aboutsummaryrefslogtreecommitdiff
path: root/drivers/misc/smpro-errmon.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/misc/smpro-errmon.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/misc/smpro-errmon.c')
-rw-r--r--drivers/misc/smpro-errmon.c529
1 files changed, 529 insertions, 0 deletions
diff --git a/drivers/misc/smpro-errmon.c b/drivers/misc/smpro-errmon.c
new file mode 100644
index 000000000..d1431d419
--- /dev/null
+++ b/drivers/misc/smpro-errmon.c
@@ -0,0 +1,529 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Ampere Computing SoC's SMpro Error Monitoring Driver
+ *
+ * Copyright (c) 2022, Ampere Computing LLC
+ *
+ */
+
+#include <linux/i2c.h>
+#include <linux/mod_devicetable.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+/* GPI RAS Error Registers */
+#define GPI_RAS_ERR 0x7E
+
+/* Core and L2C Error Registers */
+#define CORE_CE_ERR_CNT 0x80
+#define CORE_CE_ERR_LEN 0x81
+#define CORE_CE_ERR_DATA 0x82
+#define CORE_UE_ERR_CNT 0x83
+#define CORE_UE_ERR_LEN 0x84
+#define CORE_UE_ERR_DATA 0x85
+
+/* Memory Error Registers */
+#define MEM_CE_ERR_CNT 0x90
+#define MEM_CE_ERR_LEN 0x91
+#define MEM_CE_ERR_DATA 0x92
+#define MEM_UE_ERR_CNT 0x93
+#define MEM_UE_ERR_LEN 0x94
+#define MEM_UE_ERR_DATA 0x95
+
+/* RAS Error/Warning Registers */
+#define ERR_SMPRO_TYPE 0xA0
+#define ERR_PMPRO_TYPE 0xA1
+#define ERR_SMPRO_INFO_LO 0xA2
+#define ERR_SMPRO_INFO_HI 0xA3
+#define ERR_SMPRO_DATA_LO 0xA4
+#define ERR_SMPRO_DATA_HI 0xA5
+#define WARN_SMPRO_INFO_LO 0xAA
+#define WARN_SMPRO_INFO_HI 0xAB
+#define ERR_PMPRO_INFO_LO 0xA6
+#define ERR_PMPRO_INFO_HI 0xA7
+#define ERR_PMPRO_DATA_LO 0xA8
+#define ERR_PMPRO_DATA_HI 0xA9
+#define WARN_PMPRO_INFO_LO 0xAC
+#define WARN_PMPRO_INFO_HI 0xAD
+
+/* PCIE Error Registers */
+#define PCIE_CE_ERR_CNT 0xC0
+#define PCIE_CE_ERR_LEN 0xC1
+#define PCIE_CE_ERR_DATA 0xC2
+#define PCIE_UE_ERR_CNT 0xC3
+#define PCIE_UE_ERR_LEN 0xC4
+#define PCIE_UE_ERR_DATA 0xC5
+
+/* Other Error Registers */
+#define OTHER_CE_ERR_CNT 0xD0
+#define OTHER_CE_ERR_LEN 0xD1
+#define OTHER_CE_ERR_DATA 0xD2
+#define OTHER_UE_ERR_CNT 0xD8
+#define OTHER_UE_ERR_LEN 0xD9
+#define OTHER_UE_ERR_DATA 0xDA
+
+/* Event Data Registers */
+#define VRD_WARN_FAULT_EVENT_DATA 0x78
+#define VRD_HOT_EVENT_DATA 0x79
+#define DIMM_HOT_EVENT_DATA 0x7A
+
+#define MAX_READ_BLOCK_LENGTH 48
+
+#define RAS_SMPRO_ERR 0
+#define RAS_PMPRO_ERR 1
+
+enum RAS_48BYTES_ERR_TYPES {
+ CORE_CE_ERR,
+ CORE_UE_ERR,
+ MEM_CE_ERR,
+ MEM_UE_ERR,
+ PCIE_CE_ERR,
+ PCIE_UE_ERR,
+ OTHER_CE_ERR,
+ OTHER_UE_ERR,
+ NUM_48BYTES_ERR_TYPE,
+};
+
+struct smpro_error_hdr {
+ u8 count; /* Number of the RAS errors */
+ u8 len; /* Number of data bytes */
+ u8 data; /* Start of 48-byte data */
+ u8 max_cnt; /* Max num of errors */
+};
+
+/*
+ * Included Address of registers to get Count, Length of data and Data
+ * of the 48 bytes error data
+ */
+static struct smpro_error_hdr smpro_error_table[] = {
+ [CORE_CE_ERR] = {
+ .count = CORE_CE_ERR_CNT,
+ .len = CORE_CE_ERR_LEN,
+ .data = CORE_CE_ERR_DATA,
+ .max_cnt = 32
+ },
+ [CORE_UE_ERR] = {
+ .count = CORE_UE_ERR_CNT,
+ .len = CORE_UE_ERR_LEN,
+ .data = CORE_UE_ERR_DATA,
+ .max_cnt = 32
+ },
+ [MEM_CE_ERR] = {
+ .count = MEM_CE_ERR_CNT,
+ .len = MEM_CE_ERR_LEN,
+ .data = MEM_CE_ERR_DATA,
+ .max_cnt = 16
+ },
+ [MEM_UE_ERR] = {
+ .count = MEM_UE_ERR_CNT,
+ .len = MEM_UE_ERR_LEN,
+ .data = MEM_UE_ERR_DATA,
+ .max_cnt = 16
+ },
+ [PCIE_CE_ERR] = {
+ .count = PCIE_CE_ERR_CNT,
+ .len = PCIE_CE_ERR_LEN,
+ .data = PCIE_CE_ERR_DATA,
+ .max_cnt = 96
+ },
+ [PCIE_UE_ERR] = {
+ .count = PCIE_UE_ERR_CNT,
+ .len = PCIE_UE_ERR_LEN,
+ .data = PCIE_UE_ERR_DATA,
+ .max_cnt = 96
+ },
+ [OTHER_CE_ERR] = {
+ .count = OTHER_CE_ERR_CNT,
+ .len = OTHER_CE_ERR_LEN,
+ .data = OTHER_CE_ERR_DATA,
+ .max_cnt = 8
+ },
+ [OTHER_UE_ERR] = {
+ .count = OTHER_UE_ERR_CNT,
+ .len = OTHER_UE_ERR_LEN,
+ .data = OTHER_UE_ERR_DATA,
+ .max_cnt = 8
+ },
+};
+
+/*
+ * List of SCP registers which are used to get
+ * one type of RAS Internal errors.
+ */
+struct smpro_int_error_hdr {
+ u8 type;
+ u8 info_l;
+ u8 info_h;
+ u8 data_l;
+ u8 data_h;
+ u8 warn_l;
+ u8 warn_h;
+};
+
+static struct smpro_int_error_hdr list_smpro_int_error_hdr[] = {
+ [RAS_SMPRO_ERR] = {
+ .type = ERR_SMPRO_TYPE,
+ .info_l = ERR_SMPRO_INFO_LO,
+ .info_h = ERR_SMPRO_INFO_HI,
+ .data_l = ERR_SMPRO_DATA_LO,
+ .data_h = ERR_SMPRO_DATA_HI,
+ .warn_l = WARN_SMPRO_INFO_LO,
+ .warn_h = WARN_SMPRO_INFO_HI,
+ },
+ [RAS_PMPRO_ERR] = {
+ .type = ERR_PMPRO_TYPE,
+ .info_l = ERR_PMPRO_INFO_LO,
+ .info_h = ERR_PMPRO_INFO_HI,
+ .data_l = ERR_PMPRO_DATA_LO,
+ .data_h = ERR_PMPRO_DATA_HI,
+ .warn_l = WARN_PMPRO_INFO_LO,
+ .warn_h = WARN_PMPRO_INFO_HI,
+ },
+};
+
+struct smpro_errmon {
+ struct regmap *regmap;
+};
+
+enum EVENT_TYPES {
+ VRD_WARN_FAULT_EVENT,
+ VRD_HOT_EVENT,
+ DIMM_HOT_EVENT,
+ NUM_EVENTS_TYPE,
+};
+
+/* Included Address of event source and data registers */
+static u8 smpro_event_table[NUM_EVENTS_TYPE] = {
+ VRD_WARN_FAULT_EVENT_DATA,
+ VRD_HOT_EVENT_DATA,
+ DIMM_HOT_EVENT_DATA,
+};
+
+static ssize_t smpro_event_data_read(struct device *dev,
+ struct device_attribute *da, char *buf,
+ int channel)
+{
+ struct smpro_errmon *errmon = dev_get_drvdata(dev);
+ s32 event_data;
+ int ret;
+
+ ret = regmap_read(errmon->regmap, smpro_event_table[channel], &event_data);
+ if (ret)
+ return ret;
+ /* Clear event after read */
+ if (event_data != 0)
+ regmap_write(errmon->regmap, smpro_event_table[channel], event_data);
+
+ return sysfs_emit(buf, "%04x\n", event_data);
+}
+
+static ssize_t smpro_overflow_data_read(struct device *dev, struct device_attribute *da,
+ char *buf, int channel)
+{
+ struct smpro_errmon *errmon = dev_get_drvdata(dev);
+ struct smpro_error_hdr *err_info;
+ s32 err_count;
+ int ret;
+
+ err_info = &smpro_error_table[channel];
+
+ ret = regmap_read(errmon->regmap, err_info->count, &err_count);
+ if (ret)
+ return ret;
+
+ /* Bit 8 indicates the overflow status */
+ return sysfs_emit(buf, "%d\n", (err_count & BIT(8)) ? 1 : 0);
+}
+
+static ssize_t smpro_error_data_read(struct device *dev, struct device_attribute *da,
+ char *buf, int channel)
+{
+ struct smpro_errmon *errmon = dev_get_drvdata(dev);
+ unsigned char err_data[MAX_READ_BLOCK_LENGTH];
+ struct smpro_error_hdr *err_info;
+ s32 err_count, err_length;
+ int ret;
+
+ err_info = &smpro_error_table[channel];
+
+ ret = regmap_read(errmon->regmap, err_info->count, &err_count);
+ /* Error count is the low byte */
+ err_count &= 0xff;
+ if (ret || !err_count || err_count > err_info->max_cnt)
+ return ret;
+
+ ret = regmap_read(errmon->regmap, err_info->len, &err_length);
+ if (ret || err_length <= 0)
+ return ret;
+
+ if (err_length > MAX_READ_BLOCK_LENGTH)
+ err_length = MAX_READ_BLOCK_LENGTH;
+
+ memset(err_data, 0x00, MAX_READ_BLOCK_LENGTH);
+ ret = regmap_noinc_read(errmon->regmap, err_info->data, err_data, err_length);
+ if (ret < 0)
+ return ret;
+
+ /* clear the error */
+ ret = regmap_write(errmon->regmap, err_info->count, 0x100);
+ if (ret)
+ return ret;
+ /*
+ * The output of Core/Memory/PCIe/Others UE/CE errors follows the format
+ * specified in section 5.8.1 CE/UE Error Data record in
+ * Altra SOC BMC Interface specification.
+ */
+ return sysfs_emit(buf, "%*phN\n", MAX_READ_BLOCK_LENGTH, err_data);
+}
+
+/*
+ * Output format:
+ * <4-byte hex value of error info><4-byte hex value of error extensive data>
+ * Where:
+ * + error info : The error information
+ * + error data : Extensive data (32 bits)
+ * Reference to section 5.10 RAS Internal Error Register Definition in
+ * Altra SOC BMC Interface specification
+ */
+static ssize_t smpro_internal_err_read(struct device *dev, struct device_attribute *da,
+ char *buf, int channel)
+{
+ struct smpro_errmon *errmon = dev_get_drvdata(dev);
+ struct smpro_int_error_hdr *err_info;
+ unsigned int err[4] = { 0 };
+ unsigned int err_type;
+ unsigned int val;
+ int ret;
+
+ /* read error status */
+ ret = regmap_read(errmon->regmap, GPI_RAS_ERR, &val);
+ if (ret)
+ return ret;
+
+ if ((channel == RAS_SMPRO_ERR && !(val & BIT(0))) ||
+ (channel == RAS_PMPRO_ERR && !(val & BIT(1))))
+ return 0;
+
+ err_info = &list_smpro_int_error_hdr[channel];
+ ret = regmap_read(errmon->regmap, err_info->type, &val);
+ if (ret)
+ return ret;
+
+ err_type = (val & BIT(1)) ? BIT(1) :
+ (val & BIT(2)) ? BIT(2) : 0;
+
+ if (!err_type)
+ return 0;
+
+ ret = regmap_read(errmon->regmap, err_info->info_l, err + 1);
+ if (ret)
+ return ret;
+
+ ret = regmap_read(errmon->regmap, err_info->info_h, err);
+ if (ret)
+ return ret;
+
+ if (err_type & BIT(2)) {
+ /* Error with data type */
+ ret = regmap_read(errmon->regmap, err_info->data_l, err + 3);
+ if (ret)
+ return ret;
+
+ ret = regmap_read(errmon->regmap, err_info->data_h, err + 2);
+ if (ret)
+ return ret;
+ }
+
+ /* clear the read errors */
+ ret = regmap_write(errmon->regmap, err_info->type, err_type);
+ if (ret)
+ return ret;
+
+ return sysfs_emit(buf, "%*phN\n", (int)sizeof(err), err);
+}
+
+/*
+ * Output format:
+ * <4-byte hex value of warining info>
+ * Reference to section 5.10 RAS Internal Error Register Definition in
+ * Altra SOC BMC Interface specification
+ */
+static ssize_t smpro_internal_warn_read(struct device *dev, struct device_attribute *da,
+ char *buf, int channel)
+{
+ struct smpro_errmon *errmon = dev_get_drvdata(dev);
+ struct smpro_int_error_hdr *err_info;
+ unsigned int warn[2] = { 0 };
+ unsigned int val;
+ int ret;
+
+ /* read error status */
+ ret = regmap_read(errmon->regmap, GPI_RAS_ERR, &val);
+ if (ret)
+ return ret;
+
+ if ((channel == RAS_SMPRO_ERR && !(val & BIT(0))) ||
+ (channel == RAS_PMPRO_ERR && !(val & BIT(1))))
+ return 0;
+
+ err_info = &list_smpro_int_error_hdr[channel];
+ ret = regmap_read(errmon->regmap, err_info->type, &val);
+ if (ret)
+ return ret;
+
+ if (!(val & BIT(0)))
+ return 0;
+
+ ret = regmap_read(errmon->regmap, err_info->warn_l, warn + 1);
+ if (ret)
+ return ret;
+
+ ret = regmap_read(errmon->regmap, err_info->warn_h, warn);
+ if (ret)
+ return ret;
+
+ /* clear the warning */
+ ret = regmap_write(errmon->regmap, err_info->type, BIT(0));
+ if (ret)
+ return ret;
+
+ return sysfs_emit(buf, "%*phN\n", (int)sizeof(warn), warn);
+}
+
+#define ERROR_OVERFLOW_RO(_error, _index) \
+ static ssize_t overflow_##_error##_show(struct device *dev, \
+ struct device_attribute *da, \
+ char *buf) \
+ { \
+ return smpro_overflow_data_read(dev, da, buf, _index); \
+ } \
+ static DEVICE_ATTR_RO(overflow_##_error)
+
+ERROR_OVERFLOW_RO(core_ce, CORE_CE_ERR);
+ERROR_OVERFLOW_RO(core_ue, CORE_UE_ERR);
+ERROR_OVERFLOW_RO(mem_ce, MEM_CE_ERR);
+ERROR_OVERFLOW_RO(mem_ue, MEM_UE_ERR);
+ERROR_OVERFLOW_RO(pcie_ce, PCIE_CE_ERR);
+ERROR_OVERFLOW_RO(pcie_ue, PCIE_UE_ERR);
+ERROR_OVERFLOW_RO(other_ce, OTHER_CE_ERR);
+ERROR_OVERFLOW_RO(other_ue, OTHER_UE_ERR);
+
+#define ERROR_RO(_error, _index) \
+ static ssize_t error_##_error##_show(struct device *dev, \
+ struct device_attribute *da, \
+ char *buf) \
+ { \
+ return smpro_error_data_read(dev, da, buf, _index); \
+ } \
+ static DEVICE_ATTR_RO(error_##_error)
+
+ERROR_RO(core_ce, CORE_CE_ERR);
+ERROR_RO(core_ue, CORE_UE_ERR);
+ERROR_RO(mem_ce, MEM_CE_ERR);
+ERROR_RO(mem_ue, MEM_UE_ERR);
+ERROR_RO(pcie_ce, PCIE_CE_ERR);
+ERROR_RO(pcie_ue, PCIE_UE_ERR);
+ERROR_RO(other_ce, OTHER_CE_ERR);
+ERROR_RO(other_ue, OTHER_UE_ERR);
+
+static ssize_t error_smpro_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+ return smpro_internal_err_read(dev, da, buf, RAS_SMPRO_ERR);
+}
+static DEVICE_ATTR_RO(error_smpro);
+
+static ssize_t error_pmpro_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+ return smpro_internal_err_read(dev, da, buf, RAS_PMPRO_ERR);
+}
+static DEVICE_ATTR_RO(error_pmpro);
+
+static ssize_t warn_smpro_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+ return smpro_internal_warn_read(dev, da, buf, RAS_SMPRO_ERR);
+}
+static DEVICE_ATTR_RO(warn_smpro);
+
+static ssize_t warn_pmpro_show(struct device *dev, struct device_attribute *da, char *buf)
+{
+ return smpro_internal_warn_read(dev, da, buf, RAS_PMPRO_ERR);
+}
+static DEVICE_ATTR_RO(warn_pmpro);
+
+#define EVENT_RO(_event, _index) \
+ static ssize_t event_##_event##_show(struct device *dev, \
+ struct device_attribute *da, \
+ char *buf) \
+ { \
+ return smpro_event_data_read(dev, da, buf, _index); \
+ } \
+ static DEVICE_ATTR_RO(event_##_event)
+
+EVENT_RO(vrd_warn_fault, VRD_WARN_FAULT_EVENT);
+EVENT_RO(vrd_hot, VRD_HOT_EVENT);
+EVENT_RO(dimm_hot, DIMM_HOT_EVENT);
+
+static struct attribute *smpro_errmon_attrs[] = {
+ &dev_attr_overflow_core_ce.attr,
+ &dev_attr_overflow_core_ue.attr,
+ &dev_attr_overflow_mem_ce.attr,
+ &dev_attr_overflow_mem_ue.attr,
+ &dev_attr_overflow_pcie_ce.attr,
+ &dev_attr_overflow_pcie_ue.attr,
+ &dev_attr_overflow_other_ce.attr,
+ &dev_attr_overflow_other_ue.attr,
+ &dev_attr_error_core_ce.attr,
+ &dev_attr_error_core_ue.attr,
+ &dev_attr_error_mem_ce.attr,
+ &dev_attr_error_mem_ue.attr,
+ &dev_attr_error_pcie_ce.attr,
+ &dev_attr_error_pcie_ue.attr,
+ &dev_attr_error_other_ce.attr,
+ &dev_attr_error_other_ue.attr,
+ &dev_attr_error_smpro.attr,
+ &dev_attr_error_pmpro.attr,
+ &dev_attr_warn_smpro.attr,
+ &dev_attr_warn_pmpro.attr,
+ &dev_attr_event_vrd_warn_fault.attr,
+ &dev_attr_event_vrd_hot.attr,
+ &dev_attr_event_dimm_hot.attr,
+ NULL
+};
+
+ATTRIBUTE_GROUPS(smpro_errmon);
+
+static int smpro_errmon_probe(struct platform_device *pdev)
+{
+ struct smpro_errmon *errmon;
+
+ errmon = devm_kzalloc(&pdev->dev, sizeof(struct smpro_errmon), GFP_KERNEL);
+ if (!errmon)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, errmon);
+
+ errmon->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+ if (!errmon->regmap)
+ return -ENODEV;
+
+ return 0;
+}
+
+static struct platform_driver smpro_errmon_driver = {
+ .probe = smpro_errmon_probe,
+ .driver = {
+ .name = "smpro-errmon",
+ .dev_groups = smpro_errmon_groups,
+ },
+};
+
+module_platform_driver(smpro_errmon_driver);
+
+MODULE_AUTHOR("Tung Nguyen <tung.nguyen@amperecomputing.com>");
+MODULE_AUTHOR("Thinh Pham <thinh.pham@amperecomputing.com>");
+MODULE_AUTHOR("Hoang Nguyen <hnguyen@amperecomputing.com>");
+MODULE_AUTHOR("Thu Nguyen <thu@os.amperecomputing.com>");
+MODULE_AUTHOR("Quan Nguyen <quan@os.amperecomputing.com>");
+MODULE_DESCRIPTION("Ampere Altra SMpro driver");
+MODULE_LICENSE("GPL");