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 14/16] x86/mce/amd: Enable interrupt vectors once per-CPU on SMCA systems
Date: Thu, 13 Feb 2025 16:46:03 +0000 [thread overview]
Message-ID: <20250213-wip-mca-updates-v2-14-3636547fe05f@amd.com> (raw)
In-Reply-To: <20250213-wip-mca-updates-v2-0-3636547fe05f@amd.com>
Scalable MCA systems have a per-CPU register that gives the APIC LVT
offset for the thresholding and deferred error interrupts.
Currently, this register is read once to set up the deferred error
interrupt and then read again for each thresholding block. Furthermore,
the APIC LVT registers are configured each time, but they only need to
be configured once per-CPU.
Move the APIC LVT setup to the early part of CPU init, so that the
registers are set up once. Also, this ensures that the kernel is ready
to service the interrupts before the individual error sources (each MCA
bank) are enabled.
Apply this change only to SMCA systems to avoid breaking any legacy
behavior. The deferred error interrupt is technically advertised by the
SUCCOR feature. However, this was first made available on SMCA systems.
Therefore, only set up the deferred error interrupt on SMCA systems and
simplify the code.
Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Notes:
Link:
https://lore.kernel.org/r/20240523155641.2805411-9-yazen.ghannam@amd.com
v1->v2:
* Use new per-CPU struct.
* Don't set up interrupt vectors.
arch/x86/kernel/cpu/mce/amd.c | 113 ++++++++++++++++++------------------------
1 file changed, 48 insertions(+), 65 deletions(-)
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 5f547f5b3de0..75a48f484815 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -43,9 +43,6 @@
/* Deferred error settings */
#define MSR_CU_DEF_ERR 0xC0000410
#define MASK_DEF_LVTOFF 0x000000F0
-#define MASK_DEF_INT_TYPE 0x00000006
-#define DEF_LVT_OFF 0x2
-#define DEF_INT_TYPE_APIC 0x2
/* Scalable MCA: */
@@ -57,6 +54,8 @@ static bool thresholding_irq_en;
struct mce_amd_cpu_data {
mce_banks_t thr_intr_banks;
mce_banks_t dfr_intr_banks;
+ bool thr_intr_en;
+ bool dfr_intr_en;
};
static DEFINE_PER_CPU_READ_MOSTLY(struct mce_amd_cpu_data, mce_amd_data);
@@ -271,6 +270,7 @@ void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
static void smca_configure(unsigned int bank, unsigned int cpu)
{
+ struct mce_amd_cpu_data *data = this_cpu_ptr(&mce_amd_data);
u8 *bank_counts = this_cpu_ptr(smca_bank_counts);
const struct smca_hwid *s_hwid;
unsigned int i, hwid_mcatype;
@@ -301,8 +301,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
* APIC based interrupt. First, check that no interrupt has been
* set.
*/
- if ((low & BIT(5)) && !((high >> 5) & 0x3)) {
- __set_bit(bank, this_cpu_ptr(&mce_amd_data)->dfr_intr_banks);
+ if ((low & BIT(5)) && !((high >> 5) & 0x3) && data->dfr_intr_en) {
+ __set_bit(bank, data->dfr_intr_banks);
high |= BIT(5);
}
@@ -378,6 +378,14 @@ static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
{
int msr = (hi & MASK_LVTOFF_HI) >> 20;
+ /*
+ * On SMCA CPUs, LVT offset is programmed at a different MSR, and
+ * the BIOS provides the value. The original field where LVT offset
+ * was set is reserved. Return early here:
+ */
+ if (mce_flags.smca)
+ return false;
+
if (apic < 0) {
pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
"for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
@@ -386,14 +394,6 @@ static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
}
if (apic != msr) {
- /*
- * On SMCA CPUs, LVT offset is programmed at a different MSR, and
- * the BIOS provides the value. The original field where LVT offset
- * was set is reserved. Return early here:
- */
- if (mce_flags.smca)
- return false;
-
pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
"for bank %d, block %d (MSR%08X=0x%x%08x)\n",
b->cpu, apic, b->bank, b->block, b->address, hi, lo);
@@ -474,41 +474,6 @@ static int setup_APIC_mce_threshold(int reserved, int new)
return reserved;
}
-static int setup_APIC_deferred_error(int reserved, int new)
-{
- if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
- APIC_EILVT_MSG_FIX, 0))
- return new;
-
- return reserved;
-}
-
-static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
-{
- u32 low = 0, high = 0;
- int def_offset = -1, def_new;
-
- if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
- return;
-
- def_new = (low & MASK_DEF_LVTOFF) >> 4;
- if (!(low & MASK_DEF_LVTOFF)) {
- pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
- def_new = DEF_LVT_OFF;
- low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
- }
-
- def_offset = setup_APIC_deferred_error(def_offset, def_new);
- if ((def_offset == def_new) &&
- (deferred_error_int_vector != amd_deferred_error_interrupt))
- deferred_error_int_vector = amd_deferred_error_interrupt;
-
- if (!mce_flags.smca)
- low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
-
- wrmsr(MSR_CU_DEF_ERR, low, high);
-}
-
static u32 smca_get_block_address(unsigned int bank, unsigned int block,
unsigned int cpu)
{
@@ -551,7 +516,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
int offset, u32 misc_high)
{
unsigned int cpu = smp_processor_id();
- u32 smca_low, smca_high;
struct threshold_block b;
int new;
@@ -571,18 +535,10 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
__set_bit(bank, this_cpu_ptr(&mce_amd_data)->thr_intr_banks);
b.interrupt_enable = 1;
- if (!mce_flags.smca) {
- new = (misc_high & MASK_LVTOFF_HI) >> 20;
- goto set_offset;
- }
-
- /* Gather LVT offset for thresholding: */
- if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high))
- goto out;
-
- new = (smca_low & SMCA_THR_LVT_OFF) >> 12;
+ if (mce_flags.smca)
+ goto done;
-set_offset:
+ new = (misc_high & MASK_LVTOFF_HI) >> 20;
offset = setup_APIC_mce_threshold(offset, new);
if (offset == new)
thresholding_irq_en = true;
@@ -590,7 +546,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
done:
mce_threshold_block_init(&b, offset);
-out:
return offset;
}
@@ -659,6 +614,32 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
wrmsrl(MSR_K7_HWCR, hwcr);
}
+/*
+ * Enable the APIC LVT interrupt vectors once per-CPU. This should be done before hardware is
+ * ready to send interrupts.
+ *
+ * Individual error sources are enabled later during per-bank init.
+ */
+static void smca_enable_interrupt_vectors(void)
+{
+ struct mce_amd_cpu_data *data = this_cpu_ptr(&mce_amd_data);
+ u64 mca_intr_cfg, offset;
+
+ if (!mce_flags.smca || !mce_flags.succor)
+ return;
+
+ if (rdmsrl_safe(MSR_CU_DEF_ERR, &mca_intr_cfg))
+ return;
+
+ offset = (mca_intr_cfg & SMCA_THR_LVT_OFF) >> 12;
+ if (!setup_APIC_eilvt(offset, THRESHOLD_APIC_VECTOR, APIC_EILVT_MSG_FIX, 0))
+ data->thr_intr_en = true;
+
+ offset = (mca_intr_cfg & MASK_DEF_LVTOFF) >> 4;
+ if (!setup_APIC_eilvt(offset, DEFERRED_ERROR_VECTOR, APIC_EILVT_MSG_FIX, 0))
+ data->dfr_intr_en = true;
+}
+
static void amd_apply_quirks(struct cpuinfo_x86 *c)
{
struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
@@ -690,11 +671,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
amd_apply_quirks(c);
mce_flags.amd_threshold = 1;
+ smca_enable_interrupt_vectors();
for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
- if (mce_flags.smca)
+ if (mce_flags.smca) {
smca_configure(bank, cpu);
+ if (!this_cpu_ptr(&mce_amd_data)->thr_intr_en)
+ continue;
+ }
+
disable_err_thresholding(c, bank);
for (block = 0; block < NR_BLOCKS; ++block) {
@@ -715,9 +701,6 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
offset = prepare_threshold_block(bank, block, address, offset, high);
}
}
-
- if (mce_flags.succor)
- deferred_error_interrupt_enable(c);
}
void mce_smca_cpu_init(void)
--
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 ` [PATCH v2 05/16] x86/mce: Cleanup bank processing on init Yazen Ghannam
2025-02-13 22:32 ` 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 ` Yazen Ghannam [this message]
2025-02-18 8:23 ` [PATCH v2 14/16] x86/mce/amd: Enable interrupt vectors once per-CPU on SMCA systems 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-v2-14-3636547fe05f@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