edac: edac_mc_handle_error(): add an error_count parameter

In order to avoid loosing error events, it is desirable to group error events together and generate a single trace for several identical errors. The trace API already allows reporting multiple errors. Change the handle_error function to also allow that. The changes at the drivers were made by this small script: $file .=$_ while (<>); $file =~ s/(edac_mc_handle_error)\s*\(([^\,]+)\,([^\,]+)\,/$1($2,$3, 1,/g; print $file; Signed-off-by: Mauro Carvalho Chehab <[email protected]>
rtvt123 · Jun 12, 2012 · 9eb07a7 · 9eb07a7
1 parent 03f7eae
commit 9eb07a7
Show file tree

Hide file tree

Showing 28 changed files with 104 additions and 95 deletions.
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
@@ -1046,7 +1046,7 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 	if (!src_mci) {
 		amd64_mc_err(mci, "failed to map error addr 0x%lx to a node\n",
 			     (unsigned long)sys_addr);
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     page, offset, syndrome,
 				     -1, -1, -1,
 				     "failed to map error addr to a node",
@@ -1057,7 +1057,7 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 	/* Now map the sys_addr to a CSROW */
 	csrow = sys_addr_to_csrow(src_mci, sys_addr);
 	if (csrow < 0) {
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     page, offset, syndrome,
 				     -1, -1, -1,
 				     "failed to map error addr to a csrow",
@@ -1077,7 +1077,7 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 			amd64_mc_warn(src_mci, "unknown syndrome 0x%04x - "
 				      "possible error reporting race\n",
 				      syndrome);
-			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 					     page, offset, syndrome,
 					     csrow, -1, -1,
 					     "unknown syndrome - possible error reporting race",
@@ -1096,7 +1096,7 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 		channel = ((sys_addr & BIT(3)) != 0);
 	}
 
-	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, src_mci,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, src_mci, 1,
 			     page, offset, syndrome,
 			     csrow, channel, -1,
 			     "", "");
@@ -1608,7 +1608,7 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 	csrow = f1x_translate_sysaddr_to_cs(pvt, sys_addr, &nid, &chan);
 
 	if (csrow < 0) {
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     page, offset, syndrome,
 				     -1, -1, -1,
 				     "failed to map error addr to a csrow",
@@ -1624,7 +1624,7 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
 	if (dct_ganging_enabled(pvt))
 		chan = get_channel_from_ecc_syndrome(mci, syndrome);
 
-	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 			     page, offset, syndrome,
 			     csrow, chan, -1,
 			     "", "");
@@ -1909,7 +1909,7 @@ static void amd64_handle_ce(struct mem_ctl_info *mci, struct mce *m)
 	/* Ensure that the Error Address is VALID */
 	if (!(m->status & MCI_STATUS_ADDRV)) {
 		amd64_mc_err(mci, "HW has no ERROR_ADDRESS available\n");
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     0, 0, 0,
 				     -1, -1, -1,
 				     "HW has no ERROR_ADDRESS available",
@@ -1937,7 +1937,7 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
 
 	if (!(m->status & MCI_STATUS_ADDRV)) {
 		amd64_mc_err(mci, "HW has no ERROR_ADDRESS available\n");
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     0, 0, 0,
 				     -1, -1, -1,
 				     "HW has no ERROR_ADDRESS available",
@@ -1956,7 +1956,7 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
 	if (!src_mci) {
 		amd64_mc_err(mci, "ERROR ADDRESS (0x%lx) NOT mapped to a MC\n",
 				  (unsigned long)sys_addr);
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     page, offset, 0,
 				     -1, -1, -1,
 				     "ERROR ADDRESS NOT mapped to a MC",
@@ -1970,13 +1970,13 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
 	if (csrow < 0) {
 		amd64_mc_err(mci, "ERROR_ADDRESS (0x%lx) NOT mapped to CS\n",
 				  (unsigned long)sys_addr);
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     page, offset, 0,
 				     -1, -1, -1,
 				     "ERROR ADDRESS NOT mapped to CS",
 				     "");
 	} else {
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 				     page, offset, 0,
 				     csrow, -1, -1,
 				     "", "");

diff --git a/drivers/edac/amd76x_edac.c b/drivers/edac/amd76x_edac.c
@@ -145,7 +145,7 @@ static int amd76x_process_error_info(struct mem_ctl_info *mci,
 
 		if (handle_errors) {
 			row = (info->ecc_mode_status >> 4) & 0xf;
-			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+			edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 					     mci->csrows[row]->first_page, 0, 0,
 					     row, 0, -1,
 					     mci->ctl_name, "");
@@ -160,7 +160,7 @@ static int amd76x_process_error_info(struct mem_ctl_info *mci,
 
 		if (handle_errors) {
 			row = info->ecc_mode_status & 0xf;
-			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+			edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 					     mci->csrows[row]->first_page, 0, 0,
 					     row, 0, -1,
 					     mci->ctl_name, "");

diff --git a/drivers/edac/cell_edac.c b/drivers/edac/cell_edac.c
@@ -48,7 +48,7 @@ static void cell_edac_count_ce(struct mem_ctl_info *mci, int chan, u64 ar)
 	syndrome = (ar & 0x000000001fe00000ul) >> 21;
 
 	/* TODO: Decoding of the error address */
-	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 			     csrow->first_page + pfn, offset, syndrome,
 			     0, chan, -1, "", "");
 }
@@ -70,7 +70,7 @@ static void cell_edac_count_ue(struct mem_ctl_info *mci, int chan, u64 ar)
 	offset = address & ~PAGE_MASK;
 
 	/* TODO: Decoding of the error address */
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 			     csrow->first_page + pfn, offset, 0,
 			     0, chan, -1, "", "");
 }

diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c
@@ -554,15 +554,15 @@ static void cpc925_mc_check(struct mem_ctl_info *mci)
 	if (apiexcp & CECC_EXCP_DETECTED) {
 		cpc925_mc_printk(mci, KERN_INFO, "DRAM CECC Fault\n");
 		channel = cpc925_mc_find_channel(mci, syndrome);
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     pfn, offset, syndrome,
 				     csrow, channel, -1,
 				     mci->ctl_name, "");
 	}
 
 	if (apiexcp & UECC_EXCP_DETECTED) {
 		cpc925_mc_printk(mci, KERN_INFO, "DRAM UECC Fault\n");
-		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 				     pfn, offset, 0,
 				     csrow, -1, -1,
 				     mci->ctl_name, "");

diff --git a/drivers/edac/e752x_edac.c b/drivers/edac/e752x_edac.c
@@ -371,7 +371,7 @@ static void do_process_ce(struct mem_ctl_info *mci, u16 error_one,
 	channel = !(error_one & 1);
 
 	/* e752x mc reads 34:6 of the DRAM linear address */
-	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
 			     page, offset_in_page(sec1_add << 4), sec1_syndrome,
 			     row, channel, -1,
 			     "e752x CE", "");
@@ -408,7 +408,7 @@ static void do_process_ue(struct mem_ctl_info *mci, u16 error_one,
 			edac_mc_find_csrow_by_page(mci, block_page);
 
 		/* e752x mc reads 34:6 of the DRAM linear address */
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 					block_page,
 					offset_in_page(error_2b << 4), 0,
 					 row, -1, -1,
@@ -427,7 +427,7 @@ static void do_process_ue(struct mem_ctl_info *mci, u16 error_one,
 			edac_mc_find_csrow_by_page(mci, block_page);
 
 		/* e752x mc reads 34:6 of the DRAM linear address */
-		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
 					block_page,
 					offset_in_page(error_2b << 4), 0,
 					row, -1, -1,
@@ -454,7 +454,7 @@ static inline void process_ue_no_info_wr(struct mem_ctl_info *mci,
 		return;
 
 	edac_dbg(3, "\n");
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 0, 0, 0,
+	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0,
 			     -1, -1, -1,
 			     "e752x UE log memory write", "");
 }

diff --git a/drivers/edac/e7xxx_edac.c b/drivers/edac/e7xxx_edac.c
@@ -219,14 +219,14 @@ static void process_ce(struct mem_ctl_info *mci, struct e7xxx_error_info *info)
 	row = edac_mc_find_csrow_by_page(mci, page);
 	/* convert syndrome to channel */
 	channel = e7xxx_find_channel(syndrome);
-	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, page, 0, syndrome,
+	edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1, page, 0, syndrome,
 			     row, channel, -1, "e7xxx CE", "");
 }
 
 static void process_ce_no_info(struct mem_ctl_info *mci)
 {
 	edac_dbg(3, "\n");
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 0, 0, 0, -1, -1, -1,
+	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
 			     "e7xxx CE log register overflow", "");
 }
 
@@ -242,15 +242,15 @@ static void process_ue(struct mem_ctl_info *mci, struct e7xxx_error_info *info)
 	block_page = error_2b >> 6;	/* convert to 4k address */
 	row = edac_mc_find_csrow_by_page(mci, block_page);
 
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, block_page, 0, 0,
+	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, block_page, 0, 0,
 			     row, -1, -1, "e7xxx UE", "");
 }
 
 static void process_ue_no_info(struct mem_ctl_info *mci)
 {
 	edac_dbg(3, "\n");
 
-	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 0, 0, 0, -1, -1, -1,
+	edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1, 0, 0, 0, -1, -1, -1,
 			     "e7xxx UE log register overflow", "");
 }
 

diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
@@ -455,6 +455,7 @@ extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
 				      unsigned long page);
 void edac_mc_handle_error(const enum hw_event_mc_err_type type,
 			  struct mem_ctl_info *mci,
+			  const u16 error_count,
 			  const unsigned long page_frame_number,
 			  const unsigned long offset_in_page,
 			  const unsigned long syndrome,