17 files changed, 79 insertions, 56 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c876bace8fdc..07e01149e3bf 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -491,7 +491,7 @@ if PARAVIRT_GUEST
 source "arch/x86/xen/Kconfig"
 
 config VMI
-        bool "VMI Guest support"
+        bool "VMI Guest support (DEPRECATED)"
         select PARAVIRT
         depends on X86_32
         ---help---
@@ -500,6 +500,15 @@ config VMI
           at the moment), by linking the kernel to a GPL-ed ROM module
           provided by the hypervisor.
 
+          As of September 2009, VMware has started a phased retirement
+          of this feature from VMware's products. Please see
+          feature-removal-schedule.txt for details.  If you are
+          planning to enable this option, please note that you cannot
+          live migrate a VMI enabled VM to a future VMware product,
+          which doesn't support VMI. So if you expect your kernel to
+          seamlessly migrate to newer VMware products, keep this
+          disabled.
+
 config KVM_CLOCK
         bool "KVM paravirtualized clock"
         select PARAVIRT
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 0f6ec455a2b1..03c0683636b6 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -53,6 +53,9 @@ SECTIONS
 
         /DISCARD/ : { *(.note*) }
 
+        /*
+         * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+         */
         . = ASSERT(_end <= 0x8000, "Setup too big!");
         . = ASSERT(hdr == 0x1f1, "The setup header has the wrong offset!");
         /* Necessary for the very-old-loader check to work... */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index f1363b72364f..227a72df6441 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -108,6 +108,8 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
+extern struct atomic_notifier_head x86_mce_decoder_chain;
+
 #ifdef __KERNEL__
 
 #include <linux/percpu.h>
@@ -213,6 +215,5 @@ extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8aebcc41041d..efb38994859c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -840,42 +840,22 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
 
 static inline unsigned long __raw_local_save_flags(void)
 {
-        unsigned long f;
-
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     : "=a"(f)
-                     : paravirt_type(pv_irq_ops.save_fl),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc");
-        return f;
+        return PVOP_CALLEE0(unsigned long, pv_irq_ops.save_fl);
 }
 
 static inline void raw_local_irq_restore(unsigned long f)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     : "=a"(f)
-                     : PV_FLAGS_ARG(f),
-                       paravirt_type(pv_irq_ops.restore_fl),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "cc");
+        PVOP_VCALLEE1(pv_irq_ops.restore_fl, f);
 }
 
 static inline void raw_local_irq_disable(void)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     :
-                     : paravirt_type(pv_irq_ops.irq_disable),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc");
+        PVOP_VCALLEE0(pv_irq_ops.irq_disable);
 }
 
 static inline void raw_local_irq_enable(void)
 {
-        asm volatile(paravirt_alt(PARAVIRT_CALL)
-                     :
-                     : paravirt_type(pv_irq_ops.irq_enable),
-                       paravirt_clobber(CLBR_EAX)
-                     : "memory", "eax", "cc");
+        PVOP_VCALLEE0(pv_irq_ops.irq_enable);
 }
 
 static inline unsigned long __raw_local_irq_save(void)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index dd0f5b32489d..9357473c8da0 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -494,10 +494,11 @@ int paravirt_disable_iospace(void);
 #define EXTRA_CLOBBERS
 #define VEXTRA_CLOBBERS
 #else  /* CONFIG_X86_64 */
+/* [re]ax isn't an arg, but the return val */
 #define PVOP_VCALL_ARGS                                 \
         unsigned long __edi = __edi, __esi = __esi,     \
-                __edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS          PVOP_VCALL_ARGS, __eax
+                __edx = __edx, __ecx = __ecx, __eax = __eax
+#define PVOP_CALL_ARGS          PVOP_VCALL_ARGS
 
 #define PVOP_CALL_ARG1(x)               "D" ((unsigned long)(x))
 #define PVOP_CALL_ARG2(x)               "S" ((unsigned long)(x))
@@ -509,6 +510,7 @@ int paravirt_disable_iospace(void);
                                 "=c" (__ecx)
 #define PVOP_CALL_CLOBBERS      PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
+/* void functions are still allowed [re]ax for scratch */
 #define PVOP_VCALLEE_CLOBBERS   "=a" (__eax)
 #define PVOP_CALLEE_CLOBBERS    PVOP_VCALLEE_CLOBBERS
 
@@ -583,8 +585,8 @@ int paravirt_disable_iospace(void);
                        VEXTRA_CLOBBERS,                                 \
                        pre, post, ##__VA_ARGS__)
 
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...)                 \
-        ____PVOP_CALL(rettype, op.func, CLBR_RET_REG,                   \
+#define __PVOP_VCALLEESAVE(op, pre, post, ...)                          \
+        ____PVOP_VCALL(op.func, CLBR_RET_REG,                           \
                       PVOP_VCALLEE_CLOBBERS, ,                          \
                       pre, post, ##__VA_ARGS__)
 
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
index 7da00b799cda..060fff8f5c5b 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
@@ -57,5 +57,8 @@ SECTIONS
                 *(.note*)
         }
 
+        /*
+         * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+         */
         . = ASSERT(_end <= WAKEUP_SIZE, "Wakeup too big!");
 }
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index f5f5886a6b53..326c25477d3d 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -352,14 +352,14 @@ static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 
         for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
                 alias.v = uv_read_local_mmr(redir_addrs[i].alias);
-                if (alias.s.base == 0) {
+                if (alias.s.enable && alias.s.base == 0) {
                         *size = (1UL << alias.s.m_alias);
                         redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
                         *base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
                         return;
                 }
         }
-        BUG();
+        *base = *size = 0;
 }
 
 enum map_type {map_wb, map_uc};
@@ -619,12 +619,12 @@ void __init uv_system_init(void)
                 uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
                 uv_cpu_hub_info(cpu)->lowmem_remap_top = lowmem_redir_size;
                 uv_cpu_hub_info(cpu)->m_val = m_val;
-                uv_cpu_hub_info(cpu)->n_val = m_val;
+                uv_cpu_hub_info(cpu)->n_val = n_val;
                 uv_cpu_hub_info(cpu)->numa_blade_id = blade;
                 uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
                 uv_cpu_hub_info(cpu)->pnode = pnode;
                 uv_cpu_hub_info(cpu)->pnode_mask = pnode_mask;
-                uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+                uv_cpu_hub_info(cpu)->gpa_mask = (1UL << (m_val + n_val)) - 1;
                 uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
                 uv_cpu_hub_info(cpu)->gnode_extra = gnode_extra;
                 uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 39caea3d8bc3..0fb9dc50697e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -88,18 +88,26 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int                      cpu_missing;
 
-static void default_decode_mce(struct mce *m)
+/*
+ * CPU/chipset specific EDAC code can register a notifier call here to print
+ * MCE errors in a human-readable form.
+ */
+ATOMIC_NOTIFIER_HEAD(x86_mce_decoder_chain);
+EXPORT_SYMBOL_GPL(x86_mce_decoder_chain);
+
+static int default_decode_mce(struct notifier_block *nb, unsigned long val,
+                               void *data)
 {
         pr_emerg("No human readable MCE decoding support on this CPU type.\n");
         pr_emerg("Run the message through 'mcelog --ascii' to decode.\n");
+
+        return NOTIFY_STOP;
 }
 
-/*
- * CPU/chipset specific EDAC code can register a callback here to print
- * MCE errors in a human-readable form:
- */
-void (*x86_mce_decode_callback)(struct mce *m) = default_decode_mce;
-EXPORT_SYMBOL(x86_mce_decode_callback);
+static struct notifier_block mce_dec_nb = {
+        .notifier_call = default_decode_mce,
+        .priority      = -1,
+};
 
 /* MCA banks polled by the period polling timer for corrected events */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
@@ -210,9 +218,9 @@ static void print_mce(struct mce *m)
 
         /*
          * Print out human-readable details about the MCE error,
-         * (if the CPU has an implementation for that):
+         * (if the CPU has an implementation for that)
          */
-        x86_mce_decode_callback(m);
+        atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, m);
 }
 
 static void print_mce_head(void)
@@ -1220,7 +1228,8 @@ static int __cpuinit mce_cap_init(void)
         rdmsrl(MSR_IA32_MCG_CAP, cap);
 
         b = cap & MCG_BANKCNT_MASK;
-        printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
+        if (!banks)
+                printk(KERN_INFO "mce: CPU supports %d MCE banks\n", b);
 
         if (b > MAX_NR_BANKS) {
                 printk(KERN_WARNING
@@ -1426,6 +1435,9 @@ void __cpuinit mcheck_init(struct cpuinfo_x86 *c)
         mce_cpu_features(c);
         mce_init_timer();
         INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
+
+        if (raw_smp_processor_id() == 0)
+                atomic_notifier_chain_register(&x86_mce_decoder_chain, &mce_dec_nb);
 }
 
 /*
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 391206199515..04bbd5278568 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -63,10 +63,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
         seq_printf(p, "  Spurious interrupts\n");
-        seq_printf(p, "%*s: ", prec, "CNT");
+        seq_printf(p, "%*s: ", prec, "PMI");
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
-        seq_printf(p, "  Performance counter interrupts\n");
+        seq_printf(p, "  Performance monitoring interrupts\n");
         seq_printf(p, "%*s: ", prec, "PND");
         for_each_online_cpu(j)
                 seq_printf(p, "%10u ", irq_stats(j)->apic_pending_irqs);
@@ -244,7 +244,6 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
                                 __func__, smp_processor_id(), vector, irq);
         }
 
-        run_local_timers();
         irq_exit();
 
         set_irq_regs(old_regs);
@@ -269,7 +268,6 @@ void smp_generic_interrupt(struct pt_regs *regs)
         if (generic_interrupt_extension)
                 generic_interrupt_extension();
 
-        run_local_timers();
         irq_exit();
 
         set_irq_regs(old_regs);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index d20009b4e6ef..b2a71dca5642 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -311,7 +311,7 @@ void pci_iommu_shutdown(void)
         amd_iommu_shutdown();
 }
 /* Must execute after PCI subsystem */
-fs_initcall(pci_iommu_init);
+rootfs_initcall(pci_iommu_init);
 
 #ifdef CONFIG_PCI
 /* Many VIA bridges seem to corrupt data for DAC. Disable it here */
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index d915d956e66d..ec1de97600e7 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -198,7 +198,6 @@ void smp_reschedule_interrupt(struct pt_regs *regs)
 {
         ack_APIC_irq();
         inc_irq_stat(irq_resched_count);
-        run_local_timers();
         /*
          * KVM uses this interrupt to force a cpu out of guest mode
          */
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index dcb00d278512..be2573448ed9 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -38,7 +38,8 @@ unsigned long profile_pc(struct pt_regs *regs)
 #ifdef CONFIG_FRAME_POINTER
                 return *(unsigned long *)(regs->bp + sizeof(long));
 #else
-                unsigned long *sp = (unsigned long *)regs->sp;
+                unsigned long *sp =
+                        (unsigned long *)kernel_stack_pointer(regs);
                 /*
                  * Return address is either directly at stack pointer
                  * or above a saved flags. Eflags has bits 22-31 zero,
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 503c1f2e8835..f99fb6acfe34 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -843,8 +843,8 @@ static int __init uv_bau_init(void)
                                        GFP_KERNEL, cpu_to_node(cur_cpu));
 
         uv_bau_retry_limit = 1;
-        uv_nshift = uv_hub_info->n_val;
-        uv_mmask = (1UL << uv_hub_info->n_val) - 1;
+        uv_nshift = uv_hub_info->m_val;
+        uv_mmask = (1UL << uv_hub_info->m_val) - 1;
         nblades = uv_num_possible_blades();
 
         uv_bau_table_bases = (struct bau_control **)
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
index 699f7eeb896a..cd022121cab6 100644
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@@ -3,8 +3,16 @@
 #include <asm/trampoline.h>
 #include <asm/e820.h>
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP)
+#define __trampinit
+#define __trampinitdata
+#else
+#define __trampinit __cpuinit
+#define __trampinitdata __cpuinitdata
+#endif
+
 /* ready for x86_64 and x86 */
-unsigned char *__cpuinitdata trampoline_base = __va(TRAMPOLINE_BASE);
+unsigned char *__trampinitdata trampoline_base = __va(TRAMPOLINE_BASE);
 
 void __init reserve_trampoline_memory(void)
 {
@@ -26,7 +34,7 @@ void __init reserve_trampoline_memory(void)
  * bootstrap into the page concerned. The caller
  * has made sure it's suitably aligned.
  */
-unsigned long __cpuinit setup_trampoline(void)
+unsigned long __trampinit setup_trampoline(void)
 {
         memcpy(trampoline_base, trampoline_data, TRAMPOLINE_SIZE);
         return virt_to_phys(trampoline_base);
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 596d54c660a5..3af2dff58b21 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -32,8 +32,12 @@
 #include <asm/segment.h>
 #include <asm/processor-flags.h>
 
+#ifdef CONFIG_ACPI_SLEEP
+.section .rodata, "a", @progbits
+#else
 /* We can free up the trampoline after bootup if cpu hotplug is not supported. */
 __CPUINITRODATA
+#endif
 .code16
 
 ENTRY(trampoline_data)
diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 31e6f6cfe53e..d430e4c30193 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -648,7 +648,7 @@ static inline int __init activate_vmi(void)
 
         pv_info.paravirt_enabled = 1;
         pv_info.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
-        pv_info.name = "vmi";
+        pv_info.name = "vmi [deprecated]";
 
         pv_init_ops.patch = vmi_patch;
 
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 92929fb3f9fa..3c68fe2d46cf 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -305,6 +305,9 @@ SECTIONS
 
 
 #ifdef CONFIG_X86_32
+/*
+ * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility:
+ */
 . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE),
            "kernel image bigger than KERNEL_IMAGE_SIZE");
 #else