summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/boot/compressed/misc.c2
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/cpufeature.h1
-rw-r--r--arch/x86/include/asm/i387.h56
-rw-r--r--arch/x86/include/asm/kvm_emulate.h16
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h4
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c2
-rw-r--r--arch/x86/kernel/dumpstack.c3
-rw-r--r--arch/x86/kernel/dumpstack_64.c8
-rw-r--r--arch/x86/kernel/microcode_amd.c24
-rw-r--r--arch/x86/kernel/reboot.c36
-rw-r--r--arch/x86/kernel/traps.c7
-rw-r--r--arch/x86/kvm/emulate.c51
-rw-r--r--arch/x86/kvm/x86.c45
-rw-r--r--arch/x86/mm/fault.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c36
-rw-r--r--arch/x86/platform/uv/tlb_uv.c2
-rw-r--r--arch/x86/platform/uv/uv_irq.c2
-rw-r--r--arch/x86/xen/spinlock.c27
21 files changed, 274 insertions, 60 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 864cc6e6ac8e..5bed94e189fa 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -360,7 +360,6 @@ config X86_NUMACHIP
depends on NUMA
depends on SMP
depends on X86_X2APIC
- depends on !EDAC_AMD64
---help---
Adds support for Numascale NumaChip large-SMP systems. Needed to
enable more than ~168 cores.
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 3a19d04cebeb..7116dcba0c9e 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -321,6 +321,8 @@ static void parse_elf(void *output)
default: /* Ignore other PT_* */ break;
}
}
+
+ free(phdrs);
}
asmlinkage void decompress_kernel(void *rmode, memptr heap,
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 0c9fa2745f13..b3b733262909 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -145,13 +145,13 @@ extern void __add_wrong_size(void)
#ifdef __HAVE_ARCH_CMPXCHG
#define cmpxchg(ptr, old, new) \
- __cmpxchg((ptr), (old), (new), sizeof(*ptr))
+ __cmpxchg(ptr, old, new, sizeof(*(ptr)))
#define sync_cmpxchg(ptr, old, new) \
- __sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
+ __sync_cmpxchg(ptr, old, new, sizeof(*(ptr)))
#define cmpxchg_local(ptr, old, new) \
- __cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
+ __cmpxchg_local(ptr, old, new, sizeof(*(ptr)))
#endif
/*
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 17c5d4bdee5e..8d67d428b0f9 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -159,6 +159,7 @@
#define X86_FEATURE_WDT (6*32+13) /* Watchdog timer */
#define X86_FEATURE_LWP (6*32+15) /* Light Weight Profiling */
#define X86_FEATURE_FMA4 (6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE (6*32+17) /* translation cache extension */
#define X86_FEATURE_NODEID_MSR (6*32+19) /* NodeId MSR */
#define X86_FEATURE_TBM (6*32+21) /* trailing bit manipulations */
#define X86_FEATURE_TOPOEXT (6*32+22) /* topology extensions CPUID leafs */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 6919e936345b..a29571821b99 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,7 +29,7 @@ extern unsigned int sig_xstate_size;
extern void fpu_init(void);
extern void mxcsr_feature_mask_init(void);
extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
+extern void math_state_restore(void);
extern void __math_state_restore(void);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
@@ -307,9 +307,54 @@ static inline void __clear_fpu(struct task_struct *tsk)
}
}
+/*
+ * Were we in an interrupt that interrupted kernel mode?
+ *
+ * We can do a kernel_fpu_begin/end() pair *ONLY* if that
+ * pair does nothing at all: TS_USEDFPU must be clear (so
+ * that we don't try to save the FPU state), and TS must
+ * be set (so that the clts/stts pair does nothing that is
+ * visible in the interrupted kernel thread).
+ */
+static inline bool interrupted_kernel_fpu_idle(void)
+{
+ return !(current_thread_info()->status & TS_USEDFPU) &&
+ (read_cr0() & X86_CR0_TS);
+}
+
+/*
+ * Were we in user mode (or vm86 mode) when we were
+ * interrupted?
+ *
+ * Doing kernel_fpu_begin/end() is ok if we are running
+ * in an interrupt context from user mode - we'll just
+ * save the FPU state as required.
+ */
+static inline bool interrupted_user_mode(void)
+{
+ struct pt_regs *regs = get_irq_regs();
+ return regs && user_mode_vm(regs);
+}
+
+/*
+ * Can we use the FPU in kernel mode with the
+ * whole "kernel_fpu_begin/end()" sequence?
+ *
+ * It's always ok in process context (ie "not interrupt")
+ * but it is sometimes ok even from an irq.
+ */
+static inline bool irq_fpu_usable(void)
+{
+ return !in_interrupt() ||
+ interrupted_user_mode() ||
+ interrupted_kernel_fpu_idle();
+}
+
static inline void kernel_fpu_begin(void)
{
struct thread_info *me = current_thread_info();
+
+ WARN_ON_ONCE(!irq_fpu_usable());
preempt_disable();
if (me->status & TS_USEDFPU)
__save_init_fpu(me->task);
@@ -323,14 +368,6 @@ static inline void kernel_fpu_end(void)
preempt_enable();
}
-static inline bool irq_fpu_usable(void)
-{
- struct pt_regs *regs;
-
- return !in_interrupt() || !(regs = get_irq_regs()) || \
- user_mode(regs) || (read_cr0() & X86_CR0_TS);
-}
-
/*
* Some instructions like VIA's padlock instructions generate a spurious
* DNA fault but don't modify SSE registers. And these instructions
@@ -367,6 +404,7 @@ static inline void irq_ts_restore(int TS_state)
*/
static inline void save_init_fpu(struct task_struct *tsk)
{
+ WARN_ON_ONCE(task_thread_info(tsk)->status & TS_USEDFPU);
preempt_disable();
__save_init_fpu(tsk);
stts();
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index ab4092e3214e..7b9cfc4878af 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -190,6 +190,9 @@ struct x86_emulate_ops {
int (*intercept)(struct x86_emulate_ctxt *ctxt,
struct x86_instruction_info *info,
enum x86_intercept_stage stage);
+
+ bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+ u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
};
typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -298,6 +301,19 @@ struct x86_emulate_ctxt {
#define X86EMUL_MODE_PROT (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
X86EMUL_MODE_PROT64)
+/* CPUID vendors */
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx 0x69444d41
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx 0x21726574
+#define X86EMUL_CPUID_VENDOR_AMDisbetterI_edx 0x74656273
+
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ebx 0x756e6547
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_ecx 0x6c65746e
+#define X86EMUL_CPUID_VENDOR_GenuineIntel_edx 0x49656e69
+
enum x86_intercept_stage {
X86_ICTP_NONE = 0, /* Allow zero-init to not match anything */
X86_ICPT_PRE_EXCEPT,
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 54a13aaebc40..21f7385badb8 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -318,13 +318,13 @@ uv_gpa_in_mmr_space(unsigned long gpa)
/* UV global physical address --> socket phys RAM */
static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa)
{
- unsigned long paddr = gpa & uv_hub_info->gpa_mask;
+ unsigned long paddr;
unsigned long remap_base = uv_hub_info->lowmem_remap_base;
unsigned long remap_top = uv_hub_info->lowmem_remap_top;
gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) |
((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val);
- gpa = gpa & uv_hub_info->gpa_mask;
+ paddr = gpa & uv_hub_info->gpa_mask;
if (paddr >= remap_base && paddr < remap_base + remap_top)
paddr -= remap_base;
return paddr;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 73da6b64f5b7..d6bd49faa40c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -439,7 +439,6 @@ void intel_pmu_pebs_enable(struct perf_event *event)
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
cpuc->pebs_enabled |= 1ULL << hwc->idx;
- WARN_ON_ONCE(cpuc->enabled);
if (x86_pmu.intel_cap.pebs_trap && event->attr.precise_ip > 1)
intel_pmu_lbr_enable(event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 3fab3de3ce96..47a7e63bfe54 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -72,8 +72,6 @@ void intel_pmu_lbr_enable(struct perf_event *event)
if (!x86_pmu.lbr_nr)
return;
- WARN_ON_ONCE(cpuc->enabled);
-
/*
* Reset the LBR stack if we changed task context to
* avoid data leaks.
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 1aae78f775fc..4025fe4f928f 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -252,7 +252,8 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err)
unsigned short ss;
unsigned long sp;
#endif
- printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+ printk(KERN_DEFAULT
+ "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
#ifdef CONFIG_PREEMPT
printk("PREEMPT ");
#endif
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6d728d9284bd..17107bd6e1f0 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -129,7 +129,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
if (!stack) {
if (regs)
stack = (unsigned long *)regs->sp;
- else if (task && task != current)
+ else if (task != current)
stack = (unsigned long *)task->thread.sp;
else
stack = &dummy;
@@ -269,11 +269,11 @@ void show_registers(struct pt_regs *regs)
unsigned char c;
u8 *ip;
- printk(KERN_EMERG "Stack:\n");
+ printk(KERN_DEFAULT "Stack:\n");
show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
- 0, KERN_EMERG);
+ 0, KERN_DEFAULT);
- printk(KERN_EMERG "Code: ");
+ printk(KERN_DEFAULT "Code: ");
ip = (u8 *)regs->ip - code_prologue;
if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) {
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index fe86493f3ed1..ac0417be9131 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -311,13 +311,33 @@ out:
return state;
}
+/*
+ * AMD microcode firmware naming convention, up to family 15h they are in
+ * the legacy file:
+ *
+ * amd-ucode/microcode_amd.bin
+ *
+ * This legacy file is always smaller than 2K in size.
+ *
+ * Starting at family 15h they are in family specific firmware files:
+ *
+ * amd-ucode/microcode_amd_fam15h.bin
+ * amd-ucode/microcode_amd_fam16h.bin
+ * ...
+ *
+ * These might be larger than 2K.
+ */
static enum ucode_state request_microcode_amd(int cpu, struct device *device)
{
- const char *fw_name = "amd-ucode/microcode_amd.bin";
+ char fw_name[36] = "amd-ucode/microcode_amd.bin";
const struct firmware *fw;
enum ucode_state ret = UCODE_NFOUND;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+ if (c->x86 >= 0x15)
+ snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86);
- if (request_firmware(&fw, fw_name, device)) {
+ if (request_firmware(&fw, (const char *)fw_name, device)) {
pr_err("failed to load file %s\n", fw_name);
goto out;
}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 37a458b521a6..d840e69a853c 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -39,6 +39,14 @@ static int reboot_mode;
enum reboot_type reboot_type = BOOT_ACPI;
int reboot_force;
+/* This variable is used privately to keep track of whether or not
+ * reboot_type is still set to its default value (i.e., reboot= hasn't
+ * been set on the command line). This is needed so that we can
+ * suppress DMI scanning for reboot quirks. Without it, it's
+ * impossible to override a faulty reboot quirk without recompiling.
+ */
+static int reboot_default = 1;
+
#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
static int reboot_cpu = -1;
#endif
@@ -67,6 +75,12 @@ bool port_cf9_safe = false;
static int __init reboot_setup(char *str)
{
for (;;) {
+ /* Having anything passed on the command line via
+ * reboot= will cause us to disable DMI checking
+ * below.
+ */
+ reboot_default = 0;
+
switch (*str) {
case 'w':
reboot_mode = 0x1234;
@@ -295,14 +309,6 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
- { /* Handle problems with rebooting on VersaLogic Menlow boards */
- .callback = set_bios_reboot,
- .ident = "VersaLogic Menlow based board",
- .matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "VersaLogic Corporation"),
- DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
- },
- },
{ /* Handle reboot issue on Acer Aspire one */
.callback = set_kbd_reboot,
.ident = "Acer Aspire One A110",
@@ -316,7 +322,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
static int __init reboot_init(void)
{
- dmi_check_system(reboot_dmi_table);
+ /* Only do the DMI check if reboot_type hasn't been overridden
+ * on the command line
+ */
+ if (reboot_default) {
+ dmi_check_system(reboot_dmi_table);
+ }
return 0;
}
core_initcall(reboot_init);
@@ -465,7 +476,12 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
static int __init pci_reboot_init(void)
{
- dmi_check_system(pci_reboot_dmi_table);
+ /* Only do the DMI check if reboot_type hasn't been overridden
+ * on the command line
+ */
+ if (reboot_default) {
+ dmi_check_system(pci_reboot_dmi_table);
+ }
return 0;
}
core_initcall(pci_reboot_init);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 482ec3af2067..8ba27dbc107a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -599,10 +599,10 @@ void __math_state_restore(void)
* Careful.. There are problems with IBM-designed IRQ13 behaviour.
* Don't touch unless you *really* know how it works.
*
- * Must be called with kernel preemption disabled (in this case,
- * local interrupts are disabled at the call-site in entry.S).
+ * Must be called with kernel preemption disabled (eg with local
+ * local interrupts as in the case of do_device_not_available).
*/
-asmlinkage void math_state_restore(void)
+void math_state_restore(void)
{
struct thread_info *thread = current_thread_info();
struct task_struct *tsk = thread->task;
@@ -631,6 +631,7 @@ EXPORT_SYMBOL_GPL(math_state_restore);
dotraplinkage void __kprobes
do_device_not_available(struct pt_regs *regs, long error_code)
{
+ WARN_ON_ONCE(!user_mode_vm(regs));
#ifdef CONFIG_MATH_EMULATION
if (read_cr0() & X86_CR0_EM) {
struct math_emu_info info = { };
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 05a562b85025..0982507b962a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1891,6 +1891,51 @@ setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
ss->p = 1;
}
+static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt)
+{
+ struct x86_emulate_ops *ops = ctxt->ops;
+ u32 eax, ebx, ecx, edx;
+
+ /*
+ * syscall should always be enabled in longmode - so only become
+ * vendor specific (cpuid) if other modes are active...
+ */
+ if (ctxt->mode == X86EMUL_MODE_PROT64)
+ return true;
+
+ eax = 0x00000000;
+ ecx = 0x00000000;
+ if (ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx)) {
+ /*
+ * Intel ("GenuineIntel")
+ * remark: Intel CPUs only support "syscall" in 64bit
+ * longmode. Also an 64bit guest with a
+ * 32bit compat-app running will #UD !! While this
+ * behaviour can be fixed (by emulating) into AMD
+ * response - CPUs of AMD can't behave like Intel.
+ */
+ if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx &&
+ ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx &&
+ edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx)
+ return false;
+
+ /* AMD ("AuthenticAMD") */
+ if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx &&
+ ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx &&
+ edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+ return true;
+
+ /* AMD ("AMDisbetter!") */
+ if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx &&
+ ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx &&
+ edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx)
+ return true;
+ }
+
+ /* default: (not Intel, not AMD), apply Intel's stricter rules... */
+ return false;
+}
+
static int em_syscall(struct x86_emulate_ctxt *ctxt)
{
struct x86_emulate_ops *ops = ctxt->ops;
@@ -1904,9 +1949,15 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
ctxt->mode == X86EMUL_MODE_VM86)
return emulate_ud(ctxt);
+ if (!(em_syscall_is_enabled(ctxt)))
+ return emulate_ud(ctxt);
+
ops->get_msr(ctxt, MSR_EFER, &efer);
setup_syscalls_segments(ctxt, &cs, &ss);
+ if (!(efer & EFER_SCE))
+ return emulate_ud(ctxt);
+
ops->get_msr(ctxt, MSR_STAR, &msr_data);
msr_data >>= 32;
cs_sel = (u16)(msr_data & 0xfffc);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 14d6cadc4ba6..9cbfc0698118 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1495,6 +1495,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
+ bool pr = false;
+
switch (msr) {
case MSR_EFER:
return set_efer(vcpu, data);
@@ -1635,6 +1637,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
+ case MSR_P6_PERFCTR0:
+ case MSR_P6_PERFCTR1:
+ pr = true;
+ case MSR_P6_EVNTSEL0:
+ case MSR_P6_EVNTSEL1:
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_set_msr(vcpu, msr, data);
+
+ if (pr || data != 0)
+ pr_unimpl(vcpu, "disabled perfctr wrmsr: "
+ "0x%x data 0x%llx\n", msr, data);
+ break;
case MSR_K7_CLK_CTL:
/*
* Ignore all writes to this no longer documented MSR.
@@ -1835,6 +1849,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_FAM10H_MMIO_CONF_BASE:
data = 0;
break;
+ case MSR_P6_PERFCTR0:
+ case MSR_P6_PERFCTR1:
+ case MSR_P6_EVNTSEL0:
+ case MSR_P6_EVNTSEL1:
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_get_msr(vcpu, msr, pdata);
+ data = 0;
+ break;
case MSR_IA32_UCODE_REV:
data = 0x100000000ULL;
break;
@@ -4180,6 +4202,28 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
}
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+ u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+ struct kvm_cpuid_entry2 *cpuid = NULL;
+
+ if (eax && ecx)
+ cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt),
+ *eax, *ecx);
+
+ if (cpuid) {
+ *eax = cpuid->eax;
+ *ecx = cpuid->ecx;
+ if (ebx)
+ *ebx = cpuid->ebx;
+ if (edx)
+ *edx = cpuid->edx;
+ return true;
+ }
+
+ return false;
+}
+
static struct x86_emulate_ops emulate_ops = {
.read_std = kvm_read_guest_virt_system,
.write_std = kvm_write_guest_virt_system,
@@ -4211,6 +4255,7 @@ static struct x86_emulate_ops emulate_ops = {
.get_fpu = emulator_get_fpu,
.put_fpu = emulator_put_fpu,
.intercept = emulator_intercept,
+ .get_cpuid = emulator_get_cpuid,
};
static void cache_all_regs(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9d74824a708d..f0b4caf85c1a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -673,7 +673,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
stackend = end_of_stack(tsk);
if (tsk != &init_task && *stackend != STACK_END_MAGIC)
- printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+ printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
tsk->thread.cr2 = address;
tsk->thread.trap_no = 14;
@@ -684,7 +684,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
sig = 0;
/* Executive summary in case the body of the oops scrolled away */
- printk(KERN_EMERG "CR2: %016lx\n", address);
+ printk(KERN_DEFAULT "CR2: %016lx\n", address);
oops_end(flags, regs, sig);
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 7b65f752c5f8..7c1b765ecc59 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -151,17 +151,18 @@ void bpf_jit_compile(struct sk_filter *fp)
cleanup_addr = proglen; /* epilogue address */
for (pass = 0; pass < 10; pass++) {
+ u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen;
/* no prologue/epilogue for trivial filters (RET something) */
proglen = 0;
prog = temp;
- if (seen) {
+ if (seen_or_pass0) {
EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */
EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */
/* note : must save %rbx in case bpf_error is hit */
- if (seen & (SEEN_XREG | SEEN_DATAREF))
+ if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF))
EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
CLEAR_X(); /* make sure we dont leek kernel memory */
/*
@@ -170,7 +171,7 @@ void bpf_jit_compile(struct sk_filter *fp)
* r9 = skb->len - skb->data_len
* r8 = skb->data
*/
- if (seen & SEEN_DATAREF) {
+ if (seen_or_pass0 & SEEN_DATAREF) {
if (offsetof(struct sk_buff, len) <= 127)
/* mov off8(%rdi),%r9d */
EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len));
@@ -260,9 +261,14 @@ void bpf_jit_compile(struct sk_filter *fp)
case BPF_S_ALU_DIV_X: /* A /= X; */
seen |= SEEN_XREG;
EMIT2(0x85, 0xdb); /* test %ebx,%ebx */
- if (pc_ret0 != -1)
- EMIT_COND_JMP(X86_JE, addrs[pc_ret0] - (addrs[i] - 4));
- else {
+ if (pc_ret0 > 0) {
+ /* addrs[pc_ret0 - 1] is start address of target
+ * (addrs[i] - 4) is the address following this jmp
+ * ("xor %edx,%edx; div %ebx" being 4 bytes long)
+ */
+ EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] -
+ (addrs[i] - 4));
+ } else {
EMIT_COND_JMP(X86_JNE, 2 + 5);
CLEAR_A();
EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */
@@ -335,12 +341,12 @@ void bpf_jit_compile(struct sk_filter *fp)
}
/* fallinto */
case BPF_S_RET_A:
- if (seen) {
+ if (seen_or_pass0) {
if (i != flen - 1) {
EMIT_JMP(cleanup_addr - addrs[i]);
break;
}
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */
EMIT1(0xc9); /* leaveq */
}
@@ -483,8 +489,9 @@ common_load: seen |= SEEN_DATAREF;
goto common_load;
case BPF_S_LDX_B_MSH:
if ((int)K < 0) {
- if (pc_ret0 != -1) {
- EMIT_JMP(addrs[pc_ret0] - addrs[i]);
+ if (pc_ret0 > 0) {
+ /* addrs[pc_ret0 - 1] is the start address */
+ EMIT_JMP(addrs[pc_ret0 - 1] - addrs[i]);
break;
}
CLEAR_A();
@@ -599,13 +606,14 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i];
* use it to give the cleanup instruction(s) addr
*/
cleanup_addr = proglen - 1; /* ret */
- if (seen)
+ if (seen_or_pass0)
cleanup_addr -= 1; /* leaveq */
- if (seen & SEEN_XREG)
+ if (seen_or_pass0 & SEEN_XREG)
cleanup_addr -= 4; /* mov -8(%rbp),%rbx */
if (image) {
- WARN_ON(proglen != oldproglen);
+ if (proglen != oldproglen)
+ pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen);
break;
}
if (proglen == oldproglen) {
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 9be4cff00a2d..3ae0e61abd23 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1851,6 +1851,8 @@ static void __init init_per_cpu_tunables(void)
bcp->cong_reps = congested_reps;
bcp->cong_period = congested_period;
bcp->clocks_per_100_usec = usec_2_cycles(100);
+ spin_lock_init(&bcp->queue_lock);
+ spin_lock_init(&bcp->uvhub_lock);
}
}
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index 374a05d8ad22..f25c2765a5c9 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -25,7 +25,7 @@ struct uv_irq_2_mmr_pnode{
int irq;
};
-static spinlock_t uv_irq_lock;
+static DEFINE_SPINLOCK(uv_irq_lock);
static struct rb_root uv_irq_root;
static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cc9b1e182fcf..d69cc6c3f808 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -116,9 +116,26 @@ static inline void spin_time_accum_blocked(u64 start)
}
#endif /* CONFIG_XEN_DEBUG_FS */
+/*
+ * Size struct xen_spinlock so it's the same as arch_spinlock_t.
+ */
+#if NR_CPUS < 256
+typedef u8 xen_spinners_t;
+# define inc_spinners(xl) \
+ asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+ asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
+#else
+typedef u16 xen_spinners_t;
+# define inc_spinners(xl) \
+ asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
+# define dec_spinners(xl) \
+ asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
+#endif
+
struct xen_spinlock {
unsigned char lock; /* 0 -> free; 1 -> locked */
- unsigned short spinners; /* count of waiting cpus */
+ xen_spinners_t spinners; /* count of waiting cpus */
};
static int xen_spin_is_locked(struct arch_spinlock *lock)
@@ -164,8 +181,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
wmb(); /* set lock of interest before count */
- asm(LOCK_PREFIX " incw %0"
- : "+m" (xl->spinners) : : "memory");
+ inc_spinners(xl);
return prev;
}
@@ -176,8 +192,7 @@ static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
*/
static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
{
- asm(LOCK_PREFIX " decw %0"
- : "+m" (xl->spinners) : : "memory");
+ dec_spinners(xl);
wmb(); /* decrement count before restoring lock */
__this_cpu_write(lock_spinners, prev);
}
@@ -373,6 +388,8 @@ void xen_uninit_lock_cpu(int cpu)
void __init xen_init_spinlocks(void)
{
+ BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+
pv_lock_ops.spin_is_locked = xen_spin_is_locked;
pv_lock_ops.spin_is_contended = xen_spin_is_contended;
pv_lock_ops.spin_lock = xen_spin_lock;