aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S12
-rw-r--r--arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S12
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/kernel/cpu/mcheck/dev-mcelog.c121
-rw-r--r--arch/x86/kernel/kvmclock.c2
-rw-r--r--arch/x86/kernel/module.c13
-rw-r--r--arch/x86/kvm/lapic.c5
-rw-r--r--arch/x86/kvm/vmx.c3
-rw-r--r--arch/x86/mm/mem_encrypt.c2
-rw-r--r--arch/x86/mm/tlb.c17
10 files changed, 75 insertions, 114 deletions
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
index 93b945597ecf..7cfba738f104 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha1-mb/sha1_mb_mgr_flush_avx2.S
@@ -157,8 +157,8 @@ LABEL skip_ %I
.endr
# Find min length
- vmovdqa _lens+0*16(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
+ vmovdqu _lens+0*16(state), %xmm0
+ vmovdqu _lens+1*16(state), %xmm1
vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
@@ -178,8 +178,8 @@ LABEL skip_ %I
vpsubd %xmm2, %xmm0, %xmm0
vpsubd %xmm2, %xmm1, %xmm1
- vmovdqa %xmm0, _lens+0*16(state)
- vmovdqa %xmm1, _lens+1*16(state)
+ vmovdqu %xmm0, _lens+0*16(state)
+ vmovdqu %xmm1, _lens+1*16(state)
# "state" and "args" are the same address, arg1
# len is arg2
@@ -235,8 +235,8 @@ ENTRY(sha1_mb_mgr_get_comp_job_avx2)
jc .return_null
# Find min length
- vmovdqa _lens(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
+ vmovdqu _lens(state), %xmm0
+ vmovdqu _lens+1*16(state), %xmm1
vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index 8fe6338bcc84..16c4ccb1f154 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -155,8 +155,8 @@ LABEL skip_ %I
.endr
# Find min length
- vmovdqa _lens+0*16(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
+ vmovdqu _lens+0*16(state), %xmm0
+ vmovdqu _lens+1*16(state), %xmm1
vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
@@ -176,8 +176,8 @@ LABEL skip_ %I
vpsubd %xmm2, %xmm0, %xmm0
vpsubd %xmm2, %xmm1, %xmm1
- vmovdqa %xmm0, _lens+0*16(state)
- vmovdqa %xmm1, _lens+1*16(state)
+ vmovdqu %xmm0, _lens+0*16(state)
+ vmovdqu %xmm1, _lens+1*16(state)
# "state" and "args" are the same address, arg1
# len is arg2
@@ -234,8 +234,8 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
jc .return_null
# Find min length
- vmovdqa _lens(state), %xmm0
- vmovdqa _lens+1*16(state), %xmm1
+ vmovdqu _lens(state), %xmm0
+ vmovdqu _lens+1*16(state), %xmm1
vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 72d867f6b518..8d0ec9df1cbe 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -150,6 +150,8 @@ static inline void disable_acpi(void) { }
extern int x86_acpi_numa_init(void);
#endif /* CONFIG_ACPI_NUMA */
+#define acpi_unlazy_tlb(x) leave_mm(x)
+
#ifdef CONFIG_ACPI_APEI
static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
{
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 10cec43aac38..7f85b76f43bc 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -24,14 +24,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
static char mce_helper[128];
static char *mce_helper_argv[2] = { mce_helper, NULL };
-#define mce_log_get_idx_check(p) \
-({ \
- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \
- !lockdep_is_held(&mce_chrdev_read_mutex), \
- "suspicious mce_log_get_idx_check() usage"); \
- smp_load_acquire(&(p)); \
-})
-
/*
* Lockless MCE logging infrastructure.
* This avoids deadlocks on printk locks without having to break locks. Also
@@ -53,43 +45,32 @@ static int dev_mce_log(struct notifier_block *nb, unsigned long val,
void *data)
{
struct mce *mce = (struct mce *)data;
- unsigned int next, entry;
-
- wmb();
- for (;;) {
- entry = mce_log_get_idx_check(mcelog.next);
- for (;;) {
-
- /*
- * When the buffer fills up discard new entries.
- * Assume that the earlier errors are the more
- * interesting ones:
- */
- if (entry >= MCE_LOG_LEN) {
- set_bit(MCE_OVERFLOW,
- (unsigned long *)&mcelog.flags);
- return NOTIFY_OK;
- }
- /* Old left over entry. Skip: */
- if (mcelog.entry[entry].finished) {
- entry++;
- continue;
- }
- break;
- }
- smp_rmb();
- next = entry + 1;
- if (cmpxchg(&mcelog.next, entry, next) == entry)
- break;
+ unsigned int entry;
+
+ mutex_lock(&mce_chrdev_read_mutex);
+
+ entry = mcelog.next;
+
+ /*
+ * When the buffer fills up discard new entries. Assume that the
+ * earlier errors are the more interesting ones:
+ */
+ if (entry >= MCE_LOG_LEN) {
+ set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog.flags);
+ goto unlock;
}
+
+ mcelog.next = entry + 1;
+
memcpy(mcelog.entry + entry, mce, sizeof(struct mce));
- wmb();
mcelog.entry[entry].finished = 1;
- wmb();
/* wake processes polling /dev/mcelog */
wake_up_interruptible(&mce_chrdev_wait);
+unlock:
+ mutex_unlock(&mce_chrdev_read_mutex);
+
return NOTIFY_OK;
}
@@ -177,13 +158,6 @@ static int mce_chrdev_release(struct inode *inode, struct file *file)
return 0;
}
-static void collect_tscs(void *data)
-{
- unsigned long *cpu_tsc = (unsigned long *)data;
-
- cpu_tsc[smp_processor_id()] = rdtsc();
-}
-
static int mce_apei_read_done;
/* Collect MCE record of previous boot in persistent storage via APEI ERST. */
@@ -231,14 +205,9 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
size_t usize, loff_t *off)
{
char __user *buf = ubuf;
- unsigned long *cpu_tsc;
- unsigned prev, next;
+ unsigned next;
int i, err;
- cpu_tsc = kmalloc(nr_cpu_ids * sizeof(long), GFP_KERNEL);
- if (!cpu_tsc)
- return -ENOMEM;
-
mutex_lock(&mce_chrdev_read_mutex);
if (!mce_apei_read_done) {
@@ -247,65 +216,29 @@ static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf,
goto out;
}
- next = mce_log_get_idx_check(mcelog.next);
-
/* Only supports full reads right now */
err = -EINVAL;
if (*off != 0 || usize < MCE_LOG_LEN*sizeof(struct mce))
goto out;
+ next = mcelog.next;
err = 0;
- prev = 0;
- do {
- for (i = prev; i < next; i++) {
- unsigned long start = jiffies;
- struct mce *m = &mcelog.entry[i];
-
- while (!m->finished) {
- if (time_after_eq(jiffies, start + 2)) {
- memset(m, 0, sizeof(*m));
- goto timeout;
- }
- cpu_relax();
- }
- smp_rmb();
- err |= copy_to_user(buf, m, sizeof(*m));
- buf += sizeof(*m);
-timeout:
- ;
- }
-
- memset(mcelog.entry + prev, 0,
- (next - prev) * sizeof(struct mce));
- prev = next;
- next = cmpxchg(&mcelog.next, prev, 0);
- } while (next != prev);
-
- synchronize_sched();
- /*
- * Collect entries that were still getting written before the
- * synchronize.
- */
- on_each_cpu(collect_tscs, cpu_tsc, 1);
-
- for (i = next; i < MCE_LOG_LEN; i++) {
+ for (i = 0; i < next; i++) {
struct mce *m = &mcelog.entry[i];
- if (m->finished && m->tsc < cpu_tsc[m->cpu]) {
- err |= copy_to_user(buf, m, sizeof(*m));
- smp_rmb();
- buf += sizeof(*m);
- memset(m, 0, sizeof(*m));
- }
+ err |= copy_to_user(buf, m, sizeof(*m));
+ buf += sizeof(*m);
}
+ memset(mcelog.entry, 0, next * sizeof(struct mce));
+ mcelog.next = 0;
+
if (err)
err = -EFAULT;
out:
mutex_unlock(&mce_chrdev_read_mutex);
- kfree(cpu_tsc);
return err ? err : buf - ubuf;
}
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d88967659098..5b609e28ce3f 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -79,7 +79,7 @@ static void kvm_get_wallclock(struct timespec *now)
static int kvm_set_wallclock(const struct timespec *now)
{
- return -1;
+ return -ENODEV;
}
static u64 kvm_clock_read(void)
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 62e7d70aadd5..da0c160e5589 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -172,19 +172,27 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
case R_X86_64_NONE:
break;
case R_X86_64_64:
+ if (*(u64 *)loc != 0)
+ goto invalid_relocation;
*(u64 *)loc = val;
break;
case R_X86_64_32:
+ if (*(u32 *)loc != 0)
+ goto invalid_relocation;
*(u32 *)loc = val;
if (val != *(u32 *)loc)
goto overflow;
break;
case R_X86_64_32S:
+ if (*(s32 *)loc != 0)
+ goto invalid_relocation;
*(s32 *)loc = val;
if ((s64)val != *(s32 *)loc)
goto overflow;
break;
case R_X86_64_PC32:
+ if (*(u32 *)loc != 0)
+ goto invalid_relocation;
val -= (u64)loc;
*(u32 *)loc = val;
#if 0
@@ -200,6 +208,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
}
return 0;
+invalid_relocation:
+ pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
+ (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
+ return -ENOEXEC;
+
overflow:
pr_err("overflow in relocation type %d val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), val);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 69c5612be786..36c90d631096 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1992,6 +1992,11 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
vcpu->arch.pv_eoi.msr_val = 0;
apic_update_ppr(apic);
+ if (vcpu->arch.apicv_active) {
+ kvm_x86_ops->apicv_post_state_restore(vcpu);
+ kvm_x86_ops->hwapic_irr_update(vcpu, -1);
+ kvm_x86_ops->hwapic_isr_update(vcpu, -1);
+ }
vcpu->arch.apic_arb_prio = 0;
vcpu->arch.apic_attention = 0;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 95a01609d7ee..a6f4f095f8f4 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5619,9 +5619,6 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
- if (kvm_vcpu_apicv_active(vcpu))
- memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
-
if (vmx->vpid != 0)
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 16c5f37933a2..0286327e65fa 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -40,7 +40,7 @@ static char sme_cmdline_off[] __initdata = "off";
* section is later cleared.
*/
u64 sme_me_mask __section(.data) = 0;
-EXPORT_SYMBOL_GPL(sme_me_mask);
+EXPORT_SYMBOL(sme_me_mask);
/* Buffer used for early in-place encryption by BSP, no locking needed */
static char sme_early_buffer[PAGE_SIZE] __aligned(PAGE_SIZE);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0f3d0cea4d00..3118392cdf75 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -85,6 +85,7 @@ void leave_mm(int cpu)
switch_mm(NULL, &init_mm, NULL);
}
+EXPORT_SYMBOL_GPL(leave_mm);
void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
@@ -195,12 +196,22 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
write_cr3(build_cr3(next, new_asid));
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH,
- TLB_FLUSH_ALL);
+
+ /*
+ * NB: This gets called via leave_mm() in the idle path
+ * where RCU functions differently. Tracing normally
+ * uses RCU, so we need to use the _rcuidle variant.
+ *
+ * (There is no good reason for this. The idle code should
+ * be rearranged to call this before rcu_idle_enter().)
+ */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
write_cr3(build_cr3_noflush(next, new_asid));
- trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
+
+ /* See above wrt _rcuidle. */
+ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
this_cpu_write(cpu_tlbstate.loaded_mm, next);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.