#define _ASM_ARM_PARAVIRT_H
#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops {
- unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
- struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_ops.time.steal_clock(cpu);
+ return static_call(pv_steal_clock)(cpu);
}
#endif
#include <linux/export.h>
#include <linux/jump_label.h>
#include <linux/types.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
#define _ASM_ARM64_PARAVIRT_H
#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops {
- unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
- struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_ops.time.steal_clock(cpu);
+ return static_call(pv_steal_clock)(cpu);
}
int __init pv_time_init(void);
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/types.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
#include <asm/pvclock-abi.h>
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
struct pv_time_stolen_time_region {
struct pvclock_vcpu_stolen_time *kaddr;
early_param("no-steal-acc", parse_no_stealacc);
/* return stolen time in ns by asking the hypervisor */
-static u64 pv_steal_clock(int cpu)
+static u64 para_steal_clock(int cpu)
{
struct pv_time_stolen_time_region *reg;
if (ret)
return ret;
- pv_ops.time.steal_clock = pv_steal_clock;
+ static_call_update(pv_steal_clock, para_steal_clock);
static_key_slow_inc(¶virt_steal_enabled);
if (steal_acc)
def_bool y
depends on X86_64 && SMP
-config X86_32_LAZY_GS
- def_bool y
- depends on X86_32 && !STACKPROTECTOR
-
config ARCH_SUPPORTS_UPROBES
def_bool y
default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC))
help
We have to make sure stack protector is unconditionally disabled if
- the compiler produces broken code.
+ the compiler produces broken code or if it does not let us control
+ the segment on 32-bit kernels.
menu "Processor type and features"
config PARAVIRT
bool "Enable paravirtualization code"
+ depends on HAVE_STATIC_CALL
help
This changes the kernel so it can modify itself when it is run
under a hypervisor, potentially improving performance significantly
select ARCH_USE_MEMREMAP_PROT
select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select INSTRUCTION_DECODER
+ select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
help
Say yes to enable support for the encryption of system memory.
This requires an AMD processor that supports Secure Memory
# temporary until string.h is fixed
KBUILD_CFLAGS += -ffreestanding
+
+ ifeq ($(CONFIG_STACKPROTECTOR),y)
+ ifeq ($(CONFIG_SMP),y)
+ KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard
+ else
+ KBUILD_CFLAGS += -mstack-protector-guard=global
+ endif
+ endif
else
BITS := 64
UTS_MACHINE := x86_64
static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
{
char buffer[MAX_INSN_SIZE];
- enum es_result ret;
+ int ret;
memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
- insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
- insn_get_length(&ctxt->insn);
+ ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+ if (ret < 0)
+ return ES_DECODE_FAILED;
- ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
-
- return ret;
+ return ES_OK;
}
static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
* 1C(%esp) - %ds
* 20(%esp) - %es
* 24(%esp) - %fs
- * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
+ * 28(%esp) - unused -- was %gs on old stackprotector kernels
* 2C(%esp) - orig_eax
* 30(%esp) - %eip
* 34(%esp) - %cs
#include <asm/processor-flags.h>
#include <asm/irq_vectors.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/frame.h>
#define PTI_SWITCH_MASK (1 << PAGE_SHIFT)
-/*
- * User gs save/restore
- *
- * %gs is used for userland TLS and kernel only uses it for stack
- * canary which is required to be at %gs:20 by gcc. Read the comment
- * at the top of stackprotector.h for more info.
- *
- * Local labels 98 and 99 are used.
- */
-#ifdef CONFIG_X86_32_LAZY_GS
-
- /* unfortunately push/pop can't be no-op */
-.macro PUSH_GS
- pushl $0
-.endm
-.macro POP_GS pop=0
- addl $(4 + \pop), %esp
-.endm
-.macro POP_GS_EX
-.endm
-
- /* all the rest are no-op */
-.macro PTGS_TO_GS
-.endm
-.macro PTGS_TO_GS_EX
-.endm
-.macro GS_TO_REG reg
-.endm
-.macro REG_TO_PTGS reg
-.endm
-.macro SET_KERNEL_GS reg
-.endm
-
-#else /* CONFIG_X86_32_LAZY_GS */
-
-.macro PUSH_GS
- pushl %gs
-.endm
-
-.macro POP_GS pop=0
-98: popl %gs
- .if \pop <> 0
- add $\pop, %esp
- .endif
-.endm
-.macro POP_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, (%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro PTGS_TO_GS
-98: mov PT_GS(%esp), %gs
-.endm
-.macro PTGS_TO_GS_EX
-.pushsection .fixup, "ax"
-99: movl $0, PT_GS(%esp)
- jmp 98b
-.popsection
- _ASM_EXTABLE(98b, 99b)
-.endm
-
-.macro GS_TO_REG reg
- movl %gs, \reg
-.endm
-.macro REG_TO_PTGS reg
- movl \reg, PT_GS(%esp)
-.endm
-.macro SET_KERNEL_GS reg
- movl $(__KERNEL_STACK_CANARY), \reg
- movl \reg, %gs
-.endm
-
-#endif /* CONFIG_X86_32_LAZY_GS */
-
/* Unconditionally switch to user cr3 */
.macro SWITCH_TO_USER_CR3 scratch_reg:req
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0 skip_gs=0 unwind_espfix=0
cld
.if \skip_gs == 0
- PUSH_GS
+ pushl $0
.endif
pushl %fs
movl $(__USER_DS), %edx
movl %edx, %ds
movl %edx, %es
-.if \skip_gs == 0
- SET_KERNEL_GS %edx
-.endif
/* Switch to kernel stack if necessary */
.if \switch_stacks > 0
SWITCH_TO_KERNEL_STACK
1: popl %ds
2: popl %es
3: popl %fs
- POP_GS \pop
+ addl $(4 + \pop), %esp /* pop the unused "gs" slot */
IRET_FRAME
.pushsection .fixup, "ax"
4: movl $0, (%esp)
_ASM_EXTABLE(1b, 4b)
_ASM_EXTABLE(2b, 5b)
_ASM_EXTABLE(3b, 6b)
- POP_GS_EX
.endm
.macro RESTORE_ALL_NMI cr3_reg:req pop=0
* will soon execute iret and the tracer was already set to
* the irqstate after the IRET:
*/
- DISABLE_INTERRUPTS(CLBR_ANY)
+ cli
lss (%esp), %esp /* switch to espfix segment */
.Lend_\@:
#endif /* CONFIG_X86_ESPFIX32 */
#ifdef CONFIG_STACKPROTECTOR
movl TASK_stack_canary(%edx), %ebx
- movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+ movl %ebx, PER_CPU_VAR(__stack_chk_guard)
#endif
#ifdef CONFIG_RETPOLINE
movl PT_EIP(%esp), %edx /* pt_regs->ip */
movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */
1: mov PT_FS(%esp), %fs
- PTGS_TO_GS
popl %ebx /* pt_regs->bx */
addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */
jmp 1b
.popsection
_ASM_EXTABLE(1b, 2b)
- PTGS_TO_GS_EX
.Lsysenter_fix_flags:
pushl $X86_EFLAGS_FIXED
* when returning from IPI handler and when returning from
* scheduler to user-space.
*/
- INTERRUPT_RETURN
+ iret
.section .fixup, "ax"
SYM_CODE_START(asm_iret_error)
SAVE_ALL switch_stacks=1 skip_gs=1 unwind_espfix=1
ENCODE_FRAME_POINTER
- /* fixup %gs */
- GS_TO_REG %ecx
movl PT_GS(%esp), %edi # get the function address
- REG_TO_PTGS %ecx
- SET_KERNEL_GS %ecx
/* fixup orig %eax */
movl PT_ORIG_EAX(%esp), %edx # get the error code
.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
#ifdef CONFIG_DEBUG_ENTRY
pushq %rax
- SAVE_FLAGS(CLBR_RAX)
+ SAVE_FLAGS
testl $X86_EFLAGS_IF, %eax
jz .Lokay_\@
ud2
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
.text
.globl __kernel_vsyscall
is_64bit = kernel_ip(to) || any_64bit_mode(regs);
#endif
insn_init(&insn, kaddr, size, is_64bit);
- insn_get_length(&insn);
+
/*
- * Make sure there was not a problem decoding the
- * instruction and getting the length. This is
- * doubly important because we have an infinite
- * loop if insn.length=0.
+ * Make sure there was not a problem decoding the instruction.
+ * This is doubly important because we have an infinite loop if
+ * insn.length=0.
*/
- if (!insn.length)
+ if (insn_get_length(&insn))
break;
to += insn.length;
is64 = kernel_ip((unsigned long)addr) || any_64bit_mode(current_pt_regs());
#endif
insn_init(&insn, addr, bytes_read, is64);
- insn_get_opcode(&insn);
- if (!insn.opcode.got)
+ if (insn_get_opcode(&insn))
return X86_BR_ABORT;
switch (insn.opcode.bytes[0]) {
ret = X86_BR_INT;
break;
case 0xe8: /* call near rel */
- insn_get_immediate(&insn);
- if (insn.immediate1.value == 0) {
+ if (insn_get_immediate(&insn) || insn.immediate1.value == 0) {
/* zero length call */
ret = X86_BR_ZERO_CALL;
break;
ret = X86_BR_JMP;
break;
case 0xff: /* call near absolute, call far absolute ind */
- insn_get_modrm(&insn);
+ if (insn_get_modrm(&insn))
+ return X86_BR_ABORT;
+
ext = (insn.modrm.bytes[0] >> 3) & 0x7;
switch (ext) {
case 2: /* near ind call */
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ALTERNATIVE_ASM_H
-#define _ASM_X86_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-#include <asm/asm.h>
-
-#ifdef CONFIG_SMP
- .macro LOCK_PREFIX
-672: lock
- .pushsection .smp_locks,"a"
- .balign 4
- .long 672b - .
- .popsection
- .endm
-#else
- .macro LOCK_PREFIX
- .endm
-#endif
-
-/*
- * objtool annotation to ignore the alternatives and only consider the original
- * instruction(s).
- */
-.macro ANNOTATE_IGNORE_ALTERNATIVE
- .Lannotate_\@:
- .pushsection .discard.ignore_alts
- .long .Lannotate_\@ - .
- .popsection
-.endm
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
- .long \orig - .
- .long \alt - .
- .word \feature
- .byte \orig_len
- .byte \alt_len
- .byte \pad_len
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr. ".skip" directive takes care of proper instruction padding
- * in case @newinstr is longer than @oldinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-140:
- \oldinstr
-141:
- .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr
-144:
- .popsection
-.endm
-
-#define old_len 141b-140b
-#define new_len1 144f-143f
-#define new_len2 145f-144f
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-
-
-/*
- * Same as ALTERNATIVE macro above but for two alternatives. If CPU
- * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
- * @feature2, it replaces @oldinstr with @feature2.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-140:
- \oldinstr
-141:
- .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
- (alt_max_short(new_len1, new_len2) - (old_len)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
- altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr1
-144:
- \newinstr2
-145:
- .popsection
-.endm
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
#ifndef _ASM_X86_ALTERNATIVE_H
#define _ASM_X86_ALTERNATIVE_H
-#ifndef __ASSEMBLY__
-
#include <linux/types.h>
-#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
+#define ALTINSTR_FLAG_INV (1 << 15)
+#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stddef.h>
+
/*
* Alternative inline assembly for SMP.
*
" .byte " alt_rlen(num) "\n" /* replacement len */ \
" .byte " alt_pad_len "\n" /* pad len */
-#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \
+#define ALTINSTR_REPLACEMENT(newinstr, num) /* replacement */ \
"# ALT: replacement " #num "\n" \
b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
ALTINSTR_ENTRY(feature, 1) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
+ ALTINSTR_REPLACEMENT(newinstr, 1) \
".popsection\n"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
ALTINSTR_ENTRY(feature2, 2) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
- ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
+ ALTINSTR_REPLACEMENT(newinstr1, 1) \
+ ALTINSTR_REPLACEMENT(newinstr2, 2) \
".popsection\n"
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+ ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \
+ newinstr_yes, feature)
+
#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
OLDINSTR_3(oldinsn, 1, 2, 3) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feat3, 3) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinsn1, feat1, 1) \
- ALTINSTR_REPLACEMENT(newinsn2, feat2, 2) \
- ALTINSTR_REPLACEMENT(newinsn3, feat3, 3) \
+ ALTINSTR_REPLACEMENT(newinsn1, 1) \
+ ALTINSTR_REPLACEMENT(newinsn2, 2) \
+ ALTINSTR_REPLACEMENT(newinsn3, 3) \
".popsection\n"
/*
#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \
+ asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory")
+
/*
* Alternative inline assembly with input.
*
*/
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SMP
+ .macro LOCK_PREFIX
+672: lock
+ .pushsection .smp_locks,"a"
+ .balign 4
+ .long 672b - .
+ .popsection
+ .endm
+#else
+ .macro LOCK_PREFIX
+ .endm
+#endif
+
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+ .Lannotate_\@:
+ .pushsection .discard.ignore_alts
+ .long .Lannotate_\@ - .
+ .popsection
+.endm
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+ .long \orig - .
+ .long \alt - .
+ .word \feature
+ .byte \orig_len
+ .byte \alt_len
+ .byte \pad_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+ \oldinstr
+141:
+ .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+ .pushsection .altinstructions,"a"
+ altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+ .popsection
+
+ .pushsection .altinstr_replacement,"ax"
+143:
+ \newinstr
+144:
+ .popsection
+.endm
+
+#define old_len 141b-140b
+#define new_len1 144f-143f
+#define new_len2 145f-144f
+
+/*
+ * gas compatible max based on the idea from:
+ * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
+ */
+#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+ \oldinstr
+141:
+ .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+ (alt_max_short(new_len1, new_len2) - (old_len)),0x90
+142:
+
+ .pushsection .altinstructions,"a"
+ altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+ altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+ .popsection
+
+ .pushsection .altinstr_replacement,"ax"
+143:
+ \newinstr1
+144:
+ \newinstr2
+145:
+ .popsection
+.endm
+
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+ ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \
+ newinstr_yes, feature
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_ALTERNATIVE_H */
#include <asm/asm.h>
#include <linux/bitops.h>
+#include <asm/alternative.h>
enum cpuid_leafs
{
*/
static __always_inline 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(
+ ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+ ".section .altinstr_aux,\"ax\"\n"
+ "6:\n"
+ " testb %[bitnum],%[cap_byte]\n"
+ " jnz %l[t_yes]\n"
+ " jmp %l[t_no]\n"
+ ".previous\n"
: : [feature] "i" (bit),
- [always] "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
[cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
: : t_yes, t_no);
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
-#include <asm/inat_types.h>
+#include <asm/inat_types.h> /* __ignore_sync_check__ */
/*
* Internal bits. Don't use bitmasks directly, because these bits are
unsigned char buf[MAX_INSN_SIZE]);
int insn_fetch_from_user_inatomic(struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE]);
-bool insn_decode(struct insn *insn, struct pt_regs *regs,
- unsigned char buf[MAX_INSN_SIZE], int buf_size);
+bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
+ unsigned char buf[MAX_INSN_SIZE], int buf_size);
#endif /* _ASM_X86_INSN_EVAL_H */
#include <asm/byteorder.h>
/* insn_attr_t is defined in inat.h */
-#include <asm/inat.h>
+#include <asm/inat.h> /* __ignore_sync_check__ */
#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
+extern int insn_get_prefixes(struct insn *insn);
+extern int insn_get_opcode(struct insn *insn);
+extern int insn_get_modrm(struct insn *insn);
+extern int insn_get_sib(struct insn *insn);
+extern int insn_get_displacement(struct insn *insn);
+extern int insn_get_immediate(struct insn *insn);
+extern int insn_get_length(struct insn *insn);
+
+enum insn_mode {
+ INSN_MODE_32,
+ INSN_MODE_64,
+ /* Mode is determined by the current kernel build. */
+ INSN_MODE_KERN,
+ INSN_NUM_MODES,
+};
+
+extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);
+
+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN)
/* Attribute will be determined after getting ModRM (for opcode groups) */
static inline void insn_get_attribute(struct insn *insn)
/* Instruction uses RIP-relative addressing */
extern int insn_rip_relative(struct insn *insn);
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
- const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
- insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
- insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
static inline int insn_is_avx(struct insn *insn)
{
if (!insn->prefixes.got)
return !!insn->emulate_prefix_size;
}
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
- return insn->opcode.got && insn->modrm.got && insn->sib.got &&
- insn->displacement.got && insn->immediate.got;
-}
-
static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
{
if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */
}
#else
-#define ENABLE_INTERRUPTS(x) sti
-#define DISABLE_INTERRUPTS(x) cli
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x) pushfq; popq %rax
+#define SAVE_FLAGS pushfq; popq %rax
#endif
#define INTERRUPT_RETURN jmp native_iret
-#else
-#define INTERRUPT_RETURN iret
#endif
#endif /* __ASSEMBLY__ */
* a post_handler).
*/
unsigned boostable:1;
- unsigned if_modifier:1;
- unsigned is_call:1;
- unsigned is_pushf:1;
- unsigned is_abs_ip:1;
+ unsigned char size; /* The size of insn */
+ union {
+ unsigned char opcode;
+ struct {
+ unsigned char type;
+ } jcc;
+ struct {
+ unsigned char type;
+ unsigned char asize;
+ } loop;
+ struct {
+ unsigned char reg;
+ } indirect;
+ };
+ s32 rel32; /* relative offset must be s32, s16, or s8 */
+ void (*emulate_op)(struct kprobe *p, struct pt_regs *regs);
/* Number of bytes of text poked */
int tp_len;
};
extern int kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data);
extern int kprobe_int3_handler(struct pt_regs *regs);
-extern int kprobe_debug_handler(struct pt_regs *regs);
#else
static __always_inline void hv_setup_sched_clock(void *sched_clock)
{
#ifdef CONFIG_PARAVIRT
- pv_ops.time.sched_clock = sched_clock;
+ paravirt_set_sched_clock(sched_clock);
#endif
}
#include <linux/objtool.h>
#include <asm/alternative.h>
-#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
#include <asm/unwind_hints.h>
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/cpumask.h>
+#include <linux/static_call_types.h>
#include <asm/frame.h>
-static inline unsigned long long paravirt_sched_clock(void)
+u64 dummy_steal_clock(int cpu);
+u64 dummy_sched_clock(void);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void));
+
+static inline u64 paravirt_sched_clock(void)
{
- return PVOP_CALL0(unsigned long long, time.sched_clock);
+ return static_call(pv_sched_clock)();
}
struct static_key;
static inline u64 paravirt_steal_clock(int cpu)
{
- return PVOP_CALL1(u64, time.steal_clock, cpu);
+ return static_call(pv_steal_clock)(cpu);
}
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+#endif
+
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
static inline unsigned long read_cr2(void)
{
- return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
+ return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
+ "mov %%cr2, %%rax;",
+ ALT_NOT(X86_FEATURE_XENPV));
}
static inline void write_cr2(unsigned long x)
static inline unsigned long __read_cr3(void)
{
- return PVOP_CALL0(unsigned long, mmu.read_cr3);
+ return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
+ "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void write_cr3(unsigned long x)
{
- PVOP_VCALL1(mmu.write_cr3, x);
+ PVOP_ALT_VCALL1(mmu.write_cr3, x,
+ "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void __write_cr4(unsigned long x)
static inline void wbinvd(void)
{
- PVOP_VCALL0(cpu.wbinvd);
+ PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
}
static inline u64 paravirt_read_msr(unsigned msr)
static inline pte_t __pte(pteval_t val)
{
- return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
+ return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pteval_t pte_val(pte_t pte)
{
- return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+ return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline pgd_t __pgd(pgdval_t val)
{
- return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
+ return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pgdval_t pgd_val(pgd_t pgd)
{
- return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+ return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
static inline pmd_t __pmd(pmdval_t val)
{
- return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
+ return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pmdval_t pmd_val(pmd_t pmd)
{
- return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+ return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void set_pud(pud_t *pudp, pud_t pud)
{
pudval_t ret;
- ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+ ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
return (pud_t) { ret };
}
static inline pudval_t pud_val(pud_t pud)
{
- return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
+ return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void pud_clear(pud_t *pudp)
static inline p4d_t __p4d(p4dval_t val)
{
- p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
+ p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV));
return (p4d_t) { ret };
}
static inline p4dval_t p4d_val(p4d_t p4d)
{
- return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
+ return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
{
- PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
+ PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock,
+ "movb $0, (%%" _ASM_ARG1 ");",
+ ALT_NOT(X86_FEATURE_PVUNLOCK));
}
static __always_inline void pv_wait(u8 *ptr, u8 val)
static __always_inline bool pv_vcpu_is_preempted(long cpu)
{
- return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
+ return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu,
+ "xor %%" _ASM_AX ", %%" _ASM_AX ";",
+ ALT_NOT(X86_FEATURE_VCPUPREEMPT));
}
void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
#ifdef CONFIG_PARAVIRT_XXL
static inline notrace unsigned long arch_local_save_flags(void)
{
- return PVOP_CALLEE0(unsigned long, irq.save_fl);
+ return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
+ ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace void arch_local_irq_disable(void)
{
- PVOP_VCALLEE0(irq.irq_disable);
+ PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace void arch_local_irq_enable(void)
{
- PVOP_VCALLEE0(irq.irq_enable);
+ PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace unsigned long arch_local_irq_save(void)
.popsection
-#define COND_PUSH(set, mask, reg) \
- .if ((~(set)) & mask); push %reg; .endif
-#define COND_POP(set, mask, reg) \
- .if ((~(set)) & mask); pop %reg; .endif
-
#ifdef CONFIG_X86_64
-
-#define PV_SAVE_REGS(set) \
- COND_PUSH(set, CLBR_RAX, rax); \
- COND_PUSH(set, CLBR_RCX, rcx); \
- COND_PUSH(set, CLBR_RDX, rdx); \
- COND_PUSH(set, CLBR_RSI, rsi); \
- COND_PUSH(set, CLBR_RDI, rdi); \
- COND_PUSH(set, CLBR_R8, r8); \
- COND_PUSH(set, CLBR_R9, r9); \
- COND_PUSH(set, CLBR_R10, r10); \
- COND_PUSH(set, CLBR_R11, r11)
-#define PV_RESTORE_REGS(set) \
- COND_POP(set, CLBR_R11, r11); \
- COND_POP(set, CLBR_R10, r10); \
- COND_POP(set, CLBR_R9, r9); \
- COND_POP(set, CLBR_R8, r8); \
- COND_POP(set, CLBR_RDI, rdi); \
- COND_POP(set, CLBR_RSI, rsi); \
- COND_POP(set, CLBR_RDX, rdx); \
- COND_POP(set, CLBR_RCX, rcx); \
- COND_POP(set, CLBR_RAX, rax)
+#ifdef CONFIG_PARAVIRT_XXL
#define PARA_PATCH(off) ((off) / 8)
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
-#else
-#define PV_SAVE_REGS(set) \
- COND_PUSH(set, CLBR_EAX, eax); \
- COND_PUSH(set, CLBR_EDI, edi); \
- COND_PUSH(set, CLBR_ECX, ecx); \
- COND_PUSH(set, CLBR_EDX, edx)
-#define PV_RESTORE_REGS(set) \
- COND_POP(set, CLBR_EDX, edx); \
- COND_POP(set, CLBR_ECX, ecx); \
- COND_POP(set, CLBR_EDI, edi); \
- COND_POP(set, CLBR_EAX, eax)
-
-#define PARA_PATCH(off) ((off) / 4)
-#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
-#define PARA_INDIRECT(addr) *%cs:addr
-#endif
-#ifdef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN \
- PARA_SITE(PARA_PATCH(PV_CPU_iret), \
- ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
-
-#define DISABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-
-#define ENABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#endif
+ ANNOTATE_RETPOLINE_SAFE; \
+ ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \
+ X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+.macro PARA_IRQ_save_fl
+ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
+ ANNOTATE_RETPOLINE_SAFE;
+ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+.endm
+
+#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
+ ALT_NOT(X86_FEATURE_XENPV)
#endif
#endif /* CONFIG_PARAVIRT_XXL */
#endif /* CONFIG_X86_64 */
{
}
#endif
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void)
+{
+}
+#endif
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PARAVIRT_H */
#define _ASM_X86_PARAVIRT_TYPES_H
/* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
#define CLBR_EAX (1 << 0)
#define CLBR_ECX (1 << 1)
#define CLBR_EDX (1 << 2)
#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX)
#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH (0)
#else
#define CLBR_RAX CLBR_EAX
#define CLBR_RCX CLBR_ECX
#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
CLBR_RCX | CLBR_R8 | CLBR_R9)
#define CLBR_RET_REG (CLBR_RAX)
-#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11)
#endif /* X86_64 */
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
-
#ifndef __ASSEMBLY__
#include <asm/desc_defs.h>
const char *name;
};
-struct pv_init_ops {
- /*
- * Patch may replace one of the defined code sequences with
- * arbitrary code, subject to the same register constraints.
- * This generally means the code is not free to clobber any
- * registers other than EAX. The patch function should return
- * the number of bytes of code generated, as we nop pad the
- * rest in generic code.
- */
- unsigned (*patch)(u8 type, void *insn_buff,
- unsigned long addr, unsigned len);
-} __no_randomize_layout;
-
#ifdef CONFIG_PARAVIRT_XXL
struct pv_lazy_ops {
/* Set deferred update mode, used for batching operations. */
} __no_randomize_layout;
#endif
-struct pv_time_ops {
- unsigned long long (*sched_clock)(void);
- unsigned long long (*steal_clock)(int cpu);
-} __no_randomize_layout;
-
struct pv_cpu_ops {
/* hooks for various privileged instructions */
void (*io_delay)(void);
u64 (*read_pmc)(int counter);
- /* Normal iret. Jump to this with the standard iret stack
- frame set up. */
- void (*iret)(void);
-
void (*start_context_switch)(struct task_struct *prev);
void (*end_context_switch)(struct task_struct *next);
#endif
* number for each function using the offset which we use to indicate
* what to patch. */
struct paravirt_patch_template {
- struct pv_init_ops init;
- struct pv_time_ops time;
struct pv_cpu_ops cpu;
struct pv_irq_ops irq;
struct pv_mmu_ops mmu;
extern struct pv_info pv_info;
extern struct paravirt_patch_template pv_ops;
+extern void (*paravirt_iret)(void);
#define PARAVIRT_PATCH(x) \
(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
/* Simple instruction patching code. */
#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
-unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len);
-unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
-
-unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
int paravirt_disable_iospace(void);
* makes sure the incoming and outgoing types are always correct.
*/
#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS \
+#define PVOP_CALL_ARGS \
unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
-
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x))
#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x))
#define VEXTRA_CLOBBERS
#else /* CONFIG_X86_64 */
/* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS \
+#define PVOP_CALL_ARGS \
unsigned long __edi = __edi, __esi = __esi, \
__edx = __edx, __ecx = __ecx, __eax = __eax;
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
-
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x))
#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x))
#define PVOP_TEST_NULL(op) ((void)pv_ops.op)
#endif
-#define PVOP_RETMASK(rettype) \
+#define PVOP_RETVAL(rettype) \
({ unsigned long __mask = ~0UL; \
+ BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long)); \
switch (sizeof(rettype)) { \
case 1: __mask = 0xffUL; break; \
case 2: __mask = 0xffffUL; break; \
case 4: __mask = 0xffffffffUL; break; \
default: break; \
} \
- __mask; \
+ __mask & __eax; \
})
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
- pre, post, ...) \
+#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...) \
({ \
- rettype __ret; \
PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- /* This is 32-bit specific, but is okay in 64-bit */ \
- /* since this condition will never hold */ \
- if (sizeof(rettype) > sizeof(unsigned long)) { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)((((u64)__edx) << 32) | __eax); \
- } else { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)(__eax & PVOP_RETMASK(rettype)); \
- } \
- __ret; \
+ asm volatile(paravirt_alt(PARAVIRT_CALL) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
+ : paravirt_type(op), \
+ paravirt_clobber(clbr), \
+ ##__VA_ARGS__ \
+ : "memory", "cc" extra_clbr); \
+ ret; \
})
-#define __PVOP_CALL(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \
- EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
-
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
- PVOP_CALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
-
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
+#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr, \
+ extra_clbr, ...) \
({ \
- PVOP_VCALL_ARGS; \
+ PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
+ asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \
+ alt, cond) \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
: "memory", "cc" extra_clbr); \
+ ret; \
})
-#define __PVOP_VCALL(op, pre, post, ...) \
- ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
- VEXTRA_CLOBBERS, \
- pre, post, ##__VA_ARGS__)
+#define __PVOP_CALL(rettype, op, ...) \
+ ____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY, \
+ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...) \
+ ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\
+ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, \
+ ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, ...) \
+ ____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG, \
+ PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...) \
+ ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond, \
+ CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+
+#define __PVOP_VCALL(op, ...) \
+ (void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
+ VEXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_VCALL(op, alt, cond, ...) \
+ (void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY, \
+ PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS, \
+ ##__VA_ARGS__)
-#define __PVOP_VCALLEESAVE(op, pre, post, ...) \
- ____PVOP_VCALL(op.func, CLBR_RET_REG, \
- PVOP_VCALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
+#define __PVOP_VCALLEESAVE(op, ...) \
+ (void)____PVOP_CALL(, op.func, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
+#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...) \
+ (void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
#define PVOP_CALL0(rettype, op) \
- __PVOP_CALL(rettype, op, "", "")
+ __PVOP_CALL(rettype, op)
#define PVOP_VCALL0(op) \
- __PVOP_VCALL(op, "", "")
+ __PVOP_VCALL(op)
+#define PVOP_ALT_CALL0(rettype, op, alt, cond) \
+ __PVOP_ALT_CALL(rettype, op, alt, cond)
+#define PVOP_ALT_VCALL0(op, alt, cond) \
+ __PVOP_ALT_VCALL(op, alt, cond)
#define PVOP_CALLEE0(rettype, op) \
- __PVOP_CALLEESAVE(rettype, op, "", "")
+ __PVOP_CALLEESAVE(rettype, op)
#define PVOP_VCALLEE0(op) \
- __PVOP_VCALLEESAVE(op, "", "")
+ __PVOP_VCALLEESAVE(op)
+#define PVOP_ALT_CALLEE0(rettype, op, alt, cond) \
+ __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond)
+#define PVOP_ALT_VCALLEE0(op, alt, cond) \
+ __PVOP_ALT_VCALLEESAVE(op, alt, cond)
#define PVOP_CALL1(rettype, op, arg1) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
#define PVOP_VCALL1(op, arg1) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALL1(op, arg1, alt, cond) \
+ __PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1))
#define PVOP_CALLEE1(rettype, op, arg1) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
#define PVOP_VCALLEE1(op, arg1) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond) \
+ __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond) \
+ __PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1))
#define PVOP_CALL2(rettype, op, arg1, arg2) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
#define PVOP_VCALL2(op, arg1, arg2) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), \
PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
#define PVOP_VCALL3(op, arg1, arg2, arg3) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), \
PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
__PVOP_CALL(rettype, op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
- PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
- __PVOP_CALL(rettype, op, "", "", \
PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, "", "", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
/* Lazy mode for batching updates / context switch */
enum paravirt_lazy_mode {
* GCC hardcodes the stack canary as %gs:40. Since the
* irq_stack is the object at %gs:0, we reserve the bottom
* 48 bytes of the irq stack for the canary.
+ *
+ * Once we are willing to require -mstack-protector-guard-symbol=
+ * support for x86_64 stackprotector, we can get rid of this.
*/
char gs_base[40];
unsigned long stack_canary;
void current_save_fsgs(void);
#else /* X86_64 */
#ifdef CONFIG_STACKPROTECTOR
-/*
- * Make sure stack canary segment base is cached-aligned:
- * "For Intel Atom processors, avoid non zero segment base address
- * that is not aligned to cache line boundary at all cost."
- * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
- */
-struct stack_canary {
- char __pad[20]; /* canary at %gs:20 */
- unsigned long canary;
-};
-DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
#endif
DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
unsigned short __esh;
unsigned short fs;
unsigned short __fsh;
- /* On interrupt, gs and __gsh store the vector number. */
+ /*
+ * On interrupt, gs and __gsh store the vector number. They never
+ * store gs any more.
+ */
unsigned short gs;
unsigned short __gsh;
/* On interrupt, this is the error code. */
*
* 26 - ESPFIX small SS
* 27 - per-cpu [ offset to per-cpu data area ]
- * 28 - stack_canary-20 [ for stack protector ] <=== cacheline #8
+ * 28 - unused
* 29 - unused
* 30 - unused
* 31 - TSS for double fault handler
#define GDT_ENTRY_ESPFIX_SS 26
#define GDT_ENTRY_PERCPU 27
-#define GDT_ENTRY_STACK_CANARY 28
#define GDT_ENTRY_DOUBLEFAULT_TSS 31
# define __KERNEL_PERCPU 0
#endif
-#ifdef CONFIG_STACKPROTECTOR
-# define __KERNEL_STACK_CANARY (GDT_ENTRY_STACK_CANARY*8)
-#else
-# define __KERNEL_STACK_CANARY 0
-#endif
-
#else /* 64-bit: */
#include <asm/cache.h>
asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
/*
- * x86-32 user GS accessors:
+ * x86-32 user GS accessors. This is ugly and could do with some cleaning up.
*/
#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_32_LAZY_GS
-# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; })
-# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v))
-# define task_user_gs(tsk) ((tsk)->thread.gs)
-# define lazy_save_gs(v) savesegment(gs, (v))
-# define lazy_load_gs(v) loadsegment(gs, (v))
-# else /* X86_32_LAZY_GS */
-# define get_user_gs(regs) (u16)((regs)->gs)
-# define set_user_gs(regs, v) do { (regs)->gs = (v); } while (0)
-# define task_user_gs(tsk) (task_pt_regs(tsk)->gs)
-# define lazy_save_gs(v) do { } while (0)
-# define lazy_load_gs(v) do { } while (0)
-# endif /* X86_32_LAZY_GS */
+# define get_user_gs(regs) (u16)({ unsigned long v; savesegment(gs, v); v; })
+# define set_user_gs(regs, v) loadsegment(gs, (unsigned long)(v))
+# define task_user_gs(tsk) ((tsk)->thread.gs)
+# define lazy_save_gs(v) savesegment(gs, (v))
+# define lazy_load_gs(v) loadsegment(gs, (v))
+# define load_gs_index(v) loadsegment(gs, (v))
#endif /* X86_32 */
#endif /* !__ASSEMBLY__ */
#include <asm/nops.h>
#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
/* "Raw" instruction opcodes */
#define __ASM_CLAC ".byte 0x0f,0x01,0xca"
#ifdef __ASSEMBLY__
-#include <asm/alternative-asm.h>
-
#ifdef CONFIG_X86_SMAP
#define ASM_CLAC \
#else /* __ASSEMBLY__ */
-#include <asm/alternative.h>
-
#ifdef CONFIG_X86_SMAP
static __always_inline void clac(void)
* Stack protector works by putting predefined pattern at the start of
* the stack frame and verifying that it hasn't been overwritten when
* returning from the function. The pattern is called stack canary
- * and unfortunately gcc requires it to be at a fixed offset from %gs.
- * On x86_64, the offset is 40 bytes and on x86_32 20 bytes. x86_64
- * and x86_32 use segment registers differently and thus handles this
- * requirement differently.
+ * and unfortunately gcc historically required it to be at a fixed offset
+ * from the percpu segment base. On x86_64, the offset is 40 bytes.
*
- * On x86_64, %gs is shared by percpu area and stack canary. All
- * percpu symbols are zero based and %gs points to the base of percpu
- * area. The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at offset 40. Userland
- * %gs is always saved and restored on kernel entry and exit using
- * swapgs, so stack protector doesn't add any complexity there.
+ * The same segment is shared by percpu area and stack canary. On
+ * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
+ * base of percpu area. The first occupant of the percpu area is always
+ * fixed_percpu_data which contains stack_canary at the approproate
+ * offset. On x86_32, the stack canary is just a regular percpu
+ * variable.
*
- * On x86_32, it's slightly more complicated. As in x86_64, %gs is
- * used for userland TLS. Unfortunately, some processors are much
- * slower at loading segment registers with different value when
- * entering and leaving the kernel, so the kernel uses %fs for percpu
- * area and manages %gs lazily so that %gs is switched only when
- * necessary, usually during task switch.
+ * Putting percpu data in %fs on 32-bit is a minor optimization compared to
+ * using %gs. Since 32-bit userspace normally has %fs == 0, we are likely
+ * to load 0 into %fs on exit to usermode, whereas with percpu data in
+ * %gs, we are likely to load a non-null %gs on return to user mode.
*
- * As gcc requires the stack canary at %gs:20, %gs can't be managed
- * lazily if stack protector is enabled, so the kernel saves and
- * restores userland %gs on kernel entry and exit. This behavior is
- * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
- * system.h to hide the details.
+ * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
+ * support, we can remove some of this complexity.
*/
#ifndef _ASM_STACKPROTECTOR_H
#include <linux/random.h>
#include <linux/sched.h>
-/*
- * 24 byte read-only segment initializer for stack canary. Linker
- * can't handle the address bit shifting. Address will be set in
- * head_32 for boot CPU and setup_per_cpu_areas() for others.
- */
-#define GDT_STACK_CANARY_INIT \
- [GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
-
/*
* Initialize the stackprotector canary value.
*
#ifdef CONFIG_X86_64
this_cpu_write(fixed_percpu_data.stack_canary, canary);
#else
- this_cpu_write(stack_canary.canary, canary);
+ this_cpu_write(__stack_chk_guard, canary);
#endif
}
#ifdef CONFIG_X86_64
per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
#else
- per_cpu(stack_canary.canary, cpu) = idle->stack_canary;
-#endif
-}
-
-static inline void setup_stack_canary_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
- unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
- struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
- struct desc_struct desc;
-
- desc = gdt_table[GDT_ENTRY_STACK_CANARY];
- set_desc_base(&desc, canary);
- write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
-#endif
-}
-
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
- asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+ per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
#endif
}
#else /* STACKPROTECTOR */
-#define GDT_STACK_CANARY_INIT
-
/* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
-static inline void setup_stack_canary_segment(int cpu)
-{ }
-
static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
{ }
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
- asm volatile ("mov %0, %%gs" : : "r" (0));
-#endif
-}
-
#endif /* STACKPROTECTOR */
#endif /* _ASM_STACKPROTECTOR_H */
/* image of the saved processor state */
struct saved_context {
/*
- * On x86_32, all segment registers, with the possible exception of
- * gs, are saved at kernel entry in pt_regs.
+ * On x86_32, all segment registers except gs are saved at kernel
+ * entry in pt_regs.
*/
-#ifdef CONFIG_X86_32_LAZY_GS
u16 gs;
-#endif
unsigned long cr0, cr2, cr3, cr4;
u64 misc_enable;
bool misc_enable_saved;
KCSAN_SANITIZE := n
OBJECT_FILES_NON_STANDARD_test_nx.o := y
-OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y
ifdef CONFIG_FRAME_POINTER
OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y
obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o
-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch.o
+obj-$(CONFIG_PARAVIRT) += paravirt.o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/fixmap.h>
+#include <asm/paravirt.h>
int __read_mostly alternatives_patched;
*/
for (a = start; a < end; a++) {
int insn_buff_sz = 0;
+ /* Mask away "NOT" flag bit for feature to test. */
+ u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
BUG_ON(a->instrlen > sizeof(insn_buff));
- BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
- if (!boot_cpu_has(a->cpuid)) {
+ BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
+
+ /*
+ * Patch if either:
+ * - feature is present
+ * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+ * patch if feature is *NOT* present.
+ */
+ if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
if (a->padlen > 1)
optimize_nops(a, instr);
continue;
}
- DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
- a->cpuid >> 5,
- a->cpuid & 0x1f,
+ DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+ (a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+ feature >> 5,
+ feature & 0x1f,
instr, instr, a->instrlen,
replacement, a->replacementlen, a->padlen);
BUG_ON(p->len > MAX_PATCH_LEN);
/* prep the buffer with the original instructions */
memcpy(insn_buff, p->instr, p->len);
- used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+ used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
BUG_ON(used > p->len);
* patching.
*/
+ /*
+ * Paravirt patching and alternative patching can be combined to
+ * replace a function call with a short direct code sequence (e.g.
+ * by setting a constant return value instead of doing that in an
+ * external function).
+ * In order to make this work the following sequence is required:
+ * 1. set (artificial) features depending on used paravirt
+ * functions which can later influence alternative patching
+ * 2. apply paravirt patching (generally replacing an indirect
+ * function call with a direct one)
+ * 3. apply alternative patching (e.g. replacing a direct function
+ * call with a custom code sequence)
+ * Doing paravirt patching after alternative patching would clobber
+ * the optimization of the custom code with a function call again.
+ */
+ paravirt_set_cap();
+
+ /*
+ * First patch paravirt functions, such that we overwrite the indirect
+ * call with the direct call.
+ */
+ apply_paravirt(__parainstructions, __parainstructions_end);
+
+ /*
+ * Then patch alternatives, such that those paravirt calls that are in
+ * alternatives can be overwritten by their immediate fragments.
+ */
apply_alternatives(__alt_instructions, __alt_instructions_end);
#ifdef CONFIG_SMP
}
#endif
- apply_paravirt(__parainstructions, __parainstructions_end);
-
restart_nmi();
alternatives_patched = 1;
}
const void *opcode, size_t len, const void *emulate)
{
struct insn insn;
+ int ret;
memcpy((void *)tp->text, opcode, len);
if (!emulate)
emulate = opcode;
- kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
- insn_get_length(&insn);
+ ret = insn_decode_kernel(&insn, emulate);
- BUG_ON(!insn_complete(&insn));
+ BUG_ON(ret < 0);
BUG_ON(len != insn.length);
tp->rel_addr = addr - (void *)_stext;
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
#endif
-#ifdef CONFIG_PARAVIRT_XXL
- BLANK();
- OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
- OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
- OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
-
#ifdef CONFIG_XEN
BLANK();
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
offsetofend(struct cpu_entry_area, entry_stack_page.stack));
-#ifdef CONFIG_STACKPROTECTOR
- BLANK();
- OFFSET(stack_canary_offset, stack_canary, canary);
-#endif
-
BLANK();
DEFINE(EFI_svam, offsetof(efi_runtime_services_t, set_virtual_address_map));
}
[GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
[GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff),
- GDT_STACK_CANARY_INIT
#endif
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
__loadsegment_simple(gs, 0);
wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
#endif
- load_stack_canary_segment();
}
#ifdef CONFIG_X86_32
EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
#ifdef CONFIG_STACKPROTECTOR
-DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
+EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
#endif
#endif /* CONFIG_X86_64 */
static bool is_copy_from_user(struct pt_regs *regs)
{
u8 insn_buf[MAX_INSN_SIZE];
- struct insn insn;
unsigned long addr;
+ struct insn insn;
+ int ret;
if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
return false;
- kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
- insn_get_opcode(&insn);
- if (!insn.opcode.got)
+ ret = insn_decode_kernel(&insn, insn_buf);
+ if (ret < 0)
return false;
switch (insn.opcode.value) {
case 0x8A: case 0x8B:
/* MOVZ mem,reg */
case 0xB60F: case 0xB70F:
- insn_get_modrm(&insn);
- insn_get_sib(&insn);
- if (!insn.modrm.got || !insn.sib.got)
- return false;
addr = (unsigned long)insn_get_addr_ref(&insn, regs);
break;
/* REP MOVS */
#include <linux/clocksource.h>
#include <linux/cpu.h>
#include <linux/reboot.h>
+#include <linux/static_call.h>
#include <asm/div64.h>
#include <asm/x86_init.h>
#include <asm/hypervisor.h>
vmware_cyc2ns_setup();
if (vmw_sched_clock)
- pv_ops.time.sched_clock = vmware_sched_clock;
+ paravirt_set_sched_clock(vmware_sched_clock);
if (vmware_is_stealclock_available()) {
has_steal_clock = true;
- pv_ops.time.steal_clock = vmware_steal_clock;
+ static_call_update(pv_steal_clock, vmware_steal_clock);
/* We use reboot notifier only to disable steal clock */
register_reboot_notifier(&vmware_pv_reboot_nb);
.ss = __KERNEL_DS,
.ds = __USER_DS,
.fs = __KERNEL_PERCPU,
-#ifndef CONFIG_X86_32_LAZY_GS
- .gs = __KERNEL_STACK_CANARY,
-#endif
+ .gs = 0,
.__cr3 = __pa_nodebug(swapper_pg_dir),
},
movl $(__KERNEL_PERCPU), %eax
movl %eax,%fs # set this cpu's percpu
- movl $(__KERNEL_STACK_CANARY),%eax
- movl %eax,%gs
+ xorl %eax,%eax
+ movl %eax,%gs # clear possible garbage in %gs
xorl %eax,%eax # Clear LDT
lldt %ax
*/
__INIT
setup_once:
-#ifdef CONFIG_STACKPROTECTOR
- /*
- * Configure the stack canary. The linker can't handle this by
- * relocation. Manually set base address in stack canary
- * segment descriptor.
- */
- movl $gdt_page,%eax
- movl $stack_canary,%ecx
- movw %cx, 8 * GDT_ENTRY_STACK_CANARY + 2(%eax)
- shrl $16, %ecx
- movb %cl, 8 * GDT_ENTRY_STACK_CANARY + 4(%eax)
- movb %ch, 8 * GDT_ENTRY_STACK_CANARY + 7(%eax)
-#endif
-
andl $0,setup_once_ref /* Once is enough, thanks */
ret
int can_boost(struct insn *insn, void *addr)
{
kprobe_opcode_t opcode;
+ insn_byte_t prefix;
+ int i;
if (search_exception_tables((unsigned long)addr))
return 0; /* Page fault may occur on this address. */
if (insn->opcode.nbytes != 1)
return 0;
- /* Can't boost Address-size override prefix */
- if (unlikely(inat_is_address_size_prefix(insn->attr)))
- return 0;
+ for_each_insn_prefix(insn, i, prefix) {
+ insn_attr_t attr;
+
+ attr = inat_get_opcode_attribute(prefix);
+ /* Can't boost Address-size override prefix and CS override prefix */
+ if (prefix == 0x2e || inat_is_address_size_prefix(attr))
+ return 0;
+ }
opcode = insn->opcode.bytes[0];
- switch (opcode & 0xf0) {
- case 0x60:
- /* can't boost "bound" */
- return (opcode != 0x62);
- case 0x70:
- return 0; /* can't boost conditional jump */
- case 0x90:
- return opcode != 0x9a; /* can't boost call far */
- case 0xc0:
- /* can't boost software-interruptions */
- return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
- case 0xd0:
- /* can boost AA* and XLAT */
- return (opcode == 0xd4 || opcode == 0xd5 || opcode == 0xd7);
- case 0xe0:
- /* can boost in/out and absolute jmps */
- return ((opcode & 0x04) || opcode == 0xea);
- case 0xf0:
- /* clear and set flags are boostable */
- return (opcode == 0xf5 || (0xf7 < opcode && opcode < 0xfe));
+ switch (opcode) {
+ case 0x62: /* bound */
+ case 0x70 ... 0x7f: /* Conditional jumps */
+ case 0x9a: /* Call far */
+ case 0xc0 ... 0xc1: /* Grp2 */
+ case 0xcc ... 0xce: /* software exceptions */
+ case 0xd0 ... 0xd3: /* Grp2 */
+ case 0xd6: /* (UD) */
+ case 0xd8 ... 0xdf: /* ESC */
+ case 0xe0 ... 0xe3: /* LOOP*, JCXZ */
+ case 0xe8 ... 0xe9: /* near Call, JMP */
+ case 0xeb: /* Short JMP */
+ case 0xf0 ... 0xf4: /* LOCK/REP, HLT */
+ case 0xf6 ... 0xf7: /* Grp3 */
+ case 0xfe: /* Grp4 */
+ /* ... are not boostable */
+ return 0;
+ case 0xff: /* Grp5 */
+ /* Only indirect jmp is boostable */
+ return X86_MODRM_REG(insn->modrm.bytes[0]) == 4;
default:
- /* CS override prefix and call are not boostable */
- return (opcode != 0x2e && opcode != 0x9a);
+ return 1;
}
}
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr) {
+ int ret;
+
/*
* Check if the instruction has been modified by another
* kprobe, in which case we replace the breakpoint by the
__addr = recover_probed_instruction(buf, addr);
if (!__addr)
return 0;
- kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
- insn_get_length(&insn);
+
+ ret = insn_decode_kernel(&insn, (void *)__addr);
+ if (ret < 0)
+ return 0;
/*
* Another debugging subsystem might insert this breakpoint.
int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
{
kprobe_opcode_t buf[MAX_INSN_SIZE];
- unsigned long recovered_insn =
- recover_probed_instruction(buf, (unsigned long)src);
+ unsigned long recovered_insn = recover_probed_instruction(buf, (unsigned long)src);
+ int ret;
if (!recovered_insn || !insn)
return 0;
MAX_INSN_SIZE))
return 0;
- kernel_insn_init(insn, dest, MAX_INSN_SIZE);
- insn_get_length(insn);
+ ret = insn_decode_kernel(insn, dest);
+ if (ret < 0)
+ return 0;
/* We can not probe force emulate prefixed instruction */
if (insn_has_emulate_prefix(insn))
return insn->length;
}
-/* Prepare reljump right after instruction to boost */
-static int prepare_boost(kprobe_opcode_t *buf, struct kprobe *p,
- struct insn *insn)
+/* Prepare reljump or int3 right after instruction */
+static int prepare_singlestep(kprobe_opcode_t *buf, struct kprobe *p,
+ struct insn *insn)
{
int len = insn->length;
- if (can_boost(insn, p->addr) &&
+ if (!IS_ENABLED(CONFIG_PREEMPTION) &&
+ !p->post_handler && can_boost(insn, p->addr) &&
MAX_INSN_SIZE - len >= JMP32_INSN_SIZE) {
/*
* These instructions can be executed directly if it
len += JMP32_INSN_SIZE;
p->ainsn.boostable = 1;
} else {
- p->ainsn.boostable = 0;
+ /* Otherwise, put an int3 for trapping singlestep */
+ if (MAX_INSN_SIZE - len < INT3_INSN_SIZE)
+ return -ENOSPC;
+
+ buf[len] = INT3_INSN_OPCODE;
+ len += INT3_INSN_SIZE;
}
return len;
module_memfree(page);
}
-static void set_resume_flags(struct kprobe *p, struct insn *insn)
+/* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */
+
+static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs)
+{
+ switch (p->ainsn.opcode) {
+ case 0xfa: /* cli */
+ regs->flags &= ~(X86_EFLAGS_IF);
+ break;
+ case 0xfb: /* sti */
+ regs->flags |= X86_EFLAGS_IF;
+ break;
+ case 0x9c: /* pushf */
+ int3_emulate_push(regs, regs->flags);
+ break;
+ case 0x9d: /* popf */
+ regs->flags = int3_emulate_pop(regs);
+ break;
+ }
+ regs->ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+}
+NOKPROBE_SYMBOL(kprobe_emulate_ifmodifiers);
+
+static void kprobe_emulate_ret(struct kprobe *p, struct pt_regs *regs)
+{
+ int3_emulate_ret(regs);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_ret);
+
+static void kprobe_emulate_call(struct kprobe *p, struct pt_regs *regs)
+{
+ unsigned long func = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+
+ func += p->ainsn.rel32;
+ int3_emulate_call(regs, func);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_call);
+
+static nokprobe_inline
+void __kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs, bool cond)
+{
+ unsigned long ip = regs->ip - INT3_INSN_SIZE + p->ainsn.size;
+
+ if (cond)
+ ip += p->ainsn.rel32;
+ int3_emulate_jmp(regs, ip);
+}
+
+static void kprobe_emulate_jmp(struct kprobe *p, struct pt_regs *regs)
+{
+ __kprobe_emulate_jmp(p, regs, true);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jmp);
+
+static const unsigned long jcc_mask[6] = {
+ [0] = X86_EFLAGS_OF,
+ [1] = X86_EFLAGS_CF,
+ [2] = X86_EFLAGS_ZF,
+ [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF,
+ [4] = X86_EFLAGS_SF,
+ [5] = X86_EFLAGS_PF,
+};
+
+static void kprobe_emulate_jcc(struct kprobe *p, struct pt_regs *regs)
+{
+ bool invert = p->ainsn.jcc.type & 1;
+ bool match;
+
+ if (p->ainsn.jcc.type < 0xc) {
+ match = regs->flags & jcc_mask[p->ainsn.jcc.type >> 1];
+ } else {
+ match = ((regs->flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^
+ ((regs->flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT);
+ if (p->ainsn.jcc.type >= 0xe)
+ match = match && (regs->flags & X86_EFLAGS_ZF);
+ }
+ __kprobe_emulate_jmp(p, regs, (match && !invert) || (!match && invert));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jcc);
+
+static void kprobe_emulate_loop(struct kprobe *p, struct pt_regs *regs)
+{
+ bool match;
+
+ if (p->ainsn.loop.type != 3) { /* LOOP* */
+ if (p->ainsn.loop.asize == 32)
+ match = ((*(u32 *)®s->cx)--) != 0;
+#ifdef CONFIG_X86_64
+ else if (p->ainsn.loop.asize == 64)
+ match = ((*(u64 *)®s->cx)--) != 0;
+#endif
+ else
+ match = ((*(u16 *)®s->cx)--) != 0;
+ } else { /* JCXZ */
+ if (p->ainsn.loop.asize == 32)
+ match = *(u32 *)(®s->cx) == 0;
+#ifdef CONFIG_X86_64
+ else if (p->ainsn.loop.asize == 64)
+ match = *(u64 *)(®s->cx) == 0;
+#endif
+ else
+ match = *(u16 *)(®s->cx) == 0;
+ }
+
+ if (p->ainsn.loop.type == 0) /* LOOPNE */
+ match = match && !(regs->flags & X86_EFLAGS_ZF);
+ else if (p->ainsn.loop.type == 1) /* LOOPE */
+ match = match && (regs->flags & X86_EFLAGS_ZF);
+
+ __kprobe_emulate_jmp(p, regs, match);
+}
+NOKPROBE_SYMBOL(kprobe_emulate_loop);
+
+static const int addrmode_regoffs[] = {
+ offsetof(struct pt_regs, ax),
+ offsetof(struct pt_regs, cx),
+ offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, sp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+ offsetof(struct pt_regs, r8),
+ offsetof(struct pt_regs, r9),
+ offsetof(struct pt_regs, r10),
+ offsetof(struct pt_regs, r11),
+ offsetof(struct pt_regs, r12),
+ offsetof(struct pt_regs, r13),
+ offsetof(struct pt_regs, r14),
+ offsetof(struct pt_regs, r15),
+#endif
+};
+
+static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs)
+{
+ unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];
+
+ int3_emulate_call(regs, regs_get_register(regs, offs));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_call_indirect);
+
+static void kprobe_emulate_jmp_indirect(struct kprobe *p, struct pt_regs *regs)
+{
+ unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg];
+
+ int3_emulate_jmp(regs, regs_get_register(regs, offs));
+}
+NOKPROBE_SYMBOL(kprobe_emulate_jmp_indirect);
+
+static int prepare_emulation(struct kprobe *p, struct insn *insn)
{
insn_byte_t opcode = insn->opcode.bytes[0];
switch (opcode) {
case 0xfa: /* cli */
case 0xfb: /* sti */
+ case 0x9c: /* pushfl */
case 0x9d: /* popf/popfd */
- /* Check whether the instruction modifies Interrupt Flag or not */
- p->ainsn.if_modifier = 1;
- break;
- case 0x9c: /* pushfl */
- p->ainsn.is_pushf = 1;
+ /*
+ * IF modifiers must be emulated since it will enable interrupt while
+ * int3 single stepping.
+ */
+ p->ainsn.emulate_op = kprobe_emulate_ifmodifiers;
+ p->ainsn.opcode = opcode;
break;
- case 0xcf: /* iret */
- p->ainsn.if_modifier = 1;
- fallthrough;
case 0xc2: /* ret/lret */
case 0xc3:
case 0xca:
case 0xcb:
- case 0xea: /* jmp absolute -- ip is correct */
- /* ip is already adjusted, no more changes required */
- p->ainsn.is_abs_ip = 1;
- /* Without resume jump, this is boostable */
- p->ainsn.boostable = 1;
+ p->ainsn.emulate_op = kprobe_emulate_ret;
break;
- case 0xe8: /* call relative - Fix return addr */
- p->ainsn.is_call = 1;
+ case 0x9a: /* far call absolute -- segment is not supported */
+ case 0xea: /* far jmp absolute -- segment is not supported */
+ case 0xcc: /* int3 */
+ case 0xcf: /* iret -- in-kernel IRET is not supported */
+ return -EOPNOTSUPP;
break;
-#ifdef CONFIG_X86_32
- case 0x9a: /* call absolute -- same as call absolute, indirect */
- p->ainsn.is_call = 1;
- p->ainsn.is_abs_ip = 1;
+ case 0xe8: /* near call relative */
+ p->ainsn.emulate_op = kprobe_emulate_call;
+ if (insn->immediate.nbytes == 2)
+ p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+ else
+ p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
break;
-#endif
- case 0xff:
+ case 0xeb: /* short jump relative */
+ case 0xe9: /* near jump relative */
+ p->ainsn.emulate_op = kprobe_emulate_jmp;
+ if (insn->immediate.nbytes == 1)
+ p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
+ else if (insn->immediate.nbytes == 2)
+ p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+ else
+ p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
+ break;
+ case 0x70 ... 0x7f:
+ /* 1 byte conditional jump */
+ p->ainsn.emulate_op = kprobe_emulate_jcc;
+ p->ainsn.jcc.type = opcode & 0xf;
+ p->ainsn.rel32 = *(char *)insn->immediate.bytes;
+ break;
+ case 0x0f:
opcode = insn->opcode.bytes[1];
+ if ((opcode & 0xf0) == 0x80) {
+ /* 2 bytes Conditional Jump */
+ p->ainsn.emulate_op = kprobe_emulate_jcc;
+ p->ainsn.jcc.type = opcode & 0xf;
+ if (insn->immediate.nbytes == 2)
+ p->ainsn.rel32 = *(s16 *)&insn->immediate.value;
+ else
+ p->ainsn.rel32 = *(s32 *)&insn->immediate.value;
+ } else if (opcode == 0x01 &&
+ X86_MODRM_REG(insn->modrm.bytes[0]) == 0 &&
+ X86_MODRM_MOD(insn->modrm.bytes[0]) == 3) {
+ /* VM extensions - not supported */
+ return -EOPNOTSUPP;
+ }
+ break;
+ case 0xe0: /* Loop NZ */
+ case 0xe1: /* Loop */
+ case 0xe2: /* Loop */
+ case 0xe3: /* J*CXZ */
+ p->ainsn.emulate_op = kprobe_emulate_loop;
+ p->ainsn.loop.type = opcode & 0x3;
+ p->ainsn.loop.asize = insn->addr_bytes * 8;
+ p->ainsn.rel32 = *(s8 *)&insn->immediate.value;
+ break;
+ case 0xff:
+ /*
+ * Since the 0xff is an extended group opcode, the instruction
+ * is determined by the MOD/RM byte.
+ */
+ opcode = insn->modrm.bytes[0];
if ((opcode & 0x30) == 0x10) {
- /*
- * call absolute, indirect
- * Fix return addr; ip is correct.
- * But this is not boostable
- */
- p->ainsn.is_call = 1;
- p->ainsn.is_abs_ip = 1;
+ if ((opcode & 0x8) == 0x8)
+ return -EOPNOTSUPP; /* far call */
+ /* call absolute, indirect */
+ p->ainsn.emulate_op = kprobe_emulate_call_indirect;
+ } else if ((opcode & 0x30) == 0x20) {
+ if ((opcode & 0x8) == 0x8)
+ return -EOPNOTSUPP; /* far jmp */
+ /* jmp near absolute indirect */
+ p->ainsn.emulate_op = kprobe_emulate_jmp_indirect;
+ } else
break;
- } else if (((opcode & 0x31) == 0x20) ||
- ((opcode & 0x31) == 0x21)) {
- /*
- * jmp near and far, absolute indirect
- * ip is correct.
- */
- p->ainsn.is_abs_ip = 1;
- /* Without resume jump, this is boostable */
- p->ainsn.boostable = 1;
- }
+
+ if (insn->addr_bytes != sizeof(unsigned long))
+ return -EOPNOTSUPP; /* Don't support differnt size */
+ if (X86_MODRM_MOD(opcode) != 3)
+ return -EOPNOTSUPP; /* TODO: support memory addressing */
+
+ p->ainsn.indirect.reg = X86_MODRM_RM(opcode);
+#ifdef CONFIG_X86_64
+ if (X86_REX_B(insn->rex_prefix.value))
+ p->ainsn.indirect.reg += 8;
+#endif
+ break;
+ default:
break;
}
+ p->ainsn.size = insn->length;
+
+ return 0;
}
static int arch_copy_kprobe(struct kprobe *p)
{
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
- int len;
+ int ret, len;
/* Copy an instruction with recovering if other optprobe modifies it.*/
len = __copy_instruction(buf, p->addr, p->ainsn.insn, &insn);
if (!len)
return -EINVAL;
- /*
- * __copy_instruction can modify the displacement of the instruction,
- * but it doesn't affect boostable check.
- */
- len = prepare_boost(buf, p, &insn);
+ /* Analyze the opcode and setup emulate functions */
+ ret = prepare_emulation(p, &insn);
+ if (ret < 0)
+ return ret;
- /* Analyze the opcode and set resume flags */
- set_resume_flags(p, &insn);
+ /* Add int3 for single-step or booster jmp */
+ len = prepare_singlestep(buf, p, &insn);
+ if (len < 0)
+ return len;
/* Also, displacement change doesn't affect the first byte */
p->opcode = buf[0];
{
__this_cpu_write(current_kprobe, p);
kcb->kprobe_saved_flags = kcb->kprobe_old_flags
- = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF));
- if (p->ainsn.if_modifier)
- kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF;
-}
-
-static nokprobe_inline void clear_btf(void)
-{
- if (test_thread_flag(TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl &= ~DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- }
-}
-
-static nokprobe_inline void restore_btf(void)
-{
- if (test_thread_flag(TIF_BLOCKSTEP)) {
- unsigned long debugctl = get_debugctlmsr();
-
- debugctl |= DEBUGCTLMSR_BTF;
- update_debugctlmsr(debugctl);
- }
+ = (regs->flags & X86_EFLAGS_IF);
}
void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
}
NOKPROBE_SYMBOL(arch_prepare_kretprobe);
+static void kprobe_post_process(struct kprobe *cur, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
+ kcb->kprobe_status = KPROBE_HIT_SSDONE;
+ cur->post_handler(cur, regs, 0);
+ }
+
+ /* Restore back the original saved kprobes variables and continue. */
+ if (kcb->kprobe_status == KPROBE_REENTER)
+ restore_previous_kprobe(kcb);
+ else
+ reset_current_kprobe();
+}
+NOKPROBE_SYMBOL(kprobe_post_process);
+
static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb, int reenter)
{
return;
#if !defined(CONFIG_PREEMPTION)
- if (p->ainsn.boostable && !p->post_handler) {
+ if (p->ainsn.boostable) {
/* Boost up -- we can execute copied instructions directly */
if (!reenter)
reset_current_kprobe();
kcb->kprobe_status = KPROBE_REENTER;
} else
kcb->kprobe_status = KPROBE_HIT_SS;
- /* Prepare real single stepping */
- clear_btf();
- regs->flags |= X86_EFLAGS_TF;
+
+ if (p->ainsn.emulate_op) {
+ p->ainsn.emulate_op(p, regs);
+ kprobe_post_process(p, regs, kcb);
+ return;
+ }
+
+ /* Disable interrupt, and set ip register on trampoline */
regs->flags &= ~X86_EFLAGS_IF;
- /* single step inline if the instruction is an int3 */
- if (p->opcode == INT3_INSN_OPCODE)
- regs->ip = (unsigned long)p->addr;
- else
- regs->ip = (unsigned long)p->ainsn.insn;
+ regs->ip = (unsigned long)p->ainsn.insn;
}
NOKPROBE_SYMBOL(setup_singlestep);
+/*
+ * Called after single-stepping. p->addr is the address of the
+ * instruction whose first byte has been replaced by the "int3"
+ * instruction. To avoid the SMP problems that can occur when we
+ * temporarily put back the original opcode to single-step, we
+ * single-stepped a copy of the instruction. The address of this
+ * copy is p->ainsn.insn. We also doesn't use trap, but "int3" again
+ * right after the copied instruction.
+ * Different from the trap single-step, "int3" single-step can not
+ * handle the instruction which changes the ip register, e.g. jmp,
+ * call, conditional jmp, and the instructions which changes the IF
+ * flags because interrupt must be disabled around the single-stepping.
+ * Such instructions are software emulated, but others are single-stepped
+ * using "int3".
+ *
+ * When the 2nd "int3" handled, the regs->ip and regs->flags needs to
+ * be adjusted, so that we can resume execution on correct code.
+ */
+static void resume_singlestep(struct kprobe *p, struct pt_regs *regs,
+ struct kprobe_ctlblk *kcb)
+{
+ unsigned long copy_ip = (unsigned long)p->ainsn.insn;
+ unsigned long orig_ip = (unsigned long)p->addr;
+
+ /* Restore saved interrupt flag and ip register */
+ regs->flags |= kcb->kprobe_saved_flags;
+ /* Note that regs->ip is executed int3 so must be a step back */
+ regs->ip += (orig_ip - copy_ip) - INT3_INSN_SIZE;
+}
+NOKPROBE_SYMBOL(resume_singlestep);
+
/*
* We have reentered the kprobe_handler(), since another probe was hit while
* within the handler. We save the original kprobes variables and just single
}
NOKPROBE_SYMBOL(reenter_kprobe);
+static nokprobe_inline int kprobe_is_ss(struct kprobe_ctlblk *kcb)
+{
+ return (kcb->kprobe_status == KPROBE_HIT_SS ||
+ kcb->kprobe_status == KPROBE_REENTER);
+}
+
/*
* Interrupts are disabled on entry as trap3 is an interrupt gate and they
* remain disabled throughout this function.
reset_current_kprobe();
return 1;
}
- } else if (*addr != INT3_INSN_OPCODE) {
+ } else if (kprobe_is_ss(kcb)) {
+ p = kprobe_running();
+ if ((unsigned long)p->ainsn.insn < regs->ip &&
+ (unsigned long)p->ainsn.insn + MAX_INSN_SIZE > regs->ip) {
+ /* Most provably this is the second int3 for singlestep */
+ resume_singlestep(p, regs, kcb);
+ kprobe_post_process(p, regs, kcb);
+ return 1;
+ }
+ }
+
+ if (*addr != INT3_INSN_OPCODE) {
/*
* The breakpoint instruction was removed right
* after we hit it. Another cpu has removed
}
NOKPROBE_SYMBOL(trampoline_handler);
-/*
- * Called after single-stepping. p->addr is the address of the
- * instruction whose first byte has been replaced by the "int 3"
- * instruction. To avoid the SMP problems that can occur when we
- * temporarily put back the original opcode to single-step, we
- * single-stepped a copy of the instruction. The address of this
- * copy is p->ainsn.insn.
- *
- * This function prepares to return from the post-single-step
- * interrupt. We have to fix up the stack as follows:
- *
- * 0) Except in the case of absolute or indirect jump or call instructions,
- * the new ip is relative to the copied instruction. We need to make
- * it relative to the original instruction.
- *
- * 1) If the single-stepped instruction was pushfl, then the TF and IF
- * flags are set in the just-pushed flags, and may need to be cleared.
- *
- * 2) If the single-stepped instruction was a call, the return address
- * that is atop the stack is the address following the copied instruction.
- * We need to make it the address following the original instruction.
- */
-static void resume_execution(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
-{
- unsigned long *tos = stack_addr(regs);
- unsigned long copy_ip = (unsigned long)p->ainsn.insn;
- unsigned long orig_ip = (unsigned long)p->addr;
-
- regs->flags &= ~X86_EFLAGS_TF;
-
- /* Fixup the contents of top of stack */
- if (p->ainsn.is_pushf) {
- *tos &= ~(X86_EFLAGS_TF | X86_EFLAGS_IF);
- *tos |= kcb->kprobe_old_flags;
- } else if (p->ainsn.is_call) {
- *tos = orig_ip + (*tos - copy_ip);
- }
-
- if (!p->ainsn.is_abs_ip)
- regs->ip += orig_ip - copy_ip;
-
- restore_btf();
-}
-NOKPROBE_SYMBOL(resume_execution);
-
-/*
- * Interrupts are disabled on entry as trap1 is an interrupt gate and they
- * remain disabled throughout this function.
- */
-int kprobe_debug_handler(struct pt_regs *regs)
-{
- struct kprobe *cur = kprobe_running();
- struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
- if (!cur)
- return 0;
-
- resume_execution(cur, regs, kcb);
- regs->flags |= kcb->kprobe_saved_flags;
-
- if ((kcb->kprobe_status != KPROBE_REENTER) && cur->post_handler) {
- kcb->kprobe_status = KPROBE_HIT_SSDONE;
- cur->post_handler(cur, regs, 0);
- }
-
- /* Restore back the original saved kprobes variables and continue. */
- if (kcb->kprobe_status == KPROBE_REENTER) {
- restore_previous_kprobe(kcb);
- goto out;
- }
- reset_current_kprobe();
-out:
- /*
- * if somebody else is singlestepping across a probe point, flags
- * will have TF set, in which case, continue the remaining processing
- * of do_debug, as if this is not a probe hit.
- */
- if (regs->flags & X86_EFLAGS_TF)
- return 0;
-
- return 1;
-}
-NOKPROBE_SYMBOL(kprobe_debug_handler);
-
int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
{
struct kprobe *cur = kprobe_running();
* normal page fault.
*/
regs->ip = (unsigned long)cur->addr;
- /*
- * Trap flag (TF) has been set here because this fault
- * happened where the single stepping will be done.
- * So clear it by resetting the current kprobe:
- */
- regs->flags &= ~X86_EFLAGS_TF;
- /*
- * Since the single step (trap) has been cancelled,
- * we need to restore BTF here.
- */
- restore_btf();
/*
- * If the TF flag was set before the kprobe hit,
+ * If the IF flag was set before the kprobe hit,
* don't touch it:
*/
regs->flags |= kcb->kprobe_old_flags;
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
unsigned long recovered_insn;
+ int ret;
+
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
recovered_insn = recover_probed_instruction(buf, addr);
if (!recovered_insn)
return 0;
- kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
- insn_get_length(&insn);
+
+ ret = insn_decode_kernel(&insn, (void *)recovered_insn);
+ if (ret < 0)
+ return 0;
+
/*
* In the case of detecting unknown breakpoint, this could be
* a padding INT3 between functions. Let's check that all the
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
- pv_ops.time.steal_clock = kvm_steal_clock;
+ static_call_update(pv_steal_clock, kvm_steal_clock);
}
if (pv_tlb_flush_supported()) {
if (!stable)
clear_sched_clock_stable();
kvm_sched_clock_offset = kvm_clock_read();
- pv_ops.time.sched_clock = kvm_sched_clock_read;
+ paravirt_set_sched_clock(kvm_sched_clock_read);
pr_info("kvm-clock: using sched offset of %llu cycles",
kvm_sched_clock_offset);
return pv_ops.lock.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
+
+void __init paravirt_set_cap(void)
+{
+ if (!pv_is_native_spin_unlock())
+ setup_force_cpu_cap(X86_FEATURE_PVUNLOCK);
+
+ if (!pv_is_native_vcpu_is_preempted())
+ setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
+}
#include <linux/highmem.h>
#include <linux/kprobes.h>
#include <linux/pgtable.h>
+#include <linux/static_call.h>
#include <asm/bug.h>
#include <asm/paravirt.h>
}
/* Undefined instruction for dealing with missing ops pointers. */
-static const unsigned char ud2a[] = { 0x0f, 0x0b };
+static void paravirt_BUG(void)
+{
+ BUG();
+}
struct branch {
unsigned char opcode;
{
return x;
}
-
-static unsigned paravirt_patch_jmp(void *insn_buff, const void *target,
- unsigned long addr, unsigned len)
-{
- struct branch *b = insn_buff;
- unsigned long delta = (unsigned long)target - (addr+5);
-
- if (len < 5) {
-#ifdef CONFIG_RETPOLINE
- WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
-#endif
- return len; /* call too long for patch site */
- }
-
- b->opcode = 0xe9; /* jmp */
- b->delta = delta;
-
- return 5;
-}
#endif
DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
static_branch_disable(&virt_spin_lock_key);
}
-unsigned paravirt_patch_default(u8 type, void *insn_buff,
- unsigned long addr, unsigned len)
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
+ unsigned int len)
{
/*
* Neat trick to map patch type back to the call within the
unsigned ret;
if (opfunc == NULL)
- /* If there's no function, patch it with a ud2a (BUG) */
- ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a));
+ /* If there's no function, patch it with paravirt_BUG() */
+ ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
else if (opfunc == _paravirt_nop)
ret = 0;
-
-#ifdef CONFIG_PARAVIRT_XXL
- /* identity functions just return their single argument */
- else if (opfunc == _paravirt_ident_64)
- ret = paravirt_patch_ident_64(insn_buff, len);
-
- else if (type == PARAVIRT_PATCH(cpu.iret))
- /* If operation requires a jmp, then jmp */
- ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
-#endif
else
/* Otherwise call the function. */
ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
return ret;
}
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
- const char *start, const char *end)
-{
- unsigned insn_len = end - start;
-
- /* Alternative instruction is too large for the patch site and we cannot continue: */
- BUG_ON(insn_len > len || start == NULL);
-
- memcpy(insn_buff, start, insn_len);
-
- return insn_len;
-}
-
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
return 0;
}
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+ static_call_update(pv_sched_clock, func);
+}
+
/* These are in entry.S */
extern void native_iret(void);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
struct paravirt_patch_template pv_ops = {
- /* Init ops. */
- .init.patch = native_patch,
-
- /* Time ops. */
- .time.sched_clock = native_sched_clock,
- .time.steal_clock = native_steal_clock,
-
/* Cpu ops. */
.cpu.io_delay = native_io_delay,
.cpu.load_sp0 = native_load_sp0,
- .cpu.iret = native_iret,
-
#ifdef CONFIG_X86_IOPL_IOPERM
.cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap,
.cpu.update_io_bitmap = native_tss_update_io_bitmap,
NOKPROBE_SYMBOL(native_get_debugreg);
NOKPROBE_SYMBOL(native_set_debugreg);
NOKPROBE_SYMBOL(native_load_idt);
+
+void (*paravirt_iret)(void) = native_iret;
#endif
EXPORT_SYMBOL(pv_ops);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stringify.h>
-
-#include <asm/paravirt.h>
-#include <asm/asm-offsets.h>
-
-#define PSTART(d, m) \
- patch_data_##d.m
-
-#define PEND(d, m) \
- (PSTART(d, m) + sizeof(patch_data_##d.m))
-
-#define PATCH(d, m, insn_buff, len) \
- paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m))
-
-#define PATCH_CASE(ops, m, data, insn_buff, len) \
- case PARAVIRT_PATCH(ops.m): \
- return PATCH(data, ops##_##m, insn_buff, len)
-
-#ifdef CONFIG_PARAVIRT_XXL
-struct patch_xxl {
- const unsigned char irq_irq_disable[1];
- const unsigned char irq_irq_enable[1];
- const unsigned char irq_save_fl[2];
- const unsigned char mmu_read_cr2[3];
- const unsigned char mmu_read_cr3[3];
- const unsigned char mmu_write_cr3[3];
- const unsigned char cpu_wbinvd[2];
- const unsigned char mov64[3];
-};
-
-static const struct patch_xxl patch_data_xxl = {
- .irq_irq_disable = { 0xfa }, // cli
- .irq_irq_enable = { 0xfb }, // sti
- .irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax
- .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax
- .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax
- .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3
- .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd
- .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax
-};
-
-unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
-{
- return PATCH(xxl, mov64, insn_buff, len);
-}
-# endif /* CONFIG_PARAVIRT_XXL */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-struct patch_lock {
- unsigned char queued_spin_unlock[3];
- unsigned char vcpu_is_preempted[2];
-};
-
-static const struct patch_lock patch_data_lock = {
- .vcpu_is_preempted = { 0x31, 0xc0 }, // xor %eax, %eax
-
-# ifdef CONFIG_X86_64
- .queued_spin_unlock = { 0xc6, 0x07, 0x00 }, // movb $0, (%rdi)
-# else
- .queued_spin_unlock = { 0xc6, 0x00, 0x00 }, // movb $0, (%eax)
-# endif
-};
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
-unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
- unsigned int len)
-{
- switch (type) {
-
-#ifdef CONFIG_PARAVIRT_XXL
- PATCH_CASE(irq, save_fl, xxl, insn_buff, len);
- PATCH_CASE(irq, irq_enable, xxl, insn_buff, len);
- PATCH_CASE(irq, irq_disable, xxl, insn_buff, len);
-
- PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len);
- PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
- PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-
- PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-#endif
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
- case PARAVIRT_PATCH(lock.queued_spin_unlock):
- if (pv_is_native_spin_unlock())
- return PATCH(lock, queued_spin_unlock, insn_buff, len);
- break;
-
- case PARAVIRT_PATCH(lock.vcpu_is_preempted):
- if (pv_is_native_vcpu_is_preempted())
- return PATCH(lock, vcpu_is_preempted, insn_buff, len);
- break;
-#endif
- default:
- break;
- }
-
- return paravirt_patch_default(type, insn_buff, addr, len);
-}
per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
per_cpu(cpu_number, cpu) = cpu;
setup_percpu_segment(cpu);
- setup_stack_canary_segment(cpu);
/*
* Copy data used in early init routines from the
* initial arrays to the per cpu data areas. These
return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
}
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
{
char buffer[MAX_INSN_SIZE];
- enum es_result ret;
int res;
- if (user_mode(ctxt->regs)) {
- res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
- if (!res) {
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
- ctxt->fi.cr2 = ctxt->regs->ip;
- return ES_EXCEPTION;
- }
+ res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+ if (!res) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
+ ctxt->fi.cr2 = ctxt->regs->ip;
+ return ES_EXCEPTION;
+ }
- if (!insn_decode(&ctxt->insn, ctxt->regs, buffer, res))
- return ES_DECODE_FAILED;
- } else {
- res = vc_fetch_insn_kernel(ctxt, buffer);
- if (res) {
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = X86_PF_INSTR;
- ctxt->fi.cr2 = ctxt->regs->ip;
- return ES_EXCEPTION;
- }
+ if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, res))
+ return ES_DECODE_FAILED;
+
+ if (ctxt->insn.immediate.got)
+ return ES_OK;
+ else
+ return ES_DECODE_FAILED;
+}
- insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1);
- insn_get_length(&ctxt->insn);
+static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+{
+ char buffer[MAX_INSN_SIZE];
+ int res, ret;
+
+ res = vc_fetch_insn_kernel(ctxt, buffer);
+ if (res) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_INSTR;
+ ctxt->fi.cr2 = ctxt->regs->ip;
+ return ES_EXCEPTION;
}
- ret = ctxt->insn.immediate.got ? ES_OK : ES_DECODE_FAILED;
+ ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+ if (ret < 0)
+ return ES_DECODE_FAILED;
+ else
+ return ES_OK;
+}
- return ret;
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+ if (user_mode(ctxt->regs))
+ return __vc_decode_user_insn(ctxt);
+ else
+ return __vc_decode_kern_insn(ctxt);
}
static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
savesegment(fs, sel);
if (sel == modified_sel)
loadsegment(fs, sel);
-
- savesegment(gs, sel);
- if (sel == modified_sel)
- load_gs_index(sel);
#endif
-#ifdef CONFIG_X86_32_LAZY_GS
savesegment(gs, sel);
if (sel == modified_sel)
- loadsegment(gs, sel);
-#endif
+ load_gs_index(sel);
} else {
#ifdef CONFIG_X86_64
if (p->thread.fsindex == modified_sel)
{
u8 insn_buf[MAX_INSN_SIZE];
struct insn insn;
+ int ret;
if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
MAX_INSN_SIZE))
return GP_NO_HINT;
- kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
- insn_get_modrm(&insn);
- insn_get_sib(&insn);
+ ret = insn_decode_kernel(&insn, insn_buf);
+ if (ret < 0)
+ return GP_NO_HINT;
*addr = (unsigned long)insn_get_addr_ref(&insn, regs);
if (*addr == -1UL)
if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs))
dr6 &= ~DR_STEP;
- if (kprobe_debug_handler(regs))
- goto out;
-
/*
* The kernel doesn't use INT1
*/
#include <linux/percpu.h>
#include <linux/timex.h>
#include <linux/static_key.h>
+#include <linux/static_call.h>
#include <asm/hpet.h>
#include <asm/timer.h>
bool using_native_sched_clock(void)
{
- return pv_ops.time.sched_clock == native_sched_clock;
+ return static_call_query(pv_sched_clock) == native_sched_clock;
}
#else
unsigned long long
if (!nr_copied)
return false;
- if (!insn_decode(&insn, regs, buf, nr_copied))
+ if (!insn_decode_from_regs(&insn, regs, buf, nr_copied))
return false;
umip_inst = identify_insn(&insn);
static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64)
{
+ enum insn_mode m = x86_64 ? INSN_MODE_64 : INSN_MODE_32;
u32 volatile *good_insns;
+ int ret;
- insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
- /* has the side-effect of processing the entire instruction */
- insn_get_length(insn);
- if (!insn_complete(insn))
+ ret = insn_decode(insn, auprobe->insn, sizeof(auprobe->insn), m);
+ if (ret < 0)
return -ENOEXEC;
if (is_prefix_bad(insn))
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
.macro read64 reg
movl %ebx, %eax
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
/*
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/export.h>
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
-#include <asm/insn.h>
+#include <asm/insn.h> /* __ignore_sync_check__ */
/* Attribute tables are generated from opcode map */
#include "inat-tables.c"
case INAT_SEG_REG_FS:
return (unsigned short)(regs->fs & 0xffff);
case INAT_SEG_REG_GS:
- /*
- * GS may or may not be in regs as per CONFIG_X86_32_LAZY_GS.
- * The macro below takes care of both cases.
- */
return get_user_gs(regs);
case INAT_SEG_REG_IGNORE:
default:
static int get_eff_addr_reg(struct insn *insn, struct pt_regs *regs,
int *regoff, long *eff_addr)
{
- insn_get_modrm(insn);
+ int ret;
- if (!insn->modrm.nbytes)
- return -EINVAL;
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
if (X86_MODRM_MOD(insn->modrm.value) != 3)
return -EINVAL;
int *regoff, long *eff_addr)
{
long tmp;
+ int ret;
if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
return -EINVAL;
- insn_get_modrm(insn);
-
- if (!insn->modrm.nbytes)
- return -EINVAL;
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
if (X86_MODRM_MOD(insn->modrm.value) > 2)
return -EINVAL;
* @base_offset will have a register, as an offset from the base of pt_regs,
* that can be used to resolve the associated segment.
*
- * -EINVAL on error.
+ * Negative value on error.
*/
static int get_eff_addr_sib(struct insn *insn, struct pt_regs *regs,
int *base_offset, long *eff_addr)
{
long base, indx;
int indx_offset;
+ int ret;
if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
return -EINVAL;
- insn_get_modrm(insn);
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
if (!insn->modrm.nbytes)
return -EINVAL;
if (X86_MODRM_MOD(insn->modrm.value) > 2)
return -EINVAL;
- insn_get_sib(insn);
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
if (!insn->sib.nbytes)
return -EINVAL;
short eff_addr;
long tmp;
- insn_get_modrm(insn);
- insn_get_displacement(insn);
+ if (insn_get_displacement(insn))
+ goto out;
if (insn->addr_bytes != 2)
goto out;
}
/**
- * insn_decode() - Decode an instruction
+ * insn_decode_from_regs() - Decode an instruction
* @insn: Structure to store decoded instruction
* @regs: Structure with register values as seen when entering kernel mode
* @buf: Buffer containing the instruction bytes
*
* True if instruction was decoded, False otherwise.
*/
-bool insn_decode(struct insn *insn, struct pt_regs *regs,
- unsigned char buf[MAX_INSN_SIZE], int buf_size)
+bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
+ unsigned char buf[MAX_INSN_SIZE], int buf_size)
{
int seg_defs;
insn->addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs);
insn->opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs);
- insn_get_length(insn);
+ if (insn_get_length(insn))
+ return false;
+
if (buf_size < insn->length)
return false;
#else
#include <string.h>
#endif
-#include <asm/inat.h>
-#include <asm/insn.h>
+#include <asm/inat.h> /*__ignore_sync_check__ */
+#include <asm/insn.h> /* __ignore_sync_check__ */
-#include <asm/emulate_prefix.h>
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include <asm/emulate_prefix.h> /* __ignore_sync_check__ */
#define leXX_to_cpu(t, r) \
({ \
* insn_init() - initialize struct insn
* @insn: &struct insn to be initialized
* @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
* @x86_64: !0 for 64-bit kernel or 64-bit app
*/
void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
* Populates the @insn->prefixes bitmap, and updates @insn->next_byte
* to point to the (first) opcode. No effect if @insn->prefixes.got
* is already set.
+ *
+ * * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_prefixes(struct insn *insn)
+int insn_get_prefixes(struct insn *insn)
{
struct insn_field *prefixes = &insn->prefixes;
insn_attr_t attr;
int i, nb;
if (prefixes->got)
- return;
+ return 0;
insn_get_emulate_prefix(insn);
prefixes->got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
/**
* If necessary, first collects any preceding (prefix) bytes.
* Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got
* is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_opcode(struct insn *insn)
+int insn_get_opcode(struct insn *insn)
{
struct insn_field *opcode = &insn->opcode;
+ int pfx_id, ret;
insn_byte_t op;
- int pfx_id;
+
if (opcode->got)
- return;
- if (!insn->prefixes.got)
- insn_get_prefixes(insn);
+ return 0;
+
+ if (!insn->prefixes.got) {
+ ret = insn_get_prefixes(insn);
+ if (ret)
+ return ret;
+ }
/* Get first opcode */
op = get_next(insn_byte_t, insn);
insn->attr = inat_get_avx_attribute(op, m, p);
if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
(!inat_accept_vex(insn->attr) &&
- !inat_is_group(insn->attr)))
- insn->attr = 0; /* This instruction is bad */
- goto end; /* VEX has only 1 byte for opcode */
+ !inat_is_group(insn->attr))) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ /* VEX has only 1 byte for opcode */
+ goto end;
}
insn->attr = inat_get_opcode_attribute(op);
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
}
- if (inat_must_vex(insn->attr))
- insn->attr = 0; /* This instruction is bad */
+
+ if (inat_must_vex(insn->attr)) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
end:
opcode->got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
* Populates @insn->modrm and updates @insn->next_byte to point past the
* ModRM byte, if any. If necessary, first collects the preceding bytes
* (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_modrm(struct insn *insn)
+int insn_get_modrm(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
insn_byte_t pfx_id, mod;
+ int ret;
+
if (modrm->got)
- return;
- if (!insn->opcode.got)
- insn_get_opcode(insn);
+ return 0;
+
+ if (!insn->opcode.got) {
+ ret = insn_get_opcode(insn);
+ if (ret)
+ return ret;
+ }
if (inat_has_modrm(insn->attr)) {
mod = get_next(insn_byte_t, insn);
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_group_attribute(mod, pfx_id,
insn->attr);
- if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
- insn->attr = 0; /* This is bad */
+ if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) {
+ /* Bad insn */
+ insn->attr = 0;
+ return -EINVAL;
+ }
}
}
if (insn->x86_64 && inat_is_force64(insn->attr))
insn->opnd_bytes = 8;
+
modrm->got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
int insn_rip_relative(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
+ int ret;
if (!insn->x86_64)
return 0;
- if (!modrm->got)
- insn_get_modrm(insn);
+
+ if (!modrm->got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return 0;
+ }
/*
* For rip-relative instructions, the mod field (top 2 bits)
* is zero and the r/m field (bottom 3 bits) is 0x5.
*
* If necessary, first collects the instruction up to and including the
* ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
*/
-void insn_get_sib(struct insn *insn)
+int insn_get_sib(struct insn *insn)
{
insn_byte_t modrm;
+ int ret;
if (insn->sib.got)
- return;
- if (!insn->modrm.got)
- insn_get_modrm(insn);
+ return 0;
+
+ if (!insn->modrm.got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+ }
+
if (insn->modrm.nbytes) {
modrm = insn->modrm.bytes[0];
if (insn->addr_bytes != 2 &&
}
insn->sib.got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
* If necessary, first collects the instruction up to and including the
* SIB byte.
* Displacement value is sign-expanded.
+ *
+ * * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
*/
-void insn_get_displacement(struct insn *insn)
+int insn_get_displacement(struct insn *insn)
{
insn_byte_t mod, rm, base;
+ int ret;
if (insn->displacement.got)
- return;
- if (!insn->sib.got)
- insn_get_sib(insn);
+ return 0;
+
+ if (!insn->sib.got) {
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
+ }
+
if (insn->modrm.nbytes) {
/*
* Interpreting the modrm byte:
}
out:
insn->displacement.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/* Decode moffset16/32/64. Return 0 if failed */
}
/**
- * insn_get_immediate() - Get the immediates of instruction
+ * insn_get_immediate() - Get the immediate in an instruction
* @insn: &struct insn containing instruction
*
* If necessary, first collects the instruction up to and including the
* displacement bytes.
* Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_immediate(struct insn *insn)
+int insn_get_immediate(struct insn *insn)
{
+ int ret;
+
if (insn->immediate.got)
- return;
- if (!insn->displacement.got)
- insn_get_displacement(insn);
+ return 0;
+
+ if (!insn->displacement.got) {
+ ret = insn_get_displacement(insn);
+ if (ret)
+ return ret;
+ }
if (inat_has_moffset(insn->attr)) {
if (!__get_moffset(insn))
}
done:
insn->immediate.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
*
* If necessary, first collects the instruction up to and including the
* immediates bytes.
- */
-void insn_get_length(struct insn *insn)
+ *
+ * Returns:
+ * - 0 on success
+ * - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
{
+ int ret;
+
if (insn->length)
- return;
- if (!insn->immediate.got)
- insn_get_immediate(insn);
+ return 0;
+
+ if (!insn->immediate.got) {
+ ret = insn_get_immediate(insn);
+ if (ret)
+ return ret;
+ }
+
insn->length = (unsigned char)((unsigned long)insn->next_byte
- (unsigned long)insn->kaddr);
+
+ return 0;
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+ return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+ insn->displacement.got && insn->immediate.got;
+}
+
+/**
+ * insn_decode() - Decode an x86 instruction
+ * @insn: &struct insn to be initialized
+ * @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
+ * @m: insn mode, see enum insn_mode
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m)
+{
+ int ret;
+
+/* #define INSN_MODE_KERN -1 __ignore_sync_check__ mode is only valid in the kernel */
+
+ if (m == INSN_MODE_KERN)
+ insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64));
+ else
+ insn_init(insn, kaddr, buf_len, m == INSN_MODE_64);
+
+ ret = insn_get_length(insn);
+ if (ret)
+ return ret;
+
+ if (insn_complete(insn))
+ return 0;
+
+ return -EINVAL;
}
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
.pushsection .noinstr.text, "ax"
*/
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
#undef memmove
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
/*
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/dma-mapping.h>
+#include <linux/virtio_config.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
print_mem_encrypt_feature_info();
}
+int arch_has_restricted_virtio_memory_access(void)
+{
+ return sev_active();
+}
+EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access);
#define PVH_GDT_ENTRY_CS 1
#define PVH_GDT_ENTRY_DS 2
-#define PVH_GDT_ENTRY_CANARY 3
#define PVH_CS_SEL (PVH_GDT_ENTRY_CS * 8)
#define PVH_DS_SEL (PVH_GDT_ENTRY_DS * 8)
-#define PVH_CANARY_SEL (PVH_GDT_ENTRY_CANARY * 8)
SYM_CODE_START_LOCAL(pvh_start_xen)
cld
#else /* CONFIG_X86_64 */
- /* Set base address in stack canary descriptor. */
- movl $_pa(gdt_start),%eax
- movl $_pa(canary),%ecx
- movw %cx, (PVH_GDT_ENTRY_CANARY * 8) + 2(%eax)
- shrl $16, %ecx
- movb %cl, (PVH_GDT_ENTRY_CANARY * 8) + 4(%eax)
- movb %ch, (PVH_GDT_ENTRY_CANARY * 8) + 7(%eax)
-
- mov $PVH_CANARY_SEL,%eax
- mov %eax,%gs
-
call mk_early_pgtbl_32
mov $_pa(initial_page_table), %eax
.quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */
#endif
.quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */
- .quad GDT_ENTRY(0x4090, 0, 0x18) /* PVH_CANARY_SEL */
SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
.balign 16
/*
* segment registers
*/
-#ifdef CONFIG_X86_32_LAZY_GS
savesegment(gs, ctxt->gs);
-#endif
#ifdef CONFIG_X86_64
- savesegment(gs, ctxt->gs);
savesegment(fs, ctxt->fs);
savesegment(ds, ctxt->ds);
savesegment(es, ctxt->es);
wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
#else
loadsegment(fs, __KERNEL_PERCPU);
- loadsegment(gs, __KERNEL_STACK_CANARY);
#endif
/* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
*/
wrmsrl(MSR_FS_BASE, ctxt->fs_base);
wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
-#elif defined(CONFIG_X86_32_LAZY_GS)
+#else
loadsegment(gs, ctxt->gs);
#endif
while (fgets(line, BUFSIZE, stdin)) {
char copy[BUFSIZE], *s, *tab1, *tab2;
- int nb = 0;
+ int nb = 0, ret;
unsigned int b;
if (line[0] == '<') {
} else
break;
}
+
/* Decode an instruction */
- insn_init(&insn, insn_buff, sizeof(insn_buff), x86_64);
- insn_get_length(&insn);
- if (insn.length != nb) {
+ ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+
+ if (ret < 0 || insn.length != nb) {
warnings++;
pr_warn("Found an x86 instruction decoder bug, "
"please report this.\n", sym);
int main(int argc, char **argv)
{
+ int insns = 0, ret;
struct insn insn;
- int insns = 0;
int errors = 0;
unsigned long i;
unsigned char insn_buff[MAX_INSN_SIZE * 2];
continue;
/* Decode an instruction */
- insn_init(&insn, insn_buff, sizeof(insn_buff), x86_64);
- insn_get_length(&insn);
+ ret = insn_decode(&insn, insn_buff, sizeof(insn_buff),
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
if (insn.next_byte <= insn.kaddr ||
insn.kaddr + MAX_INSN_SIZE < insn.next_byte) {
/* Access out-of-range memory */
dump_stream(stderr, "Error: Found an access violation", i, insn_buff, &insn);
errors++;
- } else if (verbose && !insn_complete(&insn))
+ } else if (verbose && ret < 0)
dump_stream(stdout, "Info: Found an undecodable input", i, insn_buff, &insn);
else if (verbose >= 2)
dump_insn(stdout, &insn);
.read_pmc = xen_read_pmc,
- .iret = xen_iret,
-
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.load_gdt = xen_load_gdt,
pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot;
pv_ops.cpu.load_gdt = xen_load_gdt_boot;
- setup_stack_canary_segment(cpu);
switch_to_new_gdt(cpu);
pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry;
/* Install Xen paravirt ops */
pv_info = xen_info;
- pv_ops.init.patch = paravirt_patch_default;
pv_ops.cpu = xen_cpu_ops;
+ paravirt_iret = xen_iret;
xen_init_irq_ops();
/*
}
}
-static const struct pv_time_ops xen_time_ops __initconst = {
- .sched_clock = xen_sched_clock,
- .steal_clock = xen_steal_clock,
-};
-
static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
static u64 xen_clock_value_saved;
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
}
-void __init xen_init_time_ops(void)
+static void __init xen_init_time_common(void)
{
xen_sched_clock_offset = xen_clocksource_read();
- pv_ops.time = xen_time_ops;
+ static_call_update(pv_steal_clock, xen_steal_clock);
+ paravirt_set_sched_clock(xen_sched_clock);
+
+ x86_platform.calibrate_tsc = xen_tsc_khz;
+ x86_platform.get_wallclock = xen_get_wallclock;
+}
+
+void __init xen_init_time_ops(void)
+{
+ xen_init_time_common();
x86_init.timers.timer_init = xen_time_init;
x86_init.timers.setup_percpu_clockev = x86_init_noop;
x86_cpuinit.setup_percpu_clockev = x86_init_noop;
- x86_platform.calibrate_tsc = xen_tsc_khz;
- x86_platform.get_wallclock = xen_get_wallclock;
/* Dom0 uses the native method to set the hardware RTC. */
if (!xen_initial_domain())
x86_platform.set_wallclock = xen_set_wallclock;
return;
}
- xen_sched_clock_offset = xen_clocksource_read();
- pv_ops.time = xen_time_ops;
+ xen_init_time_common();
+
x86_init.timers.setup_percpu_clockev = xen_time_init;
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
- x86_platform.calibrate_tsc = xen_tsc_khz;
- x86_platform.get_wallclock = xen_get_wallclock;
x86_platform.set_wallclock = xen_set_wallclock;
}
#endif
#include <linux/math64.h>
#include <linux/gfp.h>
#include <linux/slab.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
#include <asm/xen/hypervisor.h>
xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
VMASST_TYPE_runstate_update_flag);
- pv_ops.time.steal_clock = xen_steal_clock;
+ static_call_update(pv_steal_clock, xen_steal_clock);
static_key_slow_inc(¶virt_steal_enabled);
if (xen_runstate_remote)
* static_call(name)(args...);
* static_call_cond(name)(args...);
* static_call_update(name, func);
+ * static_call_query(name);
*
* Usage example:
*
*
* which will include the required value tests to avoid NULL-pointer
* dereferences.
+ *
+ * To query which function is currently set to be called, use:
+ *
+ * func = static_call_query(name);
*/
#include <linux/types.h>
STATIC_CALL_TRAMP_ADDR(name), func); \
})
+#define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func))
+
#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
extern int __init static_call_init(void);
struct static_call_site *sites;
};
-struct static_call_key {
- void *func;
- union {
- /* bit 0: 0 = mods, 1 = sites */
- unsigned long type;
- struct static_call_mod *mods;
- struct static_call_site *sites;
- };
-};
-
/* For finding the key associated with a trampoline */
struct static_call_tramp_key {
s32 tramp;
static inline int static_call_init(void) { return 0; }
-struct static_call_key {
- void *func;
-};
-
#define __DEFINE_STATIC_CALL(name, _func, _func_init) \
DECLARE_STATIC_CALL(name, _func); \
struct static_call_key STATIC_CALL_KEY(name) = { \
}; \
ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
#define static_call_cond(name) (void)__static_call(name)
static inline
static inline int static_call_init(void) { return 0; }
-struct static_call_key {
- void *func;
-};
-
static inline long __static_call_return0(void)
{
return 0;
__raw_static_call(name); \
})
+struct static_call_key {
+ void *func;
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
+};
+
#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
#define __STATIC_CALL_ADDRESSABLE(name)
#define __static_call(name) __raw_static_call(name)
+struct static_call_key {
+ void *func;
+};
+
#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
#ifdef MODULE
#else
+struct static_call_key {
+ void *func;
+};
+
#define static_call(name) \
((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+# This requires GCC 8.1 or better. Specifically, we require
+# -mstack-protector-guard-reg, added by
+# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
+
+echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
-#include "inat_types.h"
+#include "inat_types.h" /* __ignore_sync_check__ */
/*
* Internal bits. Don't use bitmasks directly, because these bits are
#include <asm/byteorder.h>
/* insn_attr_t is defined in inat.h */
-#include "inat.h"
+#include "inat.h" /* __ignore_sync_check__ */
#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN)
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
-extern void insn_get_prefixes(struct insn *insn);
-extern void insn_get_opcode(struct insn *insn);
-extern void insn_get_modrm(struct insn *insn);
-extern void insn_get_sib(struct insn *insn);
-extern void insn_get_displacement(struct insn *insn);
-extern void insn_get_immediate(struct insn *insn);
-extern void insn_get_length(struct insn *insn);
+extern int insn_get_prefixes(struct insn *insn);
+extern int insn_get_opcode(struct insn *insn);
+extern int insn_get_modrm(struct insn *insn);
+extern int insn_get_sib(struct insn *insn);
+extern int insn_get_displacement(struct insn *insn);
+extern int insn_get_immediate(struct insn *insn);
+extern int insn_get_length(struct insn *insn);
+
+enum insn_mode {
+ INSN_MODE_32,
+ INSN_MODE_64,
+ /* Mode is determined by the current kernel build. */
+ INSN_MODE_KERN,
+ INSN_NUM_MODES,
+};
+
+extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m);
+
+#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN)
/* Attribute will be determined after getting ModRM (for opcode groups) */
static inline void insn_get_attribute(struct insn *insn)
/* Instruction uses RIP-relative addressing */
extern int insn_rip_relative(struct insn *insn);
-/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn,
- const void *kaddr, int buf_len)
-{
-#ifdef CONFIG_X86_64
- insn_init(insn, kaddr, buf_len, 1);
-#else /* CONFIG_X86_32 */
- insn_init(insn, kaddr, buf_len, 0);
-#endif
-}
-
static inline int insn_is_avx(struct insn *insn)
{
if (!insn->prefixes.got)
return !!insn->emulate_prefix_size;
}
-/* Ensure this instruction is decoded completely */
-static inline int insn_complete(struct insn *insn)
-{
- return insn->opcode.got && insn->modrm.got && insn->sib.got &&
- insn->displacement.got && insn->immediate.got;
-}
-
static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
{
if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
-#include "../include/asm/insn.h"
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
/* Attribute tables are generated from opcode map */
#include "inat-tables.c"
#else
#include <string.h>
#endif
-#include "../include/asm/inat.h"
-#include "../include/asm/insn.h"
+#include "../include/asm/inat.h" /* __ignore_sync_check__ */
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
-#include "../include/asm/emulate_prefix.h"
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include "../include/asm/emulate_prefix.h" /* __ignore_sync_check__ */
#define leXX_to_cpu(t, r) \
({ \
* insn_init() - initialize struct insn
* @insn: &struct insn to be initialized
* @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
* @x86_64: !0 for 64-bit kernel or 64-bit app
*/
void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
* Populates the @insn->prefixes bitmap, and updates @insn->next_byte
* to point to the (first) opcode. No effect if @insn->prefixes.got
* is already set.
+ *
+ * * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_prefixes(struct insn *insn)
+int insn_get_prefixes(struct insn *insn)
{
struct insn_field *prefixes = &insn->prefixes;
insn_attr_t attr;
int i, nb;
if (prefixes->got)
- return;
+ return 0;
insn_get_emulate_prefix(insn);
prefixes->got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
/**
* If necessary, first collects any preceding (prefix) bytes.
* Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got
* is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_opcode(struct insn *insn)
+int insn_get_opcode(struct insn *insn)
{
struct insn_field *opcode = &insn->opcode;
+ int pfx_id, ret;
insn_byte_t op;
- int pfx_id;
+
if (opcode->got)
- return;
- if (!insn->prefixes.got)
- insn_get_prefixes(insn);
+ return 0;
+
+ if (!insn->prefixes.got) {
+ ret = insn_get_prefixes(insn);
+ if (ret)
+ return ret;
+ }
/* Get first opcode */
op = get_next(insn_byte_t, insn);
insn->attr = inat_get_avx_attribute(op, m, p);
if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
(!inat_accept_vex(insn->attr) &&
- !inat_is_group(insn->attr)))
- insn->attr = 0; /* This instruction is bad */
- goto end; /* VEX has only 1 byte for opcode */
+ !inat_is_group(insn->attr))) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ /* VEX has only 1 byte for opcode */
+ goto end;
}
insn->attr = inat_get_opcode_attribute(op);
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
}
- if (inat_must_vex(insn->attr))
- insn->attr = 0; /* This instruction is bad */
+
+ if (inat_must_vex(insn->attr)) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
end:
opcode->got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
* Populates @insn->modrm and updates @insn->next_byte to point past the
* ModRM byte, if any. If necessary, first collects the preceding bytes
* (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_modrm(struct insn *insn)
+int insn_get_modrm(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
insn_byte_t pfx_id, mod;
+ int ret;
+
if (modrm->got)
- return;
- if (!insn->opcode.got)
- insn_get_opcode(insn);
+ return 0;
+
+ if (!insn->opcode.got) {
+ ret = insn_get_opcode(insn);
+ if (ret)
+ return ret;
+ }
if (inat_has_modrm(insn->attr)) {
mod = get_next(insn_byte_t, insn);
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_group_attribute(mod, pfx_id,
insn->attr);
- if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
- insn->attr = 0; /* This is bad */
+ if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) {
+ /* Bad insn */
+ insn->attr = 0;
+ return -EINVAL;
+ }
}
}
if (insn->x86_64 && inat_is_force64(insn->attr))
insn->opnd_bytes = 8;
+
modrm->got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
int insn_rip_relative(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
+ int ret;
if (!insn->x86_64)
return 0;
- if (!modrm->got)
- insn_get_modrm(insn);
+
+ if (!modrm->got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return 0;
+ }
/*
* For rip-relative instructions, the mod field (top 2 bits)
* is zero and the r/m field (bottom 3 bits) is 0x5.
*
* If necessary, first collects the instruction up to and including the
* ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
*/
-void insn_get_sib(struct insn *insn)
+int insn_get_sib(struct insn *insn)
{
insn_byte_t modrm;
+ int ret;
if (insn->sib.got)
- return;
- if (!insn->modrm.got)
- insn_get_modrm(insn);
+ return 0;
+
+ if (!insn->modrm.got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+ }
+
if (insn->modrm.nbytes) {
modrm = insn->modrm.bytes[0];
if (insn->addr_bytes != 2 &&
}
insn->sib.got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
* If necessary, first collects the instruction up to and including the
* SIB byte.
* Displacement value is sign-expanded.
+ *
+ * * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
*/
-void insn_get_displacement(struct insn *insn)
+int insn_get_displacement(struct insn *insn)
{
insn_byte_t mod, rm, base;
+ int ret;
if (insn->displacement.got)
- return;
- if (!insn->sib.got)
- insn_get_sib(insn);
+ return 0;
+
+ if (!insn->sib.got) {
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
+ }
+
if (insn->modrm.nbytes) {
/*
* Interpreting the modrm byte:
}
out:
insn->displacement.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/* Decode moffset16/32/64. Return 0 if failed */
}
/**
- * insn_get_immediate() - Get the immediates of instruction
+ * insn_get_immediate() - Get the immediate in an instruction
* @insn: &struct insn containing instruction
*
* If necessary, first collects the instruction up to and including the
* displacement bytes.
* Basically, most of immediates are sign-expanded. Unsigned-value can be
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_immediate(struct insn *insn)
+int insn_get_immediate(struct insn *insn)
{
+ int ret;
+
if (insn->immediate.got)
- return;
- if (!insn->displacement.got)
- insn_get_displacement(insn);
+ return 0;
+
+ if (!insn->displacement.got) {
+ ret = insn_get_displacement(insn);
+ if (ret)
+ return ret;
+ }
if (inat_has_moffset(insn->attr)) {
if (!__get_moffset(insn))
}
done:
insn->immediate.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
*
* If necessary, first collects the instruction up to and including the
* immediates bytes.
- */
-void insn_get_length(struct insn *insn)
+ *
+ * Returns:
+ * - 0 on success
+ * - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
{
+ int ret;
+
if (insn->length)
- return;
- if (!insn->immediate.got)
- insn_get_immediate(insn);
+ return 0;
+
+ if (!insn->immediate.got) {
+ ret = insn_get_immediate(insn);
+ if (ret)
+ return ret;
+ }
+
insn->length = (unsigned char)((unsigned long)insn->next_byte
- (unsigned long)insn->kaddr);
+
+ return 0;
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+ return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+ insn->displacement.got && insn->immediate.got;
+}
+
+/**
+ * insn_decode() - Decode an x86 instruction
+ * @insn: &struct insn to be initialized
+ * @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
+ * @m: insn mode, see enum insn_mode
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m)
+{
+ int ret;
+
+#define INSN_MODE_KERN (enum insn_mode)-1 /* __ignore_sync_check__ mode is only valid in the kernel */
+
+ if (m == INSN_MODE_KERN)
+ insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64));
+ else
+ insn_init(insn, kaddr, buf_len, m == INSN_MODE_64);
+
+ ret = insn_get_length(insn);
+ if (ret)
+ return ret;
+
+ if (insn_complete(insn))
+ return 0;
+
+ return -EINVAL;
}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_KCONFIG_H
+#define _TOOLS_LINUX_KCONFIG_H
+
+/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define __BIG_ENDIAN 4321
+#else
+#define __LITTLE_ENDIAN 1234
+#endif
+
+#define __ARG_PLACEHOLDER_1 0,
+#define __take_second_arg(__ignored, val, ...) val
+
+/*
+ * The use of "&&" / "||" is limited in certain expressions.
+ * The following enable to calculate "and" / "or" with macro expansion only.
+ */
+#define __and(x, y) ___and(x, y)
+#define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y)
+#define ____and(arg1_or_junk, y) __take_second_arg(arg1_or_junk y, 0)
+
+#define __or(x, y) ___or(x, y)
+#define ___or(x, y) ____or(__ARG_PLACEHOLDER_##x, y)
+#define ____or(arg1_or_junk, y) __take_second_arg(arg1_or_junk 1, y)
+
+/*
+ * Helper macros to use CONFIG_ options in C/CPP expressions. Note that
+ * these only work with boolean and tristate options.
+ */
+
+/*
+ * Getting something that works in C and CPP for an arg that may or may
+ * not be defined is tricky. Here, if we have "#define CONFIG_BOOGER 1"
+ * we match on the placeholder define, insert the "0," for arg1 and generate
+ * the triplet (0, 1, 0). Then the last step cherry picks the 2nd arg (a one).
+ * When CONFIG_BOOGER is not defined, we generate a (... 1, 0) pair, and when
+ * the last step cherry picks the 2nd arg, we get a zero.
+ */
+#define __is_defined(x) ___is_defined(x)
+#define ___is_defined(val) ____is_defined(__ARG_PLACEHOLDER_##val)
+#define ____is_defined(arg1_or_junk) __take_second_arg(arg1_or_junk 1, 0)
+
+/*
+ * IS_BUILTIN(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y', 0
+ * otherwise. For boolean options, this is equivalent to
+ * IS_ENABLED(CONFIG_FOO).
+ */
+#define IS_BUILTIN(option) __is_defined(option)
+
+/*
+ * IS_MODULE(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'm', 0
+ * otherwise.
+ */
+#define IS_MODULE(option) __is_defined(option##_MODULE)
+
+/*
+ * IS_REACHABLE(CONFIG_FOO) evaluates to 1 if the currently compiled
+ * code can call a function defined in code compiled based on CONFIG_FOO.
+ * This is similar to IS_ENABLED(), but returns false when invoked from
+ * built-in code when CONFIG_FOO is set to 'm'.
+ */
+#define IS_REACHABLE(option) __or(IS_BUILTIN(option), \
+ __and(IS_MODULE(option), __is_defined(MODULE)))
+
+/*
+ * IS_ENABLED(CONFIG_FOO) evaluates to 1 if CONFIG_FOO is set to 'y' or 'm',
+ * 0 otherwise.
+ */
+#define IS_ENABLED(option) __or(IS_BUILTIN(option), IS_MODULE(option))
+
+#endif /* _TOOLS_LINUX_KCONFIG_H */
__raw_static_call(name); \
})
+struct static_call_key {
+ void *func;
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
+};
+
#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
#define __STATIC_CALL_ADDRESSABLE(name)
#define __static_call(name) __raw_static_call(name)
+struct static_call_key {
+ void *func;
+};
+
#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
#ifdef MODULE
#else
+struct static_call_key {
+ void *func;
+};
+
#define static_call(name) \
((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
struct list_head *ops_list)
{
struct insn insn;
- int x86_64, sign;
+ int x86_64, sign, ret;
unsigned char op1, op2, rex = 0, rex_b = 0, rex_r = 0, rex_w = 0,
rex_x = 0, modrm = 0, modrm_mod = 0, modrm_rm = 0,
modrm_reg = 0, sib = 0;
if (x86_64 == -1)
return -1;
- insn_init(&insn, sec->data->d_buf + offset, maxlen, x86_64);
- insn_get_length(&insn);
-
- if (!insn_complete(&insn)) {
+ ret = insn_decode(&insn, sec->data->d_buf + offset, maxlen,
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret < 0) {
WARN("can't decode instruction at %s:0x%lx", sec->name, offset);
return -1;
}
arch/x86/lib/x86-opcode-map.txt
arch/x86/tools/gen-insn-attr-x86.awk
include/linux/static_call_types.h
-arch/x86/include/asm/inat.h -I '^#include [\"<]\(asm/\)*inat_types.h[\">]'
-arch/x86/include/asm/insn.h -I '^#include [\"<]\(asm/\)*inat.h[\">]'
-arch/x86/lib/inat.c -I '^#include [\"<]\(../include/\)*asm/insn.h[\">]'
-arch/x86/lib/insn.c -I '^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]' -I '^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]'
"
+
+SYNC_CHECK_FILES='
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/insn.h
+arch/x86/lib/inat.c
+arch/x86/lib/insn.c
+'
fi
check_2 () {
done <<EOF
$FILES
EOF
+
+if [ "$SRCARCH" = "x86" ]; then
+ for i in $SYNC_CHECK_FILES; do
+ check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+ done
+fi
static int test_data_item(struct test_data *dat, int x86_64)
{
struct intel_pt_insn intel_pt_insn;
+ int op, branch, ret;
struct insn insn;
- int op, branch;
- insn_init(&insn, dat->data, MAX_INSN_SIZE, x86_64);
- insn_get_length(&insn);
-
- if (!insn_complete(&insn)) {
+ ret = insn_decode(&insn, dat->data, MAX_INSN_SIZE,
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret < 0) {
pr_debug("Failed to decode: %s\n", dat->asm_rep);
return -1;
}
struct machine *machine)
{
struct insn insn;
- int len;
+ int len, ret;
bool is64bit = false;
if (!sample->ip)
len = thread__memcpy(thread, machine, sample->insn, sample->ip, sizeof(sample->insn), &is64bit);
if (len <= 0)
return;
- insn_init(&insn, sample->insn, len, is64bit);
- insn_get_length(&insn);
- if (insn_complete(&insn) && insn.length <= len)
+
+ ret = insn_decode(&insn, sample->insn, len,
+ is64bit ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret >= 0 && insn.length <= len)
sample->insn_len = insn.length;
}
include/uapi/asm-generic/unistd.h
'
+SYNC_CHECK_FILES='
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/insn.h
+arch/x86/lib/inat.c
+arch/x86/lib/insn.c
+'
+
# These copies are under tools/perf/trace/beauty/ as they are not used to in
# building object files only by scripts in tools/perf/trace/beauty/ to generate
# tables that then gets included in .c files for things like id->string syscall
check $i -B
done
+for i in $SYNC_CHECK_FILES; do
+ check $i '-I "^.*\/\*.*__ignore_sync_check__.*\*\/.*$"'
+done
+
# diff with extra ignore lines
check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
check include/linux/ctype.h '-I "isdigit("'
check lib/ctype.c '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
-check arch/x86/include/asm/inat.h '-I "^#include [\"<]\(asm/\)*inat_types.h[\">]"'
-check arch/x86/include/asm/insn.h '-I "^#include [\"<]\(asm/\)*inat.h[\">]"'
-check arch/x86/lib/inat.c '-I "^#include [\"<]\(../include/\)*asm/insn.h[\">]"'
-check arch/x86/lib/insn.c '-I "^#include [\"<]\(../include/\)*asm/in\(at\|sn\).h[\">]" -I "^#include [\"<]\(../include/\)*asm/emulate_prefix.h[\">]"'
# diff non-symmetric files
check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
struct intel_pt_insn *intel_pt_insn)
{
struct insn insn;
+ int ret;
- insn_init(&insn, buf, len, x86_64);
- insn_get_length(&insn);
- if (!insn_complete(&insn) || insn.length > len)
+ ret = insn_decode(&insn, buf, len,
+ x86_64 ? INSN_MODE_64 : INSN_MODE_32);
+ if (ret < 0 || insn.length > len)
return -1;
+
intel_pt_insn_decoder(&insn, intel_pt_insn);
if (insn.length < INTEL_PT_INSN_BUF_SZ)
memcpy(intel_pt_insn->buf, buf, insn.length);
u8 *inbuf, int inlen, int *lenp)
{
struct insn insn;
- int n, i;
+ int n, i, ret;
int left;
- insn_init(&insn, inbuf, inlen, x->is64bit);
- insn_get_length(&insn);
- if (!insn_complete(&insn) || insn.length > inlen)
+ ret = insn_decode(&insn, inbuf, inlen,
+ x->is64bit ? INSN_MODE_64 : INSN_MODE_32);
+
+ if (ret < 0 || insn.length > inlen)
return "<bad>";
if (lenp)
*lenp = insn.length;