| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210831175025.27570-12-jiangshanlai@gmail.com>
Date: Wed, 1 Sep 2021 01:50:12 +0800
From: Lai Jiangshan <jiangshanlai@...il.com>
To: linux-kernel@...r.kernel.org
Cc: Lai Jiangshan <laijs@...ux.alibaba.com>,
Andy Lutomirski <luto@...nel.org>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
Joerg Roedel <jroedel@...e.de>,
Youquan Song <youquan.song@...el.com>,
Tony Luck <tony.luck@...el.com>
Subject: [PATCH 11/24] x86/entry: Replace the most of asm code of error_entry to C code
From: Lai Jiangshan <laijs@...ux.alibaba.com>
All the needed facilities are set in traps.c, the major body of
error_entry() can be implemented in C in traps.c. The C version
generally has better readibility and easier to be updated/improved.
No function change intended.
Signed-off-by: Lai Jiangshan <laijs@...ux.alibaba.com>
---
arch/x86/entry/entry_64.S | 71 +--------------------------------
arch/x86/entry/traps.c | 76 ++++++++++++++++++++++++++++++++++++
arch/x86/include/asm/traps.h | 1 +
3 files changed, 78 insertions(+), 70 deletions(-)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 42d2918f5646..bc9e2f5ad370 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -972,83 +972,14 @@ SYM_CODE_START_LOCAL(error_entry)
cld
PUSH_AND_CLEAR_REGS save_ret=1
ENCODE_FRAME_POINTER 8
- 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
-
-.Lerror_entry_from_usermode_after_swapgs:
- /* Put us onto the real thread stack. */
popq %r12 /* save return addr in %12 */
movq %rsp, %rdi /* arg0 = pt_regs pointer */
- call sync_regs
+ call do_error_entry
movq %rax, %rsp /* switch stack */
ENCODE_FRAME_POINTER
pushq %r12
ret
-
-.Lerror_entry_done_lfence:
- FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
- 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
- FENCE_SWAPGS_USER_ENTRY
- jmp .Lerror_entry_done
-
-.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.
- */
- popq %r12 /* save return addr in %12 */
- movq %rsp, %rdi /* arg0 = pt_regs pointer */
- call fixup_bad_iret
- mov %rax, %rsp
- ENCODE_FRAME_POINTER
- pushq %r12
- jmp .Lerror_entry_from_usermode_after_swapgs
SYM_CODE_END(error_entry)
SYM_CODE_START_LOCAL(error_return)
diff --git a/arch/x86/entry/traps.c b/arch/x86/entry/traps.c
index c718663e57ef..b8fdf6a9682f 100644
--- a/arch/x86/entry/traps.c
+++ b/arch/x86/entry/traps.c
@@ -804,6 +804,82 @@ static __always_inline void fence_swapgs_kernel_entry(void)
{
alternative("", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL);
}
+
+/*
+ * Put pt_regs onto the task stack and switch GS and CR3 if needed.
+ * The actual stack switch is done in entry_64.S.
+ *
+ * Becareful, it might be in the user CR3 and user GS base at the start
+ * of the function.
+ */
+asmlinkage __visible __entry_text
+struct pt_regs *do_error_entry(struct pt_regs *eregs)
+{
+ unsigned long iret_ip = (unsigned long)native_irq_return_iret;
+
+ /*
+ * When XENPV, it is already in the task stack, and it can't fault
+ * from native_irq_return_iret and asm_load_gs_index_gs_change()
+ * since XENPV uses its own pvops for iret and load_gs_index.
+ * So it can directly return.
+ */
+ if (static_cpu_has(X86_FEATURE_XENPV))
+ return eregs;
+
+ if (user_mode(eregs)) {
+ /*
+ * We entered from user mode.
+ * Switch to kernel gsbase and CR3.
+ */
+ native_swapgs();
+ fence_swapgs_user_entry();
+ 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:
+ */
+ native_swapgs();
+ fence_swapgs_user_entry();
+ 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();
+ fence_swapgs_user_entry();
+ } else {
+ fence_swapgs_kernel_entry();
+ }
+
+ /* Enter from kernel, don't move pt_regs */
+ return eregs;
+}
#endif
static bool is_sysenter_singlestep(struct pt_regs *regs)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index e9e3801391d5..7b51a8081ae4 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 *do_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
Powered by blists - more mailing lists