From: Yazen Ghannam <yazen.ghannam@amd.com>
To: <x86@kernel.org>, Tony Luck <tony.luck@intel.com>,
"Rafael J. Wysocki" <rafael@kernel.org>
Cc: <linux-kernel@vger.kernel.org>, <linux-edac@vger.kernel.org>,
<Smita.KoralahalliChannabasappa@amd.com>,
Qiuxu Zhuo <qiuxu.zhuo@intel.com>,
Nikolay Borisov <nik.borisov@suse.com>,
<linux-acpi@vger.kernel.org>,
"Yazen Ghannam" <yazen.ghannam@amd.com>
Subject: [PATCH v5 11/20] x86/mce: Separate global and per-CPU quirks
Date: Mon, 25 Aug 2025 17:33:08 +0000 [thread overview]
Message-ID: <20250825-wip-mca-updates-v5-11-865768a2eef8@amd.com> (raw)
In-Reply-To: <20250825-wip-mca-updates-v5-0-865768a2eef8@amd.com>
Many quirks are global configuration settings and a handful apply to
each CPU.
Move the per-CPU quirks to vendor init to execute them on each online
CPU. Set the global quirks during BSP-only init so they're only executed
once and early.
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Notes:
Link:
https://lore.kernel.org/r/20250624-wip-mca-updates-v4-14-236dd74f645f@amd.com
v4->v5:
* Apply consistent naming to quirk functions.
v3->v4:
* Add newline in mce_amd_feature_init().
* Remove __mcheck_cpu_apply_quirks().
* Update code comment ref. __mcheck_cpu_apply_quirks().
v2->v3:
* Update code comment.
* Add tags from Qiuxu and Tony.
v1->v2:
* New in v2.
arch/x86/kernel/cpu/mce/amd.c | 24 ++++++++++++
arch/x86/kernel/cpu/mce/core.c | 85 +++++++++++------------------------------
arch/x86/kernel/cpu/mce/intel.c | 18 +++++++++
3 files changed, 65 insertions(+), 62 deletions(-)
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index efcfce329ca7..42f5c115395b 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -650,6 +650,28 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
wrmsrq(MSR_K7_HWCR, hwcr);
}
+static void amd_apply_cpu_quirks(struct cpuinfo_x86 *c)
+{
+ struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+
+ /* This should be disabled by the BIOS, but isn't always */
+ if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
+ /*
+ * disable GART TBL walk error reporting, which
+ * trips off incorrectly with the IOMMU & 3ware
+ * & Cerberus:
+ */
+ clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
+ }
+
+ /*
+ * Various K7s with broken bank 0 around. Always disable
+ * by default.
+ */
+ if (c->x86 == 6 && this_cpu_read(mce_num_banks))
+ mce_banks[0].ctl = 0;
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
@@ -657,6 +679,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
u32 low = 0, high = 0, address = 0;
int offset = -1;
+ amd_apply_cpu_quirks(c);
+
mce_flags.amd_threshold = 1;
for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 14456f6c2f7b..21a5ea239e93 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1807,8 +1807,9 @@ static void __mcheck_cpu_mce_banks_init(void)
struct mce_bank *b = &mce_banks[i];
/*
- * Init them all, __mcheck_cpu_apply_quirks() is going to apply
- * the required vendor quirks before
+ * Init them all by default.
+ *
+ * The required vendor quirks will be applied before
* __mcheck_cpu_init_prepare_banks() does the final bank setup.
*/
b->ctl = -1ULL;
@@ -1882,20 +1883,8 @@ static void __mcheck_cpu_init_prepare_banks(void)
}
}
-static void apply_quirks_amd(struct cpuinfo_x86 *c)
+static void amd_apply_global_quirks(struct cpuinfo_x86 *c)
{
- struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-
- /* This should be disabled by the BIOS, but isn't always */
- if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
- /*
- * disable GART TBL walk error reporting, which
- * trips off incorrectly with the IOMMU & 3ware
- * & Cerberus:
- */
- clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
- }
-
if (c->x86 < 0x11 && mca_cfg.bootlog < 0) {
/*
* Lots of broken BIOS around that don't clear them
@@ -1904,13 +1893,6 @@ static void apply_quirks_amd(struct cpuinfo_x86 *c)
mca_cfg.bootlog = 0;
}
- /*
- * Various K7s with broken bank 0 around. Always disable
- * by default.
- */
- if (c->x86 == 6 && this_cpu_read(mce_num_banks))
- mce_banks[0].ctl = 0;
-
/*
* overflow_recov is supported for F15h Models 00h-0fh
* even though we don't have a CPUID bit for it.
@@ -1922,25 +1904,12 @@ static void apply_quirks_amd(struct cpuinfo_x86 *c)
mce_flags.zen_ifu_quirk = 1;
}
-static void apply_quirks_intel(struct cpuinfo_x86 *c)
+static void intel_apply_global_quirks(struct cpuinfo_x86 *c)
{
- struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-
/* Older CPUs (prior to family 6) don't need quirks. */
if (c->x86_vfm < INTEL_PENTIUM_PRO)
return;
- /*
- * SDM documents that on family 6 bank 0 should not be written
- * because it aliases to another special BIOS controlled
- * register.
- * But it's not aliased anymore on model 0x1a+
- * Don't ignore bank 0 completely because there could be a
- * valid event later, merely don't write CTL0.
- */
- if (c->x86_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks))
- mce_banks[0].init = false;
-
/*
* All newer Intel systems support MCE broadcasting. Enable
* synchronization with a one second timeout.
@@ -1966,7 +1935,7 @@ static void apply_quirks_intel(struct cpuinfo_x86 *c)
mce_flags.skx_repmov_quirk = 1;
}
-static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
+static void zhaoxin_apply_global_quirks(struct cpuinfo_x86 *c)
{
/*
* All newer Zhaoxin CPUs support MCE broadcasting. Enable
@@ -1978,29 +1947,6 @@ static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
}
}
-/* Add per CPU specific workarounds here */
-static void __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
-{
- struct mca_config *cfg = &mca_cfg;
-
- switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- apply_quirks_amd(c);
- break;
- case X86_VENDOR_INTEL:
- apply_quirks_intel(c);
- break;
- case X86_VENDOR_ZHAOXIN:
- apply_quirks_zhaoxin(c);
- break;
- }
-
- if (cfg->monarch_timeout < 0)
- cfg->monarch_timeout = 0;
- if (cfg->bootlog != 0)
- cfg->panic_timeout = 30;
-}
-
static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c)
{
if (c->x86 != 5)
@@ -2258,6 +2204,23 @@ void mca_bsp_init(struct cpuinfo_x86 *c)
if (cap & MCG_SER_P)
mca_cfg.ser = 1;
+
+ switch (c->x86_vendor) {
+ case X86_VENDOR_AMD:
+ amd_apply_global_quirks(c);
+ break;
+ case X86_VENDOR_INTEL:
+ intel_apply_global_quirks(c);
+ break;
+ case X86_VENDOR_ZHAOXIN:
+ zhaoxin_apply_global_quirks(c);
+ break;
+ }
+
+ if (mca_cfg.monarch_timeout < 0)
+ mca_cfg.monarch_timeout = 0;
+ if (mca_cfg.bootlog != 0)
+ mca_cfg.panic_timeout = 30;
}
/*
@@ -2277,8 +2240,6 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_cap_init();
- __mcheck_cpu_apply_quirks(c);
-
if (!mce_gen_pool_init()) {
mca_cfg.disabled = 1;
pr_emerg("Couldn't allocate MCE records pool!\n");
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 9b149b9c4109..4655223ba560 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -468,8 +468,26 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
}
}
+static void intel_apply_cpu_quirks(struct cpuinfo_x86 *c)
+{
+ /*
+ * SDM documents that on family 6 bank 0 should not be written
+ * because it aliases to another special BIOS controlled
+ * register.
+ * But it's not aliased anymore on model 0x1a+
+ * Don't ignore bank 0 completely because there could be a
+ * valid event later, merely don't write CTL0.
+ *
+ * Older CPUs (prior to family 6) can't reach this point and already
+ * return early due to the check of __mcheck_cpu_ancient_init().
+ */
+ if (c->x86_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks))
+ this_cpu_ptr(mce_banks_array)[0].init = false;
+}
+
void mce_intel_feature_init(struct cpuinfo_x86 *c)
{
+ intel_apply_cpu_quirks(c);
intel_init_cmci();
intel_init_lmce();
intel_imc_init(c);
--
2.51.0
next prev parent reply other threads:[~2025-08-25 17:33 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-25 17:32 [PATCH v5 00/20] AMD MCA interrupts rework Yazen Ghannam
2025-08-25 17:32 ` [PATCH v5 01/20] x86/mce/amd: Rename threshold restart function Yazen Ghannam
2025-08-25 17:32 ` [PATCH v5 02/20] x86/mce/amd: Remove return value for mce_threshold_{create,remove}_device() Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 03/20] x86/mce/amd: Remove smca_banks_map Yazen Ghannam
2025-08-25 18:19 ` Borislav Petkov
2025-08-25 19:54 ` Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 04/20] x86/mce/amd: Put list_head in threshold_bank Yazen Ghannam
2025-09-01 15:41 ` Nikolay Borisov
2025-09-01 16:41 ` Borislav Petkov
2025-08-25 17:33 ` [PATCH v5 05/20] x86/mce: Cleanup bank processing on init Yazen Ghannam
2025-08-26 12:35 ` Borislav Petkov
2025-08-26 13:47 ` Yazen Ghannam
2025-08-26 14:33 ` Borislav Petkov
2025-08-25 17:33 ` [PATCH v5 06/20] x86/mce: Remove __mcheck_cpu_init_early() Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 07/20] x86/mce: Reorder __mcheck_cpu_init_generic() call Yazen Ghannam
2025-09-01 17:07 ` Borislav Petkov
2025-09-02 13:30 ` Yazen Ghannam
2025-09-02 16:26 ` Borislav Petkov
2025-09-02 17:14 ` Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 08/20] x86/mce: Define BSP-only init Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 09/20] x86/mce: Define BSP-only SMCA init Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 10/20] x86/mce: Do 'UNKNOWN' vendor check early Yazen Ghannam
2025-08-25 17:33 ` Yazen Ghannam [this message]
2025-08-25 17:33 ` [PATCH v5 12/20] x86/mce: Move machine_check_poll() status checks to helper functions Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 13/20] x86/mce: Unify AMD THR handler with MCA Polling Yazen Ghannam
2025-09-02 11:10 ` Borislav Petkov
2025-09-02 13:37 ` Yazen Ghannam
2025-09-02 17:04 ` Borislav Petkov
2025-09-02 17:25 ` Yazen Ghannam
2025-09-03 9:48 ` Borislav Petkov
2025-08-25 17:33 ` [PATCH v5 14/20] x86/mce: Unify AMD DFR " Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 15/20] x86/mce/amd: Enable interrupt vectors once per-CPU on SMCA systems Yazen Ghannam
2025-09-03 10:03 ` Borislav Petkov
2025-09-03 14:00 ` Yazen Ghannam
2025-09-03 15:39 ` Borislav Petkov
2025-08-25 17:33 ` [PATCH v5 16/20] x86/mce/amd: Support SMCA Corrected Error Interrupt Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 17/20] x86/mce/amd: Remove redundant reset_block() Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 18/20] x86/mce/amd: Define threshold restart function for banks Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 19/20] x86/mce: Handle AMD threshold interrupt storms Yazen Ghannam
2025-08-25 17:33 ` [PATCH v5 20/20] x86/mce: Save and use APEI corrected threshold limit Yazen Ghannam
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250825-wip-mca-updates-v5-11-865768a2eef8@amd.com \
--to=yazen.ghannam@amd.com \
--cc=Smita.KoralahalliChannabasappa@amd.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-edac@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nik.borisov@suse.com \
--cc=qiuxu.zhuo@intel.com \
--cc=rafael@kernel.org \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).