Commit-ID: af104e394e17e328df85c25a9e21448539725b67
Gitweb: http://git.kernel.org/tip/af104e394e17e328df85c25a9e21448539725b67
Author: Tony Luck <tony.luck@xxxxxxxxx>
AuthorDate: Wed, 14 Dec 2011 15:55:20 -0800
Committer: Tony Luck <tony.luck@xxxxxxxxx>
CommitDate: Tue, 3 Jan 2012 12:06:53 -0800
x86/mce: Add mechanism to safely save information in MCE handler
Machine checks on Intel cpus interrupt execution on all cpus, regardless
of interrupt masking. We have a need to save some data about the cause
of the machine check (physical address) in the machine check handler that
can be retrieved later to attempt recovery in a more flexible execution
state.
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---
arch/x86/kernel/cpu/mcheck/mce.c | 43 ++++++++++++++++++++++++++++++++++++++
1 files changed, 43 insertions(+), 0 deletions(-)
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 2f1c200..e1579c5 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -887,6 +887,49 @@ static void mce_clear_state(unsigned long *toclear)
}
/*
+ * Need to save faulting physical address associated with a process
+ * in the machine check handler some place where we can grab it back
+ * later in mce_notify_process()
+ */
+#define MCE_INFO_MAX 16
+
+struct mce_info {
+ atomic_t inuse;
+ struct task_struct *t;
+ __u64 paddr;
+} mce_info[MCE_INFO_MAX];
+
+static void mce_save_info(__u64 addr)
+{
+ struct mce_info *mi;
+
+ for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) {
+ if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
+ mi->t = current;
+ mi->paddr = addr;
+ return;
+ }
+ }
+
+ mce_panic("Too many concurrent recoverable errors", NULL, NULL);
+}
+
+static struct mce_info *mce_find_info(void)
+{
+ struct mce_info *mi;
+
+ for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++)
+ if (atomic_read(&mi->inuse) && mi->t == current)
+ return mi;
+ return NULL;
+}
+
+static void mce_clear_info(struct mce_info *mi)
+{
+ atomic_set(&mi->inuse, 0);
+}
+
+/*
* The actual machine check handler. This only handles real
* exceptions when something got corrupted coming in through int 18.
*
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|