diff options
author | Ingo Molnar <mingo@kernel.org> | 2020-06-26 13:24:42 +0300 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2020-06-26 13:24:42 +0300 |
commit | 2c92d787cc9fad57d05c96bd117782183768258a (patch) | |
tree | 51c0c567b8be2fd56073a8ce31f8ebd123a7d562 /arch | |
parent | 145a773aef83181d47ebab21bb33c89233aadb1e (diff) | |
parent | 8be3a53e18e0e1a98f288f6c7f5e9da3adbe9c49 (diff) | |
download | linux-2c92d787cc9fad57d05c96bd117782183768258a.tar.xz |
Merge branch 'linus' into x86/entry, to resolve conflicts
Conflicts:
arch/x86/kernel/traps.c
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
95 files changed, 961 insertions, 329 deletions
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 10499d44964a..9a79ef6b1876 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -84,7 +84,8 @@ static int ftrace_modify_code(unsigned long pc, unsigned long old, old = __opcode_to_mem_arm(old); if (validate) { - if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&replaced, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (replaced != old) diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c index 6a95b9296640..7bd30c0a4280 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -236,7 +236,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) /* patch_text() only supports int-sized breakpoints */ BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE); - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 65a3b1e75480..17d5a785df28 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -396,7 +396,7 @@ int is_valid_bugaddr(unsigned long pc) u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); #endif - if (probe_kernel_address((unsigned *)pc, bkpt)) + if (get_kernel_nofault(bkpt, (void *)pc)) return 0; return bkpt == insn; diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index 84718eddae60..81a627e6e1c5 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -774,7 +774,7 @@ static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_arm(instr); @@ -789,7 +789,7 @@ static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst) if (user_mode(regs)) fault = get_user(instr, ip); else - fault = probe_kernel_address(ip, instr); + fault = get_kernel_nofault(instr, ip); *inst = __mem_to_opcode_thumb16(instr); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 31380da53689..a4a094bedcb2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1564,7 +1564,7 @@ config CC_HAS_SIGN_RETURN_ADDRESS def_bool $(cc-option,-msign-return-address=all) config AS_HAS_PAC - def_bool $(as-option,-Wa$(comma)-march=armv8.3-a) + def_bool $(cc-option,-Wa$(comma)-march=armv8.3-a) config AS_HAS_CFI_NEGATE_RA_STATE def_bool $(as-instr,.cfi_startproc\n.cfi_negate_ra_state\n.cfi_endproc\n) @@ -1630,6 +1630,8 @@ config ARM64_BTI_KERNEL depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697 depends on !CC_IS_GCC || GCC_VERSION >= 100100 + # https://reviews.llvm.org/rGb8ae3fdfa579dbf366b1bb1cbfdbf8c51db7fa55 + depends on !CC_IS_CLANG || CLANG_VERSION >= 100001 depends on !(CC_IS_CLANG && GCOV_KERNEL) depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) help diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug index cdf7ec0b975e..265c4461031f 100644 --- a/arch/arm64/Kconfig.debug +++ b/arch/arm64/Kconfig.debug @@ -8,21 +8,6 @@ config PID_IN_CONTEXTIDR instructions during context switch. Say Y here only if you are planning to use hardware trace tools with this kernel. -config ARM64_RANDOMIZE_TEXT_OFFSET - bool "Randomize TEXT_OFFSET at build time" - help - Say Y here if you want the image load offset (AKA TEXT_OFFSET) - of the kernel to be randomized at build-time. When selected, - this option will cause TEXT_OFFSET to be randomized upon any - build of the kernel, and the offset will be reflected in the - text_offset field of the resulting Image. This can be used to - fuzz-test bootloaders which respect text_offset. - - This option is intended for bootloader and/or kernel testing - only. Bootloaders must make no assumptions regarding the value - of TEXT_OFFSET and platforms must not require a specific - value. - config DEBUG_EFI depends on EFI && DEBUG_INFO bool "UEFI debugging" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 76359cfb328a..a0d94d063fa8 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -121,13 +121,7 @@ endif head-y := arch/arm64/kernel/head.o # The byte offset of the kernel image in RAM from the start of RAM. -ifeq ($(CONFIG_ARM64_RANDOMIZE_TEXT_OFFSET), y) -TEXT_OFFSET := $(shell awk "BEGIN {srand(); printf \"0x%06x\n\", \ - int(2 * 1024 * 1024 / (2 ^ $(CONFIG_ARM64_PAGE_SHIFT)) * \ - rand()) * (2 ^ $(CONFIG_ARM64_PAGE_SHIFT))}") -else TEXT_OFFSET := 0x0 -endif ifeq ($(CONFIG_KASAN_SW_TAGS), y) KASAN_SHADOW_SCALE_SHIFT := 4 diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6dbd267ab931..758e2d1577d0 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -416,7 +416,7 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd) __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ - __pgprot_modify(prot, 0, PTE_PXN) + __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 35cb5e66c504..55c8f3ec6705 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -12,6 +12,7 @@ #include <linux/bug.h> #include <linux/cache.h> #include <linux/compat.h> +#include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/kernel.h> @@ -119,10 +120,20 @@ struct fpsimd_last_state_struct { static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); /* Default VL for tasks that don't set it explicitly: */ -static int sve_default_vl = -1; +static int __sve_default_vl = -1; + +static int get_sve_default_vl(void) +{ + return READ_ONCE(__sve_default_vl); +} #ifdef CONFIG_ARM64_SVE +static void set_sve_default_vl(int val) +{ + WRITE_ONCE(__sve_default_vl, val); +} + /* Maximum supported vector length across all CPUs (initially poisoned) */ int __ro_after_init sve_max_vl = SVE_VL_MIN; int __ro_after_init sve_max_virtualisable_vl = SVE_VL_MIN; @@ -338,13 +349,13 @@ static unsigned int find_supported_vector_length(unsigned int vl) return sve_vl_from_vq(__bit_to_vq(bit)); } -#ifdef CONFIG_SYSCTL +#if defined(CONFIG_ARM64_SVE) && defined(CONFIG_SYSCTL) static int sve_proc_do_default_vl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; - int vl = sve_default_vl; + int vl = get_sve_default_vl(); struct ctl_table tmp_table = { .data = &vl, .maxlen = sizeof(vl), @@ -361,7 +372,7 @@ static int sve_proc_do_default_vl(struct ctl_table *table, int write, if (!sve_vl_valid(vl)) return -EINVAL; - sve_default_vl = find_supported_vector_length(vl); + set_sve_default_vl(find_supported_vector_length(vl)); return 0; } @@ -383,9 +394,9 @@ static int __init sve_sysctl_init(void) return 0; } -#else /* ! CONFIG_SYSCTL */ +#else /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ static int __init sve_sysctl_init(void) { return 0; } -#endif /* ! CONFIG_SYSCTL */ +#endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #define ZREG(sve_state, vq, n) ((char *)(sve_state) + \ (SVE_SIG_ZREG_OFFSET(vq, n) - SVE_SIG_REGS_OFFSET)) @@ -868,7 +879,7 @@ void __init sve_setup(void) * For the default VL, pick the maximum supported value <= 64. * VL == 64 is guaranteed not to grow the signal frame. */ - sve_default_vl = find_supported_vector_length(64); + set_sve_default_vl(find_supported_vector_length(64)); bitmap_andnot(tmp_map, sve_vq_partial_map, sve_vq_map, SVE_VQ_MAX); @@ -889,7 +900,7 @@ void __init sve_setup(void) pr_info("SVE: maximum available vector length %u bytes per vector\n", sve_max_vl); pr_info("SVE: default vector length %u bytes per vector\n", - sve_default_vl); + get_sve_default_vl()); /* KVM decides whether to support mismatched systems. Just warn here: */ if (sve_max_virtualisable_vl < sve_max_vl) @@ -1029,13 +1040,13 @@ void fpsimd_flush_thread(void) * vector length configured: no kernel task can become a user * task without an exec and hence a call to this function. * By the time the first call to this function is made, all - * early hardware probing is complete, so sve_default_vl + * early hardware probing is complete, so __sve_default_vl * should be valid. * If a bug causes this to go wrong, we make some noise and * try to fudge thread.sve_vl to a safe value here. */ vl = current->thread.sve_vl_onexec ? - current->thread.sve_vl_onexec : sve_default_vl; + current->thread.sve_vl_onexec : get_sve_default_vl(); if (WARN_ON(!sve_vl_valid(vl))) vl = SVE_VL_MIN; diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 0b727edf4104..af234a1e08b7 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -730,6 +730,27 @@ static u64 get_distance_from_watchpoint(unsigned long addr, u64 val, return 0; } +static int watchpoint_report(struct perf_event *wp, unsigned long addr, + struct pt_regs *regs) +{ + int step = is_default_overflow_handler(wp); + struct arch_hw_breakpoint *info = counter_arch_bp(wp); + + info->trigger = addr; + + /* + * If we triggered a user watchpoint from a uaccess routine, then + * handle the stepping ourselves since userspace really can't help + * us with this. + */ + if (!user_mode(regs) && info->ctrl.privilege == AARCH64_BREAKPOINT_EL0) + step = 1; + else + perf_bp_event(wp, regs); + + return step; +} + static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -739,7 +760,6 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, u64 val; struct perf_event *wp, **slots; struct debug_info *debug_info; - struct arch_hw_breakpoint *info; struct arch_hw_breakpoint_ctrl ctrl; slots = this_cpu_ptr(wp_on_reg); @@ -777,25 +797,13 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr, if (dist != 0) continue; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; + step = watchpoint_report(wp, addr, regs); } - if (min_dist > 0 && min_dist != -1) { - /* No exact match found. */ - wp = slots[closest_match]; - info = counter_arch_bp(wp); - info->trigger = addr; - perf_bp_event(wp, regs); - /* Do we need to handle the stepping? */ - if (is_default_overflow_handler(wp)) - step = 1; - } + /* No exact match found? */ + if (min_dist > 0 && min_dist != -1) + step = watchpoint_report(slots[closest_match], addr, regs); + rcu_read_unlock(); if (!step) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 684d871ae38d..a107375005bc 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -135,7 +135,7 @@ int __kprobes aarch64_insn_read(void *addr, u32 *insnp) int ret; __le32 val; - ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE); + ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE); if (!ret) *insnp = le32_to_cpu(val); @@ -151,7 +151,7 @@ static int __kprobes __aarch64_insn_write(void *addr, __le32 insn) raw_spin_lock_irqsave(&patch_lock, flags); waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); + ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE); patch_unmap(FIX_TEXT_POKE0); raw_spin_unlock_irqrestore(&patch_lock, flags); diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 522e6f517ec0..361a1143e09e 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -219,8 +219,7 @@ static int prepare_elf_headers(void **addr, unsigned long *sz) MEMBLOCK_NONE, &start, &end, NULL) nr_ranges++; - cmem = kmalloc(sizeof(struct crash_mem) + - sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + cmem = kmalloc(struct_size(cmem, ranges, nr_ranges), GFP_KERNEL); if (!cmem) return -ENOMEM; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 50cc30acf106..47f651df781c 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -376,7 +376,7 @@ static int call_undef_hook(struct pt_regs *regs) if (!user_mode(regs)) { __le32 instr_le; - if (probe_kernel_address((__force __le32 *)pc, instr_le)) + if (get_kernel_nofault(instr_le, (__force __le32 *)pc)) goto exit; instr = le32_to_cpu(instr_le); } else if (compat_thumb_mode(regs)) { @@ -813,6 +813,7 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) handler[reason], smp_processor_id(), esr, esr_get_class_string(esr)); + __show_regs(regs); local_daif_mask(); panic("bad mode"); } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index e631e6425165..1e93cfc7c47a 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -404,11 +404,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma32_phys_limit); - -#ifdef CONFIG_ARM64_4K_PAGES - hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); -#endif - } void __init bootmem_init(void) @@ -424,6 +419,16 @@ void __init bootmem_init(void) min_low_pfn = min; arm64_numa_init(); + + /* + * must be done after arm64_numa_init() which calls numa_init() to + * initialize node_online_map that gets used in hugetlb_cma_reserve() + * while allocating required CMA size across online nodes. + */ +#ifdef CONFIG_ARM64_4K_PAGES + hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT); +#endif + /* * Sparsemem tries to allocate bootmem in memory_present(), so must be * done after the fixed reservations. diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 990929c8837e..1df25f26571d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -723,6 +723,7 @@ int kern_addr_valid(unsigned long addr) pmd_t *pmdp, pmd; pte_t *ptep, pte; + addr = arch_kasan_reset_tag(addr); if ((((long)addr) >> VA_BITS) != -1UL) return 0; diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c index 3c425b84e3be..b4a7ec1517ff 100644 --- a/arch/csky/kernel/ftrace.c +++ b/arch/csky/kernel/ftrace.c @@ -72,7 +72,8 @@ static int ftrace_check_current_nop(unsigned long hook) uint16_t olds[7]; unsigned long hook_pos = hook - 2; - if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops))) + if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos, + sizeof(nops))) return -EFAULT; if (memcmp((void *)nops, (void *)olds, sizeof(nops))) { @@ -97,7 +98,7 @@ static int ftrace_modify_code(unsigned long hook, unsigned long target, make_jbsr(target, hook, call, nolr); - ret = probe_kernel_write((void *)hook_pos, enable ? call : nops, + ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops, sizeof(nops)); if (ret) return -EPERM; diff --git a/arch/ia64/include/asm/sections.h b/arch/ia64/include/asm/sections.h index cea15f2dd38d..3a033d2008b3 100644 --- a/arch/ia64/include/asm/sections.h +++ b/arch/ia64/include/asm/sections.h @@ -35,7 +35,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->ip, p)) + if (!get_kernel_nofault(p, (void *)&desc->ip)) ptr = p; return ptr; } diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c index cee411e647ca..b2ab2d58fb30 100644 --- a/arch/ia64/kernel/ftrace.c +++ b/arch/ia64/kernel/ftrace.c @@ -108,7 +108,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, goto skip_check; /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -117,7 +117,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, skip_check: /* replace the text with the new text */ - if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE)) return -EPERM; flush_icache_range(ip, ip + MCOUNT_INSN_SIZE); @@ -129,7 +129,7 @@ static int ftrace_make_nop_check(struct dyn_ftrace *rec, unsigned long addr) unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE]; unsigned long ip = rec->ip; - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (rec->flags & FTRACE_FL_CONVERTED) { struct ftrace_call_insn *call_insn, *tmp_call; diff --git a/arch/ia64/kernel/unwind_i.h b/arch/ia64/kernel/unwind_i.h index 67994a7e5816..1dd57ba44327 100644 --- a/arch/ia64/kernel/unwind_i.h +++ b/arch/ia64/kernel/unwind_i.h @@ -42,7 +42,7 @@ enum unw_register_index { struct unw_info_block { u64 header; - u64 desc[0]; /* unwind descriptors */ + u64 desc[]; /* unwind descriptors */ /* personality routine and language-specific data follow behind descriptors */ }; diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index 6cfae2411c04..d043c2f897fc 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -86,9 +86,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) goto out; } - if ((probe_kernel_read(&prev_insn, p->addr - 1, - sizeof(mips_instruction)) == 0) && - insn_has_delayslot(prev_insn)) { + if (copy_from_kernel_nofault(&prev_insn, p->addr - 1, + sizeof(mips_instruction)) == 0 && + insn_has_delayslot(prev_insn)) { pr_notice("Kprobes for branch delayslot are not supported\n"); ret = -EINVAL; goto out; diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 521bd5891e84..666d3350b4ac 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -67,8 +67,10 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("vz_ghfc", vz_ghfc_exits), VCPU_STAT("vz_gpa", vz_gpa_exits), VCPU_STAT("vz_resvd", vz_resvd_exits), +#ifdef CONFIG_CPU_LOONGSON64 VCPU_STAT("vz_cpucfg", vz_cpucfg_exits), #endif +#endif VCPU_STAT("halt_successful_poll", halt_successful_poll), VCPU_STAT("halt_attempted_poll", halt_attempted_poll), VCPU_STAT("halt_poll_invalid", halt_poll_invalid), diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index 22ab77ea27ad..3763b3f8c3db 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -131,13 +131,14 @@ static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, unsigned long orig_insn[3]; if (validate) { - if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(orig_insn, (void *)pc, + MCOUNT_INSN_SIZE)) return -EFAULT; if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) return -EINVAL; } - if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE)) return -EPERM; return 0; diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index b836fc61a24f..1df0f67ed667 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -172,7 +172,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) ip = (void *)(rec->ip + 4 - size); - ret = probe_kernel_read(insn, ip, size); + ret = copy_from_kernel_nofault(insn, ip, size); if (ret) return ret; diff --git a/arch/parisc/kernel/kgdb.c b/arch/parisc/kernel/kgdb.c index 664278db9b97..c4554ac13eac 100644 --- a/arch/parisc/kernel/kgdb.c +++ b/arch/parisc/kernel/kgdb.c @@ -154,8 +154,8 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip) int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) { - int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, - BREAK_INSTR_SIZE); + int ret = copy_from_kernel_nofault(bpt->saved_instr, + (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (ret) return ret; diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 230a6422b99f..b7abb12edd3a 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -293,7 +293,7 @@ void *dereference_function_descriptor(void *ptr) Elf64_Fdesc *desc = ptr; void *p; - if (!probe_kernel_address(&desc->addr, p)) + if (!get_kernel_nofault(p, (void *)&desc->addr)) ptr = p; return ptr; } diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c index 94a9fe2702c2..4b75388190b4 100644 --- a/arch/parisc/lib/memcpy.c +++ b/arch/parisc/lib/memcpy.c @@ -57,7 +57,7 @@ void * memcpy(void * dst,const void *src, size_t count) EXPORT_SYMBOL(raw_copy_in_user); EXPORT_SYMBOL(memcpy); -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { if ((unsigned long)unsafe_src < PAGE_SIZE) return false; diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index b56f14160ae5..b0afbdd07740 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -205,10 +205,6 @@ static inline void pmd_clear(pmd_t *pmdp) *pmdp = __pmd(0); } -/* to find an entry in a page-table-directory */ -#define pgd_index(address) ((address) >> PGDIR_SHIFT) -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address)) - /* * PTE updates. This function is called whenever an existing * valid PTE is updated. This does -not- include set_pte_at() @@ -230,6 +226,8 @@ static inline void pmd_clear(pmd_t *pmdp) * For other page sizes, we have a single entry in the table. */ #ifdef CONFIG_PPC_8xx +static pmd_t *pmd_off(struct mm_struct *mm, unsigned long addr); + static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p, unsigned long clr, unsigned long set, int huge) { @@ -237,7 +235,7 @@ static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, p pte_basic_t old = pte_val(*p); pte_basic_t new = (old & ~(pte_basic_t)clr) | set; int num, i; - pmd_t *pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr); + pmd_t *pmd = pmd_off(mm, addr); if (!huge) num = PAGE_SIZE / SZ_4K; @@ -286,6 +284,16 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, return __pte(pte_update(mm, addr, ptep, ~0, 0, 0)); } +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) +#define __HAVE_ARCH_PTEP_GET +static inline pte_t ptep_get(pte_t *ptep) +{ + pte_t pte = {READ_ONCE(ptep->pte), 0, 0, 0}; + + return pte; +} +#endif + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h index d19871763ed4..324d7b298ec3 100644 --- a/arch/powerpc/include/asm/sections.h +++ b/arch/powerpc/include/asm/sections.h @@ -85,7 +85,7 @@ static inline void *dereference_function_descriptor(void *ptr) struct ppc64_opd_entry *desc = ptr; void *p; - if (!probe_kernel_address(&desc->funcaddr, p)) + if (!get_kernel_nofault(p, (void *)&desc->funcaddr)) ptr = p; return ptr; } diff --git a/arch/powerpc/include/uapi/asm/papr_pdsm.h b/arch/powerpc/include/uapi/asm/papr_pdsm.h new file mode 100644 index 000000000000..9ccecc1d6840 --- /dev/null +++ b/arch/powerpc/include/uapi/asm/papr_pdsm.h @@ -0,0 +1,132 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * PAPR nvDimm Specific Methods (PDSM) and structs for libndctl + * + * (C) Copyright IBM 2020 + * + * Author: Vaibhav Jain <vaibhav at linux.ibm.com> + */ + +#ifndef _UAPI_ASM_POWERPC_PAPR_PDSM_H_ +#define _UAPI_ASM_POWERPC_PAPR_PDSM_H_ + +#include <linux/types.h> +#include <linux/ndctl.h> + +/* + * PDSM Envelope: + * + * The ioctl ND_CMD_CALL exchange data between user-space and kernel via + * envelope which consists of 2 headers sections and payload sections as + * illustrated below: + * +-----------------+---------------+---------------------------+ + * | 64-Bytes | 8-Bytes | Max 184-Bytes | + * +-----------------+---------------+---------------------------+ + * | ND-HEADER | PDSM-HEADER | PDSM-PAYLOAD | + * +-----------------+---------------+---------------------------+ + * | nd_family | | | + * | nd_size_out | cmd_status | | + * | nd_size_in | reserved | nd_pdsm_payload | + * | nd_command | payload --> | | + * | nd_fw_size | | | + * | nd_payload ---> | | | + * +---------------+-----------------+---------------------------+ + * + * ND Header: + * This is the generic libnvdimm header described as 'struct nd_cmd_pkg' + * which is interpreted by libnvdimm before passed on to papr_scm. Important + * member fields used are: + * 'nd_family' : (In) NVDIMM_FAMILY_PAPR_SCM + * 'nd_size_in' : (In) PDSM-HEADER + PDSM-IN-PAYLOAD (usually 0) + * 'nd_size_out' : (In) PDSM-HEADER + PDSM-RETURN-PAYLOAD + * 'nd_command' : (In) One of PAPR_PDSM_XXX + * 'nd_fw_size' : (Out) PDSM-HEADER + size of actual payload returned + * + * PDSM Header: + * This is papr-scm specific header that precedes the payload. This is defined + * as nd_cmd_pdsm_pkg. Following fields aare available in this header: + * + * 'cmd_status' : (Out) Errors if any encountered while servicing PDSM. + * 'reserved' : Not used, reserved for future and should be set to 0. + * 'payload' : A union of all the possible payload structs + * + * PDSM Payload: + * + * The layout of the PDSM Payload is defined by various structs shared between + * papr_scm and libndctl so that contents of payload can be interpreted. As such + * its defined as a union of all possible payload structs as + * 'union nd_pdsm_payload'. Based on the value of 'nd_cmd_pkg.nd_command' + * appropriate member of the union is accessed. + */ + +/* Max payload size that we can handle */ +#define ND_PDSM_PAYLOAD_MAX_SIZE 184 + +/* Max payload size that we can handle */ +#define ND_PDSM_HDR_SIZE \ + (sizeof(struct nd_pkg_pdsm) - ND_PDSM_PAYLOAD_MAX_SIZE) + +/* Various nvdimm health indicators */ +#define PAPR_PDSM_DIMM_HEALTHY 0 +#define PAPR_PDSM_DIMM_UNHEALTHY 1 +#define PAPR_PDSM_DIMM_CRITICAL 2 +#define PAPR_PDSM_DIMM_FATAL 3 + +/* + * Struct exchanged between kernel & ndctl in for PAPR_PDSM_HEALTH + * Various flags indicate the health status of the dimm. + * + * extension_flags : Any extension fields present in the struct. + * dimm_unarmed : Dimm not armed. So contents wont persist. + * dimm_bad_shutdown : Previous shutdown did not persist contents. + * dimm_bad_restore : Contents from previous shutdown werent restored. + * dimm_scrubbed : Contents of the dimm have been scrubbed. + * dimm_locked : Contents of the dimm cant be modified until CEC reboot + * dimm_encrypted : Contents of dimm are encrypted. + * dimm_health : Dimm health indicator. One of PAPR_PDSM_DIMM_XXXX + */ +struct nd_papr_pdsm_health { + union { + struct { + __u32 extension_flags; + __u8 dimm_unarmed; + __u8 dimm_bad_shutdown; + __u8 dimm_bad_restore; + __u8 dimm_scrubbed; + __u8 dimm_locked; + __u8 dimm_encrypted; + __u16 dimm_health; + }; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; + }; +}; + +/* + * Methods to be embedded in ND_CMD_CALL request. These are sent to the kernel + * via 'nd_cmd_pkg.nd_command' member of the ioctl struct + */ +enum papr_pdsm { + PAPR_PDSM_MIN = 0x0, + PAPR_PDSM_HEALTH, + PAPR_PDSM_MAX, +}; + +/* Maximal union that can hold all possible payload types */ +union nd_pdsm_payload { + struct nd_papr_pdsm_health health; + __u8 buf[ND_PDSM_PAYLOAD_MAX_SIZE]; +} __packed; + +/* + * PDSM-header + payload expected with ND_CMD_CALL ioctl from libnvdimm + * Valid member of union 'payload' is identified via 'nd_cmd_pkg.nd_command' + * that should always precede this struct when sent to papr_scm via CMD_CALL + * interface. + */ +struct nd_pkg_pdsm { + __s32 cmd_status; /* Out: Sub-cmd status returned back */ + __u16 reserved[2]; /* Ignored and to be set as '0' */ + union nd_pdsm_payload payload; +} __packed; + +#endif /* _UAPI_ASM_POWERPC_PAPR_PDSM_H_ */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e70ebb5c318c..fa080694e581 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -270,7 +270,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_CFAR) .endif - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 BEGIN_FTR_SECTION ld r10,IAREA+EX_PPR(r13) @@ -298,7 +298,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) .if IKVM_SKIP 89: mtocrf 0x80,r9 - ld r10,PACA_EXGEN+EX_CTR(r13) + ld r10,IAREA+EX_CTR(r13) mtctr r10 ld r9,IAREA+EX_R9(r13) ld r10,IAREA+EX_R10(r13) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 652b2852bea3..409080208a6c 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -421,7 +421,7 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) unsigned int instr; struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr; - err = probe_kernel_address(addr, instr); + err = get_kernel_nofault(instr, (unsigned *) addr); if (err) return err; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 6f96f65ebfe8..9cc792a3a6a9 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -289,7 +289,7 @@ int kprobe_handler(struct pt_regs *regs) if (!p) { unsigned int instr; - if (probe_kernel_address(addr, instr)) + if (get_kernel_nofault(instr, addr)) goto no_kprobe; if (instr != BREAKPOINT_INSTRUCTION) { diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index f4c2fa190192..ae2b188365b1 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -756,7 +756,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, stub = (struct ppc64_stub_entry *)addr; - if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) { + if (copy_from_kernel_nofault(&magic, &stub->magic, + sizeof(magic))) { pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } @@ -766,7 +767,8 @@ int module_trampoline_target(struct module *mod, unsigned long addr, return -EFAULT; } - if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) { + if (copy_from_kernel_nofault(&funcdata, &stub->funcdata, + sizeof(funcdata))) { pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name); return -EFAULT; } diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7bb7faf84490..4650b9bb217f 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1252,29 +1252,31 @@ struct task_struct *__switch_to(struct task_struct *prev, static void show_instructions(struct pt_regs *regs) { int i; + unsigned long nip = regs->nip; unsigned long pc = regs->nip - (NR_INSN_TO_PRINT * 3 / 4 * sizeof(int)); printk("Instruction dump:"); + /* + * If we were executing with the MMU off for instructions, adjust pc + * rather than printing XXXXXXXX. + */ + if (!IS_ENABLED(CONFIG_BOOKE) && !(regs->msr & MSR_IR)) { + pc = (unsigned long)phys_to_virt(pc); + nip = (unsigned long)phys_to_virt(regs->nip); + } + for (i = 0; i < NR_INSN_TO_PRINT; i++) { int instr; if (!(i % 8)) pr_cont("\n"); -#if !defined(CONFIG_BOOKE) - /* If executing with the IMMU off, adjust pc rather - * than print XXXXXXXX. - */ - if (!(regs->msr & MSR_IR)) - pc = (unsigned long)phys_to_virt(pc); -#endif - if (!__kernel_text_address(pc) || - probe_kernel_address((const void *)pc, instr)) { + get_kernel_nofault(instr, (const void *)pc)) { pr_cont("XXXXXXXX "); } else { - if (regs->nip == pc) + if (nip == pc) pr_cont("<%08x> ", instr); else pr_cont("%08x ", instr); @@ -1305,7 +1307,8 @@ void show_user_instructions(struct pt_regs *regs) for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) { int instr; - if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) { + if (copy_from_user_nofault(&instr, (void __user *)pc, + sizeof(instr))) { seq_buf_printf(&s, "XXXXXXXX "); continue; } diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5e399628f51a..c1fede6ec934 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -226,7 +226,7 @@ __ftrace_make_nop(struct module *mod, unsigned long ip = rec->ip; unsigned long tramp; - if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure that that this is still a 24bit jump */ @@ -249,7 +249,7 @@ __ftrace_make_nop(struct module *mod, pr_devel("ip:%lx jumps to %lx", ip, tramp); /* Find where the trampoline jumps to */ - if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) { + if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) { pr_err("Failed to read %lx\n", tramp); return -EFAULT; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 3cb0c9843d01..e738ea652192 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -64,9 +64,9 @@ unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid, isync(); if (is_load) - ret = probe_user_read(to, (const void __user *)from, n); + ret = copy_from_user_nofault(to, (const void __user *)from, n); else - ret = probe_user_write((void __user *)to, from, n); + ret = copy_to_user_nofault((void __user *)to, from, n); /* switch the pid first to avoid running host with unallocated pid */ if (quadrant == 1 && pid != old_pid) diff --git a/arch/powerpc/lib/inst.c b/arch/powerpc/lib/inst.c index aedfd6e31e53..9cc17eb62462 100644 --- a/arch/powerpc/lib/inst.c +++ b/arch/powerpc/lib/inst.c @@ -15,11 +15,11 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_user_read(&suffix, (void __user *)nip + 4, 4); + err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -33,11 +33,11 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val, suffix; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (err) return err; if (get_op(val) == OP_PREFIX) { - err = probe_kernel_read(&suffix, (void *)src + 4, 4); + err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4); *inst = ppc_inst_prefix(val, suffix); } else { *inst = ppc_inst(val); @@ -51,7 +51,7 @@ int probe_user_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_user_read(&val, nip, sizeof(val)); + err = copy_from_user_nofault(&val, nip, sizeof(val)); if (!err) *inst = ppc_inst(val); @@ -64,7 +64,7 @@ int probe_kernel_read_inst(struct ppc_inst *inst, unsigned int val; int err; - err = probe_kernel_read(&val, src, sizeof(val)); + err = copy_from_kernel_nofault(&val, src, sizeof(val)); if (!err) *inst = ppc_inst(val); diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c index 6f347fa29f41..9db7ada79d10 100644 --- a/arch/powerpc/oprofile/backtrace.c +++ b/arch/powerpc/oprofile/backtrace.c @@ -33,7 +33,8 @@ static unsigned int user_getsp32(unsigned int sp, int is_first) * which means that we've done all that we can do from * interrupt context. */ - if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)p, + sizeof(stack_frame))) return 0; if (!is_first) @@ -51,7 +52,8 @@ static unsigned long user_getsp64(unsigned long sp, int is_first) { unsigned long stack_frame[3]; - if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame))) + if (copy_from_user_nofault(stack_frame, (void __user *)sp, + sizeof(stack_frame))) return 0; if (!is_first) diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c index f7d888d39cd3..542e68b8eae0 100644 --- a/arch/powerpc/perf/callchain_32.c +++ b/arch/powerpc/perf/callchain_32.c @@ -44,7 +44,7 @@ static int read_user_stack_32(unsigned int __user *ptr, unsigned int *ret) ((unsigned long)ptr & 3)) return -EFAULT; - rc = probe_user_read(ret, ptr, sizeof(*ret)); + rc = copy_from_user_nofault(ret, ptr, sizeof(*ret)); if (IS_ENABLED(CONFIG_PPC64) && rc) return read_user_stack_slow(ptr, ret, 4); diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c index 814d1c2c2b9c..fa2a1b83b9b0 100644 --- a/arch/powerpc/perf/callchain_64.c +++ b/arch/powerpc/perf/callchain_64.c @@ -50,7 +50,7 @@ static int read_user_stack_64(unsigned long __user *ptr, unsigned long *ret) ((unsigned long)ptr & 7)) return -EFAULT; - if (!probe_user_read(ret, ptr, sizeof(*ret))) + if (!copy_from_user_nofault(ret, ptr, sizeof(*ret))) return 0; return read_user_stack_slow(ptr, ret, 8); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 13b9dd5e4a76..cd6a742ac6ef 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -418,14 +418,16 @@ static __u64 power_pmu_bhrb_to(u64 addr) __u64 target; if (is_kernel_addr(addr)) { - if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + if (copy_from_kernel_nofault(&instr, (void *)addr, + sizeof(instr))) return 0; return branch_target((struct ppc_inst *)&instr); } /* Userspace: need copy instruction here then translate it */ - if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr))) + if (copy_from_user_nofault(&instr, (unsigned int __user *)addr, + sizeof(instr))) return 0; target = branch_target((struct ppc_inst *)&instr); diff --git a/arch/powerpc/platforms/cell/spu_callbacks.c b/arch/powerpc/platforms/cell/spu_callbacks.c index cbee3666da07..abdef9bcf432 100644 --- a/arch/powerpc/platforms/cell/spu_callbacks.c +++ b/arch/powerpc/platforms/cell/spu_callbacks.c @@ -35,7 +35,7 @@ */ static void *spu_syscall_table[] = { -#define __SYSCALL(nr, entry) entry, +#define __SYSCALL(nr, entry) [nr] = entry, #include <asm/syscall_table_spu.h> #undef __SYSCALL }; diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index f35592423380..9c569078a09f 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -12,16 +12,57 @@ #include <linux/libnvdimm.h> #include <linux/platform_device.h> #include <linux/delay.h> +#include <linux/seq_buf.h> #include <asm/plpar_wrappers.h> +#include <asm/papr_pdsm.h> #define BIND_ANY_ADDR (~0ul) #define PAPR_SCM_DIMM_CMD_MASK \ ((1ul << ND_CMD_GET_CONFIG_SIZE) | \ (1ul << ND_CMD_GET_CONFIG_DATA) | \ - (1ul << ND_CMD_SET_CONFIG_DATA)) - + (1ul << ND_CMD_SET_CONFIG_DATA) | \ + (1ul << ND_CMD_CALL)) + +/* DIMM health bitmap bitmap indicators */ +/* SCM device is unable to persist memory contents */ +#define PAPR_PMEM_UNARMED (1ULL << (63 - 0)) +/* SCM device failed to persist memory contents */ +#define PAPR_PMEM_SHUTDOWN_DIRTY (1ULL << (63 - 1)) +/* SCM device contents are persisted from previous IPL */ +#define PAPR_PMEM_SHUTDOWN_CLEAN (1ULL << (63 - 2)) +/* SCM device contents are not persisted from previous IPL */ +#define PAPR_PMEM_EMPTY (1ULL << (63 - 3)) +/* SCM device memory life remaining is critically low */ +#define PAPR_PMEM_HEALTH_CRITICAL (1ULL << (63 - 4)) +/* SCM device will be garded off next IPL due to failure */ +#define PAPR_PMEM_HEALTH_FATAL (1ULL << (63 - 5)) +/* SCM contents cannot persist due to current platform health status */ +#define PAPR_PMEM_HEALTH_UNHEALTHY (1ULL << (63 - 6)) +/* SCM device is unable to persist memory contents in certain conditions */ +#define PAPR_PMEM_HEALTH_NON_CRITICAL (1ULL << (63 - 7)) +/* SCM device is encrypted */ +#define PAPR_PMEM_ENCRYPTED (1ULL << (63 - 8)) +/* SCM device has been scrubbed and locked */ +#define PAPR_PMEM_SCRUBBED_AND_LOCKED (1ULL << (63 - 9)) + +/* Bits status indicators for health bitmap indicating unarmed dimm */ +#define PAPR_PMEM_UNARMED_MASK (PAPR_PMEM_UNARMED | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* Bits status indicators for health bitmap indicating unflushed dimm */ +#define PAPR_PMEM_BAD_SHUTDOWN_MASK (PAPR_PMEM_SHUTDOWN_DIRTY) + +/* Bits status indicators for health bitmap indicating unrestored dimm */ +#define PAPR_PMEM_BAD_RESTORE_MASK (PAPR_PMEM_EMPTY) + +/* Bit status indicators for smart event notification */ +#define PAPR_PMEM_SMART_EVENT_MASK (PAPR_PMEM_HEALTH_CRITICAL | \ + PAPR_PMEM_HEALTH_FATAL | \ + PAPR_PMEM_HEALTH_UNHEALTHY) + +/* private struct associated with each region */ struct papr_scm_priv { struct platform_device *pdev; struct device_node *dn; @@ -39,6 +80,15 @@ struct papr_scm_priv { struct resource res; struct nd_region *region; struct nd_interleave_set nd_set; + + /* Protect dimm health data from concurrent read/writes */ + struct mutex health_mutex; + + /* Last time the health information of the dimm was updated */ + unsigned long lasthealth_jiffies; + + /* Health information for the dimm */ + u64 health_bitmap; }; static int drc_pmem_bind(struct papr_scm_priv *p) @@ -144,6 +194,61 @@ err_out: return drc_pmem_bind(p); } +/* + * Issue hcall to retrieve dimm health info and populate papr_scm_priv with the + * health information. + */ +static int __drc_pmem_query_health(struct papr_scm_priv *p) +{ + unsigned long ret[PLPAR_HCALL_BUFSIZE]; + long rc; + + /* issue the hcall */ + rc = plpar_hcall(H_SCM_HEALTH, ret, p->drc_index); + if (rc != H_SUCCESS) { + dev_err(&p->pdev->dev, + "Failed to query health information, Err:%ld\n", rc); + return -ENXIO; + } + + p->lasthealth_jiffies = jiffies; + p->health_bitmap = ret[0] & ret[1]; + + dev_dbg(&p->pdev->dev, + "Queried dimm health info. Bitmap:0x%016lx Mask:0x%016lx\n", + ret[0], ret[1]); + + return 0; +} + +/* Min interval in seconds for assuming stable dimm health */ +#define MIN_HEALTH_QUERY_INTERVAL 60 + +/* Query cached health info and if needed call drc_pmem_query_health */ +static int drc_pmem_query_health(struct papr_scm_priv *p) +{ + unsigned long cache_timeout; + int rc; + + /* Protect concurrent modifications to papr_scm_priv */ + rc = mutex_lock_interruptible(&p->health_mutex); + if (rc) + return rc; + + /* Jiffies offset for which the health data is assumed to be same */ + cache_timeout = p->lasthealth_jiffies + + msecs_to_jiffies(MIN_HEALTH_QUERY_INTERVAL * 1000); + + /* Fetch new health info is its older than MIN_HEALTH_QUERY_INTERVAL */ + if (time_after(jiffies, cache_timeout)) + rc = __drc_pmem_query_health(p); + else + /* Assume cached health data is valid */ + rc = 0; + + mutex_unlock(&p->health_mutex); + return rc; +} static int papr_scm_meta_get(struct papr_scm_priv *p, struct nd_cmd_get_config_data_hdr *hdr) @@ -246,16 +351,250 @@ static int papr_scm_meta_set(struct papr_scm_priv *p, return 0; } +/* + * Do a sanity checks on the inputs args to dimm-control function and return + * '0' if valid. Validation of PDSM payloads happens later in + * papr_scm_service_pdsm. + */ +static int is_cmd_valid(struct nvdimm *nvdimm, unsigned int cmd, void *buf, + unsigned int buf_len) +{ + unsigned long cmd_mask = PAPR_SCM_DIMM_CMD_MASK; + struct nd_cmd_pkg *nd_cmd; + struct papr_scm_priv *p; + enum papr_pdsm pdsm; + + /* Only dimm-specific calls are supported atm */ + if (!nvdimm) + return -EINVAL; + + /* get the provider data from struct nvdimm */ + p = nvdimm_provider_data(nvdimm); + + if (!test_bit(cmd, &cmd_mask)) { + dev_dbg(&p->pdev->dev, "Unsupported cmd=%u\n", cmd); + return -EINVAL; + } + + /* For CMD_CALL verify pdsm request */ + if (cmd == ND_CMD_CALL) { + /* Verify the envelope and envelop size */ + if (!buf || + buf_len < (sizeof(struct nd_cmd_pkg) + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "Invalid pkg size=%u\n", + buf_len); + return -EINVAL; + } + + /* Verify that the nd_cmd_pkg.nd_family is correct */ + nd_cmd = (struct nd_cmd_pkg *)buf; + + if (nd_cmd->nd_family != NVDIMM_FAMILY_PAPR) { + dev_dbg(&p->pdev->dev, "Invalid pkg family=0x%llx\n", + nd_cmd->nd_family); + return -EINVAL; + } + + pdsm = (enum papr_pdsm)nd_cmd->nd_command; + + /* Verify if the pdsm command is valid */ + if (pdsm <= PAPR_PDSM_MIN || pdsm >= PAPR_PDSM_MAX) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid PDSM\n", + pdsm); + return -EINVAL; + } + + /* Have enough space to hold returned 'nd_pkg_pdsm' header */ + if (nd_cmd->nd_size_out < ND_PDSM_HDR_SIZE) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid payload\n", + pdsm); + return -EINVAL; + } + } + + /* Let the command be further processed */ + return 0; +} + +/* Fetch the DIMM health info and populate it in provided package. */ +static int papr_pdsm_health(struct papr_scm_priv *p, + union nd_pdsm_payload *payload) +{ + int rc; + + /* Ensure dimm health mutex is taken preventing concurrent access */ + rc = mutex_lock_interruptible(&p->health_mutex); + if (rc) + goto out; + + /* Always fetch upto date dimm health data ignoring cached values */ + rc = __drc_pmem_query_health(p); + if (rc) { + mutex_unlock(&p->health_mutex); + goto out; + } + + /* update health struct with various flags derived from health bitmap */ + payload->health = (struct nd_papr_pdsm_health) { + .extension_flags = 0, + .dimm_unarmed = !!(p->health_bitmap & PAPR_PMEM_UNARMED_MASK), + .dimm_bad_shutdown = !!(p->health_bitmap & PAPR_PMEM_BAD_SHUTDOWN_MASK), + .dimm_bad_restore = !!(p->health_bitmap & PAPR_PMEM_BAD_RESTORE_MASK), + .dimm_scrubbed = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED), + .dimm_locked = !!(p->health_bitmap & PAPR_PMEM_SCRUBBED_AND_LOCKED), + .dimm_encrypted = !!(p->health_bitmap & PAPR_PMEM_ENCRYPTED), + .dimm_health = PAPR_PDSM_DIMM_HEALTHY, + }; + + /* Update field dimm_health based on health_bitmap flags */ + if (p->health_bitmap & PAPR_PMEM_HEALTH_FATAL) + payload->health.dimm_health = PAPR_PDSM_DIMM_FATAL; + else if (p->health_bitmap & PAPR_PMEM_HEALTH_CRITICAL) + payload->health.dimm_health = PAPR_PDSM_DIMM_CRITICAL; + else if (p->health_bitmap & PAPR_PMEM_HEALTH_UNHEALTHY) + payload->health.dimm_health = PAPR_PDSM_DIMM_UNHEALTHY; + + /* struct populated hence can release the mutex now */ + mutex_unlock(&p->health_mutex); + rc = sizeof(struct nd_papr_pdsm_health); + +out: + return rc; +} + +/* + * 'struct pdsm_cmd_desc' + * Identifies supported PDSMs' expected length of in/out payloads + * and pdsm service function. + * + * size_in : Size of input payload if any in the PDSM request. + * size_out : Size of output payload if any in the PDSM request. + * service : Service function for the PDSM request. Return semantics: + * rc < 0 : Error servicing PDSM and rc indicates the error. + * rc >=0 : Serviced successfully and 'rc' indicate number of + * bytes written to payload. + */ +struct pdsm_cmd_desc { + u32 size_in; + u32 size_out; + int (*service)(struct papr_scm_priv *dimm, + union nd_pdsm_payload *payload); +}; + +/* Holds all supported PDSMs' command descriptors */ +static const struct pdsm_cmd_desc __pdsm_cmd_descriptors[] = { + [PAPR_PDSM_MIN] = { + .size_in = 0, + .size_out = 0, + .service = NULL, + }, + /* New PDSM command descriptors to be added below */ + + [PAPR_PDSM_HEALTH] = { + .size_in = 0, + .size_out = sizeof(struct nd_papr_pdsm_health), + .service = papr_pdsm_health, + }, + /* Empty */ + [PAPR_PDSM_MAX] = { + .size_in = 0, + .size_out = 0, + .service = NULL, + }, +}; + +/* Given a valid pdsm cmd return its command descriptor else return NULL */ +static inline const struct pdsm_cmd_desc *pdsm_cmd_desc(enum papr_pdsm cmd) +{ + if (cmd >= 0 || cmd < ARRAY_SIZE(__pdsm_cmd_descriptors)) + return &__pdsm_cmd_descriptors[cmd]; + + return NULL; +} + +/* + * For a given pdsm request call an appropriate service function. + * Returns errors if any while handling the pdsm command package. + */ +static int papr_scm_service_pdsm(struct papr_scm_priv *p, + struct nd_cmd_pkg *pkg) +{ + /* Get the PDSM header and PDSM command */ + struct nd_pkg_pdsm *pdsm_pkg = (struct nd_pkg_pdsm *)pkg->nd_payload; + enum papr_pdsm pdsm = (enum papr_pdsm)pkg->nd_command; + const struct pdsm_cmd_desc *pdsc; + int rc; + + /* Fetch corresponding pdsm descriptor for validation and servicing */ + pdsc = pdsm_cmd_desc(pdsm); + + /* Validate pdsm descriptor */ + /* Ensure that reserved fields are 0 */ + if (pdsm_pkg->reserved[0] || pdsm_pkg->reserved[1]) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Invalid reserved field\n", + pdsm); + return -EINVAL; + } + + /* If pdsm expects some input, then ensure that the size_in matches */ + if (pdsc->size_in && + pkg->nd_size_in != (pdsc->size_in + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_in=%d\n", + pdsm, pkg->nd_size_in); + return -EINVAL; + } + + /* If pdsm wants to return data, then ensure that size_out matches */ + if (pdsc->size_out && + pkg->nd_size_out != (pdsc->size_out + ND_PDSM_HDR_SIZE)) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Mismatched size_out=%d\n", + pdsm, pkg->nd_size_out); + return -EINVAL; + } + + /* Service the pdsm */ + if (pdsc->service) { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Servicing..\n", pdsm); + + rc = pdsc->service(p, &pdsm_pkg->payload); + + if (rc < 0) { + /* error encountered while servicing pdsm */ + pdsm_pkg->cmd_status = rc; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE; + } else { + /* pdsm serviced and 'rc' bytes written to payload */ + pdsm_pkg->cmd_status = 0; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE + rc; + } + } else { + dev_dbg(&p->pdev->dev, "PDSM[0x%x]: Unsupported PDSM request\n", + pdsm); + pdsm_pkg->cmd_status = -ENOENT; + pkg->nd_fw_size = ND_PDSM_HDR_SIZE; + } + + return pdsm_pkg->cmd_status; +} + static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc) { struct nd_cmd_get_config_size *get_size_hdr; + struct nd_cmd_pkg *call_pkg = NULL; struct papr_scm_priv *p; + int rc; - /* Only dimm-specific calls are supported atm */ - if (!nvdimm) - return -EINVAL; + rc = is_cmd_valid(nvdimm, cmd, buf, buf_len); + if (rc) { + pr_debug("Invalid cmd=0x%x. Err=%d\n", cmd, rc); + return rc; + } + + /* Use a local variable in case cmd_rc pointer is NULL */ + if (!cmd_rc) + cmd_rc = &rc; p = nvdimm_provider_data(nvdimm); @@ -277,7 +616,13 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, *cmd_rc = papr_scm_meta_set(p, buf); break; + case ND_CMD_CALL: + call_pkg = (struct nd_cmd_pkg *)buf; + *cmd_rc = papr_scm_service_pdsm(p, call_pkg); + break; + default: + dev_dbg(&p->pdev->dev, "Unknown command = %d\n", cmd); return -EINVAL; } @@ -286,6 +631,64 @@ static int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, return 0; } +static ssize_t flags_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvdimm *dimm = to_nvdimm(dev); + struct papr_scm_priv *p = nvdimm_provider_data(dimm); + struct seq_buf s; + u64 health; + int rc; + + rc = drc_pmem_query_health(p); + if (rc) + return rc; + + /* Copy health_bitmap locally, check masks & update out buffer */ + health = READ_ONCE(p->health_bitmap); + + seq_buf_init(&s, buf, PAGE_SIZE); + if (health & PAPR_PMEM_UNARMED_MASK) + seq_buf_printf(&s, "not_armed "); + + if (health & PAPR_PMEM_BAD_SHUTDOWN_MASK) + seq_buf_printf(&s, "flush_fail "); + + if (health & PAPR_PMEM_BAD_RESTORE_MASK) + seq_buf_printf(&s, "restore_fail "); + + if (health & PAPR_PMEM_ENCRYPTED) + seq_buf_printf(&s, "encrypted "); + + if (health & PAPR_PMEM_SMART_EVENT_MASK) + seq_buf_printf(&s, "smart_notify "); + + if (health & PAPR_PMEM_SCRUBBED_AND_LOCKED) + seq_buf_printf(&s, "scrubbed locked "); + + if (seq_buf_used(&s)) + seq_buf_printf(&s, "\n"); + + return seq_buf_used(&s); +} +DEVICE_ATTR_RO(flags); + +/* papr_scm specific dimm attributes */ +static struct attribute *papr_nd_attributes[] = { + &dev_attr_flags.attr, + NULL, +}; + +static struct attribute_group papr_nd_attribute_group = { + .name = "papr", + .attrs = papr_nd_attributes, +}; + +static const struct attribute_group *papr_nd_attr_groups[] = { + &papr_nd_attribute_group, + NULL, +}; + static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; @@ -312,8 +715,8 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) dimm_flags = 0; set_bit(NDD_LABELING, &dimm_flags); - p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags, - PAPR_SCM_DIMM_CMD_MASK, 0, NULL); + p->nvdimm = nvdimm_create(p->bus, p, papr_nd_attr_groups, + dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); if (!p->nvdimm) { dev_err(dev, "Error creating DIMM object for %pOF\n", p->dn); goto err; @@ -399,6 +802,9 @@ static int papr_scm_probe(struct platform_device *pdev) if (!p) return -ENOMEM; + /* Initialize the dimm mutex */ + mutex_init(&p->health_mutex); + /* optional DT properties */ of_property_read_u32(dn, "ibm,metadata-size", &metadata_size); diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 4a8874bc1057..040b9d01c079 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -1066,10 +1066,10 @@ int fsl_pci_mcheck_exception(struct pt_regs *regs) if (is_in_pci_mem_space(addr)) { if (user_mode(regs)) - ret = probe_user_read(&inst, (void __user *)regs->nip, - sizeof(inst)); + ret = copy_from_user_nofault(&inst, + (void __user *)regs->nip, sizeof(inst)); else - ret = probe_kernel_address((void *)regs->nip, inst); + ret = get_kernel_nofault(inst, (void *)regs->nip); if (!ret && mcheck_handle_load(regs, inst)) { regs->nip += 4; diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h index d969bab4a26b..262e5bbb2776 100644 --- a/arch/riscv/include/asm/cmpxchg.h +++ b/arch/riscv/include/asm/cmpxchg.h @@ -179,7 +179,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -224,7 +224,7 @@ RISCV_ACQUIRE_BARRIER \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -270,7 +270,7 @@ " bnez %1, 0b\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ @@ -316,7 +316,7 @@ " fence rw, rw\n" \ "1:\n" \ : "=&r" (__ret), "=&r" (__rc), "+A" (*__ptr) \ - : "rJ" (__old), "rJ" (__new) \ + : "rJ" ((long)__old), "rJ" (__new) \ : "memory"); \ break; \ case 8: \ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 08396614d6f4..2ff63d0cbb50 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -38,7 +38,8 @@ static int ftrace_check_current_call(unsigned long hook_pos, * Read the text we want to modify; * return must be -EFAULT on read error */ - if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)hook_pos, + MCOUNT_INSN_SIZE)) return -EFAULT; /* diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c index f16ade84a11f..c3275f42d1ac 100644 --- a/arch/riscv/kernel/kgdb.c +++ b/arch/riscv/kernel/kgdb.c @@ -62,7 +62,7 @@ int get_step_address(struct pt_regs *regs, unsigned long *next_addr) unsigned int rs1_num, rs2_num; int op_code; - if (probe_kernel_address((void *)pc, op_code)) + if (get_kernel_nofault(op_code, (void *)pc)) return -EINVAL; if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) { if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) { @@ -146,14 +146,14 @@ int do_single_step(struct pt_regs *regs) return error; /* Store the op code in the stepped address */ - error = probe_kernel_address((void *)addr, stepped_opcode); + error = get_kernel_nofault(stepped_opcode, (void *)addr); if (error) return error; stepped_address = addr; /* Replace the op code with the break instruction */ - error = probe_kernel_write((void *)stepped_address, + error = copy_to_kernel_nofault((void *)stepped_address, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); /* Flush and return */ @@ -173,7 +173,7 @@ int do_single_step(struct pt_regs *regs) static void undo_single_step(struct pt_regs *regs) { if (stepped_opcode != 0) { - probe_kernel_write((void *)stepped_address, + copy_to_kernel_nofault((void *)stepped_address, (void *)&stepped_opcode, BREAK_INSTR_SIZE); flush_icache_range(stepped_address, stepped_address + BREAK_INSTR_SIZE); diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c index d4a64dfed342..3fe7a5296aa5 100644 --- a/arch/riscv/kernel/patch.c +++ b/arch/riscv/kernel/patch.c @@ -63,7 +63,7 @@ static int patch_insn_write(void *addr, const void *insn, size_t len) waddr = patch_map(addr, FIX_TEXT_POKE0); - ret = probe_kernel_write(waddr, insn, len); + ret = copy_to_kernel_nofault(waddr, insn, len); patch_unmap(FIX_TEXT_POKE0); @@ -76,7 +76,7 @@ NOKPROBE_SYMBOL(patch_insn_write); #else static int patch_insn_write(void *addr, const void *insn, size_t len) { - return probe_kernel_write(addr, insn, len); + return copy_to_kernel_nofault(addr, insn, len); } NOKPROBE_SYMBOL(patch_insn_write); #endif /* CONFIG_MMU */ diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index f3619f59d85c..12f8a7fce78b 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -8,6 +8,7 @@ #include <linux/syscalls.h> #include <asm/unistd.h> #include <asm/cacheflush.h> +#include <asm-generic/mman-common.h> static long riscv_sys_mmap(unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, @@ -16,6 +17,11 @@ static long riscv_sys_mmap(unsigned long addr, unsigned long len, { if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL; + + if ((prot & PROT_WRITE) && (prot & PROT_EXEC)) + if (unlikely(!(prot & PROT_READ))) + return -EINVAL; + return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index ecec1778e3a4..7d95cce5e47c 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -137,7 +137,7 @@ static inline unsigned long get_break_insn_length(unsigned long pc) { bug_insn_t insn; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; return GET_INSN_LENGTH(insn); @@ -165,7 +165,7 @@ int is_valid_bugaddr(unsigned long pc) if (pc < VMALLOC_START) return 0; - if (probe_kernel_address((bug_insn_t *)pc, insn)) + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) return 0; if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) return (insn == __BUG_INSN_32); diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c index ec2c70f84994..289a9a5ea5b5 100644 --- a/arch/riscv/mm/pageattr.c +++ b/arch/riscv/mm/pageattr.c @@ -151,6 +151,7 @@ int set_memory_nx(unsigned long addr, int numpages) int set_direct_map_invalid_noflush(struct page *page) { + int ret; unsigned long start = (unsigned long)page_address(page); unsigned long end = start + PAGE_SIZE; struct pageattr_masks masks = { @@ -158,11 +159,16 @@ int set_direct_map_invalid_noflush(struct page *page) .clear_mask = __pgprot(_PAGE_PRESENT) }; - return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_lock(&init_mm); + ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_unlock(&init_mm); + + return ret; } int set_direct_map_default_noflush(struct page *page) { + int ret; unsigned long start = (unsigned long)page_address(page); unsigned long end = start + PAGE_SIZE; struct pageattr_masks masks = { @@ -170,7 +176,11 @@ int set_direct_map_default_noflush(struct page *page) .clear_mask = __pgprot(0) }; - return walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_lock(&init_mm); + ret = walk_page_range(&init_mm, start, end, &pageattr_ops, &masks); + mmap_read_unlock(&init_mm); + + return ret; } void __kernel_map_pages(struct page *page, int numpages, int enable) diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 194824932a60..c7d7ede6300c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -462,6 +462,7 @@ config NUMA config NODES_SHIFT int + depends on NEED_MULTIPLE_NODES default "1" config SCHED_SMT diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index d977643fa627..e1ae23911ccd 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -693,7 +693,7 @@ static ssize_t prng_chunksize_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); + return scnprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); } static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL); @@ -712,7 +712,7 @@ static ssize_t prng_counter_show(struct device *dev, counter = prng_data->prngws.byte_counter; mutex_unlock(&prng_data->mutex); - return snprintf(buf, PAGE_SIZE, "%llu\n", counter); + return scnprintf(buf, PAGE_SIZE, "%llu\n", counter); } static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL); @@ -721,7 +721,7 @@ static ssize_t prng_errorflag_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); + return scnprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); } static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL); @@ -731,9 +731,9 @@ static ssize_t prng_mode_show(struct device *dev, char *buf) { if (prng_mode == PRNG_MODE_TDES) - return snprintf(buf, PAGE_SIZE, "TDES\n"); + return scnprintf(buf, PAGE_SIZE, "TDES\n"); else - return snprintf(buf, PAGE_SIZE, "SHA512\n"); + return scnprintf(buf, PAGE_SIZE, "SHA512\n"); } static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL); @@ -756,7 +756,7 @@ static ssize_t prng_reseed_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); + return scnprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); } static ssize_t prng_reseed_limit_store(struct device *dev, struct device_attribute *attr, @@ -787,7 +787,7 @@ static ssize_t prng_strength_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "256\n"); + return scnprintf(buf, PAGE_SIZE, "256\n"); } static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL); diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h index f073292e9fdb..d9d5de0f67ff 100644 --- a/arch/s390/include/asm/syscall.h +++ b/arch/s390/include/asm/syscall.h @@ -33,7 +33,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - return IS_ERR_VALUE(regs->gprs[2]) ? regs->gprs[2] : 0; + unsigned long error = regs->gprs[2]; +#ifdef CONFIG_COMPAT + if (test_tsk_thread_flag(task, TIF_31BIT)) { + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + error = (long)(int)error; + } +#endif + return IS_ERR_VALUE(error) ? error : 0; } static inline long syscall_get_return_value(struct task_struct *task, diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h index 3bcfdeb01395..0cd085cdeb4f 100644 --- a/arch/s390/include/asm/vdso.h +++ b/arch/s390/include/asm/vdso.h @@ -36,6 +36,7 @@ struct vdso_data { __u32 tk_shift; /* Shift used for xtime_nsec 0x60 */ __u32 ts_dir; /* TOD steering direction 0x64 */ __u64 ts_end; /* TOD steering end 0x68 */ + __u32 hrtimer_res; /* hrtimer resolution 0x70 */ }; struct vdso_per_cpu_data { diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 165031bd3370..5d8cc1864566 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -76,6 +76,7 @@ int main(void) OFFSET(__VDSO_TK_SHIFT, vdso_data, tk_shift); OFFSET(__VDSO_TS_DIR, vdso_data, ts_dir); OFFSET(__VDSO_TS_END, vdso_data, ts_end); + OFFSET(__VDSO_CLOCK_REALTIME_RES, vdso_data, hrtimer_res); OFFSET(__VDSO_ECTG_BASE, vdso_per_cpu_data, ectg_timer_base); OFFSET(__VDSO_ECTG_USER, vdso_per_cpu_data, ectg_user_time); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); @@ -86,7 +87,6 @@ int main(void) DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); BLANK(); /* idle data offsets */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 50ff6dd0f995..496f74d98473 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -401,9 +401,9 @@ ENTRY(system_call) jnz .Lsysc_nr_ok # svc 0: system call number in %r1 llgfr %r1,%r1 # clear high word in r1 + sth %r1,__PT_INT_CODE+2(%r11) cghi %r1,NR_syscalls jnl .Lsysc_nr_ok - sth %r1,__PT_INT_CODE+2(%r11) slag %r8,%r1,3 .Lsysc_nr_ok: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 44e01dd1e624..b388e87a08bf 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -83,7 +83,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; if (addr == MCOUNT_ADDR) { /* Initial code replacement */ @@ -105,7 +105,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { struct ftrace_insn orig, new, old; - if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old))) + if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old))) return -EFAULT; /* Replace nop with an ftrace call. */ ftrace_generate_nop_insn(&orig); diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index ccea9a245867..90a2a17239b0 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -181,7 +181,7 @@ static ssize_t sys_##_prefix##_##_name##_show(struct kobject *kobj, \ struct kobj_attribute *attr, \ char *page) \ { \ - return snprintf(page, PAGE_SIZE, _format, ##args); \ + return scnprintf(page, PAGE_SIZE, _format, ##args); \ } #define IPL_ATTR_CCW_STORE_FN(_prefix, _name, _ipl_blk) \ diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index ce60a459a143..3cc15c066298 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -323,6 +323,25 @@ static inline void __poke_user_per(struct task_struct *child, child->thread.per_user.end = data; } +static void fixup_int_code(struct task_struct *child, addr_t data) +{ + struct pt_regs *regs = task_pt_regs(child); + int ilc = regs->int_code >> 16; + u16 insn; + + if (ilc > 6) + return; + + if (ptrace_access_vm(child, regs->psw.addr - (regs->int_code >> 16), + &insn, sizeof(insn), FOLL_FORCE) != sizeof(insn)) + return; + + /* double check that tracee stopped on svc instruction */ + if ((insn >> 8) != 0xa) + return; + + regs->int_code = 0x20000 | (data & 0xffff); +} /* * Write a word to the user area of a process at location addr. This * operation does have an additional problem compared to peek_user. @@ -334,7 +353,9 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) struct user *dummy = NULL; addr_t offset; + if (addr < (addr_t) &dummy->regs.acrs) { + struct pt_regs *regs = task_pt_regs(child); /* * psw and gprs are stored on the stack */ @@ -352,7 +373,11 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data) /* Invalid addressing mode bits */ return -EINVAL; } - *(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data; + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct user, regs.gprs[2])) + fixup_int_code(child, data); + *(addr_t *)((addr_t) ®s->psw + addr) = data; } else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) { /* @@ -718,6 +743,10 @@ static int __poke_user_compat(struct task_struct *child, regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) | (__u64)(tmp & PSW32_ADDR_AMODE); } else { + + if (test_pt_regs_flag(regs, PIF_SYSCALL) && + addr == offsetof(struct compat_user, regs.gprs[2])) + fixup_int_code(child, data); /* gpr 0-15 */ *(__u32*)((addr_t) ®s->psw + addr*2 + 4) = tmp; } @@ -837,40 +866,66 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, asmlinkage long do_syscall_trace_enter(struct pt_regs *regs) { unsigned long mask = -1UL; + long ret = -1; + + if (is_compat_task()) + mask = 0xffffffff; /* * The sysc_tracesys code in entry.S stored the system * call number to gprs[2]. */ if (test_thread_flag(TIF_SYSCALL_TRACE) && - (tracehook_report_syscall_entry(regs) || - regs->gprs[2] >= NR_syscalls)) { + tracehook_report_syscall_entry(regs)) { /* - * Tracing decided this syscall should not happen or the - * debugger stored an invalid system call number. Skip + * Tracing decided this syscall should not happen. Skip * the system call and the system call restart handling. */ - clear_pt_regs_flag(regs, PIF_SYSCALL); - return -1; + goto skip; } +#ifdef CONFIG_SECCOMP /* Do the secure computing check after ptrace. */ - if (secure_computing()) { - /* seccomp failures shouldn't expose any additional code. */ - return -1; + if (unlikely(test_thread_flag(TIF_SECCOMP))) { + struct seccomp_data sd; + + if (is_compat_task()) { + sd.instruction_pointer = regs->psw.addr & 0x7fffffff; + sd.arch = AUDIT_ARCH_S390; + } else { + sd.instruction_pointer = regs->psw.addr; + sd.arch = AUDIT_ARCH_S390X; + } + + sd.nr = regs->int_code & 0xffff; + sd.args[0] = regs->orig_gpr2 & mask; + sd.args[1] = regs->gprs[3] & mask; + sd.args[2] = regs->gprs[4] & mask; + sd.args[3] = regs->gprs[5] & mask; + sd.args[4] = regs->gprs[6] & mask; + sd.args[5] = regs->gprs[7] & mask; + + if (__secure_computing(&sd) == -1) + goto skip; } +#endif /* CONFIG_SECCOMP */ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT))) - trace_sys_enter(regs, regs->gprs[2]); + trace_sys_enter(regs, regs->int_code & 0xffff); - if (is_compat_task()) - mask = 0xffffffff; - audit_syscall_entry(regs->gprs[2], regs->orig_gpr2 & mask, + audit_syscall_entry(regs->int_code & 0xffff, regs->orig_gpr2 & mask, regs->gprs[3] &mask, regs->gprs[4] &mask, regs->gprs[5] &mask); + if ((signed long)regs->gprs[2] >= NR_syscalls) { + regs->gprs[2] = -ENOSYS; + ret = -ENOSYS; + } return regs->gprs[2]; +skip: + clear_pt_regs_flag(regs, PIF_SYSCALL); + return ret; } asmlinkage void do_syscall_trace_exit(struct pt_regs *regs) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index f9d070d016e3..b1113b519432 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -301,6 +301,7 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->tk_mult = tk->tkr_mono.mult; vdso_data->tk_shift = tk->tkr_mono.shift; + vdso_data->hrtimer_res = hrtimer_resolution; smp_wmb(); ++vdso_data->tb_update_count; } diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 66e89b2866d7..c296e5c8dbf9 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -331,7 +331,7 @@ EXPORT_SYMBOL_GPL(arch_make_page_accessible); static ssize_t uv_query_facilities(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", + return scnprintf(page, PAGE_SIZE, "%lx\n%lx\n%lx\n%lx\n", uv_info.inst_calls_list[0], uv_info.inst_calls_list[1], uv_info.inst_calls_list[2], @@ -344,7 +344,7 @@ static struct kobj_attribute uv_query_facilities_attr = static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%d\n", + return scnprintf(page, PAGE_SIZE, "%d\n", uv_info.max_guest_cpus); } @@ -354,7 +354,7 @@ static struct kobj_attribute uv_query_max_guest_cpus_attr = static ssize_t uv_query_max_guest_vms(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%d\n", + return scnprintf(page, PAGE_SIZE, "%d\n", uv_info.max_num_sec_conf); } @@ -364,7 +364,7 @@ static struct kobj_attribute uv_query_max_guest_vms_attr = static ssize_t uv_query_max_guest_addr(struct kobject *kobj, struct kobj_attribute *attr, char *page) { - return snprintf(page, PAGE_SIZE, "%lx\n", + return scnprintf(page, PAGE_SIZE, "%lx\n", uv_info.max_sec_stor_addr); } diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index bec19e7e6e1c..4a66a1cb919b 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -18,8 +18,8 @@ KBUILD_AFLAGS_64 += -m64 -s KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS)) KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin -KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \ - -Wl,--hash-style=both +ldflags-y := -fPIC -shared -nostdlib -soname=linux-vdso64.so.1 \ + --hash-style=both --build-id -T $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64) $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64) @@ -37,8 +37,8 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE - $(call if_changed,vdso64ld) +$(obj)/vdso64.so.dbg: $(obj)/vdso64.lds $(obj-vdso64) FORCE + $(call if_changed,ld) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -50,8 +50,6 @@ $(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands -quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S index 081435398e0a..0c79caa32b59 100644 --- a/arch/s390/kernel/vdso64/clock_getres.S +++ b/arch/s390/kernel/vdso64/clock_getres.S @@ -17,12 +17,14 @@ .type __kernel_clock_getres,@function __kernel_clock_getres: CFI_STARTPROC - larl %r1,4f + larl %r1,3f + lg %r0,0(%r1) cghi %r2,__CLOCK_REALTIME_COARSE je 0f cghi %r2,__CLOCK_MONOTONIC_COARSE je 0f - larl %r1,3f + larl %r1,_vdso_data + llgf %r0,__VDSO_CLOCK_REALTIME_RES(%r1) cghi %r2,__CLOCK_REALTIME je 0f cghi %r2,__CLOCK_MONOTONIC @@ -36,7 +38,6 @@ __kernel_clock_getres: jz 2f 0: ltgr %r3,%r3 jz 1f /* res == NULL */ - lg %r0,0(%r1) xc 0(8,%r3),0(%r3) /* set tp->tv_sec to zero */ stg %r0,8(%r3) /* store tp->tv_usec */ 1: lghi %r2,0 @@ -45,6 +46,5 @@ __kernel_clock_getres: svc 0 br %r14 CFI_ENDPROC -3: .quad __CLOCK_REALTIME_RES -4: .quad __CLOCK_COARSE_RES +3: .quad __CLOCK_COARSE_RES .size __kernel_clock_getres,.-__kernel_clock_getres diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index 6a24751557f0..d53c2e2ea1fd 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -105,7 +105,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long asce, unsigned long address) diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 1b04270e5460..0646c5961846 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -119,7 +119,7 @@ static void ftrace_mod_code(void) * But if one were to fail, then they all should, and if one were * to succeed, then they all should. */ - mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode, + mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode, MCOUNT_INSN_SIZE); /* if we fail, then kill any new writers */ @@ -203,7 +203,7 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, */ /* read the text we want to modify */ - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; /* Make sure it is what we expect it to be */ @@ -268,7 +268,7 @@ static int ftrace_mod(unsigned long ip, unsigned long old_addr, { unsigned char code[MCOUNT_INSN_SIZE]; - if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE)) + if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; if (old_addr != __raw_readl((unsigned long *)code)) diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index a33025451fcd..9c3d32b80038 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -118,7 +118,7 @@ int is_valid_bugaddr(unsigned long addr) if (addr < PAGE_OFFSET) return 0; - if (probe_kernel_address((insn_size_t *)addr, opcode)) + if (get_kernel_nofault(opcode, (insn_size_t *)addr)) return 0; if (opcode == TRAPA_BUG_OPCODE) return 1; diff --git a/arch/um/kernel/maccess.c b/arch/um/kernel/maccess.c index e929c0966696..8ccd56813f68 100644 --- a/arch/um/kernel/maccess.c +++ b/arch/um/kernel/maccess.c @@ -7,7 +7,7 @@ #include <linux/kernel.h> #include <os.h> -bool probe_kernel_read_allowed(const void *src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *src, size_t size) { void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8998e97457f..be5363b21540 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -943,7 +943,7 @@ struct kvm_arch { atomic_t vapics_in_nmi_mode; struct mutex apic_map_lock; struct kvm_apic_map *apic_map; - bool apic_map_dirty; + atomic_t apic_map_dirty; bool apic_access_page_done; unsigned long apicv_inhibit_reasons; @@ -1220,7 +1220,7 @@ struct kvm_x86_ops { void (*enable_log_dirty_pt_masked)(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask); - int (*write_log_dirty)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); /* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops; diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 73d997aa2966..e039a933aca3 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -25,8 +25,6 @@ #define TPAUSE_C01_STATE 1 #define TPAUSE_C02_STATE 0 -u32 get_umwait_control_msr(void); - static inline void __monitor(const void *eax, unsigned long ecx, unsigned long edx) { diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index ebedeab48704..255b2dde2c1b 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -278,7 +278,7 @@ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs } /* To avoid include hell, we can't include uaccess.h */ -extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack @@ -298,7 +298,7 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { - ret = probe_kernel_read(&val, addr, sizeof(val)); + ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c index 300e3fd5ade3..ec8064c0ae03 100644 --- a/arch/x86/kernel/cpu/umwait.c +++ b/arch/x86/kernel/cpu/umwait.c @@ -18,12 +18,6 @@ */ static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE); -u32 get_umwait_control_msr(void) -{ - return umwait_control_cached; -} -EXPORT_SYMBOL_GPL(get_umwait_control_msr); - /* * Cache the original IA32_UMWAIT_CONTROL MSR value which is configured by * hardware or BIOS before kernel boot. diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 456511b2284e..b037cfa7c0c5 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -106,7 +106,7 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl) bad_ip = user_mode(regs) && __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); - if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue, + if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue, OPCODE_BUFSIZE)) { printk("%sCode: Bad RIP value.\n", loglvl); } else { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index c84d28e90a58..51504566b3a6 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -86,7 +86,7 @@ static int ftrace_verify_code(unsigned long ip, const char *old_code) * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ - if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { WARN_ON(1); return -EFAULT; } @@ -355,7 +355,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE); /* Copy ftrace_caller onto the trampoline memory */ - ret = probe_kernel_read(trampoline, (void *)start_offset, size); + ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size); if (WARN_ON(ret < 0)) goto fail; @@ -363,13 +363,13 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* The trampoline ends with ret(q) */ retq = (unsigned long)ftrace_stub; - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller); - ret = probe_kernel_read(ip, (void *)retq, RET_SIZE); + ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE); if (WARN_ON(ret < 0)) goto fail; } @@ -506,7 +506,7 @@ static void *addr_from_call(void *ptr) union text_poke_insn call; int ret; - ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); + ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index c44fe7d8d9a4..68acd30c6b87 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -732,11 +732,11 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) int err; bpt->type = BP_BREAKPOINT; - err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr, + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE); if (err) return err; - err = probe_kernel_write((char *)bpt->bpt_addr, + err = copy_to_kernel_nofault((char *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE); if (!err) return err; @@ -768,7 +768,7 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) return 0; knl_write: - return probe_kernel_write((char *)bpt->bpt_addr, + return copy_to_kernel_nofault((char *)bpt->bpt_addr, (char *)bpt->saved_instr, BREAK_INSTR_SIZE); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3bafe1bd4dc7..ada39ddbc922 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -243,7 +243,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr) * Fortunately, we know that the original code is the ideal 5-byte * long NOP. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; @@ -346,7 +346,8 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* This can access kernel text if given address is not recovered */ - if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(dest, (void *)recovered_insn, + MAX_INSN_SIZE)) return 0; kernel_insn_init(insn, dest, MAX_INSN_SIZE); @@ -753,16 +754,11 @@ asm( NOKPROBE_SYMBOL(kretprobe_trampoline); STACK_FRAME_NON_STANDARD(kretprobe_trampoline); -static struct kprobe kretprobe_kprobe = { - .addr = (void *)kretprobe_trampoline, -}; - /* * Called from kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { - struct kprobe_ctlblk *kcb; struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; struct hlist_node *tmp; @@ -772,16 +768,12 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) void *frame_pointer; bool skipped = false; - preempt_disable(); - /* * Set a dummy kprobe for avoiding kretprobe recursion. * Since kretprobe never run in kprobe handler, kprobe must not * be running at this point. */ - kcb = get_kprobe_ctlblk(); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; + kprobe_busy_begin(); INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); @@ -857,7 +849,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) __this_cpu_write(current_kprobe, &ri->rp->kp); ri->ret_addr = correct_ret_addr; ri->rp->handler(ri, regs); - __this_cpu_write(current_kprobe, &kretprobe_kprobe); + __this_cpu_write(current_kprobe, &kprobe_busy); } recycle_rp_inst(ri, &empty_rp); @@ -873,8 +865,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) kretprobe_hash_unlock(current, &flags); - __this_cpu_write(current_kprobe, NULL); - preempt_enable(); + kprobe_busy_end(); hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 321c19950285..7af4c61dde52 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -56,7 +56,7 @@ found: * overwritten by jump destination address. In this case, original * bytes must be recovered from op->optinsn.copied_insn buffer. */ - if (probe_kernel_read(buf, (void *)addr, + if (copy_from_kernel_nofault(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t))) return 0UL; diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index ee0286390a4c..9e1def3744f2 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -94,12 +94,12 @@ static bool match_id(struct pci_dev *pdev, unsigned short vendor, unsigned short } static bool probe_list(struct pci_dev *pdev, unsigned short vendor, - const unsigned char *rom_list) + const void *rom_list) { unsigned short device; do { - if (probe_kernel_address(rom_list, device) != 0) + if (get_kernel_nofault(device, rom_list) != 0) device = 0; if (device && match_id(pdev, vendor, device)) @@ -119,19 +119,19 @@ static struct resource *find_oprom(struct pci_dev *pdev) for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) { struct resource *res = &adapter_rom_resources[i]; unsigned short offset, vendor, device, list, rev; - const unsigned char *rom; + const void *rom; if (res->end == 0) break; rom = isa_bus_to_virt(res->start); - if (probe_kernel_address(rom + 0x18, offset) != 0) + if (get_kernel_nofault(offset, rom + 0x18) != 0) continue; - if (probe_kernel_address(rom + offset + 0x4, vendor) != 0) + if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0) continue; - if (probe_kernel_address(rom + offset + 0x6, device) != 0) + if (get_kernel_nofault(device, rom + offset + 0x6) != 0) continue; if (match_id(pdev, vendor, device)) { @@ -139,8 +139,8 @@ static struct resource *find_oprom(struct pci_dev *pdev) break; } - if (probe_kernel_address(rom + offset + 0x8, list) == 0 && - probe_kernel_address(rom + offset + 0xc, rev) == 0 && + if (get_kernel_nofault(list, rom + offset + 0x8) == 0 && + get_kernel_nofault(rev, rom + offset + 0xc) == 0 && rev >= 3 && list && probe_list(pdev, vendor, rom + offset + list)) { oprom = res; @@ -183,14 +183,14 @@ static int __init romsignature(const unsigned char *rom) const unsigned short * const ptr = (const unsigned short *)rom; unsigned short sig; - return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE; + return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE; } static int __init romchecksum(const unsigned char *rom, unsigned long length) { unsigned char sum, c; - for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--) + for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--) sum += c; return !length && !sum; } @@ -211,7 +211,7 @@ void __init probe_roms(void) video_rom_resource.start = start; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ @@ -249,7 +249,7 @@ void __init probe_roms(void) if (!romsignature(rom)) continue; - if (probe_kernel_address(rom + 2, c) != 0) + if (get_kernel_nofault(c, rom + 2) != 0) continue; /* 0 < length <= 0x7f * 512, historically */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1d9ea2101b97..f58679e487f6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -492,7 +492,8 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, u8 insn_buf[MAX_INSN_SIZE]; struct insn insn; - if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, + MAX_INSN_SIZE)) return GP_NO_HINT; kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 34a7e0533dad..5bf72fc86a8e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -169,6 +169,18 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +/* + * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. + * + * DIRTY -> UPDATE_IN_PROGRESS and UPDATE_IN_PROGRESS -> CLEAN happen with + * apic_map_lock_held. + */ +enum { + CLEAN, + UPDATE_IN_PROGRESS, + DIRTY +}; + void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; @@ -176,17 +188,17 @@ void kvm_recalculate_apic_map(struct kvm *kvm) int i; u32 max_id = 255; /* enough space for any xAPIC ID */ - if (!kvm->arch.apic_map_dirty) { - /* - * Read kvm->arch.apic_map_dirty before - * kvm->arch.apic_map - */ - smp_rmb(); + /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ + if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) return; - } mutex_lock(&kvm->arch.apic_map_lock); - if (!kvm->arch.apic_map_dirty) { + /* + * Read kvm->arch.apic_map_dirty before kvm->arch.apic_map + * (if clean) or the APIC registers (if dirty). + */ + if (atomic_cmpxchg_acquire(&kvm->arch.apic_map_dirty, + DIRTY, UPDATE_IN_PROGRESS) == CLEAN) { /* Someone else has updated the map. */ mutex_unlock(&kvm->arch.apic_map_lock); return; @@ -256,11 +268,11 @@ out: lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); /* - * Write kvm->arch.apic_map before - * clearing apic->apic_map_dirty + * Write kvm->arch.apic_map before clearing apic->apic_map_dirty. + * If another update has come in, leave it DIRTY. */ - smp_wmb(); - kvm->arch.apic_map_dirty = false; + atomic_cmpxchg_release(&kvm->arch.apic_map_dirty, + UPDATE_IN_PROGRESS, CLEAN); mutex_unlock(&kvm->arch.apic_map_lock); if (old) @@ -282,20 +294,20 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) else static_key_slow_inc(&apic_sw_disabled.key); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } static inline void kvm_apic_set_xapic_id(struct kvm_lapic *apic, u8 id) { kvm_lapic_set_reg(apic, APIC_ID, id << 24); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id) { kvm_lapic_set_reg(apic, APIC_LDR, id); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) @@ -311,7 +323,7 @@ static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) kvm_lapic_set_reg(apic, APIC_ID, id); kvm_lapic_set_reg(apic, APIC_LDR, ldr); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type) @@ -1976,7 +1988,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_DFR: if (!apic_x2apic_mode(apic)) { kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF); - apic->vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } else ret = 1; break; @@ -2232,7 +2244,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) static_key_slow_dec_deferred(&apic_hw_disabled); } else { static_key_slow_inc(&apic_hw_disabled.key); - vcpu->kvm->arch.apic_map_dirty = true; + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } } @@ -2273,7 +2285,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) if (!apic) return; - vcpu->kvm->arch.apic_map_dirty = false; /* Stop the timer in case it's a reset to an active apic */ hrtimer_cancel(&apic->lapic_timer.timer); @@ -2567,6 +2578,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 0ad06bfe2c2c..444bb9c54548 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -222,7 +222,7 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn); -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa); int kvm_mmu_post_init_vm(struct kvm *kvm); void kvm_mmu_pre_destroy_vm(struct kvm *kvm); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index fdd05c233308..76817d13c86e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1745,10 +1745,10 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, * Emulate arch specific page modification logging for the * nested hypervisor */ -int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) +int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu, gpa_t l2_gpa) { if (kvm_x86_ops.write_log_dirty) - return kvm_x86_ops.write_log_dirty(vcpu); + return kvm_x86_ops.write_log_dirty(vcpu, l2_gpa); return 0; } diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index a6d484ea110b..bd70ece1ef8b 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -235,7 +235,7 @@ static inline unsigned FNAME(gpte_access)(u64 gpte) static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, - int write_fault) + gpa_t addr, int write_fault) { unsigned level, index; pt_element_t pte, orig_pte; @@ -260,7 +260,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); #if PTTYPE == PTTYPE_EPT - if (kvm_arch_write_log_dirty(vcpu)) + if (kvm_arch_write_log_dirty(vcpu, addr)) return -EINVAL; #endif pte |= PT_GUEST_DIRTY_MASK; @@ -360,7 +360,6 @@ retry_walk: ++walker->level; do { - gfn_t real_gfn; unsigned long host_addr; pt_access = pte_access; @@ -375,7 +374,7 @@ retry_walk: walker->table_gfn[walker->level - 1] = table_gfn; walker->pte_gpa[walker->level - 1] = pte_gpa; - real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), + real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn), nested_access, &walker->fault); @@ -389,12 +388,10 @@ retry_walk: * information to fix the exit_qualification or exit_info_1 * fields. */ - if (unlikely(real_gfn == UNMAPPED_GVA)) + if (unlikely(real_gpa == UNMAPPED_GVA)) return 0; - real_gfn = gpa_to_gfn(real_gfn); - - host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, real_gfn, + host_addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gpa_to_gfn(real_gpa), &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; @@ -457,7 +454,8 @@ retry_walk: (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { - ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); + ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, + addr, write_fault); if (unlikely(ret < 0)) goto error; else if (ret) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8ccfa4197d9c..c0da4dd78ac5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3344,7 +3344,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); -static fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { fastpath_t exit_fastpath; struct vcpu_svm *svm = to_svm(vcpu); diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index 5c0ff80b85c0..7a3675fddec2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -72,11 +72,24 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; +static inline bool is_intr_type(u32 intr_info, u32 type) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type); +} + +static inline bool is_intr_type_n(u32 intr_info, u32 type, u8 vector) +{ + const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK | + INTR_INFO_VECTOR_MASK; + + return (intr_info & mask) == (INTR_INFO_VALID_MASK | type | vector); +} + static inline bool is_exception_n(u32 intr_info, u8 vector) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK); + return is_intr_type_n(intr_info, INTR_TYPE_HARD_EXCEPTION, vector); } static inline bool is_debug(u32 intr_info) @@ -106,28 +119,23 @@ static inline bool is_gp_fault(u32 intr_info) static inline bool is_machine_check(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK | - INTR_INFO_VALID_MASK)) == - (INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK); + return is_exception_n(intr_info, MC_VECTOR); } /* Undocumented: icebp/int1 */ static inline bool is_icebp(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } static inline bool is_nmi(u32 intr_info) { - return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); + return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } static inline bool is_external_intr(u32 intr_info) { - return (intr_info & (INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK)) - == (INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR); + return is_intr_type(intr_info, INTR_TYPE_EXT_INTR); } enum vmcs_field_width { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 36c771728c8c..cb22f33bf1d8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6606,23 +6606,6 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void atomic_switch_umwait_control_msr(struct vcpu_vmx *vmx) -{ - u32 host_umwait_control; - - if (!vmx_has_waitpkg(vmx)) - return; - - host_umwait_control = get_umwait_control_msr(); - - if (vmx->msr_ia32_umwait_control != host_umwait_control) - add_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL, - vmx->msr_ia32_umwait_control, - host_umwait_control, false); - else - clear_atomic_switch_msr(vmx, MSR_IA32_UMWAIT_CONTROL); -} - static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6728,9 +6711,7 @@ reenter_guest: pt_guest_enter(vmx); - if (vcpu_to_pmu(vcpu)->version) - atomic_switch_perf_msrs(vmx); - atomic_switch_umwait_control_msr(vmx); + atomic_switch_perf_msrs(vmx); if (enable_preemption_timer) vmx_update_hv_timer(vcpu); @@ -7501,11 +7482,11 @@ static void vmx_flush_log_dirty(struct kvm *kvm) kvm_flush_pml_buffers(kvm); } -static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) +static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) { struct vmcs12 *vmcs12; struct vcpu_vmx *vmx = to_vmx(vcpu); - gpa_t gpa, dst; + gpa_t dst; if (is_guest_mode(vcpu)) { WARN_ON_ONCE(vmx->nested.pml_full); @@ -7524,7 +7505,7 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) return 1; } - gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull; + gpa &= ~0xFFFull; dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index; if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 8a83b5edc820..639798e4a6ca 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -288,8 +288,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - u32 host_pkru; - unsigned long host_debugctlmsr; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 00c88c2f34e4..3b92db412335 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2856,7 +2856,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: return kvm_set_apic_base(vcpu, msr_info); - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); case MSR_IA32_TSCDEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); @@ -3196,7 +3196,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_APICBASE: msr_info->data = kvm_get_apic_base(vcpu); break; - case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff: + case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); case MSR_IA32_TSCDEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); @@ -4603,7 +4603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_has_tsc_control && + user_tsc_khz >= kvm_max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 66be9bd60307..1ead568c0101 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -99,7 +99,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && @@ -133,7 +133,7 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) while (instr < max_instr) { unsigned char opcode; - if (probe_kernel_address(instr, opcode)) + if (get_kernel_nofault(opcode, instr)) break; instr++; @@ -301,7 +301,7 @@ static int bad_address(void *p) { unsigned long dummy; - return probe_kernel_address((unsigned long *)p, dummy); + return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) @@ -442,7 +442,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) return; } - if (probe_kernel_read(&desc, (void *)(gdt->address + offset), + if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index bda909e3e37e..8b4afad84f4a 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -737,7 +737,7 @@ static void __init test_wp_bit(void) __set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO); - if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { + if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) { clear_fixmap(FIX_WP_TEST); printk(KERN_CONT "Ok.\n"); return; diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index e1d7d7477c22..92ec176a7293 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -9,7 +9,7 @@ static __always_inline u64 canonical_address(u64 vaddr, u8 vaddr_bits) return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); } -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { unsigned long vaddr = (unsigned long)unsafe_src; @@ -22,7 +22,7 @@ bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr; } #else -bool probe_kernel_read_allowed(const void *unsafe_src, size_t size) +bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return (unsigned long)unsafe_src >= TASK_SIZE_MAX; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9c97d814125e..4f15280732ed 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -302,7 +302,7 @@ static const struct pci_raw_ops *__init pci_find_bios(void) check <= (union bios32 *) __va(0xffff0); ++check) { long sig; - if (probe_kernel_address(&check->fields.signature, sig)) + if (get_kernel_nofault(sig, &check->fields.signature)) continue; if (check->fields.signature != BIOS32_SIGNATURE) diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c index b8f7f193f383..30bd5714a3d4 100644 --- a/arch/x86/platform/intel-mid/sfi.c +++ b/arch/x86/platform/intel-mid/sfi.c @@ -287,8 +287,8 @@ void intel_scu_devices_create(void) adapter = i2c_get_adapter(i2c_bus[i]); if (adapter) { - client = i2c_new_device(adapter, i2c_devs[i]); - if (!client) + client = i2c_new_client_device(adapter, i2c_devs[i]); + if (IS_ERR(client)) pr_err("can't create i2c device %s\n", i2c_devs[i]->type); } else diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index b04e6e72a592..088bd764e0b7 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -34,6 +34,7 @@ KCOV_INSTRUMENT := n PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING +PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector) # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That # in turn leaves some undefined symbols like __fentry__ in purgatory and not diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 33b309d65955..acc49fa6a097 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -386,7 +386,7 @@ static void set_aliased_prot(void *v, pgprot_t prot) preempt_disable(); - probe_kernel_read(&dummy, v, 1); + copy_from_kernel_nofault(&dummy, v, 1); if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0)) BUG(); |