Merge branch 'master' into queue

* master: (15791 commits)
  Linux 3.9-rc1
  btrfs/raid56: Add missing #include <linux/vmalloc.h>
  fix compat_sys_rt_sigprocmask()
  SUNRPC: One line comment fix
  ext4: enable quotas before orphan cleanup
  ext4: don't allow quota mount options when quota feature enabled
  ext4: fix a warning from sparse check for ext4_dir_llseek
  ext4: convert number of blocks to clusters properly
  ext4: fix possible memory leak in ext4_remount()
  jbd2: fix ERR_PTR dereference in jbd2__journal_start
  metag: Provide dma_get_sgtable()
  metag: prom.h: remove declaration of metag_dt_memblock_reserve()
  metag: copy devicetree to non-init memory
  metag: cleanup metag_ksyms.c includes
  metag: move mm/init.c exports out of metag_ksyms.c
  metag: move usercopy.c exports out of metag_ksyms.c
  metag: move setup.c exports out of metag_ksyms.c
  metag: move kick.c exports out of metag_ksyms.c
  metag: move traps.c exports out of metag_ksyms.c
  metag: move irq enable out of irqflags.h on SMP
  ...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Conflicts:
	arch/x86/kernel/kvmclock.c

2 files changed, 37 insertions, 29 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4ed3edbe06bd..956ca358108a 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1644,13 +1644,13 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
-#define for_each_gfn_sp(kvm, sp, gfn, pos)				\
-  hlist_for_each_entry(sp, pos,						\
+#define for_each_gfn_sp(kvm, sp, gfn)					\
+  hlist_for_each_entry(sp,						\
    &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link)	\
 	if ((sp)->gfn != (gfn)) {} else
 
-#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn, pos)		\
-  hlist_for_each_entry(sp, pos,						\
+#define for_each_gfn_indirect_valid_sp(kvm, sp, gfn)			\
+  hlist_for_each_entry(sp,						\
    &(kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)], hash_link)	\
 		if ((sp)->gfn != (gfn) || (sp)->role.direct ||		\
 			(sp)->role.invalid) {} else
@@ -1706,11 +1706,10 @@ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 static void kvm_sync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	bool flush = false;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (!s->unsync)
 			continue;
 
@@ -1848,7 +1847,6 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	union kvm_mmu_page_role role;
 	unsigned quadrant;
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	bool need_sync = false;
 
 	role = vcpu->arch.mmu.base_role;
@@ -1863,7 +1861,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		quadrant &= (1 << ((PT32_PT_BITS - PT64_PT_BITS) * level)) - 1;
 		role.quadrant = quadrant;
 	}
-	for_each_gfn_sp(vcpu->kvm, sp, gfn, node) {
+	for_each_gfn_sp(vcpu->kvm, sp, gfn) {
 		if (!need_sync && sp->unsync)
 			need_sync = true;
 
@@ -2151,14 +2149,13 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
 int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn)
 {
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	int r;
 
 	pgprintk("%s: looking for gfn %llx\n", __func__, gfn);
 	r = 0;
 	spin_lock(&kvm->mmu_lock);
-	for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) {
+	for_each_gfn_indirect_valid_sp(kvm, sp, gfn) {
 		pgprintk("%s: gfn %llx role %x\n", __func__, gfn,
 			 sp->role.word);
 		r = 1;
@@ -2288,9 +2285,8 @@ static void __kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 static void kvm_unsync_pages(struct kvm_vcpu *vcpu,  gfn_t gfn)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (s->unsync)
 			continue;
 		WARN_ON(s->role.level != PT_PAGE_TABLE_LEVEL);
@@ -2302,10 +2298,9 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 				  bool can_unsync)
 {
 	struct kvm_mmu_page *s;
-	struct hlist_node *node;
 	bool need_unsync = false;
 
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, s, gfn) {
 		if (!can_unsync)
 			return 1;
 
@@ -3933,7 +3928,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
-	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
@@ -3964,7 +3958,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
 	mask.cr0_wp = mask.cr4_pae = mask.nxe = 1;
-	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) {
+	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {
 			zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d0cf7371a558..811c5c9c8880 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -120,7 +120,7 @@ struct kvm_shared_msrs {
 };
 
 static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
-static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);
+static struct kvm_shared_msrs __percpu *shared_msrs;
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
@@ -191,10 +191,10 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 
 static void shared_msr_update(unsigned slot, u32 msr)
 {
-	struct kvm_shared_msrs *smsr;
 	u64 value;
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
-	smsr = &__get_cpu_var(shared_msrs);
 	/* only read, and nobody should modify it at this time,
 	 * so don't need lock */
 	if (slot >= shared_msrs_global.nr) {
@@ -226,7 +226,8 @@ static void kvm_shared_msr_cpu_online(void)
 
 void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
 {
-	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
 	if (((value ^ smsr->values[slot].curr) & mask) == 0)
 		return;
@@ -242,7 +243,8 @@ EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
 
 static void drop_user_return_notifiers(void *ignore)
 {
-	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+	unsigned int cpu = smp_processor_id();
+	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
 
 	if (smsr->registered)
 		kvm_on_user_return(&smsr->urn);
@@ -1877,6 +1879,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	u64 data = msr_info->data;
 
 	switch (msr) {
+	case MSR_AMD64_NB_CFG:
+	case MSR_IA32_UCODE_REV:
+	case MSR_IA32_UCODE_WRITE:
+	case MSR_VM_HSAVE_PA:
+	case MSR_AMD64_PATCH_LOADER:
+	case MSR_AMD64_BU_CFG2:
+		break;
+
 	case MSR_EFER:
 		return set_efer(vcpu, data);
 	case MSR_K7_HWCR:
@@ -1896,8 +1906,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		}
 		break;
-	case MSR_AMD64_NB_CFG:
-		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		if (!data) {
 			/* We support the non-activated case already */
@@ -1910,11 +1918,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
 			    __func__, data);
 		break;
-	case MSR_IA32_UCODE_REV:
-	case MSR_IA32_UCODE_WRITE:
-	case MSR_VM_HSAVE_PA:
-	case MSR_AMD64_PATCH_LOADER:
-		break;
 	case 0x200 ... 0x2ff:
 		return set_msr_mtrr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
@@ -2249,6 +2252,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_K8_INT_PENDING_MSG:
 	case MSR_AMD64_NB_CFG:
 	case MSR_FAM10H_MMIO_CONF_BASE:
+	case MSR_AMD64_BU_CFG2:
 		data = 0;
 		break;
 	case MSR_P6_PERFCTR0:
@@ -5269,9 +5273,16 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
+	r = -ENOMEM;
+	shared_msrs = alloc_percpu(struct kvm_shared_msrs);
+	if (!shared_msrs) {
+		printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n");
+		goto out;
+	}
+
 	r = kvm_mmu_module_init();
 	if (r)
-		goto out;
+		goto out_free_percpu;
 
 	kvm_set_mmio_spte_mask();
 	kvm_init_msr_list();
@@ -5294,6 +5305,8 @@ int kvm_arch_init(void *opaque)
 
 	return 0;
 
+out_free_percpu:
+	free_percpu(shared_msrs);
 out:
 	return r;
 }
@@ -5311,6 +5324,7 @@ void kvm_arch_exit(void)
 #endif
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
+	free_percpu(shared_msrs);
 }
 
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)