diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-06 21:51:49 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-10-06 21:51:49 +0300 |
| commit | 18fd049731e67651009f316195da9281b756f2cf (patch) | |
| tree | 082c87950f33bc466672ea3fd2ea24e5b2a37253 /arch/arm64/kernel | |
| parent | 41fc64a0550b86f4428e8d3fa23ab97678a65ae8 (diff) | |
| parent | d2995249a2f72333a4ab4922ff3c42a76c023791 (diff) | |
| download | linux-18fd049731e67651009f316195da9281b756f2cf.tar.xz | |
Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Catalin Marinas:
- arm64 perf: DDR PMU driver for Alibaba's T-Head Yitian 710 SoC, SVE
vector granule register added to the user regs together with SVE perf
extensions documentation.
- SVE updates: add HWCAP for SVE EBF16, update the SVE ABI
documentation to match the actual kernel behaviour (zeroing the
registers on syscall rather than "zeroed or preserved" previously).
- More conversions to automatic system registers generation.
- vDSO: use self-synchronising virtual counter access in gettimeofday()
if the architecture supports it.
- arm64 stacktrace cleanups and improvements.
- arm64 atomics improvements: always inline assembly, remove LL/SC
trampolines.
- Improve the reporting of EL1 exceptions: rework BTI and FPAC
exception handling, better EL1 undefs reporting.
- Cortex-A510 erratum 2658417: remove BF16 support due to incorrect
result.
- arm64 defconfig updates: build CoreSight as a module, enable options
necessary for docker, memory hotplug/hotremove, enable all PMUs
provided by Arm.
- arm64 ptrace() support for TPIDR2_EL0 (register provided with the SME
extensions).
- arm64 ftraces updates/fixes: fix module PLTs with mcount, remove
unused function.
- kselftest updates for arm64: simple HWCAP validation, FP stress test
improvements, validation of ZA regs in signal handlers, include
larger SVE and SME vector lengths in signal tests, various cleanups.
- arm64 alternatives (code patching) improvements to robustness and
consistency: replace cpucap static branches with equivalent
alternatives, associate callback alternatives with a cpucap.
- Miscellaneous updates: optimise kprobe performance of patching
single-step slots, simplify uaccess_mask_ptr(), move MTE registers
initialisation to C, support huge vmalloc() mappings, run softirqs on
the per-CPU IRQ stack, compat (arm32) misalignment fixups for
multiword accesses.
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (126 commits)
arm64: alternatives: Use vdso/bits.h instead of linux/bits.h
arm64/kprobe: Optimize the performance of patching single-step slot
arm64: defconfig: Add Coresight as module
kselftest/arm64: Handle EINTR while reading data from children
kselftest/arm64: Flag fp-stress as exiting when we begin finishing up
kselftest/arm64: Don't repeat termination handler for fp-stress
ARM64: reloc_test: add __init/__exit annotations to module init/exit funcs
arm64/mm: fold check for KFENCE into can_set_direct_map()
arm64: ftrace: fix module PLTs with mcount
arm64: module: Remove unused plt_entry_is_initialized()
arm64: module: Make plt_equals_entry() static
arm64: fix the build with binutils 2.27
kselftest/arm64: Don't enable v8.5 for MTE selftest builds
arm64: uaccess: simplify uaccess_mask_ptr()
arm64: asm/perf_regs.h: Avoid C++-style comment in UAPI header
kselftest/arm64: Fix typo in hwcap check
arm64: mte: move register initialization to C
arm64: mm: handle ARM64_KERNEL_USES_PMD_MAPS in vmemmap_populate()
arm64: dma: Drop cache invalidation from arch_dma_prep_coherent()
arm64/sve: Add Perf extensions documentation
...
Diffstat (limited to 'arch/arm64/kernel')
30 files changed, 939 insertions, 338 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 1add7b01efa7..38a0b0291edb 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -45,6 +45,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o obj-$(CONFIG_COMPAT) += sigreturn32.o +obj-$(CONFIG_COMPAT_ALIGNMENT_FIXUPS) += compat_alignment.o obj-$(CONFIG_KUSER_HELPERS) += kuser32.o obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o obj-$(CONFIG_MODULES) += module.o diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index d2c66507398d..91263d09ea65 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -10,17 +10,23 @@ #include <linux/init.h> #include <linux/cpu.h> +#include <linux/elf.h> #include <asm/cacheflush.h> #include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/insn.h> +#include <asm/module.h> #include <asm/sections.h> +#include <asm/vdso.h> #include <linux/stop_machine.h> #define __ALT_PTR(a, f) ((void *)&(a)->f + (a)->f) #define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) #define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) +#define ALT_CAP(a) ((a)->cpufeature & ~ARM64_CB_BIT) +#define ALT_HAS_CB(a) ((a)->cpufeature & ARM64_CB_BIT) + /* Volatile, as we may be patching the guts of READ_ONCE() */ static volatile int all_alternatives_applied; @@ -133,7 +139,8 @@ static void clean_dcache_range_nopatch(u64 start, u64 end) } while (cur += d_size, cur < end); } -static void __apply_alternatives(struct alt_region *region, bool is_module, +static void __apply_alternatives(const struct alt_region *region, + bool is_module, unsigned long *feature_mask) { struct alt_instr *alt; @@ -142,30 +149,27 @@ static void __apply_alternatives(struct alt_region *region, bool is_module, for (alt = region->begin; alt < region->end; alt++) { int nr_inst; + int cap = ALT_CAP(alt); - if (!test_bit(alt->cpufeature, feature_mask)) + if (!test_bit(cap, feature_mask)) continue; - /* Use ARM64_CB_PATCH as an unconditional patch */ - if (alt->cpufeature < ARM64_CB_PATCH && - !cpus_have_cap(alt->cpufeature)) + if (!cpus_have_cap(cap)) continue; - if (alt->cpufeature == ARM64_CB_PATCH) + if (ALT_HAS_CB(alt)) BUG_ON(alt->alt_len != 0); else BUG_ON(alt->alt_len != alt->orig_len); - pr_info_once("patching kernel code\n"); - origptr = ALT_ORIG_PTR(alt); updptr = is_module ? origptr : lm_alias(origptr); nr_inst = alt->orig_len / AARCH64_INSN_SIZE; - if (alt->cpufeature < ARM64_CB_PATCH) - alt_cb = patch_alternative; - else + if (ALT_HAS_CB(alt)) alt_cb = ALT_REPL_PTR(alt); + else + alt_cb = patch_alternative; alt_cb(alt, origptr, updptr, nr_inst); @@ -192,30 +196,55 @@ static void __apply_alternatives(struct alt_region *region, bool is_module, } } +void apply_alternatives_vdso(void) +{ + struct alt_region region; + const struct elf64_hdr *hdr; + const struct elf64_shdr *shdr; + const struct elf64_shdr *alt; + DECLARE_BITMAP(all_capabilities, ARM64_NCAPS); + + bitmap_fill(all_capabilities, ARM64_NCAPS); + + hdr = (struct elf64_hdr *)vdso_start; + shdr = (void *)hdr + hdr->e_shoff; + alt = find_section(hdr, shdr, ".altinstructions"); + if (!alt) + return; + + region = (struct alt_region){ + .begin = (void *)hdr + alt->sh_offset, + .end = (void *)hdr + alt->sh_offset + alt->sh_size, + }; + + __apply_alternatives(®ion, false, &all_capabilities[0]); +} + +static const struct alt_region kernel_alternatives = { + .begin = (struct alt_instr *)__alt_instructions, + .end = (struct alt_instr *)__alt_instructions_end, +}; + /* * We might be patching the stop_machine state machine, so implement a * really simple polling protocol here. */ static int __apply_alternatives_multi_stop(void *unused) { - struct alt_region region = { - .begin = (struct alt_instr *)__alt_instructions, - .end = (struct alt_instr *)__alt_instructions_end, - }; - /* We always have a CPU 0 at this point (__init) */ if (smp_processor_id()) { while (!all_alternatives_applied) cpu_relax(); isb(); } else { - DECLARE_BITMAP(remaining_capabilities, ARM64_NPATCHABLE); + DECLARE_BITMAP(remaining_capabilities, ARM64_NCAPS); bitmap_complement(remaining_capabilities, boot_capabilities, - ARM64_NPATCHABLE); + ARM64_NCAPS); BUG_ON(all_alternatives_applied); - __apply_alternatives(®ion, false, remaining_capabilities); + __apply_alternatives(&kernel_alternatives, false, + remaining_capabilities); /* Barriers provided by the cache flushing */ all_alternatives_applied = 1; } @@ -225,6 +254,9 @@ static int __apply_alternatives_multi_stop(void *unused) void __init apply_alternatives_all(void) { + pr_info("applying system-wide alternatives\n"); + + apply_alternatives_vdso(); /* better not try code patching on a live SMP system */ stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask); } @@ -236,15 +268,13 @@ void __init apply_alternatives_all(void) */ void __init apply_boot_alternatives(void) { - struct alt_region region = { - .begin = (struct alt_instr *)__alt_instructions, - .end = (struct alt_instr *)__alt_instructions_end, - }; - /* If called on non-boot cpu things could go wrong */ WARN_ON(smp_processor_id() != 0); - __apply_alternatives(®ion, false, &boot_capabilities[0]); + pr_info("applying boot alternatives\n"); + + __apply_alternatives(&kernel_alternatives, false, + &boot_capabilities[0]); } #ifdef CONFIG_MODULES @@ -254,10 +284,18 @@ void apply_alternatives_module(void *start, size_t length) .begin = start, .end = start + length, }; - DECLARE_BITMAP(all_capabilities, ARM64_NPATCHABLE); + DECLARE_BITMAP(all_capabilities, ARM64_NCAPS); - bitmap_fill(all_capabilities, ARM64_NPATCHABLE); + bitmap_fill(all_capabilities, ARM64_NCAPS); __apply_alternatives(®ion, true, &all_capabilities[0]); } #endif + +noinstr void alt_cb_patch_nops(struct alt_instr *alt, __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + for (int i = 0; i < nr_inst; i++) + updptr[i] = cpu_to_le32(aarch64_insn_gen_nop()); +} +EXPORT_SYMBOL(alt_cb_patch_nops); diff --git a/arch/arm64/kernel/compat_alignment.c b/arch/arm64/kernel/compat_alignment.c new file mode 100644 index 000000000000..5edec2f49ec9 --- /dev/null +++ b/arch/arm64/kernel/compat_alignment.c @@ -0,0 +1,387 @@ +// SPDX-License-Identifier: GPL-2.0-only +// based on arch/arm/mm/alignment.c + +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/perf_event.h> +#include <linux/uaccess.h> + +#include <asm/exception.h> +#include <asm/ptrace.h> +#include <asm/traps.h> + +/* + * 32-bit misaligned trap handler (c) 1998 San Mehat (CCC) -July 1998 + * + * Speed optimisations and better fault handling by Russell King. + */ +#define CODING_BITS(i) (i & 0x0e000000) + +#define LDST_P_BIT(i) (i & (1 << 24)) /* Preindex */ +#define LDST_U_BIT(i) (i & (1 << 23)) /* Add offset */ +#define LDST_W_BIT(i) (i & (1 << 21)) /* Writeback */ +#define LDST_L_BIT(i) (i & (1 << 20)) /* Load */ + +#define LDST_P_EQ_U(i) ((((i) ^ ((i) >> 1)) & (1 << 23)) == 0) + +#define LDSTHD_I_BIT(i) (i & (1 << 22)) /* double/half-word immed */ + +#define RN_BITS(i) ((i >> 16) & 15) /* Rn */ +#define RD_BITS(i) ((i >> 12) & 15) /* Rd */ +#define RM_BITS(i) (i & 15) /* Rm */ + +#define REGMASK_BITS(i) (i & 0xffff) + +#define BAD_INSTR 0xdeadc0de + +/* Thumb-2 32 bit format per ARMv7 DDI0406A A6.3, either f800h,e800h,f800h */ +#define IS_T32(hi16) \ + (((hi16) & 0xe000) == 0xe000 && ((hi16) & 0x1800)) + +union offset_union { + unsigned long un; + signed long sn; +}; + +#define TYPE_ERROR 0 +#define TYPE_FAULT 1 +#define TYPE_LDST 2 +#define TYPE_DONE 3 + +static void +do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, + union offset_union offset) +{ + if (!LDST_U_BIT(instr)) + offset.un = -offset.un; + + if (!LDST_P_BIT(instr)) + addr += offset.un; + + if (!LDST_P_BIT(instr) || LDST_W_BIT(instr)) + regs->regs[RN_BITS(instr)] = addr; +} + +static int +do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs) +{ + unsigned int rd = RD_BITS(instr); + unsigned int rd2; + int load; + + if ((instr & 0xfe000000) == 0xe8000000) { + /* ARMv7 Thumb-2 32-bit LDRD/STRD */ + rd2 = (instr >> 8) & 0xf; + load = !!(LDST_L_BIT(instr)); + } else if (((rd & 1) == 1) || (rd == 14)) { + return TYPE_ERROR; + } else { + load = ((instr & 0xf0) == 0xd0); + rd2 = rd + 1; + } + + if (load) { + unsigned int val, val2; + + if (get_user(val, (u32 __user *)addr) || + get_user(val2, (u32 __user *)(addr + 4))) + return TYPE_FAULT; + regs->regs[rd] = val; + regs->regs[rd2] = val2; + } else { + if (put_user(regs->regs[rd], (u32 __user *)addr) || + put_user(regs->regs[rd2], (u32 __user *)(addr + 4))) + return TYPE_FAULT; + } + return TYPE_LDST; +} + +/* + * LDM/STM alignment handler. + * + * There are 4 variants of this instruction: + * + * B = rn pointer before instruction, A = rn pointer after instruction + * ------ increasing address -----> + * | | r0 | r1 | ... | rx | | + * PU = 01 B A + * PU = 11 B A + * PU = 00 A B + * PU = 10 A B + */ +static int +do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs) +{ + unsigned int rd, rn, nr_regs, regbits; + unsigned long eaddr, newaddr; + unsigned int val; + + /* count the number of registers in the mask to be transferred */ + nr_regs = hweight16(REGMASK_BITS(instr)) * 4; + + rn = RN_BITS(instr); + newaddr = eaddr = regs->regs[rn]; + + if (!LDST_U_BIT(instr)) + nr_regs = -nr_regs; + newaddr += nr_regs; + if (!LDST_U_BIT(instr)) + eaddr = newaddr; + + if (LDST_P_EQ_U(instr)) /* U = P */ + eaddr += 4; + + for (regbits = REGMASK_BITS(instr), rd = 0; regbits; + regbits >>= 1, rd += 1) + if (regbits & 1) { + if (LDST_L_BIT(instr)) { + if (get_user(val, (u32 __user *)eaddr)) + return TYPE_FAULT; + if (rd < 15) + regs->regs[rd] = val; + else + regs->pc = val; + } else { + /* + * The PC register has a bias of +8 in ARM mode + * and +4 in Thumb mode. This means that a read + * of the value of PC should account for this. + * Since Thumb does not permit STM instructions + * to refer to PC, just add 8 here. + */ + val = (rd < 15) ? regs->regs[rd] : regs->pc + 8; + if (put_user(val, (u32 __user *)eaddr)) + return TYPE_FAULT; + } + eaddr += 4; + } + + if (LDST_W_BIT(instr)) + regs->regs[rn] = newaddr; + + return TYPE_DONE; +} + +/* + * Convert Thumb multi-word load/store instruction forms to equivalent ARM + * instructions so we can reuse ARM userland alignment fault fixups for Thumb. + * + * This implementation was initially based on the algorithm found in + * gdb/sim/arm/thumbemu.c. It is basically just a code reduction of same + * to convert only Thumb ld/st instruction forms to equivalent ARM forms. + * + * NOTES: + * 1. Comments below refer to ARM ARM DDI0100E Thumb Instruction sections. + * 2. If for some reason we're passed an non-ld/st Thumb instruction to + * decode, we return 0xdeadc0de. This should never happen under normal + * circumstances but if it does, we've got other problems to deal with + * elsewhere and we obviously can't fix those problems here. + */ + +static unsigned long thumb2arm(u16 tinstr) +{ + u32 L = (tinstr & (1<<11)) >> 11; + + switch ((tinstr & 0xf800) >> 11) { + /* 6.6.1 Format 1: */ + case 0xc000 >> 11: /* 7.1.51 STMIA */ + case 0xc800 >> 11: /* 7.1.25 LDMIA */ + { + u32 Rn = (tinstr & (7<<8)) >> 8; + u32 W = ((L<<Rn) & (tinstr&255)) ? 0 : 1<<21; + + return 0xe8800000 | W | (L<<20) | (Rn<<16) | + (tinstr&255); + } + + /* 6.6.1 Format 2: */ + case 0xb000 >> 11: /* 7.1.48 PUSH */ + case 0xb800 >> 11: /* 7.1.47 POP */ + if ((tinstr & (3 << 9)) == 0x0400) { + static const u32 subset[4] = { + 0xe92d0000, /* STMDB sp!,{registers} */ + 0xe92d4000, /* STMDB sp!,{registers,lr} */ + 0xe8bd0000, /* LDMIA sp!,{registers} */ + 0xe8bd8000 /* LDMIA sp!,{registers,pc} */ + }; + return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] | + (tinstr & 255); /* register_list */ + } + fallthrough; /* for illegal instruction case */ + + default: + return BAD_INSTR; + } +} + +/* + * Convert Thumb-2 32 bit LDM, STM, LDRD, STRD to equivalent instruction + * handlable by ARM alignment handler, also find the corresponding handler, + * so that we can reuse ARM userland alignment fault fixups for Thumb. + * + * @pinstr: original Thumb-2 instruction; returns new handlable instruction + * @regs: register context. + * @poffset: return offset from faulted addr for later writeback + * + * NOTES: + * 1. Comments below refer to ARMv7 DDI0406A Thumb Instruction sections. + * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt) + */ +static void * +do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs, + union offset_union *poffset) +{ + u32 instr = *pinstr; + u16 tinst1 = (instr >> 16) & 0xffff; + u16 tinst2 = instr & 0xffff; + + switch (tinst1 & 0xffe0) { + /* A6.3.5 Load/Store multiple */ + case 0xe880: /* STM/STMIA/STMEA,LDM/LDMIA, PUSH/POP T2 */ + case 0xe8a0: /* ...above writeback version */ + case 0xe900: /* STMDB/STMFD, LDMDB/LDMEA */ + case 0xe920: /* ...above writeback version */ + /* no need offset decision since handler calculates it */ + return do_alignment_ldmstm; + + case 0xf840: /* POP/PUSH T3 (single register) */ + if (RN_BITS(instr) == 13 && (tinst2 & 0x09ff) == 0x0904) { + u32 L = !!(LDST_L_BIT(instr)); + const u32 subset[2] = { + 0xe92d0000, /* STMDB sp!,{registers} */ + 0xe8bd0000, /* LDMIA sp!,{registers} */ + }; + *pinstr = subset[L] | (1<<RD_BITS(instr)); + return do_alignment_ldmstm; + } + /* Else fall through for illegal instruction case */ + break; + + /* A6.3.6 Load/store double, STRD/LDRD(immed, lit, reg) */ + case 0xe860: + case 0xe960: + case 0xe8e0: + case 0xe9e0: + poffset->un = (tinst2 & 0xff) << 2; + fallthrough; + + case 0xe940: + case 0xe9c0: + return do_alignment_ldrdstrd; + + /* + * No need to handle load/store instructions up to word size + * since ARMv6 and later CPUs can perform unaligned accesses. + */ + default: + break; + } + return NULL; +} + +static int alignment_get_arm(struct pt_regs *regs, __le32 __user *ip, u32 *inst) +{ + __le32 instr = 0; + int fault; + + fault = get_user(instr, ip); + if (fault) + return fault; + + *inst = __le32_to_cpu(instr); + return 0; +} + +static int alignment_get_thumb(struct pt_regs *regs, __le16 __user *ip, u16 *inst) +{ + __le16 instr = 0; + int fault; + + fault = get_user(instr, ip); + if (fault) + return fault; + + *inst = __le16_to_cpu(instr); + return 0; +} + +int do_compat_alignment_fixup(unsigned long addr, struct pt_regs *regs) +{ + union offset_union offset; + unsigned long instrptr; + int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs); + unsigned int type; + u32 instr = 0; + u16 tinstr = 0; + int isize = 4; + int thumb2_32b = 0; + int fault; + + instrptr = instruction_pointer(regs); + + if (compat_thumb_mode(regs)) { + __le16 __user *ptr = (__le16 __user *)(instrptr & ~1); + + fault = alignment_get_thumb(regs, ptr, &tinstr); + if (!fault) { + if (IS_T32(tinstr)) { + /* Thumb-2 32-bit */ + u16 tinst2; + fault = alignment_get_thumb(regs, ptr + 1, &tinst2); + instr = ((u32)tinstr << 16) | tinst2; + thumb2_32b = 1; + } else { + isize = 2; + instr = thumb2arm(tinstr); + } + } + } else { + fault = alignment_get_arm(regs, (__le32 __user *)instrptr, &instr); + } + + if (fault) + return 1; + + switch (CODING_BITS(instr)) { + case 0x00000000: /* 3.13.4 load/store instruction extensions */ + if (LDSTHD_I_BIT(instr)) + offset.un = (instr & 0xf00) >> 4 | (instr & 15); + else + offset.un = regs->regs[RM_BITS(instr)]; + + if ((instr & 0x001000f0) == 0x000000d0 || /* LDRD */ + (instr & 0x001000f0) == 0x000000f0) /* STRD */ + handler = do_alignment_ldrdstrd; + else + return 1; + break; + + case 0x08000000: /* ldm or stm, or thumb-2 32bit instruction */ + if (thumb2_32b) { + offset.un = 0; + handler = do_alignment_t32_to_handler(&instr, regs, &offset); + } else { + offset.un = 0; + handler = do_alignment_ldmstm; + } + break; + + default: + return 1; + } + + type = handler(addr, instr, regs); + + if (type == TYPE_ERROR || type == TYPE_FAULT) + return 1; + + if (type == TYPE_LDST) + do_alignment_finish_ldst(addr, instr, regs, offset); + + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->pc); + arm64_skip_faulting_instruction(regs, isize); + + return 0; +} diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 53b973b6059f..58ca4f6b25d6 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -121,6 +121,22 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0); } +static DEFINE_RAW_SPINLOCK(reg_user_mask_modification); +static void __maybe_unused +cpu_clear_bf16_from_user_emulation(const struct arm64_cpu_capabilities *__unused) +{ + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64ISAR1_EL1); + if (!regp) + return; + + raw_spin_lock(®_user_mask_modification); + if (regp->user_mask & ID_AA64ISAR1_EL1_BF16_MASK) + regp->user_mask &= ~ID_AA64ISAR1_EL1_BF16_MASK; + raw_spin_unlock(®_user_mask_modification); +} + #define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \ .matches = is_affected_midr_range, \ .midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max) @@ -692,6 +708,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2658417 + { + .desc = "ARM erratum 2658417", + .capability = ARM64_WORKAROUND_2658417, + /* Cortex-A510 r0p0 - r1p1 */ + ERRATA_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1), + MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)), + .cpu_enable = cpu_clear_bf16_from_user_emulation, + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d8361691efeb..6062454a9067 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -108,8 +108,7 @@ DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcaps); static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS]; -/* Need also bit for ARM64_CB_PATCH */ -DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); +DECLARE_BITMAP(boot_capabilities, ARM64_NCAPS); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); @@ -134,31 +133,12 @@ DEFINE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); */ static cpumask_var_t cpu_32bit_el0_mask __cpumask_var_read_mostly; -/* - * Flag to indicate if we have computed the system wide - * capabilities based on the boot time active CPUs. This - * will be used to determine if a new booting CPU should - * go through the verification process to make sure that it - * supports the system capabilities, without using a hotplug - * notifier. This is also used to decide if we could use - * the fast path for checking constant CPU caps. - */ -DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); -EXPORT_SYMBOL(arm64_const_caps_ready); -static inline void finalize_system_capabilities(void) -{ - static_branch_enable(&arm64_const_caps_ready); -} - void dump_cpu_features(void) { /* file-wide pr_fmt adds "CPU features: " prefix */ pr_emerg("0x%*pb\n", ARM64_NCAPS, &cpu_hwcaps); } -DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS); -EXPORT_SYMBOL(cpu_hwcap_keys); - #define __ARM64_FTR_BITS(SIGNED, VISIBLE, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \ { \ .sign = SIGNED, \ @@ -243,35 +223,35 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { }; static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_CSV2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_DIT_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_AMU_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_MPAM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SEL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_DIT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AMU_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_MPAM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SEL2_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), - FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_SVE_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_RAS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), - S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), - S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SVE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_RAS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_GIC_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, ID_AA64PFR0_EL1_AdvSIMD_NI), + S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_FP_SHIFT, 4, ID_AA64PFR0_EL1_FP_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL1_SHIFT, 4, ID_AA64PFR0_EL1_ELx_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_EL0_SHIFT, 4, ID_AA64PFR0_EL1_ELx_64BIT_ONLY), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), - FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SME_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MPAMFRAC_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_RASFRAC_SHIFT, 4, 0), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SME_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MPAM_frac_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_RAS_frac_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_MTE), - FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_MTE_SHIFT, 4, ID_AA64PFR1_MTE_NI), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MTE_SHIFT, 4, ID_AA64PFR1_EL1_MTE_NI), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, ID_AA64PFR1_EL1_SSBS_NI), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_BTI), - FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_BT_SHIFT, 4, 0), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_BT_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -316,9 +296,9 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ECV_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_FGT_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EXS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_FGT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_EXS_SHIFT, 4, 0), /* * Page size not being supported at Stage-2 is not fatal. You * just give up KVM if PAGE_SIZE isn't supported there. Go fix @@ -334,9 +314,9 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { * fields are inconsistent across vCPUs, then it isn't worth * trying to bring KVM up. */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_2_SHIFT, 4, 1), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_2_SHIFT, 4, 1), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN16_2_SHIFT, 4, 1), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN4_2_SHIFT, 4, 1), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN64_2_SHIFT, 4, 1), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64MMFR0_EL1_TGRAN16_2_SHIFT, 4, 1), /* * We already refuse to boot CPUs that don't support our configured * page size, so we can only detect mismatches for a page size other @@ -344,55 +324,55 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { * exist in the wild so, even though we don't like it, we'll have to go * along with it and treat them as non-strict. */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI), - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN16_SHIFT, 4, ID_AA64MMFR0_TGRAN16_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN4_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN4_NI), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN64_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN64_NI), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_TGRAN16_SHIFT, 4, ID_AA64MMFR0_EL1_TGRAN16_NI), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL0_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT, 4, 0), /* Linux shouldn't care about secure memory */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_SNSMEM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_BIGENDEL_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_ASID_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_SNSMEM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_BIGEND_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_ASIDBITS_SHIFT, 4, 0), /* * Differing PARange is fine as long as all peripherals and memory are mapped * within the minimum PARange of all CPUs */ - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_PARANGE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_EL1_PARANGE_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TIDCP1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_AFP_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_ETS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_TWED_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_XNX_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_SPECSEI_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_LOR_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HPD_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VHE_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_VMIDBITS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_HADBS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TIDCP1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_ETS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_TWED_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_XNX_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64MMFR1_EL1_SpecSEI_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_PAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_LO_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HPDS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VH_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_VMIDBits_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, 4, 0), ARM64_FTR_END, }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EVT_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_BBM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_TTL_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IDS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_ST_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_NV_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CCIDX_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_IESB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LSM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_UAO_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_CNP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_E0PD_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_EVT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_BBM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_TTL_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_FWB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IDS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_AT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_ST_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_NV_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CCIDX_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_VARange_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_IESB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_LSM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_UAO_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_EL1_CnP_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -434,17 +414,17 @@ static const struct arm64_ftr_bits ftr_id_mmfr0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_DOUBLELOCK_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_PMSVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_BRPS_SHIFT, 4, 0), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_DoubleLock_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_PMSVer_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_CTX_CMPs_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_WRPs_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_EL1_BRPs_SHIFT, 4, 0), /* * We can instantiate multiple PMU instances with different levels * of support. */ - S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), + S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_EL1_PMUVer_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_EL1_DebugVer_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -750,7 +730,7 @@ static struct arm64_ftr_reg *get_arm64_ftr_reg_nowarn(u32 sys_id) * returns - Upon success, matching ftr_reg entry for id. * - NULL on failure but with an WARN_ON(). */ -static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id) +struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id) { struct arm64_ftr_reg *reg; @@ -1392,6 +1372,12 @@ u64 __read_sysreg_by_encoding(u32 sys_id) #include <linux/irqchip/arm-gic-v3.h> static bool +has_always(const struct arm64_cpu_capabilities *entry, int scope) +{ + return true; +} + +static bool feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) { int val = cpuid_feature_extract_field_width(reg, entry->field_pos, @@ -1401,17 +1387,40 @@ feature_matches(u64 reg, const struct arm64_cpu_capabilities *entry) return val >= entry->min_field_value; } -static bool -has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +static u64 +read_scoped_sysreg(const struct arm64_cpu_capabilities *entry, int scope) { - u64 val; - WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); if (scope == SCOPE_SYSTEM) - val = read_sanitised_ftr_reg(entry->sys_reg); + return read_sanitised_ftr_reg(entry->sys_reg); else - val = __read_sysreg_by_encoding(entry->sys_reg); + return __read_sysreg_by_encoding(entry->sys_reg); +} +static bool +has_user_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + int mask; + struct arm64_ftr_reg *regp; + u64 val = read_scoped_sysreg(entry, scope); + + regp = get_arm64_ftr_reg(entry->sys_reg); + if (!regp) + return false; + + mask = cpuid_feature_extract_unsigned_field_width(regp->user_mask, + entry->field_pos, + entry->field_width); + if (!mask) + return false; + + return feature_matches(val, entry); +} + +static bool +has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope) +{ + u64 val = read_scoped_sysreg(entry, scope); return feature_matches(val, entry); } @@ -1492,7 +1501,7 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); return cpuid_feature_extract_signed_field(pfr0, - ID_AA64PFR0_FP_SHIFT) < 0; + ID_AA64PFR0_EL1_FP_SHIFT) < 0; } static bool has_cache_idc(const struct arm64_cpu_capabilities *entry, @@ -1571,7 +1580,7 @@ bool kaslr_requires_kpti(void) if (IS_ENABLED(CONFIG_ARM64_E0PD)) { u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); if (cpuid_feature_extract_unsigned_field(mmfr2, - ID_AA64MMFR2_E0PD_SHIFT)) + ID_AA64MMFR2_EL1_E0PD_SHIFT)) return false; } @@ -2034,7 +2043,8 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused) static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ATA | SCTLR_EL1_ATA0); - isb(); + + mte_cpu_setup(); /* * Clear the tags in the zero page. This needs to be done via the @@ -2088,12 +2098,22 @@ cpucap_panic_on_conflict(const struct arm64_cpu_capabilities *cap) static const struct arm64_cpu_capabilities arm64_features[] = { { + .capability = ARM64_ALWAYS_BOOT, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_always, + }, + { + .capability = ARM64_ALWAYS_SYSTEM, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_always, + }, + { .desc = "GIC system register CPU interface", .capability = ARM64_HAS_SYSREG_GIC_CPUIF, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_useable_gicv3_cpuif, .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_GIC_SHIFT, + .field_pos = ID_AA64PFR0_EL1_GIC_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, @@ -2104,7 +2124,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR0_EL1, - .field_pos = ID_AA64MMFR0_ECV_SHIFT, + .field_pos = ID_AA64MMFR0_EL1_ECV_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, @@ -2116,7 +2136,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, - .field_pos = ID_AA64MMFR1_PAN_SHIFT, + .field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, @@ -2130,7 +2150,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64MMFR1_EL1, - .field_pos = ID_AA64MMFR1_PAN_SHIFT, + .field_pos = ID_AA64MMFR1_EL1_PAN_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 3, @@ -2168,9 +2188,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_32bit_el0, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL0_SHIFT, + .field_pos = ID_AA64PFR0_EL1_EL0_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT, + .min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT, }, #ifdef CONFIG_KVM { @@ -2180,9 +2200,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_EL1_SHIFT, + .field_pos = ID_AA64PFR0_EL1_EL1_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT, + .min_field_value = ID_AA64PFR0_EL1_ELx_32BIT_64BIT, }, { .desc = "Protected KVM", @@ -2201,7 +2221,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { * more details. */ .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_CSV3_SHIFT, + .field_pos = ID_AA64PFR0_EL1_CSV3_SHIFT, .field_width = 4, .min_field_value = 1, .matches = unmap_kernel_at_el0, @@ -2244,9 +2264,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_SVE, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_SVE_SHIFT, + .field_pos = ID_AA64PFR0_EL1_SVE_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR0_SVE, + .min_field_value = ID_AA64PFR0_EL1_SVE_IMP, .matches = has_cpuid_feature, .cpu_enable = sve_kernel_enable, }, @@ -2259,9 +2279,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_RAS_SHIFT, + .field_pos = ID_AA64PFR0_EL1_RAS_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR0_RAS_V1, + .min_field_value = ID_AA64PFR0_EL1_RAS_IMP, .cpu_enable = cpu_clear_disr, }, #endif /* CONFIG_ARM64_RAS_EXTN */ @@ -2278,9 +2298,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_amu, .sys_reg = SYS_ID_AA64PFR0_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR0_AMU_SHIFT, + .field_pos = ID_AA64PFR0_EL1_AMU_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR0_AMU, + .min_field_value = ID_AA64PFR0_EL1_AMU_IMP, .cpu_enable = cpu_amu_enable, }, #endif /* CONFIG_ARM64_AMU_EXTN */ @@ -2303,7 +2323,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_STAGE2_FWB, .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_FWB_SHIFT, + .field_pos = ID_AA64MMFR2_EL1_FWB_SHIFT, .field_width = 4, .min_field_value = 1, .matches = has_cpuid_feature, @@ -2314,7 +2334,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_ARMv8_4_TTL, .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_TTL_SHIFT, + .field_pos = ID_AA64MMFR2_EL1_TTL_SHIFT, .field_width = 4, .min_field_value = 1, .matches = has_cpuid_feature, @@ -2344,7 +2364,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HW_DBM, .sys_reg = SYS_ID_AA64MMFR1_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR1_HADBS_SHIFT, + .field_pos = ID_AA64MMFR1_EL1_HAFDBS_SHIFT, .field_width = 4, .min_field_value = 2, .matches = has_hw_dbm, @@ -2367,10 +2387,10 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_SSBS_SHIFT, + .field_pos = ID_AA64PFR1_EL1_SSBS_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, - .min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY, + .min_field_value = ID_AA64PFR1_EL1_SSBS_IMP, }, #ifdef CONFIG_ARM64_CNP { @@ -2380,7 +2400,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_useable_cnp, .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR2_CNP_SHIFT, + .field_pos = ID_AA64MMFR2_EL1_CnP_SHIFT, .field_width = 4, .min_field_value = 1, .cpu_enable = cpu_enable_cnp, @@ -2485,7 +2505,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = can_use_gic_priorities, .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_GIC_SHIFT, + .field_pos = ID_AA64PFR0_EL1_GIC_SHIFT, .field_width = 4, .sign = FTR_UNSIGNED, .min_field_value = 1, @@ -2499,7 +2519,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sys_reg = SYS_ID_AA64MMFR2_EL1, .sign = FTR_UNSIGNED, .field_width = 4, - .field_pos = ID_AA64MMFR2_E0PD_SHIFT, + .field_pos = ID_AA64MMFR2_EL1_E0PD_SHIFT, .matches = has_cpuid_feature, .min_field_value = 1, .cpu_enable = cpu_enable_e0pd, @@ -2528,9 +2548,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .cpu_enable = bti_enable, .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_BT_SHIFT, + .field_pos = ID_AA64PFR1_EL1_BT_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR1_BT_BTI, + .min_field_value = ID_AA64PFR1_EL1_BT_IMP, .sign = FTR_UNSIGNED, }, #endif @@ -2541,9 +2561,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_MTE_SHIFT, + .field_pos = ID_AA64PFR1_EL1_MTE_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR1_MTE, + .min_field_value = ID_AA64PFR1_EL1_MTE_MTE2, .sign = FTR_UNSIGNED, .cpu_enable = cpu_enable_mte, }, @@ -2553,9 +2573,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, .sys_reg = SYS_ID_AA64PFR1_EL1, - .field_pos = ID_AA64PFR1_MTE_SHIFT, + .field_pos = ID_AA64PFR1_EL1_MTE_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR1_MTE_ASYMM, + .min_field_value = ID_AA64PFR1_EL1_MTE_MTE3, .sign = FTR_UNSIGNED, }, #endif /* CONFIG_ARM64_MTE */ @@ -2577,9 +2597,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_SME, .sys_reg = SYS_ID_AA64PFR1_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64PFR1_SME_SHIFT, + .field_pos = ID_AA64PFR1_EL1_SME_SHIFT, .field_width = 4, - .min_field_value = ID_AA64PFR1_SME, + .min_field_value = ID_AA64PFR1_EL1_SME_IMP, .matches = has_cpuid_feature, .cpu_enable = sme_kernel_enable, }, @@ -2614,9 +2634,9 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .sys_reg = SYS_ID_AA64MMFR1_EL1, .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR1_TIDCP1_SHIFT, + .field_pos = ID_AA64MMFR1_EL1_TIDCP1_SHIFT, .field_width = 4, - .min_field_value = ID_AA64MMFR1_TIDCP1_IMP, + .min_field_value = ID_AA64MMFR1_EL1_TIDCP1_IMP, .matches = has_cpuid_feature, .cpu_enable = cpu_trap_el0_impdef, }, @@ -2624,7 +2644,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }; #define HWCAP_CPUID_MATCH(reg, field, width, s, min_value) \ - .matches = has_cpuid_feature, \ + .matches = has_user_cpuid_feature, \ .sys_reg = reg, \ .field_pos = field, \ .field_width = width, \ @@ -2708,11 +2728,11 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_TS_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_EL1_RNDR_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_JSCVT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT), @@ -2725,38 +2745,39 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM), - HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), + HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BitPerm_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_BF16_EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SHA3_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SHA3_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SM4_IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_I8MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F32MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_F64MM_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SSBS_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SSBS_SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_BTI - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_BT_BTI, CAP_HWCAP, KERNEL_HWCAP_BTI), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_BT_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_BT_IMP, CAP_HWCAP, KERNEL_HWCAP_BTI), #endif #ifdef CONFIG_ARM64_PTR_AUTH HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA), HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG), #endif #ifdef CONFIG_ARM64_MTE - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_MTE, CAP_HWCAP, KERNEL_HWCAP_MTE), - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_MTE_ASYMM, CAP_HWCAP, KERNEL_HWCAP_MTE3), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE2, CAP_HWCAP, KERNEL_HWCAP_MTE), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_MTE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_MTE_MTE3, CAP_HWCAP, KERNEL_HWCAP_MTE3), #endif /* CONFIG_ARM64_MTE */ - HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), - HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), + HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), + HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), #ifdef CONFIG_ARM64_SME - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_SME, CAP_HWCAP, KERNEL_HWCAP_SME), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), @@ -2929,9 +2950,6 @@ static void __init enable_cpu_capabilities(u16 scope_mask) if (!cpus_have_cap(num)) continue; - /* Ensure cpus_have_const_cap(num) works */ - static_branch_enable(&cpu_hwcap_keys[num]); - if (boot_scope && caps->cpu_enable) /* * Capabilities with SCOPE_BOOT_CPU scope are finalised @@ -3102,7 +3120,7 @@ static void verify_hyp_capabilities(void) /* Verify IPA range */ parange = cpuid_feature_extract_unsigned_field(mmfr0, - ID_AA64MMFR0_PARANGE_SHIFT); + ID_AA64MMFR0_EL1_PARANGE_SHIFT); ipa_max = id_aa64mmfr0_parange_to_phys_shift(parange); if (ipa_max < get_kvm_ipa_limit()) { pr_crit("CPU%d: IPA range mismatch\n", smp_processor_id()); @@ -3253,9 +3271,6 @@ void __init setup_cpu_features(void) sme_setup(); minsigstksz_setup(); - /* Advertise that we have computed the system capabilities */ - finalize_system_capabilities(); - /* * Check for sane CTR_EL0.CWG value. */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d7702f39b4d3..28d4f442b0bc 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -115,6 +115,7 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_FA64] = "smefa64", [KERNEL_HWCAP_WFXT] = "wfxt", [KERNEL_HWCAP_EBF16] = "ebf16", + [KERNEL_HWCAP_SVE_EBF16] = "sveebf16", }; #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index bf9fe71589bc..3da09778267e 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -28,7 +28,7 @@ u8 debug_monitors_arch(void) { return cpuid_feature_extract_unsigned_field(read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1), - ID_AA64DFR0_DEBUGVER_SHIFT); + ID_AA64DFR0_EL1_DebugVer_SHIFT); } /* diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index c75ca36b4a49..9173fad279af 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -379,11 +379,20 @@ static void noinstr el1_pc(struct pt_regs *regs, unsigned long esr) exit_to_kernel_mode(regs); } -static void noinstr el1_undef(struct pt_regs *regs) +static void noinstr el1_undef(struct pt_regs *regs, unsigned long esr) { enter_from_kernel_mode(regs); local_daif_inherit(regs); - do_undefinstr(regs); + do_undefinstr(regs, esr); + local_daif_mask(); + exit_to_kernel_mode(regs); +} + +static void noinstr el1_bti(struct pt_regs *regs, unsigned long esr) +{ + enter_from_kernel_mode(regs); + local_daif_inherit(regs); + do_el1_bti(regs, esr); local_daif_mask(); exit_to_kernel_mode(regs); } @@ -402,7 +411,7 @@ static void noinstr el1_fpac(struct pt_regs *regs, unsigned long esr) { enter_from_kernel_mode(regs); local_daif_inherit(regs); - do_ptrauth_fault(regs, esr); + do_el1_fpac(regs, esr); local_daif_mask(); exit_to_kernel_mode(regs); } @@ -425,7 +434,10 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs) break; case ESR_ELx_EC_SYS64: case ESR_ELx_EC_UNKNOWN: - el1_undef(regs); + el1_undef(regs, esr); + break; + case ESR_ELx_EC_BTI: + el1_bti(regs, esr); break; case ESR_ELx_EC_BREAKPT_CUR: case ESR_ELx_EC_SOFTSTP_CUR: @@ -582,11 +594,11 @@ static void noinstr el0_sp(struct pt_regs *regs, unsigned long esr) exit_to_user_mode(regs); } -static void noinstr el0_undef(struct pt_regs *regs) +static void noinstr el0_undef(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); - do_undefinstr(regs); + do_undefinstr(regs, esr); exit_to_user_mode(regs); } @@ -594,7 +606,7 @@ static void noinstr el0_bti(struct pt_regs *regs) { enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); - do_bti(regs); + do_el0_bti(regs); exit_to_user_mode(regs); } @@ -629,7 +641,7 @@ static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr) { enter_from_user_mode(regs); local_daif_restore(DAIF_PROCCTX); - do_ptrauth_fault(regs, esr); + do_el0_fpac(regs, esr); exit_to_user_mode(regs); } @@ -670,7 +682,7 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs) el0_pc(regs, esr); break; case ESR_ELx_EC_UNKNOWN: - el0_undef(regs); + el0_undef(regs, esr); break; case ESR_ELx_EC_BTI: el0_bti(regs); @@ -788,7 +800,7 @@ asmlinkage void noinstr el0t_32_sync_handler(struct pt_regs *regs) case ESR_ELx_EC_CP14_MR: case ESR_ELx_EC_CP14_LS: case ESR_ELx_EC_CP14_64: - el0_undef(regs); + el0_undef(regs, esr); break; case ESR_ELx_EC_CP15_32: case ESR_ELx_EC_CP15_64: diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2d73b3e793b2..e28137d64b76 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -114,7 +114,7 @@ * them if required. */ .macro apply_ssbd, state, tmp1, tmp2 -alternative_cb spectre_v4_patch_fw_mitigation_enable +alternative_cb ARM64_ALWAYS_SYSTEM, spectre_v4_patch_fw_mitigation_enable b .L__asm_ssbd_skip\@ // Patched to NOP alternative_cb_end ldr_this_cpu \tmp2, arm64_ssbd_callback_required, \tmp1 @@ -123,7 +123,7 @@ alternative_cb_end tbnz \tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 mov w1, #\state -alternative_cb smccc_patch_fw_mitigation_conduit +alternative_cb ARM64_ALWAYS_SYSTEM, smccc_patch_fw_mitigation_conduit nop // Patched to SMC/HVC #0 alternative_cb_end .L__asm_ssbd_skip\@: @@ -175,7 +175,7 @@ alternative_else_nop_endif .macro mte_set_kernel_gcr, tmp, tmp2 #ifdef CONFIG_KASAN_HW_TAGS -alternative_cb kasan_hw_tags_enable +alternative_cb ARM64_ALWAYS_SYSTEM, kasan_hw_tags_enable b 1f alternative_cb_end mov \tmp, KERNEL_GCR_EL1 @@ -186,7 +186,7 @@ alternative_cb_end .macro mte_set_user_gcr, tsk, tmp, tmp2 #ifdef CONFIG_KASAN_HW_TAGS -alternative_cb kasan_hw_tags_enable +alternative_cb ARM64_ALWAYS_SYSTEM, kasan_hw_tags_enable b 1f alternative_cb_end ldr \tmp, [\tsk, #THREAD_MTE_CTRL] diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 26789865748c..8745175f4a75 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -217,11 +217,26 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long pc = rec->ip; u32 old = 0, new; + new = aarch64_insn_gen_nop(); + + /* + * When using mcount, callsites in modules may have been initalized to + * call an arbitrary module PLT (which redirects to the _mcount stub) + * rather than the ftrace PLT we'll use at runtime (which redirects to + * the ftrace trampoline). We can ignore the old PLT when initializing + * the callsite. + * + * Note: 'mod' is only set at module load time. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && + IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) { + return aarch64_insn_patch_text_nosync((void *)pc, new); + } + if (!ftrace_find_callable_addr(rec, mod, &addr)) return -EINVAL; old = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); - new = aarch64_insn_gen_nop(); return ftrace_modify_code(pc, old, new, true); } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 814b6587ccb7..2196aad7b55b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -99,7 +99,7 @@ SYM_CODE_START(primary_entry) */ #if VA_BITS > 48 mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, #0xf << ID_AA64MMFR2_LVA_SHIFT + tst x0, #0xf << ID_AA64MMFR2_EL1_VARange_SHIFT mov x0, #VA_BITS mov x25, #VA_BITS_MIN csel x25, x25, x0, eq @@ -658,10 +658,10 @@ SYM_FUNC_END(__secondary_too_slow) */ SYM_FUNC_START(__enable_mmu) mrs x3, ID_AA64MMFR0_EL1 - ubfx x3, x3, #ID_AA64MMFR0_TGRAN_SHIFT, 4 - cmp x3, #ID_AA64MMFR0_TGRAN_SUPPORTED_MIN + ubfx x3, x3, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4 + cmp x3, #ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MIN b.lt __no_granule_support - cmp x3, #ID_AA64MMFR0_TGRAN_SUPPORTED_MAX + cmp x3, #ID_AA64MMFR0_EL1_TGRAN_SUPPORTED_MAX b.gt __no_granule_support phys_to_ttbr x2, x2 msr ttbr0_el1, x2 // load TTBR0 @@ -679,7 +679,7 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) b.ne 2f mrs_s x0, SYS_ID_AA64MMFR2_EL1 - and x0, x0, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + and x0, x0, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) cbnz x0, 2f update_early_cpu_boot_status \ diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 12c7fad02ae5..2ee18c860f2a 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -98,7 +98,7 @@ SYM_CODE_START_LOCAL(elx_sync) SYM_CODE_END(elx_sync) SYM_CODE_START_LOCAL(__finalise_el2) - check_override id_aa64pfr0 ID_AA64PFR0_SVE_SHIFT .Linit_sve .Lskip_sve + check_override id_aa64pfr0 ID_AA64PFR0_EL1_SVE_SHIFT .Linit_sve .Lskip_sve .Linit_sve: /* SVE register access */ mrs x0, cptr_el2 // Disable SVE traps @@ -109,7 +109,7 @@ SYM_CODE_START_LOCAL(__finalise_el2) msr_s SYS_ZCR_EL2, x1 // length for EL1. .Lskip_sve: - check_override id_aa64pfr1 ID_AA64PFR1_SME_SHIFT .Linit_sme .Lskip_sme + check_override id_aa64pfr1 ID_AA64PFR1_EL1_SME_SHIFT .Linit_sme .Lskip_sme .Linit_sme: /* SME register access and priority mapping */ mrs x0, cptr_el2 // Disable SME traps @@ -142,7 +142,7 @@ SYM_CODE_START_LOCAL(__finalise_el2) msr_s SYS_SMPRIMAP_EL2, xzr // Make all priorities equal mrs x1, id_aa64mmfr1_el1 // HCRX_EL2 present? - ubfx x1, x1, #ID_AA64MMFR1_HCX_SHIFT, #4 + ubfx x1, x1, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 cbz x1, .Lskip_sme mrs_s x1, SYS_HCRX_EL2 @@ -157,7 +157,7 @@ SYM_CODE_START_LOCAL(__finalise_el2) tbnz x1, #0, 1f // Needs to be VHE capable, obviously - check_override id_aa64mmfr1 ID_AA64MMFR1_VHE_SHIFT 2f 1f + check_override id_aa64mmfr1 ID_AA64MMFR1_EL1_VH_SHIFT 2f 1f 1: mov_q x0, HVC_STUB_ERR eret diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 1b0542c69738..95133765ed29 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -50,7 +50,7 @@ static const struct ftr_set_desc mmfr1 __initconst = { .name = "id_aa64mmfr1", .override = &id_aa64mmfr1_override, .fields = { - FIELD("vh", ID_AA64MMFR1_VHE_SHIFT, mmfr1_vh_filter), + FIELD("vh", ID_AA64MMFR1_EL1_VH_SHIFT, mmfr1_vh_filter), {} }, }; @@ -74,7 +74,7 @@ static const struct ftr_set_desc pfr0 __initconst = { .name = "id_aa64pfr0", .override = &id_aa64pfr0_override, .fields = { - FIELD("sve", ID_AA64PFR0_SVE_SHIFT, pfr0_sve_filter), + FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter), {} }, }; @@ -98,9 +98,9 @@ static const struct ftr_set_desc pfr1 __initconst = { .name = "id_aa64pfr1", .override = &id_aa64pfr1_override, .fields = { - FIELD("bt", ID_AA64PFR1_BT_SHIFT, NULL ), - FIELD("mte", ID_AA64PFR1_MTE_SHIFT, NULL), - FIELD("sme", ID_AA64PFR1_SME_SHIFT, pfr1_sme_filter), + FIELD("bt", ID_AA64PFR1_EL1_BT_SHIFT, NULL ), + FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL), + FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter), {} }, }; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index afa69e04e75e..4aaa5f3d1f65 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -73,6 +73,7 @@ KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter); KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable); KVM_NVHE_ALIAS(spectre_bhb_patch_wa3); KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb); +KVM_NVHE_ALIAS(alt_cb_patch_nops); /* Global kernel state accessed by nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_vgic_global_state); @@ -89,10 +90,6 @@ KVM_NVHE_ALIAS(__icache_flags); /* VMID bits set by the KVM VMID allocator */ KVM_NVHE_ALIAS(kvm_arm_vmid_bits); -/* Kernel symbols needed for cpus_have_final/const_caps checks. */ -KVM_NVHE_ALIAS(arm64_const_caps_ready); -KVM_NVHE_ALIAS(cpu_hwcap_keys); - /* Static keys which are set if a vGIC trap should be handled in hyp. */ KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index bda49430c9ea..38dbd3828f13 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -21,7 +21,9 @@ #include <linux/seq_file.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> +#include <asm/exception.h> #include <asm/vmap_stack.h> +#include <asm/softirq_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); @@ -71,6 +73,18 @@ static void init_irq_stacks(void) } #endif +#ifndef CONFIG_PREEMPT_RT +static void ____do_softirq(struct pt_regs *regs) +{ + __do_softirq(); +} + +void do_softirq_own_stack(void) +{ + call_on_irq_stack(NULL, ____do_softirq); +} +#endif + static void default_handle_irq(struct pt_regs *regs) { panic("IRQ taken without a root IRQ handler\n"); diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index a3d0494f25a9..5a0a8f552a61 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -37,7 +37,8 @@ struct plt_entry get_plt_entry(u64 dst, void *pc) return plt; } -bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b) +static bool plt_entries_equal(const struct plt_entry *a, + const struct plt_entry *b) { u64 p, q; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f2d4bb14bfab..76b41e4ca9fa 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -476,21 +476,6 @@ overflow: return -ENOEXEC; } -static const Elf_Shdr *find_section(const Elf_Ehdr *hdr, - const Elf_Shdr *sechdrs, - const char *name) -{ - const Elf_Shdr *s, *se; - const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - - for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { - if (strcmp(name, secstrs + s->sh_name) == 0) - return s; - } - - return NULL; -} - static inline void __init_plt(struct plt_entry *plt, unsigned long addr) { *plt = get_plt_entry(addr, plt); diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index b2b730233274..aca88470fb69 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -285,6 +285,49 @@ void mte_thread_switch(struct task_struct *next) mte_check_tfsr_el1(); } +void mte_cpu_setup(void) +{ + u64 rgsr; + + /* + * CnP must be enabled only after the MAIR_EL1 register has been set + * up. Inconsistent MAIR_EL1 between CPUs sharing the same TLB may + * lead to the wrong memory type being used for a brief window during + * CPU power-up. + * + * CnP is not a boot feature so MTE gets enabled before CnP, but let's + * make sure that is the case. + */ + BUG_ON(read_sysreg(ttbr0_el1) & TTBR_CNP_BIT); + BUG_ON(read_sysreg(ttbr1_el1) & TTBR_CNP_BIT); + + /* Normal Tagged memory type at the corresponding MAIR index */ + sysreg_clear_set(mair_el1, + MAIR_ATTRIDX(MAIR_ATTR_MASK, MT_NORMAL_TAGGED), + MAIR_ATTRIDX(MAIR_ATTR_NORMAL_TAGGED, + MT_NORMAL_TAGGED)); + + write_sysreg_s(KERNEL_GCR_EL1, SYS_GCR_EL1); + + /* + * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then + * RGSR_EL1.SEED must be non-zero for IRG to produce + * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we + * must initialize it. + */ + rgsr = (read_sysreg(CNTVCT_EL0) & SYS_RGSR_EL1_SEED_MASK) << + SYS_RGSR_EL1_SEED_SHIFT; + if (rgsr == 0) + rgsr = 1 << SYS_RGSR_EL1_SEED_SHIFT; + write_sysreg_s(rgsr, SYS_RGSR_EL1); + + /* clear any pending tag check faults in TFSR*_EL1 */ + write_sysreg_s(0, SYS_TFSR_EL1); + write_sysreg_s(0, SYS_TFSRE0_EL1); + + local_flush_tlb_all(); +} + void mte_suspend_enter(void) { if (!system_supports_mte()) @@ -301,6 +344,14 @@ void mte_suspend_enter(void) mte_check_tfsr_el1(); } +void mte_suspend_exit(void) +{ + if (!system_supports_mte()) + return; + + mte_cpu_setup(); +} + long set_mte_ctrl(struct task_struct *task, unsigned long arg) { u64 mte_ctrl = (~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) & diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index cb69ff1e6138..7b0643fe2f13 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -390,7 +390,7 @@ static const struct attribute_group armv8_pmuv3_caps_attr_group = { */ static bool armv8pmu_has_long_event(struct arm_pmu *cpu_pmu) { - return (cpu_pmu->pmuver >= ID_AA64DFR0_PMUVER_8_5); + return (cpu_pmu->pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P5); } static inline bool armv8pmu_event_has_user_read(struct perf_event *event) @@ -1145,8 +1145,8 @@ static void __armv8pmu_probe_pmu(void *info) dfr0 = read_sysreg(id_aa64dfr0_el1); pmuver = cpuid_feature_extract_unsigned_field(dfr0, - ID_AA64DFR0_PMUVER_SHIFT); - if (pmuver == ID_AA64DFR0_PMUVER_IMP_DEF || pmuver == 0) + ID_AA64DFR0_EL1_PMUVer_SHIFT); + if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || pmuver == 0) return; cpu_pmu->pmuver = pmuver; @@ -1172,7 +1172,7 @@ static void __armv8pmu_probe_pmu(void *info) pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); /* store PMMIR_EL1 register for sysfs */ - if (pmuver >= ID_AA64DFR0_PMUVER_8_4 && (pmceid_raw[1] & BIT(31))) + if (pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P4 && (pmceid_raw[1] & BIT(31))) cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1); else cpu_pmu->reg_pmmir = 0; diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c index f6f58e6265df..b4eece3eb17d 100644 --- a/arch/arm64/kernel/perf_regs.c +++ b/arch/arm64/kernel/perf_regs.c @@ -9,9 +9,27 @@ #include <asm/perf_regs.h> #include <asm/ptrace.h> +static u64 perf_ext_regs_value(int idx) +{ + switch (idx) { + case PERF_REG_ARM64_VG: + if (WARN_ON_ONCE(!system_supports_sve())) + return 0; + + /* + * Vector granule is current length in bits of SVE registers + * divided by 64. + */ + return (task_get_sve_vl(current) * 8) / 64; + default: + WARN_ON_ONCE(true); + return 0; + } +} + u64 perf_reg_value(struct pt_regs *regs, int idx) { - if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX)) + if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_EXTENDED_MAX)) return 0; /* @@ -51,6 +69,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) if ((u32)idx == PERF_REG_ARM64_PC) return regs->pc; + if ((u32)idx >= PERF_REG_ARM64_MAX) + return perf_ext_regs_value(idx); + return regs->regs[idx]; } @@ -58,7 +79,12 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) int perf_reg_validate(u64 mask) { - if (!mask || mask & REG_RESERVED) + u64 reserved_mask = REG_RESERVED; + + if (system_supports_sve()) + reserved_mask &= ~(1ULL << PERF_REG_ARM64_VG); + + if (!mask || mask & reserved_mask) return -EINVAL; return 0; diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index d1d182320245..c9e4d0720285 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -44,13 +44,28 @@ post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *); static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { kprobe_opcode_t *addr = p->ainsn.api.insn; - void *addrs[] = {addr, addr + 1}; - u32 insns[] = {p->opcode, BRK64_OPCODE_KPROBES_SS}; - /* prepare insn slot */ - aarch64_insn_patch_text(addrs, insns, 2); - - flush_icache_range((uintptr_t)addr, (uintptr_t)(addr + MAX_INSN_SIZE)); + /* + * Prepare insn slot, Mark Rutland points out it depends on a coupe of + * subtleties: + * + * - That the I-cache maintenance for these instructions is complete + * *before* the kprobe BRK is written (and aarch64_insn_patch_text_nosync() + * ensures this, but just omits causing a Context-Synchronization-Event + * on all CPUS). + * + * - That the kprobe BRK results in an exception (and consequently a + * Context-Synchronoization-Event), which ensures that the CPU will + * fetch thesingle-step slot instructions *after* this, ensuring that + * the new instructions are used + * + * It supposes to place ISB after patching to guarantee I-cache maintenance + * is observed on all CPUS, however, single-step slot is installed in + * the BRK exception handler, so it is unnecessary to generate + * Contex-Synchronization-Event via ISB again. + */ + aarch64_insn_patch_text_nosync(addr, p->opcode); + aarch64_insn_patch_text_nosync(addr + 1, BRK64_OPCODE_KPROBES_SS); /* * Needs restoring of return address after stepping xol. diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 40be3a7c2c53..a8ea1637b137 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -168,7 +168,7 @@ static enum mitigation_state spectre_v2_get_cpu_hw_mitigation_state(void) /* If the CPU has CSV2 set, we're safe */ pfr0 = read_cpuid(ID_AA64PFR0_EL1); - if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT)) + if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT)) return SPECTRE_UNAFFECTED; /* Alternatively, we have a list of unaffected CPUs */ @@ -586,7 +586,7 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt, if (spectre_v4_mitigations_off()) return; - if (cpus_have_final_cap(ARM64_SSBS)) + if (cpus_have_cap(ARM64_SSBS)) return; if (spectre_v4_mitigations_dynamic()) @@ -945,7 +945,7 @@ static bool supports_ecbhb(int scope) mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, - ID_AA64MMFR1_ECBHB_SHIFT); + ID_AA64MMFR1_EL1_ECBHB_SHIFT); } bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, @@ -988,6 +988,14 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) isb(); } +static bool __read_mostly __nospectre_bhb; +static int __init parse_spectre_bhb_param(char *str) +{ + __nospectre_bhb = true; + return 0; +} +early_param("nospectre_bhb", parse_spectre_bhb_param); + void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) { bp_hardening_cb_t cpu_cb; @@ -1001,7 +1009,7 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) /* No point mitigating Spectre-BHB alone. */ } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); - } else if (cpu_mitigations_off()) { + } else if (cpu_mitigations_off() || __nospectre_bhb) { pr_info_once("spectre-bhb mitigation disabled by command line option\n"); } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { state = SPECTRE_MITIGATED; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 041d2ae5c30a..c2fb5755bbec 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -121,7 +121,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || - on_irq_stack(addr, sizeof(unsigned long), NULL); + on_irq_stack(addr, sizeof(unsigned long)); } /** @@ -666,10 +666,18 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, static int tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { + int ret; + if (target == current) tls_preserve_current_state(); - return membuf_store(&to, target->thread.uw.tp_value); + ret = membuf_store(&to, target->thread.uw.tp_value); + if (system_supports_tpidr2()) + ret = membuf_store(&to, target->thread.tpidr2_el0); + else + ret = membuf_zero(&to, sizeof(u64)); + + return ret; } static int tls_set(struct task_struct *target, const struct user_regset *regset, @@ -677,13 +685,20 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - unsigned long tls = target->thread.uw.tp_value; + unsigned long tls[2]; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); + tls[0] = target->thread.uw.tp_value; + if (system_supports_sme()) + tls[1] = target->thread.tpidr2_el0; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count); if (ret) return ret; - target->thread.uw.tp_value = tls; + target->thread.uw.tp_value = tls[0]; + if (system_supports_sme()) + target->thread.tpidr2_el0 = tls[1]; + return ret; } @@ -1390,7 +1405,7 @@ static const struct user_regset aarch64_regsets[] = { }, [REGSET_TLS] = { .core_note_type = NT_ARM_TLS, - .n = 1, + .n = 2, .size = sizeof(void *), .align = sizeof(void *), .regset_get = tls_get, diff --git a/arch/arm64/kernel/reloc_test_core.c b/arch/arm64/kernel/reloc_test_core.c index e87a2b7f20f6..99f2ffe9fc05 100644 --- a/arch/arm64/kernel/reloc_test_core.c +++ b/arch/arm64/kernel/reloc_test_core.c @@ -48,7 +48,7 @@ static struct { { "R_AARCH64_PREL16", relative_data16, (u64)&sym64_rel }, }; -static int reloc_test_init(void) +static int __init reloc_test_init(void) { int i; @@ -67,7 +67,7 @@ static int reloc_test_init(void) return 0; } -static void reloc_test_exit(void) +static void __exit reloc_test_exit(void) { } diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index d20620a1c51a..d56e170e1ca7 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -162,38 +162,6 @@ static int init_sdei_scs(void) return err; } -static bool on_sdei_normal_stack(unsigned long sp, unsigned long size, - struct stack_info *info) -{ - unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); - unsigned long high = low + SDEI_STACK_SIZE; - - return on_stack(sp, size, low, high, STACK_TYPE_SDEI_NORMAL, info); -} - -static bool on_sdei_critical_stack(unsigned long sp, unsigned long size, - struct stack_info *info) -{ - unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr); - unsigned long high = low + SDEI_STACK_SIZE; - - return on_stack(sp, size, low, high, STACK_TYPE_SDEI_CRITICAL, info); -} - -bool _on_sdei_stack(unsigned long sp, unsigned long size, struct stack_info *info) -{ - if (!IS_ENABLED(CONFIG_VMAP_STACK)) - return false; - - if (on_sdei_critical_stack(sp, size, info)) - return true; - - if (on_sdei_normal_stack(sp, size, info)) - return true; - - return false; -} - unsigned long sdei_arch_get_entry_point(int conduit) { /* diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ce190ee18a20..634279b3b03d 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -68,31 +68,6 @@ static inline void unwind_init_from_task(struct unwind_state *state, } /* - * We can only safely access per-cpu stacks from current in a non-preemptible - * context. - */ -static bool on_accessible_stack(const struct task_struct *tsk, - unsigned long sp, unsigned long size, - struct stack_info *info) -{ - if (info) - info->type = STACK_TYPE_UNKNOWN; - - if (on_task_stack(tsk, sp, size, info)) - return true; - if (tsk != current || preemptible()) - return false; - if (on_irq_stack(sp, size, info)) - return true; - if (on_overflow_stack(sp, size, info)) - return true; - if (on_sdei_stack(sp, size, info)) - return true; - - return false; -} - -/* * Unwind from one frame record (A) to the next frame record (B). * * We terminate early if the location of B indicates a malformed chain of frame @@ -103,14 +78,13 @@ static int notrace unwind_next(struct unwind_state *state) { struct task_struct *tsk = state->task; unsigned long fp = state->fp; - struct stack_info info; int err; /* Final frame; nothing to unwind */ if (fp == (unsigned long)task_pt_regs(tsk)->stackframe) return -ENOENT; - err = unwind_next_common(state, &info, on_accessible_stack, NULL); + err = unwind_next_frame_record(state); if (err) return err; @@ -190,11 +164,47 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) barrier(); } +/* + * Per-cpu stacks are only accessible when unwinding the current task in a + * non-preemptible context. + */ +#define STACKINFO_CPU(name) \ + ({ \ + ((task == current) && !preemptible()) \ + ? stackinfo_get_##name() \ + : stackinfo_get_unknown(); \ + }) + +/* + * SDEI stacks are only accessible when unwinding the current task in an NMI + * context. + */ +#define STACKINFO_SDEI(name) \ + ({ \ + ((task == current) && in_nmi()) \ + ? stackinfo_get_sdei_##name() \ + : stackinfo_get_unknown(); \ + }) + noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { - struct unwind_state state; + struct stack_info stacks[] = { + stackinfo_get_task(task), + STACKINFO_CPU(irq), +#if defined(CONFIG_VMAP_STACK) + STACKINFO_CPU(overflow), +#endif +#if defined(CONFIG_VMAP_STACK) && defined(CONFIG_ARM_SDE_INTERFACE) + STACKINFO_SDEI(normal), + STACKINFO_SDEI(critical), +#endif + }; + struct unwind_state state = { + .stacks = stacks, + .nr_stacks = ARRAY_SIZE(stacks), + }; if (regs) { if (task != current) diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 9135fe0f3df5..8b02d310838f 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -43,6 +43,8 @@ void notrace __cpu_suspend_exit(void) { unsigned int cpu = smp_processor_id(); + mte_suspend_exit(); + /* * We are resuming from reset with the idmap active in TTBR0_EL1. * We must uninstall the idmap and restore the expected MMU diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 3c026da95bbc..23d281ed7621 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -181,12 +181,12 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs) #define S_SMP " SMP" -static int __die(const char *str, int err, struct pt_regs *regs) +static int __die(const char *str, long err, struct pt_regs *regs) { static int die_counter; int ret; - pr_emerg("Internal error: %s: %x [#%d]" S_PREEMPT S_SMP "\n", + pr_emerg("Internal error: %s: %016lx [#%d]" S_PREEMPT S_SMP "\n", str, err, ++die_counter); /* trap and error numbers are mostly meaningless on ARM */ @@ -207,7 +207,7 @@ static DEFINE_RAW_SPINLOCK(die_lock); /* * This function is protected against re-entrancy. */ -void die(const char *str, struct pt_regs *regs, int err) +void die(const char *str, struct pt_regs *regs, long err) { int ret; unsigned long flags; @@ -486,7 +486,7 @@ void arm64_notify_segfault(unsigned long addr) force_signal_inject(SIGSEGV, code, addr, 0); } -void do_undefinstr(struct pt_regs *regs) +void do_undefinstr(struct pt_regs *regs, unsigned long esr) { /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) @@ -495,28 +495,38 @@ void do_undefinstr(struct pt_regs *regs) if (call_undef_hook(regs) == 0) return; - BUG_ON(!user_mode(regs)); + if (!user_mode(regs)) + die("Oops - Undefined instruction", regs, esr); + force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } NOKPROBE_SYMBOL(do_undefinstr); -void do_bti(struct pt_regs *regs) +void do_el0_bti(struct pt_regs *regs) { - BUG_ON(!user_mode(regs)); force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); } -NOKPROBE_SYMBOL(do_bti); -void do_ptrauth_fault(struct pt_regs *regs, unsigned long esr) +void do_el1_bti(struct pt_regs *regs, unsigned long esr) +{ + die("Oops - BTI", regs, esr); +} +NOKPROBE_SYMBOL(do_el1_bti); + +void do_el0_fpac(struct pt_regs *regs, unsigned long esr) +{ + force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); +} + +void do_el1_fpac(struct pt_regs *regs, unsigned long esr) { /* - * Unexpected FPAC exception or pointer authentication failure in - * the kernel: kill the task before it does any more harm. + * Unexpected FPAC exception in the kernel: kill the task before it + * does any more harm. */ - BUG_ON(!user_mode(regs)); - force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr); + die("Oops - FPAC", regs, esr); } -NOKPROBE_SYMBOL(do_ptrauth_fault); +NOKPROBE_SYMBOL(do_el1_fpac) #define __user_cache_maint(insn, address, res) \ if (address >= TASK_SIZE_MAX) { \ @@ -759,7 +769,7 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs) hook_base = cp15_64_hooks; break; default: - do_undefinstr(regs); + do_undefinstr(regs, esr); return; } @@ -774,7 +784,7 @@ void do_cp15instr(unsigned long esr, struct pt_regs *regs) * EL0. Fall back to our usual undefined instruction handler * so that we handle these consistently. */ - do_undefinstr(regs); + do_undefinstr(regs, esr); } NOKPROBE_SYMBOL(do_cp15instr); #endif @@ -794,7 +804,7 @@ void do_sysinstr(unsigned long esr, struct pt_regs *regs) * back to our usual undefined instruction handler so that we handle * these consistently. */ - do_undefinstr(regs); + do_undefinstr(regs, esr); } NOKPROBE_SYMBOL(do_sysinstr); @@ -971,7 +981,7 @@ static int bug_handler(struct pt_regs *regs, unsigned long esr) { switch (report_bug(regs->pc, regs)) { case BUG_TRAP_TYPE_BUG: - die("Oops - BUG", regs, 0); + die("Oops - BUG", regs, esr); break; case BUG_TRAP_TYPE_WARN: @@ -1071,7 +1081,7 @@ static int kasan_handler(struct pt_regs *regs, unsigned long esr) * This is something that might be fixed at some point in the future. */ if (!recover) - die("Oops - KASAN", regs, 0); + die("Oops - KASAN", regs, esr); /* If thread survives, skip over the brk instruction and continue: */ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index a61fc4f989b3..ac93a2ee9c07 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -29,9 +29,6 @@ #include <asm/signal32.h> #include <asm/vdso.h> -extern char vdso_start[], vdso_end[]; -extern char vdso32_start[], vdso32_end[]; - enum vdso_abi { VDSO_ABI_AA64, VDSO_ABI_AA32, diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index e69fb4aaaf3e..6028f1fe2d1c 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -48,6 +48,13 @@ SECTIONS PROVIDE (_etext = .); PROVIDE (etext = .); + . = ALIGN(4); + .altinstructions : { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } + .dynamic : { *(.dynamic) } :text :dynamic .rela.dyn : ALIGN(8) { *(.rela .rela*) } |