From 479696840239e0cc43efb3c917bdcad2174d2215 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Mon, 15 Oct 2012 21:48:48 -0300 Subject: i82975x_edac: Fix dimm label initialization The driver has only 4 hardcoded labels, but allows much more memory. Fix it by removing the hardcoded logic, using snprintf() instead. [ 19.833972] general protection fault: 0000 [#1] SMP [ 19.837733] Modules linked in: i82975x_edac(+) edac_core firewire_ohci firewire_core crc_itu_t nouveau mxm_wmi wmi video i2c_algo_bit drm_kms_helper ttm drm i2c_core [ 19.837733] CPU 0 [ 19.837733] Pid: 390, comm: udevd Not tainted 3.6.1-1.fc17.x86_64.debug #1 Dell Inc. Precision WorkStation 390 /0MY510 [ 19.837733] RIP: 0010:[] [] strncpy+0x18/0x30 [ 19.837733] RSP: 0018:ffff880078535b68 EFLAGS: 00010202 [ 19.837733] RAX: ffff880069fa9708 RBX: ffff880078588000 RCX: ffff880069fa9708 [ 19.837733] RDX: 000000000000001f RSI: 5f706f5f63616465 RDI: ffff880069fa9708 [ 19.837733] RBP: ffff880078535b68 R08: ffff880069fa9727 R09: 000000000000fffe [ 19.837733] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000003 [ 19.837733] R13: 0000000000000000 R14: ffff880069fa9290 R15: ffff880079624a80 [ 19.837733] FS: 00007f3de01ee840(0000) GS:ffff88007c400000(0000) knlGS:0000000000000000 [ 19.837733] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 19.837733] CR2: 00007f3de00b9000 CR3: 0000000078dbc000 CR4: 00000000000007f0 [ 19.837733] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 19.837733] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 19.837733] Process udevd (pid: 390, threadinfo ffff880078534000, task ffff880079642450) [ 19.837733] Stack: [ 19.837733] ffff880078535c18 ffffffffa017c6b8 00040000816d627f ffff880079624a88 [ 19.837733] ffffc90004cd6000 ffff880079624520 ffff88007ac21148 0000000000000000 [ 19.837733] 0000000000000000 0004000000000000 feda000078535bc8 ffffffff810d696d [ 19.837733] Call Trace: [ 19.837733] [] i82975x_init_one+0x2e6/0x3e6 [i82975x_edac] ... Fix bug reported at: https://bugzilla.redhat.com/show_bug.cgi?id=848149 And, very likely: https://bbs.archlinux.org/viewtopic.php?id=148033 https://bugzilla.kernel.org/show_bug.cgi?id=47171 Cc: Alan Cox Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/i82975x_edac.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/edac/i82975x_edac.c b/drivers/edac/i82975x_edac.c index 069e26c11c4..a98020409fa 100644 --- a/drivers/edac/i82975x_edac.c +++ b/drivers/edac/i82975x_edac.c @@ -370,10 +370,6 @@ static enum dev_type i82975x_dram_type(void __iomem *mch_window, int rank) static void i82975x_init_csrows(struct mem_ctl_info *mci, struct pci_dev *pdev, void __iomem *mch_window) { - static const char *labels[4] = { - "DIMM A1", "DIMM A2", - "DIMM B1", "DIMM B2" - }; struct csrow_info *csrow; unsigned long last_cumul_size; u8 value; @@ -423,9 +419,10 @@ static void i82975x_init_csrows(struct mem_ctl_info *mci, dimm = mci->csrows[index]->channels[chan]->dimm; dimm->nr_pages = nr_pages / csrow->nr_channels; - strncpy(csrow->channels[chan]->dimm->label, - labels[(index >> 1) + (chan * 2)], - EDAC_MC_LABEL_LEN); + + snprintf(csrow->channels[chan]->dimm->label, EDAC_MC_LABEL_LEN, "DIMM %c%d", + (chan == 0) ? 'A' : 'B', + index); dimm->grain = 1 << 7; /* 128Byte cache-line resolution */ dimm->dtype = i82975x_dram_type(mch_window, index); dimm->mtype = MEM_DDR2; /* I82975x supports only DDR2 */ -- cgit v1.2.3-70-g09d2 From 24bef66e74d647aebd34e0bef7693512b7912029 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Wed, 24 Oct 2012 10:30:01 -0200 Subject: edac: Fix the dimm filling for csrows-based layouts The driver is currently filling data in a wrong way, on drivers for csrows-based memory controller, when the first layer is a csrow. This is not easily to notice, as, in general, memories are filed in dual, interleaved, symetric mode, as very few memory controllers support asymetric modes. While digging into a bug for i82795_edac driver, the asymetric mode there is now working, allowing us to fill the machine with 4x1GB ranks at channel 0, and 2x512GB at channel 1: Channel 0 ranks: EDAC DEBUG: i82975x_init_csrows: DIMM A0: from page 0x00000000 to 0x0003ffff (size: 0x00040000 pages) EDAC DEBUG: i82975x_init_csrows: DIMM A1: from page 0x00040000 to 0x0007ffff (size: 0x00040000 pages) EDAC DEBUG: i82975x_init_csrows: DIMM A2: from page 0x00080000 to 0x000bffff (size: 0x00040000 pages) EDAC DEBUG: i82975x_init_csrows: DIMM A3: from page 0x000c0000 to 0x000fffff (size: 0x00040000 pages) Channel 1 ranks: EDAC DEBUG: i82975x_init_csrows: DIMM B0: from page 0x00100000 to 0x0011ffff (size: 0x00020000 pages) EDAC DEBUG: i82975x_init_csrows: DIMM B1: from page 0x00120000 to 0x0013ffff (size: 0x00020000 pages) Instead of properly showing the memories as such, before this patch, it shows the memory layout as: +-----------------------------------+ | mc0 | | csrow0 | csrow1 | csrow2 | ----------+-----------------------------------+ channel1: | 1024 MB | 1024 MB | 512 MB | channel0: | 1024 MB | 1024 MB | 512 MB | ----------+-----------------------------------+ as if both channels were symetric, grouping the DIMMs on a wrong layout. After this patch, the memory is correctly represented. So, for csrows at layers[0], it shows: +-----------------------------------------------+ | mc0 | | csrow0 | csrow1 | csrow2 | csrow3 | ----------+-----------------------------------------------+ channel1: | 512 MB | 512 MB | 0 MB | 0 MB | channel0: | 1024 MB | 1024 MB | 1024 MB | 1024 MB | ----------+-----------------------------------------------+ For csrows at layers[1], it shows: +-----------------------+ | mc0 | | channel0 | channel1 | --------+-----------------------+ csrow3: | 1024 MB | 0 MB | csrow2: | 1024 MB | 0 MB | --------+-----------------------+ csrow1: | 1024 MB | 512 MB | csrow0: | 1024 MB | 512 MB | --------+-----------------------+ So, no matter of what comes first, the information between channel and csrow will be properly represented. Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/edac_mc.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index d5dc9da7f99..81eb9fd3f71 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -416,10 +416,18 @@ struct mem_ctl_info *edac_mc_alloc(unsigned mc_num, dimm->cschannel = chn; /* Increment csrow location */ - row++; - if (row == tot_csrows) { - row = 0; + if (layers[0].is_virt_csrow) { chn++; + if (chn == tot_channels) { + chn = 0; + row++; + } + } else { + row++; + if (row == tot_csrows) { + row = 0; + chn++; + } } /* Increment dimm location */ -- cgit v1.2.3-70-g09d2 From 7e06b7a3333f5c7a0cec12aff20d39c5c87c0795 Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Thu, 18 Oct 2012 15:54:45 +0200 Subject: i7300_edac: Fix error flag testing * Right-shift the values in GET_FBD_FAT_IDX and GET_FBD_NF_IDX, so that the callers get the result they expect. * Fix definition of FERR_FAT_FBD_ERR_MASK. * Call GET_FBD_NF_IDX, not GET_FBD_FAT_IDX, when operating on register FERR_NF_FBD. We were lucky they have the same definition. This fixes kernel bug #44131: https://bugzilla.kernel.org/show_bug.cgi?id=44131 Signed-off-by: Jean Delvare Cc: Mauro Carvalho Chehab Cc: Doug Thompson Cc: stable@vger.kernel.org Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/i7300_edac.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/edac/i7300_edac.c b/drivers/edac/i7300_edac.c index a09d0667f72..9d669cd4361 100644 --- a/drivers/edac/i7300_edac.c +++ b/drivers/edac/i7300_edac.c @@ -197,8 +197,8 @@ static const char *ferr_fat_fbd_name[] = { [0] = "Memory Write error on non-redundant retry or " "FBD configuration Write error on retry", }; -#define GET_FBD_FAT_IDX(fbderr) (fbderr & (3 << 28)) -#define FERR_FAT_FBD_ERR_MASK ((1 << 0) | (1 << 1) | (1 << 2) | (1 << 3)) +#define GET_FBD_FAT_IDX(fbderr) (((fbderr) >> 28) & 3) +#define FERR_FAT_FBD_ERR_MASK ((1 << 0) | (1 << 1) | (1 << 2) | (1 << 22)) #define FERR_NF_FBD 0xa0 static const char *ferr_nf_fbd_name[] = { @@ -225,7 +225,7 @@ static const char *ferr_nf_fbd_name[] = { [1] = "Aliased Uncorrectable Non-Mirrored Demand Data ECC", [0] = "Uncorrectable Data ECC on Replay", }; -#define GET_FBD_NF_IDX(fbderr) (fbderr & (3 << 28)) +#define GET_FBD_NF_IDX(fbderr) (((fbderr) >> 28) & 3) #define FERR_NF_FBD_ERR_MASK ((1 << 24) | (1 << 23) | (1 << 22) | (1 << 21) |\ (1 << 18) | (1 << 17) | (1 << 16) | (1 << 15) |\ (1 << 14) | (1 << 13) | (1 << 11) | (1 << 10) |\ @@ -464,7 +464,7 @@ static void i7300_process_fbd_error(struct mem_ctl_info *mci) errnum = find_first_bit(&errors, ARRAY_SIZE(ferr_nf_fbd_name)); specific = GET_ERR_FROM_TABLE(ferr_nf_fbd_name, errnum); - branch = (GET_FBD_FAT_IDX(error_reg) == 2) ? 1 : 0; + branch = (GET_FBD_NF_IDX(error_reg) == 2) ? 1 : 0; pci_read_config_dword(pvt->pci_dev_16_1_fsb_addr_map, REDMEMA, &syndrome); -- cgit v1.2.3-70-g09d2 From 42709efb3a47524c6252e1bdc85e205f7bc356fb Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Tue, 16 Oct 2012 09:02:27 -0400 Subject: i7core_edac: fix panic when accessing sysfs files The i7core_edac addrmatch_dev and chancounts_dev have sysfs files associated with them. The sysfs files, however, are coded so that the parent device is is the mci device. This is incorrect and the mci struct should be obtained through the addrmatch_dev and chancounts_dev device's private data field which is populated in i7core_create_sysfs_devices(). Signed-off-by: Prarit Bhargava Signed-off-by: Mauro Carvalho Chehab --- drivers/edac/i7core_edac.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 3672101023b..10c8c00d646 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -816,7 +816,7 @@ static ssize_t i7core_inject_store_##param( \ struct device_attribute *mattr, \ const char *data, size_t count) \ { \ - struct mem_ctl_info *mci = to_mci(dev); \ + struct mem_ctl_info *mci = dev_get_drvdata(dev); \ struct i7core_pvt *pvt; \ long value; \ int rc; \ @@ -845,7 +845,7 @@ static ssize_t i7core_inject_show_##param( \ struct device_attribute *mattr, \ char *data) \ { \ - struct mem_ctl_info *mci = to_mci(dev); \ + struct mem_ctl_info *mci = dev_get_drvdata(dev); \ struct i7core_pvt *pvt; \ \ pvt = mci->pvt_info; \ @@ -1052,7 +1052,7 @@ static ssize_t i7core_show_counter_##param( \ struct device_attribute *mattr, \ char *data) \ { \ - struct mem_ctl_info *mci = to_mci(dev); \ + struct mem_ctl_info *mci = dev_get_drvdata(dev); \ struct i7core_pvt *pvt = mci->pvt_info; \ \ edac_dbg(1, "\n"); \ -- cgit v1.2.3-70-g09d2