diff options
Diffstat (limited to 'arch/x86')
-rw-r--r-- | arch/x86/boot/compressed/head_64.S | 2 | ||||
-rw-r--r-- | arch/x86/events/intel/core.c | 2 | ||||
-rw-r--r-- | arch/x86/events/intel/ds.c | 28 | ||||
-rw-r--r-- | arch/x86/include/asm/intel-family.h | 3 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/amd.c | 7 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 11 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_monitor.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 37 | ||||
-rw-r--r-- | arch/x86/kernel/cpu/microcode/core.c | 13 | ||||
-rw-r--r-- | arch/x86/kernel/ftrace.c | 3 | ||||
-rw-r--r-- | arch/x86/kernel/ptrace.c | 5 | ||||
-rw-r--r-- | arch/x86/kernel/tls.c | 9 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 11 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.h | 3 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_amd.c | 2 | ||||
-rw-r--r-- | arch/x86/kvm/pmu_intel.c | 26 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 6 | ||||
-rw-r--r-- | arch/x86/mm/kasan_init_64.c | 2 | ||||
-rw-r--r-- | arch/x86/mm/kaslr.c | 11 | ||||
-rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 74 | ||||
-rw-r--r-- | arch/x86/pci/irq.c | 10 |
23 files changed, 155 insertions, 125 deletions
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index f105ae8651c9..f62e347862cc 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -602,10 +602,12 @@ ENTRY(trampoline_32bit_src) 3: /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ pushl %ecx + pushl %edx movl $MSR_EFER, %ecx rdmsr btsl $_EFER_LME, %eax wrmsr + popl %edx popl %ecx /* Enable PAE and LA57 (if required) paging modes */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 09c53bcbd497..c8b0bf2b0d5e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3072,7 +3072,7 @@ static int intel_pmu_hw_config(struct perf_event *event) return ret; if (event->attr.precise_ip) { - if (!(event->attr.freq || event->attr.wakeup_events)) { + if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event))) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index b7b01d762d32..e91814d1a27f 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -684,7 +684,7 @@ struct event_constraint intel_core2_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), EVENT_CONSTRAINT_END }; @@ -693,7 +693,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x01), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -701,7 +701,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { struct event_constraint intel_slm_pebs_event_constraints[] = { /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x1), /* Allow all events as PEBS with no flags */ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END @@ -726,7 +726,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -743,7 +743,7 @@ struct event_constraint intel_westmere_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), EVENT_CONSTRAINT_END }; @@ -752,7 +752,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -767,9 +767,9 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -783,9 +783,9 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -806,9 +806,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c2, 0xf), /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -829,9 +829,9 @@ struct event_constraint intel_bdw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108001c0, 0x2), /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 058b1a1994c4..2e38fb82b91d 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -52,6 +52,9 @@ #define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_ICELAKE_X 0x6A +#define INTEL_FAM6_ICELAKE_XEON_D 0x6C +#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D #define INTEL_FAM6_ICELAKE_MOBILE 0x7E /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6a25278e0092..da1f5e78363e 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -819,8 +819,11 @@ static void init_amd_zn(struct cpuinfo_x86 *c) { set_cpu_cap(c, X86_FEATURE_ZEN); - /* Fix erratum 1076: CPB feature bit not being set in CPUID. */ - if (!cpu_has(c, X86_FEATURE_CPB)) + /* + * Fix erratum 1076: CPB feature bit not being set in CPUID. + * Always set it, except when running under a hypervisor. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 9b096f26d1c8..a5cde748cf76 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -821,6 +821,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* + * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper + * bit in the mask to allow guests to use the mitigation even in the + * case where the host does not enable it. + */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + } + + /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -837,7 +847,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); } } diff --git a/arch/x86/kernel/cpu/intel_rdt_monitor.c b/arch/x86/kernel/cpu/intel_rdt_monitor.c index b0f3aed76b75..3d4ec80a6bb9 100644 --- a/arch/x86/kernel/cpu/intel_rdt_monitor.c +++ b/arch/x86/kernel/cpu/intel_rdt_monitor.c @@ -371,6 +371,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) struct list_head *head; struct rdtgroup *entry; + if (!is_mbm_local_enabled()) + return; + r_mba = &rdt_resources_all[RDT_RESOURCE_MBA]; closid = rgrp->closid; rmid = rgrp->mon.rmid; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 643670fb8943..2013699a5c54 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -792,8 +792,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct rdt_resource *r = of->kn->parent->priv; - u32 sw_shareable = 0, hw_shareable = 0; - u32 exclusive = 0, pseudo_locked = 0; + /* + * Use unsigned long even though only 32 bits are used to ensure + * test_bit() is used safely. + */ + unsigned long sw_shareable = 0, hw_shareable = 0; + unsigned long exclusive = 0, pseudo_locked = 0; struct rdt_domain *dom; int i, hwb, swb, excl, psl; enum rdtgrp_mode mode; @@ -838,10 +842,10 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, } for (i = r->cache.cbm_len - 1; i >= 0; i--) { pseudo_locked = dom->plr ? dom->plr->cbm : 0; - hwb = test_bit(i, (unsigned long *)&hw_shareable); - swb = test_bit(i, (unsigned long *)&sw_shareable); - excl = test_bit(i, (unsigned long *)&exclusive); - psl = test_bit(i, (unsigned long *)&pseudo_locked); + hwb = test_bit(i, &hw_shareable); + swb = test_bit(i, &sw_shareable); + excl = test_bit(i, &exclusive); + psl = test_bit(i, &pseudo_locked); if (hwb && swb) seq_putc(seq, 'X'); else if (hwb && !swb) @@ -2320,26 +2324,19 @@ out_destroy: */ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) { - /* - * Convert the u32 _val to an unsigned long required by all the bit - * operations within this function. No more than 32 bits of this - * converted value can be accessed because all bit operations are - * additionally provided with cbm_len that is initialized during - * hardware enumeration using five bits from the EAX register and - * thus never can exceed 32 bits. - */ - unsigned long *val = (unsigned long *)_val; + unsigned long val = *_val; unsigned int cbm_len = r->cache.cbm_len; unsigned long first_bit, zero_bit; - if (*val == 0) + if (val == 0) return; - first_bit = find_first_bit(val, cbm_len); - zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + first_bit = find_first_bit(&val, cbm_len); + zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); /* Clear any remaining bits to ensure contiguous region */ - bitmap_clear(val, zero_bit, cbm_len - zero_bit); + bitmap_clear(&val, zero_bit, cbm_len - zero_bit); + *_val = (u32)val; } /** @@ -2379,7 +2376,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) if (closid_allocated(i) && i != closid) { mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) - break; + continue; used_b |= *ctrl; if (mode == RDT_MODE_SHAREABLE) d->new_ctrl |= *ctrl; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b43ddefd77f4..a96091d44a45 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -790,13 +790,16 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static int mc_cpu_online(unsigned int cpu) +static int mc_cpu_starting(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); microcode_update_cpu(cpu); pr_debug("CPU%d added\n", cpu); + return 0; +} + +static int mc_cpu_online(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); @@ -873,6 +876,8 @@ int __init microcode_init(void) goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); + cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", + mc_cpu_starting, NULL); cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", mc_cpu_online, mc_cpu_down_prep); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 9f033dfd2766..50d309662d78 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -22,6 +22,7 @@ #include <linux/init.h> #include <linux/list.h> #include <linux/module.h> +#include <linux/memory.h> #include <trace/syscall.h> @@ -35,6 +36,7 @@ int ftrace_arch_code_modify_prepare(void) { + mutex_lock(&text_mutex); set_kernel_text_rw(); set_all_modules_text_rw(); return 0; @@ -44,6 +46,7 @@ int ftrace_arch_code_modify_post_process(void) { set_all_modules_text_ro(); set_kernel_text_ro(); + mutex_unlock(&text_mutex); return 0; } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index e2ee403865eb..aeba77881d85 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -24,6 +24,7 @@ #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/context_tracking.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/pgtable.h> @@ -651,9 +652,11 @@ static unsigned long ptrace_get_debugreg(struct task_struct *tsk, int n) { struct thread_struct *thread = &tsk->thread; unsigned long val = 0; + int index = n; if (n < HBP_NUM) { - struct perf_event *bp = thread->ptrace_bps[n]; + struct perf_event *bp = thread->ptrace_bps[index]; + index = array_index_nospec(index, HBP_NUM); if (bp) val = bp->hw.info.address; diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index a5b802a12212..71d3fef1edc9 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -5,6 +5,7 @@ #include <linux/user.h> #include <linux/regset.h> #include <linux/syscalls.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/desc.h> @@ -220,6 +221,7 @@ int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *u_info) { struct user_desc info; + int index; if (idx == -1 && get_user(idx, &u_info->entry_number)) return -EFAULT; @@ -227,8 +229,11 @@ int do_get_thread_area(struct task_struct *p, int idx, if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) return -EINVAL; - fill_user_desc(&info, idx, - &p->thread.tls_array[idx - GDT_ENTRY_TLS_MIN]); + index = idx - GDT_ENTRY_TLS_MIN; + index = array_index_nospec(index, + GDT_ENTRY_TLS_MAX - GDT_ENTRY_TLS_MIN + 1); + + fill_user_desc(&info, idx, &p->thread.tls_array[index]); if (copy_to_user(u_info, &info, sizeof(info))) return -EFAULT; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e4e4147daa93..4b2a399f1df5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2275,7 +2275,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu) struct kvm_lapic *apic = vcpu->arch.apic; u32 ppr; - if (!apic_enabled(apic)) + if (!kvm_apic_hw_enabled(apic)) return -1; __apic_update_ppr(apic, &ppr); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 779ed52047d1..e0f982e35c96 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5386,7 +5386,16 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) struct page *page; int i; - if (tdp_enabled) + /* + * When using PAE paging, the four PDPTEs are treated as 'root' pages, + * while the PDP table is a per-vCPU construct that's allocated at MMU + * creation. When emulating 32-bit mode, cr3 is only 32 bits even on + * x86_64. Therefore we need to allocate the PDP table in the first + * 4GB of memory, which happens to fit the DMA32 zone. Except for + * SVM's 32-bit NPT support, TDP paging doesn't use PAE paging and can + * skip allocating the PDP table. + */ + if (tdp_enabled && kvm_x86_ops->get_tdp_level(vcpu) > PT32E_ROOT_LEVEL) return 0; /* diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 58ead7db71a3..952aebd0a8a3 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -282,20 +282,16 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { bool fast_mode = idx & (1u << 31); struct kvm_pmc *pmc; - u64 ctr_val; + u64 mask = fast_mode ? ~0u : ~0ull; if (is_vmware_backdoor_pmc(idx)) return kvm_pmu_rdpmc_vmware(vcpu, idx, data); - pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx); + pmc = kvm_x86_ops->pmu_ops->msr_idx_to_pmc(vcpu, idx, &mask); if (!pmc) return 1; - ctr_val = pmc_read_counter(pmc); - if (fast_mode) - ctr_val = (u32)ctr_val; - - *data = ctr_val; + *data = pmc_read_counter(pmc) & mask; return 0; } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index ba8898e1a854..22dff661145a 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -25,7 +25,8 @@ struct kvm_pmu_ops { unsigned (*find_fixed_event)(int idx); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); - struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx); + struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, unsigned idx, + u64 *mask); int (*is_valid_msr_idx)(struct kvm_vcpu *vcpu, unsigned idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr, u64 *data); diff --git a/arch/x86/kvm/pmu_amd.c b/arch/x86/kvm/pmu_amd.c index 1495a735b38e..41dff881e0f0 100644 --- a/arch/x86/kvm/pmu_amd.c +++ b/arch/x86/kvm/pmu_amd.c @@ -186,7 +186,7 @@ static int amd_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) } /* idx is the ECX register of RDPMC instruction */ -static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx) +static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *counters; diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c index 5ab4a364348e..c3f103e2b08e 100644 --- a/arch/x86/kvm/pmu_intel.c +++ b/arch/x86/kvm/pmu_intel.c @@ -126,7 +126,7 @@ static int intel_is_valid_msr_idx(struct kvm_vcpu *vcpu, unsigned idx) } static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, - unsigned idx) + unsigned idx, u64 *mask) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); bool fixed = idx & (1u << 30); @@ -138,6 +138,7 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, if (fixed && idx >= pmu->nr_arch_fixed_counters) return NULL; counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; return &counters[idx]; } @@ -183,9 +184,13 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *data) *data = pmu->global_ovf_ctrl; return 0; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, msr))) { - *data = pmc_read_counter(pmc); + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { + u64 val = pmc_read_counter(pmc); + *data = val & pmu->counter_bitmask[KVM_PMC_GP]; + return 0; + } else if ((pmc = get_fixed_pmc(pmu, msr))) { + u64 val = pmc_read_counter(pmc); + *data = val & pmu->counter_bitmask[KVM_PMC_FIXED]; return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { *data = pmc->eventsel; @@ -235,11 +240,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } break; default: - if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || - (pmc = get_fixed_pmc(pmu, msr))) { - if (!msr_info->host_initiated) - data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0))) { + if (msr_info->host_initiated) + pmc->counter = data; + else + pmc->counter = (s32)data; + return 0; + } else if ((pmc = get_fixed_pmc(pmu, msr))) { + pmc->counter = data; return 0; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b2b11374c663..c90545667fd6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1447,7 +1447,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) vcpu->arch.tsc_always_catchup = 1; return 0; } else { - WARN(1, "user requested TSC rate below hardware speed\n"); + pr_warn_ratelimited("user requested TSC rate below hardware speed\n"); return -1; } } @@ -1457,8 +1457,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) user_tsc_khz, tsc_khz); if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { - WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", - user_tsc_khz); + pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); return -1; } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index e3e77527f8df..4bfd14d5da8e 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -198,7 +198,7 @@ static inline p4d_t *early_p4d_offset(pgd_t *pgd, unsigned long addr) if (!pgtable_l5_enabled()) return (p4d_t *)pgd; - p4d = __pa_nodebug(pgd_val(*pgd)) & PTE_PFN_MASK; + p4d = pgd_val(*pgd) & PTE_PFN_MASK; p4d += __START_KERNEL_map - phys_base; return (p4d_t *)p4d + p4d_index(addr); } diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 0988971069c9..bfe769209eae 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -51,7 +51,7 @@ static __initdata struct kaslr_memory_region { } kaslr_regions[] = { { &page_offset_base, 0 }, { &vmalloc_base, 0 }, - { &vmemmap_base, 1 }, + { &vmemmap_base, 0 }, }; /* Get size in bytes used by the memory region */ @@ -77,6 +77,7 @@ void __init kernel_randomize_memory(void) unsigned long rand, memory_tb; struct rnd_state rand_state; unsigned long remain_entropy; + unsigned long vmemmap_size; vaddr_start = pgtable_l5_enabled() ? __PAGE_OFFSET_BASE_L5 : __PAGE_OFFSET_BASE_L4; vaddr = vaddr_start; @@ -108,6 +109,14 @@ void __init kernel_randomize_memory(void) if (memory_tb < kaslr_regions[0].size_tb) kaslr_regions[0].size_tb = memory_tb; + /* + * Calculate the vmemmap region size in TBs, aligned to a TB + * boundary. + */ + vmemmap_size = (kaslr_regions[0].size_tb << (TB_SHIFT - PAGE_SHIFT)) * + sizeof(struct page); + kaslr_regions[2].size_tb = DIV_ROUND_UP(vmemmap_size, 1UL << TB_SHIFT); + /* Calculate entropy available between regions */ remain_entropy = vaddr_end - vaddr_start; for (i = 0; i < ARRAY_SIZE(kaslr_regions); i++) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2580cd2e98b1..a32fc3d99407 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -190,9 +190,7 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define AUX_STACK_SPACE 40 /* Space for RBX, R13, R14, R15, tailcnt */ - -#define PROLOGUE_SIZE 37 +#define PROLOGUE_SIZE 20 /* * Emit x86-64 prologue code for BPF program and check its size. @@ -203,44 +201,19 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) u8 *prog = *pprog; int cnt = 0; - /* push rbp */ - EMIT1(0x55); - - /* mov rbp,rsp */ - EMIT3(0x48, 0x89, 0xE5); - - /* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */ - EMIT3_off32(0x48, 0x81, 0xEC, - round_up(stack_depth, 8) + AUX_STACK_SPACE); - - /* sub rbp, AUX_STACK_SPACE */ - EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE); - - /* mov qword ptr [rbp+0],rbx */ - EMIT4(0x48, 0x89, 0x5D, 0); - /* mov qword ptr [rbp+8],r13 */ - EMIT4(0x4C, 0x89, 0x6D, 8); - /* mov qword ptr [rbp+16],r14 */ - EMIT4(0x4C, 0x89, 0x75, 16); - /* mov qword ptr [rbp+24],r15 */ - EMIT4(0x4C, 0x89, 0x7D, 24); - + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + /* sub rsp, rounded_stack_depth */ + EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8)); + EMIT1(0x53); /* push rbx */ + EMIT2(0x41, 0x55); /* push r13 */ + EMIT2(0x41, 0x56); /* push r14 */ + EMIT2(0x41, 0x57); /* push r15 */ if (!ebpf_from_cbpf) { - /* - * Clear the tail call counter (tail_call_cnt): for eBPF tail - * calls we need to reset the counter to 0. It's done in two - * instructions, resetting RAX register to 0, and moving it - * to the counter location. - */ - - /* xor eax, eax */ - EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp+32], rax */ - EMIT4(0x48, 0x89, 0x45, 32); - + /* zero init tail_call_cnt */ + EMIT2(0x6a, 0x00); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); } - *pprog = prog; } @@ -285,13 +258,13 @@ static void emit_bpf_tail_call(u8 **pprog) * if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ + EMIT2_off32(0x8B, 0x85, -36 - MAX_BPF_STACK); /* mov eax, dword ptr [rbp - 548] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ #define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE) EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, 36); /* mov dword ptr [rbp + 36], eax */ + EMIT2_off32(0x89, 0x85, -36 - MAX_BPF_STACK); /* mov dword ptr [rbp -548], eax */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ @@ -1006,19 +979,14 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; - /* mov rbx, qword ptr [rbp+0] */ - EMIT4(0x48, 0x8B, 0x5D, 0); - /* mov r13, qword ptr [rbp+8] */ - EMIT4(0x4C, 0x8B, 0x6D, 8); - /* mov r14, qword ptr [rbp+16] */ - EMIT4(0x4C, 0x8B, 0x75, 16); - /* mov r15, qword ptr [rbp+24] */ - EMIT4(0x4C, 0x8B, 0x7D, 24); - - /* add rbp, AUX_STACK_SPACE */ - EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE); - EMIT1(0xC9); /* leave */ - EMIT1(0xC3); /* ret */ + if (!bpf_prog_was_classic(bpf_prog)) + EMIT1(0x5B); /* get rid of tail_call_cnt */ + EMIT2(0x41, 0x5F); /* pop r15 */ + EMIT2(0x41, 0x5E); /* pop r14 */ + EMIT2(0x41, 0x5D); /* pop r13 */ + EMIT1(0x5B); /* pop rbx */ + EMIT1(0xC9); /* leave */ + EMIT1(0xC3); /* ret */ break; default: diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 52e55108404e..d3a73f9335e1 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1119,6 +1119,8 @@ static const struct dmi_system_id pciirq_dmi_table[] __initconst = { void __init pcibios_irq_init(void) { + struct irq_routing_table *rtable = NULL; + DBG(KERN_DEBUG "PCI: IRQ init\n"); if (raw_pci_ops == NULL) @@ -1129,8 +1131,10 @@ void __init pcibios_irq_init(void) pirq_table = pirq_find_routing_table(); #ifdef CONFIG_PCI_BIOS - if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) + if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) { pirq_table = pcibios_get_irq_routing_table(); + rtable = pirq_table; + } #endif if (pirq_table) { pirq_peer_trick(); @@ -1145,8 +1149,10 @@ void __init pcibios_irq_init(void) * If we're using the I/O APIC, avoid using the PCI IRQ * routing table */ - if (io_apic_assign_pci_irqs) + if (io_apic_assign_pci_irqs) { + kfree(rtable); pirq_table = NULL; + } } x86_init.pci.fixup_irqs(); |