diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-16 12:21:15 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-16 12:21:15 -0700 |
| commit | 96685f8666714233d34abb71b242448c80077536 (patch) | |
| tree | 70ef4b4acc88b45ffcf5ebf57e0031b69a76e5d2 /arch | |
| parent | c4cf498dc0241fa2d758dba177634268446afb06 (diff) | |
| parent | ffd0b25ca049a477cb757e5bcf2d5e1664d12e5d (diff) | |
| download | linux-96685f8666714233d34abb71b242448c80077536.tar.bz2 | |
Merge tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
- A series from Nick adding ARCH_WANT_IRQS_OFF_ACTIVATE_MM & selecting
it for powerpc, as well as a related fix for sparc.
- Remove support for PowerPC 601.
- Some fixes for watchpoints & addition of a new ptrace flag for
detecting ISA v3.1 (Power10) watchpoint features.
- A fix for kernels using 4K pages and the hash MMU on bare metal
Power9 systems with > 16TB of RAM, or RAM on the 2nd node.
- A basic idle driver for shallow stop states on Power10.
- Tweaks to our sched domains code to better inform the scheduler about
the hardware topology on Power9/10, where two SMT4 cores can be
presented by firmware as an SMT8 core.
- A series doing further reworks & cleanups of our EEH code.
- Addition of a filter for RTAS (firmware) calls done via sys_rtas(),
to prevent root from overwriting kernel memory.
- Other smaller features, fixes & cleanups.
Thanks to: Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
Athira Rajeev, Biwen Li, Cameron Berkenpas, Cédric Le Goater, Christophe
Leroy, Christoph Hellwig, Colin Ian King, Daniel Axtens, David Dai, Finn
Thain, Frederic Barrat, Gautham R. Shenoy, Greg Kurz, Gustavo Romero,
Ira Weiny, Jason Yan, Joel Stanley, Jordan Niethe, Kajol Jain, Konrad
Rzeszutek Wilk, Laurent Dufour, Leonardo Bras, Liu Shixin, Luca
Ceresoli, Madhavan Srinivasan, Mahesh Salgaonkar, Nathan Lynch, Nicholas
Mc Guire, Nicholas Piggin, Nick Desaulniers, Oliver O'Halloran, Pedro
Miraglia Franco de Carvalho, Pratik Rajesh Sampat, Qian Cai, Qinglang
Miao, Ravi Bangoria, Russell Currey, Satheesh Rajendran, Scott Cheloha,
Segher Boessenkool, Srikar Dronamraju, Stan Johnson, Stephen Kitt,
Stephen Rothwell, Thiago Jung Bauermann, Tyrel Datwyler, Vaibhav Jain,
Vaidyanathan Srinivasan, Vasant Hegde, Wang Wensheng, Wolfram Sang, Yang
Yingliang, zhengbin.
* tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (228 commits)
Revert "powerpc/pci: unmap legacy INTx interrupts when a PHB is removed"
selftests/powerpc: Fix eeh-basic.sh exit codes
cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_reboot_notifier
powerpc/time: Make get_tb() common to PPC32 and PPC64
powerpc/time: Make get_tbl() common to PPC32 and PPC64
powerpc/time: Remove get_tbu()
powerpc/time: Avoid using get_tbl() and get_tbu() internally
powerpc/time: Make mftb() common to PPC32 and PPC64
powerpc/time: Rename mftbl() to mftb()
powerpc/32s: Remove #ifdef CONFIG_PPC_BOOK3S_32 in head_book3s_32.S
powerpc/32s: Rename head_32.S to head_book3s_32.S
powerpc/32s: Setup the early hash table at all time.
powerpc/time: Remove ifdef in get_dec() and set_dec()
powerpc: Remove get_tb_or_rtc()
powerpc: Remove __USE_RTC()
powerpc: Tidy up a bit after removal of PowerPC 601.
powerpc: Remove support for PowerPC 601
powerpc: Remove PowerPC 601
powerpc: Drop SYNC_601() ISYNC_601() and SYNC()
powerpc: Remove CONFIG_PPC601_SYNC_FIX
...
Diffstat (limited to 'arch')
171 files changed, 2660 insertions, 2361 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 8519d9f42e33..958be0531eb9 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -420,6 +420,13 @@ config MMU_GATHER_NO_GATHER bool depends on MMU_GATHER_TABLE_FREE +config ARCH_WANT_IRQS_OFF_ACTIVATE_MM + bool + help + Temporary select until all architectures can be converted to have + irqs disabled over activate_mm. Architectures that do IPI based TLB + shootdowns should enable this. + config ARCH_HAVE_NMI_SAFE_CMPXCHG bool diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 1f0bd7e223f5..e9f13fe08492 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -59,7 +59,10 @@ config HAVE_SETUP_PER_CPU_AREA def_bool PPC64 config NEED_PER_CPU_EMBED_FIRST_CHUNK - def_bool PPC64 + def_bool y if PPC64 + +config NEED_PER_CPU_PAGE_FIRST_CHUNK + def_bool y if PPC64 config NR_IRQS int "Number of virtual interrupt numbers" @@ -148,6 +151,7 @@ config PPC select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS select ARCH_WANT_IPC_PARSE_VERSION + select ARCH_WANT_IRQS_OFF_ACTIVATE_MM select ARCH_WEAK_RELEASE_ACQUIRE select BINFMT_ELF select BUILDTIME_TABLE_SORT @@ -964,7 +968,7 @@ config PPC_MEM_KEYS config PPC_SECURE_BOOT prompt "Enable secure boot support" bool - depends on PPC_POWERNV + depends on PPC_POWERNV || PPC_PSERIES depends on IMA_ARCH_POLICY imply IMA_SECURE_AND_OR_TRUSTED_BOOT help @@ -984,6 +988,19 @@ config PPC_SECVAR_SYSFS read/write operations on these variables. Say Y if you have secure boot enabled and want to expose variables to userspace. +config PPC_RTAS_FILTER + bool "Enable filtering of RTAS syscalls" + default y + depends on PPC_RTAS + help + The RTAS syscall API has security issues that could be used to + compromise system integrity. This option enforces restrictions on the + RTAS calls and arguments passed by userspace programs to mitigate + these issues. + + Say Y unless you know what you are doing and the filter is causing + problems for you. + endmenu config ISA_DMA_API diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 3e8da9cf2eb9..c4f9dbd12577 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -264,7 +264,8 @@ KBUILD_CFLAGS += $(cpu-as-y) KBUILD_AFLAGS += $(aflags-y) KBUILD_CFLAGS += $(cflags-y) -head-y := arch/powerpc/kernel/head_$(BITS).o +head-$(CONFIG_PPC64) := arch/powerpc/kernel/head_64.o +head-$(CONFIG_PPC_BOOK3S_32) := arch/powerpc/kernel/head_book3s_32.o head-$(CONFIG_PPC_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o head-$(CONFIG_44x) := arch/powerpc/kernel/head_44x.o diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 2268396ff4bb..a6c77f4d32b2 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -18,7 +18,7 @@ quiet_cmd_relocs_check = CHKREL $@ ifdef CONFIG_PPC_BOOK3S_64 cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" ; \ - $(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$@" + $(BASH) $(srctree)/arch/powerpc/tools/unrel_branch_check.sh "$(OBJDUMP)" "$(NM)" "$@" else cmd_relocs_check = \ $(CONFIG_SHELL) $(srctree)/arch/powerpc/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index b88fd27a45f0..f8ce6d2dde7b 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -7,7 +7,7 @@ # Based on coffboot by Paul Mackerras # Simplified for ppc64 by Todd Inglett # -# NOTE: this code is built for 32 bit in ELF32 format even though +# NOTE: this code may be built for 32 bit in ELF32 format even though # it packages a 64 bit kernel. We do this to simplify the # bootloader and increase compatibility with OpenFirmware. # diff --git a/arch/powerpc/boot/dts/fsl/t1024rdb.dts b/arch/powerpc/boot/dts/fsl/t1024rdb.dts index 73a645324bc1..dbcd31cc35dc 100644 --- a/arch/powerpc/boot/dts/fsl/t1024rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t1024rdb.dts @@ -161,7 +161,6 @@ rtc@68 { compatible = "dallas,ds1339"; reg = <0x68>; - interrupts = <0x1 0x1 0 0>; }; }; diff --git a/arch/powerpc/boot/dts/fsl/t4240rdb.dts b/arch/powerpc/boot/dts/fsl/t4240rdb.dts index a56a705d41f7..145896f2eef6 100644 --- a/arch/powerpc/boot/dts/fsl/t4240rdb.dts +++ b/arch/powerpc/boot/dts/fsl/t4240rdb.dts @@ -144,7 +144,6 @@ rtc@68 { compatible = "dallas,ds1374"; reg = <0x68>; - interrupts = <0x1 0x1 0 0>; }; }; diff --git a/arch/powerpc/boot/util.S b/arch/powerpc/boot/util.S index f11f0589a669..d03cdb7606dc 100644 --- a/arch/powerpc/boot/util.S +++ b/arch/powerpc/boot/util.S @@ -18,7 +18,7 @@ .text -/* udelay (on non-601 processors) needs to know the period of the +/* udelay needs to know the period of the * timebase in nanoseconds. This used to be hardcoded to be 60ns * (period of 66MHz/4). Now a variable is used that is initialized to * 60 for backward compatibility, but it can be overridden as necessary @@ -37,19 +37,6 @@ timebase_period_ns: */ .globl udelay udelay: - mfspr r4,SPRN_PVR - srwi r4,r4,16 - cmpwi 0,r4,1 /* 601 ? */ - bne .Ludelay_not_601 -00: li r0,86 /* Instructions / microsecond? */ - mtctr r0 -10: addi r0,r0,0 /* NOP */ - bdnz 10b - subic. r3,r3,1 - bne 00b - blr - -.Ludelay_not_601: mulli r4,r3,1000 /* nanoseconds */ /* Change r4 to be the number of ticks using: * (nanoseconds + (timebase_period_ns - 1 )) / timebase_period_ns diff --git a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig index 0683d8c292a8..cea72e85ed26 100644 --- a/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig +++ b/arch/powerpc/configs/85xx/mpc85xx_cds_defconfig @@ -29,9 +29,9 @@ CONFIG_SYN_COOKIES=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E1000=y diff --git a/arch/powerpc/configs/85xx/tqm8540_defconfig b/arch/powerpc/configs/85xx/tqm8540_defconfig index 98982a0e82d8..bbf040aa1f9a 100644 --- a/arch/powerpc/configs/85xx/tqm8540_defconfig +++ b/arch/powerpc/configs/85xx/tqm8540_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8541_defconfig b/arch/powerpc/configs/85xx/tqm8541_defconfig index a6e21db1dafe..523ad8dcfd9d 100644 --- a/arch/powerpc/configs/85xx/tqm8541_defconfig +++ b/arch/powerpc/configs/85xx/tqm8541_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8555_defconfig b/arch/powerpc/configs/85xx/tqm8555_defconfig index ca1de3979474..0032ce1e8c9c 100644 --- a/arch/powerpc/configs/85xx/tqm8555_defconfig +++ b/arch/powerpc/configs/85xx/tqm8555_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/configs/85xx/tqm8560_defconfig b/arch/powerpc/configs/85xx/tqm8560_defconfig index ca3b8c8ef30f..a80b971f7d6e 100644 --- a/arch/powerpc/configs/85xx/tqm8560_defconfig +++ b/arch/powerpc/configs/85xx/tqm8560_defconfig @@ -30,9 +30,9 @@ CONFIG_MTD_CFI_AMDSTD=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=32768 -CONFIG_IDE=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_VIA82CXXX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_GIANFAR=y CONFIG_E100=y diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index de14b1a34d56..d0b832cbbec8 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -67,6 +67,7 @@ void single_step_exception(struct pt_regs *regs); void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); +void stack_overflow_exception(struct pt_regs *regs); void kernel_fp_unavailable_exception(struct pt_regs *regs); void altivec_unavailable_exception(struct pt_regs *regs); void vsx_unavailable_exception(struct pt_regs *regs); @@ -144,7 +145,9 @@ void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr); /* Patch sites */ -extern s32 patch__call_flush_branch_caches; +extern s32 patch__call_flush_branch_caches1; +extern s32 patch__call_flush_branch_caches2; +extern s32 patch__call_flush_branch_caches3; extern s32 patch__flush_count_cache_return; extern s32 patch__flush_link_stack_return; extern s32 patch__call_kvm_flush_link_stack; diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 082b98808701..b6ac4f86c87b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,24 @@ */ #define MAX_EA_BITS_PER_CONTEXT 46 -#define REGION_SHIFT (MAX_EA_BITS_PER_CONTEXT - 2) /* - * Our page table limit us to 64TB. Hence for the kernel mapping, - * each MAP area is limited to 16 TB. - * The four map areas are: linear mapping, vmap, IO and vmemmap + * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB + * of vmemmap space. To better support sparse memory layout, we use 61TB + * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap. */ +#define REGION_SHIFT (40) #define H_KERN_MAP_SIZE (ASM_CONST(1) << REGION_SHIFT) /* - * Define the address range of the kernel non-linear virtual area - * 16TB + * Limits the linear mapping range */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#define H_MAX_PHYSMEM_BITS 46 + +/* + * Define the address range of the kernel non-linear virtual area (61TB) + */ +#define H_KERN_VIRT_START ASM_CONST(0xc0003d0000000000) #ifndef __ASSEMBLY__ #define H_PTE_TABLE_SIZE (sizeof(pte_t) << H_PTE_INDEX_SIZE) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index f20de1149ebe..338e62fbea0b 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -7,6 +7,19 @@ #define H_PUD_INDEX_SIZE 10 // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB #define H_PGD_INDEX_SIZE 8 // size: 8B << 8 = 2KB, maps 2^8 x 16TB = 4PB +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define H_MAX_PHYSMEM_BITS 51 +#else +#define H_MAX_PHYSMEM_BITS 46 +#endif /* * Each context is 512TB size. SLB miss for first context/default context diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h index 93d18da5e7ec..683a9c7d1b03 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h @@ -577,8 +577,8 @@ extern void slb_set_size(u16 size); * For vmalloc and memmap, we use just one context with 512TB. With 64 byte * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)). */ -#if (MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) -#define MAX_KERNEL_CTX_CNT (1UL << (MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) +#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT) +#define MAX_KERNEL_CTX_CNT (1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT)) #else #define MAX_KERNEL_CTX_CNT 1 #endif diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index b392384a3b15..e0b52940e43c 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -27,21 +27,6 @@ struct mmu_psize_def { extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; #endif /* __ASSEMBLY__ */ -/* - * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS - * if we increase SECTIONS_WIDTH we will not store node details in page->flags and - * page_to_nid does a page->section->node lookup - * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce - * memory requirements with large number of sections. - * 51 bits is the max physical real address on POWER9 - */ -#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) && \ - defined(CONFIG_PPC_64K_PAGES) -#define MAX_PHYSMEM_BITS 51 -#else -#define MAX_PHYSMEM_BITS 46 -#endif - /* 64-bit classic hash table MMU */ #include <asm/book3s/64/mmu-hash.h> @@ -85,7 +70,7 @@ extern unsigned int mmu_base_pid; /* * memory block size used with radix translation. */ -extern unsigned int __ro_after_init radix_mem_block_size; +extern unsigned long __ro_after_init radix_mem_block_size; #define PRTB_SIZE_SHIFT (mmu_pid_bits + 4) #define PRTB_ENTRIES (1ul << mmu_pid_bits) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index f6d2c4449aeb..cd3feeac6e87 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -294,6 +294,13 @@ extern unsigned long pci_io_base; #include <asm/book3s/64/hash.h> #include <asm/book3s/64/radix.h> +#if H_MAX_PHYSMEM_BITS > R_MAX_PHYSMEM_BITS +#define MAX_PHYSMEM_BITS H_MAX_PHYSMEM_BITS +#else +#define MAX_PHYSMEM_BITS R_MAX_PHYSMEM_BITS +#endif + + #ifdef CONFIG_PPC_64K_PAGES #include <asm/book3s/64/pgtable-64k.h> #else diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h index 0cba794c4fb8..c7813dc628fc 100644 --- a/arch/powerpc/include/asm/book3s/64/radix.h +++ b/arch/powerpc/include/asm/book3s/64/radix.h @@ -91,6 +91,22 @@ * +------------------------------+ Kernel linear (0xc.....) */ + +/* + * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS + * if we increase SECTIONS_WIDTH we will not store node details in page->flags and + * page_to_nid does a page->section->node lookup + * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce + * memory requirements with large number of sections. + * 51 bits is the max physical real address on POWER9 + */ + +#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) +#define R_MAX_PHYSMEM_BITS 51 +#else +#define R_MAX_PHYSMEM_BITS 46 +#endif + #define RADIX_KERN_VIRT_START ASM_CONST(0xc008000000000000) /* * 49 = MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h index 54764c6e922d..138e46d8c04e 100644 --- a/arch/powerpc/include/asm/cacheflush.h +++ b/arch/powerpc/include/asm/cacheflush.h @@ -98,6 +98,16 @@ static inline void invalidate_dcache_range(unsigned long start, mb(); /* sync */ } +#ifdef CONFIG_4xx +static inline void flush_instruction_cache(void) +{ + iccci((void *)KERNELBASE); + isync(); +} +#else +void flush_instruction_cache(void); +#endif + #include <asm-generic/cacheflush.h> #endif /* _ASM_POWERPC_CACHEFLUSH_H */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 32a15dc49e8c..93bc70d4c9a1 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -9,11 +9,6 @@ #ifndef __ASSEMBLY__ -/* - * Added to include __machine_check_early_realmode_* functions - */ -#include <asm/mce.h> - /* This structure can grow, it's real size is used by head.S code * via the mkdefs mechanism. */ @@ -170,6 +165,7 @@ static inline void cpu_feature_keys_init(void) { } #else /* CONFIG_PPC32 */ /* Define these to 0 for the sake of tests in common code */ #define CPU_FTR_PPC_LE (0) +#define CPU_FTR_SPE (0) #endif /* @@ -299,8 +295,6 @@ static inline void cpu_feature_keys_init(void) { } #define CPU_FTR_MAYBE_CAN_NAP 0 #endif -#define CPU_FTRS_PPC601 (CPU_FTR_COMMON | \ - CPU_FTR_COHERENT_ICACHE) #define CPU_FTRS_603 (CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \ CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE) #define CPU_FTRS_604 (CPU_FTR_COMMON | CPU_FTR_PPC_LE) @@ -516,10 +510,8 @@ static inline void cpu_feature_keys_init(void) { } #else enum { CPU_FTRS_POSSIBLE = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 | -#elif defined(CONFIG_PPC_BOOK3S_32) - CPU_FTRS_PPC601 | CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | +#ifdef CONFIG_PPC_BOOK3S_32 + CPU_FTRS_603 | CPU_FTRS_604 | CPU_FTRS_740_NOTAU | CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 | CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX | CPU_FTRS_7400_NOTAU | CPU_FTRS_7400 | CPU_FTRS_7450_20 | @@ -594,9 +586,7 @@ enum { #else enum { CPU_FTRS_ALWAYS = -#ifdef CONFIG_PPC_BOOK3S_601 - CPU_FTRS_PPC601 & -#elif defined(CONFIG_PPC_BOOK3S_32) +#ifdef CONFIG_PPC_BOOK3S_32 CPU_FTRS_603 & CPU_FTRS_604 & CPU_FTRS_740_NOTAU & CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 & CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX & diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h index deb99fd6e060..98c8bd155bf9 100644 --- a/arch/powerpc/include/asm/cputhreads.h +++ b/arch/powerpc/include/asm/cputhreads.h @@ -23,7 +23,6 @@ extern int threads_per_core; extern int threads_per_subcore; extern int threads_shift; -extern bool has_big_cores; extern cpumask_t threads_core_mask; #else #define threads_per_core 1 diff --git a/arch/powerpc/include/asm/delay.h b/arch/powerpc/include/asm/delay.h index 66963f7d3e64..51bb8c1476c7 100644 --- a/arch/powerpc/include/asm/delay.h +++ b/arch/powerpc/include/asm/delay.h @@ -54,7 +54,7 @@ extern void udelay(unsigned long usecs); ({ \ typeof(condition) __ret; \ unsigned long __loops = tb_ticks_per_usec * timeout; \ - unsigned long __start = get_tbl(); \ + unsigned long __start = mftb(); \ \ if (delay) { \ while (!(__ret = (condition)) && \ diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 17ccc6474ab6..bf2402fed3e0 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,26 +8,39 @@ #ifndef _ASM_POWERPC_LMB_H #define _ASM_POWERPC_LMB_H +#include <linux/sched.h> + struct drmem_lmb { u64 base_addr; u32 drc_index; u32 aa_index; u32 flags; -#ifdef CONFIG_MEMORY_HOTPLUG - int nid; -#endif }; struct drmem_lmb_info { struct drmem_lmb *lmbs; int n_lmbs; - u32 lmb_size; + u64 lmb_size; }; extern struct drmem_lmb_info *drmem_info; +static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb, + const struct drmem_lmb *start) +{ + /* + * DLPAR code paths can take several milliseconds per element + * when interacting with firmware. Ensure that we don't + * unfairly monopolize the CPU. + */ + if (((++lmb - start) % 16) == 0) + cond_resched(); + + return lmb; +} + #define for_each_drmem_lmb_in_range(lmb, start, end) \ - for ((lmb) = (start); (lmb) < (end); (lmb)++) + for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start)) #define for_each_drmem_lmb(lmb) \ for_each_drmem_lmb_in_range((lmb), \ @@ -67,7 +80,7 @@ struct of_drconf_cell_v2 { #define DRCONF_MEM_RESERVED 0x00000080 #define DRCONF_MEM_HOTREMOVABLE 0x00000100 -static inline u32 drmem_lmb_size(void) +static inline u64 drmem_lmb_size(void) { return drmem_info->lmb_size; } @@ -105,22 +118,4 @@ static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb) lmb->aa_index = 0xffffffff; } -#ifdef CONFIG_MEMORY_HOTPLUG -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ - lmb->nid = memory_add_physaddr_to_nid(lmb->base_addr); -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ - lmb->nid = -1; -} -#else -static inline void lmb_set_nid(struct drmem_lmb *lmb) -{ -} -static inline void lmb_clear_nid(struct drmem_lmb *lmb) -{ -} -#endif - #endif /* _ASM_POWERPC_LMB_H */ diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index d5f369bcd130..b1a5bba2e0b9 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -27,7 +27,6 @@ struct pci_dn; #define EEH_FORCE_DISABLED 0x02 /* EEH disabled */ #define EEH_PROBE_MODE_DEV 0x04 /* From PCI device */ #define EEH_PROBE_MODE_DEVTREE 0x08 /* From device tree */ -#define EEH_VALID_PE_ZERO 0x10 /* PE#0 is valid */ #define EEH_ENABLE_IO_FOR_LOG 0x20 /* Enable IO for log */ #define EEH_EARLY_DUMP_LOG 0x40 /* Dump log immediately */ @@ -74,7 +73,6 @@ struct pci_dn; struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ int state; /* PE EEH dependent mode */ - int config_addr; /* Traditional PCI address */ int addr; /* PE configuration address */ struct pci_controller *phb; /* Associated PHB */ struct pci_bus *bus; /* Top PCI bus for bus PE */ @@ -216,7 +214,6 @@ enum { struct eeh_ops { char *name; - int (*init)(void); struct eeh_dev *(*probe)(struct pci_dev *pdev); int (*set_option)(struct eeh_pe *pe, int option); int (*get_state)(struct eeh_pe *pe, int *delay); @@ -281,8 +278,7 @@ int eeh_phb_pe_create(struct pci_controller *phb); int eeh_wait_state(struct eeh_pe *pe, int max_wait); struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb); struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root); -struct eeh_pe *eeh_pe_get(struct pci_controller *phb, - int pe_no, int config_addr); +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no); int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent); int eeh_pe_tree_remove(struct eeh_dev *edev); void eeh_pe_update_time_stamp(struct eeh_pe *pe); @@ -295,8 +291,7 @@ const char *eeh_pe_loc_get(struct eeh_pe *pe); struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe); void eeh_show_enabled(void); -int __init eeh_ops_register(struct eeh_ops *ops); -int __exit eeh_ops_unregister(const char *name); +int __init eeh_init(struct eeh_ops *ops); int eeh_check_failure(const volatile void __iomem *token); int eeh_dev_check_failure(struct eeh_dev *edev); void eeh_addr_cache_init(void); diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index fbb377055471..c1fbccb04390 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -375,11 +375,13 @@ #define H_CPU_CHAR_THREAD_RECONFIG_CTRL (1ull << 57) // IBM bit 6 #define H_CPU_CHAR_COUNT_CACHE_DISABLED (1ull << 56) // IBM bit 7 #define H_CPU_CHAR_BCCTR_FLUSH_ASSIST (1ull << 54) // IBM bit 9 +#define H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST (1ull << 52) // IBM bit 11 #define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 #define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 #define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 #define H_CPU_BEHAV_FLUSH_COUNT_CACHE (1ull << 58) // IBM bit 5 +#define H_CPU_BEHAV_FLUSH_LINK_STACK (1ull << 57) // IBM bit 6 /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 @@ -560,6 +562,42 @@ struct hv_guest_state { /* Latest version of hv_guest_state structure */ #define HV_GUEST_STATE_VERSION 1 +/* + * From the document "H_GetPerformanceCounterInfo Interface" v1.07 + * + * H_GET_PERF_COUNTER_INFO argument + */ +struct hv_get_perf_counter_info_params { + __be32 counter_request; /* I */ + __be32 starting_index; /* IO */ + __be16 secondary_index; /* IO */ + __be16 returned_values; /* O */ + __be32 detail_rc; /* O, only needed when called via *_norets() */ + + /* + * O, size each of counter_value element in bytes, only set for version + * >= 0x3 + */ + __be16 cv_element_size; + + /* I, 0 (zero) for versions < 0x3 */ + __u8 counter_info_version_in; + + /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */ + __u8 counter_info_version_out; + __u8 reserved[0xC]; + __u8 counter_value[]; +} __packed; + +#define HGPCI_REQ_BUFFER_SIZE 4096 +#define HGPCI_MAX_DATA_BYTES \ + (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) + +struct hv_gpci_request_buffer { + struct hv_get_perf_counter_info_params params; + uint8_t bytes[HGPCI_MAX_DATA_BYTES]; +} __packed; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h index db206a7f38e2..abebfbee5b1c 100644 --- a/arch/powerpc/include/asm/hw_breakpoint.h +++ b/arch/powerpc/include/asm/hw_breakpoint.h @@ -10,6 +10,7 @@ #define _PPC_BOOK3S_64_HW_BREAKPOINT_H #include <asm/cpu_has_feature.h> +#include <asm/inst.h> #ifdef __KERNEL__ struct arch_hw_breakpoint { @@ -17,6 +18,7 @@ struct arch_hw_breakpoint { u16 type; u16 len; /* length of the target data symbol */ u16 hw_len; /* length programmed in hw */ + u8 flags; }; /* Note: Don't change the first 6 bits below as they are in the same order @@ -36,12 +38,15 @@ struct arch_hw_breakpoint { #define HW_BRK_TYPE_PRIV_ALL (HW_BRK_TYPE_USER | HW_BRK_TYPE_KERNEL | \ HW_BRK_TYPE_HYP) +#define HW_BRK_FLAG_DISABLED 0x1 + /* Minimum granularity */ #ifdef CONFIG_PPC_8xx #define HW_BREAKPOINT_SIZE 0x4 #else #define HW_BREAKPOINT_SIZE 0x8 #endif +#define HW_BREAKPOINT_SIZE_QUADWORD 0x10 #define DABR_MAX_LEN 8 #define DAWR_MAX_LEN 512 @@ -51,6 +56,13 @@ static inline int nr_wp_slots(void) return cpu_has_feature(CPU_FTR_DAWR1) ? 2 : 1; } +bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info); + +void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, + int *type, int *size, unsigned long *ea); + #ifdef CONFIG_HAVE_HW_BREAKPOINT #include <linux/kdebug.h> #include <asm/reg.h> diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 35060be09073..0363734ff56e 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -25,9 +25,8 @@ #define PACA_IRQ_DBELL 0x02 #define PACA_IRQ_EE 0x04 #define PACA_IRQ_DEC 0x08 /* Or FIT */ -#define PACA_IRQ_EE_EDGE 0x10 /* BookE only */ -#define PACA_IRQ_HMI 0x20 -#define PACA_IRQ_PMI 0x40 +#define PACA_IRQ_HMI 0x10 +#define PACA_IRQ_PMI 0x20 /* * Some soft-masked interrupts must be hard masked until they are replayed @@ -369,12 +368,6 @@ static inline void may_hard_irq_enable(void) { } #define ARCH_IRQ_INIT_FLAGS IRQ_NOREQUEST -/* - * interrupt-retrigger: should we handle this via lost interrupts and IPIs - * or should we not care like we do now ? --BenH. - */ -struct irq_chip; - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HW_IRQ_H */ diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index b0c70a35fd0e..f6599ccb3012 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -156,8 +156,7 @@ struct coprocessor_request_block { u8 reserved[32]; struct coprocessor_status_block csb; -} __packed; - +} __aligned(128); /* RFC02167 Initiate Coprocessor Instructions document * Chapter 8.2.1.1.1 RS @@ -188,6 +187,9 @@ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) __be64 ccw_reg = ccw; u32 cr; + /* NB: the same structures are used by VAS-NX */ + BUILD_BUG_ON(sizeof(*crb) != 128); + __asm__ __volatile__( PPC_ICSWX(%1,0,%2) "\n" "mfcr %0\n" diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 814dfab7e392..4f983ca4030a 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -35,7 +35,6 @@ static __inline__ int irq_canonicalize(int irq) extern int distribute_irqs; -struct irqaction; struct pt_regs; #define __ARCH_HAS_DO_SOFTIRQ diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index a90b892f0bfe..95081078aa8a 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -65,7 +65,6 @@ struct machdep_calls { void __noreturn (*restart)(char *cmd); void __noreturn (*halt)(void); void (*panic)(char *str); - void (*cpu_die)(void); long (*time_init)(void); /* Optional, may be NULL */ @@ -222,8 +221,6 @@ struct machdep_calls { extern void e500_idle(void); extern void power4_idle(void); -extern void power7_idle(void); -extern void power9_idle(void); extern void ppc6xx_idle(void); extern void book3e_idle(void); diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 7f3658a97384..e02aa793420b 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -244,7 +244,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, */ static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next) { - switch_mm(prev, next, current); + switch_mm_irqs_off(prev, next, current); } /* We don't currently use enter_lazy_tlb() for anything */ diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h index e752a5807a59..39be9aea86db 100644 --- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h @@ -65,4 +65,18 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, pte_update(mm, addr, ptep, clr, set, 1); } +#ifdef CONFIG_PPC_4K_PAGES +static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable) +{ + size_t size = huge_page_size(hstate_vma(vma)); + + if (size == SZ_16K) + return __pte(pte_val(entry) & ~_PAGE_HUGE); + else + return entry; +} +#define arch_make_huge_pte arch_make_huge_pte +#endif + #endif /* _ASM_POWERPC_NOHASH_32_HUGETLB_8XX_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b9e134d0f03a..ee2243ba96cf 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -227,6 +227,19 @@ static inline void pmd_clear(pmd_t *pmdp) */ #ifdef CONFIG_PPC_8xx static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); +static int hugepd_ok(hugepd_t hpd); + +static int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) +{ + if (!huge) + return PAGE_SIZE / SZ_4K; + else if (hugepd_ok(*((hugepd_t *)pmd))) + return 1; + else if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && !(val & _PAGE_HUGE)) + return SZ_16K / SZ_4K; + else + return SZ_512K / SZ_4K; +} static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) @@ -237,12 +250,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p int num, i; pmd_t *pmd = pmd_off(mm, addr); - if (!huge) - num = PAGE_SIZE / SZ_4K; - else if ((pmd_val(*pmd) & _PMD_PAGE_MASK) != _PMD_PAGE_8M) - num = SZ_512K / SZ_4K; - else - num = 1; + num = number_of_cells_per_pte(pmd, new, huge); for (i = 0; i < num; i++, entry++, new += SZ_4K) *entry = new; diff --git a/arch/powerpc/include/asm/pnv-ocxl.h b/arch/powerpc/include/asm/pnv-ocxl.h index ee79d2cd9fb6..d37ededca3ee 100644 --- a/arch/powerpc/include/asm/pnv-ocxl.h +++ b/arch/powerpc/include/asm/pnv-ocxl.h @@ -28,7 +28,4 @@ int pnv_ocxl_spa_setup(struct pci_dev *dev, void *spa_mem, int PE_mask, void **p void pnv_ocxl_spa_release(void *platform_data); int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle); -int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr); -void pnv_ocxl_free_xive_irq(u32 irq); - #endif /* _ASM_PNV_OCXL_H */ diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h index b4cc6608131c..511786f0e40d 100644 --- a/arch/powerpc/include/asm/ppc_asm.h +++ b/arch/powerpc/include/asm/ppc_asm.h @@ -382,16 +382,6 @@ n: #endif /* various errata or part fixups */ -#ifdef CONFIG_PPC601_SYNC_FIX -#define SYNC sync; isync -#define SYNC_601 sync -#define ISYNC_601 isync -#else -#define SYNC -#define SYNC_601 -#define ISYNC_601 -#endif - #if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) #define MFTB(dest) \ 90: mfspr dest, SPRN_TBRL; \ @@ -411,8 +401,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_CELL_TB_BUG, CPU_FTR_CELL_TB_BUG, 96) #define MFTBU(dest) mfspr dest, SPRN_TBRU #endif -/* tlbsync is not implemented on 601 */ -#if !defined(CONFIG_SMP) || defined(CONFIG_PPC_BOOK3S_601) +#ifndef CONFIG_SMP #define TLBSYNC #else #define TLBSYNC tlbsync; sync diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index ed0d633ab5aa..365290b9a24b 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -220,6 +220,7 @@ struct thread_struct { unsigned long tm_tar; unsigned long tm_ppr; unsigned long tm_dscr; + unsigned long tm_amr; /* * Checkpointed FP and VSX 0-31 register set. @@ -432,16 +433,10 @@ enum idle_boot_override {IDLE_NO_OVERRIDE = 0, IDLE_POWERSAVE_OFF}; extern int powersave_nap; /* set if nap mode can be used in idle loop */ extern void power7_idle_type(unsigned long type); -extern void power9_idle_type(unsigned long stop_psscr_val, +extern void arch300_idle_type(unsigned long stop_psscr_val, unsigned long stop_psscr_mask); -extern void flush_instruction_cache(void); -extern void hard_reset_now(void); -extern void poweroff_now(void); extern int fix_alignment(struct pt_regs *); -extern void cvt_fd(float *from, double *to); -extern void cvt_df(double *from, float *to); -extern void _nmask_and_or_msr(unsigned long nmask, unsigned long or_val); #ifdef CONFIG_PPC64 /* diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 155a197c0aa1..e2c778c176a3 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -243,11 +243,7 @@ static inline void set_trap_norestart(struct pt_regs *regs) } #define arch_has_single_step() (1) -#ifndef CONFIG_PPC_BOOK3S_601 #define arch_has_block_step() (true) -#else -#define arch_has_block_step() (false) -#endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT /* diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index 88fb88491fe9..f877a576b338 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -521,6 +521,8 @@ #define SPRN_TSCR 0x399 /* Thread Switch Control Register */ #define SPRN_DEC 0x016 /* Decrement Register */ +#define SPRN_PIT 0x3DB /* Programmable Interval Timer (40x/BOOKE) */ + #define SPRN_DER 0x095 /* Debug Enable Register */ #define DER_RSTE 0x40000000 /* Reset Interrupt */ #define DER_CHSTPE 0x20000000 /* Check Stop */ @@ -817,7 +819,7 @@ #define THRM1_TIN (1 << 31) #define THRM1_TIV (1 << 30) #define THRM1_THRES(x) ((x&0x7f)<<23) -#define THRM3_SITV(x) ((x&0x3fff)<<1) +#define THRM3_SITV(x) ((x & 0x1fff) << 1) #define THRM1_TID (1<<2) #define THRM1_TIE (1<<1) #define THRM1_V (1<<0) @@ -1353,6 +1355,7 @@ #define PVR_POWER8NVL 0x004C #define PVR_POWER8 0x004D #define PVR_POWER9 0x004E +#define PVR_POWER10 0x0080 #define PVR_BE 0x0070 #define PVR_PA6T 0x0090 @@ -1416,8 +1419,7 @@ static inline void msr_check_and_clear(unsigned long bits) __msr_check_and_clear(bits); } -#ifdef __powerpc64__ -#if defined(CONFIG_PPC_CELL) || defined(CONFIG_PPC_FSL_BOOK3E) +#if defined(CONFIG_PPC_CELL) || defined(CONFIG_E500) #define mftb() ({unsigned long rval; \ asm volatile( \ "90: mfspr %0, %2;\n" \ @@ -1427,29 +1429,23 @@ static inline void msr_check_and_clear(unsigned long bits) : "=r" (rval) \ : "i" (CPU_FTR_CELL_TB_BUG), "i" (SPRN_TBRL) : "cr0"); \ rval;}) +#elif defined(CONFIG_PPC_8xx) +#define mftb() ({unsigned long rval; \ + asm volatile("mftbl %0" : "=r" (rval)); rval;}) #else #define mftb() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : \ "=r" (rval) : "i" (SPRN_TBRL)); rval;}) #endif /* !CONFIG_PPC_CELL */ -#else /* __powerpc64__ */ - #if defined(CONFIG_PPC_8xx) -#define mftbl() ({unsigned long rval; \ - asm volatile("mftbl %0" : "=r" (rval)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mftbu %0" : "=r" (rval)); rval;}) #else -#define mftbl() ({unsigned long rval; \ - asm volatile("mfspr %0, %1" : "=r" (rval) : \ - "i" (SPRN_TBRL)); rval;}) #define mftbu() ({unsigned long rval; \ asm volatile("mfspr %0, %1" : "=r" (rval) : \ "i" (SPRN_TBRU)); rval;}) #endif -#define mftb() mftbl() -#endif /* !__powerpc64__ */ #define mttbl(v) asm volatile("mttbl %0":: "r"(v)) #define mttbu(v) asm volatile("mttbu %0":: "r"(v)) diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h index ff30f1076162..29a948e0c0f2 100644 --- a/arch/powerpc/include/asm/reg_booke.h +++ b/arch/powerpc/include/asm/reg_booke.h @@ -174,7 +174,6 @@ #define SPRN_L1CSR1 0x3F3 /* L1 Cache Control and Status Register 1 */ #define SPRN_MMUCSR0 0x3F4 /* MMU Control and Status Register 0 */ #define SPRN_MMUCFG 0x3F7 /* MMU Configuration Register */ -#define SPRN_PIT 0x3DB /* Programmable Interval Timer */ #define SPRN_BUCSR 0x3F5 /* Branch Unit Control and Status */ #define SPRN_L2CSR0 0x3F9 /* L2 Data Cache Control and Status Register 0 */ #define SPRN_L2CSR1 0x3FA /* L2 Data Cache Control and Status Register 1 */ diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h index 49a25e2400f2..b2035b2f57ce 100644 --- a/arch/powerpc/include/asm/smp.h +++ b/arch/powerpc/include/asm/smp.h @@ -28,8 +28,8 @@ extern int boot_cpuid; extern int spinning_secondaries; extern u32 *cpu_to_phys_id; +extern bool coregroup_enabled; -extern void cpu_die(void); extern int cpu_to_chip_id(int cpu); #ifdef CONFIG_SMP @@ -50,6 +50,9 @@ struct smp_ops_t { int (*cpu_disable)(void); void (*cpu_die)(unsigned int nr); int (*cpu_bootable)(unsigned int nr); +#ifdef CONFIG_HOTPLUG_CPU + void (*cpu_offline_self)(void); +#endif }; extern int smp_send_nmi_ipi(int cpu, void (*fn)(struct pt_regs *), u64 delay_us); @@ -118,11 +121,6 @@ static inline struct cpumask *cpu_sibling_mask(int cpu) return per_cpu(cpu_sibling_map, cpu); } -static inline struct cpumask *cpu_core_mask(int cpu) -{ - return per_cpu(cpu_core_map, cpu); -} - static inline struct cpumask *cpu_l2_cache_mask(int cpu) { return per_cpu(cpu_l2_cache_map, cpu); @@ -135,6 +133,19 @@ static inline struct cpumask *cpu_smallcore_mask(int cpu) extern int cpu_to_core_id(int cpu); +extern bool has_big_cores; + +#define cpu_smt_mask cpu_smt_mask +#ifdef CONFIG_SCHED_SMT +static inline const struct cpumask *cpu_smt_mask(int cpu) +{ + if (has_big_cores) + return per_cpu(cpu_smallcore_map, cpu); + + return per_cpu(cpu_sibling_map, cpu); +} +#endif /* CONFIG_SCHED_SMT */ + /* Since OpenPIC has only 4 IPIs, we use slightly different message numbers. * * Make sure this matches openpic_request_IPIs in open_pic.c, or what shows up @@ -243,7 +254,6 @@ extern void arch_send_call_function_ipi_mask(const struct cpumask *mask); * 64-bit but defining them all here doesn't harm */ extern void generic_secondary_smp_init(void); -extern void generic_secondary_thread_init(void); extern unsigned long __secondary_hold_spinloop; extern unsigned long __secondary_hold_acknowledge; extern char __secondary_hold; diff --git a/arch/powerpc/include/asm/svm.h b/arch/powerpc/include/asm/svm.h index 85580b30aba4..7546402d796a 100644 --- a/arch/powerpc/include/asm/svm.h +++ b/arch/powerpc/include/asm/svm.h @@ -15,6 +15,8 @@ static inline bool is_secure_guest(void) return mfmsr() & MSR_S; } +void __init svm_swiotlb_init(void); + void dtl_cache_ctor(void *addr); #define get_dtl_cache_ctor() (is_secure_guest() ? dtl_cache_ctor : NULL) @@ -25,6 +27,8 @@ static inline bool is_secure_guest(void) return false; } +static inline void svm_swiotlb_init(void) {} + #define get_dtl_cache_ctor() NULL #endif /* CONFIG_PPC_SVM */ diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h index aca70fb43147..1d67bc8d7bc6 100644 --- a/arch/powerpc/include/asm/synch.h +++ b/arch/powerpc/include/asm/synch.h @@ -3,8 +3,9 @@ #define _ASM_POWERPC_SYNCH_H #ifdef __KERNEL__ +#include <asm/cputable.h> #include <asm/feature-fixups.h> -#include <asm/asm-const.h> +#include <asm/ppc-opcode.h> #ifndef __ASSEMBLY__ extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup; @@ -20,6 +21,22 @@ static inline void isync(void) { __asm__ __volatile__ ("isync" : : : "memory"); } + +static inline void ppc_after_tlbiel_barrier(void) +{ + asm volatile("ptesync": : :"memory"); + /* + * POWER9, POWER10 need a cp_abort after tlbiel to ensure the copy is + * invalidated correctly. If this is not done, the paste can take data + * from the physical address that was translated at copy time. + * + * POWER9 in practice does not need this, because address spaces with + * accelerators mapped will use tlbie (which does invalidate the copy) + * to invalidate translations. It's not possible to limit POWER10 this + * way due to local copy-paste. + */ + asm volatile(ASM_FTR_IFSET(PPC_CP_ABORT, "", %0) : : "i" (CPU_FTR_ARCH_31) : "memory"); +} #endif /* __ASSEMBLY__ */ #if defined(__powerpc64__) diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index cb326720a8a1..2f566c1a754c 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -38,44 +38,10 @@ struct div_result { u64 result_low; }; -/* Accessor functions for the timebase (RTC on 601) registers. */ -#define __USE_RTC() (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - -#ifdef CONFIG_PPC64 - /* For compatibility, get_tbl() is defined as get_tb() on ppc64 */ -#define get_tbl get_tb - -#else - static inline unsigned long get_tbl(void) { - return mftbl(); -} - -static inline unsigned int get_tbu(void) -{ - return mftbu(); -} -#endif /* !CONFIG_PPC64 */ - -static inline unsigned int get_rtcl(void) -{ - unsigned int rtcl; - - asm volatile("mfrtcl %0" : "=r" (rtcl)); - return rtcl; -} - -static inline u64 get_rtc(void) -{ - unsigned int hi, lo, hi2; - - do { - asm volatile("mfrtcu %0; mfrtcl %1; mfrtcu %2" - : "=r" (hi), "=r" (lo), "=r" (hi2)); - } while (hi2 != hi); - return (u64)hi * 1000000000 + lo; + return mftb(); } static inline u64 get_vtb(void) @@ -87,30 +53,21 @@ static inline u64 get_vtb(void) return 0; } -#ifdef CONFIG_PPC64 -static inline u64 get_tb(void) -{ - return mftb(); -} -#else /* CONFIG_PPC64 */ static inline u64 get_tb(void) { unsigned int tbhi, tblo, tbhi2; + if (IS_ENABLED(CONFIG_PPC64)) + return mftb(); + do { - tbhi = get_tbu(); - tblo = get_tbl(); - tbhi2 = get_tbu(); + tbhi = mftbu(); + tblo = mftb(); + tbhi2 = mftbu(); } while (tbhi != tbhi2); return ((u64)tbhi << 32) | tblo; } -#endif /* !CONFIG_PPC64 */ - -static inline u64 get_tb_or_rtc(void) -{ - return __USE_RTC() ? get_rtc() : get_tb(); -} static inline void set_tb(unsigned int upper, unsigned int lower) { @@ -127,11 +84,10 @@ static inline void set_tb(unsigned int upper, unsigned int lower) */ static inline u64 get_dec(void) { -#if defined(CONFIG_40x) - return (mfspr(SPRN_PIT)); -#else - return (mfspr(SPRN_DEC)); -#endif + if (IS_ENABLED(CONFIG_40x)) + return mfspr(SPRN_PIT); + + return mfspr(SPRN_DEC); } /* @@ -141,23 +97,17 @@ static inline u64 get_dec(void) */ static inline void set_dec(u64 val) { -#if defined(CONFIG_40x) - mtspr(SPRN_PIT, (u32) val); -#else -#ifndef CONFIG_BOOKE - --val; -#endif - mtspr(SPRN_DEC, val); -#endif /* not 40x */ + if (IS_ENABLED(CONFIG_40x)) + mtspr(SPRN_PIT, (u32)val); + else if (IS_ENABLED(CONFIG_BOOKE)) + mtspr(SPRN_DEC, val); + else + mtspr(SPRN_DEC, val - 1); } static inline unsigned long tb_ticks_since(unsigned long tstamp) { - if (__USE_RTC()) { - int delta = get_rtcl() - (unsigned int) tstamp; - return delta < 0 ? delta + 1000000000 : delta; - } - return get_tbl() - tstamp; + return mftb() - tstamp; } #define mulhwu(x,y) \ diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index 6047402b0a4d..95988870a57b 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -17,9 +17,6 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return 0; - return mftb(); } diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index fbc6f3002f23..d97f061fecac 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -66,19 +66,6 @@ static inline int mm_is_thread_local(struct mm_struct *mm) return false; return cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)); } -static inline void mm_reset_thread_local(struct mm_struct *mm) -{ - WARN_ON(atomic_read(&mm->context.copros) > 0); - /* - * It's possible for mm_access to take a reference on mm_users to - * access the remote mm from another thread, but it's not allowed - * to set mm_cpumask, so mm_users may be > 1 here. - */ - WARN_ON(current->mm != mm); - atomic_set(&mm->context.active_cpus, 1); - cpumask_clear(mm_cpumask(mm)); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); -} #else /* CONFIG_PPC_BOOK3S_64 */ static inline int mm_is_thread_local(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f0b6300e7dd3..8728590f514a 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -86,14 +86,27 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) #endif /* CONFIG_NUMA */ +struct drmem_lmb; +int of_drconf_to_nid_single(struct drmem_lmb *lmb); + #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); +extern int cpu_to_coregroup_id(int cpu); #else static inline int find_and_online_cpu_nid(int cpu) { return 0; } +static inline int cpu_to_coregroup_id(int cpu) +{ +#ifdef CONFIG_SMP + return cpu_to_core_id(cpu); +#else + return 0; +#endif +} + #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ #include <asm-generic/topology.h> @@ -104,15 +117,10 @@ static inline int find_and_online_cpu_nid(int cpu) #ifdef CONFIG_PPC64 #include <asm/smp.h> -#ifdef CONFIG_PPC_SPLPAR -int get_physical_package_id(int cpu); -#define topology_physical_package_id(cpu) (get_physical_package_id(cpu)) -#else #define topology_physical_package_id(cpu) (cpu_to_chip_id(cpu)) -#endif #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) -#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_core_cpumask(cpu) (cpu_cpu_mask(cpu)) #define topology_core_id(cpu) (cpu_to_core_id(cpu)) #endif diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 20a35373cafc..604d705f1bb8 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -151,52 +151,16 @@ static inline int __access_ok(unsigned long addr, unsigned long size, extern long __put_user_bad(void); -/* - * We don't tell gcc that we are accessing memory, but this is OK - * because we do not write to any memory gcc knows about, so there - * are no aliasing issues. - */ -#define __put_user_asm(x, addr, err, op) \ - __asm__ __volatile__( \ - "1: " op " %1,0(%2) # put_user\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: li %0,%3\n" \ - " b 2b\n" \ - ".previous\n" \ - EX_TABLE(1b, 3b) \ - : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) - -#ifdef __powerpc64__ -#define __put_user_asm2(x, ptr, retval) \ - __put_user_asm(x, ptr, retval, "std") -#else /* __powerpc64__ */ -#define __put_user_asm2(x, addr, err) \ - __asm__ __volatile__( \ - "1: stw %1,0(%2)\n" \ - "2: stw %1+1,4(%2)\n" \ - "3:\n" \ - ".section .fixup,\"ax\"\n" \ - "4: li %0,%3\n" \ - " b 3b\n" \ - ".previous\n" \ - EX_TABLE(1b, 4b) \ - EX_TABLE(2b, 4b) \ - : "=r" (err) \ - : "r" (x), "b" (addr), "i" (-EFAULT), "0" (err)) -#endif /* __powerpc64__ */ - #define __put_user_size_allowed(x, ptr, size, retval) \ do { \ + __label__ __pu_failed; \ + \ retval = 0; \ - switch (size) { \ - case 1: __put_user_asm(x, ptr, retval, "stb"); break; \ - case 2: __put_user_asm(x, ptr, retval, "sth"); break; \ - case 4: __put_user_asm(x, ptr, retval, "stw"); break; \ - case 8: __put_user_asm2(x, ptr, retval); break; \ - default: __put_user_bad(); \ - } \ + __put_user_size_goto(x, ptr, size, __pu_failed); \ + break; \ + \ +__pu_failed: \ + retval = -EFAULT; \ } while (0) #define __put_user_size(x, ptr, size, retval) \ @@ -249,12 +213,17 @@ do { \ }) +/* + * We don't tell gcc that we are accessing memory, but this is OK + * because we do not write to any memory gcc knows about, so there + * are no aliasing issues. + */ #define __put_user_asm_goto(x, addr, label, op) \ asm volatile goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ - : "r" (x), "m" (*addr) \ + : "r" (x), "m<>" (*addr) \ : \ : label) @@ -316,7 +285,7 @@ extern long __get_user_bad(void); #define __get_user_asm(x, addr, err, op) \ __asm__ __volatile__( \ - "1: "op" %1,0(%2) # get_user\n" \ + "1: "op"%U2%X2 %1, %2 # get_user\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: li %0,%3\n" \ @@ -325,7 +294,7 @@ extern long __get_user_bad(void); ".previous\n" \ EX_TABLE(1b, 3b) \ : "=r" (err), "=r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m<>" (*addr), "i" (-EFAULT), "0" (err)) #ifdef __powerpc64__ #define __get_user_asm2(x, addr, err) \ @@ -333,8 +302,8 @@ extern long __get_user_bad(void); #else /* __powerpc64__ */ #define __get_user_asm2(x, addr, err) \ __asm__ __volatile__( \ - "1: lwz %1,0(%2)\n" \ - "2: lwz %1+1,4(%2)\n" \ + "1: lwz%X2 %1, %2\n" \ + "2: lwz%X2 %L1, %L2\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: li %0,%3\n" \ @@ -345,7 +314,7 @@ extern long __get_user_bad(void); EX_TABLE(1b, 4b) \ EX_TABLE(2b, 4b) \ : "=r" (err), "=&r" (x) \ - : "b" (addr), "i" (-EFAULT), "0" (err)) + : "m" (*addr), "i" (-EFAULT), "0" (err)) #endif /* __powerpc64__ */ #define __get_user_size_allowed(x, ptr, size, retval) \ @@ -355,10 +324,10 @@ do { \ if (size > sizeof(x)) \ (x) = __get_user_bad(); \ switch (size) { \ - case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \ - case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \ - case 4: __get_user_asm(x, ptr, retval, "lwz"); break; \ - case 8: __get_user_asm2(x, ptr, retval); break; \ + case 1: __get_user_asm(x, (u8 __user *)ptr, retval, "lbz"); break; \ + case 2: __get_user_asm(x, (u16 __user *)ptr, retval, "lhz"); break; \ + case 4: __get_user_asm(x, (u32 __user *)ptr, retval, "lwz"); break; \ + case 8: __get_user_asm2(x, (u64 __user *)ptr, retval); break; \ default: (x) = __get_user_bad(); \ } \ } while (0) diff --git a/arch/powerpc/include/uapi/asm/ptrace.h b/arch/powerpc/include/uapi/asm/ptrace.h index f5f1ccc740fc..7004cfea3f5f 100644 --- a/arch/powerpc/include/uapi/asm/ptrace.h +++ b/arch/powerpc/include/uapi/asm/ptrace.h @@ -222,6 +222,7 @@ struct ppc_debug_info { #define PPC_DEBUG_FEATURE_DATA_BP_RANGE 0x0000000000000004 #define PPC_DEBUG_FEATURE_DATA_BP_MASK 0x0000000000000008 #define PPC_DEBUG_FEATURE_DATA_BP_DAWR 0x0000000000000010 +#define PPC_DEBUG_FEATURE_DATA_BP_ARCH_31 0x0000000000000020 #ifndef __ASSEMBLY__ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index cbf41fb4ee89..bf0bf1b900d2 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -45,7 +45,8 @@ obj-y := cputable.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o firmware.o + of_platform.o prom_parse.o firmware.o \ + hw_breakpoint_constraints.o obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ paca.o nvram_64.o note.o syscall_64.o @@ -94,7 +95,8 @@ obj-$(CONFIG_PPC_FSL_BOOK3E) += cpu_setup_fsl_booke.o obj-$(CONFIG_PPC_DOORBELL) += dbell.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o -extra-y := head_$(BITS).o +extra-$(CONFIG_PPC64) := head_64.o +extra-$(CONFIG_PPC_BOOK3S_32) := head_book3s_32.o extra-$(CONFIG_40x) := head_40x.o extra-$(CONFIG_44x) := head_44x.o extra-$(CONFIG_FSL_BOOKE) := head_fsl_booke.o diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8711c2164b45..c2722ff36e98 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -176,6 +176,7 @@ int main(void) OFFSET(THREAD_TM_TAR, thread_struct, tm_tar); OFFSET(THREAD_TM_PPR, thread_struct, tm_ppr); OFFSET(THREAD_TM_DSCR, thread_struct, tm_dscr); + OFFSET(THREAD_TM_AMR, thread_struct, tm_amr); OFFSET(PT_CKPT_REGS, thread_struct, ckpt_regs); OFFSET(THREAD_CKVRSTATE, thread_struct, ckvr_state.vr); OFFSET(THREAD_CKVRSAVE, thread_struct, ckvrsave); diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index 02300edc6989..c22a8e0dbc93 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -95,19 +95,10 @@ void __init btext_prepare_BAT(void) boot_text_mapped = 0; return; } - if (PVR_VER(mfspr(SPRN_PVR)) != 1) { - /* 603, 604, G3, G4, ... */ - lowbits = addr & ~0xFF000000UL; - addr &= 0xFF000000UL; - disp_BAT[0] = vaddr | (BL_16M<<2) | 2; - disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); - } else { - /* 601 */ - lowbits = addr & ~0xFF800000UL; - addr &= 0xFF800000UL; - disp_BAT[0] = vaddr | (_PAGE_NO_CACHE | PP_RWXX) | 4; - disp_BAT[1] = addr | BL_8M | 0x40; - } + lowbits = addr & ~0xFF000000UL; + addr &= 0xFF000000UL; + disp_BAT[0] = vaddr | (BL_16M<<2) | 2; + disp_BAT[1] = addr | (_PAGE_NO_CACHE | _PAGE_GUARDED | BPP_RW); logicalDisplayBase = (void *) (vaddr + lowbits); } #endif diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 2aa89c6b2896..492c0b36aff6 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -16,6 +16,7 @@ #include <asm/oprofile_impl.h> #include <asm/cputable.h> #include <asm/prom.h> /* for PTRRELOC on ARCH=ppc */ +#include <asm/mce.h> #include <asm/mmu.h> #include <asm/setup.h> @@ -608,21 +609,6 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_PPC_BOOK3S_64 */ #ifdef CONFIG_PPC32 -#ifdef CONFIG_PPC_BOOK3S_601 - { /* 601 */ - .pvr_mask = 0xffff0000, - .pvr_value = 0x00010000, - .cpu_name = "601", - .cpu_features = CPU_FTRS_PPC601, - .cpu_user_features = COMMON_USER | PPC_FEATURE_601_INSTR | - PPC_FEATURE_UNIFIED_CACHE | PPC_FEATURE_NO_TB, - .mmu_features = MMU_FTR_HPTE_TABLE, - .icache_bsize = 32, - .dcache_bsize = 32, - .machine_check = machine_check_generic, - .platform = "ppc601", - }, -#endif /* CONFIG_PPC_BOOK3S_601 */ #ifdef CONFIG_PPC_BOOK3S_6xx { /* 603 */ .pvr_mask = 0xffff0000, diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index f204ad79b6b5..1098863e17ee 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -17,6 +17,7 @@ #include <asm/cputable.h> #include <asm/dt_cpu_ftrs.h> +#include <asm/mce.h> #include <asm/mmu.h> #include <asm/oprofile_impl.h> #include <asm/prom.h> diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 94682382fc8c..0e160dffcb86 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -466,7 +466,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) return 0; } - if (!pe->addr && !pe->config_addr) { + if (!pe->addr) { eeh_stats.no_cfg_addr++; return 0; } @@ -929,56 +929,6 @@ void eeh_save_bars(struct eeh_dev *edev) edev->config_space[1] |= PCI_COMMAND_MASTER; } -/** - * eeh_ops_register - Register platform dependent EEH operations - * @ops: platform dependent EEH operations - * - * Register the platform dependent EEH operation callback - * functions. The platform should call this function before - * any other EEH operations. - */ -int __init eeh_ops_register(struct eeh_ops *ops) -{ - if (!ops->name) { - pr_warn("%s: Invalid EEH ops name for %p\n", - __func__, ops); - return -EINVAL; - } - - if (eeh_ops && eeh_ops != ops) { - pr_warn("%s: EEH ops of platform %s already existing (%s)\n", - __func__, eeh_ops->name, ops->name); - return -EEXIST; - } - - eeh_ops = ops; - - return 0; -} - -/** - * eeh_ops_unregister - Unreigster platform dependent EEH operations - * @name: name of EEH platform operations - * - * Unregister the platform dependent EEH operation callback - * functions. - */ -int __exit eeh_ops_unregister(const char *name) -{ - if (!name || !strlen(name)) { - pr_warn("%s: Invalid EEH ops name\n", - __func__); - return -EINVAL; - } - - if (eeh_ops && !strcmp(eeh_ops->name, name)) { - eeh_ops = NULL; - return 0; - } - - return -EEXIST; -} - static int eeh_reboot_notifier(struct notifier_block *nb, unsigned long action, void *unused) { @@ -990,54 +940,6 @@ static struct notifier_block eeh_reboot_nb = { .notifier_call = eeh_reboot_notifier, }; -/** - * eeh_init - EEH initialization - * - * Initialize EEH by trying to enable it for all of the adapters in the system. - * As a side effect we can determine here if eeh is supported at all. - * Note that we leave EEH on so failed config cycles won't cause a machine - * check. If a user turns off EEH for a particular adapter they are really - * telling Linux to ignore errors. Some hardware (e.g. POWER5) won't - * grant access to a slot if EEH isn't enabled, and so we always enable - * EEH for all slots/all devices. - * - * The eeh-force-off option disables EEH checking globally, for all slots. - * Even if force-off is set, the EEH hardware is still enabled, so that - * newer systems can boot. - */ -static int eeh_init(void) -{ - struct pci_controller *hose, *tmp; - int ret = 0; - - /* Register reboot notifier */ - ret = register_reboot_notifier(&eeh_reboot_nb); - if (ret) { - pr_warn("%s: Failed to register notifier (%d)\n", - __func__, ret); - return ret; - } - - /* call platform initialization function */ - if (!eeh_ops) { - pr_warn("%s: Platform EEH operation not found\n", - __func__); - return -EEXIST; - } else if ((ret = eeh_ops->init())) - return ret; - - /* Initialize PHB PEs */ - list_for_each_entry_safe(hose, tmp, &hose_list, list_node) - eeh_phb_pe_create(hose); - - eeh_addr_cache_init(); - - /* Initialize EEH event */ - return eeh_event_init(); -} - -core_initcall_sync(eeh_init); - static int eeh_device_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -1062,12 +964,47 @@ static struct notifier_block eeh_device_nb = { .notifier_call = eeh_device_notifier, }; -static __init int eeh_set_bus_notifier(void) +/** + * eeh_init - System wide EEH initialization + * + * It's the platform's job to call this from an arch_initcall(). + */ +int eeh_init(struct eeh_ops *ops) { - bus_register_notifier(&pci_bus_type, &eeh_device_nb); - return 0; + struct pci_controller *hose, *tmp; + int ret = 0; + + /* the platform should only initialise EEH once */ + if (WARN_ON(eeh_ops)) + return -EEXIST; + if (WARN_ON(!ops)) + return -ENOENT; + eeh_ops = ops; + + /* Register reboot notifier */ + ret = register_reboot_notifier(&eeh_reboot_nb); + if (ret) { + pr_warn("%s: Failed to register reboot notifier (%d)\n", + __func__, ret); + return ret; + } + + ret = bus_register_notifier(&pci_bus_type, &eeh_device_nb); + if (ret) { + pr_warn("%s: Failed to register bus notifier (%d)\n", + __func__, ret); + return ret; + } + + /* Initialize PHB PEs */ + list_for_each_entry_safe(hose, tmp, &hose_list, list_node) + eeh_phb_pe_create(hose); + + eeh_addr_cache_init(); + + /* Initialize EEH event */ + return eeh_event_init(); } -arch_initcall(eeh_set_bus_notifier); /** * eeh_probe_device() - Perform EEH initialization for the indicated pci device @@ -1720,7 +1657,7 @@ static ssize_t eeh_force_recover_write(struct file *filp, return -ENODEV; /* Retrieve PE */ - pe = eeh_pe_get(hose, pe_no, 0); + pe = eeh_pe_get(hose, pe_no); if (!pe) return -ENODEV; diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d2aaaa73fdd5..845e024321d4 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -251,43 +251,21 @@ void eeh_pe_dev_traverse(struct eeh_pe *root, /** * __eeh_pe_get - Check the PE address - * @data: EEH PE - * @flag: EEH device * * For one particular PE, it can be identified by PE address * or tranditional BDF address. BDF address is composed of * Bus/Device/Function number. The extra data referred by flag * indicates which type of address should be used. */ -struct eeh_pe_get_flag { - int pe_no; - int config_addr; -}; - static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) { - struct eeh_pe_get_flag *tmp = (struct eeh_pe_get_flag *) flag; + int *target_pe = flag; - /* Unexpected PHB PE */ + /* PHB PEs are special and should be ignored */ if (pe->type & EEH_PE_PHB) return NULL; - /* - * We prefer PE address. For most cases, we should - * have non-zero PE address - */ - if (eeh_has_flag(EEH_VALID_PE_ZERO)) { - if (tmp->pe_no == pe->addr) - return pe; - } else { - if (tmp->pe_no && - (tmp->pe_no == pe->addr)) - return pe; - } - - /* Try BDF address */ - if (tmp->config_addr && - (tmp->config_addr == pe->config_addr)) + if (*target_pe == pe->addr) return pe; return NULL; @@ -297,7 +275,6 @@ static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) * eeh_pe_get - Search PE based on the given address * @phb: PCI controller * @pe_no: PE number - * @config_addr: Config address * * Search the corresponding PE based on the specified address which * is included in the eeh device. The function is used to check if @@ -306,16 +283,11 @@ static void *__eeh_pe_get(struct eeh_pe *pe, void *flag) * which is composed of PCI bus/device/function number, or unified * PE address. */ -struct eeh_pe *eeh_pe_get(struct pci_controller *phb, - int pe_no, int config_addr) +struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no) { struct eeh_pe *root = eeh_phb_pe_get(phb); - struct eeh_pe_get_flag tmp = { pe_no, config_addr }; - struct eeh_pe *pe; - pe = eeh_pe_traverse(root, __eeh_pe_get, &tmp); - - return pe; + return eeh_pe_traverse(root, __eeh_pe_get, &pe_no); } /** @@ -336,19 +308,13 @@ int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) struct pci_controller *hose = edev->controller; struct eeh_pe *pe, *parent; - /* Check if the PE number is valid */ - if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) { - eeh_edev_err(edev, "PE#0 is invalid for this PHB!\n"); - return -EINVAL; - } - /* * Search the PE has been existing or not according * to the PE address. If that has been existing, the * PE should be composed of PCI bus and its subordinate * components. */ - pe = eeh_pe_get(hose, edev->pe_config_addr, edev->bdfn); + pe = eeh_pe_get(hose, edev->pe_config_addr); if (pe) { if (pe->type & EEH_PE_INVALID) { list_add_tail(&edev->entry, &pe->edevs); @@ -388,8 +354,8 @@ int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent) pr_err("%s: out of memory!\n", __func__); return -ENOMEM; } - pe->addr = edev->pe_config_addr; - pe->config_addr = edev->bdfn; + + pe->addr = edev->pe_config_addr; /* * Put the new EEH PE into hierarchy tree. If the parent diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index f4d0af8e1136..8cdc8bcde703 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -234,7 +234,6 @@ transfer_to_handler_cont: mtspr SPRN_SRR0,r11 mtspr SPRN_SRR1,r10 mtlr r9 - SYNC RFI /* jump to handler, enable MMU */ #if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) @@ -264,7 +263,6 @@ _ASM_NOKPROBE_SYMBOL(transfer_to_handler_cont) LOAD_REG_IMMEDIATE(r0, MSR_KERNEL) mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r0 - SYNC RFI reenable_mmu: @@ -323,7 +321,6 @@ stack_ovf: #endif mtspr SPRN_SRR0,r9 mtspr SPRN_SRR1,r10 - SYNC RFI _ASM_NOKPROBE_SYMBOL(stack_ovf) #endif @@ -411,7 +408,6 @@ ret_from_syscall: /* disable interrupts so current_thread_info()->flags can't change */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */ /* Note: We don't bother telling lockdep about it */ - SYNC mtmsr r10 lwz r9,TI_FLAGS(r2) li r8,-MAX_ERRNO @@ -474,7 +470,6 @@ syscall_exit_finish: #endif mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - SYNC RFI _ASM_NOKPROBE_SYMBOL(syscall_exit_finish) #ifdef CONFIG_44x @@ -567,7 +562,6 @@ syscall_exit_work: * lockdep as we are supposed to have IRQs on at this point */ ori r10,r10,MSR_EE - SYNC mtmsr r10 /* Save NVGPRS if they're not saved already */ @@ -606,7 +600,6 @@ ret_from_kernel_syscall: #endif mtspr SPRN_SRR0, r9 mtspr SPRN_SRR1, r10 - SYNC RFI _ASM_NOKPROBE_SYMBOL(ret_from_kernel_syscall) @@ -810,7 +803,6 @@ fast_exception_return: REST_GPR(9, r11) REST_GPR(12, r11) lwz r11,GPR11(r11) - SYNC RFI _ASM_NOKPROBE_SYMBOL(fast_exception_return) @@ -819,19 +811,11 @@ _ASM_NOKPROBE_SYMBOL(fast_exception_return) 1: lis r3,exc_exit_restart_end@ha addi r3,r3,exc_exit_restart_end@l cmplw r12,r3 -#ifdef CONFIG_PPC_BOOK3S_601 - bge 2b -#else bge 3f -#endif lis r4,exc_exit_restart@ha addi r4,r4,exc_exit_restart@l cmplw r12,r4 -#ifdef CONFIG_PPC_BOOK3S_601 - blt 2b -#else blt 3f -#endif lis r3,fee_restarts@ha tophys(r3,r3) lwz r5,fee_restarts@l(r3) @@ -848,7 +832,6 @@ fee_restarts: /* aargh, a nonrecoverable interrupt, panic */ /* aargh, we don't know which trap this is */ -/* but the 601 doesn't implement the RI bit, so assume it's OK */ 3: li r10,-1 stw r10,_TRAP(r11) @@ -872,7 +855,6 @@ ret_from_except: * from the interrupt. */ /* Note: We don't bother telling lockdep about it */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) - SYNC /* Some chip revs have problems here... */ mtmsr r10 /* disable interrupts */ lwz r3,_MSR(r1) /* Returning to user mode? */ @@ -1035,7 +1017,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX) * exc_exit_restart below. -- paulus */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI) - SYNC mtmsr r10 /* clear the RI bit */ .globl exc_exit_restart exc_exit_restart: @@ -1046,7 +1027,6 @@ exc_exit_restart: lwz r1,GPR1(r1) .globl exc_exit_restart_end exc_exit_restart_end: - SYNC RFI _ASM_NOKPROBE_SYMBOL(exc_exit_restart) _ASM_NOKPROBE_SYMBOL(exc_exit_restart_end) @@ -1274,7 +1254,6 @@ do_resched: /* r10 contains MSR_KERNEL here */ mfmsr r10 #endif ori r10,r10,MSR_EE - SYNC mtmsr r10 /* hard-enable interrupts */ bl schedule recheck: @@ -1283,7 +1262,6 @@ recheck: * TI_FLAGS aren't advertised. */ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) - SYNC mtmsr r10 /* disable interrupts */ lwz r9,TI_FLAGS(r2) andi. r0,r9,_TIF_NEED_RESCHED @@ -1292,7 +1270,6 @@ recheck: beq restore_user do_user_signal: /* r10 contains MSR_KERNEL here */ ori r10,r10,MSR_EE - SYNC mtmsr r10 /* hard-enable interrupts */ /* save r13-r31 in the exception frame, if not already done */ lwz r3,_TRAP(r1) @@ -1316,19 +1293,11 @@ nonrecoverable: lis r10,exc_exit_restart_end@ha addi r10,r10,exc_exit_restart_end@l cmplw r12,r10 -#ifdef CONFIG_PPC_BOOK3S_601 - bgelr -#else bge 3f -#endif lis r11,exc_exit_restart@ha addi r11,r11,exc_exit_restart@l cmplw r12,r11 -#ifdef CONFIG_PPC_BOOK3S_601 - bltlr -#else blt 3f -#endif lis r10,ee_restarts@ha lwz r12,ee_restarts@l(r10) addi r12,r12,1 @@ -1336,7 +1305,6 @@ nonrecoverable: mr r12,r11 /* restart at exc_exit_restart */ blr 3: /* OK, we can't recover, kill this process */ - /* but the 601 doesn't implement the RI bit, so assume it's OK */ lwz r3,_TRAP(r1) andi. r0,r3,1 beq 5f @@ -1382,8 +1350,7 @@ _GLOBAL(enter_rtas) mfmsr r9 stw r9,8(r1) LOAD_REG_IMMEDIATE(r0,MSR_KERNEL) - SYNC /* disable interrupts so SRR0/1 */ - mtmsr r0 /* don't get trashed */ + mtmsr r0 /* disable interrupts so SRR0/1 don't get trashed */ li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR) mtlr r6 stw r7, THREAD + RTAS_SP(r2) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 733e40eba4eb..2f3846192ec7 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -430,7 +430,11 @@ _ASM_NOKPROBE_SYMBOL(save_nvgprs); #define FLUSH_COUNT_CACHE \ 1: nop; \ - patch_site 1b, patch__call_flush_branch_caches + patch_site 1b, patch__call_flush_branch_caches1; \ +1: nop; \ + patch_site 1b, patch__call_flush_branch_caches2; \ +1: nop; \ + patch_site 1b, patch__call_flush_branch_caches3 .macro nops number .rept \number @@ -512,7 +516,7 @@ _GLOBAL(_switch) kuap_check_amr r9, r10 - FLUSH_COUNT_CACHE + FLUSH_COUNT_CACHE /* Clobbers r9, ctr */ /* * On SMP kernels, care must be taken because a task may be diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index d9ed79415100..f579ce46eef2 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -988,7 +988,6 @@ kernel_dbg_exc: .endm masked_interrupt_book3e_0x500: - // XXX When adding support for EPR, use PACA_IRQ_EE_EDGE masked_interrupt_book3e PACA_IRQ_EE 1 masked_interrupt_book3e_0x900: @@ -1303,16 +1302,6 @@ fast_exception_return: addi r3,r1,STACK_FRAME_OVERHEAD; bl do_IRQ b ret_from_except -1: cmpwi cr0,r3,0xf00 - bne 1f - addi r3,r1,STACK_FRAME_OVERHEAD; - bl performance_monitor_exception - b ret_from_except -1: cmpwi cr0,r3,0xe60 - bne 1f - addi r3,r1,STACK_FRAME_OVERHEAD; - bl handle_hmi_exception - b ret_from_except 1: cmpwi cr0,r3,0x900 bne 1f addi r3,r1,STACK_FRAME_OVERHEAD; diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 5cdf4168a61a..8482739d42f3 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -754,10 +754,8 @@ u32 *fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs) void fadump_update_elfcore_header(char *bufp) { - struct elfhdr *elf; struct elf_phdr *phdr; - elf = (struct elfhdr *)bufp; bufp += sizeof(struct elfhdr); /* First note is a place holder for cpu notes info. */ diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S index 4ae39db70044..3ff9a8fafa46 100644 --- a/arch/powerpc/kernel/fpu.S +++ b/arch/powerpc/kernel/fpu.S @@ -87,7 +87,6 @@ BEGIN_FTR_SECTION oris r5,r5,MSR_VSX@h END_FTR_SECTION_IFSET(CPU_FTR_VSX) #endif - SYNC MTMSRD(r5) /* enable use of fpu now */ isync /* enable use of FP after return */ @@ -134,18 +133,3 @@ _GLOBAL(save_fpu) mffs fr0 stfd fr0,FPSTATE_FPSCR(r6) blr - -/* - * These are used in the alignment trap handler when emulating - * single-precision loads and stores. - */ - -_GLOBAL(cvt_fd) - lfs 0,0(r3) - stfd 0,0(r4) - blr - -_GLOBAL(cvt_df) - lfd 0,0(r3) - stfs 0,0(r4) - blr diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h index 9abec6cd099c..7c767765071d 100644 --- a/arch/powerpc/kernel/head_32.h +++ b/arch/powerpc/kernel/head_32.h @@ -40,48 +40,52 @@ .macro EXCEPTION_PROLOG_1 for_rtas=0 #ifdef CONFIG_VMAP_STACK - .ifeq \for_rtas - li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ - mtmsr r11 - isync - .endif - subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ + mr r11, r1 + subi r1, r1, INT_FRAME_SIZE /* use r1 if kernel */ + beq 1f + mfspr r1,SPRN_SPRG_THREAD + lwz r1,TASK_STACK-THREAD(r1) + addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE #else - tophys(r11,r1) /* use tophys(r1) if kernel */ - subi r11, r11, INT_FRAME_SIZE /* alloc exc. frame */ -#endif + subi r11, r1, INT_FRAME_SIZE /* use r1 if kernel */ beq 1f mfspr r11,SPRN_SPRG_THREAD - tovirt_vmstack r11, r11 lwz r11,TASK_STACK-THREAD(r11) addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE - tophys_novmstack r11, r11 +#endif 1: + tophys_novmstack r11, r11 #ifdef CONFIG_VMAP_STACK - mtcrf 0x7f, r11 + mtcrf 0x7f, r1 bt 32 - THREAD_ALIGN_SHIFT, stack_overflow #endif .endm .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0 -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION +#ifdef CONFIG_VMAP_STACK mtcr r10 -FTR_SECTION_ELSE - stw r10, _CCR(r11) -ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) + li r10, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ + mtmsr r10 + isync #else stw r10,_CCR(r11) /* save registers */ #endif mfspr r10, SPRN_SPRG_SCRATCH0 +#ifdef CONFIG_VMAP_STACK + stw r11,GPR1(r1) + stw r11,0(r1) + mr r11, r1 +#else + stw r1,GPR1(r11) + stw r1,0(r11) + tovirt(r1, r11) /* set new kernel sp */ +#endif stw r12,GPR12(r11) stw r9,GPR9(r11) stw r10,GPR10(r11) -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION +#ifdef CONFIG_VMAP_STACK mfcr r10 stw r10, _CCR(r11) -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #endif mfspr r12,SPRN_SPRG_SCRATCH1 stw r12,GPR11(r11) @@ -97,19 +101,12 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) stw r10, _DSISR(r11) .endif lwz r9, SRR1(r12) -#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_PPC_BOOK3S) -BEGIN_MMU_FTR_SECTION andi. r10, r9, MSR_PR -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) -#endif lwz r12, SRR0(r12) #else mfspr r12,SPRN_SRR0 mfspr r9,SPRN_SRR1 #endif - stw r1,GPR1(r11) - stw r1,0(r11) - tovirt_novmstack r1, r11 /* set new kernel sp */ #ifdef CONFIG_40x rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */ #else @@ -225,7 +222,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #endif mtspr SPRN_SRR1,r10 mtspr SPRN_SRR0,r11 - SYNC RFI /* jump to handler, enable MMU */ 99: b ret_from_kernel_syscall .endm @@ -327,20 +323,19 @@ label: .macro vmap_stack_overflow_exception #ifdef CONFIG_VMAP_STACK #ifdef CONFIG_SMP - mfspr r11, SPRN_SPRG_THREAD - tovirt(r11, r11) - lwz r11, TASK_CPU - THREAD(r11) - slwi r11, r11, 3 - addis r11, r11, emergency_ctx@ha + mfspr r1, SPRN_SPRG_THREAD + lwz r1, TASK_CPU - THREAD(r1) + slwi r1, r1, 3 + addis r1, r1, emergency_ctx@ha #else - lis r11, emergency_ctx@ha + lis r1, emergency_ctx@ha #endif - lwz r11, emergency_ctx@l(r11) - cmpwi cr1, r11, 0 + lwz r1, emergency_ctx@l(r1) + cmpwi cr1, r1, 0 bne cr1, 1f - lis r11, init_thread_union@ha - addi r11, r11, init_thread_union@l -1: addi r11, r11, THREAD_SIZE - INT_FRAME_SIZE + lis r1, init_thread_union@ha + addi r1, r1, init_thread_union@l +1: addi r1, r1, THREAD_SIZE - INT_FRAME_SIZE EXCEPTION_PROLOG_2 SAVE_NVGPRS(r11) addi r3, r1, STACK_FRAME_OVERHEAD diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 5b282d9965a5..44c9018aed1b 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -72,7 +72,6 @@ turn_on_mmu: lis r0,start_here@h ori r0,r0,start_here@l mtspr SPRN_SRR0,r0 - SYNC rfi /* enables MMU */ b . /* prevent prefetch past rfi */ diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index 0e05a9a47a4b..1510b2a56669 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -300,9 +300,6 @@ _GLOBAL(fsl_secondary_thread_init) rlwimi r3, r3, 30, 2, 30 mtspr SPRN_PIR, r3 1: -#endif - -_GLOBAL(generic_secondary_thread_init) mr r24,r3 /* turn on 64-bit mode */ @@ -312,13 +309,13 @@ _GLOBAL(generic_secondary_thread_init) bl relative_toc tovirt(r2,r2) -#ifdef CONFIG_PPC_BOOK3E /* Book3E initialization */ mr r3,r24 bl book3e_secondary_thread_init -#endif b generic_secondary_common_init +#endif /* CONFIG_PPC_BOOK3E */ + /* * On pSeries and most other platforms, secondary processors spin * in the following code. diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_book3s_32.S index f3ab94d73936..5eb9eedac920 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -34,16 +34,6 @@ #include "head_32.h" -/* 601 only have IBAT */ -#ifdef CONFIG_PPC_BOOK3S_601 -#define LOAD_BAT(n, reg, RA, RB) \ - li RA,0; \ - mtspr SPRN_IBAT##n##U,RA; \ - lwz RA,(n*16)+0(reg); \ - lwz RB,(n*16)+4(reg); \ - mtspr SPRN_IBAT##n##U,RA; \ - mtspr SPRN_IBAT##n##L,RB -#else #define LOAD_BAT(n, reg, RA, RB) \ /* see the comment for clear_bats() -- Cort */ \ li RA,0; \ @@ -57,11 +47,10 @@ lwz RB,(n*16)+12(reg); \ mtspr SPRN_DBAT##n##U,RA; \ mtspr SPRN_DBAT##n##L,RB -#endif __HEAD .stabs "arch/powerpc/kernel/",N_SO,0,0,0f - .stabs "head_32.S",N_SO,0,0,0f + .stabs "head_book3s_32.S",N_SO,0,0,0f 0: _ENTRY(_stext); @@ -166,9 +155,9 @@ __after_mmu_off: bl initial_bats bl load_segment_registers -#ifdef CONFIG_KASAN +BEGIN_MMU_FTR_SECTION bl early_hash_table -#endif +END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) #if defined(CONFIG_BOOTX_TEXT) bl setup_disp_bat #endif @@ -185,10 +174,8 @@ __after_mmu_off: bl reloc_offset li r24,0 /* cpu# */ bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_PPC_BOOK3S_32 bl reloc_offset bl init_idle_6xx -#endif /* CONFIG_PPC_BOOK3S_32 */ /* @@ -219,7 +206,6 @@ turn_on_mmu: lis r0,start_here@h ori r0,r0,start_here@l mtspr SPRN_SRR0,r0 - SYNC RFI /* enables MMU */ /* @@ -274,14 +260,8 @@ __secondary_hold_acknowledge: DO_KVM 0x200 MachineCheck: EXCEPTION_PROLOG_0 -#ifdef CONFIG_VMAP_STACK - li r11, MSR_KERNEL & ~(MSR_IR | MSR_RI) /* can take DTLB miss */ - mtmsr r11 - isync -#endif #ifdef CONFIG_PPC_CHRP mfspr r11, SPRN_SPRG_THREAD - tovirt_vmstack r11, r11 lwz r11, RTAS_SP(r11) cmpwi cr1, r11, 0 bne cr1, 7f @@ -439,7 +419,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_FPU_UNAVAILABLE) SystemCall: SYSCALL_ENTRY 0xc00 -/* Single step - not used on 601 */ EXCEPTION(0xd00, SingleStep, single_step_exception, EXC_XFER_STD) EXCEPTION(0xe00, Trap_0e, unknown_exception, EXC_XFER_STD) @@ -790,14 +769,12 @@ fast_hash_page_return: mtcr r11 lwz r11, THR11(r10) mfspr r10, SPRN_SPRG_SCRATCH0 - SYNC RFI 1: /* ISI */ mtcr r11 mfspr r11, SPRN_SPRG_SCRATCH1 mfspr r10, SPRN_SPRG_SCRATCH0 - SYNC RFI stack_overflow: @@ -888,7 +865,6 @@ __secondary_start_pmac_0: set to map the 0xf0000000 - 0xffffffff region */ mfmsr r0 rlwinm r0,r0,0,28,26 /* clear DR (0x10) */ - SYNC mtmsr r0 isync @@ -900,10 +876,8 @@ __secondary_start: lis r3,-KERNELBASE@h mr r4,r24 bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_PPC_BOOK3S_32 lis r3,-KERNELBASE@h bl init_idle_6xx -#endif /* CONFIG_PPC_BOOK3S_32 */ /* get current's stack and current */ lis r2,secondary_current@ha @@ -936,7 +910,6 @@ __secondary_start: ori r3,r3,start_secondary@l mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - SYNC RFI #endif /* CONFIG_SMP */ @@ -945,21 +918,9 @@ __secondary_start: #endif /* - * Those generic dummy functions are kept for CPUs not - * included in CONFIG_PPC_BOOK3S_32 - */ -#if !defined(CONFIG_PPC_BOOK3S_32) -_ENTRY(__save_cpu_setup) - blr -_ENTRY(__restore_cpu_setup) - blr -#endif /* !defined(CONFIG_PPC_BOOK3S_32) */ - -/* * Load stuff into the MMU. Intended to be called with * IR=0 and DR=0. */ -#ifdef CONFIG_KASAN early_hash_table: sync /* Force all PTE updates to finish */ isync @@ -970,8 +931,10 @@ early_hash_table: lis r6, early_hash - PAGE_OFFSET@h ori r6, r6, 3 /* 256kB table */ mtspr SPRN_SDR1, r6 + lis r6, early_hash@h + lis r3, Hash@ha + stw r6, Hash@l(r3) blr -#endif load_up_mmu: sync /* Force all PTE updates to finish */ @@ -985,8 +948,7 @@ load_up_mmu: lwz r6,_SDR1@l(r6) mtspr SPRN_SDR1,r6 -/* Load the BAT registers with the values set up by MMU_init. - MMU_init takes care of whether we're on a 601 or not. */ +/* Load the BAT registers with the values set up by MMU_init. */ lis r3,BATS@ha addi r3,r3,BATS@l tophys(r3,r3) @@ -1002,7 +964,7 @@ BEGIN_MMU_FTR_SECTION END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) blr -load_segment_registers: +_GLOBAL(load_segment_registers) li r0, NUM_USER_SEGMENTS /* load up user segment register values */ mtctr r0 /* for context 0 */ li r3, 0 /* Kp = 0, Ks = 0, VSID = 0 */ @@ -1061,11 +1023,7 @@ start_here: bl machine_init bl __save_cpu_setup bl MMU_init -#ifdef CONFIG_KASAN -BEGIN_MMU_FTR_SECTION bl MMU_init_hw_patch -END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) -#endif /* * Go back to running unmapped so we can load up new values @@ -1080,7 +1038,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) .align 4 mtspr SPRN_SRR0,r4 mtspr SPRN_SRR1,r3 - SYNC RFI /* Load up the kernel context */ 2: bl load_up_mmu @@ -1092,7 +1049,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) */ lis r5, abatron_pteptrs@h ori r5, r5, abatron_pteptrs@l - stw r5, 0xf0(r0) /* This much match your Abatron config */ + stw r5, 0xf0(0) /* This much match your Abatron config */ lis r6, swapper_pg_dir@h ori r6, r6, swapper_pg_dir@l tophys(r5, r5) @@ -1105,7 +1062,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE) ori r3,r3,start_kernel@l mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - SYNC RFI /* @@ -1165,7 +1121,6 @@ EXPORT_SYMBOL(switch_mmu_context) clear_bats: li r10,0 -#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT0U,r10 mtspr SPRN_DBAT0L,r10 mtspr SPRN_DBAT1U,r10 @@ -1174,7 +1129,6 @@ clear_bats: mtspr SPRN_DBAT2L,r10 mtspr SPRN_DBAT3U,r10 mtspr SPRN_DBAT3L,r10 -#endif mtspr SPRN_IBAT0U,r10 mtspr SPRN_IBAT0L,r10 mtspr SPRN_IBAT1U,r10 @@ -1223,7 +1177,6 @@ _ENTRY(update_bats) .align 4 mtspr SPRN_SRR0, r4 mtspr SPRN_SRR1, r3 - SYNC RFI 1: bl clear_bats lis r3, BATS@ha @@ -1243,7 +1196,6 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) mtmsr r3 mtspr SPRN_SRR0, r7 mtspr SPRN_SRR1, r6 - SYNC RFI flush_tlbs: @@ -1267,26 +1219,9 @@ mmu_off: sync RFI -/* - * On 601, we use 3 BATs to map up to 24M of RAM at _PAGE_OFFSET - * (we keep one for debugging) and on others, we use one 256M BAT. - */ +/* We use one BAT to map up to 256M of RAM at _PAGE_OFFSET */ initial_bats: lis r11,PAGE_OFFSET@h -#ifdef CONFIG_PPC_BOOK3S_601 - ori r11,r11,4 /* set up BAT registers for 601 */ - li r8,0x7f /* valid, block length = 8MB */ - mtspr SPRN_IBAT0U,r11 /* N.B. 601 has valid bit in */ - mtspr SPRN_IBAT0L,r8 /* lower BAT register */ - addis r11,r11,0x800000@h - addis r8,r8,0x800000@h - mtspr SPRN_IBAT1U,r11 - mtspr SPRN_IBAT1L,r8 - addis r11,r11,0x800000@h - addis r8,r8,0x800000@h - mtspr SPRN_IBAT2U,r11 - mtspr SPRN_IBAT2L,r8 -#else tophys(r8,r11) #ifdef CONFIG_SMP ori r8,r8,0x12 /* R/W access, M=1 */ @@ -1295,11 +1230,10 @@ initial_bats: #endif /* CONFIG_SMP */ ori r11,r11,BL_256M<<2|0x2 /* set up BAT registers for 604 */ - mtspr SPRN_DBAT0L,r8 /* N.B. 6xx (not 601) have valid */ + mtspr SPRN_DBAT0L,r8 /* N.B. 6xx have valid */ mtspr SPRN_DBAT0U,r11 /* bit in upper BAT register */ mtspr SPRN_IBAT0L,r8 mtspr SPRN_IBAT0U,r11 -#endif isync blr @@ -1317,13 +1251,8 @@ setup_disp_bat: beqlr lwz r11,0(r8) lwz r8,4(r8) -#ifndef CONFIG_PPC_BOOK3S_601 mtspr SPRN_DBAT3L,r8 mtspr SPRN_DBAT3U,r11 -#else - mtspr SPRN_IBAT3L,r8 - mtspr SPRN_IBAT3U,r11 -#endif blr #endif /* CONFIG_BOOTX_TEXT */ diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 18f87bf9e32b..71c359d438b5 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -176,7 +176,6 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) #endif mtspr SPRN_SRR1,r10 mtspr SPRN_SRR0,r11 - SYNC RFI /* jump to handler, enable MMU */ 99: b ret_from_kernel_syscall .endm diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index 1f4a1efa0074..f4e8f21046f5 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -494,151 +494,6 @@ reset: } } -static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info) -{ - return ((info->address <= dar) && (dar - info->address < info->len)); -} - -static bool ea_user_range_overlaps(unsigned long ea, int size, - struct arch_hw_breakpoint *info) -{ - return ((ea < info->address + info->len) && - (ea + size > info->address)); -} - -static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) -{ - unsigned long hw_start_addr, hw_end_addr; - - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); - - return ((hw_start_addr <= dar) && (hw_end_addr > dar)); -} - -static bool ea_hw_range_overlaps(unsigned long ea, int size, - struct arch_hw_breakpoint *info) -{ - unsigned long hw_start_addr, hw_end_addr; - - hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); - hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); - - return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); -} - -/* - * If hw has multiple DAWR registers, we also need to check all - * dawrx constraint bits to confirm this is _really_ a valid event. - * If type is UNKNOWN, but privilege level matches, consider it as - * a positive match. - */ -static bool check_dawrx_constraints(struct pt_regs *regs, int type, - struct arch_hw_breakpoint *info) -{ - if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ)) - return false; - - /* - * The Cache Management instructions other than dcbz never - * cause a match. i.e. if type is CACHEOP, the instruction - * is dcbz, and dcbz is treated as Store. - */ - if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE)) - return false; - - if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL)) - return false; - - if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER)) - return false; - - return true; -} - -/* - * Return true if the event is valid wrt dawr configuration, - * including extraneous exception. Otherwise return false. - */ -static bool check_constraints(struct pt_regs *regs, struct ppc_inst instr, - unsigned long ea, int type, int size, - struct arch_hw_breakpoint *info) -{ - bool in_user_range = dar_in_user_range(regs->dar, info); - bool dawrx_constraints; - - /* - * 8xx supports only one breakpoint and thus we can - * unconditionally return true. - */ - if (IS_ENABLED(CONFIG_PPC_8xx)) { - if (!in_user_range) - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - return true; - } - - if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) { - if (cpu_has_feature(CPU_FTR_ARCH_31) && - !dar_in_hw_range(regs->dar, info)) - return false; - - return true; - } - - dawrx_constraints = check_dawrx_constraints(regs, type, info); - - if (type == UNKNOWN) { - if (cpu_has_feature(CPU_FTR_ARCH_31) && - !dar_in_hw_range(regs->dar, info)) - return false; - - return dawrx_constraints; - } - - if (ea_user_range_overlaps(ea, size, info)) - return dawrx_constraints; - - if (ea_hw_range_overlaps(ea, size, info)) { - if (dawrx_constraints) { - info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; - return true; - } - } - return false; -} - -static int cache_op_size(void) -{ -#ifdef __powerpc64__ - return ppc64_caches.l1d.block_size; -#else - return L1_CACHE_BYTES; -#endif -} - -static void get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, - int *type, int *size, unsigned long *ea) -{ - struct instruction_op op; - - if (__get_user_instr_inatomic(*instr, (void __user *)regs->nip)) - return; - - analyse_instr(&op, regs, *instr); - *type = GETTYPE(op.type); - *ea = op.ea; -#ifdef __powerpc64__ - if (!(regs->msr & MSR_64BIT)) - *ea &= 0xffffffffUL; -#endif - - *size = GETSIZE(op.type); - if (*type == CACHEOP) { - *size = cache_op_size(); - *ea &= ~(*size - 1); - } -} - static bool is_larx_stcx_instr(int type) { return type == LARX || type == STCX; @@ -722,7 +577,7 @@ int hw_breakpoint_handler(struct die_args *args) rcu_read_lock(); if (!IS_ENABLED(CONFIG_PPC_8xx)) - get_instr_detail(regs, &instr, &type, &size, &ea); + wp_get_instr_detail(regs, &instr, &type, &size, &ea); for (i = 0; i < nr_wp_slots(); i++) { bp[i] = __this_cpu_read(bp_per_reg[i]); @@ -732,7 +587,7 @@ int hw_breakpoint_handler(struct die_args *args) info[i] = counter_arch_bp(bp[i]); info[i]->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ; - if (check_constraints(regs, instr, ea, type, size, info[i])) { + if (wp_check_constraints(regs, instr, ea, type, size, info[i])) { if (!IS_ENABLED(CONFIG_PPC_8xx) && ppc_inst_equal(instr, ppc_inst(0))) { handler_error(bp[i], info[i]); diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c new file mode 100644 index 000000000000..867ee4aa026a --- /dev/null +++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0+ +#include <linux/kernel.h> +#include <linux/uaccess.h> +#include <linux/sched.h> +#include <asm/hw_breakpoint.h> +#include <asm/sstep.h> +#include <asm/cache.h> + +static bool dar_in_user_range(unsigned long dar, struct arch_hw_breakpoint *info) +{ + return ((info->address <= dar) && (dar - info->address < info->len)); +} + +static bool ea_user_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) +{ + return ((ea < info->address + info->len) && + (ea + size > info->address)); +} + +static bool dar_in_hw_range(unsigned long dar, struct arch_hw_breakpoint *info) +{ + unsigned long hw_start_addr, hw_end_addr; + + hw_start_addr = ALIGN_DOWN(info->address, HW_BREAKPOINT_SIZE); + hw_end_addr = ALIGN(info->address + info->len, HW_BREAKPOINT_SIZE); + + return ((hw_start_addr <= dar) && (hw_end_addr > dar)); +} + +static bool ea_hw_range_overlaps(unsigned long ea, int size, + struct arch_hw_breakpoint *info) +{ + unsigned long hw_start_addr, hw_end_addr; + unsigned long align_size = HW_BREAKPOINT_SIZE; + + /* + * On p10 predecessors, quadword is handle differently then + * other instructions. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_31) && size == 16) + align_size = HW_BREAKPOINT_SIZE_QUADWORD; + + hw_start_addr = ALIGN_DOWN(info->address, align_size); + hw_end_addr = ALIGN(info->address + info->len, align_size); + + return ((ea < hw_end_addr) && (ea + size > hw_start_addr)); +} + +/* + * If hw has multiple DAWR registers, we also need to check all + * dawrx constraint bits to confirm this is _really_ a valid event. + * If type is UNKNOWN, but privilege level matches, consider it as + * a positive match. + */ +static bool check_dawrx_constraints(struct pt_regs *regs, int type, + struct arch_hw_breakpoint *info) +{ + if (OP_IS_LOAD(type) && !(info->type & HW_BRK_TYPE_READ)) + return false; + + /* + * The Cache Management instructions other than dcbz never + * cause a match. i.e. if type is CACHEOP, the instruction + * is dcbz, and dcbz is treated as Store. + */ + if ((OP_IS_STORE(type) || type == CACHEOP) && !(info->type & HW_BRK_TYPE_WRITE)) + return false; + + if (is_kernel_addr(regs->nip) && !(info->type & HW_BRK_TYPE_KERNEL)) + return false; + + if (user_mode(regs) && !(info->type & HW_BRK_TYPE_USER)) + return false; + + return true; +} + +/* + * Return true if the event is valid wrt dawr configuration, + * including extraneous exception. Otherwise return false. + */ +bool wp_check_constraints(struct pt_regs *regs, struct ppc_inst instr, + unsigned long ea, int type, int size, + struct arch_hw_breakpoint *info) +{ + bool in_user_range = dar_in_user_range(regs->dar, info); + bool dawrx_constraints; + + /* + * 8xx supports only one breakpoint and thus we can + * unconditionally return true. + */ + if (IS_ENABLED(CONFIG_PPC_8xx)) { + if (!in_user_range) + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + return true; + } + + if (unlikely(ppc_inst_equal(instr, ppc_inst(0)))) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; + + return true; + } + + dawrx_constraints = check_dawrx_constraints(regs, type, info); + + if (type == UNKNOWN) { + if (cpu_has_feature(CPU_FTR_ARCH_31) && + !dar_in_hw_range(regs->dar, info)) + return false; + + return dawrx_constraints; + } + + if (ea_user_range_overlaps(ea, size, info)) + return dawrx_constraints; + + if (ea_hw_range_overlaps(ea, size, info)) { + if (dawrx_constraints) { + info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ; + return true; + } + } + return false; +} + +static int cache_op_size(void) +{ +#ifdef __powerpc64__ + return ppc64_caches.l1d.block_size; +#else + return L1_CACHE_BYTES; +#endif +} + +void wp_get_instr_detail(struct pt_regs *regs, struct ppc_inst *instr, + int *type, int *size, unsigned long *ea) +{ + struct instruction_op op; + + if (__get_user_instr_inatomic(*instr, (void __user *)regs->nip)) + return; + + analyse_instr(&op, regs, *instr); + *type = GETTYPE(op.type); + *ea = op.ea; +#ifdef __powerpc64__ + if (!(regs->msr & MSR_64BIT)) + *ea &= 0xffffffffUL; +#endif + + *size = GETSIZE(op.type); + if (*type == CACHEOP) { + *size = cache_op_size(); + *ea &= ~(*size - 1); + } else if (*type == LOAD_VMX || *type == STORE_VMX) { + *ea &= ~(*size - 1); + } +} diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 422e31d2f5a2..ae0e2632393d 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -41,14 +41,6 @@ static int __init powersave_off(char *arg) } __setup("powersave=off", powersave_off); -#ifdef CONFIG_HOTPLUG_CPU -void arch_cpu_idle_dead(void) -{ - sched_preempt_enable_no_resched(); - cpu_die(); -} -#endif - void arch_cpu_idle(void) { ppc64_runlatch_off(); diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index bf21ebd36190..7d0f7682d01d 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -104,7 +104,7 @@ static inline notrace unsigned long get_irq_happened(void) static inline notrace int decrementer_check_overflow(void) { - u64 now = get_tb_or_rtc(); + u64 now = get_tb(); u64 *next_tb = this_cpu_ptr(&decrementers_next_tb); return now >= *next_tb; @@ -113,7 +113,7 @@ static inline notrace int decrementer_check_overflow(void) #ifdef CONFIG_PPC_BOOK3E /* This is called whenever we are re-enabling interrupts - * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if + * and returns either 0 (nothing to do) or 500/900/280 if * there's an EE, DEC or DBELL to generate. * * This is called in two contexts: From arch_local_irq_restore() @@ -181,16 +181,6 @@ notrace unsigned int __check_irq_replay(void) return 0x500; } - /* - * Check if an EPR external interrupt happened this bit is typically - * set if we need to handle another "edge" interrupt from within the - * MPIC "EPR" handler. - */ - if (happened & PACA_IRQ_EE_EDGE) { - local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; - return 0x500; - } - if (happened & PACA_IRQ_DBELL) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; return 0x280; @@ -201,6 +191,25 @@ notrace unsigned int __check_irq_replay(void) return 0; } + +/* + * This is specifically called by assembly code to re-enable interrupts + * if they are currently disabled. This is typically called before + * schedule() or do_signal() when returning to userspace. We do it + * in C to avoid the burden of dealing with lockdep etc... + * + * NOTE: This is called with interrupts hard disabled but not marked + * as such in paca->irq_happened, so we need to resync this. + */ +void notrace restore_interrupts(void) +{ + if (irqs_disabled()) { + local_paca->irq_happened |= PACA_IRQ_HARD_DIS; + local_irq_enable(); + } else + __hard_irq_enable(); +} + #endif /* CONFIG_PPC_BOOK3E */ void replay_soft_interrupts(void) @@ -214,7 +223,7 @@ void replay_soft_interrupts(void) struct pt_regs regs; ppc_save_regs(®s); - regs.softe = IRQS_ALL_DISABLED; + regs.softe = IRQS_ENABLED; again: if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) @@ -270,19 +279,6 @@ again: hard_irq_disable(); } - /* - * Check if an EPR external interrupt happened this bit is typically - * set if we need to handle another "edge" interrupt from within the - * MPIC "EPR" handler. - */ - if (IS_ENABLED(CONFIG_PPC_BOOK3E) && (happened & PACA_IRQ_EE_EDGE)) { - local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE; - regs.trap = 0x500; - do_IRQ(®s); - if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) - hard_irq_disable(); - } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) @@ -368,6 +364,12 @@ notrace void arch_local_irq_restore(unsigned long mask) } } + /* + * Disable preempt here, so that the below preempt_enable will + * perform resched if required (a replayed interrupt may set + * need_resched). + */ + preempt_disable(); irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); @@ -377,28 +379,11 @@ notrace void arch_local_irq_restore(unsigned long mask) trace_hardirqs_on(); irq_soft_mask_set(IRQS_ENABLED); __hard_irq_enable(); + preempt_enable(); } EXPORT_SYMBOL(arch_local_irq_restore); /* - * This is specifically called by assembly code to re-enable interrupts - * if they are currently disabled. This is typically called before - * schedule() or do_signal() when returning to userspace. We do it - * in C to avoid the burden of dealing with lockdep etc... - * - * NOTE: This is called with interrupts hard disabled but not marked - * as such in paca->irq_happened, so we need to resync this. - */ -void notrace restore_interrupts(void) -{ - if (irqs_disabled()) { - local_paca->irq_happened |= PACA_IRQ_HARD_DIS; - local_irq_enable(); - } else - __hard_irq_enable(); -} - -/* * This is a helper to use when about to go into idle low-power * when the latter has the side effect of re-enabling interrupts * (such as calling H_CEDE under pHyp). diff --git a/arch/powerpc/kernel/l2cr_6xx.S b/arch/powerpc/kernel/l2cr_6xx.S index 5f07aa5e9851..225511d73bef 100644 --- a/arch/powerpc/kernel/l2cr_6xx.S +++ b/arch/powerpc/kernel/l2cr_6xx.S @@ -256,7 +256,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450) sync /* Restore MSR (restores EE and DR bits to original state) */ - SYNC mtmsr r7 isync @@ -377,7 +376,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_L3CR) 1: bdnz 1b /* Restore MSR (restores EE and DR bits to original state) */ -4: SYNC +4: mtmsr r7 isync blr diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index b24f866fef81..717e658b90fd 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -215,19 +215,6 @@ _GLOBAL(low_choose_7447a_dfs) #endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */ -/* - * complement mask on the msr then "or" some values on. - * _nmask_and_or_msr(nmask, value_to_or) - */ -_GLOBAL(_nmask_and_or_msr) - mfmsr r0 /* Get current msr */ - andc r0,r0,r3 /* And off the bits set in r3 (first parm) */ - or r0,r0,r4 /* Or on the bits in r4 (second parm) */ - SYNC /* Some chip revs have problems here... */ - mtmsr r0 /* Update machine state */ - isync - blr /* Done */ - #ifdef CONFIG_40x /* @@ -268,41 +255,6 @@ _ASM_NOKPROBE_SYMBOL(real_writeb) #endif /* CONFIG_40x */ - -/* - * Flush instruction cache. - * This is a no-op on the 601. - */ -#ifndef CONFIG_PPC_8xx -_GLOBAL(flush_instruction_cache) -#if defined(CONFIG_4xx) - lis r3, KERNELBASE@h - iccci 0,r3 -#elif defined(CONFIG_FSL_BOOKE) -#ifdef CONFIG_E200 - mfspr r3,SPRN_L1CSR0 - ori r3,r3,L1CSR0_CFI|L1CSR0_CLFC - /* msync; isync recommended here */ - mtspr SPRN_L1CSR0,r3 - isync - blr -#endif - mfspr r3,SPRN_L1CSR1 - ori r3,r3,L1CSR1_ICFI|L1CSR1_ICLFR - mtspr SPRN_L1CSR1,r3 -#elif defined(CONFIG_PPC_BOOK3S_601) - blr /* for 601, do nothing */ -#else - /* 603/604 processor - use invalidate-all bit in HID0 */ - mfspr r3,SPRN_HID0 - ori r3,r3,HID0_ICFI - mtspr SPRN_HID0,r3 -#endif /* CONFIG_4xx */ - isync - blr -EXPORT_SYMBOL(flush_instruction_cache) -#endif /* CONFIG_PPC_8xx */ - /* * Copy a whole page. We use the dcbz instruction on the destination * to reduce memory traffic (it eliminates the unnecessary reads of diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S index 7bb46ad98207..070465825c21 100644 --- a/arch/powerpc/kernel/misc_64.S +++ b/arch/powerpc/kernel/misc_64.S @@ -365,7 +365,6 @@ _GLOBAL(kexec_smp_wait) li r4,KEXEC_STATE_REAL_MODE stb r4,PACAKEXECSTATE(r13) - SYNC b kexec_wait diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 73a57043ee66..d421a2c7f822 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -124,10 +124,8 @@ unsigned long notrace msr_check_and_set(unsigned long bits) newmsr = oldmsr | bits; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) newmsr |= MSR_VSX; -#endif if (oldmsr != newmsr) mtmsr_isync(newmsr); @@ -144,10 +142,8 @@ void notrace __msr_check_and_clear(unsigned long bits) newmsr = oldmsr & ~bits; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX) && (bits & MSR_FP)) newmsr &= ~MSR_VSX; -#endif if (oldmsr != newmsr) mtmsr_isync(newmsr); @@ -162,10 +158,8 @@ static void __giveup_fpu(struct task_struct *tsk) save_fpu(tsk); msr = tsk->thread.regs->msr; msr &= ~(MSR_FP|MSR_FE0|MSR_FE1); -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr &= ~MSR_VSX; -#endif tsk->thread.regs->msr = msr; } @@ -235,6 +229,8 @@ void enable_kernel_fp(void) } } EXPORT_SYMBOL(enable_kernel_fp); +#else +static inline void __giveup_fpu(struct task_struct *tsk) { } #endif /* CONFIG_PPC_FPU */ #ifdef CONFIG_ALTIVEC @@ -245,10 +241,8 @@ static void __giveup_altivec(struct task_struct *tsk) save_altivec(tsk); msr = tsk->thread.regs->msr; msr &= ~MSR_VEC; -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr &= ~MSR_VSX; -#endif tsk->thread.regs->msr = msr; } @@ -414,21 +408,14 @@ static unsigned long msr_all_available; static int __init init_msr_all_available(void) { -#ifdef CONFIG_PPC_FPU - msr_all_available |= MSR_FP; -#endif -#ifdef CONFIG_ALTIVEC + if (IS_ENABLED(CONFIG_PPC_FPU)) + msr_all_available |= MSR_FP; if (cpu_has_feature(CPU_FTR_ALTIVEC)) msr_all_available |= MSR_VEC; -#endif -#ifdef CONFIG_VSX if (cpu_has_feature(CPU_FTR_VSX)) msr_all_available |= MSR_VSX; -#endif -#ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) msr_all_available |= MSR_SPE; -#endif return 0; } @@ -452,18 +439,12 @@ void giveup_all(struct task_struct *tsk) WARN_ON((usermsr & MSR_VSX) && !((usermsr & MSR_FP) && (usermsr & MSR_VEC))); -#ifdef CONFIG_PPC_FPU if (usermsr & MSR_FP) __giveup_fpu(tsk); -#endif -#ifdef CONFIG_ALTIVEC if (usermsr & MSR_VEC) __giveup_altivec(tsk); -#endif -#ifdef CONFIG_SPE if (usermsr & MSR_SPE) __giveup_spe(tsk); -#endif msr_check_and_clear(msr_all_available); } @@ -509,19 +490,18 @@ static bool should_restore_altivec(void) { return false; } static void do_restore_altivec(void) { } #endif /* CONFIG_ALTIVEC */ -#ifdef CONFIG_VSX static bool should_restore_vsx(void) { if (cpu_has_feature(CPU_FTR_VSX)) return true; return false; } +#ifdef CONFIG_VSX static void do_restore_vsx(void) { current->thread.used_vsr = 1; } #else -static bool should_restore_vsx(void) { return false; } static void do_restore_vsx(void) { } #endif /* CONFIG_VSX */ @@ -581,7 +561,7 @@ void notrace restore_math(struct pt_regs *regs) regs->msr |= new_msr | fpexc_mode; } } -#endif +#endif /* CONFIG_PPC_BOOK3S_64 */ static void save_all(struct task_struct *tsk) { @@ -642,6 +622,44 @@ void do_send_trap(struct pt_regs *regs, unsigned long address, (void __user *)address); } #else /* !CONFIG_PPC_ADV_DEBUG_REGS */ + +static void do_break_handler(struct pt_regs *regs) +{ + struct arch_hw_breakpoint null_brk = {0}; + struct arch_hw_breakpoint *info; + struct ppc_inst instr = ppc_inst(0); + int type = 0; + int size = 0; + unsigned long ea; + int i; + + /* + * If underneath hw supports only one watchpoint, we know it + * caused exception. 8xx also falls into this category. + */ + if (nr_wp_slots() == 1) { + __set_breakpoint(0, &null_brk); + current->thread.hw_brk[0] = null_brk; + current->thread.hw_brk[0].flags |= HW_BRK_FLAG_DISABLED; + return; + } + + /* Otherwise findout which DAWR caused exception and disable it. */ + wp_get_instr_detail(regs, &instr, &type, &size, &ea); + + for (i = 0; i < nr_wp_slots(); i++) { + info = ¤t->thread.hw_brk[i]; + if (!info->address) + continue; + + if (wp_check_constraints(regs, instr, ea, type, size, info)) { + __set_breakpoint(i, &null_brk); + current->thread.hw_brk[i] = null_brk; + current->thread.hw_brk[i].flags |= HW_BRK_FLAG_DISABLED; + } + } +} + void do_break (struct pt_regs *regs, unsigned long address, unsigned long error_code) { @@ -653,6 +671,16 @@ void do_break (struct pt_regs *regs, unsigned long address, if (debugger_break_match(regs)) return; + /* + * We reach here only when watchpoint exception is generated by ptrace + * event (or hw is buggy!). Now if CONFIG_HAVE_HW_BREAKPOINT is set, + * watchpoint is already handled by hw_breakpoint_handler() so we don't + * have to do anything. But when CONFIG_HAVE_HW_BREAKPOINT is not set, + * we need to manually handle the watchpoint here. + */ + if (!IS_ENABLED(CONFIG_HAVE_HW_BREAKPOINT)) + do_break_handler(regs); + /* Deliver the signal to userspace */ force_sig_fault(SIGTRAP, TRAP_HWBKPT, (void __user *)address); } @@ -783,9 +811,8 @@ static void switch_hw_breakpoint(struct task_struct *new) static inline int __set_dabr(unsigned long dabr, unsigned long dabrx) { mtspr(SPRN_DAC1, dabr); -#ifdef CONFIG_PPC_47x - isync(); -#endif + if (IS_ENABLED(CONFIG_PPC_47x)) + isync(); return 0; } #elif defined(CONFIG_PPC_BOOK3S) @@ -1256,15 +1283,17 @@ struct task_struct *__switch_to(struct task_struct *prev, restore_math(current->thread.regs); /* - * The copy-paste buffer can only store into foreign real - * addresses, so unprivileged processes can not see the - * data or use it in any way unless they have foreign real - * mappings. If the new process has the foreign real address - * mappings, we must issue a cp_abort to clear any state and - * prevent snooping, corruption or a covert channel. + * On POWER9 the copy-paste buffer can only paste into + * foreign real addresses, so unprivileged processes can not + * see the data or use it in any way unless they have + * foreign real mappings. If the new process has the foreign + * real address mappings, we must issue a cp_abort to clear + * any state and prevent snooping, corruption or a covert + * channel. ISA v3.1 supports paste into local memory. */ if (current->mm && - atomic_read(¤t->mm->context.vas_windows)) + (cpu_has_feature(CPU_FTR_ARCH_31) || + atomic_read(¤t->mm->context.vas_windows))) asm volatile(PPC_CP_ABORT); } #endif /* CONFIG_PPC_BOOK3S_64 */ @@ -1453,12 +1482,13 @@ void show_regs(struct pt_regs * regs) trap = TRAP(regs); if (!trap_is_syscall(regs) && cpu_has_feature(CPU_FTR_CFAR)) pr_cont("CFAR: "REG" ", regs->orig_gpr3); - if (trap == 0x200 || trap == 0x300 || trap == 0x600) -#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE) - pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); -#else - pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); -#endif + if (trap == 0x200 || trap == 0x300 || trap == 0x600) { + if (IS_ENABLED(CONFIG_4xx) || IS_ENABLED(CONFIG_BOOKE)) + pr_cont("DEAR: "REG" ESR: "REG" ", regs->dar, regs->dsisr); + else + pr_cont("DAR: "REG" DSISR: %08lx ", regs->dar, regs->dsisr); + } + #ifdef CONFIG_PPC64 pr_cont("IRQMASK: %lx ", regs->softe); #endif @@ -1475,14 +1505,14 @@ void show_regs(struct pt_regs * regs) break; } pr_cont("\n"); -#ifdef CONFIG_KALLSYMS /* * Lookup NIP late so we have the best change of getting the * above info out without failing */ - printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); - printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); -#endif + if (IS_ENABLED(CONFIG_KALLSYMS)) { + printk("NIP ["REG"] %pS\n", regs->nip, (void *)regs->nip); + printk("LR ["REG"] %pS\n", regs->link, (void *)regs->link); + } show_stack(current, (unsigned long *) regs->gpr[1], KERN_DEFAULT); if (!user_mode(regs)) show_instructions(regs); @@ -1731,11 +1761,9 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) #ifdef CONFIG_PPC64 unsigned long load_addr = regs->gpr[2]; /* saved by ELF_PLAT_INIT */ -#ifdef CONFIG_PPC_BOOK3S_64 - if (!radix_enabled()) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !radix_enabled()) preload_new_slb_context(start, sp); #endif -#endif /* * If we exec out of a kernel thread then thread.regs will not be @@ -1866,7 +1894,6 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) * fpexc_mode. fpexc_mode is also used for setting FP exception * mode (asyn, precise, disabled) for 'Classic' FP. */ if (val & PR_FP_EXC_SW_ENABLE) { -#ifdef CONFIG_SPE if (cpu_has_feature(CPU_FTR_SPE)) { /* * When the sticky exception bits are set @@ -1880,16 +1907,15 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) * anyway to restore the prctl settings from * the saved environment. */ +#ifdef CONFIG_SPE tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); tsk->thread.fpexc_mode = val & (PR_FP_EXC_SW_ENABLE | PR_FP_ALL_EXCEPT); +#endif return 0; } else { return -EINVAL; } -#else - return -EINVAL; -#endif } /* on a CONFIG_SPE this does not hurt us. The bits that @@ -1908,10 +1934,9 @@ int set_fpexc_mode(struct task_struct *tsk, unsigned int val) int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) { - unsigned int val; + unsigned int val = 0; - if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) -#ifdef CONFIG_SPE + if (tsk->thread.fpexc_mode & PR_FP_EXC_SW_ENABLE) { if (cpu_has_feature(CPU_FTR_SPE)) { /* * When the sticky exception bits are set @@ -1925,15 +1950,15 @@ int get_fpexc_mode(struct task_struct *tsk, unsigned long adr) * anyway to restore the prctl settings from * the saved environment. */ +#ifdef CONFIG_SPE tsk->thread.spefscr_last = mfspr(SPRN_SPEFSCR); val = tsk->thread.fpexc_mode; +#endif } else return -EINVAL; -#else - return -EINVAL; -#endif - else + } else { val = __unpack_fe01(tsk->thread.fpexc_mode); + } return put_user(val, (unsigned int __user *) adr); } @@ -2102,10 +2127,8 @@ void show_stack(struct task_struct *tsk, unsigned long *stack, unsigned long sp, ip, lr, newsp; int count = 0; int firstframe = 1; -#ifdef CONFIG_FUNCTION_GRAPH_TRACER unsigned long ret_addr; int ftrace_idx = 0; -#endif if (tsk == NULL) tsk = current; @@ -2133,12 +2156,10 @@ void show_stack(struct task_struct *tsk, unsigned long *stack, if (!firstframe || ip != lr) { printk("%s["REG"] ["REG"] %pS", loglvl, sp, ip, (void *)ip); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER ret_addr = ftrace_graph_ret_addr(current, &ftrace_idx, ip, stack); if (ret_addr != ip) pr_cont(" (%pS)", (void *)ret_addr); -#endif if (firstframe) pr_cont(" (unreliable)"); pr_cont("\n"); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d8a2fb87ba0c..c1545f22c077 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -776,6 +776,11 @@ void __init early_init_devtree(void *params) limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); +#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_4K_PAGES) + if (!early_radix_enabled()) + memblock_cap_memory_range(0, 1UL << (H_MAX_PHYSMEM_BITS)); +#endif + memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index ae7ec9903191..5090a5ab54e5 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2422,10 +2422,19 @@ static void __init prom_check_displays(void) u32 width, height, pitch, addr; prom_printf("Setting btext !\n"); - prom_getprop(node, "width", &width, 4); - prom_getprop(node, "height", &height, 4); - prom_getprop(node, "linebytes", &pitch, 4); - prom_getprop(node, "address", &addr, 4); + + if (prom_getprop(node, "width", &width, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "height", &height, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "linebytes", &pitch, 4) == PROM_ERROR) + return; + + if (prom_getprop(node, "address", &addr, 4) == PROM_ERROR) + return; + prom_printf("W=%d H=%d LB=%d addr=0x%x\n", width, height, pitch, addr); btext_setup_display(width, height, 8, pitch, addr); diff --git a/arch/powerpc/kernel/ptrace/ptrace-noadv.c b/arch/powerpc/kernel/ptrace/ptrace-noadv.c index 697c7e4b5877..aa36fcad36cd 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-noadv.c +++ b/arch/powerpc/kernel/ptrace/ptrace-noadv.c @@ -57,6 +57,8 @@ void ppc_gethwdinfo(struct ppc_debug_info *dbginfo) } else { dbginfo->features = 0; } + if (cpu_has_feature(CPU_FTR_ARCH_31)) + dbginfo->features |= PPC_DEBUG_FEATURE_DATA_BP_ARCH_31; } int ptrace_get_debugreg(struct task_struct *child, unsigned long addr, @@ -217,8 +219,9 @@ long ppc_set_hwdebug(struct task_struct *child, struct ppc_hw_breakpoint *bp_inf return -EIO; brk.address = ALIGN_DOWN(bp_info->addr, HW_BREAKPOINT_SIZE); - brk.type = HW_BRK_TYPE_TRANSLATE; + brk.type = HW_BRK_TYPE_TRANSLATE | HW_BRK_TYPE_PRIV_ALL; brk.len = DABR_MAX_LEN; + brk.hw_len = DABR_MAX_LEN; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_READ) brk.type |= HW_BRK_TYPE_READ; if (bp_info->trigger_type & PPC_BREAKPOINT_TRIGGER_WRITE) @@ -286,11 +289,13 @@ long ppc_del_hwdebug(struct task_struct *child, long data) } return ret; #else /* CONFIG_HAVE_HW_BREAKPOINT */ - if (child->thread.hw_brk[data - 1].address == 0) + if (!(child->thread.hw_brk[data - 1].flags & HW_BRK_FLAG_DISABLED) && + child->thread.hw_brk[data - 1].address == 0) return -ENOENT; child->thread.hw_brk[data - 1].address = 0; child->thread.hw_brk[data - 1].type = 0; + child->thread.hw_brk[data - 1].flags = 0; #endif /* CONFIG_HAVE_HW_BREAKPOINT */ return 0; diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index 806d554ce357..954f41676f69 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -992,6 +992,147 @@ struct pseries_errorlog *get_pseries_errorlog(struct rtas_error_log *log, return NULL; } +#ifdef CONFIG_PPC_RTAS_FILTER + +/* + * The sys_rtas syscall, as originally designed, allows root to pass + * arbitrary physical addresses to RTAS calls. A number of RTAS calls + * can be abused to write to arbitrary memory and do other things that + * are potentially harmful to system integrity, and thus should only + * be used inside the kernel and not exposed to userspace. + * + * All known legitimate users of the sys_rtas syscall will only ever + * pass addresses that fall within the RMO buffer, and use a known + * subset of RTAS calls. + * + * Accordingly, we filter RTAS requests to check that the call is + * permitted, and that provided pointers fall within the RMO buffer. + * The rtas_filters list contains an entry for each permitted call, + * with the indexes of the parameters which are expected to contain + * addresses and sizes of buffers allocated inside the RMO buffer. + */ +struct rtas_filter { + const char *name; + int token; + /* Indexes into the args buffer, -1 if not used */ + int buf_idx1; + int size_idx1; + int buf_idx2; + int size_idx2; + + int fixed_size; +}; + +static struct rtas_filter rtas_filters[] __ro_after_init = { + { "ibm,activate-firmware", -1, -1, -1, -1, -1 }, + { "ibm,configure-connector", -1, 0, -1, 1, -1, 4096 }, /* Special cased */ + { "display-character", -1, -1, -1, -1, -1 }, + { "ibm,display-message", -1, 0, -1, -1, -1 }, + { "ibm,errinjct", -1, 2, -1, -1, -1, 1024 }, + { "ibm,close-errinjct", -1, -1, -1, -1, -1 }, + { "ibm,open-errinct", -1, -1, -1, -1, -1 }, + { "ibm,get-config-addr-info2", -1, -1, -1, -1, -1 }, + { "ibm,get-dynamic-sensor-state", -1, 1, -1, -1, -1 }, + { "ibm,get-indices", -1, 2, 3, -1, -1 }, + { "get-power-level", -1, -1, -1, -1, -1 }, + { "get-sensor-state", -1, -1, -1, -1, -1 }, + { "ibm,get-system-parameter", -1, 1, 2, -1, -1 }, + { "get-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,get-vpd", -1, 0, -1, 1, 2 }, + { "ibm,lpar-perftools", -1, 2, 3, -1, -1 }, + { "ibm,platform-dump", -1, 4, 5, -1, -1 }, + { "ibm,read-slot-reset-state", -1, -1, -1, -1, -1 }, + { "ibm,scan-log-dump", -1, 0, 1, -1, -1 }, + { "ibm,set-dynamic-indicator", -1, 2, -1, -1, -1 }, + { "ibm,set-eeh-option", -1, -1, -1, -1, -1 }, + { "set-indicator", -1, -1, -1, -1, -1 }, + { "set-power-level", -1, -1, -1, -1, -1 }, + { "set-time-for-power-on", -1, -1, -1, -1, -1 }, + { "ibm,set-system-parameter", -1, 1, -1, -1, -1 }, + { "set-time-of-day", -1, -1, -1, -1, -1 }, + { "ibm,suspend-me", -1, -1, -1, -1, -1 }, + { "ibm,update-nodes", -1, 0, -1, -1, -1, 4096 }, + { "ibm,update-properties", -1, 0, -1, -1, -1, 4096 }, + { "ibm,physical-attestation", -1, 0, 1, -1, -1 }, +}; + +static bool in_rmo_buf(u32 base, u32 end) +{ + return base >= rtas_rmo_buf && + base < (rtas_rmo_buf + RTAS_RMOBUF_MAX) && + base <= end && + end >= rtas_rmo_buf && + end < (rtas_rmo_buf + RTAS_RMOBUF_MAX); +} + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + struct rtas_filter *f = &rtas_filters[i]; + u32 base, size, end; + + if (token != f->token) + continue; + + if (f->buf_idx1 != -1) { + base = be32_to_cpu(args->args[f->buf_idx1]); + if (f->size_idx1 != -1) + size = be32_to_cpu(args->args[f->size_idx1]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + + end = base + size - 1; + if (!in_rmo_buf(base, end)) + goto err; + } + + if (f->buf_idx2 != -1) { + base = be32_to_cpu(args->args[f->buf_idx2]); + if (f->size_idx2 != -1) + size = be32_to_cpu(args->args[f->size_idx2]); + else if (f->fixed_size) + size = f->fixed_size; + else + size = 1; + end = base + size - 1; + + /* + * Special case for ibm,configure-connector where the + * address can be 0 + */ + if (!strcmp(f->name, "ibm,configure-connector") && + base == 0) + return false; + + if (!in_rmo_buf(base, end)) + goto err; + } + + return false; + } + +err: + pr_err_ratelimited("sys_rtas: RTAS call blocked - exploit attempt?\n"); + pr_err_ratelimited("sys_rtas: token=0x%x, nargs=%d (called by %s)\n", + token, nargs, current->comm); + return true; +} + +#else + +static bool block_rtas_call(int token, int nargs, + struct rtas_args *args) +{ + return false; +} + +#endif /* CONFIG_PPC_RTAS_FILTER */ + /* We assume to be passed big endian arguments */ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) { @@ -1029,6 +1170,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs) args.rets = &args.args[nargs]; memset(args.rets, 0, nret * sizeof(rtas_arg_t)); + if (block_rtas_call(token, nargs, &args)) + return -EINVAL; + /* Need to handle ibm,suspend_me call specially */ if (token == ibm_suspend_me_token) { @@ -1090,6 +1234,9 @@ void __init rtas_initialize(void) unsigned long rtas_region = RTAS_INSTANTIATE_MAX; u32 base, size, entry; int no_base, no_size, no_entry; +#ifdef CONFIG_PPC_RTAS_FILTER + int i; +#endif /* Get RTAS dev node and fill up our "rtas" structure with infos * about it. @@ -1129,6 +1276,12 @@ void __init rtas_initialize(void) #ifdef CONFIG_RTAS_ERROR_LOGGING rtas_last_error_token = rtas_token("rtas-last-error"); #endif + +#ifdef CONFIG_PPC_RTAS_FILTER + for (i = 0; i < ARRAY_SIZE(rtas_filters); i++) { + rtas_filters[i].token = rtas_token(rtas_filters[i].name); + } +#endif } int __init early_init_dt_scan_rtas(unsigned long node, diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index c9876aab3142..e4e1a94ccf6a 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -430,30 +430,44 @@ device_initcall(stf_barrier_debugfs_init); static void update_branch_cache_flush(void) { + u32 *site; + #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + site = &patch__call_kvm_flush_link_stack; // This controls the branch from guest_exit_cont to kvm_flush_link_stack if (link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { - patch_instruction_site(&patch__call_kvm_flush_link_stack, - ppc_inst(PPC_INST_NOP)); + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); } else { // Could use HW flush, but that could also flush count cache - patch_branch_site(&patch__call_kvm_flush_link_stack, - (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); + patch_branch_site(site, (u64)&kvm_flush_link_stack, BRANCH_SET_LINK); } #endif + // Patch out the bcctr first, then nop the rest + site = &patch__call_flush_branch_caches3; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + site = &patch__call_flush_branch_caches2; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + site = &patch__call_flush_branch_caches1; + patch_instruction_site(site, ppc_inst(PPC_INST_NOP)); + // This controls the branch from _switch to flush_branch_caches if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE && link_stack_flush_type == BRANCH_CACHE_FLUSH_NONE) { - patch_instruction_site(&patch__call_flush_branch_caches, - ppc_inst(PPC_INST_NOP)); + // Nothing to be done + } else if (count_cache_flush_type == BRANCH_CACHE_FLUSH_HW && link_stack_flush_type == BRANCH_CACHE_FLUSH_HW) { - patch_instruction_site(&patch__call_flush_branch_caches, - ppc_inst(PPC_INST_BCCTR_FLUSH)); + // Patch in the bcctr last + site = &patch__call_flush_branch_caches1; + patch_instruction_site(site, ppc_inst(0x39207fff)); // li r9,0x7fff + site = &patch__call_flush_branch_caches2; + patch_instruction_site(site, ppc_inst(0x7d2903a6)); // mtctr r9 + site = &patch__call_flush_branch_caches3; + patch_instruction_site(site, ppc_inst(PPC_INST_BCCTR_FLUSH)); + } else { - patch_branch_site(&patch__call_flush_branch_caches, - (u64)&flush_branch_caches, BRANCH_SET_LINK); + patch_branch_site(site, (u64)&flush_branch_caches, BRANCH_SET_LINK); // If we just need to flush the link stack, early return if (count_cache_flush_type == BRANCH_CACHE_FLUSH_NONE) { diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 1823706ae076..057d6b8e9bb0 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -223,6 +223,6 @@ __init void initialize_cache_info(void) dcache_bsize = cur_cpu_spec->dcache_bsize; icache_bsize = cur_cpu_spec->icache_bsize; ucache_bsize = 0; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601) || IS_ENABLED(CONFIG_E200)) + if (IS_ENABLED(CONFIG_E200)) ucache_bsize = icache_bsize = dcache_bsize; } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6be430107c6f..bb9cab3641d7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -66,6 +66,7 @@ #include <asm/feature-fixups.h> #include <asm/kup.h> #include <asm/early_ioremap.h> +#include <asm/pgalloc.h> #include "setup.h" @@ -756,17 +757,46 @@ void __init emergency_stack_init(void) } #ifdef CONFIG_SMP -#define PCPU_DYN_SIZE () - -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) +/** + * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu + * @cpu: cpu to allocate for + * @size: size allocation in bytes + * @align: alignment + * + * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper + * does the right thing for NUMA regardless of the current + * configuration. + * + * RETURNS: + * Pointer to the allocated area on success, NULL on failure. + */ +static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, + size_t align) { - return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, - early_cpu_to_node(cpu)); + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NEED_MULTIPLE_NODES + int node = early_cpu_to_node(cpu); + void *ptr; + if (!node_online(node) || !NODE_DATA(node)) { + ptr = memblock_alloc_from(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", + cpu, size, __pa(ptr)); + } else { + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, node); + pr_debug("per cpu data for cpu%d %lu bytes on node%d at " + "%016lx\n", cpu, size, node, __pa(ptr)); + } + return ptr; +#else + return memblock_alloc_from(size, align, goal); +#endif } -static void __init pcpu_fc_free(void *ptr, size_t size) +static void __init pcpu_free_bootmem(void *ptr, size_t size) { memblock_free(__pa(ptr), size); } @@ -782,13 +812,58 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); +static void __init pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", + __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); +} + + void __init setup_per_cpu_areas(void) { const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; size_t atom_size; unsigned long delta; unsigned int cpu; - int rc; + int rc = -EINVAL; /* * Linear mapping is one of 4K, 1M and 16M. For 4K, no need @@ -800,8 +875,18 @@ void __init setup_per_cpu_areas(void) else atom_size = 1 << 20; - rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_fc_alloc, pcpu_fc_free); + if (pcpu_chosen_fc != PCPU_FC_PAGE) { + rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, + pcpu_alloc_bootmem, pcpu_free_bootmem); + if (rc) + pr_warn("PERCPU: %s allocator failed (%d), " + "falling back to page size\n", + pcpu_fc_names[pcpu_chosen_fc], rc); + } + + if (rc < 0) + rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem, + pcpu_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 8261999c7d52..0dc1b8591cc8 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -75,17 +75,28 @@ static DEFINE_PER_CPU(int, cpu_state) = { 0 }; struct task_struct *secondary_current; bool has_big_cores; +bool coregroup_enabled; DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map); DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map); DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map); DEFINE_PER_CPU(cpumask_var_t, cpu_core_map); +DEFINE_PER_CPU(cpumask_var_t, cpu_coregroup_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map); EXPORT_PER_CPU_SYMBOL(cpu_core_map); EXPORT_SYMBOL_GPL(has_big_cores); +enum { +#ifdef CONFIG_SCHED_SMT + smt_idx, +#endif + cache_idx, + mc_idx, + die_idx, +}; + #define MAX_THREAD_LIST_SIZE 8 #define THREAD_GROUP_SHARE_L1 1 struct thread_groups { @@ -660,6 +671,28 @@ static void set_cpus_unrelated(int i, int j, #endif /* + * Extends set_cpus_related. Instead of setting one CPU at a time in + * dstmask, set srcmask at oneshot. dstmask should be super set of srcmask. + */ +static void or_cpumasks_related(int i, int j, struct cpumask *(*srcmask)(int), + struct cpumask *(*dstmask)(int)) +{ + struct cpumask *mask; + int k; + + mask = srcmask(j); + for_each_cpu(k, srcmask(i)) + cpumask_or(dstmask(k), dstmask(k), mask); + + if (i == j) + return; + + mask = srcmask(i); + for_each_cpu(k, srcmask(j)) + cpumask_or(dstmask(k), dstmask(k), mask); +} + +/* * parse_thread_groups: Parses the "ibm,thread-groups" device tree * property for the CPU device node @dn and stores * the parsed output in the thread_groups @@ -789,10 +822,6 @@ static int init_cpu_l1_cache_map(int cpu) if (err) goto out; - zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu), - GFP_KERNEL, - cpu_to_node(cpu)); - cpu_group_start = get_cpu_thread_group_start(cpu, &tg); if (unlikely(cpu_group_start == -1)) { @@ -801,6 +830,9 @@ static int init_cpu_l1_cache_map(int cpu) goto out; } + zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + for (i = first_thread; i < first_thread + threads_per_core; i++) { int i_group_start = get_cpu_thread_group_start(i, &tg); @@ -819,6 +851,74 @@ out: return err; } +static bool shared_caches; + +#ifdef CONFIG_SCHED_SMT +/* cpumask of CPUs with asymmetric SMT dependency */ +static int powerpc_smt_flags(void) +{ + int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + flags |= SD_ASYM_PACKING; + } + return flags; +} +#endif + +/* + * P9 has a slightly odd architecture where pairs of cores share an L2 cache. + * This topology makes it *much* cheaper to migrate tasks between adjacent cores + * since the migrated task remains cache hot. We want to take advantage of this + * at the scheduler level so an extra topology level is required. + */ +static int powerpc_shared_cache_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} + +/* + * We can't just pass cpu_l2_cache_mask() directly because + * returns a non-const pointer and the compiler barfs on that. + */ +static const struct cpumask *shared_cache_mask(int cpu) +{ + return per_cpu(cpu_l2_cache_map, cpu); +} + +#ifdef CONFIG_SCHED_SMT +static const struct cpumask *smallcore_smt_mask(int cpu) +{ + return cpu_smallcore_mask(cpu); +} +#endif + +static struct cpumask *cpu_coregroup_mask(int cpu) +{ + return per_cpu(cpu_coregroup_map, cpu); +} + +static bool has_coregroup_support(void) +{ + return coregroup_enabled; +} + +static const struct cpumask *cpu_mc_mask(int cpu) +{ + return cpu_coregroup_mask(cpu); +} + +static struct sched_domain_topology_level powerpc_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, + { cpu_mc_mask, SD_INIT_NAME(MC) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int init_big_cores(void) { int cpu; @@ -861,6 +961,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus) GFP_KERNEL, cpu_to_node(cpu)); zalloc_cpumask_var_node(&per_cpu(cpu_core_map, cpu), GFP_KERNEL, cpu_to_node(cpu)); + if (has_coregroup_support()) + zalloc_cpumask_var_node(&per_cpu(cpu_coregroup_map, cpu), + GFP_KERNEL, cpu_to_node(cpu)); + +#ifdef CONFIG_NEED_MULTIPLE_NODES /* * numa_node_id() works after this. */ @@ -869,12 +974,21 @@ void __init smp_prepare_cpus(unsigned int max_cpus) set_cpu_numa_mem(cpu, local_memory_node(numa_cpu_lookup_table[cpu])); } +#endif + /* + * cpu_core_map is now more updated and exists only since + * its been exported for long. It only will have a snapshot + * of cpu_cpu_mask. + */ + cpumask_copy(per_cpu(cpu_core_map, cpu), cpu_cpu_mask(cpu)); } /* Init the cpumasks so the boot CPU is related to itself */ cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid)); cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid)); - cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid)); + + if (has_coregroup_support()) + cpumask_set_cpu(boot_cpuid, cpu_coregroup_mask(boot_cpuid)); init_big_cores(); if (has_big_cores) { @@ -1126,30 +1240,61 @@ static struct device_node *cpu_to_l2cache(int cpu) return cache; } -static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) +static bool update_mask_by_l2(int cpu) { + struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; struct device_node *l2_cache, *np; + cpumask_var_t mask; int i; l2_cache = cpu_to_l2cache(cpu); - if (!l2_cache) + if (!l2_cache) { + struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; + + /* + * If no l2cache for this CPU, assume all siblings to share + * cache with this CPU. + */ + if (has_big_cores) + sibling_mask = cpu_smallcore_mask; + + for_each_cpu(i, sibling_mask(cpu)) + set_cpus_related(cpu, i, cpu_l2_cache_mask); + return false; + } + + alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu)); + cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu)); - for_each_cpu(i, cpu_online_mask) { + if (has_big_cores) + submask_fn = cpu_smallcore_mask; + + /* Update l2-cache mask with all the CPUs that are part of submask */ + or_cpumasks_related(cpu, cpu, submask_fn, cpu_l2_cache_mask); + + /* Skip all CPUs already part of current CPU l2-cache mask */ + cpumask_andnot(mask, mask, cpu_l2_cache_mask(cpu)); + + for_each_cpu(i, mask) { /* * when updating the marks the current CPU has not been marked * online, but we need to update the cache masks */ np = cpu_to_l2cache(i); - if (!np) - continue; - if (np == l2_cache) - set_cpus_related(cpu, i, mask_fn); + /* Skip all CPUs already part of current CPU l2-cache */ + if (np == l2_cache) { + or_cpumasks_related(cpu, i, submask_fn, cpu_l2_cache_mask); + cpumask_andnot(mask, mask, submask_fn(i)); + } else { + cpumask_andnot(mask, mask, cpu_l2_cache_mask(i)); + } of_node_put(np); } of_node_put(l2_cache); + free_cpumask_var(mask); return true; } @@ -1157,59 +1302,75 @@ static bool update_mask_by_l2(int cpu, struct cpumask *(*mask_fn)(int)) #ifdef CONFIG_HOTPLUG_CPU static void remove_cpu_from_masks(int cpu) { + struct cpumask *(*mask_fn)(int) = cpu_sibling_mask; int i; - /* NB: cpu_core_mask is a superset of the others */ - for_each_cpu(i, cpu_core_mask(cpu)) { - set_cpus_unrelated(cpu, i, cpu_core_mask); + if (shared_caches) + mask_fn = cpu_l2_cache_mask; + + for_each_cpu(i, mask_fn(cpu)) { set_cpus_unrelated(cpu, i, cpu_l2_cache_mask); set_cpus_unrelated(cpu, i, cpu_sibling_mask); if (has_big_cores) set_cpus_unrelated(cpu, i, cpu_smallcore_mask); } + + if (has_coregroup_support()) { + for_each_cpu(i, cpu_coregroup_mask(cpu)) + set_cpus_unrelated(cpu, i, cpu_coregroup_mask); + } } #endif static inline void add_cpu_to_smallcore_masks(int cpu) { - struct cpumask *this_l1_cache_map = per_cpu(cpu_l1_cache_map, cpu); - int i, first_thread = cpu_first_thread_sibling(cpu); + int i; if (!has_big_cores) return; cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu)); - for (i = first_thread; i < first_thread + threads_per_core; i++) { - if (cpu_online(i) && cpumask_test_cpu(i, this_l1_cache_map)) + for_each_cpu(i, per_cpu(cpu_l1_cache_map, cpu)) { + if (cpu_online(i)) set_cpus_related(i, cpu, cpu_smallcore_mask); } } -int get_physical_package_id(int cpu) +static void update_coregroup_mask(int cpu) { - int pkg_id = cpu_to_chip_id(cpu); + struct cpumask *(*submask_fn)(int) = cpu_sibling_mask; + cpumask_var_t mask; + int coregroup_id = cpu_to_coregroup_id(cpu); + int i; - /* - * If the platform is PowerNV or Guest on KVM, ibm,chip-id is - * defined. Hence we would return the chip-id as the result of - * get_physical_package_id. - */ - if (pkg_id == -1 && firmware_has_feature(FW_FEATURE_LPAR) && - IS_ENABLED(CONFIG_PPC_SPLPAR)) { - struct device_node *np = of_get_cpu_node(cpu, NULL); - pkg_id = of_node_to_nid(np); - of_node_put(np); - } + alloc_cpumask_var_node(&mask, GFP_KERNEL, cpu_to_node(cpu)); + cpumask_and(mask, cpu_online_mask, cpu_cpu_mask(cpu)); + + if (shared_caches) + submask_fn = cpu_l2_cache_mask; - return pkg_id; + /* Update coregroup mask with all the CPUs that are part of submask */ + or_cpumasks_related(cpu, cpu, submask_fn, cpu_coregroup_mask); + + /* Skip all CPUs already part of coregroup mask */ + cpumask_andnot(mask, mask, cpu_coregroup_mask(cpu)); + + for_each_cpu(i, mask) { + /* Skip all CPUs not part of this coregroup */ + if (coregroup_id == cpu_to_coregroup_id(i)) { + or_cpumasks_related(cpu, i, submask_fn, cpu_coregroup_mask); + cpumask_andnot(mask, mask, submask_fn(i)); + } else { + cpumask_andnot(mask, mask, cpu_coregroup_mask(i)); + } + } + free_cpumask_var(mask); } -EXPORT_SYMBOL_GPL(get_physical_package_id); static void add_cpu_to_masks(int cpu) { int first_thread = cpu_first_thread_sibling(cpu); - int pkg_id = get_physical_package_id(cpu); int i; /* @@ -1223,36 +1384,16 @@ static void add_cpu_to_masks(int cpu) set_cpus_related(i, cpu, cpu_sibling_mask); add_cpu_to_smallcore_masks(cpu); - /* - * Copy the thread sibling mask into the cache sibling mask - * and mark any CPUs that share an L2 with this CPU. - */ - for_each_cpu(i, cpu_sibling_mask(cpu)) - set_cpus_related(cpu, i, cpu_l2_cache_mask); - update_mask_by_l2(cpu, cpu_l2_cache_mask); + update_mask_by_l2(cpu); - /* - * Copy the cache sibling mask into core sibling mask and mark - * any CPUs on the same chip as this CPU. - */ - for_each_cpu(i, cpu_l2_cache_mask(cpu)) - set_cpus_related(cpu, i, cpu_core_mask); - - if (pkg_id == -1) - return; - - for_each_cpu(i, cpu_online_mask) - if (get_physical_package_id(i) == pkg_id) - set_cpus_related(cpu, i, cpu_core_mask); + if (has_coregroup_support()) + update_coregroup_mask(cpu); } -static bool shared_caches; - /* Activate a secondary processor. */ void start_secondary(void *unused) { unsigned int cpu = smp_processor_id(); - struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; mmgrab(&init_mm); current->active_mm = &init_mm; @@ -1278,14 +1419,20 @@ void start_secondary(void *unused) /* Update topology CPU masks */ add_cpu_to_masks(cpu); - if (has_big_cores) - sibling_mask = cpu_smallcore_mask; /* * Check for any shared caches. Note that this must be done on a * per-core basis because one core in the pair might be disabled. */ - if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu))) - shared_caches = true; + if (!shared_caches) { + struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask; + struct cpumask *mask = cpu_l2_cache_mask(cpu); + + if (has_big_cores) + sibling_mask = cpu_smallcore_mask; + + if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu))) + shared_caches = true; + } set_numa_node(numa_cpu_lookup_table[cpu]); set_numa_mem(local_memory_node(numa_cpu_lookup_table[cpu])); @@ -1311,63 +1458,44 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } -#ifdef CONFIG_SCHED_SMT -/* cpumask of CPUs with asymetric SMT dependancy */ -static int powerpc_smt_flags(void) +static void fixup_topology(void) { - int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; + int i; - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - flags |= SD_ASYM_PACKING; +#ifdef CONFIG_SCHED_SMT + if (has_big_cores) { + pr_info("Big cores detected but using small core scheduling\n"); + powerpc_topology[smt_idx].mask = smallcore_smt_mask; } - return flags; -} #endif -static struct sched_domain_topology_level powerpc_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, -#endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; + if (!has_coregroup_support()) + powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask; -/* - * P9 has a slightly odd architecture where pairs of cores share an L2 cache. - * This topology makes it *much* cheaper to migrate tasks between adjacent cores - * since the migrated task remains cache hot. We want to take advantage of this - * at the scheduler level so an extra topology level is required. - */ -static int powerpc_shared_cache_flags(void) -{ - return SD_SHARE_PKG_RESOURCES; -} + /* + * Try to consolidate topology levels here instead of + * allowing scheduler to degenerate. + * - Dont consolidate if masks are different. + * - Dont consolidate if sd_flags exists and are different. + */ + for (i = 1; i <= die_idx; i++) { + if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask) + continue; -/* - * We can't just pass cpu_l2_cache_mask() directly because - * returns a non-const pointer and the compiler barfs on that. - */ -static const struct cpumask *shared_cache_mask(int cpu) -{ - return cpu_l2_cache_mask(cpu); -} + if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags && + powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags) + continue; -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *smallcore_smt_mask(int cpu) -{ - return cpu_smallcore_mask(cpu); -} -#endif + if (!powerpc_topology[i - 1].sd_flags) + powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags; -static struct sched_domain_topology_level power9_topology[] = { -#ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, + powerpc_topology[i].mask = powerpc_topology[i + 1].mask; + powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags; +#ifdef CONFIG_SCHED_DEBUG + powerpc_topology[i].name = powerpc_topology[i + 1].name; #endif - { shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) }, - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; + } +} void __init smp_cpus_done(unsigned int max_cpus) { @@ -1382,24 +1510,8 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); -#ifdef CONFIG_SCHED_SMT - if (has_big_cores) { - pr_info("Big cores detected but using small core scheduling\n"); - power9_topology[0].mask = smallcore_smt_mask; - powerpc_topology[0].mask = smallcore_smt_mask; - } -#endif - /* - * If any CPU detects that it's sharing a cache with another CPU then - * use the deeper topology that is aware of this sharing. - */ - if (shared_caches) { - pr_info("Using shared cache scheduler topology\n"); - set_sched_topology(power9_topology); - } else { - pr_info("Using standard scheduler topology\n"); - set_sched_topology(powerpc_topology); - } + fixup_topology(); + set_sched_topology(powerpc_topology); } #ifdef CONFIG_HOTPLUG_CPU @@ -1429,16 +1541,18 @@ void __cpu_die(unsigned int cpu) smp_ops->cpu_die(cpu); } -void cpu_die(void) +void arch_cpu_idle_dead(void) { + sched_preempt_enable_no_resched(); + /* * Disable on the down path. This will be re-enabled by * start_secondary() via start_secondary_resume() below */ this_cpu_disable_ftrace(); - if (ppc_md.cpu_die) - ppc_md.cpu_die(); + if (smp_ops->cpu_offline_self) + smp_ops->cpu_offline_self(); /* If we return, we re-enter start_secondary */ start_secondary_resume(); diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 46b4ebc33db7..2e08640bb3b4 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -32,29 +32,27 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices); -/* - * SMT snooze delay stuff, 64-bit only for now - */ - #ifdef CONFIG_PPC64 -/* Time in microseconds we delay before sleeping in the idle loop */ -static DEFINE_PER_CPU(long, smt_snooze_delay) = { 100 }; +/* + * Snooze delay has not been hooked up since 3fa8cad82b94 ("powerpc/pseries/cpuidle: + * smt-snooze-delay cleanup.") and has been broken even longer. As was foretold in + * 2014: + * + * "ppc64_util currently utilises it. Once we fix ppc64_util, propose to clean + * up the kernel code." + * + * powerpc-utils stopped using it as of 1.3.8. At some point in the future this + * code should be removed. + */ static ssize_t store_smt_snooze_delay(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - ssize_t ret; - long snooze; - - ret = sscanf(buf, "%ld", &snooze); - if (ret != 1) - return -EINVAL; - - per_cpu(smt_snooze_delay, cpu->dev.id) = snooze; + pr_warn_once("%s (%d) stored to unsupported smt_snooze_delay, which has no effect.\n", + current->comm, current->pid); return count; } @@ -62,9 +60,9 @@ static ssize_t show_smt_snooze_delay(struct device *dev, struct device_attribute *attr, char *buf) { - struct cpu *cpu = container_of(dev, struct cpu, dev); - - return sprintf(buf, "%ld\n", per_cpu(smt_snooze_delay, cpu->dev.id)); + pr_warn_once("%s (%d) read from unsupported smt_snooze_delay\n", + current->comm, current->pid); + return sprintf(buf, "100\n"); } static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, @@ -72,16 +70,10 @@ static DEVICE_ATTR(smt_snooze_delay, 0644, show_smt_snooze_delay, static int __init setup_smt_snooze_delay(char *str) { - unsigned int cpu; - long snooze; - if (!cpu_has_feature(CPU_FTR_SMT)) return 1; - snooze = simple_strtol(str, NULL, 10); - for_each_possible_cpu(cpu) - per_cpu(smt_snooze_delay, cpu) = snooze; - + pr_warn("smt-snooze-delay command line option has no effect\n"); return 1; } __setup("smt-snooze-delay=", setup_smt_snooze_delay); @@ -225,14 +217,13 @@ static DEVICE_ATTR(dscr_default, 0600, static void sysfs_create_dscr_default(void) { if (cpu_has_feature(CPU_FTR_DSCR)) { - int err = 0; int cpu; dscr_default = spr_default_dscr; for_each_possible_cpu(cpu) paca_ptrs[cpu]->dscr_default = dscr_default; - err = device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); + device_create_file(cpu_subsys.dev_root, &dev_attr_dscr_default); } } #endif /* CONFIG_PPC64 */ @@ -1168,6 +1159,7 @@ static int __init topology_init(void) for_each_possible_cpu(cpu) { struct cpu *c = &per_cpu(cpu_devices, cpu); +#ifdef CONFIG_HOTPLUG_CPU /* * For now, we just see if the system supports making * the RTAS calls for CPU hotplug. But, there may be a @@ -1175,8 +1167,9 @@ static int __init topology_init(void) * CPU. For instance, the boot cpu might never be valid * for hotplugging. */ - if (ppc_md.cpu_die) + if (smp_ops->cpu_offline_self) c->hotpluggable = 1; +#endif if (cpu_online(cpu) || c->hotpluggable) { register_cpu(c, cpu); diff --git a/arch/powerpc/kernel/tau_6xx.c b/arch/powerpc/kernel/tau_6xx.c index e2ab8a111b69..0b4694b8d248 100644 --- a/arch/powerpc/kernel/tau_6xx.c +++ b/arch/powerpc/kernel/tau_6xx.c @@ -13,13 +13,14 @@ */ #include <linux/errno.h> -#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/param.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <linux/init.h> +#include <linux/delay.h> +#include <linux/workqueue.h> #include <asm/io.h> #include <asm/reg.h> @@ -39,9 +40,7 @@ static struct tau_temp unsigned char grew; } tau[NR_CPUS]; -struct timer_list tau_timer; - -#undef DEBUG +static bool tau_int_enable; /* TODO: put these in a /proc interface, with some sanity checks, and maybe * dynamic adjustment to minimize # of interrupts */ @@ -50,72 +49,49 @@ struct timer_list tau_timer; #define step_size 2 /* step size when temp goes out of range */ #define window_expand 1 /* expand the window by this much */ /* configurable values for shrinking the window */ -#define shrink_timer 2*HZ /* period between shrinking the window */ +#define shrink_timer 2000 /* period between shrinking the window */ #define min_window 2 /* minimum window size, degrees C */ static void set_thresholds(unsigned long cpu) { -#ifdef CONFIG_TAU_INT - /* - * setup THRM1, - * threshold, valid bit, enable interrupts, interrupt when below threshold - */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TIE | THRM1_TID); + u32 maybe_tie = tau_int_enable ? THRM1_TIE : 0; - /* setup THRM2, - * threshold, valid bit, enable interrupts, interrupt when above threshold - */ - mtspr (SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | THRM1_TIE); -#else - /* same thing but don't enable interrupts */ - mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | THRM1_TID); - mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V); -#endif + /* setup THRM1, threshold, valid bit, interrupt when below threshold */ + mtspr(SPRN_THRM1, THRM1_THRES(tau[cpu].low) | THRM1_V | maybe_tie | THRM1_TID); + + /* setup THRM2, threshold, valid bit, interrupt when above threshold */ + mtspr(SPRN_THRM2, THRM1_THRES(tau[cpu].high) | THRM1_V | maybe_tie); } static void TAUupdate(int cpu) { - unsigned thrm; - -#ifdef DEBUG - printk("TAUupdate "); -#endif + u32 thrm; + u32 bits = THRM1_TIV | THRM1_TIN | THRM1_V; /* if both thresholds are crossed, the step_sizes cancel out * and the window winds up getting expanded twice. */ - if((thrm = mfspr(SPRN_THRM1)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed low threshold */ - if (tau[cpu].low >= step_size){ - tau[cpu].low -= step_size; - tau[cpu].high -= (step_size - window_expand); - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("low threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM1); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM1, 0); + + if (tau[cpu].low >= step_size) { + tau[cpu].low -= step_size; + tau[cpu].high -= (step_size - window_expand); } + tau[cpu].grew = 1; + pr_debug("%s: low threshold crossed\n", __func__); } - if((thrm = mfspr(SPRN_THRM2)) & THRM1_TIV){ /* is valid? */ - if(thrm & THRM1_TIN){ /* crossed high threshold */ - if (tau[cpu].high <= 127-step_size){ - tau[cpu].low += (step_size - window_expand); - tau[cpu].high += step_size; - } - tau[cpu].grew = 1; -#ifdef DEBUG - printk("high threshold crossed "); -#endif + thrm = mfspr(SPRN_THRM2); + if ((thrm & bits) == bits) { + mtspr(SPRN_THRM2, 0); + + if (tau[cpu].high <= 127 - step_size) { + tau[cpu].low += (step_size - window_expand); + tau[cpu].high += step_size; } + tau[cpu].grew = 1; + pr_debug("%s: high threshold crossed\n", __func__); } - -#ifdef DEBUG - printk("grew = %d\n", tau[cpu].grew); -#endif - -#ifndef CONFIG_TAU_INT /* tau_timeout will do this if not using interrupts */ - set_thresholds(cpu); -#endif - } #ifdef CONFIG_TAU_INT @@ -140,17 +116,16 @@ void TAUException(struct pt_regs * regs) static void tau_timeout(void * info) { int cpu; - unsigned long flags; int size; int shrink; - /* disabling interrupts *should* be okay */ - local_irq_save(flags); cpu = smp_processor_id(); -#ifndef CONFIG_TAU_INT - TAUupdate(cpu); -#endif + if (!tau_int_enable) + TAUupdate(cpu); + + /* Stop thermal sensor comparisons and interrupts */ + mtspr(SPRN_THRM3, 0); size = tau[cpu].high - tau[cpu].low; if (size > min_window && ! tau[cpu].grew) { @@ -173,32 +148,26 @@ static void tau_timeout(void * info) set_thresholds(cpu); - /* - * Do the enable every time, since otherwise a bunch of (relatively) - * complex sleep code needs to be added. One mtspr every time - * tau_timeout is called is probably not a big deal. - * - * Enable thermal sensor and set up sample interval timer - * need 20 us to do the compare.. until a nice 'cpu_speed' function - * call is implemented, just assume a 500 mhz clock. It doesn't really - * matter if we take too long for a compare since it's all interrupt - * driven anyway. - * - * use a extra long time.. (60 us @ 500 mhz) + /* Restart thermal sensor comparisons and interrupts. + * The "PowerPC 740 and PowerPC 750 Microprocessor Datasheet" + * recommends that "the maximum value be set in THRM3 under all + * conditions." */ - mtspr(SPRN_THRM3, THRM3_SITV(500*60) | THRM3_E); - - local_irq_restore(flags); + mtspr(SPRN_THRM3, THRM3_SITV(0x1fff) | THRM3_E); } -static void tau_timeout_smp(struct timer_list *unused) -{ +static struct workqueue_struct *tau_workq; - /* schedule ourselves to be run again */ - mod_timer(&tau_timer, jiffies + shrink_timer) ; +static void tau_work_func(struct work_struct *work) +{ + msleep(shrink_timer); on_each_cpu(tau_timeout, NULL, 0); + /* schedule ourselves to be run again */ + queue_work(tau_workq, work); } +DECLARE_WORK(tau_work, tau_work_func); + /* * setup the TAU * @@ -231,21 +200,19 @@ static int __init TAU_init(void) return 1; } + tau_int_enable = IS_ENABLED(CONFIG_TAU_INT) && + !strcmp(cur_cpu_spec->platform, "ppc750"); - /* first, set up the window shrinking timer */ - timer_setup(&tau_timer, tau_timeout_smp, 0); - tau_timer.expires = jiffies + shrink_timer; - add_timer(&tau_timer); + tau_workq = alloc_workqueue("tau", WQ_UNBOUND, 1, 0); + if (!tau_workq) + return -ENOMEM; on_each_cpu(TAU_init_smp, NULL, 0); - printk("Thermal assist unit "); -#ifdef CONFIG_TAU_INT - printk("using interrupts, "); -#else - printk("using timers, "); -#endif - printk("shrink_timer: %d jiffies\n", shrink_timer); + queue_work(tau_workq, &tau_work); + + pr_info("Thermal assist unit using %s, shrink_timer: %d ms\n", + tau_int_enable ? "interrupts" : "workqueue", shrink_timer); tau_initialized = 1; return 0; diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index f85539ebb513..74efe46f5532 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -75,15 +75,6 @@ #include <linux/clockchips.h> #include <linux/timekeeper_internal.h> -static u64 rtc_read(struct clocksource *); -static struct clocksource clocksource_rtc = { - .name = "rtc", - .rating = 400, - .flags = CLOCK_SOURCE_IS_CONTINUOUS, - .mask = CLOCKSOURCE_MASK(64), - .read = rtc_read, -}; - static u64 timebase_read(struct clocksource *); static struct clocksource clocksource_timebase = { .name = "timebase", @@ -447,19 +438,9 @@ void vtime_flush(struct task_struct *tsk) void __delay(unsigned long loops) { unsigned long start; - int diff; spin_begin(); - if (__USE_RTC()) { - start = get_rtcl(); - do { - /* the RTCL register wraps at 1000000000 */ - diff = get_rtcl() - start; - if (diff < 0) - diff += 1000000000; - spin_cpu_relax(); - } while (diff < loops); - } else if (tb_invalid) { + if (tb_invalid) { /* * TB is in error state and isn't ticking anymore. * HMI handler was unable to recover from TB error. @@ -467,8 +448,8 @@ void __delay(unsigned long loops) */ spin_cpu_relax(); } else { - start = get_tbl(); - while (get_tbl() - start < loops) + start = mftb(); + while (mftb() - start < loops) spin_cpu_relax(); } spin_end(); @@ -614,7 +595,7 @@ void timer_interrupt(struct pt_regs *regs) irq_work_run(); } - now = get_tb_or_rtc(); + now = get_tb(); if (now >= *next_tb) { *next_tb = ~(u64)0; if (evt->event_handler) @@ -696,8 +677,6 @@ EXPORT_SYMBOL_GPL(tb_to_ns); */ notrace unsigned long long sched_clock(void) { - if (__USE_RTC()) - return get_rtc(); return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } @@ -847,11 +826,6 @@ void read_persistent_clock64(struct timespec64 *ts) } /* clocksource code */ -static notrace u64 rtc_read(struct clocksource *cs) -{ - return (u64)get_rtc(); -} - static notrace u64 timebase_read(struct clocksource *cs) { return (u64)get_tb(); @@ -948,12 +922,7 @@ void update_vsyscall_tz(void) static void __init clocksource_init(void) { - struct clocksource *clock; - - if (__USE_RTC()) - clock = &clocksource_rtc; - else - clock = &clocksource_timebase; + struct clocksource *clock = &clocksource_timebase; if (clocksource_register_hz(clock, tb_ticks_per_sec)) { printk(KERN_ERR "clocksource: %s is already registered\n", @@ -968,7 +937,7 @@ static void __init clocksource_init(void) static int decrementer_set_next_event(unsigned long evt, struct clock_event_device *dev) { - __this_cpu_write(decrementers_next_tb, get_tb_or_rtc() + evt); + __this_cpu_write(decrementers_next_tb, get_tb() + evt); set_dec(evt); /* We may have raced with new irq work */ @@ -1071,17 +1040,12 @@ void __init time_init(void) u64 scale; unsigned shift; - if (__USE_RTC()) { - /* 601 processor: dec counts down by 128 every 128ns */ - ppc_tb_freq = 1000000000; - } else { - /* Normal PowerPC with timebase register */ - ppc_md.calibrate_decr(); - printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", - ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); - printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", - ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); - } + /* Normal PowerPC with timebase register */ + ppc_md.calibrate_decr(); + printk(KERN_DEBUG "time_init: decrementer frequency = %lu.%.6lu MHz\n", + ppc_tb_freq / 1000000, ppc_tb_freq % 1000000); + printk(KERN_DEBUG "time_init: processor frequency = %lu.%.6lu MHz\n", + ppc_proc_freq / 1000000, ppc_proc_freq % 1000000); tb_ticks_per_jiffy = ppc_tb_freq / HZ; tb_ticks_per_sec = ppc_tb_freq; @@ -1107,7 +1071,7 @@ void __init time_init(void) tb_to_ns_scale = scale; tb_to_ns_shift = shift; /* Save the current timebase to pretty up CONFIG_PRINTK_TIME */ - boot_tb = get_tb_or_rtc(); + boot_tb = get_tb(); /* If platform provided a timezone (pmac), we correct the time */ if (timezone_offset) { diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S index 6ba0fdd1e7f8..2b91f233b05d 100644 --- a/arch/powerpc/kernel/tm.S +++ b/arch/powerpc/kernel/tm.S @@ -122,6 +122,13 @@ _GLOBAL(tm_reclaim) std r3, STK_PARAM(R3)(r1) SAVE_NVGPRS(r1) + /* + * Save kernel live AMR since it will be clobbered by treclaim + * but can be used elsewhere later in kernel space. + */ + mfspr r3, SPRN_AMR + std r3, TM_FRAME_L1(r1) + /* We need to setup MSR for VSX register save instructions. */ mfmsr r14 mr r15, r14 @@ -245,7 +252,7 @@ _GLOBAL(tm_reclaim) * but is used in signal return to 'wind back' to the abort handler. */ - /* ******************** CR,LR,CCR,MSR ********** */ + /* ***************** CTR, LR, CR, XER ********** */ mfctr r3 mflr r4 mfcr r5 @@ -256,7 +263,6 @@ _GLOBAL(tm_reclaim) std r5, _CCR(r7) std r6, _XER(r7) - /* ******************** TAR, DSCR ********** */ mfspr r3, SPRN_TAR mfspr r4, SPRN_DSCR @@ -264,6 +270,10 @@ _GLOBAL(tm_reclaim) std r3, THREAD_TM_TAR(r12) std r4, THREAD_TM_DSCR(r12) + /* ******************** AMR **************** */ + mfspr r3, SPRN_AMR + std r3, THREAD_TM_AMR(r12) + /* * MSR and flags: We don't change CRs, and we don't need to alter MSR. */ @@ -308,7 +318,9 @@ _GLOBAL(tm_reclaim) std r3, THREAD_TM_TFHAR(r12) std r4, THREAD_TM_TFIAR(r12) - /* AMR is checkpointed too, but is unsupported by Linux. */ + /* Restore kernel live AMR */ + ld r8, TM_FRAME_L1(r1) + mtspr SPRN_AMR, r8 /* Restore original MSR/IRQ state & clear TM mode */ ld r14, TM_FRAME_L0(r1) /* Orig MSR */ @@ -355,6 +367,13 @@ _GLOBAL(__tm_recheckpoint) */ SAVE_NVGPRS(r1) + /* + * Save kernel live AMR since it will be clobbered for trechkpt + * but can be used elsewhere later in kernel space. + */ + mfspr r8, SPRN_AMR + std r8, TM_FRAME_L0(r1) + /* Load complete register state from ts_ckpt* registers */ addi r7, r3, PT_CKPT_REGS /* Thread's ckpt_regs */ @@ -404,7 +423,7 @@ _GLOBAL(__tm_recheckpoint) restore_gprs: - /* ******************** CR,LR,CCR,MSR ********** */ + /* ****************** CTR, LR, XER ************* */ ld r4, _CTR(r7) ld r5, _LINK(r7) ld r8, _XER(r7) @@ -417,6 +436,10 @@ restore_gprs: ld r4, THREAD_TM_TAR(r3) mtspr SPRN_TAR, r4 + /* ******************** AMR ******************** */ + ld r4, THREAD_TM_AMR(r3) + mtspr SPRN_AMR, r4 + /* Load up the PPR and DSCR in GPRs only at this stage */ ld r5, THREAD_TM_DSCR(r3) ld r6, THREAD_TM_PPR(r3) @@ -509,6 +532,10 @@ restore_gprs: li r4, MSR_RI mtmsrd r4, 1 + /* Restore kernel live AMR */ + ld r8, TM_FRAME_L0(r1) + mtspr SPRN_AMR, r8 + REST_NVGPRS(r1) addi r1, r1, TM_FRAME_SIZE diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index d1ebe152f210..c5f39f13e96e 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -529,9 +529,6 @@ out: * Check if the NIP corresponds to the address of a sync * instruction for which there is an entry in the exception * table. - * Note that the 601 only takes a machine check on TEA - * (transfer error ack) signal assertion, and does not - * set any of the top 16 bits of SRR1. * -- paulus. */ static inline int check_io_access(struct pt_regs *regs) @@ -796,7 +793,6 @@ int machine_check_generic(struct pt_regs *regs) case 0x80000: pr_cont("Machine check signal\n"); break; - case 0: /* for 601 */ case 0x40000: case 0x140000: /* 7450 MSS error and TEA */ pr_cont("Transfer error ack signal\n"); diff --git a/arch/powerpc/kernel/vdso32/datapage.S b/arch/powerpc/kernel/vdso32/datapage.S index 217bb630f8f9..1d23e2771dba 100644 --- a/arch/powerpc/kernel/vdso32/datapage.S +++ b/arch/powerpc/kernel/vdso32/datapage.S @@ -47,7 +47,6 @@ V_FUNCTION_END(__kernel_get_syscall_map) * * returns the timebase frequency in HZ */ -#ifndef CONFIG_PPC_BOOK3S_601 V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 @@ -60,4 +59,3 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) blr .cfi_endproc V_FUNCTION_END(__kernel_get_tbfreq) -#endif diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S index 5206c2eb2a1d..7eadac74c7f9 100644 --- a/arch/powerpc/kernel/vdso32/vdso32.lds.S +++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S @@ -144,13 +144,11 @@ VERSION __kernel_datapage_offset; __kernel_get_syscall_map; -#ifndef CONFIG_PPC_BOOK3S_601 __kernel_gettimeofday; __kernel_clock_gettime; __kernel_clock_getres; __kernel_time; __kernel_get_tbfreq; -#endif __kernel_sync_dicache; __kernel_sync_dicache_p5; __kernel_sigtramp32; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 4ba06a2a306c..3bd3118c7633 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3530,6 +3530,13 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit, */ asm volatile("eieio; tlbsync; ptesync"); + /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ + if (cpu_has_feature(CPU_FTR_ARCH_31)) + asm volatile(PPC_CP_ABORT); + mtspr(SPRN_LPID, vcpu->kvm->arch.host_lpid); /* restore host LPID */ isync(); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 799d6d0f4ead..cd9995ee8441 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1831,6 +1831,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_RADIX_PREFETCH_BUG) #endif /* CONFIG_PPC_RADIX_MMU */ /* + * cp_abort is required if the processor supports local copy-paste + * to clear the copy buffer that was under control of the guest. + */ +BEGIN_FTR_SECTION + PPC_CP_ABORT +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_31) + + /* * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index 8c3934ea6220..2333625b5e31 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -21,21 +21,18 @@ static int __patch_instruction(struct ppc_inst *exec_addr, struct ppc_inst instr, struct ppc_inst *patch_addr) { - int err = 0; - - if (!ppc_inst_prefixed(instr)) { - __put_user_asm(ppc_inst_val(instr), patch_addr, err, "stw"); - } else { - __put_user_asm(ppc_inst_as_u64(instr), patch_addr, err, "std"); - } - - if (err) - return err; + if (!ppc_inst_prefixed(instr)) + __put_user_asm_goto(ppc_inst_val(instr), patch_addr, failed, "stw"); + else + __put_user_asm_goto(ppc_inst_as_u64(instr), patch_addr, failed, "std"); asm ("dcbst 0, %0; sync; icbi 0,%1; sync; isync" :: "r" (patch_addr), "r" (exec_addr)); return 0; + +failed: + return -EFAULT; } int raw_patch_instruction(struct ppc_inst *addr, struct ppc_inst instr) diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index caee8cc77e19..e9dcaba9a4f8 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -219,10 +219,13 @@ static nokprobe_inline unsigned long mlsd_8lsd_ea(unsigned int instr, ea += regs->gpr[ra]; else if (!prefix_r && !ra) ; /* Leave ea as is */ - else if (prefix_r && !ra) + else if (prefix_r) ea += regs->nip; - else if (prefix_r && ra) - ; /* Invalid form. Should already be checked for by caller! */ + + /* + * (prefix_r && ra) is an invalid form. Should already be + * checked for by caller! + */ return ea; } diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S index 1690d369688b..b2c912e517b9 100644 --- a/arch/powerpc/mm/book3s32/hash_low.S +++ b/arch/powerpc/mm/book3s32/hash_low.S @@ -15,6 +15,7 @@ */ #include <linux/pgtable.h> +#include <linux/init.h> #include <asm/reg.h> #include <asm/page.h> #include <asm/cputable.h> @@ -199,11 +200,9 @@ _GLOBAL(add_hash_page) * covered by a BAT). -- paulus */ mfmsr r9 - SYNC rlwinm r0,r9,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear MSR_DR */ mtmsr r0 - SYNC_601 isync #ifdef CONFIG_SMP @@ -262,7 +261,6 @@ _GLOBAL(add_hash_page) /* reenable interrupts and DR */ mtmsr r9 - SYNC_601 isync lwz r0,4(r1) @@ -287,9 +285,9 @@ _ASM_NOKPROBE_SYMBOL(add_hash_page) * * For speed, 4 of the instructions get patched once the size and * physical address of the hash table are known. These definitions - * of Hash_base and Hash_bits below are just an example. + * of Hash_base and Hash_bits below are for the early hash table. */ -Hash_base = 0xc0180000 +Hash_base = early_hash Hash_bits = 12 /* e.g. 256kB hash table */ Hash_msk = (((1 << Hash_bits) - 1) * 64) @@ -310,6 +308,7 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64) #define HASH_LEFT 31-(LG_PTEG_SIZE+Hash_bits-1) #define HASH_RIGHT 31-LG_PTEG_SIZE +__REF _GLOBAL(create_hpte) /* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */ rlwinm r8,r5,32-9,30,30 /* _PAGE_RW -> PP msb */ @@ -476,6 +475,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_NEED_COHERENT) sync /* make sure pte updates get to memory */ blr + .previous _ASM_NOKPROBE_SYMBOL(create_hpte) .section .bss @@ -496,6 +496,7 @@ htab_hash_searches: * * We assume that there is a hash table in use (Hash != 0). */ +__REF _GLOBAL(flush_hash_pages) /* * We disable interrupts here, even on UP, because we want @@ -506,11 +507,9 @@ _GLOBAL(flush_hash_pages) * covered by a BAT). -- paulus */ mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear MSR_DR */ mtmsr r0 - SYNC_601 isync /* First find a PTE in the range that has _PAGE_HASHPTE set */ @@ -629,9 +628,9 @@ _GLOBAL(flush_hash_pages) #endif 19: mtmsr r10 - SYNC_601 isync blr + .previous EXPORT_SYMBOL(flush_hash_pages) _ASM_NOKPROBE_SYMBOL(flush_hash_pages) @@ -643,11 +642,9 @@ _GLOBAL(_tlbie) lwz r8,TASK_CPU(r2) oris r8,r8,11 mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear DR */ mtmsr r0 - SYNC_601 isync lis r9,mmu_hash_lock@h ori r9,r9,mmu_hash_lock@l @@ -664,7 +661,6 @@ _GLOBAL(_tlbie) li r0,0 stw r0,0(r9) /* clear mmu_hash_lock */ mtmsr r10 - SYNC_601 isync #else /* CONFIG_SMP */ tlbie r3 @@ -681,11 +677,9 @@ _GLOBAL(_tlbia) lwz r8,TASK_CPU(r2) oris r8,r8,10 mfmsr r10 - SYNC rlwinm r0,r10,0,17,15 /* clear bit 16 (MSR_EE) */ rlwinm r0,r0,0,28,26 /* clear DR */ mtmsr r0 - SYNC_601 isync lis r9,mmu_hash_lock@h ori r9,r9,mmu_hash_lock@l @@ -709,7 +703,6 @@ _GLOBAL(_tlbia) li r0,0 stw r0,0(r9) /* clear mmu_hash_lock */ mtmsr r10 - SYNC_601 isync #endif /* CONFIG_SMP */ blr diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index d426eaf76bb0..a59e7ec98180 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -31,6 +31,8 @@ #include <mm/mmu_decl.h> +u8 __initdata early_hash[SZ_256K] __aligned(SZ_256K) = {0}; + struct hash_pte *Hash; static unsigned long Hash_size, Hash_mask; unsigned long _SDR1; @@ -73,23 +75,13 @@ unsigned long p_block_mapped(phys_addr_t pa) static int find_free_bat(void) { int b; + int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { - for (b = 0; b < 4; b++) { - struct ppc_bat *bat = BATS[b]; - - if (!(bat[0].batl & 0x40)) - return b; - } - } else { - int n = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; + for (b = 0; b < n; b++) { + struct ppc_bat *bat = BATS[b]; - for (b = 0; b < n; b++) { - struct ppc_bat *bat = BATS[b]; - - if (!(bat[1].batu & 3)) - return b; - } + if (!(bat[1].batu & 3)) + return b; } return -1; } @@ -97,7 +89,7 @@ static int find_free_bat(void) /* * This function calculates the size of the larger block usable to map the * beginning of an area based on the start address and size of that area: - * - max block size is 8M on 601 and 256 on other 6xx. + * - max block size is 256 on 6xx. * - base address must be aligned to the block size. So the maximum block size * is identified by the lowest bit set to 1 in the base address (for instance * if base is 0x16000000, max size is 0x02000000). @@ -106,7 +98,7 @@ static int find_free_bat(void) */ static unsigned int block_size(unsigned long base, unsigned long top) { - unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M; + unsigned int max_size = SZ_256M; unsigned int base_shift = (ffs(base) - 1) & 31; unsigned int block_shift = (fls(top - base) - 1) & 31; @@ -117,7 +109,6 @@ static unsigned int block_size(unsigned long base, unsigned long top) * Set up one of the IBAT (block address translation) register pairs. * The parameters are not checked; in particular size must be a power * of 2 between 128k and 256M. - * Only for 603+ ... */ static void setibat(int index, unsigned long virt, phys_addr_t phys, unsigned int size, pgprot_t prot) @@ -214,9 +205,6 @@ void mmu_mark_initmem_nx(void) unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; unsigned long size; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return; - for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) { size = block_size(base, top); setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); @@ -253,9 +241,6 @@ void mmu_mark_rodata_ro(void) int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4; int i; - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return; - for (i = 0; i < nb; i++) { struct ppc_bat *bat = BATS[i]; @@ -294,35 +279,22 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys, flags &= ~_PAGE_COHERENT; bl = (size >> 17) - 1; - if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) { - /* 603, 604, etc. */ - /* Do DBAT first */ - wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE - | _PAGE_COHERENT | _PAGE_GUARDED); - wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX; - bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ - bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp; - if (flags & _PAGE_USER) - bat[1].batu |= 1; /* Vp = 1 */ - if (flags & _PAGE_GUARDED) { - /* G bit must be zero in IBATs */ - flags &= ~_PAGE_EXEC; - } - if (flags & _PAGE_EXEC) - bat[0] = bat[1]; - else - bat[0].batu = bat[0].batl = 0; - } else { - /* 601 cpu */ - if (bl > BL_8M) - bl = BL_8M; - wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE - | _PAGE_COHERENT); - wimgxpp |= (flags & _PAGE_RW)? - ((flags & _PAGE_USER)? PP_RWRW: PP_RWXX): PP_RXRX; - bat->batu = virt | wimgxpp | 4; /* Ks=0, Ku=1 */ - bat->batl = phys | bl | 0x40; /* V=1 */ + /* Do DBAT first */ + wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE + | _PAGE_COHERENT | _PAGE_GUARDED); + wimgxpp |= (flags & _PAGE_RW)? BPP_RW: BPP_RX; + bat[1].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */ + bat[1].batl = BAT_PHYS_ADDR(phys) | wimgxpp; + if (flags & _PAGE_USER) + bat[1].batu |= 1; /* Vp = 1 */ + if (flags & _PAGE_GUARDED) { + /* G bit must be zero in IBATs */ + flags &= ~_PAGE_EXEC; } + if (flags & _PAGE_EXEC) + bat[0] = bat[1]; + else + bat[0].batu = bat[0].batl = 0; bat_addrs[index].start = virt; bat_addrs[index].limit = virt + ((bl + 1) << 17) - 1; @@ -425,15 +397,6 @@ void __init MMU_init_hw(void) hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg; if (lg_n_hpteg > 16) hash_mb2 = 16 - LG_HPTEG_SIZE; - - /* - * When KASAN is selected, there is already an early temporary hash - * table and the switch to the final hash table is done later. - */ - if (IS_ENABLED(CONFIG_KASAN)) - return; - - MMU_init_hw_patch(); } void __init MMU_init_hw_patch(void) @@ -441,6 +404,9 @@ void __init MMU_init_hw_patch(void) unsigned int hmask = Hash_mask >> (16 - LG_HPTEG_SIZE); unsigned int hash = (unsigned int)Hash - PAGE_OFFSET; + if (!mmu_has_feature(MMU_FTR_HPTE_TABLE)) + return; + if (ppc_md.progress) ppc_md.progress("hash:patch", 0x345); if (ppc_md.progress) @@ -474,11 +440,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base, */ BUG_ON(first_memblock_base != 0); - /* 601 can only access 16MB at the moment */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000)); - else /* Anything else has 256M mapped */ - memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000)); + memblock_set_current_limit(min_t(u64, first_memblock_size, SZ_256M)); } void __init print_system_hash_info(void) diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index cf20e5229ce1..0203cdf48c54 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -82,7 +82,7 @@ static void tlbiel_all_isa206(unsigned int num_sets, unsigned int is) for (set = 0; set < num_sets; set++) tlbiel_hash_set_isa206(set, is); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) @@ -110,7 +110,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) */ tlbiel_hash_set_isa300(0, is, 0, 2, 1); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory"); } @@ -303,7 +303,7 @@ static inline void tlbie(unsigned long vpn, int psize, int apsize, asm volatile("ptesync": : :"memory"); if (use_local) { __tlbiel(vpn, psize, apsize, ssize); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } else { __tlbie(vpn, psize, apsize, ssize); fixup_tlbie_vpn(vpn, psize, apsize, ssize); @@ -879,7 +879,7 @@ static void native_flush_hash_range(unsigned long number, int local) __tlbiel(vpn, psize, psize, ssize); } pte_iterate_hashed_end(); } - asm volatile("ptesync":::"memory"); + ppc_after_tlbiel_barrier(); } else { int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE); diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index b830adee51f5..24702c0a92e0 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -260,8 +260,12 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend, DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n", vstart, vend, pstart, prot, psize, ssize); - for (vaddr = vstart, paddr = pstart; vaddr < vend; - vaddr += step, paddr += step) { + /* Carefully map only the possible range */ + vaddr = ALIGN(vstart, step); + paddr = ALIGN(pstart, step); + vend = ALIGN_DOWN(vend, step); + + for (; vaddr < vend; vaddr += step, paddr += step) { unsigned long hash, hpteg; unsigned long vsid = get_kernel_vsid(vaddr, ssize); unsigned long vpn = hpt_vpn(vaddr, vsid, ssize); @@ -343,7 +347,9 @@ int htab_remove_mapping(unsigned long vstart, unsigned long vend, if (!mmu_hash_ops.hpte_removebolted) return -ENODEV; - for (vaddr = vstart; vaddr < vend; vaddr += step) { + /* Unmap the full range specificied */ + vaddr = ALIGN_DOWN(vstart, step); + for (;vaddr < vend; vaddr += step) { rc = mmu_hash_ops.hpte_removebolted(vaddr, psize, ssize); if (rc == -ENOENT) { ret = -ENOENT; diff --git a/arch/powerpc/mm/book3s64/internal.h b/arch/powerpc/mm/book3s64/internal.h index 7eda0d30d765..c12d78ee42f5 100644 --- a/arch/powerpc/mm/book3s64/internal.h +++ b/arch/powerpc/mm/book3s64/internal.h @@ -13,4 +13,6 @@ static inline bool stress_slb(void) return static_branch_unlikely(&stress_slb_key); } +void slb_setup_new_exec(void); + #endif /* ARCH_POWERPC_MM_BOOK3S64_INTERNAL_H */ diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index 0ba30b8b935b..1c54821de7bf 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -21,6 +21,8 @@ #include <asm/mmu_context.h> #include <asm/pgalloc.h> +#include "internal.h" + static DEFINE_IDA(mmu_context_ida); static int alloc_context_id(int min_id, int max_id) @@ -48,8 +50,6 @@ int hash__alloc_context_id(void) } EXPORT_SYMBOL_GPL(hash__alloc_context_id); -void slb_setup_new_exec(void); - static int realloc_context_ids(mm_context_t *ctx) { int i, id; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index cc72666e891a..3adcf730f478 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -34,7 +34,7 @@ unsigned int mmu_pid_bits; unsigned int mmu_base_pid; -unsigned int radix_mem_block_size __ro_after_init; +unsigned long radix_mem_block_size __ro_after_init; static __ref void *early_alloc_pgtable(unsigned long size, int nid, unsigned long region_start, unsigned long region_end) @@ -276,6 +276,7 @@ static int __meminit create_physical_mapping(unsigned long start, int psize; start = ALIGN(start, PAGE_SIZE); + end = ALIGN_DOWN(end, PAGE_SIZE); for (addr = start; addr < end; addr += mapping_size) { unsigned long gap, previous_size; int rc; @@ -497,7 +498,7 @@ static int __init probe_memory_block_size(unsigned long node, const char *uname, depth, void *data) { unsigned long *mem_block_size = (unsigned long *)data; - const __be64 *prop; + const __be32 *prop; int len; if (depth != 1) @@ -507,13 +508,14 @@ static int __init probe_memory_block_size(unsigned long node, const char *uname, return 0; prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len); - if (!prop || len < sizeof(__be64)) + + if (!prop || len < dt_root_size_cells * sizeof(__be32)) /* * Nothing in the device tree */ *mem_block_size = MIN_MEMORY_BLOCK_SIZE; else - *mem_block_size = be64_to_cpup(prop); + *mem_block_size = of_read_number(prop, dt_root_size_cells); return 1; } diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 0d233763441f..b487b489d4b6 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -65,7 +65,7 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is) for (set = 1; set < num_sets; set++) tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } void radix__tlbiel_all(unsigned int action) @@ -296,7 +296,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric) /* For PWC, only one flush is needed */ if (ric == RIC_FLUSH_PWC) { - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); return; } @@ -304,7 +304,7 @@ static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric) for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++) __tlbiel_pid(pid, set, RIC_FLUSH_TLB); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory"); } @@ -431,7 +431,7 @@ static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid, asm volatile("ptesync": : :"memory"); __tlbiel_va(va, pid, ap, ric); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static inline void _tlbiel_va_range(unsigned long start, unsigned long end, @@ -442,7 +442,7 @@ static inline void _tlbiel_va_range(unsigned long start, unsigned long end, if (also_pwc) __tlbiel_pid(pid, 0, RIC_FLUSH_PWC); __tlbiel_va_range(start, end, pid, page_size, psize); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } static inline void __tlbie_va_range(unsigned long start, unsigned long end, @@ -645,19 +645,29 @@ static void do_exit_flush_lazy_tlb(void *arg) struct mm_struct *mm = arg; unsigned long pid = mm->context.id; + /* + * A kthread could have done a mmget_not_zero() after the flushing CPU + * checked mm_is_singlethreaded, and be in the process of + * kthread_use_mm when interrupted here. In that case, current->mm will + * be set to mm, because kthread_use_mm() setting ->mm and switching to + * the mm is done with interrupts off. + */ if (current->mm == mm) - return; /* Local CPU */ + goto out_flush; if (current->active_mm == mm) { - /* - * Must be a kernel thread because sender is single-threaded. - */ - BUG_ON(current->mm); + WARN_ON_ONCE(current->mm != NULL); + /* Is a kernel thread and is using mm as the lazy tlb */ mmgrab(&init_mm); - switch_mm(mm, &init_mm, current); current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); mmdrop(mm); } + + atomic_dec(&mm->context.active_cpus); + cpumask_clear_cpu(smp_processor_id(), mm_cpumask(mm)); + +out_flush: _tlbiel_pid(pid, RIC_FLUSH_ALL); } @@ -672,7 +682,6 @@ static void exit_flush_lazy_tlbs(struct mm_struct *mm) */ smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb, (void *)mm, 1); - mm_reset_thread_local(mm); } void radix__flush_tlb_mm(struct mm_struct *mm) @@ -940,7 +949,7 @@ is_local: if (hflush) __tlbiel_va_range(hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M); - asm volatile("ptesync": : :"memory"); + ppc_after_tlbiel_barrier(); } else if (cputlb_use_tlbie()) { asm volatile("ptesync": : :"memory"); __tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize); diff --git a/arch/powerpc/mm/book3s64/slb.c b/arch/powerpc/mm/book3s64/slb.c index 156c38f89511..c30fcbfa0e32 100644 --- a/arch/powerpc/mm/book3s64/slb.c +++ b/arch/powerpc/mm/book3s64/slb.c @@ -765,8 +765,8 @@ static long slb_allocate_kernel(unsigned long ea, unsigned long id) if (id == LINEAR_MAP_REGION_ID) { - /* We only support upto MAX_PHYSMEM_BITS */ - if ((ea & EA_MASK) > (1UL << MAX_PHYSMEM_BITS)) + /* We only support upto H_MAX_PHYSMEM_BITS */ + if ((ea & EA_MASK) > (1UL << H_MAX_PHYSMEM_BITS)) return -EFAULT; flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp; diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index b2eeea39684c..9af3832c9d8d 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -389,10 +389,8 @@ static void __init init_drmem_v1_lmbs(const __be32 *prop) if (!drmem_info->lmbs) return; - for_each_drmem_lmb(lmb) { + for_each_drmem_lmb(lmb) read_drconf_v1_cell(lmb, &prop); - lmb_set_nid(lmb); - } } static void __init init_drmem_v2_lmbs(const __be32 *prop) @@ -437,8 +435,6 @@ static void __init init_drmem_v2_lmbs(const __be32 *prop) lmb->aa_index = dr_cell.aa_index; lmb->flags = dr_cell.flags; - - lmb_set_nid(lmb); } } } diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 26292544630f..36c3800769fb 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -180,7 +180,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz if (!hpdp) return NULL; - if (IS_ENABLED(CONFIG_PPC_8xx) && sz == SZ_512K) + if (IS_ENABLED(CONFIG_PPC_8xx) && pshift < PMD_SHIFT) return pte_alloc_map(mm, (pmd_t *)hpdp, addr); BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp)); @@ -330,10 +330,24 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif get_hugepd_cache_index(pdshift - shift)); } -static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, unsigned long addr) +static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) { + unsigned long start = addr; pgtable_t token = pmd_pgtable(*pmd); + start &= PMD_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + pmd_clear(pmd); pte_free_tlb(tlb, token, addr); mm_dec_nr_ptes(tlb->mm); @@ -363,7 +377,7 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud, */ WARN_ON(!IS_ENABLED(CONFIG_PPC_8xx)); - hugetlb_free_pte_range(tlb, pmd, addr); + hugetlb_free_pte_range(tlb, pmd, addr, end, floor, ceiling); continue; } diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 8459056cce67..386be136026e 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -162,16 +162,16 @@ static __meminit struct vmemmap_backing * vmemmap_list_alloc(int node) return next++; } -static __meminit void vmemmap_list_populate(unsigned long phys, - unsigned long start, - int node) +static __meminit int vmemmap_list_populate(unsigned long phys, + unsigned long start, + int node) { struct vmemmap_backing *vmem_back; vmem_back = vmemmap_list_alloc(node); if (unlikely(!vmem_back)) { - WARN_ON(1); - return; + pr_debug("vmemap list allocation failed\n"); + return -ENOMEM; } vmem_back->phys = phys; @@ -179,6 +179,7 @@ static __meminit void vmemmap_list_populate(unsigned long phys, vmem_back->list = vmemmap_list; vmemmap_list = vmem_back; + return 0; } static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start, @@ -199,6 +200,7 @@ static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long star int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { + bool altmap_alloc; unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift; /* Align to the page size of the linear mapping. */ @@ -228,13 +230,32 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, p = vmemmap_alloc_block_buf(page_size, node, altmap); if (!p) pr_debug("altmap block allocation failed, falling back to system memory"); + else + altmap_alloc = true; } - if (!p) + if (!p) { p = vmemmap_alloc_block_buf(page_size, node, NULL); + altmap_alloc = false; + } if (!p) return -ENOMEM; - vmemmap_list_populate(__pa(p), start, node); + if (vmemmap_list_populate(__pa(p), start, node)) { + /* + * If we don't populate vmemap list, we don't have + * the ability to free the allocated vmemmap + * pages in section_deactivate. Hence free them + * here. + */ + int nr_pfns = page_size >> PAGE_SHIFT; + unsigned long page_order = get_order(page_size); + + if (altmap_alloc) + vmem_altmap_free(altmap, nr_pfns); + else + free_pages((unsigned long)p, page_order); + return -ENOMEM; + } pr_debug(" * %016lx..%016lx allocated at %p\n", start, start + page_size, p); @@ -264,10 +285,8 @@ static unsigned long vmemmap_list_free(unsigned long start) vmem_back_prev = vmem_back; } - if (unlikely(!vmem_back)) { - WARN_ON(1); + if (unlikely(!vmem_back)) return 0; - } /* remove it from vmemmap_list */ if (vmem_back == vmemmap_list) /* remove head */ diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c index 26fda3203320..cf8770b1a692 100644 --- a/arch/powerpc/mm/kasan/kasan_init_32.c +++ b/arch/powerpc/mm/kasan/kasan_init_32.c @@ -127,8 +127,7 @@ void __init kasan_mmu_init(void) { int ret; - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE) || - IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) { ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); if (ret) @@ -140,10 +139,10 @@ void __init kasan_init(void) { phys_addr_t base, end; u64 i; + int ret; for_each_mem_range(i, &base, &end) { phys_addr_t top = min(end, total_lowmem); - int ret; if (base >= top) continue; @@ -153,6 +152,13 @@ void __init kasan_init(void) panic("kasan: kasan_init_region() failed"); } + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + ret = kasan_init_shadow_page_tables(KASAN_SHADOW_START, KASAN_SHADOW_END); + + if (ret) + panic("kasan: kasan_init_shadow_page_tables() failed"); + } + kasan_remap_early_shadow_ro(); clear_page(kasan_early_shadow_page); @@ -168,22 +174,6 @@ void __init kasan_late_init(void) kasan_unmap_early_shadow_vmalloc(); } -#ifdef CONFIG_PPC_BOOK3S_32 -u8 __initdata early_hash[256 << 10] __aligned(256 << 10) = {0}; - -static void __init kasan_early_hash_table(void) -{ - unsigned int hash = __pa(early_hash); - - modify_instruction_site(&patch__hash_page_A0, 0xffff, hash >> 16); - modify_instruction_site(&patch__flush_hash_A0, 0xffff, hash >> 16); - - Hash = (struct hash_pte *)early_hash; -} -#else -static void __init kasan_early_hash_table(void) {} -#endif - void __init kasan_early_init(void) { unsigned long addr = KASAN_SHADOW_START; @@ -199,7 +189,4 @@ void __init kasan_early_init(void) next = pgd_addr_end(addr, end); pmd_populate_kernel(&init_mm, pmd, kasan_early_shadow_pte); } while (pmd++, addr = next, addr != end); - - if (early_mmu_has_feature(MMU_FTR_HPTE_TABLE)) - kasan_early_hash_table(); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 5e2e7c0a8f1a..01ec2a252f09 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -49,6 +49,7 @@ #include <asm/swiotlb.h> #include <asm/rtas.h> #include <asm/kasan.h> +#include <asm/svm.h> #include <mm/mmu_decl.h> @@ -283,7 +284,10 @@ void __init mem_init(void) * back to to-down. */ memblock_set_bottom_up(true); - swiotlb_init(0); + if (is_secure_guest()) + svm_swiotlb_init(); + else + swiotlb_init(0); #endif high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index d2b37146ae6c..231ca95f9ffb 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -244,13 +244,6 @@ void set_context(unsigned long id, pgd_t *pgd) mb(); } -void flush_instruction_cache(void) -{ - isync(); - mtspr(SPRN_IC_CST, IDC_INVALL); - isync(); -} - #ifdef CONFIG_PPC_KUEP void __init setup_kuep(bool disabled) { diff --git a/arch/powerpc/mm/nohash/fsl_booke.c b/arch/powerpc/mm/nohash/fsl_booke.c index 0c294827d6e5..36bda962d3b3 100644 --- a/arch/powerpc/mm/nohash/fsl_booke.c +++ b/arch/powerpc/mm/nohash/fsl_booke.c @@ -219,6 +219,22 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) return tlbcam_addrs[tlbcam_index - 1].limit - PAGE_OFFSET + 1; } +void flush_instruction_cache(void) +{ + unsigned long tmp; + + if (IS_ENABLED(CONFIG_E200)) { + tmp = mfspr(SPRN_L1CSR0); + tmp |= L1CSR0_CFI | L1CSR0_CLFC; + mtspr(SPRN_L1CSR0, tmp); + } else { + tmp = mfspr(SPRN_L1CSR1); + tmp |= L1CSR1_ICFI | L1CSR1_ICLFR; + mtspr(SPRN_L1CSR1, tmp); + } + isync(); +} + /* * MMU_init_hw does the chip-specific initialization of the MMU hardware. */ diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 14514585db98..5872f69141d5 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -83,16 +83,12 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { }; #elif defined(CONFIG_PPC_8xx) struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { - /* we only manage 4k and 16k pages as normal pages */ -#ifdef CONFIG_PPC_4K_PAGES [MMU_PAGE_4K] = { .shift = 12, }, -#else [MMU_PAGE_16K] = { .shift = 14, }, -#endif [MMU_PAGE_512K] = { .shift = 19, }, diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f4e20d8e6c02..63f61d8b55e5 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -430,7 +430,7 @@ static int of_get_assoc_arrays(struct assoc_arrays *aa) * This is like of_node_to_nid_single() for memory represented in the * ibm,dynamic-reconfiguration-memory node. */ -static int of_drconf_to_nid_single(struct drmem_lmb *lmb) +int of_drconf_to_nid_single(struct drmem_lmb *lmb) { struct assoc_arrays aa = { .arrays = NULL }; int default_nid = NUMA_NO_NODE; @@ -507,6 +507,11 @@ static int numa_setup_cpu(unsigned long lcpu) int fcpu = cpu_first_thread_sibling(lcpu); int nid = NUMA_NO_NODE; + if (!cpu_present(lcpu)) { + set_cpu_numa_node(lcpu, first_online_node); + return first_online_node; + } + /* * If a valid cpu-to-node mapping is already available, use it * directly instead of querying the firmware, since it represents @@ -723,21 +728,22 @@ static int __init parse_numa_properties(void) */ for_each_present_cpu(i) { struct device_node *cpu; - int nid; - - cpu = of_get_cpu_node(i, NULL); - BUG_ON(!cpu); - nid = of_node_to_nid_single(cpu); - of_node_put(cpu); + int nid = vphn_get_nid(i); /* * Don't fall back to default_nid yet -- we will plug * cpus into nodes once the memory scan has discovered * the topology. */ - if (nid < 0) - continue; - node_set_online(nid); + if (nid == NUMA_NO_NODE) { + cpu = of_get_cpu_node(i, NULL); + BUG_ON(!cpu); + nid = of_node_to_nid_single(cpu); + of_node_put(cpu); + } + + if (likely(nid > 0)) + node_set_online(nid); } get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells); @@ -888,7 +894,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) static void __init find_possible_nodes(void) { struct device_node *rtas; - u32 numnodes, i; + const __be32 *domains; + int prop_length, max_nodes; + u32 i; if (!numa_enabled) return; @@ -897,16 +905,31 @@ static void __init find_possible_nodes(void) if (!rtas) return; - if (of_property_read_u32_index(rtas, - "ibm,max-associativity-domains", - min_common_depth, &numnodes)) - goto out; + /* + * ibm,current-associativity-domains is a fairly recent property. If + * it doesn't exist, then fallback on ibm,max-associativity-domains. + * Current denotes what the platform can support compared to max + * which denotes what the Hypervisor can support. + */ + domains = of_get_property(rtas, "ibm,current-associativity-domains", + &prop_length); + if (!domains) { + domains = of_get_property(rtas, "ibm,max-associativity-domains", + &prop_length); + if (!domains) + goto out; + } - for (i = 0; i < numnodes; i++) { + max_nodes = of_read_number(&domains[min_common_depth], 1); + for (i = 0; i < max_nodes; i++) { if (!node_possible(i)) node_set(i, node_possible_map); } + prop_length /= sizeof(int); + if (prop_length > min_common_depth + 2) + coregroup_enabled = 1; + out: of_node_put(rtas); } @@ -915,6 +938,16 @@ void __init mem_topology_setup(void) { int cpu; + /* + * Linux/mm assumes node 0 to be online at boot. However this is not + * true on PowerPC, where node 0 is similar to any other node, it + * could be cpuless, memoryless node. So force node 0 to be offline + * for now. This will prevent cpuless, memoryless node 0 showing up + * unnecessarily as online. If a node has cpus or memory that need + * to be online, then node will anyway be marked online. + */ + node_set_offline(0); + if (parse_numa_properties()) setup_nonnuma(); @@ -932,8 +965,17 @@ void __init mem_topology_setup(void) reset_numa_cpu_lookup_table(); - for_each_present_cpu(cpu) + for_each_possible_cpu(cpu) { + /* + * Powerpc with CONFIG_NUMA always used to have a node 0, + * even if it was memoryless or cpuless. For all cpus that + * are possible but not present, cpu_to_node() would point + * to node 0. To remove a cpuless, memoryless dummy node, + * powerpc need to make sure all possible but not present + * cpu_to_node are set to a proper node. + */ numa_setup_cpu(cpu); + } } void __init initmem_init(void) @@ -1200,6 +1242,31 @@ int find_and_online_cpu_nid(int cpu) return new_nid; } +int cpu_to_coregroup_id(int cpu) +{ + __be32 associativity[VPHN_ASSOC_BUFSIZE] = {0}; + int index; + + if (cpu < 0 || cpu > nr_cpu_ids) + return -1; + + if (!coregroup_enabled) + goto out; + + if (!firmware_has_feature(FW_FEATURE_VPHN)) + goto out; + + if (vphn_get_associativity(cpu, associativity)) + goto out; + + index = of_read_number(associativity, 1); + if (index > min_common_depth + 1) + return of_read_number(&associativity[index - 1], 1); + +out: + return cpu_to_core_id(cpu); +} + static int topology_update_init(void) { topology_inited = 1; diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index ab57b07ef39a..15555c95cebc 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -263,8 +263,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ pmd_t *pmd = pmd_off(mm, addr); pte_basic_t val; pte_basic_t *entry = &ptep->pte; - int num = is_hugepd(*((hugepd_t *)pmd)) ? 1 : SZ_512K / SZ_4K; - int i; + int num, i; /* * Make sure hardware valid bit is not set. We don't do @@ -275,6 +274,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_ pte = set_pte_filter(pte); val = pte_val(pte); + + num = number_of_cells_per_pte(pmd, val, 1); + for (i = 0; i < num; i++, entry++, val += SZ_4K) *entry = val; } diff --git a/arch/powerpc/mm/ptdump/8xx.c b/arch/powerpc/mm/ptdump/8xx.c index 8a797dcbf475..86da2a669680 100644 --- a/arch/powerpc/mm/ptdump/8xx.c +++ b/arch/powerpc/mm/ptdump/8xx.c @@ -11,8 +11,13 @@ static const struct flag_info flag_array[] = { { +#ifdef CONFIG_PPC_16K_PAGES .mask = _PAGE_HUGE, .val = _PAGE_HUGE, +#else + .mask = _PAGE_SPS, + .val = _PAGE_SPS, +#endif .set = "huge", .clear = " ", }, { diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c index e29b338d499f..c4c628b03cf8 100644 --- a/arch/powerpc/mm/ptdump/bats.c +++ b/arch/powerpc/mm/ptdump/bats.c @@ -12,62 +12,6 @@ #include "ptdump.h" -static char *pp_601(int k, int pp) -{ - if (pp == 0) - return k ? " " : "rwx"; - if (pp == 1) - return k ? "r x" : "rwx"; - if (pp == 2) - return "rwx"; - return "r x"; -} - -static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper) -{ - u32 blpi = upper & 0xfffe0000; - u32 k = (upper >> 2) & 3; - u32 pp = upper & 3; - phys_addr_t pbn = PHYS_BAT_ADDR(lower); - u32 bsm = lower & 0x3ff; - u32 size = (bsm + 1) << 17; - - seq_printf(m, "%d: ", idx); - if (!(lower & 0x40)) { - seq_puts(m, " -\n"); - return; - } - - seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1); -#ifdef CONFIG_PHYS_64BIT - seq_printf(m, "0x%016llx ", pbn); -#else - seq_printf(m, "0x%08x ", pbn); -#endif - pt_dump_size(m, size); - - seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp)); - - seq_puts(m, lower & _PAGE_WRITETHRU ? "w " : " "); - seq_puts(m, lower & _PAGE_NO_CACHE ? "i " : " "); - seq_puts(m, lower & _PAGE_COHERENT ? "m " : " "); - seq_puts(m, "\n"); -} - -#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u)) - -static int bats_show_601(struct seq_file *m, void *v) -{ - seq_puts(m, "---[ Block Address Translation ]---\n"); - - BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U); - BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U); - BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U); - BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U); - - return 0; -} - static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d) { u32 bepi = upper & 0xfffe0000; @@ -146,9 +90,6 @@ static int bats_show_603(struct seq_file *m, void *v) static int bats_open(struct inode *inode, struct file *file) { - if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) - return single_open(file, bats_show_601, NULL); - return single_open(file, bats_show_603, NULL); } diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c index df59d0bb121f..489f993100d5 100644 --- a/arch/powerpc/oprofile/cell/spu_task_sync.c +++ b/arch/powerpc/oprofile/cell/spu_task_sync.c @@ -572,7 +572,7 @@ void spu_sync_buffer(int spu_num, unsigned int *samples, * samples are recorded. * No big deal -- so we just drop a few samples. */ - pr_debug("SPU_PROF: No cached SPU contex " + pr_debug("SPU_PROF: No cached SPU context " "for SPU #%d. Dropping samples.\n", spu_num); goto out; } diff --git a/arch/powerpc/perf/hv-gpci-requests.h b/arch/powerpc/perf/hv-gpci-requests.h index e608f9db12dd..8965b4463d43 100644 --- a/arch/powerpc/perf/hv-gpci-requests.h +++ b/arch/powerpc/perf/hv-gpci-requests.h @@ -95,7 +95,7 @@ REQUEST(__field(0, 8, partition_id) #define REQUEST_NAME system_performance_capabilities #define REQUEST_NUM 0x40 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__field(0, 1, perf_collect_privileged) __field(0x1, 1, capability_mask) @@ -223,7 +223,7 @@ REQUEST(__field(0, 2, partition_id) #define REQUEST_NAME system_hypervisor_times #define REQUEST_NUM 0xF0 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) __count(0x8, 8, time_spent_processing_virtual_processor_timers) @@ -234,7 +234,7 @@ REQUEST(__count(0, 8, time_spent_to_dispatch_virtual_processors) #define REQUEST_NAME system_tlbie_count_and_time #define REQUEST_NUM 0xF4 -#define REQUEST_IDX_KIND "starting_index=0xffffffffffffffff" +#define REQUEST_IDX_KIND "starting_index=0xffffffff" #include I(REQUEST_BEGIN) REQUEST(__count(0, 8, tlbie_instructions_issued) /* diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c index 6884d16ec19b..d48413e28c39 100644 --- a/arch/powerpc/perf/hv-gpci.c +++ b/arch/powerpc/perf/hv-gpci.c @@ -48,6 +48,8 @@ EVENT_DEFINE_RANGE_FORMAT(length, config1, 24, 31); /* u32, byte offset */ EVENT_DEFINE_RANGE_FORMAT(offset, config1, 32, 63); +static cpumask_t hv_gpci_cpumask; + static struct attribute *format_attrs[] = { &format_attr_request.attr, &format_attr_starting_index.attr, @@ -94,7 +96,15 @@ static ssize_t kernel_version_show(struct device *dev, return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT); } +static ssize_t cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &hv_gpci_cpumask); +} + static DEVICE_ATTR_RO(kernel_version); +static DEVICE_ATTR_RO(cpumask); + HV_CAPS_ATTR(version, "0x%x\n"); HV_CAPS_ATTR(ga, "%d\n"); HV_CAPS_ATTR(expanded, "%d\n"); @@ -111,6 +121,15 @@ static struct attribute *interface_attrs[] = { NULL, }; +static struct attribute *cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group cpumask_attr_group = { + .attrs = cpumask_attrs, +}; + static struct attribute_group interface_group = { .name = "interface", .attrs = interface_attrs, @@ -120,20 +139,12 @@ static const struct attribute_group *attr_groups[] = { &format_group, &event_group, &interface_group, + &cpumask_attr_group, NULL, }; -#define HGPCI_REQ_BUFFER_SIZE 4096 -#define HGPCI_MAX_DATA_BYTES \ - (HGPCI_REQ_BUFFER_SIZE - sizeof(struct hv_get_perf_counter_info_params)) - static DEFINE_PER_CPU(char, hv_gpci_reqb[HGPCI_REQ_BUFFER_SIZE]) __aligned(sizeof(uint64_t)); -struct hv_gpci_request_buffer { - struct hv_get_perf_counter_info_params params; - uint8_t bytes[HGPCI_MAX_DATA_BYTES]; -} __packed; - static unsigned long single_gpci_request(u32 req, u32 starting_index, u16 secondary_index, u8 version_in, u32 offset, u8 length, u64 *value) @@ -275,6 +286,45 @@ static struct pmu h_gpci_pmu = { .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }; +static int ppc_hv_gpci_cpu_online(unsigned int cpu) +{ + if (cpumask_empty(&hv_gpci_cpumask)) + cpumask_set_cpu(cpu, &hv_gpci_cpumask); + + return 0; +} + +static int ppc_hv_gpci_cpu_offline(unsigned int cpu) +{ + int target; + + /* Check if exiting cpu is used for collecting gpci events */ + if (!cpumask_test_and_clear_cpu(cpu, &hv_gpci_cpumask)) + return 0; + + /* Find a new cpu to collect gpci events */ + target = cpumask_last(cpu_active_mask); + + if (target < 0 || target >= nr_cpu_ids) { + pr_err("hv_gpci: CPU hotplug init failed\n"); + return -1; + } + + /* Migrate gpci events to the new target */ + cpumask_set_cpu(target, &hv_gpci_cpumask); + perf_pmu_migrate_context(&h_gpci_pmu, cpu, target); + + return 0; +} + +static int hv_gpci_cpu_hotplug_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE, + "perf/powerpc/hv_gcpi:online", + ppc_hv_gpci_cpu_online, + ppc_hv_gpci_cpu_offline); +} + static int hv_gpci_init(void) { int r; @@ -295,6 +345,11 @@ static int hv_gpci_init(void) return -ENODEV; } + /* init cpuhotplug */ + r = hv_gpci_cpu_hotplug_init(); + if (r) + return r; + /* sampling not supported */ h_gpci_pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; diff --git a/arch/powerpc/perf/hv-gpci.h b/arch/powerpc/perf/hv-gpci.h index a3053eda5dcc..4d108262bed7 100644 --- a/arch/powerpc/perf/hv-gpci.h +++ b/arch/powerpc/perf/hv-gpci.h @@ -2,33 +2,6 @@ #ifndef LINUX_POWERPC_PERF_HV_GPCI_H_ #define LINUX_POWERPC_PERF_HV_GPCI_H_ -#include <linux/types.h> - -/* From the document "H_GetPerformanceCounterInfo Interface" v1.07 */ - -/* H_GET_PERF_COUNTER_INFO argument */ -struct hv_get_perf_counter_info_params { - __be32 counter_request; /* I */ - __be32 starting_index; /* IO */ - __be16 secondary_index; /* IO */ - __be16 returned_values; /* O */ - __be32 detail_rc; /* O, only needed when called via *_norets() */ - - /* - * O, size each of counter_value element in bytes, only set for version - * >= 0x3 - */ - __be16 cv_element_size; - - /* I, 0 (zero) for versions < 0x3 */ - __u8 counter_info_version_in; - - /* O, 0 (zero) if version < 0x3. Must be set to 0 when making hcall */ - __u8 counter_info_version_out; - __u8 reserved[0xC]; - __u8 counter_value[]; -} __packed; - /* * counter info version => fw version/reference (spec version) * diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 62d0b54086f8..9ed4fcccf8a9 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -1426,8 +1426,6 @@ static void trace_imc_event_del(struct perf_event *event, int flags) static int trace_imc_event_init(struct perf_event *event) { - struct task_struct *target; - if (event->attr.type != event->pmu->type) return -ENOENT; @@ -1458,7 +1456,6 @@ static int trace_imc_event_init(struct perf_event *event) mutex_unlock(&imc_global_refc.lock); event->hw.idx = -1; - target = event->hw.target; event->pmu->task_ctx_nr = perf_hw_context; event->destroy = reset_global_refc; diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 964437adec18..2848904df638 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -288,6 +288,15 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) mask |= CNST_PMC_MASK(pmc); value |= CNST_PMC_VAL(pmc); + + /* + * PMC5 and PMC6 are used to count cycles and instructions and + * they do not support most of the constraint bits. Add a check + * to exclude PMC5/6 from most of the constraints except for + * EBB/BHRB. + */ + if (pmc >= 5) + goto ebb_bhrb; } if (pmc <= 4) { @@ -357,6 +366,7 @@ int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp) } } +ebb_bhrb: if (!pmc && ebb) /* EBB events must specify the PMC */ return -1; diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h index 044de65e96b9..7025de5e60e7 100644 --- a/arch/powerpc/perf/isa207-common.h +++ b/arch/powerpc/perf/isa207-common.h @@ -13,6 +13,8 @@ #include <asm/firmware.h> #include <asm/cputable.h> +#include "internal.h" + #define EVENT_EBB_MASK 1ull #define EVENT_EBB_SHIFT PERF_EVENT_CONFIG_EBB_SHIFT #define EVENT_BHRB_MASK 1ull diff --git a/arch/powerpc/perf/power10-pmu.c b/arch/powerpc/perf/power10-pmu.c index 83148656b524..9dbe8f9b89b4 100644 --- a/arch/powerpc/perf/power10-pmu.c +++ b/arch/powerpc/perf/power10-pmu.c @@ -9,7 +9,6 @@ #define pr_fmt(fmt) "power10-pmu: " fmt #include "isa207-common.h" -#include "internal.h" /* * Raw event encoding for Power10: diff --git a/arch/powerpc/perf/power5+-pmu.c b/arch/powerpc/perf/power5+-pmu.c index a62b2cd7914f..3e64b4a1511f 100644 --- a/arch/powerpc/perf/power5+-pmu.c +++ b/arch/powerpc/perf/power5+-pmu.c @@ -10,6 +10,8 @@ #include <asm/reg.h> #include <asm/cputable.h> +#include "internal.h" + /* * Bits in event code for POWER5+ (POWER5 GS) and POWER5++ (POWER5 GS DD3) */ diff --git a/arch/powerpc/perf/power5-pmu.c b/arch/powerpc/perf/power5-pmu.c index 8732b587cf71..017bb19b73fb 100644 --- a/arch/powerpc/perf/power5-pmu.c +++ b/arch/powerpc/perf/power5-pmu.c @@ -10,6 +10,8 @@ #include <asm/reg.h> #include <asm/cputable.h> +#include "internal.h" + /* * Bits in event code for POWER5 (not POWER5++) */ diff --git a/arch/powerpc/perf/power6-pmu.c b/arch/powerpc/perf/power6-pmu.c index 0e318cf87129..189974478e9f 100644 --- a/arch/powerpc/perf/power6-pmu.c +++ b/arch/powerpc/perf/power6-pmu.c @@ -10,6 +10,8 @@ #include <asm/reg.h> #include <asm/cputable.h> +#include "internal.h" + /* * Bits in event code for POWER6 */ diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index 5e0bf09cf077..bacfab104a1a 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -10,6 +10,8 @@ #include <asm/reg.h> #include <asm/cputable.h> +#include "internal.h" + /* * Bits in event code for POWER7 */ diff --git a/arch/powerpc/perf/ppc970-pmu.c b/arch/powerpc/perf/ppc970-pmu.c index d35223fb112c..7d78df97f272 100644 --- a/arch/powerpc/perf/ppc970-pmu.c +++ b/arch/powerpc/perf/ppc970-pmu.c @@ -9,6 +9,8 @@ #include <asm/reg.h> #include <asm/cputable.h> +#include "internal.h" + /* * Bits in event code for PPC970 */ diff --git a/arch/powerpc/platforms/44x/machine_check.c b/arch/powerpc/platforms/44x/machine_check.c index 90ad6ac529d2..a5c898bb9bab 100644 --- a/arch/powerpc/platforms/44x/machine_check.c +++ b/arch/powerpc/platforms/44x/machine_check.c @@ -7,6 +7,7 @@ #include <linux/ptrace.h> #include <asm/reg.h> +#include <asm/cacheflush.h> int machine_check_440A(struct pt_regs *regs) { diff --git a/arch/powerpc/platforms/44x/ppc476.c b/arch/powerpc/platforms/44x/ppc476.c index cba83eee685c..07f7e3ce67b5 100644 --- a/arch/powerpc/platforms/44x/ppc476.c +++ b/arch/powerpc/platforms/44x/ppc476.c @@ -86,8 +86,7 @@ static void __noreturn avr_reset_system(char *cmd) avr_halt_system(AVR_PWRCTL_RESET); } -static int avr_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int avr_probe(struct i2c_client *client) { avr_i2c_client = client; ppc_md.restart = avr_reset_system; @@ -104,7 +103,7 @@ static struct i2c_driver avr_driver = { .driver = { .name = "akebono-avr", }, - .probe = avr_probe, + .probe_new = avr_probe, .id_table = avr_id, }; diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c index 0967bdfb1691..409481016928 100644 --- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c +++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c @@ -142,7 +142,7 @@ static int mcu_gpiochip_remove(struct mcu *mcu) return 0; } -static int mcu_probe(struct i2c_client *client, const struct i2c_device_id *id) +static int mcu_probe(struct i2c_client *client) { struct mcu *mcu; int ret; @@ -221,7 +221,7 @@ static struct i2c_driver mcu_driver = { .name = "mcu-mpc8349emitx", .of_match_table = mcu_of_match_table, }, - .probe = mcu_probe, + .probe_new = mcu_probe, .remove = mcu_remove, .id_table = mcu_ids, }; diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c index fda108bae95f..c6df294054fe 100644 --- a/arch/powerpc/platforms/85xx/smp.c +++ b/arch/powerpc/platforms/85xx/smp.c @@ -112,7 +112,7 @@ static void mpc85xx_take_timebase(void) local_irq_restore(flags); } -static void smp_85xx_mach_cpu_die(void) +static void smp_85xx_cpu_offline_self(void) { unsigned int cpu = smp_processor_id(); @@ -506,7 +506,7 @@ void __init mpc85xx_smp_init(void) if (qoriq_pm_ops) { smp_85xx_ops.give_timebase = mpc85xx_give_timebase; smp_85xx_ops.take_timebase = mpc85xx_take_timebase; - ppc_md.cpu_die = smp_85xx_mach_cpu_die; + smp_85xx_ops.cpu_offline_self = smp_85xx_cpu_offline_self; smp_85xx_ops.cpu_die = qoriq_cpu_kill; } #endif diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index fb7515b4fa9c..7a5e8f4541e3 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -199,21 +199,6 @@ source "drivers/cpuidle/Kconfig" endmenu -config PPC601_SYNC_FIX - bool "Workarounds for PPC601 bugs" - depends on PPC_BOOK3S_601 && PPC_PMAC - default y - help - Some versions of the PPC601 (the first PowerPC chip) have bugs which - mean that extra synchronization instructions are required near - certain instructions, typically those that make major changes to the - CPU state. These extra instructions reduce performance slightly. - If you say N here, these extra instructions will not be included, - resulting in a kernel which will run faster but may not run at all - on some systems with the PPC601 chip. - - If in doubt, say Y here. - config TAU bool "On-chip CPU temperature sensor support" depends on PPC_BOOK3S_32 @@ -223,12 +208,11 @@ config TAU temperature within 2-4 degrees Celsius. This option shows the current on-die temperature in /proc/cpuinfo if the cpu supports it. - Unfortunately, on some chip revisions, this sensor is very inaccurate - and in many cases, does not work at all, so don't assume the cpu - temp is actually what /proc/cpuinfo says it is. + Unfortunately, this sensor is very inaccurate when uncalibrated, so + don't assume the cpu temp is actually what /proc/cpuinfo says it is. config TAU_INT - bool "Interrupt driven TAU driver (DANGEROUS)" + bool "Interrupt driven TAU driver (EXPERIMENTAL)" depends on TAU help The TAU supports an interrupt driven mode which causes an interrupt @@ -236,12 +220,7 @@ config TAU_INT to get notified the temp has exceeded a range. With this option off, a timer is used to re-check the temperature periodically. - However, on some cpus it appears that the TAU interrupt hardware - is buggy and can cause a situation which would lead unexplained hard - lockups. - - Unless you are extending the TAU driver, or enjoy kernel/hardware - debugging, leave this option off. + If in doubt, say N here. config TAU_AVERAGE bool "Average high and low temp" diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 1dc9d3c81872..c194c4ae8bc7 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -20,7 +20,7 @@ choice depends on PPC32 help There are five families of 32 bit PowerPC chips supported. - The most common ones are the desktop and server CPUs (601, 603, + The most common ones are the desktop and server CPUs (603, 604, 740, 750, 74xx) CPUs from Freescale and IBM, with their embedded 512x/52xx/82xx/83xx/86xx counterparts. The other embedded parts, namely 4xx, 8xx, e200 (55xx) and e500 @@ -30,7 +30,7 @@ choice If unsure, select 52xx/6xx/7xx/74xx/82xx/83xx/86xx. config PPC_BOOK3S_6xx - bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx except 601" + bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx" select PPC_BOOK3S_32 select PPC_FPU select PPC_HAVE_PMU_SUPPORT @@ -38,13 +38,6 @@ config PPC_BOOK3S_6xx select PPC_HAVE_KUAP select HAVE_ARCH_VMAP_STACK if !ADB_PMU -config PPC_BOOK3S_601 - bool "PowerPC 601" - select PPC_BOOK3S_32 - select PPC_FPU - select PPC_HAVE_KUAP - select HAVE_ARCH_VMAP_STACK - config PPC_85xx bool "Freescale 85xx" select E500 @@ -490,13 +483,12 @@ endmenu config VDSO32 def_bool y - depends on PPC32 || CPU_BIG_ENDIAN + depends on PPC32 || COMPAT help This symbol controls whether we build the 32-bit VDSO. We obviously want to do that if we're building a 32-bit kernel. If we're building - a 64-bit kernel then we only want a 32-bit VDSO if we're building for - big endian. That is because the only little endian configuration we - support is ppc64le which is 64-bit only. + a 64-bit kernel then we only want a 32-bit VDSO if we're also enabling + COMPAT. choice prompt "Endianness selection" diff --git a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c index 15437abe1f6d..b95c3380d2b5 100644 --- a/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c +++ b/arch/powerpc/platforms/embedded6xx/mpc7448_hpc2.c @@ -147,7 +147,8 @@ static void __noreturn mpc7448_hpc2_restart(char *cmd) local_irq_disable(); /* Set exception prefix high - to the firmware */ - _nmask_and_or_msr(0, MSR_IP); + mtmsr(mfmsr() | MSR_IP); + isync(); for (;;) ; /* Spin until reset happens */ } diff --git a/arch/powerpc/platforms/embedded6xx/storcenter.c b/arch/powerpc/platforms/embedded6xx/storcenter.c index ed1914dd34bb..e346ddcef45e 100644 --- a/arch/powerpc/platforms/embedded6xx/storcenter.c +++ b/arch/powerpc/platforms/embedded6xx/storcenter.c @@ -101,7 +101,8 @@ static void __noreturn storcenter_restart(char *cmd) local_irq_disable(); /* Set exception prefix high - to the firmware */ - _nmask_and_or_msr(0, MSR_IP); + mtmsr(mfmsr() | MSR_IP); + isync(); /* Wait for reset to happen */ for (;;) ; diff --git a/arch/powerpc/platforms/powermac/pmac.h b/arch/powerpc/platforms/powermac/pmac.h index 16a52afdb76e..0d715db434dc 100644 --- a/arch/powerpc/platforms/powermac/pmac.h +++ b/arch/powerpc/platforms/powermac/pmac.h @@ -34,7 +34,7 @@ extern void pmac_check_ht_link(void); extern void pmac_setup_smp(void); extern int psurge_secondary_virq; -extern void low_cpu_die(void) __attribute__((noreturn)); +extern void low_cpu_offline_self(void) __attribute__((noreturn)); extern int pmac_nvram_init(void); extern void pmac_pic_init(void); diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index f002b0fa69b8..2e2cc0c75d87 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -284,7 +284,7 @@ static void __init pmac_setup_arch(void) /* 604, G3, G4 etc. */ loops_per_jiffy = *fp / HZ; else - /* 601, 603, etc. */ + /* 603, etc. */ loops_per_jiffy = *fp / (2 * HZ); of_node_put(cpu); break; diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index f9a680fdd9c4..7e0f8ba6e54a 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -201,8 +201,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS) addi r3,r3,sleep_storage@l stw r5,0(r3) - .globl low_cpu_die -low_cpu_die: + .globl low_cpu_offline_self +low_cpu_offline_self: /* Flush & disable all caches */ bl flush_disable_caches @@ -244,7 +244,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_SPEC7450) mtmsr r2 isync b 1b -_ASM_NOKPROBE_SYMBOL(low_cpu_die) +_ASM_NOKPROBE_SYMBOL(low_cpu_offline_self) /* * Here is the resume code. */ @@ -294,14 +294,7 @@ grackle_wake_up: * we do any r1 memory access as we are not sure they * are in a sane state above the first 256Mb region */ - li r0,16 /* load up segment register values */ - mtctr r0 /* for context 0 */ - lis r3,0x2000 /* Ku = 1, VSID = 0 */ - li r4,0 -3: mtsrin r3,r4 - addi r3,r3,0x111 /* increment VSID */ - addis r4,r4,0x1000 /* address of next segment */ - bdnz 3b + bl load_segment_registers sync isync diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c index eb23264910e1..74ebe664b016 100644 --- a/arch/powerpc/platforms/powermac/smp.c +++ b/arch/powerpc/platforms/powermac/smp.c @@ -270,10 +270,6 @@ static void __init smp_psurge_probe(void) int i, ncpus; struct device_node *dn; - /* We don't do SMP on the PPC601 -- paulus */ - if (PVR_VER(mfspr(SPRN_PVR)) == 1) - return; - /* * The powersurge cpu board can be used in the generation * of powermacs that have a socket for an upgradeable cpu card, @@ -920,7 +916,7 @@ static int smp_core99_cpu_disable(void) #ifdef CONFIG_PPC32 -static void pmac_cpu_die(void) +static void pmac_cpu_offline_self(void) { int cpu = smp_processor_id(); @@ -930,12 +926,12 @@ static void pmac_cpu_die(void) generic_set_cpu_dead(cpu); smp_wmb(); mb(); - low_cpu_die(); + low_cpu_offline_self(); } #else /* CONFIG_PPC32 */ -static void pmac_cpu_die(void) +static void pmac_cpu_offline_self(void) { int cpu = smp_processor_id(); @@ -1020,7 +1016,7 @@ void __init pmac_setup_smp(void) #endif /* CONFIG_PPC_PMAC32_PSURGE */ #ifdef CONFIG_HOTPLUG_CPU - ppc_md.cpu_die = pmac_cpu_die; + smp_ops->cpu_offline_self = pmac_cpu_offline_self; #endif } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 9af8c3b98853..89e22c460ebf 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -38,60 +38,12 @@ static int eeh_event_irq = -EINVAL; -void pnv_pcibios_bus_add_device(struct pci_dev *pdev) +static void pnv_pcibios_bus_add_device(struct pci_dev *pdev) { dev_dbg(&pdev->dev, "EEH: Setting up device\n"); eeh_probe_device(pdev); } -static int pnv_eeh_init(void) -{ - struct pci_controller *hose; - struct pnv_phb *phb; - int max_diag_size = PNV_PCI_DIAG_BUF_SIZE; - - if (!firmware_has_feature(FW_FEATURE_OPAL)) { - pr_warn("%s: OPAL is required !\n", - __func__); - return -EINVAL; - } - - /* Set probe mode */ - eeh_add_flag(EEH_PROBE_MODE_DEV); - - /* - * P7IOC blocks PCI config access to frozen PE, but PHB3 - * doesn't do that. So we have to selectively enable I/O - * prior to collecting error log. - */ - list_for_each_entry(hose, &hose_list, list_node) { - phb = hose->private_data; - - if (phb->model == PNV_PHB_MODEL_P7IOC) - eeh_add_flag(EEH_ENABLE_IO_FOR_LOG); - - if (phb->diag_data_size > max_diag_size) - max_diag_size = phb->diag_data_size; - - /* - * PE#0 should be regarded as valid by EEH core - * if it's not the reserved one. Currently, we - * have the reserved PE#255 and PE#127 for PHB3 - * and P7IOC separately. So we should regard - * PE#0 as valid for PHB3 and P7IOC. - */ - if (phb->ioda.reserved_pe_idx != 0) - eeh_add_flag(EEH_VALID_PE_ZERO); - - break; - } - - eeh_set_pe_aux_size(max_diag_size); - ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device; - - return 0; -} - static irqreturn_t pnv_eeh_event(int irq, void *data) { /* @@ -135,7 +87,7 @@ static ssize_t pnv_eeh_ei_write(struct file *filp, return -EINVAL; /* Retrieve PE */ - pe = eeh_pe_get(hose, pe_no, 0); + pe = eeh_pe_get(hose, pe_no); if (!pe) return -ENODEV; @@ -190,7 +142,7 @@ PNV_EEH_DBGFS_ENTRY(inbB, 0xE10); #endif /* CONFIG_DEBUG_FS */ -void pnv_eeh_enable_phbs(void) +static void pnv_eeh_enable_phbs(void) { struct pci_controller *hose; struct pnv_phb *phb; @@ -354,7 +306,7 @@ static struct eeh_pe *pnv_eeh_get_upstream_pe(struct pci_dev *pdev) if (parent) { struct pnv_ioda_pe *ioda_pe = pnv_ioda_get_pe(parent); - return eeh_pe_get(phb->hose, ioda_pe->pe_number, 0); + return eeh_pe_get(phb->hose, ioda_pe->pe_number); } return NULL; @@ -1406,7 +1358,7 @@ static int pnv_eeh_get_pe(struct pci_controller *hose, } /* Find the PE according to PE# */ - dev_pe = eeh_pe_get(hose, pe_no, 0); + dev_pe = eeh_pe_get(hose, pe_no); if (!dev_pe) return -EEXIST; @@ -1674,7 +1626,6 @@ static int pnv_eeh_restore_config(struct eeh_dev *edev) static struct eeh_ops pnv_eeh_ops = { .name = "powernv", - .init = pnv_eeh_init, .probe = pnv_eeh_probe, .set_option = pnv_eeh_set_option, .get_state = pnv_eeh_get_state, @@ -1715,9 +1666,44 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pnv_pci_fixup_vf_mps); */ static int __init eeh_powernv_init(void) { + int max_diag_size = PNV_PCI_DIAG_BUF_SIZE; + struct pci_controller *hose; + struct pnv_phb *phb; int ret = -EINVAL; - ret = eeh_ops_register(&pnv_eeh_ops); + if (!firmware_has_feature(FW_FEATURE_OPAL)) { + pr_warn("%s: OPAL is required !\n", __func__); + return -EINVAL; + } + + /* Set probe mode */ + eeh_add_flag(EEH_PROBE_MODE_DEV); + + /* + * P7IOC blocks PCI config access to frozen PE, but PHB3 + * doesn't do that. So we have to selectively enable I/O + * prior to collecting error log. + */ + list_for_each_entry(hose, &hose_list, list_node) { + phb = hose->private_data; + + if (phb->model == PNV_PHB_MODEL_P7IOC) + eeh_add_flag(EEH_ENABLE_IO_FOR_LOG); + + if (phb->diag_data_size > max_diag_size) + max_diag_size = phb->diag_data_size; + + break; + } + + /* + * eeh_init() allocates the eeh_pe and its aux data buf so the + * size needs to be set before calling eeh_init(). + */ + eeh_set_pe_aux_size(max_diag_size); + ppc_md.pcibios_bus_add_device = pnv_pcibios_bus_add_device; + + ret = eeh_init(&pnv_eeh_ops); if (!ret) pr_info("EEH: PowerNV platform initialized\n"); else @@ -1725,4 +1711,4 @@ static int __init eeh_powernv_init(void) return ret; } -machine_early_initcall(powernv, eeh_powernv_init); +machine_arch_initcall(powernv, eeh_powernv_init); diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c index 345ab062b21a..1ed7c5286487 100644 --- a/arch/powerpc/platforms/powernv/idle.c +++ b/arch/powerpc/platforms/powernv/idle.c @@ -565,7 +565,7 @@ void power7_idle_type(unsigned long type) irq_set_pending_from_srr1(srr1); } -void power7_idle(void) +static void power7_idle(void) { if (!powersave_nap) return; @@ -659,20 +659,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mmcr0 = mfspr(SPRN_MMCR0); } - if (cpu_has_feature(CPU_FTR_ARCH_31)) { - /* - * POWER10 uses MMCRA (BHRBRD) as BHRB disable bit. - * If the user hasn't asked for the BHRB to be - * written, the value of MMCRA[BHRBRD] is 1. - * On wakeup from stop, MMCRA[BHRBD] will be 0, - * since it is previleged resource and will be lost. - * Thus, if we do not save and restore the MMCRA[BHRBD], - * hardware will be needlessly writing to the BHRB - * in problem mode. - */ - mmcra = mfspr(SPRN_MMCRA); - } - if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) { sprs.lpcr = mfspr(SPRN_LPCR); sprs.hfscr = mfspr(SPRN_HFSCR); @@ -735,10 +721,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on) mtspr(SPRN_MMCR0, mmcr0); } - /* Reload MMCRA to restore BHRB disable bit for POWER10 */ - if (cpu_has_feature(CPU_FTR_ARCH_31)) - mtspr(SPRN_MMCRA, mmcra); - /* * DD2.2 and earlier need to set then clear bit 60 in MMCRA * to ensure the PMU starts running. @@ -823,73 +805,6 @@ out: return srr1; } -#ifdef CONFIG_HOTPLUG_CPU -static unsigned long power9_offline_stop(unsigned long psscr) -{ - unsigned long srr1; - -#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, true); - __ppc64_runlatch_on(); -#else - /* - * Tell KVM we're entering idle. - * This does not have to be done in real mode because the P9 MMU - * is independent per-thread. Some steppings share radix/hash mode - * between threads, but in that case KVM has a barrier sync in real - * mode before and after switching between radix and hash. - * - * kvm_start_guest must still be called in real mode though, hence - * the false argument. - */ - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE; - - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, false); - __ppc64_runlatch_on(); - - local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL; - /* Order setting hwthread_state vs. testing hwthread_req */ - smp_mb(); - if (local_paca->kvm_hstate.hwthread_req) - srr1 = idle_kvm_start_guest(srr1); - mtmsr(MSR_KERNEL); -#endif - - return srr1; -} -#endif - -void power9_idle_type(unsigned long stop_psscr_val, - unsigned long stop_psscr_mask) -{ - unsigned long psscr; - unsigned long srr1; - - if (!prep_irq_for_idle_irqsoff()) - return; - - psscr = mfspr(SPRN_PSSCR); - psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val; - - __ppc64_runlatch_off(); - srr1 = power9_idle_stop(psscr, true); - __ppc64_runlatch_on(); - - fini_irq_for_idle_irqsoff(); - - irq_set_pending_from_srr1(srr1); -} - -/* - * Used for ppc_md.power_save which needs a function with no parameters - */ -void power9_idle(void) -{ - power9_idle_type(pnv_default_stop_val, pnv_default_stop_mask); -} - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE /* * This is used in working around bugs in thread reconfiguration @@ -962,6 +877,198 @@ void pnv_power9_force_smt4_release(void) EXPORT_SYMBOL_GPL(pnv_power9_force_smt4_release); #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ +struct p10_sprs { + /* + * SPRs that get lost in shallow states: + * + * P10 loses CR, LR, CTR, FPSCR, VSCR, XER, TAR, SPRG2, and HSPRG1 + * isa300 idle routines restore CR, LR. + * CTR is volatile + * idle thread doesn't use FP or VEC + * kernel doesn't use TAR + * HSPRG1 is only live in HV interrupt entry + * SPRG2 is only live in KVM guests, KVM handles it. + */ +}; + +static unsigned long power10_idle_stop(unsigned long psscr, bool mmu_on) +{ + int cpu = raw_smp_processor_id(); + int first = cpu_first_thread_sibling(cpu); + unsigned long *state = &paca_ptrs[first]->idle_state; + unsigned long core_thread_mask = (1UL << threads_per_core) - 1; + unsigned long srr1; + unsigned long pls; +// struct p10_sprs sprs = {}; /* avoid false used-uninitialised */ + bool sprs_saved = false; + + if (!(psscr & (PSSCR_EC|PSSCR_ESL))) { + /* EC=ESL=0 case */ + + BUG_ON(!mmu_on); + + /* + * Wake synchronously. SRESET via xscom may still cause + * a 0x100 powersave wakeup with SRR1 reason! + */ + srr1 = isa300_idle_stop_noloss(psscr); /* go idle */ + if (likely(!srr1)) + return 0; + + /* + * Registers not saved, can't recover! + * This would be a hardware bug + */ + BUG_ON((srr1 & SRR1_WAKESTATE) != SRR1_WS_NOLOSS); + + goto out; + } + + /* EC=ESL=1 case */ + if ((psscr & PSSCR_RL_MASK) >= deep_spr_loss_state) { + /* XXX: save SPRs for deep state loss here. */ + + sprs_saved = true; + + atomic_start_thread_idle(); + } + + srr1 = isa300_idle_stop_mayloss(psscr); /* go idle */ + + psscr = mfspr(SPRN_PSSCR); + + WARN_ON_ONCE(!srr1); + WARN_ON_ONCE(mfmsr() & (MSR_IR|MSR_DR)); + + if (unlikely((srr1 & SRR1_WAKEMASK_P8) == SRR1_WAKEHMI)) + hmi_exception_realmode(NULL); + + /* + * On POWER10, SRR1 bits do not match exactly as expected. + * SRR1_WS_GPRLOSS (10b) can also result in SPR loss, so + * just always test PSSCR for SPR/TB state loss. + */ + pls = (psscr & PSSCR_PLS) >> PSSCR_PLS_SHIFT; + if (likely(pls < deep_spr_loss_state)) { + if (sprs_saved) + atomic_stop_thread_idle(); + goto out; + } + + /* HV state loss */ + BUG_ON(!sprs_saved); + + atomic_lock_thread_idle(); + + if ((*state & core_thread_mask) != 0) + goto core_woken; + + /* XXX: restore per-core SPRs here */ + + if (pls >= pnv_first_tb_loss_level) { + /* TB loss */ + if (opal_resync_timebase() != OPAL_SUCCESS) + BUG(); + } + + /* + * isync after restoring shared SPRs and before unlocking. Unlock + * only contains hwsync which does not necessarily do the right + * thing for SPRs. + */ + isync(); + +core_woken: + atomic_unlock_and_stop_thread_idle(); + + /* XXX: restore per-thread SPRs here */ + + if (!radix_enabled()) + __slb_restore_bolted_realmode(); + +out: + if (mmu_on) + mtmsr(MSR_KERNEL); + + return srr1; +} + +#ifdef CONFIG_HOTPLUG_CPU +static unsigned long arch300_offline_stop(unsigned long psscr) +{ + unsigned long srr1; + +#ifndef CONFIG_KVM_BOOK3S_HV_POSSIBLE + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, true); + else + srr1 = power9_idle_stop(psscr, true); + __ppc64_runlatch_on(); +#else + /* + * Tell KVM we're entering idle. + * This does not have to be done in real mode because the P9 MMU + * is independent per-thread. Some steppings share radix/hash mode + * between threads, but in that case KVM has a barrier sync in real + * mode before and after switching between radix and hash. + * + * kvm_start_guest must still be called in real mode though, hence + * the false argument. + */ + local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_IDLE; + + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, false); + else + srr1 = power9_idle_stop(psscr, false); + __ppc64_runlatch_on(); + + local_paca->kvm_hstate.hwthread_state = KVM_HWTHREAD_IN_KERNEL; + /* Order setting hwthread_state vs. testing hwthread_req */ + smp_mb(); + if (local_paca->kvm_hstate.hwthread_req) + srr1 = idle_kvm_start_guest(srr1); + mtmsr(MSR_KERNEL); +#endif + + return srr1; +} +#endif + +void arch300_idle_type(unsigned long stop_psscr_val, + unsigned long stop_psscr_mask) +{ + unsigned long psscr; + unsigned long srr1; + + if (!prep_irq_for_idle_irqsoff()) + return; + + psscr = mfspr(SPRN_PSSCR); + psscr = (psscr & ~stop_psscr_mask) | stop_psscr_val; + + __ppc64_runlatch_off(); + if (cpu_has_feature(CPU_FTR_ARCH_31)) + srr1 = power10_idle_stop(psscr, true); + else + srr1 = power9_idle_stop(psscr, true); + __ppc64_runlatch_on(); + + fini_irq_for_idle_irqsoff(); + + irq_set_pending_from_srr1(srr1); +} + +/* + * Used for ppc_md.power_save which needs a function with no parameters + */ +static void arch300_idle(void) +{ + arch300_idle_type(pnv_default_stop_val, pnv_default_stop_mask); +} + #ifdef CONFIG_HOTPLUG_CPU void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val) @@ -995,7 +1102,7 @@ unsigned long pnv_cpu_offline(unsigned int cpu) psscr = mfspr(SPRN_PSSCR); psscr = (psscr & ~pnv_deepest_stop_psscr_mask) | pnv_deepest_stop_psscr_val; - srr1 = power9_offline_stop(psscr); + srr1 = arch300_offline_stop(psscr); } else if (cpu_has_feature(CPU_FTR_ARCH_206) && power7_offline_type) { srr1 = power7_offline(); } else { @@ -1093,11 +1200,15 @@ int validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags) * @dt_idle_states: Number of idle state entries * Returns 0 on success */ -static void __init pnv_power9_idle_init(void) +static void __init pnv_arch300_idle_init(void) { u64 max_residency_ns = 0; int i; + /* stop is not really architected, we only have p9,p10 drivers */ + if (!pvr_version_is(PVR_POWER10) && !pvr_version_is(PVR_POWER9)) + return; + /* * pnv_deepest_stop_{val,mask} should be set to values corresponding to * the deepest stop state. @@ -1112,6 +1223,11 @@ static void __init pnv_power9_idle_init(void) struct pnv_idle_states_t *state = &pnv_idle_states[i]; u64 psscr_rl = state->psscr_val & PSSCR_RL_MASK; + /* No deep loss driver implemented for POWER10 yet */ + if (pvr_version_is(PVR_POWER10) && + state->flags & (OPAL_PM_TIMEBASE_STOP|OPAL_PM_LOSE_FULL_CONTEXT)) + continue; + if ((state->flags & OPAL_PM_TIMEBASE_STOP) && (pnv_first_tb_loss_level > psscr_rl)) pnv_first_tb_loss_level = psscr_rl; @@ -1162,7 +1278,7 @@ static void __init pnv_power9_idle_init(void) if (unlikely(!default_stop_found)) { pr_warn("cpuidle-powernv: No suitable default stop state found. Disabling platform idle.\n"); } else { - ppc_md.power_save = power9_idle; + ppc_md.power_save = arch300_idle; pr_info("cpuidle-powernv: Default stop: psscr = 0x%016llx,mask=0x%016llx\n", pnv_default_stop_val, pnv_default_stop_mask); } @@ -1224,7 +1340,7 @@ static void __init pnv_probe_idle_states(void) } if (cpu_has_feature(CPU_FTR_ARCH_300)) - pnv_power9_idle_init(); + pnv_arch300_idle_init(); for (i = 0; i < nr_pnv_idle_states; i++) supported_cpuidle_states |= pnv_idle_states[i].flags; @@ -1295,7 +1411,7 @@ static int pnv_parse_cpuidle_dt(void) for (i = 0; i < nr_idle_states; i++) pnv_idle_states[i].residency_ns = temp_u32[i]; - /* For power9 */ + /* For power9 and later */ if (cpu_has_feature(CPU_FTR_ARCH_300)) { /* Read pm_crtl_val */ if (of_property_read_u64_array(np, "ibm,cpu-idle-state-psscr", @@ -1358,8 +1474,8 @@ static int __init pnv_init_idle_states(void) if (!cpu_has_feature(CPU_FTR_ARCH_300)) { /* P7/P8 nap */ p->thread_idle_state = PNV_THREAD_RUNNING; - } else { - /* P9 stop */ + } else if (pvr_version_is(PVR_POWER9)) { + /* P9 stop workarounds */ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE p->requested_psscr = 0; atomic_set(&p->dont_stop, 0); diff --git a/arch/powerpc/platforms/powernv/ocxl.c b/arch/powerpc/platforms/powernv/ocxl.c index 8c65aacda9c8..ecdad219d704 100644 --- a/arch/powerpc/platforms/powernv/ocxl.c +++ b/arch/powerpc/platforms/powernv/ocxl.c @@ -2,7 +2,6 @@ // Copyright 2017 IBM Corp. #include <asm/pnv-ocxl.h> #include <asm/opal.h> -#include <asm/xive.h> #include <misc/ocxl-config.h> #include "pci.h" @@ -484,32 +483,3 @@ int pnv_ocxl_spa_remove_pe_from_cache(void *platform_data, int pe_handle) return rc; } EXPORT_SYMBOL_GPL(pnv_ocxl_spa_remove_pe_from_cache); - -int pnv_ocxl_alloc_xive_irq(u32 *irq, u64 *trigger_addr) -{ - __be64 flags, trigger_page; - s64 rc; - u32 hwirq; - - hwirq = xive_native_alloc_irq(); - if (!hwirq) - return -ENOENT; - - rc = opal_xive_get_irq_info(hwirq, &flags, NULL, &trigger_page, NULL, - NULL); - if (rc || !trigger_page) { - xive_native_free_irq(hwirq); - return -ENOENT; - } - *irq = hwirq; - *trigger_addr = be64_to_cpu(trigger_page); - return 0; - -} -EXPORT_SYMBOL_GPL(pnv_ocxl_alloc_xive_irq); - -void pnv_ocxl_free_xive_irq(u32 irq) -{ - xive_native_free_irq(irq); -} -EXPORT_SYMBOL_GPL(pnv_ocxl_free_xive_irq); diff --git a/arch/powerpc/platforms/powernv/opal-core.c b/arch/powerpc/platforms/powernv/opal-core.c index 6dba3b62269f..23571f0b555a 100644 --- a/arch/powerpc/platforms/powernv/opal-core.c +++ b/arch/powerpc/platforms/powernv/opal-core.c @@ -510,7 +510,7 @@ static void __init opalcore_config_init(void) idx = be32_to_cpu(opalc_metadata->region_cnt); if (idx > MAX_PT_LOAD_CNT) { pr_warn("WARNING: OPAL regions count (%d) adjusted to limit (%d)", - MAX_PT_LOAD_CNT, idx); + idx, MAX_PT_LOAD_CNT); idx = MAX_PT_LOAD_CNT; } for (i = 0; i < idx; i++) { diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c index 62ef7ad995da..5e33b1fc67c2 100644 --- a/arch/powerpc/platforms/powernv/opal-elog.c +++ b/arch/powerpc/platforms/powernv/opal-elog.c @@ -179,14 +179,14 @@ static ssize_t raw_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) +static void create_elog_obj(uint64_t id, size_t size, uint64_t type) { struct elog_obj *elog; int rc; elog = kzalloc(sizeof(*elog), GFP_KERNEL); if (!elog) - return NULL; + return; elog->kobj.kset = elog_kset; @@ -219,18 +219,37 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type) rc = kobject_add(&elog->kobj, NULL, "0x%llx", id); if (rc) { kobject_put(&elog->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this elog is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the elog before kobject_uevent() is called. If that + * happens then there is a potential race between + * elog_ack_store->kobject_put() and kobject_uevent() which leads to a + * use-after-free of a kernfs object resulting in a kernel crash. + * + * To avoid that, we need to take a reference on behalf of the bin file, + * so that our reference remains valid while we call kobject_uevent(). + * We then drop our reference before exiting the function, leaving the + * bin file to drop the last reference (if it hasn't already). + */ + + /* Take a reference for the bin file */ + kobject_get(&elog->kobj); rc = sysfs_create_bin_file(&elog->kobj, &elog->raw_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&elog->kobj, KOBJ_ADD); + } else { + /* Drop the reference taken for the bin file */ kobject_put(&elog->kobj); - return NULL; } - kobject_uevent(&elog->kobj, KOBJ_ADD); + /* Drop our reference */ + kobject_put(&elog->kobj); - return elog; + return; } static irqreturn_t elog_event(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/opal-msglog.c b/arch/powerpc/platforms/powernv/opal-msglog.c index d26da19a611f..d3b6e135c18b 100644 --- a/arch/powerpc/platforms/powernv/opal-msglog.c +++ b/arch/powerpc/platforms/powernv/opal-msglog.c @@ -12,6 +12,8 @@ #include <linux/types.h> #include <asm/barrier.h> +#include "powernv.h" + /* OPAL in-memory console. Defined in OPAL source at core/console.c */ struct memcons { __be64 magic; diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c index 45f4223a790f..deddaebf8c14 100644 --- a/arch/powerpc/platforms/powernv/opal-prd.c +++ b/arch/powerpc/platforms/powernv/opal-prd.c @@ -24,7 +24,7 @@ #include <linux/uaccess.h> -/** +/* * The msg member must be at the end of the struct, as it's followed by the * message data. */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 023a4f987bb2..2b4ceb5e6ce4 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -894,7 +894,6 @@ int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { - struct pci_dev *parent; uint8_t bcomp, dcomp, fcomp; long rc, rid_end, rid; @@ -904,7 +903,6 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) dcomp = OPAL_IGNORE_RID_DEVICE_NUMBER; fcomp = OPAL_IGNORE_RID_FUNCTION_NUMBER; - parent = pe->pbus->self; if (pe->flags & PNV_IODA_PE_BUS_ALL) count = resource_size(&pe->pbus->busn_res); else @@ -925,12 +923,6 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) } rid_end = pe->rid + (count << 8); } else { -#ifdef CONFIG_PCI_IOV - if (pe->flags & PNV_IODA_PE_VF) - parent = pe->parent_dev; - else -#endif /* CONFIG_PCI_IOV */ - parent = pe->pdev->bus->self; bcomp = OpalPciBusAll; dcomp = OPAL_COMPARE_RID_DEVICE_NUMBER; fcomp = OPAL_COMPARE_RID_FUNCTION_NUMBER; diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h index 1aa51c4fa904..11df4e16a1cc 100644 --- a/arch/powerpc/platforms/powernv/powernv.h +++ b/arch/powerpc/platforms/powernv/powernv.h @@ -2,6 +2,13 @@ #ifndef _POWERNV_H #define _POWERNV_H +/* + * There's various hacks scattered throughout the generic powerpc arch code + * that needs to call into powernv platform stuff. The prototypes for those + * functions are in asm/powernv.h + */ +#include <asm/powernv.h> + #ifdef CONFIG_SMP extern void pnv_smp_init(void); #else diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c index 8035caf6e297..72c25295c1c2 100644 --- a/arch/powerpc/platforms/powernv/rng.c +++ b/arch/powerpc/platforms/powernv/rng.c @@ -65,7 +65,7 @@ int powernv_get_random_real_mode(unsigned long *v) return 1; } -int powernv_get_random_darn(unsigned long *v) +static int powernv_get_random_darn(unsigned long *v) { unsigned long val; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 7fcb88623081..9acaa0f131b9 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -130,6 +130,28 @@ static void pnv_setup_rfi_flush(void) setup_count_cache_flush(); } +static void __init pnv_check_guarded_cores(void) +{ + struct device_node *dn; + int bad_count = 0; + + for_each_node_by_type(dn, "cpu") { + if (of_property_match_string(dn, "status", "bad") >= 0) + bad_count++; + }; + + if (bad_count) { + printk(" _ _______________\n"); + pr_cont(" | | / \\\n"); + pr_cont(" | | | WARNING! |\n"); + pr_cont(" | | | |\n"); + pr_cont(" | | | It looks like |\n"); + pr_cont(" |_| | you have %*d |\n", 3, bad_count); + pr_cont(" _ | guarded cores |\n"); + pr_cont(" (_) \\_______________/\n"); + } +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -150,6 +172,8 @@ static void __init pnv_setup_arch(void) /* Enable NAP mode */ powersave_nap = 1; + pnv_check_guarded_cores(); + /* XXX PMCS */ } diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index b2ba3e95bda7..54c4ba45c7ce 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -43,7 +43,7 @@ #include <asm/udbg.h> #define DBG(fmt...) udbg_printf(fmt) #else -#define DBG(fmt...) +#define DBG(fmt...) do { } while (0) #endif static void pnv_smp_setup_cpu(int cpu) @@ -158,7 +158,7 @@ static void pnv_flush_interrupts(void) } } -static void pnv_smp_cpu_kill_self(void) +static void pnv_cpu_offline_self(void) { unsigned long srr1, unexpected_mask, wmask; unsigned int cpu; @@ -417,6 +417,7 @@ static struct smp_ops_t pnv_smp_ops = { #ifdef CONFIG_HOTPLUG_CPU .cpu_disable = pnv_smp_cpu_disable, .cpu_die = generic_cpu_die, + .cpu_offline_self = pnv_cpu_offline_self, #endif /* CONFIG_HOTPLUG_CPU */ }; @@ -430,7 +431,6 @@ void __init pnv_smp_init(void) smp_ops = &pnv_smp_ops; #ifdef CONFIG_HOTPLUG_CPU - ppc_md.cpu_die = pnv_smp_cpu_kill_self; #ifdef CONFIG_KEXEC_CORE crash_wake_offline = 1; #endif diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c index 6434f9cb5aed..5f5fe63a3d1c 100644 --- a/arch/powerpc/platforms/powernv/vas-window.c +++ b/arch/powerpc/platforms/powernv/vas-window.c @@ -186,7 +186,7 @@ static void unmap_winctx_mmio_bars(struct vas_window *window) * OS/User Window Context (UWC) MMIO Base Address Region for the given window. * Map these bus addresses and save the mapped kernel addresses in @window. */ -int map_winctx_mmio_bars(struct vas_window *window) +static int map_winctx_mmio_bars(struct vas_window *window) { int len; u64 start; @@ -214,7 +214,7 @@ int map_winctx_mmio_bars(struct vas_window *window) * registers are not sequential. And, we can only write to offsets * with valid registers. */ -void reset_window_regs(struct vas_window *window) +static void reset_window_regs(struct vas_window *window) { write_hvwc_reg(window, VREG(LPID), 0ULL); write_hvwc_reg(window, VREG(PID), 0ULL); @@ -357,7 +357,8 @@ static void init_rsvd_tx_buf_count(struct vas_window *txwin, * as a one-time task? That could work for NX but what about other * receivers? Let the receivers tell us the rx-fifo buffers for now. */ -int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx) +static void init_winctx_regs(struct vas_window *window, + struct vas_winctx *winctx) { u64 val; int fifo_size; @@ -499,8 +500,6 @@ int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx) val = SET_FIELD(VAS_WINCTL_NX_WIN, val, winctx->nx_win); val = SET_FIELD(VAS_WINCTL_OPEN, val, 1); write_hvwc_reg(window, VREG(WINCTL), val); - - return 0; } static void vas_release_window_id(struct ida *ida, int winid) diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c index 1193c294b8d0..0c252478e556 100644 --- a/arch/powerpc/platforms/ps3/spu.c +++ b/arch/powerpc/platforms/ps3/spu.c @@ -448,7 +448,7 @@ static void ps3_disable_spu(struct spu_context *ctx) ctx->ops->runcntl_stop(ctx); } -const struct spu_management_ops spu_management_ps3_ops = { +static const struct spu_management_ops spu_management_ps3_ops = { .enumerate_spus = ps3_enumerate_spus, .create_spu = ps3_create_spu, .destroy_spu = ps3_destroy_spu, @@ -589,7 +589,7 @@ static u64 resource_allocation_enable_get(struct spu *spu) return 0; /* No support. */ } -const struct spu_priv1_ops spu_priv1_ps3_ops = { +static const struct spu_priv1_ops spu_priv1_ps3_ops = { .int_mask_and = int_mask_and, .int_mask_or = int_mask_or, .int_mask_set = int_mask_set, diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index cb2d9a970b7b..cf024fa37bda 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -33,8 +33,6 @@ #include <asm/ppc-pci.h> #include <asm/rtas.h> -static int pseries_eeh_get_pe_addr(struct pci_dn *pdn); - /* RTAS tokens */ static int ibm_set_eeh_option; static int ibm_set_slot_reset; @@ -86,42 +84,43 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev) /** - * pseries_eeh_get_config_addr - Retrieve config address + * pseries_eeh_get_pe_config_addr - Find the pe_config_addr for a device + * @pdn: pci_dn of the input device + * + * The EEH RTAS calls use a tuple consisting of: (buid_hi, buid_lo, + * pe_config_addr) as a handle to a given PE. This function finds the + * pe_config_addr based on the device's config addr. * - * Retrieve the assocated config address. Actually, there're 2 RTAS - * function calls dedicated for the purpose. We need implement - * it through the new function and then the old one. Besides, - * you should make sure the config address is figured out from - * FDT node before calling the function. + * Keep in mind that the pe_config_addr *might* be numerically identical to the + * device's config addr, but the two are conceptually distinct. * - * It's notable that zero'ed return value means invalid PE config - * address. + * Returns the pe_config_addr, or a negative error code. */ -static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_addr) +static int pseries_eeh_get_pe_config_addr(struct pci_dn *pdn) { - int ret = 0; - int rets[3]; + int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); + struct pci_controller *phb = pdn->phb; + int ret, rets[3]; if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { /* - * First of all, we need to make sure there has one PE - * associated with the device. Otherwise, PE address is - * meaningless. + * First of all, use function 1 to determine if this device is + * part of a PE or not. ret[0] being zero indicates it's not. */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, config_addr, BUID_HI(phb->buid), BUID_LO(phb->buid), 1); if (ret || (rets[0] == 0)) - return 0; + return -ENOENT; - /* Retrieve the associated PE config address */ + /* Retrieve the associated PE config address with function 0 */ ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, config_addr, BUID_HI(phb->buid), BUID_LO(phb->buid), 0); if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", __func__, phb->global_number, config_addr); - return 0; + return -ENXIO; } return rets[0]; @@ -134,13 +133,20 @@ static int pseries_eeh_get_config_addr(struct pci_controller *phb, int config_ad if (ret) { pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", __func__, phb->global_number, config_addr); - return 0; + return -ENXIO; } return rets[0]; } - return ret; + /* + * PAPR does describe a process for finding the pe_config_addr that was + * used before the ibm,get-config-addr-info calls were added. However, + * I haven't found *any* systems that don't have that RTAS call + * implemented. If you happen to find one that needs the old DT based + * process, patches are welcome! + */ + return -ENOENT; } /** @@ -161,8 +167,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in BUID_LO(phb->buid), option); /* If fundamental-reset not supported, try hot-reset */ - if (option == EEH_RESET_FUNDAMENTAL && - ret == -8) { + if (option == EEH_RESET_FUNDAMENTAL && ret == -8) { option = EEH_RESET_HOT; ret = rtas_call(ibm_set_slot_reset, 4, 1, NULL, config_addr, BUID_HI(phb->buid), @@ -170,8 +175,7 @@ static int pseries_eeh_phb_reset(struct pci_controller *phb, int config_addr, in } /* We need reset hold or settlement delay */ - if (option == EEH_RESET_FUNDAMENTAL || - option == EEH_RESET_HOT) + if (option == EEH_RESET_FUNDAMENTAL || option == EEH_RESET_HOT) msleep(EEH_PE_RST_HOLD_TIME); else msleep(EEH_PE_RST_SETTLE_TIME); @@ -239,88 +243,6 @@ static unsigned char slot_errbuf[RTAS_ERROR_LOG_MAX]; static DEFINE_SPINLOCK(slot_errbuf_lock); static int eeh_error_buf_size; -/** - * pseries_eeh_init - EEH platform dependent initialization - * - * EEH platform dependent initialization on pseries. - */ -static int pseries_eeh_init(void) -{ - struct pci_controller *phb; - struct pci_dn *pdn; - int addr, config_addr; - - /* figure out EEH RTAS function call tokens */ - ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); - ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); - ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); - ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); - ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); - ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); - ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); - ibm_configure_pe = rtas_token("ibm,configure-pe"); - - /* - * ibm,configure-pe and ibm,configure-bridge have the same semantics, - * however ibm,configure-pe can be faster. If we can't find - * ibm,configure-pe then fall back to using ibm,configure-bridge. - */ - if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) - ibm_configure_pe = rtas_token("ibm,configure-bridge"); - - /* - * Necessary sanity check. We needn't check "get-config-addr-info" - * and its variant since the old firmware probably support address - * of domain/bus/slot/function for EEH RTAS operations. - */ - if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE || - ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE || - (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && - ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || - ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || - ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { - pr_info("EEH functionality not supported\n"); - return -EINVAL; - } - - /* Initialize error log lock and size */ - spin_lock_init(&slot_errbuf_lock); - eeh_error_buf_size = rtas_token("rtas-error-log-max"); - if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { - pr_info("%s: unknown EEH error log size\n", - __func__); - eeh_error_buf_size = 1024; - } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { - pr_info("%s: EEH error log size %d exceeds the maximal %d\n", - __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX); - eeh_error_buf_size = RTAS_ERROR_LOG_MAX; - } - - /* Set EEH probe mode */ - eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); - - /* Set EEH machine dependent code */ - ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; - - if (is_kdump_kernel() || reset_devices) { - pr_info("Issue PHB reset ...\n"); - list_for_each_entry(phb, &hose_list, list_node) { - pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); - addr = (pdn->busno << 16) | (pdn->devfn << 8); - config_addr = pseries_eeh_get_config_addr(phb, addr); - /* invalid PE config addr */ - if (config_addr == 0) - continue; - - pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); - pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); - pseries_eeh_phb_configure_bridge(phb, config_addr); - } - } - - return 0; -} - static int pseries_eeh_cap_start(struct pci_dn *pdn) { u32 status; @@ -439,10 +361,9 @@ static struct eeh_pe *pseries_eeh_pe_get_parent(struct eeh_dev *edev) */ void pseries_eeh_init_edev(struct pci_dn *pdn) { + struct eeh_pe pe, *parent; struct eeh_dev *edev; - struct eeh_pe pe; u32 pcie_flags; - int enable = 0; int ret; if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))) @@ -499,51 +420,38 @@ void pseries_eeh_init_edev(struct pci_dn *pdn) } } - /* Initialize the fake PE */ + /* first up, find the pe_config_addr for the PE containing the device */ + ret = pseries_eeh_get_pe_config_addr(pdn); + if (ret < 0) { + eeh_edev_dbg(edev, "Unable to find pe_config_addr\n"); + goto err; + } + + /* Try enable EEH on the fake PE */ memset(&pe, 0, sizeof(struct eeh_pe)); pe.phb = pdn->phb; - pe.config_addr = (pdn->busno << 16) | (pdn->devfn << 8); + pe.addr = ret; - /* Enable EEH on the device */ eeh_edev_dbg(edev, "Enabling EEH on device\n"); ret = eeh_ops->set_option(&pe, EEH_OPT_ENABLE); if (ret) { eeh_edev_dbg(edev, "EEH failed to enable on device (code %d)\n", ret); - } else { - struct eeh_pe *parent; + goto err; + } - /* Retrieve PE address */ - edev->pe_config_addr = pseries_eeh_get_pe_addr(pdn); - pe.addr = edev->pe_config_addr; + edev->pe_config_addr = pe.addr; - /* Some older systems (Power4) allow the ibm,set-eeh-option - * call to succeed even on nodes where EEH is not supported. - * Verify support explicitly. - */ - ret = eeh_ops->get_state(&pe, NULL); - if (ret > 0 && ret != EEH_STATE_NOT_SUPPORT) - enable = 1; + eeh_add_flag(EEH_ENABLED); - /* - * This device doesn't support EEH, but it may have an - * EEH parent. In this case any error on the device will - * freeze the PE of it's upstream bridge, so added it to - * the upstream PE. - */ - parent = pseries_eeh_pe_get_parent(edev); - if (parent && !enable) - edev->pe_config_addr = parent->addr; + parent = pseries_eeh_pe_get_parent(edev); + eeh_pe_tree_insert(edev, parent); + eeh_save_bars(edev); + eeh_edev_dbg(edev, "EEH enabled for device"); - if (enable || parent) { - eeh_add_flag(EEH_ENABLED); - eeh_pe_tree_insert(edev, parent); - } - eeh_edev_dbg(edev, "EEH is %s on device (code %d)\n", - (enable ? "enabled" : "unsupported"), ret); - } + return; - /* Save memory bars */ - eeh_save_bars(edev); +err: + eeh_edev_dbg(edev, "EEH is unsupported on device (code = %d)\n", ret); } static struct eeh_dev *pseries_eeh_probe(struct pci_dev *pdev) @@ -600,7 +508,6 @@ EXPORT_SYMBOL_GPL(pseries_eeh_init_edev_recursive); static int pseries_eeh_set_option(struct eeh_pe *pe, int option) { int ret = 0; - int config_addr; /* * When we're enabling or disabling EEH functioality on @@ -613,85 +520,23 @@ static int pseries_eeh_set_option(struct eeh_pe *pe, int option) case EEH_OPT_ENABLE: case EEH_OPT_THAW_MMIO: case EEH_OPT_THAW_DMA: - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; break; case EEH_OPT_FREEZE_PE: /* Not support */ return 0; default: - pr_err("%s: Invalid option %d\n", - __func__, option); + pr_err("%s: Invalid option %d\n", __func__, option); return -EINVAL; } ret = rtas_call(ibm_set_eeh_option, 4, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid), option); return ret; } /** - * pseries_eeh_get_pe_addr - Retrieve PE address - * @pe: EEH PE - * - * Retrieve the assocated PE address. Actually, there're 2 RTAS - * function calls dedicated for the purpose. We need implement - * it through the new function and then the old one. Besides, - * you should make sure the config address is figured out from - * FDT node before calling the function. - * - * It's notable that zero'ed return value means invalid PE config - * address. - */ -static int pseries_eeh_get_pe_addr(struct pci_dn *pdn) -{ - int config_addr = rtas_config_addr(pdn->busno, pdn->devfn, 0); - unsigned long buid = pdn->phb->buid; - int ret = 0; - int rets[3]; - - if (ibm_get_config_addr_info2 != RTAS_UNKNOWN_SERVICE) { - /* - * First of all, we need to make sure there has one PE - * associated with the device. Otherwise, PE address is - * meaningless. - */ - ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 1); - if (ret || (rets[0] == 0)) - return 0; - - /* Retrieve the associated PE config address */ - ret = rtas_call(ibm_get_config_addr_info2, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 0); - if (ret) { - pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pdn->phb->global_number, config_addr); - return 0; - } - - return rets[0]; - } - - if (ibm_get_config_addr_info != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_get_config_addr_info, 4, 2, rets, - config_addr, BUID_HI(buid), BUID_LO(buid), 0); - if (ret) { - pr_warn("%s: Failed to get address for PHB#%x-PE#%x\n", - __func__, pdn->phb->global_number, config_addr); - return 0; - } - - return rets[0]; - } - - return ret; -} - -/** * pseries_eeh_get_state - Retrieve PE state * @pe: EEH PE * @delay: suggested time to wait if state is unavailable @@ -706,25 +551,19 @@ static int pseries_eeh_get_pe_addr(struct pci_dn *pdn) */ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) { - int config_addr; int ret; int rets[4]; int result; - /* Figure out PE config address if possible */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - if (ibm_read_slot_reset_state2 != RTAS_UNKNOWN_SERVICE) { ret = rtas_call(ibm_read_slot_reset_state2, 3, 4, rets, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); } else if (ibm_read_slot_reset_state != RTAS_UNKNOWN_SERVICE) { /* Fake PE unavailable info */ rets[2] = 0; ret = rtas_call(ibm_read_slot_reset_state, 3, 3, rets, - config_addr, BUID_HI(pe->phb->buid), + pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); } else { return EEH_STATE_NOT_SUPPORT; @@ -778,14 +617,7 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) */ static int pseries_eeh_reset(struct eeh_pe *pe, int option) { - int config_addr; - - /* Figure out PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - return pseries_eeh_phb_reset(pe->phb, config_addr, option); + return pseries_eeh_phb_reset(pe->phb, pe->addr, option); } /** @@ -801,19 +633,13 @@ static int pseries_eeh_reset(struct eeh_pe *pe, int option) */ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len) { - int config_addr; unsigned long flags; int ret; spin_lock_irqsave(&slot_errbuf_lock, flags); memset(slot_errbuf, 0, eeh_error_buf_size); - /* Figure out the PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, config_addr, + ret = rtas_call(ibm_slot_error_detail, 8, 1, NULL, pe->addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid), virt_to_phys(drv_log), len, virt_to_phys(slot_errbuf), eeh_error_buf_size, @@ -832,14 +658,7 @@ static int pseries_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, u */ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { - int config_addr; - - /* Figure out the PE address */ - config_addr = pe->config_addr; - if (pe->addr) - config_addr = pe->addr; - - return pseries_eeh_phb_configure_bridge(pe->phb, config_addr); + return pseries_eeh_phb_configure_bridge(pe->phb, pe->addr); } /** @@ -954,8 +773,7 @@ static int pseries_notify_resume(struct eeh_dev *edev) if (!edev) return -EEXIST; - if (rtas_token("ibm,open-sriov-allow-unfreeze") - == RTAS_UNKNOWN_SERVICE) + if (rtas_token("ibm,open-sriov-allow-unfreeze") == RTAS_UNKNOWN_SERVICE) return -EINVAL; if (edev->pdev->is_physfn || edev->pdev->is_virtfn) @@ -967,7 +785,6 @@ static int pseries_notify_resume(struct eeh_dev *edev) static struct eeh_ops pseries_eeh_ops = { .name = "pseries", - .init = pseries_eeh_init, .probe = pseries_eeh_probe, .set_option = pseries_eeh_set_option, .get_state = pseries_eeh_get_state, @@ -992,15 +809,84 @@ static struct eeh_ops pseries_eeh_ops = { */ static int __init eeh_pseries_init(void) { - int ret; + struct pci_controller *phb; + struct pci_dn *pdn; + int ret, config_addr; - ret = eeh_ops_register(&pseries_eeh_ops); + /* figure out EEH RTAS function call tokens */ + ibm_set_eeh_option = rtas_token("ibm,set-eeh-option"); + ibm_set_slot_reset = rtas_token("ibm,set-slot-reset"); + ibm_read_slot_reset_state2 = rtas_token("ibm,read-slot-reset-state2"); + ibm_read_slot_reset_state = rtas_token("ibm,read-slot-reset-state"); + ibm_slot_error_detail = rtas_token("ibm,slot-error-detail"); + ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); + ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); + ibm_configure_pe = rtas_token("ibm,configure-pe"); + + /* + * ibm,configure-pe and ibm,configure-bridge have the same semantics, + * however ibm,configure-pe can be faster. If we can't find + * ibm,configure-pe then fall back to using ibm,configure-bridge. + */ + if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) + ibm_configure_pe = rtas_token("ibm,configure-bridge"); + + /* + * Necessary sanity check. We needn't check "get-config-addr-info" + * and its variant since the old firmware probably support address + * of domain/bus/slot/function for EEH RTAS operations. + */ + if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE || + ibm_set_slot_reset == RTAS_UNKNOWN_SERVICE || + (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && + ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || + ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || + ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { + pr_info("EEH functionality not supported\n"); + return -EINVAL; + } + + /* Initialize error log lock and size */ + spin_lock_init(&slot_errbuf_lock); + eeh_error_buf_size = rtas_token("rtas-error-log-max"); + if (eeh_error_buf_size == RTAS_UNKNOWN_SERVICE) { + pr_info("%s: unknown EEH error log size\n", + __func__); + eeh_error_buf_size = 1024; + } else if (eeh_error_buf_size > RTAS_ERROR_LOG_MAX) { + pr_info("%s: EEH error log size %d exceeds the maximal %d\n", + __func__, eeh_error_buf_size, RTAS_ERROR_LOG_MAX); + eeh_error_buf_size = RTAS_ERROR_LOG_MAX; + } + + /* Set EEH probe mode */ + eeh_add_flag(EEH_PROBE_MODE_DEVTREE | EEH_ENABLE_IO_FOR_LOG); + + /* Set EEH machine dependent code */ + ppc_md.pcibios_bus_add_device = pseries_pcibios_bus_add_device; + + if (is_kdump_kernel() || reset_devices) { + pr_info("Issue PHB reset ...\n"); + list_for_each_entry(phb, &hose_list, list_node) { + pdn = list_first_entry(&PCI_DN(phb->dn)->child_list, struct pci_dn, list); + config_addr = pseries_eeh_get_pe_config_addr(pdn); + + /* invalid PE config addr */ + if (config_addr < 0) + continue; + + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_FUNDAMENTAL); + pseries_eeh_phb_reset(phb, config_addr, EEH_RESET_DEACTIVATE); + pseries_eeh_phb_configure_bridge(phb, config_addr); + } + } + + ret = eeh_init(&pseries_eeh_ops); if (!ret) pr_info("EEH: pSeries platform initialized\n"); else pr_info("EEH: pSeries platform initialization failure (%d)\n", ret); - return ret; } -machine_early_initcall(pseries, eeh_pseries_init); +machine_arch_initcall(pseries, eeh_pseries_init); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 7a974ed6b240..f2837e33bf5d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -55,7 +55,7 @@ static void rtas_stop_self(void) panic("Alas, I survived.\n"); } -static void pseries_mach_cpu_die(void) +static void pseries_cpu_offline_self(void) { unsigned int hwcpu = hard_smp_processor_id(); @@ -102,7 +102,7 @@ static int pseries_cpu_disable(void) * to self-destroy so that the cpu-offline thread can send the CPU_DEAD * notifications. * - * OTOH, pseries_mach_cpu_die() is called by the @cpu when it wants to + * OTOH, pseries_cpu_offline_self() is called by the @cpu when it wants to * self-destruct. */ static void pseries_cpu_die(unsigned int cpu) @@ -901,7 +901,7 @@ static int __init pseries_cpu_hotplug_init(void) return 0; } - ppc_md.cpu_die = pseries_mach_cpu_die; + smp_ops->cpu_offline_self = pseries_cpu_offline_self; smp_ops->cpu_disable = pseries_cpu_disable; smp_ops->cpu_die = pseries_cpu_die; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index d8bbf0cc1601..7efe6ec5d14a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -30,12 +30,17 @@ unsigned long pseries_memory_block_size(void) np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); if (np) { - const __be64 *size; + int len; + int size_cells; + const __be32 *prop; - size = of_get_property(np, "ibm,lmb-size", NULL); - if (size) - memblock_size = be64_to_cpup(size); + size_cells = of_n_size_cells(np); + + prop = of_get_property(np, "ibm,lmb-size", &len); + if (prop && len >= size_cells * sizeof(__be32)) + memblock_size = of_read_number(prop, size_cells); of_node_put(np); + } else if (machine_is(pseries)) { /* This fallback really only applies to pseries */ unsigned int memzero_size = 0; @@ -277,7 +282,7 @@ static int dlpar_offline_lmb(struct drmem_lmb *lmb) return dlpar_change_lmb_state(lmb, false); } -static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) +static int pseries_remove_memblock(unsigned long base, unsigned long memblock_size) { unsigned long block_sz, start_pfn; int sections_per_block; @@ -308,10 +313,11 @@ out: static int pseries_remove_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually removing memory @@ -322,12 +328,19 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Find the base address and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); pseries_remove_memblock(base, lmb_size); return 0; @@ -354,25 +367,32 @@ static int dlpar_add_lmb(struct drmem_lmb *); static int dlpar_remove_lmb(struct drmem_lmb *lmb) { + struct memory_block *mem_block; unsigned long block_sz; int rc; if (!lmb_is_removable(lmb)) return -EINVAL; + mem_block = lmb_to_memblock(lmb); + if (mem_block == NULL) + return -EINVAL; + rc = dlpar_offline_lmb(lmb); - if (rc) + if (rc) { + put_device(&mem_block->dev); return rc; + } block_sz = pseries_memory_block_size(); - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(mem_block->nid, lmb->base_addr, block_sz); + put_device(&mem_block->dev); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); lmb->flags &= ~DRCONF_MEM_ASSIGNED; return 0; @@ -557,7 +577,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) #else static inline int pseries_remove_memblock(unsigned long base, - unsigned int memblock_size) + unsigned long memblock_size) { return -EOPNOTSUPP; } @@ -591,7 +611,7 @@ static int dlpar_memory_remove_by_ic(u32 lmbs_to_remove, u32 drc_index) static int dlpar_add_lmb(struct drmem_lmb *lmb) { unsigned long block_sz; - int rc; + int nid, rc; if (lmb->flags & DRCONF_MEM_ASSIGNED) return -EINVAL; @@ -602,11 +622,15 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) return rc; } - lmb_set_nid(lmb); block_sz = memory_block_size_bytes(); + /* Find the node id for this LMB. Fake one if necessary. */ + nid = of_drconf_to_nid_single(lmb); + if (nid < 0 || !node_possible(nid)) + nid = first_online_node; + /* Add the memory */ - rc = __add_memory(lmb->nid, lmb->base_addr, block_sz, MHP_NONE); + rc = __add_memory(nid, lmb->base_addr, block_sz, MHP_NONE); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; @@ -614,9 +638,8 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - __remove_memory(lmb->nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); - lmb_clear_nid(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; } @@ -878,10 +901,11 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const __be32 *regs; + const __be32 *prop; unsigned long base; - unsigned int lmb_size; + unsigned long lmb_size; int ret = -EINVAL; + int addr_cells, size_cells; /* * Check to see if we are actually adding memory @@ -892,12 +916,18 @@ static int pseries_add_mem_node(struct device_node *np) /* * Find the base and size of the memblock */ - regs = of_get_property(np, "reg", NULL); - if (!regs) + prop = of_get_property(np, "reg", NULL); + if (!prop) return ret; - base = be64_to_cpu(*(unsigned long *)regs); - lmb_size = be32_to_cpu(regs[3]); + addr_cells = of_n_addr_cells(np); + size_cells = of_n_size_cells(np); + /* + * "reg" property represents (addr,size) tuple. + */ + base = of_read_number(prop, addr_cells); + prop += addr_cells; + lmb_size = of_read_number(prop, size_cells); /* * Update memory region to represent the memory add diff --git a/arch/powerpc/platforms/pseries/hvCall_inst.c b/arch/powerpc/platforms/pseries/hvCall_inst.c index c40c62ec432e..2c59b4986ea5 100644 --- a/arch/powerpc/platforms/pseries/hvCall_inst.c +++ b/arch/powerpc/platforms/pseries/hvCall_inst.c @@ -70,31 +70,14 @@ static int hc_show(struct seq_file *m, void *p) return 0; } -static const struct seq_operations hcall_inst_seq_ops = { +static const struct seq_operations hcall_inst_sops = { .start = hc_start, .next = hc_next, .stop = hc_stop, .show = hc_show }; -static int hcall_inst_seq_open(struct inode *inode, struct file *file) -{ - int rc; - struct seq_file *seq; - - rc = seq_open(file, &hcall_inst_seq_ops); - seq = file->private_data; - seq->private = file_inode(file)->i_private; - - return rc; -} - -static const struct file_operations hcall_inst_seq_fops = { - .open = hcall_inst_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; +DEFINE_SEQ_ATTRIBUTE(hcall_inst); #define HCALL_ROOT_DIR "hcall_inst" #define CPU_NAME_BUF_SIZE 32 @@ -149,7 +132,7 @@ static int __init hcall_inst_init(void) snprintf(cpu_name_buf, CPU_NAME_BUF_SIZE, "cpu%d", cpu); debugfs_create_file(cpu_name_buf, 0444, hcall_root, per_cpu(hcall_stats, cpu), - &hcall_inst_seq_fops); + &hcall_inst_fops); } return 0; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 6d47b4a3ce39..e4198700ed1a 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -39,6 +39,20 @@ #include "pseries.h" +enum { + DDW_QUERY_PE_DMA_WIN = 0, + DDW_CREATE_PE_DMA_WIN = 1, + DDW_REMOVE_PE_DMA_WIN = 2, + + DDW_APPLICABLE_SIZE +}; + +enum { + DDW_EXT_SIZE = 0, + DDW_EXT_RESET_DMA_WIN = 1, + DDW_EXT_QUERY_OUT_SIZE = 2 +}; + static struct iommu_table_group *iommu_pseries_alloc_group(int node) { struct iommu_table_group *table_group; @@ -334,7 +348,7 @@ struct direct_window { /* Dynamic DMA Window support */ struct ddw_query_response { u32 windows_available; - u32 largest_available_block; + u64 largest_available_block; u32 page_size; u32 migration_capable; }; @@ -767,25 +781,14 @@ static int __init disable_ddw_setup(char *str) early_param("disable_ddw", disable_ddw_setup); -static void remove_ddw(struct device_node *np, bool remove_prop) +static void remove_dma_window(struct device_node *np, u32 *ddw_avail, + struct property *win) { struct dynamic_dma_window_prop *dwp; - struct property *win64; - u32 ddw_avail[3]; u64 liobn; - int ret = 0; - - ret = of_property_read_u32_array(np, "ibm,ddw-applicable", - &ddw_avail[0], 3); - - win64 = of_find_property(np, DIRECT64_PROPNAME, NULL); - if (!win64) - return; - - if (ret || win64->length < sizeof(*dwp)) - goto delprop; + int ret; - dwp = win64->value; + dwp = win->value; liobn = (u64)be32_to_cpu(dwp->liobn); /* clear the whole window, note the arg is in kernel pages */ @@ -798,19 +801,39 @@ static void remove_ddw(struct device_node *np, bool remove_prop) pr_debug("%pOF successfully cleared tces in window.\n", np); - ret = rtas_call(ddw_avail[2], 1, 1, NULL, liobn); + ret = rtas_call(ddw_avail[DDW_REMOVE_PE_DMA_WIN], 1, 1, NULL, liobn); if (ret) pr_warn("%pOF: failed to remove direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); else pr_debug("%pOF: successfully removed direct window: rtas returned " "%d to ibm,remove-pe-dma-window(%x) %llx\n", - np, ret, ddw_avail[2], liobn); + np, ret, ddw_avail[DDW_REMOVE_PE_DMA_WIN], liobn); +} + +static void remove_ddw(struct device_node *np, bool remove_prop) +{ + struct property *win; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; + int ret = 0; -delprop: - if (remove_prop) - ret = of_remove_property(np, win64); + ret = of_property_read_u32_array(np, "ibm,ddw-applicable", + &ddw_avail[0], DDW_APPLICABLE_SIZE); + if (ret) + return; + + win = of_find_property(np, DIRECT64_PROPNAME, NULL); + if (!win) + return; + + if (win->length >= sizeof(struct dynamic_dma_window_prop)) + remove_dma_window(np, ddw_avail, win); + + if (!remove_prop) + return; + + ret = of_remove_property(np, win); if (ret) pr_warn("%pOF: failed to remove direct window property: %d\n", np, ret); @@ -869,14 +892,62 @@ static int find_existing_ddw_windows(void) } machine_arch_initcall(pseries, find_existing_ddw_windows); +/** + * ddw_read_ext - Get the value of an DDW extension + * @np: device node from which the extension value is to be read. + * @extnum: index number of the extension. + * @value: pointer to return value, modified when extension is available. + * + * Checks if "ibm,ddw-extensions" exists for this node, and get the value + * on index 'extnum'. + * It can be used only to check if a property exists, passing value == NULL. + * + * Returns: + * 0 if extension successfully read + * -EINVAL if the "ibm,ddw-extensions" does not exist, + * -ENODATA if "ibm,ddw-extensions" does not have a value, and + * -EOVERFLOW if "ibm,ddw-extensions" does not contain this extension. + */ +static inline int ddw_read_ext(const struct device_node *np, int extnum, + u32 *value) +{ + static const char propname[] = "ibm,ddw-extensions"; + u32 count; + int ret; + + ret = of_property_read_u32_index(np, propname, DDW_EXT_SIZE, &count); + if (ret) + return ret; + + if (count < extnum) + return -EOVERFLOW; + + if (!value) + value = &count; + + return of_property_read_u32_index(np, propname, extnum, value); +} + static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, - struct ddw_query_response *query) + struct ddw_query_response *query, + struct device_node *parent) { struct device_node *dn; struct pci_dn *pdn; - u32 cfg_addr; + u32 cfg_addr, ext_query, query_out[5]; u64 buid; - int ret; + int ret, out_sz; + + /* + * From LoPAR level 2.8, "ibm,ddw-extensions" index 3 can rule how many + * output parameters ibm,query-pe-dma-windows will have, ranging from + * 5 to 6. + */ + ret = ddw_read_ext(parent, DDW_EXT_QUERY_OUT_SIZE, &ext_query); + if (!ret && ext_query == 1) + out_sz = 6; + else + out_sz = 5; /* * Get the config address and phb buid of the PE window. @@ -889,11 +960,28 @@ static int query_ddw(struct pci_dev *dev, const u32 *ddw_avail, buid = pdn->phb->buid; cfg_addr = ((pdn->busno << 16) | (pdn->devfn << 8)); - ret = rtas_call(ddw_avail[0], 3, 5, (u32 *)query, - cfg_addr, BUID_HI(buid), BUID_LO(buid)); - dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x" - " returned %d\n", ddw_avail[0], cfg_addr, BUID_HI(buid), - BUID_LO(buid), ret); + ret = rtas_call(ddw_avail[DDW_QUERY_PE_DMA_WIN], 3, out_sz, query_out, + cfg_addr, BUID_HI(buid), BUID_LO(buid)); + dev_info(&dev->dev, "ibm,query-pe-dma-windows(%x) %x %x %x returned %d\n", + ddw_avail[DDW_QUERY_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), ret); + + switch (out_sz) { + case 5: + query->windows_available = query_out[0]; + query->largest_available_block = query_out[1]; + query->page_size = query_out[2]; + query->migration_capable = query_out[3]; + break; + case 6: + query->windows_available = query_out[0]; + query->largest_available_block = ((u64)query_out[1] << 32) | + query_out[2]; + query->page_size = query_out[3]; + query->migration_capable = query_out[4]; + break; + } + return ret; } @@ -920,15 +1008,16 @@ static int create_ddw(struct pci_dev *dev, const u32 *ddw_avail, do { /* extra outputs are LIOBN and dma-addr (hi, lo) */ - ret = rtas_call(ddw_avail[1], 5, 4, (u32 *)create, - cfg_addr, BUID_HI(buid), BUID_LO(buid), - page_shift, window_shift); + ret = rtas_call(ddw_avail[DDW_CREATE_PE_DMA_WIN], 5, 4, + (u32 *)create, cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift); } while (rtas_busy_delay(ret)); dev_info(&dev->dev, "ibm,create-pe-dma-window(%x) %x %x %x %x %x returned %d " - "(liobn = 0x%x starting addr = %x %x)\n", ddw_avail[1], - cfg_addr, BUID_HI(buid), BUID_LO(buid), page_shift, - window_shift, ret, create->liobn, create->addr_hi, create->addr_lo); + "(liobn = 0x%x starting addr = %x %x)\n", + ddw_avail[DDW_CREATE_PE_DMA_WIN], cfg_addr, BUID_HI(buid), + BUID_LO(buid), page_shift, window_shift, ret, create->liobn, + create->addr_hi, create->addr_lo); return ret; } @@ -978,6 +1067,38 @@ static phys_addr_t ddw_memory_hotplug_max(void) } /* + * Platforms supporting the DDW option starting with LoPAR level 2.7 implement + * ibm,ddw-extensions, which carries the rtas token for + * ibm,reset-pe-dma-windows. + * That rtas-call can be used to restore the default DMA window for the device. + */ +static void reset_dma_window(struct pci_dev *dev, struct device_node *par_dn) +{ + int ret; + u32 cfg_addr, reset_dma_win; + u64 buid; + struct device_node *dn; + struct pci_dn *pdn; + + ret = ddw_read_ext(par_dn, DDW_EXT_RESET_DMA_WIN, &reset_dma_win); + if (ret) + return; + + dn = pci_device_to_OF_node(dev); + pdn = PCI_DN(dn); + buid = pdn->phb->buid; + cfg_addr = (pdn->busno << 16) | (pdn->devfn << 8); + + ret = rtas_call(reset_dma_win, 3, 1, NULL, cfg_addr, BUID_HI(buid), + BUID_LO(buid)); + if (ret) + dev_info(&dev->dev, + "ibm,reset-pe-dma-windows(%x) %x %x %x returned %d ", + reset_dma_win, cfg_addr, BUID_HI(buid), BUID_LO(buid), + ret); +} + +/* * If the PE supports dynamic dma windows, and there is space for a table * that can map all pages in a linear offset, then setup such a table, * and record the dma-offset in the struct device. @@ -996,11 +1117,12 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) int page_shift; u64 dma_addr, max_addr; struct device_node *dn; - u32 ddw_avail[3]; + u32 ddw_avail[DDW_APPLICABLE_SIZE]; struct direct_window *window; struct property *win64; struct dynamic_dma_window_prop *ddwprop; struct failed_ddw_pdn *fpdn; + bool default_win_removed = false; mutex_lock(&direct_window_init_mutex); @@ -1029,7 +1151,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * the property is actually in the parent, not the PE */ ret = of_property_read_u32_array(pdn, "ibm,ddw-applicable", - &ddw_avail[0], 3); + &ddw_avail[0], DDW_APPLICABLE_SIZE); if (ret) goto out_failed; @@ -1040,18 +1162,42 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) * of page sizes: supported and supported for migrate-dma. */ dn = pci_device_to_OF_node(dev); - ret = query_ddw(dev, ddw_avail, &query); + ret = query_ddw(dev, ddw_avail, &query, pdn); if (ret != 0) goto out_failed; + /* + * If there is no window available, remove the default DMA window, + * if it's present. This will make all the resources available to the + * new DDW window. + * If anything fails after this, we need to restore it, so also check + * for extensions presence. + */ if (query.windows_available == 0) { - /* - * no additional windows are available for this device. - * We might be able to reallocate the existing window, - * trading in for a larger page size. - */ - dev_dbg(&dev->dev, "no free dynamic windows"); - goto out_failed; + struct property *default_win; + int reset_win_ext; + + default_win = of_find_property(pdn, "ibm,dma-window", NULL); + if (!default_win) + goto out_failed; + + reset_win_ext = ddw_read_ext(pdn, DDW_EXT_RESET_DMA_WIN, NULL); + if (reset_win_ext) + goto out_failed; + + remove_dma_window(pdn, ddw_avail, default_win); + default_win_removed = true; + + /* Query again, to check if the window is available */ + ret = query_ddw(dev, ddw_avail, &query, pdn); + if (ret != 0) + goto out_failed; + + if (query.windows_available == 0) { + /* no windows are available for this device. */ + dev_dbg(&dev->dev, "no free dynamic windows"); + goto out_failed; + } } if (query.page_size & 4) { page_shift = 24; /* 16MB */ @@ -1068,7 +1214,7 @@ static u64 enable_ddw(struct pci_dev *dev, struct device_node *pdn) /* check largest block * page size > max memory hotplug addr */ max_addr = ddw_memory_hotplug_max(); if (query.largest_available_block < (max_addr >> page_shift)) { - dev_dbg(&dev->dev, "can't map partition max 0x%llx with %u " + dev_dbg(&dev->dev, "can't map partition max 0x%llx with %llu " "%llu-sized pages\n", max_addr, query.largest_available_block, 1ULL << page_shift); goto out_failed; @@ -1142,6 +1288,8 @@ out_free_prop: kfree(win64); out_failed: + if (default_win_removed) + reset_dma_window(dev, pdn); fpdn = kzalloc(sizeof(*fpdn), GFP_KERNEL); if (!fpdn) diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index baf24eacd268..764170fdb0f7 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -1724,6 +1724,7 @@ void __init hpte_init_pseries(void) pseries_lpar_register_process_table(0, 0, 0); } +#ifdef CONFIG_PPC_RADIX_MMU void radix_init_pseries(void) { pr_info("Using radix MMU under hypervisor\n"); @@ -1731,6 +1732,7 @@ void radix_init_pseries(void) pseries_lpar_register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12); } +#endif #ifdef CONFIG_PPC_SMLPAR #define CMO_FREE_HINT_DEFAULT 1 diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c index b8d28ab88178..e278390ab28d 100644 --- a/arch/powerpc/platforms/pseries/lparcfg.c +++ b/arch/powerpc/platforms/pseries/lparcfg.c @@ -136,6 +136,39 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data) return rc; } +static void show_gpci_data(struct seq_file *m) +{ + struct hv_gpci_request_buffer *buf; + unsigned int affinity_score; + long ret; + + buf = kmalloc(sizeof(*buf), GFP_KERNEL); + if (buf == NULL) + return; + + /* + * Show the local LPAR's affinity score. + * + * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall. + * The score is at byte 0xB in the output buffer. + */ + memset(&buf->params, 0, sizeof(buf->params)); + buf->params.counter_request = cpu_to_be32(0xB1); + buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */ + buf->params.counter_info_version_in = 0x5; /* v5+ for score */ + ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf), + sizeof(*buf)); + if (ret != H_SUCCESS) { + pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n", + ret, be32_to_cpu(buf->params.detail_rc)); + goto out; + } + affinity_score = buf->bytes[0xB]; + seq_printf(m, "partition_affinity_score=%u\n", affinity_score); +out: + kfree(buf); +} + static unsigned h_pic(unsigned long *pool_idle_time, unsigned long *num_procs) { @@ -487,6 +520,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v) partition_active_processors * 100); } + show_gpci_data(m); + seq_printf(m, "partition_active_processors=%d\n", partition_active_processors); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index a88a707a608a..835163f54244 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -785,7 +785,8 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, static ssize_t perf_stats_show(struct device *dev, struct device_attribute *attr, char *buf) { - int index, rc; + int index; + ssize_t rc; struct seq_buf s; struct papr_scm_perf_stat *stat; struct papr_scm_perf_stats *stats; @@ -820,9 +821,9 @@ static ssize_t perf_stats_show(struct device *dev, free_stats: kfree(stats); - return rc ? rc : seq_buf_used(&s); + return rc ? rc : (ssize_t)seq_buf_used(&s); } -DEVICE_ATTR_ADMIN_RO(perf_stats); +static DEVICE_ATTR_ADMIN_RO(perf_stats); static ssize_t flags_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -897,6 +898,9 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) p->bus_desc.of_node = p->pdev->dev.of_node; p->bus_desc.provider_name = kstrdup(p->pdev->name, GFP_KERNEL); + /* Set the dimm command family mask to accept PDSMs */ + set_bit(NVDIMM_FAMILY_PAPR, &p->bus_desc.dimm_family_mask); + if (!p->bus_desc.provider_name) return -ENOMEM; diff --git a/arch/powerpc/platforms/pseries/rng.c b/arch/powerpc/platforms/pseries/rng.c index bbb97169bf63..6268545947b8 100644 --- a/arch/powerpc/platforms/pseries/rng.c +++ b/arch/powerpc/platforms/pseries/rng.c @@ -36,6 +36,7 @@ static __init int rng_init(void) ppc_md.get_random_seed = pseries_get_random_long; + of_node_put(dn); return 0; } machine_subsys_initcall(pseries, rng_init); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 2f4ee0a90284..633c45ec406d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -519,9 +519,15 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) if (result->character & H_CPU_CHAR_BCCTR_FLUSH_ASSIST) security_ftr_set(SEC_FTR_BCCTR_FLUSH_ASSIST); + if (result->character & H_CPU_CHAR_BCCTR_LINK_FLUSH_ASSIST) + security_ftr_set(SEC_FTR_BCCTR_LINK_FLUSH_ASSIST); + if (result->behaviour & H_CPU_BEHAV_FLUSH_COUNT_CACHE) security_ftr_set(SEC_FTR_FLUSH_COUNT_CACHE); + if (result->behaviour & H_CPU_BEHAV_FLUSH_LINK_STACK) + security_ftr_set(SEC_FTR_FLUSH_LINK_STACK); + /* * The features below are enabled by default, so we instead look to see * if firmware has *disabled* them, and clear them if so. diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index e6d7a344d9f2..7b739cc7a8a9 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -7,6 +7,7 @@ */ #include <linux/mm.h> +#include <linux/memblock.h> #include <asm/machdep.h> #include <asm/svm.h> #include <asm/swiotlb.h> @@ -35,6 +36,31 @@ static int __init init_svm(void) } machine_early_initcall(pseries, init_svm); +/* + * Initialize SWIOTLB. Essentially the same as swiotlb_init(), except that it + * can allocate the buffer anywhere in memory. Since the hypervisor doesn't have + * any addressing limitation, we don't need to allocate it in low addresses. + */ +void __init svm_swiotlb_init(void) +{ + unsigned char *vstart; + unsigned long bytes, io_tlb_nslabs; + + io_tlb_nslabs = (swiotlb_size_or_default() >> IO_TLB_SHIFT); + io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE); + + bytes = io_tlb_nslabs << IO_TLB_SHIFT; + + vstart = memblock_alloc(PAGE_ALIGN(bytes), PAGE_SIZE); + if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, false)) + return; + + if (io_tlb_start) + memblock_free_early(io_tlb_start, + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + panic("SVM: Cannot allocate SWIOTLB buffer"); +} + int set_memory_encrypted(unsigned long addr, int numpages) { if (!PAGE_ALIGNED(addr)) diff --git a/arch/powerpc/sysdev/xics/icp-hv.c b/arch/powerpc/sysdev/xics/icp-hv.c index ad8117148ea3..21b9d1bf39ff 100644 --- a/arch/powerpc/sysdev/xics/icp-hv.c +++ b/arch/powerpc/sysdev/xics/icp-hv.c @@ -174,6 +174,7 @@ int icp_hv_init(void) icp_ops = &icp_hv_ops; + of_node_put(np); return 0; } diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index f591be9f01f4..a80440af491a 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -1565,7 +1565,7 @@ static int __init xive_off(char *arg) } __setup("xive=off", xive_off); -void xive_debug_show_cpu(struct seq_file *m, int cpu) +static void xive_debug_show_cpu(struct seq_file *m, int cpu) { struct xive_cpu *xc = per_cpu(xive_cpu, cpu); @@ -1599,7 +1599,7 @@ void xive_debug_show_cpu(struct seq_file *m, int cpu) seq_puts(m, "\n"); } -void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d) +static void xive_debug_show_irq(struct seq_file *m, u32 hw_irq, struct irq_data *d) { struct irq_chip *chip = irq_data_get_irq_chip(d); int rc; diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh index 3ce5c093b19d..91c04802ec31 100755 --- a/arch/powerpc/tools/checkpatch.sh +++ b/arch/powerpc/tools/checkpatch.sh @@ -9,7 +9,6 @@ script_base=$(realpath $(dirname $0)) exec $script_base/../../../scripts/checkpatch.pl \ --subjective \ --no-summary \ - --max-line-length=90 \ --show-types \ --ignore ARCH_INCLUDE_LINUX \ --ignore BIT_MACRO \ diff --git a/arch/powerpc/tools/unrel_branch_check.sh b/arch/powerpc/tools/unrel_branch_check.sh index 6e6a30aea3ed..8301efee1e6c 100755 --- a/arch/powerpc/tools/unrel_branch_check.sh +++ b/arch/powerpc/tools/unrel_branch_check.sh @@ -1,60 +1,79 @@ -# Copyright © 2016 IBM Corporation +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# Copyright © 2016,2020 IBM Corporation # -# This program is free software; you can redistribute it and/or -# modify it under the terms of the GNU General Public License -# as published by the Free Software Foundation; either version -# 2 of the License, or (at your option) any later version. -# -# This script checks the relocations of a vmlinux for "suspicious" -# branches from unrelocated code (head_64.S code). - -# Turn this on if you want more debug output: -# set -x +# This script checks the unrelocated code of a vmlinux for "suspicious" +# branches to relocated code (head_64.S code). -# Have Kbuild supply the path to objdump so we handle cross compilation. +# Have Kbuild supply the path to objdump and nm so we handle cross compilation. objdump="$1" -vmlinux="$2" - -#__end_interrupts should be located within the first 64K - -end_intr=0x$( -$objdump -R "$vmlinux" -d --start-address=0xc000000000000000 \ - --stop-address=0xc000000000010000 | -grep '\<__end_interrupts>:' | -awk '{print $1}' -) - -BRANCHES=$( -$objdump -R "$vmlinux" -D --start-address=0xc000000000000000 \ - --stop-address=${end_intr} | -grep -e "^c[0-9a-f]*:[[:space:]]*\([0-9a-f][0-9a-f][[:space:]]\)\{4\}[[:space:]]*b" | -grep -v '\<__start_initialization_multiplatform>' | -grep -v -e 'b.\?.\?ctr' | -grep -v -e 'b.\?.\?lr' | -sed -e 's/\bbt.\?[[:space:]]*[[:digit:]][[:digit:]]*,/beq/' \ - -e 's/\bbf.\?[[:space:]]*[[:digit:]][[:digit:]]*,/bne/' \ - -e 's/[[:space:]]0x/ /' \ - -e 's/://' | -awk '{ print $1 ":" $6 ":0x" $7 ":" $8 " "}' -) - -for tuple in $BRANCHES -do - from=`echo $tuple | cut -d':' -f1` - branch=`echo $tuple | cut -d':' -f2` - to=`echo $tuple | cut -d':' -f3 | sed 's/cr[0-7],//'` - sym=`echo $tuple | cut -d':' -f4` - - if (( $to > $end_intr )) - then - if [ -z "$bad_branches" ]; then - echo "WARNING: Unrelocated relative branches" - bad_branches="yes" +nm="$2" +vmlinux="$3" + +kstart=0xc000000000000000 + +end_intr=0x$($nm -p "$vmlinux" | + sed -E -n '/\s+[[:alpha:]]\s+__end_interrupts\s*$/{s///p;q}') +if [ "$end_intr" = "0x" ]; then + exit 0 +fi + +# we know that there is a correct branch to +# __start_initialization_multiplatform, so find its address +# so we can exclude it. +sim=0x$($nm -p "$vmlinux" | + sed -E -n '/\s+[[:alpha:]]\s+__start_initialization_multiplatform\s*$/{s///p;q}') + +$objdump -D --no-show-raw-insn --start-address="$kstart" --stop-address="$end_intr" "$vmlinux" | +sed -E -n ' +# match lines that start with a kernel address +/^c[0-9a-f]*:\s*b/ { + # drop branches via ctr or lr + /\<b.?.?(ct|l)r/d + # cope with some differences between Clang and GNU objdumps + s/\<bt.?\s*[[:digit:]]+,/beq/ + s/\<bf.?\s*[[:digit:]]+,/bne/ + # tidy up + s/\s0x/ / + s/:// + # format for the loop below + s/^(\S+)\s+(\S+)\s+(\S+)\s*(\S*).*$/\1:\2:\3:\4/ + # strip out condition registers + s/:cr[0-7],/:/ + p +}' | { + +all_good=true +while IFS=: read -r from branch to sym; do + case "$to" in + c*) to="0x$to" + ;; + .+*) + to=${to#.+} + if [ "$branch" = 'b' ]; then + if (( to >= 0x2000000 )); then + to=$(( to - 0x4000000 )) + fi + elif (( to >= 0x8000 )); then + to=$(( to - 0x10000 )) + fi + printf -v to '0x%x' $(( "0x$from" + to )) + ;; + *) printf 'Unkown branch format\n' + ;; + esac + if [ "$to" = "$sim" ]; then + continue + fi + if (( to > end_intr )); then + if $all_good; then + printf '%s\n' 'WARNING: Unrelocated relative branches' + all_good=false fi - echo "$from $branch-> $to $sym" + printf '%s %s-> %s %s\n' "$from" "$branch" "$to" "$sym" fi done -if [ -z "$bad_branches" ]; then - exit 0 -fi +$all_good + +} diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index df7bca00f5ec..55c43a6c9111 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -969,6 +969,7 @@ static void insert_cpu_bpts(void) brk.address = dabr[i].address; brk.type = (dabr[i].enabled & HW_BRK_TYPE_DABR) | HW_BRK_TYPE_PRIV_ALL; brk.len = 8; + brk.hw_len = 8; __set_breakpoint(i, &brk); } } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index e286e2badc8a..e38d8bf454e8 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1039,38 +1039,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1080,18 +1051,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1114,17 +1080,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1134,14 +1098,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); |