aboutsummaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kbuild2
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/include/asm/acpi.h9
-rw-r--r--arch/x86/include/asm/dma-contiguous.h13
-rw-r--r--arch/x86/include/asm/dma-mapping.h5
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h13
-rw-r--r--arch/x86/include/asm/kvm_para.h24
-rw-r--r--arch/x86/include/asm/pgtable-3level.h50
-rw-r--r--arch/x86/include/asm/processor.h7
-rw-r--r--arch/x86/include/asm/pvclock-abi.h1
-rw-r--r--arch/x86/include/asm/realmode.h62
-rw-r--r--arch/x86/include/asm/sta2x11.h12
-rw-r--r--arch/x86/include/asm/trampoline.h39
-rw-r--r--arch/x86/include/asm/uaccess.h4
-rw-r--r--arch/x86/include/asm/uaccess_32.h17
-rw-r--r--arch/x86/include/asm/uaccess_64.h3
-rw-r--r--arch/x86/include/asm/word-at-a-time.h32
-rw-r--r--arch/x86/include/asm/xen/events.h1
-rw-r--r--arch/x86/include/asm/xen/page.h1
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/acpi/Makefile9
-rw-r--r--arch/x86/kernel/acpi/realmode/.gitignore3
-rw-r--r--arch/x86/kernel/acpi/realmode/Makefile59
-rw-r--r--arch/x86/kernel/acpi/realmode/bioscall.S1
-rw-r--r--arch/x86/kernel/acpi/realmode/copy.S1
-rw-r--r--arch/x86/kernel/acpi/realmode/regs.c1
-rw-r--r--arch/x86/kernel/acpi/realmode/video-bios.c1
-rw-r--r--arch/x86/kernel/acpi/realmode/video-mode.c1
-rw-r--r--arch/x86/kernel/acpi/realmode/video-vesa.c1
-rw-r--r--arch/x86/kernel/acpi/realmode/video-vga.c1
-rw-r--r--arch/x86/kernel/acpi/realmode/wakeup.lds.S62
-rw-r--r--arch/x86/kernel/acpi/sleep.c33
-rw-r--r--arch/x86/kernel/acpi/sleep.h2
-rw-r--r--arch/x86/kernel/acpi/wakeup_rm.S12
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c26
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c24
-rw-r--r--arch/x86/kernel/e820.c53
-rw-r--r--arch/x86/kernel/head32.c1
-rw-r--r--arch/x86/kernel/head64.c1
-rw-r--r--arch/x86/kernel/head_32.S5
-rw-r--r--arch/x86/kernel/head_64.S4
-rw-r--r--arch/x86/kernel/kvmclock.c20
-rw-r--r--arch/x86/kernel/mpparse.c11
-rw-r--r--arch/x86/kernel/pci-dma.c18
-rw-r--r--arch/x86/kernel/pci-nommu.c8
-rw-r--r--arch/x86/kernel/reboot.c25
-rw-r--r--arch/x86/kernel/setup.c24
-rw-r--r--arch/x86/kernel/smpboot.c18
-rw-r--r--arch/x86/kernel/tboot.c7
-rw-r--r--arch/x86/kernel/trampoline.c42
-rw-r--r--arch/x86/kernel/trampoline_32.S83
-rw-r--r--arch/x86/kernel/vmlinux.lds.S12
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/cpuid.c5
-rw-r--r--arch/x86/kvm/emulate.c293
-rw-r--r--arch/x86/kvm/i8254.c31
-rw-r--r--arch/x86/kvm/i8254.h7
-rw-r--r--arch/x86/kvm/lapic.c31
-rw-r--r--arch/x86/kvm/mmu.c345
-rw-r--r--arch/x86/kvm/mmu_audit.c10
-rw-r--r--arch/x86/kvm/paging_tmpl.h2
-rw-r--r--arch/x86/kvm/svm.c9
-rw-r--r--arch/x86/kvm/vmx.c41
-rw-r--r--arch/x86/kvm/x86.c280
-rw-r--r--arch/x86/kvm/x86.h2
-rw-r--r--arch/x86/lib/usercopy.c97
-rw-r--r--arch/x86/lib/usercopy_32.c41
-rw-r--r--arch/x86/lib/usercopy_64.c48
-rw-r--r--arch/x86/mm/init.c16
-rw-r--r--arch/x86/mm/numa.c32
-rw-r--r--arch/x86/mm/numa_emulation.c4
-rw-r--r--arch/x86/mm/pat.c42
-rw-r--r--arch/x86/mm/srat.c5
-rw-r--r--arch/x86/pci/xen.c4
-rw-r--r--arch/x86/realmode/Makefile18
-rw-r--r--arch/x86/realmode/init.c115
-rw-r--r--arch/x86/realmode/rm/.gitignore3
-rw-r--r--arch/x86/realmode/rm/Makefile82
-rw-r--r--arch/x86/realmode/rm/bioscall.S1
-rw-r--r--arch/x86/realmode/rm/copy.S1
-rw-r--r--arch/x86/realmode/rm/header.S41
-rw-r--r--arch/x86/realmode/rm/realmode.h21
-rw-r--r--arch/x86/realmode/rm/realmode.lds.S76
-rw-r--r--arch/x86/realmode/rm/reboot_32.S (renamed from arch/x86/kernel/reboot_32.S)89
-rw-r--r--arch/x86/realmode/rm/regs.c1
-rw-r--r--arch/x86/realmode/rm/stack.S19
-rw-r--r--arch/x86/realmode/rm/trampoline_32.S74
-rw-r--r--arch/x86/realmode/rm/trampoline_64.S (renamed from arch/x86/kernel/trampoline_64.S)148
-rw-r--r--arch/x86/realmode/rm/trampoline_common.S7
-rw-r--r--arch/x86/realmode/rm/video-bios.c1
-rw-r--r--arch/x86/realmode/rm/video-mode.c1
-rw-r--r--arch/x86/realmode/rm/video-vesa.c1
-rw-r--r--arch/x86/realmode/rm/video-vga.c1
-rw-r--r--arch/x86/realmode/rm/wakemain.c (renamed from arch/x86/kernel/acpi/realmode/wakemain.c)3
-rw-r--r--arch/x86/realmode/rm/wakeup.h (renamed from arch/x86/kernel/acpi/realmode/wakeup.h)10
-rw-r--r--arch/x86/realmode/rm/wakeup_asm.S (renamed from arch/x86/kernel/acpi/realmode/wakeup.S)131
-rw-r--r--arch/x86/realmode/rmpiggy.S20
-rw-r--r--arch/x86/tools/relocs.c7
-rw-r--r--arch/x86/xen/debugfs.c104
-rw-r--r--arch/x86/xen/debugfs.h4
-rw-r--r--arch/x86/xen/enlighten.c13
-rw-r--r--arch/x86/xen/mmu.c23
-rw-r--r--arch/x86/xen/p2m.c104
-rw-r--r--arch/x86/xen/setup.c171
-rw-r--r--arch/x86/xen/smp.c112
-rw-r--r--arch/x86/xen/smp.h12
-rw-r--r--arch/x86/xen/spinlock.c12
-rw-r--r--arch/x86/xen/xen-ops.h1
110 files changed, 2083 insertions, 1566 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
index 0e9dec6cadd..e5287d8517a 100644
--- a/arch/x86/Kbuild
+++ b/arch/x86/Kbuild
@@ -1,4 +1,3 @@
-
obj-$(CONFIG_KVM) += kvm/
# Xen paravirtualization support
@@ -7,6 +6,7 @@ obj-$(CONFIG_XEN) += xen/
# lguest paravirtualization support
obj-$(CONFIG_LGUEST_GUEST) += lguest/
+obj-y += realmode/
obj-y += kernel/
obj-y += mm/
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 66cc380bebf..d700811785e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -32,6 +32,7 @@ config X86
select ARCH_WANT_OPTIONAL_GPIOLIB
select ARCH_WANT_FRAME_POINTERS
select HAVE_DMA_ATTRS
+ select HAVE_DMA_CONTIGUOUS if !SWIOTLB
select HAVE_KRETPROBES
select HAVE_OPTPROBES
select HAVE_FTRACE_MCOUNT_RECORD
@@ -92,6 +93,8 @@ config X86
select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC)
select GENERIC_TIME_VSYSCALL if X86_64
select KTIME_SCALAR if X86_32
+ select GENERIC_STRNCPY_FROM_USER
+ select GENERIC_STRNLEN_USER
config INSTRUCTION_DECODER
def_bool (KPROBES || PERF_EVENTS || UPROBES)
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 610001d385d..0c44630d178 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -29,7 +29,7 @@
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/mpspec.h>
-#include <asm/trampoline.h>
+#include <asm/realmode.h>
#define COMPILER_DEPENDENT_INT64 long long
#define COMPILER_DEPENDENT_UINT64 unsigned long long
@@ -117,11 +117,8 @@ static inline void acpi_disable_pci(void)
/* Low-level suspend routine. */
extern int acpi_suspend_lowlevel(void);
-extern const unsigned char acpi_wakeup_code[];
-#define acpi_wakeup_address (__pa(TRAMPOLINE_SYM(acpi_wakeup_code)))
-
-/* early initialization routine */
-extern void acpi_reserve_wakeup_memory(void);
+/* Physical address to resume after wakeup */
+#define acpi_wakeup_address ((unsigned long)(real_mode_header->wakeup_start))
/*
* Check if the CPU can handle C2 and deeper
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
new file mode 100644
index 00000000000..c0924165997
--- /dev/null
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -0,0 +1,13 @@
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 61c0bd25845..f7b4c7903e7 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -13,6 +13,7 @@
#include <asm/io.h>
#include <asm/swiotlb.h>
#include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
#ifdef CONFIG_ISA
# define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_addr, gfp_t flag,
struct dma_attrs *attrs);
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+ void *vaddr, dma_addr_t dma_addr,
+ struct dma_attrs *attrs);
+
#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index c222e1a1b12..1ac46c22dd5 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -200,7 +200,7 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
/* Type, address-of, and value of an instruction's operand. */
struct operand {
- enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type;
+ enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
unsigned int bytes;
union {
unsigned long orig_val;
@@ -213,12 +213,14 @@ struct operand {
unsigned seg;
} mem;
unsigned xmm;
+ unsigned mm;
} addr;
union {
unsigned long val;
u64 val64;
char valptr[sizeof(unsigned long) + 2];
sse128_t vec_val;
+ u64 mm_val;
};
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e5b97be12d2..db7c1f2709a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -173,6 +173,9 @@ enum {
#define DR7_FIXED_1 0x00000400
#define DR7_VOLATILE 0xffff23ff
+/* apic attention bits */
+#define KVM_APIC_CHECK_VAPIC 0
+
/*
* We don't want allocation failures within the mmu code, so we preallocate
* enough memory for a single page fault in a cache.
@@ -238,8 +241,6 @@ struct kvm_mmu_page {
#endif
int write_flooding_count;
-
- struct rcu_head rcu;
};
struct kvm_pio_request {
@@ -338,6 +339,7 @@ struct kvm_vcpu_arch {
u64 efer;
u64 apic_base;
struct kvm_lapic *apic; /* kernel irqchip context */
+ unsigned long apic_attention;
int32_t apic_arb_prio;
int mp_state;
int sipi_vector;
@@ -537,8 +539,6 @@ struct kvm_arch {
u64 hv_guest_os_id;
u64 hv_hypercall;
- atomic_t reader_counter;
-
#ifdef CONFIG_KVM_MMU_AUDIT
int audit_point;
#endif
@@ -713,8 +713,9 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
- struct kvm_memory_slot *slot);
+void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 183922e13de..63ab1661d00 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -95,6 +95,14 @@ struct kvm_vcpu_pv_apf_data {
extern void kvmclock_init(void);
extern int kvm_register_clock(char *txt);
+#ifdef CONFIG_KVM_CLOCK
+bool kvm_check_and_clear_guest_paused(void);
+#else
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+ return false;
+}
+#endif /* CONFIG_KVMCLOCK */
/* This instruction is vmcall. On non-VT architectures, it will generate a
* trap that we will then rewrite to the appropriate instruction.
@@ -173,14 +181,16 @@ static inline int kvm_para_available(void)
if (boot_cpu_data.cpuid_level < 0)
return 0; /* So we don't blow up on old processors */
- cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
- memcpy(signature + 0, &ebx, 4);
- memcpy(signature + 4, &ecx, 4);
- memcpy(signature + 8, &edx, 4);
- signature[12] = 0;
+ if (cpu_has_hypervisor) {
+ cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
+ memcpy(signature + 0, &ebx, 4);
+ memcpy(signature + 4, &ecx, 4);
+ memcpy(signature + 8, &edx, 4);
+ signature[12] = 0;
- if (strcmp(signature, "KVMKVMKVM") == 0)
- return 1;
+ if (strcmp(signature, "KVMKVMKVM") == 0)
+ return 1;
+ }
return 0;
}
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index effff47a3c8..43876f16caf 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
ptep->pte_low = pte.pte_low;
}
+#define pmd_read_atomic pmd_read_atomic
+/*
+ * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by gcc. Problem is, in certain places
+ * where pte_offset_map_lock is called, concurrent page faults are
+ * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * vs page faults vs MADV_DONTNEED. On the page fault side
+ * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
+ * because gcc will not read the 64bit of the pmd atomically. To fix
+ * this all places running pmd_offset_map_lock() while holding the
+ * mmap_sem in read mode, shall read the pmdp pointer using this
+ * function to know if the pmd is null nor not, and in turn to know if
+ * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * operations.
+ *
+ * Without THP if the mmap_sem is hold for reading, the
+ * pmd can only transition from null to not null while pmd_read_atomic runs.
+ * So there's no need of literally reading it atomically.
+ *
+ * With THP if the mmap_sem is hold for reading, the pmd can become
+ * THP or null or point to a pte (and in turn become "stable") at any
+ * time under pmd_read_atomic, so it's mandatory to read it atomically
+ * with cmpxchg8b.
+ */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+ pmdval_t ret;
+ u32 *tmp = (u32 *)pmdp;
+
+ ret = (pmdval_t) (*tmp);
+ if (ret) {
+ /*
+ * If the low part is null, we must not read the high part
+ * or we can end up with a partial pmd.
+ */
+ smp_rmb();
+ ret |= ((pmdval_t)*(tmp + 1)) << 32;
+ }
+
+ return (pmd_t) { ret };
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+ return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7745b257f03..39bc5777211 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -544,13 +544,16 @@ static inline void load_sp0(struct tss_struct *tss,
* enable), so that any CPU's that boot up
* after us can get the correct flags.
*/
-extern unsigned long mmu_cr4_features;
+extern unsigned long mmu_cr4_features;
+extern u32 *trampoline_cr4_features;
static inline void set_in_cr4(unsigned long mask)
{
unsigned long cr4;
mmu_cr4_features |= mask;
+ if (trampoline_cr4_features)
+ *trampoline_cr4_features = mmu_cr4_features;
cr4 = read_cr4();
cr4 |= mask;
write_cr4(cr4);
@@ -561,6 +564,8 @@ static inline void clear_in_cr4(unsigned long mask)
unsigned long cr4;
mmu_cr4_features &= ~mask;
+ if (trampoline_cr4_features)
+ *trampoline_cr4_features = mmu_cr4_features;
cr4 = read_cr4();
cr4 &= ~mask;
write_cr4(cr4);
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 35f2d1948ad..6167fd79818 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -40,5 +40,6 @@ struct pvclock_wall_clock {
} __attribute__((__packed__));
#define PVCLOCK_TSC_STABLE_BIT (1 << 0)
+#define PVCLOCK_GUEST_STOPPED (1 << 1)
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
new file mode 100644
index 00000000000..fce3f4ae5bd
--- /dev/null
+++ b/arch/x86/include/asm/realmode.h
@@ -0,0 +1,62 @@
+#ifndef _ARCH_X86_REALMODE_H
+#define _ARCH_X86_REALMODE_H
+
+#include <linux/types.h>
+#include <asm/io.h>
+
+/* This must match data at realmode.S */
+struct real_mode_header {
+ u32 text_start;
+ u32 ro_end;
+ /* SMP trampoline */
+ u32 trampoline_start;
+ u32 trampoline_status;
+ u32 trampoline_header;
+#ifdef CONFIG_X86_64
+ u32 trampoline_pgd;
+#endif
+ /* ACPI S3 wakeup */
+#ifdef CONFIG_ACPI_SLEEP
+ u32 wakeup_start;
+ u32 wakeup_header;
+#endif
+ /* APM/BIOS reboot */
+#ifdef CONFIG_X86_32
+ u32 machine_real_restart_asm;
+#endif
+};
+
+/* This must match data at trampoline_32/64.S */
+struct trampoline_header {
+#ifdef CONFIG_X86_32
+ u32 start;
+ u16 gdt_pad;
+ u16 gdt_limit;
+ u32 gdt_base;
+#else
+ u64 start;
+ u64 efer;
+ u32 cr4;
+#endif
+};
+
+extern struct real_mode_header *real_mode_header;
+extern unsigned char real_mode_blob_end[];
+
+extern unsigned long init_rsp;
+extern unsigned long initial_code;
+extern unsigned long initial_gs;
+
+extern unsigned char real_mode_blob[];
+extern unsigned char real_mode_relocs[];
+
+#ifdef CONFIG_X86_32
+extern unsigned char startup_32_smp[];
+extern unsigned char boot_gdt[];
+#else
+extern unsigned char secondary_startup_64[];
+#endif
+
+extern void __init setup_real_mode(void);
+
+#endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
new file mode 100644
index 00000000000..e9d32df89cc
--- /dev/null
+++ b/arch/x86/include/asm/sta2x11.h
@@ -0,0 +1,12 @@
+/*
+ * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
+ */
+#ifndef __ASM_STA2X11_H
+#define __ASM_STA2X11_H
+
+#include <linux/pci.h>
+
+/* This needs to be called from the MFD to configure its sub-devices */
+struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
+
+#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
deleted file mode 100644
index feca3118a73..00000000000
--- a/arch/x86/include/asm/trampoline.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef _ASM_X86_TRAMPOLINE_H
-#define _ASM_X86_TRAMPOLINE_H
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-#include <asm/io.h>
-
-/*
- * Trampoline 80x86 program as an array. These are in the init rodata
- * segment, but that's okay, because we only care about the relative
- * addresses of the symbols.
- */
-extern const unsigned char x86_trampoline_start [];
-extern const unsigned char x86_trampoline_end [];
-extern unsigned char *x86_trampoline_base;
-
-extern unsigned long init_rsp;
-extern unsigned long initial_code;
-extern unsigned long initial_gs;
-
-extern void __init setup_trampolines(void);
-
-extern const unsigned char trampoline_data[];
-extern const unsigned char trampoline_status[];
-
-#define TRAMPOLINE_SYM(x) \
- ((void *)(x86_trampoline_base + \
- ((const unsigned char *)(x) - x86_trampoline_start)))
-
-/* Address of the SMP trampoline */
-static inline unsigned long trampoline_address(void)
-{
- return virt_to_phys(TRAMPOLINE_SYM(trampoline_data));
-}
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_TRAMPOLINE_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 851fe0dc13b..04cd6882308 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -32,6 +32,7 @@
#define segment_eq(a, b) ((a).seg == (b).seg)
+#define user_addr_max() (current_thread_info()->addr_limit.seg)
#define __addr_ok(addr) \
((unsigned long __force)(addr) < \
(current_thread_info()->addr_limit.seg))
@@ -565,6 +566,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
extern __must_check long
strncpy_from_user(char *dst, const char __user *src, long count);
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
+
/*
* movsl can be slow when source and dest are not both 8-byte aligned
*/
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 8084bc73b18..576e39bca6a 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,23 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
return n;
}
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only. This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, LONG_MAX)
-
-long strnlen_user(const char __user *str, long n);
unsigned long __must_check clear_user(void __user *mem, unsigned long len);
unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index fcd4b6f3ef0..8e796fbbf9c 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,9 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
}
}
-__must_check long strnlen_user(const char __user *str, long n);
-__must_check long __strnlen_user(const char __user *str, long n);
-__must_check long strlen_user(const char __user *str);
__must_check unsigned long clear_user(void __user *mem, unsigned long len);
__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index ae03facfadd..5b238981542 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -10,6 +10,11 @@
* bit count instruction, that might be better than the multiply
* and shift, for example.
*/
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
#ifdef CONFIG_64BIT
@@ -37,10 +42,31 @@ static inline long count_masked_bytes(long mask)
#endif
-/* Return the high bit set in the first byte that is a zero */
-static inline unsigned long has_zero(unsigned long a)
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
{
- return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+ return count_masked_bytes(mask);
}
/*
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index 1df35417c41..cc146d51449 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -6,6 +6,7 @@ enum ipi_vector {
XEN_CALL_FUNCTION_VECTOR,
XEN_CALL_FUNCTION_SINGLE_VECTOR,
XEN_SPIN_UNLOCK_VECTOR,
+ XEN_IRQ_WORK_VECTOR,
XEN_NR_IPIS,
};
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c34f96c2f7a..93971e841dd 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -44,6 +44,7 @@ extern unsigned long machine_to_phys_nr;
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern unsigned long set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9bba5b79902..8215e5652d9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -35,7 +35,6 @@ obj-y += tsc.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
-obj-y += trampoline.o trampoline_$(BITS).o
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
@@ -48,7 +47,6 @@ obj-$(CONFIG_STACKTRACE) += stacktrace.o
obj-y += cpu/
obj-y += acpi/
obj-y += reboot.o
-obj-$(CONFIG_X86_32) += reboot_32.o
obj-$(CONFIG_X86_MSR) += msr.o
obj-$(CONFIG_X86_CPUID) += cpuid.o
obj-$(CONFIG_PCI) += early-quirks.o
diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
index 6f35260bb3e..163b2258147 100644
--- a/arch/x86/kernel/acpi/Makefile
+++ b/arch/x86/kernel/acpi/Makefile
@@ -1,14 +1,7 @@
-subdir- := realmode
-
obj-$(CONFIG_ACPI) += boot.o
-obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_rm.o wakeup_$(BITS).o
+obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup_$(BITS).o
ifneq ($(CONFIG_ACPI_PROCESSOR),)
obj-y += cstate.o
endif
-$(obj)/wakeup_rm.o: $(obj)/realmode/wakeup.bin
-
-$(obj)/realmode/wakeup.bin: FORCE
- $(Q)$(MAKE) $(build)=$(obj)/realmode
-
diff --git a/arch/x86/kernel/acpi/realmode/.gitignore b/arch/x86/kernel/acpi/realmode/.gitignore
deleted file mode 100644
index 58f1f48a58f..00000000000
--- a/arch/x86/kernel/acpi/realmode/.gitignore
+++ /dev/null
@@ -1,3 +0,0 @@
-wakeup.bin
-wakeup.elf
-wakeup.lds
diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile
deleted file mode 100644
index 6a564ac67ef..00000000000
--- a/arch/x86/kernel/acpi/realmode/Makefile
+++ /dev/null
@@ -1,59 +0,0 @@
-#
-# arch/x86/kernel/acpi/realmode/Makefile
-#
-# This file is subject to the terms and conditions of the GNU General Public
-# License. See the file "COPYING" in the main directory of this archive
-# for more details.
-#
-
-always := wakeup.bin
-targets := wakeup.elf wakeup.lds
-
-wakeup-y += wakeup.o wakemain.o video-mode.o copy.o bioscall.o regs.o
-
-# The link order of the video-*.o modules can matter. In particular,
-# video-vga.o *must* be listed first, followed by video-vesa.o.
-# Hardware-specific drivers should follow in the order they should be
-# probed, and video-bios.o should typically be last.
-wakeup-y += video-vga.o
-wakeup-y += video-vesa.o
-wakeup-y += video-bios.o
-
-targets += $(wakeup-y)
-
-bootsrc := $(src)/../../../boot
-
-# ---------------------------------------------------------------------------
-
-# How to compile the 16-bit code. Note we always compile for -march=i386,
-# that way we can complain to the user if the CPU is insufficient.
-# Compile with _SETUP since this is similar to the boot-time setup code.
-KBUILD_CFLAGS := $(LINUXINCLUDE) -g -Os -D_SETUP -D_WAKEUP -D__KERNEL__ \
- -I$(srctree)/$(bootsrc) \
- $(cflags-y) \
- -Wall -Wstrict-prototypes \
- -march=i386 -mregparm=3 \
- -include $(srctree)/$(bootsrc)/code16gcc.h \
- -fno-strict-aliasing -fomit-frame-pointer \
- $(call cc-option, -ffreestanding) \
- $(call cc-option, -fno-toplevel-reorder,\
- $(call cc-option, -fno-unit-at-a-time)) \
- $(call cc-option, -fno-stack-protector) \
- $(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS += $(call cc-option, -m32)
-KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
-GCOV_PROFILE := n
-
-WAKEUP_OBJS = $(addprefix $(obj)/,$(wakeup-y))
-
-LDFLAGS_wakeup.elf := -T
-
-CPPFLAGS_wakeup.lds += -P -C
-
-$(obj)/wakeup.elf: $(obj)/wakeup.lds $(WAKEUP_OBJS) FORCE
- $(call if_changed,ld)
-
-OBJCOPYFLAGS_wakeup.bin := -O binary
-
-$(obj)/wakeup.bin: $(obj)/wakeup.elf FORCE
- $(call if_changed,objcopy)
diff --git a/arch/x86/kernel/acpi/realmode/bioscall.S b/arch/x86/kernel/acpi/realmode/bioscall.S
deleted file mode 100644
index f51eb0bb56c..00000000000
--- a/arch/x86/kernel/acpi/realmode/bioscall.S
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/bioscall.S"
diff --git a/arch/x86/kernel/acpi/realmode/copy.S b/arch/x86/kernel/acpi/realmode/copy.S
deleted file mode 100644
index dc59ebee69d..00000000000
--- a/arch/x86/kernel/acpi/realmode/copy.S
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/copy.S"
diff --git a/arch/x86/kernel/acpi/realmode/regs.c b/arch/x86/kernel/acpi/realmode/regs.c
deleted file mode 100644
index 6206033ba20..00000000000
--- a/arch/x86/kernel/acpi/realmode/regs.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/regs.c"
diff --git a/arch/x86/kernel/acpi/realmode/video-bios.c b/arch/x86/kernel/acpi/realmode/video-bios.c
deleted file mode 100644
index 7deabc144a2..00000000000
--- a/arch/x86/kernel/acpi/realmode/video-bios.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/video-bios.c"
diff --git a/arch/x86/kernel/acpi/realmode/video-mode.c b/arch/x86/kernel/acpi/realmode/video-mode.c
deleted file mode 100644
index 328ad209f11..00000000000
--- a/arch/x86/kernel/acpi/realmode/video-mode.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/video-mode.c"
diff --git a/arch/x86/kernel/acpi/realmode/video-vesa.c b/arch/x86/kernel/acpi/realmode/video-vesa.c
deleted file mode 100644
index 9dbb9672226..00000000000
--- a/arch/x86/kernel/acpi/realmode/video-vesa.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/video-vesa.c"
diff --git a/arch/x86/kernel/acpi/realmode/video-vga.c b/arch/x86/kernel/acpi/realmode/video-vga.c
deleted file mode 100644
index bcc81255f37..00000000000
--- a/arch/x86/kernel/acpi/realmode/video-vga.c
+++ /dev/null
@@ -1 +0,0 @@
-#include "../../../boot/video-vga.c"
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.lds.S b/arch/x86/kernel/acpi/realmode/wakeup.lds.S
deleted file mode 100644
index d4f8010a5b1..00000000000
--- a/arch/x86/kernel/acpi/realmode/wakeup.lds.S
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * wakeup.ld
- *
- * Linker script for the real-mode wakeup code
- */
-#undef i386
-#include "wakeup.h"
-
-OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
-OUTPUT_ARCH(i386)
-ENTRY(_start)
-
-SECTIONS
-{
- . = 0;
- .jump : {
- *(.jump)
- } = 0x90909090
-
- . = WAKEUP_HEADER_OFFSET;
- .header : {
- *(.header)
- }
-
- . = ALIGN(16);
- .text : {
- *(.text*)
- } = 0x90909090
-
- . = ALIGN(16);
- .rodata : {
- *(.rodata*)
- }
-
- .videocards : {
- video_cards = .;
- *(.videocards)
- video_cards_end = .;
- }
-
- . = ALIGN(16);
- .data : {
- *(.data*)
- }
-
- . = ALIGN(16);
- .bss : {
- __bss_start = .;
- *(.bss)
- __bss_end = .;
- }
-
- .signature : {
- *(.signature)
- }
-
- _end = .;
-
- /DISCARD/ : {
- *(.note*)
- }
-}
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 146a49c763a..95bf99de905 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -14,8 +14,9 @@
#include <asm/desc.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
+#include <asm/realmode.h>
-#include "realmode/wakeup.h"
+#include "../../realmode/rm/wakeup.h"
#include "sleep.h"
unsigned long acpi_realmode_flags;
@@ -36,13 +37,9 @@ asmlinkage void acpi_enter_s3(void)
*/
int acpi_suspend_lowlevel(void)
{
- struct wakeup_header *header;
- /* address in low memory of the wakeup routine. */
- char *acpi_realmode;
+ struct wakeup_header *header =
+ (struct wakeup_header *) __va(real_mode_header->wakeup_header);
- acpi_realmode = TRAMPOLINE_SYM(acpi_wakeup_code);
-
- header = (struct wakeup_header *)(acpi_realmode + WAKEUP_HEADER_OFFSET);
if (header->signature != WAKEUP_HEADER_SIGNATURE) {
printk(KERN_ERR "wakeup header does not match\n");
return -EINVAL;
@@ -50,27 +47,6 @@ int acpi_suspend_lowlevel(void)
header->video_mode = saved_video_mode;
- header->wakeup_jmp_seg = acpi_wakeup_address >> 4;
-
- /*
- * Set up the wakeup GDT. We set these up as Big Real Mode,
- * that is, with limits set to 4 GB. At least the Lenovo
- * Thinkpad X61 is known to need this for the video BIOS
- * initialization quirk to work; this is likely to also
- * be the case for other laptops or integrated video devices.
- */
-
- /* GDT[0]: GDT self-pointer */
- header->wakeup_gdt[0] =
- (u64)(sizeof(header->wakeup_gdt) - 1) +
- ((u64)__pa(&header->wakeup_gdt) << 16);
- /* GDT[1]: big real mode-like code segment */
- header->wakeup_gdt[1] =
- GDT_ENTRY(0x809b, acpi_wakeup_address, 0xfffff);
- /* GDT[2]: big real mode-like data segment */
- header->wakeup_gdt[2] =
- GDT_ENTRY(0x8093, acpi_wakeup_address, 0xfffff);
-
#ifndef CONFIG_64BIT
store_gdt((struct desc_ptr *)&header->pmode_gdt);
@@ -95,7 +71,6 @@ int acpi_suspend_lowlevel(void)
header->pmode_cr3 = (u32)__pa(&initial_page_table);
saved_magic = 0x12345678;
#else /* CONFIG_64BIT */
- header->trampoline_segment = trampoline_address() >> 4;
#ifdef CONFIG_SMP
stack_start = (unsigned long)temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index d68677a2a01..5653a5791ec 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -2,8 +2,8 @@
* Variables and functions used by the code in sleep.c
*/
-#include <asm/trampoline.h>
#include <linux/linkage.h>
+#include <asm/realmode.h>
extern unsigned long saved_video_mode;
extern long saved_magic;
diff --git a/arch/x86/kernel/acpi/wakeup_rm.S b/arch/x86/kernel/acpi/wakeup_rm.S
deleted file mode 100644
index 63b8ab524f2..00000000000
--- a/arch/x86/kernel/acpi/wakeup_rm.S
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Wrapper script for the realmode binary as a transport object
- * before copying to low memory.
- */
-#include <asm/page_types.h>
-
- .section ".x86_trampoline","a"
- .balign PAGE_SIZE
- .globl acpi_wakeup_code
-acpi_wakeup_code:
- .incbin "arch/x86/kernel/acpi/realmode/wakeup.bin"
- .size acpi_wakeup_code, .-acpi_wakeup_code
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index 507ea58688e..cd8b166a173 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -42,7 +42,8 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
struct mce m;
/* Only corrected MC is reported */
- if (!corrected)
+ if (!corrected || !(mem_err->validation_bits &
+ CPER_MEM_VALID_PHYSICAL_ADDRESS))
return;
mce_setup(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 0c82091b165..413c2ced887 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -126,6 +126,16 @@ static struct severity {
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
USER
),
+ MCESEV(
+ KEEP, "HT thread notices Action required: instruction fetch error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ MCGMASK(MCG_STATUS_EIPV, 0)
+ ),
+ MCESEV(
+ AR, "Action required: instruction fetch error",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
+ USER
+ ),
#endif
MCESEV(
PANIC, "Action required: unknown MCACOD",
@@ -165,15 +175,19 @@ static struct severity {
};
/*
- * If the EIPV bit is set, it means the saved IP is the
- * instruction which caused the MCE.
+ * If mcgstatus indicated that ip/cs on the stack were
+ * no good, then "m->cs" will be zero and we will have
+ * to assume the worst case (IN_KERNEL) as we actually
+ * have no idea what we were executing when the machine
+ * check hit.
+ * If we do have a good "m->cs" (or a faked one in the
+ * case we were executing in VM86 mode) we can use it to
+ * distinguish an exception taken in user from from one
+ * taken in the kernel.
*/
static int error_context(struct mce *m)
{
- if (m->mcgstatus & MCG_STATUS_EIPV)
- return (m->ip && (m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
- /* Unknown, assume kernel */
- return IN_KERNEL;
+ return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
}
int mce_severity(struct mce *m, int tolerant, char **msg)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index aaa056f3169..b4180f425fb 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -437,6 +437,14 @@ static inline void mce_gather_info(struct mce *m, struct pt_regs *regs)
if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) {
m->ip = regs->ip;
m->cs = regs->cs;
+
+ /*
+ * When in VM86 mode make the cs look like ring 3
+ * always. This is a lie, but it's better than passing
+ * the additional vm86 bit around everywhere.
+ */
+ if (v8086_mode(regs))
+ m->cs |= 3;
}
/* Use accurate RIP reporting if available. */
if (rip_msr)
@@ -641,16 +649,18 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
* Do a quick check if any of the events requires a panic.
* This decides if we keep the events around or clear them.
*/
-static int mce_no_way_out(struct mce *m, char **msg)
+static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp)
{
- int i;
+ int i, ret = 0;
for (i = 0; i < banks; i++) {
m->status = mce_rdmsrl(MSR_IA32_MCx_STATUS(i));
+ if (m->status & MCI_STATUS_VAL)
+ __set_bit(i, validp);
if (mce_severity(m, tolerant, msg) >= MCE_PANIC_SEVERITY)
- return 1;
+ ret = 1;
}
- return 0;
+ return ret;
}
/*
@@ -1013,6 +1023,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*/
int kill_it = 0;
DECLARE_BITMAP(toclear, MAX_NR_BANKS);
+ DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
char *msg = "Unknown";
atomic_inc(&mce_entry);
@@ -1027,7 +1038,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
final = &__get_cpu_var(mces_seen);
*final = m;
- no_way_out = mce_no_way_out(&m, &msg);
+ memset(valid_banks, 0, sizeof(valid_banks));
+ no_way_out = mce_no_way_out(&m, &msg, valid_banks);
barrier();
@@ -1047,6 +1059,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
order = mce_start(&no_way_out);
for (i = 0; i < banks; i++) {
__clear_bit(i, toclear);
+ if (!test_bit(i, valid_banks))
+ continue;
if (!mce_banks[i].ctl)
continue;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 62d61e9976e..41857970517 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -113,7 +113,9 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
int x = e820x->nr_map;
if (x >= ARRAY_SIZE(e820x->map)) {
- printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
+ printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n",
+ (unsigned long long) start,
+ (unsigned long long) (start + size - 1));
return;
}
@@ -133,19 +135,19 @@ static void __init e820_print_type(u32 type)
switch (type) {
case E820_RAM:
case E820_RESERVED_KERN:
- printk(KERN_CONT "(usable)");
+ printk(KERN_CONT "usable");
break;
case E820_RESERVED:
- printk(KERN_CONT "(reserved)");
+ printk(KERN_CONT "reserved");
break;
case E820_ACPI:
- printk(KERN_CONT "(ACPI data)");
+ printk(KERN_CONT "ACPI data");
break;
case E820_NVS:
- printk(KERN_CONT "(ACPI NVS)");
+ printk(KERN_CONT "ACPI NVS");
break;
case E820_UNUSABLE:
- printk(KERN_CONT "(unusable)");
+ printk(KERN_CONT "unusable");
break;
default:
printk(KERN_CONT "type %u", type);
@@ -158,10 +160,10 @@ void __init e820_print_map(char *who)
int i;
for (i = 0; i < e820.nr_map; i++) {
- printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
+ printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who,
(unsigned long long) e820.map[i].addr,
(unsigned long long)
- (e820.map[i].addr + e820.map[i].size));
+ (e820.map[i].addr + e820.map[i].size - 1));
e820_print_type(e820.map[i].type);
printk(KERN_CONT "\n");
}
@@ -428,9 +430,8 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
size = ULLONG_MAX - start;
end = start + size;
- printk(KERN_DEBUG "e820 update range: %016Lx - %016Lx ",
- (unsigned long long) start,
- (unsigned long long) end);
+ printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ",
+ (unsigned long long) start, (unsigned long long) (end - 1));
e820_print_type(old_type);
printk(KERN_CONT " ==> ");
e820_print_type(new_type);
@@ -509,9 +510,8 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
size = ULLONG_MAX - start;
end = start + size;
- printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
- (unsigned long long) start,
- (unsigned long long) end);
+ printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ",
+ (unsigned long long) start, (unsigned long long) (end - 1));
if (checktype)
e820_print_type(old_type);
printk(KERN_CONT "\n");
@@ -567,7 +567,7 @@ void __init update_e820(void)
if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
return;
e820.nr_map = nr_map;
- printk(KERN_INFO "modified physical RAM map:\n");
+ printk(KERN_INFO "e820: modified physical RAM map:\n");
e820_print_map("modified");
}
static void __init update_e820_saved(void)
@@ -637,8 +637,8 @@ __init void e820_setup_gap(void)
if (!found) {
gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
printk(KERN_ERR
- "PCI: Warning: Cannot find a gap in the 32bit address range\n"
- "PCI: Unassigned devices with 32bit resource registers may break!\n");
+ "e820: cannot find a gap in the 32bit address range\n"
+ "e820: PCI devices with unassigned 32bit BARs may break!\n");
}
#endif
@@ -648,8 +648,8 @@ __init void e820_setup_gap(void)
pci_mem_start = gapstart;
printk(KERN_INFO
- "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
- pci_mem_start, gapstart, gapsize);
+ "e820: [mem %#010lx-%#010lx] available for PCI devices\n",
+ gapstart, gapstart + gapsize - 1);
}
/**
@@ -667,7 +667,7 @@ void __init parse_e820_ext(struct setup_data *sdata)
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
- printk(KERN_INFO "extended physical RAM map:\n");
+ printk(KERN_INFO "e820: extended physical RAM map:\n");
e820_print_map("extended");
}
@@ -734,7 +734,7 @@ u64 __init early_reserve_e820(u64 size, u64 align)
addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
if (addr) {
e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
- printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
+ printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n");
update_e820_saved();
}
@@ -784,7 +784,7 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
if (last_pfn > max_arch_pfn)
last_pfn = max_arch_pfn;
- printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
+ printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
last_pfn, max_arch_pfn);
return last_pfn;
}
@@ -888,7 +888,7 @@ void __init finish_e820_parsing(void)
early_panic("Invalid user supplied memory map");
e820.nr_map = nr;
- printk(KERN_INFO "user-defined physical RAM map:\n");
+ printk(KERN_INFO "e820: user-defined physical RAM map:\n");
e820_print_map("user");
}
}
@@ -996,8 +996,9 @@ void __init e820_reserve_resources_late(void)
end = MAX_RESOURCE_SIZE;
if (start >= end)
continue;
- printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
- start, end);
+ printk(KERN_DEBUG
+ "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n",
+ start, end);
reserve_region_with_split(&iomem_resource, start, end,
"RAM buffer");
}
@@ -1047,7 +1048,7 @@ void __init setup_memory_map(void)
who = x86_init.resources.memory_setup();
memcpy(&e820_saved, &e820, sizeof(struct e820map));
- printk(KERN_INFO "BIOS-provided physical RAM map:\n");
+ printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n");
e820_print_map(who);
}
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 51ff18616d5..c18f59d1010 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -14,7 +14,6 @@
#include <asm/sections.h>
#include <asm/e820.h>
#include <asm/page.h>
-#include <asm/trampoline.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/bios_ebda.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 3a3b779f41d..037df57a99a 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -24,7 +24,6 @@
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/e820.h>
-#include <asm/trampoline.h>
#include <asm/bios_ebda.h>
static void __init zap_identity_mappings(void)
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 463c9797ca6..d42ab17b739 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -274,10 +274,7 @@ num_subarch_entries = (. - subarch_entries) / 4
* If cpu hotplug is not supported then this code can go in init section
* which will be freed later
*/
-
__CPUINIT
-
-#ifdef CONFIG_SMP
ENTRY(startup_32_smp)
cld
movl $(__BOOT_DS),%eax
@@ -288,7 +285,7 @@ ENTRY(startup_32_smp)
movl pa(stack_start),%ecx
movl %eax,%ss
leal -__PAGE_OFFSET(%ecx),%esp
-#endif /* CONFIG_SMP */
+
default_entry:
/*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7a40f244732..94bf9cc2c7e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -139,10 +139,6 @@ ident_complete:
/* Fixup phys_base */
addq %rbp, phys_base(%rip)
- /* Fixup trampoline */
- addq %rbp, trampoline_level4_pgt + 0(%rip)
- addq %rbp, trampoline_level4_pgt + (511*8)(%rip)
-
/* Due to ENTRY(), sometimes the empty space gets filled with
* zeros. Better take a jmp than relying on empty space being
* filled with 0x90 (nop)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index f8492da65bf..086eb58c6e8 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -22,6 +22,7 @@
#include <asm/msr.h>
#include <asm/apic.h>
#include <linux/percpu.h>
+#include <linux/hardirq.h>
#include <asm/x86_init.h>
#include <asm/reboot.h>
@@ -114,6 +115,25 @@ static void kvm_get_preset_lpj(void)
preset_lpj = lpj;
}
+bool kvm_check_and_clear_guest_paused(void)
+{
+ bool ret = false;
+ struct pvclock_vcpu_time_info *src;
+
+ /*
+ * per_cpu() is safe here because this function is only called from
+ * timer functions where preemption is already disabled.
+ */
+ WARN_ON(!in_atomic());
+ src = &__get_cpu_var(hv_clock);
+ if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
+ __this_cpu_and(hv_clock.flags, ~PVCLOCK_GUEST_STOPPED);
+ ret = true;
+ }
+
+ return ret;
+}
+
static struct clocksource kvm_clock = {
.name = "kvm-clock",
.read = kvm_clock_get_cycles,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index b02d4dd6b8a..d2b56489d70 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -27,7 +27,6 @@
#include <asm/proto.h>
#include <asm/bios_ebda.h>
#include <asm/e820.h>
-#include <asm/trampoline.h>
#include <asm/setup.h>
#include <asm/smp.h>
@@ -568,8 +567,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
struct mpf_intel *mpf;
unsigned long mem;
- apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
- bp, length);
+ apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n",
+ base, base + length - 1);
BUILD_BUG_ON(sizeof(*mpf) != 16);
while (length > 0) {
@@ -584,8 +583,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
#endif
mpf_found = mpf;
- printk(KERN_INFO "found SMP MP-table at [%p] %llx\n",
- mpf, (u64)virt_to_phys(mpf));
+ printk(KERN_INFO "found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n",
+ (unsigned long long) virt_to_phys(mpf),
+ (unsigned long long) virt_to_phys(mpf) +
+ sizeof(*mpf) - 1, mpf);
mem = virt_to_phys(mpf);
memblock_reserve(mem, sizeof(*mpf));
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 3003250ac51..62c9457ccd2 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -100,14 +100,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
struct dma_attrs *attrs)
{
unsigned long dma_mask;
- struct page *page;
+ struct page *page = NULL;
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
dma_addr_t addr;
dma_mask = dma_alloc_coherent_mask(dev, flag);
flag |= __GFP_ZERO;
again:
- page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+ if (!(flag & GFP_ATOMIC))
+ page = dma_alloc_from_contiguous(dev, count, get_order(size));
+ if (!page)
+ page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
if (!page)
return NULL;
@@ -127,6 +131,16 @@ again:
return page_address(page);
}
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr, struct dma_attrs *attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ struct page *page = virt_to_page(vaddr);
+
+ if (!dma_release_from_contiguous(dev, page, count))
+ free_pages((unsigned long)vaddr, get_order(size));
+}
+
/*
* See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
* parameter documentation.
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index f96050685b4..871be4a84c7 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
return nents;
}
-static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
- dma_addr_t dma_addr, struct dma_attrs *attrs)
-{
- free_pages((unsigned long)vaddr, get_order(size));
-}
-
static void nommu_sync_single_for_device(struct device *dev,
dma_addr_t addr, size_t size,
enum dma_data_direction dir)
@@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev,
struct dma_map_ops nommu_dma_ops = {
.alloc = dma_generic_alloc_coherent,
- .free = nommu_free_coherent,
+ .free = dma_generic_free_coherent,
.map_sg = nommu_map_sg,
.map_page = nommu_map_page,
.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 77215c23fba..79c45af8160 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -24,6 +24,7 @@
#ifdef CONFIG_X86_32
# include <linux/ctype.h>
# include <linux/mc146818rtc.h>
+# include <asm/realmode.h>
#else
# include <asm/x86_init.h>
#endif
@@ -156,15 +157,10 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
return 0;
}
-extern const unsigned char machine_real_restart_asm[];
-extern const u64 machine_real_restart_gdt[3];
-
void machine_real_restart(unsigned int type)
{
- void *restart_va;
- unsigned long restart_pa;
- void (*restart_lowmem)(unsigned int);
- u64 *lowmem_gdt;
+ void (*restart_lowmem)(unsigned int) = (void (*)(unsigned int))
+ real_mode_header->machine_real_restart_asm;
local_irq_disable();
@@ -195,21 +191,6 @@ void machine_real_restart(unsigned int type)
* too. */
*((unsigned short *)0x472) = reboot_mode;
- /* Patch the GDT in the low memory trampoline */
- lowmem_gdt = TRAMPOLINE_SYM(machine_real_restart_gdt);
-
- restart_va = TRAMPOLINE_SYM(machine_real_restart_asm);
- restart_pa = virt_to_phys(restart_va);
- restart_lowmem = (void (*)(unsigned int))restart_pa;
-
- /* GDT[0]: GDT self-pointer */
- lowmem_gdt[0] =
- (u64)(sizeof(machine_real_restart_gdt) - 1) +
- ((u64)virt_to_phys(lowmem_gdt) << 16);
- /* GDT[1]: 64K real mode code segment */
- lowmem_gdt[1] =
- GDT_ENTRY(0x009b, restart_pa, 0xffff);
-
/* Jump to the identity-mapped low memory code */
restart_lowmem(type);
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 366c688d619..16be6dc14db 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -49,6 +49,7 @@
#include <asm/pci-direct.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/kvm_para.h>
+#include <linux/dma-contiguous.h>
#include <linux/errno.h>
#include <linux/kernel.h>
@@ -72,7 +73,7 @@
#include <asm/mtrr.h>
#include <asm/apic.h>
-#include <asm/trampoline.h>
+#include <asm/realmode.h>
#include <asm/e820.h>
#include <asm/mpspec.h>
#include <asm/setup.h>
@@ -333,8 +334,8 @@ static void __init relocate_initrd(void)
memblock_reserve(ramdisk_here, area_size);
initrd_start = ramdisk_here + PAGE_OFFSET;
initrd_end = initrd_start + ramdisk_size;
- printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
- ramdisk_here, ramdisk_here + ramdisk_size);
+ printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
+ ramdisk_here, ramdisk_here + ramdisk_size - 1);
q = (char *)initrd_start;
@@ -365,8 +366,8 @@ static void __init relocate_initrd(void)
/* high pages is not converted by early_res_to_bootmem */
ramdisk_image = boot_params.hdr.ramdisk_image;
ramdisk_size = boot_params.hdr.ramdisk_size;
- printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
- " %08llx - %08llx\n",
+ printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
+ " [mem %#010llx-%#010llx]\n",
ramdisk_image, ramdisk_image + ramdisk_size - 1,
ramdisk_here, ramdisk_here + ramdisk_size - 1);
}
@@ -391,8 +392,8 @@ static void __init reserve_initrd(void)
ramdisk_size, end_of_lowmem>>1);
}
- printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image,
- ramdisk_end);
+ printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
+ ramdisk_end - 1);
if (ramdisk_end <= end_of_lowmem) {
@@ -905,10 +906,10 @@ void __init setup_arch(char **cmdline_p)
setup_bios_corruption_check();
#endif
- printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
- max_pfn_mapped<<PAGE_SHIFT);
+ printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
+ (max_pfn_mapped<<PAGE_SHIFT) - 1);
- setup_trampolines();
+ setup_real_mode();
init_gbpages();
@@ -925,6 +926,7 @@ void __init setup_arch(char **cmdline_p)
}
#endif
memblock.current_limit = get_max_mapped();
+ dma_contiguous_reserve(0);
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -966,6 +968,8 @@ void __init setup_arch(char **cmdline_p)
if (boot_cpu_data.cpuid_level >= 0) {
/* A CPU has %cr4 if and only if it has CPUID */
mmu_cr4_features = read_cr4();
+ if (trampoline_cr4_features)
+ *trampoline_cr4_features = mmu_cr4_features;
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 433529e29be..f56f96da77f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -57,7 +57,7 @@
#include <asm/nmi.h>
#include <asm/irq.h>
#include <asm/idle.h>
-#include <asm/trampoline.h>
+#include <asm/realmode.h>
#include <asm/cpu.h>
#include <asm/numa.h>
#include <asm/pgtable.h>
@@ -73,6 +73,8 @@
#include <asm/smpboot_hooks.h>
#include <asm/i8259.h>
+#include <asm/realmode.h>
+
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -660,8 +662,12 @@ static void __cpuinit announce_cpu(int cpu, int apicid)
*/
static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
{
+ volatile u32 *trampoline_status =
+ (volatile u32 *) __va(real_mode_header->trampoline_status);
+ /* start_ip had better be page-aligned! */
+ unsigned long start_ip = real_mode_header->trampoline_start;
+
unsigned long boot_error = 0;
- unsigned long start_ip;
int timeout;
alternatives_smp_switch(1);
@@ -684,9 +690,6 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
initial_code = (unsigned long)start_secondary;
stack_start = idle->thread.sp;
- /* start_ip had better be page-aligned! */
- start_ip = trampoline_address();
-
/* So we see what's up */
announce_cpu(cpu, apicid);
@@ -749,8 +752,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
pr_debug("CPU%d: has booted.\n", cpu);
} else {
boot_error = 1;
- if (*(volatile u32 *)TRAMPOLINE_SYM(trampoline_status)
- == 0xA5A5A5A5)
+ if (*trampoline_status == 0xA5A5A5A5)
/* trampoline started but...? */
pr_err("CPU%d: Stuck ??\n", cpu);
else
@@ -776,7 +778,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
}
/* mark "stuck" area as not stuck */
- *(volatile u32 *)TRAMPOLINE_SYM(trampoline_status) = 0;
+ *trampoline_status = 0;
if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
/*
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 6410744ac5c..f84fe00fad4 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -32,7 +32,7 @@
#include <linux/mm.h>
#include <linux/tboot.h>
-#include <asm/trampoline.h>
+#include <asm/realmode.h>
#include <asm/processor.h>
#include <asm/bootparam.h>
#include <asm/pgtable.h>
@@ -44,7 +44,7 @@
#include <asm/e820.h>
#include <asm/io.h>
-#include "acpi/realmode/wakeup.h"
+#include "../realmode/rm/wakeup.h"
/* Global pointer to shared data; NULL means no measured launch. */
struct tboot *tboot __read_mostly;
@@ -201,7 +201,8 @@ static int tboot_setup_sleep(void)
add_mac_region(e820.map[i].addr, e820.map[i].size);
}
- tboot->acpi_sinfo.kernel_s3_resume_vector = acpi_wakeup_address;
+ tboot->acpi_sinfo.kernel_s3_resume_vector =
+ real_mode_header->wakeup_start;
return 0;
}
diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c
deleted file mode 100644
index a73b61055ad..00000000000
--- a/arch/x86/kernel/trampoline.c
+++ /dev/null
@@ -1,42 +0,0 @@
-#include <linux/io.h>
-#include <linux/memblock.h>
-
-#include <asm/trampoline.h>
-#include <asm/cacheflush.h>
-#include <asm/pgtable.h>
-
-unsigned char *x86_trampoline_base;
-
-void __init setup_trampolines(void)
-{
- phys_addr_t mem;
- size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start);
-
- /* Has to be in very low memory so we can execute real-mode AP code. */
- mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
- if (!mem)
- panic("Cannot allocate trampoline\n");
-
- x86_trampoline_base = __va(mem);
- memblock_reserve(mem, size);
-
- printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
- x86_trampoline_base, (unsigned long long)mem, size);
-
- memcpy(x86_trampoline_base, x86_trampoline_start, size);
-}
-
-/*
- * setup_trampolines() gets called very early, to guarantee the
- * availability of low memory. This is before the proper kernel page
- * tables are set up, so we cannot set page permissions in that
- * function. Thus, we use an arch_initcall instead.
- */
-static int __init configure_trampolines(void)
-{
- size_t size = PAGE_ALIGN(x86_trampoline_end - x86_trampoline_start);
-
- set_memory_x((unsigned long)x86_trampoline_base, size >> PAGE_SHIFT);
- return 0;
-}
-arch_initcall(configure_trampolines);
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
deleted file mode 100644
index 451c0a7ef7f..00000000000
--- a/arch/x86/kernel/trampoline_32.S
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- *
- * Trampoline.S Derived from Setup.S by Linus Torvalds
- *
- * 4 Jan 1997 Michael Chastain: changed to gnu as.
- *
- * This is only used for booting secondary CPUs in SMP machine
- *
- * Entry: CS:IP point to the start of our code, we are
- * in real mode with no stack, but the rest of the
- * trampoline page to make our stack and everything else
- * is a mystery.
- *
- * We jump into arch/x86/kernel/head_32.S.
- *
- * On entry to trampoline_data, the processor is in real mode
- * with 16-bit addressing and 16-bit data. CS has some value
- * and IP is zero. Thus, data addresses need to be absolute
- * (no relocation) and are taken with regard to r_base.
- *
- * If you work on this file, check the object module with
- * objdump --reloc to make sure there are no relocation
- * entries except for:
- *
- * TYPE VALUE
- * R_386_32 startup_32_smp
- * R_386_32 boot_gdt
- */
-
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/segment.h>
-#include <asm/page_types.h>
-
-#ifdef CONFIG_SMP
-
- .section ".x86_trampoline","a"
- .balign PAGE_SIZE
- .code16
-
-ENTRY(trampoline_data)
-r_base = .
- wbinvd # Needed for NUMA-Q should be harmless for others
- mov %cs, %ax # Code and data in the same place
- mov %ax, %ds
-
- cli # We should be safe anyway
-
- movl $0xA5A5A5A5, trampoline_status - r_base
- # write marker for master knows we're running
-
- /* GDT tables in non default location kernel can be beyond 16MB and
- * lgdt will not be able to load the address as in real mode default
- * operand size is 16bit. Use lgdtl instead to force operand size
- * to 32 bit.
- */
-
- lidtl boot_idt_descr - r_base # load idt with 0, 0
- lgdtl boot_gdt_descr - r_base # load gdt with whatever is appropriate
-
- xor %ax, %ax
- inc %ax # protected mode (PE) bit
- lmsw %ax # into protected mode
- # flush prefetch and jump to startup_32_smp in arch/i386/kernel/head.S
- ljmpl $__BOOT_CS, $(startup_32_smp-__PAGE_OFFSET)
-
- # These need to be in the same 64K segment as the above;
- # hence we don't use the boot_gdt_descr defined in head.S
-boot_gdt_descr:
- .word __BOOT_DS + 7 # gdt limit
- .long boot_gdt - __PAGE_OFFSET # gdt base
-
-boot_idt_descr:
- .word 0 # idt limit = 0
- .long 0 # idt base = 0L
-
-ENTRY(trampoline_status)
- .long 0
-
-.globl trampoline_end
-trampoline_end:
-
-#endif /* CONFIG_SMP */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0f703f10901..22a1530146a 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -197,18 +197,6 @@ SECTIONS
INIT_DATA_SECTION(16)
- /*
- * Code and data for a variety of lowlevel trampolines, to be
- * copied into base memory (< 1 MiB) during initialization.
- * Since it is copied early, the main copy can be discarded
- * afterwards.
- */
- .x86_trampoline : AT(ADDR(.x86_trampoline) - LOAD_OFFSET) {
- x86_trampoline_start = .;
- *(.x86_trampoline)
- x86_trampoline_end = .;
- }
-
.x86_cpu_dev.init : AT(ADDR(.x86_cpu_dev.init) - LOAD_OFFSET) {
__x86_cpu_dev_start = .;
*(.x86_cpu_dev.init)
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 1a7fe868f37..a28f338843e 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -36,6 +36,7 @@ config KVM
select TASKSTATS
select TASK_DELAY_ACCT
select PERF_EVENTS
+ select HAVE_KVM_MSI
---help---
Support hosting fully virtualized guest machines using hardware
virtualization extensions. You will need a fairly recent
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9fed5bedaad..7df1c6d839f 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -247,7 +247,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
/* cpuid 7.0.ebx */
const u32 kvm_supported_word9_x86_features =
- F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS);
+ F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
+ F(BMI2) | F(ERMS) | F(RTM);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -397,7 +398,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
case KVM_CPUID_SIGNATURE: {
char signature[12] = "KVMKVMKVM\0\0";
u32 *sigptr = (u32 *)signature;
- entry->eax = 0;
+ entry->eax = KVM_CPUID_FEATURES;
entry->ebx = sigptr[0];
entry->ecx = sigptr[1];
entry->edx = sigptr[2];
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 83756223f8a..f95d242ee9f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -142,6 +142,10 @@
#define Src2FS (OpFS << Src2Shift)
#define Src2GS (OpGS << Src2Shift)
#define Src2Mask (OpMask << Src2Shift)
+#define Mmx ((u64)1 << 40) /* MMX Vector instruction */
+#define Aligned ((u64)1 << 41) /* Explicitly aligned (e.g. MOVDQA) */
+#define Unaligned ((u64)1 << 42) /* Explicitly unaligned (e.g. MOVDQU) */
+#define Avx ((u64)1 << 43) /* Advanced Vector Extensions */
#define X2(x...) x, x
#define X3(x...) X2(x), x
@@ -557,6 +561,29 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector,
ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg);
}
+/*
+ * x86 defines three classes of vector instructions: explicitly
+ * aligned, explicitly unaligned, and the rest, which change behaviour
+ * depending on whether they're AVX encoded or not.
+ *
+ * Also included is CMPXCHG16B which is not a vector instruction, yet it is
+ * subject to the same check.
+ */
+static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
+{
+ if (likely(size < 16))
+ return false;
+
+ if (ctxt->d & Aligned)
+ return true;
+ else if (ctxt->d & Unaligned)
+ return false;
+ else if (ctxt->d & Avx)
+ return false;
+ else
+ return true;
+}
+
static int __linearize(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
unsigned size, bool write, bool fetch,
@@ -621,6 +648,8 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
}
if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : ctxt->ad_bytes != 8)
la &= (u32)-1;
+ if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
+ return emulate_gp(ctxt, 0);
*linear = la;
return X86EMUL_CONTINUE;
bad:
@@ -859,6 +888,40 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
ctxt->ops->put_fpu(ctxt);
}
+static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+{
+ ctxt->ops->get_fpu(ctxt);
+ switch (reg) {
+ case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
+ case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
+ case 2: asm("movq %%mm2, %0" : "=m"(*data)); break;
+ case 3: asm("movq %%mm3, %0" : "=m"(*data)); break;
+ case 4: asm("movq %%mm4, %0" : "=m"(*data)); break;
+ case 5: asm("movq %%mm5, %0" : "=m"(*data)); break;
+ case 6: asm("movq %%mm6, %0" : "=m"(*data)); break;
+ case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
+ default: BUG();
+ }
+ ctxt->ops->put_fpu(ctxt);
+}
+
+static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
+{
+ ctxt->ops->get_fpu(ctxt);
+ switch (reg) {
+ case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
+ case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
+ case 2: asm("movq %0, %%mm2" : : "m"(*data)); break;
+ case 3: asm("movq %0, %%mm3" : : "m"(*data)); break;
+ case 4: asm("movq %0, %%mm4" : : "m"(*data)); break;
+ case 5: asm("movq %0, %%mm5" : : "m"(*data)); break;
+ case 6: asm("movq %0, %%mm6" : : "m"(*data)); break;
+ case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
+ default: BUG();
+ }
+ ctxt->ops->put_fpu(ctxt);
+}
+
static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
struct operand *op)
{
@@ -875,6 +938,13 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
read_sse_reg(ctxt, &op->vec_val, reg);
return;
}
+ if (ctxt->d & Mmx) {
+ reg &= 7;
+ op->type = OP_MM;
+ op->bytes = 8;
+ op->addr.mm = reg;
+ return;
+ }
op->type = OP_REG;
if (ctxt->d & ByteOp) {
@@ -902,7 +972,6 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
ctxt->modrm_rm = base_reg = (ctxt->rex_prefix & 1) << 3; /* REG.B */
}
- ctxt->modrm = insn_fetch(u8, ctxt);
ctxt->modrm_mod |= (ctxt->modrm & 0xc0) >> 6;
ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3;
ctxt->modrm_rm |= (ctxt->modrm & 0x07);
@@ -920,6 +989,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm);
return rc;
}
+ if (ctxt->d & Mmx) {
+ op->type = OP_MM;
+ op->bytes = 8;
+ op->addr.xmm = ctxt->modrm_rm & 7;
+ return rc;
+ }
fetch_register_operand(op);
return rc;
}
@@ -1387,6 +1462,9 @@ static int writeback(struct x86_emulate_ctxt *ctxt)
case OP_XMM:
write_sse_reg(ctxt, &ctxt->dst.vec_val, ctxt->dst.addr.xmm);
break;
+ case OP_MM:
+ write_mmx_reg(ctxt, &ctxt->dst.mm_val, ctxt->dst.addr.mm);
+ break;
case OP_NONE:
/* no writeback */
break;
@@ -2790,7 +2868,7 @@ static int em_rdpmc(struct x86_emulate_ctxt *ctxt)
static int em_mov(struct x86_emulate_ctxt *ctxt)
{
- ctxt->dst.val = ctxt->src.val;
+ memcpy(ctxt->dst.valptr, ctxt->src.valptr, ctxt->op_bytes);
return X86EMUL_CONTINUE;
}
@@ -2870,12 +2948,6 @@ static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt)
return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg);
}
-static int em_movdqu(struct x86_emulate_ctxt *ctxt)
-{
- memcpy(&ctxt->dst.vec_val, &ctxt->src.vec_val, ctxt->op_bytes);
- return X86EMUL_CONTINUE;
-}
-
static int em_invlpg(struct x86_emulate_ctxt *ctxt)
{
int rc;
@@ -3061,35 +3133,13 @@ static int em_btc(struct x86_emulate_ctxt *ctxt)
static int em_bsf(struct x86_emulate_ctxt *ctxt)
{
- u8 zf;
-
- __asm__ ("bsf %2, %0; setz %1"
- : "=r"(ctxt->dst.val), "=q"(zf)
- : "r"(ctxt->src.val));
-
- ctxt->eflags &= ~X86_EFLAGS_ZF;
- if (zf) {
- ctxt->eflags |= X86_EFLAGS_ZF;
- /* Disable writeback. */
- ctxt->dst.type = OP_NONE;
- }
+ emulate_2op_SrcV_nobyte(ctxt, "bsf");
return X86EMUL_CONTINUE;
}
static int em_bsr(struct x86_emulate_ctxt *ctxt)
{
- u8 zf;
-
- __asm__ ("bsr %2, %0; setz %1"
- : "=r"(ctxt->dst.val), "=q"(zf)
- : "r"(ctxt->src.val));
-
- ctxt->eflags &= ~X86_EFLAGS_ZF;
- if (zf) {
- ctxt->eflags |= X86_EFLAGS_ZF;
- /* Disable writeback. */
- ctxt->dst.type = OP_NONE;
- }
+ emulate_2op_SrcV_nobyte(ctxt, "bsr");
return X86EMUL_CONTINUE;
}
@@ -3286,8 +3336,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
.check_perm = (_p) }
#define N D(0)
#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
-#define G(_f, _g) { .flags = ((_f) | Group), .u.group = (_g) }
-#define GD(_f, _g) { .flags = ((_f) | GroupDual), .u.gdual = (_g) }
+#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
+#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
#define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
#define II(_f, _e, _i) \
{ .flags = (_f), .u.execute = (_e), .intercept = x86_intercept_##_i }
@@ -3307,25 +3357,25 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
I2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
static struct opcode group7_rm1[] = {
- DI(SrcNone | ModRM | Priv, monitor),
- DI(SrcNone | ModRM | Priv, mwait),
+ DI(SrcNone | Priv, monitor),
+ DI(SrcNone | Priv, mwait),
N, N, N, N, N, N,
};
static struct opcode group7_rm3[] = {
- DIP(SrcNone | ModRM | Prot | Priv, vmrun, check_svme_pa),
- II(SrcNone | ModRM | Prot | VendorSpecific, em_vmmcall, vmmcall),
- DIP(SrcNone | ModRM | Prot | Priv, vmload, check_svme_pa),
- DIP(SrcNone | ModRM | Prot | Priv, vmsave, check_svme_pa),
- DIP(SrcNone | ModRM | Prot | Priv, stgi, check_svme),
- DIP(SrcNone | ModRM | Prot | Priv, clgi, check_svme),
- DIP(SrcNone | ModRM | Prot | Priv, skinit, check_svme),
- DIP(SrcNone | ModRM | Prot | Priv, invlpga, check_svme),
+ DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa),
+ II(SrcNone | Prot | VendorSpecific, em_vmmcall, vmmcall),
+ DIP(SrcNone | Prot | Priv, vmload, check_svme_pa),
+ DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa),
+ DIP(SrcNone | Prot | Priv, stgi, check_svme),
+ DIP(SrcNone | Prot | Priv, clgi, check_svme),
+ DIP(SrcNone | Prot | Priv, skinit, check_svme),
+ DIP(SrcNone | Prot | Priv, invlpga, check_svme),
};
static struct opcode group7_rm7[] = {
N,
- DIP(SrcNone | ModRM, rdtscp, check_rdtsc),
+ DIP(SrcNone, rdtscp, check_rdtsc),
N, N, N, N, N, N,
};
@@ -3341,81 +3391,86 @@ static struct opcode group1[] = {
};
static struct opcode group1A[] = {
- I(DstMem | SrcNone | ModRM | Mov | Stack, em_pop), N, N, N, N, N, N, N,
+ I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
};
static struct opcode group3[] = {
- I(DstMem | SrcImm | ModRM, em_test),
- I(DstMem | SrcImm | ModRM, em_test),
- I(DstMem | SrcNone | ModRM | Lock, em_not),
- I(DstMem | SrcNone | ModRM | Lock, em_neg),
- I(SrcMem | ModRM, em_mul_ex),
- I(SrcMem | ModRM, em_imul_ex),
- I(SrcMem | ModRM, em_div_ex),
- I(SrcMem | ModRM, em_idiv_ex),
+ I(DstMem | SrcImm, em_test),
+ I(DstMem | SrcImm, em_test),
+ I(DstMem | SrcNone | Lock, em_not),
+ I(DstMem | SrcNone | Lock, em_neg),
+ I(SrcMem, em_mul_ex),
+ I(SrcMem, em_imul_ex),
+ I(SrcMem, em_div_ex),
+ I(SrcMem, em_idiv_ex),
};
static struct opcode group4[] = {
- I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45),
- I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45),
+ I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
+ I(ByteOp | DstMem | SrcNone | Lock, em_grp45),
N, N, N, N, N, N,
};
static struct opcode group5[] = {
- I(DstMem | SrcNone | ModRM | Lock, em_grp45),
- I(DstMem | SrcNone | ModRM | Lock, em_grp45),
- I(SrcMem | ModRM | Stack, em_grp45),
- I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far),
- I(SrcMem | ModRM | Stack, em_grp45),
- I(SrcMemFAddr | ModRM | ImplicitOps, em_grp45),
- I(SrcMem | ModRM | Stack, em_grp45), N,
+ I(DstMem | SrcNone | Lock, em_grp45),
+ I(DstMem | SrcNone | Lock, em_grp45),
+ I(SrcMem | Stack, em_grp45),
+ I(SrcMemFAddr | ImplicitOps | Stack, em_call_far),
+ I(SrcMem | Stack, em_grp45),
+ I(SrcMemFAddr | ImplicitOps, em_grp45),
+ I(SrcMem | Stack, em_grp45), N,
};
static struct opcode group6[] = {
- DI(ModRM | Prot, sldt),
- DI(ModRM | Prot, str),
- DI(ModRM | Prot | Priv, lldt),
- DI(ModRM | Prot | Priv, ltr),
+ DI(Prot, sldt),
+ DI(Prot, str),
+ DI(Prot | Priv, lldt),
+ DI(Prot | Priv, ltr),
N, N, N, N,
};
static struct group_dual group7 = { {
- DI(ModRM | Mov | DstMem | Priv, sgdt),
- DI(ModRM | Mov | DstMem | Priv, sidt),
- II(ModRM | SrcMem | Priv, em_lgdt, lgdt),
- II(ModRM | SrcMem | Priv, em_lidt, lidt),
- II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N,
- II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw),
- II(SrcMem | ModRM | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
+ DI(Mov | DstMem | Priv, sgdt),
+ DI(Mov | DstMem | Priv, sidt),
+ II(SrcMem | Priv, em_lgdt, lgdt),
+ II(SrcMem | Priv, em_lidt, lidt),
+ II(SrcNone | DstMem | Mov, em_smsw, smsw), N,
+ II(SrcMem16 | Mov | Priv, em_lmsw, lmsw),
+ II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
}, {
- I(SrcNone | ModRM | Priv | VendorSpecific, em_vmcall),
+ I(SrcNone | Priv | VendorSpecific, em_vmcall),
EXT(0, group7_rm1),
N, EXT(0, group7_rm3),
- II(SrcNone | ModRM | DstMem | Mov, em_smsw, smsw), N,
- II(SrcMem16 | ModRM | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7),
+ II(SrcNone | DstMem | Mov, em_smsw, smsw), N,
+ II(SrcMem16 | Mov | Priv, em_lmsw, lmsw),
+ EXT(0, group7_rm7),
} };
static struct opcode group8[] = {
N, N, N, N,
- I(DstMem | SrcImmByte | ModRM, em_bt),
- I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_bts),
- I(DstMem | SrcImmByte | ModRM | Lock, em_btr),
- I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_btc),
+ I(DstMem | SrcImmByte, em_bt),
+ I(DstMem | SrcImmByte | Lock | PageTable, em_bts),
+ I(DstMem | SrcImmByte | Lock, em_btr),
+ I(DstMem | SrcImmByte | Lock | PageTable, em_btc),
};
static struct group_dual group9 = { {
- N, I(DstMem64 | ModRM | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
+ N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N,
}, {
N, N, N, N, N, N, N, N,
} };
static struct opcode group11[] = {
- I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov),
+ I(DstMem | SrcImm | Mov | PageTable, em_mov),
X7(D(Undefined)),
};
static struct gprefix pfx_0f_6f_0f_7f = {
- N, N, N, I(Sse, em_movdqu),
+ I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
+};
+
+static struct gprefix pfx_vmovntpx = {
+ I(0, em_mov), N, N, N,
};
static struct opcode opcode_table[256] = {
@@ -3464,10 +3519,10 @@ static struct opcode opcode_table[256] = {
/* 0x70 - 0x7F */
X16(D(SrcImmByte)),
/* 0x80 - 0x87 */
- G(ByteOp | DstMem | SrcImm | ModRM | Group, group1),
- G(DstMem | SrcImm | ModRM | Group, group1),
- G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1),
- G(DstMem | SrcImmByte | ModRM | Group, group1),
+ G(ByteOp | DstMem | SrcImm, group1),
+ G(DstMem | SrcImm, group1),
+ G(ByteOp | DstMem | SrcImm | No64, group1),
+ G(DstMem | SrcImmByte, group1),
I2bv(DstMem | SrcReg | ModRM, em_test),
I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg),
/* 0x88 - 0x8F */
@@ -3549,7 +3604,8 @@ static struct opcode twobyte_table[256] = {
IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write),
IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write),
N, N, N, N,
- N, N, N, N, N, N, N, N,
+ N, N, N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+ N, N, N, N,
/* 0x30 - 0x3F */
II(ImplicitOps | Priv, em_wrmsr, wrmsr),
IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
@@ -3897,17 +3953,16 @@ done_prefixes:
}
ctxt->d = opcode.flags;
+ if (ctxt->d & ModRM)
+ ctxt->modrm = insn_fetch(u8, ctxt);
+
while (ctxt->d & GroupMask) {
switch (ctxt->d & GroupMask) {
case Group:
- ctxt->modrm = insn_fetch(u8, ctxt);
- --ctxt->_eip;
goffset = (ctxt->modrm >> 3) & 7;
opcode = opcode.u.group[goffset];
break;
case GroupDual:
- ctxt->modrm = insn_fetch(u8, ctxt);
- --ctxt->_eip;
goffset = (ctxt->modrm >> 3) & 7;
if ((ctxt->modrm >> 6) == 3)
opcode = opcode.u.gdual->mod3[goffset];
@@ -3960,6 +4015,8 @@ done_prefixes:
if (ctxt->d & Sse)
ctxt->op_bytes = 16;
+ else if (ctxt->d & Mmx)
+ ctxt->op_bytes = 8;
/* ModRM and SIB bytes. */
if (ctxt->d & ModRM) {
@@ -4030,6 +4087,35 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt)
return false;
}
+static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
+{
+ bool fault = false;
+
+ ctxt->ops->get_fpu(ctxt);
+ asm volatile("1: fwait \n\t"
+ "2: \n\t"
+ ".pushsection .fixup,\"ax\" \n\t"
+ "3: \n\t"
+ "movb $1, %[fault] \n\t"
+ "jmp 2b \n\t"
+ ".popsection \n\t"
+ _ASM_EXTABLE(1b, 3b)
+ : [fault]"+qm"(fault));
+ ctxt->ops->put_fpu(ctxt);
+
+ if (unlikely(fault))
+ return emulate_exception(ctxt, MF_VECTOR, 0, false);
+
+ return X86EMUL_CONTINUE;
+}
+
+static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt,
+ struct operand *op)
+{
+ if (op->type == OP_MM)
+ read_mmx_reg(ctxt, &op->mm_val, op->addr.mm);
+}
+
int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
{
struct x86_emulate_ops *ops = ctxt->ops;
@@ -4054,18 +4140,31 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
- if ((ctxt->d & Sse)
- && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)
- || !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
+ if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM)))
+ || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) {
rc = emulate_ud(ctxt);
goto done;
}
- if ((ctxt->d & Sse) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
+ if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) {
rc = emulate_nm(ctxt);
goto done;
}
+ if (ctxt->d & Mmx) {
+ rc = flush_pending_x87_faults(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ /*
+ * Now that we know the fpu is exception safe, we can fetch
+ * operands from it.
+ */
+ fetch_possible_mmx_operand(ctxt, &ctxt->src);
+ fetch_possible_mmx_operand(ctxt, &ctxt->src2);
+ if (!(ctxt->d & Mov))
+ fetch_possible_mmx_operand(ctxt, &ctxt->dst);
+ }
+
if (unlikely(ctxt->guest_mode) && ctxt->intercept) {
rc = emulator_check_intercept(ctxt, ctxt->intercept,
X86_ICPT_PRE_EXCEPT);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index d68f99df690..adba28f88d1 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -34,7 +34,6 @@
#include <linux/kvm_host.h>
#include <linux/slab.h>
-#include <linux/workqueue.h>
#include "irq.h"
#include "i8254.h"
@@ -249,7 +248,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
/* in this case, we had multiple outstanding pit interrupts
* that we needed to inject. Reinject
*/
- queue_work(ps->pit->wq, &ps->pit->expired);
+ queue_kthread_work(&ps->pit->worker, &ps->pit->expired);
ps->irq_ack = 1;
spin_unlock(&ps->inject_lock);
}
@@ -270,7 +269,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
static void destroy_pit_timer(struct kvm_pit *pit)
{
hrtimer_cancel(&pit->pit_state.pit_timer.timer);
- cancel_work_sync(&pit->expired);
+ flush_kthread_work(&pit->expired);
}
static bool kpit_is_periodic(struct kvm_timer *ktimer)
@@ -284,7 +283,7 @@ static struct kvm_timer_ops kpit_ops = {
.is_periodic = kpit_is_periodic,
};
-static void pit_do_work(struct work_struct *work)
+static void pit_do_work(struct kthread_work *work)
{
struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
struct kvm *kvm = pit->kvm;
@@ -328,7 +327,7 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
atomic_inc(&ktimer->pending);
- queue_work(pt->wq, &pt->expired);
+ queue_kthread_work(&pt->worker, &pt->expired);
}
if (ktimer->t_ops->is_periodic(ktimer)) {
@@ -353,7 +352,7 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
/* TODO The new value only affected after the retriggered */
hrtimer_cancel(&pt->timer);
- cancel_work_sync(&ps->pit->expired);
+ flush_kthread_work(&ps->pit->expired);
pt->period = interval;
ps->is_periodic = is_period;
@@ -669,6 +668,8 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
{
struct kvm_pit *pit;
struct kvm_kpit_state *pit_state;
+ struct pid *pid;
+ pid_t pid_nr;
int ret;
pit = kzalloc(sizeof(struct kvm_pit), GFP_KERNEL);
@@ -685,14 +686,20 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
mutex_lock(&pit->pit_state.lock);
spin_lock_init(&pit->pit_state.inject_lock);
- pit->wq = create_singlethread_workqueue("kvm-pit-wq");
- if (!pit->wq) {
+ pid = get_pid(task_tgid(current));
+ pid_nr = pid_vnr(pid);
+ put_pid(pid);
+
+ init_kthread_worker(&pit->worker);
+ pit->worker_task = kthread_run(kthread_worker_fn, &pit->worker,
+ "kvm-pit/%d", pid_nr);
+ if (IS_ERR(pit->worker_task)) {
mutex_unlock(&pit->pit_state.lock);
kvm_free_irq_source_id(kvm, pit->irq_source_id);
kfree(pit);
return NULL;
}
- INIT_WORK(&pit->expired, pit_do_work);
+ init_kthread_work(&pit->expired, pit_do_work);
kvm->arch.vpit = pit;
pit->kvm = kvm;
@@ -736,7 +743,7 @@ fail:
kvm_unregister_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
kvm_unregister_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
kvm_free_irq_source_id(kvm, pit->irq_source_id);
- destroy_workqueue(pit->wq);
+ kthread_stop(pit->worker_task);
kfree(pit);
return NULL;
}
@@ -756,10 +763,10 @@ void kvm_free_pit(struct kvm *kvm)
mutex_lock(&kvm->arch.vpit->pit_state.lock);
timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
hrtimer_cancel(timer);
- cancel_work_sync(&kvm->arch.vpit->expired);
+ flush_kthread_work(&kvm->arch.vpit->expired);
+ kthread_stop(kvm->arch.vpit->worker_task);
kvm_free_irq_source_id(kvm, kvm->arch.vpit->irq_source_id);
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
- destroy_workqueue(kvm->arch.vpit->wq);
kfree(kvm->arch.vpit);
}
}
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 51a97426e79..fdf40425ea1 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -1,6 +1,8 @@
#ifndef __I8254_H
#define __I8254_H
+#include <linux/kthread.h>
+
#include "iodev.h"
struct kvm_kpit_channel_state {
@@ -39,8 +41,9 @@ struct kvm_pit {
struct kvm_kpit_state pit_state;
int irq_source_id;
struct kvm_irq_mask_notifier mask_notifier;
- struct workqueue_struct *wq;
- struct work_struct expired;
+ struct kthread_worker worker;
+ struct task_struct *worker_task;
+ struct kthread_work expired;
};
#define KVM_PIT_BASE_ADDRESS 0x40
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 858432287ab..93c15743f1e 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -92,6 +92,11 @@ static inline int apic_test_and_clear_vector(int vec, void *bitmap)
return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}
+static inline int apic_test_vector(int vec, void *bitmap)
+{
+ return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+}
+
static inline void apic_set_vector(int vec, void *bitmap)
{
set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -480,7 +485,6 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
static void apic_set_eoi(struct kvm_lapic *apic)
{
int vector = apic_find_highest_isr(apic);
- int trigger_mode;
/*
* Not every write EOI will has corresponding ISR,
* one example is when Kernel check timer on setup_IO_APIC
@@ -491,12 +495,15 @@ static void apic_set_eoi(struct kvm_lapic *apic)
apic_clear_vector(vector, apic->regs + APIC_ISR);
apic_update_ppr(apic);
- if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR))
- trigger_mode = IOAPIC_LEVEL_TRIG;
- else
- trigger_mode = IOAPIC_EDGE_TRIG;
- if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
+ if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+ kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+ int trigger_mode;
+ if (apic_test_vector(vector, apic->regs + APIC_TMR))
+ trigger_mode = IOAPIC_LEVEL_TRIG;
+ else
+ trigger_mode = IOAPIC_EDGE_TRIG;
kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+ }
kvm_make_request(KVM_REQ_EVENT, apic->vcpu);
}
@@ -1081,6 +1088,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
apic_update_ppr(apic);
vcpu->arch.apic_arb_prio = 0;
+ vcpu->arch.apic_attention = 0;
apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
"0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
@@ -1280,7 +1288,7 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
u32 data;
void *vapic;
- if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+ if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
@@ -1297,7 +1305,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
struct kvm_lapic *apic;
void *vapic;
- if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
+ if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
return;
apic = vcpu->arch.apic;
@@ -1317,10 +1325,11 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
{
- if (!irqchip_in_kernel(vcpu->kvm))
- return;
-
vcpu->arch.apic->vapic_addr = vapic_addr;
+ if (vapic_addr)
+ __set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+ else
+ __clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
}
int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4cb16426884..72102e0ab7c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -135,8 +135,6 @@ module_param(dbg, bool, 0644);
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
| PT64_NX_MASK)
-#define PTE_LIST_EXT 4
-
#define ACC_EXEC_MASK 1
#define ACC_WRITE_MASK PT_WRITABLE_MASK
#define ACC_USER_MASK PT_USER_MASK
@@ -151,6 +149,9 @@ module_param(dbg, bool, 0644);
#define SHADOW_PT_INDEX(addr, level) PT64_INDEX(addr, level)
+/* make pte_list_desc fit well in cache line */
+#define PTE_LIST_EXT 3
+
struct pte_list_desc {
u64 *sptes[PTE_LIST_EXT];
struct pte_list_desc *more;
@@ -550,19 +551,29 @@ static u64 mmu_spte_get_lockless(u64 *sptep)
static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
{
- rcu_read_lock();
- atomic_inc(&vcpu->kvm->arch.reader_counter);
-
- /* Increase the counter before walking shadow page table */
- smp_mb__after_atomic_inc();
+ /*
+ * Prevent page table teardown by making any free-er wait during
+ * kvm_flush_remote_tlbs() IPI to all active vcpus.
+ */
+ local_irq_disable();
+ vcpu->mode = READING_SHADOW_PAGE_TABLES;
+ /*
+ * Make sure a following spte read is not reordered ahead of the write
+ * to vcpu->mode.
+ */
+ smp_mb();
}
static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
{
- /* Decrease the counter after walking shadow page table finished */
- smp_mb__before_atomic_dec();
- atomic_dec(&vcpu->kvm->arch.reader_counter);
- rcu_read_unlock();
+ /*
+ * Make sure the write to vcpu->mode is not reordered in front of
+ * reads to sptes. If it does, kvm_commit_zap_page() can see us
+ * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
+ */
+ smp_mb();
+ vcpu->mode = OUTSIDE_GUEST_MODE;
+ local_irq_enable();
}
static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
@@ -841,32 +852,6 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
return count;
}
-static u64 *pte_list_next(unsigned long *pte_list, u64 *spte)
-{
- struct pte_list_desc *desc;
- u64 *prev_spte;
- int i;
-
- if (!*pte_list)
- return NULL;
- else if (!(*pte_list & 1)) {
- if (!spte)
- return (u64 *)*pte_list;
- return NULL;
- }
- desc = (struct pte_list_desc *)(*pte_list & ~1ul);
- prev_spte = NULL;
- while (desc) {
- for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) {
- if (prev_spte == spte)
- return desc->sptes[i];
- prev_spte = desc->sptes[i];
- }
- desc = desc->more;
- }
- return NULL;
-}
-
static void
pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc,
int i, struct pte_list_desc *prev_desc)
@@ -987,11 +972,6 @@ static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
return pte_list_add(vcpu, spte, rmapp);
}
-static u64 *rmap_next(unsigned long *rmapp, u64 *spte)
-{
- return pte_list_next(rmapp, spte);
-}
-
static void rmap_remove(struct kvm *kvm, u64 *spte)
{
struct kvm_mmu_page *sp;
@@ -1004,106 +984,201 @@ static void rmap_remove(struct kvm *kvm, u64 *spte)
pte_list_remove(spte, rmapp);
}
+/*
+ * Used by the following functions to iterate through the sptes linked by a
+ * rmap. All fields are private and not assumed to be used outside.
+ */
+struct rmap_iterator {
+ /* private fields */
+ struct pte_list_desc *desc; /* holds the sptep if not NULL */
+ int pos; /* index of the sptep */
+};
+
+/*
+ * Iteration must be started by this function. This should also be used after
+ * removing/dropping sptes from the rmap link because in such cases the
+ * information in the itererator may not be valid.
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter)
+{
+ if (!rmap)
+ return NULL;
+
+ if (!(rmap & 1)) {
+ iter->desc = NULL;
+ return (u64 *)rmap;
+ }
+
+ iter->desc = (struct pte_list_desc *)(rmap & ~1ul);
+ iter->pos = 0;
+ return iter->desc->sptes[iter->pos];
+}
+
+/*
+ * Must be used with a valid iterator: e.g. after rmap_get_first().
+ *
+ * Returns sptep if found, NULL otherwise.
+ */
+static u64 *rmap_get_next(struct rmap_iterator *iter)
+{
+ if (iter->desc) {
+ if (iter->pos < PTE_LIST_EXT - 1) {
+ u64 *sptep;
+
+ ++iter->pos;
+ sptep = iter->desc->sptes[iter->pos];
+ if (sptep)
+ return sptep;
+ }
+
+ iter->desc = iter->desc->more;
+
+ if (iter->desc) {
+ iter->pos = 0;
+ /* desc->sptes[0] cannot be NULL */
+ return iter->desc->sptes[iter->pos];
+ }
+ }
+
+ return NULL;
+}
+
static void drop_spte(struct kvm *kvm, u64 *sptep)
{
if (mmu_spte_clear_track_bits(sptep))
rmap_remove(kvm, sptep);
}
-int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn,
- struct kvm_memory_slot *slot)
+static int __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, int level)
{
- unsigned long *rmapp;
- u64 *spte;
- int i, write_protected = 0;
-
- rmapp = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot);
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- BUG_ON(!(*spte & PT_PRESENT_MASK));
- rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte);
- if (is_writable_pte(*spte)) {
- mmu_spte_update(spte, *spte & ~PT_WRITABLE_MASK);
- write_protected = 1;
+ u64 *sptep;
+ struct rmap_iterator iter;
+ int write_protected = 0;
+
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+ rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
+
+ if (!is_writable_pte(*sptep)) {
+ sptep = rmap_get_next(&iter);
+ continue;
}
- spte = rmap_next(rmapp, spte);
- }
- /* check for huge page mappings */
- for (i = PT_DIRECTORY_LEVEL;
- i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
- rmapp = __gfn_to_rmap(gfn, i, slot);
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- BUG_ON(!(*spte & PT_PRESENT_MASK));
- BUG_ON(!is_large_pte(*spte));
- pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn);
- if (is_writable_pte(*spte)) {
- drop_spte(kvm, spte);
- --kvm->stat.lpages;
- spte = NULL;
- write_protected = 1;
- }
- spte = rmap_next(rmapp, spte);
+ if (level == PT_PAGE_TABLE_LEVEL) {
+ mmu_spte_update(sptep, *sptep & ~PT_WRITABLE_MASK);
+ sptep = rmap_get_next(&iter);
+ } else {
+ BUG_ON(!is_large_pte(*sptep));
+ drop_spte(kvm, sptep);
+ --kvm->stat.lpages;
+ sptep = rmap_get_first(*rmapp, &iter);
}
+
+ write_protected = 1;
}
return write_protected;
}
+/**
+ * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages
+ * @kvm: kvm instance
+ * @slot: slot to protect
+ * @gfn_offset: start of the BITS_PER_LONG pages we care about
+ * @mask: indicates which pages we should protect
+ *
+ * Used when we do not need to care about huge page mappings: e.g. during dirty
+ * logging we do not have any such mappings.
+ */
+void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ gfn_t gfn_offset, unsigned long mask)
+{
+ unsigned long *rmapp;
+
+ while (mask) {
+ rmapp = &slot->rmap[gfn_offset + __ffs(mask)];
+ __rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL);
+
+ /* clear the first set bit */
+ mask &= mask - 1;
+ }
+}
+
static int rmap_write_protect(struct kvm *kvm, u64 gfn)
{
struct kvm_memory_slot *slot;
+ unsigned long *rmapp;
+ int i;
+ int write_protected = 0;
slot = gfn_to_memslot(kvm, gfn);
- return kvm_mmu_rmap_write_protect(kvm, gfn, slot);
+
+ for (i = PT_PAGE_TABLE_LEVEL;
+ i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) {
+ rmapp = __gfn_to_rmap(gfn, i, slot);
+ write_protected |= __rmap_write_protect(kvm, rmapp, i);
+ }
+
+ return write_protected;
}
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long data)
{
- u64 *spte;
+ u64 *sptep;
+ struct rmap_iterator iter;
int need_tlb_flush = 0;
- while ((spte = rmap_next(rmapp, NULL))) {
- BUG_ON(!(*spte & PT_PRESENT_MASK));
- rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", spte, *spte);
- drop_spte(kvm, spte);
+ while ((sptep = rmap_get_first(*rmapp, &iter))) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+ rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep);
+
+ drop_spte(kvm, sptep);
need_tlb_flush = 1;
}
+
return need_tlb_flush;
}
static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long data)
{
+ u64 *sptep;
+ struct rmap_iterator iter;
int need_flush = 0;
- u64 *spte, new_spte;
+ u64 new_spte;
pte_t *ptep = (pte_t *)data;
pfn_t new_pfn;
WARN_ON(pte_huge(*ptep));
new_pfn = pte_pfn(*ptep);
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- BUG_ON(!is_shadow_present_pte(*spte));
- rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", spte, *spte);
+
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
+ BUG_ON(!is_shadow_present_pte(*sptep));
+ rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep);
+
need_flush = 1;
+
if (pte_write(*ptep)) {
- drop_spte(kvm, spte);
- spte = rmap_next(rmapp, NULL);
+ drop_spte(kvm, sptep);
+ sptep = rmap_get_first(*rmapp, &iter);
} else {
- new_spte = *spte &~ (PT64_BASE_ADDR_MASK);
+ new_spte = *sptep & ~PT64_BASE_ADDR_MASK;
new_spte |= (u64)new_pfn << PAGE_SHIFT;
new_spte &= ~PT_WRITABLE_MASK;
new_spte &= ~SPTE_HOST_WRITEABLE;
new_spte &= ~shadow_accessed_mask;
- mmu_spte_clear_track_bits(spte);
- mmu_spte_set(spte, new_spte);
- spte = rmap_next(rmapp, spte);
+
+ mmu_spte_clear_track_bits(sptep);
+ mmu_spte_set(sptep, new_spte);
+ sptep = rmap_get_next(&iter);
}
}
+
if (need_flush)
kvm_flush_remote_tlbs(kvm);
@@ -1162,7 +1237,8 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long data)
{
- u64 *spte;
+ u64 *sptep;
+ struct rmap_iterator iter;
int young = 0;
/*
@@ -1175,25 +1251,24 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
if (!shadow_accessed_mask)
return kvm_unmap_rmapp(kvm, rmapp, data);
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- int _young;
- u64 _spte = *spte;
- BUG_ON(!(_spte & PT_PRESENT_MASK));
- _young = _spte & PT_ACCESSED_MASK;
- if (_young) {
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+ sptep = rmap_get_next(&iter)) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+
+ if (*sptep & PT_ACCESSED_MASK) {
young = 1;
- clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte);
+ clear_bit(PT_ACCESSED_SHIFT, (unsigned long *)sptep);
}
- spte = rmap_next(rmapp, spte);
}
+
return young;
}
static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
unsigned long data)
{
- u64 *spte;
+ u64 *sptep;
+ struct rmap_iterator iter;
int young = 0;
/*
@@ -1204,16 +1279,14 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
if (!shadow_accessed_mask)
goto out;
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- u64 _spte = *spte;
- BUG_ON(!(_spte & PT_PRESENT_MASK));
- young = _spte & PT_ACCESSED_MASK;
- if (young) {
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+ sptep = rmap_get_next(&iter)) {
+ BUG_ON(!(*sptep & PT_PRESENT_MASK));
+
+ if (*sptep & PT_ACCESSED_MASK) {
young = 1;
break;
}
- spte = rmap_next(rmapp, spte);
}
out:
return young;
@@ -1865,10 +1938,11 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte)
static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
{
- u64 *parent_pte;
+ u64 *sptep;
+ struct rmap_iterator iter;
- while ((parent_pte = pte_list_next(&sp->parent_ptes, NULL)))
- drop_parent_pte(sp, parent_pte);
+ while ((sptep = rmap_get_first(sp->parent_ptes, &iter)))
+ drop_parent_pte(sp, sptep);
}
static int mmu_zap_unsync_children(struct kvm *kvm,
@@ -1925,30 +1999,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
return ret;
}
-static void kvm_mmu_isolate_pages(struct list_head *invalid_list)
-{
- struct kvm_mmu_page *sp;
-
- list_for_each_entry(sp, invalid_list, link)
- kvm_mmu_isolate_page(sp);
-}
-
-static void free_pages_rcu(struct rcu_head *head)
-{
- struct kvm_mmu_page *next, *sp;
-
- sp = container_of(head, struct kvm_mmu_page, rcu);
- while (sp) {
- if (!list_empty(&sp->link))
- next = list_first_entry(&sp->link,
- struct kvm_mmu_page, link);
- else
- next = NULL;
- kvm_mmu_free_page(sp);
- sp = next;
- }
-}
-
static void kvm_mmu_commit_zap_page(struct kvm *kvm,
struct list_head *invalid_list)
{
@@ -1957,17 +2007,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
if (list_empty(invalid_list))
return;
- kvm_flush_remote_tlbs(kvm);
-
- if (atomic_read(&kvm->arch.reader_counter)) {
- kvm_mmu_isolate_pages(invalid_list);
- sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
- list_del_init(invalid_list);
+ /*
+ * wmb: make sure everyone sees our modifications to the page tables
+ * rmb: make sure we see changes to vcpu->mode
+ */
+ smp_mb();
- trace_kvm_mmu_delay_free_pages(sp);
- call_rcu(&sp->rcu, free_pages_rcu);
- return;
- }
+ /*
+ * Wait for all vcpus to exit guest mode and/or lockless shadow
+ * page table walks.
+ */
+ kvm_flush_remote_tlbs(kvm);
do {
sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
@@ -1975,7 +2025,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
kvm_mmu_isolate_page(sp);
kvm_mmu_free_page(sp);
} while (!list_empty(invalid_list));
-
}
/*
@@ -3554,7 +3603,7 @@ static bool detect_write_flooding(struct kvm_mmu_page *sp)
* Skip write-flooding detected for the sp whose level is 1, because
* it can become unsync, then the guest page is not write-protected.
*/
- if (sp->role.level == 1)
+ if (sp->role.level == PT_PAGE_TABLE_LEVEL)
return false;
return ++sp->write_flooding_count >= 3;
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 715da5a19a5..7d7d0b9e23e 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -192,7 +192,8 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
{
struct kvm_memory_slot *slot;
unsigned long *rmapp;
- u64 *spte;
+ u64 *sptep;
+ struct rmap_iterator iter;
if (sp->role.direct || sp->unsync || sp->role.invalid)
return;
@@ -200,13 +201,12 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
slot = gfn_to_memslot(kvm, sp->gfn);
rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
- spte = rmap_next(rmapp, NULL);
- while (spte) {
- if (is_writable_pte(*spte))
+ for (sptep = rmap_get_first(*rmapp, &iter); sptep;
+ sptep = rmap_get_next(&iter)) {
+ if (is_writable_pte(*sptep))
audit_printk(kvm, "shadow page has writable "
"mappings: gfn %llx role %x\n",
sp->gfn, sp->role.word);
- spte = rmap_next(rmapp, spte);
}
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index df5a70311be..34f970937ef 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -658,7 +658,7 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp)
{
int offset = 0;
- WARN_ON(sp->role.level != 1);
+ WARN_ON(sp->role.level != PT_PAGE_TABLE_LEVEL);
if (PTTYPE == 32)
offset = sp->role.quadrant << PT64_LEVEL_BITS;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e334389e1c7..f75af406b26 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -22,6 +22,7 @@
#include "x86.h"
#include <linux/module.h>
+#include <linux/mod_devicetable.h>
#include <linux/kernel.h>
#include <linux/vmalloc.h>
#include <linux/highmem.h>
@@ -42,6 +43,12 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+static const struct x86_cpu_id svm_cpu_id[] = {
+ X86_FEATURE_MATCH(X86_FEATURE_SVM),
+ {}
+};
+MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
+
#define IOPM_ALLOC_ORDER 2
#define MSRPM_ALLOC_ORDER 1
@@ -3240,6 +3247,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
svm_clear_vintr(svm);
svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
mark_dirty(svm->vmcb, VMCB_INTR);
+ ++svm->vcpu.stat.irq_window_exits;
/*
* If the user space waits to inject interrupts, exit as soon as
* possible
@@ -3247,7 +3255,6 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
if (!irqchip_in_kernel(svm->vcpu.kvm) &&
kvm_run->request_interrupt_window &&
!kvm_cpu_has_interrupt(&svm->vcpu)) {
- ++svm->vcpu.stat.irq_window_exits;
kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
return 0;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4ff0ab9bc3c..32eb5886629 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -27,6 +27,7 @@
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/moduleparam.h>
+#include <linux/mod_devicetable.h>
#include <linux/ftrace_event.h>
#include <linux/slab.h>
#include <linux/tboot.h>
@@ -51,6 +52,12 @@
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
+static const struct x86_cpu_id vmx_cpu_id[] = {
+ X86_FEATURE_MATCH(X86_FEATURE_VMX),
+ {}
+};
+MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
+
static bool __read_mostly enable_vpid = 1;
module_param_named(vpid, enable_vpid, bool, 0444);
@@ -386,6 +393,9 @@ struct vcpu_vmx {
struct {
int loaded;
u16 fs_sel, gs_sel, ldt_sel;
+#ifdef CONFIG_X86_64
+ u16 ds_sel, es_sel;
+#endif
int gs_ldt_reload_needed;
int fs_reload_needed;
} host_state;
@@ -1411,6 +1421,11 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
}
#ifdef CONFIG_X86_64
+ savesegment(ds, vmx->host_state.ds_sel);
+ savesegment(es, vmx->host_state.es_sel);
+#endif
+
+#ifdef CONFIG_X86_64
vmcs_writel(HOST_FS_BASE, read_msr(MSR_FS_BASE));
vmcs_writel(HOST_GS_BASE, read_msr(MSR_GS_BASE));
#else
@@ -1450,6 +1465,19 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
}
if (vmx->host_state.fs_reload_needed)
loadsegment(fs, vmx->host_state.fs_sel);
+#ifdef CONFIG_X86_64
+ if (unlikely(vmx->host_state.ds_sel | vmx->host_state.es_sel)) {
+ loadsegment(ds, vmx->host_state.ds_sel);
+ loadsegment(es, vmx->host_state.es_sel);
+ }
+#else
+ /*
+ * The sysexit path does not restore ds/es, so we must set them to
+ * a reasonable value ourselves.
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
reload_tss();
#ifdef CONFIG_X86_64
wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
@@ -3633,8 +3661,18 @@ static void vmx_set_constant_host_state(void)
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
+#ifdef CONFIG_X86_64
+ /*
+ * Load null selectors, so we can avoid reloading them in
+ * __vmx_load_host_state(), in case userspace uses the null selectors
+ * too (the expected case).
+ */
+ vmcs_write16(HOST_DS_SELECTOR, 0);
+ vmcs_write16(HOST_ES_SELECTOR, 0);
+#else
vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS); /* 22.2.4 */
+#endif
vmcs_write16(HOST_SS_SELECTOR, __KERNEL_DS); /* 22.2.4 */
vmcs_write16(HOST_TR_SELECTOR, GDT_ENTRY_TSS*8); /* 22.2.4 */
@@ -6256,7 +6294,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
}
}
- asm("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
vmx->loaded_vmcs->launched = 1;
vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
@@ -6343,7 +6380,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
return &vmx->vcpu;
free_vmcs:
- free_vmcs(vmx->loaded_vmcs->vmcs);
+ free_loaded_vmcs(vmx->loaded_vmcs);
free_msrs:
kfree(vmx->guest_msrs);
uninit_vcpu:
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 185a2b823a2..be6d54929fa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_ASYNC_PF:
case KVM_CAP_GET_TSC_KHZ:
case KVM_CAP_PCI_2_3:
+ case KVM_CAP_KVMCLOCK_CTRL:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
@@ -2597,6 +2598,23 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
return r;
}
+/*
+ * kvm_set_guest_paused() indicates to the guest kernel that it has been
+ * stopped by the hypervisor. This function will be called from the host only.
+ * EINVAL is returned when the host attempts to set the flag for a guest that
+ * does not support pv clocks.
+ */
+static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
+{
+ struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock;
+ if (!vcpu->arch.time_page)
+ return -EINVAL;
+ src->flags |= PVCLOCK_GUEST_STOPPED;
+ mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+ return 0;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2873,6 +2891,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = vcpu->arch.virtual_tsc_khz;
goto out;
}
+ case KVM_KVMCLOCK_CTRL: {
+ r = kvm_set_guest_paused(vcpu);
+ goto out;
+ }
default:
r = -EINVAL;
}
@@ -3045,57 +3067,32 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
}
/**
- * write_protect_slot - write protect a slot for dirty logging
- * @kvm: the kvm instance
- * @memslot: the slot we protect
- * @dirty_bitmap: the bitmap indicating which pages are dirty
- * @nr_dirty_pages: the number of dirty pages
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
*
- * We have two ways to find all sptes to protect:
- * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and
- * checks ones that have a spte mapping a page in the slot.
- * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap.
+ * We need to keep it in mind that VCPU threads can write to the bitmap
+ * concurrently. So, to avoid losing data, we keep the following order for
+ * each bit:
*
- * Generally speaking, if there are not so many dirty pages compared to the
- * number of shadow pages, we should use the latter.
+ * 1. Take a snapshot of the bit and clear it if needed.
+ * 2. Write protect the corresponding page.
+ * 3. Flush TLB's if needed.
+ * 4. Copy the snapshot to the userspace.
*
- * Note that letting others write into a page marked dirty in the old bitmap
- * by using the remaining tlb entry is not a problem. That page will become
- * write protected again when we flush the tlb and then be reported dirty to
- * the user space by copying the old bitmap.
- */
-static void write_protect_slot(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
- unsigned long *dirty_bitmap,
- unsigned long nr_dirty_pages)
-{
- spin_lock(&kvm->mmu_lock);
-
- /* Not many dirty pages compared to # of shadow pages. */
- if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) {
- unsigned long gfn_offset;
-
- for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) {
- unsigned long gfn = memslot->base_gfn + gfn_offset;
-
- kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
- }
- kvm_flush_remote_tlbs(kvm);
- } else
- kvm_mmu_slot_remove_write_access(kvm, memslot->id);
-
- spin_unlock(&kvm->mmu_lock);
-}
-
-/*
- * Get (and clear) the dirty memory log for a memory slot.
+ * Between 2 and 3, the guest may write to the page using the remaining TLB
+ * entry. This is not a problem because the page will be reported dirty at
+ * step 4 using the snapshot taken before and step 3 ensures that successive
+ * writes will be logged for the next call.
*/
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
- struct kvm_dirty_log *log)
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
int r;
struct kvm_memory_slot *memslot;
- unsigned long n, nr_dirty_pages;
+ unsigned long n, i;
+ unsigned long *dirty_bitmap;
+ unsigned long *dirty_bitmap_buffer;
+ bool is_dirty = false;
mutex_lock(&kvm->slots_lock);
@@ -3104,49 +3101,42 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
goto out;
memslot = id_to_memslot(kvm->memslots, log->slot);
+
+ dirty_bitmap = memslot->dirty_bitmap;
r = -ENOENT;
- if (!memslot->dirty_bitmap)
+ if (!dirty_bitmap)
goto out;
n = kvm_dirty_bitmap_bytes(memslot);
- nr_dirty_pages = memslot->nr_dirty_pages;
- /* If nothing is dirty, don't bother messing with page tables. */
- if (nr_dirty_pages) {
- struct kvm_memslots *slots, *old_slots;
- unsigned long *dirty_bitmap, *dirty_bitmap_head;
+ dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long);
+ memset(dirty_bitmap_buffer, 0, n);
- dirty_bitmap = memslot->dirty_bitmap;
- dirty_bitmap_head = memslot->dirty_bitmap_head;
- if (dirty_bitmap == dirty_bitmap_head)
- dirty_bitmap_head += n / sizeof(long);
- memset(dirty_bitmap_head, 0, n);
+ spin_lock(&kvm->mmu_lock);
- r = -ENOMEM;
- slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL);
- if (!slots)
- goto out;
+ for (i = 0; i < n / sizeof(long); i++) {
+ unsigned long mask;
+ gfn_t offset;
- memslot = id_to_memslot(slots, log->slot);
- memslot->nr_dirty_pages = 0;
- memslot->dirty_bitmap = dirty_bitmap_head;
- update_memslots(slots, NULL);
+ if (!dirty_bitmap[i])
+ continue;
- old_slots = kvm->memslots;
- rcu_assign_pointer(kvm->memslots, slots);
- synchronize_srcu_expedited(&kvm->srcu);
- kfree(old_slots);
+ is_dirty = true;
- write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages);
+ mask = xchg(&dirty_bitmap[i], 0);
+ dirty_bitmap_buffer[i] = mask;
- r = -EFAULT;
- if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
- goto out;
- } else {
- r = -EFAULT;
- if (clear_user(log->dirty_bitmap, n))
- goto out;
+ offset = i * BITS_PER_LONG;
+ kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
}
+ if (is_dirty)
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+
+ r = -EFAULT;
+ if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
+ goto out;
r = 0;
out:
@@ -3728,9 +3718,8 @@ struct read_write_emulator_ops {
static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
{
if (vcpu->mmio_read_completed) {
- memcpy(val, vcpu->mmio_data, bytes);
trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
- vcpu->mmio_phys_addr, *(u64 *)val);
+ vcpu->mmio_fragments[0].gpa, *(u64 *)val);
vcpu->mmio_read_completed = 0;
return 1;
}
@@ -3766,8 +3755,9 @@ static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
void *val, int bytes)
{
- memcpy(vcpu->mmio_data, val, bytes);
- memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8);
+ struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
+
+ memcpy(vcpu->run->mmio.data, frag->data, frag->len);
return X86EMUL_CONTINUE;
}
@@ -3794,10 +3784,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
gpa_t gpa;
int handled, ret;
bool write = ops->write;
-
- if (ops->read_write_prepare &&
- ops->read_write_prepare(vcpu, val, bytes))
- return X86EMUL_CONTINUE;
+ struct kvm_mmio_fragment *frag;
ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
@@ -3823,15 +3810,19 @@ mmio:
bytes -= handled;
val += handled;
- vcpu->mmio_needed = 1;
- vcpu->run->exit_reason = KVM_EXIT_MMIO;
- vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
- vcpu->mmio_size = bytes;
- vcpu->run->mmio.len = min(vcpu->mmio_size, 8);
- vcpu->run->mmio.is_write = vcpu->mmio_is_write = write;
- vcpu->mmio_index = 0;
+ while (bytes) {
+ unsigned now = min(bytes, 8U);
- return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
+ frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+ frag->gpa = gpa;
+ frag->data = val;
+ frag->len = now;
+
+ gpa += now;
+ val += now;
+ bytes -= now;
+ }
+ return X86EMUL_CONTINUE;
}
int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
@@ -3840,10 +3831,18 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
struct read_write_emulator_ops *ops)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+ gpa_t gpa;
+ int rc;
+
+ if (ops->read_write_prepare &&
+ ops->read_write_prepare(vcpu, val, bytes))
+ return X86EMUL_CONTINUE;
+
+ vcpu->mmio_nr_fragments = 0;
/* Crossing a page boundary? */
if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
- int rc, now;
+ int now;
now = -addr & ~PAGE_MASK;
rc = emulator_read_write_onepage(addr, val, now, exception,
@@ -3856,8 +3855,25 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
bytes -= now;
}
- return emulator_read_write_onepage(addr, val, bytes, exception,
- vcpu, ops);
+ rc = emulator_read_write_onepage(addr, val, bytes, exception,
+ vcpu, ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ if (!vcpu->mmio_nr_fragments)
+ return rc;
+
+ gpa = vcpu->mmio_fragments[0].gpa;
+
+ vcpu->mmio_needed = 1;
+ vcpu->mmio_cur_fragment = 0;
+
+ vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+ vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
+ vcpu->run->exit_reason = KVM_EXIT_MMIO;
+ vcpu->run->mmio.phys_addr = gpa;
+
+ return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
}
static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
@@ -5263,10 +5279,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_deliver_pmi(vcpu);
}
- r = kvm_mmu_reload(vcpu);
- if (unlikely(r))
- goto out;
-
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
inject_pending_event(vcpu);
@@ -5282,6 +5294,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
}
}
+ r = kvm_mmu_reload(vcpu);
+ if (unlikely(r)) {
+ kvm_x86_ops->cancel_injection(vcpu);
+ goto out;
+ }
+
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
@@ -5456,33 +5474,55 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
return r;
}
+/*
+ * Implements the following, as a state machine:
+ *
+ * read:
+ * for each fragment
+ * write gpa, len
+ * exit
+ * copy data
+ * execute insn
+ *
+ * write:
+ * for each fragment
+ * write gpa, len
+ * copy data
+ * exit
+ */
static int complete_mmio(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
+ struct kvm_mmio_fragment *frag;
int r;
if (!(vcpu->arch.pio.count || vcpu->mmio_needed))
return 1;
if (vcpu->mmio_needed) {
- vcpu->mmio_needed = 0;
+ /* Complete previous fragment */
+ frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
if (!vcpu->mmio_is_write)
- memcpy(vcpu->mmio_data + vcpu->mmio_index,
- run->mmio.data, 8);
- vcpu->mmio_index += 8;
- if (vcpu->mmio_index < vcpu->mmio_size) {
- run->exit_reason = KVM_EXIT_MMIO;
- run->mmio.phys_addr = vcpu->mmio_phys_addr + vcpu->mmio_index;
- memcpy(run->mmio.data, vcpu->mmio_data + vcpu->mmio_index, 8);
- run->mmio.len = min(vcpu->mmio_size - vcpu->mmio_index, 8);
- run->mmio.is_write = vcpu->mmio_is_write;
- vcpu->mmio_needed = 1;
- return 0;
+ memcpy(frag->data, run->mmio.data, frag->len);
+ if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+ vcpu->mmio_needed = 0;
+ if (vcpu->mmio_is_write)
+ return 1;
+ vcpu->mmio_read_completed = 1;
+ goto done;
}
+ /* Initiate next fragment */
+ ++frag;
+ run->exit_reason = KVM_EXIT_MMIO;
+ run->mmio.phys_addr = frag->gpa;
if (vcpu->mmio_is_write)
- return 1;
- vcpu->mmio_read_completed = 1;
+ memcpy(run->mmio.data, frag->data, frag->len);
+ run->mmio.len = frag->len;
+ run->mmio.is_write = vcpu->mmio_is_write;
+ return 0;
+
}
+done:
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6399,21 +6439,9 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
kvm_cpu_has_interrupt(vcpu));
}
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
- int me;
- int cpu = vcpu->cpu;
-
- if (waitqueue_active(&vcpu->wq)) {
- wake_up_interruptible(&vcpu->wq);
- ++vcpu->stat.halt_wakeup;
- }
-
- me = get_cpu();
- if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
- if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE)
- smp_send_reschedule(cpu);
- put_cpu();
+ return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index cb80c293cdd..3d1134ddb88 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -64,7 +64,7 @@ static inline int is_pse(struct kvm_vcpu *vcpu)
static inline int is_paging(struct kvm_vcpu *vcpu)
{
- return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
+ return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG));
}
static inline u32 bit(int bitno)
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 2e4e4b02c37..f61ee67ec00 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -43,100 +43,3 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
return len;
}
EXPORT_SYMBOL_GPL(copy_from_user_nmi);
-
-/*
- * Do a strncpy, return length of string without final '\0'.
- * 'count' is the user-supplied count (return 'count' if we
- * hit it), 'max' is the address space maximum (and we return
- * -EFAULT if we hit it).
- */
-static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
-{
- long res = 0;
-
- /*
- * Truncate 'max' to the user-specified limit, so that
- * we only have one limit we need to check in the loop
- */
- if (max > count)
- max = count;
-
- while (max >= sizeof(unsigned long)) {
- unsigned long c, mask;
-
- /* Fall back to byte-at-a-time if we get a page fault */
- if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
- break;
- mask = has_zero(c);
- if (mask) {
- mask = (mask - 1) & ~mask;
- mask >>= 7;
- *(unsigned long *)(dst+res) = c & mask;
- return res + count_masked_bytes(mask);
- }
- *(unsigned long *)(dst+res) = c;
- res += sizeof(unsigned long);
- max -= sizeof(unsigned long);
- }
-
- while (max) {
- char c;
-
- if (unlikely(__get_user(c,src+res)))
- return -EFAULT;
- dst[res] = c;
- if (!c)
- return res;
- res++;
- max--;
- }
-
- /*
- * Uhhuh. We hit 'max'. But was that the user-specified maximum
- * too? If so, that's ok - we got as much as the user asked for.
- */
- if (res >= count)
- return res;
-
- /*
- * Nope: we hit the address space limit, and we still had more
- * characters the caller would have wanted. That's an EFAULT.
- */
- return -EFAULT;
-}
-
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst: Destination address, in kernel space. This buffer must be at
- * least @count bytes long.
- * @src: Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
- unsigned long max_addr, src_addr;
-
- if (unlikely(count <= 0))
- return 0;
-
- max_addr = current_thread_info()->addr_limit.seg;
- src_addr = (unsigned long)src;
- if (likely(src_addr < max_addr)) {
- unsigned long max = max_addr - src_addr;
- return do_strncpy_from_user(dst, src, count, max);
- }
- return -EFAULT;
-}
-EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 883b216c60b..1781b2f950e 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -95,47 +95,6 @@ __clear_user(void __user *to, unsigned long n)
}
EXPORT_SYMBOL(__clear_user);
-/**
- * strnlen_user: - Get the size of a string in user space.
- * @s: The string to measure.
- * @n: The maximum valid length
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- * If the string is too long, returns a value greater than @n.
- */
-long strnlen_user(const char __user *s, long n)
-{
- unsigned long mask = -__addr_ok(s);
- unsigned long res, tmp;
-
- might_fault();
-
- __asm__ __volatile__(
- " testl %0, %0\n"
- " jz 3f\n"
- " andl %0,%%ecx\n"
- "0: repne; scasb\n"
- " setne %%al\n"
- " subl %%ecx,%0\n"
- " addl %0,%%eax\n"
- "1:\n"
- ".section .fixup,\"ax\"\n"
- "2: xorl %%eax,%%eax\n"
- " jmp 1b\n"
- "3: movb $1,%%al\n"
- " jmp 1b\n"
- ".previous\n"
- _ASM_EXTABLE(0b,2b)
- :"=&r" (n), "=&D" (s), "=&a" (res), "=&c" (tmp)
- :"0" (n), "1" (s), "2" (0), "3" (mask)
- :"cc");
- return res & mask;
-}
-EXPORT_SYMBOL(strnlen_user);
-
#ifdef CONFIG_X86_INTEL_USERCOPY
static unsigned long
__copy_user_intel(void __user *to, const void *from, unsigned long size)
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 0d0326f388c..e5b130bc2d0 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -52,54 +52,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
}
EXPORT_SYMBOL(clear_user);
-/*
- * Return the size of a string (including the ending 0)
- *
- * Return 0 on exception, a value greater than N if too long
- */
-
-long __strnlen_user(const char __user *s, long n)
-{
- long res = 0;
- char c;
-
- while (1) {
- if (res>n)
- return n+1;
- if (__get_user(c, s))
- return 0;
- if (!c)
- return res+1;
- res++;
- s++;
- }
-}
-EXPORT_SYMBOL(__strnlen_user);
-
-long strnlen_user(const char __user *s, long n)
-{
- if (!access_ok(VERIFY_READ, s, 1))
- return 0;
- return __strnlen_user(s, n);
-}
-EXPORT_SYMBOL(strnlen_user);
-
-long strlen_user(const char __user *s)
-{
- long res = 0;
- char c;
-
- for (;;) {
- if (get_user(c, s))
- return 0;
- if (!c)
- return res+1;
- res++;
- s++;
- }
-}
-EXPORT_SYMBOL(strlen_user);
-
unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len)
{
if (access_ok(VERIFY_WRITE, to, len) && access_ok(VERIFY_READ, from, len)) {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 319b6f2fb8b..97141c26a13 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -84,8 +84,9 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
pgt_buf_end = pgt_buf_start;
pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
- printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
- end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
+ printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
+ end - 1, pgt_buf_start << PAGE_SHIFT,
+ (pgt_buf_top << PAGE_SHIFT) - 1);
}
void __init native_pagetable_reserve(u64 start, u64 end)
@@ -132,7 +133,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
int nr_range, i;
int use_pse, use_gbpages;
- printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
+ printk(KERN_INFO "init_memory_mapping: [mem %#010lx-%#010lx]\n",
+ start, end - 1);
#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
/*
@@ -251,8 +253,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
}
for (i = 0; i < nr_range; i++)
- printk(KERN_DEBUG " %010lx - %010lx page %s\n",
- mr[i].start, mr[i].end,
+ printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
+ mr[i].start, mr[i].end - 1,
(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
(mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
@@ -350,8 +352,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
* create a kernel page fault:
*/
#ifdef CONFIG_DEBUG_PAGEALLOC
- printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
- begin, end);
+ printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
+ begin, end - 1);
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
/*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 19d3fa08b11..2d125be1bae 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -141,8 +141,8 @@ static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
/* whine about and ignore invalid blks */
if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
- pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
- nid, start, end);
+ pr_warning("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start, end - 1);
return 0;
}
@@ -210,8 +210,8 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
start = roundup(start, ZONE_ALIGN);
- printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
- nid, start, end);
+ printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+ nid, start, end - 1);
/*
* Allocate node data. Try remap allocator first, node-local
@@ -232,7 +232,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
}
/* report and initialize */
- printk(KERN_INFO " NODE_DATA [%016Lx - %016Lx]%s\n",
+ printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]%s\n",
nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (!remapped && tnid != nid)
@@ -291,14 +291,14 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
*/
if (bi->end > bj->start && bi->start < bj->end) {
if (bi->nid != bj->nid) {
- pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
- bi->nid, bi->start, bi->end,
- bj->nid, bj->start, bj->end);
+ pr_err("NUMA: node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
+ bi->nid, bi->start, bi->end - 1,
+ bj->nid, bj->start, bj->end - 1);
return -EINVAL;
}
- pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
- bi->nid, bi->start, bi->end,
- bj->start, bj->end);
+ pr_warning("NUMA: Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
+ bi->nid, bi->start, bi->end - 1,
+ bj->start, bj->end - 1);
}
/*
@@ -320,9 +320,9 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
}
if (k < mi->nr_blks)
continue;
- printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
- bi->nid, bi->start, bi->end, bj->start, bj->end,
- start, end);
+ printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n",
+ bi->nid, bi->start, bi->end - 1, bj->start,
+ bj->end - 1, start, end - 1);
bi->start = start;
bi->end = end;
numa_remove_memblk_from(j--, mi);
@@ -616,8 +616,8 @@ static int __init dummy_numa_init(void)
{
printk(KERN_INFO "%s\n",
numa_off ? "NUMA turned off" : "No NUMA configuration found");
- printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
- 0LLU, PFN_PHYS(max_pfn));
+ printk(KERN_INFO "Faking a node at [mem %#018Lx-%#018Lx]\n",
+ 0LLU, PFN_PHYS(max_pfn) - 1);
node_set(0, numa_nodes_parsed);
numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 871dd886817..dbbbb47260c 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -68,8 +68,8 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
numa_remove_memblk_from(phys_blk, pi);
}
- printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
- eb->start, eb->end, (eb->end - eb->start) >> 20);
+ printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
+ nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
return 0;
}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index bea6e573e02..3d68ef6d226 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -225,9 +225,8 @@ static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
page = pfn_to_page(pfn);
type = get_page_memtype(page);
if (type != -1) {
- printk(KERN_INFO "reserve_ram_pages_type failed "
- "0x%Lx-0x%Lx, track 0x%lx, req 0x%lx\n",
- start, end, type, req_type);
+ printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
+ start, end - 1, type, req_type);
if (new_type)
*new_type = type;
@@ -330,9 +329,9 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
err = rbt_memtype_check_insert(new, new_type);
if (err) {
- printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
- "track %s, req %s\n",
- start, end, cattr_name(new->type), cattr_name(req_type));
+ printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+ start, end - 1,
+ cattr_name(new->type), cattr_name(req_type));
kfree(new);
spin_unlock(&memtype_lock);
@@ -341,8 +340,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
spin_unlock(&memtype_lock);
- dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
- start, end, cattr_name(new->type), cattr_name(req_type),
+ dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
+ start, end - 1, cattr_name(new->type), cattr_name(req_type),
new_type ? cattr_name(*new_type) : "-");
return err;
@@ -376,14 +375,14 @@ int free_memtype(u64 start, u64 end)
spin_unlock(&memtype_lock);
if (!entry) {
- printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
- current->comm, current->pid, start, end);
+ printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+ current->comm, current->pid, start, end - 1);
return -EINVAL;
}
kfree(entry);
- dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
+ dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1);
return 0;
}
@@ -507,9 +506,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
while (cursor < to) {
if (!devmem_is_allowed(pfn)) {
- printk(KERN_INFO
- "Program %s tried to access /dev/mem between %Lx->%Lx.\n",
- current->comm, from, to);
+ printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n",
+ current->comm, from, to - 1);
return 0;
}
cursor += PAGE_SIZE;
@@ -570,12 +568,11 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
size;
if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
- printk(KERN_INFO
- "%s:%d ioremap_change_attr failed %s "
- "for %Lx-%Lx\n",
+ printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
+ "for [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid,
cattr_name(flags),
- base, (unsigned long long)(base + size));
+ base, (unsigned long long)(base + size-1));
return -EINVAL;
}
return 0;
@@ -607,12 +604,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
flags = lookup_memtype(paddr);
if (want_flags != flags) {
- printk(KERN_WARNING
- "%s:%d map pfn RAM range req %s for %Lx-%Lx, got %s\n",
+ printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_flags),
(unsigned long long)paddr,
- (unsigned long long)(paddr + size),
+ (unsigned long long)(paddr + size - 1),
cattr_name(flags));
*vma_prot = __pgprot((pgprot_val(*vma_prot) &
(~_PAGE_CACHE_MASK)) |
@@ -630,11 +626,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
!is_new_memtype_allowed(paddr, size, want_flags, flags)) {
free_memtype(paddr, paddr + size);
printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
- " for %Lx-%Lx, got %s\n",
+ " for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
cattr_name(want_flags),
(unsigned long long)paddr,
- (unsigned long long)(paddr + size),
+ (unsigned long long)(paddr + size - 1),
cattr_name(flags));
return -EINVAL;
}
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index efb5b4b9371..732af3a9618 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,8 +176,9 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
return;
}
- printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
- start, end);
+ printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+ node, pxm,
+ (unsigned long long) start, (unsigned long long) end - 1);
}
void __init acpi_numa_arch_fixup(void) {}
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 7415aa92791..56ab74989cf 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -64,6 +64,10 @@ static int xen_register_pirq(u32 gsi, int gsi_override, int triggering,
int shareable = 0;
char *name;
+ irq = xen_irq_from_gsi(gsi);
+ if (irq > 0)
+ return irq;
+
if (set_pirq)
pirq = gsi;
diff --git a/arch/x86/realmode/Makefile b/arch/x86/realmode/Makefile
new file mode 100644
index 00000000000..94f7fbe97b0
--- /dev/null
+++ b/arch/x86/realmode/Makefile
@@ -0,0 +1,18 @@
+#
+# arch/x86/realmode/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+#
+
+subdir- := rm
+
+obj-y += init.o
+obj-y += rmpiggy.o
+
+$(obj)/rmpiggy.o: $(obj)/rm/realmode.bin
+
+$(obj)/rm/realmode.bin: FORCE
+ $(Q)$(MAKE) $(build)=$(obj)/rm $@
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
new file mode 100644
index 00000000000..cbca565af5b
--- /dev/null
+++ b/arch/x86/realmode/init.c
@@ -0,0 +1,115 @@
+#include <linux/io.h>
+#include <linux/memblock.h>
+
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <asm/realmode.h>
+
+struct real_mode_header *real_mode_header;
+u32 *trampoline_cr4_features;
+
+void __init setup_real_mode(void)
+{
+ phys_addr_t mem;
+ u16 real_mode_seg;
+ u32 *rel;
+ u32 count;
+ u32 *ptr;
+ u16 *seg;
+ int i;
+ unsigned char *base;
+ struct trampoline_header *trampoline_header;
+ size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
+#ifdef CONFIG_X86_64
+ u64 *trampoline_pgd;
+ u64 efer;
+#endif
+
+ /* Has to be in very low memory so we can execute real-mode AP code. */
+ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
+ if (!mem)
+ panic("Cannot allocate trampoline\n");
+
+ base = __va(mem);
+ memblock_reserve(mem, size);
+ real_mode_header = (struct real_mode_header *) base;
+ printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
+ base, (unsigned long long)mem, size);
+
+ memcpy(base, real_mode_blob, size);
+
+ real_mode_seg = __pa(base) >> 4;
+ rel = (u32 *) real_mode_relocs;
+
+ /* 16-bit segment relocations. */
+ count = rel[0];
+ rel = &rel[1];
+ for (i = 0; i < count; i++) {
+ seg = (u16 *) (base + rel[i]);
+ *seg = real_mode_seg;
+ }
+
+ /* 32-bit linear relocations. */
+ count = rel[i];
+ rel = &rel[i + 1];
+ for (i = 0; i < count; i++) {
+ ptr = (u32 *) (base + rel[i]);
+ *ptr += __pa(base);
+ }
+
+ /* Must be perfomed *after* relocation. */
+ trampoline_header = (struct trampoline_header *)
+ __va(real_mode_header->trampoline_header);
+
+#ifdef CONFIG_X86_32
+ trampoline_header->start = __pa(startup_32_smp);
+ trampoline_header->gdt_limit = __BOOT_DS + 7;
+ trampoline_header->gdt_base = __pa(boot_gdt);
+#else
+ /*
+ * Some AMD processors will #GP(0) if EFER.LMA is set in WRMSR
+ * so we need to mask it out.
+ */
+ rdmsrl(MSR_EFER, efer);
+ trampoline_header->efer = efer & ~EFER_LMA;
+
+ trampoline_header->start = (u64) secondary_startup_64;
+ trampoline_cr4_features = &trampoline_header->cr4;
+ *trampoline_cr4_features = read_cr4();
+
+ trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd);
+ trampoline_pgd[0] = __pa(level3_ident_pgt) + _KERNPG_TABLE;
+ trampoline_pgd[511] = __pa(level3_kernel_pgt) + _KERNPG_TABLE;
+#endif
+}
+
+/*
+ * set_real_mode_permissions() gets called very early, to guarantee the
+ * availability of low memory. This is before the proper kernel page
+ * tables are set up, so we cannot set page permissions in that
+ * function. Thus, we use an arch_initcall instead.
+ */
+static int __init set_real_mode_permissions(void)
+{
+ unsigned char *base = (unsigned char *) real_mode_header;
+ size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob);
+
+ size_t ro_size =
+ PAGE_ALIGN(real_mode_header->ro_end) -
+ __pa(base);
+
+ size_t text_size =
+ PAGE_ALIGN(real_mode_header->ro_end) -
+ real_mode_header->text_start;
+
+ unsigned long text_start =
+ (unsigned long) __va(real_mode_header->text_start);
+
+ set_memory_nx((unsigned long) base, size >> PAGE_SHIFT);
+ set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT);
+ set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT);
+
+ return 0;
+}
+
+arch_initcall(set_real_mode_permissions);
diff --git a/arch/x86/realmode/rm/.gitignore b/arch/x86/realmode/rm/.gitignore
new file mode 100644
index 00000000000..b6ed3a2555c
--- /dev/null
+++ b/arch/x86/realmode/rm/.gitignore
@@ -0,0 +1,3 @@
+pasyms.h
+realmode.lds
+realmode.relocs
diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile
new file mode 100644
index 00000000000..5b84a2d3088
--- /dev/null
+++ b/arch/x86/realmode/rm/Makefile
@@ -0,0 +1,82 @@
+#
+# arch/x86/realmode/Makefile
+#
+# This file is subject to the terms and conditions of the GNU General Public
+# License. See the file "COPYING" in the main directory of this archive
+# for more details.
+#
+#
+
+always := realmode.bin realmode.relocs
+
+wakeup-objs := wakeup_asm.o wakemain.o video-mode.o
+wakeup-objs += copy.o bioscall.o regs.o
+# The link order of the video-*.o modules can matter. In particular,
+# video-vga.o *must* be listed first, followed by video-vesa.o.
+# Hardware-specific drivers should follow in the order they should be
+# probed, and video-bios.o should typically be last.
+wakeup-objs += video-vga.o
+wakeup-objs += video-vesa.o
+wakeup-objs += video-bios.o
+
+realmode-y += header.o
+realmode-y += trampoline_$(BITS).o
+realmode-y += stack.o
+realmode-$(CONFIG_X86_32) += reboot_32.o
+realmode-$(CONFIG_ACPI_SLEEP) += $(wakeup-objs)
+
+targets += $(realmode-y)
+
+REALMODE_OBJS = $(addprefix $(obj)/,$(realmode-y))
+
+sed-pasyms := -n -r -e 's/^([0-9a-fA-F]+) [ABCDGRSTVW] (.+)$$/pa_\2 = \2;/p'
+
+quiet_cmd_pasyms = PASYMS $@
+ cmd_pasyms = $(NM) $(filter-out FORCE,$^) | \
+ sed $(sed-pasyms) | sort | uniq > $@
+
+targets += pasyms.h
+$(obj)/pasyms.h: $(REALMODE_OBJS) FORCE
+ $(call if_changed,pasyms)
+
+targets += realmode.lds
+$(obj)/realmode.lds: $(obj)/pasyms.h
+
+LDFLAGS_realmode.elf := --emit-relocs -T
+CPPFLAGS_realmode.lds += -P -C -I$(obj)
+
+targets += realmode.elf
+$(obj)/realmode.elf: $(obj)/realmode.lds $(REALMODE_OBJS) FORCE
+ $(call if_changed,ld)
+
+OBJCOPYFLAGS_realmode.bin := -O binary
+
+targets += realmode.bin
+$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs
+ $(call if_changed,objcopy)
+
+quiet_cmd_relocs = RELOCS $@
+ cmd_relocs = arch/x86/tools/relocs --realmode $< > $@
+
+targets += realmode.relocs
+$(obj)/realmode.relocs: $(obj)/realmode.elf FORCE
+ $(call if_changed,relocs)
+
+# ---------------------------------------------------------------------------
+
+# How to compile the 16-bit code. Note we always compile for -march=i386,
+# that way we can complain to the user if the CPU is insufficient.
+KBUILD_CFLAGS := $(LINUXINCLUDE) -m32 -g -Os -D_SETUP -D__KERNEL__ -D_WAKEUP \
+ -I$(srctree)/arch/x86/boot \
+ -DDISABLE_BRANCH_PROFILING \
+ -Wall -Wstrict-prototypes \
+ -march=i386 -mregparm=3 \
+ -include $(srctree)/$(src)/../../boot/code16gcc.h \
+ -fno-strict-aliasing -fomit-frame-pointer \
+ $(call cc-option, -ffreestanding) \
+ $(call cc-option, -fno-toplevel-reorder,\
+ $(call cc-option, -fno-unit-at-a-time)) \
+ $(call cc-option, -fno-stack-protector) \
+ $(call cc-option, -mpreferred-stack-boundary=2)
+KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
diff --git a/arch/x86/realmode/rm/bioscall.S b/arch/x86/realmode/rm/bioscall.S
new file mode 100644
index 00000000000..16162d19791
--- /dev/null
+++ b/arch/x86/realmode/rm/bioscall.S
@@ -0,0 +1 @@
+#include "../../boot/bioscall.S"
diff --git a/arch/x86/realmode/rm/copy.S b/arch/x86/realmode/rm/copy.S
new file mode 100644
index 00000000000..b785e6f38fd
--- /dev/null
+++ b/arch/x86/realmode/rm/copy.S
@@ -0,0 +1 @@
+#include "../../boot/copy.S"
diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S
new file mode 100644
index 00000000000..fadf48378ad
--- /dev/null
+++ b/arch/x86/realmode/rm/header.S
@@ -0,0 +1,41 @@
+/*
+ * Real-mode blob header; this should match realmode.h and be
+ * readonly; for mutable data instead add pointers into the .data
+ * or .bss sections as appropriate.
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+#include "realmode.h"
+
+ .section ".header", "a"
+
+ .balign 16
+GLOBAL(real_mode_header)
+ .long pa_text_start
+ .long pa_ro_end
+ /* SMP trampoline */
+ .long pa_trampoline_start
+ .long pa_trampoline_status
+ .long pa_trampoline_header
+#ifdef CONFIG_X86_64
+ .long pa_trampoline_pgd;
+#endif
+ /* ACPI S3 wakeup */
+#ifdef CONFIG_ACPI_SLEEP
+ .long pa_wakeup_start
+ .long pa_wakeup_header
+#endif
+ /* APM/BIOS reboot */
+#ifdef CONFIG_X86_32
+ .long pa_machine_real_restart_asm
+#endif
+END(real_mode_header)
+
+ /* End signature, used to verify integrity */
+ .section ".signature","a"
+ .balign 4
+GLOBAL(end_signature)
+ .long REALMODE_END_SIGNATURE
+END(end_signature)
diff --git a/arch/x86/realmode/rm/realmode.h b/arch/x86/realmode/rm/realmode.h
new file mode 100644
index 00000000000..d74cff6350e
--- /dev/null
+++ b/arch/x86/realmode/rm/realmode.h
@@ -0,0 +1,21 @@
+#ifndef ARCH_X86_REALMODE_RM_REALMODE_H
+#define ARCH_X86_REALMODE_RM_REALMODE_H
+
+#ifdef __ASSEMBLY__
+
+/*
+ * 16-bit ljmpw to the real_mode_seg
+ *
+ * This must be open-coded since gas will choke on using a
+ * relocatable symbol for the segment portion.
+ */
+#define LJMPW_RM(to) .byte 0xea ; .word (to), real_mode_seg
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Signature at the end of the realmode region
+ */
+#define REALMODE_END_SIGNATURE 0x65a22c82
+
+#endif /* ARCH_X86_REALMODE_RM_REALMODE_H */
diff --git a/arch/x86/realmode/rm/realmode.lds.S b/arch/x86/realmode/rm/realmode.lds.S
new file mode 100644
index 00000000000..86b2e8d6b1f
--- /dev/null
+++ b/arch/x86/realmode/rm/realmode.lds.S
@@ -0,0 +1,76 @@
+/*
+ * realmode.lds.S
+ *
+ * Linker script for the real-mode code
+ */
+
+#include <asm/page_types.h>
+
+#undef i386
+
+OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
+OUTPUT_ARCH(i386)
+
+SECTIONS
+{
+ real_mode_seg = 0;
+
+ . = 0;
+ .header : {
+ pa_real_mode_base = .;
+ *(.header)
+ }
+
+ . = ALIGN(4);
+ .rodata : {
+ *(.rodata)
+ *(.rodata.*)
+ . = ALIGN(16);
+ video_cards = .;
+ *(.videocards)
+ video_cards_end = .;
+ }
+
+ . = ALIGN(PAGE_SIZE);
+ pa_text_start = .;
+ .text : {
+ *(.text)
+ *(.text.*)
+ }
+
+ .text32 : {
+ *(.text32)
+ *(.text32.*)
+ }
+
+ .text64 : {
+ *(.text64)
+ *(.text64.*)
+ }
+ pa_ro_end = .;
+
+ . = ALIGN(PAGE_SIZE);
+ .data : {
+ *(.data)
+ *(.data.*)
+ }
+
+ . = ALIGN(128);
+ .bss : {
+ *(.bss*)
+ }
+
+ /* End signature for integrity checking */
+ . = ALIGN(4);
+ .signature : {
+ *(.signature)
+ }
+
+ /DISCARD/ : {
+ *(.note*)
+ *(.debug*)
+ *(.eh_frame*)
+ }
+
+#include "pasyms.h"
+}
diff --git a/arch/x86/kernel/reboot_32.S b/arch/x86/realmode/rm/reboot_32.S
index 1d5c46df0d7..114044876b3 100644
--- a/arch/x86/kernel/reboot_32.S
+++ b/arch/x86/realmode/rm/reboot_32.S
@@ -2,6 +2,7 @@
#include <linux/init.h>
#include <asm/segment.h>
#include <asm/page_types.h>
+#include "realmode.h"
/*
* The following code and data reboots the machine by switching to real
@@ -13,34 +14,20 @@
*
* This code is called with the restart type (0 = BIOS, 1 = APM) in %eax.
*/
- .section ".x86_trampoline","a"
- .balign 16
+ .section ".text32", "ax"
.code32
-ENTRY(machine_real_restart_asm)
-r_base = .
- /* Get our own relocated address */
- call 1f
-1: popl %ebx
- subl $(1b - r_base), %ebx
-
- /* Compute the equivalent real-mode segment */
- movl %ebx, %ecx
- shrl $4, %ecx
-
- /* Patch post-real-mode segment jump */
- movw (dispatch_table - r_base)(%ebx,%eax,2),%ax
- movw %ax, (101f - r_base)(%ebx)
- movw %cx, (102f - r_base)(%ebx)
+ .balign 16
+ENTRY(machine_real_restart_asm)
/* Set up the IDT for real mode. */
- lidtl (machine_real_restart_idt - r_base)(%ebx)
+ lidtl pa_machine_real_restart_idt
/*
* Set up a GDT from which we can load segment descriptors for real
* mode. The GDT is not used in real mode; it is just needed here to
* prepare the descriptors.
*/
- lgdtl (machine_real_restart_gdt - r_base)(%ebx)
+ lgdtl pa_machine_real_restart_gdt
/*
* Load the data segment registers with 16-bit compatible values
@@ -51,7 +38,7 @@ r_base = .
movl %ecx, %fs
movl %ecx, %gs
movl %ecx, %ss
- ljmpl $8, $1f - r_base
+ ljmpw $8, $1f
/*
* This is 16-bit protected mode code to disable paging and the cache,
@@ -76,27 +63,29 @@ r_base = .
*
* Most of this work is probably excessive, but it is what is tested.
*/
+ .text
.code16
+
+ .balign 16
+machine_real_restart_asm16:
1:
xorl %ecx, %ecx
- movl %cr0, %eax
- andl $0x00000011, %eax
- orl $0x60000000, %eax
- movl %eax, %cr0
+ movl %cr0, %edx
+ andl $0x00000011, %edx
+ orl $0x60000000, %edx
+ movl %edx, %cr0
movl %ecx, %cr3
movl %cr0, %edx
- andl $0x60000000, %edx /* If no cache bits -> no wbinvd */
+ testl $0x60000000, %edx /* If no cache bits -> no wbinvd */
jz 2f
wbinvd
2:
- andb $0x10, %al
- movl %eax, %cr0
- .byte 0xea /* ljmpw */
-101: .word 0 /* Offset */
-102: .word 0 /* Segment */
-
-bios:
- ljmpw $0xf000, $0xfff0
+ andb $0x10, %dl
+ movl %edx, %cr0
+ LJMPW_RM(3f)
+3:
+ andw %ax, %ax
+ jz bios
apm:
movw $0x1000, %ax
@@ -106,26 +95,34 @@ apm:
movw $0x0001, %bx
movw $0x0003, %cx
int $0x15
+ /* This should never return... */
-END(machine_real_restart_asm)
+bios:
+ ljmpw $0xf000, $0xfff0
- .balign 16
- /* These must match <asm/reboot.h */
-dispatch_table:
- .word bios - r_base
- .word apm - r_base
-END(dispatch_table)
+ .section ".rodata", "a"
- .balign 16
-machine_real_restart_idt:
+ .balign 16
+GLOBAL(machine_real_restart_idt)
.word 0xffff /* Length - real mode default value */
.long 0 /* Base - real mode default value */
END(machine_real_restart_idt)
- .balign 16
-ENTRY(machine_real_restart_gdt)
- .quad 0 /* Self-pointer, filled in by PM code */
- .quad 0 /* 16-bit code segment, filled in by PM code */
+ .balign 16
+GLOBAL(machine_real_restart_gdt)
+ /* Self-pointer */
+ .word 0xffff /* Length - real mode default value */
+ .long pa_machine_real_restart_gdt
+ .word 0
+
+ /*
+ * 16-bit code segment pointing to real_mode_seg
+ * Selector value 8
+ */
+ .word 0xffff /* Limit */
+ .long 0x9b000000 + pa_real_mode_base
+ .word 0
+
/*
* 16-bit data segment with the selector value 16 = 0x10 and
* base value 0x100; since this is consistent with real mode
diff --git a/arch/x86/realmode/rm/regs.c b/arch/x86/realmode/rm/regs.c
new file mode 100644
index 00000000000..fbb15b9f9ca
--- /dev/null
+++ b/arch/x86/realmode/rm/regs.c
@@ -0,0 +1 @@
+#include "../../boot/regs.c"
diff --git a/arch/x86/realmode/rm/stack.S b/arch/x86/realmode/rm/stack.S
new file mode 100644
index 00000000000..867ae87adfa
--- /dev/null
+++ b/arch/x86/realmode/rm/stack.S
@@ -0,0 +1,19 @@
+/*
+ * Common heap and stack allocations
+ */
+
+#include <linux/linkage.h>
+
+ .data
+GLOBAL(HEAP)
+ .long rm_heap
+GLOBAL(heap_end)
+ .long rm_stack
+
+ .bss
+ .balign 16
+GLOBAL(rm_heap)
+ .space 2048
+GLOBAL(rm_stack)
+ .space 2048
+GLOBAL(rm_stack_end)
diff --git a/arch/x86/realmode/rm/trampoline_32.S b/arch/x86/realmode/rm/trampoline_32.S
new file mode 100644
index 00000000000..c1b2791183e
--- /dev/null
+++ b/arch/x86/realmode/rm/trampoline_32.S
@@ -0,0 +1,74 @@
+/*
+ *
+ * Trampoline.S Derived from Setup.S by Linus Torvalds
+ *
+ * 4 Jan 1997 Michael Chastain: changed to gnu as.
+ *
+ * This is only used for booting secondary CPUs in SMP machine
+ *
+ * Entry: CS:IP point to the start of our code, we are
+ * in real mode with no stack, but the rest of the
+ * trampoline page to make our stack and everything else
+ * is a mystery.
+ *
+ * We jump into arch/x86/kernel/head_32.S.
+ *
+ * On entry to trampoline_start, the processor is in real mode
+ * with 16-bit addressing and 16-bit data. CS has some value
+ * and IP is zero. Thus, we load CS to the physical segment
+ * of the real mode code before doing anything further.
+ */
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/segment.h>
+#include <asm/page_types.h>
+#include "realmode.h"
+
+ .text
+ .code16
+
+ .balign PAGE_SIZE
+ENTRY(trampoline_start)
+ wbinvd # Needed for NUMA-Q should be harmless for others
+
+ LJMPW_RM(1f)
+1:
+ mov %cs, %ax # Code and data in the same place
+ mov %ax, %ds
+
+ cli # We should be safe anyway
+
+ movl tr_start, %eax # where we need to go
+
+ movl $0xA5A5A5A5, trampoline_status
+ # write marker for master knows we're running
+
+ /*
+ * GDT tables in non default location kernel can be beyond 16MB and
+ * lgdt will not be able to load the address as in real mode default
+ * operand size is 16bit. Use lgdtl instead to force operand size
+ * to 32 bit.
+ */
+ lidtl tr_idt # load idt with 0, 0
+ lgdtl tr_gdt # load gdt with whatever is appropriate
+
+ movw $1, %dx # protected mode (PE) bit
+ lmsw %dx # into protected mode
+
+ ljmpl $__BOOT_CS, $pa_startup_32
+
+ .section ".text32","ax"
+ .code32
+ENTRY(startup_32) # note: also used from wakeup_asm.S
+ jmp *%eax
+
+ .bss
+ .balign 8
+GLOBAL(trampoline_header)
+ tr_start: .space 4
+ tr_gdt_pad: .space 2
+ tr_gdt: .space 6
+END(trampoline_header)
+
+#include "trampoline_common.S"
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S
index 09ff51799e9..bb360dc39d2 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/realmode/rm/trampoline_64.S
@@ -5,12 +5,12 @@
* 4 Jan 1997 Michael Chastain: changed to gnu as.
* 15 Sept 2005 Eric Biederman: 64bit PIC support
*
- * Entry: CS:IP point to the start of our code, we are
- * in real mode with no stack, but the rest of the
+ * Entry: CS:IP point to the start of our code, we are
+ * in real mode with no stack, but the rest of the
* trampoline page to make our stack and everything else
* is a mystery.
*
- * On entry to trampoline_data, the processor is in real mode
+ * On entry to trampoline_start, the processor is in real mode
* with 16-bit addressing and 16-bit data. CS has some value
* and IP is zero. Thus, data addresses need to be absolute
* (no relocation) and are taken with regard to r_base.
@@ -31,43 +31,33 @@
#include <asm/msr.h>
#include <asm/segment.h>
#include <asm/processor-flags.h>
+#include "realmode.h"
- .section ".x86_trampoline","a"
- .balign PAGE_SIZE
+ .text
.code16
-ENTRY(trampoline_data)
-r_base = .
+ .balign PAGE_SIZE
+ENTRY(trampoline_start)
cli # We should be safe anyway
wbinvd
+
+ LJMPW_RM(1f)
+1:
mov %cs, %ax # Code and data in the same place
mov %ax, %ds
mov %ax, %es
mov %ax, %ss
+ movl $0xA5A5A5A5, trampoline_status
+ # write marker for master knows we're running
- movl $0xA5A5A5A5, trampoline_status - r_base
- # write marker for master knows we're running
-
- # Setup stack
- movw $(trampoline_stack_end - r_base), %sp
+ # Setup stack
+ movl $rm_stack_end, %esp
call verify_cpu # Verify the cpu supports long mode
testl %eax, %eax # Check for return code
jnz no_longmode
- mov %cs, %ax
- movzx %ax, %esi # Find the 32bit trampoline location
- shll $4, %esi
-
- # Fixup the absolute vectors
- leal (startup_32 - r_base)(%esi), %eax
- movl %eax, startup_32_vector - r_base
- leal (startup_64 - r_base)(%esi), %eax
- movl %eax, startup_64_vector - r_base
- leal (tgdt - r_base)(%esi), %eax
- movl %eax, (tgdt + 2 - r_base)
-
/*
* GDT tables in non default location kernel can be beyond 16MB and
* lgdt will not be able to load the address as in real mode default
@@ -75,36 +65,49 @@ r_base = .
* to 32 bit.
*/
- lidtl tidt - r_base # load idt with 0, 0
- lgdtl tgdt - r_base # load gdt with whatever is appropriate
+ lidtl tr_idt # load idt with 0, 0
+ lgdtl tr_gdt # load gdt with whatever is appropriate
+
+ movw $__KERNEL_DS, %dx # Data segment descriptor
- mov $X86_CR0_PE, %ax # protected mode (PE) bit
- lmsw %ax # into protected mode
+ # Enable protected mode
+ movl $X86_CR0_PE, %eax # protected mode (PE) bit
+ movl %eax, %cr0 # into protected mode
# flush prefetch and jump to startup_32
- ljmpl *(startup_32_vector - r_base)
+ ljmpl $__KERNEL32_CS, $pa_startup_32
+no_longmode:
+ hlt
+ jmp no_longmode
+#include "../kernel/verify_cpu.S"
+
+ .section ".text32","ax"
.code32
.balign 4
-startup_32:
- movl $__KERNEL_DS, %eax # Initialize the %ds segment register
- movl %eax, %ds
-
- movl $X86_CR4_PAE, %eax
+ENTRY(startup_32)
+ movl %edx, %ss
+ addl $pa_real_mode_base, %esp
+ movl %edx, %ds
+ movl %edx, %es
+ movl %edx, %fs
+ movl %edx, %gs
+
+ movl pa_tr_cr4, %eax
movl %eax, %cr4 # Enable PAE mode
- # Setup trampoline 4 level pagetables
- leal (trampoline_level4_pgt - r_base)(%esi), %eax
+ # Setup trampoline 4 level pagetables
+ movl $pa_trampoline_pgd, %eax
movl %eax, %cr3
+ # Set up EFER
+ movl pa_tr_efer, %eax
+ movl pa_tr_efer + 4, %edx
movl $MSR_EFER, %ecx
- movl $(1 << _EFER_LME), %eax # Enable Long Mode
- xorl %edx, %edx
wrmsr
# Enable paging and in turn activate Long Mode
- # Enable protected mode
- movl $(X86_CR0_PG | X86_CR0_PE), %eax
+ movl $(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax
movl %eax, %cr0
/*
@@ -113,59 +116,38 @@ startup_32:
* EFER.LMA = 1). Now we want to jump in 64bit mode, to do that we use
* the new gdt/idt that has __KERNEL_CS with CS.L = 1.
*/
- ljmp *(startup_64_vector - r_base)(%esi)
+ ljmpl $__KERNEL_CS, $pa_startup_64
+ .section ".text64","ax"
.code64
.balign 4
-startup_64:
+ENTRY(startup_64)
# Now jump into the kernel using virtual addresses
- movq $secondary_startup_64, %rax
- jmp *%rax
-
- .code16
-no_longmode:
- hlt
- jmp no_longmode
-#include "verify_cpu.S"
-
- .balign 4
- # Careful these need to be in the same 64K segment as the above;
-tidt:
- .word 0 # idt limit = 0
- .word 0, 0 # idt base = 0L
+ jmpq *tr_start(%rip)
+ .section ".rodata","a"
# Duplicate the global descriptor table
# so the kernel can live anywhere
- .balign 4
-tgdt:
- .short tgdt_end - tgdt # gdt limit
- .long tgdt - r_base
- .short 0
+ .balign 16
+ .globl tr_gdt
+tr_gdt:
+ .short tr_gdt_end - tr_gdt - 1 # gdt limit
+ .long pa_tr_gdt
+ .short 0
.quad 0x00cf9b000000ffff # __KERNEL32_CS
.quad 0x00af9b000000ffff # __KERNEL_CS
.quad 0x00cf93000000ffff # __KERNEL_DS
-tgdt_end:
+tr_gdt_end:
- .balign 4
-startup_32_vector:
- .long startup_32 - r_base
- .word __KERNEL32_CS, 0
+ .bss
+ .balign PAGE_SIZE
+GLOBAL(trampoline_pgd) .space PAGE_SIZE
- .balign 4
-startup_64_vector:
- .long startup_64 - r_base
- .word __KERNEL_CS, 0
+ .balign 8
+GLOBAL(trampoline_header)
+ tr_start: .space 8
+ GLOBAL(tr_efer) .space 8
+ GLOBAL(tr_cr4) .space 4
+END(trampoline_header)
- .balign 4
-ENTRY(trampoline_status)
- .long 0
-
-trampoline_stack:
- .org 0x1000
-trampoline_stack_end:
-ENTRY(trampoline_level4_pgt)
- .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
- .fill 510,8,0
- .quad level3_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE
-
-ENTRY(trampoline_end)
+#include "trampoline_common.S"
diff --git a/arch/x86/realmode/rm/trampoline_common.S b/arch/x86/realmode/rm/trampoline_common.S
new file mode 100644
index 00000000000..b1ecdb9692a
--- /dev/null
+++ b/arch/x86/realmode/rm/trampoline_common.S
@@ -0,0 +1,7 @@
+ .section ".rodata","a"
+ .balign 16
+tr_idt: .fill 1, 6, 0
+
+ .bss
+ .balign 4
+GLOBAL(trampoline_status) .space 4
diff --git a/arch/x86/realmode/rm/video-bios.c b/arch/x86/realmode/rm/video-bios.c
new file mode 100644
index 00000000000..848b25aaf11
--- /dev/null
+++ b/arch/x86/realmode/rm/video-bios.c
@@ -0,0 +1 @@
+#include "../../boot/video-bios.c"
diff --git a/arch/x86/realmode/rm/video-mode.c b/arch/x86/realmode/rm/video-mode.c
new file mode 100644
index 00000000000..2a98b7e2368
--- /dev/null
+++ b/arch/x86/realmode/rm/video-mode.c
@@ -0,0 +1 @@
+#include "../../boot/video-mode.c"
diff --git a/arch/x86/realmode/rm/video-vesa.c b/arch/x86/realmode/rm/video-vesa.c
new file mode 100644
index 00000000000..413edddb51e
--- /dev/null
+++ b/arch/x86/realmode/rm/video-vesa.c
@@ -0,0 +1 @@
+#include "../../boot/video-vesa.c"
diff --git a/arch/x86/realmode/rm/video-vga.c b/arch/x86/realmode/rm/video-vga.c
new file mode 100644
index 00000000000..3085f5c9d28
--- /dev/null
+++ b/arch/x86/realmode/rm/video-vga.c
@@ -0,0 +1 @@
+#include "../../boot/video-vga.c"
diff --git a/arch/x86/kernel/acpi/realmode/wakemain.c b/arch/x86/realmode/rm/wakemain.c
index 883962d9eef..91405d515ec 100644
--- a/arch/x86/kernel/acpi/realmode/wakemain.c
+++ b/arch/x86/realmode/rm/wakemain.c
@@ -65,7 +65,8 @@ void main(void)
{
/* Kill machine if structures are wrong */
if (wakeup_header.real_magic != 0x12345678)
- while (1);
+ while (1)
+ ;
if (wakeup_header.realmode_flags & 4)
send_morse("...-");
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/realmode/rm/wakeup.h
index 97a29e1430e..9317e0042f2 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/realmode/rm/wakeup.h
@@ -12,9 +12,8 @@
/* This must match data at wakeup.S */
struct wakeup_header {
u16 video_mode; /* Video mode number */
- u16 _jmp1; /* ljmpl opcode, 32-bit only */
u32 pmode_entry; /* Protected mode resume point, 32-bit only */
- u16 _jmp2; /* CS value, 32-bit only */
+ u16 pmode_cs;
u32 pmode_cr0; /* Protected mode cr0 */
u32 pmode_cr3; /* Protected mode cr3 */
u32 pmode_cr4; /* Protected mode cr4 */
@@ -26,12 +25,6 @@ struct wakeup_header {
u32 pmode_behavior; /* Wakeup routine behavior flags */
u32 realmode_flags;
u32 real_magic;
- u16 trampoline_segment; /* segment with trampoline code, 64-bit only */
- u8 _pad1;
- u8 wakeup_jmp;
- u16 wakeup_jmp_off;
- u16 wakeup_jmp_seg;
- u64 wakeup_gdt[3];
u32 signature; /* To check we have correct structure */
} __attribute__((__packed__));
@@ -40,7 +33,6 @@ extern struct wakeup_header wakeup_header;
#define WAKEUP_HEADER_OFFSET 8
#define WAKEUP_HEADER_SIGNATURE 0x51ee1111
-#define WAKEUP_END_SIGNATURE 0x65a22c82
/* Wakeup behavior bits */
#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE 0
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/realmode/rm/wakeup_asm.S
index b4fd836e405..8905166b0bb 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/realmode/rm/wakeup_asm.S
@@ -1,50 +1,47 @@
/*
* ACPI wakeup real mode startup stub
*/
+#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/msr-index.h>
#include <asm/page_types.h>
#include <asm/pgtable_types.h>
#include <asm/processor-flags.h>
+#include "realmode.h"
#include "wakeup.h"
.code16
- .section ".jump", "ax"
- .globl _start
-_start:
- cli
- jmp wakeup_code
/* This should match the structure in wakeup.h */
- .section ".header", "a"
- .globl wakeup_header
-wakeup_header:
-video_mode: .short 0 /* Video mode number */
-pmode_return: .byte 0x66, 0xea /* ljmpl */
- .long 0 /* offset goes here */
- .short __KERNEL_CS
-pmode_cr0: .long 0 /* Saved %cr0 */
-pmode_cr3: .long 0 /* Saved %cr3 */
-pmode_cr4: .long 0 /* Saved %cr4 */
-pmode_efer: .quad 0 /* Saved EFER */
-pmode_gdt: .quad 0
-pmode_misc_en: .quad 0 /* Saved MISC_ENABLE MSR */
-pmode_behavior: .long 0 /* Wakeup behavior flags */
-realmode_flags: .long 0
-real_magic: .long 0
-trampoline_segment: .word 0
-_pad1: .byte 0
-wakeup_jmp: .byte 0xea /* ljmpw */
-wakeup_jmp_off: .word 3f
-wakeup_jmp_seg: .word 0
-wakeup_gdt: .quad 0, 0, 0
-signature: .long WAKEUP_HEADER_SIGNATURE
+ .section ".data", "aw"
+
+ .balign 16
+GLOBAL(wakeup_header)
+ video_mode: .short 0 /* Video mode number */
+ pmode_entry: .long 0
+ pmode_cs: .short __KERNEL_CS
+ pmode_cr0: .long 0 /* Saved %cr0 */
+ pmode_cr3: .long 0 /* Saved %cr3 */
+ pmode_cr4: .long 0 /* Saved %cr4 */
+ pmode_efer: .quad 0 /* Saved EFER */
+ pmode_gdt: .quad 0
+ pmode_misc_en: .quad 0 /* Saved MISC_ENABLE MSR */
+ pmode_behavior: .long 0 /* Wakeup behavior flags */
+ realmode_flags: .long 0
+ real_magic: .long 0
+ signature: .long WAKEUP_HEADER_SIGNATURE
+END(wakeup_header)
.text
.code16
-wakeup_code:
+
+ .balign 16
+ENTRY(wakeup_start)
+ cli
cld
+ LJMPW_RM(3f)
+3:
/* Apparently some dimwit BIOS programmers don't know how to
program a PM to RM transition, and we might end up here with
junk in the data segment descriptor registers. The only way
@@ -54,8 +51,7 @@ wakeup_code:
movl %cr0, %eax
orb $X86_CR0_PE, %al
movl %eax, %cr0
- jmp 1f
-1: ljmpw $8, $2f
+ ljmpw $8, $2f
2:
movw %cx, %ds
movw %cx, %es
@@ -65,16 +61,18 @@ wakeup_code:
andb $~X86_CR0_PE, %al
movl %eax, %cr0
- jmp wakeup_jmp
+ LJMPW_RM(3f)
3:
/* Set up segments */
movw %cs, %ax
+ movw %ax, %ss
+ movl $rm_stack_end, %esp
movw %ax, %ds
movw %ax, %es
- movw %ax, %ss
- lidtl wakeup_idt
+ movw %ax, %fs
+ movw %ax, %gs
- movl $wakeup_stack_end, %esp
+ lidtl wakeup_idt
/* Clear the EFLAGS */
pushl $0
@@ -87,7 +85,7 @@ wakeup_code:
/* Check we really have everything... */
movl end_signature, %eax
- cmpl $WAKEUP_END_SIGNATURE, %eax
+ cmpl $REALMODE_END_SIGNATURE, %eax
jne bogus_real_magic
/* Call the C code */
@@ -128,14 +126,13 @@ wakeup_code:
lgdtl pmode_gdt
/* This really couldn't... */
- movl pmode_cr0, %eax
- movl %eax, %cr0
- jmp pmode_return
+ movl pmode_entry, %eax
+ movl pmode_cr0, %ecx
+ movl %ecx, %cr0
+ ljmpl $__KERNEL_CS, $pa_startup_32
+ /* -> jmp *%eax in trampoline_32.S */
#else
- pushw $0
- pushw trampoline_segment
- pushw $0
- lret
+ jmp trampoline_start
#endif
bogus_real_magic:
@@ -143,28 +140,38 @@ bogus_real_magic:
hlt
jmp 1b
- .data
+ .section ".rodata","a"
+
+ /*
+ * Set up the wakeup GDT. We set these up as Big Real Mode,
+ * that is, with limits set to 4 GB. At least the Lenovo
+ * Thinkpad X61 is known to need this for the video BIOS
+ * initialization quirk to work; this is likely to also
+ * be the case for other laptops or integrated video devices.
+ */
+
+ .balign 16
+GLOBAL(wakeup_gdt)
+ .word 3*8-1 /* Self-descriptor */
+ .long pa_wakeup_gdt
+ .word 0
+
+ .word 0xffff /* 16-bit code segment @ real_mode_base */
+ .long 0x9b000000 + pa_real_mode_base
+ .word 0x008f /* big real mode */
+
+ .word 0xffff /* 16-bit data segment @ real_mode_base */
+ .long 0x93000000 + pa_real_mode_base
+ .word 0x008f /* big real mode */
+END(wakeup_gdt)
+
+ .section ".rodata","a"
.balign 8
/* This is the standard real-mode IDT */
-wakeup_idt:
+ .balign 16
+GLOBAL(wakeup_idt)
.word 0xffff /* limit */
.long 0 /* address */
.word 0
-
- .globl HEAP, heap_end
-HEAP:
- .long wakeup_heap
-heap_end:
- .long wakeup_stack
-
- .bss
-wakeup_heap:
- .space 2048
-wakeup_stack:
- .space 2048
-wakeup_stack_end:
-
- .section ".signature","a"
-end_signature:
- .long WAKEUP_END_SIGNATURE
+END(wakeup_idt)
diff --git a/arch/x86/realmode/rmpiggy.S b/arch/x86/realmode/rmpiggy.S
new file mode 100644
index 00000000000..204c6ece0e9
--- /dev/null
+++ b/arch/x86/realmode/rmpiggy.S
@@ -0,0 +1,20 @@
+/*
+ * Wrapper script for the realmode binary as a transport object
+ * before copying to low memory.
+ */
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+ .section ".init.data","aw"
+
+ .balign PAGE_SIZE
+
+GLOBAL(real_mode_blob)
+ .incbin "arch/x86/realmode/rm/realmode.bin"
+END(real_mode_blob)
+
+GLOBAL(real_mode_blob_end);
+
+GLOBAL(real_mode_relocs)
+ .incbin "arch/x86/realmode/rm/realmode.relocs"
+END(real_mode_relocs)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b685296d446..5a1847d6193 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -78,6 +78,13 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
static const char * const sym_regex_realmode[S_NSYMTYPES] = {
/*
+ * These symbols are known to be relative, even if the linker marks them
+ * as absolute (typically defined outside any section in the linker script.)
+ */
+ [S_REL] =
+ "^pa_",
+
+/*
* These are 16-bit segment symbols when compiling 16-bit code.
*/
[S_SEG] =
diff --git a/arch/x86/xen/debugfs.c b/arch/x86/xen/debugfs.c
index ef1db1900d8..c8377fb26cd 100644
--- a/arch/x86/xen/debugfs.c
+++ b/arch/x86/xen/debugfs.c
@@ -19,107 +19,3 @@ struct dentry * __init xen_init_debugfs(void)
return d_xen_debug;
}
-struct array_data
-{
- void *array;
- unsigned elements;
-};
-
-static int u32_array_open(struct inode *inode, struct file *file)
-{
- file->private_data = NULL;
- return nonseekable_open(inode, file);
-}
-
-static size_t format_array(char *buf, size_t bufsize, const char *fmt,
- u32 *array, unsigned array_size)
-{
- size_t ret = 0;
- unsigned i;
-
- for(i = 0; i < array_size; i++) {
- size_t len;
-
- len = snprintf(buf, bufsize, fmt, array[i]);
- len++; /* ' ' or '\n' */
- ret += len;
-
- if (buf) {
- buf += len;
- bufsize -= len;
- buf[-1] = (i == array_size-1) ? '\n' : ' ';
- }
- }
-
- ret++; /* \0 */
- if (buf)
- *buf = '\0';
-
- return ret;
-}
-
-static char *format_array_alloc(const char *fmt, u32 *array, unsigned array_size)
-{
- size_t len = format_array(NULL, 0, fmt, array, array_size);
- char *ret;
-
- ret = kmalloc(len, GFP_KERNEL);
- if (ret == NULL)
- return NULL;
-
- format_array(ret, len, fmt, array, array_size);
- return ret;
-}
-
-static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len,
- loff_t *ppos)
-{
- struct inode *inode = file->f_path.dentry->d_inode;
- struct array_data *data = inode->i_private;
- size_t size;
-
- if (*ppos == 0) {
- if (file->private_data) {
- kfree(file->private_data);
- file->private_data = NULL;
- }
-
- file->private_data = format_array_alloc("%u", data->array, data->elements);
- }
-
- size = 0;
- if (file->private_data)
- size = strlen(file->private_data);
-
- return simple_read_from_buffer(buf, len, ppos, file->private_data, size);
-}
-
-static int xen_array_release(struct inode *inode, struct file *file)
-{
- kfree(file->private_data);
-
- return 0;
-}
-
-static const struct file_operations u32_array_fops = {
- .owner = THIS_MODULE,
- .open = u32_array_open,
- .release= xen_array_release,
- .read = u32_array_read,
- .llseek = no_llseek,
-};
-
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
- struct dentry *parent,
- u32 *array, unsigned elements)
-{
- struct array_data *data = kmalloc(sizeof(*data), GFP_KERNEL);
-
- if (data == NULL)
- return NULL;
-
- data->array = array;
- data->elements = elements;
-
- return debugfs_create_file(name, mode, parent, data, &u32_array_fops);
-}
diff --git a/arch/x86/xen/debugfs.h b/arch/x86/xen/debugfs.h
index 78d25499be5..12ebf3325c7 100644
--- a/arch/x86/xen/debugfs.h
+++ b/arch/x86/xen/debugfs.h
@@ -3,8 +3,4 @@
struct dentry * __init xen_init_debugfs(void);
-struct dentry *xen_debugfs_create_u32_array(const char *name, umode_t mode,
- struct dentry *parent,
- u32 *array, unsigned elements);
-
#endif /* _XEN_DEBUGFS_H */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0f5facdb10..75f33b2a593 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -42,6 +42,7 @@
#include <xen/page.h>
#include <xen/hvm.h>
#include <xen/hvc-console.h>
+#include <xen/acpi.h>
#include <asm/paravirt.h>
#include <asm/apic.h>
@@ -75,6 +76,7 @@
#include "xen-ops.h"
#include "mmu.h"
+#include "smp.h"
#include "multicalls.h"
EXPORT_SYMBOL_GPL(hypercall_page);
@@ -883,6 +885,14 @@ static void set_xen_basic_apic_ops(void)
apic->safe_wait_icr_idle = xen_safe_apic_wait_icr_idle;
apic->set_apic_id = xen_set_apic_id;
apic->get_apic_id = xen_get_apic_id;
+
+#ifdef CONFIG_SMP
+ apic->send_IPI_allbutself = xen_send_IPI_allbutself;
+ apic->send_IPI_mask_allbutself = xen_send_IPI_mask_allbutself;
+ apic->send_IPI_mask = xen_send_IPI_mask;
+ apic->send_IPI_all = xen_send_IPI_all;
+ apic->send_IPI_self = xen_send_IPI_self;
+#endif
}
#endif
@@ -1340,7 +1350,6 @@ asmlinkage void __init xen_start_kernel(void)
xen_raw_console_write("mapping kernel into physical memory\n");
pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);
- xen_ident_map_ISA();
/* Allocate and initialize top and mid mfn levels for p2m structure */
xen_build_mfn_list_list();
@@ -1400,6 +1409,8 @@ asmlinkage void __init xen_start_kernel(void)
/* Make sure ACS will be enabled */
pci_request_acs();
+
+ xen_acpi_sleep_register();
}
#ifdef CONFIG_PCI
/* PCI BIOS service won't work from a PV guest. */
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3506cd4f9a4..3a73785631c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1933,29 +1933,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
#endif
}
-void __init xen_ident_map_ISA(void)
-{
- unsigned long pa;
-
- /*
- * If we're dom0, then linear map the ISA machine addresses into
- * the kernel's address space.
- */
- if (!xen_initial_domain())
- return;
-
- xen_raw_printk("Xen: setup ISA identity maps\n");
-
- for (pa = ISA_START_ADDRESS; pa < ISA_END_ADDRESS; pa += PAGE_SIZE) {
- pte_t pte = mfn_pte(PFN_DOWN(pa), PAGE_KERNEL_IO);
-
- if (HYPERVISOR_update_va_mapping(PAGE_OFFSET + pa, pte, 0))
- BUG();
- }
-
- xen_flush_tlb();
-}
-
static void __init xen_post_allocator_init(void)
{
pv_mmu_ops.set_pte = xen_set_pte;
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 1b267e75158..ffd08c414e9 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -499,16 +499,18 @@ static bool alloc_p2m(unsigned long pfn)
return true;
}
-static bool __init __early_alloc_p2m(unsigned long pfn)
+static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary)
{
unsigned topidx, mididx, idx;
+ unsigned long *p2m;
+ unsigned long *mid_mfn_p;
topidx = p2m_top_index(pfn);
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
/* Pfff.. No boundary cross-over, lets get out. */
- if (!idx)
+ if (!idx && check_boundary)
return false;
WARN(p2m_top[topidx][mididx] == p2m_identity,
@@ -522,24 +524,66 @@ static bool __init __early_alloc_p2m(unsigned long pfn)
return false;
/* Boundary cross-over for the edges: */
- if (idx) {
- unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
- unsigned long *mid_mfn_p;
+ p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_init(p2m);
+ p2m_init(p2m);
- p2m_top[topidx][mididx] = p2m;
+ p2m_top[topidx][mididx] = p2m;
- /* For save/restore we need to MFN of the P2M saved */
-
- mid_mfn_p = p2m_top_mfn_p[topidx];
- WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
- "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
- topidx, mididx);
- mid_mfn_p[mididx] = virt_to_mfn(p2m);
+ /* For save/restore we need to MFN of the P2M saved */
+
+ mid_mfn_p = p2m_top_mfn_p[topidx];
+ WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
+ "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
+ topidx, mididx);
+ mid_mfn_p[mididx] = virt_to_mfn(p2m);
+
+ return true;
+}
+
+static bool __init early_alloc_p2m(unsigned long pfn)
+{
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned long *mid_mfn_p;
+ unsigned long **mid;
+
+ mid = p2m_top[topidx];
+ mid_mfn_p = p2m_top_mfn_p[topidx];
+ if (mid == p2m_mid_missing) {
+ mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+ p2m_mid_init(mid);
+
+ p2m_top[topidx] = mid;
+ BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
}
- return idx != 0;
+ /* And the save/restore P2M tables.. */
+ if (mid_mfn_p == p2m_mid_missing_mfn) {
+ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_mfn_init(mid_mfn_p);
+
+ p2m_top_mfn_p[topidx] = mid_mfn_p;
+ p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
+ /* Note: we don't set mid_mfn_p[midix] here,
+ * look in early_alloc_p2m_middle */
+ }
+ return true;
+}
+bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+ if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
+ if (!early_alloc_p2m(pfn))
+ return false;
+
+ if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/))
+ return false;
+
+ if (!__set_phys_to_machine(pfn, mfn))
+ return false;
+ }
+
+ return true;
}
unsigned long __init set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e)
@@ -559,35 +603,11 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
{
- unsigned topidx = p2m_top_index(pfn);
- unsigned long *mid_mfn_p;
- unsigned long **mid;
-
- mid = p2m_top[topidx];
- mid_mfn_p = p2m_top_mfn_p[topidx];
- if (mid == p2m_mid_missing) {
- mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-
- p2m_mid_init(mid);
-
- p2m_top[topidx] = mid;
-
- BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
- }
- /* And the save/restore P2M tables.. */
- if (mid_mfn_p == p2m_mid_missing_mfn) {
- mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_mfn_init(mid_mfn_p);
-
- p2m_top_mfn_p[topidx] = mid_mfn_p;
- p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
- /* Note: we don't set mid_mfn_p[midix] here,
- * look in __early_alloc_p2m */
- }
+ WARN_ON(!early_alloc_p2m(pfn));
}
- __early_alloc_p2m(pfn_s);
- __early_alloc_p2m(pfn_e);
+ early_alloc_p2m_middle(pfn_s, true);
+ early_alloc_p2m_middle(pfn_e, true);
for (pfn = pfn_s; pfn < pfn_e; pfn++)
if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1ba8dff2675..3ebba0753d3 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -26,7 +26,6 @@
#include <xen/interface/memory.h>
#include <xen/interface/physdev.h>
#include <xen/features.h>
-
#include "xen-ops.h"
#include "vdso.h"
@@ -84,8 +83,8 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
-static unsigned long __init xen_release_chunk(unsigned long start,
- unsigned long end)
+static unsigned long __init xen_do_chunk(unsigned long start,
+ unsigned long end, bool release)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
@@ -96,30 +95,138 @@ static unsigned long __init xen_release_chunk(unsigned long start,
unsigned long pfn;
int ret;
- for(pfn = start; pfn < end; pfn++) {
+ for (pfn = start; pfn < end; pfn++) {
+ unsigned long frame;
unsigned long mfn = pfn_to_mfn(pfn);
- /* Make sure pfn exists to start with */
- if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
- continue;
-
- set_xen_guest_handle(reservation.extent_start, &mfn);
+ if (release) {
+ /* Make sure pfn exists to start with */
+ if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+ continue;
+ frame = mfn;
+ } else {
+ if (mfn != INVALID_P2M_ENTRY)
+ continue;
+ frame = pfn;
+ }
+ set_xen_guest_handle(reservation.extent_start, &frame);
reservation.nr_extents = 1;
- ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+ ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
&reservation);
- WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
+ WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
+ release ? "release" : "populate", pfn, ret);
+
if (ret == 1) {
- __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
+ if (release)
+ break;
+ set_xen_guest_handle(reservation.extent_start, &frame);
+ reservation.nr_extents = 1;
+ ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
+ &reservation);
+ break;
+ }
len++;
- }
+ } else
+ break;
}
- printk(KERN_INFO "Freeing %lx-%lx pfn range: %lu pages freed\n",
- start, end, len);
+ if (len)
+ printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
+ release ? "Freeing" : "Populating",
+ start, end, len,
+ release ? "freed" : "added");
return len;
}
+static unsigned long __init xen_release_chunk(unsigned long start,
+ unsigned long end)
+{
+ return xen_do_chunk(start, end, true);
+}
+
+static unsigned long __init xen_populate_chunk(
+ const struct e820entry *list, size_t map_size,
+ unsigned long max_pfn, unsigned long *last_pfn,
+ unsigned long credits_left)
+{
+ const struct e820entry *entry;
+ unsigned int i;
+ unsigned long done = 0;
+ unsigned long dest_pfn;
+
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ unsigned long credits = credits_left;
+ unsigned long s_pfn;
+ unsigned long e_pfn;
+ unsigned long pfns;
+ long capacity;
+
+ if (credits <= 0)
+ break;
+
+ if (entry->type != E820_RAM)
+ continue;
+
+ e_pfn = PFN_UP(entry->addr + entry->size);
+
+ /* We only care about E820 after the xen_start_info->nr_pages */
+ if (e_pfn <= max_pfn)
+ continue;
+
+ s_pfn = PFN_DOWN(entry->addr);
+ /* If the E820 falls within the nr_pages, we want to start
+ * at the nr_pages PFN.
+ * If that would mean going past the E820 entry, skip it
+ */
+ if (s_pfn <= max_pfn) {
+ capacity = e_pfn - max_pfn;
+ dest_pfn = max_pfn;
+ } else {
+ /* last_pfn MUST be within E820_RAM regions */
+ if (*last_pfn && e_pfn >= *last_pfn)
+ s_pfn = *last_pfn;
+ capacity = e_pfn - s_pfn;
+ dest_pfn = s_pfn;
+ }
+ /* If we had filled this E820_RAM entry, go to the next one. */
+ if (capacity <= 0)
+ continue;
+
+ if (credits > capacity)
+ credits = capacity;
+
+ pfns = xen_do_chunk(dest_pfn, dest_pfn + credits, false);
+ done += pfns;
+ credits_left -= pfns;
+ *last_pfn = (dest_pfn + pfns);
+ }
+ return done;
+}
+
+static void __init xen_set_identity_and_release_chunk(
+ unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+ unsigned long *released, unsigned long *identity)
+{
+ unsigned long pfn;
+
+ /*
+ * If the PFNs are currently mapped, the VA mapping also needs
+ * to be updated to be 1:1.
+ */
+ for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+ (void)HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+
+ if (start_pfn < nr_pages)
+ *released += xen_release_chunk(
+ start_pfn, min(end_pfn, nr_pages));
+
+ *identity += set_phys_range_identity(start_pfn, end_pfn);
+}
+
static unsigned long __init xen_set_identity_and_release(
const struct e820entry *list, size_t map_size, unsigned long nr_pages)
{
@@ -142,7 +249,6 @@ static unsigned long __init xen_set_identity_and_release(
*/
for (i = 0, entry = list; i < map_size; i++, entry++) {
phys_addr_t end = entry->addr + entry->size;
-
if (entry->type == E820_RAM || i == map_size - 1) {
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
@@ -150,20 +256,19 @@ static unsigned long __init xen_set_identity_and_release(
if (entry->type == E820_RAM)
end_pfn = PFN_UP(entry->addr);
- if (start_pfn < end_pfn) {
- if (start_pfn < nr_pages)
- released += xen_release_chunk(
- start_pfn, min(end_pfn, nr_pages));
+ if (start_pfn < end_pfn)
+ xen_set_identity_and_release_chunk(
+ start_pfn, end_pfn, nr_pages,
+ &released, &identity);
- identity += set_phys_range_identity(
- start_pfn, end_pfn);
- }
start = end;
}
}
- printk(KERN_INFO "Released %lu pages of unused memory\n", released);
- printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
+ if (released)
+ printk(KERN_INFO "Released %lu pages of unused memory\n", released);
+ if (identity)
+ printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
return released;
}
@@ -217,7 +322,9 @@ char * __init xen_memory_setup(void)
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
+ unsigned long last_pfn = 0;
unsigned long extra_pages = 0;
+ unsigned long populated;
int i;
int op;
@@ -257,9 +364,20 @@ char * __init xen_memory_setup(void)
*/
xen_released_pages = xen_set_identity_and_release(
map, memmap.nr_entries, max_pfn);
- extra_pages += xen_released_pages;
/*
+ * Populate back the non-RAM pages and E820 gaps that had been
+ * released. */
+ populated = xen_populate_chunk(map, memmap.nr_entries,
+ max_pfn, &last_pfn, xen_released_pages);
+
+ extra_pages += (xen_released_pages - populated);
+
+ if (last_pfn > max_pfn) {
+ max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
+ mem_end = PFN_PHYS(max_pfn);
+ }
+ /*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
* size is the full initial memory allocation; on highmem it
@@ -272,7 +390,6 @@ char * __init xen_memory_setup(void)
*/
extra_pages = min(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages);
-
i = 0;
while (i < memmap.nr_entries) {
u64 addr = map[i].addr;
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3700945ed0d..afb250d22a6 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -16,6 +16,7 @@
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/smp.h>
+#include <linux/irq_work.h>
#include <asm/paravirt.h>
#include <asm/desc.h>
@@ -41,10 +42,12 @@ cpumask_var_t xen_cpu_initialized_map;
static DEFINE_PER_CPU(int, xen_resched_irq);
static DEFINE_PER_CPU(int, xen_callfunc_irq);
static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
+static DEFINE_PER_CPU(int, xen_irq_work);
static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
/*
* Reschedule call back.
@@ -143,6 +146,17 @@ static int xen_smp_intr_init(unsigned int cpu)
goto fail;
per_cpu(xen_callfuncsingle_irq, cpu) = rc;
+ callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
+ rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
+ cpu,
+ xen_irq_work_interrupt,
+ IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+ callfunc_name,
+ NULL);
+ if (rc < 0)
+ goto fail;
+ per_cpu(xen_irq_work, cpu) = rc;
+
return 0;
fail:
@@ -155,6 +169,8 @@ static int xen_smp_intr_init(unsigned int cpu)
if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
NULL);
+ if (per_cpu(xen_irq_work, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
return rc;
}
@@ -407,6 +423,7 @@ static void xen_cpu_die(unsigned int cpu)
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
@@ -469,8 +486,8 @@ static void xen_smp_send_reschedule(int cpu)
xen_send_IPI_one(cpu, XEN_RESCHEDULE_VECTOR);
}
-static void xen_send_IPI_mask(const struct cpumask *mask,
- enum ipi_vector vector)
+static void __xen_send_IPI_mask(const struct cpumask *mask,
+ int vector)
{
unsigned cpu;
@@ -482,7 +499,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
{
int cpu;
- xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
+ __xen_send_IPI_mask(mask, XEN_CALL_FUNCTION_VECTOR);
/* Make sure other vcpus get a chance to run if they need to. */
for_each_cpu(cpu, mask) {
@@ -495,10 +512,86 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
static void xen_smp_send_call_function_single_ipi(int cpu)
{
- xen_send_IPI_mask(cpumask_of(cpu),
+ __xen_send_IPI_mask(cpumask_of(cpu),
XEN_CALL_FUNCTION_SINGLE_VECTOR);
}
+static inline int xen_map_vector(int vector)
+{
+ int xen_vector;
+
+ switch (vector) {
+ case RESCHEDULE_VECTOR:
+ xen_vector = XEN_RESCHEDULE_VECTOR;
+ break;
+ case CALL_FUNCTION_VECTOR:
+ xen_vector = XEN_CALL_FUNCTION_VECTOR;
+ break;
+ case CALL_FUNCTION_SINGLE_VECTOR:
+ xen_vector = XEN_CALL_FUNCTION_SINGLE_VECTOR;
+ break;
+ case IRQ_WORK_VECTOR:
+ xen_vector = XEN_IRQ_WORK_VECTOR;
+ break;
+ default:
+ xen_vector = -1;
+ printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
+ vector);
+ }
+
+ return xen_vector;
+}
+
+void xen_send_IPI_mask(const struct cpumask *mask,
+ int vector)
+{
+ int xen_vector = xen_map_vector(vector);
+
+ if (xen_vector >= 0)
+ __xen_send_IPI_mask(mask, xen_vector);
+}
+
+void xen_send_IPI_all(int vector)
+{
+ int xen_vector = xen_map_vector(vector);
+
+ if (xen_vector >= 0)
+ __xen_send_IPI_mask(cpu_online_mask, xen_vector);
+}
+
+void xen_send_IPI_self(int vector)
+{
+ int xen_vector = xen_map_vector(vector);
+
+ if (xen_vector >= 0)
+ xen_send_IPI_one(smp_processor_id(), xen_vector);
+}
+
+void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
+ int vector)
+{
+ unsigned cpu;
+ unsigned int this_cpu = smp_processor_id();
+
+ if (!(num_online_cpus() > 1))
+ return;
+
+ for_each_cpu_and(cpu, mask, cpu_online_mask) {
+ if (this_cpu == cpu)
+ continue;
+
+ xen_smp_send_call_function_single_ipi(cpu);
+ }
+}
+
+void xen_send_IPI_allbutself(int vector)
+{
+ int xen_vector = xen_map_vector(vector);
+
+ if (xen_vector >= 0)
+ xen_send_IPI_mask_allbutself(cpu_online_mask, xen_vector);
+}
+
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id)
{
irq_enter();
@@ -519,6 +612,16 @@ static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id)
return IRQ_HANDLED;
}
+static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
+{
+ irq_enter();
+ irq_work_run();
+ inc_irq_stat(apic_irq_work_irqs);
+ irq_exit();
+
+ return IRQ_HANDLED;
+}
+
static const struct smp_ops xen_smp_ops __initconst = {
.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu,
.smp_prepare_cpus = xen_smp_prepare_cpus,
@@ -565,6 +668,7 @@ static void xen_hvm_cpu_die(unsigned int cpu)
unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_irq_work, cpu), NULL);
native_cpu_die(cpu);
}
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
new file mode 100644
index 00000000000..8981a76d081
--- /dev/null
+++ b/arch/x86/xen/smp.h
@@ -0,0 +1,12 @@
+#ifndef _XEN_SMP_H
+
+extern void xen_send_IPI_mask(const struct cpumask *mask,
+ int vector);
+extern void xen_send_IPI_mask_allbutself(const struct cpumask *mask,
+ int vector);
+extern void xen_send_IPI_allbutself(int vector);
+extern void physflat_send_IPI_allbutself(int vector);
+extern void xen_send_IPI_all(int vector);
+extern void xen_send_IPI_self(int vector);
+
+#endif
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index d69cc6c3f80..83e866d714c 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -440,12 +440,12 @@ static int __init xen_spinlock_debugfs(void)
debugfs_create_u64("time_total", 0444, d_spin_debug,
&spinlock_stats.time_total);
- xen_debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
- spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
- xen_debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
- spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
- xen_debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
- spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
+ debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
+ spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
+ debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
+ spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
+ debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+ spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
return 0;
}
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 45c0c0667bd..202d4c15015 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -28,7 +28,6 @@ void xen_setup_shared_info(void);
void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
-void xen_ident_map_ISA(void);
void xen_reserve_top(void);
extern unsigned long xen_max_p2m_pfn;