Merge tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 RAS updates from Thomas Gleixner:
 "RAS updates from Borislav Petkov:

   - Unmap a whole guest page if an MCE is encountered in it to avoid
     follow-on MCEs leading to the guest crashing, by Tony Luck.

     This change collided with the entry changes and the merge
     resolution would have been rather unpleasant. To avoid that the
     entry branch was merged in before applying this. The resulting code
     did not change over the rebase.

   - AMD MCE error thresholding machinery cleanup and hotplug
     sanitization, by Thomas Gleixner.

   - Change the MCE notifiers to denote whether they have handled the
     error and not break the chain early by returning NOTIFY_STOP, thus
     giving the opportunity for the later handlers in the chain to see
     it. By Tony Luck.

   - Add AMD family 0x17, models 0x60-6f support, by Alexander Monakov.

   - Last but not least, the usual round of fixes and improvements"

* tag 'ras-core-2020-06-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/mce/dev-mcelog: Fix -Wstringop-truncation warning about strncpy()
  x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned
  EDAC/amd64: Add AMD family 17h model 60h PCI IDs
  hwmon: (k10temp) Add AMD family 17h model 60h PCI match
  x86/amd_nb: Add AMD family 17h model 60h PCI IDs
  x86/mcelog: Add compat_ioctl for 32-bit mcelog support
  x86/mce: Drop bogus comment about mce.kflags
  x86/mce: Fixup exception only for the correct MCEs
  EDAC: Drop the EDAC report status checks
  x86/mce: Add mce=print_all option
  x86/mce: Change default MCE logger to check mce->kflags
  x86/mce: Fix all mce notifiers to update the mce->kflags bitmask
  x86/mce: Add a struct mce.kflags field
  x86/mce: Convert the CEC to use the MCE notifier
  x86/mce: Rename "first" function as "early"
  x86/mce/amd, edac: Remove report_gart_errors
  x86/mce/amd: Make threshold bank setting hotplug robust
  x86/mce/amd: Cleanup threshold device remove path
  x86/mce/amd: Straighten CPU hotplug path
  x86/mce/amd: Sanitize thresholding device creation hotplug path
  ...

1 files changed, 4 insertions, 24 deletions

diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 8874b7722b2f..2b5401db56ad 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -10,15 +10,8 @@ static struct amd_decoder_ops fam_ops;
 
 static u8 xec_mask	 = 0xf;
 
-static bool report_gart_errors;
 static void (*decode_dram_ecc)(int node_id, struct mce *m);
 
-void amd_report_gart_errors(bool v)
-{
-	report_gart_errors = v;
-}
-EXPORT_SYMBOL_GPL(amd_report_gart_errors);
-
 void amd_register_ecc_decoder(void (*f)(int, struct mce *))
 {
 	decode_dram_ecc = f;
@@ -1030,20 +1023,6 @@ static inline void amd_decode_err_code(u16 ec)
 	pr_cont("\n");
 }
 
-/*
- * Filter out unwanted MCE signatures here.
- */
-static bool ignore_mce(struct mce *m)
-{
-	/*
-	 * NB GART TLB error reporting is disabled by default.
-	 */
-	if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5 && !report_gart_errors)
-		return true;
-
-	return false;
-}
-
 static const char *decode_error_status(struct mce *m)
 {
 	if (m->status & MCI_STATUS_UC) {
@@ -1067,8 +1046,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
-	if (ignore_mce(m))
-		return NOTIFY_STOP;
+	if (m->kflags & MCE_HANDLED_CEC)
+		return NOTIFY_DONE;
 
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
 
@@ -1170,7 +1149,8 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
  err_code:
 	amd_decode_err_code(m->status & 0xffff);
 
-	return NOTIFY_STOP;
+	m->kflags |= MCE_HANDLED_EDAC;
+	return NOTIFY_OK;
 }
 
 static struct notifier_block amd_mce_dec_nb = {