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, 160 insertions, 22 deletions

diff --git a/include/linux/edac.h b/include/linux/edac.h
index c621d762bb2..91ba3bae42e 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -71,6 +71,25 @@ enum dev_type {
 #define DEV_FLAG_X64		BIT(DEV_X64)
 
 /**
+ * enum hw_event_mc_err_type - type of the detected error
+ *
+ * @HW_EVENT_ERR_CORRECTED:	Corrected Error - Indicates that an ECC
+ *				corrected error was detected
+ * @HW_EVENT_ERR_UNCORRECTED:	Uncorrected Error - Indicates an error that
+ *				can't be corrected by ECC, but it is not
+ *				fatal (maybe it is on an unused memory area,
+ *				or the memory controller could recover from
+ *				it for example, by re-trying the operation).
+ * @HW_EVENT_ERR_FATAL:		Fatal Error - Uncorrected error that could not
+ *				be recovered.
+ */
+enum hw_event_mc_err_type {
+	HW_EVENT_ERR_CORRECTED,
+	HW_EVENT_ERR_UNCORRECTED,
+	HW_EVENT_ERR_FATAL,
+};
+
+/**
  * enum mem_type - memory types. For a more detailed reference, please see
  *			http://en.wikipedia.org/wiki/DRAM
  *
@@ -313,38 +332,141 @@ enum scrub_type {
  */
 
 /**
+ * enum edac_mc_layer - memory controller hierarchy layer
+ *
+ * @EDAC_MC_LAYER_BRANCH:	memory layer is named "branch"
+ * @EDAC_MC_LAYER_CHANNEL:	memory layer is named "channel"
+ * @EDAC_MC_LAYER_SLOT:		memory layer is named "slot"
+ * @EDAC_MC_LAYER_CHIP_SELECT:	memory layer is named "chip select"
+ *
+ * This enum is used by the drivers to tell edac_mc_sysfs what name should
+ * be used when describing a memory stick location.
+ */
+enum edac_mc_layer_type {
+	EDAC_MC_LAYER_BRANCH,
+	EDAC_MC_LAYER_CHANNEL,
+	EDAC_MC_LAYER_SLOT,
+	EDAC_MC_LAYER_CHIP_SELECT,
+};
+
+/**
+ * struct edac_mc_layer - describes the memory controller hierarchy
+ * @layer:		layer type
+ * @size:		number of components per layer. For example,
+ *			if the channel layer has two channels, size = 2
+ * @is_virt_csrow:	This layer is part of the "csrow" when old API
+ *			compatibility mode is enabled. Otherwise, it is
+ *			a channel
+ */
+struct edac_mc_layer {
+	enum edac_mc_layer_type	type;
+	unsigned		size;
+	bool			is_virt_csrow;
+};
+
+/*
+ * Maximum number of layers used by the memory controller to uniquely
+ * identify a single memory stick.
+ * NOTE: Changing this constant requires not only to change the constant
+ * below, but also to change the existing code at the core, as there are
+ * some code there that are optimized for 3 layers.
+ */
+#define EDAC_MAX_LAYERS		3
+
+/**
+ * EDAC_DIMM_PTR - Macro responsible to find a pointer inside a pointer array
+ *		   for the element given by [layer0,layer1,layer2] position
+ *
+ * @layers:	a struct edac_mc_layer array, describing how many elements
+ *		were allocated for each layer
+ * @var:	name of the var where we want to get the pointer
+ *		(like mci->dimms)
+ * @n_layers:	Number of layers at the @layers array
+ * @layer0:	layer0 position
+ * @layer1:	layer1 position. Unused if n_layers < 2
+ * @layer2:	layer2 position. Unused if n_layers < 3
+ *
+ * For 1 layer, this macro returns &var[layer0]
+ * For 2 layers, this macro is similar to allocate a bi-dimensional array
+ *		and to return "&var[layer0][layer1]"
+ * For 3 layers, this macro is similar to allocate a tri-dimensional array
+ *		and to return "&var[layer0][layer1][layer2]"
+ *
+ * A loop could be used here to make it more generic, but, as we only have
+ * 3 layers, this is a little faster.
+ * By design, layers can never be 0 or more than 3. If that ever happens,
+ * a NULL is returned, causing an OOPS during the memory allocation routine,
+ * with would point to the developer that he's doing something wrong.
+ */
+#define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({	\
+	typeof(var) __p;						\
+	if ((nlayers) == 1)						\
+		__p = &var[layer0];					\
+	else if ((nlayers) == 2)					\
+		__p = &var[(layer1) + ((layers[1]).size * (layer0))];	\
+	else if ((nlayers) == 3)					\
+		__p = &var[(layer2) + ((layers[2]).size * ((layer1) +	\
+			    ((layers[1]).size * (layer0))))];		\
+	else								\
+		__p = NULL;						\
+	__p;								\
+})
+
+
+/* FIXME: add the proper per-location error counts */
+struct dimm_info {
+	char label[EDAC_MC_LABEL_LEN + 1];	/* DIMM label on motherboard */
+
+	/* Memory location data */
+	unsigned location[EDAC_MAX_LAYERS];
+
+	struct mem_ctl_info *mci;	/* the parent */
+
+	u32 grain;		/* granularity of reported error in bytes */
+	enum dev_type dtype;	/* memory device type */
+	enum mem_type mtype;	/* memory dimm type */
+	enum edac_type edac_mode;	/* EDAC mode for this dimm */
+
+	u32 nr_pages;			/* number of pages on this dimm */
+
+	unsigned csrow, cschannel;	/* Points to the old API data */
+};
+
+/**
  * struct rank_info - contains the information for one DIMM rank
  *
  * @chan_idx:	channel number where the rank is (typically, 0 or 1)
  * @ce_count:	number of correctable errors for this rank
- * @label:	DIMM label. Different ranks for the same DIMM should be
- *		filled, on userspace, with the same label.
- *		FIXME: The core currently won't enforce it.
  * @csrow:	A pointer to the chip select row structure (the parent
  *		structure). The location of the rank is given by
  *		the (csrow->csrow_idx, chan_idx) vector.
+ * @dimm:	A pointer to the DIMM structure, where the DIMM label
+ *		information is stored.
+ *
+ * FIXME: Currently, the EDAC core model will assume one DIMM per rank.
+ *	  This is a bad assumption, but it makes this patch easier. Later
+ *	  patches in this series will fix this issue.
  */
 struct rank_info {
 	int chan_idx;
-	u32 ce_count;
-	char label[EDAC_MC_LABEL_LEN + 1];
-	struct csrow_info *csrow;	/* the parent */
+	struct csrow_info *csrow;
+	struct dimm_info *dimm;
+
+	u32 ce_count;		/* Correctable Errors for this csrow */
 };
 
 struct csrow_info {
-	unsigned long first_page;	/* first page number in dimm */
-	unsigned long last_page;	/* last page number in dimm */
+	/* Used only by edac_mc_find_csrow_by_page() */
+	unsigned long first_page;	/* first page number in csrow */
+	unsigned long last_page;	/* last page number in csrow */
 	unsigned long page_mask;	/* used for interleaving -
-					 * 0UL for non intlv
-					 */
-	u32 nr_pages;		/* number of pages in csrow */
-	u32 grain;		/* granularity of reported error in bytes */
-	int csrow_idx;		/* the chip-select row */
-	enum dev_type dtype;	/* memory device type */
+					 * 0UL for non intlv */
+
+	int csrow_idx;			/* the chip-select row */
+
 	u32 ue_count;		/* Uncorrectable Errors for this csrow */
 	u32 ce_count;		/* Correctable Errors for this csrow */
-	enum mem_type mtype;	/* memory csrow type */
-	enum edac_type edac_mode;	/* EDAC mode for this csrow */
+
 	struct mem_ctl_info *mci;	/* the parent */
 
 	struct kobject kobj;	/* sysfs kobject for this csrow */
@@ -426,8 +548,20 @@ struct mem_ctl_info {
 	unsigned long (*ctl_page_to_phys) (struct mem_ctl_info * mci,
 					   unsigned long page);
 	int mc_idx;
-	int nr_csrows;
 	struct csrow_info *csrows;
+	unsigned nr_csrows, num_cschannel;
+
+	/* Memory Controller hierarchy */
+	unsigned n_layers;
+	struct edac_mc_layer *layers;
+	bool mem_is_per_rank;
+
+	/*
+	 * DIMM info. Will eventually remove the entire csrows_info some day
+	 */
+	unsigned tot_dimms;
+	struct dimm_info *dimms;
+
 	/*
 	 * FIXME - what about controllers on other busses? - IDs must be
 	 * unique.  dev pointer should be sufficiently unique, but
@@ -440,12 +574,16 @@ struct mem_ctl_info {
 	const char *dev_name;
 	char proc_name[MC_PROC_NAME_MAX_LEN + 1];
 	void *pvt_info;
-	u32 ue_noinfo_count;	/* Uncorrectable Errors w/o info */
-	u32 ce_noinfo_count;	/* Correctable Errors w/o info */
-	u32 ue_count;		/* Total Uncorrectable Errors for this MC */
-	u32 ce_count;		/* Total Correctable Errors for this MC */
 	unsigned long start_time;	/* mci load start time (in jiffies) */
 
+	/*
+	 * drivers shouldn't access those fields directly, as the core
+	 * already handles that.
+	 */
+	u32 ce_noinfo_count, ue_noinfo_count;
+	u32 ue_mc, ce_mc;
+	u32 *ce_per_layer[EDAC_MAX_LAYERS], *ue_per_layer[EDAC_MAX_LAYERS];
+
 	struct completion complete;
 
 	/* edac sysfs device control */
@@ -458,7 +596,7 @@ struct mem_ctl_info {
 	 * by the low level driver.
 	 *
 	 * Set by the low level driver to provide attributes at the
-	 * controller level, same level as 'ue_count' and 'ce_count' above.
+	 * controller level.
 	 * An array of structures, NULL terminated
 	 *
 	 * If attributes are desired, then set to array of attributes