summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig3
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/eboot.c10
-rw-r--r--arch/x86/boot/tools/build.c7
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/entry/calling.h2
-rw-r--r--arch/x86/entry/entry_32.S13
-rw-r--r--arch/x86/entry/entry_64.S13
-rw-r--r--arch/x86/include/asm/alternative-asm.h20
-rw-r--r--arch/x86/include/asm/alternative.h11
-rw-r--r--arch/x86/include/asm/asm.h57
-rw-r--r--arch/x86/include/asm/atomic.h8
-rw-r--r--arch/x86/include/asm/atomic64_64.h8
-rw-r--r--arch/x86/include/asm/bitops.h9
-rw-r--r--arch/x86/include/asm/bug.h98
-rw-r--r--arch/x86/include/asm/cpufeature.h82
-rw-r--r--arch/x86/include/asm/efi.h1
-rw-r--r--arch/x86/include/asm/elf.h3
-rw-r--r--arch/x86/include/asm/extable.h3
-rw-r--r--arch/x86/include/asm/fpu/internal.h4
-rw-r--r--arch/x86/include/asm/futex.h6
-rw-r--r--arch/x86/include/asm/io.h12
-rw-r--r--arch/x86/include/asm/jump_label.h80
-rw-r--r--arch/x86/include/asm/local.h8
-rw-r--r--arch/x86/include/asm/paravirt_types.h56
-rw-r--r--arch/x86/include/asm/percpu.h8
-rw-r--r--arch/x86/include/asm/pgtable_types.h2
-rw-r--r--arch/x86/include/asm/preempt.h2
-rw-r--r--arch/x86/include/asm/ptrace.h2
-rw-r--r--arch/x86/include/asm/qspinlock.h15
-rw-r--r--arch/x86/include/asm/refcount.h79
-rw-r--r--arch/x86/include/asm/rmwcc.h69
-rw-r--r--arch/x86/include/asm/suspend.h8
-rw-r--r--arch/x86/include/asm/suspend_32.h4
-rw-r--r--arch/x86/include/asm/uaccess.h22
-rw-r--r--arch/x86/include/asm/xen/events.h2
-rw-r--r--arch/x86/kernel/amd_gart_64.c6
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c2
-rw-r--r--arch/x86/kernel/fpu/signal.c1
-rw-r--r--arch/x86/kernel/jump_label.c62
-rw-r--r--arch/x86/kernel/kprobes/core.c38
-rw-r--r--arch/x86/kernel/macros.S16
-rw-r--r--arch/x86/kernel/module.c6
-rw-r--r--arch/x86/kernel/pci-swiotlb.c2
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/time.c2
-rw-r--r--arch/x86/kernel/traps.c16
-rw-r--r--arch/x86/kernel/tsc.c6
-rw-r--r--arch/x86/kvm/svm.c6
-rw-r--r--arch/x86/kvm/vmx.c6
-rw-r--r--arch/x86/lib/checksum_32.S4
-rw-r--r--arch/x86/lib/copy_user_64.S90
-rw-r--r--arch/x86/lib/csum-copy_64.S8
-rw-r--r--arch/x86/lib/getuser.S12
-rw-r--r--arch/x86/lib/putuser.S10
-rw-r--r--arch/x86/lib/usercopy_32.c126
-rw-r--r--arch/x86/lib/usercopy_64.c4
-rw-r--r--arch/x86/mm/extable.c114
-rw-r--r--arch/x86/mm/fault.c35
-rw-r--r--arch/x86/mm/pgtable.c10
-rw-r--r--arch/x86/platform/efi/early_printk.c8
-rw-r--r--arch/x86/platform/efi/efi_64.c10
-rw-r--r--arch/x86/platform/efi/quirks.c78
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c17
-rw-r--r--arch/x86/platform/ts5500/ts5500.c1
-rw-r--r--arch/x86/power/Makefile2
-rw-r--r--arch/x86/power/hibernate.c248
-rw-r--r--arch/x86/power/hibernate_32.c52
-rw-r--r--arch/x86/power/hibernate_64.c224
-rw-r--r--arch/x86/power/hibernate_asm_32.S37
-rw-r--r--arch/x86/power/hibernate_asm_64.S2
-rw-r--r--arch/x86/tools/relocs.c10
-rw-r--r--arch/x86/um/asm/elf.h3
-rw-r--r--arch/x86/xen/enlighten.c1
-rw-r--r--arch/x86/xen/enlighten_pvh.c1
-rw-r--r--arch/x86/xen/platform-pci-unplug.c1
-rw-r--r--arch/x86/xen/pmu.c1
79 files changed, 1176 insertions, 842 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1a0be022f91d..45b94fa9e98c 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -119,6 +119,7 @@ config X86
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if X86_64
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS if MMU
@@ -2422,7 +2423,7 @@ menu "Power management and ACPI options"
config ARCH_HIBERNATION_HEADER
def_bool y
- depends on X86_64 && HIBERNATION
+ depends on HIBERNATION
source "kernel/power/Kconfig"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8f6e7eb8ae9f..5b562e464009 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -193,7 +193,6 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
# does binutils support specific instructions?
asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
-asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
avx512_instr :=$(call as-instr,vpmovm2b %k1$(comma)%zmm5,-DCONFIG_AS_AVX512=1)
@@ -237,6 +236,13 @@ archscripts: scripts_basic
archheaders:
$(Q)$(MAKE) $(build)=arch/x86/entry/syscalls all
+archmacros:
+ $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s
+
+ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,-
+export ASM_MACRO_FLAGS
+KBUILD_CFLAGS += $(ASM_MACRO_FLAGS)
+
###
# Kernel objects
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 28764dacf018..466f66c8a7f8 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -37,6 +37,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
+KBUILD_CFLAGS += -Wno-pointer-sign
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
GCOV_PROFILE := n
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 1458b1700fc7..8b4c5e001157 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -738,6 +738,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
struct desc_struct *desc;
void *handle;
efi_system_table_t *_table;
+ unsigned long cmdline_paddr;
efi_early = c;
@@ -756,6 +757,15 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
setup_boot_services32(efi_early);
/*
+ * make_boot_params() may have been called before efi_main(), in which
+ * case this is the second time we parse the cmdline. This is ok,
+ * parsing the cmdline multiple times does not have side-effects.
+ */
+ cmdline_paddr = ((u64)hdr->cmd_line_ptr |
+ ((u64)boot_params->ext_cmd_line_ptr << 32));
+ efi_parse_options((char *)cmdline_paddr);
+
+ /*
* If the boot loader gave us a value for secure_boot then we use that,
* otherwise we ask the BIOS.
*/
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index d4e6cd4577e5..bf0e82400358 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -391,6 +391,13 @@ int main(int argc, char ** argv)
die("Unable to mmap '%s': %m", argv[2]);
/* Number of 16-byte paragraphs, including space for a 4-byte CRC */
sys_size = (sz + 15 + 4) / 16;
+#ifdef CONFIG_EFI_STUB
+ /*
+ * COFF requires minimum 32-byte alignment of sections, and
+ * adding a signature is problematic without that alignment.
+ */
+ sys_size = (sys_size + 1) & ~1;
+#endif
/* Patch the setup code with the appropriate size parameters */
buf[0x1f1] = setup_sectors-1;
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 0eb9f92f3717..6c3ab05c231d 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -247,6 +247,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index e32fc1f274d8..ac9ae487cfeb 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -243,6 +243,7 @@ CONFIG_USB_HIDDEV=y
CONFIG_USB=y
CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
CONFIG_USB_MON=y
+CONFIG_USB_XHCI_HCD=y
CONFIG_USB_EHCI_HCD=y
CONFIG_USB_EHCI_TT_NEWSCHED=y
CONFIG_USB_OHCI_HCD=y
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 352e70cd33e8..708b46a54578 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -338,7 +338,7 @@ For 32-bit we have the following conventions - kernel is built with
.macro CALL_enter_from_user_mode
#ifdef CONFIG_CONTEXT_TRACKING
#ifdef HAVE_JUMP_LABEL
- STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+ STATIC_BRANCH_JMP l_yes=.Lafter_call_\@, key=context_tracking_enabled, branch=1
#endif
call enter_from_user_mode
.Lafter_call_\@:
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 2767c625a52c..fbbf1ba57ec6 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -389,6 +389,13 @@
* that register for the time this macro runs
*/
+ /*
+ * The high bits of the CS dword (__csh) are used for
+ * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case
+ * hardware didn't do this for us.
+ */
+ andl $(0x0000ffff), PT_CS(%esp)
+
/* Are we on the entry stack? Bail out if not! */
movl PER_CPU_VAR(cpu_entry_area), %ecx
addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
@@ -407,12 +414,6 @@
/* Load top of task-stack into %edi */
movl TSS_entry2task_stack(%edi), %edi
- /*
- * Clear unused upper bits of the dword containing the word-sized CS
- * slot in pt_regs in case hardware didn't clear it for us.
- */
- andl $(0x0000ffff), PT_CS(%esp)
-
/* Special case - entry from kernel mode via entry stack */
#ifdef CONFIG_VM86
movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 957dfb693ecc..f95dcb209fdf 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1187,6 +1187,16 @@ ENTRY(paranoid_entry)
xorl %ebx, %ebx
1:
+ /*
+ * Always stash CR3 in %r14. This value will be restored,
+ * verbatim, at exit. Needed if paranoid_entry interrupted
+ * another entry that already switched to the user CR3 value
+ * but has not yet returned to userspace.
+ *
+ * This is also why CS (stashed in the "iret frame" by the
+ * hardware at entry) can not be used: this may be a return
+ * to kernel code, but with a user CR3 value.
+ */
SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
ret
@@ -1211,11 +1221,13 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
TRACE_IRQS_IRETQ_DEBUG
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
.Lparanoid_exit_restore:
jmp restore_regs_and_return_to_kernel
@@ -1626,6 +1638,7 @@ end_repeat_nmi:
movq $-1, %rsi
call do_nmi
+ /* Always restore stashed CR3 value (see paranoid_entry) */
RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
testl %ebx, %ebx /* swapgs needed? */
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..8e4ea39e55d0 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -7,16 +7,24 @@
#include <asm/asm.h>
#ifdef CONFIG_SMP
- .macro LOCK_PREFIX
-672: lock
+.macro LOCK_PREFIX_HERE
.pushsection .smp_locks,"a"
.balign 4
- .long 672b - .
+ .long 671f - . # offset
.popsection
- .endm
+671:
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+ LOCK_PREFIX_HERE
+ lock \insn
+.endm
#else
- .macro LOCK_PREFIX
- .endm
+.macro LOCK_PREFIX_HERE
+.endm
+
+.macro LOCK_PREFIX insn:vararg
+.endm
#endif
/*
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4cd6a3b71824..d7faa16622d8 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -31,15 +31,8 @@
*/
#ifdef CONFIG_SMP
-#define LOCK_PREFIX_HERE \
- ".pushsection .smp_locks,\"a\"\n" \
- ".balign 4\n" \
- ".long 671f - .\n" /* offset */ \
- ".popsection\n" \
- "671:"
-
-#define LOCK_PREFIX LOCK_PREFIX_HERE "\n\tlock; "
-
+#define LOCK_PREFIX_HERE "LOCK_PREFIX_HERE\n\t"
+#define LOCK_PREFIX "LOCK_PREFIX "
#else /* ! CONFIG_SMP */
#define LOCK_PREFIX_HERE ""
#define LOCK_PREFIX ""
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 990770f9e76b..21b086786404 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -120,16 +120,32 @@
/* Exception table entry */
#ifdef __ASSEMBLY__
# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- .pushsection "__ex_table","a" ; \
- .balign 4 ; \
- .long (from) - . ; \
- .long (to) - . ; \
- .long (handler) - . ; \
+ ASM_EXTABLE_HANDLE from to handler
+
+.macro ASM_EXTABLE_HANDLE from:req to:req handler:req
+ .pushsection "__ex_table","a"
+ .balign 4
+ .long (\from) - .
+ .long (\to) - .
+ .long (\handler) - .
.popsection
+.endm
+#else /* __ASSEMBLY__ */
+
+# define _ASM_EXTABLE_HANDLE(from, to, handler) \
+ "ASM_EXTABLE_HANDLE from=" #from " to=" #to \
+ " handler=\"" #handler "\"\n\t"
+
+/* For C file, we already have NOKPROBE_SYMBOL macro */
+
+#endif /* __ASSEMBLY__ */
# define _ASM_EXTABLE(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+# define _ASM_EXTABLE_UA(from, to) \
+ _ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
# define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
@@ -145,6 +161,7 @@
_ASM_PTR (entry); \
.popsection
+#ifdef __ASSEMBLY__
.macro ALIGN_DESTINATION
/* check for bad alignment of destination */
movl %edi,%ecx
@@ -165,34 +182,10 @@
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(100b,103b)
- _ASM_EXTABLE(101b,103b)
+ _ASM_EXTABLE_UA(100b, 103b)
+ _ASM_EXTABLE_UA(101b, 103b)
.endm
-
-#else
-# define _EXPAND_EXTABLE_HANDLE(x) #x
-# define _ASM_EXTABLE_HANDLE(from, to, handler) \
- " .pushsection \"__ex_table\",\"a\"\n" \
- " .balign 4\n" \
- " .long (" #from ") - .\n" \
- " .long (" #to ") - .\n" \
- " .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n" \
- " .popsection\n"
-
-# define _ASM_EXTABLE(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
-
-# define _ASM_EXTABLE_FAULT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
-
-# define _ASM_EXTABLE_EX(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
-
-# define _ASM_EXTABLE_REFCOUNT(from, to) \
- _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
-
-/* For C file, we already have NOKPROBE_SYMBOL macro */
-#endif
+#endif /* __ASSEMBLY__ */
#ifndef __ASSEMBLY__
/*
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ce84388e540c..ea3d95275b43 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -82,7 +82,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
*/
static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i);
}
#define arch_atomic_sub_and_test arch_atomic_sub_and_test
@@ -122,7 +122,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
*/
static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e);
}
#define arch_atomic_dec_and_test arch_atomic_dec_and_test
@@ -136,7 +136,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
*/
static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e);
}
#define arch_atomic_inc_and_test arch_atomic_inc_and_test
@@ -151,7 +151,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
*/
static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i);
}
#define arch_atomic_add_negative arch_atomic_add_negative
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 5f851d92eecd..dadc20adba21 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -73,7 +73,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
*/
static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i);
}
#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
@@ -115,7 +115,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
*/
static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e);
}
#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
@@ -129,7 +129,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
*/
static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
{
- GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
+ return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e);
}
#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
@@ -144,7 +144,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
*/
static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i);
}
#define arch_atomic64_add_negative arch_atomic64_add_negative
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 9f645ba57dbb..124f9195eb3e 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -217,8 +217,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
*/
static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr);
}
/**
@@ -264,8 +263,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
*/
static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr);
}
/**
@@ -318,8 +316,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
*/
static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
{
- GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc),
- *addr, "Ir", nr, "%0", c);
+ return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
}
static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 6804d6642767..5090035e6d16 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -4,6 +4,8 @@
#include <linux/stringify.h>
+#ifndef __ASSEMBLY__
+
/*
* Despite that some emulators terminate on UD2, we use it for WARN().
*
@@ -20,53 +22,15 @@
#define LEN_UD2 2
-#ifdef CONFIG_GENERIC_BUG
-
-#ifdef CONFIG_X86_32
-# define __BUG_REL(val) ".long " __stringify(val)
-#else
-# define __BUG_REL(val) ".long " __stringify(val) " - 2b"
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#define _BUG_FLAGS(ins, flags) \
-do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \
- "\t.word %c1" "\t# bug_entry::line\n" \
- "\t.word %c2" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c3\n" \
- ".popsection" \
- : : "i" (__FILE__), "i" (__LINE__), \
- "i" (flags), \
- "i" (sizeof(struct bug_entry))); \
-} while (0)
-
-#else /* !CONFIG_DEBUG_BUGVERBOSE */
-
#define _BUG_FLAGS(ins, flags) \
do { \
- asm volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t.word %c0" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c1\n" \
- ".popsection" \
- : : "i" (flags), \
+ asm volatile("ASM_BUG ins=\"" ins "\" file=%c0 line=%c1 " \
+ "flags=%c2 size=%c3" \
+ : : "i" (__FILE__), "i" (__LINE__), \
+ "i" (flags), \
"i" (sizeof(struct bug_entry))); \
} while (0)
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
-
-#else
-
-#define _BUG_FLAGS(ins, flags) asm volatile(ins)
-
-#endif /* CONFIG_GENERIC_BUG */
-
#define HAVE_ARCH_BUG
#define BUG() \
do { \
@@ -82,4 +46,54 @@ do { \
#include <asm-generic/bug.h>
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_GENERIC_BUG
+
+#ifdef CONFIG_X86_32
+.macro __BUG_REL val:req
+ .long \val
+.endm
+#else
+.macro __BUG_REL val:req
+ .long \val - 2b
+.endm
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ __BUG_REL val=\file # bug_entry::file
+ .word \line # bug_entry::line
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#else /* !CONFIG_DEBUG_BUGVERBOSE */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+1: \ins
+ .pushsection __bug_table,"aw"
+2: __BUG_REL val=1b # bug_entry::bug_addr
+ .word \flags # bug_entry::flags
+ .org 2b+\size
+ .popsection
+.endm
+
+#endif /* CONFIG_DEBUG_BUGVERBOSE */
+
+#else /* CONFIG_GENERIC_BUG */
+
+.macro ASM_BUG ins:req file:req line:req flags:req size:req
+ \ins
+.endm
+
+#endif /* CONFIG_GENERIC_BUG */
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index aced6c9290d6..7d442722ef24 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -2,10 +2,10 @@
#ifndef _ASM_X86_CPUFEATURE_H
#define _ASM_X86_CPUFEATURE_H
-#include <asm/processor.h>
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
#include <asm/asm.h>
#include <linux/bitops.h>
@@ -161,37 +161,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
*/
static __always_inline __pure bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto("1: jmp 6f\n"
- "2:\n"
- ".skip -(((5f-4f) - (2b-1b)) > 0) * "
- "((5f-4f) - (2b-1b)),0x90\n"
- "3:\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 4f - .\n" /* repl offset */
- " .word %P[always]\n" /* always replace */
- " .byte 3b - 1b\n" /* src len */
- " .byte 5f - 4f\n" /* repl len */
- " .byte 3b - 2b\n" /* pad len */
- ".previous\n"
- ".section .altinstr_replacement,\"ax\"\n"
- "4: jmp %l[t_no]\n"
- "5:\n"
- ".previous\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 0\n" /* no replacement */
- " .word %P[feature]\n" /* feature bit */
- " .byte 3b - 1b\n" /* src len */
- " .byte 0\n" /* repl len */
- " .byte 0\n" /* pad len */
- ".previous\n"
- ".section .altinstr_aux,\"ax\"\n"
- "6:\n"
- " testb %[bitnum],%[cap_byte]\n"
- " jnz %l[t_yes]\n"
- " jmp %l[t_no]\n"
- ".previous\n"
+ asm_volatile_goto("STATIC_CPU_HAS bitnum=%[bitnum] "
+ "cap_byte=\"%[cap_byte]\" "
+ "feature=%P[feature] t_yes=%l[t_yes] "
+ "t_no=%l[t_no] always=%P[always]"
: : [feature] "i" (bit),
[always] "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
@@ -226,5 +199,44 @@ t_no:
#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \
boot_cpu_data.x86_model
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+#else /* __ASSEMBLY__ */
+
+.macro STATIC_CPU_HAS bitnum:req cap_byte:req feature:req t_yes:req t_no:req always:req
+1:
+ jmp 6f
+2:
+ .skip -(((5f-4f) - (2b-1b)) > 0) * ((5f-4f) - (2b-1b)),0x90
+3:
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 4f - . /* repl offset */
+ .word \always /* always replace */
+ .byte 3b - 1b /* src len */
+ .byte 5f - 4f /* repl len */
+ .byte 3b - 2b /* pad len */
+ .previous
+ .section .altinstr_replacement,"ax"
+4:
+ jmp \t_no
+5:
+ .previous
+ .section .altinstructions,"a"
+ .long 1b - . /* src offset */
+ .long 0 /* no replacement */
+ .word \feature /* feature bit */
+ .byte 3b - 1b /* src len */
+ .byte 0 /* repl len */
+ .byte 0 /* pad len */
+ .previous
+ .section .altinstr_aux,"ax"
+6:
+ testb \bitnum,\cap_byte
+ jnz \t_yes
+ jmp \t_no
+ .previous
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
#endif /* _ASM_X86_CPUFEATURE_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index cec5fae23eb3..eea40d52ca78 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -140,6 +140,7 @@ extern void __init efi_apply_memmap_quirks(void);
extern int __init efi_reuse_config(u64 tables, int nr_tables);
extern void efi_delete_dummy_variable(void);
extern void efi_switch_mm(struct mm_struct *mm);
+extern void efi_recover_from_page_fault(unsigned long phys_addr);
struct efi_setup_data {
u64 fw_vendor;
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 0d157d2a1e2a..a357031d85b5 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -62,8 +62,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* These are used to set parameters in the core dumps.
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index f9c3a5d502f4..d8c2198d543b 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -29,7 +29,8 @@ struct pt_regs;
(b)->handler = (tmp).handler - (delta); \
} while (0)
-extern int fixup_exception(struct pt_regs *regs, int trapnr);
+extern int fixup_exception(struct pt_regs *regs, int trapnr,
+ unsigned long error_code, unsigned long fault_addr);
extern int fixup_bug(struct pt_regs *regs, int trapnr);
extern bool ex_has_fault_handler(unsigned long ip);
extern void early_fixup_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index a38bf5a1e37a..5f7290e6e954 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -226,7 +226,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu)
"3: movl $-2,%[err]\n\t" \
"jmp 2b\n\t" \
".popsection\n\t" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: [err] "=r" (err) \
: "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \
: "memory")
@@ -528,7 +528,7 @@ static inline void fpregs_activate(struct fpu *fpu)
static inline void
switch_fpu_prepare(struct fpu *old_fpu, int cpu)
{
- if (old_fpu->initialized) {
+ if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
if (!copy_fpregs_to_fpstate(old_fpu))
old_fpu->last_cpu = -1;
else
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index de4d68852d3a..13c83fe97988 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -20,7 +20,7 @@
"3:\tmov\t%3, %1\n" \
"\tjmp\t2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (oldval), "=r" (ret), "+m" (*uaddr) \
: "i" (-EFAULT), "0" (oparg), "1" (0))
@@ -36,8 +36,8 @@
"4:\tmov\t%5, %1\n" \
"\tjmp\t3b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=&a" (oldval), "=&r" (ret), \
"+m" (*uaddr), "=&r" (tem) \
: "r" (oparg), "i" (-EFAULT), "1" (0))
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 6de64840dd22..9a92a3ac2ac5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -369,18 +369,6 @@ extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size);
extern bool is_early_ioremap_ptep(pte_t *ptep);
-#ifdef CONFIG_XEN
-#include <xen/xen.h>
-struct bio_vec;
-
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
- const struct bio_vec *vec2);
-
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
- (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \
- (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-#endif /* CONFIG_XEN */
-
#define IO_SPACE_LIMIT 0xffff
#include <asm-generic/io.h>
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 8c0de4282659..a5fb34fe56a4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -2,19 +2,6 @@
#ifndef _ASM_X86_JUMP_LABEL_H
#define _ASM_X86_JUMP_LABEL_H
-#ifndef HAVE_JUMP_LABEL
-/*
- * For better or for worse, if jump labels (the gcc extension) are missing,
- * then the entire static branch patching infrastructure is compiled out.
- * If that happens, the code in here will malfunction. Raise a compiler
- * error instead.
- *
- * In theory, jump labels and the static branch patching infrastructure
- * could be decoupled to fix this.
- */
-#error asm/jump_label.h included on a non-jump-label kernel
-#endif
-
#define JUMP_LABEL_NOP_SIZE 5
#ifdef CONFIG_X86_64
@@ -33,14 +20,9 @@
static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
- : : "i" (key), "i" (branch) : : l_yes);
-
+ asm_volatile_goto("STATIC_BRANCH_NOP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
+ : : "i" (key), "i" (branch) : : l_yes);
return false;
l_yes:
return true;
@@ -48,13 +30,8 @@ l_yes:
static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
{
- asm_volatile_goto("1:"
- ".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
- "2:\n\t"
- ".pushsection __jump_table, \"aw\" \n\t"
- _ASM_ALIGN "\n\t"
- _ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
- ".popsection \n\t"
+ asm_volatile_goto("STATIC_BRANCH_JMP l_yes=\"%l[l_yes]\" key=\"%c0\" "
+ "branch=\"%c1\""
: : "i" (key), "i" (branch) : : l_yes);
return false;
@@ -62,49 +39,28 @@ l_yes:
return true;
}
-#ifdef CONFIG_X86_64
-typedef u64 jump_label_t;
-#else
-typedef u32 jump_label_t;
-#endif
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#else /* __ASSEMBLY__ */
-.macro STATIC_JUMP_IF_TRUE target, key, def
-.Lstatic_jump_\@:
- .if \def
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .else
- .byte STATIC_KEY_INIT_NOP
- .endif
+.macro STATIC_BRANCH_NOP l_yes:req key:req branch:req
+.Lstatic_branch_nop_\@:
+ .byte STATIC_KEY_INIT_NOP
+.Lstatic_branch_no_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key
+ .long .Lstatic_branch_nop_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
-.macro STATIC_JUMP_IF_FALSE target, key, def
-.Lstatic_jump_\@:
- .if \def
- .byte STATIC_KEY_INIT_NOP
- .else
- /* Equivalent to "jmp.d32 \target" */
- .byte 0xe9
- .long \target - .Lstatic_jump_after_\@
-.Lstatic_jump_after_\@:
- .endif
+.macro STATIC_BRANCH_JMP l_yes:req key:req branch:req
+.Lstatic_branch_jmp_\@:
+ .byte 0xe9
+ .long \l_yes - .Lstatic_branch_jmp_after_\@
+.Lstatic_branch_jmp_after_\@:
.pushsection __jump_table, "aw"
_ASM_ALIGN
- _ASM_PTR .Lstatic_jump_\@, \target, \key + 1
+ .long .Lstatic_branch_jmp_\@ - ., \l_yes - .
+ _ASM_PTR \key + \branch - .
.popsection
.endm
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index c91083c59845..349a47acaa4a 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -53,7 +53,7 @@ static inline void local_sub(long i, local_t *l)
*/
static inline bool local_sub_and_test(long i, local_t *l)
{
- GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
+ return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i);
}
/**
@@ -66,7 +66,7 @@ static inline bool local_sub_and_test(long i, local_t *l)
*/
static inline bool local_dec_and_test(local_t *l)
{
- GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
+ return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e);
}
/**
@@ -79,7 +79,7 @@ static inline bool local_dec_and_test(local_t *l)
*/
static inline bool local_inc_and_test(local_t *l)
{
- GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
+ return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e);
}
/**
@@ -93,7 +93,7 @@ static inline bool local_inc_and_test(local_t *l)
*/
static inline bool local_add_negative(long i, local_t *l)
{
- GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
+ return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i);
}
/**
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4b75acc23b30..83ce282eed0a 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -346,23 +346,11 @@ extern struct pv_lock_ops pv_lock_ops;
#define paravirt_clobber(clobber) \
[paravirt_clobber] "i" (clobber)
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type, clobber) \
- "771:\n\t" insn_string "\n" "772:\n" \
- ".pushsection .parainstructions,\"a\"\n" \
- _ASM_ALIGN "\n" \
- _ASM_PTR " 771b\n" \
- " .byte " type "\n" \
- " .byte 772b-771b\n" \
- " .short " clobber "\n" \
- ".popsection\n"
-
/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string) \
- _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+#define paravirt_call \
+ "PARAVIRT_CALL type=\"%c[paravirt_typenum]\"" \
+ " clobber=\"%c[paravirt_clobber]\"" \
+ " pv_opptr=\"%c[paravirt_opptr]\";"
/* Simple instruction patching code. */
#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
@@ -391,16 +379,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
int paravirt_disable_iospace(void);
/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
-#define PARAVIRT_CALL \
- ANNOTATE_RETPOLINE_SAFE \
- "call *%c[paravirt_opptr];"
-
-/*
* These macros are intended to wrap calls through one of the paravirt
* ops structs, so that they can be later identified and patched at
* runtime.
@@ -537,7 +515,7 @@ int paravirt_disable_iospace(void);
/* since this condition will never hold */ \
if (sizeof(rettype) > sizeof(unsigned long)) { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -547,7 +525,7 @@ int paravirt_disable_iospace(void);
__ret = (rettype)((((u64)__edx) << 32) | __eax); \
} else { \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -574,7 +552,7 @@ int paravirt_disable_iospace(void);
PVOP_VCALL_ARGS; \
PVOP_TEST_NULL(op); \
asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
+ paravirt_call \
post \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
@@ -694,6 +672,26 @@ struct paravirt_patch_site {
extern struct paravirt_patch_site __parainstructions[],
__parainstructions_end[];
+#else /* __ASSEMBLY__ */
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
+ */
+.macro PARAVIRT_CALL type:req clobber:req pv_opptr:req
+771: ANNOTATE_RETPOLINE_SAFE
+ call *\pv_opptr
+772: .pushsection .parainstructions,"a"
+ _ASM_ALIGN
+ _ASM_PTR 771b
+ .byte \type
+ .byte 772b-771b
+ .short \clobber
+ .popsection
+.endm
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PARAVIRT_TYPES_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e9202a0de8f0..1a19d11cfbbd 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -185,22 +185,22 @@ do { \
typeof(var) pfo_ret__; \
switch (sizeof(var)) { \
case 1: \
- asm(op "b "__percpu_arg(1)",%0" \
+ asm volatile(op "b "__percpu_arg(1)",%0"\
: "=q" (pfo_ret__) \
: "m" (var)); \
break; \
case 2: \
- asm(op "w "__percpu_arg(1)",%0" \
+ asm volatile(op "w "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
case 4: \
- asm(op "l "__percpu_arg(1)",%0" \
+ asm volatile(op "l "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
case 8: \
- asm(op "q "__percpu_arg(1)",%0" \
+ asm volatile(op "q "__percpu_arg(1)",%0"\
: "=r" (pfo_ret__) \
: "m" (var)); \
break; \
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b64acb08a62b..106b7d0e2dae 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -124,7 +124,7 @@
*/
#define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \
- _PAGE_SOFT_DIRTY)
+ _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
/*
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7f2dbd91fc74..90cb2f36c042 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -88,7 +88,7 @@ static __always_inline void __preempt_count_sub(int val)
*/
static __always_inline bool __preempt_count_dec_and_test(void)
{
- GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
+ return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
}
/*
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index ee696efec99f..25f49af1b13c 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -37,8 +37,10 @@ struct pt_regs {
unsigned short __esh;
unsigned short fs;
unsigned short __fsh;
+ /* On interrupt, gs and __gsh store the vector number. */
unsigned short gs;
unsigned short __gsh;
+ /* On interrupt, this is the error code. */
unsigned long orig_ax;
unsigned long ip;
unsigned short cs;
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 3e70bed8a978..87623c6b13db 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -6,9 +6,24 @@
#include <asm/cpufeature.h>
#include <asm-generic/qspinlock_types.h>
#include <asm/paravirt.h>
+#include <asm/rmwcc.h>
#define _Q_PENDING_LOOPS (1 << 9)
+#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+ u32 val = 0;
+
+ if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c,
+ "I", _Q_PENDING_OFFSET))
+ val |= _Q_PENDING_VAL;
+
+ val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
+
+ return val;
+}
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
extern void __pv_init_lock_hash(void);
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 19b90521954c..a8b5e1e13319 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -4,6 +4,41 @@
* x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
* PaX/grsecurity.
*/
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/bug.h>
+
+.macro REFCOUNT_EXCEPTION counter:req
+ .pushsection .text..refcount
+111: lea \counter, %_ASM_CX
+112: ud2
+ ASM_UNREACHABLE
+ .popsection
+113: _ASM_EXTABLE_REFCOUNT(112b, 113b)
+.endm
+
+/* Trigger refcount exception if refcount result is negative. */
+.macro REFCOUNT_CHECK_LT_ZERO counter:req
+ js 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+.macro REFCOUNT_CHECK_LE_ZERO counter:req
+ jz 111f
+ REFCOUNT_CHECK_LT_ZERO counter="\counter"
+.endm
+
+/* Trigger refcount exception unconditionally. */
+.macro REFCOUNT_ERROR counter:req
+ jmp 111f
+ REFCOUNT_EXCEPTION counter="\counter"
+.endm
+
+#else /* __ASSEMBLY__ */
+
#include <linux/refcount.h>
#include <asm/bug.h>
@@ -15,34 +50,11 @@
* central refcount exception. The fixup address for the exception points
* back to the regular execution flow in .text.
*/
-#define _REFCOUNT_EXCEPTION \
- ".pushsection .text..refcount\n" \
- "111:\tlea %[counter], %%" _ASM_CX "\n" \
- "112:\t" ASM_UD2 "\n" \
- ASM_UNREACHABLE \
- ".popsection\n" \
- "113:\n" \
- _ASM_EXTABLE_REFCOUNT(112b, 113b)
-
-/* Trigger refcount exception if refcount result is negative. */
-#define REFCOUNT_CHECK_LT_ZERO \
- "js 111f\n\t" \
- _REFCOUNT_EXCEPTION
-
-/* Trigger refcount exception if refcount result is zero or negative. */
-#define REFCOUNT_CHECK_LE_ZERO \
- "jz 111f\n\t" \
- REFCOUNT_CHECK_LT_ZERO
-
-/* Trigger refcount exception unconditionally. */
-#define REFCOUNT_ERROR \
- "jmp 111f\n\t" \
- _REFCOUNT_EXCEPTION
static __always_inline void refcount_add(unsigned int i, refcount_t *r)
{
asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: "ir" (i)
: "cc", "cx");
@@ -51,7 +63,7 @@ static __always_inline void refcount_add(unsigned int i, refcount_t *r)
static __always_inline void refcount_inc(refcount_t *r)
{
asm volatile(LOCK_PREFIX "incl %0\n\t"
- REFCOUNT_CHECK_LT_ZERO
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -59,7 +71,7 @@ static __always_inline void refcount_inc(refcount_t *r)
static __always_inline void refcount_dec(refcount_t *r)
{
asm volatile(LOCK_PREFIX "decl %0\n\t"
- REFCOUNT_CHECK_LE_ZERO
+ "REFCOUNT_CHECK_LE_ZERO counter=\"%[counter]\""
: [counter] "+m" (r->refs.counter)
: : "cc", "cx");
}
@@ -67,14 +79,17 @@ static __always_inline void refcount_dec(refcount_t *r)
static __always_inline __must_check
bool refcount_sub_and_test(unsigned int i, refcount_t *r)
{
- GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
- r->refs.counter, "er", i, "%0", e, "cx");
+
+ return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"",
+ r->refs.counter, e, "er", i, "cx");
}
static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
{
- GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
- r->refs.counter, "%0", e, "cx");
+ return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl",
+ "REFCOUNT_CHECK_LT_ZERO counter=\"%[var]\"",
+ r->refs.counter, e, "cx");
}
static __always_inline __must_check
@@ -91,7 +106,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
/* Did we try to increment from/to an undesirable state? */
if (unlikely(c < 0 || c == INT_MAX || result < c)) {
- asm volatile(REFCOUNT_ERROR
+ asm volatile("REFCOUNT_ERROR counter=\"%[counter]\""
: : [counter] "m" (r->refs.counter)
: "cc", "cx");
break;
@@ -107,4 +122,6 @@ static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
return refcount_add_not_zero(1, r);
}
+#endif /* __ASSEMBLY__ */
+
#endif
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 4914a3e7c803..46ac84b506f5 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -2,56 +2,69 @@
#ifndef _ASM_X86_RMWcc
#define _ASM_X86_RMWcc
+/* This counts to 12. Any more, it will return 13th argument. */
+#define __RMWcc_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
+#define RMWcc_ARGS(X...) __RMWcc_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+#define __RMWcc_CONCAT(a, b) a ## b
+#define RMWcc_CONCAT(a, b) __RMWcc_CONCAT(a, b)
+
#define __CLOBBERS_MEM(clb...) "memory", ## clb
#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
/* Use asm goto */
-#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \
-do { \
+#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
+({ \
+ bool c = false; \
asm_volatile_goto (fullop "; j" #cc " %l[cc_label]" \
- : : [counter] "m" (var), ## __VA_ARGS__ \
+ : : [var] "m" (_var), ## __VA_ARGS__ \
: clobbers : cc_label); \
- return 0; \
-cc_label: \
- return 1; \
-} while (0)
-
-#define __BINARY_RMWcc_ARG " %1, "
-
+ if (0) { \
+cc_label: c = true; \
+ } \
+ c; \
+})
#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
/* Use flags output or a set instruction */
-#define __GEN_RMWcc(fullop, var, cc, clobbers, ...) \
-do { \
+#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \
+({ \
bool c; \
asm volatile (fullop CC_SET(cc) \
- : [counter] "+m" (var), CC_OUT(cc) (c) \
+ : [var] "+m" (_var), CC_OUT(cc) (c) \
: __VA_ARGS__ : clobbers); \
- return c; \
-} while (0)
-
-#define __BINARY_RMWcc_ARG " %2, "
+ c; \
+})
#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
-#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \
__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
-#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\
- __GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc, \
- __CLOBBERS_MEM(clobbers))
+#define GEN_UNARY_RMWcc_3(op, var, cc) \
+ GEN_UNARY_RMWcc_4(op, var, cc, "%[var]")
-#define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc) \
- __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc, \
- __CLOBBERS_MEM(), vcon (val))
+#define GEN_UNARY_RMWcc(X...) RMWcc_CONCAT(GEN_UNARY_RMWcc_, RMWcc_ARGS(X))(X)
+
+#define GEN_BINARY_RMWcc_6(op, var, cc, vcon, _val, arg0) \
+ __GEN_RMWcc(op " %[val], " arg0, var, cc, \
+ __CLOBBERS_MEM(), [val] vcon (_val))
+
+#define GEN_BINARY_RMWcc_5(op, var, cc, vcon, val) \
+ GEN_BINARY_RMWcc_6(op, var, cc, vcon, val, "%[var]")
+
+#define GEN_BINARY_RMWcc(X...) RMWcc_CONCAT(GEN_BINARY_RMWcc_, RMWcc_ARGS(X))(X)
+
+#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, cc, clobbers...) \
+ __GEN_RMWcc(op " %[var]\n\t" suffix, var, cc, \
+ __CLOBBERS_MEM(clobbers))
-#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc, \
- clobbers...) \
- __GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc, \
- __CLOBBERS_MEM(clobbers), vcon (val))
+#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, cc, vcon, _val, clobbers...)\
+ __GEN_RMWcc(op " %[val], %[var]\n\t" suffix, var, cc, \
+ __CLOBBERS_MEM(clobbers), [val] vcon (_val))
#endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h
index ecffe81ff65c..a892494ca5e4 100644
--- a/arch/x86/include/asm/suspend.h
+++ b/arch/x86/include/asm/suspend.h
@@ -4,3 +4,11 @@
#else
# include <asm/suspend_64.h>
#endif
+extern unsigned long restore_jump_address __visible;
+extern unsigned long jump_address_phys;
+extern unsigned long restore_cr3 __visible;
+extern unsigned long temp_pgt __visible;
+extern unsigned long relocated_restore_code __visible;
+extern int relocate_restore_code(void);
+/* Defined in hibernate_asm_32/64.S */
+extern asmlinkage __visible int restore_image(void);
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 8be6afb58471..fdbd9d7b7bca 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -32,4 +32,8 @@ struct saved_context {
unsigned long return_address;
} __attribute__((packed));
+/* routines for saving/restoring kernel state */
+extern char core_restore_code[];
+extern char restore_registers[];
+
#endif /* _ASM_X86_SUSPEND_32_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index aae77eb8491c..b5e58cc0c5e7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -198,8 +198,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
"4: movl %3,%0\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (err) \
: "A" (x), "r" (addr), "i" (errret), "0" (err))
@@ -340,8 +340,8 @@ do { \
" xorl %%edx,%%edx\n" \
" jmp 3b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 4b) \
- _ASM_EXTABLE(2b, 4b) \
+ _ASM_EXTABLE_UA(1b, 4b) \
+ _ASM_EXTABLE_UA(2b, 4b) \
: "=r" (retval), "=&A"(x) \
: "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \
"i" (errret), "0" (retval)); \
@@ -386,7 +386,7 @@ do { \
" xor"itype" %"rtype"1,%"rtype"1\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -398,7 +398,7 @@ do { \
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r" (err), ltype(x) \
: "m" (__m(addr)), "i" (errret), "0" (err))
@@ -474,7 +474,7 @@ struct __large_struct { unsigned long buf[100]; };
"3: mov %3,%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "=r"(err) \
: ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
@@ -602,7 +602,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "q" (__new), "1" (__old) \
: "memory" \
@@ -618,7 +618,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -634,7 +634,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
@@ -653,7 +653,7 @@ extern void __cmpxchg_wrong_size(void)
"3:\tmov %3, %0\n" \
"\tjmp 2b\n" \
"\t.previous\n" \
- _ASM_EXTABLE(1b, 3b) \
+ _ASM_EXTABLE_UA(1b, 3b) \
: "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \
: "i" (-EFAULT), "r" (__new), "1" (__old) \
: "memory" \
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index d383140e1dc8..068d9b067c83 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_XEN_EVENTS_H
#define _ASM_X86_XEN_EVENTS_H
+#include <xen/xen.h>
+
enum ipi_vector {
XEN_RESCHEDULE_VECTOR,
XEN_CALL_FUNCTION_VECTOR,
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index f299d8a479bb..3f9d1b4019bb 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -482,7 +482,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
{
void *vaddr;
- vaddr = dma_direct_alloc(dev, size, dma_addr, flag, attrs);
+ vaddr = dma_direct_alloc_pages(dev, size, dma_addr, flag, attrs);
if (!vaddr ||
!force_iommu || dev->coherent_dma_mask <= DMA_BIT_MASK(24))
return vaddr;
@@ -494,7 +494,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
goto out_free;
return vaddr;
out_free:
- dma_direct_free(dev, size, vaddr, *dma_addr, attrs);
+ dma_direct_free_pages(dev, size, vaddr, *dma_addr, attrs);
return NULL;
}
@@ -504,7 +504,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_addr, unsigned long attrs)
{
gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, 0);
- dma_direct_free(dev, size, vaddr, dma_addr, attrs);
+ dma_direct_free_pages(dev, size, vaddr, dma_addr, attrs);
}
static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 953b3ce92dcc..ef8fd1f2ede0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1315,7 +1315,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
local_irq_disable();
ist_end_non_atomic();
} else {
- if (!fixup_exception(regs, X86_TRAP_MC))
+ if (!fixup_exception(regs, X86_TRAP_MC, error_code, 0))
mce_panic("Failed kernel mode recovery", &m, NULL);
}
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 23f1691670b6..61a949d84dfa 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -314,7 +314,6 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size)
* thread's fpu state, reconstruct fxstate from the fsave
* header. Validate and sanitize the copied state.
*/
- struct fpu *fpu = &tsk->thread.fpu;
struct user_i387_ia32_struct env;
int err = 0;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index eeea935e9bb5..aac0c1f7e354 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -42,55 +42,40 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
void *(*poker)(void *, const void *, size_t),
int init)
{
- union jump_code_union code;
+ union jump_code_union jmp;
const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+ const void *expect, *code;
+ int line;
+
+ jmp.jump = 0xe9;
+ jmp.offset = jump_entry_target(entry) -
+ (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
if (early_boot_irqs_disabled)
poker = text_poke_early;
if (type == JUMP_LABEL_JMP) {
if (init) {
- /*
- * Jump label is enabled for the first time.
- * So we expect a default_nop...
- */
- if (unlikely(memcmp((void *)entry->code, default_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- /*
- * ...otherwise expect an ideal_nop. Otherwise
- * something went horribly wrong.
- */
- if (unlikely(memcmp((void *)entry->code, ideal_nop, 5)
- != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = ideal_nop; line = __LINE__;
}
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
+ code = &jmp.code;
} else {
- /*
- * We are disabling this jump label. If it is not what
- * we think it is, then something must have gone wrong.
- * If this is the first initialization call, then we
- * are converting the default nop to the ideal nop.
- */
if (init) {
- if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = default_nop; line = __LINE__;
} else {
- code.jump = 0xe9;
- code.offset = entry->target -
- (entry->code + JUMP_LABEL_NOP_SIZE);
- if (unlikely(memcmp((void *)entry->code, &code, 5) != 0))
- bug_at((void *)entry->code, __LINE__);
+ expect = &jmp.code; line = __LINE__;
}
- memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
+
+ code = ideal_nop;
}
+ if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE))
+ bug_at((void *)jump_entry_code(entry), line);
+
/*
* Make text_poke_bp() a default fallback poker.
*
@@ -99,11 +84,14 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
* always nop being the 'currently valid' instruction
*
*/
- if (poker)
- (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
- else
- text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
- (void *)entry->code + JUMP_LABEL_NOP_SIZE);
+ if (poker) {
+ (*poker)((void *)jump_entry_code(entry), code,
+ JUMP_LABEL_NOP_SIZE);
+ return;
+ }
+
+ text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
+ (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
}
void arch_jump_label_transform(struct jump_entry *entry,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index b0d1e81c96bb..f72a47b602e2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,50 +1020,12 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
*/
if (cur->fault_handler && cur->fault_handler(cur, regs, trapnr))
return 1;
-
- /*
- * In case the user-specified fault handler returned
- * zero, try to fix up.
- */
- if (fixup_exception(regs, trapnr))
- return 1;
-
- /*
- * fixup routine could not handle it,
- * Let do_page_fault() fix it.
- */
}
return 0;
}
NOKPROBE_SYMBOL(kprobe_fault_handler);
-/*
- * Wrapper routine for handling exceptions.
- */
-int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
- void *data)
-{
- struct die_args *args = data;
- int ret = NOTIFY_DONE;
-
- if (args->regs && user_mode(args->regs))
- return ret;
-
- if (val == DIE_GPF) {
- /*
- * To be potentially processing a kprobe fault and to
- * trust the result from kprobe_running(), we have
- * be non-preemptible.
- */
- if (!preemptible() && kprobe_running() &&
- kprobe_fault_handler(args->regs, args->trapnr))
- ret = NOTIFY_STOP;
- }
- return ret;
-}
-NOKPROBE_SYMBOL(kprobe_exceptions_notify);
-
bool arch_within_kprobe_blacklist(unsigned long addr)
{
bool is_in_entry_trampoline_section = false;
diff --git a/arch/x86/kernel/macros.S b/arch/x86/kernel/macros.S
new file mode 100644
index 000000000000..161c95059044
--- /dev/null
+++ b/arch/x86/kernel/macros.S
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file includes headers whose assembly part includes macros which are
+ * commonly used. The macros are precompiled into assmebly file which is later
+ * assembled together with each compiled file.
+ */
+
+#include <linux/compiler.h>
+#include <asm/refcount.h>
+#include <asm/alternative-asm.h>
+#include <asm/bug.h>
+#include <asm/paravirt.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/jump_label.h>
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index f58336af095c..b052e883dd8c 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -201,6 +201,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
goto overflow;
#endif
break;
+ case R_X86_64_PC64:
+ if (*(u64 *)loc != 0)
+ goto invalid_relocation;
+ val -= (u64)loc;
+ *(u64 *)loc = val;
+ break;
default:
pr_err("%s: Unknown rela relocation: %llu\n",
me->name, ELF64_R_TYPE(rel[i].r_info));
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 661583662430..71c0b01d93b1 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -42,10 +42,8 @@ IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
int __init pci_swiotlb_detect_4gb(void)
{
/* don't initialize swiotlb if iommu=off (no_iommu=1) */
-#ifdef CONFIG_X86_64
if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
swiotlb = 1;
-#endif
/*
* If SME is active then swiotlb will be set to 1 so that bounce
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b4866badb235..90ecc108bc8a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1251,7 +1251,7 @@ void __init setup_arch(char **cmdline_p)
x86_init.hyper.guest_late_init();
e820__reserve_resources();
- e820__register_nosave_regions(max_low_pfn);
+ e820__register_nosave_regions(max_pfn);
x86_init.resources.reserve_resources();
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index be01328eb755..fddaefc51fb6 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -25,7 +25,7 @@
#include <asm/time.h>
#ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES;
+__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
#endif
unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e6db475164ed..16c95cb90496 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -206,7 +206,7 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
}
if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, error_code, 0))
return 0;
tsk->thread.error_code = error_code;
@@ -551,11 +551,21 @@ do_general_protection(struct pt_regs *regs, long error_code)
tsk = current;
if (!user_mode(regs)) {
- if (fixup_exception(regs, X86_TRAP_GP))
+ if (fixup_exception(regs, X86_TRAP_GP, error_code, 0))
return;
tsk->thread.error_code = error_code;
tsk->thread.trap_nr = X86_TRAP_GP;
+
+ /*
+ * To be potentially processing a kprobe fault and to
+ * trust the result from kprobe_running(), we have to
+ * be non-preemptible.
+ */
+ if (!preemptible() && kprobe_running() &&
+ kprobe_fault_handler(regs, X86_TRAP_GP))
+ return;
+
if (notify_die(DIE_GPF, "general protection fault", regs, error_code,
X86_TRAP_GP, SIGSEGV) != NOTIFY_STOP)
die("general protection fault", regs, error_code);
@@ -838,7 +848,7 @@ static void math_error(struct pt_regs *regs, int error_code, int trapnr)
cond_local_irq_enable(regs);
if (!user_mode(regs)) {
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, error_code, 0))
return;
task->thread.error_code = error_code;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 19c3c6bec325..03b7529333a6 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -58,7 +58,7 @@ struct cyc2ns {
static DEFINE_PER_CPU_ALIGNED(struct cyc2ns, cyc2ns);
-void cyc2ns_read_begin(struct cyc2ns_data *data)
+void __always_inline cyc2ns_read_begin(struct cyc2ns_data *data)
{
int seq, idx;
@@ -75,7 +75,7 @@ void cyc2ns_read_begin(struct cyc2ns_data *data)
} while (unlikely(seq != this_cpu_read(cyc2ns.seq.sequence)));
}
-void cyc2ns_read_end(void)
+void __always_inline cyc2ns_read_end(void)
{
preempt_enable_notrace();
}
@@ -104,7 +104,7 @@ void cyc2ns_read_end(void)
* -johnstul@us.ibm.com "math is hard, lets go shopping!"
*/
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+static __always_inline unsigned long long cycles_2_ns(unsigned long long cyc)
{
struct cyc2ns_data data;
unsigned long long ns;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d96092b35936..61ccfb13899e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -436,14 +436,18 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
static inline bool svm_sev_enabled(void)
{
- return max_sev_asid;
+ return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
}
static inline bool sev_guest(struct kvm *kvm)
{
+#ifdef CONFIG_KVM_AMD_SEV
struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
return sev->active;
+#else
+ return false;
+#endif
}
static inline int sev_get_asid(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 612fd17be635..e665aa7167cf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1572,8 +1572,12 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
goto out;
}
+ /*
+ * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the
+ * base of EPT PML4 table, strip off EPT configuration information.
+ */
ret = hyperv_flush_guest_mapping(
- to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer);
+ to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK);
out:
spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 46e71a74e612..ad8e0906d1ea 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -273,11 +273,11 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst,
#define SRC(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6001f)
+ _ASM_EXTABLE_UA(9999b, 6001f)
#define DST(y...) \
9999: y; \
- _ASM_EXTABLE(9999b, 6002f)
+ _ASM_EXTABLE_UA(9999b, 6002f)
#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 020f75cc8cf6..db4e5aa0858b 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -92,26 +92,26 @@ ENTRY(copy_user_generic_unrolled)
60: jmp copy_user_handle_tail /* ecx is zerorest also */
.previous
- _ASM_EXTABLE(1b,30b)
- _ASM_EXTABLE(2b,30b)
- _ASM_EXTABLE(3b,30b)
- _ASM_EXTABLE(4b,30b)
- _ASM_EXTABLE(5b,30b)
- _ASM_EXTABLE(6b,30b)
- _ASM_EXTABLE(7b,30b)
- _ASM_EXTABLE(8b,30b)
- _ASM_EXTABLE(9b,30b)
- _ASM_EXTABLE(10b,30b)
- _ASM_EXTABLE(11b,30b)
- _ASM_EXTABLE(12b,30b)
- _ASM_EXTABLE(13b,30b)
- _ASM_EXTABLE(14b,30b)
- _ASM_EXTABLE(15b,30b)
- _ASM_EXTABLE(16b,30b)
- _ASM_EXTABLE(18b,40b)
- _ASM_EXTABLE(19b,40b)
- _ASM_EXTABLE(21b,50b)
- _ASM_EXTABLE(22b,50b)
+ _ASM_EXTABLE_UA(1b, 30b)
+ _ASM_EXTABLE_UA(2b, 30b)
+ _ASM_EXTABLE_UA(3b, 30b)
+ _ASM_EXTABLE_UA(4b, 30b)
+ _ASM_EXTABLE_UA(5b, 30b)
+ _ASM_EXTABLE_UA(6b, 30b)
+ _ASM_EXTABLE_UA(7b, 30b)
+ _ASM_EXTABLE_UA(8b, 30b)
+ _ASM_EXTABLE_UA(9b, 30b)
+ _ASM_EXTABLE_UA(10b, 30b)
+ _ASM_EXTABLE_UA(11b, 30b)
+ _ASM_EXTABLE_UA(12b, 30b)
+ _ASM_EXTABLE_UA(13b, 30b)
+ _ASM_EXTABLE_UA(14b, 30b)
+ _ASM_EXTABLE_UA(15b, 30b)
+ _ASM_EXTABLE_UA(16b, 30b)
+ _ASM_EXTABLE_UA(18b, 40b)
+ _ASM_EXTABLE_UA(19b, 40b)
+ _ASM_EXTABLE_UA(21b, 50b)
+ _ASM_EXTABLE_UA(22b, 50b)
ENDPROC(copy_user_generic_unrolled)
EXPORT_SYMBOL(copy_user_generic_unrolled)
@@ -156,8 +156,8 @@ ENTRY(copy_user_generic_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,11b)
- _ASM_EXTABLE(3b,12b)
+ _ASM_EXTABLE_UA(1b, 11b)
+ _ASM_EXTABLE_UA(3b, 12b)
ENDPROC(copy_user_generic_string)
EXPORT_SYMBOL(copy_user_generic_string)
@@ -189,7 +189,7 @@ ENTRY(copy_user_enhanced_fast_string)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,12b)
+ _ASM_EXTABLE_UA(1b, 12b)
ENDPROC(copy_user_enhanced_fast_string)
EXPORT_SYMBOL(copy_user_enhanced_fast_string)
@@ -319,27 +319,27 @@ ENTRY(__copy_user_nocache)
jmp copy_user_handle_tail
.previous
- _ASM_EXTABLE(1b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(2b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(3b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(4b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(5b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(6b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(7b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(8b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(9b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(10b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(11b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(12b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(13b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(14b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(15b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(16b,.L_fixup_4x8b_copy)
- _ASM_EXTABLE(20b,.L_fixup_8b_copy)
- _ASM_EXTABLE(21b,.L_fixup_8b_copy)
- _ASM_EXTABLE(30b,.L_fixup_4b_copy)
- _ASM_EXTABLE(31b,.L_fixup_4b_copy)
- _ASM_EXTABLE(40b,.L_fixup_1b_copy)
- _ASM_EXTABLE(41b,.L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(1b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(2b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(3b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(4b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(5b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(6b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(7b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(8b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(9b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(10b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(11b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(12b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(13b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(14b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(15b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(16b, .L_fixup_4x8b_copy)
+ _ASM_EXTABLE_UA(20b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(21b, .L_fixup_8b_copy)
+ _ASM_EXTABLE_UA(30b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(31b, .L_fixup_4b_copy)
+ _ASM_EXTABLE_UA(40b, .L_fixup_1b_copy)
+ _ASM_EXTABLE_UA(41b, .L_fixup_1b_copy)
ENDPROC(__copy_user_nocache)
EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 45a53dfe1859..a4a379e79259 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -31,14 +31,18 @@
.macro source
10:
- _ASM_EXTABLE(10b, .Lbad_source)
+ _ASM_EXTABLE_UA(10b, .Lbad_source)
.endm
.macro dest
20:
- _ASM_EXTABLE(20b, .Lbad_dest)
+ _ASM_EXTABLE_UA(20b, .Lbad_dest)
.endm
+ /*
+ * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
+ * potentially unmapped kernel address.
+ */
.macro ignore L=.Lignore
30:
_ASM_EXTABLE(30b, \L)
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 49b167f73215..74fdff968ea3 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -132,12 +132,12 @@ bad_get_user_8:
END(bad_get_user_8)
#endif
- _ASM_EXTABLE(1b,bad_get_user)
- _ASM_EXTABLE(2b,bad_get_user)
- _ASM_EXTABLE(3b,bad_get_user)
+ _ASM_EXTABLE_UA(1b, bad_get_user)
+ _ASM_EXTABLE_UA(2b, bad_get_user)
+ _ASM_EXTABLE_UA(3b, bad_get_user)
#ifdef CONFIG_X86_64
- _ASM_EXTABLE(4b,bad_get_user)
+ _ASM_EXTABLE_UA(4b, bad_get_user)
#else
- _ASM_EXTABLE(4b,bad_get_user_8)
- _ASM_EXTABLE(5b,bad_get_user_8)
+ _ASM_EXTABLE_UA(4b, bad_get_user_8)
+ _ASM_EXTABLE_UA(5b, bad_get_user_8)
#endif
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 96dce5fe2a35..d2e5c9c39601 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -94,10 +94,10 @@ bad_put_user:
EXIT
END(bad_put_user)
- _ASM_EXTABLE(1b,bad_put_user)
- _ASM_EXTABLE(2b,bad_put_user)
- _ASM_EXTABLE(3b,bad_put_user)
- _ASM_EXTABLE(4b,bad_put_user)
+ _ASM_EXTABLE_UA(1b, bad_put_user)
+ _ASM_EXTABLE_UA(2b, bad_put_user)
+ _ASM_EXTABLE_UA(3b, bad_put_user)
+ _ASM_EXTABLE_UA(4b, bad_put_user)
#ifdef CONFIG_X86_32
- _ASM_EXTABLE(5b,bad_put_user)
+ _ASM_EXTABLE_UA(5b, bad_put_user)
#endif
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 7add8ba06887..71fb58d44d58 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -47,8 +47,8 @@ do { \
"3: lea 0(%2,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0) \
: "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
} while (0)
@@ -153,44 +153,44 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
"101: lea 0(%%eax,%0,4),%0\n"
" jmp 100b\n"
".previous\n"
- _ASM_EXTABLE(1b,100b)
- _ASM_EXTABLE(2b,100b)
- _ASM_EXTABLE(3b,100b)
- _ASM_EXTABLE(4b,100b)
- _ASM_EXTABLE(5b,100b)
- _ASM_EXTABLE(6b,100b)
- _ASM_EXTABLE(7b,100b)
- _ASM_EXTABLE(8b,100b)
- _ASM_EXTABLE(9b,100b)
- _ASM_EXTABLE(10b,100b)
- _ASM_EXTABLE(11b,100b)
- _ASM_EXTABLE(12b,100b)
- _ASM_EXTABLE(13b,100b)
- _ASM_EXTABLE(14b,100b)
- _ASM_EXTABLE(15b,100b)
- _ASM_EXTABLE(16b,100b)
- _ASM_EXTABLE(17b,100b)
- _ASM_EXTABLE(18b,100b)
- _ASM_EXTABLE(19b,100b)
- _ASM_EXTABLE(20b,100b)
- _ASM_EXTABLE(21b,100b)
- _ASM_EXTABLE(22b,100b)
- _ASM_EXTABLE(23b,100b)
- _ASM_EXTABLE(24b,100b)
- _ASM_EXTABLE(25b,100b)
- _ASM_EXTABLE(26b,100b)
- _ASM_EXTABLE(27b,100b)
- _ASM_EXTABLE(28b,100b)
- _ASM_EXTABLE(29b,100b)
- _ASM_EXTABLE(30b,100b)
- _ASM_EXTABLE(31b,100b)
- _ASM_EXTABLE(32b,100b)
- _ASM_EXTABLE(33b,100b)
- _ASM_EXTABLE(34b,100b)
- _ASM_EXTABLE(35b,100b)
- _ASM_EXTABLE(36b,100b)
- _ASM_EXTABLE(37b,100b)
- _ASM_EXTABLE(99b,101b)
+ _ASM_EXTABLE_UA(1b, 100b)
+ _ASM_EXTABLE_UA(2b, 100b)
+ _ASM_EXTABLE_UA(3b, 100b)
+ _ASM_EXTABLE_UA(4b, 100b)
+ _ASM_EXTABLE_UA(5b, 100b)
+ _ASM_EXTABLE_UA(6b, 100b)
+ _ASM_EXTABLE_UA(7b, 100b)
+ _ASM_EXTABLE_UA(8b, 100b)
+ _ASM_EXTABLE_UA(9b, 100b)
+ _ASM_EXTABLE_UA(10b, 100b)
+ _ASM_EXTABLE_UA(11b, 100b)
+ _ASM_EXTABLE_UA(12b, 100b)
+ _ASM_EXTABLE_UA(13b, 100b)
+ _ASM_EXTABLE_UA(14b, 100b)
+ _ASM_EXTABLE_UA(15b, 100b)
+ _ASM_EXTABLE_UA(16b, 100b)
+ _ASM_EXTABLE_UA(17b, 100b)
+ _ASM_EXTABLE_UA(18b, 100b)
+ _ASM_EXTABLE_UA(19b, 100b)
+ _ASM_EXTABLE_UA(20b, 100b)
+ _ASM_EXTABLE_UA(21b, 100b)
+ _ASM_EXTABLE_UA(22b, 100b)
+ _ASM_EXTABLE_UA(23b, 100b)
+ _ASM_EXTABLE_UA(24b, 100b)
+ _ASM_EXTABLE_UA(25b, 100b)
+ _ASM_EXTABLE_UA(26b, 100b)
+ _ASM_EXTABLE_UA(27b, 100b)
+ _ASM_EXTABLE_UA(28b, 100b)
+ _ASM_EXTABLE_UA(29b, 100b)
+ _ASM_EXTABLE_UA(30b, 100b)
+ _ASM_EXTABLE_UA(31b, 100b)
+ _ASM_EXTABLE_UA(32b, 100b)
+ _ASM_EXTABLE_UA(33b, 100b)
+ _ASM_EXTABLE_UA(34b, 100b)
+ _ASM_EXTABLE_UA(35b, 100b)
+ _ASM_EXTABLE_UA(36b, 100b)
+ _ASM_EXTABLE_UA(37b, 100b)
+ _ASM_EXTABLE_UA(99b, 101b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -259,26 +259,26 @@ static unsigned long __copy_user_intel_nocache(void *to,
"9: lea 0(%%eax,%0,4),%0\n"
"16: jmp 8b\n"
".previous\n"
- _ASM_EXTABLE(0b,16b)
- _ASM_EXTABLE(1b,16b)
- _ASM_EXTABLE(2b,16b)
- _ASM_EXTABLE(21b,16b)
- _ASM_EXTABLE(3b,16b)
- _ASM_EXTABLE(31b,16b)
- _ASM_EXTABLE(4b,16b)
- _ASM_EXTABLE(41b,16b)
- _ASM_EXTABLE(10b,16b)
- _ASM_EXTABLE(51b,16b)
- _ASM_EXTABLE(11b,16b)
- _ASM_EXTABLE(61b,16b)
- _ASM_EXTABLE(12b,16b)
- _ASM_EXTABLE(71b,16b)
- _ASM_EXTABLE(13b,16b)
- _ASM_EXTABLE(81b,16b)
- _ASM_EXTABLE(14b,16b)
- _ASM_EXTABLE(91b,16b)
- _ASM_EXTABLE(6b,9b)
- _ASM_EXTABLE(7b,16b)
+ _ASM_EXTABLE_UA(0b, 16b)
+ _ASM_EXTABLE_UA(1b, 16b)
+ _ASM_EXTABLE_UA(2b, 16b)
+ _ASM_EXTABLE_UA(21b, 16b)
+ _ASM_EXTABLE_UA(3b, 16b)
+ _ASM_EXTABLE_UA(31b, 16b)
+ _ASM_EXTABLE_UA(4b, 16b)
+ _ASM_EXTABLE_UA(41b, 16b)
+ _ASM_EXTABLE_UA(10b, 16b)
+ _ASM_EXTABLE_UA(51b, 16b)
+ _ASM_EXTABLE_UA(11b, 16b)
+ _ASM_EXTABLE_UA(61b, 16b)
+ _ASM_EXTABLE_UA(12b, 16b)
+ _ASM_EXTABLE_UA(71b, 16b)
+ _ASM_EXTABLE_UA(13b, 16b)
+ _ASM_EXTABLE_UA(81b, 16b)
+ _ASM_EXTABLE_UA(14b, 16b)
+ _ASM_EXTABLE_UA(91b, 16b)
+ _ASM_EXTABLE_UA(6b, 9b)
+ _ASM_EXTABLE_UA(7b, 16b)
: "=&c"(size), "=&D" (d0), "=&S" (d1)
: "1"(to), "2"(from), "0"(size)
: "eax", "edx", "memory");
@@ -321,9 +321,9 @@ do { \
"3: lea 0(%3,%0,4),%0\n" \
" jmp 2b\n" \
".previous\n" \
- _ASM_EXTABLE(4b,5b) \
- _ASM_EXTABLE(0b,3b) \
- _ASM_EXTABLE(1b,2b) \
+ _ASM_EXTABLE_UA(4b, 5b) \
+ _ASM_EXTABLE_UA(0b, 3b) \
+ _ASM_EXTABLE_UA(1b, 2b) \
: "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
: "3"(size), "0"(size), "1"(to), "2"(from) \
: "memory"); \
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 9c5606d88f61..fefe64436398 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -37,8 +37,8 @@ unsigned long __clear_user(void __user *addr, unsigned long size)
"3: lea 0(%[size1],%[size8],8),%[size8]\n"
" jmp 2b\n"
".previous\n"
- _ASM_EXTABLE(0b,3b)
- _ASM_EXTABLE(1b,2b)
+ _ASM_EXTABLE_UA(0b, 3b)
+ _ASM_EXTABLE_UA(1b, 2b)
: [size8] "=&c"(size), [dst] "=&D" (__d0)
: [size1] "r"(size & 7), "[size8]" (size / 8), "[dst]"(addr));
clac();
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 45f5d6cf65ae..6521134057e8 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -8,7 +8,8 @@
#include <asm/kdebug.h>
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
- struct pt_regs *, int);
+ struct pt_regs *, int, unsigned long,
+ unsigned long);
static inline unsigned long
ex_fixup_addr(const struct exception_table_entry *x)
@@ -22,7 +23,9 @@ ex_fixup_handler(const struct exception_table_entry *x)
}
__visible bool ex_handler_default(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
@@ -30,7 +33,9 @@ __visible bool ex_handler_default(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_default);
__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
@@ -43,7 +48,9 @@ EXPORT_SYMBOL_GPL(ex_handler_fault);
* result of a refcount inc/dec/add/sub.
*/
__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
/* First unconditionally saturate the refcount. */
*(int *)regs->cx = INT_MIN / 2;
@@ -96,7 +103,9 @@ EXPORT_SYMBOL(ex_handler_refcount);
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
@@ -108,9 +117,79 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
}
EXPORT_SYMBOL_GPL(ex_handler_fprestore);
+/* Helper to check whether a uaccess fault indicates a kernel bug. */
+static bool bogus_uaccess(struct pt_regs *regs, int trapnr,
+ unsigned long fault_addr)
+{
+ /* This is the normal case: #PF with a fault address in userspace. */
+ if (trapnr == X86_TRAP_PF && fault_addr < TASK_SIZE_MAX)
+ return false;
+
+ /*
+ * This code can be reached for machine checks, but only if the #MC
+ * handler has already decided that it looks like a candidate for fixup.
+ * This e.g. happens when attempting to access userspace memory which
+ * the CPU can't access because of uncorrectable bad memory.
+ */
+ if (trapnr == X86_TRAP_MC)
+ return false;
+
+ /*
+ * There are two remaining exception types we might encounter here:
+ * - #PF for faulting accesses to kernel addresses
+ * - #GP for faulting accesses to noncanonical addresses
+ * Complain about anything else.
+ */
+ if (trapnr != X86_TRAP_PF && trapnr != X86_TRAP_GP) {
+ WARN(1, "unexpected trap %d in uaccess\n", trapnr);
+ return false;
+ }
+
+ /*
+ * This is a faulting memory access in kernel space, on a kernel
+ * address, in a usercopy function. This can e.g. be caused by improper
+ * use of helpers like __put_user and by improper attempts to access
+ * userspace addresses in KERNEL_DS regions.
+ * The one (semi-)legitimate exception are probe_kernel_{read,write}(),
+ * which can be invoked from places like kgdb, /dev/mem (for reading)
+ * and privileged BPF code (for reading).
+ * The probe_kernel_*() functions set the kernel_uaccess_faults_ok flag
+ * to tell us that faulting on kernel addresses, and even noncanonical
+ * addresses, in a userspace accessor does not necessarily imply a
+ * kernel bug, root might just be doing weird stuff.
+ */
+ if (current->kernel_uaccess_faults_ok)
+ return false;
+
+ /* This is bad. Refuse the fixup so that we go into die(). */
+ if (trapnr == X86_TRAP_PF) {
+ pr_emerg("BUG: pagefault on kernel address 0x%lx in non-whitelisted uaccess\n",
+ fault_addr);
+ } else {
+ pr_emerg("BUG: GPF in non-whitelisted uaccess (non-canonical address?)\n");
+ }
+ return true;
+}
+
+__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
+{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
+ regs->ip = ex_fixup_addr(fixup);
+ return true;
+}
+EXPORT_SYMBOL(ex_handler_uaccess);
+
__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
+ if (bogus_uaccess(regs, trapnr, fault_addr))
+ return false;
/* Special hack for uaccess_err */
current->thread.uaccess_err = 1;
regs->ip = ex_fixup_addr(fixup);
@@ -119,7 +198,9 @@ __visible bool ex_handler_ext(const struct exception_table_entry *fixup,
EXPORT_SYMBOL(ex_handler_ext);
__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
@@ -134,7 +215,9 @@ __visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
@@ -148,12 +231,14 @@ __visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
- struct pt_regs *regs, int trapnr)
+ struct pt_regs *regs, int trapnr,
+ unsigned long error_code,
+ unsigned long fault_addr)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
asm volatile ("mov %0, %%fs" : : "rm" (0));
- return ex_handler_default(fixup, regs, trapnr);
+ return ex_handler_default(fixup, regs, trapnr, error_code, fault_addr);
}
EXPORT_SYMBOL(ex_handler_clear_fs);
@@ -170,7 +255,8 @@ __visible bool ex_has_fault_handler(unsigned long ip)
return handler == ex_handler_fault;
}
-int fixup_exception(struct pt_regs *regs, int trapnr)
+int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
+ unsigned long fault_addr)
{
const struct exception_table_entry *e;
ex_handler_t handler;
@@ -194,7 +280,7 @@ int fixup_exception(struct pt_regs *regs, int trapnr)
return 0;
handler = ex_fixup_handler(e);
- return handler(e, regs, trapnr);
+ return handler(e, regs, trapnr, error_code, fault_addr);
}
extern unsigned int early_recursion_flag;
@@ -230,9 +316,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
* result in a hard-to-debug panic.
*
* Keep in mind that not all vectors actually get here. Early
- * fage faults, for example, are special.
+ * page faults, for example, are special.
*/
- if (fixup_exception(regs, trapnr))
+ if (fixup_exception(regs, trapnr, regs->orig_ax, 0))
return;
if (fixup_bug(regs, trapnr))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 47bebfe6efa7..0d45f6debb3a 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -16,6 +16,7 @@
#include <linux/prefetch.h> /* prefetchw */
#include <linux/context_tracking.h> /* exception_enter(), ... */
#include <linux/uaccess.h> /* faulthandler_disabled() */
+#include <linux/efi.h> /* efi_recover_from_page_fault()*/
#include <linux/mm_types.h>
#include <asm/cpufeature.h> /* boot_cpu_has, ... */
@@ -25,6 +26,7 @@
#include <asm/vsyscall.h> /* emulate_vsyscall */
#include <asm/vm86.h> /* struct vm86 */
#include <asm/mmu_context.h> /* vma_pkey() */
+#include <asm/efi.h> /* efi_recover_from_page_fault()*/
#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>
@@ -44,17 +46,19 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
static nokprobe_inline int kprobes_fault(struct pt_regs *regs)
{
- int ret = 0;
-
- /* kprobe_running() needs smp_processor_id() */
- if (kprobes_built_in() && !user_mode(regs)) {
- preempt_disable();
- if (kprobe_running() && kprobe_fault_handler(regs, 14))
- ret = 1;
- preempt_enable();
- }
-
- return ret;
+ if (!kprobes_built_in())
+ return 0;
+ if (user_mode(regs))
+ return 0;
+ /*
+ * To be potentially processing a kprobe fault and to be allowed to call
+ * kprobe_running(), we have to be non-preemptible.
+ */
+ if (preemptible())
+ return 0;
+ if (!kprobe_running())
+ return 0;
+ return kprobe_fault_handler(regs, X86_TRAP_PF);
}
/*
@@ -709,7 +713,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
int sig;
/* Are we prepared to handle this kernel fault? */
- if (fixup_exception(regs, X86_TRAP_PF)) {
+ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
/*
* Any interrupt that takes a fault gets the fixup. This makes
* the below recursive fault logic only apply to a faults from
@@ -789,6 +793,13 @@ no_context(struct pt_regs *regs, unsigned long error_code,
return;
/*
+ * Buggy firmware could access regions which might page fault, try to
+ * recover from such faults.
+ */
+ if (IS_ENABLED(CONFIG_EFI))
+ efi_recover_from_page_fault(address);
+
+ /*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice:
*/
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 089e78c4effd..59274e2c1ac4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -115,6 +115,8 @@ static inline void pgd_list_del(pgd_t *pgd)
#define UNSHARED_PTRS_PER_PGD \
(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
+#define MAX_UNSHARED_PTRS_PER_PGD \
+ max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
@@ -181,6 +183,7 @@ static void pgd_dtor(pgd_t *pgd)
* and initialize the kernel pmds here.
*/
#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD
+#define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD
/*
* We allocate separate PMDs for the kernel part of the user page-table
@@ -189,6 +192,7 @@ static void pgd_dtor(pgd_t *pgd)
*/
#define PREALLOCATED_USER_PMDS (static_cpu_has(X86_FEATURE_PTI) ? \
KERNEL_PGD_PTRS : 0)
+#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
{
@@ -210,7 +214,9 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS 0
+#define MAX_PREALLOCATED_PMDS 0
#define PREALLOCATED_USER_PMDS 0
+#define MAX_PREALLOCATED_USER_PMDS 0
#endif /* CONFIG_X86_PAE */
static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
@@ -428,8 +434,8 @@ static inline void _pgd_free(pgd_t *pgd)
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
- pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
- pmd_t *pmds[PREALLOCATED_PMDS];
+ pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
+ pmd_t *pmds[MAX_PREALLOCATED_PMDS];
pgd = _pgd_alloc();
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 5fdacb322ceb..7476b3b097e1 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -26,12 +26,14 @@ static bool early_efi_keep;
*/
static __init int early_efi_map_fb(void)
{
- unsigned long base, size;
+ u64 base, size;
if (!early_efi_keep)
return 0;
base = boot_params.screen_info.lfb_base;
+ if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
size = boot_params.screen_info.lfb_size;
efi_fb = ioremap(base, size);
@@ -46,9 +48,11 @@ early_initcall(early_efi_map_fb);
*/
static __ref void *early_efi_map(unsigned long start, unsigned long len)
{
- unsigned long base;
+ u64 base;
base = boot_params.screen_info.lfb_base;
+ if (boot_params.screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+ base |= (u64)boot_params.screen_info.ext_lfb_base << 32;
if (efi_fb)
return (efi_fb + start);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index ee5d08f25ce4..e8da7f492970 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void)
/*
* Makes the calling thread switch to/from efi_mm context. Can be used
- * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well
- * as during efi runtime calls i.e current->active_mm == current_mm.
- * We are not mm_dropping()/mm_grabbing() any mm, because we are not
- * losing/creating any references.
+ * in a kernel thread and user context. Preemption needs to remain disabled
+ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm
+ * can not change under us.
+ * It should be ensured that there are no concurent calls to this function.
*/
void efi_switch_mm(struct mm_struct *mm)
{
- task_lock(current);
efi_scratch.prev_mm = current->active_mm;
current->active_mm = mm;
switch_mm(efi_scratch.prev_mm, mm, NULL);
- task_unlock(current);
}
#ifdef CONFIG_EFI_MIXED
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 844d31cb8a0c..669babcaf245 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -16,6 +16,7 @@
#include <asm/efi.h>
#include <asm/uv/uv.h>
#include <asm/cpu_device_id.h>
+#include <asm/reboot.h>
#define EFI_MIN_RESERVE 5120
@@ -654,3 +655,80 @@ int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff,
}
#endif
+
+/*
+ * If any access by any efi runtime service causes a page fault, then,
+ * 1. If it's efi_reset_system(), reboot through BIOS.
+ * 2. If any other efi runtime service, then
+ * a. Return error status to the efi caller process.
+ * b. Disable EFI Runtime Services forever and
+ * c. Freeze efi_rts_wq and schedule new process.
+ *
+ * @return: Returns, if the page fault is not handled. This function
+ * will never return if the page fault is handled successfully.
+ */
+void efi_recover_from_page_fault(unsigned long phys_addr)
+{
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ /*
+ * Make sure that an efi runtime service caused the page fault.
+ * "efi_mm" cannot be used to check if the page fault had occurred
+ * in the firmware context because efi=old_map doesn't use efi_pgd.
+ */
+ if (efi_rts_work.efi_rts_id == NONE)
+ return;
+
+ /*
+ * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
+ * page faulting on these addresses isn't expected.
+ */
+ if (phys_addr >= 0x0000 && phys_addr <= 0x0fff)
+ return;
+
+ /*
+ * Print stack trace as it might be useful to know which EFI Runtime
+ * Service is buggy.
+ */
+ WARN(1, FW_BUG "Page fault caused by firmware at PA: 0x%lx\n",
+ phys_addr);
+
+ /*
+ * Buggy efi_reset_system() is handled differently from other EFI
+ * Runtime Services as it doesn't use efi_rts_wq. Although,
+ * native_machine_emergency_restart() says that machine_real_restart()
+ * could fail, it's better not to compilcate this fault handler
+ * because this case occurs *very* rarely and hence could be improved
+ * on a need by basis.
+ */
+ if (efi_rts_work.efi_rts_id == RESET_SYSTEM) {
+ pr_info("efi_reset_system() buggy! Reboot through BIOS\n");
+ machine_real_restart(MRR_BIOS);
+ return;
+ }
+
+ /*
+ * Before calling EFI Runtime Service, the kernel has switched the
+ * calling process to efi_mm. Hence, switch back to task_mm.
+ */
+ arch_efi_call_virt_teardown();
+
+ /* Signal error status to the efi caller process */
+ efi_rts_work.status = EFI_ABORTED;
+ complete(&efi_rts_work.efi_rts_comp);
+
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ pr_info("Froze efi_rts_wq and disabled EFI Runtime Services\n");
+
+ /*
+ * Call schedule() in an infinite loop, so that any spurious wake ups
+ * will never run efi_rts_wq again.
+ */
+ for (;;) {
+ set_current_state(TASK_IDLE);
+ schedule();
+ }
+
+ return;
+}
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
index 4392c15ed9e0..dbfc5cf2aa93 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bcm43xx.c
@@ -10,7 +10,7 @@
* of the License.
*/
-#include <linux/gpio.h>
+#include <linux/gpio/machine.h>
#include <linux/platform_device.h>
#include <linux/regulator/machine.h>
#include <linux/regulator/fixed.h>
@@ -43,7 +43,6 @@ static struct fixed_voltage_config bcm43xx_vmmc = {
* real voltage and signaling are still 1.8V.
*/
.microvolts = 2000000, /* 1.8V */
- .gpio = -EINVAL,
.startup_delay = 250 * 1000, /* 250ms */
.enable_high = 1, /* active high */
.enabled_at_boot = 0, /* disabled at boot */
@@ -58,11 +57,23 @@ static struct platform_device bcm43xx_vmmc_regulator = {
},
};
+static struct gpiod_lookup_table bcm43xx_vmmc_gpio_table = {
+ .dev_id = "reg-fixed-voltage.0",
+ .table = {
+ GPIO_LOOKUP("0000:00:0c.0", -1, NULL, GPIO_ACTIVE_LOW),
+ {}
+ },
+};
+
static int __init bcm43xx_regulator_register(void)
{
+ struct gpiod_lookup_table *table = &bcm43xx_vmmc_gpio_table;
+ struct gpiod_lookup *lookup = table->table;
int ret;
- bcm43xx_vmmc.gpio = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME);
+ lookup[0].chip_hwnum = get_gpio_by_name(WLAN_SFI_GPIO_ENABLE_NAME);
+ gpiod_add_lookup_table(table);
+
ret = platform_device_register(&bcm43xx_vmmc_regulator);
if (ret) {
pr_err("%s: vmmc regulator register failed\n", __func__);
diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c
index fd39301f25ac..7e56fc74093c 100644
--- a/arch/x86/platform/ts5500/ts5500.c
+++ b/arch/x86/platform/ts5500/ts5500.c
@@ -24,7 +24,6 @@
#include <linux/kernel.h>
#include <linux/leds.h>
#include <linux/init.h>
-#include <linux/platform_data/gpio-ts5500.h>
#include <linux/platform_data/max197.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index a4701389562c..37923d715741 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -7,4 +7,4 @@ nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_cpu.o := $(nostackp)
obj-$(CONFIG_PM_SLEEP) += cpu.o
-obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o
+obj-$(CONFIG_HIBERNATION) += hibernate_$(BITS).o hibernate_asm_$(BITS).o hibernate.o
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
new file mode 100644
index 000000000000..bcddf09b5aa3
--- /dev/null
+++ b/arch/x86/power/hibernate.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hibernation support for x86
+ *
+ * Copyright (c) 2007 Rafael J. Wysocki <rjw@sisk.pl>
+ * Copyright (c) 2002 Pavel Machek <pavel@ucw.cz>
+ * Copyright (c) 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#include <linux/gfp.h>
+#include <linux/smp.h>
+#include <linux/suspend.h>
+#include <linux/scatterlist.h>
+#include <linux/kdebug.h>
+
+#include <crypto/hash.h>
+
+#include <asm/e820/api.h>
+#include <asm/init.h>
+#include <asm/proto.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include <asm/mtrr.h>
+#include <asm/sections.h>
+#include <asm/suspend.h>
+#include <asm/tlbflush.h>
+
+/*
+ * Address to jump to in the last phase of restore in order to get to the image
+ * kernel's text (this value is passed in the image header).
+ */
+unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
+
+/*
+ * Value of the cr3 register from before the hibernation (this value is passed
+ * in the image header).
+ */
+unsigned long restore_cr3 __visible;
+unsigned long temp_pgt __visible;
+unsigned long relocated_restore_code __visible;
+
+/**
+ * pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+int pfn_is_nosave(unsigned long pfn)
+{
+ unsigned long nosave_begin_pfn;
+ unsigned long nosave_end_pfn;
+
+ nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+ nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+
+ return pfn >= nosave_begin_pfn && pfn < nosave_end_pfn;
+}
+
+
+#define MD5_DIGEST_SIZE 16
+
+struct restore_data_record {
+ unsigned long jump_address;
+ unsigned long jump_address_phys;
+ unsigned long cr3;
+ unsigned long magic;
+ u8 e820_digest[MD5_DIGEST_SIZE];
+};
+
+#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
+/**
+ * get_e820_md5 - calculate md5 according to given e820 table
+ *
+ * @table: the e820 table to be calculated
+ * @buf: the md5 result to be stored to
+ */
+static int get_e820_md5(struct e820_table *table, void *buf)
+{
+ struct crypto_shash *tfm;
+ struct shash_desc *desc;
+ int size;
+ int ret = 0;
+
+ tfm = crypto_alloc_shash("md5", 0, 0);
+ if (IS_ERR(tfm))
+ return -ENOMEM;
+
+ desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+ GFP_KERNEL);
+ if (!desc) {
+ ret = -ENOMEM;
+ goto free_tfm;
+ }
+
+ desc->tfm = tfm;
+ desc->flags = 0;
+
+ size = offsetof(struct e820_table, entries) +
+ sizeof(struct e820_entry) * table->nr_entries;
+
+ if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+ ret = -EINVAL;
+
+ kzfree(desc);
+
+free_tfm:
+ crypto_free_shash(tfm);
+ return ret;
+}
+
+static int hibernation_e820_save(void *buf)
+{
+ return get_e820_md5(e820_table_firmware, buf);
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+ int ret;
+ u8 result[MD5_DIGEST_SIZE];
+
+ memset(result, 0, MD5_DIGEST_SIZE);
+ /* If there is no digest in suspend kernel, let it go. */
+ if (!memcmp(result, buf, MD5_DIGEST_SIZE))
+ return false;
+
+ ret = get_e820_md5(e820_table_firmware, result);
+ if (ret)
+ return true;
+
+ return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
+}
+#else
+static int hibernation_e820_save(void *buf)
+{
+ return 0;
+}
+
+static bool hibernation_e820_mismatch(void *buf)
+{
+ /* If md5 is not builtin for restore kernel, let it go. */
+ return false;
+}
+#endif
+
+#ifdef CONFIG_X86_64
+#define RESTORE_MAGIC 0x23456789ABCDEF01UL
+#else
+#define RESTORE_MAGIC 0x12345678UL
+#endif
+
+/**
+ * arch_hibernation_header_save - populate the architecture specific part
+ * of a hibernation image header
+ * @addr: address to save the data at
+ */
+int arch_hibernation_header_save(void *addr, unsigned int max_size)
+{
+ struct restore_data_record *rdr = addr;
+
+ if (max_size < sizeof(struct restore_data_record))
+ return -EOVERFLOW;
+ rdr->magic = RESTORE_MAGIC;
+ rdr->jump_address = (unsigned long)restore_registers;
+ rdr->jump_address_phys = __pa_symbol(restore_registers);
+
+ /*
+ * The restore code fixes up CR3 and CR4 in the following sequence:
+ *
+ * [in hibernation asm]
+ * 1. CR3 <= temporary page tables
+ * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
+ * 3. CR3 <= rdr->cr3
+ * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
+ * [in restore_processor_state()]
+ * 5. CR4 <= saved CR4
+ * 6. CR3 <= saved CR3
+ *
+ * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
+ * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
+ * rdr->cr3 needs to point to valid page tables but must not
+ * have any of the PCID bits set.
+ */
+ rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
+
+ return hibernation_e820_save(rdr->e820_digest);
+}
+
+/**
+ * arch_hibernation_header_restore - read the architecture specific data
+ * from the hibernation image header
+ * @addr: address to read the data from
+ */
+int arch_hibernation_header_restore(void *addr)
+{
+ struct restore_data_record *rdr = addr;
+
+ if (rdr->magic != RESTORE_MAGIC) {
+ pr_crit("Unrecognized hibernate image header format!\n");
+ return -EINVAL;
+ }
+
+ restore_jump_address = rdr->jump_address;
+ jump_address_phys = rdr->jump_address_phys;
+ restore_cr3 = rdr->cr3;
+
+ if (hibernation_e820_mismatch(rdr->e820_digest)) {
+ pr_crit("Hibernate inconsistent memory map detected!\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+int relocate_restore_code(void)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ relocated_restore_code = get_safe_page(GFP_ATOMIC);
+ if (!relocated_restore_code)
+ return -ENOMEM;
+
+ memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
+
+ /* Make the page containing the relocated code executable */
+ pgd = (pgd_t *)__va(read_cr3_pa()) +
+ pgd_index(relocated_restore_code);
+ p4d = p4d_offset(pgd, relocated_restore_code);
+ if (p4d_large(*p4d)) {
+ set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
+ goto out;
+ }
+ pud = pud_offset(p4d, relocated_restore_code);
+ if (pud_large(*pud)) {
+ set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+ goto out;
+ }
+ pmd = pmd_offset(pud, relocated_restore_code);
+ if (pmd_large(*pmd)) {
+ set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+ goto out;
+ }
+ pte = pte_offset_kernel(pmd, relocated_restore_code);
+ set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+out:
+ __flush_tlb_all();
+ return 0;
+}
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index afc4ed7b1578..15695e30f982 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -14,9 +14,7 @@
#include <asm/pgtable.h>
#include <asm/mmzone.h>
#include <asm/sections.h>
-
-/* Defined in hibernate_asm_32.S */
-extern int restore_image(void);
+#include <asm/suspend.h>
/* Pointer to the temporary resume page tables */
pgd_t *resume_pg_dir;
@@ -145,6 +143,32 @@ static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
#endif
}
+static int set_up_temporary_text_mapping(pgd_t *pgd_base)
+{
+ pgd_t *pgd;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_base + pgd_index(restore_jump_address);
+
+ pmd = resume_one_md_table_init(pgd);
+ if (!pmd)
+ return -ENOMEM;
+
+ if (boot_cpu_has(X86_FEATURE_PSE)) {
+ set_pmd(pmd + pmd_index(restore_jump_address),
+ __pmd((jump_address_phys & PMD_MASK) | pgprot_val(PAGE_KERNEL_LARGE_EXEC)));
+ } else {
+ pte = resume_one_page_table_init(pmd);
+ if (!pte)
+ return -ENOMEM;
+ set_pte(pte + pte_index(restore_jump_address),
+ __pte((jump_address_phys & PAGE_MASK) | pgprot_val(PAGE_KERNEL_EXEC)));
+ }
+
+ return 0;
+}
+
asmlinkage int swsusp_arch_resume(void)
{
int error;
@@ -154,22 +178,22 @@ asmlinkage int swsusp_arch_resume(void)
return -ENOMEM;
resume_init_first_level_page_table(resume_pg_dir);
+
+ error = set_up_temporary_text_mapping(resume_pg_dir);
+ if (error)
+ return error;
+
error = resume_physical_mapping_init(resume_pg_dir);
if (error)
return error;
+ temp_pgt = __pa(resume_pg_dir);
+
+ error = relocate_restore_code();
+ if (error)
+ return error;
+
/* We have got enough memory and from now on we cannot recover */
restore_image();
return 0;
}
-
-/*
- * pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
- unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
- unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
- return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index f8e3b668d20b..239f424ccb29 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -26,26 +26,6 @@
#include <asm/suspend.h>
#include <asm/tlbflush.h>
-/* Defined in hibernate_asm_64.S */
-extern asmlinkage __visible int restore_image(void);
-
-/*
- * Address to jump to in the last phase of restore in order to get to the image
- * kernel's text (this value is passed in the image header).
- */
-unsigned long restore_jump_address __visible;
-unsigned long jump_address_phys;
-
-/*
- * Value of the cr3 register from before the hibernation (this value is passed
- * in the image header).
- */
-unsigned long restore_cr3 __visible;
-
-unsigned long temp_level4_pgt __visible;
-
-unsigned long relocated_restore_code __visible;
-
static int set_up_temporary_text_mapping(pgd_t *pgd)
{
pmd_t *pmd;
@@ -141,46 +121,7 @@ static int set_up_temporary_mappings(void)
return result;
}
- temp_level4_pgt = __pa(pgd);
- return 0;
-}
-
-static int relocate_restore_code(void)
-{
- pgd_t *pgd;
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- relocated_restore_code = get_safe_page(GFP_ATOMIC);
- if (!relocated_restore_code)
- return -ENOMEM;
-
- memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE);
-
- /* Make the page containing the relocated code executable */
- pgd = (pgd_t *)__va(read_cr3_pa()) +
- pgd_index(relocated_restore_code);
- p4d = p4d_offset(pgd, relocated_restore_code);
- if (p4d_large(*p4d)) {
- set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
- goto out;
- }
- pud = pud_offset(p4d, relocated_restore_code);
- if (pud_large(*pud)) {
- set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
- goto out;
- }
- pmd = pmd_offset(pud, relocated_restore_code);
- if (pmd_large(*pmd)) {
- set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
- goto out;
- }
- pte = pte_offset_kernel(pmd, relocated_restore_code);
- set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
-out:
- __flush_tlb_all();
+ temp_pgt = __pa(pgd);
return 0;
}
@@ -200,166 +141,3 @@ asmlinkage int swsusp_arch_resume(void)
restore_image();
return 0;
}
-
-/*
- * pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-int pfn_is_nosave(unsigned long pfn)
-{
- unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
- unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
- return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
-#define MD5_DIGEST_SIZE 16
-
-struct restore_data_record {
- unsigned long jump_address;
- unsigned long jump_address_phys;
- unsigned long cr3;
- unsigned long magic;
- u8 e820_digest[MD5_DIGEST_SIZE];
-};
-
-#define RESTORE_MAGIC 0x23456789ABCDEF01UL
-
-#if IS_BUILTIN(CONFIG_CRYPTO_MD5)
-/**
- * get_e820_md5 - calculate md5 according to given e820 table
- *
- * @table: the e820 table to be calculated
- * @buf: the md5 result to be stored to
- */
-static int get_e820_md5(struct e820_table *table, void *buf)
-{
- struct crypto_shash *tfm;
- struct shash_desc *desc;
- int size;
- int ret = 0;
-
- tfm = crypto_alloc_shash("md5", 0, 0);
- if (IS_ERR(tfm))
- return -ENOMEM;
-
- desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
- GFP_KERNEL);
- if (!desc) {
- ret = -ENOMEM;
- goto free_tfm;
- }
-
- desc->tfm = tfm;
- desc->flags = 0;
-
- size = offsetof(struct e820_table, entries) +
- sizeof(struct e820_entry) * table->nr_entries;
-
- if (crypto_shash_digest(desc, (u8 *)table, size, buf))
- ret = -EINVAL;
-
- kzfree(desc);
-
-free_tfm:
- crypto_free_shash(tfm);
- return ret;
-}
-
-static void hibernation_e820_save(void *buf)
-{
- get_e820_md5(e820_table_firmware, buf);
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
- int ret;
- u8 result[MD5_DIGEST_SIZE];
-
- memset(result, 0, MD5_DIGEST_SIZE);
- /* If there is no digest in suspend kernel, let it go. */
- if (!memcmp(result, buf, MD5_DIGEST_SIZE))
- return false;
-
- ret = get_e820_md5(e820_table_firmware, result);
- if (ret)
- return true;
-
- return memcmp(result, buf, MD5_DIGEST_SIZE) ? true : false;
-}
-#else
-static void hibernation_e820_save(void *buf)
-{
-}
-
-static bool hibernation_e820_mismatch(void *buf)
-{
- /* If md5 is not builtin for restore kernel, let it go. */
- return false;
-}
-#endif
-
-/**
- * arch_hibernation_header_save - populate the architecture specific part
- * of a hibernation image header
- * @addr: address to save the data at
- */
-int arch_hibernation_header_save(void *addr, unsigned int max_size)
-{
- struct restore_data_record *rdr = addr;
-
- if (max_size < sizeof(struct restore_data_record))
- return -EOVERFLOW;
- rdr->jump_address = (unsigned long)restore_registers;
- rdr->jump_address_phys = __pa_symbol(restore_registers);
-
- /*
- * The restore code fixes up CR3 and CR4 in the following sequence:
- *
- * [in hibernation asm]
- * 1. CR3 <= temporary page tables
- * 2. CR4 <= mmu_cr4_features (from the kernel that restores us)
- * 3. CR3 <= rdr->cr3
- * 4. CR4 <= mmu_cr4_features (from us, i.e. the image kernel)
- * [in restore_processor_state()]
- * 5. CR4 <= saved CR4
- * 6. CR3 <= saved CR3
- *
- * Our mmu_cr4_features has CR4.PCIDE=0, and toggling
- * CR4.PCIDE while CR3's PCID bits are nonzero is illegal, so
- * rdr->cr3 needs to point to valid page tables but must not
- * have any of the PCID bits set.
- */
- rdr->cr3 = restore_cr3 & ~CR3_PCID_MASK;
-
- rdr->magic = RESTORE_MAGIC;
-
- hibernation_e820_save(rdr->e820_digest);
-
- return 0;
-}
-
-/**
- * arch_hibernation_header_restore - read the architecture specific data
- * from the hibernation image header
- * @addr: address to read the data from
- */
-int arch_hibernation_header_restore(void *addr)
-{
- struct restore_data_record *rdr = addr;
-
- restore_jump_address = rdr->jump_address;
- jump_address_phys = rdr->jump_address_phys;
- restore_cr3 = rdr->cr3;
-
- if (rdr->magic != RESTORE_MAGIC) {
- pr_crit("Unrecognized hibernate image header format!\n");
- return -EINVAL;
- }
-
- if (hibernation_e820_mismatch(rdr->e820_digest)) {
- pr_crit("Hibernate inconsistent memory map detected!\n");
- return -ENODEV;
- }
-
- return 0;
-}
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 6e56815e13a0..6fe383002125 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -12,6 +12,7 @@
#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
+#include <asm/frame.h>
.text
@@ -24,13 +25,30 @@ ENTRY(swsusp_arch_suspend)
pushfl
popl saved_context_eflags
+ /* save cr3 */
+ movl %cr3, %eax
+ movl %eax, restore_cr3
+
+ FRAME_BEGIN
call swsusp_save
+ FRAME_END
ret
+ENDPROC(swsusp_arch_suspend)
ENTRY(restore_image)
+ /* prepare to jump to the image kernel */
+ movl restore_jump_address, %ebx
+ movl restore_cr3, %ebp
+
movl mmu_cr4_features, %ecx
- movl resume_pg_dir, %eax
- subl $__PAGE_OFFSET, %eax
+
+ /* jump to relocated restore code */
+ movl relocated_restore_code, %eax
+ jmpl *%eax
+
+/* code below has been relocated to a safe page */
+ENTRY(core_restore_code)
+ movl temp_pgt, %eax
movl %eax, %cr3
jecxz 1f # cr4 Pentium and higher, skip if zero
@@ -49,7 +67,7 @@ copy_loop:
movl pbe_address(%edx), %esi
movl pbe_orig_address(%edx), %edi
- movl $1024, %ecx
+ movl $(PAGE_SIZE >> 2), %ecx
rep
movsl
@@ -58,10 +76,13 @@ copy_loop:
.p2align 4,,7
done:
+ jmpl *%ebx
+
+ /* code below belongs to the image kernel */
+ .align PAGE_SIZE
+ENTRY(restore_registers)
/* go back to the original page tables */
- movl $swapper_pg_dir, %eax
- subl $__PAGE_OFFSET, %eax
- movl %eax, %cr3
+ movl %ebp, %cr3
movl mmu_cr4_features, %ecx
jecxz 1f # cr4 Pentium and higher, skip if zero
movl %ecx, %cr4; # turn PGE back on
@@ -82,4 +103,8 @@ done:
xorl %eax, %eax
+ /* tell the hibernation core that we've just restored the memory */
+ movl %eax, in_suspend
+
ret
+ENDPROC(restore_registers)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index fd369a6e9ff8..3008baa2fa95 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -59,7 +59,7 @@ ENTRY(restore_image)
movq restore_cr3(%rip), %r9
/* prepare to switch to temporary page tables */
- movq temp_level4_pgt(%rip), %rax
+ movq temp_pgt(%rip), %rax
movq mmu_cr4_features(%rip), %rbx
/* prepare to copy image data to their original locations */
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 3a6c8ebc8032..0b08067c45f3 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -196,6 +196,7 @@ static const char *rel_type(unsigned type)
#if ELF_BITS == 64
REL_TYPE(R_X86_64_NONE),
REL_TYPE(R_X86_64_64),
+ REL_TYPE(R_X86_64_PC64),
REL_TYPE(R_X86_64_PC32),
REL_TYPE(R_X86_64_GOT32),
REL_TYPE(R_X86_64_PLT32),
@@ -782,6 +783,15 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
add_reloc(&relocs32neg, offset);
break;
+ case R_X86_64_PC64:
+ /*
+ * Only used by jump labels
+ */
+ if (is_percpu_sym(sym, symname))
+ die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n",
+ symname);
+ break;
+
case R_X86_64_32:
case R_X86_64_32S:
case R_X86_64_64:
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 548197212a45..413f3519d9a1 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -116,8 +116,7 @@ do { \
#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */
#define R_X86_64_8 14 /* Direct 8 bit sign extended */
#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM 16
+#define R_X86_64_PC64 24 /* Place relative 64-bit signed */
/*
* This is used to ensure we don't load something for the wrong architecture.
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2eeddd814653..0ca46e03b830 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -5,6 +5,7 @@
#include <linux/kexec.h>
#include <linux/slab.h>
+#include <xen/xen.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/interface/memory.h>
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index c85d1a88f476..2a9025343534 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -11,6 +11,7 @@
#include <asm/xen/interface.h>
#include <asm/xen/hypercall.h>
+#include <xen/xen.h>
#include <xen/interface/memory.h>
#include <xen/interface/hvm/start_info.h>
diff --git a/arch/x86/xen/platform-pci-unplug.c b/arch/x86/xen/platform-pci-unplug.c
index 33a783c77d96..b99585034dd2 100644
--- a/arch/x86/xen/platform-pci-unplug.c
+++ b/arch/x86/xen/platform-pci-unplug.c
@@ -23,6 +23,7 @@
#include <linux/io.h>
#include <linux/export.h>
+#include <xen/xen.h>
#include <xen/platform_pci.h>
#include "xen-ops.h"
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 95997e6c0696..0972184f3f19 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -3,6 +3,7 @@
#include <linux/interrupt.h>
#include <asm/xen/hypercall.h>
+#include <xen/xen.h>
#include <xen/page.h>
#include <xen/interface/xen.h>
#include <xen/interface/vcpu.h>