Merge tag 'ras_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Borislav Petkov:

 - Fix the APEI MCE callback handler to consult the hardware about the
   granularity of the memory error instead of hard-coding it

 - Offline memory pages on Intel machines after 2 errors reported per
   page

* tag 'ras_core_for_v6.1_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mce: Retrieve poison range from hardware
  RAS/CEC: Reduce offline page threshold for Intel systems

Author: torvalds

arch/x86/kernel/cpu/mce/apei.c

@@ -29,15 +29,26 @@
 void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err)
 {
 	struct mce m;
+	int lsb;
 
 	if (!(mem_err->validation_bits & CPER_MEM_VALID_PA))
 		return;
 
+	/*
+	 * Even if the ->validation_bits are set for address mask,
+	 * to be extra safe, check and reject an error radius '0',
+	 * and fall back to the default page size.
+	 */
+	if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK)
+		lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT);
+	else
+		lsb = PAGE_SHIFT;
+
 	mce_setup(&m);
 	m.bank = -1;
 	/* Fake a memory read error with unknown channel */
 	m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f;
-	m.misc = (MCI_MISC_ADDR_PHYS << 6) | PAGE_SHIFT;
+	m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb;
 
 	if (severity >= GHES_SEV_RECOVERABLE)
 		m.status |= MCI_STATUS_UC;

drivers/ras/cec.c

@@ -556,6 +556,14 @@ static int __init cec_init(void)
 	if (ce_arr.disabled)
 		return -ENODEV;
 
+	/*
+	 * Intel systems may avoid uncorrectable errors
+	 * if pages with corrected errors are aggressively
+	 * taken offline.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+		action_threshold = 2;
+
 	ce_arr.array = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!ce_arr.array) {
 		pr_err("Error allocating CE array page!\n");