| 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: <20251028231825.GDaQFPQflC7gyVOwMa@fat_crate.local>
Date: Wed, 29 Oct 2025 00:18:25 +0100
From: Borislav Petkov <bp@...en8.de>
To: Yazen Ghannam <yazen.ghannam@....com>
Cc: x86@...nel.org, Tony Luck <tony.luck@...el.com>,
"Rafael J. Wysocki" <rafael@...nel.org>,
Len Brown <lenb@...nel.org>, linux-kernel@...r.kernel.org,
linux-edac@...r.kernel.org, Smita.KoralahalliChannabasappa@....com,
Qiuxu Zhuo <qiuxu.zhuo@...el.com>,
Nikolay Borisov <nik.borisov@...e.com>,
Bert Karwatzki <spasswolf@....de>, linux-acpi@...r.kernel.org
Subject: Re: [PATCH v7 2/8] x86/mce: Unify AMD DFR handler with MCA Polling
On Tue, Oct 28, 2025 at 04:37:19PM -0400, Yazen Ghannam wrote:
> Yep, that's it. Much cleaner. :)
:-)
Final version:
>From dd705221b2b3fb06fd2dc25dd51a8aaa1b1bd6d5 Mon Sep 17 00:00:00 2001
From: Yazen Ghannam <yazen.ghannam@....com>
Date: Thu, 16 Oct 2025 16:37:48 +0000
Subject: [PATCH] x86/mce/amd: Enable interrupt vectors once per-CPU on SMCA
systems
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.
Guidance from hardware designers is that the LVT offsets provided from the
platform should be used. The kernel should not try to enforce specific values.
However, the kernel should check that an LVT offset is not reused for multiple
sources.
Therefore, remove the extra checking and value enforcement from the MCE code.
The "reuse/conflict" case is already handled in setup_APIC_eilvt().
[ bp: Simplify and drop some comments. ]
Signed-off-by: Yazen Ghannam <yazen.ghannam@....com>
Signed-off-by: Borislav Petkov (AMD) <bp@...en8.de>
Reviewed-by: Tony Luck <tony.luck@...el.com>
Tested-by: Tony Luck <tony.luck@...el.com>
Link: https://lore.kernel.org/all/20251016-wip-mca-updates-v7-0-5c139a4062cb@amd.com
---
arch/x86/kernel/cpu/mce/amd.c | 121 +++++++++++++++------------------
arch/x86/kernel/cpu/mce/core.c | 19 +-----
2 files changed, 56 insertions(+), 84 deletions(-)
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d9f9ee7db5c8..0f4a01056ad3 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 +54,10 @@ static bool thresholding_irq_en;
struct mce_amd_cpu_data {
mce_banks_t thr_intr_banks;
mce_banks_t dfr_intr_banks;
+
+ u32 thr_intr_en: 1,
+ dfr_intr_en: 1,
+ __resv: 30;
};
static DEFINE_PER_CPU_READ_MOSTLY(struct mce_amd_cpu_data, mce_amd_data);
@@ -271,6 +272,7 @@ 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 +303,8 @@ 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);
}
@@ -377,6 +379,14 @@ 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,
@@ -385,14 +395,6 @@ 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);
@@ -473,41 +475,6 @@ 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 get_block_address(u32 current_addr, u32 low, u32 high,
unsigned int bank, unsigned int block,
unsigned int cpu)
@@ -543,12 +510,10 @@ static u32 get_block_address(u32 current_addr, u32 low, u32 high,
return addr;
}
-static int
-prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
- int offset, u32 misc_high)
+static int 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;
@@ -568,18 +533,10 @@ 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;
@@ -587,7 +544,6 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
done:
mce_threshold_block_init(&b, offset);
-out:
return offset;
}
@@ -678,6 +634,32 @@ static void amd_apply_cpu_quirks(struct cpuinfo_x86 *c)
mce_banks[0].ctl = 0;
}
+/*
+ * 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 (rdmsrq_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 = 1;
+
+ 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 = 1;
+}
+
/* cpu init entry point, called from mce.c with preempt off */
void mce_amd_feature_init(struct cpuinfo_x86 *c)
{
@@ -689,10 +671,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *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) {
@@ -713,9 +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 smca_bsp_init(void)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 7be062429ce3..4aff14e04287 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -726,24 +726,11 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
* 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and
* log it.
*/
-static bool smca_should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
+static bool smca_should_log_poll_error(struct mce *m)
{
- struct mce *m = &err->m;
-
- /*
- * If the MCA_STATUS register has a deferred error, then continue using it as
- * the status register.
- *
- * MCA_DESTAT will be cleared at the end of the handler.
- */
- if ((m->status & MCI_STATUS_VAL) && (m->status & MCI_STATUS_DEFERRED))
+ if (m->status & MCI_STATUS_VAL)
return true;
- /*
- * If the MCA_DESTAT register has a deferred error, then use it instead.
- *
- * MCA_STATUS will not be cleared at the end of the handler.
- */
m->status = mce_rdmsrq(MSR_AMD64_SMCA_MCx_DESTAT(m->bank));
if ((m->status & MCI_STATUS_VAL) && (m->status & MCI_STATUS_DEFERRED)) {
m->kflags |= MCE_CHECK_DFR_REGS;
@@ -780,7 +767,7 @@ static bool should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
struct mce *m = &err->m;
if (mce_flags.smca)
- return smca_should_log_poll_error(flags, err);
+ return smca_should_log_poll_error(m);
/* If this entry is not valid, ignore it. */
if (!(m->status & MCI_STATUS_VAL))
--
2.51.0
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
Powered by blists - more mailing lists