summaryrefslogtreecommitdiffstats
path: root/arch/ia64/kernel/mca.c
diff options
context:
space:
mode:
authorRuss Anderson <rja@sgi.com>2006-03-24 09:49:52 -0800
committerTony Luck <tony.luck@intel.com>2006-03-24 09:49:52 -0800
commitd2a28ad9fa7bf16761d070d8a3338375e1574b32 (patch)
tree9da2c18c91a4ee12fa6a9b2d23dcb55d13dd0ca8 /arch/ia64/kernel/mca.c
parenta5b00bb4fe60796c791238cf5653b82110031c93 (diff)
[IA64] MCA recovery: kernel context recovery table
Memory errors encountered by user applications may surface when the CPU is running in kernel context. The current code will not attempt recovery if the MCA surfaces in kernel context (privilage mode 0). This patch adds a check for cases where the user initiated the load that surfaces in kernel interrupt code. An example is a user process lauching a load from memory and the data in memory had bad ECC. Before the bad data gets to the CPU register, and interrupt comes in. The code jumps to the IVT interrupt entry point and begins execution in kernel context. The process of saving the user registers (SAVE_REST) causes the bad data to be loaded into a CPU register, triggering the MCA. The MCA surfaces in kernel context, even though the load was initiated from user context. As suggested by David and Tony, this patch uses an exception table like approach, puting the tagged recovery addresses in a searchable table. One difference from the exception table is that MCAs do not surface in precise places (such as with a TLB miss), so instead of tagging specific instructions, address ranges are registers. A single macro is used to do the tagging, with the input parameter being the label of the starting address and the macro being the ending address. This limits clutter in the code. This patch only tags one spot, the interrupt ivt entry. Testing showed that spot to be a "heavy hitter" with MCAs surfacing while saving user registers. Other spots can be added as needed by adding a single macro. Signed-off-by: Russ Anderson (rja@sgi.com) Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch/ia64/kernel/mca.c')
-rw-r--r--arch/ia64/kernel/mca.c98
1 files changed, 73 insertions, 25 deletions
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index cedcae713e9..87ff7fe33cf 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -83,6 +83,7 @@
#include <asm/irq.h>
#include <asm/hw_irq.h>
+#include "mca_drv.h"
#include "entry.h"
#if defined(IA64_MCA_DEBUG_INFO)
@@ -281,6 +282,50 @@ ia64_mca_log_sal_error_record(int sal_info_type)
ia64_sal_clear_state_info(sal_info_type);
}
+/*
+ * search_mca_table
+ * See if the MCA surfaced in an instruction range
+ * that has been tagged as recoverable.
+ *
+ * Inputs
+ * first First address range to check
+ * last Last address range to check
+ * ip Instruction pointer, address we are looking for
+ *
+ * Return value:
+ * 1 on Success (in the table)/ 0 on Failure (not in the table)
+ */
+int
+search_mca_table (const struct mca_table_entry *first,
+ const struct mca_table_entry *last,
+ unsigned long ip)
+{
+ const struct mca_table_entry *curr;
+ u64 curr_start, curr_end;
+
+ curr = first;
+ while (curr <= last) {
+ curr_start = (u64) &curr->start_addr + curr->start_addr;
+ curr_end = (u64) &curr->end_addr + curr->end_addr;
+
+ if ((ip >= curr_start) && (ip <= curr_end)) {
+ return 1;
+ }
+ curr++;
+ }
+ return 0;
+}
+
+/* Given an address, look for it in the mca tables. */
+int mca_recover_range(unsigned long addr)
+{
+ extern struct mca_table_entry __start___mca_table[];
+ extern struct mca_table_entry __stop___mca_table[];
+
+ return search_mca_table(__start___mca_table, __stop___mca_table-1, addr);
+}
+EXPORT_SYMBOL_GPL(mca_recover_range);
+
#ifdef CONFIG_ACPI
int cpe_vector = -1;
@@ -747,31 +792,34 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
ia64_mca_modify_comm(previous_current);
goto no_mod;
}
- if (r13 != sos->prev_IA64_KR_CURRENT) {
- msg = "inconsistent previous current and r13";
- goto no_mod;
- }
- if ((r12 - r13) >= KERNEL_STACK_SIZE) {
- msg = "inconsistent r12 and r13";
- goto no_mod;
- }
- if ((ar_bspstore - r13) >= KERNEL_STACK_SIZE) {
- msg = "inconsistent ar.bspstore and r13";
- goto no_mod;
- }
- va.p = old_bspstore;
- if (va.f.reg < 5) {
- msg = "old_bspstore is in the wrong region";
- goto no_mod;
- }
- if ((ar_bsp - r13) >= KERNEL_STACK_SIZE) {
- msg = "inconsistent ar.bsp and r13";
- goto no_mod;
- }
- size += (ia64_rse_skip_regs(old_bspstore, slots) - old_bspstore) * 8;
- if (ar_bspstore + size > r12) {
- msg = "no room for blocked state";
- goto no_mod;
+
+ if (!mca_recover_range(ms->pmsa_iip)) {
+ if (r13 != sos->prev_IA64_KR_CURRENT) {
+ msg = "inconsistent previous current and r13";
+ goto no_mod;
+ }
+ if ((r12 - r13) >= KERNEL_STACK_SIZE) {
+ msg = "inconsistent r12 and r13";
+ goto no_mod;
+ }
+ if ((ar_bspstore - r13) >= KERNEL_STACK_SIZE) {
+ msg = "inconsistent ar.bspstore and r13";
+ goto no_mod;
+ }
+ va.p = old_bspstore;
+ if (va.f.reg < 5) {
+ msg = "old_bspstore is in the wrong region";
+ goto no_mod;
+ }
+ if ((ar_bsp - r13) >= KERNEL_STACK_SIZE) {
+ msg = "inconsistent ar.bsp and r13";
+ goto no_mod;
+ }
+ size += (ia64_rse_skip_regs(old_bspstore, slots) - old_bspstore) * 8;
+ if (ar_bspstore + size > r12) {
+ msg = "no room for blocked state";
+ goto no_mod;
+ }
}
ia64_mca_modify_comm(previous_current);