diff options
28 files changed, 214 insertions, 98 deletions
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index c6938e5..4da60b4 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -56,6 +56,7 @@ stable kernels. | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | +| Cavium | ThunderX ITS | #23144 | CAVIUM_ERRATUM_23144 | | Cavium | ThunderX GICv3 | #23154 | CAVIUM_ERRATUM_23154 | | Cavium | ThunderX Core | #27456 | CAVIUM_ERRATUM_27456 | | Cavium | ThunderX SMMUv2 | #27704 | N/A | diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c index ef9119f..4d93758 100644 --- a/arch/arm/kernel/ptrace.c +++ b/arch/arm/kernel/ptrace.c @@ -733,8 +733,8 @@ static int vfp_set(struct task_struct *target, if (ret) return ret; - vfp_flush_hwstate(thread); thread->vfpstate.hard = new_vfp; + vfp_flush_hwstate(thread); return 0; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 76747d9..5a0a691 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -113,6 +113,18 @@ config ARCH_PHYS_ADDR_T_64BIT config MMU def_bool y +config ARM64_PAGE_SHIFT + int + default 16 if ARM64_64K_PAGES + default 14 if ARM64_16K_PAGES + default 12 + +config ARM64_CONT_SHIFT + int + default 5 if ARM64_64K_PAGES + default 7 if ARM64_16K_PAGES + default 4 + config ARCH_MMAP_RND_BITS_MIN default 14 if ARM64_64K_PAGES default 16 if ARM64_16K_PAGES @@ -426,6 +438,15 @@ config CAVIUM_ERRATUM_22375 If unsure, say Y. +config CAVIUM_ERRATUM_23144 + bool "Cavium erratum 23144: ITS SYNC hang on dual socket system" + depends on NUMA + default y + help + ITS SYNC command hang for cross node io and collections/cpu mapping. + + If unsure, say Y. + config CAVIUM_ERRATUM_23154 bool "Cavium erratum 23154: Access to ICC_IAR1_EL1 is not sync'ed" default y diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index 710fde4..0cc758c 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -12,7 +12,8 @@ config ARM64_PTDUMP who are working in architecture specific areas of the kernel. It is probably not a good idea to enable this feature in a production kernel. - If in doubt, say "N" + + If in doubt, say N. config PID_IN_CONTEXTIDR bool "Write the current PID to the CONTEXTIDR register" @@ -38,15 +39,15 @@ config ARM64_RANDOMIZE_TEXT_OFFSET value. config DEBUG_SET_MODULE_RONX - bool "Set loadable kernel module data as NX and text as RO" - depends on MODULES - help - This option helps catch unintended modifications to loadable - kernel module's text and read-only data. It also prevents execution - of module data. Such protection may interfere with run-time code - patching and dynamic kernel tracing - and they might also protect - against certain classes of kernel exploits. - If in doubt, say "N". + bool "Set loadable kernel module data as NX and text as RO" + depends on MODULES + default y + help + Is this is set, kernel module text and rodata will be made read-only. + This is to help catch accidental or malicious attempts to change the + kernel's executable code. + + If in doubt, say Y. config DEBUG_RODATA bool "Make kernel text and rodata read-only" @@ -56,7 +57,7 @@ config DEBUG_RODATA is to help catch accidental or malicious attempts to change the kernel's executable code. - If in doubt, say Y + If in doubt, say Y. config DEBUG_ALIGN_RODATA depends on DEBUG_RODATA @@ -69,7 +70,7 @@ config DEBUG_ALIGN_RODATA alignment and potentially wasted space. Turn on this option if performance is more important than memory pressure. - If in doubt, say N + If in doubt, say N. source "drivers/hwtracing/coresight/Kconfig" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 354d754..7085e32 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -60,7 +60,9 @@ head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk 'BEGIN {srand(); printf "0x%03x000\n", int(512 * rand())}') +TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ + int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ + rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") else TEXT_OFFSET := 0x00080000 endif diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 7a09c48..579b6e6 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -160,14 +160,14 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12)) #endif -#ifdef CONFIG_COMPAT - #ifdef __AARCH64EB__ #define COMPAT_ELF_PLATFORM ("v8b") #else #define COMPAT_ELF_PLATFORM ("v8l") #endif +#ifdef CONFIG_COMPAT + #define COMPAT_ELF_ET_DYN_BASE (2 * TASK_SIZE_32 / 3) /* AArch32 registers. */ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 72a3025..31b7322 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -55,8 +55,9 @@ #define VMEMMAP_SIZE (UL(1) << (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT)) /* - * PAGE_OFFSET - the virtual address of the start of the kernel image (top + * PAGE_OFFSET - the virtual address of the start of the linear map (top * (VA_BITS - 1)) + * KIMAGE_VADDR - the virtual address of the start of the kernel image * VA_BITS - the maximum number of bits for virtual addresses. * VA_START - the first kernel virtual address. * TASK_SIZE - the maximum size of a user space task. diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index 17b45f7..8472c6d 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -23,16 +23,8 @@ /* PAGE_SHIFT determines the page size */ /* CONT_SHIFT determines the number of pages which can be tracked together */ -#ifdef CONFIG_ARM64_64K_PAGES -#define PAGE_SHIFT 16 -#define CONT_SHIFT 5 -#elif defined(CONFIG_ARM64_16K_PAGES) -#define PAGE_SHIFT 14 -#define CONT_SHIFT 7 -#else -#define PAGE_SHIFT 12 -#define CONT_SHIFT 4 -#endif +#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT +#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT #define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 0685d74..9e397a5 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -81,19 +81,6 @@ static inline void set_fs(mm_segment_t fs) #define segment_eq(a, b) ((a) == (b)) /* - * Return 1 if addr < current->addr_limit, 0 otherwise. - */ -#define __addr_ok(addr) \ -({ \ - unsigned long flag; \ - asm("cmp %1, %0; cset %0, lo" \ - : "=&r" (flag) \ - : "r" (addr), "0" (current_thread_info()->addr_limit) \ - : "cc"); \ - flag; \ -}) - -/* * Test whether a block of memory is a valid user space address. * Returns 1 if the range is valid, 0 otherwise. * diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 41e58fe..e78ac26 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 390 +#define __NR_compat_syscalls 394 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 5b925b7..b7e8ef1 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -801,6 +801,14 @@ __SYSCALL(__NR_execveat, compat_sys_execveat) __SYSCALL(__NR_userfaultfd, sys_userfaultfd) #define __NR_membarrier 389 __SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 390 +__SYSCALL(__NR_mlock2, sys_mlock2) +#define __NR_copy_file_range 391 +__SYSCALL(__NR_copy_file_range, sys_copy_file_range) +#define __NR_preadv2 392 +__SYSCALL(__NR_preadv2, compat_sys_preadv2) +#define __NR_pwritev2 393 +__SYSCALL(__NR_pwritev2, compat_sys_pwritev2) /* * Please add new compat syscalls above this comment and update diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 3808470..c173d32 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -22,6 +22,8 @@ #include <linux/bitops.h> #include <linux/bug.h> +#include <linux/compat.h> +#include <linux/elf.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/personality.h> @@ -104,6 +106,7 @@ static const char *const compat_hwcap2_str[] = { static int c_show(struct seq_file *m, void *v) { int i, j; + bool compat = personality(current->personality) == PER_LINUX32; for_each_online_cpu(i) { struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i); @@ -115,6 +118,9 @@ static int c_show(struct seq_file *m, void *v) * "processor". Give glibc what it expects. */ seq_printf(m, "processor\t: %d\n", i); + if (compat) + seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n", + MIDR_REVISION(midr), COMPAT_ELF_PLATFORM); seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", loops_per_jiffy / (500000UL/HZ), @@ -127,7 +133,7 @@ static int c_show(struct seq_file *m, void *v) * software which does already (at least for 32-bit). */ seq_puts(m, "Features\t:"); - if (personality(current->personality) == PER_LINUX32) { + if (compat) { #ifdef CONFIG_COMPAT for (j = 0; compat_hwcap_str[j]; j++) if (compat_elf_hwcap & (1 << j)) diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index c539208..f7cf463 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -477,8 +477,9 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __user *pc = (void __user *)instruction_pointer(regs); console_verbose(); - pr_crit("Bad mode in %s handler detected, code 0x%08x -- %s\n", - handler[reason], esr, esr_get_class_string(esr)); + pr_crit("Bad mode in %s handler detected on CPU%d, code 0x%08x -- %s\n", + handler[reason], smp_processor_id(), esr, + esr_get_class_string(esr)); __show_regs(regs); info.si_signo = SIGILL; diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 8404190..ccfde23 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -150,6 +150,7 @@ static const struct prot_bits pte_bits[] = { struct pg_level { const struct prot_bits *bits; + const char *name; size_t num; u64 mask; }; @@ -157,15 +158,19 @@ struct pg_level { static struct pg_level pg_level[] = { { }, { /* pgd */ + .name = "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pud */ + .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pmd */ + .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pte */ + .name = "PTE", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, @@ -214,7 +219,8 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, delta >>= 10; unit++; } - seq_printf(st->seq, "%9lu%c", delta, *unit); + seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); if (pg_level[st->level].bits) dump_prot(st, pg_level[st->level].bits, pg_level[st->level].num); diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index aa8aee7..2e49bd2 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -306,6 +306,10 @@ static __init int setup_hugepagesz(char *opt) hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else if (ps == (PAGE_SIZE * CONT_PTES)) { + hugetlb_add_hstate(CONT_PTE_SHIFT); + } else if (ps == (PMD_SIZE * CONT_PMDS)) { + hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { hugetlb_bad_size(); pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); @@ -314,3 +318,13 @@ static __init int setup_hugepagesz(char *opt) return 1; } __setup("hugepagesz=", setup_hugepagesz); + +#ifdef CONFIG_ARM64_64K_PAGES +static __init int add_default_hugepagesz(void) +{ + if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) + hugetlb_add_hstate(CONT_PMD_SHIFT); + return 0; +} +arch_initcall(add_default_hugepagesz); +#endif diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index c1e82e9..a0948f4 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -717,7 +717,7 @@ #define MMCR0_FCWAIT 0x00000002UL /* freeze counter in WAIT state */ #define MMCR0_FCHV 0x00000001UL /* freeze conditions in hypervisor mode */ #define SPRN_MMCR1 798 -#define SPRN_MMCR2 769 +#define SPRN_MMCR2 785 #define SPRN_MMCRA 0x312 #define MMCRA_SDSYNC 0x80000000UL /* SDAR synced with SIAR */ #define MMCRA_SDAR_DCACHE_MISS 0x40000000UL @@ -754,13 +754,13 @@ #define SPRN_PMC6 792 #define SPRN_PMC7 793 #define SPRN_PMC8 794 -#define SPRN_SIAR 780 -#define SPRN_SDAR 781 #define SPRN_SIER 784 #define SIER_SIPR 0x2000000 /* Sampled MSR_PR */ #define SIER_SIHV 0x1000000 /* Sampled MSR_HV */ #define SIER_SIAR_VALID 0x0400000 /* SIAR contents valid */ #define SIER_SDAR_VALID 0x0200000 /* SDAR contents valid */ +#define SPRN_SIAR 796 +#define SPRN_SDAR 797 #define SPRN_TACR 888 #define SPRN_TCSCR 889 #define SPRN_CSIGR 890 diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index da51925..ccd2037 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -656,6 +656,7 @@ unsigned char ibm_architecture_vec[] = { W(0xffff0000), W(0x003e0000), /* POWER6 */ W(0xffff0000), W(0x003f0000), /* POWER7 */ W(0xffff0000), W(0x004b0000), /* POWER8E */ + W(0xffff0000), W(0x004c0000), /* POWER8NVL */ W(0xffff0000), W(0x004d0000), /* POWER8 */ W(0xffffffff), W(0x0f000004), /* all 2.07-compliant */ W(0xffffffff), W(0x0f000003), /* all 2.06-compliant */ diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c index 5926896..b2740c6 100644 --- a/arch/powerpc/mm/hash_utils_64.c +++ b/arch/powerpc/mm/hash_utils_64.c @@ -159,6 +159,19 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = { }, }; +/* + * 'R' and 'C' update notes: + * - Under pHyp or KVM, the updatepp path will not set C, thus it *will* + * create writeable HPTEs without C set, because the hcall H_PROTECT + * that we use in that case will not update C + * - The above is however not a problem, because we also don't do that + * fancy "no flush" variant of eviction and we use H_REMOVE which will + * do the right thing and thus we don't have the race I described earlier + * + * - Under bare metal, we do have the race, so we need R and C set + * - We make sure R is always set and never lost + * - C is _PAGE_DIRTY, and *should* always be set for a writeable mapping + */ unsigned long htab_convert_pte_flags(unsigned long pteflags) { unsigned long rflags = 0; @@ -186,9 +199,14 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags) rflags |= 0x1; } /* - * Always add "C" bit for perf. Memory coherence is always enabled + * We can't allow hardware to update hpte bits. Hence always + * set 'R' bit and set 'C' if it is a write fault + * Memory coherence is always enabled */ - rflags |= HPTE_R_C | HPTE_R_M; + rflags |= HPTE_R_R | HPTE_R_M; + + if (pteflags & _PAGE_DIRTY) + rflags |= HPTE_R_C; /* * Add in WIG bits */ diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index eb44511..6703187 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -33,10 +33,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, changed = !pmd_same(*(pmdp), entry); if (changed) { __ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry)); - /* - * Since we are not supporting SW TLB systems, we don't - * have any thing similar to flush_tlb_page_nohash() - */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } return changed; } diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c index 18b2c11..c939e6e 100644 --- a/arch/powerpc/mm/pgtable-radix.c +++ b/arch/powerpc/mm/pgtable-radix.c @@ -296,11 +296,6 @@ found: void __init radix__early_init_mmu(void) { unsigned long lpcr; - /* - * setup LPCR UPRT based on mmu_features - */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); #ifdef CONFIG_PPC_64K_PAGES /* PAGE_SIZE mappings */ @@ -343,8 +338,11 @@ void __init radix__early_init_mmu(void) __pte_frag_size_shift = H_PTE_FRAG_SIZE_SHIFT; radix_init_page_sizes(); - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); radix_init_partition_table(); + } radix_init_pgtable(); } @@ -353,16 +351,15 @@ void radix__early_init_mmu_secondary(void) { unsigned long lpcr; /* - * setup LPCR UPRT based on mmu_features + * update partition table control register and UPRT */ - lpcr = mfspr(SPRN_LPCR); - mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); - /* - * update partition table control register, 64 K size. - */ - if (!firmware_has_feature(FW_FEATURE_LPAR)) + if (!firmware_has_feature(FW_FEATURE_LPAR)) { + lpcr = mfspr(SPRN_LPCR); + mtspr(SPRN_LPCR, lpcr | LPCR_UPRT); + mtspr(SPRN_PTCR, __pa(partition_tb) | (PATB_SIZE_SHIFT - 12)); + } } void radix__setup_initial_memory_limit(phys_addr_t first_memblock_base, diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index ac3ffd9..3998e0f 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -53,7 +53,6 @@ static int ibm_read_slot_reset_state2; static int ibm_slot_error_detail; static int ibm_get_config_addr_info; static int ibm_get_config_addr_info2; -static int ibm_configure_bridge; static int ibm_configure_pe; /* @@ -81,7 +80,14 @@ static int pseries_eeh_init(void) ibm_get_config_addr_info2 = rtas_token("ibm,get-config-addr-info2"); ibm_get_config_addr_info = rtas_token("ibm,get-config-addr-info"); ibm_configure_pe = rtas_token("ibm,configure-pe"); - ibm_configure_bridge = rtas_token("ibm,configure-bridge"); + + /* + * ibm,configure-pe and ibm,configure-bridge have the same semantics, + * however ibm,configure-pe can be faster. If we can't find + * ibm,configure-pe then fall back to using ibm,configure-bridge. + */ + if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE) + ibm_configure_pe = rtas_token("ibm,configure-bridge"); /* * Necessary sanity check. We needn't check "get-config-addr-info" @@ -93,8 +99,7 @@ static int pseries_eeh_init(void) (ibm_read_slot_reset_state2 == RTAS_UNKNOWN_SERVICE && ibm_read_slot_reset_state == RTAS_UNKNOWN_SERVICE) || ibm_slot_error_detail == RTAS_UNKNOWN_SERVICE || - (ibm_configure_pe == RTAS_UNKNOWN_SERVICE && - ibm_configure_bridge == RTAS_UNKNOWN_SERVICE)) { + ibm_configure_pe == RTAS_UNKNOWN_SERVICE) { pr_info("EEH functionality not supported\n"); return -EINVAL; } @@ -615,29 +620,41 @@ static int pseries_eeh_configure_bridge(struct eeh_pe *pe) { int config_addr; int ret; + /* Waiting 0.2s maximum before skipping configuration */ + int max_wait = 200; /* Figure out the PE address */ config_addr = pe->config_addr; if (pe->addr) config_addr = pe->addr; - /* Use new configure-pe function, if supported */ - if (ibm_configure_pe != RTAS_UNKNOWN_SERVICE) { + while (max_wait > 0) { ret = rtas_call(ibm_configure_pe, 3, 1, NULL, config_addr, BUID_HI(pe->phb->buid), BUID_LO(pe->phb->buid)); - } else if (ibm_configure_bridge != RTAS_UNKNOWN_SERVICE) { - ret = rtas_call(ibm_configure_bridge, 3, 1, NULL, - config_addr, BUID_HI(pe->phb->buid), - BUID_LO(pe->phb->buid)); - } else { - return -EFAULT; - } - if (ret) - pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", - __func__, pe->phb->global_number, pe->addr, ret); + if (!ret) + return ret; + + /* + * If RTAS returns a delay value that's above 100ms, cut it + * down to 100ms in case firmware made a mistake. For more + * on how these delay values work see rtas_busy_delay_time + */ + if (ret > RTAS_EXTENDED_DELAY_MIN+2 && + ret <= RTAS_EXTENDED_DELAY_MAX) + ret = RTAS_EXTENDED_DELAY_MIN+2; + + max_wait -= rtas_busy_delay_time(ret); + + if (max_wait < 0) + break; + + rtas_busy_delay(ret); + } + pr_warn("%s: Unable to configure bridge PHB#%d-PE#%x (%d)\n", + __func__, pe->phb->global_number, pe->addr, ret); return ret; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 6bd881b..5eb1f9e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -41,6 +41,7 @@ #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING (1ULL << 0) #define ITS_FLAGS_WORKAROUND_CAVIUM_22375 (1ULL << 1) +#define ITS_FLAGS_WORKAROUND_CAVIUM_23144 (1ULL << 2) #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0) @@ -82,6 +83,7 @@ struct its_node { u64 flags; u32 ite_size; u32 device_ids; + int numa_node; }; #define ITS_ITT_ALIGN SZ_256 @@ -613,11 +615,23 @@ static void its_unmask_irq(struct irq_data *d) static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { - unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask); + unsigned int cpu; + const struct cpumask *cpu_mask = cpu_online_mask; struct its_device *its_dev = irq_data_get_irq_chip_data(d); struct its_collection *target_col; u32 id = its_get_event_id(d); + /* lpi cannot be routed to a redistributor that is on a foreign node */ + if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) { + if (its_dev->its->numa_node >= 0) { + cpu_mask = cpumask_of_node(its_dev->its->numa_node); + if (!cpumask_intersects(mask_val, cpu_mask)) + return -EINVAL; + } + } + + cpu = cpumask_any_and(mask_val, cpu_mask); + if (cpu >= nr_cpu_ids) return -EINVAL; @@ -1101,6 +1115,16 @@ static void its_cpu_init_collection(void) list_for_each_entry(its, &its_nodes, entry) { u64 target; + /* avoid cross node collections and its mapping */ + if (its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) { + struct device_node *cpu_node; + + cpu_node = of_get_cpu_node(cpu, NULL); + if (its->numa_node != NUMA_NO_NODE && + its->numa_node != of_node_to_nid(cpu_node)) + continue; + } + /* * We now have to bind each collection to its target * redistributor. @@ -1351,9 +1375,14 @@ static void its_irq_domain_activate(struct irq_domain *domain, { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); + const struct cpumask *cpu_mask = cpu_online_mask; + + /* get the cpu_mask of local node */ + if (its_dev->its->numa_node >= 0) + cpu_mask = cpumask_of_node(its_dev->its->numa_node); /* Bind the LPI to the first possible CPU */ - its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask); + its_dev->event_map.col_map[event] = cpumask_first(cpu_mask); /* Map the GIC IRQ and event to the device */ its_send_mapvi(its_dev, d->hwirq, event); @@ -1443,6 +1472,13 @@ static void __maybe_unused its_enable_quirk_cavium_22375(void *data) its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_22375; } +static void __maybe_unused its_enable_quirk_cavium_23144(void *data) +{ + struct its_node *its = data; + + its->flags |= ITS_FLAGS_WORKAROUND_CAVIUM_23144; +} + static const struct gic_quirk its_quirks[] = { #ifdef CONFIG_CAVIUM_ERRATUM_22375 { @@ -1452,6 +1488,14 @@ static const struct gic_quirk its_quirks[] = { .init = its_enable_quirk_cavium_22375, }, #endif +#ifdef CONFIG_CAVIUM_ERRATUM_23144 + { + .desc = "ITS: Cavium erratum 23144", + .iidr = 0xa100034c, /* ThunderX pass 1.x */ + .mask = 0xffff0fff, + .init = its_enable_quirk_cavium_23144, + }, +#endif { } }; @@ -1514,6 +1558,7 @@ static int __init its_probe(struct device_node *node, its->base = its_base; its->phys_base = res.start; its->ite_size = ((readl_relaxed(its_base + GITS_TYPER) >> 4) & 0xf) + 1; + its->numa_node = of_node_to_nid(node); its->cmd_base = kzalloc(ITS_CMD_QUEUE_SZ, GFP_KERNEL); if (!its->cmd_base) { diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index fb042ba..2c5ba0e 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -155,7 +155,7 @@ static void gic_enable_redist(bool enable) while (count--) { val = readl_relaxed(rbase + GICR_WAKER); - if (enable ^ (val & GICR_WAKER_ChildrenAsleep)) + if (enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep)) break; cpu_relax(); udelay(1); diff --git a/drivers/irqchip/irq-pic32-evic.c b/drivers/irqchip/irq-pic32-evic.c index e7155db..73addb4 100644 --- a/drivers/irqchip/irq-pic32-evic.c +++ b/drivers/irqchip/irq-pic32-evic.c @@ -91,7 +91,7 @@ static int pic32_set_type_edge(struct irq_data *data, /* set polarity for external interrupts only */ for (i = 0; i < ARRAY_SIZE(priv->ext_irqs); i++) { if (priv->ext_irqs[i] == data->hwirq) { - ret = pic32_set_ext_polarity(i + 1, flow_type); + ret = pic32_set_ext_polarity(i, flow_type); if (ret) return ret; } diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index f2d01d4..1b8304e 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -950,17 +950,14 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) /* For SPIs, we need to track the affinity per IRQ */ if (using_spi) { - if (i >= pdev->num_resources) { - of_node_put(dn); + if (i >= pdev->num_resources) break; - } irqs[i] = cpu; } /* Keep track of the CPUs containing this PMU type */ cpumask_set_cpu(cpu, &pmu->supported_cpus); - of_node_put(dn); i++; } while (1); @@ -995,9 +992,6 @@ int arm_pmu_device_probe(struct platform_device *pdev, armpmu_init(pmu); - if (!__oprofile_cpu_pmu) - __oprofile_cpu_pmu = pmu; - pmu->plat_device = pdev; if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) { @@ -1033,6 +1027,9 @@ int arm_pmu_device_probe(struct platform_device *pdev, if (ret) goto out_destroy; + if (!__oprofile_cpu_pmu) + __oprofile_cpu_pmu = pmu; + pr_info("enabled with %s PMU driver, %d counters available\n", pmu->name, pmu->num_events); @@ -1043,6 +1040,7 @@ out_destroy: out_free: pr_info("%s: failed to register PMU devices!\n", of_node_full_name(node)); + kfree(pmu->irq_affinity); kfree(pmu); return ret; } diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index bfbd707..dc493e0 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -305,12 +305,12 @@ #define ICC_SGI1R_AFFINITY_1_SHIFT 16 #define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT) #define ICC_SGI1R_SGI_ID_SHIFT 24 -#define ICC_SGI1R_SGI_ID_MASK (0xff << ICC_SGI1R_SGI_ID_SHIFT) +#define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT) #define ICC_SGI1R_AFFINITY_2_SHIFT 32 -#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT) #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40 #define ICC_SGI1R_AFFINITY_3_SHIFT 48 -#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT) #include <asm/arch_gicv3.h> diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 37dbacf..816b754 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -21,6 +21,9 @@ static inline int do_sys_settimeofday(const struct timespec *tv, struct timespec64 ts64; if (!tv) + return do_sys_settimeofday64(NULL, tz); + + if (!timespec_valid(tv)) return -EINVAL; ts64 = timespec_to_timespec64(*tv); diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index c427422..89b49f6 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -125,7 +125,7 @@ int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest) domain = data->domain; if (WARN_ON(domain == NULL)) - return; + return -EINVAL; if (!irq_domain_is_ipi(domain)) { pr_warn("Trying to destroy a non IPI domain!\n"); |