diff options
Diffstat (limited to 'arch/x86/kernel')
59 files changed, 1038 insertions, 1206 deletions
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index ca13851f0570..26b7256f590f 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -27,6 +27,17 @@ static char temp_stack[4096]; #endif /** + * acpi_get_wakeup_address - provide physical address for S3 wakeup + * + * Returns the physical address where the kernel should be resumed after the + * system awakes from S3, e.g. for programming into the firmware waking vector. + */ +unsigned long acpi_get_wakeup_address(void) +{ + return ((unsigned long)(real_mode_header->wakeup_start)); +} + +/** * x86_acpi_enter_sleep_state - enter sleep state * @state: Sleep state to enter. * diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h index fbb60ca4255c..d06c2079b6c1 100644 --- a/arch/x86/kernel/acpi/sleep.h +++ b/arch/x86/kernel/acpi/sleep.h @@ -3,7 +3,7 @@ * Variables and functions used by the code in sleep.c */ -#include <asm/realmode.h> +#include <linux/linkage.h> extern unsigned long saved_video_mode; extern long saved_magic; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 9ec463fe96f2..34360ca301a2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -936,44 +936,81 @@ static void do_sync_core(void *info) sync_core(); } -static struct bp_patching_desc { +void text_poke_sync(void) +{ + on_each_cpu(do_sync_core, NULL, 1); +} + +struct text_poke_loc { + s32 rel_addr; /* addr := _stext + rel_addr */ + s32 rel32; + u8 opcode; + const u8 text[POKE_MAX_OPCODE_SIZE]; +}; + +struct bp_patching_desc { struct text_poke_loc *vec; int nr_entries; -} bp_patching; + atomic_t refs; +}; + +static struct bp_patching_desc *bp_desc; + +static inline struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp) +{ + struct bp_patching_desc *desc = READ_ONCE(*descp); /* rcu_dereference */ + + if (!desc || !atomic_inc_not_zero(&desc->refs)) + return NULL; + + return desc; +} + +static inline void put_desc(struct bp_patching_desc *desc) +{ + smp_mb__before_atomic(); + atomic_dec(&desc->refs); +} -static int patch_cmp(const void *key, const void *elt) +static inline void *text_poke_addr(struct text_poke_loc *tp) +{ + return _stext + tp->rel_addr; +} + +static int notrace patch_cmp(const void *key, const void *elt) { struct text_poke_loc *tp = (struct text_poke_loc *) elt; - if (key < tp->addr) + if (key < text_poke_addr(tp)) return -1; - if (key > tp->addr) + if (key > text_poke_addr(tp)) return 1; return 0; } NOKPROBE_SYMBOL(patch_cmp); -int poke_int3_handler(struct pt_regs *regs) +int notrace poke_int3_handler(struct pt_regs *regs) { + struct bp_patching_desc *desc; struct text_poke_loc *tp; + int len, ret = 0; void *ip; + if (user_mode(regs)) + return 0; + /* * Having observed our INT3 instruction, we now must observe - * bp_patching.nr_entries. + * bp_desc: * - * nr_entries != 0 INT3 + * bp_desc = desc INT3 * WMB RMB - * write INT3 if (nr_entries) - * - * Idem for other elements in bp_patching. + * write INT3 if (desc) */ smp_rmb(); - if (likely(!bp_patching.nr_entries)) - return 0; - - if (user_mode(regs)) + desc = try_get_desc(&bp_desc); + if (!desc) return 0; /* @@ -984,19 +1021,20 @@ int poke_int3_handler(struct pt_regs *regs) /* * Skip the binary search if there is a single member in the vector. */ - if (unlikely(bp_patching.nr_entries > 1)) { - tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries, + if (unlikely(desc->nr_entries > 1)) { + tp = bsearch(ip, desc->vec, desc->nr_entries, sizeof(struct text_poke_loc), patch_cmp); if (!tp) - return 0; + goto out_put; } else { - tp = bp_patching.vec; - if (tp->addr != ip) - return 0; + tp = desc->vec; + if (text_poke_addr(tp) != ip) + goto out_put; } - ip += tp->len; + len = text_opcode_size(tp->opcode); + ip += len; switch (tp->opcode) { case INT3_INSN_OPCODE: @@ -1004,7 +1042,7 @@ int poke_int3_handler(struct pt_regs *regs) * Someone poked an explicit INT3, they'll want to handle it, * do not consume. */ - return 0; + goto out_put; case CALL_INSN_OPCODE: int3_emulate_call(regs, (long)ip + tp->rel32); @@ -1019,10 +1057,18 @@ int poke_int3_handler(struct pt_regs *regs) BUG(); } - return 1; + ret = 1; + +out_put: + put_desc(desc); + return ret; } NOKPROBE_SYMBOL(poke_int3_handler); +#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) +static struct text_poke_loc tp_vec[TP_VEC_MAX]; +static int tp_vec_nr; + /** * text_poke_bp_batch() -- update instructions on live kernel on SMP * @tp: vector of instructions to patch @@ -1044,16 +1090,20 @@ NOKPROBE_SYMBOL(poke_int3_handler); * replacing opcode * - sync cores */ -void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) +static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) { + struct bp_patching_desc desc = { + .vec = tp, + .nr_entries = nr_entries, + .refs = ATOMIC_INIT(1), + }; unsigned char int3 = INT3_INSN_OPCODE; unsigned int i; int do_sync; lockdep_assert_held(&text_mutex); - bp_patching.vec = tp; - bp_patching.nr_entries = nr_entries; + smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */ /* * Corresponding read barrier in int3 notifier for making sure the @@ -1065,18 +1115,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * First step: add a int3 trap to the address that will be patched. */ for (i = 0; i < nr_entries; i++) - text_poke(tp[i].addr, &int3, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE); - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* * Second step: update all but the first byte of the patched range. */ for (do_sync = 0, i = 0; i < nr_entries; i++) { - if (tp[i].len - sizeof(int3) > 0) { - text_poke((char *)tp[i].addr + sizeof(int3), - (const char *)tp[i].text + sizeof(int3), - tp[i].len - sizeof(int3)); + int len = text_opcode_size(tp[i].opcode); + + if (len - INT3_INSN_SIZE > 0) { + text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE, + (const char *)tp[i].text + INT3_INSN_SIZE, + len - INT3_INSN_SIZE); do_sync++; } } @@ -1087,7 +1139,7 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) * not necessary and we'd be safe even without it. But * better safe than sorry (plus there's not only Intel). */ - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); } /* @@ -1098,19 +1150,20 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries) if (tp[i].text[0] == INT3_INSN_OPCODE) continue; - text_poke(tp[i].addr, tp[i].text, sizeof(int3)); + text_poke(text_poke_addr(&tp[i]), tp[i].text, INT3_INSN_SIZE); do_sync++; } if (do_sync) - on_each_cpu(do_sync_core, NULL, 1); + text_poke_sync(); /* - * sync_core() implies an smp_mb() and orders this store against - * the writing of the new instruction. + * Remove and synchronize_rcu(), except we have a very primitive + * refcount based completion. */ - bp_patching.vec = NULL; - bp_patching.nr_entries = 0; + WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */ + if (!atomic_dec_and_test(&desc.refs)) + atomic_cond_read_acquire(&desc.refs, !VAL); } void text_poke_loc_init(struct text_poke_loc *tp, void *addr, @@ -1118,11 +1171,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, { struct insn insn; - if (!opcode) - opcode = (void *)tp->text; - else - memcpy((void *)tp->text, opcode, len); - + memcpy((void *)tp->text, opcode, len); if (!emulate) emulate = opcode; @@ -1132,8 +1181,7 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, BUG_ON(!insn_complete(&insn)); BUG_ON(len != insn.length); - tp->addr = addr; - tp->len = len; + tp->rel_addr = addr - (void *)_stext; tp->opcode = insn.opcode.bytes[0]; switch (tp->opcode) { @@ -1167,6 +1215,55 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, } } +/* + * We hard rely on the tp_vec being ordered; ensure this is so by flushing + * early if needed. + */ +static bool tp_order_fail(void *addr) +{ + struct text_poke_loc *tp; + + if (!tp_vec_nr) + return false; + + if (!addr) /* force */ + return true; + + tp = &tp_vec[tp_vec_nr - 1]; + if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr) + return true; + + return false; +} + +static void text_poke_flush(void *addr) +{ + if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) { + text_poke_bp_batch(tp_vec, tp_vec_nr); + tp_vec_nr = 0; + } +} + +void text_poke_finish(void) +{ + text_poke_flush(NULL); +} + +void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate) +{ + struct text_poke_loc *tp; + + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + + text_poke_flush(addr); + + tp = &tp_vec[tp_vec_nr++]; + text_poke_loc_init(tp, addr, opcode, len, emulate); +} + /** * text_poke_bp() -- update instructions on live kernel on SMP * @addr: address to patch @@ -1178,10 +1275,15 @@ void text_poke_loc_init(struct text_poke_loc *tp, void *addr, * dynamically allocated memory. This function should be used when it is * not possible to allocate memory. */ -void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) +void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate) { struct text_poke_loc tp; + if (unlikely(system_state == SYSTEM_BOOTING)) { + text_poke_early(addr, opcode, len); + return; + } + text_poke_loc_init(&tp, addr, opcode, len, emulate); text_poke_bp_batch(&tp, 1); } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 251c795b4eb3..69aed0ebbdfc 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -22,6 +22,7 @@ #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 +#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -52,6 +53,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, {} }; EXPORT_SYMBOL_GPL(amd_nb_misc_ids); @@ -66,6 +68,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c index 5da106f84e84..fe698f96617c 100644 --- a/arch/x86/kernel/apb_timer.c +++ b/arch/x86/kernel/apb_timer.c @@ -95,7 +95,7 @@ static inline void apbt_set_mapping(void) printk(KERN_WARNING "No timer base from SFI, use default\n"); apbt_address = APBT_DEFAULT_BASE; } - apbt_virt_address = ioremap_nocache(apbt_address, APBT_MMAP_SIZE); + apbt_virt_address = ioremap(apbt_address, APBT_MMAP_SIZE); if (!apbt_virt_address) { pr_debug("Failed mapping APBT phy address at %lu\n",\ (unsigned long)apbt_address); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index d5b51a740524..ad53b2abc859 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -1493,65 +1493,34 @@ static void check_efi_reboot(void) } /* Setup user proc fs files */ -static int proc_hubbed_show(struct seq_file *file, void *data) +static int __maybe_unused proc_hubbed_show(struct seq_file *file, void *data) { seq_printf(file, "0x%x\n", uv_hubbed_system); return 0; } -static int proc_hubless_show(struct seq_file *file, void *data) +static int __maybe_unused proc_hubless_show(struct seq_file *file, void *data) { seq_printf(file, "0x%x\n", uv_hubless_system); return 0; } -static int proc_oemid_show(struct seq_file *file, void *data) +static int __maybe_unused proc_oemid_show(struct seq_file *file, void *data) { seq_printf(file, "%s/%s\n", oem_id, oem_table_id); return 0; } -static int proc_hubbed_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_hubbed_show, (void *)NULL); -} - -static int proc_hubless_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_hubless_show, (void *)NULL); -} - -static int proc_oemid_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_oemid_show, (void *)NULL); -} - -/* (struct is "non-const" as open function is set at runtime) */ -static struct file_operations proc_version_fops = { - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static const struct file_operations proc_oemid_fops = { - .open = proc_oemid_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static __init void uv_setup_proc_files(int hubless) { struct proc_dir_entry *pde; - char *name = hubless ? "hubless" : "hubbed"; pde = proc_mkdir(UV_PROC_NODE, NULL); - proc_create("oemid", 0, pde, &proc_oemid_fops); - proc_create(name, 0, pde, &proc_version_fops); + proc_create_single("oemid", 0, pde, proc_oemid_show); if (hubless) - proc_version_fops.open = proc_hubless_open; + proc_create_single("hubless", 0, pde, proc_hubless_show); else - proc_version_fops.open = proc_hubbed_open; + proc_create_single("hubbed", 0, pde, proc_hubbed_show); } /* Initialize UV hubless systems */ diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 890f60083eca..7dc4ad68eb41 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -29,6 +29,7 @@ obj-y += umwait.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o +obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL obj-y += intel.o intel_pconfig.o tsx.o obj-$(CONFIG_PM) += intel_epb.o @@ -53,11 +54,12 @@ obj-$(CONFIG_ACRN_GUEST) += acrn.o ifdef CONFIG_X86_FEATURE_NAMES quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ + cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ cpufeature = $(src)/../../include/asm/cpufeatures.h +vmxfeature = $(src)/../../include/asm/vmxfeatures.h -$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE +$(obj)/capflags.c: $(cpufeature) $(vmxfeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) endif targets += capflags.c diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 62c30279be77..ac83a0fef628 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -319,13 +319,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) c->cpu_core_id %= cus_per_node; } - -static void amd_get_topology_early(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; -} - /* * Fixup core topology information for * (1) AMD multi-node processors @@ -717,7 +710,8 @@ static void early_init_amd(struct cpuinfo_x86 *c) } } - amd_get_topology_early(c); + if (cpu_has(c, X86_FEATURE_TOPOEXT)) + smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; } static void init_amd_k8(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 8bf64899f56a..ed54b3b21c39 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -286,6 +286,13 @@ early_param("mds", mds_cmdline); #undef pr_fmt #define pr_fmt(fmt) "TAA: " fmt +enum taa_mitigations { + TAA_MITIGATION_OFF, + TAA_MITIGATION_UCODE_NEEDED, + TAA_MITIGATION_VERW, + TAA_MITIGATION_TSX_DISABLED, +}; + /* Default mitigation for TAA-affected CPUs */ static enum taa_mitigations taa_mitigation __ro_after_init = TAA_MITIGATION_VERW; static bool taa_nosmt __ro_after_init; diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 14433ff5b828..426792565d86 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -18,13 +18,6 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 6) /* MSR_VIA_RNG */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 - static void init_c3(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -71,8 +64,6 @@ static void init_c3(struct cpuinfo_x86 *c) c->x86_cache_alignment = c->x86_clflush_size * 2; set_cpu_cap(c, X86_FEATURE_REP_GOOD); } - - cpu_detect_cache_sizes(c); } enum { @@ -119,31 +110,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c) } } -static void centaur_detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) - set_cpu_cap(c, X86_FEATURE_EPT); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - static void init_centaur(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_32 @@ -250,8 +216,7 @@ static void init_centaur(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif - if (cpu_has(c, X86_FEATURE_VMX)) - centaur_detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 2e4d90294fe6..86b8241c8209 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -14,6 +14,7 @@ #include <linux/sched/mm.h> #include <linux/sched/clock.h> #include <linux/sched/task.h> +#include <linux/sched/smt.h> #include <linux/init.h> #include <linux/kprobes.h> #include <linux/kgdb.h> @@ -49,7 +50,7 @@ #include <asm/cpu.h> #include <asm/mce.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/intel-family.h> @@ -1023,6 +1024,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define MSBDS_ONLY BIT(5) #define NO_SWAPGS BIT(6) #define NO_ITLB_MULTIHIT BIT(7) +#define NO_SPECTRE_V2 BIT(8) #define VULNWL(_vendor, _family, _model, _whitelist) \ { X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist } @@ -1084,6 +1086,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT), + + /* Zhaoxin Family 7 */ + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS), {} }; @@ -1116,7 +1122,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) return; setup_force_cpu_bug(X86_BUG_SPECTRE_V1); - setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + + if (!cpu_matches(NO_SPECTRE_V2)) + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) @@ -1449,6 +1457,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) #endif c->x86_cache_alignment = c->x86_clflush_size; memset(&c->x86_capability, 0, sizeof(c->x86_capability)); +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + memset(&c->vmx_capability, 0, sizeof(c->vmx_capability)); +#endif generic_identify(c); diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 38ab6e115eac..37fdefd14f28 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -80,4 +80,8 @@ extern void x86_spec_ctrl_setup_ap(void); extern u64 x86_read_arch_cap_msr(void); +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#endif + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c new file mode 100644 index 000000000000..0268185bef94 --- /dev/null +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/tboot.h> + +#include <asm/cpufeature.h> +#include <asm/msr-index.h> +#include <asm/processor.h> +#include <asm/vmx.h> + +#undef pr_fmt +#define pr_fmt(fmt) "x86/cpu: " fmt + +#ifdef CONFIG_X86_VMX_FEATURE_NAMES +enum vmx_feature_leafs { + MISC_FEATURES = 0, + PRIMARY_CTLS, + SECONDARY_CTLS, + NR_VMX_FEATURE_WORDS, +}; + +#define VMX_F(x) BIT(VMX_FEATURE_##x & 0x1f) + +static void init_vmx_capabilities(struct cpuinfo_x86 *c) +{ + u32 supported, funcs, ept, vpid, ign; + + BUILD_BUG_ON(NVMXINTS != NR_VMX_FEATURE_WORDS); + + /* + * The high bits contain the allowed-1 settings, i.e. features that can + * be turned on. The low bits contain the allowed-0 settings, i.e. + * features that can be turned off. Ignore the allowed-0 settings, + * if a feature can be turned on then it's supported. + * + * Use raw rdmsr() for primary processor controls and pin controls MSRs + * as they exist on any CPU that supports VMX, i.e. we want the WARN if + * the RDMSR faults. + */ + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, ign, supported); + c->vmx_capability[PRIMARY_CTLS] = supported; + + rdmsr_safe(MSR_IA32_VMX_PROCBASED_CTLS2, &ign, &supported); + c->vmx_capability[SECONDARY_CTLS] = supported; + + rdmsr(MSR_IA32_VMX_PINBASED_CTLS, ign, supported); + rdmsr_safe(MSR_IA32_VMX_VMFUNC, &ign, &funcs); + + /* + * Except for EPT+VPID, which enumerates support for both in a single + * MSR, low for EPT, high for VPID. + */ + rdmsr_safe(MSR_IA32_VMX_EPT_VPID_CAP, &ept, &vpid); + + /* Pin, EPT, VPID and VM-Func are merged into a single word. */ + WARN_ON_ONCE(supported >> 16); + WARN_ON_ONCE(funcs >> 4); + c->vmx_capability[MISC_FEATURES] = (supported & 0xffff) | + ((vpid & 0x1) << 16) | + ((funcs & 0xf) << 28); + + /* EPT bits are full on scattered and must be manually handled. */ + if (ept & VMX_EPT_EXECUTE_ONLY_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_EXECUTE_ONLY); + if (ept & VMX_EPT_AD_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_AD); + if (ept & VMX_EPT_1GB_PAGE_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_1GB); + + /* Synthetic APIC features that are aggregates of multiple features. */ + if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(VIRT_APIC_ACCESSES))) + c->vmx_capability[MISC_FEATURES] |= VMX_F(FLEXPRIORITY); + + if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(APIC_REGISTER_VIRT)) && + (c->vmx_capability[SECONDARY_CTLS] & VMX_F(VIRT_INTR_DELIVERY)) && + (c->vmx_capability[MISC_FEATURES] & VMX_F(POSTED_INTR))) + c->vmx_capability[MISC_FEATURES] |= VMX_F(APICV); + + /* Set the synthetic cpufeatures to preserve /proc/cpuinfo's ABI. */ + if (c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) + set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(FLEXPRIORITY)) + set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(VIRTUAL_NMIS)) + set_cpu_cap(c, X86_FEATURE_VNMI); + if (c->vmx_capability[SECONDARY_CTLS] & VMX_F(EPT)) + set_cpu_cap(c, X86_FEATURE_EPT); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(EPT_AD)) + set_cpu_cap(c, X86_FEATURE_EPT_AD); + if (c->vmx_capability[MISC_FEATURES] & VMX_F(VPID)) + set_cpu_cap(c, X86_FEATURE_VPID); +} +#endif /* CONFIG_X86_VMX_FEATURE_NAMES */ + +void init_ia32_feat_ctl(struct cpuinfo_x86 *c) +{ + bool tboot = tboot_enabled(); + u64 msr; + + if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) { + clear_cpu_cap(c, X86_FEATURE_VMX); + return; + } + + if (msr & FEAT_CTL_LOCKED) + goto update_caps; + + /* + * Ignore whatever value BIOS left in the MSR to avoid enabling random + * features or faulting on the WRMSR. + */ + msr = FEAT_CTL_LOCKED; + + /* + * Enable VMX if and only if the kernel may do VMXON at some point, + * i.e. KVM is enabled, to avoid unnecessarily adding an attack vector + * for the kernel, e.g. using VMX to hide malicious code. + */ + if (cpu_has(c, X86_FEATURE_VMX) && IS_ENABLED(CONFIG_KVM_INTEL)) { + msr |= FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; + + if (tboot) + msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX; + } + + wrmsrl(MSR_IA32_FEAT_CTL, msr); + +update_caps: + set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL); + + if (!cpu_has(c, X86_FEATURE_VMX)) + return; + + if ( (tboot && !(msr & FEAT_CTL_VMX_ENABLED_INSIDE_SMX)) || + (!tboot && !(msr & FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX))) { + if (IS_ENABLED(CONFIG_KVM_INTEL)) + pr_err_once("VMX (%s TXT) disabled by BIOS\n", + tboot ? "inside" : "outside"); + clear_cpu_cap(c, X86_FEATURE_VMX); + } else { +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + init_vmx_capabilities(c); +#endif + } +} diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 4a900804a023..57473e2c0869 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -494,52 +494,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - /* Intel VMX MSR indicated features */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 -#define x86_VMX_FEATURE_EPT_CAP_AD 0x00200000 - - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - u32 msr_vpid_cap, msr_ept_cap; - - clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - clear_cpu_cap(c, X86_FEATURE_VNMI); - clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - clear_cpu_cap(c, X86_FEATURE_EPT); - clear_cpu_cap(c, X86_FEATURE_VPID); - clear_cpu_cap(c, X86_FEATURE_EPT_AD); - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) { - set_cpu_cap(c, X86_FEATURE_EPT); - rdmsr(MSR_IA32_VMX_EPT_VPID_CAP, - msr_ept_cap, msr_vpid_cap); - if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD) - set_cpu_cap(c, X86_FEATURE_EPT_AD); - } - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - #define MSR_IA32_TME_ACTIVATE 0x982 /* Helpers to access TME_ACTIVATE MSR */ @@ -755,8 +709,7 @@ static void init_intel(struct cpuinfo_x86 *c) /* Work around errata */ srat_detect_node(c); - if (cpu_has(c, X86_FEATURE_VMX)) - detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); if (cpu_has(c, X86_FEATURE_TME)) detect_tme(c); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index d6cf5c18a7e0..b3a50d962851 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -78,6 +78,7 @@ struct smca_bank_name { static struct smca_bank_name smca_names[] = { [SMCA_LS] = { "load_store", "Load Store Unit" }, + [SMCA_LS_V2] = { "load_store", "Load Store Unit" }, [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, [SMCA_DE] = { "decode_unit", "Decode Unit" }, @@ -138,6 +139,7 @@ static struct smca_hwid smca_hwid_mcatypes[] = { /* ZN Core (HWID=0xB0) MCA types */ { SMCA_LS, HWID_MCATYPE(0xB0, 0x0), 0x1FFFFF }, + { SMCA_LS_V2, HWID_MCATYPE(0xB0, 0x10), 0xFFFFFF }, { SMCA_IF, HWID_MCATYPE(0xB0, 0x1), 0x3FFF }, { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2), 0xF }, { SMCA_DE, HWID_MCATYPE(0xB0, 0x3), 0x1FF }, diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 2e2a421c8528..2c4f949611e4 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,8 +53,6 @@ #include "internal.h" -static DEFINE_MUTEX(mce_log_mutex); - /* sysfs synchronization */ static DEFINE_MUTEX(mce_sysfs_mutex); @@ -156,19 +154,10 @@ void mce_log(struct mce *m) if (!mce_gen_pool_add(m)) irq_work_queue(&mce_irq_work); } - -void mce_inject_log(struct mce *m) -{ - mutex_lock(&mce_log_mutex); - mce_log(m); - mutex_unlock(&mce_log_mutex); -} -EXPORT_SYMBOL_GPL(mce_inject_log); - -static struct notifier_block mce_srao_nb; +EXPORT_SYMBOL_GPL(mce_log); /* - * We run the default notifier if we have only the SRAO, the first and the + * We run the default notifier if we have only the UC, the first and the * default notifier registered. I.e., the mandatory NUM_DEFAULT_NOTIFIERS * notifiers registered on the chain. */ @@ -594,26 +583,29 @@ static struct notifier_block first_nb = { .priority = MCE_PRIO_FIRST, }; -static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, - void *data) +static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) { struct mce *mce = (struct mce *)data; unsigned long pfn; - if (!mce) + if (!mce || !mce_usable_address(mce)) return NOTIFY_DONE; - if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { - pfn = mce->addr >> PAGE_SHIFT; - if (!memory_failure(pfn, 0)) - set_mce_nospec(pfn); - } + if (mce->severity != MCE_AO_SEVERITY && + mce->severity != MCE_DEFERRED_SEVERITY) + return NOTIFY_DONE; + + pfn = mce->addr >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); return NOTIFY_OK; } -static struct notifier_block mce_srao_nb = { - .notifier_call = srao_decode_notifier, - .priority = MCE_PRIO_SRAO, + +static struct notifier_block mce_uc_nb = { + .notifier_call = uc_decode_notifier, + .priority = MCE_PRIO_UC, }; static int mce_default_notifier(struct notifier_block *nb, unsigned long val, @@ -763,26 +755,22 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) log_it: error_seen = true; - mce_read_aux(&m, i); + if (flags & MCP_DONTLOG) + goto clear_it; + mce_read_aux(&m, i); m.severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) - mce_log(&m); - else if (mce_usable_address(&m)) { - /* - * Although we skipped logging this, we still want - * to take action. Add to the pool so the registered - * notifiers will see it. - */ - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } + if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) + goto clear_it; + + mce_log(&m); + +clear_it: /* * Clear state for this bank. */ @@ -807,7 +795,7 @@ EXPORT_SYMBOL_GPL(machine_check_poll); static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, struct pt_regs *regs) { - char *tmp; + char *tmp = *msg; int i; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { @@ -1232,8 +1220,8 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(toclear, MAX_NR_BANKS); struct mca_config *cfg = &mca_cfg; int cpu = smp_processor_id(); - char *msg = "Unknown"; struct mce m, *final; + char *msg = NULL; int worst = 0; /* @@ -1365,7 +1353,7 @@ void do_machine_check(struct pt_regs *regs, long error_code) ist_end_non_atomic(); } else { if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0)) - mce_panic("Failed kernel mode recovery", &m, NULL); + mce_panic("Failed kernel mode recovery", &m, msg); } out_ist: @@ -2041,7 +2029,7 @@ int __init mcheck_init(void) { mcheck_intel_therm_init(); mce_register_decode_chain(&first_nb); - mce_register_decode_chain(&mce_srao_nb); + mce_register_decode_chain(&mce_uc_nb); mce_register_decode_chain(&mce_default_nb); mcheck_vendor_init_severity(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 1f30117b24ba..3413b41b8d55 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -494,7 +494,7 @@ static void do_inject(void) i_mce.status |= MCI_STATUS_SYNDV; if (inj_type == SW_INJ) { - mce_inject_log(&i_mce); + mce_log(&i_mce); return; } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index e270d0770134..5627b1091b85 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -115,15 +115,16 @@ static bool lmce_supported(void) /* * BIOS should indicate support for LMCE by setting bit 20 in - * IA32_FEATURE_CONTROL without which touching MCG_EXT_CTL will - * generate a #GP fault. + * IA32_FEAT_CTL without which touching MCG_EXT_CTL will generate a #GP + * fault. The MSR must also be locked for LMCE_ENABLED to take effect. + * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally + * locks the MSR in the event that it wasn't already locked by BIOS. */ - rdmsrl(MSR_IA32_FEATURE_CONTROL, tmp); - if ((tmp & (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) == - (FEATURE_CONTROL_LOCKED | FEATURE_CONTROL_LMCE)) - return true; + rdmsrl(MSR_IA32_FEAT_CTL, tmp); + if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED))) + return false; - return false; + return tmp & FEAT_CTL_LMCE_ENABLED; } bool mce_intel_cmci_poll(void) diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 842b273bce31..b785c0d0b590 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -84,8 +84,6 @@ static inline int apei_clear_mce(u64 record_id) } #endif -void mce_inject_log(struct mce *m); - /* * We consider records to be equivalent if bank+status+addr+misc all match. * This is only used when the system is going down because of a fatal error diff --git a/arch/x86/kernel/cpu/mce/therm_throt.c b/arch/x86/kernel/cpu/mce/therm_throt.c index 6c3e1c92f183..58b4ee3cda77 100644 --- a/arch/x86/kernel/cpu/mce/therm_throt.c +++ b/arch/x86/kernel/cpu/mce/therm_throt.c @@ -235,7 +235,7 @@ static void get_therm_status(int level, bool *proc_hot, u8 *temp) *temp = (msr_val >> 16) & 0x7F; } -static void throttle_active_work(struct work_struct *work) +static void __maybe_unused throttle_active_work(struct work_struct *work) { struct _thermal_state *state = container_of(to_delayed_work(work), struct _thermal_state, therm_work); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh index aed45b8895d5..1db560ed2ca3 100644 --- a/arch/x86/kernel/cpu/mkcapflags.sh +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -6,8 +6,7 @@ set -e -IN=$1 -OUT=$2 +OUT=$1 dump_array() { @@ -15,6 +14,7 @@ dump_array() SIZE=$2 PFX=$3 POSTFIX=$4 + IN=$5 PFX_SZ=$(echo $PFX | wc -c) TABS="$(printf '\t\t\t\t\t')" @@ -57,11 +57,18 @@ trap 'rm "$OUT"' EXIT echo "#endif" echo "" - dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" + dump_array "x86_cap_flags" "NCAPINTS*32" "X86_FEATURE_" "" $2 echo "" - dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" + dump_array "x86_bug_flags" "NBUGINTS*32" "X86_BUG_" "NCAPINTS*32" $2 + echo "" + echo "#ifdef CONFIG_X86_VMX_FEATURE_NAMES" + echo "#ifndef _ASM_X86_VMXFEATURES_H" + echo "#include <asm/vmxfeatures.h>" + echo "#endif" + dump_array "x86_vmx_flags" "NVMXINTS*32" "VMX_FEATURE_" "" $3 + echo "#endif /* CONFIG_X86_VMX_FEATURE_NAMES */" ) > $OUT trap - EXIT diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index aa5c064a6a22..51b9190c628b 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -15,7 +15,7 @@ #include <asm/tlbflush.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c index 4d36dcc1cf87..da532f656a7b 100644 --- a/arch/x86/kernel/cpu/mtrr/if.c +++ b/arch/x86/kernel/cpu/mtrr/if.c @@ -101,9 +101,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos) int length; size_t linelen; - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - memset(line, 0, LINE_SIZE); len = min_t(size_t, len, LINE_SIZE - 1); @@ -226,8 +223,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_ADD_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_add(sentry.base, sentry.size, sentry.type, true, file, 0); @@ -236,24 +231,18 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_SET_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_add(sentry.base, sentry.size, sentry.type, false); break; case MTRRIOC_DEL_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_DEL_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_del(sentry.base, sentry.size, file, 0); break; case MTRRIOC_KILL_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_KILL_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_del(-1, sentry.base, sentry.size); break; case MTRRIOC_GET_ENTRY: @@ -279,8 +268,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_ADD_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_add(sentry.base, sentry.size, sentry.type, true, file, 1); @@ -289,8 +276,6 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_SET_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_add_page(sentry.base, sentry.size, sentry.type, false); break; @@ -298,16 +283,12 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg) #ifdef CONFIG_COMPAT case MTRRIOC32_DEL_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_file_del(sentry.base, sentry.size, file, 1); break; case MTRRIOC_KILL_PAGE_ENTRY: #ifdef CONFIG_COMPAT case MTRRIOC32_KILL_PAGE_ENTRY: #endif - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; err = mtrr_del_page(-1, sentry.base, sentry.size); break; case MTRRIOC_GET_PAGE_ENTRY: @@ -373,28 +354,6 @@ static int mtrr_close(struct inode *ino, struct file *file) return single_release(ino, file); } -static int mtrr_seq_show(struct seq_file *seq, void *offset); - -static int mtrr_open(struct inode *inode, struct file *file) -{ - if (!mtrr_if) - return -EIO; - if (!mtrr_if->get) - return -ENXIO; - return single_open(file, mtrr_seq_show, NULL); -} - -static const struct file_operations mtrr_fops = { - .owner = THIS_MODULE, - .open = mtrr_open, - .read = seq_read, - .llseek = seq_lseek, - .write = mtrr_write, - .unlocked_ioctl = mtrr_ioctl, - .compat_ioctl = mtrr_ioctl, - .release = mtrr_close, -}; - static int mtrr_seq_show(struct seq_file *seq, void *offset) { char factor; @@ -426,6 +385,28 @@ static int mtrr_seq_show(struct seq_file *seq, void *offset) return 0; } +static int mtrr_open(struct inode *inode, struct file *file) +{ + if (!mtrr_if) + return -EIO; + if (!mtrr_if->get) + return -ENXIO; + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + return single_open(file, mtrr_seq_show, NULL); +} + +static const struct file_operations mtrr_fops = { + .owner = THIS_MODULE, + .open = mtrr_open, + .read = seq_read, + .llseek = seq_lseek, + .write = mtrr_write, + .unlocked_ioctl = mtrr_ioctl, + .compat_ioctl = mtrr_ioctl, + .release = mtrr_close, +}; + static int __init mtrr_if_init(void) { struct cpuinfo_x86 *c = &boot_cpu_data; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 507039c20128..6a80f36b5d59 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -52,7 +52,7 @@ #include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include "mtrr.h" diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index cb2e49810d68..4eec8889b0ff 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -7,6 +7,10 @@ #include "cpu.h" +#ifdef CONFIG_X86_VMX_FEATURE_NAMES +extern const char * const x86_vmx_flags[NVMXINTS*32]; +#endif + /* * Get CPU information for use by the procfs. */ @@ -102,6 +106,17 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has(c, i) && x86_cap_flags[i] != NULL) seq_printf(m, " %s", x86_cap_flags[i]); +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + if (cpu_has(c, X86_FEATURE_VMX) && c->vmx_capability[0]) { + seq_puts(m, "\nvmx flags\t:"); + for (i = 0; i < 32*NVMXINTS; i++) { + if (test_bit(i, (unsigned long *)c->vmx_capability) && + x86_vmx_flags[i] != NULL) + seq_printf(m, " %s", x86_vmx_flags[i]); + } + } +#endif + seq_puts(m, "\nbugs\t\t:"); for (i = 0; i < 32*NBUGINTS; i++) { unsigned int bug_bit = 32*NCAPINTS + i; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index e49b77283924..181c992f448c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -57,6 +57,7 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) } DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /** * struct mon_evt - Entry in the event list of a resource diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 397206f23d14..773124b0e18a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -514,7 +514,7 @@ void mbm_handle_overflow(struct work_struct *work) mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) goto out_unlock; d = get_domain_from_cpu(cpu, &rdt_resources_all[RDT_RESOURCE_L3]); @@ -543,7 +543,7 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_enable_key)) + if (!static_branch_likely(&rdt_mon_enable_key)) return; cpu = cpumask_any(&dom->cpu_mask); dom->mbm_work_cpu = cpu; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index dac7209a0708..1504bcabc63c 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -532,11 +532,15 @@ static void move_myself(struct callback_head *head) kfree(rdtgrp); } + if (unlikely(current->flags & PF_EXITING)) + goto out; + preempt_disable(); /* update PQR_ASSOC MSR to make resource group go into effect */ resctrl_sched_in(); preempt_enable(); +out: kfree(callback); } @@ -725,6 +729,92 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +#ifdef CONFIG_PROC_CPU_RESCTRL + +/* + * A task can only be part of one resctrl control group and of one monitor + * group which is associated to that control group. + * + * 1) res: + * mon: + * + * resctrl is not available. + * + * 2) res:/ + * mon: + * + * Task is part of the root resctrl control group, and it is not associated + * to any monitor group. + * + * 3) res:/ + * mon:mon0 + * + * Task is part of the root resctrl control group and monitor group mon0. + * + * 4) res:group0 + * mon: + * + * Task is part of resctrl control group group0, and it is not associated + * to any monitor group. + * + * 5) res:group0 + * mon:mon1 + * + * Task is part of resctrl control group group0 and monitor group mon1. + */ +int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk) +{ + struct rdtgroup *rdtg; + int ret = 0; + + mutex_lock(&rdtgroup_mutex); + + /* Return empty if resctrl has not been mounted. */ + if (!static_branch_unlikely(&rdt_enable_key)) { + seq_puts(s, "res:\nmon:\n"); + goto unlock; + } + + list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) { + struct rdtgroup *crg; + + /* + * Task information is only relevant for shareable + * and exclusive groups. + */ + if (rdtg->mode != RDT_MODE_SHAREABLE && + rdtg->mode != RDT_MODE_EXCLUSIVE) + continue; + + if (rdtg->closid != tsk->closid) + continue; + + seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", + rdtg->kn->name); + seq_puts(s, "mon:"); + list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, + mon.crdtgrp_list) { + if (tsk->rmid != crg->mon.rmid) + continue; + seq_printf(s, "%s", crg->kn->name); + break; + } + seq_putc(s, '\n'); + goto unlock; + } + /* + * The above search should succeed. Otherwise return + * with an error. + */ + ret = -ENOENT; +unlock: + mutex_unlock(&rdtgroup_mutex); + + return ret; +} +#endif + static int rdt_last_cmd_status_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index adf9b71386ef..62b137c3c97a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -4,7 +4,7 @@ */ #include <linux/cpu.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/apic.h> #include <asm/processor.h> diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index ee48c3fc8a65..d3a0791bc052 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -7,7 +7,7 @@ #include <linux/cpu.h> #include <asm/apic.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/processor.h> #include "cpu.h" diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index 3e20d322bc98..e2ad30e474f8 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -14,6 +14,9 @@ #include "cpu.h" +#undef pr_fmt +#define pr_fmt(fmt) "tsx: " fmt + enum tsx_ctrl_states tsx_ctrl_state __ro_after_init = TSX_CTRL_NOT_SUPPORTED; void tsx_disable(void) @@ -99,7 +102,7 @@ void __init tsx_init(void) tsx_ctrl_state = x86_get_tsx_auto_mode(); } else { tsx_ctrl_state = TSX_CTRL_DISABLE; - pr_err("tsx: invalid option, defaulting to off\n"); + pr_err("invalid option, defaulting to off\n"); } } else { /* tsx= not provided */ @@ -115,11 +118,12 @@ void __init tsx_init(void) tsx_disable(); /* - * tsx_disable() will change the state of the - * RTM CPUID bit. Clear it here since it is now - * expected to be not set. + * tsx_disable() will change the state of the RTM and HLE CPUID + * bits. Clear them here since they are now expected to be not + * set. */ setup_clear_cpu_cap(X86_FEATURE_RTM); + setup_clear_cpu_cap(X86_FEATURE_HLE); } else if (tsx_ctrl_state == TSX_CTRL_ENABLE) { /* @@ -131,10 +135,10 @@ void __init tsx_init(void) tsx_enable(); /* - * tsx_enable() will change the state of the - * RTM CPUID bit. Force it here since it is now - * expected to be set. + * tsx_enable() will change the state of the RTM and HLE CPUID + * bits. Force them here since they are now expected to be set. */ setup_force_cpu_cap(X86_FEATURE_RTM); + setup_force_cpu_cap(X86_FEATURE_HLE); } } diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 8e6f2f4b4afe..df1358ba622b 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -16,13 +16,6 @@ #define RNG_ENABLED (1 << 3) #define RNG_ENABLE (1 << 8) /* MSR_ZHAOXIN_RNG */ -#define X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW 0x00200000 -#define X86_VMX_FEATURE_PROC_CTLS_VNMI 0x00400000 -#define X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS 0x80000000 -#define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC 0x00000001 -#define X86_VMX_FEATURE_PROC_CTLS2_EPT 0x00000002 -#define X86_VMX_FEATURE_PROC_CTLS2_VPID 0x00000020 - static void init_zhaoxin_cap(struct cpuinfo_x86 *c) { u32 lo, hi; @@ -58,8 +51,6 @@ static void init_zhaoxin_cap(struct cpuinfo_x86 *c) if (c->x86 >= 0x6) set_cpu_cap(c, X86_FEATURE_REP_GOOD); - - cpu_detect_cache_sizes(c); } static void early_init_zhaoxin(struct cpuinfo_x86 *c) @@ -89,31 +80,6 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c) } -static void zhaoxin_detect_vmx_virtcap(struct cpuinfo_x86 *c) -{ - u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2; - - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high); - msr_ctl = vmx_msr_high | vmx_msr_low; - - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW) - set_cpu_cap(c, X86_FEATURE_TPR_SHADOW); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_VNMI) - set_cpu_cap(c, X86_FEATURE_VNMI); - if (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_2ND_CTLS) { - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - vmx_msr_low, vmx_msr_high); - msr_ctl2 = vmx_msr_high | vmx_msr_low; - if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) && - (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW)) - set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) - set_cpu_cap(c, X86_FEATURE_EPT); - if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID) - set_cpu_cap(c, X86_FEATURE_VPID); - } -} - static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); @@ -141,8 +107,7 @@ static void init_zhaoxin(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); #endif - if (cpu_has(c, X86_FEATURE_VMX)) - zhaoxin_detect_vmx_virtcap(c); + init_ia32_feat_ctl(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 00fc55ac7ffa..fd87b59452a3 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -370,7 +370,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) /* Add crashk_low_res region */ if (crashk_low_res.end) { ei.addr = crashk_low_res.start; - ei.size = crashk_low_res.end - crashk_low_res.start + 1; + ei.size = resource_size(&crashk_low_res); ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index e07424e19274..ae64ec7f752f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -365,7 +365,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) } NOKPROBE_SYMBOL(oops_end); -int __die(const char *str, struct pt_regs *regs, long err) +static void __die_header(const char *str, struct pt_regs *regs, long err) { const char *pr = ""; @@ -384,7 +384,11 @@ int __die(const char *str, struct pt_regs *regs, long err) IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); +} +NOKPROBE_SYMBOL(__die_header); +static int __die_body(const char *str, struct pt_regs *regs, long err) +{ show_regs(regs); print_modules(); @@ -394,6 +398,13 @@ int __die(const char *str, struct pt_regs *regs, long err) return 0; } +NOKPROBE_SYMBOL(__die_body); + +int __die(const char *str, struct pt_regs *regs, long err) +{ + __die_header(str, regs, err); + return __die_body(str, regs, err); +} NOKPROBE_SYMBOL(__die); /* @@ -410,6 +421,19 @@ void die(const char *str, struct pt_regs *regs, long err) oops_end(flags, regs, sig); } +void die_addr(const char *str, struct pt_regs *regs, long err, long gp_addr) +{ + unsigned long flags = oops_begin(); + int sig = SIGSEGV; + + __die_header(str, regs, err); + if (gp_addr) + kasan_non_canonical_hook(gp_addr); + if (__die_body(str, regs, err)) + sig = 0; + oops_end(flags, regs, sig); +} + void show_regs(struct pt_regs *regs) { show_regs_print_info(KERN_DEFAULT); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 0071b794ed19..400a05e1c1c5 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -352,6 +352,7 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) fpregs_unlock(); return 0; } + fpregs_deactivate(fpu); fpregs_unlock(); } @@ -403,6 +404,8 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) } if (!ret) fpregs_mark_activate(); + else + fpregs_deactivate(fpu); fpregs_unlock(); err_out: diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index fa31470bbf24..a1806598aaa4 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -107,23 +107,20 @@ int cpu_has_xfeatures(u64 xfeatures_needed, const char **feature_name) } EXPORT_SYMBOL_GPL(cpu_has_xfeatures); -static int xfeature_is_supervisor(int xfeature_nr) +static bool xfeature_is_supervisor(int xfeature_nr) { /* - * We currently do not support supervisor states, but if - * we did, we could find out like this. - * - * SDM says: If state component 'i' is a user state component, - * ECX[0] return 0; if state component i is a supervisor - * state component, ECX[0] returns 1. + * Extended State Enumeration Sub-leaves (EAX = 0DH, ECX = n, n > 1) + * returns ECX[0] set to (1) for a supervisor state, and cleared (0) + * for a user state. */ u32 eax, ebx, ecx, edx; cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); - return !!(ecx & 1); + return ecx & 1; } -static int xfeature_is_user(int xfeature_nr) +static bool xfeature_is_user(int xfeature_nr) { return !xfeature_is_supervisor(xfeature_nr); } @@ -419,7 +416,8 @@ static void __init setup_init_fpu_buf(void) print_xstate_features(); if (boot_cpu_has(X86_FEATURE_XSAVES)) - init_fpstate.xsave.header.xcomp_bv = (u64)1 << 63 | xfeatures_mask; + init_fpstate.xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; /* * Init all the features state with header.xfeatures being 0x0 diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 024c3053dbba..37a0aeaf89e7 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -23,6 +23,7 @@ #include <linux/list.h> #include <linux/module.h> #include <linux/memory.h> +#include <linux/vmalloc.h> #include <trace/syscall.h> @@ -34,6 +35,8 @@ #ifdef CONFIG_DYNAMIC_FTRACE +static int ftrace_poke_late = 0; + int ftrace_arch_code_modify_prepare(void) __acquires(&text_mutex) { @@ -43,84 +46,37 @@ int ftrace_arch_code_modify_prepare(void) * ftrace has it set to "read/write". */ mutex_lock(&text_mutex); - set_kernel_text_rw(); - set_all_modules_text_rw(); + ftrace_poke_late = 1; return 0; } int ftrace_arch_code_modify_post_process(void) __releases(&text_mutex) { - set_all_modules_text_ro(); - set_kernel_text_ro(); + /* + * ftrace_make_{call,nop}() may be called during + * module load, and we need to finish the text_poke_queue() + * that they do, here. + */ + text_poke_finish(); + ftrace_poke_late = 0; mutex_unlock(&text_mutex); return 0; } -union ftrace_code_union { - char code[MCOUNT_INSN_SIZE]; - struct { - unsigned char op; - int offset; - } __attribute__((packed)); -}; - -static int ftrace_calc_offset(long ip, long addr) -{ - return (int)(addr - ip); -} - -static unsigned char * -ftrace_text_replace(unsigned char op, unsigned long ip, unsigned long addr) +static const char *ftrace_nop_replace(void) { - static union ftrace_code_union calc; - - calc.op = op; - calc.offset = ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr); - - return calc.code; -} - -static unsigned char * -ftrace_call_replace(unsigned long ip, unsigned long addr) -{ - return ftrace_text_replace(0xe8, ip, addr); -} - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) -{ - return addr >= start && addr < end; + return ideal_nops[NOP_ATOMIC5]; } -static unsigned long text_ip_addr(unsigned long ip) +static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) { - /* - * On x86_64, kernel text mappings are mapped read-only, so we use - * the kernel identity mapping instead of the kernel text mapping - * to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); - - return ip; + return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); } -static const unsigned char *ftrace_nop_replace(void) +static int ftrace_verify_code(unsigned long ip, const char *old_code) { - return ideal_nops[NOP_ATOMIC5]; -} - -static int -ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - - ftrace_expected = old_code; + char cur_code[MCOUNT_INSN_SIZE]; /* * Note: @@ -129,31 +85,46 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, * Carefully read and modify the code with probe_kernel_*(), and make * 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(replaced, (void *)ip, MCOUNT_INSN_SIZE)) + if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) { + WARN_ON(1); return -EFAULT; + } /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0) + if (memcmp(cur_code, old_code, MCOUNT_INSN_SIZE) != 0) { + WARN_ON(1); return -EINVAL; + } - ip = text_ip_addr(ip); - - /* replace the text with the new text */ - if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE)) - return -EPERM; + return 0; +} - sync_core(); +/* + * Marked __ref because it calls text_poke_early() which is .init.text. That is + * ok because that call will happen early, during boot, when .init sections are + * still present. + */ +static int __ref +ftrace_modify_code_direct(unsigned long ip, const char *old_code, + const char *new_code) +{ + int ret = ftrace_verify_code(ip, old_code); + if (ret) + return ret; + /* replace the text with the new text */ + if (ftrace_poke_late) + text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL); + else + text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE); return 0; } -int ftrace_make_nop(struct module *mod, - struct dyn_ftrace *rec, unsigned long addr) +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_call_replace(ip, addr); new = ftrace_nop_replace(); @@ -167,19 +138,20 @@ int ftrace_make_nop(struct module *mod, * just modify the code directly. */ if (addr == MCOUNT_ADDR) - return ftrace_modify_code_direct(rec->ip, old, new); + return ftrace_modify_code_direct(ip, old, new); - ftrace_expected = NULL; - - /* Normal cases use add_brk_on_nop */ + /* + * x86 overrides ftrace_replace_code -- this function will never be used + * in this case. + */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; } int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { - unsigned const char *new, *old; unsigned long ip = rec->ip; + const char *new, *old; old = ftrace_nop_replace(); new = ftrace_call_replace(ip, addr); @@ -189,43 +161,6 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) } /* - * The modifying_ftrace_code is used to tell the breakpoint - * handler to call ftrace_int3_handler(). If it fails to - * call this handler for a breakpoint added by ftrace, then - * the kernel may crash. - * - * As atomic_writes on x86 do not need a barrier, we do not - * need to add smp_mb()s for this to work. It is also considered - * that we can not read the modifying_ftrace_code before - * executing the breakpoint. That would be quite remarkable if - * it could do that. Here's the flow that is required: - * - * CPU-0 CPU-1 - * - * atomic_inc(mfc); - * write int3s - * <trap-int3> // implicit (r)mb - * if (atomic_read(mfc)) - * call ftrace_int3_handler() - * - * Then when we are finished: - * - * atomic_dec(mfc); - * - * If we hit a breakpoint that was not set by ftrace, it does not - * matter if ftrace_int3_handler() is called or not. It will - * simply be ignored. But it is crucial that a ftrace nop/caller - * breakpoint is handled. No other user should ever place a - * breakpoint on an ftrace nop/caller location. It must only - * be done by this code. - */ -atomic_t modifying_ftrace_code __read_mostly; - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code); - -/* * Should never be called: * As it is only called by __ftrace_replace_code() which is called by * ftrace_replace_code() that x86 overrides, and by ftrace_update_code() @@ -237,452 +172,84 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); - ftrace_expected = NULL; return -EINVAL; } -static unsigned long ftrace_update_func; -static unsigned long ftrace_update_func_call; - -static int update_ftrace_func(unsigned long ip, void *new) -{ - unsigned char old[MCOUNT_INSN_SIZE]; - int ret; - - memcpy(old, (void *)ip, MCOUNT_INSN_SIZE); - - ftrace_update_func = ip; - /* Make sure the breakpoints see the ftrace_update_func update */ - smp_wmb(); - - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - - ret = ftrace_modify_code(ip, old, new); - - atomic_dec(&modifying_ftrace_code); - - return ret; -} - int ftrace_update_ftrace_func(ftrace_func_t func) { - unsigned long ip = (unsigned long)(&ftrace_call); - unsigned char *new; - int ret; - - ftrace_update_func_call = (unsigned long)func; - - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - - /* Also update the regs callback function */ - if (!ret) { - ip = (unsigned long)(&ftrace_regs_call); - new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - } - - return ret; -} - -static nokprobe_inline int is_ftrace_caller(unsigned long ip) -{ - if (ip == ftrace_update_func) - return 1; - - return 0; -} - -/* - * A breakpoint was added to the code address we are about to - * modify, and this is the handle that will just skip over it. - * We are either changing a nop into a trace call, or a trace - * call to a nop. While the change is taking place, we treat - * it just like it was a nop. - */ -int ftrace_int3_handler(struct pt_regs *regs) -{ unsigned long ip; + const char *new; - if (WARN_ON_ONCE(!regs)) - return 0; - - ip = regs->ip - INT3_INSN_SIZE; - - if (ftrace_location(ip)) { - int3_emulate_call(regs, (unsigned long)ftrace_regs_caller); - return 1; - } else if (is_ftrace_caller(ip)) { - if (!ftrace_update_func_call) { - int3_emulate_jmp(regs, ip + CALL_INSN_SIZE); - return 1; - } - int3_emulate_call(regs, ftrace_update_func_call); - return 1; - } - - return 0; -} -NOKPROBE_SYMBOL(ftrace_int3_handler); - -static int ftrace_write(unsigned long ip, const char *val, int size) -{ - ip = text_ip_addr(ip); - - if (probe_kernel_write((void *)ip, val, size)) - return -EPERM; - - return 0; -} - -static int add_break(unsigned long ip, const char *old) -{ - unsigned char replaced[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - - if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - ftrace_expected = old; - - /* Make sure it is what we expect it to be */ - if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) - return -EINVAL; - - return ftrace_write(ip, &brk, 1); -} - -static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned const char *old; - unsigned long ip = rec->ip; - - old = ftrace_call_replace(ip, addr); - - return add_break(rec->ip, old); -} - - -static int add_brk_on_nop(struct dyn_ftrace *rec) -{ - unsigned const char *old; - - old = ftrace_nop_replace(); - - return add_break(rec->ip, old); -} - -static int add_breakpoints(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ftrace_addr = ftrace_get_addr_curr(rec); - - ret = ftrace_test_record(rec, enable); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_brk_on_nop(rec); - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_brk_on_call(rec, ftrace_addr); - } - return 0; -} - -/* - * On error, we need to remove breakpoints. This needs to - * be done caefully. If the address does not currently have a - * breakpoint, we know we are done. Otherwise, we look at the - * remaining 4 bytes of the instruction. If it matches a nop - * we replace the breakpoint with the nop. Otherwise we replace - * it with the call instruction. - */ -static int remove_breakpoint(struct dyn_ftrace *rec) -{ - unsigned char ins[MCOUNT_INSN_SIZE]; - unsigned char brk = BREAKPOINT_INSTRUCTION; - const unsigned char *nop; - unsigned long ftrace_addr; - unsigned long ip = rec->ip; - - /* If we fail the read, just give up */ - if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE)) - return -EFAULT; - - /* If this does not have a breakpoint, we are done */ - if (ins[0] != brk) - return 0; - - nop = ftrace_nop_replace(); - - /* - * If the last 4 bytes of the instruction do not match - * a nop, then we assume that this is a call to ftrace_addr. - */ - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) { - /* - * For extra paranoidism, we check if the breakpoint is on - * a call that would actually jump to the ftrace_addr. - * If not, don't touch the breakpoint, we make just create - * a disaster. - */ - ftrace_addr = ftrace_get_addr_new(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) - goto update; - - /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = ftrace_get_addr_curr(rec); - nop = ftrace_call_replace(ip, ftrace_addr); - - ftrace_expected = nop; - - if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) - return -EINVAL; - } - - update: - return ftrace_write(ip, nop, 1); -} - -static int add_update_code(unsigned long ip, unsigned const char *new) -{ - /* skip breakpoint */ - ip++; - new++; - return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1); -} - -static int add_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - return add_update_code(ip, new); -} - -static int add_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - return add_update_code(ip, new); -} - -static int add_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_test_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return add_update_call(rec, ftrace_addr); - - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return add_update_nop(rec); - } - - return 0; -} - -static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_call_replace(ip, addr); - - return ftrace_write(ip, new, 1); -} - -static int finish_update_nop(struct dyn_ftrace *rec) -{ - unsigned long ip = rec->ip; - unsigned const char *new; - - new = ftrace_nop_replace(); - - return ftrace_write(ip, new, 1); -} - -static int finish_update(struct dyn_ftrace *rec, bool enable) -{ - unsigned long ftrace_addr; - int ret; - - ret = ftrace_update_record(rec, enable); - - ftrace_addr = ftrace_get_addr_new(rec); - - switch (ret) { - case FTRACE_UPDATE_IGNORE: - return 0; - - case FTRACE_UPDATE_MODIFY_CALL: - case FTRACE_UPDATE_MAKE_CALL: - /* converting nop to call */ - return finish_update_call(rec, ftrace_addr); + ip = (unsigned long)(&ftrace_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); - case FTRACE_UPDATE_MAKE_NOP: - /* converting a call to a nop */ - return finish_update_nop(rec); - } + ip = (unsigned long)(&ftrace_regs_call); + new = ftrace_call_replace(ip, (unsigned long)func); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); return 0; } -static void do_sync_core(void *data) -{ - sync_core(); -} - -static void run_sync(void) -{ - int enable_irqs; - - /* No need to sync if there's only one CPU */ - if (num_online_cpus() == 1) - return; - - enable_irqs = irqs_disabled(); - - /* We may be called with interrupts disabled (on bootup). */ - if (enable_irqs) - local_irq_enable(); - on_each_cpu(do_sync_core, NULL, 1); - if (enable_irqs) - local_irq_disable(); -} - void ftrace_replace_code(int enable) { struct ftrace_rec_iter *iter; struct dyn_ftrace *rec; - const char *report = "adding breakpoints"; - int count = 0; + const char *new, *old; int ret; for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = add_breakpoints(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } - - run_sync(); + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - report = "updating code"; - count = 0; + case FTRACE_UPDATE_MAKE_CALL: + old = ftrace_nop_replace(); + break; - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); + case FTRACE_UPDATE_MODIFY_CALL: + case FTRACE_UPDATE_MAKE_NOP: + old = ftrace_call_replace(rec->ip, ftrace_get_addr_curr(rec)); + break; + } - ret = add_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; + ret = ftrace_verify_code(rec->ip, old); + if (ret) { + ftrace_bug(ret, rec); + return; + } } - run_sync(); - - report = "removing breakpoints"; - count = 0; - for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); - ret = finish_update(rec, enable); - if (ret) - goto remove_breakpoints; - count++; - } + switch (ftrace_test_record(rec, enable)) { + case FTRACE_UPDATE_IGNORE: + default: + continue; - run_sync(); + case FTRACE_UPDATE_MAKE_CALL: + case FTRACE_UPDATE_MODIFY_CALL: + new = ftrace_call_replace(rec->ip, ftrace_get_addr_new(rec)); + break; - return; + case FTRACE_UPDATE_MAKE_NOP: + new = ftrace_nop_replace(); + break; + } - remove_breakpoints: - pr_warn("Failed on %s (%d):\n", report, count); - ftrace_bug(ret, rec); - for_ftrace_rec_iter(iter) { - rec = ftrace_rec_iter_record(iter); - /* - * Breakpoints are handled only when this function is in - * progress. The system could not work with them. - */ - if (remove_breakpoint(rec)) - BUG(); + text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL); + ftrace_update_record(rec, enable); } - run_sync(); -} - -static int -ftrace_modify_code(unsigned long ip, unsigned const char *old_code, - unsigned const char *new_code) -{ - int ret; - - ret = add_break(ip, old_code); - if (ret) - goto out; - - run_sync(); - - ret = add_update_code(ip, new_code); - if (ret) - goto fail_update; - - run_sync(); - - ret = ftrace_write(ip, new_code, 1); - /* - * The breakpoint is handled only when this function is in progress. - * The system could not work if we could not remove it. - */ - BUG_ON(ret); - out: - run_sync(); - return ret; - - fail_update: - /* Also here the system could not work with the breakpoint */ - if (ftrace_write(ip, old_code, 1)) - BUG(); - goto out; + text_poke_finish(); } void arch_ftrace_update_code(int command) { - /* See comment above by declaration of modifying_ftrace_code */ - atomic_inc(&modifying_ftrace_code); - ftrace_modify_all_code(command); - - atomic_dec(&modifying_ftrace_code); } int __init ftrace_dyn_arch_init(void) @@ -747,6 +314,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long start_offset; unsigned long end_offset; unsigned long op_offset; + unsigned long call_offset; unsigned long offset; unsigned long npages; unsigned long size; @@ -763,10 +331,12 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) start_offset = (unsigned long)ftrace_regs_caller; end_offset = (unsigned long)ftrace_regs_caller_end; op_offset = (unsigned long)ftrace_regs_caller_op_ptr; + call_offset = (unsigned long)ftrace_regs_call; } else { start_offset = (unsigned long)ftrace_caller; end_offset = (unsigned long)ftrace_epilogue; op_offset = (unsigned long)ftrace_caller_op_ptr; + call_offset = (unsigned long)ftrace_call; } size = end_offset - start_offset; @@ -823,16 +393,21 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* put in the new offset to the ftrace_ops */ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE); + /* put in the call to the function */ + mutex_lock(&text_mutex); + call_offset -= start_offset; + memcpy(trampoline + call_offset, + text_gen_insn(CALL_INSN_OPCODE, + trampoline + call_offset, + ftrace_ops_get_func(ops)), CALL_INSN_SIZE); + mutex_unlock(&text_mutex); + /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; set_vm_flush_reset_perms(trampoline); - /* - * Module allocation needs to be completed by making the page - * executable. The page is still writable, which is a security hazard, - * but anyhow ftrace breaks W^X completely. - */ + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -859,62 +434,54 @@ static unsigned long calc_trampoline_call_offset(bool save_regs) void arch_ftrace_update_trampoline(struct ftrace_ops *ops) { ftrace_func_t func; - unsigned char *new; unsigned long offset; unsigned long ip; unsigned int size; - int ret, npages; + const char *new; - if (ops->trampoline) { - /* - * The ftrace_ops caller may set up its own trampoline. - * In such a case, this code must not modify it. - */ - if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) - return; - npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT; - set_memory_rw(ops->trampoline, npages); - } else { + if (!ops->trampoline) { ops->trampoline = create_trampoline(ops, &size); if (!ops->trampoline) return; ops->trampoline_size = size; - npages = PAGE_ALIGN(size) >> PAGE_SHIFT; + return; } + /* + * The ftrace_ops caller may set up its own trampoline. + * In such a case, this code must not modify it. + */ + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + return; + offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS); ip = ops->trampoline + offset; - func = ftrace_ops_get_func(ops); - ftrace_update_func_call = (unsigned long)func; - + mutex_lock(&text_mutex); /* Do a safe modify in case the trampoline is executing */ new = ftrace_call_replace(ip, (unsigned long)func); - ret = update_ftrace_func(ip, new); - set_memory_ro(ops->trampoline, npages); - - /* The update should never fail */ - WARN_ON(ret); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + mutex_unlock(&text_mutex); } /* Return the address of the function the trampoline calls */ static void *addr_from_call(void *ptr) { - union ftrace_code_union calc; + union text_poke_insn call; int ret; - ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE); + ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE); if (WARN_ON_ONCE(ret < 0)) return NULL; /* Make sure this is a call */ - if (WARN_ON_ONCE(calc.op != 0xe8)) { - pr_warn("Expected e8, got %x\n", calc.op); + if (WARN_ON_ONCE(call.opcode != CALL_INSN_OPCODE)) { + pr_warn("Expected E8, got %x\n", call.opcode); return NULL; } - return ptr + MCOUNT_INSN_SIZE + calc.offset; + return ptr + CALL_INSN_SIZE + call.disp; } void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, @@ -981,19 +548,18 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_DYNAMIC_FTRACE extern void ftrace_graph_call(void); -static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) +static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { - return ftrace_text_replace(0xe9, ip, addr); + return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); } static int ftrace_mod_jmp(unsigned long ip, void *func) { - unsigned char *new; + const char *new; - ftrace_update_func_call = 0UL; new = ftrace_jmp_replace(ip, (unsigned long)func); - - return update_ftrace_func(ip, new); + text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL); + return 0; } int ftrace_enable_ftrace_graph_caller(void) @@ -1019,10 +585,9 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { + unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; int faulted; - unsigned long return_hooker = (unsigned long) - &return_to_handler; /* * When resuming from suspend-to-ram, this function can be indirectly diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c6f791bc481e..7a50f0b62a70 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -84,7 +84,7 @@ static inline void hpet_writel(unsigned int d, unsigned int a) static inline void hpet_set_mapping(void) { - hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); + hpet_virt_address = ioremap(hpet_address, HPET_MMAP_SIZE); } static inline void hpet_clear_mapping(void) diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index c1a8b9e71408..9c4498ea0b3c 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -16,15 +16,7 @@ #include <asm/alternative.h> #include <asm/text-patching.h> -union jump_code_union { - char code[JUMP_LABEL_NOP_SIZE]; - struct { - char jump; - int offset; - } __attribute__((packed)); -}; - -static void bug_at(unsigned char *ip, int line) +static void bug_at(const void *ip, int line) { /* * The location is not an op that we were expecting. @@ -35,42 +27,42 @@ static void bug_at(unsigned char *ip, int line) BUG(); } -static void __jump_label_set_jump_code(struct jump_entry *entry, - enum jump_label_type type, - union jump_code_union *code, - int init) +static const void * +__jump_label_set_jump_code(struct jump_entry *entry, enum jump_label_type type, int init) { const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP }; const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5]; - const void *expect; + const void *expect, *code; + const void *addr, *dest; int line; - code->jump = 0xe9; - code->offset = jump_entry_target(entry) - - (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE); + addr = (void *)jump_entry_code(entry); + dest = (void *)jump_entry_target(entry); + + code = text_gen_insn(JMP32_INSN_OPCODE, addr, dest); if (init) { expect = default_nop; line = __LINE__; } else if (type == JUMP_LABEL_JMP) { expect = ideal_nop; line = __LINE__; } else { - expect = code->code; line = __LINE__; + expect = code; line = __LINE__; } - if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE)) - bug_at((void *)jump_entry_code(entry), line); + if (memcmp(addr, expect, JUMP_LABEL_NOP_SIZE)) + bug_at(addr, line); if (type == JUMP_LABEL_NOP) - memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE); + code = ideal_nop; + + return code; } -static void __ref __jump_label_transform(struct jump_entry *entry, - enum jump_label_type type, - int init) +static void inline __jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { - union jump_code_union code; - - __jump_label_set_jump_code(entry, type, &code, init); + const void *opcode = __jump_label_set_jump_code(entry, type, init); /* * As long as only a single processor is running and the code is still @@ -84,31 +76,33 @@ static void __ref __jump_label_transform(struct jump_entry *entry, * always nop being the 'currently valid' instruction */ if (init || system_state == SYSTEM_BOOTING) { - text_poke_early((void *)jump_entry_code(entry), &code, + text_poke_early((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE); return; } - text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE, NULL); + text_poke_bp((void *)jump_entry_code(entry), opcode, JUMP_LABEL_NOP_SIZE, NULL); } -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +static void __ref jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + int init) { mutex_lock(&text_mutex); - __jump_label_transform(entry, type, 0); + __jump_label_transform(entry, type, init); mutex_unlock(&text_mutex); } -#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc)) -static struct text_poke_loc tp_vec[TP_VEC_MAX]; -static int tp_vec_nr; +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + jump_label_transform(entry, type, 0); +} bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type) { - struct text_poke_loc *tp; - void *entry_code; + const void *opcode; if (system_state == SYSTEM_BOOTING) { /* @@ -118,53 +112,19 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, return true; } - /* - * No more space in the vector, tell upper layer to apply - * the queue before continuing. - */ - if (tp_vec_nr == TP_VEC_MAX) - return false; - - tp = &tp_vec[tp_vec_nr]; - - entry_code = (void *)jump_entry_code(entry); - - /* - * The INT3 handler will do a bsearch in the queue, so we need entries - * to be sorted. We can survive an unsorted list by rejecting the entry, - * forcing the generic jump_label code to apply the queue. Warning once, - * to raise the attention to the case of an unsorted entry that is - * better not happen, because, in the worst case we will perform in the - * same way as we do without batching - with some more overhead. - */ - if (tp_vec_nr > 0) { - int prev = tp_vec_nr - 1; - struct text_poke_loc *prev_tp = &tp_vec[prev]; - - if (WARN_ON_ONCE(prev_tp->addr > entry_code)) - return false; - } - - __jump_label_set_jump_code(entry, type, - (union jump_code_union *)&tp->text, 0); - - text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL); - - tp_vec_nr++; - + mutex_lock(&text_mutex); + opcode = __jump_label_set_jump_code(entry, type, 0); + text_poke_queue((void *)jump_entry_code(entry), + opcode, JUMP_LABEL_NOP_SIZE, NULL); + mutex_unlock(&text_mutex); return true; } void arch_jump_label_transform_apply(void) { - if (!tp_vec_nr) - return; - mutex_lock(&text_mutex); - text_poke_bp_batch(tp_vec, tp_vec_nr); + text_poke_finish(); mutex_unlock(&text_mutex); - - tp_vec_nr = 0; } static enum { @@ -193,5 +153,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry, jlstate = JL_STATE_NO_UPDATE; } if (jlstate == JL_STATE_UPDATE) - __jump_label_transform(entry, type, 1); + jump_label_transform(entry, type, 1); } diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index d2f4e706a428..f293d872602a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -177,7 +177,7 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, * acpi_rsdp=<addr> on kernel command line to make second kernel boot * without efi. */ - if (efi_enabled(EFI_OLD_MEMMAP)) + if (efi_have_uv1_memmap()) return 0; params->secure_boot = boot_params.secure_boot; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 4f13af7cbcdb..4d7022a740ab 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -40,6 +40,7 @@ #include <linux/frame.h> #include <linux/kasan.h> #include <linux/moduleloader.h> +#include <linux/vmalloc.h> #include <asm/text-patching.h> #include <asm/cacheflush.h> @@ -119,14 +120,14 @@ __synthesize_relative_insn(void *dest, void *from, void *to, u8 op) /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ void synthesize_reljump(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVEJUMP_OPCODE); + __synthesize_relative_insn(dest, from, to, JMP32_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ void synthesize_relcall(void *dest, void *from, void *to) { - __synthesize_relative_insn(dest, from, to, RELATIVECALL_OPCODE); + __synthesize_relative_insn(dest, from, to, CALL_INSN_OPCODE); } NOKPROBE_SYMBOL(synthesize_relcall); @@ -301,7 +302,7 @@ static int can_probe(unsigned long paddr) * Another debugging subsystem might insert this breakpoint. * In that case, we can't recover it. */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; addr += insn.length; } @@ -356,7 +357,7 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn) return 0; /* Another subsystem puts a breakpoint, failed to recover */ - if (insn->opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn->opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* We should not singlestep on the exception masking instructions */ @@ -400,14 +401,14 @@ static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p, int len = insn->length; if (can_boost(insn, p->addr) && - MAX_INSN_SIZE - len >= RELATIVEJUMP_SIZE) { + MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) { /* * These instructions can be executed directly if it * jumps back to correct address. */ synthesize_reljump(buf + len, p->ainsn.insn + len, p->addr + insn->length); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; p->ainsn.boostable = true; } else { p->ainsn.boostable = false; @@ -501,12 +502,14 @@ int arch_prepare_kprobe(struct kprobe *p) void arch_arm_kprobe(struct kprobe *p) { - text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); + text_poke(p->addr, ((unsigned char []){INT3_INSN_OPCODE}), 1); + text_poke_sync(); } void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); + text_poke_sync(); } void arch_remove_kprobe(struct kprobe *p) @@ -609,7 +612,7 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, regs->flags |= X86_EFLAGS_TF; regs->flags &= ~X86_EFLAGS_IF; /* single step inline if the instruction is an int3 */ - if (p->opcode == BREAKPOINT_INSTRUCTION) + if (p->opcode == INT3_INSN_OPCODE) regs->ip = (unsigned long)p->addr; else regs->ip = (unsigned long)p->ainsn.insn; @@ -695,7 +698,7 @@ int kprobe_int3_handler(struct pt_regs *regs) reset_current_kprobe(); return 1; } - } else if (*addr != BREAKPOINT_INSTRUCTION) { + } else if (*addr != INT3_INSN_OPCODE) { /* * The breakpoint instruction was removed right * after we hit it. Another cpu has removed diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 8900329c28a7..3f45b5c43a71 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -38,7 +38,7 @@ unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr) long offs; int i; - for (i = 0; i < RELATIVEJUMP_SIZE; i++) { + for (i = 0; i < JMP32_INSN_SIZE; i++) { kp = get_kprobe((void *)addr - i); /* This function only handles jump-optimized kprobe */ if (kp && kprobe_optimized(kp)) { @@ -62,10 +62,10 @@ found: if (addr == (unsigned long)kp->addr) { buf[0] = kp->opcode; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); + memcpy(buf + 1, op->optinsn.copied_insn, DISP32_SIZE); } else { offs = addr - (unsigned long)kp->addr - 1; - memcpy(buf, op->optinsn.copied_insn + offs, RELATIVE_ADDR_SIZE - offs); + memcpy(buf, op->optinsn.copied_insn + offs, DISP32_SIZE - offs); } return (unsigned long)buf; @@ -141,8 +141,6 @@ STACK_FRAME_NON_STANDARD(optprobe_template_func); #define TMPL_END_IDX \ ((long)optprobe_template_end - (long)optprobe_template_entry) -#define INT3_SIZE sizeof(kprobe_opcode_t) - /* Optimized kprobe call back function: called from optinsn */ static void optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) @@ -162,7 +160,7 @@ optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) regs->cs |= get_kernel_rpl(); regs->gs = 0; #endif - regs->ip = (unsigned long)op->kp.addr + INT3_SIZE; + regs->ip = (unsigned long)op->kp.addr + INT3_INSN_SIZE; regs->orig_ax = ~0UL; __this_cpu_write(current_kprobe, &op->kp); @@ -179,7 +177,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src, u8 *real) struct insn insn; int len = 0, ret; - while (len < RELATIVEJUMP_SIZE) { + while (len < JMP32_INSN_SIZE) { ret = __copy_instruction(dest + len, src + len, real + len, &insn); if (!ret || !can_boost(&insn, src + len)) return -EINVAL; @@ -271,7 +269,7 @@ static int can_optimize(unsigned long paddr) return 0; /* Check there is enough space for a relative jump. */ - if (size - offset < RELATIVEJUMP_SIZE) + if (size - offset < JMP32_INSN_SIZE) return 0; /* Decode instructions */ @@ -290,15 +288,15 @@ static int can_optimize(unsigned long paddr) kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE); insn_get_length(&insn); /* Another subsystem puts a breakpoint */ - if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION) + if (insn.opcode.bytes[0] == INT3_INSN_OPCODE) return 0; /* Recover address */ insn.kaddr = (void *)addr; insn.next_byte = (void *)(addr + insn.length); /* Check any instructions don't jump into target */ if (insn_is_indirect_jump(&insn) || - insn_jump_into_range(&insn, paddr + INT3_SIZE, - RELATIVE_ADDR_SIZE)) + insn_jump_into_range(&insn, paddr + INT3_INSN_SIZE, + DISP32_SIZE)) return 0; addr += insn.length; } @@ -374,7 +372,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, * Verify if the address gap is in 2GB range, because this uses * a relative jump. */ - rel = (long)slot - (long)op->kp.addr + RELATIVEJUMP_SIZE; + rel = (long)slot - (long)op->kp.addr + JMP32_INSN_SIZE; if (abs(rel) > 0x7fffffff) { ret = -ERANGE; goto err; @@ -401,7 +399,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, /* Set returning jmp instruction at the tail of out-of-line buffer */ synthesize_reljump(buf + len, slot + len, (u8 *)op->kp.addr + op->optinsn.size); - len += RELATIVEJUMP_SIZE; + len += JMP32_INSN_SIZE; /* We have to use text_poke() for instruction buffer because it is RO */ text_poke(slot, buf, len); @@ -416,49 +414,50 @@ err: } /* - * Replace breakpoints (int3) with relative jumps. + * Replace breakpoints (INT3) with relative jumps (JMP.d32). * Caller must call with locking kprobe_mutex and text_mutex. + * + * The caller will have installed a regular kprobe and after that issued + * syncrhonize_rcu_tasks(), this ensures that the instruction(s) that live in + * the 4 bytes after the INT3 are unused and can now be overwritten. */ void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - u8 insn_buff[RELATIVEJUMP_SIZE]; + u8 insn_buff[JMP32_INSN_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + ((long)op->kp.addr + JMP32_INSN_SIZE)); WARN_ON(kprobe_disabled(&op->kp)); /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_INSN_SIZE, + DISP32_SIZE); - insn_buff[0] = RELATIVEJUMP_OPCODE; + insn_buff[0] = JMP32_INSN_OPCODE; *(s32 *)(&insn_buff[1]) = rel; - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL); + text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL); list_del_init(&op->list); } } -/* Replace a relative jump with a breakpoint (int3). */ +/* + * Replace a relative jump (JMP.d32) with a breakpoint (INT3). + * + * After that, we can restore the 4 bytes after the INT3 to undo what + * arch_optimize_kprobes() scribbled. This is safe since those bytes will be + * unused once the INT3 lands. + */ void arch_unoptimize_kprobe(struct optimized_kprobe *op) { - u8 insn_buff[RELATIVEJUMP_SIZE]; - u8 emulate_buff[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - insn_buff[0] = BREAKPOINT_INSTRUCTION; - memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - emulate_buff[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, - emulate_buff); + arch_arm_kprobe(&op->kp); + text_poke(op->kp.addr + INT3_INSN_SIZE, + op->optinsn.copied_insn, DISP32_SIZE); + text_poke_sync(); } /* diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 32ef1ee733b7..81045aabb6f4 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -245,17 +245,13 @@ NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { - enum ctx_state prev_state; - switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code, address); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - prev_state = exception_enter(); kvm_async_pf_task_wait((u32)address, !user_mode(regs)); - exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index b2463fcb20a8..c57e1ca70fd1 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -28,6 +28,89 @@ #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> +#include <asm/pgtable_areas.h> + +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +} + +void load_mm_ldt(struct mm_struct *mm) +{ + struct ldt_struct *ldt; + + /* READ_ONCE synchronizes with smp_store_release */ + ldt = READ_ONCE(mm->context.ldt); + + /* + * Any change to mm->context.ldt is followed by an IPI to all + * CPUs with the mm active. The LDT will not be freed until + * after the IPI is handled by all such CPUs. This means that, + * if the ldt_struct changes before we return, the values we see + * will be safe, and the new values will be loaded before we run + * any user code. + * + * NB: don't try to convert this to use RCU without extreme care. + * We would still need IRQs off, because we don't want to change + * the local LDT after an IPI loaded a newer value than the one + * that we can see. + */ + + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { + clear_LDT(); + } +} + +void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ + /* + * Load the LDT if either the old or new mm had an LDT. + * + * An mm will never go from having an LDT to not having an LDT. Two + * mms never share an LDT, so we don't gain anything by checking to + * see whether the LDT changed. There's also no guarantee that + * prev->context.ldt actually matches LDTR, but, if LDTR is non-NULL, + * then prev->context.ldt will also be non-NULL. + * + * If we really cared, we could optimize the case where prev == next + * and we're exiting lazy mode. Most of the time, if this happens, + * we don't actually need to reload LDTR, but modify_ldt() is mostly + * used by legacy code and emulators where we don't need this level of + * performance. + * + * This uses | instead of || because it generates better code. + */ + if (unlikely((unsigned long)prev->context.ldt | + (unsigned long)next->context.ldt)) + load_mm_ldt(next); + + DEBUG_LOCKS_WARN_ON(preemptible()); +} static void refresh_ldt_segments(void) { diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index e676a9916c49..54c21d6abd5a 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -104,18 +104,22 @@ static int __init nmi_warning_debugfs(void) } fs_initcall(nmi_warning_debugfs); -static void nmi_max_handler(struct irq_work *w) +static void nmi_check_duration(struct nmiaction *action, u64 duration) { - struct nmiaction *a = container_of(w, struct nmiaction, irq_work); + u64 whole_msecs = READ_ONCE(action->max_duration); int remainder_ns, decimal_msecs; - u64 whole_msecs = READ_ONCE(a->max_duration); + + if (duration < nmi_longest_ns || duration < action->max_duration) + return; + + action->max_duration = duration; remainder_ns = do_div(whole_msecs, (1000 * 1000)); decimal_msecs = remainder_ns / 1000; printk_ratelimited(KERN_INFO "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n", - a->handler, whole_msecs, decimal_msecs); + action->handler, whole_msecs, decimal_msecs); } static int nmi_handle(unsigned int type, struct pt_regs *regs) @@ -142,11 +146,7 @@ static int nmi_handle(unsigned int type, struct pt_regs *regs) delta = sched_clock() - delta; trace_nmi_handler(a->handler, (int)delta, thishandled); - if (delta < nmi_longest_ns || delta < a->max_duration) - continue; - - a->max_duration = delta; - irq_work_queue(&a->irq_work); + nmi_check_duration(a, delta); } rcu_read_unlock(); @@ -164,8 +164,6 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action) if (!action->handler) return -EINVAL; - init_irq_work(&action->irq_work, nmi_max_handler); - raw_spin_lock_irqsave(&desc->lock, flags); /* diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 61e93a318983..839b5244e3b7 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -615,12 +615,8 @@ void speculation_ctrl_update_current(void) void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { - struct thread_struct *prev, *next; unsigned long tifp, tifn; - prev = &prev_p->thread; - next = &next_p->thread; - tifn = READ_ONCE(task_thread_info(next_p)->flags); tifp = READ_ONCE(task_thread_info(prev_p)->flags); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 323499f48858..5052ced43373 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -124,7 +124,6 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp) regs->ip = new_ip; regs->sp = new_sp; regs->flags = X86_EFLAGS_IF; - force_iret(); } EXPORT_SYMBOL_GPL(start_thread); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 506d66830d4d..ffd497804dbc 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -394,7 +394,6 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, regs->cs = _cs; regs->ss = _ss; regs->flags = X86_EFLAGS_IF; - force_iret(); } void diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 1daf8f2aa21f..896d74cb5081 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -110,7 +110,7 @@ static void ich_force_enable_hpet(struct pci_dev *dev) } /* use bits 31:14, 16 kB aligned */ - rcba_base = ioremap_nocache(rcba, 0x4000); + rcba_base = ioremap(rcba, 0x4000); if (rcba_base == NULL) { dev_printk(KERN_DEBUG, &dev->dev, "ioremap failed; " "cannot force enable HPET\n"); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cedfe2077a69..2441b64d061f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -2,130 +2,54 @@ /* * Copyright (C) 1995 Linus Torvalds * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - * - * Memory region support - * David Parsons <orc@pell.chi.il.us>, July-August 1999 - * - * Added E820 sanitization routine (removes overlapping memory regions); - * Brian Moyle <bmoyle@mvista.com>, February 2001 - * - * Moved CPU detection code to cpu/${cpu}.c - * Patrick Mochel <mochel@osdl.org>, March 2002 - * - * Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * - */ - -/* - * This file handles the architecture-dependent parts of initialization + * This file contains the setup_arch() code, which handles the architecture-dependent + * parts of early kernel initialization. */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/mmzone.h> -#include <linux/screen_info.h> -#include <linux/ioport.h> -#include <linux/acpi.h> -#include <linux/sfi.h> -#include <linux/apm_bios.h> -#include <linux/initrd.h> -#include <linux/memblock.h> -#include <linux/seq_file.h> #include <linux/console.h> -#include <linux/root_dev.h> -#include <linux/highmem.h> -#include <linux/export.h> +#include <linux/crash_dump.h> +#include <linux/dmi.h> #include <linux/efi.h> -#include <linux/init.h> -#include <linux/edd.h> +#include <linux/init_ohci1394_dma.h> +#include <linux/initrd.h> #include <linux/iscsi_ibft.h> -#include <linux/nodemask.h> -#include <linux/kexec.h> -#include <linux/dmi.h> -#include <linux/pfn.h> +#include <linux/memblock.h> #include <linux/pci.h> -#include <asm/pci-direct.h> -#include <linux/init_ohci1394_dma.h> -#include <linux/kvm_para.h> -#include <linux/dma-contiguous.h> -#include <xen/xen.h> -#include <uapi/linux/mount.h> - -#include <linux/errno.h> -#include <linux/kernel.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/ptrace.h> -#include <linux/user.h> -#include <linux/delay.h> - -#include <linux/kallsyms.h> -#include <linux/cpufreq.h> -#include <linux/dma-mapping.h> -#include <linux/ctype.h> -#include <linux/uaccess.h> - -#include <linux/percpu.h> -#include <linux/crash_dump.h> +#include <linux/root_dev.h> +#include <linux/sfi.h> #include <linux/tboot.h> -#include <linux/jiffies.h> -#include <linux/mem_encrypt.h> -#include <linux/sizes.h> - #include <linux/usb/xhci-dbgp.h> -#include <video/edid.h> -#include <asm/mtrr.h> +#include <uapi/linux/mount.h> + +#include <xen/xen.h> + #include <asm/apic.h> -#include <asm/realmode.h> -#include <asm/e820/api.h> -#include <asm/mpspec.h> -#include <asm/setup.h> -#include <asm/efi.h> -#include <asm/timer.h> -#include <asm/i8259.h> -#include <asm/sections.h> -#include <asm/io_apic.h> -#include <asm/ist.h> -#include <asm/setup_arch.h> #include <asm/bios_ebda.h> -#include <asm/cacheflush.h> -#include <asm/processor.h> #include <asm/bugs.h> -#include <asm/kasan.h> - -#include <asm/vsyscall.h> #include <asm/cpu.h> -#include <asm/desc.h> -#include <asm/dma.h> -#include <asm/iommu.h> +#include <asm/efi.h> #include <asm/gart.h> -#include <asm/mmu_context.h> -#include <asm/proto.h> - -#include <asm/paravirt.h> #include <asm/hypervisor.h> -#include <asm/olpc_ofw.h> - -#include <asm/percpu.h> -#include <asm/topology.h> -#include <asm/apicdef.h> -#include <asm/amd_nb.h> +#include <asm/io_apic.h> +#include <asm/kasan.h> +#include <asm/kaslr.h> #include <asm/mce.h> -#include <asm/alternative.h> +#include <asm/mtrr.h> +#include <asm/realmode.h> +#include <asm/olpc_ofw.h> +#include <asm/pci-direct.h> #include <asm/prom.h> -#include <asm/microcode.h> -#include <asm/kaslr.h> +#include <asm/proto.h> #include <asm/unwind.h> +#include <asm/vsyscall.h> +#include <linux/vmalloc.h> /* - * max_low_pfn_mapped: highest direct mapped pfn under 4GB - * max_pfn_mapped: highest direct mapped pfn over 4GB + * max_low_pfn_mapped: highest directly mapped pfn < 4 GB + * max_pfn_mapped: highest directly mapped pfn > 4 GB * * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are - * represented by pfn_mapped + * represented by pfn_mapped[]. */ unsigned long max_low_pfn_mapped; unsigned long max_pfn_mapped; @@ -135,14 +59,23 @@ RESERVE_BRK(dmi_alloc, 65536); #endif -static __initdata unsigned long _brk_start = (unsigned long)__brk_base; -unsigned long _brk_end = (unsigned long)__brk_base; +/* + * Range of the BSS area. The size of the BSS area is determined + * at link time, with RESERVE_BRK*() facility reserving additional + * chunks. + */ +static __initdata +unsigned long _brk_start = (unsigned long)__brk_base; +unsigned long _brk_end = (unsigned long)__brk_base; struct boot_params boot_params; /* - * Machine setup.. + * These are the four main kernel memory regions, we put them into + * the resource tree so that kdump tools and other debugging tools + * recover it: */ + static struct resource rodata_resource = { .name = "Kernel rodata", .start = 0, @@ -173,16 +106,16 @@ static struct resource bss_resource = { #ifdef CONFIG_X86_32 -/* cpu data as detected by the assembly code in head_32.S */ +/* CPU data as detected by the assembly code in head_32.S */ struct cpuinfo_x86 new_cpu_data; -/* common cpu data for all cpus */ +/* Common CPU data for all CPUs */ struct cpuinfo_x86 boot_cpu_data __read_mostly; EXPORT_SYMBOL(boot_cpu_data); unsigned int def_to_bigsmp; -/* for MCA, but anyone else can use it if they want */ +/* For MCA, but anyone else can use it if they want */ unsigned int machine_id; unsigned int machine_submodel_id; unsigned int BIOS_revision; @@ -468,15 +401,15 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. * - * On 32 bits earlier kernels would limit the kernel to the low 512 MiB + * Earlier 32-bits kernels would limit the kernel to the low 512 MB range * due to mapping restrictions. * - * On 64bit, kdump kernel need be restricted to be under 64TB, which is + * 64-bit kdump kernels need to be restricted to be under 64 TB, which is * the upper limit of system RAM in 4-level paging mode. Since the kdump - * jumping could be from 5-level to 4-level, the jumping will fail if - * kernel is put above 64TB, and there's no way to detect the paging mode - * of the kernel which will be loaded for dumping during the 1st kernel - * bootup. + * jump could be from 5-level paging to 4-level paging, the jump will fail if + * the kernel is put above 64 TB, and during the 1st kernel bootup there's + * no good way to detect the paging mode of the target kernel which will be + * loaded for dumping. */ #ifdef CONFIG_X86_32 # define CRASH_ADDR_LOW_MAX SZ_512M @@ -887,7 +820,7 @@ void __init setup_arch(char **cmdline_p) /* * Note: Quark X1000 CPUs advertise PGE incorrectly and require * a cr3 based tlb flush, so the following __flush_tlb_all() - * will not flush anything because the cpu quirk which clears + * will not flush anything because the CPU quirk which clears * X86_FEATURE_PGE has not been invoked yet. Though due to the * load_cr3() above the TLB has been flushed already. The * quirk is invoked before subsequent calls to __flush_tlb_all() diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 8eb7193e158d..8a29573851a3 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -151,8 +151,6 @@ static int restore_sigcontext(struct pt_regs *regs, err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32)); - force_iret(); - return err; } diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c index 01f0e2263b86..298fc1edd9c9 100644 --- a/arch/x86/kernel/sysfb_simplefb.c +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -90,11 +90,11 @@ __init int create_simplefb(const struct screen_info *si, if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) size <<= 16; length = mode->height * mode->stride; - length = PAGE_ALIGN(length); if (length > size) { printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); return -EINVAL; } + length = PAGE_ALIGN(length); /* setup IORESOURCE_MEM as framebuffer memory */ memset(&res, 0, sizeof(res)); diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4c61f0713832..b89f6ac6a0c0 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -354,7 +354,7 @@ static ssize_t tboot_log_read(struct file *file, char __user *user_buf, size_t c void *kbuf; int ret = -EFAULT; - log_base = ioremap_nocache(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); + log_base = ioremap(TBOOT_SERIAL_LOG_ADDR, TBOOT_SERIAL_LOG_SIZE); if (!log_base) return ret; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 05da6b5b167b..9e6f822922a3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -56,6 +56,8 @@ #include <asm/mpx.h> #include <asm/vm86.h> #include <asm/umip.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -518,11 +520,57 @@ exit_trap: do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, 0, NULL); } -dotraplinkage void -do_general_protection(struct pt_regs *regs, long error_code) +enum kernel_gp_hint { + GP_NO_HINT, + GP_NON_CANONICAL, + GP_CANONICAL +}; + +/* + * When an uncaught #GP occurs, try to determine the memory address accessed by + * the instruction and return that address to the caller. Also, try to figure + * out whether any part of the access to that address was non-canonical. + */ +static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, + unsigned long *addr) { - const char *desc = "general protection fault"; + u8 insn_buf[MAX_INSN_SIZE]; + struct insn insn; + + if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + return GP_NO_HINT; + + kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE); + insn_get_modrm(&insn); + insn_get_sib(&insn); + + *addr = (unsigned long)insn_get_addr_ref(&insn, regs); + if (*addr == -1UL) + return GP_NO_HINT; + +#ifdef CONFIG_X86_64 + /* + * Check that: + * - the operand is not in the kernel half + * - the last byte of the operand is not in the user canonical half + */ + if (*addr < ~__VIRTUAL_MASK && + *addr + insn.opnd_bytes - 1 > __VIRTUAL_MASK) + return GP_NON_CANONICAL; +#endif + + return GP_CANONICAL; +} + +#define GPFSTR "general protection fault" + +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) +{ + char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; + enum kernel_gp_hint hint = GP_NO_HINT; struct task_struct *tsk; + unsigned long gp_addr; + int ret; RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU"); cond_local_irq_enable(regs); @@ -539,48 +587,61 @@ do_general_protection(struct pt_regs *regs, long error_code) } tsk = current; - if (!user_mode(regs)) { - if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) - return; + if (user_mode(regs)) { tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - /* - * To be potentially processing a kprobe fault and to - * trust the result from kprobe_running(), we have to - * be non-preemptible. - */ - if (!preemptible() && kprobe_running() && - kprobe_fault_handler(regs, X86_TRAP_GP)) - return; + show_signal(tsk, SIGSEGV, "", desc, regs, error_code); + force_sig(SIGSEGV); - if (notify_die(DIE_GPF, desc, regs, error_code, - X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP) - die(desc, regs, error_code); return; } + if (fixup_exception(regs, X86_TRAP_GP, error_code, 0)) + return; + tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; - show_signal(tsk, SIGSEGV, "", desc, regs, error_code); + /* + * To be potentially processing a kprobe fault and to trust the result + * from kprobe_running(), we have to be non-preemptible. + */ + if (!preemptible() && + kprobe_running() && + kprobe_fault_handler(regs, X86_TRAP_GP)) + return; + + ret = notify_die(DIE_GPF, desc, regs, error_code, X86_TRAP_GP, SIGSEGV); + if (ret == NOTIFY_STOP) + return; + + if (error_code) + snprintf(desc, sizeof(desc), "segment-related " GPFSTR); + else + hint = get_kernel_gp_address(regs, &gp_addr); + + if (hint != GP_NO_HINT) + snprintf(desc, sizeof(desc), GPFSTR ", %s 0x%lx", + (hint == GP_NON_CANONICAL) ? "probably for non-canonical address" + : "maybe for address", + gp_addr); + + /* + * KASAN is interested only in the non-canonical case, clear it + * otherwise. + */ + if (hint != GP_NON_CANONICAL) + gp_addr = 0; + + die_addr(desc, regs, error_code, gp_addr); - force_sig(SIGSEGV); } NOKPROBE_SYMBOL(do_general_protection); dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { -#ifdef CONFIG_DYNAMIC_FTRACE - /* - * ftrace must be first, everything else may cause a recursive crash. - * See note by declaration of modifying_ftrace_code in ftrace.c - */ - if (unlikely(atomic_read(&modifying_ftrace_code)) && - ftrace_int3_handler(regs)) - return; -#endif if (poke_int3_handler(regs)) return; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index b8acf639abd1..32a818764e03 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -233,7 +233,6 @@ static cycles_t check_tsc_warp(unsigned int timeout) * The measurement runs for 'timeout' msecs: */ end = start + (cycles_t) tsc_khz * timeout; - now = start; for (i = 0; ; i++) { /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 332ae6530fa8..e9cc182aa97e 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -187,6 +187,8 @@ static struct orc_entry *orc_find(unsigned long ip) return orc_ftrace_find(ip); } +#ifdef CONFIG_MODULES + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -229,7 +231,6 @@ static int orc_sort_cmp(const void *_a, const void *_b) return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1; } -#ifdef CONFIG_MODULES void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size, void *_orc, size_t orc_size) { @@ -273,9 +274,11 @@ void __init unwind_init(void) return; } - /* Sort the .orc_unwind and .orc_unwind_ip tables: */ - sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp, - orc_sort_swap); + /* + * Note, the orc_unwind and orc_unwind_ip tables were already + * sorted at build time via the 'sorttable' tool. + * It's ready for binary search straight away, no need to sort it. + */ /* Initialize the fast lookup table: */ lookup_num_blocks = orc_lookup_end - orc_lookup; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index a76c12b38e92..91d55454e702 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -381,7 +381,6 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) mark_screen_rdonly(tsk->mm); memcpy((struct kernel_vm86_regs *)regs, &vm86regs, sizeof(vm86regs)); - force_iret(); return regs->ax; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 3a1a819da137..e3296aa028fe 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -193,12 +193,10 @@ SECTIONS __vvar_beginning_hack = .; /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) \ +#define EMIT_VVAR(name, offset) \ . = __vvar_beginning_hack + offset; \ *(.vvar_ ## name) -#define __VVAR_KERNEL_LDS #include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS #undef EMIT_VVAR /* diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ce89430a7f80..23e25f3034c2 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -20,7 +20,7 @@ #include <asm/irq.h> #include <asm/io_apic.h> #include <asm/hpet.h> -#include <asm/pat.h> +#include <asm/memtype.h> #include <asm/tsc.h> #include <asm/iommu.h> #include <asm/mach_traps.h> |