From: Yazen Ghannam <yazen.ghannam@amd.com>
To: <x86@kernel.org>, Tony Luck <tony.luck@intel.com>
Cc: <linux-kernel@vger.kernel.org>, <linux-edac@vger.kernel.org>,
<Smita.KoralahalliChannabasappa@amd.com>,
Yazen Ghannam <yazen.ghannam@amd.com>
Subject: [PATCH v2 05/16] x86/mce: Cleanup bank processing on init
Date: Thu, 13 Feb 2025 16:45:54 +0000 [thread overview]
Message-ID: <20250213-wip-mca-updates-v2-5-3636547fe05f@amd.com> (raw)
In-Reply-To: <20250213-wip-mca-updates-v2-0-3636547fe05f@amd.com>
From: Borislav Petkov <bp@suse.de>
Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename
that function to what it does now - prepares banks. Do this so that
generic and vendor banks init goes first so that settings done during
that init can take effect before the first bank polling takes place.
Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks()
as it already loops over the banks.
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Notes:
Link:
https://lore.kernel.org/r/20221206173607.1185907-2-yazen.ghannam@amd.com
v1->v2:
* New in v2, but based on old patch (see link).
* Kept old tags for reference.
arch/x86/include/asm/mce.h | 3 +-
arch/x86/kernel/cpu/mce/core.c | 63 ++++++++++++------------------------------
2 files changed, 19 insertions(+), 47 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 2701aca04aec..36ff81c1b3b1 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -290,8 +290,7 @@ DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
- MCP_DONTLOG = BIT(2), /* only clear, don't log */
- MCP_QUEUE_LOG = BIT(3), /* only queue to genpool */
+ MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */
};
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index d39af20154c7..d85bd861ecca 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -785,9 +785,6 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
continue;
log_it:
- if (flags & MCP_DONTLOG)
- goto clear_it;
-
mce_read_aux(&err, i);
m->severity = mce_severity(m, NULL, NULL, false);
/*
@@ -1807,7 +1804,7 @@ static void __mcheck_cpu_mce_banks_init(void)
/*
* Init them all, __mcheck_cpu_apply_quirks() is going to apply
* the required vendor quirks before
- * __mcheck_cpu_init_clear_banks() does the final bank setup.
+ * __mcheck_cpu_init_prepare_banks() does the final bank setup.
*/
b->ctl = -1ULL;
b->init = true;
@@ -1846,21 +1843,8 @@ static void __mcheck_cpu_cap_init(void)
static void __mcheck_cpu_init_generic(void)
{
- enum mcp_flags m_fl = 0;
- mce_banks_t all_banks;
u64 cap;
- if (!mca_cfg.bootlog)
- m_fl = MCP_DONTLOG;
-
- /*
- * Log the machine checks left over from the previous reset. Log them
- * only, do not start processing them. That will happen in mcheck_late_init()
- * when all consumers have been registered on the notifier chain.
- */
- bitmap_fill(all_banks, MAX_NR_BANKS);
- machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
-
cr4_set_bits(X86_CR4_MCE);
rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -1868,36 +1852,23 @@ static void __mcheck_cpu_init_generic(void)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
}
-static void __mcheck_cpu_init_clear_banks(void)
+static void __mcheck_cpu_init_prepare_banks(void)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+ u64 msrval;
int i;
- for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
- struct mce_bank *b = &mce_banks[i];
+ /*
+ * Log the machine checks left over from the previous reset. Log them
+ * only, do not start processing them. That will happen in mcheck_late_init()
+ * when all consumers have been registered on the notifier chain.
+ */
+ if (mca_cfg.bootlog) {
+ mce_banks_t all_banks;
- if (!b->init)
- continue;
- wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
- wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+ bitmap_fill(all_banks, MAX_NR_BANKS);
+ machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
}
-}
-
-/*
- * Do a final check to see if there are any unused/RAZ banks.
- *
- * This must be done after the banks have been initialized and any quirks have
- * been applied.
- *
- * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
- * Otherwise, a user who disables a bank will not be able to re-enable it
- * without a system reboot.
- */
-static void __mcheck_cpu_check_banks(void)
-{
- struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
- u64 msrval;
- int i;
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
struct mce_bank *b = &mce_banks[i];
@@ -1905,6 +1876,9 @@ static void __mcheck_cpu_check_banks(void)
if (!b->init)
continue;
+ wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+ wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+
rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
b->init = !!msrval;
}
@@ -2310,8 +2284,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_early(c);
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
- __mcheck_cpu_init_clear_banks();
- __mcheck_cpu_check_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_setup_timer();
}
@@ -2479,7 +2452,7 @@ static void mce_syscore_resume(void)
{
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
}
static struct syscore_ops mce_syscore_ops = {
@@ -2497,7 +2470,7 @@ static void mce_cpu_restart(void *data)
if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
- __mcheck_cpu_init_clear_banks();
+ __mcheck_cpu_init_prepare_banks();
__mcheck_cpu_init_timer();
}
--
2.43.0
next prev parent reply other threads:[~2025-02-13 16:46 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-13 16:45 [PATCH v2 00/16] AMD MCA interrupts rework Yazen Ghannam
2025-02-13 16:45 ` [PATCH v2 01/16] x86/mce: Don't remove sysfs if thresholding sysfs init fails Yazen Ghannam
2025-02-17 6:58 ` Zhuo, Qiuxu
2025-02-13 16:45 ` [PATCH v2 02/16] x86/mce/amd: Remove return value for mce_threshold_create_device() Yazen Ghannam
2025-02-17 7:11 ` Zhuo, Qiuxu
2025-02-17 14:09 ` Yazen Ghannam
2025-02-13 16:45 ` [PATCH v2 03/16] x86/mce/amd: Remove smca_banks_map Yazen Ghannam
2025-02-17 7:57 ` Zhuo, Qiuxu
2025-02-17 14:17 ` Yazen Ghannam
2025-02-13 16:45 ` [PATCH v2 04/16] x86/mce/amd: Put list_head in threshold_bank Yazen Ghannam
2025-02-18 1:28 ` Zhuo, Qiuxu
2025-02-13 16:45 ` Yazen Ghannam [this message]
2025-02-13 22:32 ` [PATCH v2 05/16] x86/mce: Cleanup bank processing on init Luck, Tony
2025-02-17 13:55 ` Yazen Ghannam
2025-02-18 16:40 ` Luck, Tony
2025-02-18 2:15 ` Zhuo, Qiuxu
2025-02-13 16:45 ` [PATCH v2 06/16] x86/mce: Remove __mcheck_cpu_init_early() Yazen Ghannam
2025-02-18 3:00 ` Zhuo, Qiuxu
2025-02-19 15:53 ` Yazen Ghannam
2025-02-27 15:25 ` Borislav Petkov
2025-02-27 16:31 ` Yazen Ghannam
2025-02-27 19:33 ` Borislav Petkov
2025-02-27 19:59 ` Yazen Ghannam
2025-02-27 20:48 ` Borislav Petkov
2025-02-28 14:29 ` Yazen Ghannam
2025-02-13 16:45 ` [PATCH v2 07/16] x86/mce: Define BSP-only init Yazen Ghannam
2025-02-18 3:16 ` Zhuo, Qiuxu
2025-02-19 15:57 ` Yazen Ghannam
2025-02-20 1:37 ` Zhuo, Qiuxu
2025-02-20 14:36 ` Yazen Ghannam
2025-02-24 13:28 ` Zhuo, Qiuxu
2025-02-13 16:45 ` [PATCH v2 08/16] x86/mce: Define BSP-only SMCA init Yazen Ghannam
2025-02-18 3:33 ` Zhuo, Qiuxu
2025-02-19 16:01 ` Yazen Ghannam
2025-02-13 16:45 ` [PATCH v2 09/16] x86/mce: Do 'UNKNOWN' vendor check early Yazen Ghannam
2025-02-18 5:31 ` Zhuo, Qiuxu
2025-02-13 16:45 ` [PATCH v2 10/16] x86/mce: Separate global and per-CPU quirks Yazen Ghannam
2025-02-18 6:03 ` Zhuo, Qiuxu
2025-02-19 16:06 ` Yazen Ghannam
2025-02-20 1:27 ` Zhuo, Qiuxu
2025-02-20 14:37 ` Yazen Ghannam
2025-02-13 16:46 ` [PATCH v2 11/16] x86/mce: Move machine_check_poll() status checks to helper functions Yazen Ghannam
2025-02-18 6:29 ` Zhuo, Qiuxu
2025-02-13 16:46 ` [PATCH v2 12/16] x86/mce: Unify AMD THR handler with MCA Polling Yazen Ghannam
2025-02-18 6:42 ` Zhuo, Qiuxu
2025-02-19 16:07 ` Yazen Ghannam
2025-02-13 16:46 ` [PATCH v2 13/16] x86/mce: Unify AMD DFR " Yazen Ghannam
2025-02-18 7:37 ` Zhuo, Qiuxu
2025-02-19 16:09 ` Yazen Ghannam
2025-02-20 1:41 ` Zhuo, Qiuxu
2025-02-20 14:41 ` Yazen Ghannam
2025-02-24 13:31 ` Zhuo, Qiuxu
2025-02-13 16:46 ` [PATCH v2 14/16] x86/mce/amd: Enable interrupt vectors once per-CPU on SMCA systems Yazen Ghannam
2025-02-18 8:23 ` Zhuo, Qiuxu
2025-02-19 16:16 ` Yazen Ghannam
2025-02-13 16:46 ` [PATCH v2 15/16] x86/mce/amd: Support SMCA Corrected Error Interrupt Yazen Ghannam
2025-02-13 22:34 ` Luck, Tony
2025-02-17 14:06 ` Yazen Ghannam
2025-02-18 13:27 ` Zhuo, Qiuxu
2025-02-19 16:19 ` Yazen Ghannam
2025-02-13 16:46 ` [PATCH v2 16/16] x86/mce: Handle AMD threshold interrupt storms Yazen Ghannam
2025-02-18 13:51 ` Zhuo, Qiuxu
2025-02-13 22:40 ` [PATCH v2 00/16] AMD MCA interrupts rework Luck, Tony
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=20250213-wip-mca-updates-v2-5-3636547fe05f@amd.com \
--to=yazen.ghannam@amd.com \
--cc=Smita.KoralahalliChannabasappa@amd.com \
--cc=linux-edac@vger.kernel.org \
--cc=linux-kernel@vger.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