diff options
33 files changed, 5165 insertions, 336 deletions
diff --git a/Documentation/admin-guide/RAS/address-translation.rst b/Documentation/admin-guide/RAS/address-translation.rst new file mode 100644 index 000000000000..f0ca17b43cd3 --- /dev/null +++ b/Documentation/admin-guide/RAS/address-translation.rst @@ -0,0 +1,24 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Address translation +=================== + +x86 AMD +------- + +Zen-based AMD systems include a Data Fabric that manages the layout of +physical memory. Devices attached to the Fabric, like memory controllers, +I/O, etc., may not have a complete view of the system physical memory map. +These devices may provide a "normalized", i.e. device physical, address +when reporting memory errors. Normalized addresses must be translated to +a system physical address for the kernel to action on the memory. + +AMD Address Translation Library (CONFIG_AMD_ATL) provides translation for +this case. + +Glossary of acronyms used in address translation for Zen-based systems + +* CCM = Cache Coherent Moderator +* COD = Cluster-on-Die +* COH_ST = Coherent Station +* DF = Data Fabric diff --git a/Documentation/RAS/ras.rst b/Documentation/admin-guide/RAS/error-decoding.rst index 2556b397cd27..26a72f3fe5de 100644 --- a/Documentation/RAS/ras.rst +++ b/Documentation/admin-guide/RAS/error-decoding.rst @@ -1,15 +1,10 @@ .. SPDX-License-Identifier: GPL-2.0 -Reliability, Availability and Serviceability features -===================================================== - -This documents different aspects of the RAS functionality present in the -kernel. - Error decoding ---------------- +============== -* x86 +x86 +--- Error decoding on AMD systems should be done using the rasdaemon tool: https://github.com/mchehab/rasdaemon/ diff --git a/Documentation/admin-guide/RAS/index.rst b/Documentation/admin-guide/RAS/index.rst new file mode 100644 index 000000000000..f4087040a7c0 --- /dev/null +++ b/Documentation/admin-guide/RAS/index.rst @@ -0,0 +1,7 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. toctree:: + :maxdepth: 2 + + main + error-decoding + address-translation diff --git a/Documentation/admin-guide/ras.rst b/Documentation/admin-guide/RAS/main.rst index 8e03751d126d..7ac1d4ccc509 100644 --- a/Documentation/admin-guide/ras.rst +++ b/Documentation/admin-guide/RAS/main.rst @@ -1,8 +1,12 @@ +.. SPDX-License-Identifier: GPL-2.0 .. include:: <isonum.txt> -============================================ -Reliability, Availability and Serviceability -============================================ +================================================== +Reliability, Availability and Serviceability (RAS) +================================================== + +This documents different aspects of the RAS functionality present in the +kernel. RAS concepts ************ diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index fb40a1f6f79e..dfc06fab9432 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -122,7 +122,7 @@ configure specific aspects of kernel behavior to your liking. pmf pnp rapidio - ras + RAS/index rtc serial-console svga diff --git a/Documentation/index.rst b/Documentation/index.rst index 36e61783437c..9dfdc826618c 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -113,7 +113,6 @@ to ReStructured Text format, or are simply too old. :maxdepth: 1 staging/index - RAS/ras Translations diff --git a/MAINTAINERS b/MAINTAINERS index 747f492ce6cc..a3c7accd3877 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -897,6 +897,12 @@ Q: https://patchwork.kernel.org/project/linux-rdma/list/ F: drivers/infiniband/hw/efa/ F: include/uapi/rdma/efa-abi.h +AMD ADDRESS TRANSLATION LIBRARY (ATL) +M: Yazen Ghannam <Yazen.Ghannam@amd.com> +L: linux-edac@vger.kernel.org +S: Supported +F: drivers/ras/amd/atl/* + AMD AXI W1 DRIVER M: Kris Chaplin <kris.chaplin@amd.com> R: Thomas Delev <thomas.delev@amd.com> @@ -7583,7 +7589,6 @@ R: Robert Richter <rric@kernel.org> L: linux-edac@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras.git edac-for-next -F: Documentation/admin-guide/ras.rst F: Documentation/driver-api/edac.rst F: drivers/edac/ F: include/linux/edac.h @@ -18379,11 +18384,17 @@ M: Tony Luck <tony.luck@intel.com> M: Borislav Petkov <bp@alien8.de> L: linux-edac@vger.kernel.org S: Maintained -F: Documentation/admin-guide/ras.rst +F: Documentation/admin-guide/RAS F: drivers/ras/ F: include/linux/ras.h F: include/ras/ras_event.h +RAS FRU MEMORY POISON MANAGER (FMPM) +M: Yazen Ghannam <Yazen.Ghannam@amd.com> +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/ras/amd/fmpm.c + RC-CORE / LIRC FRAMEWORK M: Sean Young <sean@mess.org> L: linux-media@vger.kernel.org diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 76b1d87f1531..abe3a8f22cbd 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -224,7 +224,7 @@ static inline bool topology_is_primary_thread(unsigned int cpu) static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } -static inline unsigned int topology_amd_nodes_per_pkg(void) { return 0; }; +static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; } #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index 5a7f3fabee22..16c8de5050e5 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -78,6 +78,7 @@ config EDAC_GHES config EDAC_AMD64 tristate "AMD64 (Opteron, Athlon64)" depends on AMD_NB && EDAC_DECODE_MCE + imply AMD_ATL help Support for error detection and correction of DRAM ECC errors on the AMD64 families (>= K8) of memory controllers. diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 2b8c20bb926a..1f3520d76861 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#include <linux/ras.h> #include "amd64_edac.h" #include <asm/amd_nb.h> @@ -1051,281 +1052,6 @@ static int fixup_node_id(int node_id, struct mce *m) 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); - -/* - * 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); /* @@ -3073,9 +2799,10 @@ static void decode_umc_error(int node_id, struct mce *m) { u8 ecc_type = (m->status >> 45) & 0x3; struct mem_ctl_info *mci; + unsigned long sys_addr; struct amd64_pvt *pvt; + struct atl_err a_err; struct err_info err; - u64 sys_addr; node_id = fixup_node_id(node_id, m); @@ -3106,7 +2833,12 @@ static void decode_umc_error(int node_id, struct mce *m) pvt->ops->get_err_info(m, &err); - if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) { + a_err.addr = m->addr; + a_err.ipid = m->ipid; + a_err.cpu = m->extcpu; + + sys_addr = amd_convert_umc_mca_addr_to_sys_addr(&a_err); + if (IS_ERR_VALUE(sys_addr)) { err.err_code = ERR_NORM_ADDR; goto log_error; } diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c index 2b83d6de9352..3fd22a1eb1a9 100644 --- a/drivers/edac/i10nm_base.c +++ b/drivers/edac/i10nm_base.c @@ -951,6 +951,7 @@ static const struct x86_cpu_id i10nm_cpuids[] = { X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(EMERALDRAPIDS_X, X86_STEPPINGS(0x0, 0xf), &spr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(GRANITERAPIDS_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT_X, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), + X86_MATCH_INTEL_FAM6_MODEL_STEPPINGS(ATOM_CRESTMONT, X86_STEPPINGS(0x0, 0xf), &gnr_cfg), {} }; MODULE_DEVICE_TABLE(x86cpu, i10nm_cpuids); diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index 2b0ecdeba5cd..cdd8480e7368 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -238,6 +238,7 @@ static struct work_struct ecclog_work; #define DID_ADL_N_SKU9 0x4678 #define DID_ADL_N_SKU10 0x4679 #define DID_ADL_N_SKU11 0x467c +#define DID_ADL_N_SKU12 0x4632 /* Compute die IDs for Raptor Lake-P with IBECC */ #define DID_RPL_P_SKU1 0xa706 @@ -583,6 +584,7 @@ static const struct pci_device_id igen6_pci_tbl[] = { { PCI_VDEVICE(INTEL, DID_ADL_N_SKU9), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU10), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_ADL_N_SKU11), (kernel_ulong_t)&adl_n_cfg }, + { PCI_VDEVICE(INTEL, DID_ADL_N_SKU12), (kernel_ulong_t)&adl_n_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU1), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU2), (kernel_ulong_t)&rpl_p_cfg }, { PCI_VDEVICE(INTEL, DID_RPL_P_SKU3), (kernel_ulong_t)&rpl_p_cfg }, diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index 709babce43ba..5527055b0964 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -1324,11 +1324,9 @@ static int mc_probe(struct platform_device *pdev) struct synps_edac_priv *priv; struct mem_ctl_info *mci; void __iomem *baseaddr; - struct resource *res; int rc; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - baseaddr = devm_ioremap_resource(&pdev->dev, res); + baseaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(baseaddr)) return PTR_ERR(baseaddr); diff --git a/drivers/edac/versal_edac.c b/drivers/edac/versal_edac.c index 62caf454b567..1688a5050f63 100644 --- a/drivers/edac/versal_edac.c +++ b/drivers/edac/versal_edac.c @@ -42,8 +42,11 @@ #define ECCW0_FLIP_CTRL 0x109C #define ECCW0_FLIP0_OFFSET 0x10A0 +#define ECCW0_FLIP0_BITS 31 +#define ECCW0_FLIP1_OFFSET 0x10A4 #define ECCW1_FLIP_CTRL 0x10AC #define ECCW1_FLIP0_OFFSET 0x10B0 +#define ECCW1_FLIP1_OFFSET 0x10B4 #define ECCR0_CERR_STAT_OFFSET 0x10BC #define ECCR0_CE_ADDR_LO_OFFSET 0x10C0 #define ECCR0_CE_ADDR_HI_OFFSET 0x10C4 @@ -116,9 +119,6 @@ #define XDDR_BUS_WIDTH_32 1 #define XDDR_BUS_WIDTH_16 2 -#define ECC_CEPOISON_MASK 0x1 -#define ECC_UEPOISON_MASK 0x3 - #define XDDR_MAX_ROW_CNT 18 #define XDDR_MAX_COL_CNT 10 #define XDDR_MAX_RANK_CNT 2 @@ -133,6 +133,7 @@ * https://docs.xilinx.com/r/en-US/am012-versal-register-reference/PCSR_LOCK-XRAM_SLCR-Register */ #define PCSR_UNLOCK_VAL 0xF9E8D7C6 +#define PCSR_LOCK_VAL 1 #define XDDR_ERR_TYPE_CE 0 #define XDDR_ERR_TYPE_UE 1 @@ -142,6 +143,7 @@ #define XILINX_DRAM_SIZE_12G 3 #define XILINX_DRAM_SIZE_16G 4 #define XILINX_DRAM_SIZE_32G 5 +#define NUM_UE_BITPOS 2 /** * struct ecc_error_info - ECC error log information. @@ -479,7 +481,7 @@ static void err_callback(const u32 *payload, void *data) writel(regval, priv->ddrmc_baseaddr + XDDR_ISR_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); edac_dbg(3, "Total error count CE %d UE %d\n", priv->ce_cnt, priv->ue_cnt); } @@ -650,7 +652,7 @@ static void enable_intr(struct edac_priv *priv) writel(XDDR_IRQ_UE_MASK, priv->ddrmc_baseaddr + XDDR_IRQ1_EN_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } static void disable_intr(struct edac_priv *priv) @@ -663,7 +665,7 @@ static void disable_intr(struct edac_priv *priv) priv->ddrmc_baseaddr + XDDR_IRQ_DIS_OFFSET); /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); } #define to_mci(k) container_of(k, struct mem_ctl_info, dev) @@ -734,38 +736,63 @@ static void poison_setup(struct edac_priv *priv) writel(regval, priv->ddrmc_noc_baseaddr + XDDR_NOC_REG_ADEC15_OFFSET); } -static ssize_t xddr_inject_data_poison_store(struct mem_ctl_info *mci, - const char __user *data) +static void xddr_inject_data_ce_store(struct mem_ctl_info *mci, u8 ce_bitpos) { + u32 ecc0_flip0, ecc1_flip0, ecc0_flip1, ecc1_flip1; struct edac_priv *priv = mci->pvt_info; - writel(0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); - writel(0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); - - if (strncmp(data, "CE", 2) == 0) { - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_CEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + if (ce_bitpos < ECCW0_FLIP0_BITS) { + ecc0_flip0 = BIT(ce_bitpos); + ecc1_flip0 = BIT(ce_bitpos); + ecc0_flip1 = 0; + ecc1_flip1 = 0; } else { - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW0_FLIP0_OFFSET); - writel(ECC_UEPOISON_MASK, priv->ddrmc_baseaddr + - ECCW1_FLIP0_OFFSET); + ce_bitpos = ce_bitpos - ECCW0_FLIP0_BITS; + ecc0_flip1 = BIT(ce_bitpos); + ecc1_flip1 = BIT(ce_bitpos); + ecc0_flip0 = 0; + ecc1_flip0 = 0; } - /* Lock the PCSR registers */ - writel(1, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); - - return 0; + writel(ecc0_flip0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(ecc1_flip0, priv->ddrmc_baseaddr + ECCW1_FLIP0_OFFSET); + writel(ecc0_flip1, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(ecc1_flip1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); } -static ssize_t inject_data_poison_store(struct file *file, const char __user *data, - size_t count, loff_t *ppos) +/* + * To inject a correctable error, the following steps are needed: + * + * - Write the correctable error bit position value: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ce + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 to make sure default + * configuration is there and no addresses are masked. + * + * The row, column, bank, group and rank registers are written to the + * match ADEC bit to generate errors at the particular address. ADEC14 + * and ADEC15 have the match bits. + * + * xddr_inject_data_ce_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ce_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) { struct device *dev = file->private_data; struct mem_ctl_info *mci = to_mci(dev); struct edac_priv *priv = mci->pvt_info; + u8 ce_bitpos; + int ret; + + ret = kstrtou8_from_user(data, count, 0, &ce_bitpos); + if (ret) + return ret; /* Unlock the PCSR registers */ writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); @@ -773,17 +800,110 @@ static ssize_t inject_data_poison_store(struct file *file, const char __user *da poison_setup(priv); + xddr_inject_data_ce_store(mci, ce_bitpos); + ret = count; + /* Lock the PCSR registers */ - writel(1, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + + return ret; +} + +static const struct file_operations xddr_inject_ce_fops = { + .open = simple_open, + .write = inject_data_ce_store, + .llseek = generic_file_llseek, +}; + +static void xddr_inject_data_ue_store(struct mem_ctl_info *mci, u32 val0, u32 val1) +{ + struct edac_priv *priv = mci->pvt_info; + + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP0_OFFSET); + writel(val0, priv->ddrmc_baseaddr + ECCW0_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); + writel(val1, priv->ddrmc_baseaddr + ECCW1_FLIP1_OFFSET); +} + +/* + * To inject an uncorrectable error, the following steps are needed: + * echo <bit_pos val> > /sys/kernel/debug/edac/<controller instance>/inject_ue + * + * poison_setup() derives the row, column, bank, group and rank and + * writes to the ADEC registers based on the address given by the user. + * + * The ADEC12 and ADEC13 are mask registers; write 0 so that none of the + * addresses are masked. The row, column, bank, group and rank registers + * are written to the match ADEC bit to generate errors at the + * particular address. ADEC14 and ADEC15 have the match bits. + * + * xddr_inject_data_ue_store() updates the ECC FLIP registers with the + * bits to be corrupted based on the bit position given by the user. For + * uncorrectable errors + * 2 bit errors are injected. + * + * Upon doing a read to the address the errors are injected. + */ +static ssize_t inject_data_ue_store(struct file *file, const char __user *data, + size_t count, loff_t *ppos) +{ + struct device *dev = file->private_data; + struct mem_ctl_info *mci = to_mci(dev); + struct edac_priv *priv = mci->pvt_info; + char buf[6], *pbuf, *token[2]; + u32 val0 = 0, val1 = 0; + u8 len, ue0, ue1; + int i, ret; + + len = min_t(size_t, count, sizeof(buf)); + if (copy_from_user(buf, data, len)) + return -EFAULT; + + buf[len] = '\0'; + pbuf = &buf[0]; + for (i = 0; i < NUM_UE_BITPOS; i++) + token[i] = strsep(&pbuf, ","); + + ret = kstrtou8(token[0], 0, &ue0); + if (ret) + return ret; + + ret = kstrtou8(token[1], 0, &ue1); + if (ret) + return ret; + + if (ue0 < ECCW0_FLIP0_BITS) { + val0 = BIT(ue0); + } else { + ue0 = ue0 - ECCW0_FLIP0_BITS; + val1 = BIT(ue0); + } + + if (ue1 < ECCW0_FLIP0_BITS) { + val0 |= BIT(ue1); + } else { + ue1 = ue1 - ECCW0_FLIP0_BITS; + val1 |= BIT(ue1); + } - xddr_inject_data_poison_store(mci, data); + /* Unlock the PCSR registers */ + writel(PCSR_UNLOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_UNLOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + poison_setup(priv); + + xddr_inject_data_ue_store(mci, val0, val1); + + /* Lock the PCSR registers */ + writel(PCSR_LOCK_VAL, priv->ddrmc_noc_baseaddr + XDDR_PCSR_OFFSET); + writel(PCSR_LOCK_VAL, priv->ddrmc_baseaddr + XDDR_PCSR_OFFSET); return count; } |