aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig17
-rw-r--r--arch/x86/Kconfig.cpu24
-rw-r--r--arch/x86/boot/compressed/.gitignore2
-rw-r--r--arch/x86/include/asm/acpi.h1
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/dma-mapping.h4
-rw-r--r--arch/x86/include/asm/es7000/wakecpu.h9
-rw-r--r--arch/x86/include/asm/fixmap.h4
-rw-r--r--arch/x86/include/asm/fixmap_32.h4
-rw-r--r--arch/x86/include/asm/ftrace.h4
-rw-r--r--arch/x86/include/asm/highmem.h5
-rw-r--r--arch/x86/include/asm/io.h6
-rw-r--r--arch/x86/include/asm/iomap.h30
-rw-r--r--arch/x86/include/asm/iommu.h2
-rw-r--r--arch/x86/include/asm/irq_vectors.h20
-rw-r--r--arch/x86/include/asm/kvm_host.h3
-rw-r--r--arch/x86/include/asm/mach-default/mach_wakecpu.h9
-rw-r--r--arch/x86/include/asm/mmzone_32.h4
-rw-r--r--arch/x86/include/asm/msr.h2
-rw-r--r--arch/x86/include/asm/pgtable-3level.h4
-rw-r--r--arch/x86/include/asm/smp.h6
-rw-r--r--arch/x86/include/asm/topology.h7
-rw-r--r--arch/x86/include/asm/tsc.h8
-rw-r--r--arch/x86/include/asm/uaccess_64.h2
-rw-r--r--arch/x86/include/asm/unistd_64.h4
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h1
-rw-r--r--arch/x86/include/asm/voyager.h1
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/acpi/boot.c1
-rw-r--r--arch/x86/kernel/amd_iommu.c9
-rw-r--r--arch/x86/kernel/amd_iommu_init.c6
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c2
-rw-r--r--arch/x86/kernel/cpu/common.c7
-rw-r--r--arch/x86/kernel/ds.c25
-rw-r--r--arch/x86/kernel/e820.c8
-rw-r--r--arch/x86/kernel/early-quirks.c18
-rw-r--r--arch/x86/kernel/entry_32.S4
-rw-r--r--arch/x86/kernel/entry_64.S4
-rw-r--r--arch/x86/kernel/es7000_32.c9
-rw-r--r--arch/x86/kernel/ftrace.c50
-rw-r--r--arch/x86/kernel/genx2apic_uv_x.c7
-rw-r--r--arch/x86/kernel/hpet.c4
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c2
-rw-r--r--arch/x86/kernel/io_apic.c16
-rw-r--r--arch/x86/kernel/k8.c1
-rw-r--r--arch/x86/kernel/kvmclock.c2
-rw-r--r--arch/x86/kernel/machine_kexec_32.c5
-rw-r--r--arch/x86/kernel/microcode_amd.c2
-rw-r--r--arch/x86/kernel/microcode_core.c4
-rw-r--r--arch/x86/kernel/pci-dma.c16
-rw-r--r--arch/x86/kernel/pci-gart_64.c2
-rw-r--r--arch/x86/kernel/pci-swiotlb_64.c14
-rw-r--r--arch/x86/kernel/reboot.c15
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/tlb_32.c6
-rw-r--r--arch/x86/kernel/tlb_64.c5
-rw-r--r--arch/x86/kernel/tsc.c12
-rw-r--r--arch/x86/kernel/tsc_sync.c4
-rw-r--r--arch/x86/kernel/vsmp_64.c2
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c2
-rw-r--r--arch/x86/kvm/Kconfig2
-rw-r--r--arch/x86/kvm/i8254.c13
-rw-r--r--arch/x86/kvm/i8254.h1
-rw-r--r--arch/x86/kvm/mmu.c3
-rw-r--r--arch/x86/kvm/vmx.c3
-rw-r--r--arch/x86/kvm/vmx.h1
-rw-r--r--arch/x86/kvm/x86.c6
-rw-r--r--arch/x86/lguest/boot.c32
-rw-r--r--arch/x86/mach-voyager/setup.c2
-rw-r--r--arch/x86/mach-voyager/voyager_smp.c30
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/gup.c2
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c75
-rw-r--r--arch/x86/mm/iomap_32.c59
-rw-r--r--arch/x86/mm/ioremap.c22
-rw-r--r--arch/x86/mm/numa_32.c35
-rw-r--r--arch/x86/mm/pageattr.c8
-rw-r--r--arch/x86/mm/pat.c4
-rw-r--r--arch/x86/oprofile/op_model_ppro.c9
-rw-r--r--arch/x86/power/hibernate_32.c4
-rw-r--r--arch/x86/xen/Makefile2
-rw-r--r--arch/x86/xen/enlighten.c5
-rw-r--r--arch/x86/xen/mmu.c31
84 files changed, 554 insertions, 254 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 350bee1d54d..ac22bb7719f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,7 +28,7 @@ config X86
select HAVE_KRETPROBES
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_DYNAMIC_FTRACE
- select HAVE_FTRACE
+ select HAVE_FUNCTION_TRACER
select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
select HAVE_ARCH_KGDB if !X86_VOYAGER
select HAVE_ARCH_TRACEHOOK
@@ -167,9 +167,12 @@ config GENERIC_PENDING_IRQ
config X86_SMP
bool
depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
- select USE_GENERIC_SMP_HELPERS
default y
+config USE_GENERIC_SMP_HELPERS
+ def_bool y
+ depends on SMP
+
config X86_32_SMP
def_bool y
depends on X86_32 && SMP
@@ -231,6 +234,10 @@ config SMP
If you don't know what to do here, say N.
+config X86_HAS_BOOT_CPU_ID
+ def_bool y
+ depends on X86_VOYAGER
+
config X86_FIND_SMP_CONFIG
def_bool y
depends on X86_MPPARSE || X86_VOYAGER
@@ -1490,7 +1497,7 @@ config HAVE_ARCH_EARLY_PFN_TO_NID
def_bool X86_64
depends on NUMA
-menu "Power management options"
+menu "Power management and ACPI options"
depends on !X86_VOYAGER
config ARCH_HIBERNATION_HEADER
@@ -1890,6 +1897,10 @@ config SYSVIPC_COMPAT
endmenu
+config HAVE_ATOMIC_IOMAP
+ def_bool y
+ depends on X86_32
+
source "net/Kconfig"
source "drivers/Kconfig"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 0b7c4a3f065..b815664fe37 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -513,19 +513,19 @@ config CPU_SUP_UMC_32
If unsure, say N.
config X86_DS
- bool "Debug Store support"
- default y
- help
- Add support for Debug Store.
- This allows the kernel to provide a memory buffer to the hardware
- to store various profiling and tracing events.
+ def_bool X86_PTRACE_BTS
+ depends on X86_DEBUGCTLMSR
config X86_PTRACE_BTS
- bool "ptrace interface to Branch Trace Store"
+ bool "Branch Trace Store"
default y
- depends on (X86_DS && X86_DEBUGCTLMSR)
+ depends on X86_DEBUGCTLMSR
help
- Add a ptrace interface to allow collecting an execution trace
- of the traced task.
- This collects control flow changes in a (cyclic) buffer and allows
- debuggers to fill in the gaps and show an execution trace of the debuggee.
+ This adds a ptrace interface to the hardware's branch trace store.
+
+ Debuggers may use it to collect an execution trace of the debugged
+ application in order to answer the question 'how did I get here?'.
+ Debuggers may trace user mode as well as kernel mode.
+
+ Say Y unless there is no application development on this machine
+ and you want to save a small amount of code size.
diff --git a/arch/x86/boot/compressed/.gitignore b/arch/x86/boot/compressed/.gitignore
index be0ed065249..63eff3b04d0 100644
--- a/arch/x86/boot/compressed/.gitignore
+++ b/arch/x86/boot/compressed/.gitignore
@@ -1 +1,3 @@
relocs
+vmlinux.bin.all
+vmlinux.relocs
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d676d8ecde..9830681446a 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -113,7 +113,6 @@ static inline void acpi_disable_pci(void)
acpi_pci_disabled = 1;
acpi_noirq_set();
}
-extern int acpi_irq_balance_set(char *str);
/* routines for saving/restoring kernel state */
extern int acpi_save_state_mem(void);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f73e95d75b4..cfdf8c2c5c3 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -91,7 +91,7 @@
#define X86_FEATURE_11AP (3*32+19) /* "" Bad local APIC aka 11AP */
#define X86_FEATURE_NOPL (3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_AMDC1E (3*32+21) /* AMD C1E detected */
-#define X86_FEATURE_XTOPOLOGY (3*32+21) /* cpu topology enum extensions */
+#define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* "pni" SSE-3 */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 4a5397bfce2..7f225a4b2a2 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -255,9 +255,11 @@ static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
{
-#ifdef CONFIG_X86_64
unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
+ if (dma_mask <= DMA_24BIT_MASK)
+ gfp |= GFP_DMA;
+#ifdef CONFIG_X86_64
if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
gfp |= GFP_DMA32;
#endif
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
index 3ffc5a7bf66..39849346191 100644
--- a/arch/x86/include/asm/es7000/wakecpu.h
+++ b/arch/x86/include/asm/es7000/wakecpu.h
@@ -50,10 +50,9 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
{
}
-#if APIC_DEBUG
- #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
-#else
- #define inquire_remote_apic(apicid) {}
-#endif
+#define inquire_remote_apic(apicid) do { \
+ if (apic_verbosity >= APIC_DEBUG) \
+ __inquire_remote_apic(apicid); \
+ } while (0)
#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 8668a94f850..23696d44a0a 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -9,6 +9,10 @@
extern int fixmaps_set;
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
void native_set_fixmap(enum fixed_addresses idx,
unsigned long phys, pgprot_t flags);
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
index 09f29ab5c13..c7115c1d721 100644
--- a/arch/x86/include/asm/fixmap_32.h
+++ b/arch/x86/include/asm/fixmap_32.h
@@ -28,10 +28,8 @@ extern unsigned long __FIXADDR_TOP;
#include <asm/acpi.h>
#include <asm/apicdef.h>
#include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
#include <linux/threads.h>
#include <asm/kmap_types.h>
-#endif
/*
* Here we define all the compile-time 'special' virtual
@@ -75,10 +73,8 @@ enum fixed_addresses {
#ifdef CONFIG_X86_CYCLONE_TIMER
FIX_CYCLONE_TIMER, /*cyclone timer register*/
#endif
-#ifdef CONFIG_HIGHMEM
FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */
FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
#ifdef CONFIG_PCI_MMCONFIG
FIX_PCIE_MCFG,
#endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 47f7e65e6c1..9e8bc29b8b1 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -1,7 +1,7 @@
#ifndef _ASM_X86_FTRACE_H
#define _ASM_X86_FTRACE_H
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
#define MCOUNT_ADDR ((long)(mcount))
#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */
@@ -19,6 +19,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
}
#endif
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
#endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index a3b3b7c3027..bf9276bea66 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -25,14 +25,11 @@
#include <asm/kmap_types.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
+#include <asm/fixmap.h>
/* declarations for highmem.c */
extern unsigned long highstart_pfn, highend_pfn;
-extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
-extern pte_t *pkmap_page_table;
-
/*
* Right now we initialize only a single pte table. It can be extended
* easily, subsequent pte tables have to be allocated in one physical
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 5618a103f39..ac2abc88cd9 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -82,9 +82,9 @@ extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
extern void early_ioremap_init(void);
extern void early_ioremap_clear(void);
extern void early_ioremap_reset(void);
-extern void *early_ioremap(unsigned long offset, unsigned long size);
-extern void *early_memremap(unsigned long offset, unsigned long size);
-extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *early_ioremap(unsigned long offset, unsigned long size);
+extern void __iomem *early_memremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void __iomem *addr, unsigned long size);
extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
new file mode 100644
index 00000000000..c1f06289b14
--- /dev/null
+++ b/arch/x86/include/asm/iomap.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 98e28ea8cd1..0b500c5b644 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,8 +6,6 @@ extern void no_iommu_init(void);
extern struct dma_mapping_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
-extern int dmar_disabled;
-extern int forbid_dac;
extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d843ed0e9b2..0005adb0f94 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -101,30 +101,22 @@
#define LAST_VM86_IRQ 15
#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15)
-#ifdef CONFIG_X86_64
+#if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
# if NR_CPUS < MAX_IO_APICS
# define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
# else
# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
# endif
-#elif !defined(CONFIG_X86_VOYAGER)
+#elif defined(CONFIG_X86_VOYAGER)
-# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
-
-# define NR_IRQS 224
-
-# else /* IO_APIC || PARAVIRT */
-
-# define NR_IRQS 16
-
-# endif
+# define NR_IRQS 224
-#else /* !VISWS && !VOYAGER */
+#else /* IO_APIC || VOYAGER */
-# define NR_IRQS 224
+# define NR_IRQS 16
-#endif /* VISWS */
+#endif
/* Voyager specific defines */
/* These define the CPIs we use in linux */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 65679d00633..8346be87cfa 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -364,6 +364,9 @@ struct kvm_arch{
struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
+
+ unsigned long irq_sources_bitmap;
+ unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
};
struct kvm_vm_stat {
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
index d5c0b826a4f..9d80db91e99 100644
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -33,10 +33,9 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
{
}
-#if APIC_DEBUG
- #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
-#else
- #define inquire_remote_apic(apicid) {}
-#endif
+#define inquire_remote_apic(apicid) do { \
+ if (apic_verbosity >= APIC_DEBUG) \
+ __inquire_remote_apic(apicid); \
+ } while (0)
#endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 485bdf059ff..07f1af494ca 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -34,10 +34,14 @@ static inline void get_memcfg_numa(void)
extern int early_pfn_to_nid(unsigned long pfn);
+extern void resume_map_numa_kva(pgd_t *pgd);
+
#else /* !CONFIG_NUMA */
#define get_memcfg_numa get_memcfg_numa_flat
+static inline void resume_map_numa_kva(pgd_t *pgd) {}
+
#endif /* CONFIG_NUMA */
#ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 46be2fa7ac2..c2a812ebde8 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -108,9 +108,7 @@ static __always_inline unsigned long long __native_read_tsc(void)
{
DECLARE_ARGS(val, low, high);
- rdtsc_barrier();
asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
- rdtsc_barrier();
return EAX_EDX_VAL(val, low, high);
}
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index fb16cec702e..52597aeadff 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -120,13 +120,13 @@ static inline void pud_clear(pud_t *pudp)
write_cr3(pgd);
}
-#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK))
+#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *)pud_page(*(pud)) + \
+#define pmd_offset(pud, address) ((pmd_t *)pud_page_vaddr(*(pud)) + \
pmd_index(address))
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 2766021aef8..d12811ce51d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -225,5 +225,11 @@ static inline int hard_smp_processor_id(void)
#endif /* CONFIG_X86_LOCAL_APIC */
+#ifdef CONFIG_X86_HAS_BOOT_CPU_ID
+extern unsigned char boot_cpu_id;
+#else
+#define boot_cpu_id 0
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SMP_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 90ac7718469..4850e4b02b6 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -154,7 +154,7 @@ extern unsigned long node_remap_size[];
#endif
-/* sched_domains SD_NODE_INIT for NUMAQ machines */
+/* sched_domains SD_NODE_INIT for NUMA machines */
#define SD_NODE_INIT (struct sched_domain) { \
.min_interval = 8, \
.max_interval = 32, \
@@ -169,8 +169,9 @@ extern unsigned long node_remap_size[];
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_EXEC \
| SD_BALANCE_FORK \
- | SD_SERIALIZE \
- | SD_WAKE_BALANCE, \
+ | SD_WAKE_AFFINE \
+ | SD_WAKE_BALANCE \
+ | SD_SERIALIZE, \
.last_balance = jiffies, \
.balance_interval = 1, \
}
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 38ae163cc91..9cd83a8e40d 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,6 +34,8 @@ static inline cycles_t get_cycles(void)
static __always_inline cycles_t vget_cycles(void)
{
+ cycles_t cycles;
+
/*
* We only do VDSOs on TSC capable CPUs, so this shouldnt
* access boot_cpu_data (which is not VDSO-safe):
@@ -42,7 +44,11 @@ static __always_inline cycles_t vget_cycles(void)
if (!cpu_has_tsc)
return 0;
#endif
- return (cycles_t)__native_read_tsc();
+ rdtsc_barrier();
+ cycles = (cycles_t)__native_read_tsc();
+ rdtsc_barrier();
+
+ return cycles;
}
extern void tsc_init(void);
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f15280f1..f8cfd00db45 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,7 +46,7 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
return ret;
case 10:
__get_user_asm(*(u64 *)dst, (u64 __user *)src,
- ret, "q", "", "=r", 16);
+ ret, "q", "", "=r", 10);
if (unlikely(ret))
return ret;
__get_user_asm(*(u16 *)(8 + (char *)dst),
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 834b2c1d89f..d2e415e6666 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -639,8 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate)
__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
#define __NR_timerfd_gettime 287
__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
-#define __NR_paccept 288
-__SYSCALL(__NR_paccept, sys_paccept)
+#define __NR_accept4 288
+__SYSCALL(__NR_accept4, sys_accept4)
#define __NR_signalfd4 289
__SYSCALL(__NR_signalfd4, sys_signalfd4)
#define __NR_eventfd2 290
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index c6ad93e315c..7a5782610b2 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -13,6 +13,7 @@
#include <linux/numa.h>
#include <linux/percpu.h>
+#include <linux/timer.h>
#include <asm/types.h>
#include <asm/percpu.h>
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
index 9c811d2e6f9..b3e64730762 100644
--- a/arch/x86/include/asm/voyager.h
+++ b/arch/x86/include/asm/voyager.h
@@ -520,6 +520,7 @@ extern void voyager_restart(void);
extern void voyager_cat_power_off(void);
extern void voyager_cat_do_common_interrupt(void);
extern void voyager_handle_nmi(void);
+extern void voyager_smp_intr_init(void);
/* Commands for the following are */
#define VOYAGER_PSI_READ 0
#define VOYAGER_PSI_WRITE 1
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index d7e5a58ee22..e489ff9cb3e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -6,11 +6,12 @@ extra-y := head_$(BITS).o head$(BITS).o head.o init_task.o vmlinu
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_tsc.o = -pg
CFLAGS_REMOVE_rtc.o = -pg
CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
+CFLAGS_REMOVE_ftrace.o = -pg
endif
#
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 8c1f76abae9..4c51a2f8fd3 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1343,7 +1343,6 @@ static void __init acpi_process_madt(void)
error = acpi_parse_madt_ioapic_entries();
if (!error) {
acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
- acpi_irq_balance_set(NULL);
acpi_ioapic = 1;
smp_found_config = 1;
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a8fd9ebdc8e..e4899e0e878 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -50,7 +50,7 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
/* returns !0 if the IOMMU is caching non-present entries in its TLB */
static int iommu_has_npcache(struct amd_iommu *iommu)
{
- return iommu->cap & IOMMU_CAP_NPCACHE;
+ return iommu->cap & (1UL << IOMMU_CAP_NPCACHE);
}
/****************************************************************************
@@ -536,6 +536,9 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
{
address >>= PAGE_SHIFT;
iommu_area_free(dom->bitmap, address, pages);
+
+ if (address >= dom->next_bit)
+ dom->need_flush = true;
}
/****************************************************************************
@@ -992,8 +995,10 @@ static void __unmap_single(struct amd_iommu *iommu,
dma_ops_free_addresses(dma_dom, dma_addr, pages);
- if (amd_iommu_unmap_flush)
+ if (amd_iommu_unmap_flush || dma_dom->need_flush) {
iommu_flush_pages(iommu, dma_dom->domain.id, dma_addr, size);
+ dma_dom->need_flush = false;
+ }
}
/*
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 0cdcda35a05..30ae2701b3d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -121,7 +121,7 @@ u16 amd_iommu_last_bdf; /* largest PCI device id we have
LIST_HEAD(amd_iommu_unity_map); /* a list of required unity mappings
we find in ACPI */
unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
-int amd_iommu_isolate; /* if 1, device isolation is enabled */
+int amd_iommu_isolate = 1; /* if 1, device isolation is enabled */
bool amd_iommu_unmap_flush; /* if true, flush on every unmap */
LIST_HEAD(amd_iommu_list); /* list of all AMD IOMMUs in the
@@ -1213,7 +1213,9 @@ static int __init parse_amd_iommu_options(char *str)
for (; *str; ++str) {
if (strncmp(str, "isolate", 7) == 0)
amd_iommu_isolate = 1;
- if (strncmp(str, "fullflush", 11) == 0)
+ if (strncmp(str, "share", 5) == 0)
+ amd_iommu_isolate = 0;
+ if (strncmp(str, "fullflush", 9) == 0)
amd_iommu_unmap_flush = true;
}
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 0d9c993aa93..ef8f831af82 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -69,7 +69,7 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
*/
void __cpuinit detect_extended_topology(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_SMP
+#ifdef CONFIG_X86_SMP
unsigned int eax, ebx, ecx, edx, sub_index;
unsigned int ht_mask_width, core_plus_mask_width;
unsigned int core_select_mask, core_level_siblings;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 25581dcb280..b9c9ea0217a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -20,6 +20,7 @@
#include <asm/pat.h>
#include <asm/asm.h>
#include <asm/numa.h>
+#include <asm/smp.h>
#ifdef CONFIG_X86_LOCAL_APIC
#include <asm/mpspec.h>
#include <asm/apic.h>
@@ -549,6 +550,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
this_cpu->c_early_init(c);
validate_pat_support(c);
+
+#ifdef CONFIG_SMP
+ c->cpu_index = boot_cpu_id;
+#endif
}
void __init early_cpu_init(void)
@@ -1134,7 +1139,7 @@ void __cpuinit cpu_init(void)
/*
* Boot processor to setup the FP and extended state context info.
*/
- if (!smp_processor_id())
+ if (smp_processor_id() == boot_cpu_id)
init_thread_xstate();
xsave_init();
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 2b69994fd3a..d1a121443bd 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -236,17 +236,33 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task)
struct ds_context *context = *p_context;
if (!context) {
+ spin_unlock(&ds_lock);
+
context = kzalloc(sizeof(*context), GFP_KERNEL);
- if (!context)
+ if (!context) {
+ spin_lock(&ds_lock);
return NULL;
+ }
context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
if (!context->ds) {
kfree(context);
+ spin_lock(&ds_lock);
return NULL;
}
+ spin_lock(&ds_lock);
+ /*
+ * Check for race - another CPU could have allocated
+ * it meanwhile:
+ */
+ if (*p_context) {
+ kfree(context->ds);
+ kfree(context);
+ return *p_context;
+ }
+
*p_context = context;
context->this = p_context;
@@ -384,14 +400,15 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
spin_lock(&ds_lock);
- if (!check_tracer(task))
- return -EPERM;
-
error = -ENOMEM;
context = ds_alloc_context(task);
if (!context)
goto out_unlock;
+ error = -EPERM;
+ if (!check_tracer(task))
+ goto out_unlock;
+
error = -EALREADY;
if (context->owner[qual] == current)
goto out_unlock;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index ce97bf3bed1..7aafeb5263e 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1290,15 +1290,17 @@ void __init e820_reserve_resources(void)
res->start = e820.map[i].addr;
res->end = end;
- res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ res->flags = IORESOURCE_MEM;
/*
* don't register the region that could be conflicted with
* pci device BAR resource and insert them later in
* pcibios_resource_survey()
*/
- if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20))
+ if (e820.map[i].type != E820_RESERVED || res->start < (1ULL<<20)) {
+ res->flags |= IORESOURCE_BUSY;
insert_resource(&iomem_resource, res);
+ }
res++;
}
@@ -1318,7 +1320,7 @@ void __init e820_reserve_resources_late(void)
res = e820_res;
for (i = 0; i < e820.nr_map; i++) {
if (!res->parent && res->end)
- reserve_region_with_split(&iomem_resource, res->start, res->end, res->name);
+ insert_resource_expand_to_fit(&iomem_resource, res);
res++;
}
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 3ce029ffaa5..1b894b72c0f 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -188,20 +188,6 @@ static void __init ati_bugs_contd(int num, int slot, int func)
}
#endif
-#ifdef CONFIG_DMAR
-static void __init intel_g33_dmar(int num, int slot, int func)
-{
- struct acpi_table_header *dmar_tbl;
- acpi_status status;
-
- status = acpi_get_table(ACPI_SIG_DMAR, 0, &dmar_tbl);
- if (ACPI_SUCCESS(status)) {
- printk(KERN_INFO "BIOS BUG: DMAR advertised on Intel G31/G33 chipset -- ignoring\n");
- dmar_disabled = 1;
- }
-}
-#endif
-
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -225,10 +211,6 @@ static struct chipset early_qrk[] __initdata = {
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
-#ifdef CONFIG_DMAR
- { PCI_VENDOR_ID_INTEL, 0x29c0,
- PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar },
-#endif
{}
};
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index dd65143941a..28b597ef9ca 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1149,7 +1149,7 @@ ENDPROC(xen_failsafe_callback)
#endif /* CONFIG_XEN */
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
@@ -1204,7 +1204,7 @@ trace:
jmp ftrace_stub
END(mcount)
#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
.section .rodata,"a"
#include "syscall_table_32.S"
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 09e7145484c..b86f332c96a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -61,7 +61,7 @@
.code64
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(mcount)
retq
@@ -138,7 +138,7 @@ trace:
jmp ftrace_stub
END(mcount)
#endif /* CONFIG_DYNAMIC_FTRACE */
-#endif /* CONFIG_FTRACE */
+#endif /* CONFIG_FUNCTION_TRACER */
#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index f454c78fcef..0aa2c443d60 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -250,31 +250,24 @@ int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
{
struct acpi_table_header *header = NULL;
int i = 0;
- acpi_size tbl_size;
- while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) {
+ while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) {
if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) {
struct oem_table *t = (struct oem_table *)header;
oem_addrX = t->OEMTableAddr;
oem_size = t->OEMTableSize;
- early_acpi_os_unmap_memory(header, tbl_size);
*oem_addr = (unsigned long)__acpi_map_table(oem_addrX,
oem_size);
return 0;
}
- early_acpi_os_unmap_memory(header, tbl_size);
}
return -1;
}
void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
{
- if (!oem_addr)
- return;
-
- __acpi_unmap_table((char *)oem_addr, oem_size);
}
#endif
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d073d981a73..50ea0ac8c9b 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -21,8 +21,7 @@
#include <asm/nops.h>
-/* Long is fine, even if it is only 4 bytes ;-) */
-static unsigned long *ftrace_nop;
+static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
union ftrace_code_union {
char code[MCOUNT_INSN_SIZE];
@@ -33,17 +32,17 @@ union ftrace_code_union {
};
-static int notrace ftrace_calc_offset(long ip, long addr)
+static int ftrace_calc_offset(long ip, long addr)
{
return (int)(addr - ip);
}
-notrace unsigned char *ftrace_nop_replace(void)
+unsigned char *ftrace_nop_replace(void)
{
- return (char *)ftrace_nop;
+ return ftrace_nop;
}
-notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
{
static union ftrace_code_union calc;
@@ -57,7 +56,7 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
return calc.code;
}
-notrace int
+int
ftrace_modify_code(unsigned long ip, unsigned char *old_code,
unsigned char *new_code)
{
@@ -66,26 +65,31 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
/*
* Note: Due to modules and __init, code can
* disappear and change, we need to protect against faulting
- * as well as code changing.
+ * as well as code changing. We do this by using the
+ * probe_kernel_* functions.
*
* No real locking needed, this code is run through
* kstop_machine, or before SMP starts.
*/
- if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE))
- return 1;
+ /* read the text we want to modify */
+ if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+ return -EFAULT;
+
+ /* Make sure it is what we expect it to be */
if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
- return 2;
+ return -EINVAL;
- WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
- MCOUNT_INSN_SIZE));
+ /* replace the text with the new text */
+ if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+ return -EPERM;
sync_core();
return 0;
}
-notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+int ftrace_update_ftrace_func(ftrace_func_t func)
{
unsigned long ip = (unsigned long)(&ftrace_call);
unsigned char old[MCOUNT_INSN_SIZE], *new;
@@ -98,13 +102,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func)
return ret;
}
-notrace int ftrace_mcount_set(unsigned long *data)
-{
- /* mcount is initialized as a nop */
- *data = 0;
- return 0;
-}
-
int __init ftrace_dyn_arch_init(void *data)
{
extern const unsigned char ftrace_test_p6nop[];
@@ -127,9 +124,6 @@ int __init ftrace_dyn_arch_init(void *data)
* TODO: check the cpuid to determine the best nop.
*/
asm volatile (
- "jmp ftrace_test_jmp\n"
- /* This code needs to stay around */
- ".section .text, \"ax\"\n"
"ftrace_test_jmp:"
"jmp ftrace_test_p6nop\n"
"nop\n"
@@ -140,8 +134,6 @@ int __init ftrace_dyn_arch_init(void *data)
"jmp 1f\n"
"ftrace_test_nop5:"
".byte 0x66,0x66,0x66,0x66,0x90\n"
- "jmp 1f\n"
- ".previous\n"
"1:"
".section .fixup, \"ax\"\n"
"2: movl $1, %0\n"
@@ -156,15 +148,15 @@ int __init ftrace_dyn_arch_init(void *data)
switch (faulted) {
case 0:
pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
- ftrace_nop = (unsigned long *)ftrace_test_p6nop;
+ memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
break;
case 1:
pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
- ftrace_nop = (unsigned long *)ftrace_test_nop5;
+ memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
break;
case 2:
pr_info("ftrace: converting mcount calls to jmp . + 5\n");
- ftrace_nop = (unsigned long *)ftrace_test_jmp;
+ memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
break;
}
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 680a06557c5..2c7dbdb9827 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -15,7 +15,6 @@
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/sched.h>
-#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/hardirq.h>
#include <asm/smp.h>
@@ -398,16 +397,16 @@ void __init uv_system_init(void)
printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
- uv_blade_info = alloc_bootmem_pages(bytes);
+ uv_blade_info = kmalloc(bytes, GFP_KERNEL);
get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
- uv_node_to_blade = alloc_bootmem_pages(bytes);
+ uv_node_to_blade = kmalloc(bytes, GFP_KERNEL);
memset(uv_node_to_blade, 255, bytes);
bytes = sizeof(uv_cpu_to_blade[0]) * num_possible_cpus();
- uv_cpu_to_blade = alloc_bootmem_pages(bytes);
+ uv_cpu_to_blade = kmalloc(bytes, GFP_KERNEL);
memset(uv_cpu_to_blade, 255, bytes);
blade = 0;
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 77017e834cf..067d8de913f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -322,7 +322,7 @@ static int hpet_next_event(unsigned long delta,
* what we wrote hit the chip before we compare it to the
* counter.
*/
- WARN_ON((u32)hpet_readl(HPET_T0_CMP) != cnt);
+ WARN_ON_ONCE((u32)hpet_readl(HPET_Tn_CMP(timer)) != cnt);
return (s32)((u32)hpet_readl(HPET_COUNTER) - cnt) >= 0 ? -ETIME : 0;
}
@@ -445,7 +445,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
{
if (request_irq(dev->irq, hpet_interrupt_handler,
- IRQF_SHARED|IRQF_NOBALANCING, dev->name, dev))
+ IRQF_DISABLED|IRQF_NOBALANCING, dev->name, dev))
return -1;
disable_irq(dev->irq);
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index dd7ebee446a..43cec6bdda6 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -5,7 +5,7 @@
#include <asm/desc.h>
#include <asm/ftrace.h>
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
/* mcount is defined in assembly */
EXPORT_SYMBOL(mcount);
#endif
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index b764d7429c6..c9513e1ff28 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq)
cfg->vector = 0;
cpus_clear(cfg->domain);
+
+ if (likely(!cfg->move_in_progress))
+ return;
+ cpus_and(mask, cfg->old_domain, cpu_online_map);
+ for_each_cpu_mask_nr(cpu, mask) {
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+ vector++) {
+ if (per_cpu(vector_irq, cpu)[vector] != irq)
+ continue;
+ per_cpu(vector_irq, cpu)[vector] = -1;
+ break;
+ }
+ }
+ cfg->move_in_progress = 0;
}
void __setup_vector_irq(int cpu)
@@ -3611,6 +3625,8 @@ int __init probe_nr_irqs(void)
/* something wrong ? */
if (nr < nr_min)
nr = nr_min;
+ if (WARN_ON(nr > NR_IRQS))
+ nr = NR_IRQS;
return nr;
}
diff --git a/arch/x86/kernel/k8.c b/arch/x86/kernel/k8.c
index 304d8bad655..cbc4332a77b 100644
--- a/arch/x86/kernel/k8.c
+++ b/arch/x86/kernel/k8.c
@@ -18,7 +18,6 @@ static u32 *flush_words;
struct pci_device_id k8_nb_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
- { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_11H_NB_MISC) },
{}
};
EXPORT_SYMBOL(k8_nb_ids);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 774ac499156..1c9cc431ea4 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -128,7 +128,7 @@ static int kvm_register_clock(char *txt)
}
#ifdef CONFIG_X86_LOCAL_APIC
-static void kvm_setup_secondary_clock(void)
+static void __devinit kvm_setup_secondary_clock(void)
{
/*
* Now that the first cpu already had this clocksource initialized,
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 0732adba05c..7a385746509 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -162,7 +162,10 @@ void machine_kexec(struct kimage *image)
page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
page_list[PA_PTE_1] = __pa(kexec_pte1);
page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
- page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT);
+
+ if (image->type == KEXEC_TYPE_DEFAULT)
+ page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
+ << PAGE_SHIFT);
/* The segment registers are funny things, they have both a
* visible and an invisible part. Whenever the visible part is
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7a1f8eeac2c..5f8e5d75a25 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -39,7 +39,7 @@
#include <asm/microcode.h>
MODULE_DESCRIPTION("AMD Microcode Update Driver");
-MODULE_AUTHOR("Peter Oruba <peter.oruba@amd.com>");
+MODULE_AUTHOR("Peter Oruba");
MODULE_LICENSE("GPL v2");
#define UCODE_MAGIC 0x00414d44
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 936d8d55f23..82fb2809ce3 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -480,8 +480,8 @@ static int __init microcode_init(void)
printk(KERN_INFO
"Microcode Update Driver: v" MICROCODE_VERSION
- " <tigran@aivazian.fsnet.co.uk>"
- " <peter.oruba@amd.com>\n");
+ " <tigran@aivazian.fsnet.co.uk>,"
+ " Peter Oruba\n");
return 0;
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1972266e8ba..19262482021 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -9,6 +9,8 @@
#include <asm/calgary.h>
#include <asm/amd_iommu.h>
+static int forbid_dac __read_mostly;
+
struct dma_mapping_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
@@ -291,3 +293,17 @@ void pci_iommu_shutdown(void)
}
/* Must execute after PCI subsystem */
fs_initcall(pci_iommu_init);
+
+#ifdef CONFIG_PCI
+/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
+
+static __devinit void via_no_dac(struct pci_dev *dev)
+{
+ if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
+ printk(KERN_INFO "PCI: VIA PCI bridge detected."
+ "Disabling DAC.\n");
+ forbid_dac = 1;
+ }
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
+#endif
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index e3f75bbcede..a42b02b4df6 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -744,7 +744,7 @@ void __init gart_iommu_init(void)
long i;
if (cache_k8_northbridges() < 0 || num_k8_northbridges == 0) {
- printk(KERN_INFO "PCI-GART: No AMD northbridge found.\n");
+ printk(KERN_INFO "PCI-GART: No AMD GART found.\n");
return;
}
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index c4ce0332759..3c539d111ab 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -18,9 +18,21 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
}
+static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flags)
+{
+ void *vaddr;
+
+ vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+ if (vaddr)
+ return vaddr;
+
+ return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
+}
+
struct dma_mapping_ops swiotlb_dma_ops = {
.mapping_error = swiotlb_dma_mapping_error,
- .alloc_coherent = swiotlb_alloc_coherent,
+ .alloc_coherent = x86_swiotlb_alloc_coherent,
.free_coherent = swiotlb_free_coherent,
.map_single = swiotlb_map_single_phys,
.unmap_single = swiotlb_unmap_single,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f4c93f1cfc1..cc5a2545dd4 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -29,11 +29,7 @@ EXPORT_SYMBOL(pm_power_off);
static const struct desc_ptr no_idt = {};
static int reboot_mode;
-/*
- * Keyboard reset and triple fault may result in INIT, not RESET, which
- * doesn't work when we're in vmx root mode. Try ACPI first.
- */
-enum reboot_type reboot_type = BOOT_ACPI;
+enum reboot_type reboot_type = BOOT_KBD;
int reboot_force;
#if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
@@ -173,6 +169,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
},
},
+ { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+ .callback = set_bios_reboot,
+ .ident = "Dell OptiPlex 330",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+ DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+ },
+ },
{ /* Handle problems with rebooting on Dell 2400's */
.callback = set_bios_reboot,
.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0fa6790c1dd..9d5674f7b6c 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -764,7 +764,7 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
.callback = dmi_low_memory_corruption,
.ident = "Phoenix BIOS",
.matches = {
- DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+ DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
},
},
#endif
diff --git a/arch/x86/kernel/tlb_32.c b/arch/x86/kernel/tlb_32.c
index e00534b3353..f4049f3513b 100644
--- a/arch/x86/kernel/tlb_32.c
+++ b/arch/x86/kernel/tlb_32.c
@@ -154,6 +154,12 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
flush_mm = mm;
flush_va = va;
cpus_or(flush_cpumask, cpumask, flush_cpumask);
+
+ /*
+ * Make the above memory operations globally visible before
+ * sending the IPI.
+ */
+ smp_mb();
/*
* We have to send the IPI only to
* CPUs affected.
diff --git a/arch/x86/kernel/tlb_64.c b/arch/x86/kernel/tlb_64.c
index dcbf7a1159e..8f919ca6949 100644
--- a/arch/x86/kernel/tlb_64.c
+++ b/arch/x86/kernel/tlb_64.c
@@ -183,6 +183,11 @@ void native_flush_tlb_others(const cpumask_t *cpumaskp, struct mm_struct *mm,
cpus_or(f->flush_cpumask, cpumask, f->flush_cpumask);
/*
+ * Make the above memory operations globally visible before
+ * sending the IPI.
+ */
+ smp_mb();
+ /*
* We have to send the IPI only to
* CPUs affected.
*/
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 161bb850fc4..424093b157d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -55,7 +55,7 @@ u64 native_sched_clock(void)
rdtscll(this_offset);
/* return the value in ns */
- return cycles_2_ns(this_offset);
+ return __cycles_2_ns(this_offset);
}
/* We need to define a real function for sched_clock, to override the
@@ -759,7 +759,7 @@ __cpuinit int unsynchronized_tsc(void)
if (!cpu_has_tsc || tsc_unstable)
return 1;
-#ifdef CONFIG_SMP
+#ifdef CONFIG_X86_SMP
if (apic_is_clustered_box())
return 1;
#endif
@@ -813,10 +813,6 @@ void __init tsc_init(void)
cpu_khz = calibrate_cpu();
#endif
- lpj = ((u64)tsc_khz * 1000);
- do_div(lpj, HZ);
- lpj_fine = lpj;
-
printk("Detected %lu.%03lu MHz processor.\n",
(unsigned long)cpu_khz / 1000,
(unsigned long)cpu_khz % 1000);
@@ -836,6 +832,10 @@ void __init tsc_init(void)
/* now allow native_sched_clock() to use rdtsc */
tsc_disabled = 0;
+ lpj = ((u64)tsc_khz * 1000);
+ do_div(lpj, HZ);
+ lpj_fine = lpj;
+
use_tsc_delay();
/* Check and install the TSC clocksource */
dmi_check_system(bad_tsc_dmi_table);
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 9ffb01c31c4..1c0dfbca87c 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -46,7 +46,9 @@ static __cpuinit void check_tsc_warp(void)
cycles_t start, now, prev, end;
int i;
+ rdtsc_barrier();
start = get_cycles();
+ rdtsc_barrier();
/*
* The measurement runs for 20 msecs:
*/
@@ -61,7 +63,9 @@ static __cpuinit void check_tsc_warp(void)
*/
__raw_spin_lock(&sync_lock);
prev = last_tsc;
+ rdtsc_barrier();
now = get_cycles();
+ rdtsc_barrier();
last_tsc = now;
__raw_spin_unlock(&sync_lock);
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 7766d36983f..a688f3bfaec 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -78,7 +78,7 @@ static unsigned __init_or_module vsmp_patch(u8 type, u16 clobbers, void *ibuf,
static void __init set_vsmp_pv_ops(void)
{
- void *address;
+ void __iomem *address;
unsigned int cap, ctl, cfg;
/* set vSMP magic bits to indicate vSMP capable kernel */
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index b545f371b5f..695e426aa35 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -12,7 +12,7 @@
#include <asm/desc.h>
#include <asm/ftrace.h>
-#ifdef CONFIG_FTRACE
+#ifdef CONFIG_FUNCTION_TRACER
/* mcount is defined in assembly */
EXPORT_SYMBOL(mcount);
#endif
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index ce3251ce550..b81125f0bde 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -20,6 +20,8 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support"
depends on HAVE_KVM
+ # for device assignment:
+ depends on PCI
select PREEMPT_NOTIFIERS
select MMU_NOTIFIER
select ANON_INODES
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 11c6725fb79..59ebd37ad79 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -545,6 +545,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
if (!pit)
return NULL;
+ mutex_lock(&kvm->lock);
+ pit->irq_source_id = kvm_request_irq_source_id(kvm);
+ mutex_unlock(&kvm->lock);
+ if (pit->irq_source_id < 0) {
+ kfree(pit);
+ return NULL;
+ }
+
mutex_init(&pit->pit_state.lock);
mutex_lock(&pit->pit_state.lock);
spin_lock_init(&pit->pit_state.inject_lock);
@@ -587,6 +595,7 @@ void kvm_free_pit(struct kvm *kvm)
mutex_lock(&kvm->arch.vpit->pit_state.lock);
timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
hrtimer_cancel(timer);
+ kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
kfree(kvm->arch.vpit);
}
@@ -595,8 +604,8 @@ void kvm_free_pit(struct kvm *kvm)
static void __inject_pit_timer_intr(struct kvm *kvm)
{
mutex_lock(&kvm->lock);
- kvm_set_irq(kvm, 0, 1);
- kvm_set_irq(kvm, 0, 0);
+ kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
+ kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
mutex_unlock(&kvm->lock);
}
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index e436d4983aa..4178022b97a 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -44,6 +44,7 @@ struct kvm_pit {
struct kvm_io_device speaker_dev;
struct kvm *kvm;
struct kvm_kpit_state pit_state;
+ int irq_source_id;
};
#define KVM_PIT_BASE_ADDRESS 0x40
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 99c239c5c0a..f1983d9477c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -314,7 +314,7 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu)
if (r)
goto out;
r = mmu_topup_memory_cache(&vcpu->arch.mmu_rmap_desc_cache,
- rmap_desc_cache, 1);
+ rmap_desc_cache, 4);
if (r)
goto out;
r = mmu_topup_memory_cache_page(&vcpu->arch.mmu_page_cache, 8);
@@ -2634,6 +2634,7 @@ static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu,
static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
{
kvm_x86_ops->tlb_flush(vcpu);
+ set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
return 1;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2643b430d83..d06b4dc0e2e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3564,7 +3564,8 @@ static int __init vmx_init(void)
bypass_guest_pf = 0;
kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
VMX_EPT_WRITABLE_MASK |
- VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
+ VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT |
+ VMX_EPT_IGMT_BIT);
kvm_mmu_set_mask_ptes(0ull, 0ull, 0ull, 0ull,
VMX_EPT_EXECUTABLE_MASK);
kvm_enable_tdp();
diff --git a/arch/x86/kvm/vmx.h b/arch/x86/kvm/vmx.h
index 3e010d21fdd..ec5edc339da 100644
--- a/arch/x86/kvm/vmx.h
+++ b/arch/x86/kvm/vmx.h
@@ -352,6 +352,7 @@ enum vmcs_field {
#define VMX_EPT_READABLE_MASK 0x1ull
#define VMX_EPT_WRITABLE_MASK 0x2ull
#define VMX_EPT_EXECUTABLE_MASK 0x4ull
+#define VMX_EPT_IGMT_BIT (1ull << 6)
#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4f0677d1eae..f1f8ff2f1fa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1742,7 +1742,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
goto out;
if (irqchip_in_kernel(kvm)) {
mutex_lock(&kvm->lock);
- kvm_set_irq(kvm, irq_event.irq, irq_event.level);
+ kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+ irq_event.irq, irq_event.level);
mutex_unlock(&kvm->lock);
r = 0;
}
@@ -4013,6 +4014,9 @@ struct kvm *kvm_arch_create_vm(void)
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
+ /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
+ set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
+
return kvm;
}
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 48ee4f9435f..a5d8e1ace1c 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -367,10 +367,9 @@ static void lguest_cpuid(unsigned int *ax, unsigned int *bx,
* lazily after a task switch, and Linux uses that gratefully, but wouldn't a
* name like "FPUTRAP bit" be a little less cryptic?
*
- * We store cr0 (and cr3) locally, because the Host never changes it. The
- * Guest sometimes wants to read it and we'd prefer not to bother the Host
- * unnecessarily. */
-static unsigned long current_cr0, current_cr3;
+ * We store cr0 locally because the Host never changes it. The Guest sometimes
+ * wants to read it and we'd prefer not to bother the Host unnecessarily. */
+static unsigned long current_cr0;
static void lguest_write_cr0(unsigned long val)
{
lazy_hcall(LHCALL_TS, val & X86_CR0_TS, 0, 0);
@@ -399,17 +398,23 @@ static unsigned long lguest_read_cr2(void)
return lguest_data.cr2;
}
+/* See lguest_set_pte() below. */
+static bool cr3_changed = false;
+
/* cr3 is the current toplevel pagetable page: the principle is the same as
- * cr0. Keep a local copy, and tell the Host when it changes. */
+ * cr0. Keep a local copy, and tell the Host when it changes. The only
+ * difference is that our local copy is in lguest_data because the Host needs
+ * to set it upon our initial hypercall. */
static void lguest_write_cr3(unsigned long cr3)
{
+ lguest_data.pgdir = cr3;
lazy_hcall(LHCALL_NEW_PGTABLE, cr3, 0, 0);
- current_cr3 = cr3;
+ cr3_changed = true;
}
static unsigned long lguest_read_cr3(void)
{
- return current_cr3;
+ return lguest_data.pgdir;
}
/* cr4 is used to enable and disable PGE, but we don't care. */
@@ -498,13 +503,13 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval)
* to forget all of them. Fortunately, this is very rare.
*
* ... except in early boot when the kernel sets up the initial pagetables,
- * which makes booting astonishingly slow. So we don't even tell the Host
- * anything changed until we've done the first page table switch. */
+ * which makes booting astonishingly slow: 1.83 seconds! So we don't even tell
+ * the Host anything changed until we've done the first page table switch,
+ * which brings boot back to 0.25 seconds. */
static void lguest_set_pte(pte_t *ptep, pte_t pteval)
{
*ptep = pteval;
- /* Don't bother with hypercall before initial setup. */
- if (current_cr3)
+ if (cr3_changed)
lazy_hcall(LHCALL_FLUSH_TLB, 1, 0, 0);
}
@@ -521,7 +526,7 @@ static void lguest_set_pte(pte_t *ptep, pte_t pteval)
static void lguest_flush_tlb_single(unsigned long addr)
{
/* Simply set it to zero: if it was not, it will fault back in. */
- lazy_hcall(LHCALL_SET_PTE, current_cr3, addr, 0);
+ lazy_hcall(LHCALL_SET_PTE, lguest_data.pgdir, addr, 0);
}
/* This is what happens after the Guest has removed a large number of entries.
@@ -581,6 +586,9 @@ static void __init lguest_init_IRQ(void)
for (i = 0; i < LGUEST_IRQS; i++) {
int vector = FIRST_EXTERNAL_VECTOR + i;
+ /* Some systems map "vectors" to interrupts weirdly. Lguest has
+ * a straightforward 1 to 1 mapping, so force that here. */
+ __get_cpu_var(vector_irq)[vector] = i;
if (vector != SYSCALL_VECTOR) {
set_intr_gate(vector, interrupt[vector]);
set_irq_chip_and_handler_name(i, &lguest_irq_controller,
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index 6bbdd633864..a580b9562e7 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -27,7 +27,7 @@ static struct irqaction irq2 = {
void __init intr_init_hook(void)
{
#ifdef CONFIG_SMP
- smp_intr_init();
+ voyager_smp_intr_init();
#endif
setup_irq(2, &irq2);
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 0f6e8a6523a..52145007bd7 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -7,6 +7,7 @@
* This file provides all the same external entries as smp.c but uses
* the voyager hal to provide the functionality
*/
+#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
@@ -90,6 +91,7 @@ static void ack_vic_irq(unsigned int irq);
static void vic_enable_cpi(void);
static void do_boot_cpu(__u8 cpuid);
static void do_quad_bootstrap(void);
+static void initialize_secondary(void);
int hard_smp_processor_id(void);
int safe_smp_processor_id(void);
@@ -344,6 +346,12 @@ static void do_quad_bootstrap(void)
}
}
+void prefill_possible_map(void)
+{
+ /* This is empty on voyager because we need a much
+ * earlier detection which is done in find_smp_config */
+}
+
/* Set up all the basic stuff: read the SMP config and make all the
* SMP information reflect only the boot cpu. All others will be
* brought on-line later. */
@@ -413,6 +421,7 @@ void __init smp_store_cpu_info(int id)
struct cpuinfo_x86 *c = &cpu_data(id);
*c = boot_cpu_data;
+ c->cpu_index = id;
identify_secondary_cpu(c);
}
@@ -650,6 +659,8 @@ void __init smp_boot_cpus(void)
smp_tune_scheduling();
*/
smp_store_cpu_info(boot_cpu_id);
+ /* setup the jump vector */
+ initial_code = (unsigned long)initialize_secondary;
printk("CPU%d: ", boot_cpu_id);
print_cpu_info(&cpu_data(boot_cpu_id));
@@ -702,7 +713,7 @@ void __init smp_boot_cpus(void)
/* Reload the secondary CPUs task structure (this function does not
* return ) */
-void __init initialize_secondary(void)
+static void __init initialize_secondary(void)
{
#if 0
// AC kernels only
@@ -1248,7 +1259,7 @@ static void handle_vic_irq(unsigned int irq, struct irq_desc *desc)
#define QIC_SET_GATE(cpi, vector) \
set_intr_gate((cpi) + QIC_DEFAULT_CPI_BASE, (vector))
-void __init smp_intr_init(void)
+void __init voyager_smp_intr_init(void)
{
int i;
@@ -1780,6 +1791,17 @@ void __init smp_setup_processor_id(void)
x86_write_percpu(cpu_number, hard_smp_processor_id());
}
+static void voyager_send_call_func(cpumask_t callmask)
+{
+ __u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+ send_CPI(mask, VIC_CALL_FUNCTION_CPI);
+}
+
+static void voyager_send_call_func_single(int cpu)
+{
+ send_CPI(1 << cpu, VIC_CALL_FUNCTION_SINGLE_CPI);
+}
+
struct smp_ops smp_ops = {
.smp_prepare_boot_cpu = voyager_smp_prepare_boot_cpu,
.smp_prepare_cpus = voyager_smp_prepare_cpus,
@@ -1789,6 +1811,6 @@ struct smp_ops smp_ops = {
.smp_send_stop = voyager_smp_send_stop,
.smp_send_reschedule = voyager_smp_send_reschedule,
- .send_call_func_ipi = native_send_call_func_ipi,
- .send_call_func_single_ipi = native_send_call_func_single_ipi,
+ .send_call_func_ipi = voyager_send_call_func,
+ .send_call_func_single_ipi = voyager_send_call_func_single,
};
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 59f89b434b4..fea4565ff57 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
obj-y := init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
pat.o pgtable.o gup.o
-obj-$(CONFIG_X86_32) += pgtable_32.o
+obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_X86_PTDUMP) += dump_pagetables.o
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 4ba373c5b8c..be54176e9eb 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -233,7 +233,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
len = (unsigned long) nr_pages << PAGE_SHIFT;
end = start + len;
if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- start, len)))
+ (void __user *)start, len)))
goto slow_irqon;
/*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c..c483f424207 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -334,7 +334,6 @@ int devmem_is_allowed(unsigned long pagenr)
return 0;
}
-#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
@@ -357,6 +356,7 @@ static void __init kmap_init(void)
kmap_prot = PAGE_KERNEL;
}
+#ifdef CONFIG_HIGHMEM
static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
unsigned long vaddr;
@@ -436,7 +436,6 @@ static void __init set_highmem_pages_init(void)
#endif /* !CONFIG_NUMA */
#else
-# define kmap_init() do { } while (0)
# define permanent_kmaps_init(pgd_base) do { } while (0)
# define set_highmem_pages_init() do { } while (0)
#endif /* CONFIG_HIGHMEM */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b8e461d4941..9db01db6e3c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -350,8 +350,10 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
* pagetable pages as RO. So assume someone who pre-setup
* these mappings are more intelligent.
*/
- if (pte_val(*pte))
+ if (pte_val(*pte)) {
+ pages++;
continue;
+ }
if (0)
printk(" pte=%p addr=%lx pte=%016lx\n",
@@ -418,8 +420,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
* not differ with respect to page frame and
* attributes.
*/
- if (page_size_mask & (1 << PG_LEVEL_2M))
+ if (page_size_mask & (1 << PG_LEVEL_2M)) {
+ pages++;
continue;
+ }
new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
}
@@ -499,8 +503,10 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
* not differ with respect to page frame and
* attributes.
*/
- if (page_size_mask & (1 << PG_LEVEL_1G))
+ if (page_size_mask & (1 << PG_LEVEL_1G)) {
+ pages++;
continue;
+ }
prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
}
@@ -665,12 +671,13 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
unsigned long last_map_addr = 0;
unsigned long page_size_mask = 0;
unsigned long start_pfn, end_pfn;
+ unsigned long pos;
struct map_range mr[NR_RANGE_MR];
int nr_range, i;
int use_pse, use_gbpages;
- printk(KERN_INFO "init_memory_mapping\n");
+ printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
/*
* Find space for the kernel direct mapping tables.
@@ -704,35 +711,50 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
/* head if not big page alignment ?*/
start_pfn = start >> PAGE_SHIFT;
- end_pfn = ((start + (PMD_SIZE - 1)) >> PMD_SHIFT)
+ pos = start_pfn << PAGE_SHIFT;
+ end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* big page (2M) range*/
- start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
- end_pfn = ((start + (PUD_SIZE - 1))>>PUD_SHIFT)
+ end_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
<< (PUD_SHIFT - PAGE_SHIFT);
- if (end_pfn > ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT)))
- end_pfn = ((end>>PUD_SHIFT)<<(PUD_SHIFT - PAGE_SHIFT));
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
+ if (end_pfn > ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT)))
+ end_pfn = ((end>>PMD_SHIFT)<<(PMD_SHIFT - PAGE_SHIFT));
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* big page (1G) range */
- start_pfn = end_pfn;
- end_pfn = (end>>PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ start_pfn = ((pos + (PUD_SIZE - 1))>>PUD_SHIFT)
+ << (PUD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PUD_SHIFT) << (PUD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
page_size_mask &
((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* tail is not big page (1G) alignment */
- start_pfn = end_pfn;
- end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
- nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
- page_size_mask & (1<<PG_LEVEL_2M));
+ start_pfn = ((pos + (PMD_SIZE - 1))>>PMD_SHIFT)
+ << (PMD_SHIFT - PAGE_SHIFT);
+ end_pfn = (end >> PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
+ if (start_pfn < end_pfn) {
+ nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
+ page_size_mask & (1<<PG_LEVEL_2M));
+ pos = end_pfn << PAGE_SHIFT;
+ }
/* tail is not big page (2M) alignment */
- start_pfn = end_pfn;
+ start_pfn = pos>>PAGE_SHIFT;
end_pfn = end>>PAGE_SHIFT;
nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
@@ -831,12 +853,12 @@ int arch_add_memory(int nid, u64 start, u64 size)
unsigned long nr_pages = size >> PAGE_SHIFT;
int ret;
- last_mapped_pfn = init_memory_mapping(start, start + size-1);
+ last_mapped_pfn = init_memory_mapping(start, start + size);
if (last_mapped_pfn > max_pfn_mapped)
max_pfn_mapped = last_mapped_pfn;
ret = __add_pages(zone, start_pfn, nr_pages);
- WARN_ON(1);
+ WARN_ON_ONCE(ret);
return ret;
}
@@ -878,6 +900,7 @@ static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
void __init mem_init(void)
{
long codesize, reservedpages, datasize, initsize;
+ unsigned long absent_pages;
start_periodic_check_for_corruption();
@@ -893,8 +916,9 @@ void __init mem_init(void)
#else
totalram_pages = free_all_bootmem();
#endif
- reservedpages = max_pfn - totalram_pages -
- absent_pages_in_range(0, max_pfn);
+
+ absent_pages = absent_pages_in_range(0, max_pfn);
+ reservedpages = max_pfn - totalram_pages - absent_pages;
after_bootmem = 1;
codesize = (unsigned long) &_etext - (unsigned long) &_text;
@@ -911,10 +935,11 @@ void __init mem_init(void)
VSYSCALL_END - VSYSCALL_START);
printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
- "%ldk reserved, %ldk data, %ldk init)\n",
+ "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
max_pfn << (PAGE_SHIFT-10),
codesize >> 10,
+ absent_pages << (PAGE_SHIFT-10),
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10);
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 00000000000..d0151d8ce45
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+ enum fixed_addresses idx;
+ unsigned long vaddr;
+
+ pagefault_disable();
+
+ idx = type + KM_TYPE_NR*smp_processor_id();
+ vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+ set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+ arch_flush_lazy_mmu_mode();
+
+ return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+ unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+ enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+ /*
+ * Force other mappings to Oops if they'll try to access this pte
+ * without first remap it. Keeping stale mappings around is a bad idea
+ * also, in case the page changes cacheability attributes or becomes
+ * a protected page in a hypervisor.
+ */
+ if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+ kpte_clear_flush(kmap_pte-idx, vaddr);
+
+ arch_flush_lazy_mmu_mode();
+ pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index ae71e11eb3e..d4c4307ff3e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -387,7 +387,7 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
unsigned long size)
{
unsigned long flags;
- void *ret;
+ void __iomem *ret;
int err;
/*
@@ -399,11 +399,11 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
if (err < 0)
return NULL;
- ret = (void *) __ioremap_caller(phys_addr, size, flags,
- __builtin_return_address(0));
+ ret = __ioremap_caller(phys_addr, size, flags,
+ __builtin_return_address(0));
free_memtype(phys_addr, phys_addr + size);
- return (void __iomem *)ret;
+ return ret;
}
void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
@@ -622,7 +622,7 @@ static inline void __init early_clear_fixmap(enum fixed_addresses idx)
__early_set_fixmap(idx, 0, __pgprot(0));
}
-static void *prev_map[FIX_BTMAPS_SLOTS] __initdata;
+static void __iomem *prev_map[FIX_BTMAPS_SLOTS] __initdata;
static unsigned long prev_size[FIX_BTMAPS_SLOTS] __initdata;
static int __init check_early_ioremap_leak(void)
{
@@ -645,7 +645,7 @@ static int __init check_early_ioremap_leak(void)
}
late_initcall(check_early_ioremap_leak);
-static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
+static void __init __iomem *__early_ioremap(unsigned long phys_addr, unsigned long size, pgprot_t prot)
{
unsigned long offset, last_addr;
unsigned int nrpages;
@@ -713,23 +713,23 @@ static void __init *__early_ioremap(unsigned long phys_addr, unsigned long size,
if (early_ioremap_debug)
printk(KERN_CONT "%08lx + %08lx\n", offset, fix_to_virt(idx0));
- prev_map[slot] = (void *) (offset + fix_to_virt(idx0));
+ prev_map[slot] = (void __iomem *)(offset + fix_to_virt(idx0));
return prev_map[slot];
}
/* Remap an IO device */
-void __init *early_ioremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_ioremap(unsigned long phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL_IO);
}
/* Remap memory */
-void __init *early_memremap(unsigned long phys_addr, unsigned long size)
+void __init __iomem *early_memremap(unsigned long phys_addr, unsigned long size)
{
return __early_ioremap(phys_addr, size, PAGE_KERNEL);
}
-void __init early_iounmap(void *addr, unsigned long size)
+void __init early_iounmap(void __iomem *addr, unsigned long size)
{
unsigned long virt_addr;
unsigned long offset;
@@ -779,7 +779,7 @@ void __init early_iounmap(void *addr, unsigned long size)
--idx;
--nrpages;
}
- prev_map[slot] = 0;
+ prev_map[slot] = NULL;
}
void __this_fixmap_does_not_exist(void)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 847c164725f..8518c678d83 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
}
}
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ * during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+ int node;
+
+ for_each_online_node(node) {
+ unsigned long start_va, start_pfn, size, pfn;
+
+ start_va = (unsigned long)node_remap_start_vaddr[node];
+ start_pfn = node_remap_start_pfn[node];
+ size = node_remap_size[node];
+
+ printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+ for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+ unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+ pgd_t *pgd = pgd_base + pgd_index(vaddr);
+ pud_t *pud = pud_offset(pgd, vaddr);
+ pmd_t *pmd = pmd_offset(pud, vaddr);
+
+ set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+ PAGE_KERNEL_LARGE_EXEC));
+
+ printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+ __FUNCTION__, vaddr, start_pfn + pfn);
+ }
+ }
+}
+#endif
+
static unsigned long calculate_numa_remap_pages(void)
{
int nid;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d16..e89d24815f2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
void arch_report_meminfo(struct seq_file *m)
{
- seq_printf(m, "DirectMap4k: %8lu kB\n",
+ seq_printf(m, "DirectMap4k: %8lu kB\n",
direct_pages_count[PG_LEVEL_4K] << 2);
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
- seq_printf(m, "DirectMap2M: %8lu kB\n",
+ seq_printf(m, "DirectMap2M: %8lu kB\n",
direct_pages_count[PG_LEVEL_2M] << 11);
#else
- seq_printf(m, "DirectMap4M: %8lu kB\n",
+ seq_printf(m, "DirectMap4M: %8lu kB\n",
direct_pages_count[PG_LEVEL_2M] << 12);
#endif
#ifdef CONFIG_X86_64
if (direct_gbpages)
- seq_printf(m, "DirectMap1G: %8lu kB\n",
+ seq_printf(m, "DirectMap1G: %8lu kB\n",
direct_pages_count[PG_LEVEL_1G] << 20);
#endif
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 738fd0f2495..eb1bf000d12 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -481,12 +481,16 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
return 1;
}
#else
+/* This check is needed to avoid cache aliasing when PAT is enabled */
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
u64 from = ((u64)pfn) << PAGE_SHIFT;
u64 to = from + size;
u64 cursor = from;
+ if (!pat_enabled)
+ return 1;
+
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
printk(KERN_INFO
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 0620d6d45f7..3f1b81a83e2 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -27,8 +27,7 @@ static int num_counters = 2;
static int counter_width = 32;
#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
-#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1))))
+#define CTR_OVERFLOWED(n) (!((n) & (1ULL<<(counter_width-1))))
#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
#define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
@@ -124,14 +123,14 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
static int ppro_check_ctrs(struct pt_regs * const regs,
struct op_msrs const * const msrs)
{
- unsigned int low, high;
+ u64 val;
int i;
for (i = 0 ; i < num_counters; ++i) {
if (!reset_value[i])
continue;
- CTR_READ(low, high, msrs, i);
- if (CTR_OVERFLOWED(low)) {
+ rdmsrl(msrs->counters[i].addr, val);
+ if (CTR_OVERFLOWED(val)) {
oprofile_add_sample(regs, i);
wrmsrl(msrs->counters[i].addr, -reset_value[i]);
}
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index f2b6e3f11bf..81197c62d5b 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -12,6 +12,7 @@
#include <asm/system.h>
#include <asm/page.h>
#include <asm/pgtable.h>
+#include <asm/mmzone.h>
/* Defined in hibernate_asm_32.S */
extern int restore_image(void);
@@ -127,6 +128,9 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
}
}
}
+
+ resume_map_numa_kva(pgd_base);
+
return 0;
}
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 313947940a1..6dcefba7836 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -1,4 +1,4 @@
-ifdef CONFIG_FTRACE
+ifdef CONFIG_FUNCTION_TRACER
# Do not profile debug and lowlevel utilities
CFLAGS_REMOVE_spinlock.o = -pg
CFLAGS_REMOVE_time.o = -pg
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b61534c7a4c..5e4686d70f6 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -863,15 +863,16 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l
if (PagePinned(virt_to_page(mm->pgd))) {
SetPagePinned(page);
+ vm_unmap_aliases();
if (!PageHighMem(page)) {
make_lowmem_page_readonly(__va(PFN_PHYS((unsigned long)pfn)));
if (level == PT_PTE && USE_SPLIT_PTLOCKS)
pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
- } else
+ } else {
/* make sure there are no stray mappings of
this page */
kmap_flush_unused();
- vm_unmap_aliases();
+ }
}
}
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index d4d52f5a1cf..688936044dc 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -246,11 +246,21 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
{
unsigned long address = (unsigned long)vaddr;
unsigned int level;
- pte_t *pte = lookup_address(address, &level);
- unsigned offset = address & ~PAGE_MASK;
+ pte_t *pte;
+ unsigned offset;
- BUG_ON(pte == NULL);
+ /*
+ * if the PFN is in the linear mapped vaddr range, we can just use
+ * the (quick) virt_to_machine() p2m lookup
+ */
+ if (virt_addr_valid(vaddr))
+ return virt_to_machine(vaddr);
+ /* otherwise we have to do a (slower) full page-table walk */
+
+ pte = lookup_address(address, &level);
+ BUG_ON(pte == NULL);
+ offset = address & ~PAGE_MASK;
return XMADDR(((phys_addr_t)pte_mfn(*pte) << PAGE_SHIFT) + offset);
}
@@ -410,7 +420,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
xen_mc_batch();
- u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
+ u.ptr = arbitrary_virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;
u.val = pte_val_ma(pte);
xen_extend_mmu_update(&u);
@@ -840,13 +850,16 @@ static int xen_pin_page(struct mm_struct *mm, struct page *page,
read-only, and can be pinned. */
static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
{
+ vm_unmap_aliases();
+
xen_mc_batch();
- if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
- /* re-enable interrupts for kmap_flush_unused */
+ if (xen_pgd_walk(mm, xen_pin_page, USER_LIMIT)) {
+ /* re-enable interrupts for flushing */
xen_mc_issue(0);
+
kmap_flush_unused();
- vm_unmap_aliases();
+
xen_mc_batch();
}
@@ -864,7 +877,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
#else /* CONFIG_X86_32 */
#ifdef CONFIG_X86_PAE
/* Need to make sure unshared kernel PMD is pinnable */
- xen_pin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+ xen_pin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
PT_PMD);
#endif
xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
@@ -981,7 +994,7 @@ static void __xen_pgd_unpin(struct mm_struct *mm, pgd_t *pgd)
#ifdef CONFIG_X86_PAE
/* Need to make sure unshared kernel PMD is unpinned */
- xen_unpin_page(mm, virt_to_page(pgd_page(pgd[pgd_index(TASK_SIZE)])),
+ xen_unpin_page(mm, pgd_page(pgd[pgd_index(TASK_SIZE)]),
PT_PMD);
#endif