x86/mce: Unify AMD THR handler with MCA Polling

AMD systems optionally support an MCA thresholding interrupt. The interrupt
should be used as another signal to trigger MCA polling. This is similar to
how the Intel Corrected Machine Check interrupt (CMCI) is handled.

AMD MCA thresholding is managed using the MCA_MISC registers within an MCA
bank. The OS will need to modify the hardware error count field in order to
reset the threshold limit and rearm the interrupt. Management of the MCA_MISC
register should be done as a follow up to the basic MCA polling flow. It
should not be the main focus of the interrupt handler.

Furthermore, future systems will have the ability to send an MCA thresholding
interrupt to the OS even when the OS does not manage the feature, i.e.
MCA_MISC registers are Read-as-Zero/Locked.

Call the common MCA polling function when handling the MCA thresholding
interrupt. This will allow the OS to find any valid errors whether or not the
MCA thresholding feature is OS-managed. Also, this allows the common MCA
polling options and kernel parameters to apply to AMD systems.

Add a callback to the MCA polling function to check and reset any threshold
blocks that have reached their threshold limit.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20251104-wip-mca-updates-v8-0-66c8eacf67b9@amd.com

diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index d6906442f49bf98bff1b652671806114ec5ea511..ac6a98aa7bc2149d5c33f63b623dee7f14337451 100644 (file)
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -54,6 +54,12 @@
 
 static bool thresholding_irq_en;
 
+struct mce_amd_cpu_data {
+       mce_banks_t     thr_intr_banks;
+};
+
+static DEFINE_PER_CPU_READ_MOSTLY(struct mce_amd_cpu_data, mce_amd_data);
+
 static const char * const th_names[] = {
        "load_store",
        "insn_fetch",
@@ -556,6 +562,7 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr,
        if (!b.interrupt_capable)
                goto done;
 
+       __set_bit(bank, this_cpu_ptr(&mce_amd_data)->thr_intr_banks);
        b.interrupt_enable = 1;
 
        if (!mce_flags.smca) {
@@ -896,12 +903,7 @@ static void amd_deferred_error_interrupt(void)
                log_error_deferred(bank);
 }
 
-static void log_error_thresholding(unsigned int bank, u64 misc)
-{
-       _log_error_deferred(bank, misc);
-}
-
-static void log_and_reset_block(struct threshold_block *block)
+static void reset_block(struct threshold_block *block)
 {
        struct thresh_restart tr;
        u32 low = 0, high = 0;
@@ -915,23 +917,14 @@ static void log_and_reset_block(struct threshold_block *block)
        if (!(high & MASK_OVERFLOW_HI))
                return;
 
-       /* Log the MCE which caused the threshold event. */
-       log_error_thresholding(block->bank, ((u64)high << 32) | low);
-
-       /* Reset threshold block after logging error. */
        memset(&tr, 0, sizeof(tr));
        tr.b = block;
        threshold_restart_block(&tr);
 }
 
-/*
- * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt
- * goes off when error_count reaches threshold_limit.
- */
-static void amd_threshold_interrupt(void)
+static void amd_reset_thr_limit(unsigned int bank)
 {
-       struct threshold_bank **bp = this_cpu_read(threshold_banks), *thr_bank;
-       unsigned int bank, cpu = smp_processor_id();
+       struct threshold_bank **bp = this_cpu_read(threshold_banks);
        struct threshold_block *block, *tmp;
 
        /*
@@ -939,24 +932,26 @@ static void amd_threshold_interrupt(void)
         * handler is installed at boot time, but on a hotplug event the
         * interrupt might fire before the data has been initialized.
         */
-       if (!bp)
+       if (!bp || !bp[bank])
                return;
 
-       for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) {
-               if (!(per_cpu(bank_map, cpu) & BIT_ULL(bank)))
-                       continue;
-
-               thr_bank = bp[bank];
-               if (!thr_bank)
-                       continue;
+       list_for_each_entry_safe(block, tmp, &bp[bank]->miscj, miscj)
+               reset_block(block);
+}
 
-               list_for_each_entry_safe(block, tmp, &thr_bank->miscj, miscj)
-                       log_and_reset_block(block);
-       }
+/*
+ * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt
+ * goes off when error_count reaches threshold_limit.
+ */
+static void amd_threshold_interrupt(void)
+{
+       machine_check_poll(MCP_TIMESTAMP, &this_cpu_ptr(&mce_amd_data)->thr_intr_banks);
 }
 
 void amd_clear_bank(struct mce *m)
 {
+       amd_reset_thr_limit(m->bank);
+
        mce_wrmsrq(mca_msr_reg(m->bank, MCA_STATUS), 0);
 }