Merge git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac

Pull EDAC internal API changes from Mauro Carvalho Chehab:
 "This changeset is the first part of a series of patches that fixes the
  EDAC sybsystem.  On this set, it changes the Kernel EDAC API in order
  to properly represent the Intel i3/i5/i7, Xeon 3xxx/5xxx/7xxx, and
  Intel E5-xxxx memory controllers.

  The EDAC core used to assume that:

       - the DRAM chip select pin is directly accessed by the memory
         controller

       - when multiple channels are used, they're all filled with the
         same type of memory.

  None of the above premises is true on Intel memory controllers since
  2002, when RAMBUS and FB-DIMMs were introduced, and Advanced Memory
  Buffer or by some similar technologies hides the direct access to the
  DRAM pins.

  So, the existing drivers for those chipsets had to lie to the EDAC
  core, in general telling that just one channel is filled.  That
  produces some hard to understand error messages like:

       EDAC MC0: CE row 3, channel 0, label "DIMM1": 1 Unknown error(s): memory read error on FATAL area : cpu=0 Err=0008:00c2 (ch=2), addr = 0xad1f73480 => socket=0, Channel=0(mask=2), rank=1

  The location information there (row3 channel 0) is completely bogus:
  it has no physical meaning, and are just some random values that the
  driver uses to talk with the EDAC core.  The error actually happened
  at CPU socket 0, channel 0, slot 1, but this is not reported anywhere,
  as the EDAC core doesn't know anything about the memory layout.  So,
  only advanced users that know how the EDAC driver works and that tests
  their systems to see how DIMMs are mapped can actually benefit for
  such error logs.

  This patch series fixes the error report logic, in order to allow the
  EDAC to expose the memory architecture used by them to the EDAC core.
  So, as the EDAC core now understands how the memory is organized, it
  can provide an useful report:

       EDAC MC0: CE memory read error on DIMM1 (channel:0 slot:1 page:0x364b1b offset:0x600 grain:32 syndrome:0x0 - count:1 area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:4)

  The location of the DIMM where the error happened is reported by "MC0"
  (cpu socket #0), at "channel:0 slot:1" location, and matches the
  physical location of the DIMM.

  There are two remaining issues not covered by this patch series:

       - The EDAC sysfs API will still report bogus values.  So,
         userspace tools like edac-utils will still use the bogus data;

       - Add a new tracepoint-based way to get the binary information
         about the errors.

  Those are on a second series of patches (also at -next), but will
  probably miss the train for 3.5, due to the slow review process."

Fix up trivial conflict (due to spelling correction of removed code) in
drivers/edac/edac_device.c

* git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-edac: (42 commits)
  i7core: fix ranks information at the per-channel struct
  i5000: Fix the fatal error handling
  i5100_edac: Fix a warning when compiled with 32 bits
  i82975x_edac: Test nr_pages earlier to save a few CPU cycles
  e752x_edac: provide more info about how DIMMS/ranks are mapped
  i5000_edac: Fix the logic that retrieves memory information
  i5400_edac: improve debug messages to better represent the filled memory
  edac: Cleanup the logs for i7core and sb edac drivers
  edac: Initialize the dimm label with the known information
  edac: Remove the legacy EDAC ABI
  x38_edac: convert driver to use the new edac ABI
  tile_edac: convert driver to use the new edac ABI
  sb_edac: convert driver to use the new edac ABI
  r82600_edac: convert driver to use the new edac ABI
  ppc4xx_edac: convert driver to use the new edac ABI
  pasemi_edac: convert driver to use the new edac ABI
  mv64x60_edac: convert driver to use the new edac ABI
  mpc85xx_edac: convert driver to use the new edac ABI
  i82975x_edac: convert driver to use the new edac ABI
  i82875p_edac: convert driver to use the new edac ABI
  ...

1 files changed, 44 insertions, 71 deletions

diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c
index 3bafa3bca148..97c22fd650ee 100644
--- a/drivers/edac/i7300_edac.c
+++ b/drivers/edac/i7300_edac.c
@@ -464,17 +464,14 @@ static void i7300_process_fbd_error(struct mem_ctl_info *mci)
 				FERR_FAT_FBD, error_reg);
 
 		snprintf(pvt->tmp_prt_buffer, PAGE_SIZE,
-			"FATAL (Branch=%d DRAM-Bank=%d %s "
-			"RAS=%d CAS=%d Err=0x%lx (%s))",
-			branch, bank,
-			is_wr ? "RDWR" : "RD",
-			ras, cas,
-			errors, specific);
-
-		/* Call the helper to output message */
-		edac_mc_handle_fbd_ue(mci, rank, branch << 1,
-				      (branch << 1) + 1,
-				      pvt->tmp_prt_buffer);
+			 "Bank=%d RAS=%d CAS=%d Err=0x%lx (%s))",
+			 bank, ras, cas, errors, specific);
+
+		edac_mc_handle_error(HW_EVENT_ERR_FATAL, mci, 0, 0, 0,
+				     branch, -1, rank,
+				     is_wr ? "Write error" : "Read error",
+				     pvt->tmp_prt_buffer, NULL);
+
 	}
 
 	/* read in the 1st NON-FATAL error register */
@@ -513,23 +510,14 @@ static void i7300_process_fbd_error(struct mem_ctl_info *mci)
 
 		/* Form out message */
 		snprintf(pvt->tmp_prt_buffer, PAGE_SIZE,
-			"Corrected error (Branch=%d, Channel %d), "
-			" DRAM-Bank=%d %s "
-			"RAS=%d CAS=%d, CE Err=0x%lx, Syndrome=0x%08x(%s))",
-			branch, channel,
-			bank,
-			is_wr ? "RDWR" : "RD",
-			ras, cas,
-			errors, syndrome, specific);
-
-		/*
-		 * Call the helper to output message
-		 * NOTE: Errors are reported per-branch, and not per-channel
-		 *	 Currently, we don't know how to identify the right
-		 *	 channel.
-		 */
-		edac_mc_handle_fbd_ce(mci, rank, channel,
-				      pvt->tmp_prt_buffer);
+			 "DRAM-Bank=%d RAS=%d CAS=%d, Err=0x%lx (%s))",
+			 bank, ras, cas, errors, specific);
+
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 0, 0,
+				     syndrome,
+				     branch >> 1, channel % 2, rank,
+				     is_wr ? "Write error" : "Read error",
+				     pvt->tmp_prt_buffer, NULL);
 	}
 	return;
 }
@@ -617,8 +605,7 @@ static void i7300_enable_error_reporting(struct mem_ctl_info *mci)
 static int decode_mtr(struct i7300_pvt *pvt,
 		      int slot, int ch, int branch,
 		      struct i7300_dimm_info *dinfo,
-		      struct csrow_info *p_csrow,
-		      u32 *nr_pages)
+		      struct dimm_info *dimm)
 {
 	int mtr, ans, addrBits, channel;
 
@@ -650,7 +637,6 @@ static int decode_mtr(struct i7300_pvt *pvt,
 	addrBits -= 3;	/* 8 bits per bytes */
 
 	dinfo->megabytes = 1 << addrBits;
-	*nr_pages = dinfo->megabytes << 8;
 
 	debugf2("\t\tWIDTH: x%d\n", MTR_DRAM_WIDTH(mtr));
 
@@ -663,11 +649,6 @@ static int decode_mtr(struct i7300_pvt *pvt,
 	debugf2("\t\tNUMCOL: %s\n", numcol_toString[MTR_DIMM_COLS(mtr)]);
 	debugf2("\t\tSIZE: %d MB\n", dinfo->megabytes);
 
-	p_csrow->grain = 8;
-	p_csrow->mtype = MEM_FB_DDR2;
-	p_csrow->csrow_idx = slot;
-	p_csrow->page_mask = 0;
-
 	/*
 	 * The type of error detection actually depends of the
 	 * mode of operation. When it is just one single memory chip, at
@@ -677,15 +658,18 @@ static int decode_mtr(struct i7300_pvt *pvt,
 	 * See datasheet Sections 7.3.6 to 7.3.8
 	 */
 
+	dimm->nr_pages = MiB_TO_PAGES(dinfo->megabytes);
+	dimm->grain = 8;
+	dimm->mtype = MEM_FB_DDR2;
 	if (IS_SINGLE_MODE(pvt->mc_settings_a)) {
-		p_csrow->edac_mode = EDAC_SECDED;
+		dimm->edac_mode = EDAC_SECDED;
 		debugf2("\t\tECC code is 8-byte-over-32-byte SECDED+ code\n");
 	} else {
 		debugf2("\t\tECC code is on Lockstep mode\n");
 		if (MTR_DRAM_WIDTH(mtr) == 8)
-			p_csrow->edac_mode = EDAC_S8ECD8ED;
+			dimm->edac_mode = EDAC_S8ECD8ED;
 		else
-			p_csrow->edac_mode = EDAC_S4ECD4ED;
+			dimm->edac_mode = EDAC_S4ECD4ED;
 	}
 
 	/* ask what device type on this row */
@@ -694,9 +678,9 @@ static int decode_mtr(struct i7300_pvt *pvt,
 			IS_SCRBALGO_ENHANCED(pvt->mc_settings) ?
 					    "enhanced" : "normal");
 
-		p_csrow->dtype = DEV_X8;
+		dimm->dtype = DEV_X8;
 	} else
-		p_csrow->dtype = DEV_X4;
+		dimm->dtype = DEV_X4;
 
 	return mtr;
 }
@@ -774,11 +758,10 @@ static int i7300_init_csrows(struct mem_ctl_info *mci)
 {
 	struct i7300_pvt *pvt;
 	struct i7300_dimm_info *dinfo;
-	struct csrow_info *p_csrow;
 	int rc = -ENODEV;
 	int mtr;
 	int ch, branch, slot, channel;
-	u32 last_page = 0, nr_pages;
+	struct dimm_info *dimm;
 
 	pvt = mci->pvt_info;
 
@@ -809,25 +792,23 @@ static int i7300_init_csrows(struct mem_ctl_info *mci)
 			pci_read_config_word(pvt->pci_dev_2x_0_fbd_branch[branch],
 					where,
 					&pvt->mtr[slot][branch]);
-			for (ch = 0; ch < MAX_BRANCHES; ch++) {
+			for (ch = 0; ch < MAX_CH_PER_BRANCH; ch++) {
 				int channel = to_channel(ch, branch);
 
+				dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms,
+					       mci->n_layers, branch, ch, slot);
+
 				dinfo = &pvt->dimm_info[slot][channel];
-				p_csrow = &mci->csrows[slot];
 
 				mtr = decode_mtr(pvt, slot, ch, branch,
-						 dinfo, p_csrow, &nr_pages);
+						 dinfo, dimm);
+
 				/* if no DIMMS on this row, continue */
 				if (!MTR_DIMMS_PRESENT(mtr))
 					continue;
 
-				/* Update per_csrow memory count */
-				p_csrow->nr_pages += nr_pages;
-				p_csrow->first_page = last_page;
-				last_page += nr_pages;
-				p_csrow->last_page = last_page;
-
 				rc = 0;
+
 			}
 		}
 	}
@@ -1042,10 +1023,8 @@ static int __devinit i7300_init_one(struct pci_dev *pdev,
 				    const struct pci_device_id *id)
 {
 	struct mem_ctl_info *mci;
+	struct edac_mc_layer layers[3];
 	struct i7300_pvt *pvt;
-	int num_channels;
-	int num_dimms_per_channel;
-	int num_csrows;
 	int rc;
 
 	/* wake up device */
@@ -1062,23 +1041,17 @@ static int __devinit i7300_init_one(struct pci_dev *pdev,
 	if (PCI_FUNC(pdev->devfn) != 0)
 		return -ENODEV;
 
-	/* As we don't have a motherboard identification routine to determine
-	 * actual number of slots/dimms per channel, we thus utilize the
-	 * resource as specified by the chipset. Thus, we might have
-	 * have more DIMMs per channel than actually on the mobo, but this
-	 * allows the driver to support up to the chipset max, without
-	 * some fancy mobo determination.
-	 */
-	num_dimms_per_channel = MAX_SLOTS;
-	num_channels = MAX_CHANNELS;
-	num_csrows = MAX_SLOTS * MAX_CHANNELS;
-
-	debugf0("MC: %s(): Number of - Channels= %d  DIMMS= %d  CSROWS= %d\n",
-		__func__, num_channels, num_dimms_per_channel, num_csrows);
-
 	/* allocate a new MC control structure */
-	mci = edac_mc_alloc(sizeof(*pvt), num_csrows, num_channels, 0);
-
+	layers[0].type = EDAC_MC_LAYER_BRANCH;
+	layers[0].size = MAX_BRANCHES;
+	layers[0].is_virt_csrow = false;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = MAX_CH_PER_BRANCH;
+	layers[1].is_virt_csrow = true;
+	layers[2].type = EDAC_MC_LAYER_SLOT;
+	layers[2].size = MAX_SLOTS;
+	layers[2].is_virt_csrow = true;
+	mci = edac_mc_alloc(0, ARRAY_SIZE(layers), layers, sizeof(*pvt));
 	if (mci == NULL)
 		return -ENOMEM;