aboutsummaryrefslogtreecommitdiff
path: root/drivers/edac/bluefield_edac.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /drivers/edac/bluefield_edac.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'drivers/edac/bluefield_edac.c')
-rw-r--r--drivers/edac/bluefield_edac.c356
1 files changed, 356 insertions, 0 deletions
diff --git a/drivers/edac/bluefield_edac.c b/drivers/edac/bluefield_edac.c
new file mode 100644
index 000000000..e4736eb37
--- /dev/null
+++ b/drivers/edac/bluefield_edac.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Bluefield-specific EDAC driver.
+ *
+ * Copyright (c) 2019 Mellanox Technologies.
+ */
+
+#include <linux/acpi.h>
+#include <linux/arm-smccc.h>
+#include <linux/bitfield.h>
+#include <linux/edac.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "edac_module.h"
+
+#define DRIVER_NAME "bluefield-edac"
+
+/*
+ * Mellanox BlueField EMI (External Memory Interface) register definitions.
+ */
+
+#define MLXBF_ECC_CNT 0x340
+#define MLXBF_ECC_CNT__SERR_CNT GENMASK(15, 0)
+#define MLXBF_ECC_CNT__DERR_CNT GENMASK(31, 16)
+
+#define MLXBF_ECC_ERR 0x348
+#define MLXBF_ECC_ERR__SECC BIT(0)
+#define MLXBF_ECC_ERR__DECC BIT(16)
+
+#define MLXBF_ECC_LATCH_SEL 0x354
+#define MLXBF_ECC_LATCH_SEL__START BIT(24)
+
+#define MLXBF_ERR_ADDR_0 0x358
+
+#define MLXBF_ERR_ADDR_1 0x37c
+
+#define MLXBF_SYNDROM 0x35c
+#define MLXBF_SYNDROM__DERR BIT(0)
+#define MLXBF_SYNDROM__SERR BIT(1)
+#define MLXBF_SYNDROM__SYN GENMASK(25, 16)
+
+#define MLXBF_ADD_INFO 0x364
+#define MLXBF_ADD_INFO__ERR_PRANK GENMASK(9, 8)
+
+#define MLXBF_EDAC_MAX_DIMM_PER_MC 2
+#define MLXBF_EDAC_ERROR_GRAIN 8
+
+/*
+ * Request MLNX_SIP_GET_DIMM_INFO
+ *
+ * Retrieve information about DIMM on a certain slot.
+ *
+ * Call register usage:
+ * a0: MLNX_SIP_GET_DIMM_INFO
+ * a1: (Memory controller index) << 16 | (Dimm index in memory controller)
+ * a2-7: not used.
+ *
+ * Return status:
+ * a0: MLXBF_DIMM_INFO defined below describing the DIMM.
+ * a1-3: not used.
+ */
+#define MLNX_SIP_GET_DIMM_INFO 0x82000008
+
+/* Format for the SMC response about the memory information */
+#define MLXBF_DIMM_INFO__SIZE_GB GENMASK_ULL(15, 0)
+#define MLXBF_DIMM_INFO__IS_RDIMM BIT(16)
+#define MLXBF_DIMM_INFO__IS_LRDIMM BIT(17)
+#define MLXBF_DIMM_INFO__IS_NVDIMM BIT(18)
+#define MLXBF_DIMM_INFO__RANKS GENMASK_ULL(23, 21)
+#define MLXBF_DIMM_INFO__PACKAGE_X GENMASK_ULL(31, 24)
+
+struct bluefield_edac_priv {
+ int dimm_ranks[MLXBF_EDAC_MAX_DIMM_PER_MC];
+ void __iomem *emi_base;
+ int dimm_per_mc;
+};
+
+static u64 smc_call1(u64 smc_op, u64 smc_arg)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_smc(smc_op, smc_arg, 0, 0, 0, 0, 0, 0, &res);
+
+ return res.a0;
+}
+
+/*
+ * Gather the ECC information from the External Memory Interface registers
+ * and report it to the edac handler.
+ */
+static void bluefield_gather_report_ecc(struct mem_ctl_info *mci,
+ int error_cnt,
+ int is_single_ecc)
+{
+ struct bluefield_edac_priv *priv = mci->pvt_info;
+ u32 dram_additional_info, err_prank, edea0, edea1;
+ u32 ecc_latch_select, dram_syndrom, serr, derr, syndrom;
+ enum hw_event_mc_err_type ecc_type;
+ u64 ecc_dimm_addr;
+ int ecc_dimm;
+
+ ecc_type = is_single_ecc ? HW_EVENT_ERR_CORRECTED :
+ HW_EVENT_ERR_UNCORRECTED;
+
+ /*
+ * Tell the External Memory Interface to populate the relevant
+ * registers with information about the last ECC error occurrence.
+ */
+ ecc_latch_select = MLXBF_ECC_LATCH_SEL__START;
+ writel(ecc_latch_select, priv->emi_base + MLXBF_ECC_LATCH_SEL);
+
+ /*
+ * Verify that the ECC reported info in the registers is of the
+ * same type as the one asked to report. If not, just report the
+ * error without the detailed information.
+ */
+ dram_syndrom = readl(priv->emi_base + MLXBF_SYNDROM);
+ serr = FIELD_GET(MLXBF_SYNDROM__SERR, dram_syndrom);
+ derr = FIELD_GET(MLXBF_SYNDROM__DERR, dram_syndrom);
+ syndrom = FIELD_GET(MLXBF_SYNDROM__SYN, dram_syndrom);
+
+ if ((is_single_ecc && !serr) || (!is_single_ecc && !derr)) {
+ edac_mc_handle_error(ecc_type, mci, error_cnt, 0, 0, 0,
+ 0, 0, -1, mci->ctl_name, "");
+ return;
+ }
+
+ dram_additional_info = readl(priv->emi_base + MLXBF_ADD_INFO);
+ err_prank = FIELD_GET(MLXBF_ADD_INFO__ERR_PRANK, dram_additional_info);
+
+ ecc_dimm = (err_prank >= 2 && priv->dimm_ranks[0] <= 2) ? 1 : 0;
+
+ edea0 = readl(priv->emi_base + MLXBF_ERR_ADDR_0);
+ edea1 = readl(priv->emi_base + MLXBF_ERR_ADDR_1);
+
+ ecc_dimm_addr = ((u64)edea1 << 32) | edea0;
+
+ edac_mc_handle_error(ecc_type, mci, error_cnt,
+ PFN_DOWN(ecc_dimm_addr),
+ offset_in_page(ecc_dimm_addr),
+ syndrom, ecc_dimm, 0, 0, mci->ctl_name, "");
+}
+
+static void bluefield_edac_check(struct mem_ctl_info *mci)
+{
+ struct bluefield_edac_priv *priv = mci->pvt_info;
+ u32 ecc_count, single_error_count, double_error_count, ecc_error = 0;
+
+ /*
+ * The memory controller might not be initialized by the firmware
+ * when there isn't memory, which may lead to bad register readings.
+ */
+ if (mci->edac_cap == EDAC_FLAG_NONE)
+ return;
+
+ ecc_count = readl(priv->emi_base + MLXBF_ECC_CNT);
+ single_error_count = FIELD_GET(MLXBF_ECC_CNT__SERR_CNT, ecc_count);
+ double_error_count = FIELD_GET(MLXBF_ECC_CNT__DERR_CNT, ecc_count);
+
+ if (single_error_count) {
+ ecc_error |= MLXBF_ECC_ERR__SECC;
+
+ bluefield_gather_report_ecc(mci, single_error_count, 1);
+ }
+
+ if (double_error_count) {
+ ecc_error |= MLXBF_ECC_ERR__DECC;
+
+ bluefield_gather_report_ecc(mci, double_error_count, 0);
+ }
+
+ /* Write to clear reported errors. */
+ if (ecc_count)
+ writel(ecc_error, priv->emi_base + MLXBF_ECC_ERR);
+}
+
+/* Initialize the DIMMs information for the given memory controller. */
+static void bluefield_edac_init_dimms(struct mem_ctl_info *mci)
+{
+ struct bluefield_edac_priv *priv = mci->pvt_info;
+ int mem_ctrl_idx = mci->mc_idx;
+ struct dimm_info *dimm;
+ u64 smc_info, smc_arg;
+ int is_empty = 1, i;
+
+ for (i = 0; i < priv->dimm_per_mc; i++) {
+ dimm = mci->dimms[i];
+
+ smc_arg = mem_ctrl_idx << 16 | i;
+ smc_info = smc_call1(MLNX_SIP_GET_DIMM_INFO, smc_arg);
+
+ if (!FIELD_GET(MLXBF_DIMM_INFO__SIZE_GB, smc_info)) {
+ dimm->mtype = MEM_EMPTY;
+ continue;
+ }
+
+ is_empty = 0;
+
+ dimm->edac_mode = EDAC_SECDED;
+
+ if (FIELD_GET(MLXBF_DIMM_INFO__IS_NVDIMM, smc_info))
+ dimm->mtype = MEM_NVDIMM;
+ else if (FIELD_GET(MLXBF_DIMM_INFO__IS_LRDIMM, smc_info))
+ dimm->mtype = MEM_LRDDR4;
+ else if (FIELD_GET(MLXBF_DIMM_INFO__IS_RDIMM, smc_info))
+ dimm->mtype = MEM_RDDR4;
+ else
+ dimm->mtype = MEM_DDR4;
+
+ dimm->nr_pages =
+ FIELD_GET(MLXBF_DIMM_INFO__SIZE_GB, smc_info) *
+ (SZ_1G / PAGE_SIZE);
+ dimm->grain = MLXBF_EDAC_ERROR_GRAIN;
+
+ /* Mem controller for BlueField only supports x4, x8 and x16 */
+ switch (FIELD_GET(MLXBF_DIMM_INFO__PACKAGE_X, smc_info)) {
+ case 4:
+ dimm->dtype = DEV_X4;
+ break;
+ case 8:
+ dimm->dtype = DEV_X8;
+ break;
+ case 16:
+ dimm->dtype = DEV_X16;
+ break;
+ default:
+ dimm->dtype = DEV_UNKNOWN;
+ }
+
+ priv->dimm_ranks[i] =
+ FIELD_GET(MLXBF_DIMM_INFO__RANKS, smc_info);
+ }
+
+ if (is_empty)
+ mci->edac_cap = EDAC_FLAG_NONE;
+ else
+ mci->edac_cap = EDAC_FLAG_SECDED;
+}
+
+static int bluefield_edac_mc_probe(struct platform_device *pdev)
+{
+ struct bluefield_edac_priv *priv;
+ struct device *dev = &pdev->dev;
+ struct edac_mc_layer layers[1];
+ struct mem_ctl_info *mci;
+ struct resource *emi_res;
+ unsigned int mc_idx, dimm_count;
+ int rc, ret;
+
+ /* Read the MSS (Memory SubSystem) index from ACPI table. */
+ if (device_property_read_u32(dev, "mss_number", &mc_idx)) {
+ dev_warn(dev, "bf_edac: MSS number unknown\n");
+ return -EINVAL;
+ }
+
+ /* Read the DIMMs per MC from ACPI table. */
+ if (device_property_read_u32(dev, "dimm_per_mc", &dimm_count)) {
+ dev_warn(dev, "bf_edac: DIMMs per MC unknown\n");
+ return -EINVAL;
+ }
+
+ if (dimm_count > MLXBF_EDAC_MAX_DIMM_PER_MC) {
+ dev_warn(dev, "bf_edac: DIMMs per MC not valid\n");
+ return -EINVAL;
+ }
+
+ emi_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!emi_res)
+ return -EINVAL;
+
+ layers[0].type = EDAC_MC_LAYER_SLOT;
+ layers[0].size = dimm_count;
+ layers[0].is_virt_csrow = true;
+
+ mci = edac_mc_alloc(mc_idx, ARRAY_SIZE(layers), layers, sizeof(*priv));
+ if (!mci)
+ return -ENOMEM;
+
+ priv = mci->pvt_info;
+
+ priv->dimm_per_mc = dimm_count;
+ priv->emi_base = devm_ioremap_resource(dev, emi_res);
+ if (IS_ERR(priv->emi_base)) {
+ dev_err(dev, "failed to map EMI IO resource\n");
+ ret = PTR_ERR(priv->emi_base);
+ goto err;
+ }
+
+ mci->pdev = dev;
+ mci->mtype_cap = MEM_FLAG_DDR4 | MEM_FLAG_RDDR4 |
+ MEM_FLAG_LRDDR4 | MEM_FLAG_NVDIMM;
+ mci->edac_ctl_cap = EDAC_FLAG_SECDED;
+
+ mci->mod_name = DRIVER_NAME;
+ mci->ctl_name = "BlueField_Memory_Controller";
+ mci->dev_name = dev_name(dev);
+ mci->edac_check = bluefield_edac_check;
+
+ /* Initialize mci with the actual populated DIMM information. */
+ bluefield_edac_init_dimms(mci);
+
+ platform_set_drvdata(pdev, mci);
+
+ /* Register with EDAC core */
+ rc = edac_mc_add_mc(mci);
+ if (rc) {
+ dev_err(dev, "failed to register with EDAC core\n");
+ ret = rc;
+ goto err;
+ }
+
+ /* Only POLL mode supported so far. */
+ edac_op_state = EDAC_OPSTATE_POLL;
+
+ return 0;
+
+err:
+ edac_mc_free(mci);
+
+ return ret;
+
+}
+
+static int bluefield_edac_mc_remove(struct platform_device *pdev)
+{
+ struct mem_ctl_info *mci = platform_get_drvdata(pdev);
+
+ edac_mc_del_mc(&pdev->dev);
+ edac_mc_free(mci);
+
+ return 0;
+}
+
+static const struct acpi_device_id bluefield_mc_acpi_ids[] = {
+ {"MLNXBF08", 0},
+ {}
+};
+
+MODULE_DEVICE_TABLE(acpi, bluefield_mc_acpi_ids);
+
+static struct platform_driver bluefield_edac_mc_driver = {
+ .driver = {
+ .name = DRIVER_NAME,
+ .acpi_match_table = bluefield_mc_acpi_ids,
+ },
+ .probe = bluefield_edac_mc_probe,
+ .remove = bluefield_edac_mc_remove,
+};
+
+module_platform_driver(bluefield_edac_mc_driver);
+
+MODULE_DESCRIPTION("Mellanox BlueField memory edac driver");
+MODULE_AUTHOR("Mellanox Technologies");
+MODULE_LICENSE("GPL v2");