[PATCH 0/2] Interrupt Storm support on AMD SMCA systems.

[PATCH 0/2] Interrupt Storm support on AMD SMCA systems.

[Avadhut Naik]

This set adds support to handle threshold interrupt storms on AMD SMCA
systems.

The first patch fixes a bug which prevents subsequent errors after a CMCI
storm subsides from being logged.

The second patch adds support for interrupt storms on AMD SMCA systems.

Avadhut Naik (1):
  x86/mce: Do not clear bank's poll bit in mce_poll_banks on AMD SMCA
    systems

Smita Koralahalli (1):
  x86/mce: Handle AMD threshold interrupt storms

 arch/x86/kernel/cpu/mce/amd.c       | 5 +++++
 arch/x86/kernel/cpu/mce/internal.h  | 2 ++
 arch/x86/kernel/cpu/mce/threshold.c | 6 +++++-
 3 files changed, 12 insertions(+), 1 deletion(-)


base-commit: c4ce736c24f6fca2b73845022e9e80e5b5bedc83
-- 
2.43.0

[PATCH 1/2] x86/mce: Do not clear bank's poll bit in mce_poll_banks on AMD SMCA systems

[Avadhut Naik]

Currently, when a CMCI storm, detected on a Machine Check bank, subsides,
the bank's corresponding bit in the mce_poll_banks per-CPU variable is
cleared unconditionally through cmci_storm_end().

On AMD SMCA systems, this essentially disables polling on that particular
bank on that CPU. Consequently, any subsequent correctable errors or
storms will not be logged.

Since AMD SMCA systems allow banks to be managed by both polling and
interrupts, the polling banks bitmap for a CPU, i.e., mce_poll_banks,
should not be modified when a storm subsides.

Fixes: 7eae17c4add5 ("x86/mce: Add per-bank CMCI storm mitigation")
Cc: stable@vger.kernel.org
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
---
 arch/x86/kernel/cpu/mce/threshold.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index eebaa633df80..f19dd5bc2969 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -98,7 +98,8 @@ void cmci_storm_end(unsigned int bank)
 {
 	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
 
-	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+	if (!mce_flags.amd_threshold)
+		__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
 	storm->banks[bank].history = 0;
 	storm->banks[bank].in_storm_mode = false;
 
-- 
2.43.0

[tip: ras/core] x86/mce: Do not clear bank's poll bit in mce_poll_banks on AMD SMCA systems

[tip-bot2 for Avadhut Naik]

The following commit has been merged into the ras/core branch of tip:

Commit-ID:     d7ac083f095d894a0b8ac0573516bfd035e6b25a
Gitweb:        https://git.kernel.org/tip/d7ac083f095d894a0b8ac0573516bfd035e6b25a
Author:        Avadhut Naik <avadhut.naik@amd.com>
AuthorDate:    Fri, 21 Nov 2025 19:04:04 
Committer:     Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Fri, 21 Nov 2025 20:33:12 +01:00

x86/mce: Do not clear bank's poll bit in mce_poll_banks on AMD SMCA systems

Currently, when a CMCI storm detected on a Machine Check bank, subsides, the
bank's corresponding bit in the mce_poll_banks per-CPU variable is cleared
unconditionally by cmci_storm_end().

On AMD SMCA systems, this essentially disables polling on that particular bank
on that CPU. Consequently, any subsequent correctable errors or storms will not
be logged.

Since AMD SMCA systems allow banks to be managed by both polling and
interrupts, the polling banks bitmap for a CPU, i.e., mce_poll_banks, should
not be modified when a storm subsides.

Fixes: 7eae17c4add5 ("x86/mce: Add per-bank CMCI storm mitigation")
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20251121190542.2447913-2-avadhut.naik@amd.com
---
 arch/x86/kernel/cpu/mce/threshold.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index eebaa63..f19dd5b 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -98,7 +98,8 @@ void cmci_storm_end(unsigned int bank)
 {
 	struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
 
-	__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
+	if (!mce_flags.amd_threshold)
+		__clear_bit(bank, this_cpu_ptr(mce_poll_banks));
 	storm->banks[bank].history = 0;
 	storm->banks[bank].in_storm_mode = false;
 

[PATCH 2/2] x86/mce: Handle AMD threshold interrupt storms

[Avadhut Naik]

From: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>

Extend the logic of handling CMCI storms to AMD threshold interrupts.

Rely on the similar approach as of Intel's CMCI to mitigate storms per CPU
and per bank. But, unlike CMCI, do not set thresholds and reduce interrupt
rate on a storm. Rather, disable the interrupt on the corresponding CPU
and bank. Re-enable back the interrupts if enough consecutive polls of the
bank show no corrected errors (30, as programmed by Intel).

Turning off the threshold interrupts would be a better solution on AMD
systems as other error severities will still be handled even if the
threshold interrupts are disabled.

  [Tony: Small tweak because mce_handle_storm() isn't a pointer now]
  [Yazen: Rebase and simplify]
  [Avadhut: Remove check to not clear bank's bit in mce_poll_banks and fix
  checkpatch warnings.]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
---
NOTE: Since this patch has morphed from its previous submission, have
removed the Reviewed-by tag.
---
 arch/x86/kernel/cpu/mce/amd.c       | 5 +++++
 arch/x86/kernel/cpu/mce/internal.h  | 2 ++
 arch/x86/kernel/cpu/mce/threshold.c | 3 +++
 3 files changed, 10 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 5c3287a46c8f..3f1dda355307 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -852,6 +852,11 @@ static void amd_deferred_error_interrupt(void)
 	machine_check_poll(MCP_TIMESTAMP, &this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
 }
 
+void mce_amd_handle_storm(unsigned int bank, bool on)
+{
+	threshold_restart_bank(bank, on);
+}
+
 static void amd_reset_thr_limit(unsigned int bank)
 {
 	threshold_restart_bank(bank, true);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 4cf16fa7c260..a31cf984619c 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -269,6 +269,7 @@ void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m);
 #ifdef CONFIG_X86_MCE_AMD
 void mce_threshold_create_device(unsigned int cpu);
 void mce_threshold_remove_device(unsigned int cpu);
+void mce_amd_handle_storm(unsigned int bank, bool on);
 extern bool amd_filter_mce(struct mce *m);
 bool amd_mce_usable_address(struct mce *m);
 void amd_clear_bank(struct mce *m);
@@ -301,6 +302,7 @@ void smca_bsp_init(void);
 #else
 static inline void mce_threshold_create_device(unsigned int cpu)	{ }
 static inline void mce_threshold_remove_device(unsigned int cpu)	{ }
+static inline void mce_amd_handle_storm(unsigned int bank, bool on)	{ }
 static inline bool amd_filter_mce(struct mce *m) { return false; }
 static inline bool amd_mce_usable_address(struct mce *m) { return false; }
 static inline void amd_clear_bank(struct mce *m) { }
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index f19dd5bc2969..0d13c9ffcba0 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -76,6 +76,9 @@ static void mce_handle_storm(unsigned int bank, bool on)
 	case X86_VENDOR_INTEL:
 		mce_intel_handle_storm(bank, on);
 		break;
+	case X86_VENDOR_AMD:
+		mce_amd_handle_storm(bank, on);
+		break;
 	}
 }
 
-- 
2.43.0

[tip: ras/core] x86/mce: Handle AMD threshold interrupt storms

[tip-bot2 for Smita Koralahalli]

The following commit has been merged into the ras/core branch of tip:

Commit-ID:     5c4663ed1eac01987a1421f059380db48ab7b1a3
Gitweb:        https://git.kernel.org/tip/5c4663ed1eac01987a1421f059380db48ab7b1a3
Author:        Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
AuthorDate:    Fri, 21 Nov 2025 19:04:05 
Committer:     Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Fri, 21 Nov 2025 20:41:10 +01:00

x86/mce: Handle AMD threshold interrupt storms

Extend the logic of handling CMCI storms to AMD threshold interrupts.

Rely on the similar approach as of Intel's CMCI to mitigate storms per CPU and
per bank. But, unlike CMCI, do not set thresholds and reduce interrupt rate on
a storm. Rather, disable the interrupt on the corresponding CPU and bank.
Re-enable back the interrupts if enough consecutive polls of the bank show no
corrected errors (30, as programmed by Intel).

Turning off the threshold interrupts would be a better solution on AMD systems
as other error severities will still be handled even if the threshold
interrupts are disabled.

  [ Tony: Small tweak because mce_handle_storm() isn't a pointer now ]
  [ Yazen: Rebase and simplify ]
  [ Avadhut: Remove check to not clear bank's bit in mce_poll_banks and fix
    checkpatch warnings. ]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Avadhut Naik <avadhut.naik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://patch.msgid.link/20251121190542.2447913-3-avadhut.naik@amd.com
---
 arch/x86/kernel/cpu/mce/amd.c       | 5 +++++
 arch/x86/kernel/cpu/mce/internal.h  | 2 ++
 arch/x86/kernel/cpu/mce/threshold.c | 3 +++
 3 files changed, 10 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 5c3287a..3f1dda3 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -852,6 +852,11 @@ static void amd_deferred_error_interrupt(void)
 	machine_check_poll(MCP_TIMESTAMP, &this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
 }
 
+void mce_amd_handle_storm(unsigned int bank, bool on)
+{
+	threshold_restart_bank(bank, on);
+}
+
 static void amd_reset_thr_limit(unsigned int bank)
 {
 	threshold_restart_bank(bank, true);
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 4cf16fa..a31cf98 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -269,6 +269,7 @@ void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m);
 #ifdef CONFIG_X86_MCE_AMD
 void mce_threshold_create_device(unsigned int cpu);
 void mce_threshold_remove_device(unsigned int cpu);
+void mce_amd_handle_storm(unsigned int bank, bool on);
 extern bool amd_filter_mce(struct mce *m);
 bool amd_mce_usable_address(struct mce *m);
 void amd_clear_bank(struct mce *m);
@@ -301,6 +302,7 @@ void smca_bsp_init(void);
 #else
 static inline void mce_threshold_create_device(unsigned int cpu)	{ }
 static inline void mce_threshold_remove_device(unsigned int cpu)	{ }
+static inline void mce_amd_handle_storm(unsigned int bank, bool on)	{ }
 static inline bool amd_filter_mce(struct mce *m) { return false; }
 static inline bool amd_mce_usable_address(struct mce *m) { return false; }
 static inline void amd_clear_bank(struct mce *m) { }
diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c
index f19dd5b..0d13c9f 100644
--- a/arch/x86/kernel/cpu/mce/threshold.c
+++ b/arch/x86/kernel/cpu/mce/threshold.c
@@ -76,6 +76,9 @@ static void mce_handle_storm(unsigned int bank, bool on)
 	case X86_VENDOR_INTEL:
 		mce_intel_handle_storm(bank, on);
 		break;
+	case X86_VENDOR_AMD:
+		mce_amd_handle_storm(bank, on);
+		break;
 	}
 }