aboutsummaryrefslogtreecommitdiff
path: root/drivers/pci/pcie/dpc.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/pci/pcie/dpc.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/pci/pcie/dpc.c')
-rw-r--r--drivers/pci/pcie/dpc.c409
1 files changed, 409 insertions, 0 deletions
diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
new file mode 100644
index 000000000..f5ffea17c
--- /dev/null
+++ b/drivers/pci/pcie/dpc.c
@@ -0,0 +1,409 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Express Downstream Port Containment services driver
+ * Author: Keith Busch <keith.busch@intel.com>
+ *
+ * Copyright (C) 2016 Intel Corp.
+ */
+
+#define dev_fmt(fmt) "DPC: " fmt
+
+#include <linux/aer.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+
+#include "portdrv.h"
+#include "../pci.h"
+
+static const char * const rp_pio_error_string[] = {
+ "Configuration Request received UR Completion", /* Bit Position 0 */
+ "Configuration Request received CA Completion", /* Bit Position 1 */
+ "Configuration Request Completion Timeout", /* Bit Position 2 */
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ "I/O Request received UR Completion", /* Bit Position 8 */
+ "I/O Request received CA Completion", /* Bit Position 9 */
+ "I/O Request Completion Timeout", /* Bit Position 10 */
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ NULL,
+ "Memory Request received UR Completion", /* Bit Position 16 */
+ "Memory Request received CA Completion", /* Bit Position 17 */
+ "Memory Request Completion Timeout", /* Bit Position 18 */
+};
+
+void pci_save_dpc_state(struct pci_dev *dev)
+{
+ struct pci_cap_saved_state *save_state;
+ u16 *cap;
+
+ if (!pci_is_pcie(dev))
+ return;
+
+ save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_DPC);
+ if (!save_state)
+ return;
+
+ cap = (u16 *)&save_state->cap.data[0];
+ pci_read_config_word(dev, dev->dpc_cap + PCI_EXP_DPC_CTL, cap);
+}
+
+void pci_restore_dpc_state(struct pci_dev *dev)
+{
+ struct pci_cap_saved_state *save_state;
+ u16 *cap;
+
+ if (!pci_is_pcie(dev))
+ return;
+
+ save_state = pci_find_saved_ext_cap(dev, PCI_EXT_CAP_ID_DPC);
+ if (!save_state)
+ return;
+
+ cap = (u16 *)&save_state->cap.data[0];
+ pci_write_config_word(dev, dev->dpc_cap + PCI_EXP_DPC_CTL, *cap);
+}
+
+static DECLARE_WAIT_QUEUE_HEAD(dpc_completed_waitqueue);
+
+#ifdef CONFIG_HOTPLUG_PCI_PCIE
+static bool dpc_completed(struct pci_dev *pdev)
+{
+ u16 status;
+
+ pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_STATUS, &status);
+ if ((!PCI_POSSIBLE_ERROR(status)) && (status & PCI_EXP_DPC_STATUS_TRIGGER))
+ return false;
+
+ if (test_bit(PCI_DPC_RECOVERING, &pdev->priv_flags))
+ return false;
+
+ return true;
+}
+
+/**
+ * pci_dpc_recovered - whether DPC triggered and has recovered successfully
+ * @pdev: PCI device
+ *
+ * Return true if DPC was triggered for @pdev and has recovered successfully.
+ * Wait for recovery if it hasn't completed yet. Called from the PCIe hotplug
+ * driver to recognize and ignore Link Down/Up events caused by DPC.
+ */
+bool pci_dpc_recovered(struct pci_dev *pdev)
+{
+ struct pci_host_bridge *host;
+
+ if (!pdev->dpc_cap)
+ return false;
+
+ /*
+ * Synchronization between hotplug and DPC is not supported
+ * if DPC is owned by firmware and EDR is not enabled.
+ */
+ host = pci_find_host_bridge(pdev->bus);
+ if (!host->native_dpc && !IS_ENABLED(CONFIG_PCIE_EDR))
+ return false;
+
+ /*
+ * Need a timeout in case DPC never completes due to failure of
+ * dpc_wait_rp_inactive(). The spec doesn't mandate a time limit,
+ * but reports indicate that DPC completes within 4 seconds.
+ */
+ wait_event_timeout(dpc_completed_waitqueue, dpc_completed(pdev),
+ msecs_to_jiffies(4000));
+
+ return test_and_clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags);
+}
+#endif /* CONFIG_HOTPLUG_PCI_PCIE */
+
+static int dpc_wait_rp_inactive(struct pci_dev *pdev)
+{
+ unsigned long timeout = jiffies + HZ;
+ u16 cap = pdev->dpc_cap, status;
+
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
+ while (status & PCI_EXP_DPC_RP_BUSY &&
+ !time_after(jiffies, timeout)) {
+ msleep(10);
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
+ }
+ if (status & PCI_EXP_DPC_RP_BUSY) {
+ pci_warn(pdev, "root port still busy\n");
+ return -EBUSY;
+ }
+ return 0;
+}
+
+pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
+{
+ pci_ers_result_t ret;
+ u16 cap;
+
+ set_bit(PCI_DPC_RECOVERING, &pdev->priv_flags);
+
+ /*
+ * DPC disables the Link automatically in hardware, so it has
+ * already been reset by the time we get here.
+ */
+ cap = pdev->dpc_cap;
+
+ /*
+ * Wait until the Link is inactive, then clear DPC Trigger Status
+ * to allow the Port to leave DPC.
+ */
+ if (!pcie_wait_for_link(pdev, false))
+ pci_info(pdev, "Data Link Layer Link Active not cleared in 1000 msec\n");
+
+ if (pdev->dpc_rp_extensions && dpc_wait_rp_inactive(pdev)) {
+ clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags);
+ ret = PCI_ERS_RESULT_DISCONNECT;
+ goto out;
+ }
+
+ pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
+ PCI_EXP_DPC_STATUS_TRIGGER);
+
+ if (!pcie_wait_for_link(pdev, true)) {
+ pci_info(pdev, "Data Link Layer Link Active not set in 1000 msec\n");
+ clear_bit(PCI_DPC_RECOVERED, &pdev->priv_flags);
+ ret = PCI_ERS_RESULT_DISCONNECT;
+ } else {
+ set_bit(PCI_DPC_RECOVERED, &pdev->priv_flags);
+ ret = PCI_ERS_RESULT_RECOVERED;
+ }
+out:
+ clear_bit(PCI_DPC_RECOVERING, &pdev->priv_flags);
+ wake_up_all(&dpc_completed_waitqueue);
+ return ret;
+}
+
+static void dpc_process_rp_pio_error(struct pci_dev *pdev)
+{
+ u16 cap = pdev->dpc_cap, dpc_status, first_error;
+ u32 status, mask, sev, syserr, exc, dw0, dw1, dw2, dw3, log, prefix;
+ int i;
+
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, &status);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_MASK, &mask);
+ pci_err(pdev, "rp_pio_status: %#010x, rp_pio_mask: %#010x\n",
+ status, mask);
+
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SEVERITY, &sev);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SYSERROR, &syserr);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_EXCEPTION, &exc);
+ pci_err(pdev, "RP PIO severity=%#010x, syserror=%#010x, exception=%#010x\n",
+ sev, syserr, exc);
+
+ /* Get First Error Pointer */
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status);
+ first_error = (dpc_status & 0x1f00) >> 8;
+
+ for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) {
+ if ((status & ~mask) & (1 << i))
+ pci_err(pdev, "[%2d] %s%s\n", i, rp_pio_error_string[i],
+ first_error == i ? " (First)" : "");
+ }
+
+ if (pdev->dpc_rp_log_size < 4)
+ goto clear_status;
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG,
+ &dw0);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 4,
+ &dw1);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 8,
+ &dw2);
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 12,
+ &dw3);
+ pci_err(pdev, "TLP Header: %#010x %#010x %#010x %#010x\n",
+ dw0, dw1, dw2, dw3);
+
+ if (pdev->dpc_rp_log_size < 5)
+ goto clear_status;
+ pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log);
+ pci_err(pdev, "RP PIO ImpSpec Log %#010x\n", log);
+
+ for (i = 0; i < pdev->dpc_rp_log_size - 5; i++) {
+ pci_read_config_dword(pdev,
+ cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix);
+ pci_err(pdev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix);
+ }
+ clear_status:
+ pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
+}
+
+static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
+ struct aer_err_info *info)
+{
+ int pos = dev->aer_cap;
+ u32 status, mask, sev;
+
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
+ status &= ~mask;
+ if (!status)
+ return 0;
+
+ pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+ status &= sev;
+ if (status)
+ info->severity = AER_FATAL;
+ else
+ info->severity = AER_NONFATAL;
+
+ return 1;
+}
+
+void dpc_process_error(struct pci_dev *pdev)
+{
+ u16 cap = pdev->dpc_cap, status, source, reason, ext_reason;
+ struct aer_err_info info;
+
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
+
+ pci_info(pdev, "containment event, status:%#06x source:%#06x\n",
+ status, source);
+
+ reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1;
+ ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5;
+ pci_warn(pdev, "%s detected\n",
+ (reason == 0) ? "unmasked uncorrectable error" :
+ (reason == 1) ? "ERR_NONFATAL" :
+ (reason == 2) ? "ERR_FATAL" :
+ (ext_reason == 0) ? "RP PIO error" :
+ (ext_reason == 1) ? "software trigger" :
+ "reserved error");
+
+ /* show RP PIO error detail information */
+ if (pdev->dpc_rp_extensions && reason == 3 && ext_reason == 0)
+ dpc_process_rp_pio_error(pdev);
+ else if (reason == 0 &&
+ dpc_get_aer_uncorrect_severity(pdev, &info) &&
+ aer_get_device_error_info(pdev, &info)) {
+ aer_print_error(pdev, &info);
+ pci_aer_clear_nonfatal_status(pdev);
+ pci_aer_clear_fatal_status(pdev);
+ }
+}
+
+static irqreturn_t dpc_handler(int irq, void *context)
+{
+ struct pci_dev *pdev = context;
+
+ dpc_process_error(pdev);
+
+ /* We configure DPC so it only triggers on ERR_FATAL */
+ pcie_do_recovery(pdev, pci_channel_io_frozen, dpc_reset_link);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t dpc_irq(int irq, void *context)
+{
+ struct pci_dev *pdev = context;
+ u16 cap = pdev->dpc_cap, status;
+
+ pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
+
+ if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || PCI_POSSIBLE_ERROR(status))
+ return IRQ_NONE;
+
+ pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
+ PCI_EXP_DPC_STATUS_INTERRUPT);
+ if (status & PCI_EXP_DPC_STATUS_TRIGGER)
+ return IRQ_WAKE_THREAD;
+ return IRQ_HANDLED;
+}
+
+void pci_dpc_init(struct pci_dev *pdev)
+{
+ u16 cap;
+
+ pdev->dpc_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
+ if (!pdev->dpc_cap)
+ return;
+
+ pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap);
+ if (!(cap & PCI_EXP_DPC_CAP_RP_EXT))
+ return;
+
+ pdev->dpc_rp_extensions = true;
+
+ /* Quirks may set dpc_rp_log_size if device or firmware is buggy */
+ if (!pdev->dpc_rp_log_size) {
+ pdev->dpc_rp_log_size =
+ (cap & PCI_EXP_DPC_RP_PIO_LOG_SIZE) >> 8;
+ if (pdev->dpc_rp_log_size < 4 || pdev->dpc_rp_log_size > 9) {
+ pci_err(pdev, "RP PIO log size %u is invalid\n",
+ pdev->dpc_rp_log_size);
+ pdev->dpc_rp_log_size = 0;
+ }
+ }
+}
+
+#define FLAG(x, y) (((x) & (y)) ? '+' : '-')
+static int dpc_probe(struct pcie_device *dev)
+{
+ struct pci_dev *pdev = dev->port;
+ struct device *device = &dev->device;
+ int status;
+ u16 ctl, cap;
+
+ if (!pcie_aer_is_native(pdev) && !pcie_ports_dpc_native)
+ return -ENOTSUPP;
+
+ status = devm_request_threaded_irq(device, dev->irq, dpc_irq,
+ dpc_handler, IRQF_SHARED,
+ "pcie-dpc", pdev);
+ if (status) {
+ pci_warn(pdev, "request IRQ%d failed: %d\n", dev->irq,
+ status);
+ return status;
+ }
+
+ pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CAP, &cap);
+ pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl);
+
+ ctl = (ctl & 0xfff4) | PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN;
+ pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl);
+ pci_info(pdev, "enabled with IRQ %d\n", dev->irq);
+
+ pci_info(pdev, "error containment capabilities: Int Msg #%d, RPExt%c PoisonedTLP%c SwTrigger%c RP PIO Log %d, DL_ActiveErr%c\n",
+ cap & PCI_EXP_DPC_IRQ, FLAG(cap, PCI_EXP_DPC_CAP_RP_EXT),
+ FLAG(cap, PCI_EXP_DPC_CAP_POISONED_TLP),
+ FLAG(cap, PCI_EXP_DPC_CAP_SW_TRIGGER), pdev->dpc_rp_log_size,
+ FLAG(cap, PCI_EXP_DPC_CAP_DL_ACTIVE));
+
+ pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_DPC, sizeof(u16));
+ return status;
+}
+
+static void dpc_remove(struct pcie_device *dev)
+{
+ struct pci_dev *pdev = dev->port;
+ u16 ctl;
+
+ pci_read_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, &ctl);
+ ctl &= ~(PCI_EXP_DPC_CTL_EN_FATAL | PCI_EXP_DPC_CTL_INT_EN);
+ pci_write_config_word(pdev, pdev->dpc_cap + PCI_EXP_DPC_CTL, ctl);
+}
+
+static struct pcie_port_service_driver dpcdriver = {
+ .name = "dpc",
+ .port_type = PCIE_ANY_PORT,
+ .service = PCIE_PORT_SERVICE_DPC,
+ .probe = dpc_probe,
+ .remove = dpc_remove,
+};
+
+int __init pcie_dpc_init(void)
+{
+ return pcie_port_service_register(&dpcdriver);
+}