[PATCH V6 23/49] x86/entry: Implement the whole error_entry() as C code

From: Lai Jiangshan
Date: Fri Nov 26 2021 - 05:25:34 EST


From: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>

All the needed facilities are set in entry64.c, the whole error_entry()
can be implemented in C in entry64.c. The C version generally has better
readability and easier to be updated/improved.

No function change intended.

Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>
---
arch/x86/entry/entry64.c | 68 ++++++++++++++++++++++++++++++
arch/x86/entry/entry_64.S | 82 +-----------------------------------
arch/x86/include/asm/traps.h | 1 +
3 files changed, 70 insertions(+), 81 deletions(-)

diff --git a/arch/x86/entry/entry64.c b/arch/x86/entry/entry64.c
index 3db503ea0703..0dc63ae8153a 100644
--- a/arch/x86/entry/entry64.c
+++ b/arch/x86/entry/entry64.c
@@ -68,3 +68,71 @@ static __always_inline void user_entry_swapgs_and_fence(void)
native_swapgs();
fence_swapgs_user_entry();
}
+
+/*
+ * Put pt_regs onto the task stack and switch GS and CR3 if needed.
+ * The actual stack switch is done in entry_64.S.
+ *
+ * Be careful, it might be in the user CR3 and user GS base at the start
+ * of the function.
+ */
+asmlinkage __visible __entry_text
+struct pt_regs *error_entry(struct pt_regs *eregs)
+{
+ unsigned long iret_ip = (unsigned long)native_irq_return_iret;
+
+ if (user_mode(eregs)) {
+ /*
+ * We entered from user mode.
+ * Switch to kernel gsbase and CR3.
+ */
+ user_entry_swapgs_and_fence();
+ switch_to_kernel_cr3();
+
+ /* Put pt_regs onto the task stack. */
+ return sync_regs(eregs);
+ }
+
+ /*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
+ */
+ if ((eregs->ip == iret_ip) || (eregs->ip == (unsigned int)iret_ip)) {
+ eregs->ip = iret_ip; /* Fix truncated RIP */
+
+ /*
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
+ */
+ user_entry_swapgs_and_fence();
+ switch_to_kernel_cr3();
+
+ /*
+ * Pretend that the exception came from user mode: set up
+ * pt_regs as if we faulted immediately after IRET and put
+ * pt_regs onto the real task stack.
+ */
+ return sync_regs(fixup_bad_iret(eregs));
+ }
+
+ /*
+ * Hack: asm_load_gs_index_gs_change can fail with user gsbase.
+ * If this happens, fix up gsbase and proceed. We'll fix up the
+ * exception and land in asm_load_gs_index_gs_change's error
+ * handler with kernel gsbase.
+ */
+ if (eregs->ip == (unsigned long)asm_load_gs_index_gs_change)
+ native_swapgs();
+
+ /*
+ * The above code has no serializing instruction. So do an lfence
+ * to prevent GS speculation, regardless of whether it is kernel
+ * gsbase or user gsbase.
+ */
+ fence_swapgs_kernel_entry();
+
+ /* Enter from kernel, don't move pt_regs */
+ return eregs;
+}
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 4d88cd0c46c6..16b2215bdb23 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -333,7 +333,7 @@ SYM_CODE_END(ret_from_fork)
* XENPV uses its own pvops for iret and load_gs_index(). And it
* doesn't need to switch CR3. So it can skip invoking error_entry().
*/
- ALTERNATIVE "call error_entry; movq %rax, %rsp", \
+ ALTERNATIVE "movq %rsp, %rdi; call error_entry; movq %rax, %rsp", \
"", X86_FEATURE_XENPV

ENCODE_FRAME_POINTER
@@ -982,86 +982,6 @@ SYM_CODE_START_LOCAL(paranoid_exit)
jmp restore_regs_and_return_to_kernel
SYM_CODE_END(paranoid_exit)

-/*
- * Save all registers in pt_regs, and switch GS if needed.
- */
-SYM_CODE_START_LOCAL(error_entry)
- UNWIND_HINT_FUNC
- testb $3, CS+8(%rsp)
- jz .Lerror_kernelspace
-
- /*
- * We entered from user mode or we're pretending to have entered
- * from user mode due to an IRET fault.
- */
- swapgs
- FENCE_SWAPGS_USER_ENTRY
- /* We have user CR3. Change to kernel CR3. */
- SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
-
- leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */
-.Lerror_entry_from_usermode_after_swapgs:
- /* Put us onto the real thread stack. */
- call sync_regs
- ret
-
- /*
- * There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. B stepping K8s sometimes report a
- * truncated RIP for IRET exceptions returning to compat mode. Check
- * for these here too.
- */
-.Lerror_kernelspace:
- leaq native_irq_return_iret(%rip), %rcx
- cmpq %rcx, RIP+8(%rsp)
- je .Lerror_bad_iret
- movl %ecx, %eax /* zero extend */
- cmpq %rax, RIP+8(%rsp)
- je .Lbstep_iret
- cmpq $asm_load_gs_index_gs_change, RIP+8(%rsp)
- jne .Lerror_entry_done_lfence
-
- /*
- * hack: .Lgs_change can fail with user gsbase. If this happens, fix up
- * gsbase and proceed. We'll fix up the exception and land in
- * .Lgs_change's error handler with kernel gsbase.
- */
- swapgs
-
- /*
- * The above code has no serializing instruction. So do an lfence
- * to prevent GS speculation, regardless of whether it is kernel
- * gsbase or user gsbase.
- */
-.Lerror_entry_done_lfence:
- FENCE_SWAPGS_KERNEL_ENTRY
- leaq 8(%rsp), %rax /* return pt_regs pointer */
- ret
-
-.Lbstep_iret:
- /* Fix truncated RIP */
- movq %rcx, RIP+8(%rsp)
- /* fall through */
-
-.Lerror_bad_iret:
- /*
- * We came from an IRET to user mode, so we have user
- * gsbase and CR3. Switch to kernel gsbase and CR3:
- */
- swapgs
- FENCE_SWAPGS_USER_ENTRY
- SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
-
- /*
- * Pretend that the exception came from user mode: set up pt_regs
- * as if we faulted immediately after IRET.
- */
- leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */
- call fixup_bad_iret
- mov %rax, %rdi
- jmp .Lerror_entry_from_usermode_after_swapgs
-SYM_CODE_END(error_entry)
-
SYM_CODE_START_LOCAL(error_return)
UNWIND_HINT_REGS
DEBUG_ENTRY_ASSERT_IRQS_OFF
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 1cdd7e8bcba7..686461ac9803 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -14,6 +14,7 @@
asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
asmlinkage __visible notrace
struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
+asmlinkage __visible notrace struct pt_regs *error_entry(struct pt_regs *eregs);
void __init trap_init(void);
asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
#endif
--
2.19.1.6.gb485710b