x86/sev: Mark the code returning to user space as syscall gap

When returning to user space, %rsp is user-controlled value.

If it is a SNP-guest and the hypervisor decides to mess with the
code-page for this path while a CPU is executing it, a potential #VC
could hit in the syscall return path and mislead the #VC handler.

So make ip_within_syscall_gap() return true in this case.

Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20220412124909.10467-1-jiangshanlai@gmail.com

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f7bd800..2fd8a5c 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -215,8 +215,10 @@ syscall_return_via_sysret:
 
        popq    %rdi
        popq    %rsp
+SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
        swapgs
        sysretq
+SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*

diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 4fdb007..3c0e149 100644 (file)
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -297,6 +297,7 @@ sysret32_from_system_call:
         * code.  We zero R8-R10 to avoid info leaks.
          */
        movq    RSP-ORIG_RAX(%rsp), %rsp
+SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
 
        /*
         * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
@@ -314,6 +315,7 @@ sysret32_from_system_call:
        xorl    %r10d, %r10d
        swapgs
        sysretl
+SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 SYM_CODE_END(entry_SYSCALL_compat)
 
 /*

diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index feed36d..f042cfc 100644 (file)
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -13,6 +13,8 @@ void syscall_init(void);
 #ifdef CONFIG_X86_64
 void entry_SYSCALL_64(void);
 void entry_SYSCALL_64_safe_stack(void);
+void entry_SYSRETQ_unsafe_stack(void);
+void entry_SYSRETQ_end(void);
 long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2);
 #endif
 
@@ -28,6 +30,8 @@ void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
+void entry_SYSRETL_compat_unsafe_stack(void);
+void entry_SYSRETL_compat_end(void);
 void entry_INT80_compat(void);
 #ifdef CONFIG_XEN_PV
 void xen_entry_INT80_compat(void);

diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 4357e0f..f4db78b 100644 (file)
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -186,9 +186,13 @@ static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs)
        bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
                    regs->ip <  (unsigned long)entry_SYSCALL_64_safe_stack);
 
+       ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack &&
+                     regs->ip <  (unsigned long)entry_SYSRETQ_end);
 #ifdef CONFIG_IA32_EMULATION
        ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
                      regs->ip <  (unsigned long)entry_SYSCALL_compat_safe_stack);
+       ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack &&
+                     regs->ip <  (unsigned long)entry_SYSRETL_compat_end);
 #endif
 
        return ret;