summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/apic/io_apic.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c9
-rw-r--r--arch/x86/kernel/cpu/common.c2
-rw-r--r--arch/x86/kernel/cpu/intel.c11
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c70
-rw-r--r--arch/x86/kernel/tsc.c1
-rw-r--r--arch/x86/kernel/unwind_frame.c30
7 files changed, 53 insertions, 72 deletions
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 945e512a112a..1e35dd06b090 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1875,6 +1875,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_ack = irq_chip_ack_parent,
.irq_eoi = ioapic_ack_level,
.irq_set_affinity = ioapic_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
@@ -1886,6 +1887,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
.irq_ack = irq_chip_ack_parent,
.irq_eoi = ioapic_ir_ack_level,
.irq_set_affinity = ioapic_set_affinity,
+ .irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SKIP_SET_WAKE,
};
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 1bb253a6ee4d..80e657e89eed 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -309,15 +309,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
- u32 eax, ebx, ecx, edx;
- cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- node_id = ecx & 7;
-
- /* get compute unit information */
- smp_num_siblings = ((ebx >> 8) & 3) + 1;
- c->x86_max_cores /= smp_num_siblings;
- c->cpu_core_id = ebx & 0xff;
+ node_id = cpuid_ecx(0x8000001e) & 7;
/*
* We may have multiple LLCs if L3 caches exist, so check if we
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 3457186275a0..0bdb1ab7d17c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1224,7 +1224,7 @@ static __init int setup_disablecpuid(char *arg)
{
int bit;
- if (get_option(&arg, &bit) && bit < NCAPINTS*32)
+ if (get_option(&arg, &bit) && bit >= 0 && bit < NCAPINTS * 32)
setup_clear_cpu_cap(bit);
else
return 0;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 26eaff4907b2..026c728d6ba7 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -14,6 +14,7 @@
#include <asm/bugs.h>
#include <asm/cpu.h>
#include <asm/intel-family.h>
+#include <asm/microcode_intel.h>
#ifdef CONFIG_X86_64
#include <linux/topology.h>
@@ -78,14 +79,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
(c->x86 == 0x6 && c->x86_model >= 0x0e))
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
- if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64)) {
- unsigned lower_word;
-
- wrmsr(MSR_IA32_UCODE_REV, 0, 0);
- /* Required by the SDM */
- sync_core();
- rdmsr(MSR_IA32_UCODE_REV, lower_word, c->microcode);
- }
+ if (c->x86 >= 6 && !cpu_has(c, X86_FEATURE_IA64))
+ c->microcode = intel_get_microcode_revision();
/*
* Atom erratum AAE44/AAF40/AAG38/AAH41:
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index b624b54912e1..3f329b74e040 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -150,7 +150,7 @@ static struct ucode_patch *__alloc_microcode_buf(void *data, unsigned int size)
{
struct ucode_patch *p;
- p = kzalloc(size, GFP_KERNEL);
+ p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
@@ -368,26 +368,6 @@ next:
return patch;
}
-static void cpuid_1(void)
-{
- /*
- * According to the Intel SDM, Volume 3, 9.11.7:
- *
- * CPUID returns a value in a model specific register in
- * addition to its usual register return values. The
- * semantics of CPUID cause it to deposit an update ID value
- * in the 64-bit model-specific register at address 08BH
- * (IA32_BIOS_SIGN_ID). If no update is present in the
- * processor, the value in the MSR remains unmodified.
- *
- * Use native_cpuid -- this code runs very early and we don't
- * want to mess with paravirt.
- */
- unsigned int eax = 1, ebx, ecx = 0, edx;
-
- native_cpuid(&eax, &ebx, &ecx, &edx);
-}
-
static int collect_cpu_info_early(struct ucode_cpu_info *uci)
{
unsigned int val[2];
@@ -410,15 +390,8 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci)
native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]);
csig.pf = 1 << ((val[1] >> 18) & 7);
}
- native_wrmsrl(MSR_IA32_UCODE_REV, 0);
-
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
- /* get the current revision from MSR 0x8B */
- native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
-
- csig.rev = val[1];
+ csig.rev = intel_get_microcode_revision();
uci->cpu_sig = csig;
uci->valid = 1;
@@ -602,7 +575,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci)
static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
{
struct microcode_intel *mc;
- unsigned int val[2];
+ u32 rev;
mc = uci->mc;
if (!mc)
@@ -610,21 +583,16 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
/* write microcode via MSR 0x79 */
native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
- native_wrmsrl(MSR_IA32_UCODE_REV, 0);
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
-
- /* get the current revision from MSR 0x8B */
- native_rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
- if (val[1] != mc->hdr.rev)
+ rev = intel_get_microcode_revision();
+ if (rev != mc->hdr.rev)
return -1;
#ifdef CONFIG_X86_64
/* Flush global tlb. This is precaution. */
flush_tlb_early();
#endif
- uci->cpu_sig.rev = val[1];
+ uci->cpu_sig.rev = rev;
if (early)
print_ucode(uci);
@@ -804,8 +772,8 @@ static int apply_microcode_intel(int cpu)
struct microcode_intel *mc;
struct ucode_cpu_info *uci;
struct cpuinfo_x86 *c;
- unsigned int val[2];
static int prev_rev;
+ u32 rev;
/* We should bind the task to the CPU */
if (WARN_ON(raw_smp_processor_id() != cpu))
@@ -822,33 +790,28 @@ static int apply_microcode_intel(int cpu)
/* write microcode via MSR 0x79 */
wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
- wrmsrl(MSR_IA32_UCODE_REV, 0);
-
- /* As documented in the SDM: Do a CPUID 1 here */
- cpuid_1();
- /* get the current revision from MSR 0x8B */
- rdmsr(MSR_IA32_UCODE_REV, val[0], val[1]);
+ rev = intel_get_microcode_revision();
- if (val[1] != mc->hdr.rev) {
+ if (rev != mc->hdr.rev) {
pr_err("CPU%d update to revision 0x%x failed\n",
cpu, mc->hdr.rev);
return -1;
}
- if (val[1] != prev_rev) {
+ if (rev != prev_rev) {
pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n",
- val[1],
+ rev,
mc->hdr.date & 0xffff,
mc->hdr.date >> 24,
(mc->hdr.date >> 16) & 0xff);
- prev_rev = val[1];
+ prev_rev = rev;
}
c = &cpu_data(cpu);
- uci->cpu_sig.rev = val[1];
- c->microcode = val[1];
+ uci->cpu_sig.rev = rev;
+ c->microcode = rev;
return 0;
}
@@ -860,7 +823,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
int new_rev = uci->cpu_sig.rev;
unsigned int leftover = size;
- unsigned int curr_mc_size = 0;
+ unsigned int curr_mc_size = 0, new_mc_size = 0;
unsigned int csig, cpf;
while (leftover) {
@@ -901,6 +864,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
vfree(new_mc);
new_rev = mc_header.rev;
new_mc = mc;
+ new_mc_size = mc_size;
mc = NULL; /* trigger new vmalloc */
}
@@ -926,7 +890,7 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
* permanent memory. So it will be loaded early when a CPU is hot added
* or resumes.
*/
- save_mc_for_early(new_mc, curr_mc_size);
+ save_mc_for_early(new_mc, new_mc_size);
pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
cpu, new_rev, uci->cpu_sig.rev);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c8174c815d83..cb60bbe093b2 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -694,6 +694,7 @@ unsigned long native_calibrate_tsc(void)
crystal_khz = 24000; /* 24.0 MHz */
break;
case INTEL_FAM6_SKYLAKE_X:
+ case INTEL_FAM6_ATOM_DENVERTON:
crystal_khz = 25000; /* 25.0 MHz */
break;
case INTEL_FAM6_ATOM_GOLDMONT:
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 4443e499f279..23d15565d02a 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -6,6 +6,21 @@
#define FRAME_HEADER_SIZE (sizeof(long) * 2)
+/*
+ * This disables KASAN checking when reading a value from another task's stack,
+ * since the other task could be running on another CPU and could have poisoned
+ * the stack in the meantime.
+ */
+#define READ_ONCE_TASK_STACK(task, x) \
+({ \
+ unsigned long val; \
+ if (task == current) \
+ val = READ_ONCE(x); \
+ else \
+ val = READ_ONCE_NOCHECK(x); \
+ val; \
+})
+
static void unwind_dump(struct unwind_state *state, unsigned long *sp)
{
static bool dumped_before = false;
@@ -48,7 +63,8 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
if (state->regs && user_mode(state->regs))
return 0;
- addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p,
+ addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
+ addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, addr,
addr_p);
return __kernel_text_address(addr) ? addr : 0;
@@ -162,7 +178,7 @@ bool unwind_next_frame(struct unwind_state *state)
if (state->regs)
next_bp = (unsigned long *)state->regs->bp;
else
- next_bp = (unsigned long *)*state->bp;
+ next_bp = (unsigned long *)READ_ONCE_TASK_STACK(state->task,*state->bp);
/* is the next frame pointer an encoded pointer to pt_regs? */
regs = decode_frame_pointer(next_bp);
@@ -207,6 +223,16 @@ bool unwind_next_frame(struct unwind_state *state)
return true;
bad_address:
+ /*
+ * When unwinding a non-current task, the task might actually be
+ * running on another CPU, in which case it could be modifying its
+ * stack while we're reading it. This is generally not a problem and
+ * can be ignored as long as the caller understands that unwinding
+ * another task will not always succeed.
+ */
+ if (state->task != current)
+ goto the_end;
+
if (state->regs) {
printk_deferred_once(KERN_WARNING
"WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n",
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-14 23:00:22 +0000