Merge tag 'ras_core_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull RAS updates from Borislav Petkov:

 - Add initial support for RAS hardware found on AMD server GPUs (MI200).

   Those GPUs and CPUs are connected together through the coherent
   fabric and the GPU memory controllers report errors through x86's MCA
   so EDAC needs to support them. The amd64_edac driver supports now HBM
   (High Bandwidth Memory) and thus such heterogeneous memory controller
   systems

 - Other small cleanups and improvements

* tag 'ras_core_for_v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  EDAC/amd64: Cache and use GPU node map
  EDAC/amd64: Add support for AMD heterogeneous Family 19h Model 30h-3Fh
  EDAC/amd64: Document heterogeneous system enumeration
  x86/MCE/AMD, EDAC/mce_amd: Decode UMC_V2 ECC errors
  x86/amd_nb: Re-sort and re-indent PCI defines
  x86/amd_nb: Add MI200 PCI IDs
  ras/debugfs: Fix error checking for debugfs_create_dir()
  x86/MCE: Check a hw error's address to determine proper recovery action

3 files changed, 33 insertions, 25 deletions

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 7e331e8f3692..035a3db5330b 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -15,28 +15,31 @@
 #include <linux/pci_ids.h>
 #include <asm/amd_nb.h>
 
-#define PCI_DEVICE_ID_AMD_17H_ROOT	0x1450
-#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT	0x15d0
-#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT	0x1480
-#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT	0x1630
-#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT	0x14b5
-#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT	0x14a4
-#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT	0x14d8
-#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT	0x14e8
-#define PCI_DEVICE_ID_AMD_17H_DF_F4	0x1464
-#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
-#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494
-#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c
-#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444
-#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4 0x1728
-#define PCI_DEVICE_ID_AMD_19H_DF_F4	0x1654
-#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1
-#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT	0x14b5
-#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d
-#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e
-#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4
-#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4
-#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
+#define PCI_DEVICE_ID_AMD_17H_ROOT		0x1450
+#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT		0x15d0
+#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT		0x1480
+#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT		0x1630
+#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT		0x14b5
+#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT		0x14a4
+#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT		0x14b5
+#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT		0x14d8
+#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT		0x14e8
+#define PCI_DEVICE_ID_AMD_MI200_ROOT		0x14bb
+
+#define PCI_DEVICE_ID_AMD_17H_DF_F4		0x1464
+#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4	0x15ec
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4	0x1494
+#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4	0x144c
+#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4	0x1444
+#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4	0x1728
+#define PCI_DEVICE_ID_AMD_19H_DF_F4		0x1654
+#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4	0x14b1
+#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4	0x167d
+#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4	0x166e
+#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4	0x14e4
+#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4	0x14f4
+#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4	0x12fc
+#define PCI_DEVICE_ID_AMD_MI200_DF_F4		0x14d4
 
 /* Protect the PCI config register pairs used for SMN. */
 static DEFINE_MUTEX(smn_mutex);
@@ -53,6 +56,7 @@ static const struct pci_device_id amd_root_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_ROOT) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) },
 	{}
 };
 
@@ -81,6 +85,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) },
 	{}
 };
 
@@ -101,6 +106,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 0b971f974096..5e74610b39e7 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -715,11 +715,13 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 
 bool amd_mce_is_memory_error(struct mce *m)
 {
+	enum smca_bank_types bank_type;
 	/* ErrCodeExt[20:16] */
 	u8 xec = (m->status >> 16) & 0x1f;
 
+	bank_type = smca_get_bank_type(m->extcpu, m->bank);
 	if (mce_flags.smca)
-		return smca_get_bank_type(m->extcpu, m->bank) == SMCA_UMC && xec == 0x0;
+		return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0;
 
 	return m->bank == 4 && xec == 0x8;
 }
@@ -1050,7 +1052,7 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol
 	if (bank_type >= N_SMCA_BANK_TYPES)
 		return NULL;
 
-	if (b && bank_type == SMCA_UMC) {
+	if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) {
 		if (b->block < ARRAY_SIZE(smca_umc_block_names))
 			return smca_umc_block_names[b->block];
 		return NULL;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2eec60f50057..22dfcb2adcd7 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1533,7 +1533,7 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		if (kill_current_task)
+		if (!mce_usable_address(&m))
 			queue_task_work(&m, msg, kill_me_now);
 		else
 			queue_task_work(&m, msg, kill_me_maybe);