aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/ptrace.h42
-rw-r--r--arch/x86/kernel/cpu/bugs.c30
-rw-r--r--arch/x86/kernel/cpu/intel_rdt.c7
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c12
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c10
-rw-r--r--arch/x86/kernel/cpu/intel_rdt_rdtgroup.c38
-rw-r--r--arch/x86/kvm/mmu.c8
-rw-r--r--arch/x86/kvm/vmx.c22
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk4
9 files changed, 133 insertions, 40 deletions
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6de1fd3d0097..ee696efec99f 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -237,23 +237,51 @@ static inline int regs_within_kernel_stack(struct pt_regs *regs,
}
/**
+ * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack
+ * @regs: pt_regs which contains kernel stack pointer.
+ * @n: stack entry number.
+ *
+ * regs_get_kernel_stack_nth() returns the address of the @n th entry of the
+ * kernel stack which is specified by @regs. If the @n th entry is NOT in
+ * the kernel stack, this returns NULL.
+ */
+static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n)
+{
+ unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
+
+ addr += n;
+ if (regs_within_kernel_stack(regs, (unsigned long)addr))
+ return addr;
+ else
+ return NULL;
+}
+
+/* To avoid include hell, we can't include uaccess.h */
+extern long probe_kernel_read(void *dst, const void *src, size_t size);
+
+/**
* regs_get_kernel_stack_nth() - get Nth entry of the stack
* @regs: pt_regs which contains kernel stack pointer.
* @n: stack entry number.
*
* regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which
- * is specified by @regs. If the @n th entry is NOT in the kernel stack,
+ * is specified by @regs. If the @n th entry is NOT in the kernel stack
* this returns 0.
*/
static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
unsigned int n)
{
- unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs);
- addr += n;
- if (regs_within_kernel_stack(regs, (unsigned long)addr))
- return *addr;
- else
- return 0;
+ unsigned long *addr;
+ unsigned long val;
+ long ret;
+
+ addr = regs_get_kernel_stack_nth_addr(regs, n);
+ if (addr) {
+ ret = probe_kernel_read(&val, addr, sizeof(val));
+ if (!ret)
+ return val;
+ }
+ return 0;
}
#define arch_has_single_step() (1)
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4684ad7ba793..2d23a448e72d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -39,6 +39,7 @@ static void __init spectre_v2_select_mitigation(void);
static void __init ssb_select_mitigation(void);
static void __init l1tf_select_mitigation(void);
static void __init mds_select_mitigation(void);
+static void __init mds_print_mitigation(void);
static void __init taa_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
@@ -108,6 +109,12 @@ void __init check_bugs(void)
mds_select_mitigation();
taa_select_mitigation();
+ /*
+ * As MDS and TAA mitigations are inter-related, print MDS
+ * mitigation until after TAA mitigation selection is done.
+ */
+ mds_print_mitigation();
+
arch_smt_update();
#ifdef CONFIG_X86_32
@@ -245,6 +252,12 @@ static void __init mds_select_mitigation(void)
(mds_nosmt || cpu_mitigations_auto_nosmt()))
cpu_smt_disable(false);
}
+}
+
+static void __init mds_print_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
+ return;
pr_info("%s\n", mds_strings[mds_mitigation]);
}
@@ -304,8 +317,12 @@ static void __init taa_select_mitigation(void)
return;
}
- /* TAA mitigation is turned off on the cmdline (tsx_async_abort=off) */
- if (taa_mitigation == TAA_MITIGATION_OFF)
+ /*
+ * TAA mitigation via VERW is turned off if both
+ * tsx_async_abort=off and mds=off are specified.
+ */
+ if (taa_mitigation == TAA_MITIGATION_OFF &&
+ mds_mitigation == MDS_MITIGATION_OFF)
goto out;
if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
@@ -339,6 +356,15 @@ static void __init taa_select_mitigation(void)
if (taa_nosmt || cpu_mitigations_auto_nosmt())
cpu_smt_disable(false);
+ /*
+ * Update MDS mitigation, if necessary, as the mds_user_clear is
+ * now enabled for TAA mitigation.
+ */
+ if (mds_mitigation == MDS_MITIGATION_OFF &&
+ boot_cpu_has_bug(X86_BUG_MDS)) {
+ mds_mitigation = MDS_MITIGATION_FULL;
+ mds_select_mitigation();
+ }
out:
pr_info("%s\n", taa_strings[taa_mitigation]);
}
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index cc43c5abd187..b99a04da70f6 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -610,6 +610,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
cancel_delayed_work(&d->cqm_limbo);
}
+ /*
+ * rdt_domain "d" is going to be freed below, so clear
+ * its pointer from pseudo_lock_region struct.
+ */
+ if (d->plr)
+ d->plr->d = NULL;
+
kfree(d->ctrl_val);
kfree(d->mbps_val);
kfree(d->rmid_busy_llc);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 968ace3c6d73..c8b72aff55e0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -408,8 +408,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
for_each_alloc_enabled_rdt_resource(r)
seq_printf(s, "%s:uninitialized\n", r->name);
} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
- rdtgrp->plr->d->id, rdtgrp->plr->cbm);
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ seq_printf(s, "%s:%d=%x\n",
+ rdtgrp->plr->r->name,
+ rdtgrp->plr->d->id,
+ rdtgrp->plr->cbm);
+ }
} else {
closid = rdtgrp->closid;
for_each_alloc_enabled_rdt_resource(r) {
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 912d53939f4f..a999a58ca331 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -1116,6 +1116,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
goto out;
}
+ if (!plr->d) {
+ ret = -ENODEV;
+ goto out;
+ }
+
plr->thread_done = 0;
cpu = cpumask_first(&plr->d->cpu_mask);
if (!cpu_online(cpu)) {
@@ -1429,6 +1434,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
plr = rdtgrp->plr;
+ if (!plr->d) {
+ mutex_unlock(&rdtgroup_mutex);
+ return -ENODEV;
+ }
+
/*
* Task is required to run with affinity to the cpus associated
* with the pseudo-locked region. If this is not the case the task
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index ad64031e82dc..a2d7e6646cce 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
{
struct rdtgroup *rdtgrp;
+ struct cpumask *mask;
int ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (rdtgrp) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
- seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
- cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
- else
+ if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ mask = &rdtgrp->plr->d->cpu_mask;
+ seq_printf(s, is_cpu_list(of) ?
+ "%*pbl\n" : "%*pb\n",
+ cpumask_pr_args(mask));
+ }
+ } else {
seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
cpumask_pr_args(&rdtgrp->cpu_mask));
+ }
} else {
ret = -ENOENT;
}
@@ -1286,6 +1296,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
struct rdt_resource *r;
struct rdt_domain *d;
unsigned int size;
+ int ret = 0;
bool sep;
u32 ctrl;
@@ -1296,11 +1307,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
}
if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
- size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
- rdtgrp->plr->d,
- rdtgrp->plr->cbm);
- seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ if (!rdtgrp->plr->d) {
+ rdt_last_cmd_clear();
+ rdt_last_cmd_puts("Cache domain offline\n");
+ ret = -ENODEV;
+ } else {
+ seq_printf(s, "%*s:", max_name_width,
+ rdtgrp->plr->r->name);
+ size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+ rdtgrp->plr->d,
+ rdtgrp->plr->cbm);
+ seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+ }
goto out;
}
@@ -1330,7 +1348,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
out:
rdtgroup_kn_unlock(of->kn);
- return 0;
+ return ret;
}
/* rdtgroup information files for one cache resource. */
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d7db7608de5f..eddf91a0e363 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3261,7 +3261,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
* here.
*/
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
- level == PT_PAGE_TABLE_LEVEL &&
+ !kvm_is_zone_device_pfn(pfn) && level == PT_PAGE_TABLE_LEVEL &&
PageTransCompoundMap(pfn_to_page(pfn)) &&
!mmu_gfn_lpage_is_disallowed(vcpu, gfn, PT_DIRECTORY_LEVEL)) {
unsigned long mask;
@@ -5709,9 +5709,9 @@ restart:
* the guest, and the guest page table is using 4K page size
* mapping if the indirect sp has level = 1.
*/
- if (sp->role.direct &&
- !kvm_is_reserved_pfn(pfn) &&
- PageTransCompoundMap(pfn_to_page(pfn))) {
+ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
+ !kvm_is_zone_device_pfn(pfn) &&
+ PageTransCompoundMap(pfn_to_page(pfn))) {
drop_spte(kvm, sptep);
need_tlb_flush = 1;
goto restart;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1ab4bb3d6a04..0b7559bf15ea 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2079,7 +2079,7 @@ static int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
return -1;
}
-static inline void __invvpid(int ext, u16 vpid, gva_t gva)
+static inline void __invvpid(unsigned long ext, u16 vpid, gva_t gva)
{
struct {
u64 vpid : 16;
@@ -2094,7 +2094,7 @@ static inline void __invvpid(int ext, u16 vpid, gva_t gva)
BUG_ON(error);
}
-static inline void __invept(int ext, u64 eptp, gpa_t gpa)
+static inline void __invept(unsigned long ext, u64 eptp, gpa_t gpa)
{
struct {
u64 eptp, gpa;
@@ -11013,6 +11013,10 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
vmx->loaded_vmcs = vmcs;
vmx_vcpu_load(vcpu, cpu);
put_cpu();
+
+ vm_entry_controls_reset_shadow(vmx);
+ vm_exit_controls_reset_shadow(vmx);
+ vmx_segment_cache_clear(vmx);
}
/*
@@ -12690,6 +12694,9 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
+ if (from_vmentry && check_vmentry_postreqs(vcpu, vmcs12, exit_qual))
+ return EXIT_REASON_INVALID_STATE;
+
enter_guest_mode(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
@@ -12699,7 +12706,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
- vmx_segment_cache_clear(vmx);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vcpu->arch.tsc_offset += vmcs12->tsc_offset;
@@ -12833,13 +12839,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
*/
skip_emulated_instruction(vcpu);
- ret = check_vmentry_postreqs(vcpu, vmcs12, &exit_qual);
- if (ret) {
- nested_vmx_entry_failure(vcpu, vmcs12,
- EXIT_REASON_INVALID_STATE, exit_qual);
- return 1;
- }
-
/*
* We're finally done with prerequisite checking, and can start with
* the nested entry.
@@ -13530,9 +13529,6 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
}
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- vm_entry_controls_reset_shadow(vmx);
- vm_exit_controls_reset_shadow(vmx);
- vmx_segment_cache_clear(vmx);
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 9166a071484c..1c2832e9f77d 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -69,7 +69,7 @@ BEGIN {
lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
+ lprefix3_expr = "\\((F2|!F3|66&F2)\\)"
lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
@@ -257,7 +257,7 @@ function convert_operands(count,opnd, i,j,imm,mod)
return add_flags(imm, mod)
}
-/^[0-9a-f]+\:/ {
+/^[0-9a-f]+:/ {
if (NR == 1)
next
# get index
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-28 07:28:46 +0000