summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/Makefile5
-rw-r--r--arch/x86/boot/compressed/Makefile2
-rw-r--r--arch/x86/boot/compressed/error.h4
-rw-r--r--arch/x86/boot/compressed/pagetable.c2
-rw-r--r--arch/x86/entry/entry_32.S30
-rw-r--r--arch/x86/entry/entry_64.S11
-rw-r--r--arch/x86/events/intel/rapl.c2
-rw-r--r--arch/x86/include/asm/asm.h1
-rw-r--r--arch/x86/include/asm/cacheflush.h85
-rw-r--r--arch/x86/include/asm/init.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h4
-rw-r--r--arch/x86/include/asm/mce.h1
-rw-r--r--arch/x86/include/asm/pci.h7
-rw-r--r--arch/x86/include/asm/pmem.h2
-rw-r--r--arch/x86/include/asm/set_memory.h87
-rw-r--r--arch/x86/include/asm/uaccess.h11
-rw-r--r--arch/x86/include/uapi/asm/Kbuild59
-rw-r--r--arch/x86/kernel/alternative.c9
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/cpu/amd.c7
-rw-r--r--arch/x86/kernel/cpu/bugs.c2
-rw-r--r--arch/x86/kernel/cpu/cyrix.c1
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c13
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c20
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c2
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c5
-rw-r--r--arch/x86/kernel/fpu/init.c1
-rw-r--r--arch/x86/kernel/ftrace.c22
-rw-r--r--arch/x86/kernel/i8259.c1
-rw-r--r--arch/x86/kernel/kprobes/core.c10
-rw-r--r--arch/x86/kernel/kprobes/opt.c1
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kernel/machine_kexec_32.c2
-rw-r--r--arch/x86/kernel/machine_kexec_64.c7
-rw-r--r--arch/x86/kernel/module.c2
-rw-r--r--arch/x86/kernel/process_32.c2
-rw-r--r--arch/x86/kernel/setup.c19
-rw-r--r--arch/x86/kernel/setup_percpu.c10
-rw-r--r--arch/x86/kernel/tboot.c3
-rw-r--r--arch/x86/kernel/unwind_frame.c49
-rw-r--r--arch/x86/kvm/cpuid.c20
-rw-r--r--arch/x86/kvm/emulate.c2
-rw-r--r--arch/x86/kvm/lapic.c9
-rw-r--r--arch/x86/kvm/mmu.c22
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/page_track.c4
-rw-r--r--arch/x86/kvm/paging_tmpl.h39
-rw-r--r--arch/x86/kvm/pmu_intel.c2
-rw-r--r--arch/x86/kvm/svm.c29
-rw-r--r--arch/x86/kvm/vmx.c256
-rw-r--r--arch/x86/kvm/x86.c59
-rw-r--r--arch/x86/lib/csum-copy_64.S12
-rw-r--r--arch/x86/lib/kaslr.c3
-rw-r--r--arch/x86/mm/ident_map.c14
-rw-r--r--arch/x86/mm/init.c2
-rw-r--r--arch/x86/mm/init_32.c2
-rw-r--r--arch/x86/mm/init_64.c14
-rw-r--r--arch/x86/mm/ioremap.c2
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pageattr.c3
-rw-r--r--arch/x86/mm/testmmiotrace.c2
-rw-r--r--arch/x86/net/bpf_jit_comp.c1
-rw-r--r--arch/x86/pci/i386.c47
-rw-r--r--arch/x86/pci/pcbios.c2
-rw-r--r--arch/x86/platform/efi/efi.c8
-rw-r--r--arch/x86/platform/efi/efi_64.c79
-rw-r--r--arch/x86/platform/efi/quirks.c3
-rw-r--r--arch/x86/power/hibernate_64.c2
-rw-r--r--arch/x86/realmode/init.c2
-rw-r--r--arch/x86/um/ptrace_64.c2
-rw-r--r--arch/x86/um/shared/sysdep/kernel-offsets.h9
-rw-r--r--arch/x86/xen/enlighten_pv.c57
-rw-r--r--arch/x86/xen/mmu.c2
-rw-r--r--arch/x86/xen/mmu_pv.c109
-rw-r--r--arch/x86/xen/time.c2
76 files changed, 743 insertions, 591 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cd18994a9555..4ccfacc7232a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -360,7 +360,7 @@ config SMP
Management" code will be disabled if you say Y here.
See also <file:Documentation/x86/i386/IO-APIC.txt>,
- <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at
+ <file:Documentation/lockup-watchdogs.txt> and the SMP-HOWTO available at
<http://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 4430dd489620..bf240b920473 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -159,7 +159,7 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER
# If '-Os' is enabled, disable it and print a warning.
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
undefine CONFIG_CC_OPTIMIZE_FOR_SIZE
- $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
+ $(warning Disabling CONFIG_CC_OPTIMIZE_FOR_SIZE. Your compiler does not have -mfentry so you cannot optimize for size with CONFIG_FUNCTION_GRAPH_TRACER.)
endif
endif
@@ -179,7 +179,8 @@ ifdef CONFIG_JUMP_LABEL
endif
ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1)
- KBUILD_CFLAGS += -maccumulate-outgoing-args
+ # This compiler flag is not supported by Clang:
+ KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,)
endif
# Stackpointer is addressed different for 32 bit and 64 bit x86
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 44163e8c3868..2c860ad4fe06 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -94,7 +94,7 @@ vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
quiet_cmd_check_data_rel = DATAREL $@
define cmd_check_data_rel
for obj in $(filter %.o,$^); do \
- readelf -S $$obj | grep -qF .rel.local && { \
+ ${CROSS_COMPILE}readelf -S $$obj | grep -qF .rel.local && { \
echo "error: $$obj has data relocations!" >&2; \
exit 1; \
} || true; \
diff --git a/arch/x86/boot/compressed/error.h b/arch/x86/boot/compressed/error.h
index 2e59dac07f9e..d732e608e3af 100644
--- a/arch/x86/boot/compressed/error.h
+++ b/arch/x86/boot/compressed/error.h
@@ -1,7 +1,9 @@
#ifndef BOOT_COMPRESSED_ERROR_H
#define BOOT_COMPRESSED_ERROR_H
+#include <linux/compiler.h>
+
void warn(char *m);
-void error(char *m);
+void error(char *m) __noreturn;
#endif /* BOOT_COMPRESSED_ERROR_H */
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index 56589d0a804b..1d78f1739087 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -70,7 +70,7 @@ static unsigned long level4p;
* Due to relocation, pointers must be assigned at run time not build time.
*/
static struct x86_mapping_info mapping_info = {
- .pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
+ .page_flag = __PAGE_KERNEL_LARGE_EXEC,
};
/* Locates and clears a region for a new top level page table. */
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 50bc26949e9e..48ef7bb32c42 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,6 +252,23 @@ ENTRY(__switch_to_asm)
END(__switch_to_asm)
/*
+ * The unwinder expects the last frame on the stack to always be at the same
+ * offset from the end of the page, which allows it to validate the stack.
+ * Calling schedule_tail() directly would break that convention because its an
+ * asmlinkage function so its argument has to be pushed on the stack. This
+ * wrapper creates a proper "end of stack" frame header before the call.
+ */
+ENTRY(schedule_tail_wrapper)
+ FRAME_BEGIN
+
+ pushl %eax
+ call schedule_tail
+ popl %eax
+
+ FRAME_END
+ ret
+ENDPROC(schedule_tail_wrapper)
+/*
* A newly forked process directly context switches into this address.
*
* eax: prev task we switched from
@@ -259,24 +276,15 @@ END(__switch_to_asm)
* edi: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
-
- /*
- * schedule_tail() is asmlinkage so we have to put its 'prev' argument
- * on the stack.
- */
- pushl %eax
- call schedule_tail
- popl %eax
+ call schedule_tail_wrapper
testl %ebx, %ebx
jnz 1f /* kernel threads are uncommon */
2:
/* When we fork, we trace the syscall return in the child, too. */
- leal FRAME_OFFSET(%esp), %eax
+ movl %esp, %eax
call syscall_return_slowpath
- FRAME_END
jmp restore_all
/* kernel thread */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 607d72c4a485..4a4c0834f965 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -36,7 +36,6 @@
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
-#include <asm/frame.h>
#include <linux/err.h>
.code64
@@ -406,19 +405,17 @@ END(__switch_to_asm)
* r12: kernel thread arg
*/
ENTRY(ret_from_fork)
- FRAME_BEGIN /* help unwinder find end of stack */
movq %rax, %rdi
- call schedule_tail /* rdi: 'prev' task parameter */
+ call schedule_tail /* rdi: 'prev' task parameter */
- testq %rbx, %rbx /* from kernel_thread? */
- jnz 1f /* kernel threads are uncommon */
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
2:
- leaq FRAME_OFFSET(%rsp),%rdi /* pt_regs pointer */
+ movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
SWAPGS
- FRAME_END
jmp restore_regs_and_iret
1:
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 9d05c7e67f60..a45e2114a846 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -761,7 +761,7 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_CORE, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_GT3E, hsw_rapl_init),
- X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsw_rapl_init),
+ X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_X, hsx_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_BROADWELL_XEON_D, hsw_rapl_init),
X86_RAPL_MODEL_MATCH(INTEL_FAM6_XEON_PHI_KNL, knl_rapl_init),
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7acb51c49fec..7a9df3beb89b 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -32,6 +32,7 @@
#define _ASM_ADD __ASM_SIZE(add)
#define _ASM_SUB __ASM_SIZE(sub)
#define _ASM_XADD __ASM_SIZE(xadd)
+#define _ASM_MUL __ASM_SIZE(mul)
#define _ASM_AX __ASM_REG(ax)
#define _ASM_BX __ASM_REG(bx)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index e7e1942edff7..8b4140f6724f 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -5,93 +5,8 @@
#include <asm-generic/cacheflush.h>
#include <asm/special_insns.h>
-/*
- * The set_memory_* API can be used to change various attributes of a virtual
- * address range. The attributes include:
- * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack
- * Executability : eXeutable, NoteXecutable
- * Read/Write : ReadOnly, ReadWrite
- * Presence : NotPresent
- *
- * Within a category, the attributes are mutually exclusive.
- *
- * The implementation of this API will take care of various aspects that
- * are associated with changing such attributes, such as:
- * - Flushing TLBs
- * - Flushing CPU caches
- * - Making sure aliases of the memory behind the mapping don't violate
- * coherency rules as defined by the CPU in the system.
- *
- * What this API does not do:
- * - Provide exclusion between various callers - including callers that
- * operation on other mappings of the same physical page
- * - Restore default attributes when a page is freed
- * - Guarantee that mappings other than the requested one are
- * in any state, other than that these do not violate rules for
- * the CPU you have. Do not depend on any effects on other mappings,
- * CPUs other than the one you have may have more relaxed rules.
- * The caller is required to take care of these.
- */
-
-int _set_memory_uc(unsigned long addr, int numpages);
-int _set_memory_wc(unsigned long addr, int numpages);
-int _set_memory_wt(unsigned long addr, int numpages);
-int _set_memory_wb(unsigned long addr, int numpages);
-int set_memory_uc(unsigned long addr, int numpages);
-int set_memory_wc(unsigned long addr, int numpages);
-int set_memory_wt(unsigned long addr, int numpages);
-int set_memory_wb(unsigned long addr, int numpages);
-int set_memory_x(unsigned long addr, int numpages);
-int set_memory_nx(unsigned long addr, int numpages);
-int set_memory_ro(unsigned long addr, int numpages);
-int set_memory_rw(unsigned long addr, int numpages);
-int set_memory_np(unsigned long addr, int numpages);
-int set_memory_4k(unsigned long addr, int numpages);
-
-int set_memory_array_uc(unsigned long *addr, int addrinarray);
-int set_memory_array_wc(unsigned long *addr, int addrinarray);
-int set_memory_array_wt(unsigned long *addr, int addrinarray);
-int set_memory_array_wb(unsigned long *addr, int addrinarray);
-
-int set_pages_array_uc(struct page **pages, int addrinarray);
-int set_pages_array_wc(struct page **pages, int addrinarray);
-int set_pages_array_wt(struct page **pages, int addrinarray);
-int set_pages_array_wb(struct page **pages, int addrinarray);
-
-/*
- * For legacy compatibility with the old APIs, a few functions
- * are provided that work on a "struct page".
- * These functions operate ONLY on the 1:1 kernel mapping of the
- * memory that the struct page represents, and internally just
- * call the set_memory_* function. See the description of the
- * set_memory_* function for more details on conventions.
- *
- * These APIs should be considered *deprecated* and are likely going to
- * be removed in the future.
- * The reason for this is the implicit operation on the 1:1 mapping only,
- * making this not a generally useful API.
- *
- * Specifically, many users of the old APIs had a virtual address,
- * called virt_to_page() or vmalloc_to_page() on that address to
- * get a struct page* that the old API required.
- * To convert these cases, use set_memory_*() on the original
- * virtual address, do not use these functions.
- */
-
-int set_pages_uc(struct page *page, int numpages);
-int set_pages_wb(struct page *page, int numpages);
-int set_pages_x(struct page *page, int numpages);
-int set_pages_nx(struct page *page, int numpages);
-int set_pages_ro(struct page *page, int numpages);
-int set_pages_rw(struct page *page, int numpages);
-
-
void clflush_cache_range(void *addr, unsigned int size);
#define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
-extern int kernel_set_to_readonly;
-void set_kernel_text_rw(void);
-void set_kernel_text_ro(void);
-
#endif /* _ASM_X86_CACHEFLUSH_H */
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 737da62bfeb0..474eb8c66fee 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -4,8 +4,9 @@
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
- unsigned long pmd_flag; /* page flag for PMD entry */
+ unsigned long page_flag; /* page flag for PMD or PUD entry */
unsigned long offset; /* ident mapping offset */
+ bool direct_gbpages; /* PUD level 1GB page support */
};
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f5bddf92faba..695605eb1dfb 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
#define KVM_PRIVATE_MEM_SLOTS 3
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
-#define KVM_HALT_POLL_NS_DEFAULT 400000
+#define KVM_HALT_POLL_NS_DEFAULT 200000
#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS
@@ -1020,6 +1020,8 @@ struct kvm_x86_ops {
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
+ int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4fd5195deed0..3f9a3d2a5209 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -266,6 +266,7 @@ static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *s
#endif
int mce_available(struct cpuinfo_x86 *c);
+bool mce_is_memory_error(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 1411dbed5e5e..f513cc231151 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -7,6 +7,7 @@
#include <linux/string.h>
#include <linux/scatterlist.h>
#include <asm/io.h>
+#include <asm/pat.h>
#include <asm/x86_init.h>
#ifdef __KERNEL__
@@ -102,10 +103,8 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
#define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
- enum pci_mmap_state mmap_state,
- int write_combine);
-
+#define arch_can_pci_mmap_wc() pat_enabled()
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE
#ifdef CONFIG_PCI
extern void early_quirks(void);
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index d5a22bac9988..0ff8fe71b255 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -98,7 +98,7 @@ static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
if (bytes < 8) {
if (!IS_ALIGNED(dest, 4) || (bytes != 4))
- arch_wb_cache_pmem(addr, 1);
+ arch_wb_cache_pmem(addr, bytes);
} else {
if (!IS_ALIGNED(dest, 8)) {
dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
new file mode 100644
index 000000000000..eaec6c364e42
--- /dev/null
+++ b/arch/x86/include/asm/set_memory.h
@@ -0,0 +1,87 @@
+#ifndef _ASM_X86_SET_MEMORY_H
+#define _ASM_X86_SET_MEMORY_H
+
+#include <asm/page.h>
+#include <asm-generic/set_memory.h>
+
+/*
+ * The set_memory_* API can be used to change various attributes of a virtual
+ * address range. The attributes include:
+ * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack
+ * Executability : eXeutable, NoteXecutable
+ * Read/Write : ReadOnly, ReadWrite
+ * Presence : NotPresent
+ *
+ * Within a category, the attributes are mutually exclusive.
+ *
+ * The implementation of this API will take care of various aspects that
+ * are associated with changing such attributes, such as:
+ * - Flushing TLBs
+ * - Flushing CPU caches
+ * - Making sure aliases of the memory behind the mapping don't violate
+ * coherency rules as defined by the CPU in the system.
+ *
+ * What this API does not do:
+ * - Provide exclusion between various callers - including callers that
+ * operation on other mappings of the same physical page
+ * - Restore default attributes when a page is freed
+ * - Guarantee that mappings other than the requested one are
+ * in any state, other than that these do not violate rules for
+ * the CPU you have. Do not depend on any effects on other mappings,
+ * CPUs other than the one you have may have more relaxed rules.
+ * The caller is required to take care of these.
+ */
+
+int _set_memory_uc(unsigned long addr, int numpages);
+int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wt(unsigned long addr, int numpages);
+int _set_memory_wb(unsigned long addr, int numpages);
+int set_memory_uc(unsigned long addr, int numpages);
+int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wt(unsigned long addr, int numpages);
+int set_memory_wb(unsigned long addr, int numpages);
+int set_memory_np(unsigned long addr, int numpages);
+int set_memory_4k(unsigned long addr, int numpages);
+
+int set_memory_array_uc(unsigned long *addr, int addrinarray);
+int set_memory_array_wc(unsigned long *addr, int addrinarray);
+int set_memory_array_wt(unsigned long *addr, int addrinarray);
+int set_memory_array_wb(unsigned long *addr, int addrinarray);
+
+int set_pages_array_uc(struct page **pages, int addrinarray);
+int set_pages_array_wc(struct page **pages, int addrinarray);
+int set_pages_array_wt(struct page **pages, int addrinarray);
+int set_pages_array_wb(struct page **pages, int addrinarray);
+
+/*
+ * For legacy compatibility with the old APIs, a few functions
+ * are provided that work on a "struct page".
+ * These functions operate ONLY on the 1:1 kernel mapping of the
+ * memory that the struct page represents, and internally just
+ * call the set_memory_* function. See the description of the
+ * set_memory_* function for more details on conventions.
+ *
+ * These APIs should be considered *deprecated* and are likely going to
+ * be removed in the future.
+ * The reason for this is the implicit operation on the 1:1 mapping only,
+ * making this not a generally useful API.
+ *
+ * Specifically, many users of the old APIs had a virtual address,
+ * called virt_to_page() or vmalloc_to_page() on that address to
+ * get a struct page* that the old API required.
+ * To convert these cases, use set_memory_*() on the original
+ * virtual address, do not use these functions.
+ */
+
+int set_pages_uc(struct page *page, int numpages);
+int set_pages_wb(struct page *page, int numpages);
+int set_pages_x(struct page *page, int numpages);
+int set_pages_nx(struct page *page, int numpages);
+int set_pages_ro(struct page *page, int numpages);
+int set_pages_rw(struct page *page, int numpages);
+
+extern int kernel_set_to_readonly;
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+
+#endif /* _ASM_X86_SET_MEMORY_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 68766b276d9e..a059aac9e937 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -319,10 +319,10 @@ do { \
#define __get_user_asm_u64(x, ptr, retval, errret) \
({ \
__typeof__(ptr) __ptr = (ptr); \
- asm volatile(ASM_STAC "\n" \
+ asm volatile("\n" \
"1: movl %2,%%eax\n" \
"2: movl %3,%%edx\n" \
- "3: " ASM_CLAC "\n" \
+ "3:\n" \
".section .fixup,\"ax\"\n" \
"4: mov %4,%0\n" \
" xorl %%eax,%%eax\n" \
@@ -331,7 +331,7 @@ do { \
".previous\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
- : "=r" (retval), "=A"(x) \
+ : "=r" (retval), "=&A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
})
@@ -703,14 +703,15 @@ extern struct movsl_mask {
#define unsafe_put_user(x, ptr, err_label) \
do { \
int __pu_err; \
- __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \
if (unlikely(__pu_err)) goto err_label; \
} while (0)
#define unsafe_get_user(x, ptr, err_label) \
do { \
int __gu_err; \
- unsigned long __gu_val; \
+ __inttype(*(ptr)) __gu_val; \
__get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
if (unlikely(__gu_err)) goto err_label; \
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index 3dec769cadf7..83b6e9a0dce4 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -4,62 +4,3 @@ include include/uapi/asm-generic/Kbuild.asm
genhdr-y += unistd_32.h
genhdr-y += unistd_64.h
genhdr-y += unistd_x32.h
-header-y += a.out.h
-header-y += auxvec.h
-header-y += bitsperlong.h
-header-y += boot.h
-header-y += bootparam.h
-header-y += byteorder.h
-header-y += debugreg.h
-header-y += e820.h
-header-y += errno.h
-header-y += fcntl.h
-header-y += hw_breakpoint.h
-header-y += hyperv.h
-header-y += ioctl.h
-header-y += ioctls.h
-header-y += ipcbuf.h
-header-y += ist.h
-header-y += kvm.h
-header-y += kvm_para.h
-header-y += kvm_perf.h
-header-y += ldt.h
-header-y += mce.h
-header-y += mman.h
-header-y += msgbuf.h
-header-y += msr-index.h
-header-y += msr.h
-header-y += mtrr.h
-header-y += param.h
-header-y += perf_regs.h
-header-y += poll.h
-header-y += posix_types.h
-header-y += posix_types_32.h
-header-y += posix_types_64.h
-header-y += posix_types_x32.h
-header-y += prctl.h
-header-y += processor-flags.h
-header-y += ptrace-abi.h
-header-y += ptrace.h
-header-y += resource.h
-header-y += sembuf.h
-header-y += setup.h
-header-y += shmbuf.h
-header-y += sigcontext.h
-header-y += sigcontext32.h
-header-y += siginfo.h
-header-y += signal.h
-header-y += socket.h
-header-y += sockios.h
-header-y += stat.h
-header-y += statfs.h
-header-y += svm.h
-header-y += swab.h
-header-y += termbits.h
-header-y += termios.h
-header-y += types.h
-header-y += ucontext.h
-header-y += unistd.h
-header-y += vm86.h
-header-y += vmx.h
-header-y += vsyscall.h
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c5b8f760473c..32e14d137416 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -409,8 +409,13 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
memcpy(insnbuf, replacement, a->replacementlen);
insnbuf_sz = a->replacementlen;
- /* 0xe8 is a relative jump; fix the offset. */
- if (*insnbuf == 0xe8 && a->replacementlen == 5) {
+ /*
+ * 0xe8 is a relative jump; fix the offset.
+ *
+ * Instruction length is checked before the opcode to avoid
+ * accessing uninitialized bytes for zero-length replacements.
+ */
+ if (a->replacementlen == 5 && *insnbuf == 0xe8) {
*(s32 *)(insnbuf + 1) += replacement - instr;
DPRINTK("Fix CALL offset: 0x%x, CALL 0x%lx",
*(s32 *)(insnbuf + 1),
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index df083efe6ee0..815dd63f49d0 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -36,7 +36,7 @@
#include <asm/proto.h>
#include <asm/iommu.h>
#include <asm/gart.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/swiotlb.h>
#include <asm/dma.h>
#include <asm/amd_nb.h>
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c36140d788fe..bb5abe8f5fd4 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -16,7 +16,7 @@
#ifdef CONFIG_X86_64
# include <asm/mmconfig.h>
-# include <asm/cacheflush.h>
+# include <asm/set_memory.h>
#endif
#include "cpu.h"
@@ -799,8 +799,9 @@ static void init_amd(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_3DNOW) || cpu_has(c, X86_FEATURE_LM))
set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH);
- /* AMD CPUs don't reset SS attributes on SYSRET */
- set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+ /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
+ if (!cpu_has(c, X86_FEATURE_XENPV))
+ set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
}
#ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index a44ef52184df..0af86d9242da 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -17,7 +17,7 @@
#include <asm/paravirt.h>
#include <asm/alternative.h>
#include <asm/pgtable.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
void __init check_bugs(void)
{
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index a70fd61095f8..6f077445647a 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -255,6 +255,7 @@ static void init_cyrix(struct cpuinfo_x86 *c)
break;
case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
+ case 11: /* GX1 with inverted Device ID */
#ifdef CONFIG_PCI
{
u32 vendor, device;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 5abd4bf73d6e..5cfbaeb6529a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -499,16 +499,14 @@ static int mce_usable_address(struct mce *m)
return 1;
}
-static bool memory_error(struct mce *m)
+bool mce_is_memory_error(struct mce *m)
{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (m->cpuvendor == X86_VENDOR_AMD) {
/* ErrCodeExt[20:16] */
u8 xec = (m->status >> 16) & 0x1f;
return (xec == 0x0 || xec == 0x8);
- } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ } else if (m->cpuvendor == X86_VENDOR_INTEL) {
/*
* Intel SDM Volume 3B - 15.9.2 Compound Error Codes
*
@@ -529,6 +527,7 @@ static bool memory_error(struct mce *m)
return false;
}
+EXPORT_SYMBOL_GPL(mce_is_memory_error);
static bool cec_add_mce(struct mce *m)
{
@@ -536,7 +535,7 @@ static bool cec_add_mce(struct mce *m)
return false;
/* We eat only correctable DRAM errors with usable addresses. */
- if (memory_error(m) &&
+ if (mce_is_memory_error(m) &&
!(m->status & MCI_STATUS_UC) &&
mce_usable_address(m))
if (!cec_add_elem(m->addr >> PAGE_SHIFT))
@@ -713,7 +712,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
- if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m))
+ if (severity == MCE_DEFERRED_SEVERITY && mce_is_memory_error(&m))
if (m.status & MCI_STATUS_ADDRV)
m.severity = severity;
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 7889ae492af0..e9f4d762aa5b 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -10,7 +10,7 @@
* Author: Peter Oruba <peter.oruba@amd.com>
*
* Based on work by:
- * Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * Tigran Aivazian <aivazian.tigran@gmail.com>
*
* early loader:
* Copyright (C) 2013 Advanced Micro Devices, Inc.
@@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
{
@@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
if (!desc.mc)
return -EINVAL;
- ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
- desc.data, desc.size);
+ ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
if (ret != UCODE_OK)
return -EINVAL;
@@ -352,8 +351,6 @@ void reload_ucode_amd(void)
u32 rev, dummy;
mc = (struct microcode_amd *)amd_ucode_patch;
- if (!mc)
- return;
rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
@@ -677,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
}
static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
{
enum ucode_state ret;
@@ -691,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
#ifdef CONFIG_X86_32
/* save BSP's matching patch for early load */
- if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
- struct ucode_patch *p = find_patch(cpu);
+ if (save) {
+ struct ucode_patch *p = find_patch(0);
if (p) {
memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -724,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
{
char fw_name[36] = "amd-ucode/microcode_amd.bin";
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
enum ucode_state ret = UCODE_NFOUND;
const struct firmware *fw;
/* reload ucode container only on the boot cpu */
- if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+ if (!refresh_fw || !bsp)
return UCODE_OK;
if (c->x86 >= 0x15)
@@ -745,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
goto fw_release;
}
- ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+ ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
fw_release:
release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index b4a4cd39b358..e53d3c909840 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -1,7 +1,7 @@
/*
* CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * Copyright (C) 2000-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
* 2006 Shaohua Li <shaohua.li@intel.com>
* 2013-2016 Borislav Petkov <bp@alien8.de>
*
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 8325d8a09ab0..f522415bf9e5 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -1,7 +1,7 @@
/*
* Intel CPU Microcode Update Driver for Linux
*
- * Copyright (C) 2000-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ * Copyright (C) 2000-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
* 2006 Shaohua Li <shaohua.li@intel.com>
*
* Intel CPU microcode early update for Linux
@@ -619,6 +619,9 @@ int __init save_microcode_in_initrd_intel(void)
show_saved_mc();
+ /* initrd is going away, clear patch ptr. */
+ intel_ucode_patch = NULL;
+
return 0;
}
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index c2f8dde3255c..d5d44c452624 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -90,6 +90,7 @@ static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
* Boot time FPU feature detection code:
*/
unsigned int mxcsr_feature_mask __read_mostly = 0xffffffffu;
+EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
static void __init fpu__init_system_mxcsr(void)
{
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 8ee76dce9140..9bef1bbeba63 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -24,7 +24,7 @@
#include <trace/syscall.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/kprobes.h>
#include <asm/ftrace.h>
#include <asm/nops.h>
@@ -689,8 +689,12 @@ static inline void *alloc_tramp(unsigned long size)
{
return module_alloc(size);
}
-static inline void tramp_free(void *tramp)
+static inline void tramp_free(void *tramp, int size)
{
+ int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ set_memory_nx((unsigned long)tramp, npages);
+ set_memory_rw((unsigned long)tramp, npages);
module_memfree(tramp);
}
#else
@@ -699,7 +703,7 @@ static inline void *alloc_tramp(unsigned long size)
{
return NULL;
}
-static inline void tramp_free(void *tramp) { }
+static inline void tramp_free(void *tramp, int size) { }
#endif
/* Defined as markers to the end of the ftrace default trampolines */
@@ -771,7 +775,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
/* Copy ftrace_caller onto the trampoline memory */
ret = probe_kernel_read(trampoline, (void *)start_offset, size);
if (WARN_ON(ret < 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
@@ -797,7 +801,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
/* Are we pointing to the reference? */
if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
- tramp_free(trampoline);
+ tramp_free(trampoline, *tramp_size);
return 0;
}
@@ -839,7 +843,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
unsigned long offset;
unsigned long ip;
unsigned int size;
- int ret;
+ int ret, npages;
if (ops->trampoline) {
/*
@@ -848,11 +852,14 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
*/
if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
+ npages = PAGE_ALIGN(ops->trampoline_size) >> PAGE_SHIFT;
+ set_memory_rw(ops->trampoline, npages);
} else {
ops->trampoline = create_trampoline(ops, &size);
if (!ops->trampoline)
return;
ops->trampoline_size = size;
+ npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
}
offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
@@ -863,6 +870,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
/* Do a safe modify in case the trampoline is executing */
new = ftrace_call_replace(ip, (unsigned long)func);
ret = update_ftrace_func(ip, new);
+ set_memory_ro(ops->trampoline, npages);
/* The update should never fail */
WARN_ON(ret);
@@ -939,7 +947,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
return;
- tramp_free((void *)ops->trampoline);
+ tramp_free((void *)ops->trampoline, ops->trampoline_size);
ops->trampoline = 0;
}
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index be22f5a2192e..4e3b8a587c88 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -418,6 +418,7 @@ struct legacy_pic default_legacy_pic = {
};
struct legacy_pic *legacy_pic = &default_legacy_pic;
+EXPORT_SYMBOL(legacy_pic);
static int __init i8259A_init_ops(void)
{
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 19e1f2a6d7b0..6b877807598b 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -52,6 +52,7 @@
#include <linux/ftrace.h>
#include <linux/frame.h>
#include <linux/kasan.h>
+#include <linux/moduleloader.h>
#include <asm/text-patching.h>
#include <asm/cacheflush.h>
@@ -61,6 +62,7 @@
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
+#include <asm/set_memory.h>
#include "common.h"
@@ -416,6 +418,14 @@ static void prepare_boost(struct kprobe *p, struct insn *insn)
}
}
+/* Recover page to RW mode before releasing it */
+void free_insn_page(void *page)
+{
+ set_memory_nx((unsigned long)page & PAGE_MASK, 1);
+ set_memory_rw((unsigned long)page & PAGE_MASK, 1);
+ module_memfree(page);
+}
+
static int arch_copy_kprobe(struct kprobe *p)
{
struct insn insn;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 9aadff3d0902..901c640d152f 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -37,6 +37,7 @@
#include <asm/alternative.h>
#include <asm/insn.h>
#include <asm/debugreg.h>
+#include <asm/set_memory.h>
#include "common.h"
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index da5c09789984..43e10d6fdbed 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -161,8 +161,8 @@ void kvm_async_pf_task_wait(u32 token)
*/
rcu_irq_exit();
native_safe_halt();
- rcu_irq_enter();
local_irq_disable();
+ rcu_irq_enter();
}
}
if (!n.halted)
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 5f43cec296c5..8c53c5d7a1bc 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -23,7 +23,7 @@
#include <asm/io_apic.h>
#include <asm/cpufeature.h>
#include <asm/desc.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/debugreg.h>
static void set_idt(void *newidt, __u16 limit)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 085c3b300d32..6f5ca4ebe6e5 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -27,6 +27,7 @@
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
#include <asm/setup.h>
+#include <asm/set_memory.h>
#ifdef CONFIG_KEXEC_FILE
static struct kexec_file_ops *kexec_file_loaders[] = {
@@ -113,7 +114,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
struct x86_mapping_info info = {
.alloc_pgt_page = alloc_pgt_page,
.context = image,
- .pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
+ .page_flag = __PAGE_KERNEL_LARGE_EXEC,
};
unsigned long mstart, mend;
pgd_t *level4p;
@@ -122,6 +123,10 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
level4p = (pgd_t *)__va(start_pgtable);
clear_page(level4p);
+
+ if (direct_gbpages)
+ info.direct_gbpages = true;
+
for (i = 0; i < nr_pfn_mapped; i++) {
mstart = pfn_mapped[i].start << PAGE_SHIFT;
mend = pfn_mapped[i].end << PAGE_SHIFT;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 477ae806c2fa..f67bd3205df7 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -85,7 +85,7 @@ void *module_alloc(unsigned long size)
p = __vmalloc_node_range(size, MODULE_ALIGN,
MODULES_VADDR + get_module_load_offset(),
- MODULES_END, GFP_KERNEL | __GFP_HIGHMEM,
+ MODULES_END, GFP_KERNEL,
PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
__builtin_return_address(0));
if (p && (kasan_module_alloc(p, size) < 0)) {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ff40e74c9181..ffeae818aa7a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all)
printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
- smp_processor_id());
+ raw_smp_processor_id());
printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
regs->ax, regs->bx, regs->cx, regs->dx);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 603a1669a2ec..f81823695014 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -980,8 +980,6 @@ void __init setup_arch(char **cmdline_p)
*/
x86_configure_nx();
- simple_udelay_calibration();
-
parse_early_param();
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -1041,6 +1039,8 @@ void __init setup_arch(char **cmdline_p)
*/
init_hypervisor_platform();
+ simple_udelay_calibration();
+
x86_init.resources.probe_roms();
/* after parse_early_param, so could debug it */
@@ -1225,6 +1225,21 @@ void __init setup_arch(char **cmdline_p)
kasan_init();
+#ifdef CONFIG_X86_32
+ /* sync back kernel address range */
+ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
+ swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ KERNEL_PGD_PTRS);
+
+ /*
+ * sync back low identity map too. It is used for example
+ * in the 32-bit EFI stub.
+ */
+ clone_pgd_range(initial_page_table,
+ swapper_pg_dir + KERNEL_PGD_BOUNDARY,
+ min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
+#endif
+
tboot_probe();
map_vsyscall();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index bb1e8cc0bc84..10edd1e69a68 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -291,11 +291,11 @@ void __init setup_per_cpu_areas(void)
#ifdef CONFIG_X86_32
/*
- * Sync back kernel address range. We want to make sure that
- * all kernel mappings, including percpu mappings, are available
- * in the smpboot asm. We can't reliably pick up percpu
- * mappings using vmalloc_fault(), because exception dispatch
- * needs percpu data.
+ * Sync back kernel address range again. We already did this in
+ * setup_arch(), but percpu data also needs to be available in
+ * the smpboot asm. We can't reliably pick up percpu mappings
+ * using vmalloc_fault(), because exception dispatch needs
+ * percpu data.
*/
clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
swapper_pg_dir + KERNEL_PGD_BOUNDARY,
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index d4c8011a2293..4b1724059909 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -514,6 +514,9 @@ int tboot_force_iommu(void)
if (!tboot_enabled())
return 0;
+ if (!intel_iommu_tboot_noforce)
+ return 1;
+
if (no_iommu || swiotlb || dmar_disabled)
pr_warning("Forcing Intel-IOMMU to enabled\n");
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 82c6d7f1fd73..b9389d72b2f7 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -104,6 +104,11 @@ static inline unsigned long *last_frame(struct unwind_state *state)
return (unsigned long *)task_pt_regs(state->task) - 2;
}
+static bool is_last_frame(struct unwind_state *state)
+{
+ return state->bp == last_frame(state);
+}
+
#ifdef CONFIG_X86_32
#define GCC_REALIGN_WORDS 3
#else
@@ -115,16 +120,15 @@ static inline unsigned long *last_aligned_frame(struct unwind_state *state)
return last_frame(state) - GCC_REALIGN_WORDS;
}
-static bool is_last_task_frame(struct unwind_state *state)
+static bool is_last_aligned_frame(struct unwind_state *state)
{
unsigned long *last_bp = last_frame(state);
unsigned long *aligned_bp = last_aligned_frame(state);
/*
- * We have to check for the last task frame at two different locations
- * because gcc can occasionally decide to realign the stack pointer and
- * change the offset of the stack frame in the prologue of a function
- * called by head/entry code. Examples:
+ * GCC can occasionally decide to realign the stack pointer and change
+ * the offset of the stack frame in the prologue of a function called
+ * by head/entry code. Examples:
*
* <start_secondary>:
* push %edi
@@ -141,11 +145,38 @@ static bool is_last_task_frame(struct unwind_state *state)
* push %rbp
* mov %rsp,%rbp
*
- * Note that after aligning the stack, it pushes a duplicate copy of
- * the return address before pushing the frame pointer.
+ * After aligning the stack, it pushes a duplicate copy of the return
+ * address before pushing the frame pointer.
+ */
+ return (state->bp == aligned_bp && *(aligned_bp + 1) == *(last_bp + 1));
+}
+
+static bool is_last_ftrace_frame(struct unwind_state *state)
+{
+ unsigned long *last_bp = last_frame(state);
+ unsigned long *last_ftrace_bp = last_bp - 3;
+
+ /*
+ * When unwinding from an ftrace handler of a function called by entry
+ * code, the stack layout of the last frame is:
+ *
+ * bp
+ * parent ret addr
+ * bp
+ * function ret addr
+ * parent ret addr
+ * pt_regs
+ * -----------------
*/
- return (state->bp == last_bp ||
- (state->bp == aligned_bp && *(aligned_bp+1) == *(last_bp+1)));
+ return (state->bp == last_ftrace_bp &&
+ *state->bp == *(state->bp + 2) &&
+ *(state->bp + 1) == *(state->bp + 4));
+}
+
+static bool is_last_task_frame(struct unwind_state *state)
+{
+ return is_last_frame(state) || is_last_aligned_frame(state) ||
+ is_last_ftrace_frame(state);
}
/*
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a181ae76c71c..59ca2eea522c 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -780,18 +780,20 @@ out:
static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
{
struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
- int j, nent = vcpu->arch.cpuid_nent;
+ struct kvm_cpuid_entry2 *ej;
+ int j = i;
+ int nent = vcpu->arch.cpuid_nent;
e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
/* when no next entry is found, the current entry[i] is reselected */
- for (j = i + 1; ; j = (j + 1) % nent) {
- struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
- if (ej->function == e->function) {
- ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
- return j;
- }
- }
- return 0; /* silence gcc, even though control never reaches here */
+ do {
+ j = (j + 1) % nent;
+ ej = &vcpu->arch.cpuid_entries[j];
+ } while (ej->function != e->function);
+
+ ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+ return j;
}
/* find an entry with matching function, matching index (if needed), and that
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c25cfaf584e7..0816ab2e8adc 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4173,7 +4173,7 @@ static int check_dr_write(struct x86_emulate_ctxt *ctxt)
static int check_svme(struct x86_emulate_ctxt *ctxt)
{
- u64 efer;
+ u64 efer = 0;
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9fa5b8164961..d24c8742d9b0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -177,8 +177,8 @@ static void recalculate_apic_map(struct kvm *kvm)
if (kvm_apic_present(vcpu))
max_id = max(max_id, kvm_x2apic_id(vcpu->arch.apic));
- new = kvm_kvzalloc(sizeof(struct kvm_apic_map) +
- sizeof(struct kvm_lapic *) * ((u64)max_id + 1));
+ new = kvzalloc(sizeof(struct kvm_apic_map) +
+ sizeof(struct kvm_lapic *) * ((u64)max_id + 1), GFP_KERNEL);
if (!new)
goto out;
@@ -1495,8 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
static void cancel_hv_timer(struct kvm_lapic *apic)
{
+ preempt_disable();
kvm_x86_ops->cancel_hv_timer(apic->vcpu);
apic->lapic_timer.hv_timer_in_use = false;
+ preempt_enable();
}
static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1934,7 +1936,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
apic_update_lvtt(apic);
- if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
+ if (kvm_vcpu_is_reset_bsp(vcpu) &&
+ kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
kvm_lapic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 558676538fca..cb8225969255 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1498,6 +1498,21 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
+/**
+ * kvm_arch_write_log_dirty - emulate dirty page logging
+ * @vcpu: Guest mode vcpu
+ *
+ * Emulate arch specific page modification logging for the
+ * nested hypervisor
+ */
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->write_log_dirty)
+ return kvm_x86_ops->write_log_dirty(vcpu);
+
+ return 0;
+}
+
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn)
{
@@ -3683,12 +3698,15 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn)
return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
}
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
{
if (unlikely(!lapic_in_kernel(vcpu) ||
kvm_event_needs_reinjection(vcpu)))
return false;
+ if (is_guest_mode(vcpu))
+ return false;
+
return kvm_x86_ops->interrupt_allowed(vcpu);
}
@@ -3704,7 +3722,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
if (!async)
return false; /* *pfn has correct page already */
- if (!prefault && can_do_async_pf(vcpu)) {
+ if (!prefault && kvm_can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(gva, gfn);
if (kvm_find_async_pf_gfn(vcpu, gfn)) {
trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d8ccb32f7308..330bf3a811fb 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -76,6 +76,7 @@ int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct);
void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
@@ -202,4 +203,5 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
#endif
diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c
index 60168cdd0546..ea67dc876316 100644
--- a/arch/x86/kvm/page_track.c
+++ b/arch/x86/kvm/page_track.c
@@ -40,8 +40,8 @@ int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
int i;
for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
- slot->arch.gfn_track[i] = kvm_kvzalloc(npages *
- sizeof(*slot->arch.gfn_track[i]));
+ slot->arch.gfn_track[i] = kvzalloc(npages *
+ sizeof(*slot->arch.gfn_track[i]), GFP_KERNEL);
if (!slot->arch.gfn_track[i])
goto track_free;
}
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 314d2071b337..b0454c7e4cff 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -226,6 +226,10 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (level == walker->level && write_fault &&
!(pte & PT_GUEST_DIRTY_MASK)) {
trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+#if PTTYPE == PTTYPE_EPT
+ if (kvm_arch_write_log_dirty(vcpu))
+ return -EINVAL;
+#endif
pte |= PT_GUEST_DIRTY_MASK;
}
if (pte == orig_pte)
@@ -279,11 +283,13 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
pt_element_t pte;
pt_element_t __user *uninitialized_var(ptep_user);
gfn_t table_gfn;
- unsigned index, pt_access, pte_access, accessed_dirty, pte_pkey;
+ u64 pt_access, pte_access;
+ unsigned index, accessed_dirty, pte_pkey;
unsigned nested_access;
gpa_t pte_gpa;
bool have_ad;
int offset;
+ u64 walk_nx_mask = 0;
const int write_fault = access & PFERR_WRITE_MASK;
const int user_fault = access & PFERR_USER_MASK;
const int fetch_fault = access & PFERR_FETCH_MASK;
@@ -298,6 +304,7 @@ retry_walk:
have_ad = PT_HAVE_ACCESSED_DIRTY(mmu);
#if PTTYPE == 64
+ walk_nx_mask = 1ULL << PT64_NX_SHIFT;
if (walker->level == PT32E_ROOT_LEVEL) {
pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
trace_kvm_mmu_paging_element(pte, walker->level);
@@ -309,8 +316,6 @@ retry_walk:
walker->max_level = walker->level;
ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
- accessed_dirty = have_ad ? PT_GUEST_ACCESSED_MASK : 0;
-
/*
* FIXME: on Intel processors, loads of the PDPTE registers for PAE paging
* by the MOV to CR instruction are treated as reads and do not cause the
@@ -318,14 +323,14 @@ retry_walk:
*/
nested_access = (have_ad ? PFERR_WRITE_MASK : 0) | PFERR_USER_MASK;
- pt_access = pte_access = ACC_ALL;
+ pte_access = ~0;
++walker->level;
do {
gfn_t real_gfn;
unsigned long host_addr;
- pt_access &= pte_access;
+ pt_access = pte_access;
--walker->level;
index = PT_INDEX(addr, walker->level);
@@ -367,6 +372,12 @@ retry_walk:
trace_kvm_mmu_paging_element(pte, walker->level);
+ /*
+ * Inverting the NX it lets us AND it like other
+ * permission bits.
+ */
+ pte_access = pt_access & (pte ^ walk_nx_mask);
+
if (unlikely(!FNAME(is_present_gpte)(pte)))
goto error;
@@ -375,14 +386,16 @@ retry_walk:
goto error;
}
- accessed_dirty &= pte;
- pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
-
walker->ptes[walker->level - 1] = pte;
} while (!is_last_gpte(mmu, walker->level, pte));
pte_pkey = FNAME(gpte_pkeys)(vcpu, pte);
- errcode = permission_fault(vcpu, mmu, pte_access, pte_pkey, access);
+ accessed_dirty = have_ad ? pte_access & PT_GUEST_ACCESSED_MASK : 0;
+
+ /* Convert to ACC_*_MASK flags for struct guest_walker. */
+ walker->pt_access = FNAME(gpte_access)(vcpu, pt_access ^ walk_nx_mask);
+ walker->pte_access = FNAME(gpte_access)(vcpu, pte_access ^ walk_nx_mask);
+ errcode = permission_fault(vcpu, mmu, walker->pte_access, pte_pkey, access);
if (unlikely(errcode))
goto error;
@@ -399,7 +412,7 @@ retry_walk:
walker->gfn = real_gpa >> PAGE_SHIFT;
if (!write_fault)
- FNAME(protect_clean_gpte)(mmu, &pte_access, pte);
+ FNAME(protect_clean_gpte)(mmu, &walker->pte_access, pte);
else
/*
* On a write fault, fold the dirty bit into accessed_dirty.
@@ -417,10 +430,8 @@ retry_walk:
goto retry_walk;
}
- walker->pt_access = pt_access;
- walker->pte_access = pte_access;
pgprintk("%s: pte %llx pte_access %x pt_access %x\n",
- __func__, (u64)pte, pte_access, pt_access);
+ __func__, (u64)pte, walker->pte_access, walker->pt_access);
return 1;
error:
@@ -448,7 +459,7 @@ error:
*/
if (!(errcode & PFERR_RSVD_MASK)) {
vcpu->arch.exit_qualification &= 0x187;
- vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+ vcpu->arch.exit_qualification |= (pte_access & 0x7) << 3;
}
#endif
walker->fault.address = addr;
diff --git a/arch/x86/kvm/pmu_intel.c b/arch/x86/kvm/pmu_intel.c
index 9d4a8504a95a..5ab4a364348e 100644
--- a/arch/x86/kvm/pmu_intel.c
+++ b/arch/x86/kvm/pmu_intel.c
@@ -294,7 +294,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
((u64)1 << edx.split.bit_width_fixed) - 1;
}
- pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+ pmu->global_ctrl = ((1ull << pmu->nr_arch_gp_counters) - 1) |
(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
pmu->global_ctrl_mask = ~pmu->global_ctrl;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c27ac6923a18..ba9891ac5c56 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1272,7 +1272,8 @@ static void init_vmcb(struct vcpu_svm *svm)
}
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, int index)
+static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
+ unsigned int index)
{
u64 *avic_physical_id_table;
struct kvm_arch *vm_data = &vcpu->kvm->arch;
@@ -1806,7 +1807,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
* AMD's VMCB does not have an explicit unusable field, so emulate it
* for cross vendor migration purposes by "not present"
*/
- var->unusable = !var->present || (var->type == 0);
+ var->unusable = !var->present;
switch (seg) {
case VCPU_SREG_TR:
@@ -1839,6 +1840,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
*/
if (var->unusable)
var->db = 0;
+ /* This is symmetric with svm_set_segment() */
var->dpl = to_svm(vcpu)->vmcb->save.cpl;
break;
}
@@ -1979,18 +1981,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
s->base = var->base;
s->limit = var->limit;
s->selector = var->selector;
- if (var->unusable)
- s->attrib = 0;
- else {
- s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
- s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
- s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
- s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT;
- s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
- s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
- s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
- s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
- }
+ s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
+ s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
+ s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
+ s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
+ s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
+ s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
+ s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
+ s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
/*
* This is always accurate, except if SYSRET returned to a segment
@@ -1999,7 +1997,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
* would entail passing the CPL to userspace and back.
*/
if (seg == VCPU_SREG_SS)
- svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
+ /* This is symmetric with svm_get_segment() */
+ svm->vmcb->save.cpl = (var->dpl & 3);
mark_dirty(svm->vmcb, VMCB_SEG);
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5fd459c4043..ca5d2b93385c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -248,6 +248,7 @@ struct __packed vmcs12 {
u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
+ u64 pml_address;
u64 guest_ia32_debugctl;
u64 guest_ia32_pat;
u64 guest_ia32_efer;
@@ -369,6 +370,7 @@ struct __packed vmcs12 {
u16 guest_ldtr_selector;
u16 guest_tr_selector;
u16 guest_intr_status;
+ u16 guest_pml_index;
u16 host_es_selector;
u16 host_cs_selector;
u16 host_ss_selector;
@@ -407,6 +409,7 @@ struct nested_vmx {
/* Has the level1 guest done vmxon? */
bool vmxon;
gpa_t vmxon_ptr;
+ bool pml_full;
/* The guest-physical address of the current VMCS L1 keeps for L2 */
gpa_t current_vmptr;
@@ -742,6 +745,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
FIELD(GUEST_INTR_STATUS, guest_intr_status),
+ FIELD(GUEST_PML_INDEX, guest_pml_index),
FIELD(HOST_ES_SELECTOR, host_es_selector),
FIELD(HOST_CS_SELECTOR, host_cs_selector),
FIELD(HOST_SS_SELECTOR, host_ss_selector),
@@ -767,6 +771,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
+ FIELD64(PML_ADDRESS, pml_address),
FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
@@ -1314,6 +1319,11 @@ static inline bool report_flexpriority(void)
return flexpriority_enabled;
}
+static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
+{
+ return vmx_misc_cr3_count(to_vmx(vcpu)->nested.nested_vmx_misc_low);
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
@@ -1348,6 +1358,11 @@ static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
vmx_xsaves_supported();
}
+static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
+}
+
static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
{
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -2410,7 +2425,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
if (!(vmcs12->exception_bitmap & (1u << nr)))
return 0;
- nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+ nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
vmcs_read32(VM_EXIT_INTR_INFO),
vmcs_readl(EXIT_QUALIFICATION));
return 1;
@@ -2751,8 +2766,11 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_1GB_PAGE_BIT;
- if (enable_ept_ad_bits)
+ if (enable_ept_ad_bits) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_PML;
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
+ }
} else
vmx->nested.nested_vmx_ept_caps = 0;
@@ -6486,7 +6504,7 @@ static __init int hardware_setup(void)
enable_ept_ad_bits = 0;
}
- if (!cpu_has_vmx_ept_ad_bits())
+ if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
enable_ept_ad_bits = 0;
if (!cpu_has_vmx_unrestricted_guest())
@@ -6896,97 +6914,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
return 0;
}
-/*
- * This function performs the various checks including
- * - if it's 4KB aligned
- * - No bits beyond the physical address width are set
- * - Returns 0 on success or else 1
- * (Intel SDM Section 30.3)
- */
-static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
- gpa_t *vmpointer)
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
{
gva_t gva;
- gpa_t vmptr;
struct x86_exception e;
- struct page *page;
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- int maxphyaddr = cpuid_maxphyaddr(vcpu);
if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
return 1;
- if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
- sizeof(vmptr), &e)) {
+ if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
+ sizeof(*vmpointer), &e)) {
kvm_inject_page_fault(vcpu, &e);
return 1;
}
- switch (exit_reason) {
- case EXIT_REASON_VMON:
- /*
- * SDM 3: 24.11.5
- * The first 4 bytes of VMXON region contain the supported
- * VMCS revision identifier
- *
- * Note - IA32_VMX_BASIC[48] will never be 1
- * for the nested case;
- * which replaces physical address width with 32
- *
- */
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- page = nested_get_page(vcpu, vmptr);
- if (page == NULL) {
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- if (*(u32 *)kmap(page) != VMCS12_REVISION) {
- kunmap(page);
- nested_release_page_clean(page);
- nested_vmx_failInvalid(vcpu);
- return kvm_skip_emulated_instruction(vcpu);
- }
- kunmap(page);
- nested_release_page_clean(page);
- vmx->nested.vmxon_ptr = vmptr;
- break;
- case EXIT_REASON_VMCLEAR:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- case EXIT_REASON_VMPTRLD:
- if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_INVALID_ADDRESS);
- return kvm_skip_emulated_instruction(vcpu);
- }
-
- if (vmptr == vmx->nested.vmxon_ptr) {
- nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_VMXON_POINTER);
- return kvm_skip_emulated_instruction(vcpu);
- }
- break;
- default:
- return 1; /* shouldn't happen */
- }
-
- if (vmpointer)
- *vmpointer = vmptr;
return 0;
}
@@ -7048,6 +6990,8 @@ out_msr_bitmap:
static int handle_vmon(struct kvm_vcpu *vcpu)
{
int ret;
+ gpa_t vmptr;
+ struct page *page;
struct vcpu_vmx *vmx = to_vmx(vcpu);
const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
@@ -7077,9 +7021,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
return 1;
}
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
-
+
+ /*
+ * SDM 3: 24.11.5
+ * The first 4 bytes of VMXON region contain the supported
+ * VMCS revision identifier
+ *
+ * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+ * which replaces physical address width with 32
+ */
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ page = nested_get_page(vcpu, vmptr);
+ if (page == NULL) {
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ if (*(u32 *)kmap(page) != VMCS12_REVISION) {
+ kunmap(page);
+ nested_release_page_clean(page);
+ nested_vmx_failInvalid(vcpu);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+ kunmap(page);
+ nested_release_page_clean(page);
+
+ vmx->nested.vmxon_ptr = vmptr;
ret = enter_vmx_operation(vcpu);
if (ret)
return ret;
@@ -7195,9 +7167,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vmx);
@@ -7527,9 +7509,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
+ if (nested_vmx_get_vmptr(vcpu, &vmptr))
return 1;
+ if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
+ if (vmptr == vmx->nested.vmxon_ptr) {
+ nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
+ return kvm_skip_emulated_instruction(vcpu);
+ }
+
if (vmx->nested.current_vmptr != vmptr) {
struct vmcs12 *new_vmcs12;
struct page *page;
@@ -7895,11 +7887,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
{
unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
int cr = exit_qualification & 15;
- int reg = (exit_qualification >> 8) & 15;
- unsigned long val = kvm_register_readl(vcpu, reg);
+ int reg;
+ unsigned long val;
switch ((exit_qualification >> 4) & 3) {
case 0: /* mov to cr */
+ reg = (exit_qualification >> 8) & 15;
+ val = kvm_register_readl(vcpu, reg);
switch (cr) {
case 0:
if (vmcs12->cr0_guest_host_mask &
@@ -7954,6 +7948,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
* lmsw can change bits 1..3 of cr0, and only set bit 0 of
* cr0. Other attempted changes are ignored, with no exit.
*/
+ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
if (vmcs12->cr0_guest_host_mask & 0xe &
(val ^ vmcs12->cr0_read_shadow))
return true;
@@ -8114,7 +8109,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_PREEMPTION_TIMER:
return false;
case EXIT_REASON_PML_FULL:
- /* We don't expose PML support to L1. */
+ /* We emulate PML support to L1. */
return false;
default:
return true;
@@ -9364,13 +9359,20 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exit_reason;
+ unsigned long exit_qualification = vcpu->arch.exit_qualification;
- if (fault->error_code & PFERR_RSVD_MASK)
+ if (vmx->nested.pml_full) {
+ exit_reason = EXIT_REASON_PML_FULL;
+ vmx->nested.pml_full = false;
+ exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+ } else if (fault->error_code & PFERR_RSVD_MASK)
exit_reason = EXIT_REASON_EPT_MISCONFIG;
else
exit_reason = EXIT_REASON_EPT_VIOLATION;
- nested_vmx_vmexit(vcpu, exit_reason, 0, vcpu->arch.exit_qualification);
+
+ nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
}
@@ -9713,6 +9715,22 @@ static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
return 0;
}
+static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u64 address = vmcs12->pml_address;
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !IS_ALIGNED(address, 4096) ||
+ address >> maxphyaddr)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
struct vmx_msr_entry *e)
{
@@ -9886,7 +9904,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
bool from_vmentry, u32 *entry_failure_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 exec_control;
+ u32 exec_control, vmcs12_exec_ctrl;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10017,8 +10035,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
- CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
- exec_control |= vmcs12->secondary_vm_exec_control;
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
+ vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
+ ~SECONDARY_EXEC_ENABLE_PML;
+ exec_control |= vmcs12_exec_ctrl;
+ }
if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
vmcs_write64(EOI_EXIT_BITMAP0,
@@ -10248,6 +10269,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_pml_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
vmx->nested.nested_vmx_procbased_ctls_low,
vmx->nested.nested_vmx_procbased_ctls_high) ||
@@ -10266,6 +10290,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmx->nested.nested_vmx_entry_ctls_high))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
!nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
@@ -11143,6 +11170,46 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
kvm_flush_pml_buffers(kvm);
}
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ gpa_t gpa;
+ struct page *page = NULL;
+ u64 *pml_address;
+
+ if (is_guest_mode(vcpu)) {
+ WARN_ON_ONCE(vmx->nested.pml_full);
+
+ /*
+ * Check if PML is enabled for the nested guest.
+ * Whether eptp bit 6 is set is already checked
+ * as part of A/D emulation.
+ */
+ vmcs12 = get_vmcs12(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
+
+ if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
+ vmx->nested.pml_full = true;
+ return 1;
+ }
+
+ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+
+ page = nested_get_page(vcpu, vmcs12->pml_address);
+ if (!page)
+ return 0;
+
+ pml_address = kmap(page);
+ pml_address[vmcs12->guest_pml_index--] = gpa;
+ kunmap(page);
+ nested_release_page_clean(page);
+ }
+
+ return 0;
+}
+
static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *memslot,
gfn_t offset, unsigned long mask)
@@ -11502,6 +11569,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
.flush_log_dirty = vmx_flush_log_dirty,
.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+ .write_log_dirty = vmx_write_pml_buffer,
.pre_block = vmx_pre_block,
.post_block = vmx_post_block,
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b38a302858a0..87d3cb901935 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1763,6 +1763,7 @@ u64 get_kvmclock_ns(struct kvm *kvm)
{
struct kvm_arch *ka = &kvm->arch;
struct pvclock_vcpu_time_info hv_clock;
+ u64 ret;
spin_lock(&ka->pvclock_gtod_sync_lock);
if (!ka->use_master_clock) {
@@ -1774,10 +1775,17 @@ u64 get_kvmclock_ns(struct kvm *kvm)
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
spin_unlock(&ka->pvclock_gtod_sync_lock);
+ /* both __this_cpu_read() and rdtsc() should be on the same cpu */
+ get_cpu();
+
kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
&hv_clock.tsc_shift,
&hv_clock.tsc_to_system_mul);
- return __pvclock_read_cycles(&hv_clock, rdtsc());
+ ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+
+ put_cpu();
+
+ return ret;
}
static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
@@ -3288,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
}
}
+#define XSAVE_MXCSR_OFFSET 24
+
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
u64 xstate_bv =
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+ u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
if (boot_cpu_has(X86_FEATURE_XSAVE)) {
/*
@@ -3300,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
* with old userspace.
*/
- if (xstate_bv & ~kvm_supported_xcr0())
+ if (xstate_bv & ~kvm_supported_xcr0() ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
@@ -4818,16 +4831,20 @@ emul_write:
static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
{
- /* TODO: String I/O for in kernel device */
- int r;
+ int r = 0, i;
- if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
- else
- r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
- vcpu->arch.pio.port, vcpu->arch.pio.size,
- pd);
+ for (i = 0; i < vcpu->arch.pio.count; i++) {
+ if (vcpu->arch.pio.in)
+ r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+ vcpu->arch.pio.size, pd);
+ else
+ r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
+ if (r)
+ break;
+ pd += vcpu->arch.pio.size;
+ }
return r;
}
@@ -4865,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
if (vcpu->arch.pio.count)
goto data_avail;
+ memset(vcpu->arch.pio_data, 0, size * count);
+
ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
if (ret) {
data_avail:
@@ -5048,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
if (var.unusable) {
memset(desc, 0, sizeof(*desc));
+ if (base3)
+ *base3 = 0;
return false;
}
@@ -8190,13 +8211,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
slot->base_gfn, level) + 1;
slot->arch.rmap[i] =
- kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
+ kvzalloc(lpages * sizeof(*slot->arch.rmap[i]), GFP_KERNEL);
if (!slot->arch.rmap[i])
goto out_free;
if (i == 0)
continue;
- linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+ linfo = kvzalloc(lpages * sizeof(*linfo), GFP_KERNEL);
if (!linfo)
goto out_free;
@@ -8373,10 +8394,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (vcpu->arch.pv.pv_unhalted)
return true;
- if (atomic_read(&vcpu->arch.nmi_queued))
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ (vcpu->arch.nmi_pending &&
+ kvm_x86_ops->nmi_allowed(vcpu)))
return true;
- if (kvm_test_request(KVM_REQ_SMI, vcpu))
+ if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ (vcpu->arch.smi_pending && !is_smm(vcpu)))
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
@@ -8583,8 +8607,7 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
return true;
else
- return !kvm_event_needs_reinjection(vcpu) &&
- kvm_x86_ops->interrupt_allowed(vcpu);
+ return kvm_can_do_async_pf(vcpu);
}
void kvm_arch_start_assignment(struct kvm *kvm)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 7e48807b2fa1..45a53dfe1859 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -55,7 +55,7 @@ ENTRY(csum_partial_copy_generic)
movq %r12, 3*8(%rsp)
movq %r14, 4*8(%rsp)
movq %r13, 5*8(%rsp)
- movq %rbp, 6*8(%rsp)
+ movq %r15, 6*8(%rsp)
movq %r8, (%rsp)
movq %r9, 1*8(%rsp)
@@ -74,7 +74,7 @@ ENTRY(csum_partial_copy_generic)
/* main loop. clear in 64 byte blocks */
/* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
/* r11: temp3, rdx: temp4, r12 loopcnt */
- /* r10: temp5, rbp: temp6, r14 temp7, r13 temp8 */
+ /* r10: temp5, r15: temp6, r14 temp7, r13 temp8 */
.p2align 4
.Lloop:
source
@@ -89,7 +89,7 @@ ENTRY(csum_partial_copy_generic)
source
movq 32(%rdi), %r10
source
- movq 40(%rdi), %rbp
+ movq 40(%rdi), %r15
source
movq 48(%rdi), %r14
source
@@ -103,7 +103,7 @@ ENTRY(csum_partial_copy_generic)
adcq %r11, %rax
adcq %rdx, %rax
adcq %r10, %rax
- adcq %rbp, %rax
+ adcq %r15, %rax
adcq %r14, %rax
adcq %r13, %rax
@@ -121,7 +121,7 @@ ENTRY(csum_partial_copy_generic)
dest
movq %r10, 32(%rsi)
dest
- movq %rbp, 40(%rsi)
+ movq %r15, 40(%rsi)
dest
movq %r14, 48(%rsi)
dest
@@ -203,7 +203,7 @@ ENTRY(csum_partial_copy_generic)
movq 3*8(%rsp), %r12
movq 4*8(%rsp), %r14
movq 5*8(%rsp), %r13
- movq 6*8(%rsp), %rbp
+ movq 6*8(%rsp), %r15
addq $7*8, %rsp
ret
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 5761a4f19455..ab2d1d73e9e7 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -5,6 +5,7 @@
* kernel starts. This file is included in the compressed kernel and
* normally linked in the regular.
*/
+#include <asm/asm.h>
#include <asm/kaslr.h>
#include <asm/msr.h>
#include <asm/archrandom.h>
@@ -79,7 +80,7 @@ unsigned long kaslr_get_random_long(const char *purpose)
}
/* Circular multiply for better bit diffusion */
- asm("mul %3"
+ asm(_ASM_MUL "%3"
: "=a" (random), "=d" (raw)
: "a" (random), "rm" (mix_const));
random += raw;
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 04210a29dd60..adab1595f4bd 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -13,7 +13,7 @@ static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
if (pmd_present(*pmd))
continue;
- set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
+ set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
}
}
@@ -30,6 +30,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
if (next > end)
next = end;
+ if (info->direct_gbpages) {
+ pud_t pudval;
+
+ if (pud_present(*pud))
+ continue;
+
+ addr &= PUD_MASK;
+ pudval = __pud((addr - info->offset) | info->page_flag);
+ set_pud(pud, pudval);
+ continue;
+ }
+
if (pud_present(*pud)) {
pmd = pmd_offset(pud, 0);
ident_pmd_init(info, pmd, addr, next);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 138bad2fb6bc..cbc87ea98751 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -5,7 +5,7 @@
#include <linux/memblock.h>
#include <linux/bootmem.h> /* for max_low_pfn */
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/page.h>
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index f34d275ee201..99fb83819a5f 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -48,7 +48,7 @@
#include <asm/sections.h>
#include <asm/paravirt.h>
#include <asm/setup.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/page_types.h>
#include <asm/init.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 745e5e183169..95651dc58e09 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -50,7 +50,7 @@
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/init.h>
#include <asm/uv/uv.h>
#include <asm/setup.h>
@@ -94,10 +94,10 @@ __setup("noexec32=", nonx32_setup);
*/
void sync_global_pgds(unsigned long start, unsigned long end)
{
- unsigned long address;
+ unsigned long addr;
- for (address = start; address <= end; address += PGDIR_SIZE) {
- pgd_t *pgd_ref = pgd_offset_k(address);
+ for (addr = start; addr <= end; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+ pgd_t *pgd_ref = pgd_offset_k(addr);
const p4d_t *p4d_ref;
struct page *page;
@@ -106,7 +106,7 @@ void sync_global_pgds(unsigned long start, unsigned long end)
* handle synchonization on p4d level.
*/
BUILD_BUG_ON(pgd_none(*pgd_ref));
- p4d_ref = p4d_offset(pgd_ref, address);
+ p4d_ref = p4d_offset(pgd_ref, addr);
if (p4d_none(*p4d_ref))
continue;
@@ -117,8 +117,8 @@ void sync_global_pgds(unsigned long start, unsigned long end)
p4d_t *p4d;
spinlock_t *pgt_lock;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- p4d = p4d_offset(pgd, address);
+ pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+ p4d = p4d_offset(pgd, addr);
/* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index e4f7b25df18e..bbc558b88a88 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -14,7 +14,7 @@
#include <linux/vmalloc.h>
#include <linux/mmiotrace.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/e820/api.h>
#include <asm/fixmap.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 6b7ce6279133..aca6295350f3 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -100,5 +100,6 @@ void __init initmem_init(void)
printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
(ulong) pfn_to_kaddr(highstart_pfn));
+ __vmalloc_start_set = true;
setup_bootmem_allocator();
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 56b22fa504df..c8520b2c62d2 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -24,6 +24,7 @@
#include <asm/pgalloc.h>
#include <asm/proto.h>
#include <asm/pat.h>
+#include <asm/set_memory.h>
/*
* The current flushing context - we pass it instead of 5 arguments:
@@ -185,7 +186,7 @@ static void cpa_flush_range(unsigned long start, int numpages, int cache)
unsigned int i, level;
unsigned long addr;
- BUG_ON(irqs_disabled());
+ BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
WARN_ON(PAGE_ALIGN(start) != start);
on_each_cpu(__cpa_flush_range, NULL, 1);
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index 38868adf07ea..f6ae6830b341 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -9,7 +9,7 @@
#include <linux/mmiotrace.h>
static unsigned long mmio_address;
-module_param(mmio_address, ulong, 0);
+module_param_hw(mmio_address, ulong, iomem, 0);
MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
"(or 8 MB if read_far is non-zero).");
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 14f840df1d95..f58939393eef 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <linux/bpf.h>
int bpf_jit_enable __read_mostly;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 6fa84d531f4f..7b4307163eac 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -406,50 +406,3 @@ void __init pcibios_resource_survey(void)
*/
ioapic_insert_resources();
}
-
-static const struct vm_operations_struct pci_mmap_ops = {
- .access = generic_access_phys,
-};
-
-int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
- enum pci_mmap_state mmap_state, int write_combine)
-{
- unsigned long prot;
-
- /* I/O space cannot be accessed via normal processor loads and
- * stores on this platform.
- */
- if (mmap_state == pci_mmap_io)
- return -EINVAL;
-
- prot = pgprot_val(vma->vm_page_prot);
-
- /*
- * Return error if pat is not enabled and write_combine is requested.
- * Caller can followup with UC MINUS request and add a WC mtrr if there
- * is a free mtrr slot.
- */
- if (!pat_enabled() && write_combine)
- return -EINVAL;
-
- if (pat_enabled() && write_combine)
- prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
- else if (pat_enabled() || boot_cpu_data.x86 > 3)
- /*
- * ioremap() and ioremap_nocache() defaults to UC MINUS for now.
- * To avoid attribute conflicts, request UC MINUS here
- * as well.
- */
- prot |= cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
-
- vma->vm_page_prot = __pgprot(prot);
-
- if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
- vma->vm_end - vma->vm_start,
- vma->vm_page_prot))
- return -EAGAIN;
-
- vma->vm_ops = &pci_mmap_ops;
-
- return 0;
-}
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 29e9ba6ace9d..c1bdb9edcae7 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -11,7 +11,7 @@
#include <asm/pci_x86.h>
#include <asm/e820/types.h>
#include <asm/pci-functions.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
/* BIOS32 signature: "_32_" */
#define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index a15cf815ac4e..43b96f5f78ba 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -49,7 +49,7 @@
#include <asm/efi.h>
#include <asm/e820/api.h>
#include <asm/time.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/tlbflush.h>
#include <asm/x86_init.h>
#include <asm/uv/uv.h>
@@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void)
/*
* We don't do virtual mode, since we don't do runtime services, on
- * non-native EFI
+ * non-native EFI. With efi=old_map, we don't do runtime services in
+ * kexec kernel because in the initial boot something else might
+ * have been mapped at these virtual addresses.
*/
- if (!efi_is_native()) {
+ if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
efi_memmap_unmap();
clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c488625c9712..eb8dff15a7f6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -71,11 +71,13 @@ static void __init early_code_mapping_set_exec(int executable)
pgd_t * __init efi_call_phys_prolog(void)
{
- unsigned long vaddress;
- pgd_t *save_pgd;
+ unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+ pgd_t *save_pgd, *pgd_k, *pgd_efi;
+ p4d_t *p4d, *p4d_k, *p4d_efi;
+ pud_t *pud;
int pgd;
- int n_pgds;
+ int n_pgds, i, j;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
save_pgd = (pgd_t *)read_cr3();
@@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void)
n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
+ /*
+ * Build 1:1 identity mapping for efi=old_map usage. Note that
+ * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+ * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+ * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+ * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+ * This means here we can only reuse the PMD tables of the direct mapping.
+ */
for (pgd = 0; pgd < n_pgds; pgd++) {
- save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
- vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
- set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+ addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+ vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+ pgd_efi = pgd_offset_k(addr_pgd);
+ save_pgd[pgd] = *pgd_efi;
+
+ p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+ if (!p4d) {
+ pr_err("Failed to allocate p4d table!\n");
+ goto out;
+ }
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ addr_p4d = addr_pgd + i * P4D_SIZE;
+ p4d_efi = p4d + p4d_index(addr_p4d);
+
+ pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+ if (!pud) {
+ pr_err("Failed to allocate pud table!\n");
+ goto out;
+ }
+
+ for (j = 0; j < PTRS_PER_PUD; j++) {
+ addr_pud = addr_p4d + j * PUD_SIZE;
+
+ if (addr_pud > (max_pfn << PAGE_SHIFT))
+ break;
+
+ vaddr = (unsigned long)__va(addr_pud);
+
+ pgd_k = pgd_offset_k(vaddr);
+ p4d_k = p4d_offset(pgd_k, vaddr);
+ pud[j] = *pud_offset(p4d_k, vaddr);
+ }
+ }
}
out:
__flush_tlb_all();
@@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
/*
* After the lock is released, the original page table is restored.
*/
- int pgd_idx;
+ int pgd_idx, i;
int nr_pgds;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
if (!efi_enabled(EFI_OLD_MEMMAP)) {
write_cr3((unsigned long)save_pgd);
@@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
- for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+ for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+ pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
+ if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+ continue;
+
+ for (i = 0; i < PTRS_PER_P4D; i++) {
+ p4d = p4d_offset(pgd,
+ pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+ if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+ continue;
+
+ pud = (pud_t *)p4d_page_vaddr(*p4d);
+ pud_free(&init_mm, pud);
+ }
+
+ p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+ p4d_free(&init_mm, p4d);
+ }
+
kfree(save_pgd);
__flush_tlb_all();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 26615991d69c..e0cf95a83f3f 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -360,6 +360,9 @@ void __init efi_free_boot_services(void)
free_bootmem_late(start, size);
}
+ if (!num_entries)
+ return;
+
new_size = efi.memmap.desc_size * num_entries;
new_phys = efi_memmap_alloc(num_entries);
if (!new_phys) {
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 6a61194ffd58..a6e21fee22ea 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -104,7 +104,7 @@ static int set_up_temporary_mappings(void)
{
struct x86_mapping_info info = {
.alloc_pgt_page = alloc_pgt_page,
- .pmd_flag = __PAGE_KERNEL_LARGE_EXEC,
+ .page_flag = __PAGE_KERNEL_LARGE_EXEC,
.offset = __PAGE_OFFSET,
};
unsigned long mstart, mend;
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 5db706f14111..a163a90af4aa 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -2,7 +2,7 @@
#include <linux/slab.h>
#include <linux/memblock.h>
-#include <asm/cacheflush.h>
+#include <asm/set_memory.h>
#include <asm/pgtable.h>
#include <asm/realmode.h>
#include <asm/tlbflush.h>
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index a5c9910d234f..09a085bde0d4 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -125,7 +125,7 @@ int poke_user(struct task_struct *child, long addr, long data)
else if ((addr >= offsetof(struct user, u_debugreg[0])) &&
(addr <= offsetof(struct user, u_debugreg[7]))) {
addr -= offsetof(struct user, u_debugreg[0]);
- addr = addr >> 2;
+ addr = addr >> 3;
if ((addr == 4) || (addr == 5))
return -EIO;
child->thread.arch.debugregs[addr] = data;
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 46a9df99f3c5..7e1d35b6ad5c 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -2,16 +2,9 @@
#include <linux/sched.h>
#include <linux/elf.h>
#include <linux/crypto.h>
+#include <linux/kbuild.h>
#include <asm/mman.h>
-#define DEFINE(sym, val) \
- asm volatile("\n->" #sym " %0 " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : : )
-
-#define OFFSET(sym, str, mem) \
- DEFINE(sym, offsetof(struct str, mem));
-
void foo(void)
{
#include <common-offsets.h>
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index a732bc2b9dfc..f33eef4ebd12 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -142,9 +142,7 @@ static void __init xen_banner(void)
struct xen_extraversion extra;
HYPERVISOR_xen_version(XENVER_extraversion, &extra);
- pr_info("Booting paravirtualized kernel %son %s\n",
- xen_feature(XENFEAT_auto_translated_physmap) ?
- "with PVH extensions " : "", pv_info.name);
+ pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
printk(KERN_INFO "Xen version: %d.%d%s%s\n",
version >> 16, version & 0xffff, extra.extraversion,
xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
@@ -277,31 +275,19 @@ static bool __init xen_check_mwait(void)
static bool __init xen_check_xsave(void)
{
- unsigned int err, eax, edx;
+ unsigned int cx, xsave_mask;
- /*
- * Xen 4.0 and older accidentally leaked the host XSAVE flag into guest
- * view, despite not being able to support guests using the
- * functionality. Probe for the actual availability of XSAVE by seeing
- * whether xgetbv executes successfully or raises #UD.
- */
- asm volatile("1: .byte 0x0f,0x01,0xd0\n\t" /* xgetbv */
- "xor %[err], %[err]\n"
- "2:\n\t"
- ".pushsection .fixup,\"ax\"\n\t"
- "3: movl $1,%[err]\n\t"
- "jmp 2b\n\t"
- ".popsection\n\t"
- _ASM_EXTABLE(1b, 3b)
- : [err] "=r" (err), "=a" (eax), "=d" (edx)
- : "c" (0));
-
- return err == 0;
+ cx = cpuid_ecx(1);
+
+ xsave_mask = (1 << (X86_FEATURE_XSAVE % 32)) |
+ (1 << (X86_FEATURE_OSXSAVE % 32));
+
+ /* Xen will set CR4.OSXSAVE if supported and not disabled by force */
+ return (cx & xsave_mask) == xsave_mask;
}
static void __init xen_init_capabilities(void)
{
- setup_clear_cpu_cap(X86_BUG_SYSRET_SS_ATTRS);
setup_force_cpu_cap(X86_FEATURE_XENPV);
setup_clear_cpu_cap(X86_FEATURE_DCA);
setup_clear_cpu_cap(X86_FEATURE_APERFMPERF);
@@ -317,10 +303,7 @@ static void __init xen_init_capabilities(void)
else
setup_clear_cpu_cap(X86_FEATURE_MWAIT);
- if (xen_check_xsave()) {
- setup_force_cpu_cap(X86_FEATURE_XSAVE);
- setup_force_cpu_cap(X86_FEATURE_OSXSAVE);
- } else {
+ if (!xen_check_xsave()) {
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_OSXSAVE);
}
@@ -972,15 +955,10 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
void xen_setup_shared_info(void)
{
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- set_fixmap(FIX_PARAVIRT_BOOTMAP,
- xen_start_info->shared_info);
+ set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
- HYPERVISOR_shared_info =
- (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
- } else
- HYPERVISOR_shared_info =
- (struct shared_info *)__va(xen_start_info->shared_info);
+ HYPERVISOR_shared_info =
+ (struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
#ifndef CONFIG_SMP
/* In UP this is as good a place as any to set up shared info */
@@ -988,6 +966,13 @@ void xen_setup_shared_info(void)
#endif
xen_setup_mfn_list_list();
+
+ /*
+ * Now that shared info is set up we can start using routines that
+ * point to pvclock area.
+ */
+ if (system_state == SYSTEM_BOOTING)
+ xen_init_time_ops();
}
/* This is called once we have the cpu_possible_mask */
@@ -1286,8 +1271,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
x86_init.oem.arch_setup = xen_arch_setup;
x86_init.oem.banner = xen_banner;
- xen_init_time_ops();
-
/*
* Set up some pagetable state before starting to set any ptes.
*/
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 5e375a5e815f..3be06f3caf3c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -42,7 +42,7 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr)
}
EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine);
-void xen_flush_tlb_all(void)
+static void xen_flush_tlb_all(void)
{
struct mmuext_op *op;
struct multicall_space mcs;
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 9d9ae6650aa1..1f386d7fdf70 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -355,10 +355,8 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
pteval_t flags = val & PTE_FLAGS_MASK;
unsigned long mfn;
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- mfn = __pfn_to_mfn(pfn);
- else
- mfn = pfn;
+ mfn = __pfn_to_mfn(pfn);
+
/*
* If there's no mfn for the pfn, then just create an
* empty non-present pte. Unfortunately this loses
@@ -647,9 +645,6 @@ static int __xen_pgd_walk(struct mm_struct *mm, pgd_t *pgd,
limit--;
BUG_ON(limit >= FIXADDR_TOP);
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return 0;
-
/*
* 64-bit has a great big hole in the middle of the address
* space, which contains the Xen mappings. On 32-bit these
@@ -1289,9 +1284,6 @@ static void __init xen_pagetable_cleanhighmap(void)
static void __init xen_pagetable_p2m_setup(void)
{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
xen_vmalloc_p2m_tree();
#ifdef CONFIG_X86_64
@@ -1314,8 +1306,7 @@ static void __init xen_pagetable_init(void)
xen_build_mfn_list_list();
/* Remap memory freed due to conflicts with E820 map */
- if (!xen_feature(XENFEAT_auto_translated_physmap))
- xen_remap_memory();
+ xen_remap_memory();
xen_setup_shared_info();
}
@@ -1925,21 +1916,20 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
/* Zap identity mapping */
init_level4_pgt[0] = __pgd(0);
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Pre-constructed entries are in pfn, so convert to mfn */
- /* L4[272] -> level3_ident_pgt
- * L4[511] -> level3_kernel_pgt */
- convert_pfn_mfn(init_level4_pgt);
+ /* Pre-constructed entries are in pfn, so convert to mfn */
+ /* L4[272] -> level3_ident_pgt */
+ /* L4[511] -> level3_kernel_pgt */
+ convert_pfn_mfn(init_level4_pgt);
- /* L3_i[0] -> level2_ident_pgt */
- convert_pfn_mfn(level3_ident_pgt);
- /* L3_k[510] -> level2_kernel_pgt
- * L3_k[511] -> level2_fixmap_pgt */
- convert_pfn_mfn(level3_kernel_pgt);
+ /* L3_i[0] -> level2_ident_pgt */
+ convert_pfn_mfn(level3_ident_pgt);
+ /* L3_k[510] -> level2_kernel_pgt */
+ /* L3_k[511] -> level2_fixmap_pgt */
+ convert_pfn_mfn(level3_kernel_pgt);
+
+ /* L3_k[511][506] -> level1_fixmap_pgt */
+ convert_pfn_mfn(level2_fixmap_pgt);
- /* L3_k[511][506] -> level1_fixmap_pgt */
- convert_pfn_mfn(level2_fixmap_pgt);
- }
/* We get [511][511] and have Xen's version of level2_kernel_pgt */
l3 = m2v(pgd[pgd_index(__START_KERNEL_map)].pgd);
l2 = m2v(l3[pud_index(__START_KERNEL_map)].pud);
@@ -1962,34 +1952,30 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
if (i && i < pgd_index(__START_KERNEL_map))
init_level4_pgt[i] = ((pgd_t *)xen_start_info->pt_base)[i];
- if (!xen_feature(XENFEAT_auto_translated_physmap)) {
- /* Make pagetable pieces RO */
- set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
- set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
- set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
- set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
- set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
-
- /* Pin down new L4 */
- pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
- PFN_DOWN(__pa_symbol(init_level4_pgt)));
-
- /* Unpin Xen-provided one */
- pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
+ /* Make pagetable pieces RO */
+ set_page_prot(init_level4_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+ set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
+ set_page_prot(level1_fixmap_pgt, PAGE_KERNEL_RO);
+
+ /* Pin down new L4 */
+ pin_pagetable_pfn(MMUEXT_PIN_L4_TABLE,
+ PFN_DOWN(__pa_symbol(init_level4_pgt)));
+
+ /* Unpin Xen-provided one */
+ pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
- /*
- * At this stage there can be no user pgd, and no page
- * structure to attach it to, so make sure we just set kernel
- * pgd.
- */
- xen_mc_batch();
- __xen_write_cr3(true, __pa(init_level4_pgt));
- xen_mc_issue(PARAVIRT_LAZY_CPU);
- } else
- native_write_cr3(__pa(init_level4_pgt));
+ /*
+ * At this stage there can be no user pgd, and no page structure to
+ * attach it to, so make sure we just set kernel pgd.
+ */
+ xen_mc_batch();
+ __xen_write_cr3(true, __pa(init_level4_pgt));
+ xen_mc_issue(PARAVIRT_LAZY_CPU);
/* We can't that easily rip out L3 and L2, as the Xen pagetables are
* set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
@@ -2025,7 +2011,8 @@ static unsigned long __init xen_read_phys_ulong(phys_addr_t addr)
/*
* Translate a virtual address to a physical one without relying on mapped
- * page tables.
+ * page tables. Don't rely on big pages being aligned in (guest) physical
+ * space!
*/
static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
{
@@ -2046,7 +2033,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
sizeof(pud)));
if (!pud_present(pud))
return 0;
- pa = pud_pfn(pud) << PAGE_SHIFT;
+ pa = pud_val(pud) & PTE_PFN_MASK;
if (pud_large(pud))
return pa + (vaddr & ~PUD_MASK);
@@ -2054,7 +2041,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr)
sizeof(pmd)));
if (!pmd_present(pmd))
return 0;
- pa = pmd_pfn(pmd) << PAGE_SHIFT;
+ pa = pmd_val(pmd) & PTE_PFN_MASK;
if (pmd_large(pmd))
return pa + (vaddr & ~PMD_MASK);
@@ -2402,9 +2389,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
static void __init xen_post_allocator_init(void)
{
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
@@ -2510,9 +2494,6 @@ void __init xen_init_mmu_ops(void)
{
x86_init.paging.pagetable_init = xen_pagetable_init;
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
pv_mmu_ops = xen_mmu_ops;
memset(dummy_mapping, 0xff, PAGE_SIZE);
@@ -2649,9 +2630,6 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order,
* this function are redundant and can be ignored.
*/
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return 0;
-
if (unlikely(order > MAX_CONTIG_ORDER))
return -ENOMEM;
@@ -2688,9 +2666,6 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order)
int success;
unsigned long vstart;
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
-
if (unlikely(order > MAX_CONTIG_ORDER))
return;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 090c7eb4dca9..a1895a8e85c1 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -406,7 +406,7 @@ static void __init xen_time_init(void)
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
}
-void __init xen_init_time_ops(void)
+void __ref xen_init_time_ops(void)
{
pv_time_ops = xen_time_ops;