[PATCH v2 7/7] x86/mce: Decode a kernel instruction to determine if it is copying from user

[Tony Luck]

All instructions copying data between kernel and user memory
are tagged with either _ASM_EXTABLE_UA or _ASM_EXTABLE_CPY
entries in the exception table. ex_fault_handler_type() returns
EX_HANDLER_UACCESS for both of these.

Recovery is only possible when the machine check was triggered
on a read from user memory. In this case the same strategy for
recovery applies as if the user had made the access in ring3. If
the fault was in kernel memory while copying to user we do not
currently have a recovery plan.

For MOV and MOVZ instructions a full decode of the instruction
is done to find the source address. For MOVS instructions
the source address is in the %rsi register. The function
fault_in_kernel_space() determines whether the source address is
kernel or user.

Co-developed-by: Youquan Song <youquan.song@xxxxxxxxx>
Signed-off-by: Youquan Song <youquan.song@xxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/kernel/cpu/mce/core.c     | 11 +++++--
 arch/x86/kernel/cpu/mce/severity.c | 51 +++++++++++++++++++++++++++++-
 2 files changed, 58 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 9713825e6745..60bacf6e0501 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1236,14 +1236,19 @@ static void kill_me_maybe(struct callback_head *cb)
 	if (!p->mce_ripv)
 		flags |= MF_MUST_KILL;
 
-	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags)) {
+	if (!memory_failure(p->mce_addr >> PAGE_SHIFT, flags) &&
+	    !(p->mce_kflags & MCE_IN_KERNEL_COPYIN)) {
 		set_mce_nospec(p->mce_addr >> PAGE_SHIFT, p->mce_whole_page);
 		sync_core();
 		return;
 	}
 
-	pr_err("Memory error not recovered");
-	kill_me_now(cb);
+	if (p->mce_vaddr != (void __user *)~0ul) {
+		force_sig_mceerr(BUS_MCEERR_AR, p->mce_vaddr, PAGE_SHIFT);
+	} else {
+		pr_err("Memory error not recovered");
+		kill_me_now(cb);
+	}
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c
index 8517cbf7b184..6e8b38cf52d9 100644
--- a/arch/x86/kernel/cpu/mce/severity.c
+++ b/arch/x86/kernel/cpu/mce/severity.c
@@ -10,6 +10,9 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <asm/mce.h>
+#include <asm/traps.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
@@ -198,6 +201,45 @@ static struct severity {
 #define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \
 				(MCG_STATUS_RIPV|MCG_STATUS_EIPV))
 
+static bool is_copy_from_user(struct pt_regs *regs)
+{
+	u8 insn_buf[MAX_INSN_SIZE];
+	struct insn insn;
+	unsigned long addr;
+
+	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)
+		return false;
+
+	switch (insn.opcode.value) {
+	/* MOV mem,reg */
+	case 0x8A: case 0x8B:
+	/* MOVZ mem,reg */
+	case 0xB60F: case 0xB70F:
+		insn_get_modrm(&insn);
+		insn_get_sib(&insn);
+		addr = (unsigned long)insn_get_addr_ref(&insn, regs);
+		break;
+	/* REP MOVS */
+	case 0xA4: case 0xA5:
+		addr = regs->si;
+		break;
+	default:
+		return false;
+	}
+
+	if (fault_in_kernel_space(addr))
+		return false;
+
+	current->mce_vaddr = (void __user *)addr;
+
+	return true;
+}
+
 /*
  * If mcgstatus indicated that ip/cs on the stack were
  * no good, then "m->cs" will be zero and we will have
@@ -215,10 +257,17 @@ static int error_context(struct mce *m, struct pt_regs *regs)
 
 	if ((m->cs & 3) == 3)
 		return IN_USER;
+	if (!mc_recoverable(m->mcgstatus))
+		return IN_KERNEL;
 
 	t = ex_fault_handler_type(m->ip);
-	if (mc_recoverable(m->mcgstatus) && t == EX_HANDLER_FAULT) {
+	if (t == EX_HANDLER_FAULT) {
+		m->kflags |= MCE_IN_KERNEL_RECOV;
+		return IN_KERNEL_RECOV;
+	}
+	if (t == EX_HANDLER_UACCESS && regs && is_copy_from_user(regs)) {
 		m->kflags |= MCE_IN_KERNEL_RECOV;
+		m->kflags |= MCE_IN_KERNEL_COPYIN;
 		return IN_KERNEL_RECOV;
 	}
 
-- 
2.21.1