path: root/drivers/edac/edac_core.h
diff options
authorLinus Torvalds <torvalds@linux-foundation.org>2012-05-29 18:32:37 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-05-29 18:32:37 -0700
commit87a5af24e54857e7b15c1f1b0468512ee65c94e3 (patch)
treeee346852a0fc27f172a5eb57b6e3c7bf111f2fad /drivers/edac/edac_core.h
parent7e5b2db77b05746613516599c916a8cc2e321077 (diff)
parent0bf09e829dd4b07227ed5a8bc4ac85752a044458 (diff)
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 ...
Diffstat (limited to 'drivers/edac/edac_core.h')
1 files changed, 16 insertions, 31 deletions
diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
index 5b739411d62f..117490d4f835 100644
--- a/drivers/edac/edac_core.h
+++ b/drivers/edac/edac_core.h
@@ -447,8 +447,10 @@ static inline void pci_write_bits32(struct pci_dev *pdev, int offset,
#endif /* CONFIG_PCI */
-extern struct mem_ctl_info *edac_mc_alloc(unsigned sz_pvt, unsigned nr_csrows,
- unsigned nr_chans, int edac_index);
+struct mem_ctl_info *edac_mc_alloc(unsigned mc_num,
+ unsigned n_layers,
+ struct edac_mc_layer *layers,
+ unsigned sz_pvt);
extern int edac_mc_add_mc(struct mem_ctl_info *mci);
extern void edac_mc_free(struct mem_ctl_info *mci);
extern struct mem_ctl_info *edac_mc_find(int idx);
@@ -456,35 +458,17 @@ extern struct mem_ctl_info *find_mci_by_dev(struct device *dev);
extern struct mem_ctl_info *edac_mc_del_mc(struct device *dev);
extern int edac_mc_find_csrow_by_page(struct mem_ctl_info *mci,
unsigned long page);
- * The no info errors are used when error overflows are reported.
- * There are a limited number of error logging registers that can
- * be exausted. When all registers are exhausted and an additional
- * error occurs then an error overflow register records that an
- * error occurred and the type of error, but doesn't have any
- * further information. The ce/ue versions make for cleaner
- * reporting logic and function interface - reduces conditional
- * statement clutter and extra function arguments.
- */
-extern void edac_mc_handle_ce(struct mem_ctl_info *mci,
- unsigned long page_frame_number,
- unsigned long offset_in_page,
- unsigned long syndrome, int row, int channel,
- const char *msg);
-extern void edac_mc_handle_ce_no_info(struct mem_ctl_info *mci,
- const char *msg);
-extern void edac_mc_handle_ue(struct mem_ctl_info *mci,
- unsigned long page_frame_number,
- unsigned long offset_in_page, int row,
- const char *msg);
-extern void edac_mc_handle_ue_no_info(struct mem_ctl_info *mci,
- const char *msg);
-extern void edac_mc_handle_fbd_ue(struct mem_ctl_info *mci, unsigned int csrow,
- unsigned int channel0, unsigned int channel1,
- char *msg);
-extern void edac_mc_handle_fbd_ce(struct mem_ctl_info *mci, unsigned int csrow,
- unsigned int channel, char *msg);
+void edac_mc_handle_error(const enum hw_event_mc_err_type type,
+ struct mem_ctl_info *mci,
+ const unsigned long page_frame_number,
+ const unsigned long offset_in_page,
+ const unsigned long syndrome,
+ const int layer0,
+ const int layer1,
+ const int layer2,
+ const char *msg,
+ const char *other_detail,
+ const void *mcelog);
* edac_device APIs
@@ -496,6 +480,7 @@ extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev,
extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev,
int inst_nr, int block_nr, const char *msg);
extern int edac_device_alloc_index(void);
+extern const char *edac_layer_name[];
* edac_pci APIs

Privacy Policy