All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tony Luck <tony.luck@intel.com>
To: Borislav Petkov <bp@alien8.de>
Cc: linux-kernel@vger.kernel.org, linux-edac@vger.kernel.org, x86@kernel.org
Subject: [PATCH 2/3] x86, ras: Extend machine check recovery code to annotated ring0 areas
Date: Fri, 6 Nov 2015 13:01:55 -0800	[thread overview]
Message-ID: <e916478b9587ef006b30255a7adbee6d84268d7c.1447093568.git.tony.luck@intel.com> (raw)
In-Reply-To: <cover.1447093568.git.tony.luck@intel.com>

Extend the severity checking code to add a new context IN_KERN_RECOV
which is used to indicate that the machine check was triggered by code
in the kernel with a fixup entry.

Add code to check for this situation and respond by altering the return
IP to the fixup address and changing the regs->ax so that the recovery
code knows the physical address of the error. Note that we also set bit
63 because 0x0 is a legal physical address.

Signed-off-by: Tony Luck <tony.luck@intel.com>
---
 arch/x86/kernel/cpu/mcheck/mce-severity.c | 19 +++++++++++++++++--
 arch/x86/kernel/cpu/mcheck/mce.c          | 13 ++++++++++---
 2 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 9c682c222071..1e83842310e8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/debugfs.h>
 #include <asm/mce.h>
 
@@ -29,7 +30,7 @@
  * panic situations)
  */
 
-enum context { IN_KERNEL = 1, IN_USER = 2 };
+enum context { IN_KERNEL = 1, IN_USER = 2, IN_KERNEL_RECOV = 3 };
 enum ser { SER_REQUIRED = 1, NO_SER = 2 };
 enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
 
@@ -48,6 +49,7 @@ static struct severity {
 #define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c }
 #define  KERNEL		.context = IN_KERNEL
 #define  USER		.context = IN_USER
+#define  KERNEL_RECOV	.context = IN_KERNEL_RECOV
 #define  SER		.ser = SER_REQUIRED
 #define  NOSER		.ser = NO_SER
 #define  EXCP		.excp = EXCP_CONTEXT
@@ -87,6 +89,10 @@ static struct severity {
 		EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
 		),
 	MCESEV(
+		PANIC, "In kernel and no restart IP",
+		EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0)
+		),
+	MCESEV(
 		DEFERRED, "Deferred error",
 		NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
 		),
@@ -123,6 +129,11 @@ static struct severity {
 		MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV)
 		),
 	MCESEV(
+		AR, "Action required: data load error recoverable area of kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		KERNEL_RECOV
+		),
+	MCESEV(
 		AR, "Action required: data load error in a user process",
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
 		USER
@@ -183,7 +194,11 @@ static struct severity {
  */
 static int error_context(struct mce *m)
 {
-	return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
+	if ((m->cs & 3) == 3)
+		return IN_USER;
+	if (search_mcexception_tables(m->ip))
+		return IN_KERNEL_RECOV;
+	return IN_KERNEL;
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9d014b82a124..472d11150b7a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -31,6 +31,7 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/kmod.h>
 #include <linux/poll.h>
 #include <linux/nmi.h>
@@ -1132,9 +1133,15 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		if (no_way_out)
 			mce_panic("Fatal machine check on current CPU", &m, msg);
 		if (worst == MCE_AR_SEVERITY) {
-			recover_paddr = m.addr;
-			if (!(m.mcgstatus & MCG_STATUS_RIPV))
-				flags |= MF_MUST_KILL;
+			if ((m.cs & 3) == 3) {
+				recover_paddr = m.addr;
+				if (!(m.mcgstatus & MCG_STATUS_RIPV))
+					flags |= MF_MUST_KILL;
+			} else if (fixup_mcexception(regs)) {
+				regs->ax = BIT(63) | m.addr;
+			} else
+				mce_panic("Failed kernel mode recovery",
+					  &m, NULL);
 		} else if (kill_it) {
 			force_sig(SIGBUS, current);
 		}
-- 
2.1.4


  parent reply	other threads:[~2015-11-09 18:41 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-09 18:26 [RFC PATCH 0/3] Machine check recovery when kernel accesses poison Tony Luck
2015-11-06 20:57 ` [PATCH 1/3] x86, ras: Add new infrastructure for machine check fixup tables Tony Luck
2015-11-10 11:21   ` Borislav Petkov
2015-11-10 22:05     ` Luck, Tony
2015-11-12  4:14   ` Andy Lutomirski
2015-11-12 19:44     ` Luck, Tony
2015-11-12 20:04       ` Andy Lutomirski
2015-11-12 21:17         ` Luck, Tony
2015-11-06 21:01 ` Tony Luck [this message]
2015-11-10 11:21   ` [PATCH 2/3] x86, ras: Extend machine check recovery code to annotated ring0 areas Borislav Petkov
2015-11-10 22:11     ` Luck, Tony
2015-11-11 11:01       ` Borislav Petkov
2015-11-12  4:19   ` Andy Lutomirski
2015-11-12 19:55     ` Luck, Tony
2015-11-06 21:08 ` [PATCH 3/3] x86, ras: Add mcsafe_memcpy() function to recover from machine checks Tony Luck
2015-11-12  7:53   ` Ingo Molnar
2015-11-12 20:01     ` Luck, Tony
2015-11-27 10:16       ` Ingo Molnar
2015-12-08 21:30         ` Dan Williams
2015-12-08 22:08           ` Luck, Tony
2015-12-08 22:08             ` Luck, Tony
2015-12-14  9:55           ` Ingo Molnar
2015-11-09 18:48 ` [RFC PATCH 0/3] Machine check recovery when kernel accesses poison Tony Luck
2015-11-10 11:21 ` Borislav Petkov
2015-11-10 21:55   ` Luck, Tony
2015-11-11 20:41     ` Borislav Petkov
2015-11-11 21:48       ` Luck, Tony
2015-11-11 22:28         ` Borislav Petkov
2015-11-11 22:32           ` Luck, Tony

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e916478b9587ef006b30255a7adbee6d84268d7c.1447093568.git.tony.luck@intel.com \
    --to=tony.luck@intel.com \
    --cc=bp@alien8.de \
    --cc=linux-edac@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.