summaryrefslogtreecommitdiff
path: root/arch/x86/entry
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/calling.h34
-rw-r--r--arch/x86/entry/entry_32.S3
-rw-r--r--arch/x86/entry/entry_64.S153
-rw-r--r--arch/x86/entry/entry_64_compat.S71
4 files changed, 154 insertions, 107 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index dce7092ab24a..be63330c5511 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -97,7 +97,7 @@ For 32-bit we have the following conventions - kernel is built with
#define SIZEOF_PTREGS 21*8
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
/*
* Push registers and sanitize registers of values that a
* speculation attack might otherwise want to exploit. The
@@ -105,32 +105,41 @@ For 32-bit we have the following conventions - kernel is built with
* could be put to use in a speculative execution gadget.
* Interleave XOR with PUSH for better uop scheduling:
*/
+ .if \save_ret
+ pushq %rsi /* pt_regs->si */
+ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */
+ movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */
+ .else
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
+ .endif
pushq \rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq \rax /* pt_regs->ax */
pushq %r8 /* pt_regs->r8 */
- xorq %r8, %r8 /* nospec r8 */
+ xorl %r8d, %r8d /* nospec r8 */
pushq %r9 /* pt_regs->r9 */
- xorq %r9, %r9 /* nospec r9 */
+ xorl %r9d, %r9d /* nospec r9 */
pushq %r10 /* pt_regs->r10 */
- xorq %r10, %r10 /* nospec r10 */
+ xorl %r10d, %r10d /* nospec r10 */
pushq %r11 /* pt_regs->r11 */
- xorq %r11, %r11 /* nospec r11*/
+ xorl %r11d, %r11d /* nospec r11*/
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx*/
pushq %rbp /* pt_regs->rbp */
xorl %ebp, %ebp /* nospec rbp*/
pushq %r12 /* pt_regs->r12 */
- xorq %r12, %r12 /* nospec r12*/
+ xorl %r12d, %r12d /* nospec r12*/
pushq %r13 /* pt_regs->r13 */
- xorq %r13, %r13 /* nospec r13*/
+ xorl %r13d, %r13d /* nospec r13*/
pushq %r14 /* pt_regs->r14 */
- xorq %r14, %r14 /* nospec r14*/
+ xorl %r14d, %r14d /* nospec r14*/
pushq %r15 /* pt_regs->r15 */
- xorq %r15, %r15 /* nospec r15*/
+ xorl %r15d, %r15d /* nospec r15*/
UNWIND_HINT_REGS
+ .if \save_ret
+ pushq %rsi /* return address on top of stack */
+ .endif
.endm
.macro POP_REGS pop_rdi=1 skip_r11rcx=0
@@ -172,12 +181,7 @@ For 32-bit we have the following conventions - kernel is built with
*/
.macro ENCODE_FRAME_POINTER ptregs_offset=0
#ifdef CONFIG_FRAME_POINTER
- .if \ptregs_offset
- leaq \ptregs_offset(%rsp), %rbp
- .else
- mov %rsp, %rbp
- .endif
- orq $0x1, %rbp
+ leaq 1+\ptregs_offset(%rsp), %rbp
#endif
.endm
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 16c2c022540d..6ad064c8cf35 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -252,8 +252,7 @@ ENTRY(__switch_to_asm)
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
- /* Clobbers %ebx */
- FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* restore callee-saved registers */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8971bd64d515..d5c7f18f79ac 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -364,8 +364,7 @@ ENTRY(__switch_to_asm)
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
- /* Clobbers %rbx */
- FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* restore callee-saved registers */
@@ -449,9 +448,19 @@ END(irq_entries_start)
*
* The invariant is that, if irq_count != -1, then the IRQ stack is in use.
*/
-.macro ENTER_IRQ_STACK regs=1 old_rsp
+.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
DEBUG_ENTRY_ASSERT_IRQS_OFF
+
+ .if \save_ret
+ /*
+ * If save_ret is set, the original stack contains one additional
+ * entry -- the return address. Therefore, move the address one
+ * entry below %rsp to \old_rsp.
+ */
+ leaq 8(%rsp), \old_rsp
+ .else
movq %rsp, \old_rsp
+ .endif
.if \regs
UNWIND_HINT_REGS base=\old_rsp
@@ -497,6 +506,15 @@ END(irq_entries_start)
.if \regs
UNWIND_HINT_REGS indirect=1
.endif
+
+ .if \save_ret
+ /*
+ * Push the return address to the stack. This return address can
+ * be found at the "real" original RSP, which was offset by 8 at
+ * the beginning of this macro.
+ */
+ pushq -8(\old_rsp)
+ .endif
.endm
/*
@@ -520,27 +538,65 @@ END(irq_entries_start)
.endm
/*
- * Interrupt entry/exit.
- *
- * Interrupt entry points save only callee clobbered registers in fast path.
+ * Interrupt entry helper function.
*
- * Entry runs with interrupts off.
+ * Entry runs with interrupts off. Stack layout at entry:
+ * +----------------------------------------------------+
+ * | regs->ss |
+ * | regs->rsp |
+ * | regs->eflags |
+ * | regs->cs |
+ * | regs->ip |
+ * +----------------------------------------------------+
+ * | regs->orig_ax = ~(interrupt number) |
+ * +----------------------------------------------------+
+ * | return address |
+ * +----------------------------------------------------+
*/
-
-/* 0(%rsp): ~(interrupt number) */
- .macro interrupt func
+ENTRY(interrupt_entry)
+ UNWIND_HINT_FUNC
+ ASM_CLAC
cld
- testb $3, CS-ORIG_RAX(%rsp)
+ testb $3, CS-ORIG_RAX+8(%rsp)
jz 1f
SWAPGS
- call switch_to_thread_stack
+
+ /*
+ * Switch to the thread stack. The IRET frame and orig_ax are
+ * on the stack, as well as the return address. RDI..R12 are
+ * not (yet) on the stack and space has not (yet) been
+ * allocated for them.
+ */
+ pushq %rdi
+
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /*
+ * We have RDI, return address, and orig_ax on the stack on
+ * top of the IRET frame. That means offset=24
+ */
+ UNWIND_HINT_IRET_REGS base=%rdi offset=24
+
+ pushq 7*8(%rdi) /* regs->ss */
+ pushq 6*8(%rdi) /* regs->rsp */
+ pushq 5*8(%rdi) /* regs->eflags */
+ pushq 4*8(%rdi) /* regs->cs */
+ pushq 3*8(%rdi) /* regs->ip */
+ pushq 2*8(%rdi) /* regs->orig_ax */
+ pushq 8(%rdi) /* return address */
+ UNWIND_HINT_FUNC
+
+ movq (%rdi), %rdi
1:
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
- testb $3, CS(%rsp)
+ testb $3, CS+8(%rsp)
jz 1f
/*
@@ -548,7 +604,7 @@ END(irq_entries_start)
*
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
- * (which can take locks). Since TRACE_IRQS_OFF idempotent,
+ * (which can take locks). Since TRACE_IRQS_OFF is idempotent,
* the simplest way to handle it is to just call it twice if
* we enter from user mode. There's no reason to optimize this since
* TRACE_IRQS_OFF is a no-op if lockdep is off.
@@ -558,12 +614,15 @@ END(irq_entries_start)
CALL_enter_from_user_mode
1:
- ENTER_IRQ_STACK old_rsp=%rdi
+ ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
- call \func /* rdi points to pt_regs */
- .endm
+ ret
+END(interrupt_entry)
+
+
+/* Interrupt entry/exit. */
/*
* The interrupt stubs push (~vector+0x80) onto the stack and
@@ -571,9 +630,10 @@ END(irq_entries_start)
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
- ASM_CLAC
addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
- interrupt do_IRQ
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call do_IRQ /* rdi points to pt_regs */
/* 0(%rsp): old RSP */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_ANY)
@@ -766,10 +826,11 @@ END(common_interrupt)
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
UNWIND_HINT_IRET_REGS
- ASM_CLAC
pushq $~(\num)
.Lcommon_\sym:
- interrupt \do_sym
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call \do_sym /* rdi points to pt_regs */
jmp ret_from_intr
END(\sym)
.endm
@@ -832,34 +893,6 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
*/
#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
-/*
- * Switch to the thread stack. This is called with the IRET frame and
- * orig_ax on the stack. (That is, RDI..R12 are not on the stack and
- * space has not been allocated for them.)
- */
-ENTRY(switch_to_thread_stack)
- UNWIND_HINT_FUNC
-
- pushq %rdi
- /* Need to switch before accessing the thread stack. */
- SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
- movq %rsp, %rdi
- movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
-
- pushq 7*8(%rdi) /* regs->ss */
- pushq 6*8(%rdi) /* regs->rsp */
- pushq 5*8(%rdi) /* regs->eflags */
- pushq 4*8(%rdi) /* regs->cs */
- pushq 3*8(%rdi) /* regs->ip */
- pushq 2*8(%rdi) /* regs->orig_ax */
- pushq 8(%rdi) /* return address */
- UNWIND_HINT_FUNC
-
- movq (%rdi), %rdi
- ret
-END(switch_to_thread_stack)
-
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
UNWIND_HINT_IRET_REGS offset=\has_error_code*8
@@ -875,12 +908,8 @@ ENTRY(\sym)
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
- /* Save all registers in pt_regs */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
-
.if \paranoid < 2
- testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */
jnz .Lfrom_usermode_switch_stack_\@
.endif
@@ -1130,13 +1159,15 @@ idtentry machine_check do_mce has_error_code=0 paranoid=1
#endif
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch gs if needed.
* Use slow, but surefire "are we in kernel?" check.
* Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(paranoid_entry)
UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
movl $1, %ebx
movl $MSR_GS_BASE, %ecx
rdmsr
@@ -1181,12 +1212,14 @@ ENTRY(paranoid_exit)
END(paranoid_exit)
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch GS if needed.
* Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
- UNWIND_HINT_REGS offset=8
+ UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
@@ -1577,8 +1610,6 @@ end_repeat_nmi:
* frame to point back to repeat_nmi.
*/
pushq $-1 /* ORIG_RAX: no syscall to restart */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
/*
* Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index fd65e016e413..e811dd9c5e99 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -85,25 +85,25 @@ ENTRY(entry_SYSENTER_compat)
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
pushq $0 /* pt_regs->r8 = 0 */
- xorq %r8, %r8 /* nospec r8 */
+ xorl %r8d, %r8d /* nospec r8 */
pushq $0 /* pt_regs->r9 = 0 */
- xorq %r9, %r9 /* nospec r9 */
+ xorl %r9d, %r9d /* nospec r9 */
pushq $0 /* pt_regs->r10 = 0 */
- xorq %r10, %r10 /* nospec r10 */
+ xorl %r10d, %r10d /* nospec r10 */
pushq $0 /* pt_regs->r11 = 0 */
- xorq %r11, %r11 /* nospec r11 */
+ xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
pushq %rbp /* pt_regs->rbp (will be overwritten) */
xorl %ebp, %ebp /* nospec rbp */
pushq $0 /* pt_regs->r12 = 0 */
- xorq %r12, %r12 /* nospec r12 */
+ xorl %r12d, %r12d /* nospec r12 */
pushq $0 /* pt_regs->r13 = 0 */
- xorq %r13, %r13 /* nospec r13 */
+ xorl %r13d, %r13d /* nospec r13 */
pushq $0 /* pt_regs->r14 = 0 */
- xorq %r14, %r14 /* nospec r14 */
+ xorl %r14d, %r14d /* nospec r14 */
pushq $0 /* pt_regs->r15 = 0 */
- xorq %r15, %r15 /* nospec r15 */
+ xorl %r15d, %r15d /* nospec r15 */
cld
/*
@@ -224,25 +224,25 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
pushq %rbp /* pt_regs->cx (stashed in bp) */
pushq $-ENOSYS /* pt_regs->ax */
pushq $0 /* pt_regs->r8 = 0 */
- xorq %r8, %r8 /* nospec r8 */
+ xorl %r8d, %r8d /* nospec r8 */
pushq $0 /* pt_regs->r9 = 0 */
- xorq %r9, %r9 /* nospec r9 */
+ xorl %r9d, %r9d /* nospec r9 */
pushq $0 /* pt_regs->r10 = 0 */
- xorq %r10, %r10 /* nospec r10 */
+ xorl %r10d, %r10d /* nospec r10 */
pushq $0 /* pt_regs->r11 = 0 */
- xorq %r11, %r11 /* nospec r11 */
+ xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
pushq %rbp /* pt_regs->rbp (will be overwritten) */
xorl %ebp, %ebp /* nospec rbp */
pushq $0 /* pt_regs->r12 = 0 */
- xorq %r12, %r12 /* nospec r12 */
+ xorl %r12d, %r12d /* nospec r12 */
pushq $0 /* pt_regs->r13 = 0 */
- xorq %r13, %r13 /* nospec r13 */
+ xorl %r13d, %r13d /* nospec r13 */
pushq $0 /* pt_regs->r14 = 0 */
- xorq %r14, %r14 /* nospec r14 */
+ xorl %r14d, %r14d /* nospec r14 */
pushq $0 /* pt_regs->r15 = 0 */
- xorq %r15, %r15 /* nospec r15 */
+ xorl %r15d, %r15d /* nospec r15 */
/*
* User mode is traced as though IRQs are on, and SYSENTER
@@ -298,9 +298,9 @@ sysret32_from_system_call:
*/
SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
- xorq %r8, %r8
- xorq %r9, %r9
- xorq %r10, %r10
+ xorl %r8d, %r8d
+ xorl %r9d, %r9d
+ xorl %r10d, %r10d
swapgs
sysretl
END(entry_SYSCALL_compat)
@@ -347,10 +347,23 @@ ENTRY(entry_INT80_compat)
*/
movl %eax, %eax
+ /* switch to thread stack expects orig_ax and rdi to be pushed */
pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ pushq 6*8(%rdi) /* regs->ss */
+ pushq 5*8(%rdi) /* regs->rsp */
+ pushq 4*8(%rdi) /* regs->eflags */
+ pushq 3*8(%rdi) /* regs->cs */
+ pushq 2*8(%rdi) /* regs->ip */
+ pushq 1*8(%rdi) /* regs->orig_ax */
- /* switch to thread stack expects orig_ax to be pushed */
- call switch_to_thread_stack
+ movq (%rdi), %rdi /* restore %rdi */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
@@ -358,25 +371,25 @@ ENTRY(entry_INT80_compat)
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
pushq $0 /* pt_regs->r8 = 0 */
- xorq %r8, %r8 /* nospec r8 */
+ xorl %r8d, %r8d /* nospec r8 */
pushq $0 /* pt_regs->r9 = 0 */
- xorq %r9, %r9 /* nospec r9 */
+ xorl %r9d, %r9d /* nospec r9 */
pushq $0 /* pt_regs->r10 = 0 */
- xorq %r10, %r10 /* nospec r10 */
+ xorl %r10d, %r10d /* nospec r10 */
pushq $0 /* pt_regs->r11 = 0 */
- xorq %r11, %r11 /* nospec r11 */
+ xorl %r11d, %r11d /* nospec r11 */
pushq %rbx /* pt_regs->rbx */
xorl %ebx, %ebx /* nospec rbx */
pushq %rbp /* pt_regs->rbp */
xorl %ebp, %ebp /* nospec rbp */
pushq %r12 /* pt_regs->r12 */
- xorq %r12, %r12 /* nospec r12 */
+ xorl %r12d, %r12d /* nospec r12 */
pushq %r13 /* pt_regs->r13 */
- xorq %r13, %r13 /* nospec r13 */
+ xorl %r13d, %r13d /* nospec r13 */
pushq %r14 /* pt_regs->r14 */
- xorq %r14, %r14 /* nospec r14 */
+ xorl %r14d, %r14d /* nospec r14 */
pushq %r15 /* pt_regs->r15 */
- xorq %r15, %r15 /* nospec r15 */
+ xorl %r15d, %r15d /* nospec r15 */
cld
/*
generated by cgit v1.2.3-70-g09d2 (git 2.47.1) at 2024-12-26 07:36:57 +0000