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/bugs.c12
-rw-r--r--arch/x86/kernel/cpu/common.c30
-rw-r--r--arch/x86/kernel/cpu/intel.c7
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c26
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c10
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c161
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c58
-rw-r--r--arch/x86/kernel/head_64.S2
-rw-r--r--arch/x86/kernel/ioport.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c10
-rw-r--r--arch/x86/kernel/kvm.c20
-rw-r--r--arch/x86/kernel/setup.c17
-rw-r--r--arch/x86/kernel/setup_percpu.c17
-rw-r--r--arch/x86/kernel/signal_compat.c65
-rw-r--r--arch/x86/kernel/unwind_orc.c3
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
17 files changed, 346 insertions, 98 deletions
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 8ad2e410974f..7c5538769f7e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1603,7 +1603,7 @@ static void __init delay_with_tsc(void)
do {
rep_nop();
now = rdtsc();
- } while ((now - start) < 40000000000UL / HZ &&
+ } while ((now - start) < 40000000000ULL / HZ &&
time_before_eq(jiffies, end));
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d71c8b54b696..bfca937bdcc3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -300,6 +300,15 @@ retpoline_auto:
setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n");
}
+
+ /*
+ * Retpoline means the kernel is safe because it has no indirect
+ * branches. But firmware isn't, so use IBRS to protect that.
+ */
+ if (boot_cpu_has(X86_FEATURE_IBRS)) {
+ setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
+ pr_info("Enabling Restricted Speculation for firmware calls\n");
+ }
}
#undef pr_fmt
@@ -326,8 +335,9 @@ ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, c
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
return sprintf(buf, "Not affected\n");
- return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
+ return sprintf(buf, "%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
spectre_v2_module_string());
}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 824aee0117bb..348cf4821240 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1749,3 +1749,33 @@ static int __init init_cpu_syscore(void)
return 0;
}
core_initcall(init_cpu_syscore);
+
+/*
+ * The microcode loader calls this upon late microcode load to recheck features,
+ * only when microcode has been updated. Caller holds microcode_mutex and CPU
+ * hotplug lock.
+ */
+void microcode_check(void)
+{
+ struct cpuinfo_x86 info;
+
+ perf_check_microcode();
+
+ /* Reload CPUID max function as it might've changed. */
+ info.cpuid_level = cpuid_eax(0);
+
+ /*
+ * Copy all capability leafs to pick up the synthetic ones so that
+ * memcmp() below doesn't fail on that. The ones coming from CPUID will
+ * get overwritten in get_cpu_cap().
+ */
+ memcpy(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability));
+
+ get_cpu_cap(&info);
+
+ if (!memcmp(&info.x86_capability, &boot_cpu_data.x86_capability, sizeof(info.x86_capability)))
+ return;
+
+ pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
+ pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
+}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index d19e903214b4..4aa9fd379390 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -144,6 +144,13 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c)
{
int i;
+ /*
+ * We know that the hypervisor lie to us on the microcode version so
+ * we may as well hope that it is running the correct version.
+ */
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return false;
+
for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) {
if (c->x86_model == spectre_bad_microcodes[i].model &&
c->x86_stepping == spectre_bad_microcodes[i].stepping)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8ff94d1e2dce..466f47301334 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -56,6 +56,9 @@
static DEFINE_MUTEX(mce_log_mutex);
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
@@ -130,6 +133,8 @@ void mce_setup(struct mce *m)
if (this_cpu_has(X86_FEATURE_INTEL_PPIN))
rdmsrl(MSR_PPIN, m->ppin);
+
+ m->microcode = boot_cpu_data.microcode;
}
DEFINE_PER_CPU(struct mce, injectm);
@@ -262,7 +267,7 @@ static void __print_mce(struct mce *m)
*/
pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n",
m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid,
- cpu_data(m->extcpu).microcode);
+ m->microcode);
}
static void print_mce(struct mce *m)
@@ -2086,6 +2091,7 @@ static ssize_t set_ignore_ce(struct device *s,
if (kstrtou64(buf, 0, &new) < 0)
return -EINVAL;
+ mutex_lock(&mce_sysfs_mutex);
if (mca_cfg.ignore_ce ^ !!new) {
if (new) {
/* disable ce features */
@@ -2098,6 +2104,8 @@ static ssize_t set_ignore_ce(struct device *s,
on_each_cpu(mce_enable_ce, (void *)1, 1);
}
}
+ mutex_unlock(&mce_sysfs_mutex);
+
return size;
}
@@ -2110,6 +2118,7 @@ static ssize_t set_cmci_disabled(struct device *s,
if (kstrtou64(buf, 0, &new) < 0)
return -EINVAL;
+ mutex_lock(&mce_sysfs_mutex);
if (mca_cfg.cmci_disabled ^ !!new) {
if (new) {
/* disable cmci */
@@ -2121,6 +2130,8 @@ static ssize_t set_cmci_disabled(struct device *s,
on_each_cpu(mce_enable_ce, NULL, 1);
}
}
+ mutex_unlock(&mce_sysfs_mutex);
+
return size;
}
@@ -2128,8 +2139,19 @@ static ssize_t store_int_with_restart(struct device *s,
struct device_attribute *attr,
const char *buf, size_t size)
{
- ssize_t ret = device_store_int(s, attr, buf, size);
+ unsigned long old_check_interval = check_interval;
+ ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+ if (check_interval == old_check_interval)
+ return ret;
+
+ if (check_interval < 1)
+ check_interval = 1;
+
+ mutex_lock(&mce_sysfs_mutex);
mce_restart();
+ mutex_unlock(&mce_sysfs_mutex);
+
return ret;
}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 330b8462d426..a998e1a7d46f 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -498,7 +498,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
return patch_size;
}
-static int apply_microcode_amd(int cpu)
+static enum ucode_state apply_microcode_amd(int cpu)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
struct microcode_amd *mc_amd;
@@ -512,7 +512,7 @@ static int apply_microcode_amd(int cpu)
p = find_patch(cpu);
if (!p)
- return 0;
+ return UCODE_NFOUND;
mc_amd = p->data;
uci->mc = p->data;
@@ -523,13 +523,13 @@ static int apply_microcode_amd(int cpu)
if (rev >= mc_amd->hdr.patch_id) {
c->microcode = rev;
uci->cpu_sig.rev = rev;
- return 0;
+ return UCODE_OK;
}
if (__apply_microcode_amd(mc_amd)) {
pr_err("CPU%d: update failed for patch_level=0x%08x\n",
cpu, mc_amd->hdr.patch_id);
- return -1;
+ return UCODE_ERROR;
}
pr_info("CPU%d: new patch_level=0x%08x\n", cpu,
mc_amd->hdr.patch_id);
@@ -537,7 +537,7 @@ static int apply_microcode_amd(int cpu)
uci->cpu_sig.rev = mc_amd->hdr.patch_id;
c->microcode = mc_amd->hdr.patch_id;
- return 0;
+ return UCODE_UPDATED;
}
static int install_equiv_cpu_table(const u8 *buf)
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 319dd65f98a2..70ecbc8099c9 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -22,13 +22,16 @@
#define pr_fmt(fmt) "microcode: " fmt
#include <linux/platform_device.h>
+#include <linux/stop_machine.h>
#include <linux/syscore_ops.h>
#include <linux/miscdevice.h>
#include <linux/capability.h>
#include <linux/firmware.h>
#include <linux/kernel.h>
+#include <linux/delay.h>
#include <linux/mutex.h>
#include <linux/cpu.h>
+#include <linux/nmi.h>
#include <linux/fs.h>
#include <linux/mm.h>
@@ -64,6 +67,11 @@ LIST_HEAD(microcode_cache);
*/
static DEFINE_MUTEX(microcode_mutex);
+/*
+ * Serialize late loading so that CPUs get updated one-by-one.
+ */
+static DEFINE_SPINLOCK(update_lock);
+
struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
struct cpu_info_ctx {
@@ -373,26 +381,23 @@ static int collect_cpu_info(int cpu)
return ret;
}
-struct apply_microcode_ctx {
- int err;
-};
-
static void apply_microcode_local(void *arg)
{
- struct apply_microcode_ctx *ctx = arg;
+ enum ucode_state *err = arg;
- ctx->err = microcode_ops->apply_microcode(smp_processor_id());
+ *err = microcode_ops->apply_microcode(smp_processor_id());
}
static int apply_microcode_on_target(int cpu)
{
- struct apply_microcode_ctx ctx = { .err = 0 };
+ enum ucode_state err;
int ret;
- ret = smp_call_function_single(cpu, apply_microcode_local, &ctx, 1);
- if (!ret)
- ret = ctx.err;
-
+ ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1);
+ if (!ret) {
+ if (err == UCODE_ERROR)
+ ret = 1;
+ }
return ret;
}
@@ -489,31 +494,110 @@ static void __exit microcode_dev_exit(void)
/* fake device for request_firmware */
static struct platform_device *microcode_pdev;
-static int reload_for_cpu(int cpu)
+/*
+ * Late loading dance. Why the heavy-handed stomp_machine effort?
+ *
+ * - HT siblings must be idle and not execute other code while the other sibling
+ * is loading microcode in order to avoid any negative interactions caused by
+ * the loading.
+ *
+ * - In addition, microcode update on the cores must be serialized until this
+ * requirement can be relaxed in the future. Right now, this is conservative
+ * and good.
+ */
+#define SPINUNIT 100 /* 100 nsec */
+
+static int check_online_cpus(void)
{
- struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
- enum ucode_state ustate;
- int err = 0;
+ if (num_online_cpus() == num_present_cpus())
+ return 0;
- if (!uci->valid)
- return err;
+ pr_err("Not all CPUs online, aborting microcode update.\n");
- ustate = microcode_ops->request_microcode_fw(cpu, &microcode_pdev->dev, true);
- if (ustate == UCODE_OK)
- apply_microcode_on_target(cpu);
- else
- if (ustate == UCODE_ERROR)
- err = -EINVAL;
- return err;
+ return -EINVAL;
+}
+
+static atomic_t late_cpus;
+
+/*
+ * Returns:
+ * < 0 - on error
+ * 0 - no update done
+ * 1 - microcode was updated
+ */
+static int __reload_late(void *info)
+{
+ unsigned int timeout = NSEC_PER_SEC;
+ int all_cpus = num_online_cpus();
+ int cpu = smp_processor_id();
+ enum ucode_state err;
+ int ret = 0;
+
+ atomic_dec(&late_cpus);
+
+ /*
+ * Wait for all CPUs to arrive. A load will not be attempted unless all
+ * CPUs show up.
+ * */
+ while (atomic_read(&late_cpus)) {
+ if (timeout < SPINUNIT) {
+ pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n",
+ atomic_read(&late_cpus));
+ return -1;
+ }
+
+ ndelay(SPINUNIT);
+ timeout -= SPINUNIT;
+
+ touch_nmi_watchdog();
+ }
+
+ spin_lock(&update_lock);
+ apply_microcode_local(&err);
+ spin_unlock(&update_lock);
+
+ if (err > UCODE_NFOUND) {
+ pr_warn("Error reloading microcode on CPU %d\n", cpu);
+ ret = -1;
+ } else if (err == UCODE_UPDATED) {
+ ret = 1;
+ }
+
+ atomic_inc(&late_cpus);
+
+ while (atomic_read(&late_cpus) != all_cpus)
+ cpu_relax();
+
+ return ret;
+}
+
+/*
+ * Reload microcode late on all CPUs. Wait for a sec until they
+ * all gather together.
+ */
+static int microcode_reload_late(void)
+{
+ int ret;
+
+ atomic_set(&late_cpus, num_online_cpus());
+
+ ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask);
+ if (ret < 0)
+ return ret;
+ else if (ret > 0)
+ microcode_check();
+
+ return ret;
}
static ssize_t reload_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t size)
{
+ enum ucode_state tmp_ret = UCODE_OK;
+ int bsp = boot_cpu_data.cpu_index;
unsigned long val;
- int cpu;
- ssize_t ret = 0, tmp_ret;
+ ssize_t ret = 0;
ret = kstrtoul(buf, 0, &val);
if (ret)
@@ -522,23 +606,24 @@ static ssize_t reload_store(struct device *dev,
if (val != 1)
return size;
+ tmp_ret = microcode_ops->request_microcode_fw(bsp, &microcode_pdev->dev, true);
+ if (tmp_ret != UCODE_OK)
+ return size;
+
get_online_cpus();
- mutex_lock(&microcode_mutex);
- for_each_online_cpu(cpu) {
- tmp_ret = reload_for_cpu(cpu);
- if (tmp_ret != 0)
- pr_warn("Error reloading microcode on CPU %d\n", cpu);
- /* save retval of the first encountered reload error */
- if (!ret)
- ret = tmp_ret;
- }
- if (!ret)
- perf_check_microcode();
+ ret = check_online_cpus();
+ if (ret)
+ goto put;
+
+ mutex_lock(&microcode_mutex);
+ ret = microcode_reload_late();
mutex_unlock(&microcode_mutex);
+
+put:
put_online_cpus();
- if (!ret)
+ if (ret >= 0)
ret = size;
return ret;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a15db2b4e0d6..2aded9db1d42 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -589,6 +589,23 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
if (!mc)
return 0;
+ /*
+ * Save us the MSR write below - which is a particular expensive
+ * operation - when the other hyperthread has updated the microcode
+ * already.
+ */
+ rev = intel_get_microcode_revision();
+ if (rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = rev;
+ return UCODE_OK;
+ }
+
+ /*
+ * Writeback and invalidate caches before updating microcode to avoid
+ * internal issues depending on what the microcode is updating.
+ */
+ native_wbinvd();
+
/* write microcode via MSR 0x79 */
native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
@@ -772,27 +789,44 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
return 0;
}
-static int apply_microcode_intel(int cpu)
+static enum ucode_state apply_microcode_intel(int cpu)
{
+ struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
struct microcode_intel *mc;
- struct ucode_cpu_info *uci;
- struct cpuinfo_x86 *c;
static int prev_rev;
u32 rev;
/* We should bind the task to the CPU */
if (WARN_ON(raw_smp_processor_id() != cpu))
- return -1;
+ return UCODE_ERROR;
- uci = ucode_cpu_info + cpu;
- mc = uci->mc;
+ /* Look for a newer patch in our cache: */
+ mc = find_patch(uci);
if (!mc) {
- /* Look for a newer patch in our cache: */
- mc = find_patch(uci);
+ mc = uci->mc;
if (!mc)
- return 0;
+ return UCODE_NFOUND;
}
+ /*
+ * Save us the MSR write below - which is a particular expensive
+ * operation - when the other hyperthread has updated the microcode
+ * already.
+ */
+ rev = intel_get_microcode_revision();
+ if (rev >= mc->hdr.rev) {
+ uci->cpu_sig.rev = rev;
+ c->microcode = rev;
+ return UCODE_OK;
+ }
+
+ /*
+ * Writeback and invalidate caches before updating microcode to avoid
+ * internal issues depending on what the microcode is updating.
+ */
+ native_wbinvd();
+
/* write microcode via MSR 0x79 */
wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
@@ -801,7 +835,7 @@ static int apply_microcode_intel(int cpu)
if (rev != mc->hdr.rev) {
pr_err("CPU%d update to revision 0x%x failed\n",
cpu, mc->hdr.rev);
- return -1;
+ return UCODE_ERROR;
}
if (rev != prev_rev) {
@@ -813,12 +847,10 @@ static int apply_microcode_intel(int cpu)
prev_rev = rev;
}
- c = &cpu_data(cpu);
-
uci->cpu_sig.rev = rev;
c->microcode = rev;
- return 0;
+ return UCODE_UPDATED;
}
static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 04a625f0fcda..0f545b3cf926 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -23,6 +23,7 @@
#include <asm/nops.h>
#include "../entry/calling.h"
#include <asm/export.h>
+#include <asm/nospec-branch.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
@@ -134,6 +135,7 @@ ENTRY(secondary_startup_64)
/* Ensure I am executing from virtual addresses */
movq $1f, %rax
+ ANNOTATE_RETPOLINE_SAFE
jmp *%rax
1:
UNWIND_HINT_EMPTY
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 2f723301eb58..38deafebb21b 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -23,7 +23,7 @@
/*
* this changes the io permissions bitmap in the current task.
*/
-asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
+SYSCALL_DEFINE3(ioperm, unsigned long, from, unsigned long, num, int, turn_on)
{
struct thread_struct *t = &current->thread;
struct tss_struct *tss;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index bd36f3c33cd0..0715f827607c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1168,10 +1168,18 @@ NOKPROBE_SYMBOL(longjmp_break_handler);
bool arch_within_kprobe_blacklist(unsigned long addr)
{
+ bool is_in_entry_trampoline_section = false;
+
+#ifdef CONFIG_X86_64
+ is_in_entry_trampoline_section =
+ (addr >= (unsigned long)__entry_trampoline_start &&
+ addr < (unsigned long)__entry_trampoline_end);
+#endif
return (addr >= (unsigned long)__kprobes_text_start &&
addr < (unsigned long)__kprobes_text_end) ||
(addr >= (unsigned long)__entry_text_start &&
- addr < (unsigned long)__entry_text_end);
+ addr < (unsigned long)__entry_text_end) ||
+ is_in_entry_trampoline_section;
}
int __init arch_init_kprobes(void)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 4e37d1a851a6..bc1a27280c4b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -49,7 +49,7 @@
static int kvmapf = 1;
-static int parse_no_kvmapf(char *arg)
+static int __init parse_no_kvmapf(char *arg)
{
kvmapf = 0;
return 0;
@@ -58,7 +58,7 @@ static int parse_no_kvmapf(char *arg)
early_param("no-kvmapf", parse_no_kvmapf);
static int steal_acc = 1;
-static int parse_no_stealacc(char *arg)
+static int __init parse_no_stealacc(char *arg)
{
steal_acc = 0;
return 0;
@@ -67,7 +67,7 @@ static int parse_no_stealacc(char *arg)
early_param("no-steal-acc", parse_no_stealacc);
static int kvmclock_vsyscall = 1;
-static int parse_no_kvmclock_vsyscall(char *arg)
+static int __init parse_no_kvmclock_vsyscall(char *arg)
{
kvmclock_vsyscall = 0;
return 0;
@@ -341,10 +341,10 @@ static void kvm_guest_cpu_init(void)
#endif
pa |= KVM_ASYNC_PF_ENABLED;
- /* Async page fault support for L1 hypervisor is optional */
- if (wrmsr_safe(MSR_KVM_ASYNC_PF_EN,
- (pa | KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT) & 0xffffffff, pa >> 32) < 0)
- wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+ if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
+ pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
+
+ wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
__this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
@@ -545,7 +545,8 @@ static void __init kvm_guest_init(void)
pv_time_ops.steal_clock = kvm_steal_clock;
}
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH))
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+ !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME))
pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others;
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -633,7 +634,8 @@ static __init int kvm_setup_pv_tlb_flush(void)
{
int cpu;
- if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH)) {
+ if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
+ !kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
for_each_possible_cpu(cpu) {
zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu),
GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 1ae67e982af7..4c616be28506 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1204,20 +1204,13 @@ void __init setup_arch(char **cmdline_p)
kasan_init();
-#ifdef CONFIG_X86_32
- /* sync back kernel address range */
- clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- KERNEL_PGD_PTRS);
-
/*
- * sync back low identity map too. It is used for example
- * in the 32-bit EFI stub.
+ * Sync back kernel address range.
+ *
+ * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+ * this call?
*/
- clone_pgd_range(initial_page_table,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+ sync_initial_page_table();
tboot_probe();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 497aa766fab3..ea554f812ee1 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -287,24 +287,15 @@ void __init setup_per_cpu_areas(void)
/* Setup cpu initialized, callin, callout masks */
setup_cpu_local_masks();
-#ifdef CONFIG_X86_32
/*
* Sync back kernel address range again. We already did this in
* setup_arch(), but percpu data also needs to be available in
* the smpboot asm. We can't reliably pick up percpu mappings
* using vmalloc_fault(), because exception dispatch needs
* percpu data.
+ *
+ * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+ * this call?
*/
- clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- KERNEL_PGD_PTRS);
-
- /*
- * sync back low identity map too. It is used for example
- * in the 32-bit EFI stub.
- */
- clone_pgd_range(initial_page_table,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
-#endif
+ sync_initial_page_table();
}
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ac057f9b0763..0d930d8987cc 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -43,6 +43,13 @@ static inline void signal_compat_build_tests(void)
BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
#define CHECK_CSI_OFFSET(name) BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
+ BUILD_BUG_ON(offsetof(siginfo_t, si_signo) != 0);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_errno) != 4);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_code) != 8);
+
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_signo) != 0);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_errno) != 4);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_code) != 8);
/*
* Ensure that the size of each si_field never changes.
* If it does, it is a sign that the
@@ -63,36 +70,94 @@ static inline void signal_compat_build_tests(void)
CHECK_CSI_SIZE (_kill, 2*sizeof(int));
CHECK_SI_SIZE (_kill, 2*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0xC);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+
CHECK_CSI_OFFSET(_timer);
CHECK_CSI_SIZE (_timer, 3*sizeof(int));
CHECK_SI_SIZE (_timer, 6*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_tid) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_overrun) != 0x14);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_tid) != 0x0C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_overrun) != 0x10);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14);
+
CHECK_CSI_OFFSET(_rt);
CHECK_CSI_SIZE (_rt, 3*sizeof(int));
CHECK_SI_SIZE (_rt, 4*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_value) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_value) != 0x14);
+
CHECK_CSI_OFFSET(_sigchld);
CHECK_CSI_SIZE (_sigchld, 5*sizeof(int));
CHECK_SI_SIZE (_sigchld, 8*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pid) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_uid) != 0x14);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_status) != 0x18);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_utime) != 0x20);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_stime) != 0x28);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pid) != 0x0C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_uid) != 0x10);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_status) != 0x14);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_utime) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_stime) != 0x1C);
+
#ifdef CONFIG_X86_X32_ABI
CHECK_CSI_OFFSET(_sigchld_x32);
CHECK_CSI_SIZE (_sigchld_x32, 7*sizeof(int));
/* no _sigchld_x32 in the generic siginfo_t */
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._utime) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields._sigchld_x32._stime) != 0x20);
#endif
CHECK_CSI_OFFSET(_sigfault);
CHECK_CSI_SIZE (_sigfault, 4*sizeof(int));
CHECK_SI_SIZE (_sigfault, 8*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_addr) != 0x10);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr) != 0x0C);
+
+ BUILD_BUG_ON(offsetof(siginfo_t, si_addr_lsb) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_addr_lsb) != 0x10);
+
+ BUILD_BUG_ON(offsetof(siginfo_t, si_lower) != 0x20);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_upper) != 0x28);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_lower) != 0x14);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_upper) != 0x18);
+
+ BUILD_BUG_ON(offsetof(siginfo_t, si_pkey) != 0x20);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_pkey) != 0x14);
+
CHECK_CSI_OFFSET(_sigpoll);
CHECK_CSI_SIZE (_sigpoll, 2*sizeof(int));
CHECK_SI_SIZE (_sigpoll, 4*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_band) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_fd) != 0x18);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_band) != 0x0C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_fd) != 0x10);
+
CHECK_CSI_OFFSET(_sigsys);
CHECK_CSI_SIZE (_sigsys, 3*sizeof(int));
CHECK_SI_SIZE (_sigsys, 4*sizeof(int));
+ BUILD_BUG_ON(offsetof(siginfo_t, si_call_addr) != 0x10);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_syscall) != 0x18);
+ BUILD_BUG_ON(offsetof(siginfo_t, si_arch) != 0x1C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_call_addr) != 0x0C);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_syscall) != 0x10);
+ BUILD_BUG_ON(offsetof(compat_siginfo_t, si_arch) != 0x14);
+
/* any new si_fields should be added here */
}
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 1f9188f5357c..feb28fee6cea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -5,7 +5,6 @@
#include <asm/unwind.h>
#include <asm/orc_types.h>
#include <asm/orc_lookup.h>
-#include <asm/sections.h>
#define orc_warn(fmt, ...) \
printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
@@ -148,7 +147,7 @@ static struct orc_entry *orc_find(unsigned long ip)
}
/* vmlinux .init slow lookup: */
- if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+ if (init_kernel_text(ip))
return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
__stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 9b138a06c1a4..b854ebf5851b 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -118,9 +118,11 @@ SECTIONS
#ifdef CONFIG_X86_64
. = ALIGN(PAGE_SIZE);
+ VMLINUX_SYMBOL(__entry_trampoline_start) = .;
_entry_trampoline = .;
*(.entry_trampoline)
. = ALIGN(PAGE_SIZE);
+ VMLINUX_SYMBOL(__entry_trampoline_end) = .;
ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big");
#endif
OpenPOWER on IntegriCloud