summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig.cpu2
-rw-r--r--arch/x86/include/asm/rwsem.h81
-rw-r--r--arch/x86/include/asm/smp.h9
-rw-r--r--arch/x86/kernel/amd_iommu.c6
-rw-r--r--arch/x86/kernel/amd_iommu_init.c5
-rw-r--r--arch/x86/kernel/aperture_64.c15
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c250
-rw-r--r--arch/x86/kernel/cpu/perf_event.c104
-rw-r--r--arch/x86/kernel/crash.c6
-rw-r--r--arch/x86/kernel/hpet.c8
-rw-r--r--arch/x86/kernel/kgdb.c2
-rw-r--r--arch/x86/kernel/mpparse.c4
-rw-r--r--arch/x86/kernel/pci-gart_64.c3
-rw-r--r--arch/x86/kvm/mmu.c11
-rw-r--r--arch/x86/kvm/svm.c25
-rw-r--r--arch/x86/kvm/vmx.c37
-rw-r--r--arch/x86/kvm/x86.c45
-rw-r--r--arch/x86/lib/Makefile3
-rw-r--r--arch/x86/lib/cache-smp.c19
-rw-r--r--arch/x86/lib/rwsem_64.S81
-rw-r--r--arch/x86/pci/irq.c2
-rw-r--r--arch/x86/power/hibernate_asm_32.S15
23 files changed, 526 insertions, 209 deletions
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index f20ddf84a893..a19829374e6a 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -319,7 +319,7 @@ config X86_L1_CACHE_SHIFT
config X86_XADD
def_bool y
- depends on X86_32 && !M386
+ depends on X86_64 || !M386
config X86_PPRO_FENCE
bool "PentiumPro memory ordering errata workaround"
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 605191838e02..42f8a37db6fb 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -41,6 +41,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/lockdep.h>
+#include <asm/asm.h>
struct rwsem_waiter;
@@ -55,17 +56,28 @@ extern asmregparm struct rw_anon_semaphore *
/*
* the semaphore definition
+ *
+ * The bias values and the counter type limits the number of
+ * potential readers/writers to 32767 for 32 bits and 2147483647
+ * for 64 bits.
*/
-#define RWSEM_UNLOCKED_VALUE 0x00000000
-#define RWSEM_ACTIVE_BIAS 0x00000001
-#define RWSEM_ACTIVE_MASK 0x0000ffff
-#define RWSEM_WAITING_BIAS (-0x00010000)
+#ifdef CONFIG_X86_64
+# define RWSEM_ACTIVE_MASK 0xffffffffL
+#else
+# define RWSEM_ACTIVE_MASK 0x0000ffffL
+#endif
+
+#define RWSEM_UNLOCKED_VALUE 0x00000000L
+#define RWSEM_ACTIVE_BIAS 0x00000001L
+#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1)
#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS
#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+typedef signed long rwsem_count_t;
+
struct rw_anon_semaphore {
- signed long count;
+ rwsem_count_t count;
raw_spinlock_t wait_lock;
struct list_head wait_list;
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -104,7 +116,7 @@ do { \
static inline void __down_read(struct rw_anon_semaphore *sem)
{
asm volatile("# beginning down_read\n\t"
- LOCK_PREFIX " incl (%%eax)\n\t"
+ LOCK_PREFIX _ASM_INC "(%1)\n\t"
/* adds 0x00000001, returns the old value */
" jns 1f\n"
" call call_rwsem_down_read_failed\n"
@@ -120,14 +132,14 @@ static inline void __down_read(struct rw_anon_semaphore *sem)
*/
static inline int __down_read_trylock(struct rw_anon_semaphore *sem)
{
- __s32 result, tmp;
+ rwsem_count_t result, tmp;
asm volatile("# beginning __down_read_trylock\n\t"
- " movl %0,%1\n\t"
+ " mov %0,%1\n\t"
"1:\n\t"
- " movl %1,%2\n\t"
- " addl %3,%2\n\t"
+ " mov %1,%2\n\t"
+ " add %3,%2\n\t"
" jle 2f\n\t"
- LOCK_PREFIX " cmpxchgl %2,%0\n\t"
+ LOCK_PREFIX " cmpxchg %2,%0\n\t"
" jnz 1b\n\t"
"2:\n\t"
"# ending __down_read_trylock\n\t"
@@ -143,13 +155,13 @@ static inline int __down_read_trylock(struct rw_anon_semaphore *sem)
static inline void
__down_write_nested(struct rw_anon_semaphore *sem, int subclass)
{
- int tmp;
+ rwsem_count_t tmp;
tmp = RWSEM_ACTIVE_WRITE_BIAS;
asm volatile("# beginning down_write\n\t"
- LOCK_PREFIX " xadd %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtract 0x0000ffff, returns the old value */
- " testl %%edx,%%edx\n\t"
+ " test %1,%1\n\t"
/* was the count 0 before? */
" jz 1f\n"
" call call_rwsem_down_write_failed\n"
@@ -170,9 +182,9 @@ static inline void __down_write(struct rw_anon_semaphore *sem)
*/
static inline int __down_write_trylock(struct rw_anon_semaphore *sem)
{
- signed long ret = cmpxchg(&sem->count,
- RWSEM_UNLOCKED_VALUE,
- RWSEM_ACTIVE_WRITE_BIAS);
+ rwsem_count_t ret = cmpxchg(&sem->count,
+ RWSEM_UNLOCKED_VALUE,
+ RWSEM_ACTIVE_WRITE_BIAS);
if (ret == RWSEM_UNLOCKED_VALUE)
return 1;
return 0;
@@ -183,9 +195,9 @@ static inline int __down_write_trylock(struct rw_anon_semaphore *sem)
*/
static inline void __up_read(struct rw_anon_semaphore *sem)
{
- __s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+ rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS;
asm volatile("# beginning __up_read\n\t"
- LOCK_PREFIX " xadd %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xadd %1,(%2)\n\t"
/* subtracts 1, returns the old value */
" jns 1f\n\t"
" call call_rwsem_wake\n"
@@ -201,18 +213,18 @@ static inline void __up_read(struct rw_anon_semaphore *sem)
*/
static inline void __up_write(struct rw_anon_semaphore *sem)
{
+ rwsem_count_t tmp;
asm volatile("# beginning __up_write\n\t"
- " movl %2,%%edx\n\t"
- LOCK_PREFIX " xaddl %%edx,(%%eax)\n\t"
+ LOCK_PREFIX " xadd %1,(%2)\n\t"
/* tries to transition
0xffff0001 -> 0x00000000 */
" jz 1f\n"
" call call_rwsem_wake\n"
"1:\n\t"
"# ending __up_write\n"
- : "+m" (sem->count)
- : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
- : "memory", "cc", "edx");
+ : "+m" (sem->count), "=d" (tmp)
+ : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+ : "memory", "cc");
}
/*
@@ -221,33 +233,38 @@ static inline void __up_write(struct rw_anon_semaphore *sem)
static inline void __downgrade_write(struct rw_anon_semaphore *sem)
{
asm volatile("# beginning __downgrade_write\n\t"
- LOCK_PREFIX " addl %2,(%%eax)\n\t"
- /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
+ LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t"
+ /*
+ * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
+ * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
+ */
" jns 1f\n\t"
" call call_rwsem_downgrade_wake\n"
"1:\n\t"
"# ending __downgrade_write\n"
: "+m" (sem->count)
- : "a" (sem), "i" (-RWSEM_WAITING_BIAS)
+ : "a" (sem), "er" (-RWSEM_WAITING_BIAS)
: "memory", "cc");
}
/*
* implement atomic add functionality
*/
-static inline void rwsem_atomic_add(int delta, struct rw_anon_semaphore *sem)
+static inline void rwsem_atomic_add(rwsem_count_t delta,
+ struct rw_anon_semaphore *sem)
{
- asm volatile(LOCK_PREFIX "addl %1,%0"
+ asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
: "+m" (sem->count)
- : "ir" (delta));
+ : "er" (delta));
}
/*
* implement exchange and add functionality
*/
-static inline int rwsem_atomic_update(int delta, struct rw_anon_semaphore *sem)
+static inline rwsem_count_t rwsem_atomic_update(rwsem_count_t delta,
+ struct rw_anon_semaphore *sem)
{
- int tmp = delta;
+ rwsem_count_t tmp = delta;
asm volatile(LOCK_PREFIX "xadd %0,%1"
: "+r" (tmp), "+m" (sem->count)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 1e796782cd7b..4cfc90824068 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -135,6 +135,8 @@ int native_cpu_disable(void);
void native_cpu_die(unsigned int cpu);
void native_play_dead(void);
void play_dead_common(void);
+void wbinvd_on_cpu(int cpu);
+int wbinvd_on_all_cpus(void);
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
@@ -147,6 +149,13 @@ static inline int num_booting_cpus(void)
{
return cpumask_weight(cpu_callout_mask);
}
+#else /* !CONFIG_SMP */
+#define wbinvd_on_cpu(cpu) wbinvd()
+static inline int wbinvd_on_all_cpus(void)
+{
+ wbinvd();
+ return 0;
+}
#endif /* CONFIG_SMP */
extern unsigned disabled_cpus __cpuinitdata;
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index adb0ba025702..2e775169bdf0 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -2298,7 +2298,7 @@ static void cleanup_domain(struct protection_domain *domain)
list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
struct device *dev = dev_data->dev;
- do_detach(dev);
+ __detach_device(dev);
atomic_set(&dev_data->bind, 0);
}
@@ -2379,9 +2379,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom)
free_pagetable(domain);
- domain_id_free(domain->id);
-
- kfree(domain);
+ protection_domain_free(domain);
dom->priv = NULL;
}
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9dc91b431470..883d61990623 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -1288,6 +1288,8 @@ static int __init amd_iommu_init(void)
if (ret)
goto free;
+ enable_iommus();
+
if (iommu_pass_through)
ret = amd_iommu_init_passthrough();
else
@@ -1300,8 +1302,6 @@ static int __init amd_iommu_init(void)
amd_iommu_init_notifier();
- enable_iommus();
-
if (iommu_pass_through)
goto out;
@@ -1315,6 +1315,7 @@ out:
return ret;
free:
+ disable_iommus();
amd_iommu_uninit_devices();
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index f147a95fd84a..19f2c703638e 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -394,6 +394,7 @@ void __init gart_iommu_hole_init(void)
for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
int bus;
int dev_base, dev_limit;
+ u32 ctl;
bus = bus_dev_ranges[i].bus;
dev_base = bus_dev_ranges[i].dev_base;
@@ -407,7 +408,19 @@ void __init gart_iommu_hole_init(void)
gart_iommu_aperture = 1;
x86_init.iommu.iommu_init = gart_iommu_init;
- aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+ ctl = read_pci_config(bus, slot, 3,
+ AMD64_GARTAPERTURECTL);
+
+ /*
+ * Before we do anything else disable the GART. It may
+ * still be enabled if we boot into a crash-kernel here.
+ * Reconfiguring the GART while it is enabled could have
+ * unknown side-effects.
+ */
+ ctl &= ~GARTEN;
+ write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+
+ aper_order = (ctl >> 1) & 7;
aper_size = (32 * 1024 * 1024) << aper_order;
aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
aper_base <<= 25;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index dfca210f6a10..d4df51725290 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1640,8 +1640,10 @@ int __init APIC_init_uniprocessor(void)
}
#endif
+#ifndef CONFIG_SMP
enable_IR_x2apic();
default_setup_apic_routing();
+#endif
verify_local_APIC();
connect_bsp_APIC();
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index fc6c8ef92dcc..d440123c556f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -18,6 +18,7 @@
#include <asm/processor.h>
#include <linux/smp.h>
#include <asm/k8.h>
+#include <asm/smp.h>
#define LVL_1_INST 1
#define LVL_1_DATA 2
@@ -150,7 +151,8 @@ struct _cpuid4_info {
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- unsigned long can_disable;
+ bool can_disable;
+ unsigned int l3_indices;
DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
};
@@ -160,7 +162,8 @@ struct _cpuid4_info_regs {
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- unsigned long can_disable;
+ bool can_disable;
+ unsigned int l3_indices;
};
unsigned short num_cache_leaves;
@@ -290,6 +293,36 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
(ebx->split.ways_of_associativity + 1) - 1;
}
+struct _cache_attr {
+ struct attribute attr;
+ ssize_t (*show)(struct _cpuid4_info *, char *);
+ ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
+};
+
+#ifdef CONFIG_CPU_SUP_AMD
+static unsigned int __cpuinit amd_calc_l3_indices(void)
+{
+ /*
+ * We're called over smp_call_function_single() and therefore
+ * are on the correct cpu.
+ */
+ int cpu = smp_processor_id();
+ int node = cpu_to_node(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned int sc0, sc1, sc2, sc3;
+ u32 val = 0;
+
+ pci_read_config_dword(dev, 0x1C4, &val);
+
+ /* calculate subcache sizes */
+ sc0 = !(val & BIT(0));
+ sc1 = !(val & BIT(4));
+ sc2 = !(val & BIT(8)) + !(val & BIT(9));
+ sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+ return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
static void __cpuinit
amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
@@ -299,12 +332,103 @@ amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
if (boot_cpu_data.x86 == 0x11)
return;
- /* see erratum #382 */
- if ((boot_cpu_data.x86 == 0x10) && (boot_cpu_data.x86_model < 0x8))
+ /* see errata #382 and #388 */
+ if ((boot_cpu_data.x86 == 0x10) &&
+ ((boot_cpu_data.x86_model < 0x8) ||
+ (boot_cpu_data.x86_mask < 0x1)))
return;
- this_leaf->can_disable = 1;
+ this_leaf->can_disable = true;
+ this_leaf->l3_indices = amd_calc_l3_indices();
+}
+
+static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
+ unsigned int index)
+{
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = amd_get_nb_id(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned int reg = 0;
+
+ if (!this_leaf->can_disable)
+ return -EINVAL;
+
+ if (!dev)
+ return -EINVAL;
+
+ pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+ return sprintf(buf, "0x%08x\n", reg);
+}
+
+#define SHOW_CACHE_DISABLE(index) \
+static ssize_t \
+show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
+{ \
+ return show_cache_disable(this_leaf, buf, index); \
+}
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
+ const char *buf, size_t count, unsigned int index)
+{
+ int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
+ int node = amd_get_nb_id(cpu);
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
+ unsigned long val = 0;
+
+#define SUBCACHE_MASK (3UL << 20)
+#define SUBCACHE_INDEX 0xfff
+
+ if (!this_leaf->can_disable)
+ return -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!dev)
+ return -EINVAL;
+
+ if (strict_strtoul(buf, 10, &val) < 0)
+ return -EINVAL;
+
+ /* do not allow writes outside of allowed bits */
+ if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
+ ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+ return -EINVAL;
+
+ val |= BIT(30);
+ pci_write_config_dword(dev, 0x1BC + index * 4, val);
+ /*
+ * We need to WBINVD on a core on the node containing the L3 cache which
+ * indices we disable therefore a simple wbinvd() is not sufficient.
+ */
+ wbinvd_on_cpu(cpu);
+ pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31));
+ return count;
+}
+
+#define STORE_CACHE_DISABLE(index) \
+static ssize_t \
+store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
+ const char *buf, size_t count) \
+{ \
+ return store_cache_disable(this_leaf, buf, count, index); \
}
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
+ show_cache_disable_0, store_cache_disable_0);
+static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
+ show_cache_disable_1, store_cache_disable_1);
+
+#else /* CONFIG_CPU_SUP_AMD */
+static void __cpuinit
+amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
+{
+};
+#endif /* CONFIG_CPU_SUP_AMD */
static int
__cpuinit cpuid4_cache_lookup_regs(int index,
@@ -711,82 +835,6 @@ static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
#define to_object(k) container_of(k, struct _index_kobject, kobj)
#define to_attr(a) container_of(a, struct _cache_attr, attr)
-static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
- unsigned int index)
-{
- int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
- int node = cpu_to_node(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
- unsigned int reg = 0;
-
- if (!this_leaf->can_disable)
- return -EINVAL;
-
- if (!dev)
- return -EINVAL;
-
- pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
- return sprintf(buf, "%x\n", reg);
-}
-
-#define SHOW_CACHE_DISABLE(index) \
-static ssize_t \
-show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
-{ \
- return show_cache_disable(this_leaf, buf, index); \
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
- const char *buf, size_t count, unsigned int index)
-{
- int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
- int node = cpu_to_node(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
- unsigned long val = 0;
- unsigned int scrubber = 0;
-
- if (!this_leaf->can_disable)
- return -EINVAL;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (!dev)
- return -EINVAL;
-
- if (strict_strtoul(buf, 10, &val) < 0)
- return -EINVAL;
-
- val |= 0xc0000000;
-
- pci_read_config_dword(dev, 0x58, &scrubber);
- scrubber &= ~0x1f000000;
- pci_write_config_dword(dev, 0x58, scrubber);
-
- pci_write_config_dword(dev, 0x1BC + index * 4, val & ~0x40000000);
- wbinvd();
- pci_write_config_dword(dev, 0x1BC + index * 4, val);
- return count;
-}
-
-#define STORE_CACHE_DISABLE(index) \
-static ssize_t \
-store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
- const char *buf, size_t count) \
-{ \
- return store_cache_disable(this_leaf, buf, count, index); \
-}
-STORE_CACHE_DISABLE(0)
-STORE_CACHE_DISABLE(1)
-
-struct _cache_attr {
- struct attribute attr;
- ssize_t (*show)(struct _cpuid4_info *, char *);
- ssize_t (*store)(struct _cpuid4_info *, const char *, size_t count);
-};
-
#define define_one_ro(_name) \
static struct _cache_attr _name = \
__ATTR(_name, 0444, show_##_name, NULL)
@@ -801,23 +849,28 @@ define_one_ro(size);
define_one_ro(shared_cpu_map);
define_one_ro(shared_cpu_list);
-static struct _cache_attr cache_disable_0 = __ATTR(cache_disable_0, 0644,
- show_cache_disable_0, store_cache_disable_0);
-static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
- show_cache_disable_1, store_cache_disable_1);
+#define DEFAULT_SYSFS_CACHE_ATTRS \
+ &type.attr, \
+ &level.attr, \
+ &coherency_line_size.attr, \
+ &physical_line_partition.attr, \
+ &ways_of_associativity.attr, \
+ &number_of_sets.attr, \
+ &size.attr, \
+ &shared_cpu_map.attr, \
+ &shared_cpu_list.attr
static struct attribute *default_attrs[] = {
- &type.attr,
- &level.attr,
- &coherency_line_size.attr,
- &physical_line_partition.attr,
- &ways_of_associativity.attr,
- &number_of_sets.attr,
- &size.attr,
- &shared_cpu_map.attr,
- &shared_cpu_list.attr,
+ DEFAULT_SYSFS_CACHE_ATTRS,
+ NULL
+};
+
+static struct attribute *default_l3_attrs[] = {
+ DEFAULT_SYSFS_CACHE_ATTRS,
+#ifdef CONFIG_CPU_SUP_AMD
&cache_disable_0.attr,
&cache_disable_1.attr,
+#endif
NULL
};
@@ -908,6 +961,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
unsigned int cpu = sys_dev->id;
unsigned long i, j;
struct _index_kobject *this_object;
+ struct _cpuid4_info *this_leaf;
int retval;
retval = cpuid4_cache_sysfs_init(cpu);
@@ -926,6 +980,14 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
this_object = INDEX_KOBJECT_PTR(cpu, i);
this_object->cpu = cpu;
this_object->index = i;
+
+ this_leaf = CPUID4_INFO_IDX(cpu, i);
+
+ if (this_leaf->can_disable)
+ ktype_cache.default_attrs = default_l3_attrs;
+ else
+ ktype_cache.default_attrs = default_attrs;
+
retval = kobject_init_and_add(&(this_object->kobj),
&ktype_cache,
per_cpu(ici_cache_kobject, cpu),
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 98819b32bb5f..c7ca8e26aa60 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -245,6 +245,97 @@ static u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
+static const u64 westmere_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0151, /* L1D.REPL */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x0251, /* L1D.M_REPL */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x014e, /* L1D_PREFETCH.REQUESTS */
+ [ C(RESULT_MISS) ] = 0x024e, /* L1D_PREFETCH.MISS */
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* L1I.READS */
+ [ C(RESULT_MISS) ] = 0x0280, /* L1I.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0324, /* L2_RQSTS.LOADS */
+ [ C(RESULT_MISS) ] = 0x0224, /* L2_RQSTS.LD_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0c24, /* L2_RQSTS.RFOS */
+ [ C(RESULT_MISS) ] = 0x0824, /* L2_RQSTS.RFO_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x4f2e, /* LLC Reference */
+ [ C(RESULT_MISS) ] = 0x412e, /* LLC Misses */
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x010b, /* MEM_INST_RETIRED.LOADS */
+ [ C(RESULT_MISS) ] = 0x0108, /* DTLB_LOAD_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x020b, /* MEM_INST_RETURED.STORES */
+ [ C(RESULT_MISS) ] = 0x010c, /* MEM_STORE_RETIRED.DTLB_MISS */
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0,
+ [ C(RESULT_MISS) ] = 0x0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x0185, /* ITLB_MISSES.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ALL_BRANCHES */
+ [ C(RESULT_MISS) ] = 0x03e8, /* BPU_CLEARS.ANY */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static __initconst u64 nehalem_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -2118,6 +2209,7 @@ static __init int intel_pmu_init(void)
* Install the hw-cache-events table:
*/
switch (boot_cpu_data.x86_model) {
+
case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
@@ -2129,7 +2221,9 @@ static __init int intel_pmu_init(void)
event_constraints = intel_core_event_constraints;
break;
default:
- case 26:
+ case 26: /* 45 nm nehalem, "Bloomfield" */
+ case 30: /* 45 nm nehalem, "Lynnfield" */
+ case 46: /* 45 nm nehalem-ex, "Beckton" */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2142,6 +2236,14 @@ static __init int intel_pmu_init(void)
pr_cont("Atom events, ");
break;
+
+ case 37: /* 32 nm nehalem, "Clarkdale" */
+ case 44: /* 32 nm nehalem, "Gulftown" */
+ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+ pr_cont("Westmere events, ");
+ break;
}
return 0;
}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a4849c10a77e..ebd4c51d096a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -27,7 +27,6 @@
#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
-#include <asm/x86_init.h>
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
@@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
-
-#ifdef CONFIG_X86_64
- x86_platform.iommu_shutdown();
-#endif
-
crash_save_cpu(regs, safe_smp_processor_id());
}
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ad80a1c718c6..773afc9274a1 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -399,9 +399,15 @@ static int hpet_next_event(unsigned long delta,
* then we might have a real hardware problem. We can not do
* much about it here, but at least alert the user/admin with
* a prominent warning.
+ * An erratum on some chipsets (ICH9,..), results in comparator read
+ * immediately following a write returning old value. Workaround
+ * for this is to read this value second time, when first
+ * read returns old value.
*/
- WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
+ if (unlikely((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt)) {
+ WARN_ONCE(hpet_readl(HPET_Tn_CMP(timer)) != cnt,
KERN_WARNING "hpet: compare register read back failed.\n");
+ }
return (s32)(hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
}
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index bfba6019d762..b2258ca91003 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -618,8 +618,8 @@ int kgdb_arch_init(void)
* portion of kgdb because this operation requires mutexs to
* complete.
*/
+ hw_breakpoint_init(&attr);
attr.bp_addr = (unsigned long)kgdb_arch_init;
- attr.type = PERF_TYPE_BREAKPOINT;
attr.bp_len = HW_BREAKPOINT_LEN_1;
attr.bp_type = HW_BREAKPOINT_W;
attr.disabled = 1;
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index a2c1edd2d3ac..e81030f71a8f 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -664,7 +664,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf)
{
unsigned long size = get_mpc_size(mpf->physptr);
- reserve_early(mpf->physptr, mpf->physptr+size, "MP-table mpc");
+ reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc");
}
static int __init smp_scan_config(unsigned long base, unsigned long length)
@@ -693,7 +693,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
mpf, (u64)virt_to_phys(mpf));
mem = virt_to_phys(mpf);
- reserve_early(mem, mem + sizeof(*mpf), "MP-table mpf");
+ reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf");
if (mpf->physptr)
smp_reserve_memory(mpf);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 34de53b46f87..4f41b29fde98 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -564,6 +564,9 @@ static void enable_gart_translations(void)
enable_gart_translation(dev, __pa(agp_gatt_table));
}
+
+ /* Flush the GART-TLB to remove stale entries */
+ k8_flush_garts();
}
/*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 89a49fb46a27..28c3d814c092 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1502,8 +1502,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
for_each_sp(pages, sp, parents, i) {
kvm_mmu_zap_page(kvm, sp);
mmu_pages_clear_parents(&parents);
+ zapped++;
}
- zapped += pages.nr;
kvm_mmu_pages_init(parent, &parents, &pages);
}
@@ -1554,14 +1554,16 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
*/
if (used_pages > kvm_nr_mmu_pages) {
- while (used_pages > kvm_nr_mmu_pages) {
+ while (used_pages > kvm_nr_mmu_pages &&
+ !list_empty(&kvm->arch.active_mmu_pages)) {
struct kvm_mmu_page *page;
page = container_of(kvm->arch.active_mmu_pages.prev,
struct kvm_mmu_page, link);
- kvm_mmu_zap_page(kvm, page);
+ used_pages -= kvm_mmu_zap_page(kvm, page);
used_pages--;
}
+ kvm_nr_mmu_pages = used_pages;
kvm->arch.n_free_mmu_pages = 0;
}
else
@@ -1608,7 +1610,8 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
&& !sp->role.invalid) {
pgprintk("%s: zap %lx %x\n",
__func__, gfn, sp->role.word);
- kvm_mmu_zap_page(kvm, sp);
+ if (kvm_mmu_zap_page(kvm, sp))
+ nn = bucket->first;
}
}
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1d9b33843c80..d42e191b17fa 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -698,29 +698,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
if (err)
goto free_svm;
+ err = -ENOMEM;
page = alloc_page(GFP_KERNEL);
- if (!page) {
- err = -ENOMEM;
+ if (!page)
goto uninit;
- }
- err = -ENOMEM;
msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
if (!msrpm_pages)
- goto uninit;
+ goto free_page1;
nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
if (!nested_msrpm_pages)
- goto uninit;
-
- svm->msrpm = page_address(msrpm_pages);
- svm_vcpu_init_msrpm(svm->msrpm);
+ goto free_page2;
hsave_page = alloc_page(GFP_KERNEL);
if (!hsave_page)
- goto uninit;
+ goto free_page3;
+
svm->nested.hsave = page_address(hsave_page);
+ svm->msrpm = page_address(msrpm_pages);
+ svm_vcpu_init_msrpm(svm->msrpm);
+
svm->nested.msrpm = page_address(nested_msrpm_pages);
svm->vmcb = page_address(page);
@@ -737,6 +736,12 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
return &svm->vcpu;
+free_page3:
+ __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+ __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+ __free_page(page);
uninit:
kvm_vcpu_uninit(&svm->vcpu);
free_svm:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8a8e13965076..3acbe194e525 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -61,6 +61,8 @@ module_param_named(unrestricted_guest,
static int __read_mostly emulate_invalid_guest_state = 0;
module_param(emulate_invalid_guest_state, bool, S_IRUGO);
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* ple_gap: upper bound on the amount of time between two successive
@@ -115,7 +117,7 @@ struct vcpu_vmx {
} host_state;
struct {
int vm86_active;
- u8 save_iopl;
+ ulong save_rflags;
struct kvm_save_segment {
u16 selector;
unsigned long base;
@@ -787,18 +789,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
- unsigned long rflags;
+ unsigned long rflags, save_rflags;
rflags = vmcs_readl(GUEST_RFLAGS);
- if (to_vmx(vcpu)->rmode.vm86_active)
- rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+ if (to_vmx(vcpu)->rmode.vm86_active) {
+ rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+ save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+ rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+ }
return rflags;
}
static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
{
- if (to_vmx(vcpu)->rmode.vm86_active)
+ if (to_vmx(vcpu)->rmode.vm86_active) {
+ to_vmx(vcpu)->rmode.save_rflags = rflags;
rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+ }
vmcs_writel(GUEST_RFLAGS, rflags);
}
@@ -1431,8 +1438,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
flags = vmcs_readl(GUEST_RFLAGS);
- flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
- flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
+ flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+ flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
vmcs_writel(GUEST_RFLAGS, flags);
vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
@@ -1501,8 +1508,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
flags = vmcs_readl(GUEST_RFLAGS);
- vmx->rmode.save_iopl
- = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+ vmx->rmode.save_rflags = flags;
flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
@@ -2719,6 +2725,12 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
kvm_queue_exception(vcpu, vec);
return 1;
case BP_VECTOR:
+ /*
+ * Update instruction length as we may reinject the exception
+ * from user space while in guest debugging mode.
+ */
+ to_vmx(vcpu)->vcpu.arch.event_exit_inst_len =
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
return 0;
/* fall through */
@@ -2841,6 +2853,13 @@ static int handle_exception(struct kvm_vcpu *vcpu)
kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
/* fall through */
case BP_VECTOR:
+ /*
+ * Update instruction length as we may reinject #BP from
+ * user space while in guest debugging mode. Reading it for
+ * #DB as well causes no harm, it is not used in that case.
+ */
+ vmx->vcpu.arch.event_exit_inst_len =
+ vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
kvm_run->debug.arch.exception = ex_no;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d325c6345bab..55e20f8c518f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -384,21 +384,16 @@ out:
void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
if (cr0 & CR0_RESERVED_BITS) {
- printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
- cr0, vcpu->arch.cr0);
kvm_inject_gp(vcpu, 0);
return;
}
if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
- printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
kvm_inject_gp(vcpu, 0);
return;
}
if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
- printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
- "and a clear PE flag\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -409,15 +404,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
int cs_db, cs_l;
if (!is_pae(vcpu)) {
- printk(KERN_DEBUG "set_cr0: #GP, start paging "
- "in long mode while PAE is disabled\n");
kvm_inject_gp(vcpu, 0);
return;
}
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
if (cs_l) {
- printk(KERN_DEBUG "set_cr0: #GP, start paging "
- "in long mode while CS.L == 1\n");
kvm_inject_gp(vcpu, 0);
return;
@@ -425,8 +416,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
} else
#endif
if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
- printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
- "reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -453,28 +442,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
if (cr4 & CR4_RESERVED_BITS) {
- printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE)) {
- printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
- "in long mode\n");
kvm_inject_gp(vcpu, 0);
return;
}
} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
&& ((cr4 ^ old_cr4) & pdptr_bits)
&& !load_pdptrs(vcpu, vcpu->arch.cr3)) {
- printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
if (cr4 & X86_CR4_VMXE) {
- printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -495,21 +479,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
if (is_long_mode(vcpu)) {
if (cr3 & CR3_L_MODE_RESERVED_BITS) {
- printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
} else {
if (is_pae(vcpu)) {
if (cr3 & CR3_PAE_RESERVED_BITS) {
- printk(KERN_DEBUG
- "set_cr3: #GP, reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
- printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
- "reserved bits\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -541,7 +520,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3);
void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
if (cr8 & CR8_RESERVED_BITS) {
- printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
kvm_inject_gp(vcpu, 0);
return;
}
@@ -595,15 +573,12 @@ static u32 emulated_msrs[] = {
static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
if (efer & efer_reserved_bits) {
- printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
- efer);
kvm_inject_gp(vcpu, 0);
return;
}
if (is_paging(vcpu)
&& (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) {
- printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -613,7 +588,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
- printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -624,7 +598,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
- printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
kvm_inject_gp(vcpu, 0);
return;
}
@@ -913,9 +886,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
u32 offset = msr - MSR_IA32_MC0_CTL;
- /* only 0 or all 1s can be written to IA32_MCi_CTL */
+ /* only 0 or all 1s can be written to IA32_MCi_CTL
+ * some Linux kernels though clear bit 10 in bank 4 to
+ * workaround a BIOS/GART TBL issue on AMD K8s, ignore
+ * this to avoid an uncatched #GP in the guest
+ */
if ((offset & 0x3) == 0 &&
- data != 0 && data != ~(u64)0)
+ data != 0 && (data | (1 << 10)) != ~(u64)0)
return -1;
vcpu->arch.mce_banks[offset] = data;
break;
@@ -2366,7 +2343,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log)
{
int r;
- int n;
+ unsigned long n;
struct kvm_memory_slot *memslot;
int is_dirty = 0;
@@ -2382,7 +2359,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
kvm_mmu_slot_remove_write_access(kvm, log->slot);
spin_unlock(&kvm->mmu_lock);
memslot = &kvm->memslots[log->slot];
- n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+ n = kvm_dirty_bitmap_bytes(memslot);
memset(memslot->dirty_bitmap, 0, n);
}
r = 0;
@@ -4599,6 +4576,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
int ret = 0;
u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
+ u32 desc_limit;
old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base);
@@ -4621,7 +4599,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
}
}
- if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) {
+ desc_limit = get_desc_limit(&nseg_desc);
+ if (!nseg_desc.p ||
+ ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
+ desc_limit < 0x2b)) {
kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
return 1;
}
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index cffd754f3039..ddef409c2816 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -14,7 +14,7 @@ $(obj)/inat.o: $(obj)/inat-tables.c
clean-files := inat-tables.c
-obj-$(CONFIG_SMP) += msr-smp.o
+obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
lib-y := delay.o
lib-y += thunk_$(BITS).o
@@ -39,4 +39,5 @@ else
lib-y += thunk_64.o clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o rwlock_64.o copy_user_nocache_64.o
+ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem_64.o
endif
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
new file mode 100644
index 000000000000..a3c668875038
--- /dev/null
+++ b/arch/x86/lib/cache-smp.c
@@ -0,0 +1,19 @@
+#include <linux/smp.h>
+#include <linux/module.h>
+
+static void __wbinvd(void *dummy)
+{
+ wbinvd();
+}
+
+void wbinvd_on_cpu(int cpu)
+{
+ smp_call_function_single(cpu, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbinvd_on_cpu);
+
+int wbinvd_on_all_cpus(void)
+{
+ return on_each_cpu(__wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbinvd_on_all_cpus);
diff --git a/arch/x86/lib/rwsem_64.S b/arch/x86/lib/rwsem_64.S
new file mode 100644
index 000000000000..15acecf0d7aa
--- /dev/null
+++ b/arch/x86/lib/rwsem_64.S
@@ -0,0 +1,81 @@
+/*
+ * x86-64 rwsem wrappers
+ *
+ * This interfaces the inline asm code to the slow-path
+ * C routines. We need to save the call-clobbered regs
+ * that the asm does not mark as clobbered, and move the
+ * argument from %rax to %rdi.
+ *
+ * NOTE! We don't need to save %rax, because the functions
+ * will always return the semaphore pointer in %rax (which
+ * is also the input argument to these helpers)
+ *
+ * The following can clobber %rdx because the asm clobbers it:
+ * call_rwsem_down_write_failed
+ * call_rwsem_wake
+ * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
+ */
+
+#include <linux/linkage.h>
+#include <asm/rwlock.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/dwarf2.h>
+
+#define save_common_regs \
+ pushq %rdi; \
+ pushq %rsi; \
+ pushq %rcx; \
+ pushq %r8; \
+ pushq %r9; \
+ pushq %r10; \
+ pushq %r11
+
+#define restore_common_regs \
+ popq %r11; \
+ popq %r10; \
+ popq %r9; \
+ popq %r8; \
+ popq %rcx; \
+ popq %rsi; \
+ popq %rdi
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_down_read_failed)
+ save_common_regs
+ pushq %rdx
+ movq %rax,%rdi
+ call rwsem_down_read_failed
+ popq %rdx
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_down_read_failed)
+
+ENTRY(call_rwsem_down_write_failed)
+ save_common_regs
+ movq %rax,%rdi
+ call rwsem_down_write_failed
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_down_write_failed)
+
+ENTRY(call_rwsem_wake)
+ decw %dx /* do nothing if still outstanding active readers */
+ jnz 1f
+ save_common_regs
+ movq %rax,%rdi
+ call rwsem_wake
+ restore_common_regs
+1: ret
+ ENDPROC(call_rwsem_wake)
+
+/* Fix up special calling conventions */
+ENTRY(call_rwsem_downgrade_wake)
+ save_common_regs
+ pushq %rdx
+ movq %rax,%rdi
+ call rwsem_downgrade_wake
+ popq %rdx
+ restore_common_regs
+ ret
+ ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 0696d506c4ad..b02f6d8ac922 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -590,6 +590,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
case PCI_DEVICE_ID_INTEL_ICH10_1:
case PCI_DEVICE_ID_INTEL_ICH10_2:
case PCI_DEVICE_ID_INTEL_ICH10_3:
+ case PCI_DEVICE_ID_INTEL_CPT_LPC1:
+ case PCI_DEVICE_ID_INTEL_CPT_LPC2:
r->name = "PIIX/ICH";
r->get = pirq_piix_get;
r->set = pirq_piix_set;
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index b641388d8286..ad47daeafa4e 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -27,10 +27,17 @@ ENTRY(swsusp_arch_suspend)
ret
ENTRY(restore_image)
+ movl mmu_cr4_features, %ecx
movl resume_pg_dir, %eax
subl $__PAGE_OFFSET, %eax
movl %eax, %cr3
+ jecxz 1f # cr4 Pentium and higher, skip if zero
+ andl $~(X86_CR4_PGE), %ecx
+ movl %ecx, %cr4; # turn off PGE
+ movl %cr3, %eax; # flush TLB
+ movl %eax, %cr3
+1:
movl restore_pblist, %edx
.p2align 4,,7
@@ -54,16 +61,8 @@ done:
movl $swapper_pg_dir, %eax
subl $__PAGE_OFFSET, %eax
movl %eax, %cr3
- /* Flush TLB, including "global" things (vmalloc) */
movl mmu_cr4_features, %ecx
jecxz 1f # cr4 Pentium and higher, skip if zero
- movl %ecx, %edx
- andl $~(X86_CR4_PGE), %edx
- movl %edx, %cr4; # turn off PGE
-1:
- movl %cr3, %eax; # flush TLB
- movl %eax, %cr3
- jecxz 1f # cr4 Pentium and higher, skip if zero
movl %ecx, %cr4; # turn PGE back on
1: