summaryrefslogtreecommitdiffstats
path: root/drivers/edac
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-01-10 11:43:09 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-10 11:43:09 -0800
commit7e740ae6350407d68d2069ce79a6344bf1b58fe1 (patch)
tree48ebd0eff2a4d527d26ce7848485629815ad934b /drivers/edac
parent48a60bdb2be807767eba6878fdf2fe5bea5d8d27 (diff)
parent3376136300a00df9a864b88fa969177d6c3be8e5 (diff)
downloadlinux-7e740ae6350407d68d2069ce79a6344bf1b58fe1.tar.gz
linux-7e740ae6350407d68d2069ce79a6344bf1b58fe1.tar.bz2
linux-7e740ae6350407d68d2069ce79a6344bf1b58fe1.zip
Merge tag 'ras_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull RAS updates from Borislav Petkov: "A relatively big amount of movements in RAS-land this time around: - First part of a series to move the AMD address translation code from arch/x86/ to amd64_edac as that is its only user anyway - Some MCE error injection improvements to the AMD side - Reorganization of the #MC handler code and the facilities it calls to make it noinstr-safe - Add support for new AMD MCA bank types and non-uniform banks layout - The usual set of cleanups and fixes" * tag 'ras_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits) x86/mce: Reduce number of machine checks taken during recovery x86/mce/inject: Avoid out-of-bounds write when setting flags x86/MCE/AMD, EDAC/mce_amd: Support non-uniform MCA bank type enumeration x86/MCE/AMD, EDAC/mce_amd: Add new SMCA bank types x86/mce: Check regs before accessing it x86/mce: Mark mce_start() noinstr x86/mce: Mark mce_timed_out() noinstr x86/mce: Move the tainting outside of the noinstr region x86/mce: Mark mce_read_aux() noinstr x86/mce: Mark mce_end() noinstr x86/mce: Mark mce_panic() noinstr x86/mce: Prevent severity computation from being instrumented x86/mce: Allow instrumentation during task work queueing x86/mce: Remove noinstr annotation from mce_setup() x86/mce: Use mce_rdmsrl() in severity checking code x86/mce: Remove function-local cpus variables x86/mce: Do not use memset to clear the banks bitmaps x86/mce/inject: Set the valid bit in MCA_STATUS before error injection x86/mce/inject: Check if a bank is populated before injecting x86/mce: Get rid of cpu_missing ...
Diffstat (limited to 'drivers/edac')
-rw-r--r--drivers/edac/amd64_edac.c275
-rw-r--r--drivers/edac/mce_amd.c146
2 files changed, 405 insertions, 16 deletions
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 4fce75013674..ca0c67bc25c6 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -988,6 +988,281 @@ static int sys_addr_to_csrow(struct mem_ctl_info *mci, u64 sys_addr)
return csrow;
}
+/* Protect the PCI config register pairs used for DF indirect access. */
+static DEFINE_MUTEX(df_indirect_mutex);
+
+/*
+ * Data Fabric Indirect Access uses FICAA/FICAD.
+ *
+ * Fabric Indirect Configuration Access Address (FICAA): Constructed based
+ * on the device's Instance Id and the PCI function and register offset of
+ * the desired register.
+ *
+ * Fabric Indirect Configuration Access Data (FICAD): There are FICAD LO
+ * and FICAD HI registers but so far we only need the LO register.
+ *
+ * Use Instance Id 0xFF to indicate a broadcast read.
+ */
+#define DF_BROADCAST 0xFF
+static int __df_indirect_read(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+ struct pci_dev *F4;
+ u32 ficaa;
+ int err = -ENODEV;
+
+ if (node >= amd_nb_num())
+ goto out;
+
+ F4 = node_to_amd_nb(node)->link;
+ if (!F4)
+ goto out;
+
+ ficaa = (instance_id == DF_BROADCAST) ? 0 : 1;
+ ficaa |= reg & 0x3FC;
+ ficaa |= (func & 0x7) << 11;
+ ficaa |= instance_id << 16;
+
+ mutex_lock(&df_indirect_mutex);
+
+ err = pci_write_config_dword(F4, 0x5C, ficaa);
+ if (err) {
+ pr_warn("Error writing DF Indirect FICAA, FICAA=0x%x\n", ficaa);
+ goto out_unlock;
+ }
+
+ err = pci_read_config_dword(F4, 0x98, lo);
+ if (err)
+ pr_warn("Error reading DF Indirect FICAD LO, FICAA=0x%x.\n", ficaa);
+
+out_unlock:
+ mutex_unlock(&df_indirect_mutex);
+
+out:
+ return err;
+}
+
+static int df_indirect_read_instance(u16 node, u8 func, u16 reg, u8 instance_id, u32 *lo)
+{
+ return __df_indirect_read(node, func, reg, instance_id, lo);
+}
+
+static int df_indirect_read_broadcast(u16 node, u8 func, u16 reg, u32 *lo)
+{
+ return __df_indirect_read(node, func, reg, DF_BROADCAST, lo);
+}
+
+struct addr_ctx {
+ u64 ret_addr;
+ u32 tmp;
+ u16 nid;
+ u8 inst_id;
+};
+
+static int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)
+{
+ u64 dram_base_addr, dram_limit_addr, dram_hole_base;
+
+ u8 die_id_shift, die_id_mask, socket_id_shift, socket_id_mask;
+ u8 intlv_num_dies, intlv_num_chan, intlv_num_sockets;
+ u8 intlv_addr_sel, intlv_addr_bit;
+ u8 num_intlv_bits, hashed_bit;
+ u8 lgcy_mmio_hole_en, base = 0;
+ u8 cs_mask, cs_id = 0;
+ bool hash_enabled = false;
+
+ struct addr_ctx ctx;
+
+ memset(&ctx, 0, sizeof(ctx));
+
+ /* Start from the normalized address */
+ ctx.ret_addr = norm_addr;
+
+ ctx.nid = nid;
+ ctx.inst_id = umc;
+
+ /* Read D18F0x1B4 (DramOffset), check if base 1 is used. */
+ if (df_indirect_read_instance(nid, 0, 0x1B4, umc, &ctx.tmp))
+ goto out_err;
+
+ /* Remove HiAddrOffset from normalized address, if enabled: */
+ if (ctx.tmp & BIT(0)) {
+ u64 hi_addr_offset = (ctx.tmp & GENMASK_ULL(31, 20)) << 8;
+
+ if (norm_addr >= hi_addr_offset) {
+ ctx.ret_addr -= hi_addr_offset;
+ base = 1;
+ }
+ }
+
+ /* Read D18F0x110 (DramBaseAddress). */
+ if (df_indirect_read_instance(nid, 0, 0x110 + (8 * base), umc, &ctx.tmp))
+ goto out_err;
+
+ /* Check if address range is valid. */
+ if (!(ctx.tmp & BIT(0))) {
+ pr_err("%s: Invalid DramBaseAddress range: 0x%x.\n",
+ __func__, ctx.tmp);
+ goto out_err;
+ }
+
+ lgcy_mmio_hole_en = ctx.tmp & BIT(1);
+ intlv_num_chan = (ctx.tmp >> 4) & 0xF;
+ intlv_addr_sel = (ctx.tmp >> 8) & 0x7;
+ dram_base_addr = (ctx.tmp & GENMASK_ULL(31, 12)) << 16;
+
+ /* {0, 1, 2, 3} map to address bits {8, 9, 10, 11} respectively */
+ if (intlv_addr_sel > 3) {
+ pr_err("%s: Invalid interleave address select %d.\n",
+ __func__, intlv_addr_sel);
+ goto out_err;
+ }
+
+ /* Read D18F0x114 (DramLimitAddress). */
+ if (df_indirect_read_instance(nid, 0, 0x114 + (8 * base), umc, &ctx.tmp))
+ goto out_err;
+
+ intlv_num_sockets = (ctx.tmp >> 8) & 0x1;
+ intlv_num_dies = (ctx.tmp >> 10) & 0x3;
+ dram_limit_addr = ((ctx.tmp & GENMASK_ULL(31, 12)) << 16) | GENMASK_ULL(27, 0);
+
+ intlv_addr_bit = intlv_addr_sel + 8;
+
+ /* Re-use intlv_num_chan by setting it equal to log2(#channels) */
+ switch (intlv_num_chan) {
+ case 0: intlv_num_chan = 0; break;
+ case 1: intlv_num_chan = 1; break;
+ case 3: intlv_num_chan = 2; break;
+ case 5: intlv_num_chan = 3; break;
+ case 7: intlv_num_chan = 4; break;
+
+ case 8: intlv_num_chan = 1;
+ hash_enabled = true;
+ break;
+ default:
+ pr_err("%s: Invalid number of interleaved channels %d.\n",
+ __func__, intlv_num_chan);
+ goto out_err;
+ }
+
+ num_intlv_bits = intlv_num_chan;
+
+ if (intlv_num_dies > 2) {
+ pr_err("%s: Invalid number of interleaved nodes/dies %d.\n",
+ __func__, intlv_num_dies);
+ goto out_err;
+ }
+
+ num_intlv_bits += intlv_num_dies;
+
+ /* Add a bit if sockets are interleaved. */
+ num_intlv_bits += intlv_num_sockets;
+
+ /* Assert num_intlv_bits <= 4 */
+ if (num_intlv_bits > 4) {
+ pr_err("%s: Invalid interleave bits %d.\n",
+ __func__, num_intlv_bits);
+ goto out_err;
+ }
+
+ if (num_intlv_bits > 0) {
+ u64 temp_addr_x, temp_addr_i, temp_addr_y;
+ u8 die_id_bit, sock_id_bit, cs_fabric_id;
+
+ /*
+ * Read FabricBlockInstanceInformation3_CS[BlockFabricID].
+ * This is the fabric id for this coherent slave. Use
+ * umc/channel# as instance id of the coherent slave
+ * for FICAA.
+ */
+ if (df_indirect_read_instance(nid, 0, 0x50, umc, &ctx.tmp))
+ goto out_err;
+
+ cs_fabric_id = (ctx.tmp >> 8) & 0xFF;
+ die_id_bit = 0;
+
+ /* If interleaved over more than 1 channel: */
+ if (intlv_num_chan) {
+ die_id_bit = intlv_num_chan;
+ cs_mask = (1 << die_id_bit) - 1;
+ cs_id = cs_fabric_id & cs_mask;
+ }
+
+ sock_id_bit = die_id_bit;
+
+ /* Read D18F1x208 (SystemFabricIdMask). */
+ if (intlv_num_dies || intlv_num_sockets)
+ if (df_indirect_read_broadcast(nid, 1, 0x208, &ctx.tmp))
+ goto out_err;
+
+ /* If interleaved over more than 1 die. */
+ if (intlv_num_dies) {
+ sock_id_bit = die_id_bit + intlv_num_dies;
+ die_id_shift = (ctx.tmp >> 24) & 0xF;
+ die_id_mask = (ctx.tmp >> 8) & 0xFF;
+
+ cs_id |= ((cs_fabric_id & die_id_mask) >> die_id_shift) << die_id_bit;
+ }
+
+ /* If interleaved over more than 1 socket. */
+ if (intlv_num_sockets) {
+ socket_id_shift = (ctx.tmp >> 28) & 0xF;
+ socket_id_mask = (ctx.tmp >> 16) & 0xFF;
+
+ cs_id |= ((cs_fabric_id & socket_id_mask) >> socket_id_shift) << sock_id_bit;
+ }
+
+ /*
+ * The pre-interleaved address consists of XXXXXXIIIYYYYY
+ * where III is the ID for this CS, and XXXXXXYYYYY are the
+ * address bits from the post-interleaved address.
+ * "num_intlv_bits" has been calculated to tell us how many "I"
+ * bits there are. "intlv_addr_bit" tells us how many "Y" bits
+ * there are (where "I" starts).
+ */
+ temp_addr_y = ctx.ret_addr & GENMASK_ULL(intlv_addr_bit - 1, 0);
+ temp_addr_i = (cs_id << intlv_addr_bit);
+ temp_addr_x = (ctx.ret_addr & GENMASK_ULL(63, intlv_addr_bit)) << num_intlv_bits;
+ ctx.ret_addr = temp_addr_x | temp_addr_i | temp_addr_y;
+ }
+
+ /* Add dram base address */
+ ctx.ret_addr += dram_base_addr;
+
+ /* If legacy MMIO hole enabled */
+ if (lgcy_mmio_hole_en) {
+ if (df_indirect_read_broadcast(nid, 0, 0x104, &ctx.tmp))
+ goto out_err;
+
+ dram_hole_base = ctx.tmp & GENMASK(31, 24);
+ if (ctx.ret_addr >= dram_hole_base)
+ ctx.ret_addr += (BIT_ULL(32) - dram_hole_base);
+ }
+
+ if (hash_enabled) {
+ /* Save some parentheses and grab ls-bit at the end. */
+ hashed_bit = (ctx.ret_addr >> 12) ^
+ (ctx.ret_addr >> 18) ^
+ (ctx.ret_addr >> 21) ^
+ (ctx.ret_addr >> 30) ^
+ cs_id;
+
+ hashed_bit &= BIT(0);
+
+ if (hashed_bit != ((ctx.ret_addr >> intlv_addr_bit) & BIT(0)))
+ ctx.ret_addr ^= BIT(intlv_addr_bit);
+ }
+
+ /* Is calculated system address is above DRAM limit address? */
+ if (ctx.ret_addr > dram_limit_addr)
+ goto out_err;
+
+ *sys_addr = ctx.ret_addr;
+ return 0;
+
+out_err:
+ return -EINVAL;
+}
+
static int get_channel_from_ecc_syndrome(struct mem_ctl_info *, u16);
/*
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 67dbf4c31271..cc5c63feb26a 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -399,6 +399,63 @@ static const char * const smca_mp5_mce_desc[] = {
"Instruction Tag Cache Bank B ECC or parity error",
};
+static const char * const smca_mpdma_mce_desc[] = {
+ "Main SRAM [31:0] bank ECC or parity error",
+ "Main SRAM [63:32] bank ECC or parity error",
+ "Main SRAM [95:64] bank ECC or parity error",
+ "Main SRAM [127:96] bank ECC or parity error",
+ "Data Cache Bank A ECC or parity error",
+ "Data Cache Bank B ECC or parity error",
+ "Data Tag Cache Bank A ECC or parity error",
+ "Data Tag Cache Bank B ECC or parity error",
+ "Instruction Cache Bank A ECC or parity error",
+ "Instruction Cache Bank B ECC or parity error",
+ "Instruction Tag Cache Bank A ECC or parity error",
+ "Instruction Tag Cache Bank B ECC or parity error",
+ "Data Cache Bank A ECC or parity error",
+ "Data Cache Bank B ECC or parity error",
+ "Data Tag Cache Bank A ECC or parity error",
+ "Data Tag Cache Bank B ECC or parity error",
+ "Instruction Cache Bank A ECC or parity error",
+ "Instruction Cache Bank B ECC or parity error",
+ "Instruction Tag Cache Bank A ECC or parity error",
+ "Instruction Tag Cache Bank B ECC or parity error",
+ "Data Cache Bank A ECC or parity error",
+ "Data Cache Bank B ECC or parity error",
+ "Data Tag Cache Bank A ECC or parity error",
+ "Data Tag Cache Bank B ECC or parity error",
+ "Instruction Cache Bank A ECC or parity error",
+ "Instruction Cache Bank B ECC or parity error",
+ "Instruction Tag Cache Bank A ECC or parity error",
+ "Instruction Tag Cache Bank B ECC or parity error",
+ "System Hub Read Buffer ECC or parity error",
+ "MPDMA TVF DVSEC Memory ECC or parity error",
+ "MPDMA TVF MMIO Mailbox0 ECC or parity error",
+ "MPDMA TVF MMIO Mailbox1 ECC or parity error",
+ "MPDMA TVF Doorbell Memory ECC or parity error",
+ "MPDMA TVF SDP Slave Memory 0 ECC or parity error",
+ "MPDMA TVF SDP Slave Memory 1 ECC or parity error",
+ "MPDMA TVF SDP Slave Memory 2 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 0 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 1 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 2 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 3 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 4 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 5 ECC or parity error",
+ "MPDMA TVF SDP Master Memory 6 ECC or parity error",
+ "MPDMA PTE Command FIFO ECC or parity error",
+ "MPDMA PTE Hub Data FIFO ECC or parity error",
+ "MPDMA PTE Internal Data FIFO ECC or parity error",
+ "MPDMA PTE Command Memory DMA ECC or parity error",
+ "MPDMA PTE Command Memory Internal ECC or parity error",
+ "MPDMA PTE DMA Completion FIFO ECC or parity error",
+ "MPDMA PTE Tablewalk Completion FIFO ECC or parity error",
+ "MPDMA PTE Descriptor Completion FIFO ECC or parity error",
+ "MPDMA PTE ReadOnly Completion FIFO ECC or parity error",
+ "MPDMA PTE DirectWrite Completion FIFO ECC or parity error",
+ "SDP Watchdog Timer expired",
+};
+
static const char * const smca_nbio_mce_desc[] = {
"ECC or Parity error",
"PCIE error",
@@ -448,7 +505,7 @@ static const char * const smca_xgmipcs_mce_desc[] = {
"Rx Replay Timeout Error",
"LinkSub Tx Timeout Error",
"LinkSub Rx Timeout Error",
- "Rx CMD Pocket Error",
+ "Rx CMD Packet Error",
};
static const char * const smca_xgmiphy_mce_desc[] = {
@@ -458,11 +515,66 @@ static const char * const smca_xgmiphy_mce_desc[] = {
"PHY APB error",
};
-static const char * const smca_waflphy_mce_desc[] = {
- "RAM ECC Error",
- "ARC instruction buffer parity error",
- "ARC data buffer parity error",
- "PHY APB error",
+static const char * const smca_nbif_mce_desc[] = {
+ "Timeout error from GMI",
+ "SRAM ECC error",
+ "NTB Error Event",
+ "SDP Parity error",
+};
+
+static const char * const smca_sata_mce_desc[] = {
+ "Parity error for port 0",
+ "Parity error for port 1",
+ "Parity error for port 2",
+ "Parity error for port 3",
+ "Parity error for port 4",
+ "Parity error for port 5",
+ "Parity error for port 6",
+ "Parity error for port 7",
+};
+
+static const char * const smca_usb_mce_desc[] = {
+ "Parity error or ECC error for S0 RAM0",
+ "Parity error or ECC error for S0 RAM1",
+ "Parity error or ECC error for S0 RAM2",
+ "Parity error for PHY RAM0",
+ "Parity error for PHY RAM1",
+ "AXI Slave Response error",
+};
+
+static const char * const smca_gmipcs_mce_desc[] = {
+ "Data Loss Error",
+ "Training Error",
+ "Replay Parity Error",
+ "Rx Fifo Underflow Error",
+ "Rx Fifo Overflow Error",
+ "CRC Error",
+ "BER Exceeded Error",
+ "Tx Fifo Underflow Error",
+ "Replay Buffer Parity Error",
+ "Tx Overflow Error",
+ "Replay Fifo Overflow Error",
+ "Replay Fifo Underflow Error",
+ "Elastic Fifo Overflow Error",
+ "Deskew Error",
+ "Offline Error",
+ "Data Startup Limit Error",
+ "FC Init Timeout Error",
+ "Recovery Timeout Error",
+ "Ready Serial Timeout Error",
+ "Ready Serial Attempt Error",
+ "Recovery Attempt Error",
+ "Recovery Relock Attempt Error",
+ "Deskew Abort Error",
+ "Rx Buffer Error",
+ "Rx LFDS Fifo Overflow Error",
+ "Rx LFDS Fifo Underflow Error",
+ "LinkSub Tx Timeout Error",
+ "LinkSub Rx Timeout Error",
+ "Rx CMD Packet Error",
+ "LFDS Training Timeout Error",
+ "LFDS FC Init Timeout Error",
+ "Data Loss Error",
};
struct smca_mce_desc {
@@ -490,12 +602,21 @@ static struct smca_mce_desc smca_mce_descs[] = {
[SMCA_SMU] = { smca_smu_mce_desc, ARRAY_SIZE(smca_smu_mce_desc) },
[SMCA_SMU_V2] = { smca_smu2_mce_desc, ARRAY_SIZE(smca_smu2_mce_desc) },
[SMCA_MP5] = { smca_mp5_mce_desc, ARRAY_SIZE(smca_mp5_mce_desc) },
+ [SMCA_MPDMA] = { smca_mpdma_mce_desc, ARRAY_SIZE(smca_mpdma_mce_desc) },
[SMCA_NBIO] = { smca_nbio_mce_desc, ARRAY_SIZE(smca_nbio_mce_desc) },
[SMCA_PCIE] = { smca_pcie_mce_desc, ARRAY_SIZE(smca_pcie_mce_desc) },
[SMCA_PCIE_V2] = { smca_pcie2_mce_desc, ARRAY_SIZE(smca_pcie2_mce_desc) },
[SMCA_XGMI_PCS] = { smca_xgmipcs_mce_desc, ARRAY_SIZE(smca_xgmipcs_mce_desc) },
+ /* NBIF and SHUB have the same error descriptions, for now. */
+ [SMCA_NBIF] = { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc) },
+ [SMCA_SHUB] = { smca_nbif_mce_desc, ARRAY_SIZE(smca_nbif_mce_desc) },
+ [SMCA_SATA] = { smca_sata_mce_desc, ARRAY_SIZE(smca_sata_mce_desc) },
+ [SMCA_USB] = { smca_usb_mce_desc, ARRAY_SIZE(smca_usb_mce_desc) },
+ [SMCA_GMI_PCS] = { smca_gmipcs_mce_desc, ARRAY_SIZE(smca_gmipcs_mce_desc) },
+ /* All the PHY bank types have the same error descriptions, for now. */
[SMCA_XGMI_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) },
- [SMCA_WAFL_PHY] = { smca_waflphy_mce_desc, ARRAY_SIZE(smca_waflphy_mce_desc) },
+ [SMCA_WAFL_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) },
+ [SMCA_GMI_PHY] = { smca_xgmiphy_mce_desc, ARRAY_SIZE(smca_xgmiphy_mce_desc) },
};
static bool f12h_mc0_mce(u16 ec, u8 xec)
@@ -1045,20 +1166,13 @@ static void decode_mc6_mce(struct mce *m)
/* Decode errors according to Scalable MCA specification */
static void decode_smca_error(struct mce *m)
{
- struct smca_hwid *hwid;
- enum smca_bank_types bank_type;
+ enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank);
const char *ip_name;
u8 xec = XEC(m->status, xec_mask);
- if (m->bank >= ARRAY_SIZE(smca_banks))
+ if (bank_type >= N_SMCA_BANK_TYPES)
return;
- hwid = smca_banks[m->bank].hwid;
- if (!hwid)
- return;
-
- bank_type = hwid->bank_type;
-
if (bank_type == SMCA_RESERVED) {
pr_emerg(HW_ERR "Bank %d is reserved.\n", m->bank);
return;