13 files changed, 66 insertions, 40 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/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index ac95995b7bad..4b180897e6b5 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -31,6 +31,7 @@ extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_shutdown(void);
+extern void amd_iommu_apply_erratum_63(u16 devid);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
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/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 98f230f6a28d..0285521e0a99 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1220,6 +1220,8 @@ static void __detach_device(struct protection_domain *domain, u16 devid)
         amd_iommu_dev_table[devid].data[1] = 0;
         amd_iommu_dev_table[devid].data[2] = 0;
 
+        amd_iommu_apply_erratum_63(devid);
+
         /* decrease reference counter */
         domain->dev_cnt -= 1;
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index b4b61d462dcc..c20001e4f556 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -240,7 +240,7 @@ static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
         writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
 }
 
-static void __init iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
+static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 {
         u32 ctrl;
 
@@ -519,6 +519,26 @@ static void set_dev_entry_bit(u16 devid, u8 bit)
         amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
 }
 
+static int get_dev_entry_bit(u16 devid, u8 bit)
+{
+        int i = (bit >> 5) & 0x07;
+        int _bit = bit & 0x1f;
+
+        return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit;
+}
+
+
+void amd_iommu_apply_erratum_63(u16 devid)
+{
+        int sysmgt;
+
+        sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
+                 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);
+
+        if (sysmgt == 0x01)
+                set_dev_entry_bit(devid, DEV_ENTRY_IW);
+}
+
 /* Writes the specific IOMMU for a device into the rlookup table */
 static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
 {
@@ -547,6 +567,8 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
         if (flags & ACPI_DEVFLAG_LINT1)
                 set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);
 
+        amd_iommu_apply_erratum_63(devid);
+
         set_iommu_for_device(iommu, devid);
 }
 
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/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;