #include <asm/setup.h> -/* We export this macro for external modules like Alsa to know if - * ppc_md.feature_call is implemented or not - */ -#define CONFIG_PPC_HAS_FEATURE_CALLS - struct pt_regs; struct pci_bus; struct device_node; @@ -99,6 +94,8 @@ struct machdep_calls { /* Called during machine check exception to retrive fixup address. */ bool (*mce_check_early_recovery)(struct pt_regs *regs); + void (*machine_check_log_err)(void); + /* Motherboard/chipset features. This is a kind of general purpose * hook used to control some machine specific features (like reset * lines, chip power control, etc...). @@ -235,21 +232,6 @@ extern struct machdep_calls *machine_id; machine_id == &mach_##name; \ }) -#ifdef CONFIG_PPC_PMAC -/* - * Power macintoshes have either a CUDA, PMU or SMU controlling - * system reset, power, NVRAM, RTC. - */ -typedef enum sys_ctrler_kind { - SYS_CTRLER_UNKNOWN = 0, - SYS_CTRLER_CUDA = 1, - SYS_CTRLER_PMU = 2, - SYS_CTRLER_SMU = 3, -} sys_ctrler_t; -extern sys_ctrler_t sys_ctrler; - -#endif /* CONFIG_PPC_PMAC */ - static inline void log_error(char *buf, unsigned int err_type, int fatal) { if (ppc_md.log_error) diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h index 331d944280b8..c9f0936bd3c9 100644 --- a/arch/powerpc/include/asm/mce.h +++ b/arch/powerpc/include/asm/mce.h @@ -235,8 +235,21 @@ 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); +void mce_irq_work_queue(void); int mce_register_notifier(struct notifier_block *nb); int mce_unregister_notifier(struct notifier_block *nb); + +#ifdef CONFIG_PPC_BOOK3S_64 +void mce_run_irq_context_handlers(void); +#else +static inline void mce_run_irq_context_handlers(void) { }; +#endif /* CONFIG_PPC_BOOK3S_64 */ + +#ifdef CONFIG_PPC_BOOK3S_64 +void set_mce_pending_irq_work(void); +void clear_mce_pending_irq_work(void); +#endif /* CONFIG_PPC_BOOK3S_64 */ + #ifdef CONFIG_PPC_BOOK3S_64 void flush_and_reload_slb(void); void flush_erat(void); diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index dcc9b338e042..9091e4904a6b 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -338,9 +338,6 @@ static inline int pte_young(pte_t pte) return pte_val(pte) & _PAGE_ACCESSED; } -#define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) - /* * Note that on Book E processors, the pmd contains the kernel virtual * (lowmem) address of the pte page. The physical address is less useful diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 78888b0c30f6..57083f95e82b 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -282,9 +282,6 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, flush_tlb_page(vma, address); } -#define __HAVE_ARCH_PTE_SAME -#define pte_same(A,B) ((pte_val(A) ^ pte_val(B)) == 0) - #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e)) #define pmd_ERROR(e) \ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 295573a82c66..8330968ca346 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -288,6 +288,7 @@ struct paca_struct { #endif #ifdef CONFIG_PPC_BOOK3S_64 struct mce_info *mce_info; + u8 mce_pending_irq_work; #endif /* CONFIG_PPC_BOOK3S_64 */ } ____cacheline_aligned; diff --git a/arch/powerpc/include/asm/pmac_feature.h b/arch/powerpc/include/asm/pmac_feature.h index e08e829261b6..2495866f2e97 100644 --- a/arch/powerpc/include/asm/pmac_feature.h +++ b/arch/powerpc/include/asm/pmac_feature.h @@ -401,5 +401,17 @@ extern u32 __iomem *uninorth_base; */ extern int pmac_get_uninorth_variant(void); +/* + * Power macintoshes have either a CUDA, PMU or SMU controlling + * system reset, power, NVRAM, RTC. + */ +typedef enum sys_ctrler_kind { + SYS_CTRLER_UNKNOWN = 0, + SYS_CTRLER_CUDA = 1, + SYS_CTRLER_PMU = 2, + SYS_CTRLER_SMU = 3, +} sys_ctrler_t; +extern sys_ctrler_t sys_ctrler; + #endif /* __ASM_POWERPC_PMAC_FEATURE_H */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h index 9675303b724e..82f1f0041c6f 100644 --- a/arch/powerpc/include/asm/ppc-opcode.h +++ b/arch/powerpc/include/asm/ppc-opcode.h @@ -262,6 +262,8 @@ #define PPC_INST_MFSPR_PVR 0x7c1f42a6 #define PPC_INST_MFSPR_PVR_MASK 0xfc1ffffe #define PPC_INST_MTMSRD 0x7c000164 +#define PPC_INST_PASTE 0x7c20070d +#define PPC_INST_PASTE_MASK 0xfc2007ff #define PPC_INST_POPCNTB 0x7c0000f4 #define PPC_INST_POPCNTB_MASK 0xfc0007fe #define PPC_INST_RFEBB 0x4c000124 diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index f21e6bde17a1..4dea2d963738 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -203,12 +203,7 @@ GLUE(.,name): #else /* 32-bit */ -#define _ENTRY(n) \ - .globl n; \ -n: - #define _GLOBAL(n) \ - .stabs __stringify(n:F-1),N_FUN,0,0,n;\ .globl n; \ n: @@ -697,12 +692,6 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define evr30 30 #define evr31 31 -/* some stab codes */ -#define N_FUN 36 -#define N_RSYM 64 -#define N_SLINE 68 -#define N_SO 100 - #define RFSCV .long 0x4c0000a4 /* diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index 2c8686d9e964..39c25021030f 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -411,6 +411,8 @@ extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_idle_type(unsigned long type); extern void arch300_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); +void pnv_power9_force_smt4_catch(void); +void pnv_power9_force_smt4_release(void); extern int fix_alignment(struct pt_regs *); @@ -427,6 +429,12 @@ extern int fix_alignment(struct pt_regs *); int do_mathemu(struct pt_regs *regs); +/* VMX copying */ +int enter_vmx_usercopy(void); +int exit_vmx_usercopy(void); +int enter_vmx_ops(void); +void *exit_vmx_ops(void *dest); + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PROCESSOR_H */ diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 82e5b055fa2a..00531af17ce0 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -274,7 +274,6 @@ extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal); #ifdef CONFIG_PPC_PSERIES extern time64_t last_rtas_event; extern int clobbering_unread_rtas_event(void); -extern int pseries_devicetree_update(s32 scope); extern void post_mobility_fixup(void); int rtas_syscall_dispatch_ibm_suspend_me(u64 handle); #else diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index 38f79e42bf3c..8be2c491c733 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -6,6 +6,10 @@ #include <linux/elf.h> #include <linux/uaccess.h> +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +typedef struct func_desc func_desc_t; +#endif + #include <asm-generic/sections.h> extern char __head_end[]; @@ -54,31 +58,6 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end) (unsigned long)_stext < end; } -#ifdef PPC64_ELF_ABI_v1 - -#define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1 - -#undef dereference_function_descriptor -static inline void *dereference_function_descriptor(void *ptr) -{ - struct ppc64_opd_entry *desc = ptr; - void *p; - - if (!get_kernel_nofault(p, (void *)&desc->funcaddr)) - ptr = p; - return ptr; -} - -#undef dereference_kernel_function_descriptor -static inline void *dereference_kernel_function_descriptor(void *ptr) -{ - if (ptr < (void *)__start_opd || ptr >= (void *)__end_opd) - return ptr; - - return dereference_function_descriptor(ptr); -} -#endif /* PPC64_ELF_ABI_v1 */ - #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/set_memory.h b/arch/powerpc/include/asm/set_memory.h index b040094f7920..7ebc807aa8cc 100644 --- a/arch/powerpc/include/asm/set_memory.h +++ b/arch/powerpc/include/asm/set_memory.h @@ -6,6 +6,8 @@ #define SET_MEMORY_RW 1 #define SET_MEMORY_NX 2 #define SET_MEMORY_X 3 +#define SET_MEMORY_NP 4 /* Set memory non present */ +#define SET_MEMORY_P 5 /* Set memory present */ int change_memory_attr(unsigned long addr, int numpages, long action); @@ -29,6 +31,14 @@ static inline int set_memory_x(unsigned long addr, int numpages) return change_memory_attr(addr, numpages, SET_MEMORY_X); } -int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot); +static inline int set_memory_np(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_NP); +} + +static inline int set_memory_p(unsigned long addr, int numpages) +{ + return change_memory_attr(addr, numpages, SET_MEMORY_P); +} #endif diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index d0d3dd531c7f..049ca26893e6 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -76,6 +76,13 @@ static inline void setup_spectre_v2(void) {} #endif void __init do_btb_flush_fixups(void); +#ifdef CONFIG_PPC32 +unsigned long __init early_init(unsigned long dt_ptr); +void __init machine_init(u64 dt_ptr); +#endif +void __init early_setup(unsigned long dt_ptr); +void early_setup_secondary(void); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 007332a4a732..60ab739a5e3b 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -60,6 +60,9 @@ struct smp_ops_t { #endif }; +extern struct task_struct *secondary_current; + +void start_secondary(void *unused); extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern int smp_send_safe_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); extern void smp_send_debugger_break(void); diff --git a/arch/powerpc/include/asm/spu.h b/arch/powerpc/include/asm/spu.h index 8a2d11ba0dae..96ad4510c895 100644 --- a/arch/powerpc/include/asm/spu.h +++ b/arch/powerpc/include/asm/spu.h @@ -249,8 +249,8 @@ void unregister_spu_syscalls(struct spufs_calls *calls); int spu_add_dev_attr(struct device_attribute *attr); void spu_remove_dev_attr(struct device_attribute *attr); -int spu_add_dev_attr_group(struct attribute_group *attrs); -void spu_remove_dev_attr_group(struct attribute_group *attrs); +int spu_add_dev_attr_group(const struct attribute_group *attrs); +void spu_remove_dev_attr_group(const struct attribute_group *attrs); extern void notify_spus_active(void); extern void do_notify_spus_active(void); diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index 7ee66ae5444d..a2b13e55254f 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -18,6 +18,10 @@ asmlinkage long sys_mmap2(unsigned long addr, size_t len, unsigned long fd, unsigned long pgoff); asmlinkage long ppc64_personality(unsigned long personality); asmlinkage long sys_rtas(struct rtas_args __user *uargs); +int ppc_select(int n, fd_set __user *inp, fd_set __user *outp, + fd_set __user *exp, struct __kernel_old_timeval __user *tvp); +long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low, + u32 len_high, u32 len_low); #ifdef CONFIG_COMPAT unsigned long compat_sys_mmap2(unsigned long addr, size_t len, diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index d6e649b3c70b..125328d1b980 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -51,7 +51,7 @@ struct thread_info { unsigned int cpu; #endif unsigned long local_flags; /* private flags for thread */ -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 unsigned long *livepatch_sp; #endif #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC32) diff --git a/arch/powerpc/include/asm/types.h b/arch/powerpc/include/asm/types.h index f1630c553efe..84078c28c1a2 100644 --- a/arch/powerpc/include/asm/types.h +++ b/arch/powerpc/include/asm/types.h @@ -13,9 +13,9 @@ #ifdef __powerpc64__ #if defined(_CALL_ELF) && _CALL_ELF == 2 -#define PPC64_ELF_ABI_v2 +#define PPC64_ELF_ABI_v2 1 #else -#define PPC64_ELF_ABI_v1 +#define PPC64_ELF_ABI_v1 1 #endif #endif /* __powerpc64__ */ @@ -23,12 +23,6 @@ typedef __vector128 vector128; -typedef struct { - unsigned long entry; - unsigned long toc; - unsigned long env; -} func_descr_t; - #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_TYPES_H */ diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 2e83217f52de..9b82b38ff867 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -116,8 +116,11 @@ do { \ */ #define __get_user_atomic_128_aligned(kaddr, uaddr, err) \ __asm__ __volatile__( \ + ".machine push\n" \ + ".machine altivec\n" \ "1: lvx 0,0,%1 # get user\n" \ " stvx 0,0,%2 # put kernel\n" \ + ".machine pop\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ diff --git a/arch/powerpc/include/asm/vas.h b/arch/powerpc/include/asm/vas.h index 57573d9c1e09..83afcb6c194b 100644 --- a/arch/powerpc/include/asm/vas.h +++ b/arch/powerpc/include/asm/vas.h @@ -30,6 +30,16 @@ #define VAS_THRESH_FIFO_GT_EIGHTH_FULL 3 /* + * VAS window Linux status bits + */ +#define VAS_WIN_ACTIVE 0x0 /* Used in platform independent */ + /* vas mmap() */ +/* Window is closed in the hypervisor due to lost credit */ +#define VAS_WIN_NO_CRED_CLOSE 0x00000001 +/* Window is closed due to migration */ +#define VAS_WIN_MIGRATE_CLOSE 0x00000002 + +/* * Get/Set bit fields */ #define GET_FIELD(m, v) (((v) & (m)) >> MASK_LSH(m)) @@ -59,6 +69,9 @@ struct vas_user_win_ref { struct pid *pid; /* PID of owner */ struct pid *tgid; /* Thread group ID of owner */ struct mm_struct *mm; /* Linux process mm_struct */ + struct mutex mmap_mutex; /* protects paste address mmap() */ + /* with DLPAR close/open windows */ + struct vm_area_struct *vma; /* Save VMA and used in DLPAR ops */ }; /* @@ -67,6 +80,7 @@ struct vas_user_win_ref { struct vas_window { u32 winid; u32 wcreds_max; /* Window credits */ + u32 status; /* Window status used in OS */ enum vas_cop_type cop; struct vas_user_win_ref task_ref; char *dbgname; diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 1faff0be1111..f0a4cf01e85c 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -2,74 +2,9 @@ #ifndef _ASM_POWERPC_VDSO_GETTIMEOFDAY_H #define _ASM_POWERPC_VDSO_GETTIMEOFDAY_H -#include <asm/page.h> - -#ifdef __ASSEMBLY__ - -#include <asm/ppc_asm.h> - -/* - * The macros sets two stack frames, one for the caller and one for the callee - * because there are no requirement for the caller to set a stack frame when - * calling VDSO so it may have omitted to set one, especially on PPC64 - */ - -.macro cvdso_call funct - .cfi_startproc - PPC_STLU r1, -PPC_MIN_STKFRM(r1) - mflr r0 - .cfi_register lr, r0 - PPC_STLU r1, -PPC_MIN_STKFRM(r1) - PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) -#ifdef __powerpc64__ - PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) -#endif - get_datapage r5 - addi r5, r5, VDSO_DATA_OFFSET - bl DOTSYM(\funct) - PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) -#ifdef __powerpc64__ - PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) -#endif - cmpwi r3, 0 - mtlr r0 - .cfi_restore lr - addi r1, r1, 2 * PPC_MIN_STKFRM - crclr so - beqlr+ - crset so - neg r3, r3 - blr - .cfi_endproc -.endm - -.macro cvdso_call_time funct - .cfi_startproc - PPC_STLU r1, -PPC_MIN_STKFRM(r1) - mflr r0 - .cfi_register lr, r0 - PPC_STLU r1, -PPC_MIN_STKFRM(r1) - PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) -#ifdef __powerpc64__ - PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) -#endif - get_datapage r4 - addi r4, r4, VDSO_DATA_OFFSET - bl DOTSYM(\funct) - PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) -#ifdef __powerpc64__ - PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) -#endif - crclr so - mtlr r0 - .cfi_restore lr - addi r1, r1, 2 * PPC_MIN_STKFRM - blr - .cfi_endproc -.endm - -#else +#ifndef __ASSEMBLY__ +#include <asm/page.h> #include <asm/vdso/timebase.h> #include <asm/barrier.h> #include <asm/unistd.h> diff --git a/arch/powerpc/include/uapi/asm/elf.h b/arch/powerpc/include/uapi/asm/elf.h index 860c59291bfc..308857123a08 100644 --- a/arch/powerpc/include/uapi/asm/elf.h +++ b/arch/powerpc/include/uapi/asm/elf.h @@ -289,12 +289,4 @@ typedef elf_fpreg_t elf_vsrreghalf_t32[ELF_NVSRHALFREG]; /* Keep this the last entry. */ #define R_PPC64_NUM 253 -/* There's actually a third entry here, but it's unused */ -struct ppc64_opd_entry -{ - unsigned long funcaddr; - unsigned long r2; -}; - - #endif /* _UAPI_ASM_POWERPC_ELF_H */ diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h index 82488b1e7276..17439925045c 100644 --- a/arch/powerpc/include/uapi/asm/papr_pdsm.h +++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h @@ -116,6 +116,22 @@ struct nd_papr_pdsm_health { }; }; +/* Flags for injecting specific smart errors */ +#define PDSM_SMART_INJECT_HEALTH_FATAL (1 << 0) +#define PDSM_SMART_INJECT_BAD_SHUTDOWN (1 << 1) + +struct nd_papr_pdsm_smart_inject { + union { + struct { + /* One or more of PDSM_SMART_INJECT_ */ + __u32 flags; + __u8 fatal_enable; + __u8 unsafe_shutdown_enable; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + /* * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel * via 'nd_cmd_pkg.nd_command' member of the ioctl struct @@ -123,12 +139,14 @@ struct nd_papr_pdsm_health { enum papr_pdsm { PAPR_PDSM_MIN = 0x0, PAPR_PDSM_HEALTH, + PAPR_PDSM_SMART_INJECT, PAPR_PDSM_MAX, }; /* Maximal union that can hold all possible payload types */ union nd_pdsm_payload { struct nd_papr_pdsm_health health; + struct nd_papr_pdsm_smart_inject smart_inject; __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; } __packed; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 4d7829399570..4ddd161aef32 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -194,8 +194,8 @@ targets += prom_init_check clean-files := vmlinux.lds # Force dependency (incbin is bad) -$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg -$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg +$(obj)/vdso32_wrapper.o : $(obj)/vdso/vdso32.so.dbg +$(obj)/vdso64_wrapper.o : $(obj)/vdso/vdso64.so.dbg # for cleaning -subdir- += vdso32 vdso64 +subdir- += vdso diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 7582f3e3a330..eec536aef83a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -94,7 +94,7 @@ int main(void) OFFSET(TASK_CPU, task_struct, thread_info.cpu); #endif -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 OFFSET(TI_livepatch_sp, thread_info, livepatch_sp); #endif diff --git a/arch/powerpc/kernel/early_32.c b/arch/powerpc/kernel/early_32.c index ef2ad4945904..03f1135ef64f 100644 --- a/arch/powerpc/kernel/early_32.c +++ b/arch/powerpc/kernel/early_32.c @@ -8,7 +8,6 @@ #include <linux/kernel.h> #include <asm/setup.h> #include <asm/sections.h> -#include <asm/asm-prototypes.h> /* * We're called here very early in the boot. diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 4fdb7c77fda1..65562c4a0a69 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1643,9 +1643,11 @@ int __init setup_fadump(void) if (fw_dump.ops->fadump_process(&fw_dump) < 0) fadump_invalidate_release_mem(); } - /* Initialize the kernel dump memory structure for FAD registration. */ - else if (fw_dump.reserve_dump_area_size) + /* Initialize the kernel dump memory structure and register with f/w */ + else if (fw_dump.reserve_dump_area_size) { fw_dump.ops->fadump_init_mem_struct(&fw_dump); + register_fadump(); + } /* * In case of panic, fadump is triggered via ppc_panic_event() @@ -1657,7 +1659,12 @@ int __init setup_fadump(void) return 1; } -subsys_initcall(setup_fadump); +/* + * Use subsys_initcall_sync() here because there is dependency with + * crash_save_vmcoreinfo_init(), which mush run first to ensure vmcoreinfo initialization + * is done before regisering with f/w. + */ +subsys_initcall_sync(setup_fadump); #else /* !CONFIG_PRESERVE_FA_DUMP */ /* Scan the Firmware Assisted dump configuration details. */ diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index b6c6d1de5fd5..088f500896c7 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -53,8 +53,8 @@ * This is all going to change RSN when we add bi_recs....... -- Dan */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); mr r31,r3 /* save device tree ptr */ @@ -82,19 +82,19 @@ turn_on_mmu: */ . = 0xc0 crit_save: -_ENTRY(crit_r10) +_GLOBAL(crit_r10) .space 4 -_ENTRY(crit_r11) +_GLOBAL(crit_r11) .space 4 -_ENTRY(crit_srr0) +_GLOBAL(crit_srr0) .space 4 -_ENTRY(crit_srr1) +_GLOBAL(crit_srr1) .space 4 -_ENTRY(crit_r1) +_GLOBAL(crit_r1) .space 4 -_ENTRY(crit_dear) +_GLOBAL(crit_dear) .space 4 -_ENTRY(crit_esr) +_GLOBAL(crit_esr) .space 4 /* diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S index b73a56466903..f15cb9fdb692 100644 --- a/arch/powerpc/kernel/head_44x.S +++ b/arch/powerpc/kernel/head_44x.S @@ -52,8 +52,8 @@ * */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 0d073b9fd52c..0b05f2be66b9 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -53,8 +53,8 @@ #define PAGE_SHIFT_8M 23 __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* MPC8xx * This port was done on an MBX board with an 860. Right now I only diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index b876ef8c70a7..6c739beb938c 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -50,16 +50,13 @@ mtspr SPRN_DBAT##n##L,RB __HEAD - .stabs "arch/powerpc/kernel/",N_SO,0,0,0f - .stabs "head_book3s_32.S",N_SO,0,0,0f -0: -_ENTRY(_stext); +_GLOBAL(_stext); /* * _start is defined this way because the XCOFF loader in the OpenFirmware * on the powermac expects the entry point to be a procedure descriptor. */ -_ENTRY(_start); +_GLOBAL(_start); /* * These are here for legacy reasons, the kernel used to * need to look like a coff function entry for the pmac @@ -504,14 +501,12 @@ DataLoadTLBMiss: lwz r0,0(r2) /* get linux-style pte */ andc. r1,r1,r0 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ - /* - * NOTE! We are assuming this is not an SMP system, otherwise - * we would need to update the pte atomically with lwarx/stwcx. - */ /* Convert linux-style PTE to low word of PPC-style PTE */ rlwinm r1,r0,32-9,30,30 /* _PAGE_RW -> PP msb */ rlwimi r0,r0,32-1,30,30 /* _PAGE_USER -> PP msb */ + rlwimi r1,r0,32-3,24,24 /* _PAGE_RW -> _PAGE_DIRTY */ rlwimi r0,r0,32-1,31,31 /* _PAGE_USER -> PP lsb */ + xori r1,r1,_PAGE_DIRTY /* clear dirty when not rw */ ori r1,r1,0xe04 /* clear out reserved bits */ andc r1,r0,r1 /* PP = user? rw? 1: 3: 0 */ BEGIN_FTR_SECTION @@ -586,10 +581,6 @@ DataStoreTLBMiss: lwz r0,0(r2) /* get linux-style pte */ andc. r1,r1,r0 /* check access & ~permission */ bne- DataAddressInvalid /* return if access not permitted */ - /* - * NOTE! We are assuming this is not an SMP system, otherwise - * we would need to update the pte atomically with lwarx/stwcx. - */ /* Convert linux-style PTE to low word of PPC-style PTE */ rlwimi r0,r0,32-2,31,31 /* _PAGE_USER -> PP lsb */ li r1,0xe06 /* clear out reserved bits & PP msb */ @@ -784,7 +775,7 @@ relocate_kernel: * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5. */ -_ENTRY(copy_and_flush) +_GLOBAL(copy_and_flush) addi r5,r5,-4 addi r6,r6,-4 4: li r0,L1_CACHE_BYTES/4 @@ -1082,7 +1073,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr -_ENTRY(update_bats) +_GLOBAL(update_bats) lis r4, 1f@h ori r4, r4, 1f@l tophys(r4, r4) diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S index ac2b4dcf5fd3..f0db4f52bc00 100644 --- a/arch/powerpc/kernel/head_fsl_booke.S +++ b/arch/powerpc/kernel/head_fsl_booke.S @@ -54,8 +54,8 @@ * */ __HEAD -_ENTRY(_stext); -_ENTRY(_start); +_GLOBAL(_stext); +_GLOBAL(_start); /* * Reserve a word at a fixed location to store the address * of abatron_pteptrs @@ -154,7 +154,7 @@ _ENTRY(_start); * if needed */ -_ENTRY(__early_start) +_GLOBAL(__early_start) LOAD_REG_ADDR_PIC(r20, kernstart_virt_addr) lwz r20,0(r20) diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index 7cd6ce3ec423..784ea3289c84 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -5,7 +5,6 @@ #include <linux/compat.h> #include <linux/sched/debug.h> /* for show_regs */ -#include <asm/asm-prototypes.h> #include <asm/kup.h> #include <asm/cputime.h> #include <asm/hw_irq.h> diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 2cf31a97126c..752fb182eacb 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -64,7 +64,6 @@ #include <asm/udbg.h> #include <asm/smp.h> #include <asm/livepatch.h> -#include <asm/asm-prototypes.h> #include <asm/hw_irq.h> #include <asm/softirq_stack.h> diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index 2503dd4713b9..18173199b79d 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -24,23 +24,12 @@ #include <asm/machdep.h> #include <asm/mce.h> #include <asm/nmi.h> -#include <asm/asm-prototypes.h> #include "setup.h" -static void machine_check_process_queued_event(struct irq_work *work); -static void machine_check_ue_irq_work(struct irq_work *work); static void machine_check_ue_event(struct machine_check_event *evt); static void machine_process_ue_event(struct work_struct *work); -static struct irq_work mce_event_process_work = { - .func = machine_check_process_queued_event, -}; - -static struct irq_work mce_ue_event_irq_work = { - .func = machine_check_ue_irq_work, -}; - static DECLARE_WORK(mce_ue_event_work, machine_process_ue_event); static BLOCKING_NOTIFIER_HEAD(mce_notifier_list); @@ -89,6 +78,13 @@ static void mce_set_error_info(struct machine_check_event *mce, } } +void mce_irq_work_queue(void) +{ + /* Raise decrementer interrupt */ + arch_irq_work_raise(); + set_mce_pending_irq_work(); +} + /* * Decode and save high level MCE information into per cpu buffer which * is an array of machine_check_event structure. @@ -217,7 +213,7 @@ void release_mce_event(void) get_mce_event(NULL, true); } -static void machine_check_ue_irq_work(struct irq_work *work) +static void machine_check_ue_work(void) { schedule_work(&mce_ue_event_work); } @@ -239,7 +235,7 @@ static void machine_check_ue_event(struct machine_check_event *evt) evt, sizeof(*evt)); /* Queue work to process this event later. */ - irq_work_queue(&mce_ue_event_irq_work); + mce_irq_work_queue(); } /* @@ -249,7 +245,6 @@ void machine_check_queue_event(void) { int index; struct machine_check_event evt; - unsigned long msr; if (!get_mce_event(&evt, MCE_EVENT_RELEASE)) return; @@ -263,20 +258,7 @@ void machine_check_queue_event(void) memcpy(&local_paca->mce_info->mce_event_queue[index], &evt, sizeof(evt)); - /* - * Queue irq work to process this event later. Before - * queuing the work enable translation for non radix LPAR, - * as irq_work_queue may try to access memory outside RMO - * region. - */ - if (!radix_enabled() && firmware_has_feature(FW_FEATURE_LPAR)) { - msr = mfmsr(); - mtmsr(msr | MSR_IR | MSR_DR); - irq_work_queue(&mce_event_process_work); - mtmsr(msr); - } else { - irq_work_queue(&mce_event_process_work); - } + mce_irq_work_queue(); } void mce_common_process_ue(struct pt_regs *regs, @@ -338,7 +320,7 @@ static void machine_process_ue_event(struct work_struct *work) * process pending MCE event from the mce event queue. This function will be * called during syscall exit. */ -static void machine_check_process_queued_event(struct irq_work *work) +static void machine_check_process_queued_event(void) { int index; struct machine_check_event *evt; @@ -363,6 +345,27 @@ static void machine_check_process_queued_event(struct irq_work *work) } } +void set_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 1; +} + +void clear_mce_pending_irq_work(void) +{ + local_paca->mce_pending_irq_work = 0; +} + +void mce_run_irq_context_handlers(void) +{ + if (unlikely(local_paca->mce_pending_irq_work)) { + if (ppc_md.machine_check_log_err) + ppc_md.machine_check_log_err(); + machine_check_process_queued_event(); + machine_check_ue_work(); + clear_mce_pending_irq_work(); + } +} + void machine_check_print_event_info(struct machine_check_event *evt, bool user_mode, bool in_guest) { @@ -401,14 +404,14 @@ void machine_check_print_event_info(struct machine_check_event *evt, static const char *mc_ra_types[] = { "Indeterminate", "Instruction fetch (bad)", - "Instruction fetch (foreign)", + "Instruction fetch (foreign/control memory)", "Page table walk ifetch (bad)", - "Page table walk ifetch (foreign)", + "Page table walk ifetch (foreign/control memory)", "Load (bad)", "Store (bad)", "Page table walk Load/Store (bad)", - "Page table walk Load/Store (foreign)", - "Load/Store (foreign)", + "Page table walk Load/Store (foreign/control memory)", + "Load/Store (foreign/control memory)", }; static const char *mc_link_types[] = { "Indeterminate", diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c index a491ad481d85..a0432ef46967 100644 --- a/arch/powerpc/kernel/module_32.c +++ b/arch/powerpc/kernel/module_32.c @@ -18,6 +18,7 @@ #include <linux/bug.h> #include <linux/sort.h> #include <asm/setup.h> +#include <asm/code-patching.h> /* Count how many different relocations (different symbol, different addend) */ @@ -174,15 +175,25 @@ static uint32_t do_plt_call(void *location, entry++; } - entry->jump[0] = PPC_RAW_LIS(_R12, PPC_HA(val)); - entry->jump[1] = PPC_RAW_ADDI(_R12, _R12, PPC_LO(val)); - entry->jump[2] = PPC_RAW_MTCTR(_R12); - entry->jump[3] = PPC_RAW_BCTR(); + if (patch_instruction(&entry->jump[0], ppc_inst(PPC_RAW_LIS(_R12, PPC_HA(val))))) + return 0; + if (patch_instruction(&entry->jump[1], ppc_inst(PPC_RAW_ADDI(_R12, _R12, PPC_LO(val))))) + return 0; + if (patch_instruction(&entry->jump[2], ppc_inst(PPC_RAW_MTCTR(_R12)))) + return 0; + if (patch_instruction(&entry->jump[3], ppc_inst(PPC_RAW_BCTR()))) + return 0; pr_debug("Initialized plt for 0x%x at %p\n", val, entry); return (uint32_t)entry; } +static int patch_location_16(uint32_t *loc, u16 value) +{ + loc = PTR_ALIGN_DOWN(loc, sizeof(u32)); + return patch_instruction(loc, ppc_inst((*loc & 0xffff0000) | value)); +} + int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, @@ -216,37 +227,42 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, case R_PPC_ADDR16_LO: /* Low half of the symbol */ - *(uint16_t *)location = value; + if (patch_location_16(location, PPC_LO(value))) + return -EFAULT; break; case R_PPC_ADDR16_HI: /* Higher half of the symbol */ - *(uint16_t *)location = (value >> 16); + if (patch_location_16(location, PPC_HI(value))) + return -EFAULT; break; case R_PPC_ADDR16_HA: - /* Sign-adjusted lower 16 bits: PPC ELF ABI says: - (((x >> 16) + ((x & 0x8000) ? 1 : 0))) & 0xFFFF. - This is the same, only sane. - */ - *(uint16_t *)location = (value + 0x8000) >> 16; + if (patch_location_16(location, PPC_HA(value))) + return -EFAULT; break; case R_PPC_REL24: if ((int)(value - (uint32_t)location) < -0x02000000 - || (int)(value - (uint32_t)location) >= 0x02000000) + || (int)(value - (uint32_t)location) >= 0x02000000) { value = do_plt_call(location, value, sechdrs, module); + if (!value) + return -EFAULT; + } /* Only replace bits 2 through 26 */ pr_debug("REL24 value = %08X. location = %08X\n", value, (uint32_t)location); pr_debug("Location before: %08X.\n", *(uint32_t *)location); - *(uint32_t *)location - = (*(uint32_t *)location & ~0x03fffffc) + value = (*(uint32_t *)location & ~0x03fffffc) | ((value - (uint32_t)location) & 0x03fffffc); + + if (patch_instruction(location, ppc_inst(value))) + return -EFAULT; + pr_debug("Location after: %08X.\n", *(uint32_t *)location); pr_debug("ie. jump to %08X+%08X = %08X\n", diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 5d77d3f5fbb5..794720530442 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -14,6 +14,7 @@ #include <linux/ftrace.h> #include <linux/bug.h> #include <linux/uaccess.h> +#include <linux/kernel.h> #include <asm/module.h> #include <asm/firmware.h> #include <asm/code-patching.h> @@ -32,20 +33,13 @@ #ifdef PPC64_ELF_ABI_v2 -/* An address is simply the address of the function. */ -typedef unsigned long func_desc_t; - static func_desc_t func_desc(unsigned long addr) { - return addr; -} -static unsigned long func_addr(unsigned long addr) -{ - return addr; -} -static unsigned long stub_func_addr(func_desc_t func) -{ - return func; + func_desc_t desc = { + .addr = addr, + }; + + return desc; } /* PowerPC64 specific values for the Elf64_Sym st_other field. */ @@ -63,20 +57,9 @@ static unsigned int local_entry_offset(const Elf64_Sym *sym) } #else -/* An address is address of the OPD entry, which contains address of fn. */ -typedef struct ppc64_opd_entry func_desc_t; - static func_desc_t func_desc(unsigned long addr) { - return *(struct ppc64_opd_entry *)addr; -} -static unsigned long func_addr(unsigned long addr) -{ - return func_desc(addr).funcaddr; -} -static unsigned long stub_func_addr(func_desc_t func) -{ - return func.funcaddr; + return *(struct func_desc *)addr; } static unsigned int local_entry_offset(const Elf64_Sym *sym) { @@ -93,6 +76,16 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr) } #endif +static unsigned long func_addr(unsigned long addr) +{ + return func_desc(addr).addr; +} + +static unsigned long stub_func_addr(func_desc_t func) +{ + return func.addr; +} + #define STUB_MAGIC 0x73747562 /* stub */ /* Like PPC32, we need little trampolines to do > 24-bit jumps (into @@ -187,7 +180,7 @@ static int relacmp(const void *_x, const void *_y) static unsigned long get_stubs_size(const Elf64_Ehdr *hdr, const Elf64_Shdr *sechdrs) { - /* One extra reloc so it's always 0-funcaddr terminated */ + /* One extra reloc so it's always 0-addr terminated */ unsigned long relocs = 1; unsigned i; @@ -277,6 +270,12 @@ static Elf64_Sym *find_dot_toc(Elf64_Shdr *sechdrs, return NULL; } +bool module_init_section(const char *name) +{ + /* We don't handle .init for the moment: always return false. */ + return false; +} + int module_frob_arch_sections(Elf64_Ehdr *hdr, Elf64_Shdr *sechdrs, char *secstrings, @@ -286,7 +285,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, /* Find .toc and .stubs sections, symtab and strtab */ for (i = 1; i < hdr->e_shnum; i++) { - char *p; if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0) me->arch.stubs_section = i; else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0) { @@ -298,10 +296,6 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, dedotify_versions((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size); - /* We don't handle .init for the moment: rename to _init */ - while ((p = strstr(secstrings + sechdrs[i].sh_name, ".init"))) - p[0] = '_'; - if (sechdrs[i].sh_type == SHT_SYMTAB) dedotify((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size / sizeof(Elf64_Sym), @@ -428,7 +422,7 @@ static inline int create_stub(const Elf64_Shdr *sechdrs, if (is_mprofile_ftrace_call(name)) return create_ftrace_stub(entry, addr, me); - for (i = 0; i < sizeof(ppc64_stub_insns) / sizeof(u32); i++) { + for (i = 0; i < ARRAY_SIZE(ppc64_stub_insns); i++) { if (patch_instruction(&entry->jump[i], ppc_inst(ppc64_stub_insns[i]))) return 0; diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 3d30d40a0e9c..86c4f009563d 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -352,6 +352,9 @@ static int __init early_init_dt_scan_cpus(unsigned long node, be32_to_cpu(intserv[found_thread])); boot_cpuid = found; + // Pass the boot CPU's hard CPU id back to our caller + *((u32 *)data) = be32_to_cpu(intserv[found_thread]); + /* * PAPR defines "logical" PVR values for cpus that * meet various levels of the architecture: @@ -388,9 +391,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; else if (!dt_cpu_ftrs_in_use()) cur_cpu_spec->cpu_features |= CPU_FTR_SMT; - allocate_paca(boot_cpuid); #endif - set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread])); return 0; } @@ -714,6 +715,7 @@ static inline void save_fscr_to_task(void) {} void __init early_init_devtree(void *params) { + u32 boot_cpu_hwid; phys_addr_t limit; DBG(" -> early_init_devtree(%px)\n", params); @@ -790,8 +792,6 @@ void __init early_init_devtree(void *params) * FIXME .. and the initrd too? */ move_device_tree(); - allocate_paca_ptrs(); - DBG("Scanning CPUs ...\n"); dt_cpu_ftrs_scan(); @@ -799,7 +799,7 @@ void __init early_init_devtree(void *params) /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ - of_scan_flat_dt(early_init_dt_scan_cpus, NULL); + of_scan_flat_dt(early_init_dt_scan_cpus, &boot_cpu_hwid); if (boot_cpuid < 0) { printk("Failed to identify boot CPU !\n"); BUG(); @@ -816,6 +816,11 @@ void __init early_init_devtree(void *params) mmu_early_init_devtree(); + // NB. paca is not installed until later in early_setup() + allocate_paca_ptrs(); + allocate_paca(boot_cpuid); + set_hard_smp_processor_id(boot_cpuid, boot_cpu_hwid); + #ifdef CONFIG_PPC_POWERNV /* Scan and build the list of machine check recoverable ranges */ of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL); diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index b8be1d6668b5..f15bc78caf71 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -841,7 +841,7 @@ static const struct user_regset_view user_ppc_compat_view = { const struct user_regset_view *task_user_regset_view(struct task_struct *task) { - if (IS_ENABLED(CONFIG_PPC64) && test_tsk_thread_flag(task, TIF_32BIT)) + if (IS_ENABLED(CONFIG_COMPAT) && is_tsk_32bit_task(task)) return &user_ppc_compat_view; return &user_ppc_native_view; } diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c index c43f77e2ac31..55742ef1f991 100644 --- a/arch/powerpc/kernel/ptrace/ptrace.c +++ b/arch/powerpc/kernel/ptrace/ptrace.c @@ -22,7 +22,6 @@ #include <linux/syscalls.h> #include <asm/switch_to.h> -#include <asm/asm-prototypes.h> #include <asm/debug.h> #define CREATE_TRACE_POINTS @@ -445,4 +444,10 @@ void __init pt_regs_check(void) * real registers. */ BUILD_BUG_ON(PT_DSCR < sizeof(struct user_pt_regs) / sizeof(unsigned long)); + +#ifdef PPC64_ELF_ABI_v1 + BUILD_BUG_ON(!IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS)); +#else + BUILD_BUG_ON(IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS)); +#endif } diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S index 02d4719bf43a..232e4549defe 100644 --- a/arch/powerpc/kernel/reloc_64.S +++ b/arch/powerpc/kernel/reloc_64.S @@ -8,8 +8,10 @@ #include <asm/ppc_asm.h> RELA = 7 -RELACOUNT = 0x6ffffff9 +RELASZ = 8 +RELAENT = 9 R_PPC64_RELATIVE = 22 +R_PPC64_UADDR64 = 43 /* * r3 = desired final address of kernel @@ -25,29 +27,38 @@ _GLOBAL(relocate) add r9,r9,r12 /* r9 has runtime addr of .rela.dyn section */ ld r10,(p_st - 0b)(r12) add r10,r10,r12 /* r10 has runtime addr of _stext */ + ld r13,(p_sym - 0b)(r12) + add r13,r13,r12 /* r13 has runtime addr of .dynsym */ /* - * Scan the dynamic section for the RELA and RELACOUNT entries. + * Scan the dynamic section for the RELA, RELASZ and RELAENT entries. */ li r7,0 li r8,0 -1: ld r6,0(r11) /* get tag */ +.Ltags: + ld r6,0(r11) /* get tag */ cmpdi r6,0 - beq 4f /* end of list */ + beq .Lend_of_list /* end of list */ cmpdi r6,RELA bne 2f ld r7,8(r11) /* get RELA pointer in r7 */ - b 3f -2: addis r6,r6,(-RELACOUNT)@ha - cmpdi r6,RELACOUNT@l + b 4f +2: cmpdi r6,RELASZ bne 3f - ld r8,8(r11) /* get RELACOUNT value in r8 */ -3: addi r11,r11,16 - b 1b -4: cmpdi r7,0 /* check we have both RELA and RELACOUNT */ + ld r8,8(r11) /* get RELASZ value in r8 */ + b 4f +3: cmpdi r6,RELAENT + bne 4f + ld r12,8(r11) /* get RELAENT value in r12 */ +4: addi r11,r11,16 + b .Ltags +.Lend_of_list: + cmpdi r7,0 /* check we have RELA, RELASZ, RELAENT */ cmpdi cr1,r8,0 - beq 6f - beq cr1,6f + beq .Lout + beq cr1,.Lout + cmpdi r12,0 + beq .Lout /* * Work out linktime address of _stext and hence the @@ -62,23 +73,39 @@ _GLOBAL(relocate) /* * Run through the list of relocations and process the - * R_PPC64_RELATIVE ones. + * R_PPC64_RELATIVE and R_PPC64_UADDR64 ones. */ + divd r8,r8,r12 /* RELASZ / RELAENT */ mtctr r8 -5: ld r0,8(9) /* ELF64_R_TYPE(reloc->r_info) */ +.Lrels: ld r0,8(r9) /* ELF64_R_TYPE(reloc->r_info) */ cmpdi r0,R_PPC64_RELATIVE - bne 6f + bne .Luaddr64 ld r6,0(r9) /* reloc->r_offset */ ld r0,16(r9) /* reloc->r_addend */ + b .Lstore +.Luaddr64: + srdi r14,r0,32 /* ELF64_R_SYM(reloc->r_info) */ + clrldi r0,r0,32 + cmpdi r0,R_PPC64_UADDR64 + bne .Lnext + ld r6,0(r9) + ld r0,16(r9) + mulli r14,r14,24 /* 24 == sizeof(elf64_sym) */ + add r14,r14,r13 /* elf64_sym[ELF64_R_SYM] */ + ld r14,8(r14) + add r0,r0,r14 +.Lstore: add r0,r0,r3 stdx r0,r7,r6 - addi r9,r9,24 - bdnz 5b - -6: blr +.Lnext: + add r9,r9,r12 + bdnz .Lrels +.Lout: + blr .balign 8 p_dyn: .8byte __dynamic_start - 0b p_rela: .8byte __rela_dyn_start - 0b +p_sym: .8byte __dynamic_symtab - 0b p_st: .8byte _stext - 0b diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 733e6ef36758..1f42aabbbab3 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -1313,6 +1313,12 @@ int __init early_init_dt_scan_rtas(unsigned long node, entryp = of_get_flat_dt_prop(node, "linux,rtas-entry", NULL); sizep = of_get_flat_dt_prop(node, "rtas-size", NULL); +#ifdef CONFIG_PPC64 + /* need this feature to decide the crashkernel offset */ + if (of_get_flat_dt_prop(node, "ibm,hypertas-functions", NULL)) + powerpc_firmware_features |= FW_FEATURE_LPAR; +#endif + if (basep && entryp && sizep) { rtas.base = *basep; rtas.entry = *entryp; diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index e159d4093d98..d96fd14bd7c9 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -747,14 +747,29 @@ static int count_cache_flush_get(void *data, u64 *val) return 0; } +static int link_stack_flush_get(void *data, u64 *val) +{ + if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) + *val = 0; + else + *val = 1; + + return 0; +} + DEFINE_DEBUGFS_ATTRIBUTE(fops_count_cache_flush, count_cache_flush_get, count_cache_flush_set, "%llu\n"); +DEFINE_DEBUGFS_ATTRIBUTE(fops_link_stack_flush, link_stack_flush_get, + count_cache_flush_set, "%llu\n"); static __init int count_cache_flush_debugfs_init(void) { debugfs_create_file_unsafe("count_cache_flush", 0600, arch_debugfs_dir, NULL, &fops_count_cache_flush); + debugfs_create_file_unsafe("link_stack_flush", 0600, + arch_debugfs_dir, NULL, + &fops_link_stack_flush); return 0; } device_initcall(count_cache_flush_debugfs_init); diff --git a/arch/powerpc/kernel/secvar-sysfs.c b/arch/powerpc/kernel/secvar-sysfs.c index a0a78aba2083..1ee4640a2641 100644 --- a/arch/powerpc/kernel/secvar-sysfs.c +++ b/arch/powerpc/kernel/secvar-sysfs.c @@ -26,15 +26,18 @@ static ssize_t format_show(struct kobject *kobj, struct kobj_attribute *attr, const char *format; node = of_find_compatible_node(NULL, NULL, "ibm,secvar-backend"); - if (!of_device_is_available(node)) - return -ENODEV; + if (!of_device_is_available(node)) { + rc = -ENODEV; + goto out; + } rc = of_property_read_string(node, "format", &format); if (rc) - return rc; + goto out; rc = sprintf(buf, "%s\n", format); +out: of_node_put(node); return rc; diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index f8da937df918..518ae5aa9410 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -456,8 +456,8 @@ void __init smp_setup_cpu_maps(void) intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", &len); if (intserv) { - DBG(" ibm,ppc-interrupt-server#s -> %d threads\n", - nthreads); + DBG(" ibm,ppc-interrupt-server#s -> %lu threads\n", + (len / sizeof(int))); } else { DBG(" no ibm,ppc-interrupt-server#s -> 1 thread\n"); intserv = of_get_property(dn, "reg", &len); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index be8577ac9397..e547066a06aa 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -67,7 +67,6 @@ #include <asm/kup.h> #include <asm/early_ioremap.h> #include <asm/pgalloc.h> -#include <asm/asm-prototypes.h> #include "setup.h" diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index d1e1fc0acbea..73d483b07ff3 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -936,11 +936,11 @@ int handle_rt_signal64(struct ksignal *ksig, sigset_t *set, * descriptor is the entry address of signal and the second * entry is the TOC value we need to use. */ - func_descr_t __user *funct_desc_ptr = - (func_descr_t __user *) ksig->ka.sa.sa_handler; + struct func_desc __user *ptr = + (struct func_desc __user *)ksig->ka.sa.sa_handler; - err |= get_user(regs->ctr, &funct_desc_ptr->entry); - err |= get_user(regs->gpr[2], &funct_desc_ptr->toc); + err |= get_user(regs->ctr, &ptr->addr); + err |= get_user(regs->gpr[2], &ptr->toc); } /* enter the signal handler in native-endian mode */ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index b7fd6a72aa76..de0f6f09a5dd 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -57,7 +57,6 @@ #include <asm/vdso.h> #include <asm/debug.h> #include <asm/kexec.h> -#include <asm/asm-prototypes.h> #include <asm/cpu_has_feature.h> #include <asm/ftrace.h> #include <asm/kup.h> @@ -716,7 +715,7 @@ void smp_send_stop(void) } #endif /* CONFIG_NMI_IPI */ -struct task_struct *current_set[NR_CPUS]; +static struct task_struct *current_set[NR_CPUS]; static void smp_store_cpu_info(int id) { diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index 825931e400df..c4f5b4ce926f 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -35,7 +35,6 @@ #include <asm/syscalls.h> #include <asm/time.h> #include <asm/unistd.h> -#include <asm/asm-prototypes.h> static inline long do_mmap2(unsigned long addr, size_t len, unsigned long prot, unsigned long flags, diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index 8e83d19fe8fa..828d0f4106d2 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -29,7 +29,6 @@ #include <asm/cache.h> #include <asm/8xx_immap.h> #include <asm/machdep.h> -#include <asm/asm-prototypes.h> #include "setup.h" diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index cd0b8b71ecdd..f5cbfe5efd25 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -69,7 +69,7 @@ #include <asm/smp.h> #include <asm/vdso_datapage.h> #include <asm/firmware.h> -#include <asm/asm-prototypes.h> +#include <asm/mce.h> /* powerpc clocksource/clockevent code */ @@ -107,7 +107,12 @@ struct clock_event_device decrementer_clockevent = { }; EXPORT_SYMBOL(decrementer_clockevent); -DEFINE_PER_CPU(u64, decrementers_next_tb); +/* + * This always puts next_tb beyond now, so the clock event will never fire + * with the usual comparison, no need for a separate test for stopped. + */ +#define DEC_CLOCKEVENT_STOPPED ~0ULL +DEFINE_PER_CPU(u64, decrementers_next_tb) = DEC_CLOCKEVENT_STOPPED; EXPORT_SYMBOL_GPL(decrementers_next_tb); static DEFINE_PER_CPU(struct clock_event_device, decrementers); @@ -582,8 +587,9 @@ void timer_rearm_host_dec(u64 now) local_paca->irq_happened |= PACA_IRQ_DEC; } else { now = *next_tb - now; - if (now <= decrementer_max) - set_dec_or_work(now); + if (now > decrementer_max) + now = decrementer_max; + set_dec_or_work(now); } } EXPORT_SYMBOL_GPL(timer_rearm_host_dec); @@ -638,14 +644,13 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) if (test_irq_work_pending()) { clear_irq_work_pending(); + mce_run_irq_context_handlers(); irq_work_run(); } now = get_tb(); if (now >= *next_tb) { - *next_tb = ~(u64)0; - if (evt->event_handler) - evt->event_handler(evt); + evt->event_handler(evt); __this_cpu_inc(irq_stat.timer_irqs_event); } else { now = *next_tb - now; @@ -664,9 +669,6 @@ EXPORT_SYMBOL(timer_interrupt); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST void timer_broadcast_interrupt(void) { - u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); - - *next_tb = ~(u64)0; tick_receive_broadcast(); __this_cpu_inc(irq_stat.broadcast_irqs_event); } @@ -892,7 +894,9 @@ static int decrementer_set_next_event(unsigned long evt, static int decrementer_shutdown(struct clock_event_device *dev) { - decrementer_set_next_event(decrementer_max, dev); + __this_cpu_write(decrementers_next_tb, DEC_CLOCKEVENT_STOPPED); + set_dec_or_work(decrementer_max); + return 0; } diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 3beecc32940b..5a0f023a26e9 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -443,7 +443,8 @@ restore_gprs: REST_GPR(0, r7) /* GPR0 */ REST_GPRS(2, 4, r7) /* GPR2-4 */ - REST_GPRS(8, 31, r7) /* GPR8-31 */ + REST_GPRS(8, 12, r7) /* GPR8-12 */ + REST_GPRS(14, 31, r7) /* GPR14-31 */ /* Load up PPR and DSCR here so we don't run with user values for long */ mtspr SPRN_DSCR, r5 @@ -479,18 +480,24 @@ restore_gprs: REST_GPR(6, r7) /* - * Store r1 and r5 on the stack so that we can access them after we - * clear MSR RI. + * Store user r1 and r5 and r13 on the stack (in the unused save + * areas / compiler reserved areas), so that we can access them after + * we clear MSR RI. */ REST_GPR(5, r7) std r5, -8(r1) - ld r5, GPR1(r7) + ld r5, GPR13(r7) std r5, -16(r1) + ld r5, GPR1(r7) + std r5, -24(r1) REST_GPR(7, r7) - /* Clear MSR RI since we are about to use SCRATCH0. EE is already off */ + /* Stash the stack pointer away for use after recheckpoint */ + std r1, PACAR1(r13) + + /* Clear MSR RI since we are about to clobber r13. EE is already off */ li r5, 0 mtmsrd r5, 1 @@ -501,9 +508,9 @@ restore_gprs: * until we turn MSR RI back on. */ - SET_SCRATCH0(r1) ld r5, -8(r1) - ld r1, -16(r1) + ld r13, -16(r1) + ld r1, -24(r1) /* Commit register state as checkpointed state: */ TRECHKPT @@ -519,9 +526,9 @@ restore_gprs: */ GET_PACA(r13) - GET_SCRATCH0(r1) + ld r1, PACAR1(r13) - /* R1 is restored, so we are recoverable again. EE is still off */ + /* R13, R1 is restored, so we are recoverable again. EE is still off */ li r4, MSR_RI mtmsrd r4, 1 diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile index 858503775c58..542aa7a8b2b4 100644 --- a/arch/powerpc/kernel/trace/Makefile +++ b/arch/powerpc/kernel/trace/Makefile @@ -8,13 +8,13 @@ ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) endif -obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_32.o -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64.o +obj32-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o ifdef CONFIG_MPROFILE_KERNEL -obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_mprofile.o +obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_mprofile.o else obj64-$(CONFIG_FUNCTION_TRACER) += ftrace_64_pg.o endif +obj-$(CONFIG_FUNCTION_TRACER) += ftrace_low.o obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 80b6285769f2..4ee04aacf9f1 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -22,7 +22,6 @@ #include <linux/init.h> #include <linux/list.h> -#include <asm/asm-prototypes.h> #include <asm/cacheflush.h> #include <asm/code-patching.h> #include <asm/ftrace.h> @@ -910,30 +909,30 @@ int __init ftrace_dyn_arch_init(void) extern void ftrace_graph_call(void); extern void ftrace_graph_stub(void); -int ftrace_enable_ftrace_graph_caller(void) +static int ftrace_modify_ftrace_graph_caller(bool enable) { unsigned long ip = (unsigned long)(&ftrace_graph_call); unsigned long addr = (unsigned long)(&ftrace_graph_caller); unsigned long stub = (unsigned long)(&ftrace_graph_stub); ppc_inst_t old, new; - old = ftrace_call_replace(ip, stub, 0); - new = ftrace_call_replace(ip, addr, 0); + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) + return 0; + + old = ftrace_call_replace(ip, enable ? stub : addr, 0); + new = ftrace_call_replace(ip, enable ? addr : stub, 0); return ftrace_modify_code(ip, old, new); } -int ftrace_disable_ftrace_graph_caller(void) +int ftrace_enable_ftrace_graph_caller(void) { - unsigned long ip = (unsigned long)(&ftrace_graph_call); - unsigned long addr = (unsigned long)(&ftrace_graph_caller); - unsigned long stub = (unsigned long)(&ftrace_graph_stub); - ppc_inst_t old, new; - - old = ftrace_call_replace(ip, addr, 0); - new = ftrace_call_replace(ip, stub, 0); + return ftrace_modify_ftrace_graph_caller(true); +} - return ftrace_modify_code(ip, old, new); +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_ftrace_graph_caller(false); } /* @@ -944,6 +943,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { unsigned long return_hooker; + int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -951,13 +951,27 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; + bit = ftrace_test_recursion_trylock(ip, parent); + if (bit < 0) + goto out; + return_hooker = ppc_function_entry(return_to_handler); if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) parent = return_hooker; + + ftrace_test_recursion_unlock(bit); out: return parent; } + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + fregs->regs.link = prepare_ftrace_return(parent_ip, ip, fregs->regs.gpr[1]); +} +#endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ #ifdef PPC64_ELF_ABI_v1 diff --git a/arch/powerpc/kernel/trace/ftrace_32.S b/arch/powerpc/kernel/trace/ftrace_32.S deleted file mode 100644 index 0a02c0cb12d9..000000000000 --- a/arch/powerpc/kernel/trace/ftrace_32.S +++ /dev/null @@ -1,187 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Split from entry_32.S - */ - -#include <linux/magic.h> -#include <asm/reg.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/ftrace.h> -#include <asm/export.h> -#include <asm/ptrace.h> - -_GLOBAL(mcount) -_GLOBAL(_mcount) - /* - * It is required that _mcount on PPC32 must preserve the - * link register. But we have r12 to play with. We use r12 - * to push the return address back to the caller of mcount - * into the ctr register, restore the link register and - * then jump back using the ctr register. - */ - mflr r12 - mtctr r12 - mtlr r0 - bctr -EXPORT_SYMBOL(_mcount) - -_GLOBAL(ftrace_caller) - MCOUNT_SAVE_FRAME - /* r3 ends up with link register */ - subi r3, r3, MCOUNT_INSN_SIZE - lis r5,function_trace_op@ha - lwz r5,function_trace_op@l(r5) - li r6, 0 -.globl ftrace_call -ftrace_call: - bl ftrace_stub - nop - MCOUNT_RESTORE_FRAME -ftrace_caller_common: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - b ftrace_graph_stub -_GLOBAL(ftrace_graph_stub) -#endif - /* old link register ends up in ctr reg */ - bctr - - -_GLOBAL(ftrace_stub) - blr - -_GLOBAL(ftrace_regs_caller) - /* Save the original return address in A's stack frame */ - stw r0,LRSAVE(r1) - - /* Create our stack frame + pt_regs */ - stwu r1,-INT_FRAME_SIZE(r1) - - /* Save all gprs to pt_regs */ - stw r0, GPR0(r1) - stmw r2, GPR2(r1) - - /* Save previous stack pointer (r1) */ - addi r8, r1, INT_FRAME_SIZE - stw r8, GPR1(r1) - - /* Load special regs for save below */ - mfmsr r8 - mfctr r9 - mfxer r10 - mfcr r11 - - /* Get the _mcount() call site out of LR */ - mflr r7 - /* Save it as pt_regs->nip */ - stw r7, _NIP(r1) - /* Save the read LR in pt_regs->link */ - stw r0, _LINK(r1) - - lis r3,function_trace_op@ha - lwz r5,function_trace_op@l(r3) - - /* Calculate ip from nip-4 into r3 for call below */ - subi r3, r7, MCOUNT_INSN_SIZE - - /* Put the original return address in r4 as parent_ip */ - mr r4, r0 - - /* Save special regs */ - stw r8, _MSR(r1) - stw r9, _CTR(r1) - stw r10, _XER(r1) - stw r11, _CCR(r1) - - /* Load &pt_regs in r6 for call below */ - addi r6, r1, STACK_FRAME_OVERHEAD - - /* ftrace_call(r3, r4, r5, r6) */ -.globl ftrace_regs_call -ftrace_regs_call: - bl ftrace_stub - nop - - /* Load ctr with the possibly modified NIP */ - lwz r3, _NIP(r1) - mtctr r3 - - /* Restore gprs */ - lmw r2, GPR2(r1) - - /* Restore possibly modified LR */ - lwz r0, _LINK(r1) - mtlr r0 - - /* Pop our stack frame */ - addi r1, r1, INT_FRAME_SIZE - - b ftrace_caller_common - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -_GLOBAL(ftrace_graph_caller) - stwu r1,-48(r1) - stw r3, 12(r1) - stw r4, 16(r1) - stw r5, 20(r1) - stw r6, 24(r1) - stw r7, 28(r1) - stw r8, 32(r1) - stw r9, 36(r1) - stw r10,40(r1) - - addi r5, r1, 48 - mfctr r4 /* ftrace_caller has moved local addr here */ - stw r4, 44(r1) - mflr r3 /* ftrace_caller has restored LR from stack */ - subi r4, r4, MCOUNT_INSN_SIZE - - bl prepare_ftrace_return - nop - - /* - * prepare_ftrace_return gives us the address we divert to. - * Change the LR in the callers stack frame to this. - */ - stw r3,52(r1) - mtlr r3 - lwz r0,44(r1) - mtctr r0 - - lwz r3, 12(r1) - lwz r4, 16(r1) - lwz r5, 20(r1) - lwz r6, 24(r1) - lwz r7, 28(r1) - lwz r8, 32(r1) - lwz r9, 36(r1) - lwz r10,40(r1) - - addi r1, r1, 48 - - bctr - -_GLOBAL(return_to_handler) - /* need to save return values */ - stwu r1, -32(r1) - stw r3, 20(r1) - stw r4, 16(r1) - stw r31, 12(r1) - mr r31, r1 - - bl ftrace_return_to_handler - nop - - /* return value has real return address */ - mtlr r3 - - lwz r3, 20(r1) - lwz r4, 16(r1) - lwz r31,12(r1) - lwz r1, 0(r1) - - /* Jump back to real return address */ - blr -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/trace/ftrace_64.S b/arch/powerpc/kernel/trace/ftrace_low.S index 25e5b9e47c06..0bddf1fa6636 100644 --- a/arch/powerpc/kernel/trace/ftrace_64.S +++ b/arch/powerpc/kernel/trace/ftrace_low.S @@ -10,6 +10,7 @@ #include <asm/ppc-opcode.h> #include <asm/export.h> +#ifdef CONFIG_PPC64 .pushsection ".tramp.ftrace.text","aw",@progbits; .globl ftrace_tramp_text ftrace_tramp_text: @@ -21,6 +22,7 @@ ftrace_tramp_text: ftrace_tramp_init: .space 64 .popsection +#endif _GLOBAL(mcount) _GLOBAL(_mcount) @@ -33,6 +35,7 @@ EXPORT_SYMBOL(_mcount) #ifdef CONFIG_FUNCTION_GRAPH_TRACER _GLOBAL(return_to_handler) /* need to save return values */ +#ifdef CONFIG_PPC64 std r4, -32(r1) std r3, -24(r1) /* save TOC */ @@ -46,6 +49,11 @@ _GLOBAL(return_to_handler) * Switch to our TOC to run inside the core kernel. */ ld r2, PACATOC(r13) +#else + stwu r1, -16(r1) + stw r3, 8(r1) + stw r4, 12(r1) +#endif bl ftrace_return_to_handler nop @@ -53,11 +61,17 @@ _GLOBAL(return_to_handler) /* return value has real return address */ mtlr r3 +#ifdef CONFIG_PPC64 ld r1, 0(r1) ld r4, -32(r1) ld r3, -24(r1) ld r2, -16(r1) ld r31, -8(r1) +#else + lwz r3, 8(r1) + lwz r4, 12(r1) + addi r1, r1, 16 +#endif /* Jump back to real return address */ blr diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_mprofile.S index d636fc755f60..4fa23e260cab 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S +++ b/arch/powerpc/kernel/trace/ftrace_mprofile.S @@ -32,52 +32,71 @@ * Our job is to save the register state into a struct pt_regs (on the stack) * and then arrange for the ftrace function to be called. */ -_GLOBAL(ftrace_regs_caller) - /* Save the original return address in A's stack frame */ - std r0,LRSAVE(r1) - +.macro ftrace_regs_entry allregs /* Create our stack frame + pt_regs */ - stdu r1,-SWITCH_FRAME_SIZE(r1) + PPC_STLU r1,-SWITCH_FRAME_SIZE(r1) /* Save all gprs to pt_regs */ SAVE_GPR(0, r1) - SAVE_GPRS(2, 11, r1) + SAVE_GPRS(3, 10, r1) +#ifdef CONFIG_PPC64 + /* Save the original return address in A's stack frame */ + std r0, LRSAVE+SWITCH_FRAME_SIZE(r1) /* Ok to continue? */ lbz r3, PACA_FTRACE_ENABLED(r13) cmpdi r3, 0 beq ftrace_no_trace +#endif - SAVE_GPRS(12, 31, r1) + .if \allregs == 1 + SAVE_GPR(2, r1) + SAVE_GPRS(11, 31, r1) + .else +#ifdef CONFIG_LIVEPATCH_64 + SAVE_GPR(14, r1) +#endif + .endif /* Save previous stack pointer (r1) */ addi r8, r1, SWITCH_FRAME_SIZE - std r8, GPR1(r1) + PPC_STL r8, GPR1(r1) + .if \allregs == 1 /* Load special regs for save below */ mfmsr r8 mfctr r9 mfxer r10 mfcr r11 + .else + /* Clear MSR to flag as ftrace_caller versus frace_regs_caller */ + li r8, 0 + .endif /* Get the _mcount() call site out of LR */ mflr r7 /* Save it as pt_regs->nip */ - std r7, _NIP(r1) + PPC_STL r7, _NIP(r1) /* Save the read LR in pt_regs->link */ - std r0, _LINK(r1) + PPC_STL r0, _LINK(r1) +#ifdef CONFIG_PPC64 /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) + std r2, STK_GOT(r1) ld r2,PACATOC(r13) /* get kernel TOC in r2 */ addis r3,r2,function_trace_op@toc@ha addi r3,r3,function_trace_op@toc@l ld r5,0(r3) +#else + lis r3,function_trace_op@ha + lwz r5,function_trace_op@l(r3) +#endif -#ifdef CONFIG_LIVEPATCH - mr r14,r7 /* remember old NIP */ +#ifdef CONFIG_LIVEPATCH_64 + mr r14, r7 /* remember old NIP */ #endif + /* Calculate ip from nip-4 into r3 for call below */ subi r3, r7, MCOUNT_INSN_SIZE @@ -85,128 +104,87 @@ _GLOBAL(ftrace_regs_caller) mr r4, r0 /* Save special regs */ - std r8, _MSR(r1) - std r9, _CTR(r1) - std r10, _XER(r1) - std r11, _CCR(r1) + PPC_STL r8, _MSR(r1) + .if \allregs == 1 + PPC_STL r9, _CTR(r1) + PPC_STL r10, _XER(r1) + PPC_STL r11, _CCR(r1) + .endif /* Load &pt_regs in r6 for call below */ - addi r6, r1 ,STACK_FRAME_OVERHEAD - - /* ftrace_call(r3, r4, r5, r6) */ -.globl ftrace_regs_call -ftrace_regs_call: - bl ftrace_stub - nop + addi r6, r1, STACK_FRAME_OVERHEAD +.endm +.macro ftrace_regs_exit allregs /* Load ctr with the possibly modified NIP */ - ld r3, _NIP(r1) + PPC_LL r3, _NIP(r1) mtctr r3 -#ifdef CONFIG_LIVEPATCH + +#ifdef CONFIG_LIVEPATCH_64 cmpd r14, r3 /* has NIP been altered? */ #endif /* Restore gprs */ - REST_GPR(0, r1) + .if \allregs == 1 REST_GPRS(2, 31, r1) + .else + REST_GPRS(3, 10, r1) +#ifdef CONFIG_LIVEPATCH_64 + REST_GPR(14, r1) +#endif + .endif /* Restore possibly modified LR */ - ld r0, _LINK(r1) + PPC_LL r0, _LINK(r1) mtlr r0 +#ifdef CONFIG_PPC64 /* Restore callee's TOC */ - ld r2, 24(r1) + ld r2, STK_GOT(r1) +#endif /* Pop our stack frame */ addi r1, r1, SWITCH_FRAME_SIZE -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 /* Based on the cmpd above, if the NIP was altered handle livepatch */ bne- livepatch_handler #endif - -ftrace_caller_common: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -.globl ftrace_graph_call -ftrace_graph_call: - b ftrace_graph_stub -_GLOBAL(ftrace_graph_stub) -#endif - bctr /* jump after _mcount site */ +.endm -_GLOBAL(ftrace_stub) - blr - -ftrace_no_trace: - mflr r3 - mtctr r3 - REST_GPR(3, r1) - addi r1, r1, SWITCH_FRAME_SIZE - mtlr r0 - bctr +_GLOBAL(ftrace_regs_caller) + ftrace_regs_entry 1 + /* ftrace_call(r3, r4, r5, r6) */ +.globl ftrace_regs_call +ftrace_regs_call: + bl ftrace_stub + nop + ftrace_regs_exit 1 _GLOBAL(ftrace_caller) - /* Save the original return address in A's stack frame */ - std r0, LRSAVE(r1) - - /* Create our stack frame + pt_regs */ - stdu r1, -SWITCH_FRAME_SIZE(r1) - - /* Save all gprs to pt_regs */ - SAVE_GPRS(3, 10, r1) - - lbz r3, PACA_FTRACE_ENABLED(r13) - cmpdi r3, 0 - beq ftrace_no_trace - - /* Get the _mcount() call site out of LR */ - mflr r7 - std r7, _NIP(r1) - - /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) - ld r2, PACATOC(r13) /* get kernel TOC in r2 */ - - addis r3, r2, function_trace_op@toc@ha - addi r3, r3, function_trace_op@toc@l - ld r5, 0(r3) - - /* Calculate ip from nip-4 into r3 for call below */ - subi r3, r7, MCOUNT_INSN_SIZE - - /* Put the original return address in r4 as parent_ip */ - mr r4, r0 - - /* Set pt_regs to NULL */ - li r6, 0 - + ftrace_regs_entry 0 /* ftrace_call(r3, r4, r5, r6) */ .globl ftrace_call ftrace_call: bl ftrace_stub nop + ftrace_regs_exit 0 - ld r3, _NIP(r1) - mtctr r3 - - /* Restore gprs */ - REST_GPRS(3, 10, r1) - - /* Restore callee's TOC */ - ld r2, 24(r1) +_GLOBAL(ftrace_stub) + blr - /* Pop our stack frame */ +#ifdef CONFIG_PPC64 +ftrace_no_trace: + mflr r3 + mtctr r3 + REST_GPR(3, r1) addi r1, r1, SWITCH_FRAME_SIZE - - /* Reload original LR */ - ld r0, LRSAVE(r1) mtlr r0 + bctr +#endif - /* Handle function_graph or go back */ - b ftrace_caller_common - -#ifdef CONFIG_LIVEPATCH +#ifdef CONFIG_LIVEPATCH_64 /* * This function runs in the mcount context, between two functions. As * such it can only clobber registers which are volatile and used in @@ -273,55 +251,3 @@ livepatch_handler: /* Return to original caller of live patched function */ blr #endif /* CONFIG_LIVEPATCH */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -_GLOBAL(ftrace_graph_caller) - stdu r1, -112(r1) - /* with -mprofile-kernel, parameter regs are still alive at _mcount */ - std r10, 104(r1) - std r9, 96(r1) - std r8, 88(r1) - std r7, 80(r1) - std r6, 72(r1) - std r5, 64(r1) - std r4, 56(r1) - std r3, 48(r1) - - /* Save callee's TOC in the ABI compliant location */ - std r2, 24(r1) - ld r2, PACATOC(r13) /* get kernel TOC in r2 */ - - addi r5, r1, 112 - mfctr r4 /* ftrace_caller has moved local addr here */ - std r4, 40(r1) - mflr r3 /* ftrace_caller has restored LR from stack */ - subi r4, r4, MCOUNT_INSN_SIZE - - bl prepare_ftrace_return - nop - - /* - * prepare_ftrace_return gives us the address we divert to. - * Change the LR to this. - */ - mtlr r3 - - ld r0, 40(r1) - mtctr r0 - ld r10, 104(r1) - ld r9, 96(r1) - ld r8, 88(r1) - ld r7, 80(r1) - ld r6, 72(r1) - ld r5, 64(r1) - ld r4, 56(r1) - ld r3, 48(r1) - - /* Restore callee's TOC */ - ld r2, 24(r1) - - addi r1, r1, 112 - mflr r0 - std r0, LRSAVE(r1) - bctr -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/vdso64/.gitignore b/arch/powerpc/kernel/vdso/.gitignore index 84151a7ba31d..dd9bdd67758b 100644 --- a/arch/powerpc/kernel/vdso64/.gitignore +++ b/arch/powerpc/kernel/vdso/.gitignore @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only +vdso32.lds +vdso32.so.dbg vdso64.lds vdso64.so.dbg diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile new file mode 100644 index 000000000000..954974287ee7 --- /dev/null +++ b/arch/powerpc/kernel/vdso/Makefile @@ -0,0 +1,103 @@ +# SPDX-License-Identifier: GPL-2.0 + +# List of files in the vdso, has to be asm only for now + +ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 +include $(srctree)/lib/vdso/Makefile + +obj-vdso32 = sigtramp32-32.o gettimeofday-32.o datapage-32.o cacheflush-32.o note-32.o getcpu-32.o +obj-vdso64 = sigtramp64-64.o gettimeofday-64.o datapage-64.o cacheflush-64.o note-64.o getcpu-64.o + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday-32.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday-32.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + CFLAGS_vgettimeofday-32.o += $(call cc-option, -fno-stack-protector) + CFLAGS_vgettimeofday-32.o += -DDISABLE_BRANCH_PROFILING + CFLAGS_vgettimeofday-32.o += -ffreestanding -fasynchronous-unwind-tables + CFLAGS_REMOVE_vgettimeofday-32.o = $(CC_FLAGS_FTRACE) + CFLAGS_REMOVE_vgettimeofday-32.o += -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc + CFLAGS_vgettimeofday-64.o += -include $(c-gettimeofday-y) + CFLAGS_vgettimeofday-64.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) + CFLAGS_vgettimeofday-64.o += $(call cc-option, -fno-stack-protector) + CFLAGS_vgettimeofday-64.o += -DDISABLE_BRANCH_PROFILING + CFLAGS_vgettimeofday-64.o += -ffreestanding -fasynchronous-unwind-tables + CFLAGS_REMOVE_vgettimeofday-64.o = $(CC_FLAGS_FTRACE) +# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true +# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is +# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code +# generation is minimal, it will just use r29 instead. + CFLAGS_vgettimeofday-64.o += $(call cc-option, -ffixed-r30) +endif + +# Build rules + +ifdef CROSS32_COMPILE + VDSOCC := $(CROSS32_COMPILE)gcc +else + VDSOCC := $(CC) +endif + +targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday-32.o +obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) +targets += $(obj-vdso64) vdso64.so.dbg vgettimeofday-64.o +obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) + +GCOV_PROFILE := n +KCOV_INSTRUMENT := n +UBSAN_SANITIZE := n +KASAN_SANITIZE := n + +ccflags-y := -shared -fno-common -fno-builtin -nostdlib -Wl,--hash-style=both + +CC32FLAGS := -Wl,-soname=linux-vdso32.so.1 -m32 +AS32FLAGS := -D__VDSO32__ -s + +CC64FLAGS := -Wl,-soname=linux-vdso64.so.1 +AS64FLAGS := -D__VDSO64__ -s + +targets += vdso32.lds +CPPFLAGS_vdso32.lds += -P -C -Upowerpc +targets += vdso64.lds +CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) + +# link rule for the .so file, .lds has to be first +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday-32.o FORCE + $(call if_changed,vdso32ld_and_check) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday-64.o FORCE + $(call if_changed,vdso64ld_and_check) + +# assembly rules for the .S files +$(obj-vdso32): %-32.o: %.S FORCE + $(call if_changed_dep,vdso32as) +$(obj)/vgettimeofday-32.o: %-32.o: %.c FORCE + $(call if_changed_dep,vdso32cc) +$(obj-vdso64): %-64.o: %.S FORCE + $(call if_changed_dep,vdso64as) +$(obj)/vgettimeofday-64.o: %-64.o: %.c FORCE + $(call if_changed_dep,cc_o_c) + +# Generate VDSO offsets using helper script +gen-vdso32sym := $(srctree)/$(src)/gen_vdso32_offsets.sh +quiet_cmd_vdso32sym = VDSO32SYM $@ + cmd_vdso32sym = $(NM) $< | $(gen-vdso32sym) | LC_ALL=C sort > $@ +gen-vdso64sym := $(srctree)/$(src)/gen_vdso64_offsets.sh +quiet_cmd_vdso64sym = VDSO64SYM $@ + cmd_vdso64sym = $(NM) $< | $(gen-vdso64sym) | LC_ALL=C sort > $@ + +include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE + $(call if_changed,vdso32sym) +include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE + $(call if_changed,vdso64sym) + +# actual build commands +quiet_cmd_vdso32ld_and_check = VDSO32L $@ + cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) +quiet_cmd_vdso32as = VDSO32A $@ + cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) $(AS32FLAGS) -c -o $@ $< +quiet_cmd_vdso32cc = VDSO32C $@ + cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< + +quiet_cmd_vdso64ld_and_check = VDSO64L $@ + cmd_vdso64ld_and_check = $(VDSOCC) $(c_flags) $(CC64FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) +quiet_cmd_vdso64as = VDSO64A $@ + cmd_vdso64as = $(VDSOCC) $(a_flags) $(CC64FLAGS) $(AS64FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index f340e82d1981..d4e43ab2d5df 100644 --- a/arch/powerpc/kernel/vdso32/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -46,7 +46,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) add r8,r8,r5 /* ensure we get enough */ #ifdef CONFIG_PPC64 lwz r9,CFG_DCACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + PPC_SRL. r8,r8,r9 /* compute line count */ #else srwi. r8, r8, L1_CACHE_SHIFT mr r7, r6 @@ -72,7 +72,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) subf r8,r6,r4 /* compute length */ add r8,r8,r5 lwz r9,CFG_ICACHE_LOGBLOCKSZ(r10) - srw. r8,r8,r9 /* compute line count */ + PPC_SRL. r8,r8,r9 /* compute line count */ crclr cr0*4+so beqlr /* nothing to do? */ #endif diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index 65244416ab94..db8e167f0166 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -30,11 +30,15 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mr. r4,r3 get_datapage r3 mtlr r12 +#ifdef __powerpc64__ + addi r3,r3,CFG_SYSCALL_MAP64 +#else addi r3,r3,CFG_SYSCALL_MAP32 +#endif + crclr cr0*4+so beqlr li r0,NR_syscalls stw r0,0(r4) - crclr cr0*4+so blr .cfi_endproc V_FUNCTION_END(__kernel_get_syscall_map) @@ -49,8 +53,10 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) mflr r12 .cfi_register lr,r12 get_datapage r3 +#ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) - lwz r3,CFG_TB_TICKS_PER_SEC(r3) +#endif + PPC_LL r3,CFG_TB_TICKS_PER_SEC(r3) mtlr r12 crclr cr0*4+so blr diff --git a/arch/powerpc/kernel/vdso32/gen_vdso_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh index c7b54a5dcd3e..c7b54a5dcd3e 100755 --- a/arch/powerpc/kernel/vdso32/gen_vdso_offsets.sh +++ b/arch/powerpc/kernel/vdso/gen_vdso32_offsets.sh diff --git a/arch/powerpc/kernel/vdso64/gen_vdso_offsets.sh b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh index 4bf15ffd5933..4bf15ffd5933 100755 --- a/arch/powerpc/kernel/vdso64/gen_vdso_offsets.sh +++ b/arch/powerpc/kernel/vdso/gen_vdso64_offsets.sh diff --git a/arch/powerpc/kernel/vdso32/getcpu.S b/arch/powerpc/kernel/vdso/getcpu.S index ff5e214fec41..8e08ccf19062 100644 --- a/arch/powerpc/kernel/vdso32/getcpu.S +++ b/arch/powerpc/kernel/vdso/getcpu.S @@ -19,8 +19,8 @@ V_FUNCTION_BEGIN(__kernel_getcpu) .cfi_startproc mfspr r5,SPRN_SPRG_VDSO_READ - cmpwi cr0,r3,0 - cmpwi cr1,r4,0 + PPC_LCMPI cr0,r3,0 + PPC_LCMPI cr1,r4,0 clrlwi r6,r5,16 rlwinm r7,r5,16,31-15,31-0 beq cr0,1f diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S index d21d08140a5e..eb9c81e1c218 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso/gettimeofday.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* - * Userland implementation of gettimeofday() for 32 bits processes in a - * ppc64 kernel for use in the vDSO + * Userland implementation of gettimeofday() for processes + * for use in the vDSO * * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org, * IBM Corp. @@ -12,7 +12,49 @@ #include <asm/vdso_datapage.h> #include <asm/asm-offsets.h> #include <asm/unistd.h> -#include <asm/vdso/gettimeofday.h> + +/* + * The macro sets two stack frames, one for the caller and one for the callee + * because there are no requirement for the caller to set a stack frame when + * calling VDSO so it may have omitted to set one, especially on PPC64 + */ + +.macro cvdso_call funct call_time=0 + .cfi_startproc + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + mflr r0 + .cfi_register lr, r0 + PPC_STLU r1, -PPC_MIN_STKFRM(r1) + PPC_STL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) +#ifdef __powerpc64__ + PPC_STL r2, PPC_MIN_STKFRM + STK_GOT(r1) +#endif + get_datapage r5 + .ifeq \call_time + addi r5, r5, VDSO_DATA_OFFSET + .else + addi r4, r5, VDSO_DATA_OFFSET + .endif + bl DOTSYM(\funct) + PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1) +#ifdef __powerpc64__ + PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1) +#endif + .ifeq \call_time + cmpwi r3, 0 + .endif + mtlr r0 + .cfi_restore lr + addi r1, r1, 2 * PPC_MIN_STKFRM + crclr so + .ifeq \call_time + beqlr+ + crset so + neg r3, r3 + .endif + blr + .cfi_endproc +.endm .text /* @@ -41,9 +83,11 @@ V_FUNCTION_END(__kernel_clock_gettime) * int __kernel_clock_gettime64(clockid_t clock_id, struct __timespec64 *ts); * */ +#ifndef __powerpc64__ V_FUNCTION_BEGIN(__kernel_clock_gettime64) cvdso_call __c_kernel_clock_gettime64 V_FUNCTION_END(__kernel_clock_gettime64) +#endif /* * Exact prototype of clock_getres() @@ -63,12 +107,13 @@ V_FUNCTION_END(__kernel_clock_getres) * */ V_FUNCTION_BEGIN(__kernel_time) - cvdso_call_time __c_kernel_time + cvdso_call __c_kernel_time call_time=1 V_FUNCTION_END(__kernel_time) /* Routines for restoring integer registers, called by the compiler. */ /* Called with r11 pointing to the stack header word of the caller of the */ /* function, just beyond the end of the integer restore area. */ +#ifndef __powerpc64__ _GLOBAL(_restgpr_31_x) _GLOBAL(_rest32gpr_31_x) lwz r0,4(r11) @@ -76,3 +121,4 @@ _GLOBAL(_rest32gpr_31_x) mtlr r0 mr r1,r11 blr +#endif diff --git a/arch/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso/note.S index 227a7327399e..227a7327399e 100644 --- a/arch/powerpc/kernel/vdso32/note.S +++ b/arch/powerpc/kernel/vdso/note.S diff --git a/arch/powerpc/kernel/vdso32/sigtramp.S b/arch/powerpc/kernel/vdso/sigtramp32.S index 0bcc5e5fe789..0bcc5e5fe789 100644 --- a/arch/powerpc/kernel/vdso32/sigtramp.S +++ b/arch/powerpc/kernel/vdso/sigtramp32.S diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso/sigtramp64.S index 2d4067561293..2d4067561293 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso/sigtramp64.S diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S index 58e0099f70f4..58e0099f70f4 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso/vdso32.lds.S diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S index 0288cad428b0..0288cad428b0 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso/vdso64.lds.S diff --git a/arch/powerpc/kernel/vdso32/vgettimeofday.c b/arch/powerpc/kernel/vdso/vgettimeofday.c index 65fb03fb1731..55a287c9a736 100644 --- a/arch/powerpc/kernel/vdso32/vgettimeofday.c +++ b/arch/powerpc/kernel/vdso/vgettimeofday.c @@ -2,8 +2,22 @@ /* * Powerpc userspace implementations of gettimeofday() and similar. */ +#include <linux/time.h> #include <linux/types.h> +#ifdef __powerpc64__ +int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, + const struct vdso_data *vd) +{ + return __cvdso_clock_gettime_data(vd, clock, ts); +} + +int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, + const struct vdso_data *vd) +{ + return __cvdso_clock_getres_data(vd, clock_id, res); +} +#else int __c_kernel_clock_gettime(clockid_t clock, struct old_timespec32 *ts, const struct vdso_data *vd) { @@ -16,16 +30,17 @@ int __c_kernel_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts, return __cvdso_clock_gettime_data(vd, clock, ts); } -int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, +int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, const struct vdso_data *vd) { - return __cvdso_gettimeofday_data(vd, tv, tz); + return __cvdso_clock_getres_time32_data(vd, clock_id, res); } +#endif -int __c_kernel_clock_getres(clockid_t clock_id, struct old_timespec32 *res, +int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, const struct vdso_data *vd) { - return __cvdso_clock_getres_time32_data(vd, clock_id, res); + return __cvdso_gettimeofday_data(vd, tv, tz); } __kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) diff --git a/arch/powerpc/kernel/vdso32/.gitignore b/arch/powerpc/kernel/vdso32/.gitignore deleted file mode 100644 index 824b863ec6bd..000000000000 --- a/arch/powerpc/kernel/vdso32/.gitignore +++ /dev/null @@ -1,3 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -vdso32.lds -vdso32.so.dbg diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile deleted file mode 100644 index 7d9a6fee0e3d..000000000000 --- a/arch/powerpc/kernel/vdso32/Makefile +++ /dev/null @@ -1,73 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 - -# List of files in the vdso, has to be asm only for now - -ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 -include $(srctree)/lib/vdso/Makefile - -obj-vdso32 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o - -ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -endif - -# Build rules - -ifdef CROSS32_COMPILE - VDSOCC := $(CROSS32_COMPILE)gcc -else - VDSOCC := $(CC) -endif - -CC32FLAGS := -ifdef CONFIG_PPC64 -CC32FLAGS += -m32 -KBUILD_CFLAGS := $(filter-out -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc,$(KBUILD_CFLAGS)) -endif - -targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday.o -obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) - -GCOV_PROFILE := n -KCOV_INSTRUMENT := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n - -ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ - -Wl,-soname=linux-vdso32.so.1 -Wl,--hash-style=both -asflags-y := -D__VDSO32__ -s - -obj-y += vdso32_wrapper.o -targets += vdso32.lds -CPPFLAGS_vdso32.lds += -P -C -Upowerpc - -# link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE - $(call if_changed,vdso32ld_and_check) - -# assembly rules for the .S files -$(obj-vdso32): %.o: %.S FORCE - $(call if_changed_dep,vdso32as) -$(obj)/vgettimeofday.o: %.o: %.c FORCE - $(call if_changed_dep,vdso32cc) - -# Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh -quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -include/generated/vdso32-offsets.h: $(obj)/vdso32.so.dbg FORCE - $(call if_changed,vdsosym) - -# actual build commands -quiet_cmd_vdso32ld_and_check = VDSO32L $@ - cmd_vdso32ld_and_check = $(VDSOCC) $(c_flags) $(CC32FLAGS) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) ; $(cmd_vdso_check) -quiet_cmd_vdso32as = VDSO32A $@ - cmd_vdso32as = $(VDSOCC) $(a_flags) $(CC32FLAGS) -c -o $@ $< -quiet_cmd_vdso32cc = VDSO32C $@ - cmd_vdso32cc = $(VDSOCC) $(c_flags) $(CC32FLAGS) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S index 3f5ef035b0a9..10f92f265d51 100644 --- a/arch/powerpc/kernel/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32_wrapper.S @@ -7,7 +7,7 @@ .globl vdso32_start, vdso32_end .balign PAGE_SIZE vdso32_start: - .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg" + .incbin "arch/powerpc/kernel/vdso/vdso32.so.dbg" .balign PAGE_SIZE vdso32_end: diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile deleted file mode 100644 index 3c5baaa6f1e7..000000000000 --- a/arch/powerpc/kernel/vdso64/Makefile +++ /dev/null @@ -1,56 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# List of files in the vdso, has to be asm only for now - -ARCH_REL_TYPE_ABS := R_PPC_JUMP_SLOT|R_PPC_GLOB_DAT|R_PPC_ADDR32|R_PPC_ADDR24|R_PPC_ADDR16|R_PPC_ADDR16_LO|R_PPC_ADDR16_HI|R_PPC_ADDR16_HA|R_PPC_ADDR14|R_PPC_ADDR14_BRTAKEN|R_PPC_ADDR14_BRNTAKEN|R_PPC_REL24 -include $(srctree)/lib/vdso/Makefile - -obj-vdso64 = sigtramp.o gettimeofday.o datapage.o cacheflush.o note.o getcpu.o - -ifneq ($(c-gettimeofday-y),) - CFLAGS_vgettimeofday.o += -include $(c-gettimeofday-y) - CFLAGS_vgettimeofday.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) - CFLAGS_vgettimeofday.o += $(call cc-option, -fno-stack-protector) - CFLAGS_vgettimeofday.o += -DDISABLE_BRANCH_PROFILING - CFLAGS_vgettimeofday.o += -ffreestanding -fasynchronous-unwind-tables - CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -endif - -# Build rules - -targets := $(obj-vdso64) vdso64.so.dbg vgettimeofday.o -obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) - -GCOV_PROFILE := n -KCOV_INSTRUMENT := n -UBSAN_SANITIZE := n -KASAN_SANITIZE := n - -ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ - -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both - -# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true -# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is -# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code -# generation is minimal, it will just use r29 instead. -ccflags-y += $(call cc-option, -ffixed-r30) - -asflags-y := -D__VDSO64__ -s - -targets += vdso64.lds -CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) - -# link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE - $(call if_changed,vdso64ld_and_check) - -# Generate VDSO offsets using helper script -gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh -quiet_cmd_vdsosym = VDSOSYM $@ - cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -include/generated/vdso64-offsets.h: $(obj)/vdso64.so.dbg FORCE - $(call if_changed,vdsosym) - -# actual build commands -quiet_cmd_vdso64ld_and_check = VDSO64L $@ - cmd_vdso64ld_and_check = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^); $(cmd_vdso_check) diff --git a/arch/powerpc/kernel/vdso64/cacheflush.S b/arch/powerpc/kernel/vdso64/cacheflush.S deleted file mode 100644 index 76c3c8cf8ece..000000000000 --- a/arch/powerpc/kernel/vdso64/cacheflush.S +++ /dev/null @@ -1,75 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * vDSO provided cache flush routines - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - */ -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/vdso.h> -#include <asm/vdso_datapage.h> -#include <asm/asm-offsets.h> - - .text - -/* - * Default "generic" version of __kernel_sync_dicache. - * - * void __kernel_sync_dicache(unsigned long start, unsigned long end) - * - * Flushes the data cache & invalidate the instruction cache for the - * provided range [start, end[ - */ -V_FUNCTION_BEGIN(__kernel_sync_dicache) - .cfi_startproc -BEGIN_FTR_SECTION - b 3f -END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) - mflr r12 - .cfi_register lr,r12 - get_datapage r10 - mtlr r12 - .cfi_restore lr - - lwz r7,CFG_DCACHE_BLOCKSZ(r10) - addi r5,r7,-1 - 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) - srd. r8,r8,r9 /* compute line count */ - crclr cr0*4+so - beqlr /* nothing to do? */ - mtctr r8 -1: dcbst 0,r6 - add r6,r6,r7 - bdnz 1b - sync - -/* Now invalidate the instruction cache */ - - lwz r7,CFG_ICACHE_BLOCKSZ(r10) - addi r5,r7,-1 - 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) - srd. r8,r8,r9 /* compute line count */ - crclr cr0*4+so - beqlr /* nothing to do? */ - mtctr r8 -2: icbi 0,r6 - add r6,r6,r7 - bdnz 2b - isync - li r3,0 - blr -3: - crclr cr0*4+so - sync - isync - li r3,0 - blr - .cfi_endproc -V_FUNCTION_END(__kernel_sync_dicache) diff --git a/arch/powerpc/kernel/vdso64/datapage.S b/arch/powerpc/kernel/vdso64/datapage.S deleted file mode 100644 index 00760dc69d68..000000000000 --- a/arch/powerpc/kernel/vdso64/datapage.S +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Access to the shared data page by the vDSO & syscall map - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), IBM Corp. - */ - -#include <asm/processor.h> -#include <asm/ppc_asm.h> -#include <asm/asm-offsets.h> -#include <asm/unistd.h> -#include <asm/vdso.h> -#include <asm/vdso_datapage.h> - - .text - -/* - * void *__kernel_get_syscall_map(unsigned int *syscall_count) ; - * - * returns a pointer to the syscall map. the map is agnostic to the - * size of "long", unlike kernel bitops, it stores bits from top to - * bottom so that memory actually contains a linear bitmap - * check for syscall N by testing bit (0x80000000 >> (N & 0x1f)) of - * 32 bits int at N >> 5. - */ -V_FUNCTION_BEGIN(__kernel_get_syscall_map) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - mr r4,r3 - get_datapage r3 - mtlr r12 - addi r3,r3,CFG_SYSCALL_MAP64 - cmpldi cr0,r4,0 - crclr cr0*4+so - beqlr - li r0,NR_syscalls - stw r0,0(r4) - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_syscall_map) - - -/* - * void unsigned long __kernel_get_tbfreq(void); - * - * returns the timebase frequency in HZ - */ -V_FUNCTION_BEGIN(__kernel_get_tbfreq) - .cfi_startproc - mflr r12 - .cfi_register lr,r12 - get_datapage r3 - ld r3,CFG_TB_TICKS_PER_SEC(r3) - mtlr r12 - crclr cr0*4+so - blr - .cfi_endproc -V_FUNCTION_END(__kernel_get_tbfreq) diff --git a/arch/powerpc/kernel/vdso64/getcpu.S b/arch/powerpc/kernel/vdso64/getcpu.S deleted file mode 100644 index 12bbf236cdc4..000000000000 --- a/arch/powerpc/kernel/vdso64/getcpu.S +++ /dev/null @@ -1,33 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * - * Copyright (C) IBM Corporation, 2012 - * - * Author: Anton Blanchard <anton@au.ibm.com> - */ -#include <asm/ppc_asm.h> -#include <asm/vdso.h> - - .text -/* - * Exact prototype of getcpu - * - * int __kernel_getcpu(unsigned *cpu, unsigned *node); - * - */ -V_FUNCTION_BEGIN(__kernel_getcpu) - .cfi_startproc - mfspr r5,SPRN_SPRG_VDSO_READ - cmpdi cr0,r3,0 - cmpdi cr1,r4,0 - clrlwi r6,r5,16 - rlwinm r7,r5,16,31-15,31-0 - beq cr0,1f - stw r6,0(r3) -1: beq cr1,2f - stw r7,0(r4) -2: crclr cr0*4+so - li r3,0 /* always success */ - blr - .cfi_endproc -V_FUNCTION_END(__kernel_getcpu) diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S deleted file mode 100644 index d7a7bfb51081..000000000000 --- a/arch/powerpc/kernel/vdso64/gettimeofday.S +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * Userland implementation of gettimeofday() for 64 bits processes in a - * ppc64 kernel for use in the vDSO - * - * Copyright (C) 2004 Benjamin Herrenschmuidt (benh@kernel.crashing.org), - * IBM Corp. - */ -#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> -#include <asm/vdso/gettimeofday.h> - - .text -/* - * Exact prototype of gettimeofday - * - * int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); - * - */ -V_FUNCTION_BEGIN(__kernel_gettimeofday) - cvdso_call __c_kernel_gettimeofday -V_FUNCTION_END(__kernel_gettimeofday) - - -/* - * Exact prototype of clock_gettime() - * - * int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_gettime) - cvdso_call __c_kernel_clock_gettime -V_FUNCTION_END(__kernel_clock_gettime) - - -/* - * Exact prototype of clock_getres() - * - * int __kernel_clock_getres(clockid_t clock_id, struct timespec *res); - * - */ -V_FUNCTION_BEGIN(__kernel_clock_getres) - cvdso_call __c_kernel_clock_getres -V_FUNCTION_END(__kernel_clock_getres) - -/* - * Exact prototype of time() - * - * time_t time(time *t); - * - */ -V_FUNCTION_BEGIN(__kernel_time) - cvdso_call_time __c_kernel_time -V_FUNCTION_END(__kernel_time) diff --git a/arch/powerpc/kernel/vdso64/note.S b/arch/powerpc/kernel/vdso64/note.S deleted file mode 100644 index dc2a509f7e8a..000000000000 --- a/arch/powerpc/kernel/vdso64/note.S +++ /dev/null @@ -1 +0,0 @@ -#include "../vdso32/note.S" diff --git a/arch/powerpc/kernel/vdso64/vgettimeofday.c b/arch/powerpc/kernel/vdso64/vgettimeofday.c deleted file mode 100644 index 5b5500058344..000000000000 --- a/arch/powerpc/kernel/vdso64/vgettimeofday.c +++ /dev/null @@ -1,29 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Powerpc userspace implementations of gettimeofday() and similar. - */ -#include <linux/time.h> -#include <linux/types.h> - -int __c_kernel_clock_gettime(clockid_t clock, struct __kernel_timespec *ts, - const struct vdso_data *vd) -{ - return __cvdso_clock_gettime_data(vd, clock, ts); -} - -int __c_kernel_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz, - const struct vdso_data *vd) -{ - return __cvdso_gettimeofday_data(vd, tv, tz); -} - -int __c_kernel_clock_getres(clockid_t clock_id, struct __kernel_timespec *res, - const struct vdso_data *vd) -{ - return __cvdso_clock_getres_data(vd, clock_id, res); -} - -__kernel_old_time_t __c_kernel_time(__kernel_old_time_t *time, const struct vdso_data *vd) -{ - return __cvdso_time_data(vd, time); -} diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S index 1d56d81fe3b3..839d1a61411d 100644 --- a/arch/powerpc/kernel/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64_wrapper.S @@ -7,7 +7,7 @@ .globl vdso64_start, vdso64_end .balign PAGE_SIZE vdso64_start: - .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg" + .incbin "arch/powerpc/kernel/vdso/vdso64.so.dbg" .balign PAGE_SIZE vdso64_end: diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 2bcca818136a..fe22d940412f 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -281,9 +281,7 @@ SECTIONS . = ALIGN(8); .dynsym : AT(ADDR(.dynsym) - LOAD_OFFSET) { -#ifdef CONFIG_PPC32 __dynamic_symtab = .; -#endif *(.dynsym) } .dynstr : AT(ADDR(.dynstr) - LOAD_OFFSET) { *(.dynstr) } diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index 8b68d9f91a03..abf5897ae88c 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -134,11 +134,18 @@ void __init reserve_crashkernel(void) if (!crashk_res.start) { #ifdef CONFIG_PPC64 /* - * On 64bit we split the RMO in half but cap it at half of - * a small SLB (128MB) since the crash kernel needs to place - * itself and some stacks to be in the first segment. + * On the LPAR platform place the crash kernel to mid of + * RMA size (512MB or more) to ensure the crash kernel + * gets enough space to place itself and some stack to be + * in the first segment. At the same time normal kernel + * also get enough space to allocate memory for essential + * system resource in the first segment. Keep the crash + * kernel starts at 128MB offset on other platforms. */ - crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2)); + if (firmware_has_feature(FW_FEATURE_LPAR)) + crashk_res.start = ppc64_rma_size / 2; + else + crashk_res.start = min(0x8000000ULL, (ppc64_rma_size / 2)); #else crashk_res.start = KDUMP_KERNELBASE; #endif diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index 635b5fc30b53..6cc7793b8420 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -28,7 +28,6 @@ #include <asm/prom.h> #include <asm/smp.h> #include <asm/hw_breakpoint.h> -#include <asm/asm-prototypes.h> #include <asm/svm.h> #include <asm/ultravisor.h> @@ -291,7 +290,7 @@ static union thread_union kexec_stack __init_task_data = * For similar reasons to the stack above, the kexecing CPU needs to be on a * static PACA; we switch to kexec_paca. */ -struct paca_struct kexec_paca; +static struct paca_struct kexec_paca; /* Our assembly helper, in misc_64.S */ extern void kexec_sequence(void *newstack, unsigned long start, diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index c3e31fef0be1..1ae09992c9ea 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -228,7 +228,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid) struct kvmppc_sid_map *map; struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu); u16 sid_map_mask; - static int backwards_map = 0; + static int backwards_map; if (kvmppc_get_msr(vcpu) & MSR_PR) gvsid |= VSID_PR; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 213232914367..0aeb51738ca9 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -2112,7 +2112,7 @@ static const struct file_operations debugfs_htab_fops = { void kvmppc_mmu_debugfs_init(struct kvm *kvm) { - debugfs_create_file("htab", 0400, kvm->arch.debugfs_dir, kvm, + debugfs_create_file("htab", 0400, kvm->debugfs_dentry, kvm, &debugfs_htab_fops); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 8cebe5542256..e4ce2a35483f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -1454,7 +1454,7 @@ static const struct file_operations debugfs_radix_fops = { void kvmhv_radix_debugfs_init(struct kvm *kvm) { - debugfs_create_file("radix", 0400, kvm->arch.debugfs_dir, kvm, + debugfs_create_file("radix", 0400, kvm->debugfs_dentry, kvm, &debugfs_radix_fops); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 84c89f08ae9a..c886557638a1 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2767,20 +2767,17 @@ static const struct file_operations debugfs_timings_ops = { }; /* Create a debugfs directory for the vcpu */ -static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { - char buf[16]; - struct kvm *kvm = vcpu->kvm; - - snprintf(buf, sizeof(buf), "vcpu%u", id); - vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir); - debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, vcpu, + debugfs_create_file("timings", 0444, debugfs_dentry, vcpu, &debugfs_timings_ops); + return 0; } #else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ -static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id) +static int kvmppc_arch_create_vcpu_debugfs_hv(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) { + return 0; } #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */ @@ -2903,8 +2900,6 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu) vcpu->arch.cpu_type = KVM_CPU_3S_64; kvmppc_sanity_check(vcpu); - debugfs_vcpu_init(vcpu, id); - return 0; } @@ -5223,7 +5218,6 @@ void kvmppc_free_host_rm_ops(void) static int kvmppc_core_init_vm_hv(struct kvm *kvm) { unsigned long lpcr, lpid; - char buf[32]; int ret; mutex_init(&kvm->arch.uvmem_lock); @@ -5356,15 +5350,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) kvm->arch.smt_mode = 1; kvm->arch.emul_smt_mode = 1; - /* - * Create a debugfs directory for the VM - */ - snprintf(buf, sizeof(buf), "vm%d", current->pid); - kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir); + return 0; +} + +static int kvmppc_arch_create_vm_debugfs_hv(struct kvm *kvm) +{ kvmppc_mmu_debugfs_init(kvm); if (radix_enabled()) kvmhv_radix_debugfs_init(kvm); - return 0; } @@ -5379,8 +5372,6 @@ static void kvmppc_free_vcores(struct kvm *kvm) static void kvmppc_core_destroy_vm_hv(struct kvm *kvm) { - debugfs_remove_recursive(kvm->arch.debugfs_dir); - if (!cpu_has_feature(CPU_FTR_ARCH_300)) kvm_hv_vm_deactivated(); @@ -6042,6 +6033,8 @@ static struct kvmppc_ops kvm_ops_hv = { .svm_off = kvmhv_svm_off, .enable_dawr1 = kvmhv_enable_dawr1, .hash_v3_possible = kvmppc_hash_v3_possible, + .create_vcpu_debugfs = kvmppc_arch_create_vcpu_debugfs_hv, + .create_vm_debugfs = kvmppc_arch_create_vm_debugfs_hv, }; static int kvm_init_subcore_bitmap(void) @@ -6103,7 +6096,7 @@ static int kvmppc_book3s_init_hv(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) { r = kvm_init_subcore_bitmap(); if (r) - return r; + goto err; } /* @@ -6119,30 +6112,42 @@ static int kvmppc_book3s_init_hv(void) np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc"); if (!np) { pr_err("KVM-HV: Cannot determine method for accessing XICS\n"); - return -ENODEV; + r = -ENODEV; + goto err; } /* presence of intc confirmed - node can be dropped again */ of_node_put(np); } #endif - kvm_ops_hv.owner = THIS_MODULE; - kvmppc_hv_ops = &kvm_ops_hv; - init_default_hcalls(); init_vcore_lists(); r = kvmppc_mmu_hv_init(); if (r) - return r; + goto err; - if (kvmppc_radix_possible()) + if (kvmppc_radix_possible()) { r = kvmppc_radix_init(); + if (r) + goto err; + } r = kvmppc_uvmem_init(); - if (r < 0) + if (r < 0) { pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r); + return r; + } + + kvm_ops_hv.owner = THIS_MODULE; + kvmppc_hv_ops = &kvm_ops_hv; + + return 0; + +err: + kvmhv_nested_exit(); + kvmppc_radix_exit(); return r; } diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index 7d6d91338c3f..7e52d0beee77 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -15,7 +15,6 @@ #include <linux/cma.h> #include <linux/bitops.h> -#include <asm/asm-prototypes.h> #include <asm/cputable.h> #include <asm/interrupt.h> #include <asm/kvm_ppc.h> diff --git a/arch/powerpc/kvm/book3s_hv_rm_xive.c b/arch/powerpc/kvm/book3s_hv_rm_xive.c index 6f18632e30e9..dd9880731bd6 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_xive.c +++ b/arch/powerpc/kvm/book3s_hv_rm_xive.c @@ -16,7 +16,6 @@ #include <asm/pnv-pci.h> #include <asm/opal.h> #include <asm/smp.h> -#include <asm/asm-prototypes.h> #include <asm/xive.h> #include <asm/xive-regs.h> diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 9cc466006e8b..ab6d37d78c62 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1016,19 +1016,10 @@ DEFINE_SHOW_ATTRIBUTE(xics_debug); static void xics_debugfs_init(struct kvmppc_xics *xics) { - char *name; - - name = kasprintf(GFP_KERNEL, "kvm-xics-%p", xics); - if (!name) { - pr_err("%s: no memory for name\n", __func__); - return; - } - - xics->dentry = debugfs_create_file(name, 0444, arch_debugfs_dir, + xics->dentry = debugfs_create_file("xics", 0444, xics->kvm->debugfs_dentry, xics, &xics_debug_fops); - pr_debug("%s: created %s\n", __func__, name); - kfree(name); + pr_debug("%s: created\n", __func__); } static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm, @@ -1440,7 +1431,7 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) static void kvmppc_xics_init(struct kvm_device *dev) { - struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private; + struct kvmppc_xics *xics = dev->private; xics_debugfs_init(xics); } diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index e216c068075d..c0ce5531d9bc 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -2354,24 +2354,15 @@ DEFINE_SHOW_ATTRIBUTE(xive_debug); static void xive_debugfs_init(struct kvmppc_xive *xive) { - char *name; - - name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive); - if (!name) { - pr_err("%s: no memory for name\n", __func__); - return; - } - - xive->dentry = debugfs_create_file(name, S_IRUGO, arch_debugfs_dir, + xive->dentry = debugfs_create_file("xive", S_IRUGO, xive->kvm->debugfs_dentry, xive, &xive_debug_fops); - pr_debug("%s: created %s\n", __func__, name); - kfree(name); + pr_debug("%s: created\n", __func__); } static void kvmppc_xive_init(struct kvm_device *dev) { - struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private; + struct kvmppc_xive *xive = dev->private; /* Register some debug interfaces */ xive_debugfs_init(xive); diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 561a5bfe0468..f81ba6f84e72 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -1259,24 +1259,15 @@ DEFINE_SHOW_ATTRIBUTE(xive_native_debug); static void xive_native_debugfs_init(struct kvmppc_xive *xive) { - char *name; - - name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive); - if (!name) { - pr_err("%s: no memory for name\n", __func__); - return; - } - - xive->dentry = debugfs_create_file(name, 0444, arch_debugfs_dir, + xive->dentry = debugfs_create_file("xive", 0444, xive->kvm->debugfs_dentry, xive, &xive_native_debug_fops); - pr_debug("%s: created %s\n", __func__, name); - kfree(name); + pr_debug("%s: created\n", __func__); } static void kvmppc_xive_native_init(struct kvm_device *dev) { - struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private; + struct kvmppc_xive *xive = dev->private; /* Register some debug interfaces */ xive_native_debugfs_init(xive); diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 7e8b69015d20..c8b2b4478545 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -495,6 +495,7 @@ static struct kvmppc_ops kvm_ops_e500 = { .emulate_op = kvmppc_core_emulate_op_e500, .emulate_mtspr = kvmppc_core_emulate_mtspr_e500, .emulate_mfspr = kvmppc_core_emulate_mfspr_e500, + .create_vcpu_debugfs = kvmppc_create_vcpu_debugfs_e500, }; static int __init kvmppc_e500_init(void) diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 1c189b5aadcc..fa0d8dbbe484 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -381,6 +381,7 @@ static struct kvmppc_ops kvm_ops_e500mc = { .emulate_op = kvmppc_core_emulate_op_e500, .emulate_mtspr = kvmppc_core_emulate_mtspr_e500, .emulate_mfspr = kvmppc_core_emulate_mfspr_e500, + .create_vcpu_debugfs = kvmppc_create_vcpu_debugfs_e500, }; static int __init kvmppc_e500mc_init(void) diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c index 48272a9b9c30..cfc9114b87d0 100644 --- a/arch/powerpc/kvm/emulate_loadstore.c +++ b/arch/powerpc/kvm/emulate_loadstore.c @@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) { u32 inst; enum emulation_result emulated = EMULATE_FAIL; - int advance = 1; struct instruction_op op; /* this default type might be overwritten by subcategories */ @@ -98,6 +97,8 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) int type = op.type & INSTR_TYPE_MASK; int size = GETSIZE(op.type); + vcpu->mmio_is_write = OP_IS_STORE(type); + switch (type) { case LOAD: { int instr_byte_swap = op.type & BYTEREV; @@ -355,15 +356,10 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu) } } - if (emulated == EMULATE_FAIL) { - advance = 0; - kvmppc_core_queue_program(vcpu, 0); - } - trace_kvm_ppc_instr(inst, kvmppc_get_pc(vcpu), emulated); /* Advance past emulated instruction. */ - if (advance) + if (emulated != EMULATE_FAIL) kvmppc_set_pc(vcpu, kvmppc_get_pc(vcpu) + 4); return emulated; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 2ad0ccd202d5..9772b176e406 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -307,9 +307,31 @@ int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu) u32 last_inst; kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst); - /* XXX Deliver Program interrupt to guest. */ - pr_emerg("%s: emulation failed (%08x)\n", __func__, last_inst); - r = RESUME_HOST; + kvm_debug_ratelimited("Guest access to device memory using unsupported instruction (opcode: %#08x)\n", + last_inst); + + /* + * Injecting a Data Storage here is a bit more + * accurate since the instruction that caused the + * access could still be a valid one. + */ + if (!IS_ENABLED(CONFIG_BOOKE)) { + ulong dsisr = DSISR_BADACCESS; + + if (vcpu->mmio_is_write) + dsisr |= DSISR_ISSTORE; + + kvmppc_core_queue_data_storage(vcpu, vcpu->arch.vaddr_accessed, dsisr); + } else { + /* + * BookE does not send a SIGBUS on a bad + * fault, so use a Program interrupt instead + * to avoid a fault loop. + */ + kvmppc_core_queue_program(vcpu, 0); + } + + r = RESUME_GUEST; break; } default: @@ -431,6 +453,8 @@ int kvm_arch_check_processor_compat(void *opaque) int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { struct kvmppc_ops *kvm_ops = NULL; + int r; + /* * if we have both HV and PR enabled, default is HV */ @@ -452,11 +476,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) } else goto err_out; - if (kvm_ops->owner && !try_module_get(kvm_ops->owner)) + if (!try_module_get(kvm_ops->owner)) return -ENOENT; kvm->arch.kvm_ops = kvm_ops; - return kvmppc_core_init_vm(kvm); + r = kvmppc_core_init_vm(kvm); + if (r) + module_put(kvm_ops->owner); + return r; err_out: return -EINVAL; } @@ -755,7 +782,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) rcuwait_init(&vcpu->arch.wait); vcpu->arch.waitp = &vcpu->arch.wait; - kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; out_vcpu_uninit: @@ -772,8 +798,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Make sure we're not using the vcpu anymore */ hrtimer_cancel(&vcpu->arch.dec_timer); - kvmppc_remove_vcpu_debugfs(vcpu); - switch (vcpu->arch.irq_type) { case KVMPPC_IRQ_MPIC: kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu); @@ -1114,10 +1138,8 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; u64 gpr; - if (run->mmio.len > sizeof(gpr)) { - printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len); + if (run->mmio.len > sizeof(gpr)) return; - } if (!vcpu->arch.mmio_host_swabbed) { switch (run->mmio.len) { @@ -1236,10 +1258,8 @@ static int __kvmppc_handle_load(struct kvm_vcpu *vcpu, host_swabbed = !is_default_endian; } - if (bytes > sizeof(run->mmio.data)) { - printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, - run->mmio.len); - } + if (bytes > sizeof(run->mmio.data)) + return EMULATE_FAIL; run->mmio.phys_addr = vcpu->arch.paddr_accessed; run->mmio.len = bytes; @@ -1325,10 +1345,8 @@ int kvmppc_handle_store(struct kvm_vcpu *vcpu, host_swabbed = !is_default_endian; } - if (bytes > sizeof(run->mmio.data)) { - printk(KERN_ERR "%s: bad MMIO length: %d\n", __func__, - run->mmio.len); - } + if (bytes > sizeof(run->mmio.data)) + return EMULATE_FAIL; run->mmio.phys_addr = vcpu->arch.paddr_accessed; run->mmio.len = bytes; @@ -1499,7 +1517,7 @@ int kvmppc_handle_vmx_load(struct kvm_vcpu *vcpu, { enum emulation_result emulated = EMULATE_DONE; - if (vcpu->arch.mmio_vsx_copy_nums > 2) + if (vcpu->arch.mmio_vmx_copy_nums > 2) return EMULATE_FAIL; while (vcpu->arch.mmio_vmx_copy_nums) { @@ -1596,7 +1614,7 @@ int kvmppc_handle_vmx_store(struct kvm_vcpu *vcpu, unsigned int index = rs & KVM_MMIO_REG_MASK; enum emulation_result emulated = EMULATE_DONE; - if (vcpu->arch.mmio_vsx_copy_nums > 2) + if (vcpu->arch.mmio_vmx_copy_nums > 2) return EMULATE_FAIL; vcpu->arch.io_gpr = rs; @@ -1841,6 +1859,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) #ifdef CONFIG_ALTIVEC out: #endif + + /* + * We're already returning to userspace, don't pass the + * RESUME_HOST flags along. + */ + if (r > 0) + r = 0; + vcpu_put(vcpu); return r; } @@ -2497,3 +2523,16 @@ int kvm_arch_init(void *opaque) } EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr); + +void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) +{ + if (vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs) + vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry); +} + +int kvm_arch_create_vm_debugfs(struct kvm *kvm) +{ + if (kvm->arch.kvm_ops->create_vm_debugfs) + kvm->arch.kvm_ops->create_vm_debugfs(kvm); + return 0; +} diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c index ba56a5cbba97..25071331f8c1 100644 --- a/arch/powerpc/kvm/timing.c +++ b/arch/powerpc/kvm/timing.c @@ -204,21 +204,10 @@ static const struct file_operations kvmppc_exit_timing_fops = { .release = single_release, }; -void kvmppc_create_vcpu_debugfs(struct kvm_vcpu *vcpu, unsigned int id) +int kvmppc_create_vcpu_debugfs_e500(struct kvm_vcpu *vcpu, + struct dentry *debugfs_dentry) { - static char dbg_fname[50]; - struct dentry *debugfs_file; - - snprintf(dbg_fname, sizeof(dbg_fname), "vm%u_vcpu%u_timing", - current->pid, id); - debugfs_file = debugfs_create_file(dbg_fname, 0666, kvm_debugfs_dir, - vcpu, &kvmppc_exit_timing_fops); - - vcpu->arch.debugfs_exit_timing = debugfs_file; -} - -void kvmppc_remove_vcpu_debugfs(struct kvm_vcpu *vcpu) -{ - debugfs_remove(vcpu->arch.debugfs_exit_timing); - vcpu->arch.debugfs_exit_timing = NULL; + debugfs_create_file("timing", 0666, debugfs_dentry, + vcpu, &kvmppc_exit_timing_fops); + return 0; } diff --git a/arch/powerpc/kvm/timing.h b/arch/powerpc/kvm/timing.h index feef7885ba82..45817ab82bb4 100644 --- a/arch/powerpc/kvm/timing.h +++ b/arch/powerpc/kvm/timing.h @@ -14,8 +14,8 @@ #ifdef CONFIG_KVM_EXIT_TIMING void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu); void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu); -void kvmppc_create_vcpu_debugfs(struct kvm_vcpu *vcpu, unsigned int id); -void kvmppc_remove_vcpu_debugfs(struct kvm_vcpu *vcpu); +int kvmppc_create_vcpu_debugfs_e500(struct kvm_vcpu *vcpu, + struct dentry *debugfs_dentry); static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) { @@ -26,9 +26,11 @@ static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) /* if exit timing is not configured there is no need to build the c file */ static inline void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu) {} static inline void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu) {} -static inline void kvmppc_create_vcpu_debugfs(struct kvm_vcpu *vcpu, - unsigned int id) {} -static inline void kvmppc_remove_vcpu_debugfs(struct kvm_vcpu *vcpu) {} +static inline int kvmppc_create_vcpu_debugfs_e500(struct kvm_vcpu *vcpu, + struct dentry *debugfs_dentry) +{ + return 0; +} static inline void kvmppc_set_exit_type(struct kvm_vcpu *vcpu, int type) {} #endif /* CONFIG_KVM_EXIT_TIMING */ diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h index 830a126e095d..38cd0ed0a617 100644 --- a/arch/powerpc/kvm/trace_hv.h +++ b/arch/powerpc/kvm/trace_hv.h @@ -115,6 +115,7 @@ {H_VASI_STATE, "H_VASI_STATE"}, \ {H_ENABLE_CRQ, "H_ENABLE_CRQ"}, \ {H_GET_EM_PARMS, "H_GET_EM_PARMS"}, \ + {H_GET_ENERGY_SCALE_INFO, "H_GET_ENERGY_SCALE_INFO"}, \ {H_SET_MPP, "H_SET_MPP"}, \ {H_GET_MPP, "H_GET_MPP"}, \ {H_HOME_NODE_ASSOCIATIVITY, "H_HOME_NODE_ASSOCIATIVITY"}, \ diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index 27d9070617df..4541e8e29467 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -116,9 +116,6 @@ EXPORT_SYMBOL(__csum_partial) EX_TABLE(8 ## n ## 7b, fault); .text - .stabs "arch/powerpc/lib/",N_SO,0,0,0f - .stabs "checksum_32.S",N_SO,0,0,0f -0: CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 906d43463366..00c68e7fb11e 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -43,9 +43,14 @@ int raw_patch_instruction(u32 *addr, ppc_inst_t instr) #ifdef CONFIG_STRICT_KERNEL_RWX static DEFINE_PER_CPU(struct vm_struct *, text_poke_area); +static int map_patch_area(void *addr, unsigned long text_poke_addr); +static void unmap_patch_area(unsigned long addr); + static int text_area_cpu_up(unsigned int cpu) { struct vm_struct *area; + unsigned long addr; + int err; area = get_vm_area(PAGE_SIZE, VM_ALLOC); if (!area) { @@ -53,6 +58,15 @@ static int text_area_cpu_up(unsigned int cpu) cpu); return -1; } + + // Map/unmap the area to ensure all page tables are pre-allocated + addr = (unsigned long)area->addr; + err = map_patch_area(empty_zero_page, addr); + if (err) + return err; + + unmap_patch_area(addr); + this_cpu_write(text_poke_area, area); return 0; diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S index a3bcf4786e4a..3e9c27c46331 100644 --- a/arch/powerpc/lib/copy_32.S +++ b/arch/powerpc/lib/copy_32.S @@ -57,9 +57,6 @@ EX_TABLE(8 ## n ## 7b,9 ## n ## 1b) .text - .stabs "arch/powerpc/lib/",N_SO,0,0,0f - .stabs "copy_32.S",N_SO,0,0,0f -0: CACHELINE_BYTES = L1_CACHE_BYTES LG_CACHELINE_BYTES = L1_CACHE_SHIFT diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index 5ed88fbee0db..6f79bde6d6c2 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -75,10 +75,8 @@ extern int do_stqcx(unsigned long ea, unsigned long val0, unsigned long val1, static nokprobe_inline unsigned long truncate_if_32bit(unsigned long msr, unsigned long val) { -#ifdef __powerpc64__ if ((msr & MSR_64BIT) == 0) val &= 0xffffffffUL; -#endif return val; } @@ -1065,15 +1063,9 @@ Efault: int emulate_dcbz(unsigned long ea, struct pt_regs *regs) { int err; - unsigned long size; + unsigned long size = l1_dcache_bytes(); -#ifdef __powerpc64__ - size = ppc64_caches.l1d.block_size; - if (!(regs->msr & MSR_64BIT)) - ea &= 0xffffffffUL; -#else - size = L1_CACHE_BYTES; -#endif + ea = truncate_if_32bit(regs->msr, ea); ea &= ~(size - 1); if (!address_ok(regs, ea, size)) return -EFAULT; @@ -1097,7 +1089,10 @@ NOKPROBE_SYMBOL(emulate_dcbz); #define __put_user_asmx(x, addr, err, op, cr) \ __asm__ __volatile__( \ + ".machine push\n" \ + ".machine power8\n" \ "1: " op " %2,0,%3\n" \ + ".machine pop\n" \ " mfcr %1\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ @@ -1110,7 +1105,10 @@ NOKPROBE_SYMBOL(emulate_dcbz); #define __get_user_asmx(x, addr, err, op) \ __asm__ __volatile__( \ + ".machine push\n" \ + ".machine power8\n" \ "1: "op" %1,0,%2\n" \ + ".machine pop\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -1139,10 +1137,8 @@ static nokprobe_inline void set_cr0(const struct pt_regs *regs, op->type |= SETCC; op->ccval = (regs->ccr & 0x0fffffff) | ((regs->xer >> 3) & 0x10000000); -#ifdef __powerpc64__ if (!(regs->msr & MSR_64BIT)) val = (int) val; -#endif if (val < 0) op->ccval |= 0x80000000; else if (val > 0) @@ -1173,12 +1169,8 @@ static nokprobe_inline void add_with_carry(const struct pt_regs *regs, op->type = COMPUTE + SETREG + SETXER; op->reg = rd; op->val = val; -#ifdef __powerpc64__ - if (!(regs->msr & MSR_64BIT)) { - val = (unsigned int) val; - val1 = (unsigned int) val1; - } -#endif + val = truncate_if_32bit(regs->msr, val); + val1 = truncate_if_32bit(regs->msr, val1); op->xerval = regs->xer; if (val < val1 || (carry_in && val == val1)) op->xerval |= XER_CA; @@ -3389,7 +3381,7 @@ int emulate_loadstore(struct pt_regs *regs, struct instruction_op *op) __put_user_asmx(op->val, ea, err, "stbcx.", cr); break; case 2: - __put_user_asmx(op->val, ea, err, "stbcx.", cr); + __put_user_asmx(op->val, ea, err, "sthcx.", cr); break; #endif case 4: diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index 62e6c3045252..f76a50291fd7 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -9,7 +9,6 @@ #include <linux/uaccess.h> #include <linux/hardirq.h> #include <asm/switch_to.h> -#include <asm/asm-prototypes.h> int enter_vmx_usercopy(void) { diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 7abf82a698d3..985cabdd7f67 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1621,8 +1621,7 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap, } EXPORT_SYMBOL_GPL(hash_page); -DECLARE_INTERRUPT_HANDLER(__do_hash_fault); -DEFINE_INTERRUPT_HANDLER(__do_hash_fault) +DEFINE_INTERRUPT_HANDLER(do_hash_fault) { unsigned long ea = regs->dar; unsigned long dsisr = regs->dsisr; @@ -1681,35 +1680,6 @@ DEFINE_INTERRUPT_HANDLER(__do_hash_fault) } } -/* - * The _RAW interrupt entry checks for the in_nmi() case before - * running the full handler. - */ -DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault) -{ - /* - * If we are in an "NMI" (e.g., an interrupt when soft-disabled), then - * don't call hash_page, just fail the fault. This is required to - * prevent re-entrancy problems in the hash code, namely perf - * interrupts hitting while something holds H_PAGE_BUSY, and taking a - * hash fault. See the comment in hash_preload(). - * - * We come here as a result of a DSI at a point where we don't want - * to call hash_page, such as when we are accessing memory (possibly - * user memory) inside a PMU interrupt that occurred while interrupts - * were soft-disabled. We want to invoke the exception handler for - * the access, or panic if there isn't a handler. - */ - if (unlikely(in_nmi())) { - do_bad_page_fault_segv(regs); - return 0; - } - - __do_hash_fault(regs); - - return 0; -} - #ifdef CONFIG_PPC_MM_SLICES static bool should_hash_preload(struct mm_struct *mm, unsigned long ea) { @@ -1776,26 +1746,18 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, #endif /* CONFIG_PPC_64K_PAGES */ /* - * __hash_page_* must run with interrupts off, as it sets the - * H_PAGE_BUSY bit. It's possible for perf interrupts to hit at any - * time and may take a hash fault reading the user stack, see - * read_user_stack_slow() in the powerpc/perf code. - * - * If that takes a hash fault on the same page as we lock here, it - * will bail out when seeing H_PAGE_BUSY set, and retry the access - * leading to an infinite loop. + * __hash_page_* must run with interrupts off, including PMI interrupts + * off, as it sets the H_PAGE_BUSY bit. * - * Disabling interrupts here does not prevent perf interrupts, but it - * will prevent them taking hash faults (see the NMI test in - * do_hash_page), then read_user_stack's copy_from_user_nofault will - * fail and perf will fall back to read_user_stack_slow(), which - * walks the Linux page tables. + * It's otherwise possible for perf interrupts to hit at any time and + * may take a hash fault reading the user stack, which could take a + * hash miss and deadlock on the same H_PAGE_BUSY bit. * * Interrupts must also be off for the duration of the * mm_is_thread_local test and update, to prevent preempt running the * mm on another CPU (XXX: this may be racy vs kthread_use_mm). */ - local_irq_save(flags); + powerpc_local_irq_pmu_save(flags); /* Is that local to this CPU ? */ if (mm_is_thread_local(mm)) @@ -1820,7 +1782,7 @@ static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea, mm_ctx_user_psize(&mm->context), pte_val(*ptep)); - local_irq_restore(flags); + powerpc_local_irq_pmu_restore(flags); } /* diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c index ea8f83afb0ae..3bc0eb21b2a0 100644 --- a/arch/powerpc/mm/book3s64/hugetlbpage.c +++ b/arch/powerpc/mm/book3s64/hugetlbpage.c @@ -150,7 +150,7 @@ void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr set_huge_pte_at(vma->vm_mm, addr, ptep, pte); } -void __init hugetlbpage_init_default(void) +void __init hugetlbpage_init_defaultsize(void) { /* Set default large page size. Currently, we pick 16M or 1M * depending on what is available diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 31f4cef3adac..81091b9587f6 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -9,7 +9,6 @@ * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM */ -#include <asm/asm-prototypes.h> #include <asm/interrupt.h> #include <asm/mmu.h> #include <asm/mmu_context.h> diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index eb8ecd7343a9..d53fed4eccbd 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -35,7 +35,6 @@ #include <linux/kfence.h> #include <linux/pkeys.h> -#include <asm/asm-prototypes.h> #include <asm/firmware.h> #include <asm/interrupt.h> #include <asm/page.h> @@ -567,18 +566,24 @@ NOKPROBE_SYMBOL(hash__do_page_fault); static void __bad_page_fault(struct pt_regs *regs, int sig) { int is_write = page_fault_is_write(regs->dsisr); + const char *msg; /* kernel has accessed a bad area */ + if (regs->dar < PAGE_SIZE) + msg = "Kernel NULL pointer dereference"; + else + msg = "Unable to handle kernel data access"; + switch (TRAP(regs)) { case INTERRUPT_DATA_STORAGE: - case INTERRUPT_DATA_SEGMENT: case INTERRUPT_H_DATA_STORAGE: - pr_alert("BUG: %s on %s at 0x%08lx\n", - regs->dar < PAGE_SIZE ? "Kernel NULL pointer dereference" : - "Unable to handle kernel data access", + pr_alert("BUG: %s on %s at 0x%08lx\n", msg, is_write ? "write" : "read", regs->dar); break; + case INTERRUPT_DATA_SEGMENT: + pr_alert("BUG: %s at 0x%08lx\n", msg, regs->dar); + break; case INTERRUPT_INST_STORAGE: case INTERRUPT_INST_SEGMENT: pr_alert("BUG: Unable to handle kernel instruction fetch%s", diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index ddead41e2194..b642a5a8668f 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -664,10 +664,7 @@ static int __init hugetlbpage_init(void) configured = true; } - if (configured) { - if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) - hugetlbpage_init_default(); - } else + if (!configured) pr_info("Failed to initialize. Disabling HugeTLB"); return 0; diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 35f46bf54281..83c0ee9fbf05 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -59,6 +59,7 @@ #include <asm/sections.h> #include <asm/iommu.h> #include <asm/vdso.h> +#include <asm/hugetlb.h> #include <mm/mmu_decl.h> @@ -513,6 +514,9 @@ void __init mmu_early_init_devtree(void) } else hash__early_init_devtree(); + if (IS_ENABLED(CONFIG_HUGETLB_PAGE_SIZE_VARIABLE)) + hugetlbpage_init_defaultsize(); + if (!(cur_cpu_spec->mmu_features & MMU_FTR_HPTE_TABLE) && !(cur_cpu_spec->mmu_features & MMU_FTR_TYPE_RADIX)) panic("kernel does not support any MMU type offered by platform"); diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index cf8770b1a692..f3e4d069e0ba 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -83,13 +83,12 @@ void __init kasan_update_early_region(unsigned long k_start, unsigned long k_end, pte_t pte) { unsigned long k_cur; - phys_addr_t pa = __pa(kasan_early_shadow_page); for (k_cur = k_start; k_cur != k_end; k_cur += PAGE_SIZE) { pmd_t *pmd = pmd_off_k(k_cur); pte_t *ptep = pte_offset_kernel(pmd, k_cur); - if ((pte_val(*ptep) & PTE_RPN_MASK) != pa) + if (pte_page(*ptep) != virt_to_page(lm_alias(kasan_early_shadow_page))) continue; __set_pte_at(&init_mm, k_cur, ptep, pte, 0); diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 9d5f710d2c20..b9b7fefbb64b 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -956,7 +956,9 @@ static int __init parse_numa_properties(void) of_node_put(cpu); } - node_set_online(nid); + /* node_set_online() is an UB if 'nid' is negative */ + if (likely(nid >= 0)) + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); diff --git a/arch/powerpc/mm/pageattr.c b/arch/powerpc/mm/pageattr.c index edea388e9d3f..85753e32a4de 100644 --- a/arch/powerpc/mm/pageattr.c +++ b/arch/powerpc/mm/pageattr.c @@ -15,12 +15,14 @@ #include <asm/pgtable.h> +static pte_basic_t pte_update_delta(pte_t *ptep, unsigned long addr, + unsigned long old, unsigned long new) +{ + return pte_update(&init_mm, addr, ptep, old & ~new, new & ~old, 0); +} + /* - * Updates the attributes of a page in three steps: - * - * 1. take the page_table_lock - * 2. install the new entry with the updated attributes - * 3. flush the TLB + * Updates the attributes of a page atomically. * * This sequence is safe against concurrent updates, and also allows updating the * attributes of a page currently being executed or accessed. @@ -28,41 +30,39 @@ static int change_page_attr(pte_t *ptep, unsigned long addr, void *data) { long action = (long)data; - pte_t pte; - spin_lock(&init_mm.page_table_lock); - - pte = ptep_get(ptep); - - /* modify the PTE bits as desired, then apply */ + /* modify the PTE bits as desired */ switch (action) { case SET_MEMORY_RO: - pte = pte_wrprotect(pte); + /* Don't clear DIRTY bit */ + pte_update_delta(ptep, addr, _PAGE_KERNEL_RW & ~_PAGE_DIRTY, _PAGE_KERNEL_RO); break; case SET_MEMORY_RW: - pte = pte_mkwrite(pte_mkdirty(pte)); + pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_RW); break; case SET_MEMORY_NX: - pte = pte_exprotect(pte); + pte_update_delta(ptep, addr, _PAGE_KERNEL_ROX, _PAGE_KERNEL_RO); break; case SET_MEMORY_X: - pte = pte_mkexec(pte); + pte_update_delta(ptep, addr, _PAGE_KERNEL_RO, _PAGE_KERNEL_ROX); + break; + case SET_MEMORY_NP: + pte_update(&init_mm, addr, ptep, _PAGE_PRESENT, 0, 0); + break; + case SET_MEMORY_P: + pte_update(&init_mm, addr, ptep, 0, _PAGE_PRESENT, 0); break; default: WARN_ON_ONCE(1); break; } - pte_update(&init_mm, addr, ptep, ~0UL, pte_val(pte), 0); - /* See ptesync comment in radix__set_pte_at() */ if (radix_enabled()) asm volatile("ptesync": : :"memory"); flush_tlb_kernel_range(addr, addr + PAGE_SIZE); - spin_unlock(&init_mm.page_table_lock); - return 0; } @@ -96,36 +96,3 @@ int change_memory_attr(unsigned long addr, int numpages, long action) return apply_to_existing_page_range(&init_mm, start, size, change_page_attr, (void *)action); } - -/* - * Set the attributes of a page: - * - * This function is used by PPC32 at the end of init to set final kernel memory - * protection. It includes changing the maping of the page it is executing from - * and data pages it is using. - */ -static int set_page_attr(pte_t *ptep, unsigned long addr, void *data) -{ - pgprot_t prot = __pgprot((unsigned long)data); - - spin_lock(&init_mm.page_table_lock); - - set_pte_at(&init_mm, addr, ptep, pte_modify(*ptep, prot)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); - - spin_unlock(&init_mm.page_table_lock); - - return 0; -} - -int set_memory_attr(unsigned long addr, int numpages, pgprot_t prot) -{ - unsigned long start = ALIGN_DOWN(addr, PAGE_SIZE); - unsigned long sz = numpages * PAGE_SIZE; - - if (numpages <= 0) - return 0; - - return apply_to_existing_page_range(&init_mm, start, sz, set_page_attr, - (void *)pgprot_val(prot)); -} diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 906e4e4328b2..a56ade39dc68 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -135,10 +135,12 @@ void mark_initmem_nx(void) unsigned long numpages = PFN_UP((unsigned long)_einittext) - PFN_DOWN((unsigned long)_sinittext); - if (v_block_mapped((unsigned long)_sinittext)) + if (v_block_mapped((unsigned long)_sinittext)) { mmu_mark_initmem_nx(); - else - set_memory_attr((unsigned long)_sinittext, numpages, PAGE_KERNEL); + } else { + set_memory_nx((unsigned long)_sinittext, numpages); + set_memory_rw((unsigned long)_sinittext, numpages); + } } #ifdef CONFIG_STRICT_KERNEL_RWX @@ -146,24 +148,23 @@ void mark_rodata_ro(void) { unsigned long numpages; + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX) && mmu_has_feature(MMU_FTR_HPTE_TABLE)) + pr_warn("This platform has HASH MMU, STRICT_MODULE_RWX won't work\n"); + if (v_block_mapped((unsigned long)_stext + 1)) { mmu_mark_rodata_ro(); ptdump_check_wx(); return; } - numpages = PFN_UP((unsigned long)_etext) - - PFN_DOWN((unsigned long)_stext); - - set_memory_attr((unsigned long)_stext, numpages, PAGE_KERNEL_ROX); /* - * mark .rodata as read only. Use __init_begin rather than __end_rodata - * to cover NOTES and EXCEPTION_TABLE. + * mark .text and .rodata as read only. Use __init_begin rather than + * __end_rodata to cover NOTES and EXCEPTION_TABLE. */ numpages = PFN_UP((unsigned long)__init_begin) - - PFN_DOWN((unsigned long)__start_rodata); + PFN_DOWN((unsigned long)_stext); - set_memory_attr((unsigned long)__start_rodata, numpages, PAGE_KERNEL_RO); + set_memory_ro((unsigned long)_stext, numpages); // mark_initmem_nx() should have already run by now ptdump_check_wx(); @@ -179,8 +180,8 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) return; if (enable) - set_memory_attr(addr, numpages, PAGE_KERNEL); + set_memory_p(addr, numpages); else - set_memory_attr(addr, numpages, __pgprot(0)); + set_memory_np(addr, numpages); } #endif /* CONFIG_DEBUG_PAGEALLOC */ diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index c7f824d294b2..9a601587836b 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -238,7 +238,10 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64 static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r) { - struct hash_pte ptes[4]; + struct { + unsigned long v; + unsigned long r; + } ptes[4]; unsigned long vsid, vpn, hash, hpte_group, want_v; int i, j, ssize = mmu_kernel_ssize; long lpar_rc = 0; diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h index b20a2a83a6e7..979701d360da 100644 --- a/arch/powerpc/net/bpf_jit.h +++ b/arch/powerpc/net/bpf_jit.h @@ -27,21 +27,21 @@ #define PPC_JMP(dest) \ do { \ long offset = (long)(dest) - (ctx->idx * 4); \ - if (!is_offset_in_branch_range(offset)) { \ + if ((dest) != 0 && !is_offset_in_branch_range(offset)) { \ pr_err_ratelimited("Branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ return -ERANGE; \ } \ EMIT(PPC_RAW_BRANCH(offset)); \ } while (0) -/* blr; (unconditional 'branch' with link) to absolute address */ -#define PPC_BL_ABS(dest) EMIT(PPC_INST_BL | \ - (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc)) +/* bl (unconditional 'branch' with link) */ +#define PPC_BL(dest) EMIT(PPC_INST_BL | (((dest) - (unsigned long)(image + ctx->idx)) & 0x03fffffc)) + /* "cond" here covers BO:BI fields. */ #define PPC_BCC_SHORT(cond, dest) \ do { \ long offset = (long)(dest) - (ctx->idx * 4); \ - if (!is_offset_in_cond_branch_range(offset)) { \ + if ((dest) != 0 && !is_offset_in_cond_branch_range(offset)) { \ pr_err_ratelimited("Conditional branch offset 0x%lx (@%u) out of range\n", offset, ctx->idx); \ return -ERANGE; \ } \ @@ -59,10 +59,7 @@ EMIT(PPC_RAW_ORI(d, d, IMM_L(i))); \ } } while(0) -#ifdef CONFIG_PPC32 -#define PPC_EX32(r, i) EMIT(PPC_RAW_LI((r), (i) < 0 ? -1 : 0)) -#endif - +#ifdef CONFIG_PPC64 #define PPC_LI64(d, i) do { \ if ((long)(i) >= -2147483648 && \ (long)(i) < 2147483648) \ @@ -85,11 +82,6 @@ EMIT(PPC_RAW_ORI(d, d, (uintptr_t)(i) & \ 0xffff)); \ } } while (0) - -#ifdef CONFIG_PPC64 -#define PPC_FUNC_ADDR(d,i) do { PPC_LI64(d, i); } while(0) -#else -#define PPC_FUNC_ADDR(d,i) do { PPC_LI32(d, i); } while(0) #endif /* @@ -127,15 +119,6 @@ #define SEEN_FUNC 0x20000000 /* might call external helpers */ #define SEEN_TAILCALL 0x40000000 /* uses tail calls */ -#define SEEN_VREG_MASK 0x1ff80000 /* Volatile registers r3-r12 */ -#define SEEN_NVREG_MASK 0x0003ffff /* Non volatile registers r14-r31 */ - -#ifdef CONFIG_PPC64 -extern const int b2p[MAX_BPF_JIT_REG + 2]; -#else -extern const int b2p[MAX_BPF_JIT_REG + 1]; -#endif - struct codegen_context { /* * This is used to track register usage as well @@ -149,10 +132,13 @@ struct codegen_context { unsigned int seen; unsigned int idx; unsigned int stack_size; - int b2p[ARRAY_SIZE(b2p)]; + int b2p[MAX_BPF_JIT_REG + 2]; unsigned int exentry_idx; + unsigned int alt_exit_addr; }; +#define bpf_to_ppc(r) (ctx->b2p[r]) + #ifdef CONFIG_PPC32 #define BPF_FIXUP_LEN 3 /* Three instructions => 12 bytes */ #else @@ -180,12 +166,14 @@ static inline void bpf_clear_seen_register(struct codegen_context *ctx, int i) ctx->seen &= ~(1 << (31 - i)); } -void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func); +void bpf_jit_init_reg_mapping(struct codegen_context *ctx); +int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func); int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *ctx, u32 *addrs, int pass); void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx); void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx); void bpf_jit_realloc_regs(struct codegen_context *ctx); +int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr); int bpf_add_extable_entry(struct bpf_prog *fp, u32 *image, int pass, struct codegen_context *ctx, int insn_idx, int jmp_off, int dst_reg); diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h deleted file mode 100644 index b63b35e45e55..000000000000 --- a/arch/powerpc/net/bpf_jit64.h +++ /dev/null @@ -1,91 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * bpf_jit64.h: BPF JIT compiler for PPC64 - * - * Copyright 2016 Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> - * IBM Corporation - */ -#ifndef _BPF_JIT64_H -#define _BPF_JIT64_H - -#include "bpf_jit.h" - -/* - * Stack layout: - * Ensure the top half (upto local_tmp_var) stays consistent - * with our redzone usage. - * - * [ prev sp ] <------------- - * [ nv gpr save area ] 5*8 | - * [ tail_call_cnt ] 8 | - * [ local_tmp_var ] 16 | - * fp (r31) --> [ ebpf stack space ] upto 512 | - * [ frame header ] 32/112 | - * sp (r1) ---> [ stack pointer ] -------------- - */ - -/* for gpr non volatile registers BPG_REG_6 to 10 */ -#define BPF_PPC_STACK_SAVE (5*8) -/* for bpf JIT code internal usage */ -#define BPF_PPC_STACK_LOCALS 24 -/* stack frame excluding BPF stack, ensure this is quadword aligned */ -#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ - BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) - -#ifndef __ASSEMBLY__ - -/* BPF register usage */ -#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) -#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) - -/* BPF to ppc register mappings */ -const int b2p[MAX_BPF_JIT_REG + 2] = { - /* function return value */ - [BPF_REG_0] = 8, - /* function arguments */ - [BPF_REG_1] = 3, - [BPF_REG_2] = 4, - [BPF_REG_3] = 5, - [BPF_REG_4] = 6, - [BPF_REG_5] = 7, - /* non volatile registers */ - [BPF_REG_6] = 27, - [BPF_REG_7] = 28, - [BPF_REG_8] = 29, - [BPF_REG_9] = 30, - /* frame pointer aka BPF_REG_10 */ - [BPF_REG_FP] = 31, - /* eBPF jit internal registers */ - [BPF_REG_AX] = 2, - [TMP_REG_1] = 9, - [TMP_REG_2] = 10 -}; - -/* PPC NVR range -- update this if we ever use NVRs below r27 */ -#define BPF_PPC_NVR_MIN 27 - -/* - * WARNING: These can use TMP_REG_2 if the offset is not at word boundary, - * so ensure that it isn't in use already. - */ -#define PPC_BPF_LL(r, base, i) do { \ - if ((i) % 4) { \ - EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\ - EMIT(PPC_RAW_LDX(r, base, \ - b2p[TMP_REG_2])); \ - } else \ - EMIT(PPC_RAW_LD(r, base, i)); \ - } while(0) -#define PPC_BPF_STL(r, base, i) do { \ - if ((i) % 4) { \ - EMIT(PPC_RAW_LI(b2p[TMP_REG_2], (i)));\ - EMIT(PPC_RAW_STDX(r, base, \ - b2p[TMP_REG_2])); \ - } else \ - EMIT(PPC_RAW_STD(r, base, i)); \ - } while(0) -#define PPC_BPF_STLU(r, base, i) do { EMIT(PPC_RAW_STDU(r, base, i)); } while(0) - -#endif /* !__ASSEMBLY__ */ - -#endif diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index a4f4d347e6bd..427185256216 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -59,7 +59,9 @@ static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, */ tmp_idx = ctx->idx; ctx->idx = addrs[i] / 4; - bpf_jit_emit_func_call_rel(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr); + if (ret) + return ret; /* * Restore ctx->idx here. This is safe as the length @@ -70,13 +72,13 @@ static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, tmp_idx = ctx->idx; ctx->idx = addrs[i] / 4; #ifdef CONFIG_PPC32 - PPC_LI32(ctx->b2p[insn[i].dst_reg] - 1, (u32)insn[i + 1].imm); - PPC_LI32(ctx->b2p[insn[i].dst_reg], (u32)insn[i].imm); + PPC_LI32(bpf_to_ppc(insn[i].dst_reg) - 1, (u32)insn[i + 1].imm); + PPC_LI32(bpf_to_ppc(insn[i].dst_reg), (u32)insn[i].imm); for (j = ctx->idx - addrs[i] / 4; j < 4; j++) EMIT(PPC_RAW_NOP()); #else func_addr = ((u64)(u32)insn[i].imm) | (((u64)(u32)insn[i + 1].imm) << 32); - PPC_LI64(b2p[insn[i].dst_reg], func_addr); + PPC_LI64(bpf_to_ppc(insn[i].dst_reg), func_addr); /* overwrite rest with nops */ for (j = ctx->idx - addrs[i] / 4; j < 5; j++) EMIT(PPC_RAW_NOP()); @@ -89,6 +91,22 @@ static int bpf_jit_fixup_addresses(struct bpf_prog *fp, u32 *image, return 0; } +int bpf_jit_emit_exit_insn(u32 *image, struct codegen_context *ctx, int tmp_reg, long exit_addr) +{ + if (!exit_addr || is_offset_in_branch_range(exit_addr - (ctx->idx * 4))) { + PPC_JMP(exit_addr); + } else if (ctx->alt_exit_addr) { + if (WARN_ON(!is_offset_in_branch_range((long)ctx->alt_exit_addr - (ctx->idx * 4)))) + return -1; + PPC_JMP(ctx->alt_exit_addr); + } else { + ctx->alt_exit_addr = ctx->idx * 4; + bpf_jit_build_epilogue(image, ctx); + } + + return 0; +} + struct powerpc64_jit_data { struct bpf_binary_header *header; u32 *addrs; @@ -161,7 +179,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) } memset(&cgctx, 0, sizeof(struct codegen_context)); - memcpy(cgctx.b2p, b2p, sizeof(cgctx.b2p)); + bpf_jit_init_reg_mapping(&cgctx); /* Make sure that the stack is quadword aligned. */ cgctx.stack_size = round_up(fp->aux->stack_depth, 16); @@ -177,8 +195,10 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) * If we have seen a tail call, we need a second pass. * This is because bpf_jit_emit_common_epilogue() is called * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen. + * We also need a second pass if we ended up with too large + * a program so as to ensure BPF_EXIT branches are in range. */ - if (cgctx.seen & SEEN_TAILCALL) { + if (cgctx.seen & SEEN_TAILCALL || !is_offset_in_branch_range((long)cgctx.idx * 4)) { cgctx.idx = 0; if (bpf_jit_build_body(fp, 0, &cgctx, addrs, 0)) { fp = org_fp; @@ -193,6 +213,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp) * calculate total size from idx. */ bpf_jit_build_prologue(0, &cgctx); + addrs[fp->len] = cgctx.idx * 4; bpf_jit_build_epilogue(0, &cgctx); fixup_len = fp->aux->num_exentries * BPF_FIXUP_LEN * 4; @@ -233,6 +254,7 @@ skip_init_ctx: for (pass = 1; pass < 3; pass++) { /* Now build the prologue, body code & epilogue for real. */ cgctx.idx = 0; + cgctx.alt_exit_addr = 0; bpf_jit_build_prologue(code_base, &cgctx); if (bpf_jit_build_body(fp, code_base, &cgctx, addrs, pass)) { bpf_jit_binary_free(bpf_hdr); diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index cf8dd8aea386..e46ed1e8c6ca 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -33,40 +33,38 @@ /* stack frame, ensure this is quadword aligned */ #define BPF_PPC_STACKFRAME(ctx) (STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_SAVE + (ctx)->stack_size) +#define PPC_EX32(r, i) EMIT(PPC_RAW_LI((r), (i) < 0 ? -1 : 0)) + +/* PPC NVR range -- update this if we ever use NVRs below r17 */ +#define BPF_PPC_NVR_MIN _R17 +#define BPF_PPC_TC _R16 + /* BPF register usage */ -#define TMP_REG (MAX_BPF_JIT_REG + 0) +#define TMP_REG (MAX_BPF_JIT_REG + 0) /* BPF to ppc register mappings */ -const int b2p[MAX_BPF_JIT_REG + 1] = { +void bpf_jit_init_reg_mapping(struct codegen_context *ctx) +{ /* function return value */ - [BPF_REG_0] = 12, + ctx->b2p[BPF_REG_0] = _R12; /* function arguments */ - [BPF_REG_1] = 4, - [BPF_REG_2] = 6, - [BPF_REG_3] = 8, - [BPF_REG_4] = 10, - [BPF_REG_5] = 22, + ctx->b2p[BPF_REG_1] = _R4; + ctx->b2p[BPF_REG_2] = _R6; + ctx->b2p[BPF_REG_3] = _R8; + ctx->b2p[BPF_REG_4] = _R10; + ctx->b2p[BPF_REG_5] = _R22; /* non volatile registers */ - [BPF_REG_6] = 24, - [BPF_REG_7] = 26, - [BPF_REG_8] = 28, - [BPF_REG_9] = 30, + ctx->b2p[BPF_REG_6] = _R24; + ctx->b2p[BPF_REG_7] = _R26; + ctx->b2p[BPF_REG_8] = _R28; + ctx->b2p[BPF_REG_9] = _R30; /* frame pointer aka BPF_REG_10 */ - [BPF_REG_FP] = 18, + ctx->b2p[BPF_REG_FP] = _R18; /* eBPF jit internal registers */ - [BPF_REG_AX] = 20, - [TMP_REG] = 31, /* 32 bits */ -}; - -static int bpf_to_ppc(struct codegen_context *ctx, int reg) -{ - return ctx->b2p[reg]; + ctx->b2p[BPF_REG_AX] = _R20; + ctx->b2p[TMP_REG] = _R31; /* 32 bits */ } -/* PPC NVR range -- update this if we ever use NVRs below r17 */ -#define BPF_PPC_NVR_MIN 17 -#define BPF_PPC_TC 16 - static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) { if ((reg >= BPF_PPC_NVR_MIN && reg < 32) || reg == BPF_PPC_TC) @@ -77,14 +75,22 @@ static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) return BPF_PPC_STACKFRAME(ctx) - 4; } +#define SEEN_VREG_MASK 0x1ff80000 /* Volatile registers r3-r12 */ +#define SEEN_NVREG_FULL_MASK 0x0003ffff /* Non volatile registers r14-r31 */ +#define SEEN_NVREG_TEMP_MASK 0x00001e01 /* BPF_REG_5, BPF_REG_AX, TMP_REG */ + void bpf_jit_realloc_regs(struct codegen_context *ctx) { + unsigned int nvreg_mask; + if (ctx->seen & SEEN_FUNC) - return; + nvreg_mask = SEEN_NVREG_TEMP_MASK; + else + nvreg_mask = SEEN_NVREG_FULL_MASK; - while (ctx->seen & SEEN_NVREG_MASK && + while (ctx->seen & nvreg_mask && (ctx->seen & SEEN_VREG_MASK) != SEEN_VREG_MASK) { - int old = 32 - fls(ctx->seen & (SEEN_NVREG_MASK & 0xaaaaaaab)); + int old = 32 - fls(ctx->seen & (nvreg_mask & 0xaaaaaaab)); int new = 32 - fls(~ctx->seen & (SEEN_VREG_MASK & 0xaaaaaaaa)); int i; @@ -108,8 +114,8 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) int i; /* First arg comes in as a 32 bits pointer. */ - EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_1), _R3)); - EMIT(PPC_RAW_LI(bpf_to_ppc(ctx, BPF_REG_1) - 1, 0)); + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_1), _R3)); + EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_1) - 1, 0)); EMIT(PPC_RAW_STWU(_R1, _R1, -BPF_PPC_STACKFRAME(ctx))); /* @@ -118,7 +124,7 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) * invoked through a tail call. */ if (ctx->seen & SEEN_TAILCALL) - EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_1) - 1, _R1, + EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_1) - 1, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); else EMIT(PPC_RAW_NOP()); @@ -140,15 +146,15 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_STW(i, _R1, bpf_jit_stack_offsetof(ctx, i))); /* If needed retrieve arguments 9 and 10, ie 5th 64 bits arg.*/ - if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_5))) { - EMIT(PPC_RAW_LWZ(bpf_to_ppc(ctx, BPF_REG_5) - 1, _R1, BPF_PPC_STACKFRAME(ctx)) + 8); - EMIT(PPC_RAW_LWZ(bpf_to_ppc(ctx, BPF_REG_5), _R1, BPF_PPC_STACKFRAME(ctx)) + 12); + if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_5))) { + EMIT(PPC_RAW_LWZ(bpf_to_ppc(BPF_REG_5) - 1, _R1, BPF_PPC_STACKFRAME(ctx)) + 8); + EMIT(PPC_RAW_LWZ(bpf_to_ppc(BPF_REG_5), _R1, BPF_PPC_STACKFRAME(ctx)) + 12); } /* Setup frame pointer to point to the bpf stack area */ - if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_FP))) { - EMIT(PPC_RAW_LI(bpf_to_ppc(ctx, BPF_REG_FP) - 1, 0)); - EMIT(PPC_RAW_ADDI(bpf_to_ppc(ctx, BPF_REG_FP), _R1, + if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP))) { + EMIT(PPC_RAW_LI(bpf_to_ppc(BPF_REG_FP) - 1, 0)); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1, STACK_FRAME_MIN_SIZE + ctx->stack_size)); } @@ -168,7 +174,7 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) { - EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(ctx, BPF_REG_0))); + EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); bpf_jit_emit_common_epilogue(image, ctx); @@ -185,12 +191,12 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) EMIT(PPC_RAW_BLR()); } -void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) +int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) { s32 rel = (s32)func - (s32)(image + ctx->idx); if (image && rel < 0x2000000 && rel >= -0x2000000) { - PPC_BL_ABS(func); + PPC_BL(func); EMIT(PPC_RAW_NOP()); EMIT(PPC_RAW_NOP()); EMIT(PPC_RAW_NOP()); @@ -201,6 +207,8 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun EMIT(PPC_RAW_MTCTR(_R0)); EMIT(PPC_RAW_BCTRL()); } + + return 0; } static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) @@ -211,8 +219,8 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o * r5-r6/BPF_REG_2 - pointer to bpf_array * r7-r8/BPF_REG_3 - index in bpf_array */ - int b2p_bpf_array = bpf_to_ppc(ctx, BPF_REG_2); - int b2p_index = bpf_to_ppc(ctx, BPF_REG_3); + int b2p_bpf_array = bpf_to_ppc(BPF_REG_2); + int b2p_index = bpf_to_ppc(BPF_REG_3); /* * if (index >= array->map.max_entries) @@ -221,7 +229,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o EMIT(PPC_RAW_LWZ(_R0, b2p_bpf_array, offsetof(struct bpf_array, map.max_entries))); EMIT(PPC_RAW_CMPLW(b2p_index, _R0)); EMIT(PPC_RAW_LWZ(_R0, _R1, bpf_jit_stack_offsetof(ctx, BPF_PPC_TC))); - PPC_BCC(COND_GE, out); + PPC_BCC_SHORT(COND_GE, out); /* * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) @@ -230,7 +238,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT)); /* tail_call_cnt++; */ EMIT(PPC_RAW_ADDIC(_R0, _R0, 1)); - PPC_BCC(COND_GE, out); + PPC_BCC_SHORT(COND_GE, out); /* prog = array->ptrs[index]; */ EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); @@ -243,7 +251,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o * goto out; */ EMIT(PPC_RAW_CMPLWI(_R3, 0)); - PPC_BCC(COND_EQ, out); + PPC_BCC_SHORT(COND_EQ, out); /* goto *(prog->bpf_func + prologue_size); */ EMIT(PPC_RAW_LWZ(_R3, _R3, offsetof(struct bpf_prog, bpf_func))); @@ -258,7 +266,7 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o EMIT(PPC_RAW_MTCTR(_R3)); - EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(ctx, BPF_REG_1))); + EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_1))); /* tear restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); @@ -282,11 +290,11 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * for (i = 0; i < flen; i++) { u32 code = insn[i].code; - u32 dst_reg = bpf_to_ppc(ctx, insn[i].dst_reg); + u32 dst_reg = bpf_to_ppc(insn[i].dst_reg); u32 dst_reg_h = dst_reg - 1; - u32 src_reg = bpf_to_ppc(ctx, insn[i].src_reg); + u32 src_reg = bpf_to_ppc(insn[i].src_reg); u32 src_reg_h = src_reg - 1; - u32 tmp_reg = bpf_to_ppc(ctx, TMP_REG); + u32 tmp_reg = bpf_to_ppc(TMP_REG); u32 size = BPF_SIZE(code); s16 off = insn[i].off; s32 imm = insn[i].imm; @@ -834,7 +842,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * if (BPF_MODE(code) == BPF_PROBE_MEM) { PPC_LI32(_R0, TASK_SIZE - off); EMIT(PPC_RAW_CMPLW(src_reg, _R0)); - PPC_BCC(COND_GT, (ctx->idx + 5) * 4); + PPC_BCC_SHORT(COND_GT, (ctx->idx + 4) * 4); EMIT(PPC_RAW_LI(dst_reg, 0)); /* * For BPF_DW case, "li reg_h,0" would be needed when @@ -929,8 +937,11 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * * the epilogue. If we _are_ the last instruction, * we'll just fall through to the epilogue. */ - if (i != flen - 1) - PPC_JMP(exit_addr); + if (i != flen - 1) { + ret = bpf_jit_emit_exit_insn(image, ctx, _R0, exit_addr); + if (ret) + return ret; + } /* else fall through to the epilogue */ break; @@ -945,15 +956,17 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * if (ret < 0) return ret; - if (bpf_is_seen_register(ctx, bpf_to_ppc(ctx, BPF_REG_5))) { - EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_5) - 1, _R1, 8)); - EMIT(PPC_RAW_STW(bpf_to_ppc(ctx, BPF_REG_5), _R1, 12)); + if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_5))) { + EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_5) - 1, _R1, 8)); + EMIT(PPC_RAW_STW(bpf_to_ppc(BPF_REG_5), _R1, 12)); } - bpf_jit_emit_func_call_rel(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr); + if (ret) + return ret; - EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_0) - 1, _R3)); - EMIT(PPC_RAW_MR(bpf_to_ppc(ctx, BPF_REG_0), _R4)); + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_0) - 1, _R3)); + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_0), _R4)); break; /* diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index e1e8c934308a..585f257da045 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -17,7 +17,60 @@ #include <linux/bpf.h> #include <asm/security_features.h> -#include "bpf_jit64.h" +#include "bpf_jit.h" + +/* + * Stack layout: + * Ensure the top half (upto local_tmp_var) stays consistent + * with our redzone usage. + * + * [ prev sp ] <------------- + * [ nv gpr save area ] 5*8 | + * [ tail_call_cnt ] 8 | + * [ local_tmp_var ] 16 | + * fp (r31) --> [ ebpf stack space ] upto 512 | + * [ frame header ] 32/112 | + * sp (r1) ---> [ stack pointer ] -------------- + */ + +/* for gpr non volatile registers BPG_REG_6 to 10 */ +#define BPF_PPC_STACK_SAVE (5*8) +/* for bpf JIT code internal usage */ +#define BPF_PPC_STACK_LOCALS 24 +/* stack frame excluding BPF stack, ensure this is quadword aligned */ +#define BPF_PPC_STACKFRAME (STACK_FRAME_MIN_SIZE + \ + BPF_PPC_STACK_LOCALS + BPF_PPC_STACK_SAVE) + +/* BPF register usage */ +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) + +/* BPF to ppc register mappings */ +void bpf_jit_init_reg_mapping(struct codegen_context *ctx) +{ + /* function return value */ + ctx->b2p[BPF_REG_0] = _R8; + /* function arguments */ + ctx->b2p[BPF_REG_1] = _R3; + ctx->b2p[BPF_REG_2] = _R4; + ctx->b2p[BPF_REG_3] = _R5; + ctx->b2p[BPF_REG_4] = _R6; + ctx->b2p[BPF_REG_5] = _R7; + /* non volatile registers */ + ctx->b2p[BPF_REG_6] = _R27; + ctx->b2p[BPF_REG_7] = _R28; + ctx->b2p[BPF_REG_8] = _R29; + ctx->b2p[BPF_REG_9] = _R30; + /* frame pointer aka BPF_REG_10 */ + ctx->b2p[BPF_REG_FP] = _R31; + /* eBPF jit internal registers */ + ctx->b2p[BPF_REG_AX] = _R12; + ctx->b2p[TMP_REG_1] = _R9; + ctx->b2p[TMP_REG_2] = _R10; +} + +/* PPC NVR range -- update this if we ever use NVRs below r27 */ +#define BPF_PPC_NVR_MIN _R27 static inline bool bpf_has_stack_frame(struct codegen_context *ctx) { @@ -27,7 +80,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * - the bpf program uses its stack area * The latter condition is deduced from the usage of BPF_REG_FP */ - return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, b2p[BPF_REG_FP]); + return ctx->seen & SEEN_FUNC || bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP)); } /* @@ -73,22 +126,23 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) { int i; + if (__is_defined(PPC64_ELF_ABI_v2)) + EMIT(PPC_RAW_LD(_R2, _R13, offsetof(struct paca_struct, kernel_toc))); + /* * Initialize tail_call_cnt if we do tail calls. * Otherwise, put in NOPs so that it can be skipped when we are * invoked through a tail call. */ if (ctx->seen & SEEN_TAILCALL) { - EMIT(PPC_RAW_LI(b2p[TMP_REG_1], 0)); + EMIT(PPC_RAW_LI(bpf_to_ppc(TMP_REG_1), 0)); /* this goes in the redzone */ - PPC_BPF_STL(b2p[TMP_REG_1], 1, -(BPF_PPC_STACK_SAVE + 8)); + EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, -(BPF_PPC_STACK_SAVE + 8))); } else { EMIT(PPC_RAW_NOP()); EMIT(PPC_RAW_NOP()); } -#define BPF_TAILCALL_PROLOGUE_SIZE 8 - if (bpf_has_stack_frame(ctx)) { /* * We need a stack frame, but we don't necessarily need to @@ -96,10 +150,10 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) */ if (ctx->seen & SEEN_FUNC) { EMIT(PPC_RAW_MFLR(_R0)); - PPC_BPF_STL(0, 1, PPC_LR_STKOFF); + EMIT(PPC_RAW_STD(_R0, _R1, PPC_LR_STKOFF)); } - PPC_BPF_STLU(1, 1, -(BPF_PPC_STACKFRAME + ctx->stack_size)); + EMIT(PPC_RAW_STDU(_R1, _R1, -(BPF_PPC_STACKFRAME + ctx->stack_size))); } /* @@ -108,12 +162,12 @@ void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) * in the protected zone below the previous stack frame */ for (i = BPF_REG_6; i <= BPF_REG_10; i++) - if (bpf_is_seen_register(ctx, b2p[i])) - PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); + if (bpf_is_seen_register(ctx, bpf_to_ppc(i))) + EMIT(PPC_RAW_STD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i)))); /* Setup frame pointer to point to the bpf stack area */ - if (bpf_is_seen_register(ctx, b2p[BPF_REG_FP])) - EMIT(PPC_RAW_ADDI(b2p[BPF_REG_FP], 1, + if (bpf_is_seen_register(ctx, bpf_to_ppc(BPF_REG_FP))) + EMIT(PPC_RAW_ADDI(bpf_to_ppc(BPF_REG_FP), _R1, STACK_FRAME_MIN_SIZE + ctx->stack_size)); } @@ -123,15 +177,15 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx /* Restore NVRs */ for (i = BPF_REG_6; i <= BPF_REG_10; i++) - if (bpf_is_seen_register(ctx, b2p[i])) - PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); + if (bpf_is_seen_register(ctx, bpf_to_ppc(i))) + EMIT(PPC_RAW_LD(bpf_to_ppc(i), _R1, bpf_jit_stack_offsetof(ctx, bpf_to_ppc(i)))); /* Tear down our stack frame */ if (bpf_has_stack_frame(ctx)) { - EMIT(PPC_RAW_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size)); + EMIT(PPC_RAW_ADDI(_R1, _R1, BPF_PPC_STACKFRAME + ctx->stack_size)); if (ctx->seen & SEEN_FUNC) { - PPC_BPF_LL(0, 1, PPC_LR_STKOFF); - EMIT(PPC_RAW_MTLR(0)); + EMIT(PPC_RAW_LD(_R0, _R1, PPC_LR_STKOFF)); + EMIT(PPC_RAW_MTLR(_R0)); } } } @@ -141,42 +195,45 @@ void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) bpf_jit_emit_common_epilogue(image, ctx); /* Move result to r3 */ - EMIT(PPC_RAW_MR(3, b2p[BPF_REG_0])); + EMIT(PPC_RAW_MR(_R3, bpf_to_ppc(BPF_REG_0))); EMIT(PPC_RAW_BLR()); } -static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, - u64 func) +static int bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, u64 func) { -#ifdef PPC64_ELF_ABI_v1 - /* func points to the function descriptor */ - PPC_LI64(b2p[TMP_REG_2], func); - /* Load actual entry point from function descriptor */ - PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); - /* ... and move it to CTR */ - EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1])); - /* - * Load TOC from function descriptor at offset 8. - * We can clobber r2 since we get called through a - * function pointer (so caller will save/restore r2) - * and since we don't use a TOC ourself. - */ - PPC_BPF_LL(2, b2p[TMP_REG_2], 8); -#else - /* We can clobber r12 */ - PPC_FUNC_ADDR(12, func); - EMIT(PPC_RAW_MTCTR(12)); -#endif + unsigned long func_addr = func ? ppc_function_entry((void *)func) : 0; + long reladdr; + + if (WARN_ON_ONCE(!core_kernel_text(func_addr))) + return -EINVAL; + + reladdr = func_addr - kernel_toc_addr(); + if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) { + pr_err("eBPF: address of %ps out of range of kernel_toc.\n", (void *)func); + return -ERANGE; + } + + EMIT(PPC_RAW_ADDIS(_R12, _R2, PPC_HA(reladdr))); + EMIT(PPC_RAW_ADDI(_R12, _R12, PPC_LO(reladdr))); + EMIT(PPC_RAW_MTCTR(_R12)); EMIT(PPC_RAW_BCTRL()); + + return 0; } -void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) +int bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 func) { unsigned int i, ctx_idx = ctx->idx; + if (WARN_ON_ONCE(func && is_module_text_address(func))) + return -EINVAL; + + /* skip past descriptor if elf v1 */ + func += FUNCTION_DESCR_SIZE; + /* Load function address into r12 */ - PPC_LI64(12, func); + PPC_LI64(_R12, func); /* For bpf-to-bpf function calls, the callee's address is unknown * until the last extra pass. As seen above, we use PPC_LI64() to @@ -191,20 +248,10 @@ void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, u64 fun for (i = ctx->idx - ctx_idx; i < 5; i++) EMIT(PPC_RAW_NOP()); -#ifdef PPC64_ELF_ABI_v1 - /* - * Load TOC from function descriptor at offset 8. - * We can clobber r2 since we get called through a - * function pointer (so caller will save/restore r2) - * and since we don't use a TOC ourself. - */ - PPC_BPF_LL(2, 12, 8); - /* Load actual entry point from function descriptor */ - PPC_BPF_LL(12, 12, 0); -#endif - - EMIT(PPC_RAW_MTCTR(12)); + EMIT(PPC_RAW_MTCTR(_R12)); EMIT(PPC_RAW_BCTRL()); + + return 0; } static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 out) @@ -215,54 +262,53 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o * r4/BPF_REG_2 - pointer to bpf_array * r5/BPF_REG_3 - index in bpf_array */ - int b2p_bpf_array = b2p[BPF_REG_2]; - int b2p_index = b2p[BPF_REG_3]; + int b2p_bpf_array = bpf_to_ppc(BPF_REG_2); + int b2p_index = bpf_to_ppc(BPF_REG_3); + int bpf_tailcall_prologue_size = 8; + + if (__is_defined(PPC64_ELF_ABI_v2)) + bpf_tailcall_prologue_size += 4; /* skip past the toc load */ /* * if (index >= array->map.max_entries) * goto out; */ - EMIT(PPC_RAW_LWZ(b2p[TMP_REG_1], b2p_bpf_array, offsetof(struct bpf_array, map.max_entries))); + EMIT(PPC_RAW_LWZ(bpf_to_ppc(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); + EMIT(PPC_RAW_CMPLW(b2p_index, bpf_to_ppc(TMP_REG_1))); + PPC_BCC_SHORT(COND_GE, out); /* * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ - PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); - EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT)); - PPC_BCC(COND_GE, out); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx))); + EMIT(PPC_RAW_CMPLWI(bpf_to_ppc(TMP_REG_1), MAX_TAIL_CALL_CNT)); + PPC_BCC_SHORT(COND_GE, out); /* * tail_call_cnt++; */ - 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)); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), 1)); + EMIT(PPC_RAW_STD(bpf_to_ppc(TMP_REG_1), _R1, bpf_jit_stack_tailcallcnt(ctx))); /* prog = array->ptrs[index]; */ - 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)); + EMIT(PPC_RAW_MULI(bpf_to_ppc(TMP_REG_1), b2p_index, 8)); + EMIT(PPC_RAW_ADD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), b2p_bpf_array)); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_array, ptrs))); /* * if (prog == NULL) * goto out; */ - EMIT(PPC_RAW_CMPLDI(b2p[TMP_REG_1], 0)); - PPC_BCC(COND_EQ, out); + EMIT(PPC_RAW_CMPLDI(bpf_to_ppc(TMP_REG_1), 0)); + PPC_BCC_SHORT(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 */ - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], - FUNCTION_DESCR_SIZE + BPF_TAILCALL_PROLOGUE_SIZE)); -#else - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1], BPF_TAILCALL_PROLOGUE_SIZE)); -#endif - EMIT(PPC_RAW_MTCTR(b2p[TMP_REG_1])); + EMIT(PPC_RAW_LD(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), offsetof(struct bpf_prog, bpf_func))); + EMIT(PPC_RAW_ADDI(bpf_to_ppc(TMP_REG_1), bpf_to_ppc(TMP_REG_1), + FUNCTION_DESCR_SIZE + bpf_tailcall_prologue_size)); + EMIT(PPC_RAW_MTCTR(bpf_to_ppc(TMP_REG_1))); /* tear down stack, restore NVRs, ... */ bpf_jit_emit_common_epilogue(image, ctx); @@ -309,9 +355,11 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * for (i = 0; i < flen; i++) { u32 code = insn[i].code; - u32 dst_reg = b2p[insn[i].dst_reg]; - u32 src_reg = b2p[insn[i].src_reg]; + u32 dst_reg = bpf_to_ppc(insn[i].dst_reg); + u32 src_reg = bpf_to_ppc(insn[i].src_reg); u32 size = BPF_SIZE(code); + u32 tmp1_reg = bpf_to_ppc(TMP_REG_1); + u32 tmp2_reg = bpf_to_ppc(TMP_REG_2); s16 off = insn[i].off; s32 imm = insn[i].imm; bool func_addr_fixed; @@ -362,8 +410,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * } else if (imm >= -32768 && imm < 32768) { EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(imm))); } else { - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_ADD(dst_reg, dst_reg, b2p[TMP_REG_1])); + PPC_LI32(tmp1_reg, imm); + EMIT(PPC_RAW_ADD(dst_reg, dst_reg, tmp1_reg)); } goto bpf_alu32_trunc; case BPF_ALU | BPF_SUB | BPF_K: /* (u32) dst -= (u32) imm */ @@ -373,8 +421,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * } else if (imm > -32768 && imm <= 32768) { EMIT(PPC_RAW_ADDI(dst_reg, dst_reg, IMM_L(-imm))); } else { - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_SUB(dst_reg, dst_reg, b2p[TMP_REG_1])); + PPC_LI32(tmp1_reg, imm); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg)); } goto bpf_alu32_trunc; case BPF_ALU | BPF_MUL | BPF_X: /* (u32) dst *= (u32) src */ @@ -389,32 +437,28 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * if (imm >= -32768 && imm < 32768) EMIT(PPC_RAW_MULI(dst_reg, dst_reg, IMM_L(imm))); else { - PPC_LI32(b2p[TMP_REG_1], imm); + PPC_LI32(tmp1_reg, imm); if (BPF_CLASS(code) == BPF_ALU) - EMIT(PPC_RAW_MULW(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_MULW(dst_reg, dst_reg, tmp1_reg)); else - EMIT(PPC_RAW_MULD(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_MULD(dst_reg, dst_reg, tmp1_reg)); } 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) { - 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])); + EMIT(PPC_RAW_DIVWU(tmp1_reg, dst_reg, src_reg)); + EMIT(PPC_RAW_MULW(tmp1_reg, src_reg, tmp1_reg)); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg)); } else 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) { - 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])); + EMIT(PPC_RAW_DIVDU(tmp1_reg, dst_reg, src_reg)); + EMIT(PPC_RAW_MULD(tmp1_reg, src_reg, tmp1_reg)); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg)); } else EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, src_reg)); break; @@ -433,35 +477,23 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * } } - PPC_LI32(b2p[TMP_REG_1], imm); + PPC_LI32(tmp1_reg, imm); switch (BPF_CLASS(code)) { case BPF_ALU: if (BPF_OP(code) == BPF_MOD) { - 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])); - EMIT(PPC_RAW_SUB(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_DIVWU(tmp2_reg, dst_reg, tmp1_reg)); + EMIT(PPC_RAW_MULW(tmp1_reg, tmp1_reg, tmp2_reg)); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg)); } else - EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_DIVWU(dst_reg, dst_reg, tmp1_reg)); break; case BPF_ALU64: if (BPF_OP(code) == BPF_MOD) { - 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])); - EMIT(PPC_RAW_SUB(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_DIVDU(tmp2_reg, dst_reg, tmp1_reg)); + EMIT(PPC_RAW_MULD(tmp1_reg, tmp1_reg, tmp2_reg)); + EMIT(PPC_RAW_SUB(dst_reg, dst_reg, tmp1_reg)); } else - EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_DIVDU(dst_reg, dst_reg, tmp1_reg)); break; } goto bpf_alu32_trunc; @@ -483,8 +515,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * EMIT(PPC_RAW_ANDI(dst_reg, dst_reg, IMM_L(imm))); else { /* Sign-extended */ - PPC_LI32(b2p[TMP_REG_1], imm); - EMIT(PPC_RAW_AND(dst_reg, dst_reg, b2p[TMP_REG_1])); + PPC_LI32(tmp1_reg, imm); + EMIT(PPC_RAW_AND(dst_reg, dst_reg, tmp1_reg)); } goto bpf_alu32_trunc; case BPF_ALU | BPF_OR | BPF_X: /* dst = (u32) dst | (u32) src */ @@ -495,8 +527,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * 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); - EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_1])); + PPC_LI32(tmp1_reg, imm); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp1_reg)); } else { if (IMM_L(imm)) EMIT(PPC_RAW_ORI(dst_reg, dst_reg, IMM_L(imm))); @@ -512,8 +544,8 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context * 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); - EMIT(PPC_RAW_XOR(dst_reg, dst_reg, b2p[TMP_REG_1])); + PPC_LI32(tmp1_reg, imm); + EMIT(PPC_RAW_XOR(dst_reg, dst_reg, tmp1_reg)); } else { if (IMM_L(imm)) EMIT(PPC_RAW_XORI(dst_reg, dst_reg, IMM_L(imm))); @@ -614,11 +646,11 @@ bpf_alu32_trunc: switch (imm) { case 16: /* Rotate 8 bits left & mask with 0x0000ff00 */ - EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 16, 23)); + EMIT(PPC_RAW_RLWINM(tmp1_reg, dst_reg, 8, 16, 23)); /* Rotate 8 bits right & insert LSB to reg */ - EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 24, 31)); + EMIT(PPC_RAW_RLWIMI(tmp1_reg, dst_reg, 24, 24, 31)); /* Move result back to dst_reg */ - EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); + EMIT(PPC_RAW_MR(dst_reg, tmp1_reg)); break; case 32: /* @@ -626,28 +658,28 @@ bpf_alu32_trunc: * 2 bytes are already in their final position * -- byte 2 and 4 (of bytes 1, 2, 3 and 4) */ - EMIT(PPC_RAW_RLWINM(b2p[TMP_REG_1], dst_reg, 8, 0, 31)); + EMIT(PPC_RAW_RLWINM(tmp1_reg, dst_reg, 8, 0, 31)); /* Rotate 24 bits and insert byte 1 */ - EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 0, 7)); + EMIT(PPC_RAW_RLWIMI(tmp1_reg, dst_reg, 24, 0, 7)); /* Rotate 24 bits and insert byte 3 */ - EMIT(PPC_RAW_RLWIMI(b2p[TMP_REG_1], dst_reg, 24, 16, 23)); - EMIT(PPC_RAW_MR(dst_reg, b2p[TMP_REG_1])); + EMIT(PPC_RAW_RLWIMI(tmp1_reg, dst_reg, 24, 16, 23)); + EMIT(PPC_RAW_MR(dst_reg, tmp1_reg)); break; case 64: /* Store the value to stack and then use byte-reverse loads */ - PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx)); - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx))); + EMIT(PPC_RAW_STD(dst_reg, _R1, bpf_jit_stack_local(ctx))); + EMIT(PPC_RAW_ADDI(tmp1_reg, _R1, bpf_jit_stack_local(ctx))); if (cpu_has_feature(CPU_FTR_ARCH_206)) { - EMIT(PPC_RAW_LDBRX(dst_reg, 0, b2p[TMP_REG_1])); + EMIT(PPC_RAW_LDBRX(dst_reg, 0, tmp1_reg)); } else { - EMIT(PPC_RAW_LWBRX(dst_reg, 0, b2p[TMP_REG_1])); + EMIT(PPC_RAW_LWBRX(dst_reg, 0, tmp1_reg)); if (IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN)) EMIT(PPC_RAW_SLDI(dst_reg, dst_reg, 32)); - EMIT(PPC_RAW_LI(b2p[TMP_REG_2], 4)); - EMIT(PPC_RAW_LWBRX(b2p[TMP_REG_2], b2p[TMP_REG_2], b2p[TMP_REG_1])); + EMIT(PPC_RAW_LI(tmp2_reg, 4)); + EMIT(PPC_RAW_LWBRX(tmp2_reg, tmp2_reg, tmp1_reg)); if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) - EMIT(PPC_RAW_SLDI(b2p[TMP_REG_2], b2p[TMP_REG_2], 32)); - EMIT(PPC_RAW_OR(dst_reg, dst_reg, b2p[TMP_REG_2])); + EMIT(PPC_RAW_SLDI(tmp2_reg, tmp2_reg, 32)); + EMIT(PPC_RAW_OR(dst_reg, dst_reg, tmp2_reg)); } break; } @@ -686,15 +718,14 @@ emit_clear: break; case STF_BARRIER_SYNC_ORI: EMIT(PPC_RAW_SYNC()); - EMIT(PPC_RAW_LD(b2p[TMP_REG_1], _R13, 0)); + EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0)); EMIT(PPC_RAW_ORI(_R31, _R31, 0)); break; case STF_BARRIER_FALLBACK: - EMIT(PPC_RAW_MFLR(b2p[TMP_REG_1])); - PPC_LI64(12, dereference_kernel_function_descriptor(bpf_stf_barrier)); - EMIT(PPC_RAW_MTCTR(12)); + ctx->seen |= SEEN_FUNC; + PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier)); + EMIT(PPC_RAW_MTCTR(_R12)); EMIT(PPC_RAW_BCTRL()); - EMIT(PPC_RAW_MTLR(b2p[TMP_REG_1])); break; case STF_BARRIER_NONE: break; @@ -707,34 +738,39 @@ 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) { - EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm)); - src_reg = b2p[TMP_REG_1]; + EMIT(PPC_RAW_LI(tmp1_reg, imm)); + src_reg = tmp1_reg; } 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) { - EMIT(PPC_RAW_LI(b2p[TMP_REG_1], imm)); - src_reg = b2p[TMP_REG_1]; + EMIT(PPC_RAW_LI(tmp1_reg, imm)); + src_reg = tmp1_reg; } 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 */ if (BPF_CLASS(code) == BPF_ST) { - PPC_LI32(b2p[TMP_REG_1], imm); - src_reg = b2p[TMP_REG_1]; + PPC_LI32(tmp1_reg, imm); + src_reg = tmp1_reg; } 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 */ if (BPF_CLASS(code) == BPF_ST) { - PPC_LI32(b2p[TMP_REG_1], imm); - src_reg = b2p[TMP_REG_1]; + PPC_LI32(tmp1_reg, imm); + src_reg = tmp1_reg; + } + if (off % 4) { + EMIT(PPC_RAW_LI(tmp2_reg, off)); + EMIT(PPC_RAW_STDX(src_reg, dst_reg, tmp2_reg)); + } else { + EMIT(PPC_RAW_STD(src_reg, dst_reg, off)); } - PPC_BPF_STL(src_reg, dst_reg, off); break; /* @@ -751,14 +787,14 @@ emit_clear: /* *(u32 *)(dst + off) += src */ /* Get EA into TMP_REG_1 */ - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); + EMIT(PPC_RAW_ADDI(tmp1_reg, dst_reg, off)); tmp_idx = ctx->idx * 4; /* load value from memory into TMP_REG_2 */ - EMIT(PPC_RAW_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0)); + EMIT(PPC_RAW_LWARX(tmp2_reg, 0, tmp1_reg, 0)); /* add value from src_reg into this */ - EMIT(PPC_RAW_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg)); + EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); /* store result back */ - EMIT(PPC_RAW_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1])); + EMIT(PPC_RAW_STWCX(tmp2_reg, 0, tmp1_reg)); /* we're done if this succeeded */ PPC_BCC_SHORT(COND_NE, tmp_idx); break; @@ -771,11 +807,11 @@ emit_clear: } /* *(u64 *)(dst + off) += src */ - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], dst_reg, off)); + EMIT(PPC_RAW_ADDI(tmp1_reg, dst_reg, off)); tmp_idx = ctx->idx * 4; - 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])); + EMIT(PPC_RAW_LDARX(tmp2_reg, 0, tmp1_reg, 0)); + EMIT(PPC_RAW_ADD(tmp2_reg, tmp2_reg, src_reg)); + EMIT(PPC_RAW_STDCX(tmp2_reg, 0, tmp1_reg)); PPC_BCC_SHORT(COND_NE, tmp_idx); break; @@ -801,18 +837,17 @@ emit_clear: * set dst_reg=0 and move on. */ if (BPF_MODE(code) == BPF_PROBE_MEM) { - EMIT(PPC_RAW_ADDI(b2p[TMP_REG_1], src_reg, off)); + EMIT(PPC_RAW_ADDI(tmp1_reg, src_reg, off)); if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) - PPC_LI64(b2p[TMP_REG_2], 0x8000000000000000ul); + PPC_LI64(tmp2_reg, 0x8000000000000000ul); else /* BOOK3S_64 */ - PPC_LI64(b2p[TMP_REG_2], PAGE_OFFSET); - EMIT(PPC_RAW_CMPLD(b2p[TMP_REG_1], b2p[TMP_REG_2])); - PPC_BCC(COND_GT, (ctx->idx + 4) * 4); + PPC_LI64(tmp2_reg, PAGE_OFFSET); + EMIT(PPC_RAW_CMPLD(tmp1_reg, tmp2_reg)); + PPC_BCC_SHORT(COND_GT, (ctx->idx + 3) * 4); EMIT(PPC_RAW_LI(dst_reg, 0)); /* - * Check if 'off' is word aligned because PPC_BPF_LL() - * (BPF_DW case) generates two instructions if 'off' is not - * word-aligned and one instruction otherwise. + * Check if 'off' is word aligned for BPF_DW, because + * we might generate two instructions. */ if (BPF_SIZE(code) == BPF_DW && (off & 3)) PPC_JMP((ctx->idx + 3) * 4); @@ -831,7 +866,12 @@ emit_clear: EMIT(PPC_RAW_LWZ(dst_reg, src_reg, off)); break; case BPF_DW: - PPC_BPF_LL(dst_reg, src_reg, off); + if (off % 4) { + EMIT(PPC_RAW_LI(tmp1_reg, off)); + EMIT(PPC_RAW_LDX(dst_reg, src_reg, tmp1_reg)); + } else { + EMIT(PPC_RAW_LD(dst_reg, src_reg, off)); + } break; } @@ -871,8 +911,11 @@ emit_clear: * the epilogue. If we _are_ the last instruction, * we'll just fall through to the epilogue. */ - if (i != flen - 1) - PPC_JMP(exit_addr); + if (i != flen - 1) { + ret = bpf_jit_emit_exit_insn(image, ctx, tmp1_reg, exit_addr); + if (ret) + return ret; + } /* else fall through to the epilogue */ break; @@ -888,11 +931,15 @@ emit_clear: return ret; if (func_addr_fixed) - bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_hlp(image, ctx, func_addr); else - bpf_jit_emit_func_call_rel(image, ctx, func_addr); + ret = bpf_jit_emit_func_call_rel(image, ctx, func_addr); + + if (ret) + return ret; + /* move return value from r3 to BPF_REG_0 */ - EMIT(PPC_RAW_MR(b2p[BPF_REG_0], 3)); + EMIT(PPC_RAW_MR(bpf_to_ppc(BPF_REG_0), _R3)); break; /* @@ -998,14 +1045,10 @@ cond_branch: case BPF_JMP | BPF_JSET | BPF_X: case BPF_JMP32 | BPF_JSET | BPF_X: if (BPF_CLASS(code) == BPF_JMP) { - EMIT(PPC_RAW_AND_DOT(b2p[TMP_REG_1], dst_reg, - src_reg)); + EMIT(PPC_RAW_AND_DOT(tmp1_reg, dst_reg, src_reg)); } else { - int tmp_reg = b2p[TMP_REG_1]; - - EMIT(PPC_RAW_AND(tmp_reg, dst_reg, src_reg)); - EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg, 0, 0, - 31)); + EMIT(PPC_RAW_AND(tmp1_reg, dst_reg, src_reg)); + EMIT(PPC_RAW_RLWINM_DOT(tmp1_reg, tmp1_reg, 0, 0, 31)); } break; case BPF_JMP | BPF_JNE | BPF_K: @@ -1034,14 +1077,12 @@ cond_branch: EMIT(PPC_RAW_CMPLDI(dst_reg, imm)); } else { /* sign-extending load */ - PPC_LI32(b2p[TMP_REG_1], imm); + PPC_LI32(tmp1_reg, imm); /* ... but unsigned comparison */ if (is_jmp32) - EMIT(PPC_RAW_CMPLW(dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_CMPLW(dst_reg, tmp1_reg)); else - EMIT(PPC_RAW_CMPLD(dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_CMPLD(dst_reg, tmp1_reg)); } break; } @@ -1066,13 +1107,11 @@ cond_branch: else EMIT(PPC_RAW_CMPDI(dst_reg, imm)); } else { - PPC_LI32(b2p[TMP_REG_1], imm); + PPC_LI32(tmp1_reg, imm); if (is_jmp32) - EMIT(PPC_RAW_CMPW(dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_CMPW(dst_reg, tmp1_reg)); else - EMIT(PPC_RAW_CMPD(dst_reg, - b2p[TMP_REG_1])); + EMIT(PPC_RAW_CMPD(dst_reg, tmp1_reg)); } break; } @@ -1081,19 +1120,16 @@ cond_branch: /* andi does not sign-extend the immediate */ if (imm >= 0 && imm < 32768) /* PPC_ANDI is _only/always_ dot-form */ - EMIT(PPC_RAW_ANDI(b2p[TMP_REG_1], dst_reg, imm)); + EMIT(PPC_RAW_ANDI(tmp1_reg, dst_reg, imm)); else { - int tmp_reg = b2p[TMP_REG_1]; - - PPC_LI32(tmp_reg, imm); + PPC_LI32(tmp1_reg, imm); if (BPF_CLASS(code) == BPF_JMP) { - EMIT(PPC_RAW_AND_DOT(tmp_reg, dst_reg, - tmp_reg)); + EMIT(PPC_RAW_AND_DOT(tmp1_reg, dst_reg, + tmp1_reg)); } else { - EMIT(PPC_RAW_AND(tmp_reg, dst_reg, - tmp_reg)); - EMIT(PPC_RAW_RLWINM_DOT(tmp_reg, tmp_reg, - 0, 0, 31)); + EMIT(PPC_RAW_AND(tmp1_reg, dst_reg, tmp1_reg)); + EMIT(PPC_RAW_RLWINM_DOT(tmp1_reg, tmp1_reg, + 0, 0, 31)); } } break; diff --git a/arch/powerpc/perf/callchain.h b/arch/powerpc/perf/callchain.h index d6fa6e25234f..19a8d051ddf1 100644 --- a/arch/powerpc/perf/callchain.h +++ b/arch/powerpc/perf/callchain.h @@ -2,7 +2,6 @@ #ifndef _POWERPC_PERF_CALLCHAIN_H #define _POWERPC_PERF_CALLCHAIN_H -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, @@ -26,17 +25,11 @@ 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) && !radix_enabled() && rc) - return read_user_stack_slow(ptr, ret, size); - - return rc; + return copy_from_user_nofault(ret, ptr, size); } #endif /* _POWERPC_PERF_CALLCHAIN_H */ diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 8d0df4226328..488e8a21a11e 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -18,33 +18,6 @@ #include "callchain.h" -/* - * On 64-bit we don't want to invoke hash_page on user addresses from - * interrupt context, so if the access faults, we read the page tables - * to find which page (if any) is mapped and access it directly. Radix - * has no need for this so it doesn't use read_user_stack_slow. - */ -int read_user_stack_slow(const void __user *ptr, void *buf, int nb) -{ - - unsigned long addr = (unsigned long) ptr; - unsigned long offset; - struct page *page; - void *kaddr; - - if (get_user_page_fast_only(addr, FOLL_WRITE, &page)) { - kaddr = page_address(page); - - /* align address to page boundary */ - offset = addr & ~PAGE_MASK; - - memcpy(buf, kaddr + offset, nb); - put_page(page); - return 0; - } - return -EFAULT; -} - static int read_user_stack_64(const unsigned long __user *ptr, unsigned long *ret) { return __read_user_stack(ptr, ret, sizeof(*ret)); diff --git a/arch/powerpc/perf/generic-compat-pmu.c b/arch/powerpc/perf/generic-compat-pmu.c index b6e25f75109d..f3db88aee4dd 100644 --- a/arch/powerpc/perf/generic-compat-pmu.c +++ b/arch/powerpc/perf/generic-compat-pmu.c @@ -130,7 +130,7 @@ static struct attribute *generic_compat_events_attr[] = { NULL }; -static struct attribute_group generic_compat_pmu_events_group = { +static const struct attribute_group generic_compat_pmu_events_group = { .name = "events", .attrs = generic_compat_events_attr, }; @@ -146,7 +146,7 @@ static struct attribute *generic_compat_pmu_format_attr[] = { NULL, }; -static struct attribute_group generic_compat_pmu_format_group = { +static const struct attribute_group generic_compat_pmu_format_group = { .name = "format", .attrs = generic_compat_pmu_format_attr, }; diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 1e8aa934e37e..12c1777187fc 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -204,7 +204,7 @@ static struct attribute *format_attrs[] = { NULL, }; -static struct attribute_group format_group = { +static const struct attribute_group format_group = { .name = "format", .attrs = format_attrs, }; @@ -1148,7 +1148,7 @@ static struct attribute *cpumask_attrs[] = { NULL, }; -static struct attribute_group cpumask_attr_group = { +static const struct attribute_group cpumask_attr_group = { .attrs = cpumask_attrs, }; @@ -1162,7 +1162,7 @@ static struct attribute *if_attrs[] = { NULL, }; -static struct attribute_group if_group = { +static const struct attribute_group if_group = { .name = "interface", .bin_attrs = if_bin_attrs, .attrs = if_attrs, diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index c756228a081f..5eb60ed5b5e8 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -65,12 +65,12 @@ static struct attribute *format_attrs[] = { NULL, }; -static struct attribute_group format_group = { +static const struct attribute_group format_group = { .name = "format", .attrs = format_attrs, }; -static struct attribute_group event_group = { +static const struct attribute_group event_group = { .name = "events", .attrs = hv_gpci_event_attrs, }; @@ -126,11 +126,11 @@ static struct attribute *cpumask_attrs[] = { NULL, }; -static struct attribute_group cpumask_attr_group = { +static const struct attribute_group cpumask_attr_group = { .attrs = cpumask_attrs, }; -static struct attribute_group interface_group = { +static const struct attribute_group interface_group = { .name = "interface", .attrs = interface_attrs, }; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index e106909ff9c3..526d4b767534 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -71,7 +71,7 @@ static struct attribute *imc_format_attrs[] = { NULL, }; -static struct attribute_group imc_format_group = { +static const struct attribute_group imc_format_group = { .name = "format", .attrs = imc_format_attrs, }; @@ -90,7 +90,7 @@ static struct attribute *trace_imc_format_attrs[] = { NULL, }; -static struct attribute_group trace_imc_format_group = { +static const struct attribute_group trace_imc_format_group = { .name = "format", .attrs = trace_imc_format_attrs, }; @@ -125,7 +125,7 @@ static struct attribute *imc_pmu_cpumask_attrs[] = { NULL, }; -static struct attribute_group imc_pmu_cpumask_attr_group = { +static const struct attribute_group imc_pmu_cpumask_attr_group = { .attrs = imc_pmu_cpumask_attrs, }; @@ -1457,7 +1457,11 @@ static int trace_imc_event_init(struct perf_event *event) event->hw.idx = -1; - event->pmu->task_ctx_nr = perf_hw_context; + /* + * There can only be a single PMU for perf_hw_context events which is assigned to + * core PMU. Hence use "perf_sw_context" for trace_imc. + */ + event->pmu->task_ctx_nr = perf_sw_context; event->destroy = reset_global_refc; return 0; } diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 4037ea652522..a74d382ecbb7 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -37,7 +37,7 @@ static struct attribute *isa207_pmu_format_attr[] = { NULL, }; -struct attribute_group isa207_pmu_format_group = { +const struct attribute_group isa207_pmu_format_group = { .name = "format", .attrs = isa207_pmu_format_attr, }; diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c index 51d31b65e423..350dccb0143c 100644 --- a/arch/powerpc/perf/perf_regs.c +++ b/arch/powerpc/perf/perf_regs.c @@ -134,12 +134,10 @@ int perf_reg_validate(u64 mask) u64 perf_reg_abi(struct task_struct *task) { -#ifdef CONFIG_PPC64 - if (!test_tsk_thread_flag(task, TIF_32BIT)) - return PERF_SAMPLE_REGS_ABI_64; + if (is_tsk_32bit_task(task)) + return PERF_SAMPLE_REGS_ABI_32; else -#endif - return PERF_SAMPLE_REGS_ABI_32; + return PERF_SAMPLE_REGS_ABI_64; } void perf_get_regs_user(struct perf_regs *regs_user, diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index 0975ad0b42c4..d3398100a60f 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -200,12 +200,12 @@ static struct attribute *power10_events_attr[] = { NULL }; -static struct attribute_group power10_pmu_events_group_dd1 = { +static const struct attribute_group power10_pmu_events_group_dd1 = { .name = "events", .attrs = power10_events_attr_dd1, }; -static struct attribute_group power10_pmu_events_group = { +static const struct attribute_group power10_pmu_events_group = { .name = "events", .attrs = power10_events_attr, }; @@ -253,7 +253,7 @@ static struct attribute *power10_pmu_format_attr[] = { NULL, }; -static struct attribute_group power10_pmu_format_group = { +static const struct attribute_group power10_pmu_format_group = { .name = "format", .attrs = power10_pmu_format_attr, }; diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index 99b5ba314ea7..a74211410b8d 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -405,7 +405,7 @@ static struct attribute *power7_events_attr[] = { NULL }; -static struct attribute_group power7_pmu_events_group = { +static const struct attribute_group power7_pmu_events_group = { .name = "events", .attrs = power7_events_attr, }; @@ -417,7 +417,7 @@ static struct attribute *power7_pmu_format_attr[] = { NULL, }; -static struct attribute_group power7_pmu_format_group = { +static const struct attribute_group power7_pmu_format_group = { .name = "format", .attrs = power7_pmu_format_attr, }; diff --git a/arch/powerpc/perf/power8-pmu.c b/arch/powerpc/perf/power8-pmu.c index f21194b5604a..e37b1e714d2b 100644 --- a/arch/powerpc/perf/power8-pmu.c +++ b/arch/powerpc/perf/power8-pmu.c @@ -92,7 +92,7 @@ enum { */ /* PowerISA v2.07 format attribute structure*/ -extern struct attribute_group isa207_pmu_format_group; +extern const struct attribute_group isa207_pmu_format_group; /* Table of alternatives, sorted by column 0 */ static const unsigned int event_alternatives[][MAX_ALT] = { @@ -182,7 +182,7 @@ static struct attribute *power8_events_attr[] = { NULL }; -static struct attribute_group power8_pmu_events_group = { +static const struct attribute_group power8_pmu_events_group = { .name = "events", .attrs = power8_events_attr, }; diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c index 4b7c17e36100..c9eb5232e68b 100644 --- a/arch/powerpc/perf/power9-pmu.c +++ b/arch/powerpc/perf/power9-pmu.c @@ -96,7 +96,7 @@ extern u64 PERF_REG_EXTENDED_MASK; #define PVR_POWER9_CUMULUS 0x00002000 /* PowerISA v2.07 format attribute structure*/ -extern struct attribute_group isa207_pmu_format_group; +extern const struct attribute_group isa207_pmu_format_group; int p9_dd21_bl_ev[] = { PM_MRK_ST_DONE_L2, @@ -217,7 +217,7 @@ static struct attribute *power9_events_attr[] = { NULL }; -static struct attribute_group power9_pmu_events_group = { +static const struct attribute_group power9_pmu_events_group = { .name = "events", .attrs = power9_events_attr, }; @@ -253,7 +253,7 @@ static struct attribute *power9_pmu_format_attr[] = { NULL, }; -static struct attribute_group power9_pmu_format_group = { +static const struct attribute_group power9_pmu_format_group = { .name = "format", .attrs = power9_pmu_format_attr, }; diff --git a/arch/powerpc/platforms/85xx/corenet_generic.c b/arch/powerpc/platforms/85xx/corenet_generic.c index 8d6029099848..17ae75d62518 100644 --- a/arch/powerpc/platforms/85xx/corenet_generic.c +++ b/arch/powerpc/platforms/85xx/corenet_generic.c @@ -37,7 +37,7 @@ void __init corenet_gen_pic_init(void) unsigned int flags = MPIC_BIG_ENDIAN | MPIC_SINGLE_DEST_CPU | MPIC_NO_RESET; - if (ppc_md.get_irq == mpic_get_coreint_irq) + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) && !IS_ENABLED(CONFIG_KEXEC_CORE)) flags |= MPIC_ENABLE_COREINT; mpic = mpic_alloc(NULL, 0, flags, 0, 512, " OpenPIC "); diff --git a/arch/powerpc/platforms/85xx/qemu_e500.c b/arch/powerpc/platforms/85xx/qemu_e500.c index a4127b0b161f..4c4d577effd9 100644 --- a/arch/powerpc/platforms/85xx/qemu_e500.c +++ b/arch/powerpc/platforms/85xx/qemu_e500.c @@ -67,4 +67,9 @@ define_machine(qemu_e500) { .get_irq = mpic_get_coreint_irq, .calibrate_decr = generic_calibrate_decr, .progress = udbg_progress, +#ifdef CONFIG_PPC64 + .power_save = book3e_idle, +#else + .power_save = e500_idle, +#endif }; diff --git a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c index b697918b727d..a6b8ffcbf01a 100644 --- a/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c +++ b/arch/powerpc/platforms/86xx/mpc86xx_hpcn.c @@ -95,12 +95,6 @@ static int __init mpc86xx_hpcn_probe(void) if (of_machine_is_compatible("fsl,mpc8641hpcn")) return 1; /* Looks good */ - /* Be nice and don't give silent boot death. Delete this in 2.6.27 */ - if (of_machine_is_compatible("mpc86xx")) { - pr_warn("WARNING: your dts/dtb is old. You must update before the next kernel release.\n"); - return 1; - } - return 0; } diff --git a/arch/powerpc/platforms/8xx/pic.c b/arch/powerpc/platforms/8xx/pic.c index f2ba837249d6..04a6abf14c29 100644 --- a/arch/powerpc/platforms/8xx/pic.c +++ b/arch/powerpc/platforms/8xx/pic.c @@ -153,6 +153,7 @@ int __init mpc8xx_pic_init(void) if (mpc8xx_pic_host == NULL) { printk(KERN_ERR "MPC8xx PIC: failed to allocate irq host!\n"); ret = -ENOMEM; + goto out; } ret = 0; diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 87bc1929ee5a..e2e1fec91c6e 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -107,6 +107,7 @@ config PPC_BOOK3S_64 config PPC_BOOK3E_64 bool "Embedded processors" + select PPC_FSL_BOOK3E select PPC_FPU # Make it a choice ? select PPC_SMP_MUXED_IPI select PPC_DOORBELL @@ -295,7 +296,7 @@ config FSL_BOOKE config PPC_FSL_BOOK3E bool select ARCH_SUPPORTS_HUGETLBFS if PHYS_64BIT || PPC64 - select FSL_EMB_PERFMON + imply FSL_EMB_PERFMON select PPC_SMP_MUXED_IPI select PPC_DOORBELL select PPC_KUEP diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index 4d82c92ddd52..f9a1615b74da 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -316,6 +316,7 @@ static int coproc_ioc_tx_win_open(struct file *fp, unsigned long arg) return PTR_ERR(txwin); } + mutex_init(&txwin->task_ref.mmap_mutex); cp_inst->txwin = txwin; return 0; @@ -350,6 +351,124 @@ static int coproc_release(struct inode *inode, struct file *fp) return 0; } +/* + * If the executed instruction that caused the fault was a paste, then + * clear regs CR0[EQ], advance NIP, and return 0. Else return error code. + */ +static int do_fail_paste(void) +{ + struct pt_regs *regs = current->thread.regs; + u32 instword; + + if (WARN_ON_ONCE(!regs)) + return -EINVAL; + + if (WARN_ON_ONCE(!user_mode(regs))) + return -EINVAL; + + /* + * If we couldn't translate the instruction, the driver should + * return success without handling the fault, it will be retried + * or the instruction fetch will fault. + */ + if (get_user(instword, (u32 __user *)(regs->nip))) + return -EAGAIN; + + /* + * Not a paste instruction, driver may fail the fault. + */ + if ((instword & PPC_INST_PASTE_MASK) != PPC_INST_PASTE) + return -ENOENT; + + regs->ccr &= ~0xe0000000; /* Clear CR0[0-2] to fail paste */ + regs_add_return_ip(regs, 4); /* Emulate the paste */ + + return 0; +} + +/* + * This fault handler is invoked when the core generates page fault on + * the paste address. Happens if the kernel closes window in hypervisor + * (on pseries) due to lost credit or the paste address is not mapped. + */ +static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct file *fp = vma->vm_file; + struct coproc_instance *cp_inst = fp->private_data; + struct vas_window *txwin; + vm_fault_t fault; + u64 paste_addr; + int ret; + + /* + * window is not opened. Shouldn't expect this error. + */ + if (!cp_inst || !cp_inst->txwin) { + pr_err("%s(): Unexpected fault on paste address with TX window closed\n", + __func__); + return VM_FAULT_SIGBUS; + } + + txwin = cp_inst->txwin; + /* + * When the LPAR lost credits due to core removal or during + * migration, invalidate the existing mapping for the current + * paste addresses and set windows in-active (zap_page_range in + * reconfig_close_windows()). + * New mapping will be done later after migration or new credits + * available. So continue to receive faults if the user space + * issue NX request. + */ + if (txwin->task_ref.vma != vmf->vma) { + pr_err("%s(): No previous mapping with paste address\n", + __func__); + return VM_FAULT_SIGBUS; + } + + mutex_lock(&txwin->task_ref.mmap_mutex); + /* + * The window may be inactive due to lost credit (Ex: core + * removal with DLPAR). If the window is active again when + * the credit is available, map the new paste address at the + * the window virtual address. + */ + if (txwin->status == VAS_WIN_ACTIVE) { + paste_addr = cp_inst->coproc->vops->paste_addr(txwin); + if (paste_addr) { + fault = vmf_insert_pfn(vma, vma->vm_start, + (paste_addr >> PAGE_SHIFT)); + mutex_unlock(&txwin->task_ref.mmap_mutex); + return fault; + } + } + mutex_unlock(&txwin->task_ref.mmap_mutex); + + /* + * Received this fault due to closing the actual window. + * It can happen during migration or lost credits. + * Since no mapping, return the paste instruction failure + * to the user space. + */ + ret = do_fail_paste(); + /* + * The user space can retry several times until success (needed + * for migration) or should fallback to SW compression or + * manage with the existing open windows if available. + * Looking at sysfs interface, it can determine whether these + * failures are coming during migration or core removal: + * nr_used_credits > nr_total_credits when lost credits + */ + if (!ret || (ret == -EAGAIN)) + return VM_FAULT_NOPAGE; + + return VM_FAULT_SIGBUS; +} + +static const struct vm_operations_struct vas_vm_ops = { + .fault = vas_mmap_fault, +}; + static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) { struct coproc_instance *cp_inst = fp->private_data; @@ -378,10 +497,29 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) return -EACCES; } + /* + * The initial mmap is done after the window is opened + * with ioctl. But before mmap(), this window can be closed in + * the hypervisor due to lost credit (core removal on pseries). + * So if the window is not active, return mmap() failure with + * -EACCES and expects the user space reissue mmap() when it + * is active again or open new window when the credit is available. + * mmap_mutex protects the paste address mmap() with DLPAR + * close/open event and allows mmap() only when the window is + * active. + */ + mutex_lock(&txwin->task_ref.mmap_mutex); + if (txwin->status != VAS_WIN_ACTIVE) { + pr_err("%s(): Window is not active\n", __func__); + rc = -EACCES; + goto out; + } + paste_addr = cp_inst->coproc->vops->paste_addr(txwin); if (!paste_addr) { pr_err("%s(): Window paste address failed\n", __func__); - return -EINVAL; + rc = -EINVAL; + goto out; } pfn = paste_addr >> PAGE_SHIFT; @@ -398,6 +536,11 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma) pr_devel("%s(): paste addr %llx at %lx, rc %d\n", __func__, paste_addr, vma->vm_start, rc); + txwin->task_ref.vma = vma; + vma->vm_ops = &vas_vm_ops; + +out: + mutex_unlock(&txwin->task_ref.mmap_mutex); return rc; } diff --git a/arch/powerpc/platforms/cell/cbe_thermal.c b/arch/powerpc/platforms/cell/cbe_thermal.c index 2ece77f49bc3..abb5e527b4db 100644 --- a/arch/powerpc/platforms/cell/cbe_thermal.c +++ b/arch/powerpc/platforms/cell/cbe_thermal.c @@ -255,7 +255,7 @@ static struct attribute *spu_attributes[] = { NULL, }; -static struct attribute_group spu_attribute_group = { +static const struct attribute_group spu_attribute_group = { .name = "thermal", .attrs = spu_attributes, }; diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c index 83cea9e7ee72..2eecba3345c3 100644 --- a/arch/powerpc/platforms/cell/spu_base.c +++ b/arch/powerpc/platforms/cell/spu_base.c @@ -490,7 +490,7 @@ int spu_add_dev_attr(struct device_attribute *attr) } EXPORT_SYMBOL_GPL(spu_add_dev_attr); -int spu_add_dev_attr_group(struct attribute_group *attrs) +int spu_add_dev_attr_group(const struct attribute_group *attrs) { struct spu *spu; int rc = 0; @@ -529,7 +529,7 @@ void spu_remove_dev_attr(struct device_attribute *attr) } EXPORT_SYMBOL_GPL(spu_remove_dev_attr); -void spu_remove_dev_attr_group(struct attribute_group *attrs) +void spu_remove_dev_attr_group(const struct attribute_group *attrs) { struct spu *spu; diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c index 369206489895..99bd027a7f7c 100644 --- a/arch/powerpc/platforms/cell/spufs/sched.c +++ b/arch/powerpc/platforms/cell/spufs/sched.c @@ -340,8 +340,7 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff, static void aff_set_ref_point_location(struct spu_gang *gang) { int mem_aff, gs, lowest_offset; - struct spu_context *ctx; - struct spu *tmp; + struct spu_context *tmp, *ctx; mem_aff = gang->aff_ref_ctx->flags & SPU_CREATE_AFFINITY_MEM; lowest_offset = 0; @@ -1053,6 +1052,7 @@ void spuctx_switch_state(struct spu_context *ctx, } } +#ifdef CONFIG_PROC_FS static int show_spu_loadavg(struct seq_file *s, void *private) { int a, b, c; @@ -1074,7 +1074,8 @@ static int show_spu_loadavg(struct seq_file *s, void *private) atomic_read(&nr_spu_contexts), idr_get_cursor(&task_active_pid_ns(current)->idr) - 1); return 0; -}; +} +#endif int __init spu_sched_init(void) { diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 29d2036dcc9d..ba8d4e97095b 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -5,6 +5,8 @@ #include <linux/pci.h> #include <linux/irq.h> +#include <asm/pmac_feature.h> + /* * Declaration for the various functions exported by the * pmac_* files. Mostly for use by pmac_setup diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 9942289f379b..a6677a111aca 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -12,7 +12,6 @@ #include <linux/device.h> #include <linux/cpu.h> -#include <asm/asm-prototypes.h> #include <asm/firmware.h> #include <asm/interrupt.h> #include <asm/machdep.h> diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index 0331f1973f0e..b97bc179f65a 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -603,7 +603,7 @@ static struct bin_attribute *mpipl_bin_attr[] = { }; -static struct attribute_group mpipl_group = { +static const struct attribute_group mpipl_group = { .attrs = mpipl_attr, .bin_attrs = mpipl_bin_attr, }; diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 410ed5b9de29..16c5860f1372 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -150,7 +150,7 @@ static struct attribute *initiate_attrs[] = { NULL, }; -static struct attribute_group initiate_attr_group = { +static const struct attribute_group initiate_attr_group = { .attrs = initiate_attrs, }; diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c index 7e7d38b17420..18481a8c52fa 100644 --- a/arch/powerpc/platforms/powernv/opal-flash.c +++ b/arch/powerpc/platforms/powernv/opal-flash.c @@ -512,7 +512,7 @@ static struct attribute *image_op_attrs[] = { NULL /* need to NULL terminate the list of attributes */ }; -static struct attribute_group image_op_attr_group = { +static const struct attribute_group image_op_attr_group = { .attrs = image_op_attrs, }; diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c index f16a43540e30..91b36541b9e5 100644 --- a/arch/powerpc/platforms/powernv/opal-tracepoints.c +++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c @@ -2,7 +2,6 @@ #include <linux/percpu.h> #include <linux/jump_label.h> #include <asm/trace.h> -#include <asm/asm-prototypes.h> #ifdef CONFIG_JUMP_LABEL struct static_key opal_tracepoint_key = STATIC_KEY_INIT; diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index b4386714494a..e3d44b36ae98 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -43,7 +43,11 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val) unsigned long parity; /* Calculate the parity of the value */ - asm ("popcntd %0,%1" : "=r" (parity) : "r" (val)); + asm (".machine push; \ + .machine power7; \ + popcntd %0,%1; \ + .machine pop;" + : "=r" (parity) : "r" (val)); /* xor our value with the previous mask */ val ^= rng->mask; diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c index c8b50fec56bf..b637bf292047 100644 --- a/arch/powerpc/platforms/ps3/system-bus.c +++ b/arch/powerpc/platforms/ps3/system-bus.c @@ -603,7 +603,7 @@ static dma_addr_t ps3_ioc0_map_page(struct device *_dev, struct page *page, default: /* not happned */ BUG(); - }; + } result = ps3_dma_map(dev->d_region, (unsigned long)ptr, size, &bus_addr, iopte_flag); @@ -762,7 +762,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev) break; default: BUG(); - }; + } dev->core.of_node = NULL; set_dev_node(&dev->core, 0); diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index ee60b59024b4..9764e1a2ed5c 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -6,7 +6,8 @@ obj-y := lpar.o hvCall.o nvram.o reconfig.o \ of_helpers.o \ setup.o iommu.o event_sources.o ras.o \ firmware.o power.o dlpar.o mobility.o rng.o \ - pci.o pci_dlpar.o eeh_pseries.o msi.o + pci.o pci_dlpar.o eeh_pseries.o msi.o \ + papr_platform_attributes.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_KEXEC_CORE) += kexec.o obj-$(CONFIG_PSERIES_ENERGY) += pseries_energy.o @@ -29,6 +30,6 @@ obj-$(CONFIG_PPC_SVM) += svm.o obj-$(CONFIG_FA_DUMP) += rtas-fadump.o obj-$(CONFIG_SUSPEND) += suspend.o -obj-$(CONFIG_PPC_VAS) += vas.o +obj-$(CONFIG_PPC_VAS) += vas.o vas-sysfs.o obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += cc_platform.o diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c index f162156b7b68..09c119b2f623 100644 --- a/arch/powerpc/platforms/pseries/firmware.c +++ b/arch/powerpc/platforms/pseries/firmware.c @@ -66,6 +66,7 @@ hypertas_fw_features_table[] = { {FW_FEATURE_BLOCK_REMOVE, "hcall-block-remove"}, {FW_FEATURE_PAPR_SCM, "hcall-scm"}, {FW_FEATURE_RPT_INVALIDATE, "hcall-rpt-invalidate"}, + {FW_FEATURE_ENERGY_SCALE_INFO, "hcall-energy-scale-info"}, }; /* Build up the firmware features bitmask using the contents of diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index f8899d506ea4..760581c5752f 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -40,7 +40,6 @@ #include <asm/plpar_wrappers.h> #include <asm/kexec.h> #include <asm/fadump.h> -#include <asm/asm-prototypes.h> #include <asm/dtl.h> #include "pseries.h" diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index c7940fcfc911..2119c003fcf9 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -311,6 +311,92 @@ static void parse_mpp_x_data(struct seq_file *m) seq_printf(m, "coalesce_pool_spurr=%ld\n", mpp_x_data.pool_spurr_cycles); } +/* + * PAPR defines, in section "7.3.16 System Parameters Option", the token 55 to + * read the LPAR name, and the largest output data to 4000 + 2 bytes length. + */ +#define SPLPAR_LPAR_NAME_TOKEN 55 +#define GET_SYS_PARM_BUF_SIZE 4002 +#if GET_SYS_PARM_BUF_SIZE > RTAS_DATA_BUF_SIZE +#error "GET_SYS_PARM_BUF_SIZE is larger than RTAS_DATA_BUF_SIZE" +#endif + +/* + * Read the lpar name using the RTAS ibm,get-system-parameter call. + * + * The name read through this call is updated if changes are made by the end + * user on the hypervisor side. + * + * Some hypervisor (like Qemu) may not provide this value. In that case, a non + * null value is returned. + */ +static int read_rtas_lpar_name(struct seq_file *m) +{ + int rc, len, token; + union { + char raw_buffer[GET_SYS_PARM_BUF_SIZE]; + struct { + __be16 len; + char name[GET_SYS_PARM_BUF_SIZE-2]; + }; + } *local_buffer; + + token = rtas_token("ibm,get-system-parameter"); + if (token == RTAS_UNKNOWN_SERVICE) + return -EINVAL; + + local_buffer = kmalloc(sizeof(*local_buffer), GFP_KERNEL); + if (!local_buffer) + return -ENOMEM; + + do { + spin_lock(&rtas_data_buf_lock); + memset(rtas_data_buf, 0, sizeof(*local_buffer)); + rc = rtas_call(token, 3, 1, NULL, SPLPAR_LPAR_NAME_TOKEN, + __pa(rtas_data_buf), sizeof(*local_buffer)); + if (!rc) + memcpy(local_buffer->raw_buffer, rtas_data_buf, + sizeof(local_buffer->raw_buffer)); + spin_unlock(&rtas_data_buf_lock); + } while (rtas_busy_delay(rc)); + + if (!rc) { + /* Force end of string */ + len = min((int) be16_to_cpu(local_buffer->len), + (int) sizeof(local_buffer->name)-1); + local_buffer->name[len] = '\0'; + + seq_printf(m, "partition_name=%s\n", local_buffer->name); + } else + rc = -ENODATA; + + kfree(local_buffer); + return rc; +} + +/* + * Read the LPAR name from the Device Tree. + * + * The value read in the DT is not updated if the end-user is touching the LPAR + * name on the hypervisor side. + */ +static int read_dt_lpar_name(struct seq_file *m) +{ + const char *name; + + if (of_property_read_string(of_root, "ibm,partition-name", &name)) + return -ENOENT; + + seq_printf(m, "partition_name=%s\n", name); + return 0; +} + +static void read_lpar_name(struct seq_file *m) +{ + if (read_rtas_lpar_name(m) && read_dt_lpar_name(m)) + pr_err_once("Error can't get the LPAR name"); +} + #define SPLPAR_CHARACTERISTICS_TOKEN 20 #define SPLPAR_MAXLENGTH 1026*(sizeof(char)) @@ -496,6 +582,7 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) if (firmware_has_feature(FW_FEATURE_SPLPAR)) { /* this call handles the ibm,get-system-parameter contents */ + read_lpar_name(m); parse_system_parameter_string(m); parse_ppp_data(m); parse_mpp_data(m); diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 85033f392c78..78f3f74c7056 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -26,6 +26,7 @@ #include <asm/machdep.h> #include <asm/rtas.h> #include "pseries.h" +#include "vas.h" /* vas_migration_handler() */ #include "../../kernel/cacheinfo.h" static struct kobject *mobility_kobj; @@ -265,7 +266,7 @@ static int add_dt_node(struct device_node *parent_dn, __be32 drc_index) return rc; } -int pseries_devicetree_update(s32 scope) +static int pseries_devicetree_update(s32 scope) { char *rtas_buf; __be32 *data; @@ -669,12 +670,16 @@ static int pseries_migrate_partition(u64 handle) if (ret) return ret; + vas_migration_handler(VAS_SUSPEND); + ret = pseries_suspend(handle); if (ret == 0) post_mobility_fixup(); else pseries_cancel_migration(handle, ret); + vas_migration_handler(VAS_RESUME); + return ret; } diff --git a/arch/powerpc/platforms/pseries/papr_platform_attributes.c b/arch/powerpc/platforms/pseries/papr_platform_attributes.c new file mode 100644 index 000000000000..515150417bb3 --- /dev/null +++ b/arch/powerpc/platforms/pseries/papr_platform_attributes.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Platform energy and frequency attributes driver + * + * This driver creates a sys file at /sys/firmware/papr/ which encapsulates a + * directory structure containing files in keyword - value pairs that specify + * energy and frequency configuration of the system. + * + * The format of exposing the sysfs information is as follows: + * /sys/firmware/papr/energy_scale_info/ + * |-- <id>/ + * |-- desc + * |-- value + * |-- value_desc (if exists) + * |-- <id>/ + * |-- desc + * |-- value + * |-- value_desc (if exists) + * + * Copyright 2022 IBM Corp. + */ + +#include <asm/hvcall.h> +#include <asm/machdep.h> + +#include "pseries.h" + +/* + * Flag attributes to fetch either all or one attribute from the HCALL + * flag = BE(0) => fetch all attributes with firstAttributeId = 0 + * flag = BE(1) => fetch a single attribute with firstAttributeId = id + */ +#define ESI_FLAGS_ALL 0 +#define ESI_FLAGS_SINGLE (1ull << 63) + +#define KOBJ_MAX_ATTRS 3 + +#define ESI_HDR_SIZE sizeof(struct h_energy_scale_info_hdr) +#define ESI_ATTR_SIZE sizeof(struct energy_scale_attribute) +#define CURR_MAX_ESI_ATTRS 8 + +struct energy_scale_attribute { + __be64 id; + __be64 val; + u8 desc[64]; + u8 value_desc[64]; +} __packed; + +struct h_energy_scale_info_hdr { + __be64 num_attrs; + __be64 array_offset; + u8 data_header_version; +} __packed; + +struct papr_attr { + u64 id; + struct kobj_attribute kobj_attr; +}; + +struct papr_group { + struct attribute_group pg; + struct papr_attr pgattrs[KOBJ_MAX_ATTRS]; +}; + +static struct papr_group *papr_groups; +/* /sys/firmware/papr */ +static struct kobject *papr_kobj; +/* /sys/firmware/papr/energy_scale_info */ +static struct kobject *esi_kobj; + +/* + * Energy modes can change dynamically hence making a new hcall each time the + * information needs to be retrieved + */ +static int papr_get_attr(u64 id, struct energy_scale_attribute *esi) +{ + int esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * ESI_ATTR_SIZE); + int ret, max_esi_attrs = CURR_MAX_ESI_ATTRS; + struct energy_scale_attribute *curr_esi; + struct h_energy_scale_info_hdr *hdr; + char *buf; + + buf = kmalloc(esi_buf_size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + +retry: + ret = plpar_hcall_norets(H_GET_ENERGY_SCALE_INFO, ESI_FLAGS_SINGLE, + id, virt_to_phys(buf), + esi_buf_size); + + /* + * If the hcall fails with not enough memory for either the + * header or data, attempt to allocate more + */ + if (ret == H_PARTIAL || ret == H_P4) { + char *temp_buf; + + max_esi_attrs += 4; + esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); + + temp_buf = krealloc(buf, esi_buf_size, GFP_KERNEL); + if (temp_buf) + buf = temp_buf; + else + return -ENOMEM; + + goto retry; + } + + if (ret != H_SUCCESS) { + pr_warn("hcall failed: H_GET_ENERGY_SCALE_INFO"); + ret = -EIO; + goto out_buf; + } + + hdr = (struct h_energy_scale_info_hdr *) buf; + curr_esi = (struct energy_scale_attribute *) + (buf + be64_to_cpu(hdr->array_offset)); + + if (esi_buf_size < + be64_to_cpu(hdr->array_offset) + (be64_to_cpu(hdr->num_attrs) + * sizeof(struct energy_scale_attribute))) { + ret = -EIO; + goto out_buf; + } + + *esi = *curr_esi; + +out_buf: + kfree(buf); + + return ret; +} + +/* + * Extract and export the description of the energy scale attributes + */ +static ssize_t desc_show(struct kobject *kobj, + struct kobj_attribute *kobj_attr, + char *buf) +{ + struct papr_attr *pattr = container_of(kobj_attr, struct papr_attr, + kobj_attr); + struct energy_scale_attribute esi; + int ret; + + ret = papr_get_attr(pattr->id, &esi); + if (ret) + return ret; + + return sysfs_emit(buf, "%s\n", esi.desc); +} + +/* + * Extract and export the numeric value of the energy scale attributes + */ +static ssize_t val_show(struct kobject *kobj, + struct kobj_attribute *kobj_attr, + char *buf) +{ + struct papr_attr *pattr = container_of(kobj_attr, struct papr_attr, + kobj_attr); + struct energy_scale_attribute esi; + int ret; + + ret = papr_get_attr(pattr->id, &esi); + if (ret) + return ret; + + return sysfs_emit(buf, "%llu\n", be64_to_cpu(esi.val)); +} + +/* + * Extract and export the value description in string format of the energy + * scale attributes + */ +static ssize_t val_desc_show(struct kobject *kobj, + struct kobj_attribute *kobj_attr, + char *buf) +{ + struct papr_attr *pattr = container_of(kobj_attr, struct papr_attr, + kobj_attr); + struct energy_scale_attribute esi; + int ret; + + ret = papr_get_attr(pattr->id, &esi); + if (ret) + return ret; + + return sysfs_emit(buf, "%s\n", esi.value_desc); +} + +static struct papr_ops_info { + const char *attr_name; + ssize_t (*show)(struct kobject *kobj, struct kobj_attribute *kobj_attr, + char *buf); +} ops_info[KOBJ_MAX_ATTRS] = { + { "desc", desc_show }, + { "value", val_show }, + { "value_desc", val_desc_show }, +}; + +static void add_attr(u64 id, int index, struct papr_attr *attr) +{ + attr->id = id; + sysfs_attr_init(&attr->kobj_attr.attr); + attr->kobj_attr.attr.name = ops_info[index].attr_name; + attr->kobj_attr.attr.mode = 0444; + attr->kobj_attr.show = ops_info[index].show; +} + +static int add_attr_group(u64 id, struct papr_group *pg, bool show_val_desc) +{ + int i; + + for (i = 0; i < KOBJ_MAX_ATTRS; i++) { + if (!strcmp(ops_info[i].attr_name, "value_desc") && + !show_val_desc) { + continue; + } + add_attr(id, i, &pg->pgattrs[i]); + pg->pg.attrs[i] = &pg->pgattrs[i].kobj_attr.attr; + } + + return sysfs_create_group(esi_kobj, &pg->pg); +} + + +static int __init papr_init(void) +{ + int esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * ESI_ATTR_SIZE); + int ret, idx, i, max_esi_attrs = CURR_MAX_ESI_ATTRS; + struct h_energy_scale_info_hdr *esi_hdr; + struct energy_scale_attribute *esi_attrs; + uint64_t num_attrs; + char *esi_buf; + + if (!firmware_has_feature(FW_FEATURE_LPAR) || + !firmware_has_feature(FW_FEATURE_ENERGY_SCALE_INFO)) { + return -ENXIO; + } + + esi_buf = kmalloc(esi_buf_size, GFP_KERNEL); + if (esi_buf == NULL) + return -ENOMEM; + /* + * hcall( + * uint64 H_GET_ENERGY_SCALE_INFO, // Get energy scale info + * uint64 flags, // Per the flag request + * uint64 firstAttributeId, // The attribute id + * uint64 bufferAddress, // Guest physical address of the output buffer + * uint64 bufferSize); // The size in bytes of the output buffer + */ +retry: + + ret = plpar_hcall_norets(H_GET_ENERGY_SCALE_INFO, ESI_FLAGS_ALL, 0, + virt_to_phys(esi_buf), esi_buf_size); + + /* + * If the hcall fails with not enough memory for either the + * header or data, attempt to allocate more + */ + if (ret == H_PARTIAL || ret == H_P4) { + char *temp_esi_buf; + + max_esi_attrs += 4; + esi_buf_size = ESI_HDR_SIZE + (CURR_MAX_ESI_ATTRS * max_esi_attrs); + + temp_esi_buf = krealloc(esi_buf, esi_buf_size, GFP_KERNEL); + if (temp_esi_buf) + esi_buf = temp_esi_buf; + else + return -ENOMEM; + + goto retry; + } + + if (ret != H_SUCCESS) { + pr_warn("hcall failed: H_GET_ENERGY_SCALE_INFO, ret: %d\n", ret); + goto out_free_esi_buf; + } + + esi_hdr = (struct h_energy_scale_info_hdr *) esi_buf; + num_attrs = be64_to_cpu(esi_hdr->num_attrs); + esi_attrs = (struct energy_scale_attribute *) + (esi_buf + be64_to_cpu(esi_hdr->array_offset)); + + if (esi_buf_size < + be64_to_cpu(esi_hdr->array_offset) + + (num_attrs * sizeof(struct energy_scale_attribute))) { + goto out_free_esi_buf; + } + + papr_groups = kcalloc(num_attrs, sizeof(*papr_groups), GFP_KERNEL); + if (!papr_groups) + goto out_free_esi_buf; + + papr_kobj = kobject_create_and_add("papr", firmware_kobj); + if (!papr_kobj) { + pr_warn("kobject_create_and_add papr failed\n"); + goto out_papr_groups; + } + + esi_kobj = kobject_create_and_add("energy_scale_info", papr_kobj); + if (!esi_kobj) { + pr_warn("kobject_create_and_add energy_scale_info failed\n"); + goto out_kobj; + } + + /* Allocate the groups before registering */ + for (idx = 0; idx < num_attrs; idx++) { + papr_groups[idx].pg.attrs = kcalloc(KOBJ_MAX_ATTRS + 1, + sizeof(*papr_groups[idx].pg.attrs), + GFP_KERNEL); + if (!papr_groups[idx].pg.attrs) + goto out_pgattrs; + + papr_groups[idx].pg.name = kasprintf(GFP_KERNEL, "%lld", + be64_to_cpu(esi_attrs[idx].id)); + if (papr_groups[idx].pg.name == NULL) + goto out_pgattrs; + } + + for (idx = 0; idx < num_attrs; idx++) { + bool show_val_desc = true; + + /* Do not add the value desc attr if it does not exist */ + if (strnlen(esi_attrs[idx].value_desc, + sizeof(esi_attrs[idx].value_desc)) == 0) + show_val_desc = false; + + if (add_attr_group(be64_to_cpu(esi_attrs[idx].id), + &papr_groups[idx], + show_val_desc)) { + pr_warn("Failed to create papr attribute group %s\n", + papr_groups[idx].pg.name); + idx = num_attrs; + goto out_pgattrs; + } + } + + kfree(esi_buf); + return 0; +out_pgattrs: + for (i = 0; i < idx ; i++) { + kfree(papr_groups[i].pg.attrs); + kfree(papr_groups[i].pg.name); + } + kobject_put(esi_kobj); +out_kobj: + kobject_put(papr_kobj); +out_papr_groups: + kfree(papr_groups); +out_free_esi_buf: + kfree(esi_buf); + + return -ENOMEM; +} + +machine_device_initcall(pseries, papr_init); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f48e87ac89c9..1238b94b3cc1 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -120,6 +120,10 @@ struct papr_scm_priv { /* length of the stat buffer as expected by phyp */ size_t stat_buffer_len; + + /* The bits which needs to be overridden */ + u64 health_bitmap_inject_mask; + }; static int papr_scm_pmem_flush(struct nd_region *nd_region, @@ -347,19 +351,29 @@ static ssize_t drc_pmem_query_stats(struct papr_scm_priv *p, static int __drc_pmem_query_health(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; + u64 bitmap = 0; long rc; /* issue the hcall */ rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index); - if (rc != H_SUCCESS) { + if (rc == H_SUCCESS) + bitmap = ret[0] & ret[1]; + else if (rc == H_FUNCTION) + dev_info_once(&p->pdev->dev, + "Hcall H_SCM_HEALTH not implemented, assuming empty health bitmap"); + else { + dev_err(&p->pdev->dev, "Failed to query health information, Err:%ld\n", rc); return -ENXIO; } p->lasthealth_jiffies = jiffies; - p->health_bitmap = ret[0] & ret[1]; - + /* Allow injecting specific health bits via inject mask. */ + if (p->health_bitmap_inject_mask) + bitmap = (bitmap & ~p->health_bitmap_inject_mask) | + p->health_bitmap_inject_mask; + WRITE_ONCE(p->health_bitmap, bitmap); dev_dbg(&p->pdev->dev, "Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n", ret[0], ret[1]); @@ -669,6 +683,56 @@ out: return rc; } +/* Inject a smart error Add the dirty-shutdown-counter value to the pdsm */ +static int papr_pdsm_smart_inject(struct papr_scm_priv *p, + union nd_pdsm_payload *payload) +{ + int rc; + u32 supported_flags = 0; + u64 inject_mask = 0, clear_mask = 0; + u64 mask; + + /* Check for individual smart error flags and update inject/clear masks */ + if (payload->smart_inject.flags & PDSM_SMART_INJECT_HEALTH_FATAL) { + supported_flags |= PDSM_SMART_INJECT_HEALTH_FATAL; + if (payload->smart_inject.fatal_enable) + inject_mask |= PAPR_PMEM_HEALTH_FATAL; + else + clear_mask |= PAPR_PMEM_HEALTH_FATAL; + } + + if (payload->smart_inject.flags & PDSM_SMART_INJECT_BAD_SHUTDOWN) { + supported_flags |= PDSM_SMART_INJECT_BAD_SHUTDOWN; + if (payload->smart_inject.unsafe_shutdown_enable) + inject_mask |= PAPR_PMEM_SHUTDOWN_DIRTY; + else + clear_mask |= PAPR_PMEM_SHUTDOWN_DIRTY; + } + + dev_dbg(&p->pdev->dev, "[Smart-inject] inject_mask=%#llx clear_mask=%#llx\n", + inject_mask, clear_mask); + + /* Prevent concurrent access to dimm health bitmap related members */ + rc = mutex_lock_interruptible(&p->health_mutex); + if (rc) + return rc; + + /* Use inject/clear masks to set health_bitmap_inject_mask */ + mask = READ_ONCE(p->health_bitmap_inject_mask); + mask = (mask & ~clear_mask) | inject_mask; + WRITE_ONCE(p->health_bitmap_inject_mask, mask); + + /* Invalidate cached health bitmap */ + p->lasthealth_jiffies = 0; + + mutex_unlock(&p->health_mutex); + + /* Return the supported flags back to userspace */ + payload->smart_inject.flags = supported_flags; + + return sizeof(struct nd_papr_pdsm_health); +} + /* * 'struct pdsm_cmd_desc' * Identifies supported PDSMs' expected length of in/out payloads @@ -702,6 +766,12 @@ static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = { .size_out = sizeof(struct nd_papr_pdsm_health), .service = papr_pdsm_health, }, + + [PAPR_PDSM_SMART_INJECT] = { + .size_in = sizeof(struct nd_papr_pdsm_smart_inject), + .size_out = sizeof(struct nd_papr_pdsm_smart_inject), + .service = papr_pdsm_smart_inject, + }, /* Empty */ [PAPR_PDSM_MAX] = { .size_in = 0, @@ -838,6 +908,19 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } +static ssize_t health_bitmap_inject_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvdimm *dimm = to_nvdimm(dev); + struct papr_scm_priv *p = nvdimm_provider_data(dimm); + + return sprintf(buf, "%#llx\n", + READ_ONCE(p->health_bitmap_inject_mask)); +} + +static DEVICE_ATTR_ADMIN_RO(health_bitmap_inject); + static ssize_t perf_stats_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -952,10 +1035,11 @@ static struct attribute *papr_nd_attributes[] = { &dev_attr_flags.attr, &dev_attr_perf_stats.attr, &dev_attr_dirty_shutdown.attr, + &dev_attr_health_bitmap_inject.attr, NULL, }; -static struct attribute_group papr_nd_attribute_group = { +static const struct attribute_group papr_nd_attribute_group = { .name = "papr", .is_visible = papr_nd_attribute_visible, .attrs = papr_nd_attributes, diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 90c9d3531694..4ba824568119 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -78,6 +78,9 @@ int remove_phb_dynamic(struct pci_controller *phb) pseries_msi_free_domains(phb); + /* Keep a reference so phb isn't freed yet */ + get_device(&host_bridge->dev); + /* Remove the PCI bus and unregister the bridge device from sysfs */ phb->bus = NULL; pci_remove_bus(b); @@ -101,6 +104,7 @@ int remove_phb_dynamic(struct pci_controller *phb) * the pcibios_free_controller_deferred() callback; * see pseries_root_bridge_prepare(). */ + put_device(&host_bridge->dev); return 0; } diff --git a/arch/powerpc/platforms/pseries/power.c b/arch/powerpc/platforms/pseries/power.c index ee343ec6ab94..3676cb297767 100644 --- a/arch/powerpc/platforms/pseries/power.c +++ b/arch/powerpc/platforms/pseries/power.c @@ -51,7 +51,7 @@ static struct attribute *g[] = { NULL, }; -static struct attribute_group attr_group = { +static const struct attribute_group attr_group = { .attrs = g, }; diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 56c9ef9052e9..af162aeeae86 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -21,6 +21,7 @@ struct pt_regs; extern int pSeries_system_reset_exception(struct pt_regs *regs); extern int pSeries_machine_check_exception(struct pt_regs *regs); extern long pseries_machine_check_realmode(struct pt_regs *regs); +void pSeries_machine_check_log_err(void); #ifdef CONFIG_SMP extern void smp_init_pseries(void); diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 74c9b1b5bc66..f12516c3998c 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -23,11 +23,6 @@ static DEFINE_SPINLOCK(ras_log_buf_lock); static int ras_check_exception_token; -static void mce_process_errlog_event(struct irq_work *work); -static struct irq_work mce_errlog_process_work = { - .func = mce_process_errlog_event, -}; - #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 @@ -60,11 +55,17 @@ struct pseries_mc_errorlog { * XX 2: Reserved. * XXX 3: Type of UE error. * - * For error_type != MC_ERROR_TYPE_UE + * For error_type == MC_ERROR_TYPE_SLB/ERAT/TLB * XXXXXXXX * X 1: Effective address provided. * XXXXX 5: Reserved. * XX 2: Type of SLB/ERAT/TLB error. + * + * For error_type == MC_ERROR_TYPE_CTRL_MEM_ACCESS + * XXXXXXXX + * X 1: Error causing address provided. + * XXX 3: Type of error. + * XXXX 4: Reserved. */ u8 sub_err_type; u8 reserved_1[6]; @@ -80,6 +81,7 @@ struct pseries_mc_errorlog { #define MC_ERROR_TYPE_TLB 0x04 #define MC_ERROR_TYPE_D_CACHE 0x05 #define MC_ERROR_TYPE_I_CACHE 0x07 +#define MC_ERROR_TYPE_CTRL_MEM_ACCESS 0x08 /* RTAS pseries MCE error sub types */ #define MC_ERROR_UE_INDETERMINATE 0 @@ -90,6 +92,7 @@ struct pseries_mc_errorlog { #define UE_EFFECTIVE_ADDR_PROVIDED 0x40 #define UE_LOGICAL_ADDR_PROVIDED 0x20 +#define MC_EFFECTIVE_ADDR_PROVIDED 0x80 #define MC_ERROR_SLB_PARITY 0 #define MC_ERROR_SLB_MULTIHIT 1 @@ -103,6 +106,9 @@ struct pseries_mc_errorlog { #define MC_ERROR_TLB_MULTIHIT 2 #define MC_ERROR_TLB_INDETERMINATE 3 +#define MC_ERROR_CTRL_MEM_ACCESS_PTABLE_WALK 0 +#define MC_ERROR_CTRL_MEM_ACCESS_OP_ACCESS 1 + static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog) { switch (mlog->error_type) { @@ -112,6 +118,8 @@ static inline u8 rtas_mc_error_sub_type(const struct pseries_mc_errorlog *mlog) case MC_ERROR_TYPE_ERAT: case MC_ERROR_TYPE_TLB: return (mlog->sub_err_type & 0x03); + case MC_ERROR_TYPE_CTRL_MEM_ACCESS: + return (mlog->sub_err_type & 0x70) >> 4; default: return 0; } @@ -658,7 +666,7 @@ static int mce_handle_err_virtmode(struct pt_regs *regs, mce_err.u.slb_error_type = MCE_SLB_ERROR_INDETERMINATE; break; } - if (mce_log->sub_err_type & 0x80) + if (mce_log->sub_err_type & MC_EFFECTIVE_ADDR_PROVIDED) eaddr = be64_to_cpu(mce_log->effective_address); break; case MC_ERROR_TYPE_ERAT: @@ -675,7 +683,7 @@ static int mce_handle_err_virtmode(struct pt_regs *regs, mce_err.u.erat_error_type = MCE_ERAT_ERROR_INDETERMINATE; break; } - if (mce_log->sub_err_type & 0x80) + if (mce_log->sub_err_type & MC_EFFECTIVE_ADDR_PROVIDED) eaddr = be64_to_cpu(mce_log->effective_address); break; case MC_ERROR_TYPE_TLB: @@ -692,7 +700,7 @@ static int mce_handle_err_virtmode(struct pt_regs *regs, mce_err.u.tlb_error_type = MCE_TLB_ERROR_INDETERMINATE; break; } - if (mce_log->sub_err_type & 0x80) + if (mce_log->sub_err_type & MC_EFFECTIVE_ADDR_PROVIDED) eaddr = be64_to_cpu(mce_log->effective_address); break; case MC_ERROR_TYPE_D_CACHE: @@ -701,6 +709,21 @@ static int mce_handle_err_virtmode(struct pt_regs *regs, case MC_ERROR_TYPE_I_CACHE: mce_err.error_type = MCE_ERROR_TYPE_ICACHE; break; + case MC_ERROR_TYPE_CTRL_MEM_ACCESS: + mce_err.error_type = MCE_ERROR_TYPE_RA; + switch (err_sub_type) { + case MC_ERROR_CTRL_MEM_ACCESS_PTABLE_WALK: + mce_err.u.ra_error_type = + MCE_RA_ERROR_PAGE_TABLE_WALK_LOAD_STORE_FOREIGN; + break; + case MC_ERROR_CTRL_MEM_ACCESS_OP_ACCESS: + mce_err.u.ra_error_type = + MCE_RA_ERROR_LOAD_STORE_FOREIGN; + break; + } + if (mce_log->sub_err_type & MC_EFFECTIVE_ADDR_PROVIDED) + eaddr = be64_to_cpu(mce_log->effective_address); + break; case MC_ERROR_TYPE_UNKNOWN: default: mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; @@ -717,7 +740,6 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) struct pseries_errorlog *pseries_log; struct pseries_mc_errorlog *mce_log = NULL; int disposition = rtas_error_disposition(errp); - unsigned long msr; u8 error_type; if (!rtas_error_extended(errp)) @@ -731,40 +753,16 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) error_type = mce_log->error_type; disposition = mce_handle_err_realmode(disposition, error_type); - - /* - * Enable translation as we will be accessing per-cpu variables - * in save_mce_event() which may fall outside RMO region, also - * leave it enabled because subsequently we will be queuing work - * to workqueues where again per-cpu variables accessed, besides - * fwnmi_release_errinfo() crashes when called in realmode on - * pseries. - * Note: All the realmode handling like flushing SLB entries for - * SLB multihit is done by now. - */ out: - msr = mfmsr(); - mtmsr(msr | MSR_IR | MSR_DR); - disposition = mce_handle_err_virtmode(regs, errp, mce_log, disposition); - - /* - * Queue irq work to log this rtas event later. - * irq_work_queue uses per-cpu variables, so do this in virt - * mode as well. - */ - irq_work_queue(&mce_errlog_process_work); - - mtmsr(msr); - return disposition; } /* * Process MCE rtas errlog event. */ -static void mce_process_errlog_event(struct irq_work *work) +void pSeries_machine_check_log_err(void) { struct rtas_error_log *err; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 83a04d967a59..069d7b3bb142 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1086,6 +1086,7 @@ define_machine(pseries) { .system_reset_exception = pSeries_system_reset_exception, .machine_check_early = pseries_machine_check_realmode, .machine_check_exception = pSeries_machine_check_exception, + .machine_check_log_err = pSeries_machine_check_log_err, #ifdef CONFIG_KEXEC_CORE .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, diff --git a/arch/powerpc/platforms/pseries/vas-sysfs.c b/arch/powerpc/platforms/pseries/vas-sysfs.c new file mode 100644 index 000000000000..4a7fcde5afc0 --- /dev/null +++ b/arch/powerpc/platforms/pseries/vas-sysfs.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2022-23 IBM Corp. + */ + +#define pr_fmt(fmt) "vas: " fmt + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/miscdevice.h> +#include <linux/kobject.h> +#include <linux/slab.h> +#include <linux/mm.h> + +#include "vas.h" + +#ifdef CONFIG_SYSFS +static struct kobject *pseries_vas_kobj; +static struct kobject *gzip_caps_kobj; + +struct vas_caps_entry { + struct kobject kobj; + struct vas_cop_feat_caps *caps; +}; + +#define to_caps_entry(entry) container_of(entry, struct vas_caps_entry, kobj) + +/* + * This function is used to get the notification from the drmgr when + * QoS credits are changed. Though receiving the target total QoS + * credits here, get the official QoS capabilities from the hypervisor. + */ +static ssize_t update_total_credits_trigger(struct vas_cop_feat_caps *caps, + const char *buf, size_t count) +{ + int err; + u16 creds; + + err = kstrtou16(buf, 0, &creds); + if (!err) + err = vas_reconfig_capabilties(caps->win_type); + + if (err) + return -EINVAL; + + return count; +} + +#define sysfs_caps_entry_read(_name) \ +static ssize_t _name##_show(struct vas_cop_feat_caps *caps, char *buf) \ +{ \ + return sprintf(buf, "%d\n", atomic_read(&caps->_name)); \ +} + +struct vas_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct vas_cop_feat_caps *, char *); + ssize_t (*store)(struct vas_cop_feat_caps *, const char *, size_t); +}; + +#define VAS_ATTR_RO(_name) \ + sysfs_caps_entry_read(_name); \ + static struct vas_sysfs_entry _name##_attribute = __ATTR(_name, \ + 0444, _name##_show, NULL); + +/* + * Create sysfs interface: + * /sys/devices/vas/vas0/gzip/default_capabilities + * This directory contains the following VAS GZIP capabilities + * for the defaule credit type. + * /sys/devices/vas/vas0/gzip/default_capabilities/nr_total_credits + * Total number of default credits assigned to the LPAR which + * can be changed with DLPAR operation. + * /sys/devices/vas/vas0/gzip/default_capabilities/nr_used_credits + * Number of credits used by the user space. One credit will + * be assigned for each window open. + * + * /sys/devices/vas/vas0/gzip/qos_capabilities + * This directory contains the following VAS GZIP capabilities + * for the Quality of Service (QoS) credit type. + * /sys/devices/vas/vas0/gzip/qos_capabilities/nr_total_credits + * Total number of QoS credits assigned to the LPAR. The user + * has to define this value using HMC interface. It can be + * changed dynamically by the user. + * /sys/devices/vas/vas0/gzip/qos_capabilities/nr_used_credits + * Number of credits used by the user space. + * /sys/devices/vas/vas0/gzip/qos_capabilities/update_total_credits + * Update total QoS credits dynamically + */ + +VAS_ATTR_RO(nr_total_credits); +VAS_ATTR_RO(nr_used_credits); + +static struct vas_sysfs_entry update_total_credits_attribute = + __ATTR(update_total_credits, 0200, NULL, update_total_credits_trigger); + +static struct attribute *vas_def_capab_attrs[] = { + &nr_total_credits_attribute.attr, + &nr_used_credits_attribute.attr, + NULL, +}; + +static struct attribute *vas_qos_capab_attrs[] = { + &nr_total_credits_attribute.attr, + &nr_used_credits_attribute.attr, + &update_total_credits_attribute.attr, + NULL, +}; + +static ssize_t vas_type_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct vas_caps_entry *centry; + struct vas_cop_feat_caps *caps; + struct vas_sysfs_entry *entry; + + centry = to_caps_entry(kobj); + caps = centry->caps; + entry = container_of(attr, struct vas_sysfs_entry, attr); + + if (!entry->show) + return -EIO; + + return entry->show(caps, buf); +} + +static ssize_t vas_type_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct vas_caps_entry *centry; + struct vas_cop_feat_caps *caps; + struct vas_sysfs_entry *entry; + + centry = to_caps_entry(kobj); + caps = centry->caps; + entry = container_of(attr, struct vas_sysfs_entry, attr); + if (!entry->store) + return -EIO; + + return entry->store(caps, buf, count); +} + +static void vas_type_release(struct kobject *kobj) +{ + struct vas_caps_entry *centry = to_caps_entry(kobj); + kfree(centry); +} + +static const struct sysfs_ops vas_sysfs_ops = { + .show = vas_type_show, + .store = vas_type_store, +}; + +static struct kobj_type vas_def_attr_type = { + .release = vas_type_release, + .sysfs_ops = &vas_sysfs_ops, + .default_attrs = vas_def_capab_attrs, +}; + +static struct kobj_type vas_qos_attr_type = { + .release = vas_type_release, + .sysfs_ops = &vas_sysfs_ops, + .default_attrs = vas_qos_capab_attrs, +}; + +static char *vas_caps_kobj_name(struct vas_caps_entry *centry, + struct kobject **kobj) +{ + struct vas_cop_feat_caps *caps = centry->caps; + + if (caps->descriptor == VAS_GZIP_QOS_CAPABILITIES) { + kobject_init(¢ry->kobj, &vas_qos_attr_type); + *kobj = gzip_caps_kobj; + return "qos_capabilities"; + } else if (caps->descriptor == VAS_GZIP_DEFAULT_CAPABILITIES) { + kobject_init(¢ry->kobj, &vas_def_attr_type); + *kobj = gzip_caps_kobj; + return "default_capabilities"; + } else + return "Unknown"; +} + +/* + * Add feature specific capability dir entry. + * Ex: VDefGzip or VQosGzip + */ +int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps) +{ + struct vas_caps_entry *centry; + struct kobject *kobj = NULL; + int ret = 0; + char *name; + + centry = kzalloc(sizeof(*centry), GFP_KERNEL); + if (!centry) + return -ENOMEM; + + centry->caps = caps; + name = vas_caps_kobj_name(centry, &kobj); + + if (kobj) { + ret = kobject_add(¢ry->kobj, kobj, "%s", name); + + if (ret) { + pr_err("VAS: sysfs kobject add / event failed %d\n", + ret); + kobject_put(¢ry->kobj); + } + } + + return ret; +} + +static struct miscdevice vas_miscdev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "vas", +}; + +/* + * Add VAS and VasCaps (overall capabilities) dir entries. + */ +int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps) +{ + int ret; + + ret = misc_register(&vas_miscdev); + if (ret < 0) { + pr_err("%s: register vas misc device failed\n", __func__); + return ret; + } + + /* + * The hypervisor does not expose multiple VAS instances, but can + * see multiple VAS instances on PowerNV. So create 'vas0' directory + * on pseries. + */ + pseries_vas_kobj = kobject_create_and_add("vas0", + &vas_miscdev.this_device->kobj); + if (!pseries_vas_kobj) { + pr_err("Failed to create VAS sysfs entry\n"); + return -ENOMEM; + } + + if ((vas_caps->feat_type & VAS_GZIP_QOS_FEAT_BIT) || + (vas_caps->feat_type & VAS_GZIP_DEF_FEAT_BIT)) { + gzip_caps_kobj = kobject_create_and_add("gzip", + pseries_vas_kobj); + if (!gzip_caps_kobj) { + pr_err("Failed to create VAS GZIP capability entry\n"); + kobject_put(pseries_vas_kobj); + return -ENOMEM; + } + } + + return 0; +} + +#else +int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps) +{ + return 0; +} + +int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps) +{ + return 0; +} +#endif diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index d243ddc58827..1f59d78c77a1 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -26,9 +26,11 @@ static struct vas_all_caps caps_all; static bool copypaste_feat; +static struct hv_vas_cop_feat_caps hv_cop_caps; static struct vas_caps vascaps[VAS_MAX_FEAT_TYPE]; static DEFINE_MUTEX(vas_pseries_mutex); +static bool migration_in_progress; static long hcall_return_busy_check(long rc) { @@ -107,7 +109,6 @@ static int h_deallocate_vas_window(u64 winid) static int h_modify_vas_window(struct pseries_vas_window *win) { long rc; - u32 lpid = mfspr(SPRN_PID); /* * AMR value is not supported in Linux VAS implementation. @@ -115,7 +116,7 @@ static int h_modify_vas_window(struct pseries_vas_window *win) */ do { rc = plpar_hcall_norets(H_MODIFY_VAS_WINDOW, - win->vas_win.winid, lpid, 0, + win->vas_win.winid, win->pid, 0, VAS_MOD_WIN_FLAGS, 0); rc = hcall_return_busy_check(rc); @@ -124,8 +125,8 @@ static int h_modify_vas_window(struct pseries_vas_window *win) if (rc == H_SUCCESS) return 0; - pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u lpid %u\n", - rc, win->vas_win.winid, lpid); + pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u pid %u\n", + rc, win->vas_win.winid, win->pid); return -EIO; } @@ -310,8 +311,8 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, cop_feat_caps = &caps->caps; - if (atomic_inc_return(&cop_feat_caps->used_lpar_creds) > - atomic_read(&cop_feat_caps->target_lpar_creds)) { + if (atomic_inc_return(&cop_feat_caps->nr_used_credits) > + atomic_read(&cop_feat_caps->nr_total_credits)) { pr_err("Credits are not available to allocate window\n"); rc = -EINVAL; goto out; @@ -338,6 +339,8 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, } } + txwin->pid = mfspr(SPRN_PID); + /* * Allocate / Deallocate window hcalls and setup / free IRQs * have to be protected with mutex. @@ -354,7 +357,10 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - rc = allocate_setup_window(txwin, (u64 *)&domain[0], + if (migration_in_progress) + rc = -EBUSY; + else + rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); mutex_unlock(&vas_pseries_mutex); if (rc) @@ -369,13 +375,28 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, if (rc) goto out_free; - vas_user_win_add_mm_context(&txwin->vas_win.task_ref); txwin->win_type = cop_feat_caps->win_type; mutex_lock(&vas_pseries_mutex); - list_add(&txwin->win_list, &caps->list); + /* + * Possible to lose the acquired credit with DLPAR core + * removal after the window is opened. So if there are any + * closed windows (means with lost credits), do not give new + * window to user space. New windows will be opened only + * after the existing windows are reopened when credits are + * available. + */ + if (!caps->nr_close_wins) { + list_add(&txwin->win_list, &caps->list); + caps->nr_open_windows++; + mutex_unlock(&vas_pseries_mutex); + vas_user_win_add_mm_context(&txwin->vas_win.task_ref); + return &txwin->vas_win; + } mutex_unlock(&vas_pseries_mutex); - return &txwin->vas_win; + put_vas_user_win_ref(&txwin->vas_win.task_ref); + rc = -EBUSY; + pr_err("No credit is available to allocate window\n"); out_free: /* @@ -385,7 +406,7 @@ out_free: free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); out: - atomic_dec(&cop_feat_caps->used_lpar_creds); + atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); return ERR_PTR(rc); } @@ -438,14 +459,25 @@ static int vas_deallocate_window(struct vas_window *vwin) caps = &vascaps[win->win_type].caps; mutex_lock(&vas_pseries_mutex); - rc = deallocate_free_window(win); - if (rc) { - mutex_unlock(&vas_pseries_mutex); - return rc; - } + /* + * VAS window is already closed in the hypervisor when + * lost the credit or with migration. So just remove the entry + * from the list, remove task references and free vas_window + * struct. + */ + if (!(win->vas_win.status & VAS_WIN_NO_CRED_CLOSE) && + !(win->vas_win.status & VAS_WIN_MIGRATE_CLOSE)) { + rc = deallocate_free_window(win); + if (rc) { + mutex_unlock(&vas_pseries_mutex); + return rc; + } + } else + vascaps[win->win_type].nr_close_wins--; list_del(&win->win_list); - atomic_dec(&caps->used_lpar_creds); + atomic_dec(&caps->nr_used_credits); + vascaps[win->win_type].nr_open_windows--; mutex_unlock(&vas_pseries_mutex); put_vas_user_win_ref(&vwin->task_ref); @@ -500,6 +532,7 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, memset(vcaps, 0, sizeof(*vcaps)); INIT_LIST_HEAD(&vcaps->list); + vcaps->feat = feat; caps = &vcaps->caps; rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, feat, @@ -521,7 +554,7 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, } caps->max_lpar_creds = be16_to_cpu(hv_caps->max_lpar_creds); caps->max_win_creds = be16_to_cpu(hv_caps->max_win_creds); - atomic_set(&caps->target_lpar_creds, + atomic_set(&caps->nr_total_credits, be16_to_cpu(hv_caps->target_lpar_creds)); if (feat == VAS_GZIP_DEF_FEAT) { caps->def_lpar_creds = be16_to_cpu(hv_caps->def_lpar_creds); @@ -533,16 +566,409 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, } } + rc = sysfs_add_vas_caps(caps); + if (rc) + return rc; + copypaste_feat = true; return 0; } +/* + * VAS windows can be closed due to lost credits when the core is + * removed. So reopen them if credits are available due to DLPAR + * core add and set the window active status. When NX sees the page + * fault on the unmapped paste address, the kernel handles the fault + * by setting the remapping to new paste address if the window is + * active. + */ +static int reconfig_open_windows(struct vas_caps *vcaps, int creds, + bool migrate) +{ + long domain[PLPAR_HCALL9_BUFSIZE] = {VAS_DEFAULT_DOMAIN_ID}; + struct vas_cop_feat_caps *caps = &vcaps->caps; + struct pseries_vas_window *win = NULL, *tmp; + int rc, mv_ents = 0; + int flag; + + /* + * Nothing to do if there are no closed windows. + */ + if (!vcaps->nr_close_wins) + return 0; + + /* + * For the core removal, the hypervisor reduces the credits + * assigned to the LPAR and the kernel closes VAS windows + * in the hypervisor depends on reduced credits. The kernel + * uses LIFO (the last windows that are opened will be closed + * first) and expects to open in the same order when credits + * are available. + * For example, 40 windows are closed when the LPAR lost 2 cores + * (dedicated). If 1 core is added, this LPAR can have 20 more + * credits. It means the kernel can reopen 20 windows. So move + * 20 entries in the VAS windows lost and reopen next 20 windows. + * For partition migration, reopen all windows that are closed + * during resume. + */ + if ((vcaps->nr_close_wins > creds) && !migrate) + mv_ents = vcaps->nr_close_wins - creds; + + list_for_each_entry_safe(win, tmp, &vcaps->list, win_list) { + if (!mv_ents) + break; + + mv_ents--; + } + + /* + * Open windows if they are closed only with migration or + * DLPAR (lost credit) before. + */ + if (migrate) + flag = VAS_WIN_MIGRATE_CLOSE; + else + flag = VAS_WIN_NO_CRED_CLOSE; + + list_for_each_entry_safe_from(win, tmp, &vcaps->list, win_list) { + /* + * This window is closed with DLPAR and migration events. + * So reopen the window with the last event. + * The user space is not suspended with the current + * migration notifier. So the user space can issue DLPAR + * CPU hotplug while migration in progress. In this case + * this window will be opened with the last event. + */ + if ((win->vas_win.status & VAS_WIN_NO_CRED_CLOSE) && + (win->vas_win.status & VAS_WIN_MIGRATE_CLOSE)) { + win->vas_win.status &= ~flag; + continue; + } + + /* + * Nothing to do on this window if it is not closed + * with this flag + */ + if (!(win->vas_win.status & flag)) + continue; + + rc = allocate_setup_window(win, (u64 *)&domain[0], + caps->win_type); + if (rc) + return rc; + + rc = h_modify_vas_window(win); + if (rc) + goto out; + + mutex_lock(&win->vas_win.task_ref.mmap_mutex); + /* + * Set window status to active + */ + win->vas_win.status &= ~flag; + mutex_unlock(&win->vas_win.task_ref.mmap_mutex); + win->win_type = caps->win_type; + if (!--vcaps->nr_close_wins) + break; + } + + return 0; +out: + /* + * Window modify HCALL failed. So close the window to the + * hypervisor and return. + */ + free_irq_setup(win); + h_deallocate_vas_window(win->vas_win.winid); + return rc; +} + +/* + * The hypervisor reduces the available credits if the LPAR lost core. It + * means the excessive windows should not be active and the user space + * should not be using these windows to send compression requests to NX. + * So the kernel closes the excessive windows and unmap the paste address + * such that the user space receives paste instruction failure. Then up to + * the user space to fall back to SW compression and manage with the + * existing windows. + */ +static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, + bool migrate) +{ + struct pseries_vas_window *win, *tmp; + struct vas_user_win_ref *task_ref; + struct vm_area_struct *vma; + int rc = 0, flag; + + if (migrate) + flag = VAS_WIN_MIGRATE_CLOSE; + else + flag = VAS_WIN_NO_CRED_CLOSE; + + list_for_each_entry_safe(win, tmp, &vcap->list, win_list) { + /* + * This window is already closed due to lost credit + * or for migration before. Go for next window. + * For migration, nothing to do since this window + * closed for DLPAR and will be reopened even on + * the destination system with other DLPAR operation. + */ + if ((win->vas_win.status & VAS_WIN_MIGRATE_CLOSE) || + (win->vas_win.status & VAS_WIN_NO_CRED_CLOSE)) { + win->vas_win.status |= flag; + continue; + } + + task_ref = &win->vas_win.task_ref; + mutex_lock(&task_ref->mmap_mutex); + vma = task_ref->vma; + /* + * Number of available credits are reduced, So select + * and close windows. + */ + win->vas_win.status |= flag; + + mmap_write_lock(task_ref->mm); + /* + * vma is set in the original mapping. But this mapping + * is done with mmap() after the window is opened with ioctl. + * so we may not see the original mapping if the core remove + * is done before the original mmap() and after the ioctl. + */ + if (vma) + zap_page_range(vma, vma->vm_start, + vma->vm_end - vma->vm_start); + + mmap_write_unlock(task_ref->mm); + mutex_unlock(&task_ref->mmap_mutex); + /* + * Close VAS window in the hypervisor, but do not + * free vas_window struct since it may be reused + * when the credit is available later (DLPAR with + * adding cores). This struct will be used + * later when the process issued with close(FD). + */ + rc = deallocate_free_window(win); + /* + * This failure is from the hypervisor. + * No way to stop migration for these failures. + * So ignore error and continue closing other windows. + */ + if (rc && !migrate) + return rc; + + vcap->nr_close_wins++; + + /* + * For migration, do not depend on lpar_creds in case if + * mismatch with the hypervisor value (should not happen). + * So close all active windows in the list and will be + * reopened windows based on the new lpar_creds on the + * destination system during resume. + */ + if (!migrate && !--excess_creds) + break; + } + + return 0; +} + +/* + * Get new VAS capabilities when the core add/removal configuration + * changes. Reconfig window configurations based on the credits + * availability from this new capabilities. + */ +int vas_reconfig_capabilties(u8 type) +{ + struct vas_cop_feat_caps *caps; + int old_nr_creds, new_nr_creds; + struct vas_caps *vcaps; + int rc = 0, nr_active_wins; + + if (type >= VAS_MAX_FEAT_TYPE) { + pr_err("Invalid credit type %d\n", type); + return -EINVAL; + } + + vcaps = &vascaps[type]; + caps = &vcaps->caps; + + mutex_lock(&vas_pseries_mutex); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (rc) + goto out; + + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + + old_nr_creds = atomic_read(&caps->nr_total_credits); + + atomic_set(&caps->nr_total_credits, new_nr_creds); + /* + * The total number of available credits may be decreased or + * inceased with DLPAR operation. Means some windows have to be + * closed / reopened. Hold the vas_pseries_mutex so that the + * the user space can not open new windows. + */ + if (old_nr_creds < new_nr_creds) { + /* + * If the existing target credits is less than the new + * target, reopen windows if they are closed due to + * the previous DLPAR (core removal). + */ + rc = reconfig_open_windows(vcaps, new_nr_creds - old_nr_creds, + false); + } else { + /* + * # active windows is more than new LPAR available + * credits. So close the excessive windows. + * On pseries, each window will have 1 credit. + */ + nr_active_wins = vcaps->nr_open_windows - vcaps->nr_close_wins; + if (nr_active_wins > new_nr_creds) + rc = reconfig_close_windows(vcaps, + nr_active_wins - new_nr_creds, + false); + } + +out: + mutex_unlock(&vas_pseries_mutex); + return rc; +} +/* + * Total number of default credits available (target_credits) + * in LPAR depends on number of cores configured. It varies based on + * whether processors are in shared mode or dedicated mode. + * Get the notifier when CPU configuration is changed with DLPAR + * operation so that get the new target_credits (vas default capabilities) + * and then update the existing windows usage if needed. + */ +static int pseries_vas_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct of_reconfig_data *rd = data; + struct device_node *dn = rd->dn; + const __be32 *intserv = NULL; + int len, rc = 0; + + if ((action == OF_RECONFIG_ATTACH_NODE) || + (action == OF_RECONFIG_DETACH_NODE)) + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", + &len); + /* + * Processor config is not changed + */ + if (!intserv) + return NOTIFY_OK; + + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + if (rc) + pr_err("Failed reconfig VAS capabilities with DLPAR\n"); + + return rc; +} + +static struct notifier_block pseries_vas_nb = { + .notifier_call = pseries_vas_notifier, +}; + +/* + * For LPM, all windows have to be closed on the source partition + * before migration and reopen them on the destination partition + * after migration. So closing windows during suspend and + * reopen them during resume. + */ +int vas_migration_handler(int action) +{ + struct vas_cop_feat_caps *caps; + int old_nr_creds, new_nr_creds = 0; + struct vas_caps *vcaps; + int i, rc = 0; + + /* + * NX-GZIP is not enabled. Nothing to do for migration. + */ + if (!copypaste_feat) + return rc; + + mutex_lock(&vas_pseries_mutex); + + if (action == VAS_SUSPEND) + migration_in_progress = true; + else + migration_in_progress = false; + + for (i = 0; i < VAS_MAX_FEAT_TYPE; i++) { + vcaps = &vascaps[i]; + caps = &vcaps->caps; + old_nr_creds = atomic_read(&caps->nr_total_credits); + + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vcaps->feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + /* + * Should not happen. But incase print messages, close + * all windows in the list during suspend and reopen + * windows based on new lpar_creds on the destination + * system. + */ + if (old_nr_creds != new_nr_creds) { + pr_err("Target credits mismatch with the hypervisor\n"); + pr_err("state(%d): lpar creds: %d HV lpar creds: %d\n", + action, old_nr_creds, new_nr_creds); + pr_err("Used creds: %d, Active creds: %d\n", + atomic_read(&caps->nr_used_credits), + vcaps->nr_open_windows - vcaps->nr_close_wins); + } + } else { + pr_err("state(%d): Get VAS capabilities failed with %d\n", + action, rc); + /* + * We can not stop migration with the current lpm + * implementation. So continue closing all windows in + * the list (during suspend) and return without + * opening windows (during resume) if VAS capabilities + * HCALL failed. + */ + if (action == VAS_RESUME) + goto out; + } + + switch (action) { + case VAS_SUSPEND: + rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, + true); + break; + case VAS_RESUME: + atomic_set(&caps->nr_total_credits, new_nr_creds); + rc = reconfig_open_windows(vcaps, new_nr_creds, true); + break; + default: + /* should not happen */ + pr_err("Invalid migration action %d\n", action); + rc = -EINVAL; + goto out; + } + + /* + * Ignore errors during suspend and return for resume. + */ + if (rc && (action == VAS_RESUME)) + goto out; + } + +out: + mutex_unlock(&vas_pseries_mutex); + return rc; +} + static int __init pseries_vas_init(void) { - struct hv_vas_cop_feat_caps *hv_cop_caps; struct hv_vas_all_caps *hv_caps; - int rc; + int rc = 0; /* * Linux supports user space COPY/PASTE only with Radix @@ -566,35 +992,39 @@ static int __init pseries_vas_init(void) caps_all.descriptor = be64_to_cpu(hv_caps->descriptor); caps_all.feat_type = be64_to_cpu(hv_caps->feat_type); - hv_cop_caps = kmalloc(sizeof(*hv_cop_caps), GFP_KERNEL); - if (!hv_cop_caps) { - rc = -ENOMEM; - goto out; - } + sysfs_pseries_vas_init(&caps_all); + /* * QOS capabilities available */ if (caps_all.feat_type & VAS_GZIP_QOS_FEAT_BIT) { rc = get_vas_capabilities(VAS_GZIP_QOS_FEAT, - VAS_GZIP_QOS_FEAT_TYPE, hv_cop_caps); + VAS_GZIP_QOS_FEAT_TYPE, &hv_cop_caps); if (rc) - goto out_cop; + goto out; } /* * Default capabilities available */ - if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) { + if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) rc = get_vas_capabilities(VAS_GZIP_DEF_FEAT, - VAS_GZIP_DEF_FEAT_TYPE, hv_cop_caps); - if (rc) - goto out_cop; - } + VAS_GZIP_DEF_FEAT_TYPE, &hv_cop_caps); + + if (!rc && copypaste_feat) { + if (firmware_has_feature(FW_FEATURE_LPAR)) + of_reconfig_notifier_register(&pseries_vas_nb); - pr_info("GZIP feature is available\n"); + pr_info("GZIP feature is available\n"); + } else { + /* + * Should not happen, but only when get default + * capabilities HCALL failed. So disable copy paste + * feature. + */ + copypaste_feat = false; + } -out_cop: - kfree(hv_cop_caps); out: kfree(hv_caps); return rc; diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h index 4ecb3fcabd10..34177881e998 100644 --- a/arch/powerpc/platforms/pseries/vas.h +++ b/arch/powerpc/platforms/pseries/vas.h @@ -30,6 +30,14 @@ #define VAS_COPY_PASTE_USER_MODE 0x00000001 #define VAS_COP_OP_USER_MODE 0x00000010 +#define VAS_GZIP_QOS_CAPABILITIES 0x56516F73477A6970 +#define VAS_GZIP_DEFAULT_CAPABILITIES 0x56446566477A6970 + +enum vas_migrate_action { + VAS_SUSPEND, + VAS_RESUME, +}; + /* * Co-processor feature - GZIP QoS windows or GZIP default windows */ @@ -72,9 +80,8 @@ struct vas_cop_feat_caps { }; /* Total LPAR available credits. Can be different from max LPAR */ /* credits due to DLPAR operation */ - atomic_t target_lpar_creds; - atomic_t used_lpar_creds; /* Used credits so far */ - u16 avail_lpar_creds; /* Remaining available credits */ + atomic_t nr_total_credits; /* Total credits assigned to LPAR */ + atomic_t nr_used_credits; /* Used credits so far */ }; /* @@ -84,6 +91,9 @@ struct vas_cop_feat_caps { struct vas_caps { struct vas_cop_feat_caps caps; struct list_head list; /* List of open windows */ + int nr_close_wins; /* closed windows in the hypervisor for DLPAR */ + int nr_open_windows; /* Number of successful open windows */ + u8 feat; /* Feature type */ }; /* @@ -115,6 +125,7 @@ struct pseries_vas_window { u64 domain[6]; /* Associativity domain Ids */ /* this window is allocated */ u64 util; + u32 pid; /* PID associated with this window */ /* List of windows opened which is used for LPM */ struct list_head win_list; @@ -122,4 +133,17 @@ struct pseries_vas_window { char *name; int fault_virq; }; + +int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps); +int vas_reconfig_capabilties(u8 type); +int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps); + +#ifdef CONFIG_PPC_VAS +int vas_migration_handler(int action); +#else +static inline int vas_migration_handler(int action) +{ + return 0; +} +#endif #endif /* _VAS_H */ diff --git a/arch/powerpc/sysdev/fsl_gtm.c b/arch/powerpc/sysdev/fsl_gtm.c index 8963eaffb1b7..39186ad6b3c3 100644 --- a/arch/powerpc/sysdev/fsl_gtm.c +++ b/arch/powerpc/sysdev/fsl_gtm.c @@ -86,7 +86,7 @@ static LIST_HEAD(gtms); */ struct gtm_timer *gtm_get_timer16(void) { - struct gtm *gtm = NULL; + struct gtm *gtm; int i; list_for_each_entry(gtm, >ms, list_node) { @@ -103,7 +103,7 @@ struct gtm_timer *gtm_get_timer16(void) spin_unlock_irq(>m->lock); } - if (gtm) + if (!list_empty(>ms)) return ERR_PTR(-EBUSY); return ERR_PTR(-ENODEV); } diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c index d5cb48b61bbd..dbcbaa4c0663 100644 --- a/arch/powerpc/sysdev/mpic.c +++ b/arch/powerpc/sysdev/mpic.c @@ -1404,10 +1404,8 @@ struct mpic * __init mpic_alloc(struct device_node *node, * with device trees generated by older versions of QEMU. * fsl_version will be zero if MPIC_FSL is not set. */ - if (fsl_version < 0x400 && (flags & MPIC_ENABLE_COREINT)) { - WARN_ON(ppc_md.get_irq != mpic_get_coreint_irq); + if (fsl_version < 0x400 && (flags & MPIC_ENABLE_COREINT)) ppc_md.get_irq = mpic_get_irq; - } /* Reset */ diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 1ca5564bda9d..bb5bda6b2357 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1708,20 +1708,20 @@ __be32 *xive_queue_page_alloc(unsigned int cpu, u32 queue_shift) static int __init xive_off(char *arg) { xive_cmdline_disabled = true; - return 0; + return 1; } __setup("xive=off", xive_off); static int __init xive_store_eoi_cmdline(char *arg) { if (!arg) - return -EINVAL; + return 1; if (strncmp(arg, "off", 3) == 0) { pr_info("StoreEOI disabled on kernel command line\n"); xive_store_eoi = false; } - return 0; + return 1; } __setup("xive.store-eoi=", xive_store_eoi_cmdline); @@ -1791,7 +1791,7 @@ static int xive_ipi_debug_show(struct seq_file *m, void *private) if (xive_ops->debug_show) xive_ops->debug_show(m, private); - for_each_possible_cpu(cpu) + for_each_online_cpu(cpu) xive_debug_show_ipi(m, cpu); return 0; } diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c index 928f95004501..29456c255f9f 100644 --- a/arch/powerpc/sysdev/xive/spapr.c +++ b/arch/powerpc/sysdev/xive/spapr.c @@ -67,6 +67,17 @@ static int __init xive_irq_bitmap_add(int base, int count) return 0; } +static void xive_irq_bitmap_remove_all(void) +{ + struct xive_irq_bitmap *xibm, *tmp; + + list_for_each_entry_safe(xibm, tmp, &xive_irq_bitmaps, list) { + list_del(&xibm->list); + kfree(xibm->bitmap); + kfree(xibm); + } +} + static int __xive_irq_bitmap_alloc(struct xive_irq_bitmap *xibm) { int irq; @@ -803,7 +814,7 @@ bool __init xive_spapr_init(void) u32 val; u32 len; const __be32 *reg; - int i; + int i, err; if (xive_spapr_disabled()) return false; @@ -828,23 +839,26 @@ bool __init xive_spapr_init(void) } if (!xive_get_max_prio(&max_prio)) - return false; + goto err_unmap; /* Feed the IRQ number allocator with the ranges given in the DT */ reg = of_get_property(np, "ibm,xive-lisn-ranges", &len); if (!reg) { pr_err("Failed to read 'ibm,xive-lisn-ranges' property\n"); - return false; + goto err_unmap; } if (len % (2 * sizeof(u32)) != 0) { pr_err("invalid 'ibm,xive-lisn-ranges' property\n"); - return false; + goto err_unmap; } - for (i = 0; i < len / (2 * sizeof(u32)); i++, reg += 2) - xive_irq_bitmap_add(be32_to_cpu(reg[0]), - be32_to_cpu(reg[1])); + for (i = 0; i < len / (2 * sizeof(u32)); i++, reg += 2) { + err = xive_irq_bitmap_add(be32_to_cpu(reg[0]), + be32_to_cpu(reg[1])); + if (err < 0) + goto err_mem_free; + } /* Iterate the EQ sizes and pick one */ of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) { @@ -855,10 +869,16 @@ bool __init xive_spapr_init(void) /* Initialize XIVE core with our backend */ if (!xive_core_init(np, &xive_spapr_ops, tima, TM_QW1_OS, max_prio)) - return false; + goto err_mem_free; pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10)); return true; + +err_mem_free: + xive_irq_bitmap_remove_all(); +err_unmap: + iounmap(tima); + return false; } machine_arch_initcall(pseries, xive_core_debug_init); diff --git a/arch/powerpc/tools/relocs_check.sh b/arch/powerpc/tools/relocs_check.sh index 014e00e74d2b..63792af00417 100755 --- a/arch/powerpc/tools/relocs_check.sh +++ b/arch/powerpc/tools/relocs_check.sh @@ -39,6 +39,7 @@ $objdump -R "$vmlinux" | # R_PPC_NONE grep -F -w -v 'R_PPC64_RELATIVE R_PPC64_NONE +R_PPC64_UADDR64 R_PPC_ADDR16_LO R_PPC_ADDR16_HI R_PPC_ADDR16_HA @@ -54,9 +55,3 @@ fi num_bad=$(echo "$bad_relocs" | wc -l) echo "WARNING: $num_bad bad relocations" echo "$bad_relocs" - -# If we see this type of relocation it's an idication that -# we /may/ be using an old version of binutils. -if echo "$bad_relocs" | grep -q -F -w R_PPC64_UADDR64; then - echo "WARNING: You need at least binutils >= 2.19 to build a CONFIG_RELOCATABLE kernel" -fi |