aboutsummaryrefslogtreecommitdiff
path: root/fs/pstore/blk.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 /fs/pstore/blk.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 '')
-rw-r--r--fs/pstore/blk.c361
1 files changed, 361 insertions, 0 deletions
diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c
new file mode 100644
index 000000000..4ae0cfcd1
--- /dev/null
+++ b/fs/pstore/blk.c
@@ -0,0 +1,361 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implements pstore backend driver that write to block (or non-block) storage
+ * devices, using the pstore/zone API.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/string.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/pstore_blk.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/init_syscalls.h>
+#include <linux/mount.h>
+
+static long kmsg_size = CONFIG_PSTORE_BLK_KMSG_SIZE;
+module_param(kmsg_size, long, 0400);
+MODULE_PARM_DESC(kmsg_size, "kmsg dump record size in kbytes");
+
+static int max_reason = CONFIG_PSTORE_BLK_MAX_REASON;
+module_param(max_reason, int, 0400);
+MODULE_PARM_DESC(max_reason,
+ "maximum reason for kmsg dump (default 2: Oops and Panic)");
+
+#if IS_ENABLED(CONFIG_PSTORE_PMSG)
+static long pmsg_size = CONFIG_PSTORE_BLK_PMSG_SIZE;
+#else
+static long pmsg_size = -1;
+#endif
+module_param(pmsg_size, long, 0400);
+MODULE_PARM_DESC(pmsg_size, "pmsg size in kbytes");
+
+#if IS_ENABLED(CONFIG_PSTORE_CONSOLE)
+static long console_size = CONFIG_PSTORE_BLK_CONSOLE_SIZE;
+#else
+static long console_size = -1;
+#endif
+module_param(console_size, long, 0400);
+MODULE_PARM_DESC(console_size, "console size in kbytes");
+
+#if IS_ENABLED(CONFIG_PSTORE_FTRACE)
+static long ftrace_size = CONFIG_PSTORE_BLK_FTRACE_SIZE;
+#else
+static long ftrace_size = -1;
+#endif
+module_param(ftrace_size, long, 0400);
+MODULE_PARM_DESC(ftrace_size, "ftrace size in kbytes");
+
+static bool best_effort;
+module_param(best_effort, bool, 0400);
+MODULE_PARM_DESC(best_effort, "use best effort to write (i.e. do not require storage driver pstore support, default: off)");
+
+/*
+ * blkdev - the block device to use for pstore storage
+ * See Documentation/admin-guide/pstore-blk.rst for details.
+ */
+static char blkdev[80] = CONFIG_PSTORE_BLK_BLKDEV;
+module_param_string(blkdev, blkdev, 80, 0400);
+MODULE_PARM_DESC(blkdev, "block device for pstore storage");
+
+/*
+ * All globals must only be accessed under the pstore_blk_lock
+ * during the register/unregister functions.
+ */
+static DEFINE_MUTEX(pstore_blk_lock);
+static struct file *psblk_file;
+static struct pstore_device_info *pstore_device_info;
+
+#define check_size(name, alignsize) ({ \
+ long _##name_ = (name); \
+ _##name_ = _##name_ <= 0 ? 0 : (_##name_ * 1024); \
+ if (_##name_ & ((alignsize) - 1)) { \
+ pr_info(#name " must align to %d\n", \
+ (alignsize)); \
+ _##name_ = ALIGN(name, (alignsize)); \
+ } \
+ _##name_; \
+})
+
+#define verify_size(name, alignsize, enabled) { \
+ long _##name_; \
+ if (enabled) \
+ _##name_ = check_size(name, alignsize); \
+ else \
+ _##name_ = 0; \
+ /* Synchronize module parameters with resuls. */ \
+ name = _##name_ / 1024; \
+ dev->zone.name = _##name_; \
+}
+
+static int __register_pstore_device(struct pstore_device_info *dev)
+{
+ int ret;
+
+ lockdep_assert_held(&pstore_blk_lock);
+
+ if (!dev) {
+ pr_err("NULL device info\n");
+ return -EINVAL;
+ }
+ if (!dev->zone.total_size) {
+ pr_err("zero sized device\n");
+ return -EINVAL;
+ }
+ if (!dev->zone.read) {
+ pr_err("no read handler for device\n");
+ return -EINVAL;
+ }
+ if (!dev->zone.write) {
+ pr_err("no write handler for device\n");
+ return -EINVAL;
+ }
+
+ /* someone already registered before */
+ if (pstore_device_info)
+ return -EBUSY;
+
+ /* zero means not limit on which backends to attempt to store. */
+ if (!dev->flags)
+ dev->flags = UINT_MAX;
+
+ /* Copy in module parameters. */
+ verify_size(kmsg_size, 4096, dev->flags & PSTORE_FLAGS_DMESG);
+ verify_size(pmsg_size, 4096, dev->flags & PSTORE_FLAGS_PMSG);
+ verify_size(console_size, 4096, dev->flags & PSTORE_FLAGS_CONSOLE);
+ verify_size(ftrace_size, 4096, dev->flags & PSTORE_FLAGS_FTRACE);
+ dev->zone.max_reason = max_reason;
+
+ /* Initialize required zone ownership details. */
+ dev->zone.name = KBUILD_MODNAME;
+ dev->zone.owner = THIS_MODULE;
+
+ ret = register_pstore_zone(&dev->zone);
+ if (ret == 0)
+ pstore_device_info = dev;
+
+ return ret;
+}
+/**
+ * register_pstore_device() - register non-block device to pstore/blk
+ *
+ * @dev: non-block device information
+ *
+ * Return:
+ * * 0 - OK
+ * * Others - something error.
+ */
+int register_pstore_device(struct pstore_device_info *dev)
+{
+ int ret;
+
+ mutex_lock(&pstore_blk_lock);
+ ret = __register_pstore_device(dev);
+ mutex_unlock(&pstore_blk_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(register_pstore_device);
+
+static void __unregister_pstore_device(struct pstore_device_info *dev)
+{
+ lockdep_assert_held(&pstore_blk_lock);
+ if (pstore_device_info && pstore_device_info == dev) {
+ unregister_pstore_zone(&dev->zone);
+ pstore_device_info = NULL;
+ }
+}
+
+/**
+ * unregister_pstore_device() - unregister non-block device from pstore/blk
+ *
+ * @dev: non-block device information
+ */
+void unregister_pstore_device(struct pstore_device_info *dev)
+{
+ mutex_lock(&pstore_blk_lock);
+ __unregister_pstore_device(dev);
+ mutex_unlock(&pstore_blk_lock);
+}
+EXPORT_SYMBOL_GPL(unregister_pstore_device);
+
+static ssize_t psblk_generic_blk_read(char *buf, size_t bytes, loff_t pos)
+{
+ return kernel_read(psblk_file, buf, bytes, &pos);
+}
+
+static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes,
+ loff_t pos)
+{
+ /* Console/Ftrace backend may handle buffer until flush dirty zones */
+ if (in_interrupt() || irqs_disabled())
+ return -EBUSY;
+ return kernel_write(psblk_file, buf, bytes, &pos);
+}
+
+/*
+ * This takes its configuration only from the module parameters now.
+ */
+static int __register_pstore_blk(struct pstore_device_info *dev,
+ const char *devpath)
+{
+ int ret = -ENODEV;
+
+ lockdep_assert_held(&pstore_blk_lock);
+
+ psblk_file = filp_open(devpath, O_RDWR | O_DSYNC | O_NOATIME | O_EXCL, 0);
+ if (IS_ERR(psblk_file)) {
+ ret = PTR_ERR(psblk_file);
+ pr_err("failed to open '%s': %d!\n", devpath, ret);
+ goto err;
+ }
+
+ if (!S_ISBLK(file_inode(psblk_file)->i_mode)) {
+ pr_err("'%s' is not block device!\n", devpath);
+ goto err_fput;
+ }
+
+ dev->zone.total_size =
+ bdev_nr_bytes(I_BDEV(psblk_file->f_mapping->host));
+
+ ret = __register_pstore_device(dev);
+ if (ret)
+ goto err_fput;
+
+ return 0;
+
+err_fput:
+ fput(psblk_file);
+err:
+ psblk_file = NULL;
+
+ return ret;
+}
+
+/* get information of pstore/blk */
+int pstore_blk_get_config(struct pstore_blk_config *info)
+{
+ strncpy(info->device, blkdev, 80);
+ info->max_reason = max_reason;
+ info->kmsg_size = check_size(kmsg_size, 4096);
+ info->pmsg_size = check_size(pmsg_size, 4096);
+ info->ftrace_size = check_size(ftrace_size, 4096);
+ info->console_size = check_size(console_size, 4096);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(pstore_blk_get_config);
+
+
+#ifndef MODULE
+static const char devname[] = "/dev/pstore-blk";
+static __init const char *early_boot_devpath(const char *initial_devname)
+{
+ /*
+ * During early boot the real root file system hasn't been
+ * mounted yet, and no device nodes are present yet. Use the
+ * same scheme to find the device that we use for mounting
+ * the root file system.
+ */
+ dev_t dev = name_to_dev_t(initial_devname);
+
+ if (!dev) {
+ pr_err("failed to resolve '%s'!\n", initial_devname);
+ return initial_devname;
+ }
+
+ init_unlink(devname);
+ init_mknod(devname, S_IFBLK | 0600, new_encode_dev(dev));
+
+ return devname;
+}
+#else
+static inline const char *early_boot_devpath(const char *initial_devname)
+{
+ return initial_devname;
+}
+#endif
+
+static int __init __best_effort_init(void)
+{
+ struct pstore_device_info *best_effort_dev;
+ int ret;
+
+ /* No best-effort mode requested. */
+ if (!best_effort)
+ return 0;
+
+ /* Reject an empty blkdev. */
+ if (!blkdev[0]) {
+ pr_err("blkdev empty with best_effort=Y\n");
+ return -EINVAL;
+ }
+
+ best_effort_dev = kzalloc(sizeof(*best_effort_dev), GFP_KERNEL);
+ if (!best_effort_dev)
+ return -ENOMEM;
+
+ best_effort_dev->zone.read = psblk_generic_blk_read;
+ best_effort_dev->zone.write = psblk_generic_blk_write;
+
+ ret = __register_pstore_blk(best_effort_dev,
+ early_boot_devpath(blkdev));
+ if (ret)
+ kfree(best_effort_dev);
+ else
+ pr_info("attached %s (%lu) (no dedicated panic_write!)\n",
+ blkdev, best_effort_dev->zone.total_size);
+
+ return ret;
+}
+
+static void __exit __best_effort_exit(void)
+{
+ /*
+ * Currently, the only user of psblk_file is best_effort, so
+ * we can assume that pstore_device_info is associated with it.
+ * Once there are "real" blk devices, there will need to be a
+ * dedicated pstore_blk_info, etc.
+ */
+ if (psblk_file) {
+ struct pstore_device_info *dev = pstore_device_info;
+
+ __unregister_pstore_device(dev);
+ kfree(dev);
+ fput(psblk_file);
+ psblk_file = NULL;
+ }
+}
+
+static int __init pstore_blk_init(void)
+{
+ int ret;
+
+ mutex_lock(&pstore_blk_lock);
+ ret = __best_effort_init();
+ mutex_unlock(&pstore_blk_lock);
+
+ return ret;
+}
+late_initcall(pstore_blk_init);
+
+static void __exit pstore_blk_exit(void)
+{
+ mutex_lock(&pstore_blk_lock);
+ __best_effort_exit();
+ /* If we've been asked to unload, unregister any remaining device. */
+ __unregister_pstore_device(pstore_device_info);
+ mutex_unlock(&pstore_blk_lock);
+}
+module_exit(pstore_blk_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("WeiXiong Liao <liaoweixiong@allwinnertech.com>");
+MODULE_AUTHOR("Kees Cook <keescook@chromium.org>");
+MODULE_DESCRIPTION("pstore backend for block devices");