edac.h: Add generic layers for describing a memory location

The edac core were written with the idea that memory controllers
are able to directly access csrows, and that the channels are
used inside a csrows select.

This is not true for FB-DIMM and RAMBUS memory controllers.

Also, some recent advanced memory controllers don't present a per-csrows
view. Instead, they view memories as DIMMs, instead of ranks, accessed
via csrow/channel.

So, changes are needed in order to allow the EDAC core to
work with all types of architectures.

In preparation for handling non-csrows based memory controllers,
add some memory structs and a macro:

enum hw_event_mc_err_type: describes the type of error
			   (corrected, uncorrected, fatal)

To be used by the new edac_mc_handle_error function;

enum edac_mc_layer: describes the type of a given memory
architecture layer (branch, channel, slot, csrow).

struct edac_mc_layer: describes the properties of a memory
		      layer (type, size, and if the layer
		      will be used on a virtual csrow.

EDAC_DIMM_PTR() - as the number of layers can vary from 1 to 3,
this macro converts from an address with up to 3 layers into
a linear address.

Reviewed-by: Borislav Petkov <bp@amd64.org>
Cc: Doug Thompson <norsk5@yahoo.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>

diff --git a/include/linux/edac.h b/include/linux/edac.h
index 67717ca..9e62843 100644 (file)
--- 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
  *
@@ -312,7 +331,89 @@ enum scrub_type {
  * PS - I enjoyed writing all that about as much as you enjoyed reading it.
  */
 
-/* FIXME: add a per-dimm ce error count */
+/**
+ * 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 */
        unsigned memory_controller;