diff options
Diffstat (limited to 'arch/powerpc')
84 files changed, 856 insertions, 649 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 03c1b076b51b..e924ddd54618 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -171,7 +171,7 @@ config PPC select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU select HAVE_ARCH_JUMP_LABEL - select HAVE_ARCH_KASAN if PPC32 + select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14 select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -747,6 +747,7 @@ config THREAD_SHIFT range 13 15 default "15" if PPC_256K_PAGES default "14" if PPC64 + default "14" if KASAN default "13" help Used to define the stack size. The default is almost always what you diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile index dfbd7f22eef5..8c69bd07ada6 100644 --- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -119,7 +119,7 @@ src-wlib-y := string.S crt0.S stdio.c decompress.c main.c \ elf_util.c $(zlib-y) devtree.c stdlib.c \ oflib.c ofconsole.c cuboot.c -src-wlib-$(CONFIG_PPC_MPC52XX) += mpc52xx-psc.c +src-wlib-$(CONFIG_PPC_MPC52xx) += mpc52xx-psc.c src-wlib-$(CONFIG_PPC64_BOOT_WRAPPER) += opal-calls.S opal.c ifndef CONFIG_PPC64_BOOT_WRAPPER src-wlib-y += crtsavres.S diff --git a/arch/powerpc/boot/serial.c b/arch/powerpc/boot/serial.c index 9457863147f9..00179cd6bdd0 100644 --- a/arch/powerpc/boot/serial.c +++ b/arch/powerpc/boot/serial.c @@ -128,7 +128,7 @@ int serial_console_init(void) dt_is_compatible(devp, "fsl,cpm2-smc-uart")) rc = cpm_console_init(devp, &serial_cd); #endif -#ifdef CONFIG_PPC_MPC52XX +#ifdef CONFIG_PPC_MPC52xx else if (dt_is_compatible(devp, "fsl,mpc5200-psc-uart")) rc = mpc5200_psc_console_init(devp, &serial_cd); #endif diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index 9575a38c9155..b507df6ac69f 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -2,7 +2,6 @@ CONFIG_AQUANTIA_PHY=y CONFIG_AT803X_PHY=y CONFIG_ATA=y CONFIG_BLK_DEV_SD=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_BLK_DEV_SR=y CONFIG_BROADCOM_PHY=y CONFIG_C293_PCIE=y diff --git a/arch/powerpc/configs/amigaone_defconfig b/arch/powerpc/configs/amigaone_defconfig index cf94d28d0e31..340140160c7b 100644 --- a/arch/powerpc/configs/amigaone_defconfig +++ b/arch/powerpc/configs/amigaone_defconfig @@ -47,7 +47,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/chrp32_defconfig b/arch/powerpc/configs/chrp32_defconfig index 9ff493dd8439..6c5a4414e9ee 100644 --- a/arch/powerpc/configs/chrp32_defconfig +++ b/arch/powerpc/configs/chrp32_defconfig @@ -45,7 +45,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SYM53C8XX_2=y diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index fbfcc85e4dc0..a68c7f3af10e 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -62,7 +62,6 @@ CONFIG_CDROM_PKTCDVD=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SPI_ATTRS=y diff --git a/arch/powerpc/configs/maple_defconfig b/arch/powerpc/configs/maple_defconfig index 2975e64629aa..161351a18517 100644 --- a/arch/powerpc/configs/maple_defconfig +++ b/arch/powerpc/configs/maple_defconfig @@ -41,7 +41,6 @@ CONFIG_BLK_DEV_RAM_SIZE=8192 # CONFIG_SCSI_PROC_FS is not set CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_IPR=y CONFIG_ATA=y diff --git a/arch/powerpc/configs/pasemi_defconfig b/arch/powerpc/configs/pasemi_defconfig index 4b6d31d4474e..ddf5e97877e2 100644 --- a/arch/powerpc/configs/pasemi_defconfig +++ b/arch/powerpc/configs/pasemi_defconfig @@ -60,7 +60,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_CHR_DEV_OSST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=y CONFIG_SCSI_CONSTANTS=y @@ -110,7 +109,6 @@ CONFIG_FB_NVIDIA=y CONFIG_FB_NVIDIA_I2C=y CONFIG_FB_RADEON=y # CONFIG_LCD_CLASS_DEVICE is not set -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_LOGO=y CONFIG_SOUND=y CONFIG_SND=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 4e6e95f92646..5cad09f93562 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -119,7 +119,6 @@ CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/powernv_defconfig b/arch/powerpc/configs/powernv_defconfig index 6658cceb928c..2a7c53cc2f83 100644 --- a/arch/powerpc/configs/powernv_defconfig +++ b/arch/powerpc/configs/powernv_defconfig @@ -111,7 +111,6 @@ CONFIG_BLK_DEV_NVME=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index b250e6f5a7ca..5569d36066dc 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -110,7 +110,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig index 0d746774c2bd..33a01a9e86be 100644 --- a/arch/powerpc/configs/ppc64e_defconfig +++ b/arch/powerpc/configs/ppc64e_defconfig @@ -60,7 +60,6 @@ CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 9dca4cffa623..682d68f39c2b 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -372,7 +372,6 @@ CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_CHR_DEV_OSST=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_CHR_DEV_SCH=m CONFIG_SCSI_ENCLOSURE=m @@ -778,7 +777,6 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m -CONFIG_VGACON_SOFT_SCROLLBACK=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 26126b4d4de3..d58686a66388 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -97,7 +97,6 @@ CONFIG_VIRTIO_BLK=m CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=m CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_FC_ATTRS=y diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index 1253482a67c0..2e25b264f70f 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -83,7 +83,6 @@ CONFIG_EEPROM_AT24=m # CONFIG_OCXL is not set CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y CONFIG_CHR_DEV_SG=m CONFIG_SCSI_CONSTANTS=y CONFIG_SCSI_SCAN_ASYNC=y diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 1a2c80e8be84..6eb311eb818b 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -2,6 +2,7 @@ #ifndef _ASM_POWERPC_BOOK3S_32_KUP_H #define _ASM_POWERPC_BOOK3S_32_KUP_H +#include <asm/bug.h> #include <asm/book3s/32/mmu-hash.h> #ifdef __ASSEMBLY__ @@ -75,7 +76,7 @@ .macro kuap_check current, gpr #ifdef CONFIG_PPC_KUAP_DEBUG - lwz \gpr, KUAP(thread) + lwz \gpr, THREAD + KUAP(\current) 999: twnei \gpr, 0 EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) #endif diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index 3f9ae3585ab9..80c953414882 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -13,20 +13,19 @@ */ #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 + * Define the address range of the kernel non-linear virtual area (61TB) */ -#define H_KERN_VIRT_START ASM_CONST(0xc000100000000000) +#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/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index bb3deb76c951..2f4ddc802fe9 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -225,14 +225,14 @@ static inline void early_init_mmu_secondary(void) extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size); -extern void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size); static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base, phys_addr_t first_memblock_size) { - if (early_radix_enabled()) - return radix__setup_initial_memory_limit(first_memblock_base, - first_memblock_size); + /* + * Hash has more strict restrictions. At this point we don't + * know which translations we will pick. Hence go with hash + * restrictions. + */ return hash__setup_initial_memory_limit(first_memblock_base, first_memblock_size); } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index a143d394ff46..e1eb8aa9cfbb 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -998,10 +998,25 @@ extern struct page *pgd_page(pgd_t pgd); #define pud_page_vaddr(pud) __va(pud_val(pud) & ~PUD_MASKED_BITS) #define pgd_page_vaddr(pgd) __va(pgd_val(pgd) & ~PGD_MASKED_BITS) -#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & (PTRS_PER_PGD - 1)) -#define pud_index(address) (((address) >> (PUD_SHIFT)) & (PTRS_PER_PUD - 1)) -#define pmd_index(address) (((address) >> (PMD_SHIFT)) & (PTRS_PER_PMD - 1)) -#define pte_index(address) (((address) >> (PAGE_SHIFT)) & (PTRS_PER_PTE - 1)) +static inline unsigned long pgd_index(unsigned long address) +{ + return (address >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1); +} + +static inline unsigned long pud_index(unsigned long address) +{ + return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1); +} + +static inline unsigned long pmd_index(unsigned long address) +{ + return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); +} + +static inline unsigned long pte_index(unsigned long address) +{ + return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); +} /* * Find an entry in a page-table-directory. We combine the address region diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h index 28c3d936fdf3..bea7a2405ba5 100644 --- a/arch/powerpc/include/asm/drmem.h +++ b/arch/powerpc/include/asm/drmem.h @@ -8,14 +8,13 @@ #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 { @@ -26,8 +25,22 @@ struct drmem_lmb_info { 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), \ @@ -103,22 +116,4 @@ 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/fadump-internal.h b/arch/powerpc/include/asm/fadump-internal.h index c814a2b55389..8d61c8f3fec4 100644 --- a/arch/powerpc/include/asm/fadump-internal.h +++ b/arch/powerpc/include/asm/fadump-internal.h @@ -64,12 +64,14 @@ struct fadump_memory_range { }; /* fadump memory ranges info */ +#define RNG_NAME_SZ 16 struct fadump_mrange_info { - char name[16]; + char name[RNG_NAME_SZ]; struct fadump_memory_range *mem_ranges; u32 mem_ranges_sz; u32 mem_range_cnt; u32 max_mem_ranges; + bool is_static; }; /* Platform specific callback functions */ diff --git a/arch/powerpc/include/asm/kasan.h b/arch/powerpc/include/asm/kasan.h index 296e51c2f066..6db06f58deed 100644 --- a/arch/powerpc/include/asm/kasan.h +++ b/arch/powerpc/include/asm/kasan.h @@ -23,9 +23,7 @@ #define KASAN_SHADOW_OFFSET ASM_CONST(CONFIG_KASAN_SHADOW_OFFSET) -#define KASAN_SHADOW_END 0UL - -#define KASAN_SHADOW_SIZE (KASAN_SHADOW_END - KASAN_SHADOW_START) +#define KASAN_SHADOW_END (-(-KASAN_SHADOW_START >> KASAN_SHADOW_SCALE_SHIFT)) #ifdef CONFIG_KASAN void kasan_early_init(void); diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index 635fb154b33f..a3633560493b 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -150,4 +150,7 @@ #define KVM_INST_FETCH_FAILED -1 +/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 6fe6ad64cba5..740b52ec3509 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/include/asm/percpu.h b/arch/powerpc/include/asm/percpu.h index dce863a7635c..8e5b7d0b851c 100644 --- a/arch/powerpc/include/asm/percpu.h +++ b/arch/powerpc/include/asm/percpu.h @@ -10,8 +10,6 @@ #ifdef CONFIG_SMP -#include <asm/paca.h> - #define __my_cpu_offset local_paca->data_offset #endif /* CONFIG_SMP */ @@ -19,4 +17,6 @@ #include <asm-generic/percpu.h> +#include <asm/paca.h> + #endif /* _ASM_POWERPC_PERCPU_H_ */ diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h index 7426d7a90e1e..7aba3c7ea25c 100644 --- a/arch/powerpc/include/asm/perf_event.h +++ b/arch/powerpc/include/asm/perf_event.h @@ -12,6 +12,8 @@ #ifdef CONFIG_PPC_PERF_CTRS #include <asm/perf_event_server.h> +#else +static inline bool is_sier_available(void) { return false; } #endif #ifdef CONFIG_FSL_EMB_PERF_EVENT diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a9993e7a443b..64b998db9d3e 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -291,7 +291,6 @@ struct thread_struct { #else #define INIT_THREAD { \ .ksp = INIT_SP, \ - .regs = (struct pt_regs *)INIT_SP - 1, /* XXX bogus, I think */ \ .addr_limit = KERNEL_DS, \ .fpexc_mode = 0, \ .fscr = FSCR_TAR | FSCR_EBB \ diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index ee3ada66deb5..c41220f4aad9 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -203,7 +203,7 @@ do { \ #endif /* __powerpc64__ */ #define arch_has_single_step() (1) -#ifndef CONFIG_BOOK3S_601 +#ifndef CONFIG_PPC_BOOK3S_601 #define arch_has_block_step() (true) #else #define arch_has_block_step() (false) diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index b3cbb1136bce..34d08ff21b98 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -796,7 +796,7 @@ #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) diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 3c1887351c71..bd227e0eab07 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -368,8 +368,6 @@ extern int rtas_set_indicator_fast(int indicator, int index, int new_value); extern void rtas_progress(char *s, unsigned short hex); extern int rtas_suspend_cpu(struct rtas_suspend_me_data *data); extern int rtas_suspend_last_cpu(struct rtas_suspend_me_data *data); -extern int rtas_online_cpus_mask(cpumask_var_t cpus); -extern int rtas_offline_cpus_mask(cpumask_var_t cpus); extern int rtas_ibm_suspend_me(u64 handle); struct rtc_time; diff --git a/arch/powerpc/include/asm/timex.h b/arch/powerpc/include/asm/timex.h index d2d2c4bd8435..6047402b0a4d 100644 --- a/arch/powerpc/include/asm/timex.h +++ b/arch/powerpc/include/asm/timex.h @@ -17,7 +17,7 @@ typedef unsigned long cycles_t; static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_BOOK3S_601)) + if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) return 0; return mftb(); diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index 7f3a8b902325..02a1c18cdba3 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -67,19 +67,6 @@ 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/kernel/Makefile b/arch/powerpc/kernel/Makefile index 021a5b0a9123..4b4c7d26ff6c 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -19,6 +19,7 @@ CFLAGS_btext.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN) CFLAGS_prom_init.o += $(call cc-option, -fno-stack-protector) +CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING ifdef CONFIG_FUNCTION_TRACER # Do not trace early boot code @@ -36,7 +37,6 @@ KASAN_SANITIZE_btext.o := n ifdef CONFIG_KASAN CFLAGS_early_32.o += -DDISABLE_BRANCH_PROFILING CFLAGS_cputable.o += -DDISABLE_BRANCH_PROFILING -CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING CFLAGS_btext.o += -DDISABLE_BRANCH_PROFILING endif diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S index a460298c7ddb..f91ecb10d0ae 100644 --- a/arch/powerpc/kernel/cpu_setup_power.S +++ b/arch/powerpc/kernel/cpu_setup_power.S @@ -184,7 +184,7 @@ __init_LPCR_ISA300: __init_FSCR: mfspr r3,SPRN_FSCR - ori r3,r3,FSCR_TAR|FSCR_DSCR|FSCR_EBB + ori r3,r3,FSCR_TAR|FSCR_EBB mtspr SPRN_FSCR,r3 blr diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index e486d1d78de2..f4cb2c546adb 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -160,7 +160,8 @@ u64 dma_iommu_get_required_mask(struct device *dev) return bypass_mask; } - mask = 1ULL < (fls_long(tbl->it_offset + tbl->it_size) - 1); + mask = 1ULL << (fls_long(tbl->it_offset + tbl->it_size) + + tbl->it_page_shift - 1); mask += mask - 1; return mask; diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 05606025a131..3551f11accf0 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -346,6 +346,14 @@ static int __init feat_enable_dscr(struct dt_cpu_feature *f) { u64 lpcr; + /* + * Linux relies on FSCR[DSCR] being clear, so that we can take the + * facility unavailable interrupt and track the task's usage of DSCR. + * See facility_unavailable_exception(). + * Clear the bit here so that feat_enable() doesn't set it. + */ + f->fscr_bit_nr = -1; + feat_enable(f); lpcr = mfspr(SPRN_LPCR); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index bc8a551013be..c35069294ecf 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -503,7 +503,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev) rc = 1; if (pe->state & EEH_PE_ISOLATED) { pe->check_count++; - if (pe->check_count % EEH_MAX_FAILS == 0) { + if (pe->check_count == EEH_MAX_FAILS) { dn = pci_device_to_OF_node(dev); if (dn) location = of_get_property(dn, "ibm,loc-code", diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index d0018dd17e0a..70ac8a6ba0c1 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -1090,17 +1090,19 @@ EXC_COMMON_BEGIN(machine_check_idle_common) bl machine_check_queue_event /* - * We have not used any non-volatile GPRs here, and as a rule - * most exception code including machine check does not. - * Therefore PACA_NAPSTATELOST does not need to be set. Idle - * wakeup will restore volatile registers. + * GPR-loss wakeups are relatively straightforward, because the + * idle sleep code has saved all non-volatile registers on its + * own stack, and r1 in PACAR1. * - * Load the original SRR1 into r3 for pnv_powersave_wakeup_mce. + * For no-loss wakeups the r1 and lr registers used by the + * early machine check handler have to be restored first. r2 is + * the kernel TOC, so no need to restore it. * * Then decrement MCE nesting after finishing with the stack. */ ld r3,_MSR(r1) ld r4,_LINK(r1) + ld r1,GPR1(r1) lhz r11,PACA_IN_MCE(r13) subi r11,r11,1 @@ -1109,7 +1111,7 @@ EXC_COMMON_BEGIN(machine_check_idle_common) mtlr r4 rlwinm r10,r3,47-31,30,31 cmpwi cr1,r10,2 - bltlr cr1 /* no state loss, return to idle caller */ + bltlr cr1 /* no state loss, return to idle caller with r3=SRR1 */ b idle_return_gpr_loss #endif diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index ed59855430b9..9b522152d8f0 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -38,8 +38,17 @@ static void __init fadump_reserve_crash_area(u64 base); #ifndef CONFIG_PRESERVE_FA_DUMP static DEFINE_MUTEX(fadump_mutex); -struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0 }; -struct fadump_mrange_info reserved_mrange_info = { "reserved", NULL, 0, 0, 0 }; +struct fadump_mrange_info crash_mrange_info = { "crash", NULL, 0, 0, 0, false }; + +#define RESERVED_RNGS_SZ 16384 /* 16K - 128 entries */ +#define RESERVED_RNGS_CNT (RESERVED_RNGS_SZ / \ + sizeof(struct fadump_memory_range)) +static struct fadump_memory_range rngs[RESERVED_RNGS_CNT]; +struct fadump_mrange_info reserved_mrange_info = { "reserved", rngs, + RESERVED_RNGS_SZ, 0, + RESERVED_RNGS_CNT, true }; + +static void __init early_init_dt_scan_reserved_ranges(unsigned long node); #ifdef CONFIG_CMA static struct cma *fadump_cma; @@ -108,6 +117,11 @@ static int __init fadump_cma_init(void) { return 1; } int __init early_init_dt_scan_fw_dump(unsigned long node, const char *uname, int depth, void *data) { + if (depth == 0) { + early_init_dt_scan_reserved_ranges(node); + return 0; + } + if (depth != 1) return 0; @@ -429,10 +443,72 @@ static int __init fadump_get_boot_mem_regions(void) return ret; } +/* + * Returns true, if the given range overlaps with reserved memory ranges + * starting at idx. Also, updates idx to index of overlapping memory range + * with the given memory range. + * False, otherwise. + */ +static bool overlaps_reserved_ranges(u64 base, u64 end, int *idx) +{ + bool ret = false; + int i; + + for (i = *idx; i < reserved_mrange_info.mem_range_cnt; i++) { + u64 rbase = reserved_mrange_info.mem_ranges[i].base; + u64 rend = rbase + reserved_mrange_info.mem_ranges[i].size; + + if (end <= rbase) + break; + + if ((end > rbase) && (base < rend)) { + *idx = i; + ret = true; + break; + } + } + + return ret; +} + +/* + * Locate a suitable memory area to reserve memory for FADump. While at it, + * lookup reserved-ranges & avoid overlap with them, as they are used by F/W. + */ +static u64 __init fadump_locate_reserve_mem(u64 base, u64 size) +{ + struct fadump_memory_range *mrngs; + phys_addr_t mstart, mend; + int idx = 0; + u64 i, ret = 0; + + mrngs = reserved_mrange_info.mem_ranges; + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, + &mstart, &mend, NULL) { + pr_debug("%llu) mstart: %llx, mend: %llx, base: %llx\n", + i, mstart, mend, base); + + if (mstart > base) + base = PAGE_ALIGN(mstart); + + while ((mend > base) && ((mend - base) >= size)) { + if (!overlaps_reserved_ranges(base, base+size, &idx)) { + ret = base; + goto out; + } + + base = mrngs[idx].base + mrngs[idx].size; + base = PAGE_ALIGN(base); + } + } + +out: + return ret; +} + int __init fadump_reserve_mem(void) { - u64 base, size, mem_boundary, bootmem_min, align = PAGE_SIZE; - bool is_memblock_bottom_up = memblock_bottom_up(); + u64 base, size, mem_boundary, bootmem_min; int ret = 1; if (!fw_dump.fadump_enabled) @@ -453,9 +529,9 @@ int __init fadump_reserve_mem(void) PAGE_ALIGN(fadump_calculate_reserve_size()); #ifdef CONFIG_CMA if (!fw_dump.nocma) { - align = FADUMP_CMA_ALIGNMENT; fw_dump.boot_memory_size = - ALIGN(fw_dump.boot_memory_size, align); + ALIGN(fw_dump.boot_memory_size, + FADUMP_CMA_ALIGNMENT); } #endif @@ -523,13 +599,9 @@ int __init fadump_reserve_mem(void) * Reserve memory at an offset closer to bottom of the RAM to * minimize the impact of memory hot-remove operation. */ - memblock_set_bottom_up(true); - base = memblock_find_in_range(base, mem_boundary, size, align); + base = fadump_locate_reserve_mem(base, size); - /* Restore the previous allocation mode */ - memblock_set_bottom_up(is_memblock_bottom_up); - - if (!base) { + if (!base || (base + size > mem_boundary)) { pr_err("Failed to find memory chunk for reservation!\n"); goto error_out; } @@ -726,10 +798,14 @@ void fadump_free_cpu_notes_buf(void) static void fadump_free_mem_ranges(struct fadump_mrange_info *mrange_info) { + if (mrange_info->is_static) { + mrange_info->mem_range_cnt = 0; + return; + } + kfree(mrange_info->mem_ranges); - mrange_info->mem_ranges = NULL; - mrange_info->mem_ranges_sz = 0; - mrange_info->max_mem_ranges = 0; + memset((void *)((u64)mrange_info + RNG_NAME_SZ), 0, + (sizeof(struct fadump_mrange_info) - RNG_NAME_SZ)); } /* @@ -786,6 +862,12 @@ static inline int fadump_add_mem_range(struct fadump_mrange_info *mrange_info, if (mrange_info->mem_range_cnt == mrange_info->max_mem_ranges) { int ret; + if (mrange_info->is_static) { + pr_err("Reached array size limit for %s memory ranges\n", + mrange_info->name); + return -ENOSPC; + } + ret = fadump_alloc_mem_ranges(mrange_info); if (ret) return ret; @@ -1202,20 +1284,19 @@ static void sort_and_merge_mem_ranges(struct fadump_mrange_info *mrange_info) * Scan reserved-ranges to consider them while reserving/releasing * memory for FADump. */ -static inline int fadump_scan_reserved_mem_ranges(void) +static void __init early_init_dt_scan_reserved_ranges(unsigned long node) { - struct device_node *root; const __be32 *prop; int len, ret = -1; unsigned long i; - root = of_find_node_by_path("/"); - if (!root) - return ret; + /* reserved-ranges already scanned */ + if (reserved_mrange_info.mem_range_cnt != 0) + return; - prop = of_get_property(root, "reserved-ranges", &len); + prop = of_get_flat_dt_prop(node, "reserved-ranges", &len); if (!prop) - return ret; + return; /* * Each reserved range is an (address,size) pair, 2 cells each, @@ -1237,7 +1318,8 @@ static inline int fadump_scan_reserved_mem_ranges(void) } } - return ret; + /* Compact reserved ranges */ + sort_and_merge_mem_ranges(&reserved_mrange_info); } /* @@ -1251,32 +1333,21 @@ static void fadump_release_memory(u64 begin, u64 end) u64 ra_start, ra_end, tstart; int i, ret; - fadump_scan_reserved_mem_ranges(); - ra_start = fw_dump.reserve_dump_area_start; ra_end = ra_start + fw_dump.reserve_dump_area_size; /* - * Add reserved dump area to reserved ranges list - * and exclude all these ranges while releasing memory. + * If reserved ranges array limit is hit, overwrite the last reserved + * memory range with reserved dump area to ensure it is excluded from + * the memory being released (reused for next FADump registration). */ - ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end); - if (ret != 0) { - /* - * Not enough memory to setup reserved ranges but the system is - * running shortage of memory. So, release all the memory except - * Reserved dump area (reused for next fadump registration). - */ - if (begin < ra_end && end > ra_start) { - if (begin < ra_start) - fadump_release_reserved_area(begin, ra_start); - if (end > ra_end) - fadump_release_reserved_area(ra_end, end); - } else - fadump_release_reserved_area(begin, end); + if (reserved_mrange_info.mem_range_cnt == + reserved_mrange_info.max_mem_ranges) + reserved_mrange_info.mem_range_cnt--; + ret = fadump_add_mem_range(&reserved_mrange_info, ra_start, ra_end); + if (ret != 0) return; - } /* Get the reserved ranges list in order first. */ sort_and_merge_mem_ranges(&reserved_mrange_info); diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S index a7f356d121ae..53aa8f23e09f 100644 --- a/arch/powerpc/kernel/head_64.S +++ b/arch/powerpc/kernel/head_64.S @@ -945,15 +945,8 @@ start_here_multiplatform: std r0,0(r4) #endif - /* The following gets the stack set up with the regs */ - /* pointing to the real addr of the kernel stack. This is */ - /* all done to support the C function call below which sets */ - /* up the htab. This is done because we have relocated the */ - /* kernel but are still running in real mode. */ - - LOAD_REG_ADDR(r3,init_thread_union) - /* set up a stack pointer */ + LOAD_REG_ADDR(r3,init_thread_union) LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) add r1,r3,r1 li r0,0 diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index c4ed328a7b96..7a1c11a7cba5 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -114,11 +114,12 @@ void machine_kexec(struct kimage *image) void __init reserve_crashkernel(void) { - unsigned long long crash_size, crash_base; + unsigned long long crash_size, crash_base, total_mem_sz; int ret; + total_mem_sz = memory_limit ? memory_limit : memblock_phys_mem_size(); /* use common parsing */ - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { crashk_res.start = crash_base; @@ -177,6 +178,7 @@ void __init reserve_crashkernel(void) /* Crash kernel trumps memory limit */ if (memory_limit && memory_limit <= crashk_res.end) { memory_limit = crashk_res.end + 1; + total_mem_sz = memory_limit; printk("Adjusted memory limit for crashkernel, now 0x%llx\n", memory_limit); } @@ -185,7 +187,7 @@ void __init reserve_crashkernel(void) "for crashkernel (System RAM: %ldMB)\n", (unsigned long)(crash_size >> 20), (unsigned long)(crashk_res.start >> 20), - (unsigned long)(memblock_phys_mem_size() >> 20)); + (unsigned long)(total_mem_sz >> 20)); if (!memblock_is_region_memory(crashk_res.start, crash_size) || memblock_reserve(crashk_res.start, crash_size)) { diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 3f91ccaa9c74..4ea0cca52e16 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -86,7 +86,7 @@ static void *__init alloc_shared_lppaca(unsigned long size, unsigned long align, * This is very early in boot, so no harm done if the kernel crashes at * this point. */ - BUG_ON(shared_lppaca_size >= shared_lppaca_total_size); + BUG_ON(shared_lppaca_size > shared_lppaca_total_size); return ptr; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 639ceae7da9d..bd0c258a1d5d 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1218,29 +1218,31 @@ struct task_struct *__switch_to(struct task_struct *prev, static void show_instructions(struct pt_regs *regs) { int i; + unsigned long nip = regs->nip; unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); printk("Instruction dump:"); + /* + * If we were executing with the MMU off for instructions, adjust pc + * rather than printing XXXXXXXX. + */ + if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) { + pc = (unsigned long)phys_to_virt(pc); + nip = (unsigned long)phys_to_virt(regs->nip); + } + for (i = 0; i < NR_INSN_TO_PRINT; i++) { int instr; if (!(i % 8)) pr_cont("\n"); -#if !defined(CONFIG_BOOKE) - /* If executing with the IMMU off, adjust pc rather - * than print XXXXXXXX. - */ - if (!(regs->msr & MSR_IR)) - pc = (unsigned long)phys_to_virt(pc); -#endif - if (!__kernel_text_address(pc) || probe_kernel_address((const void *)pc, instr)) { pr_cont("XXXXXXXX "); } else { - if (regs->nip == pc) + if (nip == pc) pr_cont("<%08x> ", instr); else pr_cont("%08x ", instr); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 6620f37abe73..e13e96e665e0 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -685,6 +685,23 @@ static void __init tm_init(void) static void tm_init(void) { } #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */ +#ifdef CONFIG_PPC64 +static void __init save_fscr_to_task(void) +{ + /* + * Ensure the init_task (pid 0, aka swapper) uses the value of FSCR we + * have configured via the device tree features or via __init_FSCR(). + * That value will then be propagated to pid 1 (init) and all future + * processes. + */ + if (early_cpu_has_feature(CPU_FTR_ARCH_207S)) + init_task.thread.fscr = mfspr(SPRN_FSCR); +} +#else +static inline void save_fscr_to_task(void) {}; +#endif + + void __init early_init_devtree(void *params) { phys_addr_t limit; @@ -773,6 +790,8 @@ void __init early_init_devtree(void *params) BUG(); } + save_fscr_to_task(); + #if defined(CONFIG_SMP) && defined(CONFIG_PPC64) /* We'll later wait for secondaries to check in; there are * NCPUS-1 non-boot CPUs :-) diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c index c5fa251b8950..01210593d60c 100644 --- a/arch/powerpc/kernel/rtas.c +++ b/arch/powerpc/kernel/rtas.c @@ -842,96 +842,6 @@ static void rtas_percpu_suspend_me(void *info) __rtas_suspend_cpu((struct rtas_suspend_me_data *)info, 1); } -enum rtas_cpu_state { - DOWN, - UP, -}; - -#ifndef CONFIG_SMP -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - if (!cpumask_empty(cpus)) { - cpumask_clear(cpus); - return -EINVAL; - } else - return 0; -} -#else -/* On return cpumask will be altered to indicate CPUs changed. - * CPUs with states changed will be set in the mask, - * CPUs with status unchanged will be unset in the mask. */ -static int rtas_cpu_state_change_mask(enum rtas_cpu_state state, - cpumask_var_t cpus) -{ - int cpu; - int cpuret = 0; - int ret = 0; - - if (cpumask_empty(cpus)) - return 0; - - for_each_cpu(cpu, cpus) { - struct device *dev = get_cpu_device(cpu); - - switch (state) { - case DOWN: - cpuret = device_offline(dev); - break; - case UP: - cpuret = device_online(dev); - break; - } - if (cpuret < 0) { - pr_debug("%s: cpu_%s for cpu#%d returned %d.\n", - __func__, - ((state == UP) ? "up" : "down"), - cpu, cpuret); - if (!ret) - ret = cpuret; - if (state == UP) { - /* clear bits for unchanged cpus, return */ - cpumask_shift_right(cpus, cpus, cpu); - cpumask_shift_left(cpus, cpus, cpu); - break; - } else { - /* clear bit for unchanged cpu, continue */ - cpumask_clear_cpu(cpu, cpus); - } - } - cond_resched(); - } - - return ret; -} -#endif - -int rtas_online_cpus_mask(cpumask_var_t cpus) -{ - int ret; - - ret = rtas_cpu_state_change_mask(UP, cpus); - - if (ret) { - cpumask_var_t tmp_mask; - - if (!alloc_cpumask_var(&tmp_mask, GFP_KERNEL)) - return ret; - - /* Use tmp_mask to preserve cpus mask from first failure */ - cpumask_copy(tmp_mask, cpus); - rtas_offline_cpus_mask(tmp_mask); - free_cpumask_var(tmp_mask); - } - - return ret; -} - -int rtas_offline_cpus_mask(cpumask_var_t cpus) -{ - return rtas_cpu_state_change_mask(DOWN, cpus); -} - int rtas_ibm_suspend_me(u64 handle) { long state; @@ -939,8 +849,6 @@ int rtas_ibm_suspend_me(u64 handle) unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; struct rtas_suspend_me_data data; DECLARE_COMPLETION_ONSTACK(done); - cpumask_var_t offline_mask; - int cpuret; if (!rtas_service_present("ibm,suspend-me")) return -ENOSYS; @@ -961,9 +869,6 @@ int rtas_ibm_suspend_me(u64 handle) return -EIO; } - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - atomic_set(&data.working, 0); atomic_set(&data.done, 0); atomic_set(&data.error, 0); @@ -972,24 +877,8 @@ int rtas_ibm_suspend_me(u64 handle) lock_device_hotplug(); - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, cpu_online_mask); - cpuret = rtas_online_cpus_mask(offline_mask); - if (cpuret) { - pr_err("%s: Could not bring present CPUs online.\n", __func__); - atomic_set(&data.error, cpuret); - goto out; - } - cpu_hotplug_disable(); - /* Check if we raced with a CPU-Offline Operation */ - if (!cpumask_equal(cpu_present_mask, cpu_online_mask)) { - pr_info("%s: Raced against a concurrent CPU-Offline\n", __func__); - atomic_set(&data.error, -EAGAIN); - goto out_hotplug_enable; - } - /* Call function on all CPUs. One of us will make the * rtas call */ @@ -1000,18 +889,11 @@ int rtas_ibm_suspend_me(u64 handle) if (atomic_read(&data.error) != 0) printk(KERN_ERR "Error doing global join\n"); -out_hotplug_enable: - cpu_hotplug_enable(); - /* Take down CPUs not online prior to suspend */ - cpuret = rtas_offline_cpus_mask(offline_mask); - if (cpuret) - pr_warn("%s: Could not restore CPUs to offline state.\n", - __func__); + cpu_hotplug_enable(); -out: unlock_device_hotplug(); - free_cpumask_var(offline_mask); + return atomic_read(&data.error); } #else /* CONFIG_PPC_PSERIES */ 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/traps.c b/arch/powerpc/kernel/traps.c index 014ff0701f24..9432fc6af28a 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -510,11 +510,11 @@ out: #ifdef CONFIG_PPC_BOOK3S_64 BUG_ON(get_paca()->in_nmi == 0); if (get_paca()->in_nmi > 1) - nmi_panic(regs, "Unrecoverable nested System Reset"); + die("Unrecoverable nested System Reset", regs, SIGABRT); #endif /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable System Reset"); + die("Unrecoverable System Reset", regs, SIGABRT); if (saved_hsrrs) { mtspr(SPRN_HSRR0, hsrr0); @@ -858,7 +858,7 @@ void machine_check_exception(struct pt_regs *regs) /* Must die if the interrupt is not recoverable */ if (!(regs->msr & MSR_RI)) - nmi_panic(regs, "Unrecoverable Machine check"); + die("Unrecoverable Machine check", regs, SIGBUS); return; diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index eae9ddaecbcf..efb1ba40274a 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -682,7 +682,7 @@ int vdso_getcpu_init(void) node = cpu_to_node(cpu); WARN_ON_ONCE(node > 0xffff); - val = (cpu & 0xfff) | ((node & 0xffff) << 16); + val = (cpu & 0xffff) | ((node & 0xffff) << 16); mtspr(SPRN_SPRG_VDSO_WRITE, val); get_paca()->sprg_vdso = val; diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index ec2547cc5ecb..1ff971f3b06f 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -867,7 +867,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 2d415c36a61d..9d7344835469 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -38,7 +38,8 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, /* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */ if (kvmhv_on_pseries()) return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr, - __pa(to), __pa(from), n); + (to != NULL) ? __pa(to): 0, + (from != NULL) ? __pa(from): 0, n); quadrant = 1; if (!pid) @@ -353,7 +354,13 @@ static struct kmem_cache *kvm_pmd_cache; static pte_t *kvmppc_pte_alloc(void) { - return kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + pte_t *pte; + + pte = kmem_cache_alloc(kvm_pte_cache, GFP_KERNEL); + /* pmd_populate() will only reference _pa(pte). */ + kmemleak_ignore(pte); + + return pte; } static void kvmppc_pte_free(pte_t *ptep) @@ -363,7 +370,13 @@ static void kvmppc_pte_free(pte_t *ptep) static pmd_t *kvmppc_pmd_alloc(void) { - return kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + pmd_t *pmd; + + pmd = kmem_cache_alloc(kvm_pmd_cache, GFP_KERNEL); + /* pud_populate() will only reference _pa(pmd). */ + kmemleak_ignore(pmd); + + return pmd; } static void kvmppc_pmd_free(pmd_t *pmdp) @@ -1091,6 +1104,11 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm, kvm->arch.lpid); gpa += PAGE_SIZE; } + /* + * Increase the mmu notifier sequence number to prevent any page + * fault that read the memslot earlier from writing a PTE. + */ + kvm->mmu_notifier_seq++; spin_unlock(&kvm->mmu_lock); } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 5834db0a54c6..03b947429e4d 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -74,6 +74,7 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, struct kvmppc_spapr_tce_iommu_table *stit, *tmp; struct iommu_table_group *table_group = NULL; + rcu_read_lock(); list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { table_group = iommu_group_get_iommudata(grp); @@ -88,7 +89,9 @@ extern void kvm_spapr_tce_release_iommu_group(struct kvm *kvm, kref_put(&stit->kref, kvm_spapr_tce_liobn_put); } } + cond_resched_rcu(); } + rcu_read_unlock(); } extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, @@ -106,12 +109,14 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!f.file) return -EBADF; + rcu_read_lock(); list_for_each_entry_rcu(stt, &kvm->arch.spapr_tce_tables, list) { if (stt == f.file->private_data) { found = true; break; } } + rcu_read_unlock(); fdput(f); @@ -144,6 +149,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!tbl) return -EINVAL; + rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { if (tbl != stit->tbl) continue; @@ -151,14 +157,17 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, if (!kref_get_unless_zero(&stit->kref)) { /* stit is being destroyed */ iommu_tce_table_put(tbl); + rcu_read_unlock(); return -ENOTTY; } /* * The table is already known to this KVM, we just increased * its KVM reference counter and can return. */ + rcu_read_unlock(); return 0; } + rcu_read_unlock(); stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { @@ -364,18 +373,19 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt, if (kvmppc_tce_to_ua(stt->kvm, tce, &ua)) return H_TOO_HARD; + rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { unsigned long hpa = 0; struct mm_iommu_table_group_mem_t *mem; long shift = stit->tbl->it_page_shift; mem = mm_iommu_lookup(stt->kvm->mm, ua, 1ULL << shift); - if (!mem) - return H_TOO_HARD; - - if (mm_iommu_ua_to_hpa(mem, ua, shift, &hpa)) + if (!mem || mm_iommu_ua_to_hpa(mem, ua, shift, &hpa)) { + rcu_read_unlock(); return H_TOO_HARD; + } } + rcu_read_unlock(); return H_SUCCESS; } diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 0db937497169..cc90b8b82329 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -3,6 +3,8 @@ * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/kvm_ppc.h> @@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST; - case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST; - case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) } /* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 217246279dfa..fad931f224ef 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs; - switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1; - case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */ diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index 321db0fdb9db..7154bd424d24 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c index 84d5fab94f8f..1424a120710e 100644 --- a/arch/powerpc/mm/book3s32/mmu.c +++ b/arch/powerpc/mm/book3s32/mmu.c @@ -187,6 +187,7 @@ void mmu_mark_initmem_nx(void) int i; unsigned long base = (unsigned long)_stext - PAGE_OFFSET; unsigned long top = (unsigned long)_etext - PAGE_OFFSET; + unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET; unsigned long size; if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) @@ -201,9 +202,10 @@ void mmu_mark_initmem_nx(void) size = block_size(base, top); size = max(size, 128UL << 10); if ((top - base) > size) { - if (strict_kernel_rwx_enabled()) - pr_warn("Kernel _etext not properly aligned\n"); size <<= 1; + if (strict_kernel_rwx_enabled() && base + size > border) + pr_warn("Some RW data is getting mapped X. " + "Adjust CONFIG_DATA_SHIFT to avoid that.\n"); } setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT); base += size; diff --git a/arch/powerpc/mm/book3s64/iommu_api.c b/arch/powerpc/mm/book3s64/iommu_api.c index 56cc84520577..ef164851738b 100644 --- a/arch/powerpc/mm/book3s64/iommu_api.c +++ b/arch/powerpc/mm/book3s64/iommu_api.c @@ -121,24 +121,6 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua, goto free_exit; } - pageshift = PAGE_SHIFT; - for (i = 0; i < entries; ++i) { - struct page *page = mem->hpages[i]; - - /* - * Allow to use larger than 64k IOMMU pages. Only do that - * if we are backed by hugetlb. - */ - if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) - pageshift = page_shift(compound_head(page)); - mem->pageshift = min(mem->pageshift, pageshift); - /* - * We don't need struct page reference any more, switch - * to physical address. - */ - mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; - } - good_exit: atomic64_set(&mem->mapped, 1); mem->used = 1; @@ -158,6 +140,27 @@ good_exit: } } + if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) { + /* + * Allow to use larger than 64k IOMMU pages. Only do that + * if we are backed by hugetlb. Skip device memory as it is not + * backed with page structs. + */ + pageshift = PAGE_SHIFT; + for (i = 0; i < entries; ++i) { + struct page *page = mem->hpages[i]; + + if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) + pageshift = page_shift(compound_head(page)); + mem->pageshift = min(mem->pageshift, pageshift); + /* + * We don't need struct page reference any more, switch + * to physical address. + */ + mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT; + } + } + list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list); mutex_unlock(&mem_list_mutex); diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index ae7fca40e5b3..432fd9fa8c3f 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -83,13 +83,17 @@ static int pkey_initialize(void) scan_pkey_feature(); /* - * Let's assume 32 pkeys on P8 bare metal, if its not defined by device - * tree. We make this exception since skiboot forgot to expose this - * property on power8. + * Let's assume 32 pkeys on P8/P9 bare metal, if its not defined by device + * tree. We make this exception since some version of skiboot forgot to + * expose this property on power8/9. */ - if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR) && - cpu_has_feature(CPU_FTRS_POWER8)) - pkeys_total = 32; + if (!pkeys_devtree_defined && !firmware_has_feature(FW_FEATURE_LPAR)) { + unsigned long pvr = mfspr(SPRN_PVR); + + if (PVR_VER(pvr) == PVR_POWER8 || PVR_VER(pvr) == PVR_POWER8E || + PVR_VER(pvr) == PVR_POWER8NVL || PVR_VER(pvr) == PVR_POWER9) + pkeys_total = 32; + } /* * Adjust the upper limit, based on the number of bits supported by @@ -367,12 +371,14 @@ static bool pkey_access_permitted(int pkey, bool write, bool execute) return true; pkey_shift = pkeyshift(pkey); - if (execute && !(read_iamr() & (IAMR_EX_BIT << pkey_shift))) - return true; + if (execute) + return !(read_iamr() & (IAMR_EX_BIT << pkey_shift)); + + amr = read_amr(); + if (write) + return !(amr & (AMR_WR_BIT << pkey_shift)); - amr = read_amr(); /* Delay reading amr until absolutely needed */ - return ((!write && !(amr & (AMR_RD_BIT << pkey_shift))) || - (write && !(amr & (AMR_WR_BIT << pkey_shift)))); + return !(amr & (AMR_RD_BIT << pkey_shift)); } bool arch_pte_access_permitted(u64 pte, bool write, bool execute) diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 6ee17d09649c..770542ccdb46 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -643,21 +643,6 @@ void radix__mmu_cleanup_all(void) } } -void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) -{ - /* - * We don't currently support the first MEMBLOCK not mapping 0 - * physical on those processors - */ - BUG_ON(first_memblock_base != 0); - - /* - * Radix mode is not limited by RMA / VRMA addressing. - */ - ppc64_rma_size = ULONG_MAX; -} - #ifdef CONFIG_MEMORY_HOTPLUG static void free_pte_table(pte_t *pte_start, pmd_t *pmd) { diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 67af871190c6..b0f240afffa2 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -639,19 +639,29 @@ 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); } @@ -666,7 +676,6 @@ 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) diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c index 59327cefbc6a..873fcfc7b875 100644 --- a/arch/powerpc/mm/drmem.c +++ b/arch/powerpc/mm/drmem.c @@ -362,10 +362,8 @@ 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) @@ -410,8 +408,6 @@ 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/fault.c b/arch/powerpc/mm/fault.c index 881a026a603a..187047592d53 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -241,6 +241,9 @@ static bool bad_kernel_fault(struct pt_regs *regs, unsigned long error_code, return false; } +// This comes from 64-bit struct rt_sigframe + __SIGNAL_FRAMESIZE +#define SIGFRAME_MAX_SIZE (4096 + 128) + static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, struct vm_area_struct *vma, unsigned int flags, bool *must_retry) @@ -248,7 +251,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, /* * N.B. The POWER/Open ABI allows programs to access up to * 288 bytes below the stack pointer. - * The kernel signal delivery code writes up to about 1.5kB + * The kernel signal delivery code writes a bit over 4KB * below the stack pointer (r1) before decrementing it. * The exec code can write slightly over 640kB to the stack * before setting the user r1. Thus we allow the stack to @@ -273,7 +276,7 @@ static bool bad_stack_expansion(struct pt_regs *regs, unsigned long address, * between the last mapped region and the stack will * expand the stack rather than segfaulting. */ - if (address + 2048 >= uregs->gpr[1]) + if (address + SIGFRAME_MAX_SIZE >= uregs->gpr[1]) return false; if ((flags & FAULT_FLAG_WRITE) && (flags & FAULT_FLAG_USER) && diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c index 4e08246acd79..210f1c28b8e4 100644 --- a/arch/powerpc/mm/init_64.c +++ b/arch/powerpc/mm/init_64.c @@ -415,9 +415,16 @@ void __init mmu_early_init_devtree(void) if (!(mfmsr() & MSR_HV)) early_check_vec5(); - if (early_radix_enabled()) + if (early_radix_enabled()) { radix__early_init_devtree(); - else + /* + * We have finalized the translation we are going to use by now. + * Radix mode is not limited by RMA / VRMA addressing. + * Hence don't limit memblock allocations. + */ + ppc64_rma_size = ULONG_MAX; + memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE); + } else hash__early_init_devtree(); } #endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 784cae9f5697..da9f722d9f16 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -207,7 +207,7 @@ void mark_initmem_nx(void) unsigned long numpages = PFN_UP((unsigned long)_einittext) - PFN_DOWN((unsigned long)_sinittext); - if (v_block_mapped((unsigned long)_stext + 1)) + if (v_block_mapped((unsigned long)_sinittext)) mmu_mark_initmem_nx(); else change_page_attr(page, numpages, PAGE_KERNEL); @@ -219,7 +219,7 @@ void mark_rodata_ro(void) struct page *page; unsigned long numpages; - if (v_block_mapped((unsigned long)_sinittext)) { + if (v_block_mapped((unsigned long)_stext + 1)) { mmu_mark_rodata_ro(); ptdump_check_wx(); return; diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c index a07278027c6f..a2e8c3b2cf35 100644 --- a/arch/powerpc/mm/ptdump/hashpagetable.c +++ b/arch/powerpc/mm/ptdump/hashpagetable.c @@ -259,7 +259,7 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 * for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) { lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes); - if (lpar_rc != H_SUCCESS) + if (lpar_rc) continue; for (j = 0; j < 4; j++) { if (HPTE_V_COMPARE(ptes[j].v, want_v) && diff --git a/arch/powerpc/mm/ptdump/shared.c b/arch/powerpc/mm/ptdump/shared.c index f7ed2f187cb0..784f8df17f73 100644 --- a/arch/powerpc/mm/ptdump/shared.c +++ b/arch/powerpc/mm/ptdump/shared.c @@ -31,6 +31,11 @@ static const struct flag_info flag_array[] = { .set = "present", .clear = " ", }, { + .mask = _PAGE_COHERENT, + .val = _PAGE_COHERENT, + .set = "coherent", + .clear = " ", + }, { .mask = _PAGE_GUARDED, .val = _PAGE_GUARDED, .set = "guarded", diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index ca92e01d0bd1..f582aa2d9807 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1522,9 +1522,16 @@ nocheck: ret = 0; out: if (has_branch_stack(event)) { - power_pmu_bhrb_enable(event); - cpuhw->bhrb_filter = ppmu->bhrb_filter_map( - event->attr.branch_sample_type); + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( + event->attr.branch_sample_type); + + if (bhrb_filter != -1) { + cpuhw->bhrb_filter = bhrb_filter; + power_pmu_bhrb_enable(event); + } } perf_pmu_enable(event->pmu); @@ -1846,7 +1853,6 @@ static int power_pmu_event_init(struct perf_event *event) int n; int err; struct cpu_hw_events *cpuhw; - u64 bhrb_filter; if (!ppmu) return -ENOENT; @@ -1952,7 +1958,10 @@ static int power_pmu_event_init(struct perf_event *event) err = power_check_constraints(cpuhw, events, cflags, n + 1); if (has_branch_stack(event)) { - bhrb_filter = ppmu->bhrb_filter_map( + u64 bhrb_filter = -1; + + if (ppmu->bhrb_filter_map) + bhrb_filter = ppmu->bhrb_filter_map( event->attr.branch_sample_type); if (bhrb_filter == -1) { @@ -2106,6 +2115,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val, if (perf_event_overflow(event, &data, regs)) power_pmu_stop(event, 0); + } else if (period) { + /* Account for interrupt in case of invalid SIAR */ + if (perf_event_account_interrupt(event)) + power_pmu_stop(event, 0); } } diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c index 573e0b309c0c..48e8f4b17b91 100644 --- a/arch/powerpc/perf/hv-24x7.c +++ b/arch/powerpc/perf/hv-24x7.c @@ -1400,16 +1400,6 @@ static void h_24x7_event_read(struct perf_event *event) h24x7hw = &get_cpu_var(hv_24x7_hw); h24x7hw->events[i] = event; put_cpu_var(h24x7hw); - /* - * Clear the event count so we can compute the _change_ - * in the 24x7 raw counter value at the end of the txn. - * - * Note that we could alternatively read the 24x7 value - * now and save its value in event->hw.prev_count. But - * that would require issuing a hcall, which would then - * defeat the purpose of using the txn interface. - */ - local64_set(&event->count, 0); } put_cpu_var(hv_24x7_reqb); 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/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index cb50a9e1fd2d..eb82dda884e5 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -44,6 +44,16 @@ static DEFINE_PER_CPU(u64 *, trace_imc_mem); static struct imc_pmu_ref *trace_imc_refc; static int trace_imc_mem_size; +/* + * Global data structure used to avoid races between thread, + * core and trace-imc + */ +static struct imc_pmu_ref imc_global_refc = { + .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .id = 0, + .refc = 0, +}; + static struct imc_pmu *imc_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct imc_pmu, pmu); @@ -698,6 +708,16 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) return -EINVAL; ref->refc = 0; + /* + * Reduce the global reference count, if this is the + * last cpu in this core and core-imc event running + * in this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_CORE) + imc_global_refc.refc--; + + mutex_unlock(&imc_global_refc.lock); } return 0; } @@ -710,6 +730,23 @@ static int core_imc_pmu_cpumask_init(void) ppc_core_imc_cpu_offline); } +static void reset_global_refc(struct perf_event *event) +{ + mutex_lock(&imc_global_refc.lock); + imc_global_refc.refc--; + + /* + * If no other thread is running any + * event for this domain(thread/core/trace), + * set the global id to zero. + */ + if (imc_global_refc.refc <= 0) { + imc_global_refc.refc = 0; + imc_global_refc.id = 0; + } + mutex_unlock(&imc_global_refc.lock); +} + static void core_imc_counters_release(struct perf_event *event) { int rc, core_id; @@ -759,6 +796,8 @@ static void core_imc_counters_release(struct perf_event *event) ref->refc = 0; } mutex_unlock(&ref->lock); + + reset_global_refc(event); } static int core_imc_event_init(struct perf_event *event) @@ -819,6 +858,29 @@ static int core_imc_event_init(struct perf_event *event) ++ref->refc; mutex_unlock(&ref->lock); + /* + * Since the system can run either in accumulation or trace-mode + * of IMC at a time, core-imc events are allowed only if no other + * trace/thread imc events are enabled/monitored. + * + * Take the global lock, and check the refc.id + * to know whether any other trace/thread imc + * events are running. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { + /* + * No other trace/thread imc events are running in + * the system, so set the refc.id to core-imc. + */ + imc_global_refc.id = IMC_DOMAIN_CORE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; return 0; @@ -877,7 +939,23 @@ static int ppc_thread_imc_cpu_online(unsigned int cpu) static int ppc_thread_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * Set the bit 0 of LDBAR to zero. + * + * If bit 0 of LDBAR is unset, it will stop posting + * the counter data to memory. + * For thread-imc, bit 0 of LDBAR will be set to 1 in the + * event_add function. So reset this bit here, to stop the updates + * to memory in the cpu_offline path. + */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + + /* Reduce the refc if thread-imc event running on this cpu */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_THREAD) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -916,7 +994,22 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; + mutex_lock(&imc_global_refc.lock); + /* + * Check if any other trace/core imc events are running in the + * system, if not set the global id to thread-imc. + */ + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_THREAD) { + imc_global_refc.id = IMC_DOMAIN_THREAD; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + mutex_unlock(&imc_global_refc.lock); + event->pmu->task_ctx_nr = perf_sw_context; + event->destroy = reset_global_refc; return 0; } @@ -1063,10 +1156,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) int core_id; struct imc_pmu_ref *ref; - mtspr(SPRN_LDBAR, 0); - core_id = smp_processor_id() / threads_per_core; ref = &core_imc_refc[core_id]; + if (!ref) { + pr_debug("imc: Failed to get event reference count\n"); + return; + } mutex_lock(&ref->lock); ref->refc--; @@ -1082,6 +1177,10 @@ static void thread_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + + /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); + /* * Take a snapshot and calculate the delta and update * the event counter values. @@ -1133,7 +1232,18 @@ static int ppc_trace_imc_cpu_online(unsigned int cpu) static int ppc_trace_imc_cpu_offline(unsigned int cpu) { - mtspr(SPRN_LDBAR, 0); + /* + * No need to set bit 0 of LDBAR to zero, as + * it is set to zero for imc trace-mode + * + * Reduce the refc if any trace-imc event running + * on this cpu. + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == IMC_DOMAIN_TRACE) + imc_global_refc.refc--; + mutex_unlock(&imc_global_refc.lock); + return 0; } @@ -1226,15 +1336,14 @@ static int trace_imc_event_add(struct perf_event *event, int flags) local_mem = get_trace_imc_event_base_addr(); ldbar_value = ((u64)local_mem & THREAD_IMC_LDBAR_MASK) | TRACE_IMC_ENABLE; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + /* trace-imc reference count */ + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return -EINVAL; + pr_debug("imc: Failed to get the event reference count\n"); + return -EINVAL; } + mtspr(SPRN_LDBAR, ldbar_value); mutex_lock(&ref->lock); if (ref->refc == 0) { @@ -1242,13 +1351,11 @@ static int trace_imc_event_add(struct perf_event *event, int flags) get_hard_smp_processor_id(smp_processor_id()))) { mutex_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); - mtspr(SPRN_LDBAR, 0); return -EINVAL; } } ++ref->refc; mutex_unlock(&ref->lock); - return 0; } @@ -1274,16 +1381,13 @@ static void trace_imc_event_del(struct perf_event *event, int flags) int core_id = smp_processor_id() / threads_per_core; struct imc_pmu_ref *ref = NULL; - if (core_imc_refc) - ref = &core_imc_refc[core_id]; + if (trace_imc_refc) + ref = &trace_imc_refc[core_id]; if (!ref) { - /* If core-imc is not enabled, use trace-imc reference count */ - if (trace_imc_refc) - ref = &trace_imc_refc[core_id]; - if (!ref) - return; + pr_debug("imc: Failed to get event reference count\n"); + return; } - mtspr(SPRN_LDBAR, 0); + mutex_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { @@ -1297,6 +1401,7 @@ static void trace_imc_event_del(struct perf_event *event, int flags) ref->refc = 0; } mutex_unlock(&ref->lock); + trace_imc_event_stop(event, flags); } @@ -1314,10 +1419,30 @@ static int trace_imc_event_init(struct perf_event *event) if (event->attr.sample_period == 0) return -ENOENT; + /* + * Take the global lock, and make sure + * no other thread is running any core/thread imc + * events + */ + mutex_lock(&imc_global_refc.lock); + if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { + /* + * No core/thread imc events are running in the + * system, so set the refc.id to trace-imc. + */ + imc_global_refc.id = IMC_DOMAIN_TRACE; + imc_global_refc.refc++; + } else { + mutex_unlock(&imc_global_refc.lock); + return -EBUSY; + } + 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; return 0; } @@ -1429,10 +1554,10 @@ static void cleanup_all_core_imc_memory(void) static void thread_imc_ldbar_disable(void *dummy) { /* - * By Zeroing LDBAR, we disable thread-imc - * updates. + * By setting 0th bit of LDBAR to zero, we disable thread-imc + * updates to memory. */ - mtspr(SPRN_LDBAR, 0); + mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); } void thread_imc_disable(void) diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c index 4c86da5eb28a..0b5c8f4fbdbf 100644 --- a/arch/powerpc/perf/isa207-common.c +++ b/arch/powerpc/perf/isa207-common.c @@ -269,6 +269,15 @@ 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) { @@ -335,6 +344,7 @@ 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/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index e6e2adcc7b64..c13d64c3b019 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -1242,7 +1242,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) if (mbase == NULL) { printk(KERN_ERR "%pOF: Can't map internal config space !", port->node); - goto done; + return; } while (attempt && (0 == (in_le32(mbase + PECFG_460SX_DLLSTA) @@ -1252,9 +1252,7 @@ static void __init ppc460sx_pciex_check_link(struct ppc4xx_pciex_port *port) } if (attempt) port->link = 1; -done: iounmap(mbase); - } static struct ppc4xx_pciex_hwops ppc460sx_pcie_hwops __initdata = { diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index d82e3664ffdf..18792a5b003a 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -219,12 +219,11 @@ 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 @@ -232,12 +231,7 @@ 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/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig index 0f7c8241912b..f2ff359041ee 100644 --- a/arch/powerpc/platforms/cell/Kconfig +++ b/arch/powerpc/platforms/cell/Kconfig @@ -44,6 +44,7 @@ config SPU_FS tristate "SPU file system" default m depends on PPC_CELL + depends on COREDUMP select SPU_BASE help The SPU file system is used to access Synergistic Processing diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index c0f950a3f4e1..f4a4dfb191e7 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1978,8 +1978,9 @@ static ssize_t __spufs_mbox_info_read(struct spu_context *ctx, static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { - int ret; struct spu_context *ctx = file->private_data; + u32 stat, data; + int ret; if (!access_ok(buf, len)) return -EFAULT; @@ -1988,11 +1989,16 @@ static ssize_t spufs_mbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_mbox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.prob.pu_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the mbox */ + if (!(stat & 0x0000ff)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_mbox_info_fops = { @@ -2019,6 +2025,7 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + u32 stat, data; int ret; if (!access_ok(buf, len)) @@ -2028,11 +2035,16 @@ static ssize_t spufs_ibox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_ibox_info_read(ctx, buf, len, pos); + stat = ctx->csa.prob.mb_stat_R; + data = ctx->csa.priv2.puint_mb_R; spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + /* EOF if there's no entry in the ibox */ + if (!(stat & 0xff0000)) + return 0; + + return simple_read_from_buffer(buf, len, pos, &data, sizeof(data)); } static const struct file_operations spufs_ibox_info_fops = { @@ -2041,6 +2053,11 @@ static const struct file_operations spufs_ibox_info_fops = { .llseek = generic_file_llseek, }; +static size_t spufs_wbox_info_cnt(struct spu_context *ctx) +{ + return (4 - ((ctx->csa.prob.mb_stat_R & 0x00ff00) >> 8)) * sizeof(u32); +} + static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { @@ -2049,7 +2066,7 @@ static ssize_t __spufs_wbox_info_read(struct spu_context *ctx, u32 wbox_stat; wbox_stat = ctx->csa.prob.mb_stat_R; - cnt = 4 - ((wbox_stat & 0x00ff00) >> 8); + cnt = spufs_wbox_info_cnt(ctx); for (i = 0; i < cnt; i++) { data[i] = ctx->csa.spu_mailbox_data[i]; } @@ -2062,7 +2079,8 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; - int ret; + u32 data[ARRAY_SIZE(ctx->csa.spu_mailbox_data)]; + int ret, count; if (!access_ok(buf, len)) return -EFAULT; @@ -2071,11 +2089,13 @@ static ssize_t spufs_wbox_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_wbox_info_read(ctx, buf, len, pos); + count = spufs_wbox_info_cnt(ctx); + memcpy(&data, &ctx->csa.spu_mailbox_data, sizeof(data)); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &data, + count * sizeof(u32)); } static const struct file_operations spufs_wbox_info_fops = { @@ -2084,27 +2104,33 @@ static const struct file_operations spufs_wbox_info_fops = { .llseek = generic_file_llseek, }; -static ssize_t __spufs_dma_info_read(struct spu_context *ctx, - char __user *buf, size_t len, loff_t *pos) +static void spufs_get_dma_info(struct spu_context *ctx, + struct spu_dma_info *info) { - struct spu_dma_info info; - struct mfc_cq_sr *qp, *spuqp; int i; - info.dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; - info.dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; - info.dma_info_status = ctx->csa.spu_chnldata_RW[24]; - info.dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; - info.dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; + info->dma_info_type = ctx->csa.priv2.spu_tag_status_query_RW; + info->dma_info_mask = ctx->csa.lscsa->tag_mask.slot[0]; + info->dma_info_status = ctx->csa.spu_chnldata_RW[24]; + info->dma_info_stall_and_notify = ctx->csa.spu_chnldata_RW[25]; + info->dma_info_atomic_command_status = ctx->csa.spu_chnldata_RW[27]; for (i = 0; i < 16; i++) { - qp = &info.dma_info_command_data[i]; - spuqp = &ctx->csa.priv2.spuq[i]; + struct mfc_cq_sr *qp = &info->dma_info_command_data[i]; + struct mfc_cq_sr *spuqp = &ctx->csa.priv2.spuq[i]; qp->mfc_cq_data0_RW = spuqp->mfc_cq_data0_RW; qp->mfc_cq_data1_RW = spuqp->mfc_cq_data1_RW; qp->mfc_cq_data2_RW = spuqp->mfc_cq_data2_RW; qp->mfc_cq_data3_RW = spuqp->mfc_cq_data3_RW; } +} + +static ssize_t __spufs_dma_info_read(struct spu_context *ctx, + char __user *buf, size_t len, loff_t *pos) +{ + struct spu_dma_info info; + + spufs_get_dma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2114,6 +2140,7 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_dma_info info; int ret; if (!access_ok(buf, len)) @@ -2123,11 +2150,12 @@ static ssize_t spufs_dma_info_read(struct file *file, char __user *buf, if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_dma_info_read(ctx, buf, len, pos); + spufs_get_dma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_dma_info_fops = { @@ -2136,13 +2164,31 @@ static const struct file_operations spufs_dma_info_fops = { .llseek = no_llseek, }; +static void spufs_get_proxydma_info(struct spu_context *ctx, + struct spu_proxydma_info *info) +{ + int i; + + info->proxydma_info_type = ctx->csa.prob.dma_querytype_RW; + info->proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; + info->proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; + + for (i = 0; i < 8; i++) { + struct mfc_cq_sr *qp = &info->proxydma_info_command_data[i]; + struct mfc_cq_sr *puqp = &ctx->csa.priv2.puq[i]; + + qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; + qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; + qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; + qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; + } +} + static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, char __user *buf, size_t len, loff_t *pos) { struct spu_proxydma_info info; - struct mfc_cq_sr *qp, *puqp; int ret = sizeof info; - int i; if (len < ret) return -EINVAL; @@ -2150,18 +2196,7 @@ static ssize_t __spufs_proxydma_info_read(struct spu_context *ctx, if (!access_ok(buf, len)) return -EFAULT; - info.proxydma_info_type = ctx->csa.prob.dma_querytype_RW; - info.proxydma_info_mask = ctx->csa.prob.dma_querymask_RW; - info.proxydma_info_status = ctx->csa.prob.dma_tagstatus_R; - for (i = 0; i < 8; i++) { - qp = &info.proxydma_info_command_data[i]; - puqp = &ctx->csa.priv2.puq[i]; - - qp->mfc_cq_data0_RW = puqp->mfc_cq_data0_RW; - qp->mfc_cq_data1_RW = puqp->mfc_cq_data1_RW; - qp->mfc_cq_data2_RW = puqp->mfc_cq_data2_RW; - qp->mfc_cq_data3_RW = puqp->mfc_cq_data3_RW; - } + spufs_get_proxydma_info(ctx, &info); return simple_read_from_buffer(buf, len, pos, &info, sizeof info); @@ -2171,17 +2206,19 @@ static ssize_t spufs_proxydma_info_read(struct file *file, char __user *buf, size_t len, loff_t *pos) { struct spu_context *ctx = file->private_data; + struct spu_proxydma_info info; int ret; ret = spu_acquire_saved(ctx); if (ret) return ret; spin_lock(&ctx->csa.register_lock); - ret = __spufs_proxydma_info_read(ctx, buf, len, pos); + spufs_get_proxydma_info(ctx, &info); spin_unlock(&ctx->csa.register_lock); spu_release_saved(ctx); - return ret; + return simple_read_from_buffer(buf, len, pos, &info, + sizeof(info)); } static const struct file_operations spufs_proxydma_info_fops = { diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c index 543c816fa99e..0e6693bacb7e 100644 --- a/arch/powerpc/platforms/powernv/opal-dump.c +++ b/arch/powerpc/platforms/powernv/opal-dump.c @@ -318,15 +318,14 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj, return count; } -static struct dump_obj *create_dump_obj(uint32_t id, size_t size, - uint32_t type) +static void create_dump_obj(uint32_t id, size_t size, uint32_t type) { struct dump_obj *dump; int rc; dump = kzalloc(sizeof(*dump), GFP_KERNEL); if (!dump) - return NULL; + return; dump->kobj.kset = dump_kset; @@ -346,21 +345,39 @@ static struct dump_obj *create_dump_obj(uint32_t id, size_t size, rc = kobject_add(&dump->kobj, NULL, "0x%x-0x%x", type, id); if (rc) { kobject_put(&dump->kobj); - return NULL; + return; } + /* + * As soon as the sysfs file for this dump is created/activated there is + * a chance the opal_errd daemon (or any userspace) might read and + * acknowledge the dump before kobject_uevent() is called. If that + * happens then there is a potential race between + * dump_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(&dump->kobj); rc = sysfs_create_bin_file(&dump->kobj, &dump->dump_attr); - if (rc) { + if (rc == 0) { + kobject_uevent(&dump->kobj, KOBJ_ADD); + + pr_info("%s: New platform dump. ID = 0x%x Size %u\n", + __func__, dump->id, dump->size); + } else { + /* Drop reference count taken for bin file */ kobject_put(&dump->kobj); - return NULL; } - pr_info("%s: New platform dump. ID = 0x%x Size %u\n", - __func__, dump->id, dump->size); - - kobject_uevent(&dump->kobj, KOBJ_ADD); - - return dump; + /* Drop our reference */ + kobject_put(&dump->kobj); + return; } static irqreturn_t process_dump(int irq, void *data) diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c index 13e251699346..b2ba3e95bda7 100644 --- a/arch/powerpc/platforms/powernv/smp.c +++ b/arch/powerpc/platforms/powernv/smp.c @@ -167,7 +167,6 @@ static void pnv_smp_cpu_kill_self(void) /* Standard hot unplug procedure */ idle_task_exit(); - current->active_mm = NULL; /* for sanity */ cpu = smp_processor_id(); DBG("CPU%d offline\n", cpu); generic_set_cpu_dead(cpu); diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 423be34f0f5f..f42fe4e86ce5 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -200,13 +200,14 @@ void ps3_mm_vas_destroy(void) { int result; - DBG("%s:%d: map.vas_id = %llu\n", __func__, __LINE__, map.vas_id); - if (map.vas_id) { result = lv1_select_virtual_address_space(0); - BUG_ON(result); - result = lv1_destruct_virtual_address_space(map.vas_id); - BUG_ON(result); + result += lv1_destruct_virtual_address_space(map.vas_id); + + if (result) { + lv1_panic(0); + } + map.vas_id = 0; } } @@ -304,19 +305,20 @@ static void ps3_mm_region_destroy(struct mem_region *r) int result; if (!r->destroy) { - pr_info("%s:%d: Not destroying high region: %llxh %llxh\n", - __func__, __LINE__, r->base, r->size); return; } - DBG("%s:%d: r->base = %llxh\n", __func__, __LINE__, r->base); - if (r->base) { result = lv1_release_memory(r->base); - BUG_ON(result); + + if (result) { + lv1_panic(0); + } + r->size = r->base = r->offset = 0; map.total = map.rm.size; } + ps3_mm_set_repository_highmem(NULL); } diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index f1888352b4e0..66b32f46702d 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -27,7 +27,7 @@ static bool rtas_hp_event; unsigned long pseries_memory_block_size(void) { struct device_node *np; - unsigned int memblock_size = MIN_MEMORY_BLOCK_SIZE; + u64 memblock_size = MIN_MEMORY_BLOCK_SIZE; struct resource r; np = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory"); @@ -376,25 +376,32 @@ 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; @@ -651,7 +658,7 @@ 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; @@ -662,11 +669,13 @@ 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 address. */ + nid = memory_add_physaddr_to_nid(lmb->base_addr); + /* Add the memory */ - rc = __add_memory(lmb->nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; @@ -674,9 +683,8 @@ 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; } diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 753adeb624f2..b658fa627a34 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -184,7 +184,6 @@ static void handle_system_shutdown(char event_modifier) case EPOW_SHUTDOWN_ON_UPS: pr_emerg("Loss of system power detected. System is running on" " UPS/battery. Check RTAS error log for details\n"); - orderly_poweroff(true); break; case EPOW_SHUTDOWN_LOSS_OF_CRITICAL_FUNCTIONS: @@ -395,10 +394,11 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) /* * Some versions of FWNMI place the buffer inside the 4kB page starting at * 0x7000. Other versions place it inside the rtas buffer. We check both. + * Minimum size of the buffer is 16 bytes. */ #define VALID_FWNMI_BUFFER(A) \ - ((((A) >= 0x7000) && ((A) < 0x7ff0)) || \ - (((A) >= rtas.base) && ((A) < (rtas.base + rtas.size - 16)))) + ((((A) >= 0x7000) && ((A) <= 0x8000 - 16)) || \ + (((A) >= rtas.base) && ((A) <= (rtas.base + rtas.size - 16)))) static inline struct rtas_error_log *fwnmi_get_errlog(void) { @@ -494,18 +494,55 @@ int pSeries_system_reset_exception(struct pt_regs *regs) return 0; /* need to perform reset */ } +static int mce_handle_err_realmode(int disposition, u8 error_type) +{ +#ifdef CONFIG_PPC_BOOK3S_64 + if (disposition == RTAS_DISP_NOT_RECOVERED) { + switch (error_type) { + case MC_ERROR_TYPE_SLB: + case MC_ERROR_TYPE_ERAT: + /* + * Store the old slb content in paca before flushing. + * Print this when we go to virtual mode. + * There are chances that we may hit MCE again if there + * is a parity error on the SLB entry we trying to read + * for saving. Hence limit the slb saving to single + * level of recursion. + */ + if (local_paca->in_mce == 1) + slb_save_contents(local_paca->mce_faulty_slbs); + flush_and_reload_slb(); + disposition = RTAS_DISP_FULLY_RECOVERED; + break; + default: + break; + } + } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { + /* Platform corrected itself but could be degraded */ + pr_err("MCE: limited recovery, system may be degraded\n"); + disposition = RTAS_DISP_FULLY_RECOVERED; + } +#endif + return disposition; +} -static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +static int mce_handle_err_virtmode(struct pt_regs *regs, + struct rtas_error_log *errp, + struct pseries_mc_errorlog *mce_log, + int disposition) { struct mce_error_info mce_err = { 0 }; - unsigned long eaddr = 0, paddr = 0; - struct pseries_errorlog *pseries_log; - struct pseries_mc_errorlog *mce_log; - int disposition = rtas_error_disposition(errp); int initiator = rtas_error_initiator(errp); int severity = rtas_error_severity(errp); + unsigned long eaddr = 0, paddr = 0; u8 error_type, err_sub_type; + if (!mce_log) + goto out; + + error_type = mce_log->error_type; + err_sub_type = rtas_mc_error_sub_type(mce_log); + if (initiator == RTAS_INITIATOR_UNKNOWN) mce_err.initiator = MCE_INITIATOR_UNKNOWN; else if (initiator == RTAS_INITIATOR_CPU) @@ -544,18 +581,7 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; mce_err.error_class = MCE_ECLASS_UNKNOWN; - if (!rtas_error_extended(errp)) - goto out; - - pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); - if (pseries_log == NULL) - goto out; - - mce_log = (struct pseries_mc_errorlog *)pseries_log->data; - error_type = mce_log->error_type; - err_sub_type = rtas_mc_error_sub_type(mce_log); - - switch (mce_log->error_type) { + switch (error_type) { case MC_ERROR_TYPE_UE: mce_err.error_type = MCE_ERROR_TYPE_UE; switch (err_sub_type) { @@ -652,37 +678,31 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) mce_err.error_type = MCE_ERROR_TYPE_UNKNOWN; break; } +out: + save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, + &mce_err, regs->nip, eaddr, paddr); + return disposition; +} -#ifdef CONFIG_PPC_BOOK3S_64 - if (disposition == RTAS_DISP_NOT_RECOVERED) { - switch (error_type) { - case MC_ERROR_TYPE_SLB: - case MC_ERROR_TYPE_ERAT: - /* - * Store the old slb content in paca before flushing. - * Print this when we go to virtual mode. - * There are chances that we may hit MCE again if there - * is a parity error on the SLB entry we trying to read - * for saving. Hence limit the slb saving to single - * level of recursion. - */ - if (local_paca->in_mce == 1) - slb_save_contents(local_paca->mce_faulty_slbs); - flush_and_reload_slb(); - disposition = RTAS_DISP_FULLY_RECOVERED; - break; - default: - break; - } - } else if (disposition == RTAS_DISP_LIMITED_RECOVERY) { - /* Platform corrected itself but could be degraded */ - printk(KERN_ERR "MCE: limited recovery, system may " - "be degraded\n"); - disposition = RTAS_DISP_FULLY_RECOVERED; - } -#endif +static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp) +{ + struct pseries_errorlog *pseries_log; + struct pseries_mc_errorlog *mce_log = NULL; + int disposition = rtas_error_disposition(errp); + u8 error_type; + + if (!rtas_error_extended(errp)) + goto out; + + pseries_log = get_pseries_errorlog(errp, PSERIES_ELOG_SECT_ID_MCE); + if (!pseries_log) + goto out; + + mce_log = (struct pseries_mc_errorlog *)pseries_log->data; + error_type = mce_log->error_type; + + disposition = mce_handle_err_realmode(disposition, error_type); -out: /* * Enable translation as we will be accessing per-cpu variables * in save_mce_event() which may fall outside RMO region, also @@ -693,10 +713,10 @@ out: * Note: All the realmode handling like flushing SLB entries for * SLB multihit is done by now. */ +out: mtmsr(mfmsr() | MSR_IR | MSR_DR); - save_mce_event(regs, disposition == RTAS_DISP_FULLY_RECOVERED, - &mce_err, regs->nip, eaddr, paddr); - + disposition = mce_handle_err_virtmode(regs, errp, mce_log, + disposition); return disposition; } 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/suspend.c b/arch/powerpc/platforms/pseries/suspend.c index 0a24a5a185f0..f789693f61f4 100644 --- a/arch/powerpc/platforms/pseries/suspend.c +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -132,15 +132,11 @@ static ssize_t store_hibernate(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - cpumask_var_t offline_mask; int rc; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (!alloc_cpumask_var(&offline_mask, GFP_KERNEL)) - return -ENOMEM; - stream_id = simple_strtoul(buf, NULL, 16); do { @@ -150,32 +146,16 @@ static ssize_t store_hibernate(struct device *dev, } while (rc == -EAGAIN); if (!rc) { - /* All present CPUs must be online */ - cpumask_andnot(offline_mask, cpu_present_mask, - cpu_online_mask); - rc = rtas_online_cpus_mask(offline_mask); - if (rc) { - pr_err("%s: Could not bring present CPUs online.\n", - __func__); - goto out; - } - stop_topology_update(); rc = pm_suspend(PM_SUSPEND_MEM); start_topology_update(); - - /* Take down CPUs not online prior to suspend */ - if (!rtas_offline_cpus_mask(offline_mask)) - pr_warn("%s: Could not restore CPUs to offline " - "state.\n", __func__); } stream_id = 0; if (!rc) rc = count; -out: - free_cpumask_var(offline_mask); + return rc; } diff --git a/arch/powerpc/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/native.c b/arch/powerpc/sysdev/xive/native.c index 50e1a8e02497..3fd086533dcf 100644 --- a/arch/powerpc/sysdev/xive/native.c +++ b/arch/powerpc/sysdev/xive/native.c @@ -18,6 +18,7 @@ #include <linux/delay.h> #include <linux/cpumask.h> #include <linux/mm.h> +#include <linux/kmemleak.h> #include <asm/prom.h> #include <asm/io.h> @@ -646,6 +647,7 @@ static bool xive_native_provision_pages(void) pr_err("Failed to allocate provisioning page\n"); return false; } + kmemleak_ignore(p); opal_xive_donate_page(chip, __pa(p)); } return true; |