| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4F9A7813.20405@redhat.com>
Date: Fri, 27 Apr 2012 07:42:27 -0300
From: Mauro Carvalho Chehab <mchehab@...hat.com>
To: Mauro Carvalho Chehab <mchehab@...hat.com>,
Borislav Petkov <borislav.petkov@....com>
CC: Linux Edac Mailing List <linux-edac@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Doug Thompson <norsk5@...oo.com>
Subject: Re: [PATCH EDACv16 2/2] amd64_edac: convert driver to use the new
edac ABI
Em 24-04-2012 15:15, Mauro Carvalho Chehab escreveu:
> The legacy edac ABI is going to be removed. Port the driver to use
> and benefit from the new API functionality.
>
> Cc: Doug Thompson <norsk5@...oo.com>
> Cc: Borislav Petkov <borislav.petkov@....com>
> Signed-off-by: Mauro Carvalho Chehab <mchehab@...hat.com>
Ping?
> ---
>
> v16: Only context changes
>
> drivers/edac/amd64_edac.c | 137 ++++++++++++++++++++++++++++++---------------
> 1 files changed, 92 insertions(+), 45 deletions(-)
>
> diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
> index 6d6ec68..b13d5a0 100644
> --- a/drivers/edac/amd64_edac.c
> +++ b/drivers/edac/amd64_edac.c
> @@ -1039,6 +1039,37 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
> int channel, csrow;
> u32 page, offset;
>
> + error_address_to_page_and_offset(sys_addr, &page, &offset);
> +
> + /*
> + * Find out which node the error address belongs to. This may be
> + * different from the node that detected the error.
> + */
> + src_mci = find_mc_by_sys_addr(mci, sys_addr);
> + if (!src_mci) {
> + amd64_mc_err(mci, "failed to map error addr 0x%lx to a node\n",
> + (unsigned long)sys_addr);
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + page, offset, syndrome,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "failed to map error addr to a node",
> + NULL);
> + return;
> + }
> +
> + /* Now map the sys_addr to a CSROW */
> + csrow = sys_addr_to_csrow(src_mci, sys_addr);
> + if (csrow < 0) {
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + page, offset, syndrome,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "failed to map error addr to a csrow",
> + NULL);
> + return;
> + }
> +
> /* CHIPKILL enabled */
> if (pvt->nbcfg & NBCFG_CHIPKILL) {
> channel = get_channel_from_ecc_syndrome(mci, syndrome);
> @@ -1048,9 +1079,15 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
> * 2 DIMMs is in error. So we need to ID 'both' of them
> * as suspect.
> */
> - amd64_mc_warn(mci, "unknown syndrome 0x%04x - possible "
> - "error reporting race\n", syndrome);
> - edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
> + amd64_mc_warn(src_mci, "unknown syndrome 0x%04x - "
> + "possible error reporting race\n",
> + syndrome);
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + page, offset, syndrome,
> + csrow, -1, -1,
> + EDAC_MOD_STR,
> + "unknown syndrome - possible error reporting race",
> + NULL);
> return;
> }
> } else {
> @@ -1065,28 +1102,10 @@ static void k8_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
> channel = ((sys_addr & BIT(3)) != 0);
> }
>
> - /*
> - * Find out which node the error address belongs to. This may be
> - * different from the node that detected the error.
> - */
> - src_mci = find_mc_by_sys_addr(mci, sys_addr);
> - if (!src_mci) {
> - amd64_mc_err(mci, "failed to map error addr 0x%lx to a node\n",
> - (unsigned long)sys_addr);
> - edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
> - return;
> - }
> -
> - /* Now map the sys_addr to a CSROW */
> - csrow = sys_addr_to_csrow(src_mci, sys_addr);
> - if (csrow < 0) {
> - edac_mc_handle_ce_no_info(src_mci, EDAC_MOD_STR);
> - } else {
> - error_address_to_page_and_offset(sys_addr, &page, &offset);
> -
> - edac_mc_handle_ce(src_mci, page, offset, syndrome, csrow,
> - channel, EDAC_MOD_STR);
> - }
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, src_mci,
> + page, offset, syndrome,
> + csrow, channel, -1,
> + EDAC_MOD_STR, "", NULL);
> }
>
> static int ddr2_cs_size(unsigned i, bool dct_width)
> @@ -1568,15 +1587,20 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
> u32 page, offset;
> int nid, csrow, chan = 0;
>
> + error_address_to_page_and_offset(sys_addr, &page, &offset);
> +
> csrow = f1x_translate_sysaddr_to_cs(pvt, sys_addr, &nid, &chan);
>
> if (csrow < 0) {
> - edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + page, offset, syndrome,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "failed to map error addr to a csrow",
> + NULL);
> return;
> }
>
> - error_address_to_page_and_offset(sys_addr, &page, &offset);
> -
> /*
> * We need the syndromes for channel detection only when we're
> * ganged. Otherwise @chan should already contain the channel at
> @@ -1585,16 +1609,10 @@ static void f1x_map_sysaddr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr,
> if (dct_ganging_enabled(pvt))
> chan = get_channel_from_ecc_syndrome(mci, syndrome);
>
> - if (chan >= 0)
> - edac_mc_handle_ce(mci, page, offset, syndrome, csrow, chan,
> - EDAC_MOD_STR);
> - else
> - /*
> - * Channel unknown, report all channels on this CSROW as failed.
> - */
> - for (chan = 0; chan < mci->csrows[csrow].nr_channels; chan++)
> - edac_mc_handle_ce(mci, page, offset, syndrome,
> - csrow, chan, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + page, offset, syndrome,
> + csrow, chan, -1,
> + EDAC_MOD_STR, "", NULL);
> }
>
> /*
> @@ -1875,7 +1893,12 @@ static void amd64_handle_ce(struct mem_ctl_info *mci, struct mce *m)
> /* Ensure that the Error Address is VALID */
> if (!(m->status & MCI_STATUS_ADDRV)) {
> amd64_mc_err(mci, "HW has no ERROR_ADDRESS available\n");
> - edac_mc_handle_ce_no_info(mci, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci,
> + 0, 0, 0,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "HW has no ERROR_ADDRESS available",
> + NULL);
> return;
> }
>
> @@ -1899,11 +1922,17 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
>
> if (!(m->status & MCI_STATUS_ADDRV)) {
> amd64_mc_err(mci, "HW has no ERROR_ADDRESS available\n");
> - edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
> + 0, 0, 0,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "HW has no ERROR_ADDRESS available",
> + NULL);
> return;
> }
>
> sys_addr = get_error_address(m);
> + error_address_to_page_and_offset(sys_addr, &page, &offset);
>
> /*
> * Find out which node the error address belongs to. This may be
> @@ -1913,7 +1942,11 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
> if (!src_mci) {
> amd64_mc_err(mci, "ERROR ADDRESS (0x%lx) NOT mapped to a MC\n",
> (unsigned long)sys_addr);
> - edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
> + page, offset, 0,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "ERROR ADDRESS NOT mapped to a MC", NULL);
> return;
> }
>
> @@ -1923,10 +1956,17 @@ static void amd64_handle_ue(struct mem_ctl_info *mci, struct mce *m)
> if (csrow < 0) {
> amd64_mc_err(mci, "ERROR_ADDRESS (0x%lx) NOT mapped to CS\n",
> (unsigned long)sys_addr);
> - edac_mc_handle_ue_no_info(log_mci, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
> + page, offset, 0,
> + -1, -1, -1,
> + EDAC_MOD_STR,
> + "ERROR ADDRESS NOT mapped to CS",
> + NULL);
> } else {
> - error_address_to_page_and_offset(sys_addr, &page, &offset);
> - edac_mc_handle_ue(log_mci, page, offset, csrow, EDAC_MOD_STR);
> + edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci,
> + page, offset, 0,
> + csrow, -1, -1,
> + EDAC_MOD_STR, "", NULL);
> }
> }
>
> @@ -2486,6 +2526,7 @@ static int amd64_init_one_instance(struct pci_dev *F2)
> struct amd64_pvt *pvt = NULL;
> struct amd64_family_type *fam_type = NULL;
> struct mem_ctl_info *mci = NULL;
> + struct edac_mc_layer layers[2];
> int err = 0, ret;
> u8 nid = get_node_id(F2);
>
> @@ -2520,7 +2561,13 @@ static int amd64_init_one_instance(struct pci_dev *F2)
> goto err_siblings;
>
> ret = -ENOMEM;
> - mci = edac_mc_alloc(0, pvt->csels[0].b_cnt, pvt->channel_count, nid);
> + layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
> + layers[0].size = pvt->csels[0].b_cnt;
> + layers[0].is_virt_csrow = true;
> + layers[1].type = EDAC_MC_LAYER_CHANNEL;
> + layers[1].size = pvt->channel_count;
> + layers[1].is_virt_csrow = false;
> + mci = new_edac_mc_alloc(nid, ARRAY_SIZE(layers), layers, false, 0);
> if (!mci)
> goto err_siblings;
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists