[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>

6 files changed, 109 insertions, 41 deletions

diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index dcd906fe574..829a43cab79 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -865,6 +865,7 @@ ENTRY(interrupt)
 	;;
 	SAVE_REST
 	;;
+	MCA_RECOVER_RANGE(interrupt)
 	alloc r14=ar.pfs,0,0,2,0 // must be first in an insn group
 	mov out0=cr.ivr		// pass cr.ivr as first arg
 	add out1=16,sp		// pass pointer to pt_regs as second arg
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);
diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c
index e883d85906d..37c88eb5587 100644
--- a/arch/ia64/kernel/mca_drv.c
+++ b/arch/ia64/kernel/mca_drv.c
@@ -6,6 +6,7 @@
  * Copyright (C) Hidetoshi Seto (seto.hidetoshi@jp.fujitsu.com)
  * Copyright (C) 2005 Silicon Graphics, Inc
  * Copyright (C) 2005 Keith Owens <kaos@sgi.com>
+ * Copyright (C) 2006 Russ Anderson <rja@sgi.com>
  */
 #include <linux/config.h>
 #include <linux/types.h>
@@ -121,11 +122,12 @@ mca_page_isolate(unsigned long paddr)
  */
 
 void
-mca_handler_bh(unsigned long paddr)
+mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr)
 {
-	printk(KERN_ERR
-		"OS_MCA: process [pid: %d](%s) encounters MCA (paddr=%lx)\n",
-		current->pid, current->comm, paddr);
+	printk(KERN_ERR "OS_MCA: process [cpu %d, pid: %d, uid: %d, "
+		"iip: %p, psr: 0x%lx,paddr: 0x%lx](%s) encounters MCA.\n",
+		raw_smp_processor_id(), current->pid, current->uid,
+		iip, ipsr, paddr, current->comm);
 
 	spin_lock(&mca_bh_lock);
 	switch (mca_page_isolate(paddr)) {
@@ -442,21 +444,26 @@ recover_from_read_error(slidx_table_t *slidx,
 	if (!peidx_bottom(peidx) || !(peidx_bottom(peidx)->valid.minstate))
 		return 0;
 	psr1 =(struct ia64_psr *)&(peidx_minstate_area(peidx)->pmsa_ipsr);
+	psr2 =(struct ia64_psr *)&(peidx_minstate_area(peidx)->pmsa_xpsr);
 
 	/*
 	 *  Check the privilege level of interrupted context.
 	 *   If it is user-mode, then terminate affected process.
 	 */
-	if (psr1->cpl != 0) {
+
+	pmsa = sos->pal_min_state;
+	if (psr1->cpl != 0 ||
+	   ((psr2->cpl != 0) && mca_recover_range(pmsa->pmsa_iip))) {
 		smei = peidx_bus_check(peidx, 0);
 		if (smei->valid.target_identifier) {
 			/*
 			 *  setup for resume to bottom half of MCA,
 			 * "mca_handler_bhhook"
 			 */
-			pmsa = sos->pal_min_state;
-			/* pass to bhhook as 1st argument (gr8) */
+			/* pass to bhhook as argument (gr8, ...) */
 			pmsa->pmsa_gr[8-1] = smei->target_identifier;
+			pmsa->pmsa_gr[9-1] = pmsa->pmsa_iip;
+			pmsa->pmsa_gr[10-1] = pmsa->pmsa_ipsr;
 			/* set interrupted return address (but no use) */
 			pmsa->pmsa_br0 = pmsa->pmsa_iip;
 			/* change resume address to bottom half */
@@ -466,6 +473,7 @@ recover_from_read_error(slidx_table_t *slidx,
 			psr2 = (struct ia64_psr *)&pmsa->pmsa_ipsr;
 			psr2->cpl = 0;
 			psr2->ri  = 0;
+			psr2->bn  = 1;
 			psr2->i  = 0;
 
 			return 1;
diff --git a/arch/ia64/kernel/mca_drv.h b/arch/ia64/kernel/mca_drv.h
index e2f6fa1e0ef..31a2e52bb16 100644
--- a/arch/ia64/kernel/mca_drv.h
+++ b/arch/ia64/kernel/mca_drv.h
@@ -111,3 +111,10 @@ typedef struct slidx_table {
 	slidx_foreach_entry(__pos, &((slidx)->sec)) { __count++; }\
 	__count; })
 
+struct mca_table_entry {
+	int start_addr;	/* location-relative starting address of MCA recoverable range */
+	int end_addr;	/* location-relative ending address of MCA recoverable range */
+};
+
+extern const struct mca_table_entry *search_mca_tables (unsigned long addr);
+extern int mca_recover_range(unsigned long);
diff --git a/arch/ia64/kernel/mca_drv_asm.S b/arch/ia64/kernel/mca_drv_asm.S
index 3f298ee4d00..e6a580d354b 100644
--- a/arch/ia64/kernel/mca_drv_asm.S
+++ b/arch/ia64/kernel/mca_drv_asm.S
@@ -14,15 +14,12 @@
 
 GLOBAL_ENTRY(mca_handler_bhhook)
 	invala				// clear RSE ?
-	;;
 	cover
 	;;
 	clrrrb
 	;;						
-	alloc	r16=ar.pfs,0,2,1,0	// make a new frame
-	;;
+	alloc	r16=ar.pfs,0,2,3,0	// make a new frame
 	mov	ar.rsc=0
-	;;
 	mov	r13=IA64_KR(CURRENT)	// current task pointer
 	;;
 	mov	r2=r13
@@ -30,7 +27,6 @@ GLOBAL_ENTRY(mca_handler_bhhook)
 	addl	r22=IA64_RBS_OFFSET,r2
 	;;
 	mov	ar.bspstore=r22
-	;;
 	addl	sp=IA64_STK_OFFSET-IA64_PT_REGS_SIZE,r2
 	;;
 	adds	r2=IA64_TASK_THREAD_ON_USTACK_OFFSET,r13
@@ -40,12 +36,12 @@ GLOBAL_ENTRY(mca_handler_bhhook)
 	movl	loc1=mca_handler_bh	// recovery C function
 	;;
 	mov	out0=r8			// poisoned address
+	mov	out1=r9			// iip
+	mov	out2=r10		// psr
 	mov	b6=loc1
 	;;
 	mov	loc1=rp
-	;;
-	ssm	psr.i
-	;;
+	ssm	psr.i | psr.ic
 	br.call.sptk.many rp=b6		// does not return ...
 	;;
 	mov	ar.pfs=loc0
@@ -53,5 +49,4 @@ GLOBAL_ENTRY(mca_handler_bhhook)
 	;;
 	mov	r8=r0
 	br.ret.sptk.many rp
-	;;
 END(mca_handler_bhhook)
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 632d65cc068..0b9e56dd7f0 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -130,6 +130,15 @@ SECTIONS
 	  __initcall_end = .;
 	}
 
+  /* MCA table */
+  . = ALIGN(16);
+  __mca_table : AT(ADDR(__mca_table) - LOAD_OFFSET)
+	{
+	  __start___mca_table = .;
+	  *(__mca_table)
+	  __stop___mca_table = .;
+	}
+
   .data.patch.vtop : AT(ADDR(.data.patch.vtop) - LOAD_OFFSET)
 	{
 	  __start___vtop_patchlist = .;