aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/include
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2009-09-17 20:52:23 +0200
committerIngo Molnar <mingo@elte.hu>2009-09-17 20:53:10 +0200
commit45bd00d31de886f8425b4dd33204b911b0a466a9 (patch)
tree06204f2452e02ca916666173d50f5035d69065ef /arch/x86/include
parent40d9d82c8ab8c4e2373a23a1e31dc8d84c53aa01 (diff)
parentab86e5765d41a5eb4239a1c04d613db87bea5ed8 (diff)
Merge branch 'linus' into tracing/core
Merge reason: Pick up kernel/softirq.c update for dependent fix. Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'arch/x86/include')
-rw-r--r--arch/x86/include/asm/agp.h4
-rw-r--r--arch/x86/include/asm/alternative.h7
-rw-r--r--arch/x86/include/asm/amd_iommu.h1
-rw-r--r--arch/x86/include/asm/amd_iommu_types.h50
-rw-r--r--arch/x86/include/asm/apic.h7
-rw-r--r--arch/x86/include/asm/apicdef.h5
-rw-r--r--arch/x86/include/asm/asm.h10
-rw-r--r--arch/x86/include/asm/bootparam.h3
-rw-r--r--arch/x86/include/asm/cacheflush.h54
-rw-r--r--arch/x86/include/asm/cpufeature.h1
-rw-r--r--arch/x86/include/asm/current.h2
-rw-r--r--arch/x86/include/asm/desc.h13
-rw-r--r--arch/x86/include/asm/desc_defs.h6
-rw-r--r--arch/x86/include/asm/device.h3
-rw-r--r--arch/x86/include/asm/dma-mapping.h18
-rw-r--r--arch/x86/include/asm/dwarf2.h18
-rw-r--r--arch/x86/include/asm/fixmap.h3
-rw-r--r--arch/x86/include/asm/i387.h9
-rw-r--r--arch/x86/include/asm/io_apic.h13
-rw-r--r--arch/x86/include/asm/ioctls.h95
-rw-r--r--arch/x86/include/asm/iomap.h9
-rw-r--r--arch/x86/include/asm/ipcbuf.h29
-rw-r--r--arch/x86/include/asm/irqflags.h9
-rw-r--r--arch/x86/include/asm/kvm.h10
-rw-r--r--arch/x86/include/asm/kvm_emulate.h (renamed from arch/x86/include/asm/kvm_x86_emulate.h)0
-rw-r--r--arch/x86/include/asm/kvm_host.h60
-rw-r--r--arch/x86/include/asm/kvm_para.h2
-rw-r--r--arch/x86/include/asm/lguest.h5
-rw-r--r--arch/x86/include/asm/mman.h14
-rw-r--r--arch/x86/include/asm/module.h15
-rw-r--r--arch/x86/include/asm/msgbuf.h40
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/msr.h75
-rw-r--r--arch/x86/include/asm/mtrr.h6
-rw-r--r--arch/x86/include/asm/nmi.h4
-rw-r--r--arch/x86/include/asm/param.h23
-rw-r--r--arch/x86/include/asm/paravirt.h746
-rw-r--r--arch/x86/include/asm/paravirt_types.h721
-rw-r--r--arch/x86/include/asm/pat.h5
-rw-r--r--arch/x86/include/asm/pci.h1
-rw-r--r--arch/x86/include/asm/percpu.h35
-rw-r--r--arch/x86/include/asm/perf_counter.h10
-rw-r--r--arch/x86/include/asm/pgtable.h16
-rw-r--r--arch/x86/include/asm/processor.h28
-rw-r--r--arch/x86/include/asm/scatterlist.h27
-rw-r--r--arch/x86/include/asm/shmbuf.h52
-rw-r--r--arch/x86/include/asm/socket.h61
-rw-r--r--arch/x86/include/asm/sockios.h14
-rw-r--r--arch/x86/include/asm/stackprotector.h10
-rw-r--r--arch/x86/include/asm/system.h29
-rw-r--r--arch/x86/include/asm/termbits.h199
-rw-r--r--arch/x86/include/asm/termios.h115
-rw-r--r--arch/x86/include/asm/thread_info.h2
-rw-r--r--arch/x86/include/asm/topology.h47
-rw-r--r--arch/x86/include/asm/traps.h4
-rw-r--r--arch/x86/include/asm/types.h12
-rw-r--r--arch/x86/include/asm/ucontext.h8
-rw-r--r--arch/x86/include/asm/vmx.h8
58 files changed, 1188 insertions, 1586 deletions
diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h
index 9825cd64c9b..eec2a70d437 100644
--- a/arch/x86/include/asm/agp.h
+++ b/arch/x86/include/asm/agp.h
@@ -22,10 +22,6 @@
*/
#define flush_agp_cache() wbinvd()
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
/* GATT allocation. Returns/accepts GATT kernel virtual address. */
#define alloc_gatt_pages(order) \
((char *)__get_free_pages(GFP_KERNEL, (order)))
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 1a37bcdc860..c240efc74e0 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -73,8 +73,6 @@ static inline void alternatives_smp_module_del(struct module *mod) {}
static inline void alternatives_smp_switch(int smp) {}
#endif /* CONFIG_SMP */
-const unsigned char *const *find_nop_table(void);
-
/* alternative assembly primitive: */
#define ALTERNATIVE(oldinstr, newinstr, feature) \
\
@@ -144,8 +142,6 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
#define __parainstructions_end NULL
#endif
-extern void add_nops(void *insns, unsigned int len);
-
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
@@ -161,10 +157,7 @@ extern void add_nops(void *insns, unsigned int len);
* Intel's errata.
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
* inconsistent instruction while you patch.
- * The _early version expects the memory to already be RW.
*/
-
extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
#endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index bdf96f119f0..ac95995b7ba 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -25,6 +25,7 @@
#ifdef CONFIG_AMD_IOMMU
extern int amd_iommu_init(void);
extern int amd_iommu_init_dma_ops(void);
+extern int amd_iommu_init_passthrough(void);
extern void amd_iommu_detect(void);
extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
extern void amd_iommu_flush_all_domains(void);
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 0c878caaa0a..2a2cc7a78a8 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -143,22 +143,29 @@
#define EVT_BUFFER_SIZE 8192 /* 512 entries */
#define EVT_LEN_MASK (0x9ULL << 56)
+#define PAGE_MODE_NONE 0x00
#define PAGE_MODE_1_LEVEL 0x01
#define PAGE_MODE_2_LEVEL 0x02
#define PAGE_MODE_3_LEVEL 0x03
-
-#define IOMMU_PDE_NL_0 0x000ULL
-#define IOMMU_PDE_NL_1 0x200ULL
-#define IOMMU_PDE_NL_2 0x400ULL
-#define IOMMU_PDE_NL_3 0x600ULL
-
-#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL)
-#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL)
-#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL)
-
-#define IOMMU_MAP_SIZE_L1 (1ULL << 21)
-#define IOMMU_MAP_SIZE_L2 (1ULL << 30)
-#define IOMMU_MAP_SIZE_L3 (1ULL << 39)
+#define PAGE_MODE_4_LEVEL 0x04
+#define PAGE_MODE_5_LEVEL 0x05
+#define PAGE_MODE_6_LEVEL 0x06
+
+#define PM_LEVEL_SHIFT(x) (12 + ((x) * 9))
+#define PM_LEVEL_SIZE(x) (((x) < 6) ? \
+ ((1ULL << PM_LEVEL_SHIFT((x))) - 1): \
+ (0xffffffffffffffffULL))
+#define PM_LEVEL_INDEX(x, a) (((a) >> PM_LEVEL_SHIFT((x))) & 0x1ffULL)
+#define PM_LEVEL_ENC(x) (((x) << 9) & 0xe00ULL)
+#define PM_LEVEL_PDE(x, a) ((a) | PM_LEVEL_ENC((x)) | \
+ IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+#define PM_PTE_LEVEL(pte) (((pte) >> 9) & 0x7ULL)
+
+#define PM_MAP_4k 0
+#define PM_ADDR_MASK 0x000ffffffffff000ULL
+#define PM_MAP_MASK(lvl) (PM_ADDR_MASK & \
+ (~((1ULL << (12 + ((lvl) * 9))) - 1)))
+#define PM_ALIGNED(lvl, addr) ((PM_MAP_MASK(lvl) & (addr)) == (addr))
#define IOMMU_PTE_P (1ULL << 0)
#define IOMMU_PTE_TV (1ULL << 1)
@@ -167,11 +174,6 @@
#define IOMMU_PTE_IR (1ULL << 61)
#define IOMMU_PTE_IW (1ULL << 62)
-#define IOMMU_L1_PDE(address) \
- ((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-#define IOMMU_L2_PDE(address) \
- ((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-
#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
@@ -194,11 +196,14 @@
#define PD_DMA_OPS_MASK (1UL << 0) /* domain used for dma_ops */
#define PD_DEFAULT_MASK (1UL << 1) /* domain is a default dma_ops
domain for an IOMMU */
+#define PD_PASSTHROUGH_MASK (1UL << 2) /* domain has no page
+ translation */
+
extern bool amd_iommu_dump;
#define DUMP_printk(format, arg...) \
do { \
if (amd_iommu_dump) \
- printk(KERN_INFO "AMD IOMMU: " format, ## arg); \
+ printk(KERN_INFO "AMD-Vi: " format, ## arg); \
} while(0);
/*
@@ -226,6 +231,7 @@ struct protection_domain {
int mode; /* paging mode (0-6 levels) */
u64 *pt_root; /* page table root pointer */
unsigned long flags; /* flags to find out type of domain */
+ bool updated; /* complete domain flush required */
unsigned dev_cnt; /* devices assigned to this domain */
void *priv; /* private data */
};
@@ -337,6 +343,9 @@ struct amd_iommu {
/* if one, we need to send a completion wait command */
bool need_sync;
+ /* becomes true if a command buffer reset is running */
+ bool reset_in_progress;
+
/* default dma_ops domain for that IOMMU */
struct dma_ops_domain *default_dom;
};
@@ -457,4 +466,7 @@ static inline void amd_iommu_stats_init(void) { }
#endif /* CONFIG_AMD_IOMMU_STATS */
+/* some function prototypes */
+extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
+
#endif /* _ASM_X86_AMD_IOMMU_TYPES_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index bb7d4792584..586b7adb8e5 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -183,6 +183,10 @@ static inline int x2apic_enabled(void)
}
#define x2apic_supported() (cpu_has_x2apic)
+static inline void x2apic_force_phys(void)
+{
+ x2apic_phys = 1;
+}
#else
static inline void check_x2apic(void)
{
@@ -194,6 +198,9 @@ static inline int x2apic_enabled(void)
{
return 0;
}
+static inline void x2apic_force_phys(void)
+{
+}
#define x2apic_preenabled 0
#define x2apic_supported() 0
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
index 7ddb36ab933..3b62da926de 100644
--- a/arch/x86/include/asm/apicdef.h
+++ b/arch/x86/include/asm/apicdef.h
@@ -8,12 +8,14 @@
* Ingo Molnar <mingo@redhat.com>, 1999, 2000
*/
-#define APIC_DEFAULT_PHYS_BASE 0xfee00000
+#define IO_APIC_DEFAULT_PHYS_BASE 0xfec00000
+#define APIC_DEFAULT_PHYS_BASE 0xfee00000
#define APIC_ID 0x20
#define APIC_LVR 0x30
#define APIC_LVR_MASK 0xFF00FF
+#define APIC_LVR_DIRECTED_EOI (1 << 24)
#define GET_APIC_VERSION(x) ((x) & 0xFFu)
#define GET_APIC_MAXLVT(x) (((x) >> 16) & 0xFFu)
#ifdef CONFIG_X86_32
@@ -40,6 +42,7 @@
#define APIC_DFR_CLUSTER 0x0FFFFFFFul
#define APIC_DFR_FLAT 0xFFFFFFFFul
#define APIC_SPIV 0xF0
+#define APIC_SPIV_DIRECTED_EOI (1 << 12)
#define APIC_SPIV_FOCUS_DISABLED (1 << 9)
#define APIC_SPIV_APIC_ENABLED (1 << 8)
#define APIC_ISR 0x100
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 56be78f582f..b3ed1e1460f 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -3,7 +3,7 @@
#ifdef __ASSEMBLY__
# define __ASM_FORM(x) x
-# define __ASM_EX_SEC .section __ex_table
+# define __ASM_EX_SEC .section __ex_table, "a"
#else
# define __ASM_FORM(x) " " #x " "
# define __ASM_EX_SEC " .section __ex_table,\"a\"\n"
@@ -38,10 +38,18 @@
#define _ASM_DI __ASM_REG(di)
/* Exception table entry */
+#ifdef __ASSEMBLY__
+# define _ASM_EXTABLE(from,to) \
+ __ASM_EX_SEC ; \
+ _ASM_ALIGN ; \
+ _ASM_PTR from , to ; \
+ .previous
+#else
# define _ASM_EXTABLE(from,to) \
__ASM_EX_SEC \
_ASM_ALIGN "\n" \
_ASM_PTR #from "," #to "\n" \
" .previous\n"
+#endif
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 1724e8de317..6ca20218dd7 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -85,7 +85,8 @@ struct efi_info {
struct boot_params {
struct screen_info screen_info; /* 0x000 */
struct apm_bios_info apm_bios_info; /* 0x040 */
- __u8 _pad2[12]; /* 0x054 */
+ __u8 _pad2[4]; /* 0x054 */
+ __u64 tboot_addr; /* 0x058 */
struct ist_info ist_info; /* 0x060 */
__u8 _pad3[16]; /* 0x070 */
__u8 hd0_info[16]; /* obsolete! */ /* 0x080 */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e55dfc1ad45..b54f6afe7ec 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -43,8 +43,58 @@ static inline void copy_from_user_page(struct vm_area_struct *vma,
memcpy(dst, src, len);
}
-#define PG_non_WB PG_arch_1
-PAGEFLAG(NonWB, non_WB)
+#define PG_WC PG_arch_1
+PAGEFLAG(WC, WC)
+
+#ifdef CONFIG_X86_PAT
+/*
+ * X86 PAT uses page flags WC and Uncached together to keep track of
+ * memory type of pages that have backing page struct. X86 PAT supports 3
+ * different memory types, _PAGE_CACHE_WB, _PAGE_CACHE_WC and
+ * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
+ * been changed from its default (value of -1 used to denote this).
+ * Note we do not support _PAGE_CACHE_UC here.
+ *
+ * Caller must hold memtype_lock for atomicity.
+ */
+static inline unsigned long get_page_memtype(struct page *pg)
+{
+ if (!PageUncached(pg) && !PageWC(pg))
+ return -1;
+ else if (!PageUncached(pg) && PageWC(pg))
+ return _PAGE_CACHE_WC;
+ else if (PageUncached(pg) && !PageWC(pg))
+ return _PAGE_CACHE_UC_MINUS;
+ else
+ return _PAGE_CACHE_WB;
+}
+
+static inline void set_page_memtype(struct page *pg, unsigned long memtype)
+{
+ switch (memtype) {
+ case _PAGE_CACHE_WC:
+ ClearPageUncached(pg);
+ SetPageWC(pg);
+ break;
+ case _PAGE_CACHE_UC_MINUS:
+ SetPageUncached(pg);
+ ClearPageWC(pg);
+ break;
+ case _PAGE_CACHE_WB:
+ SetPageUncached(pg);
+ SetPageWC(pg);
+ break;
+ default:
+ case -1:
+ ClearPageUncached(pg);
+ ClearPageWC(pg);
+ break;
+ }
+}
+#else
+static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
+static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
+#endif
/*
* The set_memory_* API can be used to change various attributes of a virtual
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 4a28d22d479..847fee6493a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -95,6 +95,7 @@
#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
#define X86_FEATURE_EXTD_APICID (3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM (3*32+27) /* multi-node processor */
/* 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/current.h b/arch/x86/include/asm/current.h
index c68c361697e..4d447b732d8 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -11,7 +11,7 @@ DECLARE_PER_CPU(struct task_struct *, current_task);
static __always_inline struct task_struct *get_current(void)
{
- return percpu_read(current_task);
+ return percpu_read_stable(current_task);
}
#define current get_current()
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index c993e9e0fed..e8de2f6f5ca 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -291,11 +291,24 @@ static inline unsigned long get_desc_base(const struct desc_struct *desc)
return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
}
+static inline void set_desc_base(struct desc_struct *desc, unsigned long base)
+{
+ desc->base0 = base & 0xffff;
+ desc->base1 = (base >> 16) & 0xff;
+ desc->base2 = (base >> 24) & 0xff;
+}
+
static inline unsigned long get_desc_limit(const struct desc_struct *desc)
{
return desc->limit0 | (desc->limit << 16);
}
+static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
+{
+ desc->limit0 = limit & 0xffff;
+ desc->limit = (limit >> 16) & 0xf;
+}
+
static inline void _set_gate(int gate, unsigned type, void *addr,
unsigned dpl, unsigned ist, unsigned seg)
{
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
index a6adefa28b9..9d6684849fd 100644
--- a/arch/x86/include/asm/desc_defs.h
+++ b/arch/x86/include/asm/desc_defs.h
@@ -34,6 +34,12 @@ struct desc_struct {
};
} __attribute__((packed));
+#define GDT_ENTRY_INIT(flags, base, limit) { { { \
+ .a = ((limit) & 0xffff) | (((base) & 0xffff) << 16), \
+ .b = (((base) & 0xff0000) >> 16) | (((flags) & 0xf0ff) << 8) | \
+ ((limit) & 0xf0000) | ((base) & 0xff000000), \
+ } } }
+
enum {
GATE_INTERRUPT = 0xE,
GATE_TRAP = 0xF,
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
index 4994a20acbc..cee34e9ca45 100644
--- a/arch/x86/include/asm/device.h
+++ b/arch/x86/include/asm/device.h
@@ -13,4 +13,7 @@ struct dma_map_ops *dma_ops;
#endif
};
+struct pdev_archdata {
+};
+
#endif /* _ASM_X86_DEVICE_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 1c3f9435f1c..0ee770d23d0 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -55,6 +55,24 @@ extern int dma_set_mask(struct device *dev, u64 mask);
extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag);
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+ if (!dev->dma_mask)
+ return 0;
+
+ return addr + size <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+ return paddr;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+ return daddr;
+}
+
static inline void
dma_cache_sync(struct device *dev, void *vaddr, size_t size,
enum dma_data_direction dir)
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 3afc5e87cfd..ae6253ab902 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -87,9 +87,25 @@
CFI_RESTORE \reg
.endm
#else /*!CONFIG_X86_64*/
+ .macro pushl_cfi reg
+ pushl \reg
+ CFI_ADJUST_CFA_OFFSET 4
+ .endm
- /* 32bit defenitions are missed yet */
+ .macro popl_cfi reg
+ popl \reg
+ CFI_ADJUST_CFA_OFFSET -4
+ .endm
+ .macro movl_cfi reg offset=0
+ movl %\reg, \offset(%esp)
+ CFI_REL_OFFSET \reg, \offset
+ .endm
+
+ .macro movl_cfi_restore offset reg
+ movl \offset(%esp), %\reg
+ CFI_RESTORE \reg
+ .endm
#endif /*!CONFIG_X86_64*/
#endif /*__ASSEMBLY__*/
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 7b2d71df39a..14f9890eb49 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -132,6 +132,9 @@ enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_WP_TEST,
#endif
+#ifdef CONFIG_INTEL_TXT
+ FIX_TBOOT_BASE,
+#endif
__end_of_fixed_addresses
};
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 175adf58dd4..0b20bbb758f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -26,6 +26,7 @@ extern void fpu_init(void);
extern void mxcsr_feature_mask_init(void);
extern int init_fpu(struct task_struct *child);
extern asmlinkage void math_state_restore(void);
+extern void __math_state_restore(void);
extern void init_thread_xstate(void);
extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
@@ -301,6 +302,14 @@ static inline void kernel_fpu_end(void)
preempt_enable();
}
+static inline bool irq_fpu_usable(void)
+{
+ struct pt_regs *regs;
+
+ return !in_interrupt() || !(regs = get_irq_regs()) || \
+ user_mode(regs) || (read_cr0() & X86_CR0_TS);
+}
+
/*
* Some instructions like VIA's padlock instructions generate a spurious
* DNA fault but don't modify SSE registers. And these instructions
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 330ee807f89..85232d32fcb 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -150,11 +150,10 @@ extern int timer_through_8259;
#define io_apic_assign_pci_irqs \
(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
-#ifdef CONFIG_ACPI
+extern u8 io_apic_unique_id(u8 id);
extern int io_apic_get_unique_id(int ioapic, int apic_id);
extern int io_apic_get_version(int ioapic);
extern int io_apic_get_redir_entries(int ioapic);
-#endif /* CONFIG_ACPI */
struct io_apic_irq_attr;
extern int io_apic_set_pci_routing(struct device *dev, int irq,
@@ -177,6 +176,16 @@ extern int setup_ioapic_entry(int apic, int irq,
int polarity, int vector, int pin);
extern void ioapic_write_entry(int apic, int pin,
struct IO_APIC_route_entry e);
+
+struct mp_ioapic_gsi{
+ int gsi_base;
+ int gsi_end;
+};
+extern struct mp_ioapic_gsi mp_gsi_routing[];
+int mp_find_ioapic(int gsi);
+int mp_find_ioapic_pin(int ioapic, int gsi);
+void __init mp_register_ioapic(int id, u32 address, u32 gsi_base);
+
#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
static const int timer_through_8259 = 0;
diff --git a/arch/x86/include/asm/ioctls.h b/arch/x86/include/asm/ioctls.h
index 0d5b23b7b06..ec34c760665 100644
--- a/arch/x86/include/asm/ioctls.h
+++ b/arch/x86/include/asm/ioctls.h
@@ -1,94 +1 @@
-#ifndef _ASM_X86_IOCTLS_H
-#define _ASM_X86_IOCTLS_H
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS 0x5401
-#define TCSETS 0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
-#define TCSETSW 0x5403
-#define TCSETSF 0x5404
-#define TCGETA 0x5405
-#define TCSETA 0x5406
-#define TCSETAW 0x5407
-#define TCSETAF 0x5408
-#define TCSBRK 0x5409
-#define TCXONC 0x540A
-#define TCFLSH 0x540B
-#define TIOCEXCL 0x540C
-#define TIOCNXCL 0x540D
-#define TIOCSCTTY 0x540E
-#define TIOCGPGRP 0x540F
-#define TIOCSPGRP 0x5410
-#define TIOCOUTQ 0x5411
-#define TIOCSTI 0x5412
-#define TIOCGWINSZ 0x5413
-#define TIOCSWINSZ 0x5414
-#define TIOCMGET 0x5415
-#define TIOCMBIS 0x5416
-#define TIOCMBIC 0x5417
-#define TIOCMSET 0x5418
-#define TIOCGSOFTCAR 0x5419
-#define TIOCSSOFTCAR 0x541A
-#define FIONREAD 0x541B
-#define TIOCINQ FIONREAD
-#define TIOCLINUX 0x541C
-#define TIOCCONS 0x541D
-#define TIOCGSERIAL 0x541E
-#define TIOCSSERIAL 0x541F
-#define TIOCPKT 0x5420
-#define FIONBIO 0x5421
-#define TIOCNOTTY 0x5422
-#define TIOCSETD 0x5423
-#define TIOCGETD 0x5424
-#define TCSBRKP 0x5425 /* Needed for POSIX tcsendbreak() */
-/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
-#define TIOCSBRK 0x5427 /* BSD compatibility */
-#define TIOCCBRK 0x5428 /* BSD compatibility */
-#define TIOCGSID 0x5429 /* Return the session ID of FD */
-#define TCGETS2 _IOR('T', 0x2A, struct termios2)
-#define TCSETS2 _IOW('T', 0x2B, struct termios2)
-#define TCSETSW2 _IOW('T', 0x2C, struct termios2)
-#define TCSETSF2 _IOW('T', 0x2D, struct termios2)
-#define TIOCGRS485 0x542E
-#define TIOCSRS485 0x542F
-#define TIOCGPTN _IOR('T', 0x30, unsigned int)
- /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK _IOW('T', 0x31, int) /* Lock/unlock Pty */
-#define TCGETX 0x5432 /* SYS5 TCGETX compatibility */
-#define TCSETX 0x5433
-#define TCSETXF 0x5434
-#define TCSETXW 0x5435
-
-#define FIONCLEX 0x5450
-#define FIOCLEX 0x5451
-#define FIOASYNC 0x5452
-#define TIOCSERCONFIG 0x5453
-#define TIOCSERGWILD 0x5454
-#define TIOCSERSWILD 0x5455
-#define TIOCGLCKTRMIOS 0x5456
-#define TIOCSLCKTRMIOS 0x5457
-#define TIOCSERGSTRUCT 0x5458 /* For debugging only */
-#define TIOCSERGETLSR 0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT 0x545C /* wait for a change on serial input line(s) */
-#define TIOCGICOUNT 0x545D /* read serial port inline interrupt counts */
-#define TIOCGHAYESESP 0x545E /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP 0x545F /* Set Hayes ESP configuration */
-#define FIOQSIZE 0x5460
-
-/* Used for packet mode */
-#define TIOCPKT_DATA 0
-#define TIOCPKT_FLUSHREAD 1
-#define TIOCPKT_FLUSHWRITE 2
-#define TIOCPKT_STOP 4
-#define TIOCPKT_START 8
-#define TIOCPKT_NOSTOP 16
-#define TIOCPKT_DOSTOP 32
-
-#define TIOCSER_TEMT 0x01 /* Transmitter physically empty */
-
-#endif /* _ASM_X86_IOCTLS_H */
+#include <asm-generic/ioctls.h>
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index 0e9fe1d9d97..f35eb45d657 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -26,13 +26,16 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-int
-is_io_mapping_possible(resource_size_t base, unsigned long size);
-
void *
iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
void
iounmap_atomic(void *kvaddr, enum km_type type);
+int
+iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
+
+void
+iomap_free(resource_size_t base, unsigned long size);
+
#endif /* _ASM_X86_IOMAP_H */
diff --git a/arch/x86/include/asm/ipcbuf.h b/arch/x86/include/asm/ipcbuf.h
index ee678fd5159..84c7e51cb6d 100644
--- a/arch/x86/include/asm/ipcbuf.h
+++ b/arch/x86/include/asm/ipcbuf.h
@@ -1,28 +1 @@
-#ifndef _ASM_X86_IPCBUF_H
-#define _ASM_X86_IPCBUF_H
-
-/*
- * The ipc64_perm structure for x86 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 32-bit mode_t and seq
- * - 2 miscellaneous 32-bit values
- */
-
-struct ipc64_perm {
- __kernel_key_t key;
- __kernel_uid32_t uid;
- __kernel_gid32_t gid;
- __kernel_uid32_t cuid;
- __kernel_gid32_t cgid;
- __kernel_mode_t mode;
- unsigned short __pad1;
- unsigned short seq;
- unsigned short __pad2;
- unsigned long __unused1;
- unsigned long __unused2;
-};
-
-#endif /* _ASM_X86_IPCBUF_H */
+#include <asm-generic/ipcbuf.h>
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c6ccbe7e81a..9e2b952f810 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -13,14 +13,13 @@ static inline unsigned long native_save_fl(void)
unsigned long flags;
/*
- * Note: this needs to be "=r" not "=rm", because we have the
- * stack offset from what gcc expects at the time the "pop" is
- * executed, and so a memory reference with respect to the stack
- * would end up using the wrong address.
+ * "=rm" is safe here, because "pop" adjusts the stack before
+ * it evaluates its effective address -- this is part of the
+ * documented behavior of the "pop" instruction.
*/
asm volatile("# __raw_save_flags\n\t"
"pushf ; pop %0"
- : "=r" (flags)
+ : "=rm" (flags)
: /* no input */
: "memory");
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 125be8b1956..4a5fe914dc5 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -17,6 +17,8 @@
#define __KVM_HAVE_USER_NMI
#define __KVM_HAVE_GUEST_DEBUG
#define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
+#define __KVM_HAVE_PIT_STATE2
/* Architectural interrupt line count. */
#define KVM_NR_INTERRUPTS 256
@@ -236,6 +238,14 @@ struct kvm_pit_state {
struct kvm_pit_channel_state channels[3];
};
+#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001
+
+struct kvm_pit_state2 {
+ struct kvm_pit_channel_state channels[3];
+ __u32 flags;
+ __u32 reserved[9];
+};
+
struct kvm_reinject_control {
__u8 pit_reinject;
__u8 reserved[31];
diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index b7ed2c42311..b7ed2c42311 100644
--- a/arch/x86/include/asm/kvm_x86_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index eabdc1cfab5..3be000435fa 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -14,6 +14,7 @@
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/mmu_notifier.h>
+#include <linux/tracepoint.h>
#include <linux/kvm.h>
#include <linux/kvm_para.h>
@@ -37,12 +38,14 @@
#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \
0xFFFFFF0000000000ULL)
-#define KVM_GUEST_CR0_MASK \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
- | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK \
+ (KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST \
+ (X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
#define KVM_VM_CR0_ALWAYS_ON \
- (X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
- | X86_CR0_MP)
+ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_GUEST_CR4_MASK \
(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
@@ -51,12 +54,12 @@
#define INVALID_PAGE (~(hpa_t)0)
#define UNMAPPED_GVA (~(gpa_t)0)
-/* shadow tables are PAE even on non-PAE hosts */
-#define KVM_HPAGE_SHIFT 21
-#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
-#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
-
-#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+/* KVM Hugepage definitions for x86 */
+#define KVM_NR_PAGE_SIZES 3
+#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE)
#define DE_VECTOR 0
#define DB_VECTOR 1
@@ -120,6 +123,10 @@ enum kvm_reg {
NR_VCPU_REGS
};
+enum kvm_reg_ex {
+ VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+};
+
enum {
VCPU_SREG_ES,
VCPU_SREG_CS,
@@ -131,7 +138,7 @@ enum {
VCPU_SREG_LDTR,
};
-#include <asm/kvm_x86_emulate.h>
+#include <asm/kvm_emulate.h>
#define KVM_NR_MEM_OBJS 40
@@ -308,7 +315,6 @@ struct kvm_vcpu_arch {
struct {
gfn_t gfn; /* presumed gfn during guest pte update */
pfn_t pfn; /* pfn corresponding to that gfn */
- int largepage;
unsigned long mmu_seq;
} update_pte;
@@ -334,16 +340,6 @@ struct kvm_vcpu_arch {
u8 nr;
} interrupt;
- struct {
- int vm86_active;
- u8 save_iopl;
- struct kvm_save_segment {
- u16 selector;
- unsigned long base;
- u32 limit;
- u32 ar;
- } tr, es, ds, fs, gs;
- } rmode;
int halt_request; /* real mode on Intel only */
int cpuid_nent;
@@ -366,13 +362,15 @@ struct kvm_vcpu_arch {
u32 pat;
int switch_db_regs;
- unsigned long host_db[KVM_NR_DB_REGS];
- unsigned long host_dr6;
- unsigned long host_dr7;
unsigned long db[KVM_NR_DB_REGS];
unsigned long dr6;
unsigned long dr7;
unsigned long eff_db[KVM_NR_DB_REGS];
+
+ u64 mcg_cap;
+ u64 mcg_status;
+ u64 mcg_ctl;
+ u64 *mce_banks;
};
struct kvm_mem_alias {
@@ -409,6 +407,7 @@ struct kvm_arch{
struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
+ gpa_t ept_identity_map_addr;
unsigned long irq_sources_bitmap;
unsigned long irq_states[KVM_IOAPIC_NUM_PINS];
@@ -526,6 +525,9 @@ struct kvm_x86_ops {
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
int (*get_tdp_level)(void);
u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+ bool (*gb_page_enable)(void);
+
+ const struct trace_print_flags *exit_reasons_str;
};
extern struct kvm_x86_ops *kvm_x86_ops;
@@ -618,6 +620,7 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
u32 error_code);
+bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
int kvm_pic_set_irq(void *opaque, int irq, int level);
@@ -752,8 +755,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
-#define MSR_IA32_TIME_STAMP_COUNTER 0x010
-
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
@@ -796,5 +797,8 @@ asmlinkage void kvm_handle_fault_on_reboot(void);
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_age_hva(struct kvm *kvm, unsigned long hva);
int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
+int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index b8a3305ae09..c584076a47f 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -1,6 +1,8 @@
#ifndef _ASM_X86_KVM_PARA_H
#define _ASM_X86_KVM_PARA_H
+#include <linux/types.h>
+
/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx. It
* should be used to determine that a VM is running under KVM.
*/
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
index 5136dad57cb..0d97deba1e3 100644
--- a/arch/x86/include/asm/lguest.h
+++ b/arch/x86/include/asm/lguest.h
@@ -90,8 +90,9 @@ static inline void lguest_set_ts(void)
}
/* Full 4G segment descriptors, suitable for CS and DS. */
-#define FULL_EXEC_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9b00} } })
-#define FULL_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9300} } })
+#define FULL_EXEC_SEGMENT \
+ ((struct desc_struct)GDT_ENTRY_INIT(0xc09b, 0, 0xfffff))
+#define FULL_SEGMENT ((struct desc_struct)GDT_ENTRY_INIT(0xc093, 0, 0xfffff))
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
index 751af2550ed..593e51d4643 100644
--- a/arch/x86/include/asm/mman.h
+++ b/arch/x86/include/asm/mman.h
@@ -1,20 +1,8 @@
#ifndef _ASM_X86_MMAN_H
#define _ASM_X86_MMAN_H
-#include <asm-generic/mman-common.h>
-
#define MAP_32BIT 0x40 /* only give out 32bit addresses */
-#define MAP_GROWSDOWN 0x0100 /* stack-like segment */
-#define MAP_DENYWRITE 0x0800 /* ETXTBSY */
-#define MAP_EXECUTABLE 0x1000 /* mark it as an executable */
-#define MAP_LOCKED 0x2000 /* pages are locked */
-#define MAP_NORESERVE 0x4000 /* don't check for reservations */
-#define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */
-#define MAP_NONBLOCK 0x10000 /* do not block on IO */
-#define MAP_STACK 0x20000 /* give out an address that is best suited for process/thread stacks */
-
-#define MCL_CURRENT 1 /* lock all current mappings */
-#define MCL_FUTURE 2 /* lock all future mappings */
+#include <asm-generic/mman.h>
#endif /* _ASM_X86_MMAN_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 47d62743c4d..3e2ce58a31a 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -1,18 +1,7 @@
#ifndef _ASM_X86_MODULE_H
#define _ASM_X86_MODULE_H
-/* x86_32/64 are simple */
-struct mod_arch_specific {};
-
-#ifdef CONFIG_X86_32
-# define Elf_Shdr Elf32_Shdr
-# define Elf_Sym Elf32_Sym
-# define Elf_Ehdr Elf32_Ehdr
-#else
-# define Elf_Shdr Elf64_Shdr
-# define Elf_Sym Elf64_Sym
-# define Elf_Ehdr Elf64_Ehdr
-#endif
+#include <asm-generic/module.h>
#ifdef CONFIG_X86_64
/* X86_64 does not define MODULE_PROC_FAMILY */
@@ -28,6 +17,8 @@ struct mod_arch_specific {};
#define MODULE_PROC_FAMILY "586MMX "
#elif defined CONFIG_MCORE2
#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_MATOM
+#define MODULE_PROC_FAMILY "ATOM "
#elif defined CONFIG_M686
#define MODULE_PROC_FAMILY "686 "
#elif defined CONFIG_MPENTIUMII
diff --git a/arch/x86/include/asm/msgbuf.h b/arch/x86/include/asm/msgbuf.h
index 7e4e9481f51..809134c644a 100644
--- a/arch/x86/include/asm/msgbuf.h
+++ b/arch/x86/include/asm/msgbuf.h
@@ -1,39 +1 @@
-#ifndef _ASM_X86_MSGBUF_H
-#define _ASM_X86_MSGBUF_H
-
-/*
- * The msqid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space on i386 is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- *
- * Pad space on x8664 is left for:
- * - 2 miscellaneous 64-bit values
- */
-struct msqid64_ds {
- struct ipc64_perm msg_perm;
- __kernel_time_t msg_stime; /* last msgsnd time */
-#ifdef __i386__
- unsigned long __unused1;
-#endif
- __kernel_time_t msg_rtime; /* last msgrcv time */
-#ifdef __i386__
- unsigned long __unused2;
-#endif
- __kernel_time_t msg_ctime; /* last change time */
-#ifdef __i386__
- unsigned long __unused3;
-#endif
- unsigned long msg_cbytes; /* current number of bytes on queue */
- unsigned long msg_qnum; /* number of messages in queue */
- unsigned long msg_qbytes; /* max number of bytes on queue */
- __kernel_pid_t msg_lspid; /* pid of last msgsnd */
- __kernel_pid_t msg_lrpid; /* last receive pid */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-#endif /* _ASM_X86_MSGBUF_H */
+#include <asm-generic/msgbuf.h>
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6be7fc254b5..bd5549034a9 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -374,6 +374,7 @@
/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
+#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
#endif /* _ASM_X86_MSR_INDEX_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 48ad9d29484..7e2b6ba962f 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -3,10 +3,16 @@
#include <asm/msr-index.h>
-#ifdef __KERNEL__
#ifndef __ASSEMBLY__
#include <linux/types.h>
+#include <linux/ioctl.h>
+
+#define X86_IOC_RDMSR_REGS _IOWR('c', 0xA0, __u32[8])
+#define X86_IOC_WRMSR_REGS _IOWR('c', 0xA1, __u32[8])
+
+#ifdef __KERNEL__
+
#include <asm/asm.h>
#include <asm/errno.h>
#include <asm/cpumask.h>
@@ -67,23 +73,7 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
".previous\n\t"
_ASM_EXTABLE(2b, 3b)
: [err] "=r" (*err), EAX_EDX_RET(val, low, high)
- : "c" (msr), [fault] "i" (-EFAULT));
- return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
- int *err)
-{
- DECLARE_ARGS(val, low, high);
-
- asm volatile("2: rdmsr ; xor %0,%0\n"
- "1:\n\t"
- ".section .fixup,\"ax\"\n\t"
- "3: mov %3,%0 ; jmp 1b\n\t"
- ".previous\n\t"
- _ASM_EXTABLE(2b, 3b)
- : "=r" (*err), EAX_EDX_RET(val, low, high)
- : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
+ : "c" (msr), [fault] "i" (-EIO));
return EAX_EDX_VAL(val, low, high);
}
@@ -106,13 +96,16 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
_ASM_EXTABLE(2b, 3b)
: [err] "=a" (err)
: "c" (msr), "0" (low), "d" (high),
- [fault] "i" (-EFAULT)
+ [fault] "i" (-EIO)
: "memory");
return err;
}
extern unsigned long long native_read_tsc(void);
+extern int native_rdmsr_safe_regs(u32 regs[8]);
+extern int native_wrmsr_safe_regs(u32 regs[8]);
+
static __always_inline unsigned long long __native_read_tsc(void)
{
DECLARE_ARGS(val, low, high);
@@ -181,14 +174,44 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
*p = native_read_msr_safe(msr, &err);
return err;
}
+
static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
{
+ u32 gprs[8] = { 0 };
int err;
- *p = native_read_msr_amd_safe(msr, &err);
+ gprs[1] = msr;
+ gprs[7] = 0x9c5a203a;
+
+ err = native_rdmsr_safe_regs(gprs);
+
+ *p = gprs[0] | ((u64)gprs[2] << 32);
+
return err;
}
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+ u32 gprs[8] = { 0 };
+
+ gprs[0] = (u32)val;
+ gprs[1] = msr;
+ gprs[2] = val >> 32;
+ gprs[7] = 0x9c5a203a;
+
+ return native_wrmsr_safe_regs(gprs);
+}
+
+static inline int rdmsr_safe_regs(u32 regs[8])
+{
+ return native_rdmsr_safe_regs(regs);
+}
+
+static inline int wrmsr_safe_regs(u32 regs[8])
+{
+ return native_wrmsr_safe_regs(regs);
+}
+
#define rdtscl(low) \
((low) = (u32)__native_read_tsc())
@@ -228,6 +251,8 @@ void rdmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
void wrmsr_on_cpus(const cpumask_t *mask, u32 msr_no, struct msr *msrs);
int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
#else /* CONFIG_SMP */
static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
{
@@ -258,7 +283,15 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
{
return wrmsr_safe(msr_no, l, h);
}
+static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+ return rdmsr_safe_regs(regs);
+}
+static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+ return wrmsr_safe_regs(regs);
+}
#endif /* CONFIG_SMP */
-#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index a51ada8467d..4365ffdb461 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -121,6 +121,9 @@ extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
extern void mtrr_ap_init(void);
extern void mtrr_bp_init(void);
+extern void set_mtrr_aps_delayed_init(void);
+extern void mtrr_aps_init(void);
+extern void mtrr_bp_restore(void);
extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
extern int amd_special_default_mtrr(void);
# else
@@ -161,6 +164,9 @@ static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
#define mtrr_ap_init() do {} while (0)
#define mtrr_bp_init() do {} while (0)
+#define set_mtrr_aps_delayed_init() do {} while (0)
+#define mtrr_aps_init() do {} while (0)
+#define mtrr_bp_restore() do {} while (0)
# endif
#ifdef CONFIG_COMPAT
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c86e5ed4af5..e63cf7d441e 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -45,8 +45,8 @@ extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
void __user *, size_t *, loff_t *);
extern int unknown_nmi_panic;
-void __trigger_all_cpu_backtrace(void);
-#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
static inline void localise_nmi_watchdog(void)
{
diff --git a/arch/x86/include/asm/param.h b/arch/x86/include/asm/param.h
index 6f0d0422f4c..965d4542797 100644
--- a/arch/x86/include/asm/param.h
+++ b/arch/x86/include/asm/param.h
@@ -1,22 +1 @@
-#ifndef _ASM_X86_PARAM_H
-#define _ASM_X86_PARAM_H
-
-#ifdef __KERNEL__
-# define HZ CONFIG_HZ /* Internal kernel timer frequency */
-# define USER_HZ 100 /* some user interfaces are */
-# define CLOCKS_PER_SEC (USER_HZ) /* in "ticks" like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE 4096
-
-#ifndef NOGROUP
-#define NOGROUP (-1)
-#endif
-
-#define MAXHOSTNAMELEN 64 /* max length of hostname */
-
-#endif /* _ASM_X86_PARAM_H */
+#include <asm-generic/param.h>
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4fb37c8a083..40d6586af25 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -7,689 +7,11 @@
#include <asm/pgtable_types.h>
#include <asm/asm.h>
-/* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
-#define CLBR_EAX (1 << 0)
-#define CLBR_ECX (1 << 1)
-#define CLBR_EDX (1 << 2)
-#define CLBR_EDI (1 << 3)
-
-#ifdef CONFIG_X86_32
-/* CLBR_ANY should match all regs platform has. For i386, that's just it */
-#define CLBR_ANY ((1 << 4) - 1)
-
-#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX)
-#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH (0)
-#else
-#define CLBR_RAX CLBR_EAX
-#define CLBR_RCX CLBR_ECX
-#define CLBR_RDX CLBR_EDX
-#define CLBR_RDI CLBR_EDI
-#define CLBR_RSI (1 << 4)
-#define CLBR_R8 (1 << 5)
-#define CLBR_R9 (1 << 6)
-#define CLBR_R10 (1 << 7)
-#define CLBR_R11 (1 << 8)
-
-#define CLBR_ANY ((1 << 9) - 1)
-
-#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
- CLBR_RCX | CLBR_R8 | CLBR_R9)
-#define CLBR_RET_REG (CLBR_RAX)
-#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11)
-
-#include <asm/desc_defs.h>
-#endif /* X86_64 */
-
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
+#include <asm/paravirt_types.h>
#ifndef __ASSEMBLY__
#include <linux/types.h>
#include <linux/cpumask.h>
-#include <asm/kmap_types.h>
-#include <asm/desc_defs.h>
-
-struct page;
-struct thread_struct;
-struct desc_ptr;
-struct tss_struct;
-struct mm_struct;
-struct desc_struct;
-struct task_struct;
-
-/*
- * Wrapper type for pointers to code which uses the non-standard
- * calling convention. See PV_CALL_SAVE_REGS_THUNK below.
- */
-struct paravirt_callee_save {
- void *func;
-};
-
-/* general info */
-struct pv_info {
- unsigned int kernel_rpl;
- int shared_kernel_pmd;
- int paravirt_enabled;
- const char *name;
-};
-
-struct pv_init_ops {
- /*
- * Patch may replace one of the defined code sequences with
- * arbitrary code, subject to the same register constraints.
- * This generally means the code is not free to clobber any
- * registers other than EAX. The patch function should return
- * the number of bytes of code generated, as we nop pad the
- * rest in generic code.
- */
- unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
- unsigned long addr, unsigned len);
-
- /* Basic arch-specific setup */
- void (*arch_setup)(void);
- char *(*memory_setup)(void);
- void (*post_allocator_init)(void);
-
- /* Print a banner to identify the environment */
- void (*banner)(void);
-};
-
-
-struct pv_lazy_ops {
- /* Set deferred update mode, used for batching operations. */
- void (*enter)(void);
- void (*leave)(void);
-};
-
-struct pv_time_ops {
- void (*time_init)(void);
-
- /* Set and set time of day */
- unsigned long (*get_wallclock)(void);
- int (*set_wallclock)(unsigned long);
-
- unsigned long long (*sched_clock)(void);
- unsigned long (*get_tsc_khz)(void);
-};
-
-struct pv_cpu_ops {
- /* hooks for various privileged instructions */
- unsigned long (*get_debugreg)(int regno);
- void (*set_debugreg)(int regno, unsigned long value);
-
- void (*clts)(void);
-
- unsigned long (*read_cr0)(void);
- void (*write_cr0)(unsigned long);
-
- unsigned long (*read_cr4_safe)(void);
- unsigned long (*read_cr4)(void);
- void (*write_cr4)(unsigned long);
-
-#ifdef CONFIG_X86_64
- unsigned long (*read_cr8)(void);
- void (*write_cr8)(unsigned long);
-#endif
-
- /* Segment descriptor handling */
- void (*load_tr_desc)(void);
- void (*load_gdt)(const struct desc_ptr *);
- void (*load_idt)(const struct desc_ptr *);
- void (*store_gdt)(struct desc_ptr *);
- void (*store_idt)(struct desc_ptr *);
- void (*set_ldt)(const void *desc, unsigned entries);
- unsigned long (*store_tr)(void);
- void (*load_tls)(struct thread_struct *t, unsigned int cpu);
-#ifdef CONFIG_X86_64
- void (*load_gs_index)(unsigned int idx);
-#endif
- void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
- const void *desc);
- void (*write_gdt_entry)(struct desc_struct *,
- int entrynum, const void *desc, int size);
- void (*write_idt_entry)(gate_desc *,
- int entrynum, const gate_desc *gate);
- void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
- void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
-
- void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
-
- void (*set_iopl_mask)(unsigned mask);
-
- void (*wbinvd)(void);
- void (*io_delay)(void);
-
- /* cpuid emulation, mostly so that caps bits can be disabled */
- void (*cpuid)(unsigned int *eax, unsigned int *ebx,
- unsigned int *ecx, unsigned int *edx);
-
- /* MSR, PMC and TSR operations.
- err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
- u64 (*read_msr_amd)(unsigned int msr, int *err);
- u64 (*read_msr)(unsigned int msr, int *err);
- int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
-
- u64 (*read_tsc)(void);
- u64 (*read_pmc)(int counter);
- unsigned long long (*read_tscp)(unsigned int *aux);
-
- /*
- * Atomically enable interrupts and return to userspace. This
- * is only ever used to return to 32-bit processes; in a
- * 64-bit kernel, it's used for 32-on-64 compat processes, but
- * never native 64-bit processes. (Jump, not call.)
- */
- void (*irq_enable_sysexit)(void);
-
- /*
- * Switch to usermode gs and return to 64-bit usermode using
- * sysret. Only used in 64-bit kernels to return to 64-bit
- * processes. Usermode register state, including %rsp, must
- * already be restored.
- */
- void (*usergs_sysret64)(void);
-
- /*
- * Switch to usermode gs and return to 32-bit usermode using
- * sysret. Used to return to 32-on-64 compat processes.
- * Other usermode register state, including %esp, must already
- * be restored.
- */
- void (*usergs_sysret32)(void);
-
- /* Normal iret. Jump to this with the standard iret stack
- frame set up. */
- void (*iret)(void);
-
- void (*swapgs)(void);
-
- void (*start_context_switch)(struct task_struct *prev);
- void (*end_context_switch)(struct task_struct *next);
-};
-
-struct pv_irq_ops {
- void (*init_IRQ)(void);
-
- /*
- * Get/set interrupt state. save_fl and restore_fl are only
- * expected to use X86_EFLAGS_IF; all other bits
- * returned from save_fl are undefined, and may be ignored by
- * restore_fl.
- *
- * NOTE: These functions callers expect the callee to preserve
- * more registers than the standard C calling convention.
- */
- struct paravirt_callee_save save_fl;
- struct paravirt_callee_save restore_fl;
- struct paravirt_callee_save irq_disable;
- struct paravirt_callee_save irq_enable;
-
- void (*safe_halt)(void);
- void (*halt)(void);
-
-#ifdef CONFIG_X86_64
- void (*adjust_exception_frame)(void);
-#endif
-};
-
-struct pv_apic_ops {
-#ifdef CONFIG_X86_LOCAL_APIC
- void (*setup_boot_clock)(void);
- void (*setup_secondary_clock)(void);
-
- void (*startup_ipi_hook)(int phys_apicid,
- unsigned long start_eip,
- unsigned long start_esp);
-#endif
-};
-
-struct pv_mmu_ops {
- /*
- * Called before/after init_mm pagetable setup. setup_start
- * may reset %cr3, and may pre-install parts of the pagetable;
- * pagetable setup is expected to preserve any existing
- * mapping.
- */
- void (*pagetable_setup_start)(pgd_t *pgd_base);
- void (*pagetable_setup_done)(pgd_t *pgd_base);
-
- unsigned long (*read_cr2)(void);
- void (*write_cr2)(unsigned long);
-
- unsigned long (*read_cr3)(void);
- void (*write_cr3)(unsigned long);
-
- /*
- * Hooks for intercepting the creation/use/destruction of an
- * mm_struct.
- */
- void (*activate_mm)(struct mm_struct *prev,
- struct mm_struct *next);
- void (*dup_mmap)(struct mm_struct *oldmm,
- struct mm_struct *mm);
- void (*exit_mmap)(struct mm_struct *mm);
-
-
- /* TLB operations */
- void (*flush_tlb_user)(void);
- void (*flush_tlb_kernel)(void);
- void (*flush_tlb_single)(unsigned long addr);
- void (*flush_tlb_others)(const struct cpumask *cpus,
- struct mm_struct *mm,
- unsigned long va);
-
- /* Hooks for allocating and freeing a pagetable top-level */
- int (*pgd_alloc)(struct mm_struct *mm);
- void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
-
- /*
- * Hooks for allocating/releasing pagetable pages when they're
- * attached to a pagetable
- */
- void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
- void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
- void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
- void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
- void (*release_pte)(unsigned long pfn);
- void (*release_pmd)(unsigned long pfn);
- void (*release_pud)(unsigned long pfn);
-
- /* Pagetable manipulation functions */
- void (*set_pte)(pte_t *ptep, pte_t pteval);
- void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pteval);
- void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
- void (*pte_update)(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep);
- void (*pte_update_defer)(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep);
-
- pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep);
- void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte);
-
- struct paravirt_callee_save pte_val;
- struct paravirt_callee_save make_pte;
-
- struct paravirt_callee_save pgd_val;
- struct paravirt_callee_save make_pgd;
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
- void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
- void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep);
- void (*pmd_clear)(pmd_t *pmdp);
-
-#endif /* CONFIG_X86_PAE */
-
- void (*set_pud)(pud_t *pudp, pud_t pudval);
-
- struct paravirt_callee_save pmd_val;
- struct paravirt_callee_save make_pmd;
-
-#if PAGETABLE_LEVELS == 4
- struct paravirt_callee_save pud_val;
- struct paravirt_callee_save make_pud;
-
- void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
-#endif /* PAGETABLE_LEVELS == 4 */
-#endif /* PAGETABLE_LEVELS >= 3 */
-
-#ifdef CONFIG_HIGHPTE
- void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
-#endif
-
- struct pv_lazy_ops lazy_mode;
-
- /* dom0 ops */
-
- /* Sometimes the physical address is a pfn, and sometimes its
- an mfn. We can tell which is which from the index. */
- void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
- phys_addr_t phys, pgprot_t flags);
-};
-
-struct raw_spinlock;
-struct pv_lock_ops {
- int (*spin_is_locked)(struct raw_spinlock *lock);
- int (*spin_is_contended)(struct raw_spinlock *lock);
- void (*spin_lock)(struct raw_spinlock *lock);
- void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
- int (*spin_trylock)(struct raw_spinlock *lock);
- void (*spin_unlock)(struct raw_spinlock *lock);
-};
-
-/* This contains all the paravirt structures: we get a convenient
- * number for each function using the offset which we use to indicate
- * what to patch. */
-struct paravirt_patch_template {
- struct pv_init_ops pv_init_ops;
- struct pv_time_ops pv_time_ops;
- struct pv_cpu_ops pv_cpu_ops;
- struct pv_irq_ops pv_irq_ops;
- struct pv_apic_ops pv_apic_ops;
- struct pv_mmu_ops pv_mmu_ops;
- struct pv_lock_ops pv_lock_ops;
-};
-
-extern struct pv_info pv_info;
-extern struct pv_init_ops pv_init_ops;
-extern struct pv_time_ops pv_time_ops;
-extern struct pv_cpu_ops pv_cpu_ops;
-extern struct pv_irq_ops pv_irq_ops;
-extern struct pv_apic_ops pv_apic_ops;
-extern struct pv_mmu_ops pv_mmu_ops;
-extern struct pv_lock_ops pv_lock_ops;
-
-#define PARAVIRT_PATCH(x) \
- (offsetof(struct paravirt_patch_template, x) / sizeof(void *))
-
-#define paravirt_type(op) \
- [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \
- [paravirt_opptr] "i" (&(op))
-#define paravirt_clobber(clobber) \
- [paravirt_clobber] "i" (clobber)
-
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type, clobber) \
- "771:\n\t" insn_string "\n" "772:\n" \
- ".pushsection .parainstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR " 771b\n" \
- " .byte " type "\n" \
- " .byte 772b-771b\n" \
- " .short " clobber "\n" \
- ".popsection\n"
-
-/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string) \
- _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
-
-/* Simple instruction patching code. */
-#define DEF_NATIVE(ops, name, code) \
- extern const char start_##ops##_##name[], end_##ops##_##name[]; \
- asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
-
-unsigned paravirt_patch_nop(void);
-unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
-unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
-unsigned paravirt_patch_ignore(unsigned len);
-unsigned paravirt_patch_call(void *insnbuf,
- const void *target, u16 tgt_clobbers,
- unsigned long addr, u16 site_clobbers,
- unsigned len);
-unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
- unsigned long addr, unsigned len);
-unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
- unsigned long addr, unsigned len);
-
-unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
- const char *start, const char *end);
-
-unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
- unsigned long addr, unsigned len);
-
-int paravirt_disable_iospace(void);
-
-/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
-#define PARAVIRT_CALL "call *%c[paravirt_opptr];"
-
-/*
- * These macros are intended to wrap calls through one of the paravirt
- * ops structs, so that they can be later identified and patched at
- * runtime.
- *
- * Normally, a call to a pv_op function is a simple indirect call:
- * (pv_op_struct.operations)(args...).
- *
- * Unfortunately, this is a relatively slow operation for modern CPUs,
- * because it cannot necessarily determine what the destination
- * address is. In this case, the address is a runtime constant, so at
- * the very least we can patch the call to e a simple direct call, or
- * ideally, patch an inline implementation into the callsite. (Direct
- * calls are essentially free, because the call and return addresses
- * are completely predictable.)
- *
- * For i386, these macros rely on the standard gcc "regparm(3)" calling
- * convention, in which the first three arguments are placed in %eax,
- * %edx, %ecx (in that order), and the remaining arguments are placed
- * on the stack. All caller-save registers (eax,edx,ecx) are expected
- * to be modified (either clobbered or used for return values).
- * X86_64, on the other hand, already specifies a register-based calling
- * conventions, returning at %rax, with parameteres going on %rdi, %rsi,
- * %rdx, and %rcx. Note that for this reason, x86_64 does not need any
- * special handling for dealing with 4 arguments, unlike i386.
- * However, x86_64 also have to clobber all caller saved registers, which
- * unfortunately, are quite a bit (r8 - r11)
- *
- * The call instruction itself is marked by placing its start address
- * and size into the .parainstructions section, so that
- * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend pv_init_ops
- * implementation.
- *
- * Unfortunately there's no way to get gcc to generate the args setup
- * for the call, and then allow the call itself to be generated by an
- * inline asm. Because of this, we must do the complete arg setup and
- * return value handling from within these macros. This is fairly
- * cumbersome.
- *
- * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
- * It could be extended to more arguments, but there would be little
- * to be gained from that. For each number of arguments, there are
- * the two VCALL and CALL variants for void and non-void functions.
- *
- * When there is a return value, the invoker of the macro must specify
- * the return type. The macro then uses sizeof() on that type to
- * determine whether its a 32 or 64 bit value, and places the return
- * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
- * 64-bit). For x86_64 machines, it just returns at %rax regardless of
- * the return value size.
- *
- * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
- * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
- * in low,high order
- *
- * Small structures are passed and returned in registers. The macro
- * calling convention can't directly deal with this, so the wrapper
- * functions must do this.
- *
- * These PVOP_* macros are only defined within this header. This
- * means that all uses must be wrapped in inline functions. This also
- * makes sure the incoming and outgoing types are always correct.
- */
-#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS \
- unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
-
-#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
-#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x))
-#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x))
-
-#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \
- "=c" (__ecx)
-#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS
-
-#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx)
-#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
-
-#define EXTRA_CLOBBERS
-#define VEXTRA_CLOBBERS
-#else /* CONFIG_X86_64 */
-#define PVOP_VCALL_ARGS \
- unsigned long __edi = __edi, __esi = __esi, \
- __edx = __edx, __ecx = __ecx
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax
-
-#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
-#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x))
-#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x))
-#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x))
-
-#define PVOP_VCALL_CLOBBERS "=D" (__edi), \
- "=S" (__esi), "=d" (__edx), \
- "=c" (__ecx)
-#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax)
-
-#define PVOP_VCALLEE_CLOBBERS "=a" (__eax)
-#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
-
-#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11"
-#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11"
-#endif /* CONFIG_X86_32 */
-
-#ifdef CONFIG_PARAVIRT_DEBUG
-#define PVOP_TEST_NULL(op) BUG_ON(op == NULL)
-#else
-#define PVOP_TEST_NULL(op) ((void)op)
-#endif
-
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
- pre, post, ...) \
- ({ \
- rettype __ret; \
- PVOP_CALL_ARGS; \
- PVOP_TEST_NULL(op); \
- /* This is 32-bit specific, but is okay in 64-bit */ \
- /* since this condition will never hold */ \
- if (sizeof(rettype) > sizeof(unsigned long)) { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)((((u64)__edx) << 32) | __eax); \
- } else { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)__eax; \
- } \
- __ret; \
- })
-
-#define __PVOP_CALL(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \
- EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
-
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
- PVOP_CALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
-
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
- ({ \
- PVOP_VCALL_ARGS; \
- PVOP_TEST_NULL(op); \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- })
-
-#define __PVOP_VCALL(op, pre, post, ...) \
- ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
- VEXTRA_CLOBBERS, \
- pre, post, ##__VA_ARGS__)
-
-#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
- PVOP_VCALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
-
-
-
-#define PVOP_CALL0(rettype, op) \
- __PVOP_CALL(rettype, op, "", "")
-#define PVOP_VCALL0(op) \
- __PVOP_VCALL(op, "", "")
-
-#define PVOP_CALLEE0(rettype, op) \
- __PVOP_CALLEESAVE(rettype, op, "", "")
-#define PVOP_VCALLEE0(op) \
- __PVOP_VCALLEESAVE(op, "", "")
-
-
-#define PVOP_CALL1(rettype, op, arg1) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
-#define PVOP_VCALL1(op, arg1) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
-
-#define PVOP_CALLEE1(rettype, op, arg1) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
-#define PVOP_VCALLEE1(op, arg1) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
-
-
-#define PVOP_CALL2(rettype, op, arg1, arg2) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALL2(op, arg1, arg2) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
-
-#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
-#define PVOP_VCALL3(op, arg1, arg2, arg3) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
-
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
- __PVOP_CALL(rettype, op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
- PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
- __PVOP_CALL(rettype, op, "", "", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
- PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, "", "", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
- PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
static inline int paravirt_enabled(void)
{
@@ -820,15 +142,22 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err)
{
return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
}
-static inline u64 paravirt_read_msr_amd(unsigned msr, int *err)
+
+static inline int paravirt_rdmsr_regs(u32 *regs)
{
- return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err);
+ return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
}
+
static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
{
return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
}
+static inline int paravirt_wrmsr_regs(u32 *regs)
+{
+ return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
+}
+
/* These should all do BUG_ON(_err), but our headers are too tangled. */
#define rdmsr(msr, val1, val2) \
do { \
@@ -862,6 +191,9 @@ do { \
_err; \
})
+#define rdmsr_safe_regs(regs) paravirt_rdmsr_regs(regs)
+#define wrmsr_safe_regs(regs) paravirt_wrmsr_regs(regs)
+
static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
{
int err;
@@ -871,12 +203,31 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
}
static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
{
+ u32 gprs[8] = { 0 };
int err;
- *p = paravirt_read_msr_amd(msr, &err);
+ gprs[1] = msr;
+ gprs[7] = 0x9c5a203a;
+
+ err = paravirt_rdmsr_regs(gprs);
+
+ *p = gprs[0] | ((u64)gprs[2] << 32);
+
return err;
}
+static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+{
+ u32 gprs[8] = { 0 };
+
+ gprs[0] = (u32)val;
+ gprs[1] = msr;
+ gprs[2] = val >> 32;
+ gprs[7] = 0x9c5a203a;
+
+ return paravirt_wrmsr_regs(gprs);
+}
+
static inline u64 paravirt_read_tsc(void)
{
return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
@@ -1393,20 +744,6 @@ static inline void pmd_clear(pmd_t *pmdp)
}
#endif /* CONFIG_X86_PAE */
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
- PARAVIRT_LAZY_NONE,
- PARAVIRT_LAZY_MMU,
- PARAVIRT_LAZY_CPU,
-};
-
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-
#define __HAVE_ARCH_START_CONTEXT_SWITCH
static inline void arch_start_context_switch(struct task_struct *prev)
{
@@ -1437,12 +774,6 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
pv_mmu_ops.set_fixmap(idx, phys, flags);
}
-void _paravirt_nop(void);
-u32 _paravirt_ident_32(u32);
-u64 _paravirt_ident_64(u64);
-
-#define paravirt_nop ((void *)_paravirt_nop)
-
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
@@ -1479,17 +810,6 @@ static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
#endif
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
- u8 *instr; /* original instructions */
- u8 instrtype; /* type of this instruction */
- u8 len; /* length of original instruction */
- u16 clobbers; /* what registers you may clobber */
-};
-
-extern struct paravirt_patch_site __parainstructions[],
- __parainstructions_end[];
-
#ifdef CONFIG_X86_32
#define PV_SAVE_REGS "pushl %ecx; pushl %edx;"
#define PV_RESTORE_REGS "popl %edx; popl %ecx;"
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
new file mode 100644
index 00000000000..25402d0006e
--- /dev/null
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -0,0 +1,721 @@
+#ifndef _ASM_X86_PARAVIRT_TYPES_H
+#define _ASM_X86_PARAVIRT_TYPES_H
+
+/* Bitmask of what can be clobbered: usually at least eax. */
+#define CLBR_NONE 0
+#define CLBR_EAX (1 << 0)
+#define CLBR_ECX (1 << 1)
+#define CLBR_EDX (1 << 2)
+#define CLBR_EDI (1 << 3)
+
+#ifdef CONFIG_X86_32
+/* CLBR_ANY should match all regs platform has. For i386, that's just it */
+#define CLBR_ANY ((1 << 4) - 1)
+
+#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX)
+#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX)
+#define CLBR_SCRATCH (0)
+#else
+#define CLBR_RAX CLBR_EAX
+#define CLBR_RCX CLBR_ECX
+#define CLBR_RDX CLBR_EDX
+#define CLBR_RDI CLBR_EDI
+#define CLBR_RSI (1 << 4)
+#define CLBR_R8 (1 << 5)
+#define CLBR_R9 (1 << 6)
+#define CLBR_R10 (1 << 7)
+#define CLBR_R11 (1 << 8)
+
+#define CLBR_ANY ((1 << 9) - 1)
+
+#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
+ CLBR_RCX | CLBR_R8 | CLBR_R9)
+#define CLBR_RET_REG (CLBR_RAX)
+#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11)
+
+#endif /* X86_64 */
+
+#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/desc_defs.h>
+#include <asm/kmap_types.h>
+
+struct page;
+struct thread_struct;
+struct desc_ptr;
+struct tss_struct;
+struct mm_struct;
+struct desc_struct;
+struct task_struct;
+struct cpumask;
+
+/*
+ * Wrapper type for pointers to code which uses the non-standard
+ * calling convention. See PV_CALL_SAVE_REGS_THUNK below.
+ */
+struct paravirt_callee_save {
+ void *func;
+};
+
+/* general info */
+struct pv_info {
+ unsigned int kernel_rpl;
+ int shared_kernel_pmd;
+ int paravirt_enabled;
+ const char *name;
+};
+
+struct pv_init_ops {
+ /*
+ * Patch may replace one of the defined code sequences with
+ * arbitrary code, subject to the same register constraints.
+ * This generally means the code is not free to clobber any
+ * registers other than EAX. The patch function should return
+ * the number of bytes of code generated, as we nop pad the
+ * rest in generic code.
+ */
+ unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
+ unsigned long addr, unsigned len);
+
+ /* Basic arch-specific setup */
+ void (*arch_setup)(void);
+ char *(*memory_setup)(void);
+ void (*post_allocator_init)(void);
+
+ /* Print a banner to identify the environment */
+ void (*banner)(void);
+};
+
+
+struct pv_lazy_ops {
+ /* Set deferred update mode, used for batching operations. */
+ void (*enter)(void);
+ void (*leave)(void);
+};
+
+struct pv_time_ops {
+ void (*time_init)(void);
+
+ /* Set and set time of day */
+ unsigned long (*get_wallclock)(void);
+ int (*set_wallclock)(unsigned long);
+
+ unsigned long long (*sched_clock)(void);
+ unsigned long (*get_tsc_khz)(void);
+};
+
+struct pv_cpu_ops {
+ /* hooks for various privileged instructions */
+ unsigned long (*get_debugreg)(int regno);
+ void (*set_debugreg)(int regno, unsigned long value);
+
+ void (*clts)(void);
+
+ unsigned long (*read_cr0)(void);
+ void (*write_cr0)(unsigned long);
+
+ unsigned long (*read_cr4_safe)(void);
+ unsigned long (*read_cr4)(void);
+ void (*write_cr4)(unsigned long);
+
+#ifdef CONFIG_X86_64
+ unsigned long (*read_cr8)(void);
+ void (*write_cr8)(unsigned long);
+#endif
+
+ /* Segment descriptor handling */
+ void (*load_tr_desc)(void);
+ void (*load_gdt)(const struct desc_ptr *);
+ void (*load_idt)(const struct desc_ptr *);
+ void (*store_gdt)(struct desc_ptr *);
+ void (*store_idt)(struct desc_ptr *);
+ void (*set_ldt)(const void *desc, unsigned entries);
+ unsigned long (*store_tr)(void);
+ void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+#ifdef CONFIG_X86_64
+ void (*load_gs_index)(unsigned int idx);
+#endif
+ void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
+ const void *desc);
+ void (*write_gdt_entry)(struct desc_struct *,
+ int entrynum, const void *desc, int size);
+ void (*write_idt_entry)(gate_desc *,
+ int entrynum, const gate_desc *gate);
+ void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
+ void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
+
+ void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+
+ void (*set_iopl_mask)(unsigned mask);
+
+ void (*wbinvd)(void);
+ void (*io_delay)(void);
+
+ /* cpuid emulation, mostly so that caps bits can be disabled */
+ void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+ unsigned int *ecx, unsigned int *edx);
+
+ /* MSR, PMC and TSR operations.
+ err = 0/-EFAULT. wrmsr returns 0/-EFAULT. */
+ u64 (*read_msr)(unsigned int msr, int *err);
+ int (*rdmsr_regs)(u32 *regs);
+ int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+ int (*wrmsr_regs)(u32 *regs);
+
+ u64 (*read_tsc)(void);
+ u64 (*read_pmc)(int counter);
+ unsigned long long (*read_tscp)(unsigned int *aux);
+
+ /*
+ * Atomically enable interrupts and return to userspace. This
+ * is only ever used to return to 32-bit processes; in a
+ * 64-bit kernel, it's used for 32-on-64 compat processes, but
+ * never native 64-bit processes. (Jump, not call.)
+ */
+ void (*irq_enable_sysexit)(void);
+
+ /*
+ * Switch to usermode gs and return to 64-bit usermode using
+ * sysret. Only used in 64-bit kernels to return to 64-bit
+ * processes. Usermode register state, including %rsp, must
+ * already be restored.
+ */
+ void (*usergs_sysret64)(void);
+
+ /*
+ * Switch to usermode gs and return to 32-bit usermode using
+ * sysret. Used to return to 32-on-64 compat processes.
+ * Other usermode register state, including %esp, must already
+ * be restored.
+ */
+ void (*usergs_sysret32)(void);
+
+ /* Normal iret. Jump to this with the standard iret stack
+ frame set up. */
+ void (*iret)(void);
+
+ void (*swapgs)(void);
+
+ void (*start_context_switch)(struct task_struct *prev);
+ void (*end_context_switch)(struct task_struct *next);
+};
+
+struct pv_irq_ops {
+ void (*init_IRQ)(void);
+
+ /*
+ * Get/set interrupt state. save_fl and restore_fl are only
+ * expected to use X86_EFLAGS_IF; all other bits
+ * returned from save_fl are undefined, and may be ignored by
+ * restore_fl.
+ *
+ * NOTE: These functions callers expect the callee to preserve
+ * more registers than the standard C calling convention.
+ */
+ struct paravirt_callee_save save_fl;
+ struct paravirt_callee_save restore_fl;
+ struct paravirt_callee_save irq_disable;
+ struct paravirt_callee_save irq_enable;
+
+ void (*safe_halt)(void);
+ void (*halt)(void);
+
+#ifdef CONFIG_X86_64
+ void (*adjust_exception_frame)(void);
+#endif
+};
+
+struct pv_apic_ops {
+#ifdef CONFIG_X86_LOCAL_APIC
+ void (*setup_boot_clock)(void);
+ void (*setup_secondary_clock)(void);
+
+ void (*startup_ipi_hook)(int phys_apicid,
+ unsigned long start_eip,
+ unsigned long start_esp);
+#endif
+};
+
+struct pv_mmu_ops {
+ /*
+ * Called before/after init_mm pagetable setup. setup_start
+ * may reset %cr3, and may pre-install parts of the pagetable;
+ * pagetable setup is expected to preserve any existing
+ * mapping.
+ */
+ void (*pagetable_setup_start)(pgd_t *pgd_base);
+ void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+ unsigned long (*read_cr2)(void);
+ void (*write_cr2)(unsigned long);
+
+ unsigned long (*read_cr3)(void);
+ void (*write_cr3)(unsigned long);
+
+ /*
+ * Hooks for intercepting the creation/use/destruction of an
+ * mm_struct.
+ */
+ void (*activate_mm)(struct mm_struct *prev,
+ struct mm_struct *next);
+ void (*dup_mmap)(struct mm_struct *oldmm,
+ struct mm_struct *mm);
+ void (*exit_mmap)(struct mm_struct *mm);
+
+
+ /* TLB operations */
+ void (*flush_tlb_user)(void);
+ void (*flush_tlb_kernel)(void);
+ void (*flush_tlb_single)(unsigned long addr);
+ void (*flush_tlb_others)(const struct cpumask *cpus,
+ struct mm_struct *mm,
+ unsigned long va);
+
+ /* Hooks for allocating and freeing a pagetable top-level */
+ int (*pgd_alloc)(struct mm_struct *mm);
+ void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
+
+ /*
+ * Hooks for allocating/releasing pagetable pages when they're
+ * attached to a pagetable
+ */
+ void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
+ void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
+ void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
+ void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+ void (*release_pte)(unsigned long pfn);
+ void (*release_pmd)(unsigned long pfn);
+ void (*release_pud)(unsigned long pfn);
+
+ /* Pagetable manipulation functions */
+ void (*set_pte)(pte_t *ptep, pte_t pteval);
+ void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pteval);
+ void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+ void (*pte_update)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep);
+ void (*pte_update_defer)(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep);
+
+ pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep);
+ void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte);
+
+ struct paravirt_callee_save pte_val;
+ struct paravirt_callee_save make_pte;
+
+ struct paravirt_callee_save pgd_val;
+ struct paravirt_callee_save make_pgd;
+
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+ void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
+ void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep);
+ void (*pmd_clear)(pmd_t *pmdp);
+
+#endif /* CONFIG_X86_PAE */
+
+ void (*set_pud)(pud_t *pudp, pud_t pudval);
+
+ struct paravirt_callee_save pmd_val;
+ struct paravirt_callee_save make_pmd;
+
+#if PAGETABLE_LEVELS == 4
+ struct paravirt_callee_save pud_val;
+ struct paravirt_callee_save make_pud;
+
+ void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
+#endif /* PAGETABLE_LEVELS == 4 */
+#endif /* PAGETABLE_LEVELS >= 3 */
+
+#ifdef CONFIG_HIGHPTE
+ void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
+
+ struct pv_lazy_ops lazy_mode;
+
+ /* dom0 ops */
+
+ /* Sometimes the physical address is a pfn, and sometimes its
+ an mfn. We can tell which is which from the index. */
+ void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
+ phys_addr_t phys, pgprot_t flags);
+};
+
+struct raw_spinlock;
+struct pv_lock_ops {
+ int (*spin_is_locked)(struct raw_spinlock *lock);
+ int (*spin_is_contended)(struct raw_spinlock *lock);
+ void (*spin_lock)(struct raw_spinlock *lock);
+ void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
+ int (*spin_trylock)(struct raw_spinlock *lock);
+ void (*spin_unlock)(struct raw_spinlock *lock);
+};
+
+/* This contains all the paravirt structures: we get a convenient
+ * number for each function using the offset which we use to indicate
+ * what to patch. */
+struct paravirt_patch_template {
+ struct pv_init_ops pv_init_ops;
+ struct pv_time_ops pv_time_ops;
+ struct pv_cpu_ops pv_cpu_ops;
+ struct pv_irq_ops pv_irq_ops;
+ struct pv_apic_ops pv_apic_ops;
+ struct pv_mmu_ops pv_mmu_ops;
+ struct pv_lock_ops pv_lock_ops;
+};
+
+extern struct pv_info pv_info;
+extern struct pv_init_ops pv_init_ops;
+extern struct pv_time_ops pv_time_ops;
+extern struct pv_cpu_ops pv_cpu_ops;
+extern struct pv_irq_ops pv_irq_ops;
+extern struct pv_apic_ops pv_apic_ops;
+extern struct pv_mmu_ops pv_mmu_ops;
+extern struct pv_lock_ops pv_lock_ops;
+
+#define PARAVIRT_PATCH(x) \
+ (offsetof(struct paravirt_patch_template, x) / sizeof(void *))
+
+#define paravirt_type(op) \
+ [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \
+ [paravirt_opptr] "i" (&(op))
+#define paravirt_clobber(clobber) \
+ [paravirt_clobber] "i" (clobber)
+
+/*
+ * Generate some code, and mark it as patchable by the
+ * apply_paravirt() alternate instruction patcher.
+ */
+#define _paravirt_alt(insn_string, type, clobber) \
+ "771:\n\t" insn_string "\n" "772:\n" \
+ ".pushsection .parainstructions,\"a\"\n" \
+ _ASM_ALIGN "\n" \
+ _ASM_PTR " 771b\n" \
+ " .byte " type "\n" \
+ " .byte 772b-771b\n" \
+ " .short " clobber "\n" \
+ ".popsection\n"
+
+/* Generate patchable code, with the default asm parameters. */
+#define paravirt_alt(insn_string) \
+ _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+
+/* Simple instruction patching code. */
+#define DEF_NATIVE(ops, name, code) \
+ extern const char start_##ops##_##name[], end_##ops##_##name[]; \
+ asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
+
+unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len);
+unsigned paravirt_patch_ignore(unsigned len);
+unsigned paravirt_patch_call(void *insnbuf,
+ const void *target, u16 tgt_clobbers,
+ unsigned long addr, u16 site_clobbers,
+ unsigned len);
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
+ unsigned long addr, unsigned len);
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+ unsigned long addr, unsigned len);
+
+unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
+ const char *start, const char *end);
+
+unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
+ unsigned long addr, unsigned len);
+
+int paravirt_disable_iospace(void);
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
+ */
+#define PARAVIRT_CALL "call *%c[paravirt_opptr];"
+
+/*
+ * These macros are intended to wrap calls through one of the paravirt
+ * ops structs, so that they can be later identified and patched at
+ * runtime.
+ *
+ * Normally, a call to a pv_op function is a simple indirect call:
+ * (pv_op_struct.operations)(args...).
+ *
+ * Unfortunately, this is a relatively slow operation for modern CPUs,
+ * because it cannot necessarily determine what the destination
+ * address is. In this case, the address is a runtime constant, so at
+ * the very least we can patch the call to e a simple direct call, or
+ * ideally, patch an inline implementation into the callsite. (Direct
+ * calls are essentially free, because the call and return addresses
+ * are completely predictable.)
+ *
+ * For i386, these macros rely on the standard gcc "regparm(3)" calling
+ * convention, in which the first three arguments are placed in %eax,
+ * %edx, %ecx (in that order), and the remaining arguments are placed
+ * on the stack. All caller-save registers (eax,edx,ecx) are expected
+ * to be modified (either clobbered or used for return values).
+ * X86_64, on the other hand, already specifies a register-based calling
+ * conventions, returning at %rax, with parameteres going on %rdi, %rsi,
+ * %rdx, and %rcx. Note that for this reason, x86_64 does not need any
+ * special handling for dealing with 4 arguments, unlike i386.
+ * However, x86_64 also have to clobber all caller saved registers, which
+ * unfortunately, are quite a bit (r8 - r11)
+ *
+ * The call instruction itself is marked by placing its start address
+ * and size into the .parainstructions section, so that
+ * apply_paravirt() in arch/i386/kernel/alternative.c can do the
+ * appropriate patching under the control of the backend pv_init_ops
+ * implementation.
+ *
+ * Unfortunately there's no way to get gcc to generate the args setup
+ * for the call, and then allow the call itself to be generated by an
+ * inline asm. Because of this, we must do the complete arg setup and
+ * return value handling from within these macros. This is fairly
+ * cumbersome.
+ *
+ * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
+ * It could be extended to more arguments, but there would be little
+ * to be gained from that. For each number of arguments, there are
+ * the two VCALL and CALL variants for void and non-void functions.
+ *
+ * When there is a return value, the invoker of the macro must specify
+ * the return type. The macro then uses sizeof() on that type to
+ * determine whether its a 32 or 64 bit value, and places the return
+ * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
+ * 64-bit). For x86_64 machines, it just returns at %rax regardless of
+ * the return value size.
+ *
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
+ * in low,high order
+ *
+ * Small structures are passed and returned in registers. The macro
+ * calling convention can't directly deal with this, so the wrapper
+ * functions must do this.
+ *
+ * These PVOP_* macros are only defined within this header. This
+ * means that all uses must be wrapped in inline functions. This also
+ * makes sure the incoming and outgoing types are always correct.
+ */
+#ifdef CONFIG_X86_32
+#define PVOP_VCALL_ARGS \
+ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx
+#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
+
+#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x))
+
+#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \
+ "=c" (__ecx)
+#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS
+
+#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx)
+#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
+
+#define EXTRA_CLOBBERS
+#define VEXTRA_CLOBBERS
+#else /* CONFIG_X86_64 */
+#define PVOP_VCALL_ARGS \
+ unsigned long __edi = __edi, __esi = __esi, \
+ __edx = __edx, __ecx = __ecx
+#define PVOP_CALL_ARGS PVOP_VCALL_ARGS, __eax
+
+#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
+#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x))
+#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x))
+#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x))
+
+#define PVOP_VCALL_CLOBBERS "=D" (__edi), \
+ "=S" (__esi), "=d" (__edx), \
+ "=c" (__ecx)
+#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax)
+
+#define PVOP_VCALLEE_CLOBBERS "=a" (__eax)
+#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS
+
+#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11"
+#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11"
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_PARAVIRT_DEBUG
+#define PVOP_TEST_NULL(op) BUG_ON(op == NULL)
+#else
+#define PVOP_TEST_NULL(op) ((void)op)
+#endif
+
+#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
+ pre, post, ...) \
+ ({ \
+ rettype __ret; \
+ PVOP_CALL_ARGS; \
+ PVOP_TEST_NULL(op); \
+ /* This is 32-bit specific, but is okay in 64-bit */ \
+ /* since this condition will never hold */ \
+ if (sizeof(rettype) > sizeof(unsigned long)) { \
+ asm volatile(pre \
+ paravirt_alt(PARAVIRT_CALL) \
+ post \
+ : call_clbr \
+ : paravirt_type(op), \
+ paravirt_clobber(clbr), \
+ ##__VA_ARGS__ \
+ : "memory", "cc" extra_clbr); \
+ __ret = (rettype)((((u64)__edx) << 32) | __eax); \
+ } else { \
+ asm volatile(pre \
+ paravirt_alt(PARAVIRT_CALL) \
+ post \
+ : call_clbr \
+ : paravirt_type(op), \
+ paravirt_clobber(clbr), \
+ ##__VA_ARGS__ \
+ : "memory", "cc" extra_clbr); \
+ __ret = (rettype)__eax; \
+ } \
+ __ret; \
+ })
+
+#define __PVOP_CALL(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \
+ EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
+ PVOP_CALLEE_CLOBBERS, , \
+ pre, post, ##__VA_ARGS__)
+
+
+#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
+ ({ \
+ PVOP_VCALL_ARGS; \
+ PVOP_TEST_NULL(op); \
+ asm volatile(pre \
+ paravirt_alt(PARAVIRT_CALL) \
+ post \
+ : call_clbr \
+ : paravirt_type(op), \
+ paravirt_clobber(clbr), \
+ ##__VA_ARGS__ \
+ : "memory", "cc" extra_clbr); \
+ })
+
+#define __PVOP_VCALL(op, pre, post, ...) \
+ ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
+ VEXTRA_CLOBBERS, \
+ pre, post, ##__VA_ARGS__)
+
+#define __PVOP_VCALLEESAVE(rettype, op, pre, post, ...) \
+ ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , \
+ pre, post, ##__VA_ARGS__)
+
+
+
+#define PVOP_CALL0(rettype, op) \
+ __PVOP_CALL(rettype, op, "", "")
+#define PVOP_VCALL0(op) \
+ __PVOP_VCALL(op, "", "")
+
+#define PVOP_CALLEE0(rettype, op) \
+ __PVOP_CALLEESAVE(rettype, op, "", "")
+#define PVOP_VCALLEE0(op) \
+ __PVOP_VCALLEESAVE(op, "", "")
+
+
+#define PVOP_CALL1(rettype, op, arg1) \
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+#define PVOP_VCALL1(op, arg1) \
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+
+#define PVOP_CALLEE1(rettype, op, arg1) \
+ __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+#define PVOP_VCALLEE1(op, arg1) \
+ __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+
+
+#define PVOP_CALL2(rettype, op, arg1, arg2) \
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+#define PVOP_VCALL2(op, arg1, arg2) \
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+
+#define PVOP_CALLEE2(rettype, op, arg1, arg2) \
+ __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+#define PVOP_VCALLEE2(op, arg1, arg2) \
+ __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2))
+
+
+#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
+ __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
+#define PVOP_VCALL3(op, arg1, arg2, arg3) \
+ __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
+
+/* This is the only difference in x86_64. We can make it much simpler */
+#ifdef CONFIG_X86_32
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
+ __PVOP_CALL(rettype, op, \
+ "push %[_arg4];", "lea 4(%%esp),%%esp;", \
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
+ __PVOP_VCALL(op, \
+ "push %[_arg4];", "lea 4(%%esp),%%esp;", \
+ "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
+ "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+#else
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
+ __PVOP_CALL(rettype, op, "", "", \
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
+ __PVOP_VCALL(op, "", "", \
+ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
+#endif
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+ PARAVIRT_LAZY_NONE,
+ PARAVIRT_LAZY_MMU,
+ PARAVIRT_LAZY_CPU,
+};
+
+enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
+void paravirt_enter_lazy_mmu(void);
+void paravirt_leave_lazy_mmu(void);
+
+void _paravirt_nop(void);
+u32 _paravirt_ident_32(u32);
+u64 _paravirt_ident_64(u64);
+
+#define paravirt_nop ((void *)_paravirt_nop)
+
+/* These all sit in the .parainstructions section to tell us what to patch. */
+struct paravirt_patch_site {
+ u8 *instr; /* original instructions */
+ u8 instrtype; /* type of this instruction */
+ u8 len; /* length of original instruction */
+ u16 clobbers; /* what registers you may clobber */
+};
+
+extern struct paravirt_patch_site __parainstructions[],
+ __parainstructions_end[];
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 7af14e512f9..e2c1668dde7 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -19,4 +19,9 @@ extern int free_memtype(u64 start, u64 end);
extern int kernel_map_sync_memtype(u64 base, unsigned long size,
unsigned long flag);
+int io_reserve_memtype(resource_size_t start, resource_size_t end,
+ unsigned long *type);
+
+void io_free_memtype(resource_size_t start, resource_size_t end);
+
#endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 1ff685ca221..f76a162c082 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -48,7 +48,6 @@ extern unsigned int pcibios_assign_all_busses(void);
#else
#define pcibios_assign_all_busses() 0
#endif
-#define pcibios_scan_all_fns(a, b) 0
extern unsigned long pci_mem_start;
#define PCIBIOS_MIN_IO 0x1000
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 103f1ddb0d8..b65a36defeb 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -49,7 +49,7 @@
#define __percpu_arg(x) "%%"__stringify(__percpu_seg)":%P" #x
#define __my_cpu_offset percpu_read(this_cpu_off)
#else
-#define __percpu_arg(x) "%" #x
+#define __percpu_arg(x) "%P" #x
#endif
/*
@@ -104,36 +104,48 @@ do { \
} \
} while (0)
-#define percpu_from_op(op, var) \
+#define percpu_from_op(op, var, constraint) \
({ \
typeof(var) ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_arg(1)",%0" \
: "=q" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 2: \
asm(op "w "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 4: \
asm(op "l "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
case 8: \
asm(op "q "__percpu_arg(1)",%0" \
: "=r" (ret__) \
- : "m" (var)); \
+ : constraint); \
break; \
default: __bad_percpu_size(); \
} \
ret__; \
})
-#define percpu_read(var) percpu_from_op("mov", per_cpu__##var)
+/*
+ * percpu_read() makes gcc load the percpu variable every time it is
+ * accessed while percpu_read_stable() allows the value to be cached.
+ * percpu_read_stable() is more efficient and can be used if its value
+ * is guaranteed to be valid across cpus. The current users include
+ * get_current() and get_thread_info() both of which are actually
+ * per-thread variables implemented as per-cpu variables and thus
+ * stable for the duration of the respective task.
+ */
+#define percpu_read(var) percpu_from_op("mov", per_cpu__##var, \
+ "m" (per_cpu__##var))
+#define percpu_read_stable(var) percpu_from_op("mov", per_cpu__##var, \
+ "p" (&per_cpu__##var))
#define percpu_write(var, val) percpu_to_op("mov", per_cpu__##var, val)
#define percpu_add(var, val) percpu_to_op("add", per_cpu__##var, val)
#define percpu_sub(var, val) percpu_to_op("sub", per_cpu__##var, val)
@@ -156,15 +168,6 @@ do { \
/* We can use this directly for local CPU (faster). */
DECLARE_PER_CPU(unsigned long, this_cpu_off);
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-void *pcpu_lpage_remapped(void *kaddr);
-#else
-static inline void *pcpu_lpage_remapped(void *kaddr)
-{
- return NULL;
-}
-#endif
-
#endif /* !__ASSEMBLY__ */
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index fa64e401589..e7b7c938ae2 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -84,6 +84,16 @@ union cpuid10_edx {
#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b
#define X86_PMC_IDX_FIXED_BUS_CYCLES (X86_PMC_IDX_FIXED + 2)
+/*
+ * We model BTS tracing as another fixed-mode PMC.
+ *
+ * We choose a value in the middle of the fixed counter range, since lower
+ * values are used by actual fixed counters and higher values are used
+ * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
+ */
+#define X86_PMC_IDX_FIXED_BTS (X86_PMC_IDX_FIXED + 16)
+
+
#ifdef CONFIG_PERF_COUNTERS
extern void init_hw_perf_counters(void);
extern void perf_counters_lapic_init(void);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 16748077559..4c5b51fdc78 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -135,6 +135,11 @@ static inline unsigned long pte_pfn(pte_t pte)
return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+ return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
static inline int pmd_large(pmd_t pte)
@@ -359,7 +364,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
* this macro returns the index of the entry in the pmd page which would
* control the given virtual address
*/
-static inline unsigned pmd_index(unsigned long address)
+static inline unsigned long pmd_index(unsigned long address)
{
return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}
@@ -379,7 +384,7 @@ static inline unsigned pmd_index(unsigned long address)
* this function returns the index of the entry in the pte page which would
* control the given virtual address
*/
-static inline unsigned pte_index(unsigned long address)
+static inline unsigned long pte_index(unsigned long address)
{
return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}
@@ -430,11 +435,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
}
-static inline unsigned long pmd_pfn(pmd_t pmd)
-{
- return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
-}
-
static inline int pud_large(pud_t pud)
{
return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
@@ -470,7 +470,7 @@ static inline unsigned long pgd_page_vaddr(pgd_t pgd)
#define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
/* to find an entry in a page-table-directory. */
-static inline unsigned pud_index(unsigned long address)
+static inline unsigned long pud_index(unsigned long address)
{
return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c7768269b1c..e08ea043e08 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -403,7 +403,17 @@ extern unsigned long kernel_eflags;
extern asmlinkage void ignore_sysret(void);
#else /* X86_64 */
#ifdef CONFIG_CC_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, stack_canary);
+/*
+ * Make sure stack canary segment base is cached-aligned:
+ * "For Intel Atom processors, avoid non zero segment base address
+ * that is not aligned to cache line boundary at all cost."
+ * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
+ */
+struct stack_canary {
+ char __pad[20]; /* canary at %gs:20 */
+ unsigned long canary;
+};
+DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
#endif
#endif /* X86_64 */
@@ -703,13 +713,23 @@ static inline void cpu_relax(void)
rep_nop();
}
-/* Stop speculative execution: */
+/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
int tmp;
- asm volatile("cpuid" : "=a" (tmp) : "0" (1)
- : "ebx", "ecx", "edx", "memory");
+#if defined(CONFIG_M386) || defined(CONFIG_M486)
+ if (boot_cpu_data.x86 < 5)
+ /* There is no speculative execution.
+ * jmp is a barrier to prefetching. */
+ asm volatile("jmp 1f\n1:\n" ::: "memory");
+ else
+#endif
+ /* cpuid is a barrier to speculative execution.
+ * Prefetched instructions are automatically
+ * invalidated when modified. */
+ asm volatile("cpuid" : "=a" (tmp) : "0" (1)
+ : "ebx", "ecx", "edx", "memory");
}
static inline void __monitor(const void *eax, unsigned long ecx,
diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h
index 263d397d2ee..75af592677e 100644
--- a/arch/x86/include/asm/scatterlist.h
+++ b/arch/x86/include/asm/scatterlist.h
@@ -1,33 +1,8 @@
#ifndef _ASM_X86_SCATTERLIST_H
#define _ASM_X86_SCATTERLIST_H
-#include <asm/types.h>
-
-struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
- unsigned long sg_magic;
-#endif
- unsigned long page_link;
- unsigned int offset;
- unsigned int length;
- dma_addr_t dma_address;
- unsigned int dma_length;
-};
-
-#define ARCH_HAS_SG_CHAIN
#define ISA_DMA_THRESHOLD (0x00ffffff)
-/*
- * These macros should be used after a pci_map_sg call has been done
- * to get bus addresses of each of the SG entries and their lengths.
- * You should only work with the number of sg entries pci_map_sg
- * returns.
- */
-#define sg_dma_address(sg) ((sg)->dma_address)
-#ifdef CONFIG_X86_32
-# define sg_dma_len(sg) ((sg)->length)
-#else
-# define sg_dma_len(sg) ((sg)->dma_length)
-#endif
+#include <asm-generic/scatterlist.h>
#endif /* _ASM_X86_SCATTERLIST_H */
diff --git a/arch/x86/include/asm/shmbuf.h b/arch/x86/include/asm/shmbuf.h
index b51413b7497..83c05fc2de3 100644
--- a/arch/x86/include/asm/shmbuf.h
+++ b/arch/x86/include/asm/shmbuf.h
@@ -1,51 +1 @@
-#ifndef _ASM_X86_SHMBUF_H
-#define _ASM_X86_SHMBUF_H
-
-/*
- * The shmid64_ds structure for x86 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space on 32 bit is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- *
- * Pad space on 64 bit is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
- struct ipc64_perm shm_perm; /* operation perms */
- size_t shm_segsz; /* size of segment (bytes) */
- __kernel_time_t shm_atime; /* last attach time */
-#ifdef __i386__
- unsigned long __unused1;
-#endif
- __kernel_time_t shm_dtime; /* last detach time */
-#ifdef __i386__
- unsigned long __unused2;
-#endif
- __kernel_time_t shm_ctime; /* last change time */
-#ifdef __i386__
- unsigned long __unused3;
-#endif
- __kernel_pid_t shm_cpid; /* pid of creator */
- __kernel_pid_t shm_lpid; /* pid of last operator */
- unsigned long shm_nattch; /* no. of current attaches */
- unsigned long __unused4;
- unsigned long __unused5;
-};
-
-struct shminfo64 {
- unsigned long shmmax;
- unsigned long shmmin;
- unsigned long shmmni;
- unsigned long shmseg;
- unsigned long shmall;
- unsigned long __unused1;
- unsigned long __unused2;
- unsigned long __unused3;
- unsigned long __unused4;
-};
-
-#endif /* _ASM_X86_SHMBUF_H */
+#include <asm-generic/shmbuf.h>
diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h
index ca8bf2cd0ba..6b71384b9d8 100644
--- a/arch/x86/include/asm/socket.h
+++ b/arch/x86/include/asm/socket.h
@@ -1,60 +1 @@
-#ifndef _ASM_X86_SOCKET_H
-#define _ASM_X86_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET 1
-
-#define SO_DEBUG 1
-#define SO_REUSEADDR 2
-#define SO_TYPE 3
-#define SO_ERROR 4
-#define SO_DONTROUTE 5
-#define SO_BROADCAST 6
-#define SO_SNDBUF 7
-#define SO_RCVBUF 8
-#define SO_SNDBUFFORCE 32
-#define SO_RCVBUFFORCE 33
-#define SO_KEEPALIVE 9
-#define SO_OOBINLINE 10
-#define SO_NO_CHECK 11
-#define SO_PRIORITY 12
-#define SO_LINGER 13
-#define SO_BSDCOMPAT 14
-/* To add :#define SO_REUSEPORT 15 */
-#define SO_PASSCRED 16
-#define SO_PEERCRED 17
-#define SO_RCVLOWAT 18
-#define SO_SNDLOWAT 19
-#define SO_RCVTIMEO 20
-#define SO_SNDTIMEO 21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION 22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT 23
-#define SO_SECURITY_ENCRYPTION_NETWORK 24
-
-#define SO_BINDTODEVICE 25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER 26
-#define SO_DETACH_FILTER 27
-
-#define SO_PEERNAME 28
-#define SO_TIMESTAMP 29
-#define SCM_TIMESTAMP SO_TIMESTAMP
-
-#define SO_ACCEPTCONN 30
-
-#define SO_PEERSEC 31
-#define SO_PASSSEC 34
-#define SO_TIMESTAMPNS 35
-#define SCM_TIMESTAMPNS SO_TIMESTAMPNS
-
-#define SO_MARK 36
-
-#define SO_TIMESTAMPING 37
-#define SCM_TIMESTAMPING SO_TIMESTAMPING
-
-#endif /* _ASM_X86_SOCKET_H */
+#include <asm-generic/socket.h>
diff --git a/arch/x86/include/asm/sockios.h b/arch/x86/include/asm/sockios.h
index 49cc72b5d3c..def6d4746ee 100644
--- a/arch/x86/include/asm/sockios.h
+++ b/arch/x86/include/asm/sockios.h
@@ -1,13 +1 @@
-#ifndef _ASM_X86_SOCKIOS_H
-#define _ASM_X86_SOCKIOS_H
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 0x8901
-#define SIOCSPGRP 0x8902
-#define FIOGETOWN 0x8903
-#define SIOCGPGRP 0x8904
-#define SIOCATMARK 0x8905
-#define SIOCGSTAMP 0x8906 /* Get stamp (timeval) */
-#define SIOCGSTAMPNS 0x8907 /* Get stamp (timespec) */
-
-#endif /* _ASM_X86_SOCKIOS_H */
+#include <asm-generic/sockios.h>
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index c2d742c6e15..15751776356 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -48,7 +48,7 @@
* head_32 for boot CPU and setup_per_cpu_areas() for others.
*/
#define GDT_STACK_CANARY_INIT \
- [GDT_ENTRY_STACK_CANARY] = { { { 0x00000018, 0x00409000 } } },
+ [GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
/*
* Initialize the stackprotector canary value.
@@ -78,21 +78,19 @@ static __always_inline void boot_init_stack_canary(void)
#ifdef CONFIG_X86_64
percpu_write(irq_stack_union.stack_canary, canary);
#else
- percpu_write(stack_canary, canary);
+ percpu_write(stack_canary.canary, canary);
#endif
}
static inline void setup_stack_canary_segment(int cpu)
{
#ifdef CONFIG_X86_32
- unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu) - 20;
+ unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
struct desc_struct *gdt_table = get_cpu_gdt_table(cpu);
struct desc_struct desc;
desc = gdt_table[GDT_ENTRY_STACK_CANARY];
- desc.base0 = canary & 0xffff;
- desc.base1 = (canary >> 16) & 0xff;
- desc.base2 = (canary >> 24) & 0xff;
+ set_desc_base(&desc, canary);
write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
#endif
}
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 643c59b4bc6..f08f9737489 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -31,7 +31,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
"movl %P[task_canary](%[next]), %%ebx\n\t" \
"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
#define __switch_canary_oparam \
- , [stack_canary] "=m" (per_cpu_var(stack_canary))
+ , [stack_canary] "=m" (per_cpu_var(stack_canary.canary))
#define __switch_canary_iparam \
, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
#else /* CC_STACKPROTECTOR */
@@ -150,33 +150,6 @@ do { \
#endif
#ifdef __KERNEL__
-#define _set_base(addr, base) do { unsigned long __pr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
- "rorl $16,%%edx\n\t" \
- "movb %%dl,%2\n\t" \
- "movb %%dh,%3" \
- :"=&d" (__pr) \
- :"m" (*((addr)+2)), \
- "m" (*((addr)+4)), \
- "m" (*((addr)+7)), \
- "0" (base) \
- ); } while (0)
-
-#define _set_limit(addr, limit) do { unsigned long __lr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
- "rorl $16,%%edx\n\t" \
- "movb %2,%%dh\n\t" \
- "andb $0xf0,%%dh\n\t" \
- "orb %%dh,%%dl\n\t" \
- "movb %%dl,%2" \
- :"=&d" (__lr) \
- :"m" (*(addr)), \
- "m" (*((addr)+6)), \
- "0" (limit) \
- ); } while (0)
-
-#define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
-#define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
extern void native_load_gs_index(unsigned);
diff --git a/arch/x86/include/asm/termbits.h b/arch/x86/include/asm/termbits.h
index af1b70ea440..3935b106de7 100644
--- a/arch/x86/include/asm/termbits.h
+++ b/arch/x86/include/asm/termbits.h
@@ -1,198 +1 @@
-#ifndef _ASM_X86_TERMBITS_H
-#define _ASM_X86_TERMBITS_H
-
-#include <linux/posix_types.h>
-
-typedef unsigned char cc_t;
-typedef unsigned int speed_t;
-typedef unsigned int tcflag_t;
-
-#define NCCS 19
-struct termios {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
-};
-
-struct termios2 {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
- speed_t c_ispeed; /* input speed */
- speed_t c_ospeed; /* output speed */
-};
-
-struct ktermios {
- tcflag_t c_iflag; /* input mode flags */
- tcflag_t c_oflag; /* output mode flags */
- tcflag_t c_cflag; /* control mode flags */
- tcflag_t c_lflag; /* local mode flags */
- cc_t c_line; /* line discipline */
- cc_t c_cc[NCCS]; /* control characters */
- speed_t c_ispeed; /* input speed */
- speed_t c_ospeed; /* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK 0000001
-#define BRKINT 0000002
-#define IGNPAR 0000004
-#define PARMRK 0000010
-#define INPCK 0000020
-#define ISTRIP 0000040
-#define INLCR 0000100
-#define IGNCR 0000200
-#define ICRNL 0000400
-#define IUCLC 0001000
-#define IXON 0002000
-#define IXANY 0004000
-#define IXOFF 0010000
-#define IMAXBEL 0020000
-#define IUTF8 0040000
-
-/* c_oflag bits */
-#define OPOST 0000001
-#define OLCUC 0000002
-#define ONLCR 0000004
-#define OCRNL 0000010
-#define ONOCR 0000020
-#define ONLRET 0000040
-#define OFILL 0000100
-#define OFDEL 0000200
-#define NLDLY 0000400
-#define NL0 0000000
-#define NL1 0000400
-#define CRDLY 0003000
-#define CR0 0000000
-#define CR1 0001000
-#define CR2 0002000
-#define CR3 0003000
-#define TABDLY 0014000
-#define TAB0 0000000
-#define TAB1 0004000
-#define TAB2 0010000
-#define TAB3 0014000
-#define XTABS 0014000
-#define BSDLY 0020000
-#define BS0 0000000
-#define BS1 0020000
-#define VTDLY 0040000
-#define VT0 0000000
-#define VT1 0040000
-#define FFDLY 0100000
-#define FF0 0000000
-#define FF1 0100000
-
-/* c_cflag bit meaning */
-#define CBAUD 0010017
-#define B0 0000000 /* hang up */
-#define B50 0000001
-#define B75 0000002
-#define B110 0000003
-#define B134 0000004
-#define B150 0000005
-#define B200 0000006
-#define B300 0000007
-#define B600 0000010
-#define B1200 0000011
-#define B1800 0000012
-#define B2400 0000013
-#define B4800 0000014
-#define B9600 0000015
-#define B19200 0000016
-#define B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE 0000060
-#define CS5 0000000
-#define CS6 0000020
-#define CS7 0000040
-#define CS8 0000060
-#define CSTOPB 0000100
-#define CREAD 0000200
-#define PARENB 0000400
-#define PARODD 0001000
-#define HUPCL 0002000
-#define CLOCAL 0004000
-#define CBAUDEX 0010000
-#define BOTHER 0010000 /* non standard rate */
-#define B57600 0010001
-#define B115200 0010002
-#define B230400 0010003
-#define B460800 0010004
-#define B500000 0010005
-#define B576000 0010006
-#define B921600 0010007
-#define B1000000 0010010
-#define B1152000 0010011
-#define B1500000 0010012
-#define B2000000 0010013
-#define B2500000 0010014
-#define B3000000 0010015
-#define B3500000 0010016
-#define B4000000 0010017
-#define CIBAUD 002003600000 /* input baud rate */
-#define CMSPAR 010000000000 /* mark or space (stick) parity */
-#define CRTSCTS 020000000000 /* flow control */
-
-#define IBSHIFT 16 /* Shift from CBAUD to CIBAUD */
-
-/* c_lflag bits */
-#define ISIG 0000001
-#define ICANON 0000002
-#define XCASE 0000004
-#define ECHO 0000010
-#define ECHOE 0000020
-#define ECHOK 0000040
-#define ECHONL 0000100
-#define NOFLSH 0000200
-#define TOSTOP 0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE 0004000
-#define FLUSHO 0010000
-#define PENDIN 0040000
-#define IEXTEN 0100000
-
-/* tcflow() and TCXONC use these */
-#define TCOOFF 0
-#define TCOON 1
-#define TCIOFF 2
-#define TCION 3
-
-/* tcflush() and TCFLSH use these */
-#define TCIFLUSH 0
-#define TCOFLUSH 1
-#define TCIOFLUSH 2
-
-/* tcsetattr uses these */
-#define TCSANOW 0
-#define TCSADRAIN 1
-#define TCSAFLUSH 2
-
-#endif /* _ASM_X86_TERMBITS_H */
+#include <asm-generic/termbits.h>
diff --git a/arch/x86/include/asm/termios.h b/arch/x86/include/asm/termios.h
index c4ee8056bac..280d78a9d96 100644
--- a/arch/x86/include/asm/termios.h
+++ b/arch/x86/include/asm/termios.h
@@ -1,114 +1 @@
-#ifndef _ASM_X86_TERMIOS_H
-#define _ASM_X86_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
- unsigned short ws_row;
- unsigned short ws_col;
- unsigned short ws_xpixel;
- unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
- unsigned short c_iflag; /* input mode flags */
- unsigned short c_oflag; /* output mode flags */
- unsigned short c_cflag; /* control mode flags */
- unsigned short c_lflag; /* local mode flags */
- unsigned char c_line; /* line discipline */
- unsigned char c_cc[NCC]; /* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE 0x001
-#define TIOCM_DTR 0x002
-#define TIOCM_RTS 0x004
-#define TIOCM_ST 0x008
-#define TIOCM_SR 0x010
-#define TIOCM_CTS 0x020
-#define TIOCM_CAR 0x040
-#define TIOCM_RNG 0x080
-#define TIOCM_DSR 0x100
-#define TIOCM_CD TIOCM_CAR
-#define TIOCM_RI TIOCM_RNG
-#define TIOCM_OUT1 0x2000
-#define TIOCM_OUT2 0x4000
-#define TIOCM_LOOP 0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#ifdef __KERNEL__
-
-#include <asm/uaccess.h>
-
-/* intr=^C quit=^\ erase=del kill=^U
- eof=^D vtime=\0 vmin=\1 sxtc=\0
- start=^Q stop=^S susp=^Z eol=\0
- reprint=^R discard=^U werase=^W lnext=^V
- eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
- unsigned short __tmp; \
- get_user(__tmp,&(termio)->x); \
- *(unsigned short *) &(termios)->x = __tmp; \
-}
-
-static inline int user_termio_to_kernel_termios(struct ktermios *termios,
- struct termio __user *termio)
-{
- SET_LOW_TERMIOS_BITS(termios, termio, c_iflag);
- SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
- SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
- SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
- get_user(termios->c_line, &termio->c_line);
- return copy_from_user(termios->c_cc, termio->c_cc, NCC);
-}
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-static inline int kernel_termios_to_user_termio(struct termio __user *termio,
- struct ktermios *termios)
-{
- put_user((termios)->c_iflag, &(termio)->c_iflag);
- put_user((termios)->c_oflag, &(termio)->c_oflag);
- put_user((termios)->c_cflag, &(termio)->c_cflag);
- put_user((termios)->c_lflag, &(termio)->c_lflag);
- put_user((termios)->c_line, &(termio)->c_line);
- return copy_to_user((termio)->c_cc, (termios)->c_cc, NCC);
-}
-
-static inline int user_termios_to_kernel_termios(struct ktermios *k,
- struct termios2 __user *u)
-{
- return copy_from_user(k, u, sizeof(struct termios2));
-}
-
-static inline int kernel_termios_to_user_termios(struct termios2 __user *u,
- struct ktermios *k)
-{
- return copy_to_user(u, k, sizeof(struct termios2));
-}
-
-static inline int user_termios_to_kernel_termios_1(struct ktermios *k,
- struct termios __user *u)
-{
- return copy_from_user(k, u, sizeof(struct termios));
-}
-
-static inline int kernel_termios_to_user_termios_1(struct termios __user *u,
- struct ktermios *k)
-{
- return copy_to_user(u, k, sizeof(struct termios));
-}
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_TERMIOS_H */
+#include <asm-generic/termios.h>
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 6f7786aea4f..d27d0a2fec4 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -214,7 +214,7 @@ DECLARE_PER_CPU(unsigned long, kernel_stack);
static inline struct thread_info *current_thread_info(void)
{
struct thread_info *ti;
- ti = (void *)(percpu_read(kernel_stack) +
+ ti = (void *)(percpu_read_stable(kernel_stack) +
KERNEL_STACK_OFFSET - THREAD_SIZE);
return ti;
}
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 066ef590d7e..26d06e052a1 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -129,25 +129,34 @@ extern unsigned long node_remap_size[];
#endif
/* sched_domains SD_NODE_INIT for NUMA machines */
-#define SD_NODE_INIT (struct sched_domain) { \
- .min_interval = 8, \
- .max_interval = 32, \
- .busy_factor = 32, \
- .imbalance_pct = 125, \
- .cache_nice_tries = SD_CACHE_NICE_TRIES, \
- .busy_idx = 3, \
- .idle_idx = SD_IDLE_IDX, \
- .newidle_idx = SD_NEWIDLE_IDX, \
- .wake_idx = 1, \
- .forkexec_idx = SD_FORKEXEC_IDX, \
- .flags = SD_LOAD_BALANCE \
- | SD_BALANCE_EXEC \
- | SD_BALANCE_FORK \
- | SD_WAKE_AFFINE \
- | SD_WAKE_BALANCE \
- | SD_SERIALIZE, \
- .last_balance = jiffies, \
- .balance_interval = 1, \
+#define SD_NODE_INIT (struct sched_domain) { \
+ .min_interval = 8, \
+ .max_interval = 32, \
+ .busy_factor = 32, \
+ .imbalance_pct = 125, \
+ .cache_nice_tries = SD_CACHE_NICE_TRIES, \
+ .busy_idx = 3, \
+ .idle_idx = SD_IDLE_IDX, \
+ .newidle_idx = SD_NEWIDLE_IDX, \
+ .wake_idx = 1, \
+ .forkexec_idx = SD_FORKEXEC_IDX, \
+ \
+ .flags = 1*SD_LOAD_BALANCE \
+ | 1*SD_BALANCE_NEWIDLE \
+ | 1*SD_BALANCE_EXEC \
+ | 1*SD_BALANCE_FORK \
+ | 0*SD_WAKE_IDLE \
+ | 1*SD_WAKE_AFFINE \
+ | 1*SD_WAKE_BALANCE \
+ | 0*SD_SHARE_CPUPOWER \
+ | 0*SD_POWERSAVINGS_BALANCE \
+ | 0*SD_SHARE_PKG_RESOURCES \
+ | 1*SD_SERIALIZE \
+ | 1*SD_WAKE_IDLE_FAR \
+ | 0*SD_PREFER_SIBLING \
+ , \
+ .last_balance = jiffies, \
+ .balance_interval = 1, \
}
#ifdef CONFIG_X86_64_ACPI_NUMA
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index bfd74c032fc..4da91ad69e0 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -81,9 +81,7 @@ extern int panic_on_unrecovered_nmi;
void math_error(void __user *);
void math_emulate(struct math_emu_info *);
-#ifdef CONFIG_X86_32
-unsigned long patch_espfix_desc(unsigned long, unsigned long);
-#else
+#ifndef CONFIG_X86_32
asmlinkage void smp_thermal_interrupt(void);
asmlinkage void mce_threshold_interrupt(void);
#endif
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
index 09b97745772..df1da20f453 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -1,19 +1,11 @@
#ifndef _ASM_X86_TYPES_H
#define _ASM_X86_TYPES_H
-#include <asm-generic/int-ll64.h>
+#define dma_addr_t dma_addr_t
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
+#include <asm-generic/types.h>
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
#ifdef __KERNEL__
-
#ifndef __ASSEMBLY__
typedef u64 dma64_addr_t;
diff --git a/arch/x86/include/asm/ucontext.h b/arch/x86/include/asm/ucontext.h
index 87324cf439d..b7c29c8017f 100644
--- a/arch/x86/include/asm/ucontext.h
+++ b/arch/x86/include/asm/ucontext.h
@@ -7,12 +7,6 @@
* sigcontext struct (uc_mcontext).
*/
-struct ucontext {
- unsigned long uc_flags;
- struct ucontext *uc_link;
- stack_t uc_stack;
- struct sigcontext uc_mcontext;
- sigset_t uc_sigmask; /* mask last for extensibility */
-};
+#include <asm-generic/ucontext.h>
#endif /* _ASM_X86_UCONTEXT_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 11be5ad2e0e..272514c2d45 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -55,6 +55,7 @@
#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
#define PIN_BASED_EXT_INTR_MASK 0x00000001
@@ -351,9 +352,16 @@ enum vmcs_field {
#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0
#define VMX_EPT_EXTENT_CONTEXT 1
#define VMX_EPT_EXTENT_GLOBAL 2
+
+#define VMX_EPT_EXECUTE_ONLY_BIT (1ull)
+#define VMX_EPT_PAGE_WALK_4_BIT (1ull << 6)
+#define VMX_EPTP_UC_BIT (1ull << 8)
+#define VMX_EPTP_WB_BIT (1ull << 14)
+#define VMX_EPT_2MB_PAGE_BIT (1ull << 16)
#define VMX_EPT_EXTENT_INDIVIDUAL_BIT (1ull << 24)
#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25)
#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26)
+
#define VMX_EPT_DEFAULT_GAW 3
#define VMX_EPT_MAX_GAW 0x4
#define VMX_EPT_MT_EPTE_SHIFT 3