@@ -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.
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/ras.h>
#include "amd64_edac.h"
#include <asm/amd_nb.h>
@@ -1043,281 +1044,6 @@ 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);
/*
@@ -3065,9 +2791,9 @@ 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 err_info err;
- u64 sys_addr;
node_id = fixup_node_id(node_id, m);
@@ -3098,7 +2824,9 @@ 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)) {
+ sys_addr = amd_convert_umc_mca_addr_to_sys_addr(m);
+
+ if (IS_ERR_VALUE(sys_addr)) {
err.err_code = ERR_NORM_ADDR;
goto log_error;
}
Remove old address translation code and use the new AMD Address Translation Library. Use "imply" in Kconfig so that the "AMD_ATL" config option takes the value of "EDAC_AMD64" as its default. Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com> --- Link: https://lore.kernel.org/r/20231210194932.43992-3-yazen.ghannam@amd.com v3->v4: * Adjust header include and library function name. * Use IS_ERR_VALUE() to check for translation success. v2->v3: * Adjust header include and library function name. v1->v2: * Drop the "config reachable" check. drivers/edac/Kconfig | 1 + drivers/edac/amd64_edac.c | 282 +------------------------------------- 2 files changed, 6 insertions(+), 277 deletions(-)