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, 358 insertions, 32 deletions

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index de3ea2c1807d..597dae7692b1 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -975,6 +975,74 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr)
 	return csrow;
 }
 
+/*
+ * See AMD PPR DF::LclNodeTypeMap
+ *
+ * This register gives information for nodes of the same type within a system.
+ *
+ * Reading this register from a GPU node will tell how many GPU nodes are in the
+ * system and what the lowest AMD Node ID value is for the GPU nodes. Use this
+ * info to fixup the Linux logical "Node ID" value set in the AMD NB code and EDAC.
+ */
+static struct local_node_map {
+	u16 node_count;
+	u16 base_node_id;
+} gpu_node_map;
+
+#define PCI_DEVICE_ID_AMD_MI200_DF_F1		0x14d1
+#define REG_LOCAL_NODE_TYPE_MAP			0x144
+
+/* Local Node Type Map (LNTM) fields */
+#define LNTM_NODE_COUNT				GENMASK(27, 16)
+#define LNTM_BASE_NODE_ID			GENMASK(11, 0)
+
+static int gpu_get_node_map(void)
+{
+	struct pci_dev *pdev;
+	int ret;
+	u32 tmp;
+
+	/*
+	 * Node ID 0 is reserved for CPUs.
+	 * Therefore, a non-zero Node ID means we've already cached the values.
+	 */
+	if (gpu_node_map.base_node_id)
+		return 0;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F1, NULL);
+	if (!pdev) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	ret = pci_read_config_dword(pdev, REG_LOCAL_NODE_TYPE_MAP, &tmp);
+	if (ret)
+		goto out;
+
+	gpu_node_map.node_count = FIELD_GET(LNTM_NODE_COUNT, tmp);
+	gpu_node_map.base_node_id = FIELD_GET(LNTM_BASE_NODE_ID, tmp);
+
+out:
+	pci_dev_put(pdev);
+	return ret;
+}
+
+static int fixup_node_id(int node_id, struct mce *m)
+{
+	/* MCA_IPID[InstanceIdHi] give the AMD Node ID for the bank. */
+	u8 nid = (m->ipid >> 44) & 0xF;
+
+	if (smca_get_bank_type(m->extcpu, m->bank) != SMCA_UMC_V2)
+		return node_id;
+
+	/* Nodes below the GPU base node are CPU nodes and don't need a fixup. */
+	if (nid < gpu_node_map.base_node_id)
+		return node_id;
+
+	/* Convert the hardware-provided AMD Node ID to a Linux logical one. */
+	return nid - gpu_node_map.base_node_id + 1;
+}
+
 /* Protect the PCI config register pairs used for DF indirect access. */
 static DEFINE_MUTEX(df_indirect_mutex);
 
@@ -1426,12 +1494,47 @@ static int umc_get_cs_mode(int dimm, u8 ctrl, struct amd64_pvt *pvt)
 	return cs_mode;
 }
 
+static int __addr_mask_to_cs_size(u32 addr_mask_orig, unsigned int cs_mode,
+				  int csrow_nr, int dimm)
+{
+	u32 msb, weight, num_zero_bits;
+	u32 addr_mask_deinterleaved;
+	int size = 0;
+
+	/*
+	 * The number of zero bits in the mask is equal to the number of bits
+	 * in a full mask minus the number of bits in the current mask.
+	 *
+	 * The MSB is the number of bits in the full mask because BIT[0] is
+	 * always 0.
+	 *
+	 * In the special 3 Rank interleaving case, a single bit is flipped
+	 * without swapping with the most significant bit. This can be handled
+	 * by keeping the MSB where it is and ignoring the single zero bit.
+	 */
+	msb = fls(addr_mask_orig) - 1;
+	weight = hweight_long(addr_mask_orig);
+	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
+
+	/* Take the number of zero bits off from the top of the mask. */
+	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
+
+	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
+	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
+	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
+
+	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
+	size = (addr_mask_deinterleaved >> 2) + 1;
+
+	/* Return size in MBs. */
+	return size >> 10;
+}
+
 static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 				    unsigned int cs_mode, int csrow_nr)
 {
-	u32 addr_mask_orig, addr_mask_deinterleaved;
-	u32 msb, weight, num_zero_bits;
 	int cs_mask_nr = csrow_nr;
+	u32 addr_mask_orig;
 	int dimm, size = 0;
 
 	/* No Chip Selects are enabled. */
@@ -1475,33 +1578,7 @@ static int umc_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
 	else
 		addr_mask_orig = pvt->csels[umc].csmasks[cs_mask_nr];
 
-	/*
-	 * The number of zero bits in the mask is equal to the number of bits
-	 * in a full mask minus the number of bits in the current mask.
-	 *
-	 * The MSB is the number of bits in the full mask because BIT[0] is
-	 * always 0.
-	 *
-	 * In the special 3 Rank interleaving case, a single bit is flipped
-	 * without swapping with the most significant bit. This can be handled
-	 * by keeping the MSB where it is and ignoring the single zero bit.
-	 */
-	msb = fls(addr_mask_orig) - 1;
-	weight = hweight_long(addr_mask_orig);
-	num_zero_bits = msb - weight - !!(cs_mode & CS_3R_INTERLEAVE);
-
-	/* Take the number of zero bits off from the top of the mask. */
-	addr_mask_deinterleaved = GENMASK_ULL(msb - num_zero_bits, 1);
-
-	edac_dbg(1, "CS%d DIMM%d AddrMasks:\n", csrow_nr, dimm);
-	edac_dbg(1, "  Original AddrMask: 0x%x\n", addr_mask_orig);
-	edac_dbg(1, "  Deinterleaved AddrMask: 0x%x\n", addr_mask_deinterleaved);
-
-	/* Register [31:1] = Address [39:9]. Size is in kBs here. */
-	size = (addr_mask_deinterleaved >> 2) + 1;
-
-	/* Return size in MBs. */
-	return size >> 10;
+	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, dimm);
 }
 
 static void umc_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
@@ -2992,6 +3069,8 @@ static void decode_umc_error(int node_id, struct mce *m)
 	struct err_info err;
 	u64 sys_addr;
 
+	node_id = fixup_node_id(node_id, m);
+
 	mci = edac_mc_find(node_id);
 	if (!mci)
 		return;
@@ -3675,6 +3754,227 @@ static int umc_hw_info_get(struct amd64_pvt *pvt)
 	return 0;
 }
 
+/*
+ * The CPUs have one channel per UMC, so UMC number is equivalent to a
+ * channel number. The GPUs have 8 channels per UMC, so the UMC number no
+ * longer works as a channel number.
+ *
+ * The channel number within a GPU UMC is given in MCA_IPID[15:12].
+ * However, the IDs are split such that two UMC values go to one UMC, and
+ * the channel numbers are split in two groups of four.
+ *
+ * Refer to comment on gpu_get_umc_base().
+ *
+ * For example,
+ * UMC0 CH[3:0] = 0x0005[3:0]000
+ * UMC0 CH[7:4] = 0x0015[3:0]000
+ * UMC1 CH[3:0] = 0x0025[3:0]000
+ * UMC1 CH[7:4] = 0x0035[3:0]000
+ */
+static void gpu_get_err_info(struct mce *m, struct err_info *err)
+{
+	u8 ch = (m->ipid & GENMASK(31, 0)) >> 20;
+	u8 phy = ((m->ipid >> 12) & 0xf);
+
+	err->channel = ch % 2 ? phy + 4 : phy;
+	err->csrow = phy;
+}
+
+static int gpu_addr_mask_to_cs_size(struct amd64_pvt *pvt, u8 umc,
+				    unsigned int cs_mode, int csrow_nr)
+{
+	u32 addr_mask_orig = pvt->csels[umc].csmasks[csrow_nr];
+
+	return __addr_mask_to_cs_size(addr_mask_orig, cs_mode, csrow_nr, csrow_nr >> 1);
+}
+
+static void gpu_debug_display_dimm_sizes(struct amd64_pvt *pvt, u8 ctrl)
+{
+	int size, cs_mode, cs = 0;
+
+	edac_printk(KERN_DEBUG, EDAC_MC, "UMC%d chip selects:\n", ctrl);
+
+	cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY;
+
+	for_each_chip_select(cs, ctrl, pvt) {
+		size = gpu_addr_mask_to_cs_size(pvt, ctrl, cs_mode, cs);
+		amd64_info(EDAC_MC ": %d: %5dMB\n", cs, size);
+	}
+}
+
+static void gpu_dump_misc_regs(struct amd64_pvt *pvt)
+{
+	struct amd64_umc *umc;
+	u32 i;
+
+	for_each_umc(i) {
+		umc = &pvt->umc[i];
+
+		edac_dbg(1, "UMC%d UMC cfg: 0x%x\n", i, umc->umc_cfg);
+		edac_dbg(1, "UMC%d SDP ctrl: 0x%x\n", i, umc->sdp_ctrl);
+		edac_dbg(1, "UMC%d ECC ctrl: 0x%x\n", i, umc->ecc_ctrl);
+		edac_dbg(1, "UMC%d All HBMs support ECC: yes\n", i);
+
+		gpu_debug_display_dimm_sizes(pvt, i);
+	}
+}
+
+static u32 gpu_get_csrow_nr_pages(struct amd64_pvt *pvt, u8 dct, int csrow_nr)
+{
+	u32 nr_pages;
+	int cs_mode = CS_EVEN_PRIMARY | CS_ODD_PRIMARY;
+
+	nr_pages   = gpu_addr_mask_to_cs_size(pvt, dct, cs_mode, csrow_nr);
+	nr_pages <<= 20 - PAGE_SHIFT;
+
+	edac_dbg(0, "csrow: %d, channel: %d\n", csrow_nr, dct);
+	edac_dbg(0, "nr_pages/channel: %u\n", nr_pages);
+
+	return nr_pages;
+}
+
+static void gpu_init_csrows(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+	struct dimm_info *dimm;
+	u8 umc, cs;
+
+	for_each_umc(umc) {
+		for_each_chip_select(cs, umc, pvt) {
+			if (!csrow_enabled(cs, umc, pvt))
+				continue;
+
+			dimm = mci->csrows[umc]->channels[cs]->dimm;
+
+			edac_dbg(1, "MC node: %d, csrow: %d\n",
+				 pvt->mc_node_id, cs);
+
+			dimm->nr_pages = gpu_get_csrow_nr_pages(pvt, umc, cs);
+			dimm->edac_mode = EDAC_SECDED;
+			dimm->mtype = MEM_HBM2;
+			dimm->dtype = DEV_X16;
+			dimm->grain = 64;
+		}
+	}
+}
+
+static void gpu_setup_mci_misc_attrs(struct mem_ctl_info *mci)
+{
+	struct amd64_pvt *pvt = mci->pvt_info;
+
+	mci->mtype_cap		= MEM_FLAG_HBM2;
+	mci->edac_ctl_cap	= EDAC_FLAG_SECDED;
+
+	mci->edac_cap		= EDAC_FLAG_EC;
+	mci->mod_name		= EDAC_MOD_STR;
+	mci->ctl_name		= pvt->ctl_name;
+	mci->dev_name		= pci_name(pvt->F3);
+	mci->ctl_page_to_phys	= NULL;
+
+	gpu_init_csrows(mci);
+}
+
+/* ECC is enabled by default on GPU nodes */
+static bool gpu_ecc_enabled(struct amd64_pvt *pvt)
+{
+	return true;
+}
+
+static inline u32 gpu_get_umc_base(u8 umc, u8 channel)
+{
+	/*
+	 * On CPUs, there is one channel per UMC, so UMC numbering equals
+	 * channel numbering. On GPUs, there are eight channels per UMC,
+	 * so the channel numbering is different from UMC numbering.
+	 *
+	 * On CPU nodes channels are selected in 6th nibble
+	 * UMC chY[3:0]= [(chY*2 + 1) : (chY*2)]50000;
+	 *
+	 * On GPU nodes channels are selected in 3rd nibble
+	 * HBM chX[3:0]= [Y  ]5X[3:0]000;
+	 * HBM chX[7:4]= [Y+1]5X[3:0]000
+	 */
+	umc *= 2;
+
+	if (channel >= 4)
+		umc++;
+
+	return 0x50000 + (umc << 20) + ((channel % 4) << 12);
+}
+
+static void gpu_read_mc_regs(struct amd64_pvt *pvt)
+{
+	u8 nid = pvt->mc_node_id;
+	struct amd64_umc *umc;
+	u32 i, umc_base;
+
+	/* Read registers from each UMC */
+	for_each_umc(i) {
+		umc_base = gpu_get_umc_base(i, 0);
+		umc = &pvt->umc[i];
+
+		amd_smn_read(nid, umc_base + UMCCH_UMC_CFG, &umc->umc_cfg);
+		amd_smn_read(nid, umc_base + UMCCH_SDP_CTRL, &umc->sdp_ctrl);
+		amd_smn_read(nid, umc_base + UMCCH_ECC_CTRL, &umc->ecc_ctrl);
+	}
+}
+
+static void gpu_read_base_mask(struct amd64_pvt *pvt)
+{
+	u32 base_reg, mask_reg;
+	u32 *base, *mask;
+	int umc, cs;
+
+	for_each_umc(umc) {
+		for_each_chip_select(cs, umc, pvt) {
+			base_reg = gpu_get_umc_base(umc, cs) + UMCCH_BASE_ADDR;
+			base = &pvt->csels[umc].csbases[cs];
+
+			if (!amd_smn_read(pvt->mc_node_id, base_reg, base)) {
+				edac_dbg(0, "  DCSB%d[%d]=0x%08x reg: 0x%x\n",
+					 umc, cs, *base, base_reg);
+			}
+
+			mask_reg = gpu_get_umc_base(umc, cs) + UMCCH_ADDR_MASK;
+			mask = &pvt->csels[umc].csmasks[cs];
+
+			if (!amd_smn_read(pvt->mc_node_id, mask_reg, mask)) {
+				edac_dbg(0, "  DCSM%d[%d]=0x%08x reg: 0x%x\n",
+					 umc, cs, *mask, mask_reg);
+			}
+		}
+	}
+}
+
+static void gpu_prep_chip_selects(struct amd64_pvt *pvt)
+{
+	int umc;
+
+	for_each_umc(umc) {
+		pvt->csels[umc].b_cnt = 8;
+		pvt->csels[umc].m_cnt = 8;
+	}
+}
+
+static int gpu_hw_info_get(struct amd64_pvt *pvt)
+{
+	int ret;
+
+	ret = gpu_get_node_map();
+	if (ret)
+		return ret;
+
+	pvt->umc = kcalloc(pvt->max_mcs, sizeof(struct amd64_umc), GFP_KERNEL);
+	if (!pvt->umc)
+		return -ENOMEM;
+
+	gpu_prep_chip_selects(pvt);
+	gpu_read_base_mask(pvt);
+	gpu_read_mc_regs(pvt);
+
+	return 0;
+}
+
 static void hw_info_put(struct amd64_pvt *pvt)
 {
 	pci_dev_put(pvt->F1);
@@ -3690,6 +3990,14 @@ static struct low_ops umc_ops = {
 	.get_err_info			= umc_get_err_info,
 };
 
+static struct low_ops gpu_ops = {
+	.hw_info_get			= gpu_hw_info_get,
+	.ecc_enabled			= gpu_ecc_enabled,
+	.setup_mci_misc_attrs		= gpu_setup_mci_misc_attrs,
+	.dump_misc_regs			= gpu_dump_misc_regs,
+	.get_err_info			= gpu_get_err_info,
+};
+
 /* Use Family 16h versions for defaults and adjust as needed below. */
 static struct low_ops dct_ops = {
 	.map_sysaddr_to_csrow		= f1x_map_sysaddr_to_csrow,
@@ -3813,6 +4121,16 @@ static int per_family_init(struct amd64_pvt *pvt)
 		case 0x20 ... 0x2f:
 			pvt->ctl_name			= "F19h_M20h";
 			break;
+		case 0x30 ... 0x3f:
+			if (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) {
+				pvt->ctl_name		= "MI200";
+				pvt->max_mcs		= 4;
+				pvt->ops		= &gpu_ops;
+			} else {
+				pvt->ctl_name		= "F19h_M30h";
+				pvt->max_mcs		= 8;
+			}
+			break;
 		case 0x50 ... 0x5f:
 			pvt->ctl_name			= "F19h_M50h";
 			break;
@@ -3854,11 +4172,17 @@ static int init_one_instance(struct amd64_pvt *pvt)
 	struct edac_mc_layer layers[2];
 	int ret = -ENOMEM;
 
+	/*
+	 * For Heterogeneous family EDAC CHIP_SELECT and CHANNEL layers should
+	 * be swapped to fit into the layers.
+	 */
 	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
-	layers[0].size = pvt->csels[0].b_cnt;
+	layers[0].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ?
+			 pvt->max_mcs : pvt->csels[0].b_cnt;
 	layers[0].is_virt_csrow = true;
 	layers[1].type = EDAC_MC_LAYER_CHANNEL;
-	layers[1].size = pvt->max_mcs;
+	layers[1].size = (pvt->F3->device == PCI_DEVICE_ID_AMD_MI200_DF_F3) ?
+			 pvt->csels[0].b_cnt : pvt->max_mcs;
 	layers[1].is_virt_csrow = false;
 
 	mci = edac_mc_alloc(pvt->mc_node_id, ARRAY_SIZE(layers), layers, 0);
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 0bde0db76f7a..5a4e4a59682b 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/mmzone.h>
 #include <linux/edac.h>
+#include <linux/bitfield.h>
 #include <asm/cpu_device_id.h>
 #include <asm/msr.h>
 #include "edac_module.h"
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index cc5c63feb26a..9215c06783df 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1186,7 +1186,8 @@ static void decode_smca_error(struct mce *m)
 	if (xec < smca_mce_descs[bank_type].num_descs)
 		pr_cont(", %s.\n", smca_mce_descs[bank_type].descs[xec]);
 
-	if (bank_type == SMCA_UMC && xec == 0 && decode_dram_ecc)
+	if ((bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) &&
+	    xec == 0 && decode_dram_ecc)
 		decode_dram_ecc(topology_die_id(m->extcpu), m);
 }