diff options
Diffstat (limited to 'arch')
| -rw-r--r-- | arch/arm64/Kconfig | 28 | ||||
| -rw-r--r-- | arch/arm64/include/asm/assembler.h | 11 | ||||
| -rw-r--r-- | arch/arm64/include/asm/cpucaps.h | 5 | ||||
| -rw-r--r-- | arch/arm64/include/asm/insn.h | 18 | ||||
| -rw-r--r-- | arch/arm64/kernel/cpu_errata.c | 48 | ||||
| -rw-r--r-- | arch/arm64/kernel/entry.S | 4 | ||||
| -rw-r--r-- | arch/arm64/kernel/kaslr.c | 6 | ||||
| -rw-r--r-- | arch/arm64/kernel/module.c | 18 | ||||
| -rw-r--r-- | arch/arm64/kernel/syscall.c | 31 | ||||
| -rw-r--r-- | arch/arm64/kernel/traps.c | 4 | ||||
| -rw-r--r-- | arch/arm64/kernel/vdso/Makefile | 4 | ||||
| -rw-r--r-- | arch/arm64/mm/dma-mapping.c | 10 | ||||
| -rw-r--r-- | arch/arm64/mm/fault.c | 38 | ||||
| -rw-r--r-- | arch/arm64/mm/mmu.c | 11 |
14 files changed, 188 insertions, 48 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 76f6e4765f49..697ea0510729 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -69,7 +69,7 @@ config ARM64 select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG select ARCH_SUPPORTS_NUMA_BALANCING - select ARCH_WANT_COMPAT_IPC_PARSE_VERSION + select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT select ARCH_WANT_FRAME_POINTERS select ARCH_HAS_UBSAN_SANITIZE_ALL select ARM_AMBA @@ -476,16 +476,15 @@ config ARM64_ERRATUM_1024718 If unsure, say Y. -config ARM64_ERRATUM_1188873 +config ARM64_ERRATUM_1418040 bool "Cortex-A76/Neoverse-N1: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result" default y depends on COMPAT - select ARM_ARCH_TIMER_OOL_WORKAROUND help This option adds a workaround for ARM Cortex-A76/Neoverse-N1 - erratum 1188873. + errata 1188873 and 1418040. - Affected Cortex-A76/Neoverse-N1 cores (r0p0, r1p0, r2p0) could + Affected Cortex-A76/Neoverse-N1 cores (r0p0 to r3p1) could cause register corruption when accessing the timer registers from AArch32 userspace. @@ -521,6 +520,24 @@ config ARM64_ERRATUM_1286807 If unsure, say Y. +config ARM64_ERRATUM_1463225 + bool "Cortex-A76: Software Step might prevent interrupt recognition" + default y + help + This option adds a workaround for Arm Cortex-A76 erratum 1463225. + + On the affected Cortex-A76 cores (r0p0 to r3p1), software stepping + of a system call instruction (SVC) can prevent recognition of + subsequent interrupts when software stepping is disabled in the + exception handler of the system call and either kernel debugging + is enabled or VHE is in use. + + Work around the erratum by triggering a dummy step exception + when handling a system call from a task that is being stepped + in a VHE configuration of the kernel. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -1406,6 +1423,7 @@ config ARM64_MODULE_PLTS config ARM64_PSEUDO_NMI bool "Support for NMI-like interrupts" + depends on BROKEN # 1556553607-46531-1-git-send-email-julien.thierry@arm.com select CONFIG_ARM_GIC_V3 help Adds support for mimicking Non-Maskable Interrupts through the use of diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 039fbd822ec6..92b6b7cf67dd 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -718,12 +718,11 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU * the output section, any use of such directives is undefined. * * The yield itself consists of the following: - * - Check whether the preempt count is exactly 1, in which case disabling - * preemption once will make the task preemptible. If this is not the case, - * yielding is pointless. - * - Check whether TIF_NEED_RESCHED is set, and if so, disable and re-enable - * kernel mode NEON (which will trigger a reschedule), and branch to the - * yield fixup code. + * - Check whether the preempt count is exactly 1 and a reschedule is also + * needed. If so, calling of preempt_enable() in kernel_neon_end() will + * trigger a reschedule. If it is not the case, yielding is pointless. + * - Disable and re-enable kernel mode NEON, and branch to the yield fixup + * code. * * This macro sequence may clobber all CPU state that is not guaranteed by the * AAPCS to be preserved across an ordinary function call. diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index defdc67d9ab4..33401ebc187c 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -53,7 +53,7 @@ #define ARM64_HAS_STAGE2_FWB 32 #define ARM64_HAS_CRC32 33 #define ARM64_SSBS 34 -#define ARM64_WORKAROUND_1188873 35 +#define ARM64_WORKAROUND_1418040 35 #define ARM64_HAS_SB 36 #define ARM64_WORKAROUND_1165522 37 #define ARM64_HAS_ADDRESS_AUTH_ARCH 38 @@ -62,7 +62,8 @@ #define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41 #define ARM64_HAS_IRQ_PRIO_MASKING 42 #define ARM64_HAS_DCPODP 43 +#define ARM64_WORKAROUND_1463225 44 -#define ARM64_NCAPS 44 +#define ARM64_NCAPS 45 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index ec894de0ed4e..87fdfba13a30 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -18,6 +18,7 @@ */ #ifndef __ASM_INSN_H #define __ASM_INSN_H +#include <linux/build_bug.h> #include <linux/types.h> /* A64 instructions are always 32 bits. */ @@ -266,18 +267,23 @@ enum aarch64_insn_adr_type { AARCH64_INSN_ADR_TYPE_ADR, }; -#define __AARCH64_INSN_FUNCS(abbr, mask, val) \ -static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ -{ return (code & (mask)) == (val); } \ -static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ -{ return (val); } +#define __AARCH64_INSN_FUNCS(abbr, mask, val) \ +static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ +{ \ + BUILD_BUG_ON(~(mask) & (val)); \ + return (code & (mask)) == (val); \ +} \ +static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ +{ \ + return (val); \ +} __AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000) __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) __AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) -__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0xB8200000) +__AARCH64_INSN_FUNCS(ldadd, 0x3F20FC00, 0x38200000) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) __AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index e88d4e7bdfc7..d61beedba101 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -502,6 +502,22 @@ static const struct midr_range arm64_ssb_cpus[] = { {}, }; +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DEFINE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static bool +has_cortex_a76_erratum_1463225(const struct arm64_cpu_capabilities *entry, + int scope) +{ + u32 midr = read_cpuid_id(); + /* Cortex-A76 r0p0 - r3p1 */ + struct midr_range range = MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1); + + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + return is_midr_in_range(midr, &range) && is_kernel_in_hyp_mode(); +} +#endif + static void __maybe_unused cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) { @@ -682,12 +698,16 @@ static const struct midr_range workaround_clean_cache[] = { }; #endif -#ifdef CONFIG_ARM64_ERRATUM_1188873 -static const struct midr_range erratum_1188873_list[] = { - /* Cortex-A76 r0p0 to r2p0 */ - MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), - /* Neoverse-N1 r0p0 to r2p0 */ - MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 2, 0), +#ifdef CONFIG_ARM64_ERRATUM_1418040 +/* + * - 1188873 affects r0p0 to r2p0 + * - 1418040 affects r0p0 to r3p1 + */ +static const struct midr_range erratum_1418040_list[] = { + /* Cortex-A76 r0p0 to r3p1 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 1), + /* Neoverse-N1 r0p0 to r3p1 */ + MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 3, 1), {}, }; #endif @@ -809,11 +829,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_ssbd_mitigation, .midr_range_list = arm64_ssb_cpus, }, -#ifdef CONFIG_ARM64_ERRATUM_1188873 +#ifdef CONFIG_ARM64_ERRATUM_1418040 { - .desc = "ARM erratum 1188873", - .capability = ARM64_WORKAROUND_1188873, - ERRATA_MIDR_RANGE_LIST(erratum_1188873_list), + .desc = "ARM erratum 1418040", + .capability = ARM64_WORKAROUND_1418040, + ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), }, #endif #ifdef CONFIG_ARM64_ERRATUM_1165522 @@ -824,6 +844,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1463225 + { + .desc = "ARM erratum 1463225", + .capability = ARM64_WORKAROUND_1463225, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = has_cortex_a76_erratum_1463225, + }, +#endif { } }; diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 1a7811b7e3c4..cd0c7af8e4a8 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -336,8 +336,8 @@ alternative_if ARM64_WORKAROUND_845719 alternative_else_nop_endif #endif 3: -#ifdef CONFIG_ARM64_ERRATUM_1188873 -alternative_if_not ARM64_WORKAROUND_1188873 +#ifdef CONFIG_ARM64_ERRATUM_1418040 +alternative_if_not ARM64_WORKAROUND_1418040 b 4f alternative_else_nop_endif /* diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index b09b6f75f759..06941c1fe418 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -145,15 +145,15 @@ u64 __init kaslr_early_init(u64 dt_phys) if (IS_ENABLED(CONFIG_RANDOMIZE_MODULE_REGION_FULL)) { /* - * Randomize the module region over a 4 GB window covering the + * Randomize the module region over a 2 GB window covering the * kernel. This reduces the risk of modules leaking information * about the address of the kernel itself, but results in * branches between modules and the core kernel that are * resolved via PLTs. (Branches between modules will be * resolved normally.) */ - module_range = SZ_4G - (u64)(_end - _stext); - module_alloc_base = max((u64)_end + offset - SZ_4G, + module_range = SZ_2G - (u64)(_end - _stext); + module_alloc_base = max((u64)_end + offset - SZ_2G, (u64)MODULES_VADDR); } else { /* diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f713e2fc4d75..f32359cffb01 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -56,7 +56,7 @@ void *module_alloc(unsigned long size) * can simply omit this fallback in that case. */ p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_base + SZ_4G, GFP_KERNEL, + module_alloc_base + SZ_2G, GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, __builtin_return_address(0)); @@ -96,15 +96,27 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) { s64 sval = do_reloc(op, place, val); + /* + * The ELF psABI for AArch64 documents the 16-bit and 32-bit place + * relative relocations as having a range of [-2^15, 2^16) or + * [-2^31, 2^32), respectively. However, in order to be able to detect + * overflows reliably, we have to choose whether we interpret such + * quantities as signed or as unsigned, and stick with it. + * The way we organize our address space requires a signed + * interpretation of 32-bit relative references, so let's use that + * for all R_AARCH64_PRELxx relocations. This means our upper + * bound for overflow detection should be Sxx_MAX rather than Uxx_MAX. + */ + switch (len) { case 16: *(s16 *)place = sval; - if (sval < S16_MIN || sval > U16_MAX) + if (sval < S16_MIN || sval > S16_MAX) return -ERANGE; break; case 32: *(s32 *)place = sval; - if (sval < S32_MIN || sval > U32_MAX) + if (sval < S32_MIN || sval > S32_MAX) return -ERANGE; break; case 64: diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 5610ac01c1ec..871c739f060a 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm/daifflags.h> +#include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -60,6 +61,35 @@ static inline bool has_syscall_work(unsigned long flags) int syscall_trace_enter(struct pt_regs *regs); void syscall_trace_exit(struct pt_regs *regs); +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static void cortex_a76_erratum_1463225_svc_handler(void) +{ + u32 reg, val; + + if (!unlikely(test_thread_flag(TIF_SINGLESTEP))) + return; + + if (!unlikely(this_cpu_has_cap(ARM64_WORKAROUND_1463225))) + return; + + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 1); + reg = read_sysreg(mdscr_el1); + val = reg | DBG_MDSCR_SS | DBG_MDSCR_KDE; + write_sysreg(val, mdscr_el1); + asm volatile("msr daifclr, #8"); + isb(); + + /* We will have taken a single-step exception by this point */ + + write_sysreg(reg, mdscr_el1); + __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); +} +#else +static void cortex_a76_erratum_1463225_svc_handler(void) { } +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, const syscall_fn_t syscall_table[]) { @@ -68,6 +98,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, regs->orig_x0 = regs->regs[0]; regs->syscallno = scno; + cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); user_exit(); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index ade32046f3fe..e6be1a6efc0a 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -168,7 +168,6 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) static int __die(const char *str, int err, struct pt_regs *regs) { - struct task_struct *tsk = current; static int die_counter; int ret; @@ -181,9 +180,6 @@ static int __die(const char *str, int err, struct pt_regs *regs) return ret; print_modules(); - pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", - TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), - end_of_stack(tsk)); show_regs(regs); if (!user_mode(regs)) diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index 744b9dbaba03..fa230ff09aa1 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -12,8 +12,8 @@ obj-vdso := gettimeofday.o note.o sigreturn.o targets := $(obj-vdso) vdso.so vdso.so.dbg obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) -ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 \ - $(call ld-option, --hash-style=sysv) -n -T +ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ + --build-id -n -T # Disable gcov profiling for VDSO code GCOV_PROFILE := n diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 78c0a72f822c..674860e3e478 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -249,6 +249,11 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret)) return ret; + if (!is_vmalloc_addr(cpu_addr)) { + unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr)); + return __swiotlb_mmap_pfn(vma, pfn, size); + } + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { /* * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, @@ -272,6 +277,11 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; struct vm_struct *area = find_vm_area(cpu_addr); + if (!is_vmalloc_addr(cpu_addr)) { + struct page *page = virt_to_page(cpu_addr); + return __swiotlb_get_sgtable_page(sgt, page, size); + } + if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { /* * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0cb0e09995e1..a30818ed9c60 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -171,9 +171,10 @@ static void show_pte(unsigned long addr) return; } - pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", + pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - mm == &init_mm ? VA_BITS : (int) vabits_user, mm->pgd); + mm == &init_mm ? VA_BITS : (int)vabits_user, + (unsigned long)virt_to_phys(mm->pgd)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -810,6 +811,36 @@ void __init hook_debug_fault_code(int nr, debug_fault_info[nr].name = name; } +#ifdef CONFIG_ARM64_ERRATUM_1463225 +DECLARE_PER_CPU(int, __in_cortex_a76_erratum_1463225_wa); + +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + if (user_mode(regs)) + return 0; + + if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) + return 0; + + /* + * We've taken a dummy step exception from the kernel to ensure + * that interrupts are re-enabled on the syscall path. Return back + * to cortex_a76_erratum_1463225_svc_handler() with debug exceptions + * masked so that we can safely restore the mdscr and get on with + * handling the syscall. + */ + regs->pstate |= PSR_D_BIT; + return 1; +} +#else +static int __exception +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +{ + return 0; +} +#endif /* CONFIG_ARM64_ERRATUM_1463225 */ + asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, struct pt_regs *regs) @@ -817,6 +848,9 @@ asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint, const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); + if (cortex_a76_erratum_1463225_debug_handler(regs)) + return; + /* * Tell lockdep we disabled irqs in entry.S. Do nothing if they were * already disabled to preserve the last enabled/disabled addresses. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a170c6369a68..a1bfc4413982 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -955,13 +955,18 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys) int __init arch_ioremap_pud_supported(void) { - /* only 4k granule supports level 1 block mappings */ - return IS_ENABLED(CONFIG_ARM64_4K_PAGES); + /* + * Only 4k granule supports level 1 block mappings. + * SW table walks can't handle removal of intermediate entries. + */ + return IS_ENABLED(CONFIG_ARM64_4K_PAGES) && + !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int __init arch_ioremap_pmd_supported(void) { - return 1; + /* See arch_ioremap_pud_supported() */ + return !IS_ENABLED(CONFIG_ARM64_PTDUMP_DEBUGFS); } int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot) |