12 files changed, 63 insertions, 36 deletions

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index b815664fe370..8e99073b9e0f 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -520,6 +520,7 @@ config X86_PTRACE_BTS
         bool "Branch Trace Store"
         default y
         depends on X86_DEBUGCTLMSR
+        depends on BROKEN
         help
           This adds a ptrace interface to the hardware's branch trace store.
 
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
index b7c0dea119fe..61e08c0a2907 100644
--- a/arch/x86/include/asm/vmi.h
+++ b/arch/x86/include/asm/vmi.h
@@ -223,9 +223,15 @@ struct pci_header {
 } __attribute__((packed));
 
 /* Function prototypes for bootstrapping */
+#ifdef CONFIG_VMI
 extern void vmi_init(void);
+extern void vmi_activate(void);
 extern void vmi_bringup(void);
-extern void vmi_apply_boot_page_allocations(void);
+#else
+static inline void vmi_init(void) {}
+static inline void vmi_activate(void) {}
+static inline void vmi_bringup(void) {}
+#endif
 
 /* State needed to start an application processor in an SMP system. */
 struct vmi_ap_state {
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 5662e226b0c9..0a60d60ed036 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -235,8 +235,9 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
         status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
         writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
 
-        if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
-                printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
+        if (unlikely(i == EXIT_LOOP_COUNT))
+                panic("AMD IOMMU: Completion wait loop failed\n");
+
 out:
         spin_unlock_irqrestore(&iommu->lock, flags);
 
@@ -344,7 +345,7 @@ static int iommu_map(struct protection_domain *dom,
         u64 __pte, *pte, *page;
 
         bus_addr  = PAGE_ALIGN(bus_addr);
-        phys_addr = PAGE_ALIGN(bus_addr);
+        phys_addr = PAGE_ALIGN(phys_addr);
 
         /* only support 512GB address spaces for now */
         if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
@@ -600,7 +601,7 @@ static void dma_ops_free_pagetable(struct dma_ops_domain *dma_dom)
                         continue;
 
                 p2 = IOMMU_PTE_PAGE(p1[i]);
-                for (j = 0; j < 512; ++i) {
+                for (j = 0; j < 512; ++j) {
                         if (!IOMMU_PTE_PRESENT(p2[j]))
                                 continue;
                         p3 = IOMMU_PTE_PAGE(p2[j]);
@@ -910,7 +911,7 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
         if (address >= dom->aperture_size)
                 return;
 
-        WARN_ON(address & 0xfffULL || address > dom->aperture_size);
+        WARN_ON(address & ~PAGE_MASK || address >= dom->aperture_size);
 
         pte  = dom->pte_pages[IOMMU_PTE_L1_INDEX(address)];
         pte += IOMMU_PTE_L0_INDEX(address);
@@ -922,8 +923,8 @@ static void dma_ops_domain_unmap(struct amd_iommu *iommu,
 
 /*
  * This function contains common code for mapping of a physically
- * contiguous memory region into DMA address space. It is uses by all
- * mapping functions provided by this IOMMU driver.
+ * contiguous memory region into DMA address space. It is used by all
+ * mapping functions provided with this IOMMU driver.
  * Must be called with the domain lock held.
  */
 static dma_addr_t __map_single(struct device *dev,
@@ -983,7 +984,8 @@ static void __unmap_single(struct amd_iommu *iommu,
         dma_addr_t i, start;
         unsigned int pages;
 
-        if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
+        if ((dma_addr == bad_dma_address) ||
+            (dma_addr + size > dma_dom->aperture_size))
                 return;
 
         pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 30ae2701b3df..c6cc22815d35 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -427,6 +427,10 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
         memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
                         &entry, sizeof(entry));
 
+        /* set head and tail to zero manually */
+        writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+        writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
         iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
 
         return cmd_buf;
@@ -1074,7 +1078,8 @@ int __init amd_iommu_init(void)
                 goto free;
 
         /* IOMMU rlookup table - find the IOMMU for a specific device */
-        amd_iommu_rlookup_table = (void *)__get_free_pages(GFP_KERNEL,
+        amd_iommu_rlookup_table = (void *)__get_free_pages(
+                        GFP_KERNEL | __GFP_ZERO,
                         get_order(rlookup_table_size));
         if (amd_iommu_rlookup_table == NULL)
                 goto free;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 4b031a4ac856..1c838032fd37 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -510,12 +510,9 @@ static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
  */
 void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
 {
-        static cpumask_t mce_cpus = CPU_MASK_NONE;
-
         mce_cpu_quirks(c);
 
         if (mce_dont_init ||
-            cpu_test_and_set(smp_processor_id(), mce_cpus) ||
             !mce_available(c))
                 return;
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 82fb2809ce32..c4b5b24e0217 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -272,13 +272,18 @@ static struct attribute_group mc_attr_group = {
         .name = "microcode",
 };
 
-static void microcode_fini_cpu(int cpu)
+static void __microcode_fini_cpu(int cpu)
 {
         struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
-        mutex_lock(&microcode_mutex);
         microcode_ops->microcode_fini_cpu(cpu);
         uci->valid = 0;
+}
+
+static void microcode_fini_cpu(int cpu)
+{
+        mutex_lock(&microcode_mutex);
+        __microcode_fini_cpu(cpu);
         mutex_unlock(&microcode_mutex);
 }
 
@@ -306,12 +311,16 @@ static int microcode_resume_cpu(int cpu)
          * to this cpu (a bit of paranoia):
          */
         if (microcode_ops->collect_cpu_info(cpu, &nsig)) {
-                microcode_fini_cpu(cpu);
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "failed to collect_cpu_info for resuming cpu #%d\n",
+                                cpu);
                 return -1;
         }
 
-        if (memcmp(&nsig, &uci->cpu_sig, sizeof(nsig))) {
-                microcode_fini_cpu(cpu);
+        if ((nsig.sig != uci->cpu_sig.sig) || (nsig.pf != uci->cpu_sig.pf)) {
+                __microcode_fini_cpu(cpu);
+                printk(KERN_ERR "cached ucode doesn't match the resuming cpu #%d\n",
+                                cpu);
                 /* Should we look for a new ucode here? */
                 return 1;
         }
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 622dc4a21784..a8e62792d171 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -155,6 +155,7 @@ static DEFINE_SPINLOCK(microcode_update_lock);
 static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
 {
         struct cpuinfo_x86 *c = &cpu_data(cpu_num);
+        unsigned long flags;
         unsigned int val[2];
 
         memset(csig, 0, sizeof(*csig));
@@ -174,11 +175,16 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig)
                 csig->pf = 1 << ((val[1] >> 18) & 7);
         }
 
+        /* serialize access to the physical write to MSR 0x79 */
+        spin_lock_irqsave(&microcode_update_lock, flags);
+
         wrmsr(MSR_IA32_UCODE_REV, 0, 0);
         /* see notes above for revision 1.07.  Apparent chip bug */
         sync_core();
         /* get the current revision from MSR 0x8B */
         rdmsr(MSR_IA32_UCODE_REV, val[0], csig->rev);
+        spin_unlock_irqrestore(&microcode_update_lock, flags);
+
         pr_debug("microcode: collect_cpu_info : sig=0x%x, pf=0x%x, rev=0x%x\n",
                         csig->sig, csig->pf, csig->rev);
 
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 0e9f1982b1dd..95777b0faa73 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -7,7 +7,8 @@
 
 #include <asm/paravirt.h>
 
-static void default_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+static inline void
+default_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
         __raw_spin_lock(lock);
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index ba7ad83e20a8..a35eaa379ff6 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -745,10 +745,8 @@ void __init gart_iommu_init(void)
         unsigned long scratch;
         long i;
 
-        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
-                printk(KERN_INFO "PCI-GART: No AMD GART found.\n");
+        if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0)
                 return;
-        }
 
 #ifndef CONFIG_AGP_AMD64
         no_agp = 1;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index a3834f123206..5e028e1926eb 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -794,6 +794,9 @@ void __init setup_arch(char **cmdline_p)
         printk(KERN_INFO "Command line: %s\n", boot_command_line);
 #endif
 
+        /* VMI may relocate the fixmap; do this before touching ioremap area */
+        vmi_init();
+
         early_cpu_init();
         early_ioremap_init();
 
@@ -880,13 +883,8 @@ void __init setup_arch(char **cmdline_p)
         check_efer();
 #endif
 
-#if defined(CONFIG_VMI) && defined(CONFIG_X86_32)
-        /*
-         * Must be before kernel pagetables are setup
-         * or fixmap area is touched.
-         */
-        vmi_init();
-#endif
+        /* Must be before kernel pagetables are setup */
+        vmi_activate();
 
         /* after early param, so could get panic from serial */
         reserve_early_setup_data();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7b1093397319..f71f96fc9e62 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -294,9 +294,7 @@ static void __cpuinit start_secondary(void *unused)
          * fragile that we want to limit the things done here to the
          * most necessary things.
          */
-#ifdef CONFIG_VMI
         vmi_bringup();
-#endif
         cpu_init();
         preempt_disable();
         smp_callin();
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 8b6c393ab9fd..22fd6577156a 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -960,8 +960,6 @@ static inline int __init activate_vmi(void)
 
 void __init vmi_init(void)
 {
-        unsigned long flags;
-
         if (!vmi_rom)
                 probe_vmi_rom();
         else
@@ -973,13 +971,21 @@ void __init vmi_init(void)
 
         reserve_top_address(-vmi_rom->virtual_top);
 
-        local_irq_save(flags);
-        activate_vmi();
-
 #ifdef CONFIG_X86_IO_APIC
         /* This is virtual hardware; timer routing is wired correctly */
         no_timer_check = 1;
 #endif
+}
+
+void vmi_activate(void)
+{
+        unsigned long flags;
+
+        if (!vmi_rom)
+                return;
+
+        local_irq_save(flags);
+        activate_vmi();
         local_irq_restore(flags & X86_EFLAGS_IF);
 }