aboutsummaryrefslogtreecommitdiff
path: root/drivers/nvdimm/btt_devs.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/nvdimm/btt_devs.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/nvdimm/btt_devs.c')
-rw-r--r--drivers/nvdimm/btt_devs.c371
1 files changed, 371 insertions, 0 deletions
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
new file mode 100644
index 000000000..fabbb31f2
--- /dev/null
+++ b/drivers/nvdimm/btt_devs.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
+ */
+#include <linux/blkdev.h>
+#include <linux/device.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include "nd-core.h"
+#include "btt.h"
+#include "nd.h"
+
+static void nd_btt_release(struct device *dev)
+{
+ struct nd_region *nd_region = to_nd_region(dev->parent);
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+
+ dev_dbg(dev, "trace\n");
+ nd_detach_ndns(&nd_btt->dev, &nd_btt->ndns);
+ ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
+ kfree(nd_btt->uuid);
+ kfree(nd_btt);
+}
+
+struct nd_btt *to_nd_btt(struct device *dev)
+{
+ struct nd_btt *nd_btt = container_of(dev, struct nd_btt, dev);
+
+ WARN_ON(!is_nd_btt(dev));
+ return nd_btt;
+}
+EXPORT_SYMBOL(to_nd_btt);
+
+static const unsigned long btt_lbasize_supported[] = { 512, 520, 528,
+ 4096, 4104, 4160, 4224, 0 };
+
+static ssize_t sector_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+
+ return nd_size_select_show(nd_btt->lbasize, btt_lbasize_supported, buf);
+}
+
+static ssize_t sector_size_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ nvdimm_bus_lock(dev);
+ rc = nd_size_select_store(dev, buf, &nd_btt->lbasize,
+ btt_lbasize_supported);
+ dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
+ buf[len - 1] == '\n' ? "" : "\n");
+ nvdimm_bus_unlock(dev);
+ device_unlock(dev);
+
+ return rc ? rc : len;
+}
+static DEVICE_ATTR_RW(sector_size);
+
+static ssize_t uuid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+
+ if (nd_btt->uuid)
+ return sprintf(buf, "%pUb\n", nd_btt->uuid);
+ return sprintf(buf, "\n");
+}
+
+static ssize_t uuid_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ rc = nd_uuid_store(dev, &nd_btt->uuid, buf, len);
+ dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
+ buf[len - 1] == '\n' ? "" : "\n");
+ device_unlock(dev);
+
+ return rc ? rc : len;
+}
+static DEVICE_ATTR_RW(uuid);
+
+static ssize_t namespace_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ nvdimm_bus_lock(dev);
+ rc = sprintf(buf, "%s\n", nd_btt->ndns
+ ? dev_name(&nd_btt->ndns->dev) : "");
+ nvdimm_bus_unlock(dev);
+ return rc;
+}
+
+static ssize_t namespace_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ nvdimm_bus_lock(dev);
+ rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len);
+ dev_dbg(dev, "result: %zd wrote: %s%s", rc, buf,
+ buf[len - 1] == '\n' ? "" : "\n");
+ nvdimm_bus_unlock(dev);
+ device_unlock(dev);
+
+ return rc;
+}
+static DEVICE_ATTR_RW(namespace);
+
+static ssize_t size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ ssize_t rc;
+
+ device_lock(dev);
+ if (dev->driver)
+ rc = sprintf(buf, "%llu\n", nd_btt->size);
+ else {
+ /* no size to convey if the btt instance is disabled */
+ rc = -ENXIO;
+ }
+ device_unlock(dev);
+
+ return rc;
+}
+static DEVICE_ATTR_RO(size);
+
+static ssize_t log_zero_flags_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sprintf(buf, "Y\n");
+}
+static DEVICE_ATTR_RO(log_zero_flags);
+
+static struct attribute *nd_btt_attributes[] = {
+ &dev_attr_sector_size.attr,
+ &dev_attr_namespace.attr,
+ &dev_attr_uuid.attr,
+ &dev_attr_size.attr,
+ &dev_attr_log_zero_flags.attr,
+ NULL,
+};
+
+static struct attribute_group nd_btt_attribute_group = {
+ .attrs = nd_btt_attributes,
+};
+
+static const struct attribute_group *nd_btt_attribute_groups[] = {
+ &nd_btt_attribute_group,
+ &nd_device_attribute_group,
+ &nd_numa_attribute_group,
+ NULL,
+};
+
+static const struct device_type nd_btt_device_type = {
+ .name = "nd_btt",
+ .release = nd_btt_release,
+ .groups = nd_btt_attribute_groups,
+};
+
+bool is_nd_btt(struct device *dev)
+{
+ return dev->type == &nd_btt_device_type;
+}
+EXPORT_SYMBOL(is_nd_btt);
+
+static struct lock_class_key nvdimm_btt_key;
+
+static struct device *__nd_btt_create(struct nd_region *nd_region,
+ unsigned long lbasize, uuid_t *uuid,
+ struct nd_namespace_common *ndns)
+{
+ struct nd_btt *nd_btt;
+ struct device *dev;
+
+ nd_btt = kzalloc(sizeof(*nd_btt), GFP_KERNEL);
+ if (!nd_btt)
+ return NULL;
+
+ nd_btt->id = ida_simple_get(&nd_region->btt_ida, 0, 0, GFP_KERNEL);
+ if (nd_btt->id < 0)
+ goto out_nd_btt;
+
+ nd_btt->lbasize = lbasize;
+ if (uuid) {
+ uuid = kmemdup(uuid, 16, GFP_KERNEL);
+ if (!uuid)
+ goto out_put_id;
+ }
+ nd_btt->uuid = uuid;
+ dev = &nd_btt->dev;
+ dev_set_name(dev, "btt%d.%d", nd_region->id, nd_btt->id);
+ dev->parent = &nd_region->dev;
+ dev->type = &nd_btt_device_type;
+ device_initialize(&nd_btt->dev);
+ lockdep_set_class(&nd_btt->dev.mutex, &nvdimm_btt_key);
+ if (ndns && !__nd_attach_ndns(&nd_btt->dev, ndns, &nd_btt->ndns)) {
+ dev_dbg(&ndns->dev, "failed, already claimed by %s\n",
+ dev_name(ndns->claim));
+ put_device(dev);
+ return NULL;
+ }
+ return dev;
+
+out_put_id:
+ ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
+
+out_nd_btt:
+ kfree(nd_btt);
+ return NULL;
+}
+
+struct device *nd_btt_create(struct nd_region *nd_region)
+{
+ struct device *dev = __nd_btt_create(nd_region, 0, NULL, NULL);
+
+ nd_device_register(dev);
+ return dev;
+}
+
+/**
+ * nd_btt_arena_is_valid - check if the metadata layout is valid
+ * @nd_btt: device with BTT geometry and backing device info
+ * @super: pointer to the arena's info block being tested
+ *
+ * Check consistency of the btt info block with itself by validating
+ * the checksum, and with the parent namespace by verifying the
+ * parent_uuid contained in the info block with the one supplied in.
+ *
+ * Returns:
+ * false for an invalid info block, true for a valid one
+ */
+bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
+{
+ const uuid_t *ns_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);
+ uuid_t parent_uuid;
+ u64 checksum;
+
+ if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0)
+ return false;
+
+ import_uuid(&parent_uuid, super->parent_uuid);
+ if (!uuid_is_null(&parent_uuid))
+ if (!uuid_equal(&parent_uuid, ns_uuid))
+ return false;
+
+ checksum = le64_to_cpu(super->checksum);
+ super->checksum = 0;
+ if (checksum != nd_sb_checksum((struct nd_gen_sb *) super))
+ return false;
+ super->checksum = cpu_to_le64(checksum);
+
+ /* TODO: figure out action for this */
+ if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
+ dev_info(&nd_btt->dev, "Found arena with an error flag\n");
+
+ return true;
+}
+EXPORT_SYMBOL(nd_btt_arena_is_valid);
+
+int nd_btt_version(struct nd_btt *nd_btt, struct nd_namespace_common *ndns,
+ struct btt_sb *btt_sb)
+{
+ if (ndns->claim_class == NVDIMM_CCLASS_BTT2) {
+ /* Probe/setup for BTT v2.0 */
+ nd_btt->initial_offset = 0;
+ nd_btt->version_major = 2;
+ nd_btt->version_minor = 0;
+ if (nvdimm_read_bytes(ndns, 0, btt_sb, sizeof(*btt_sb), 0))
+ return -ENXIO;
+ if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
+ return -ENODEV;
+ if ((le16_to_cpu(btt_sb->version_major) != 2) ||
+ (le16_to_cpu(btt_sb->version_minor) != 0))
+ return -ENODEV;
+ } else {
+ /*
+ * Probe/setup for BTT v1.1 (NVDIMM_CCLASS_NONE or
+ * NVDIMM_CCLASS_BTT)
+ */
+ nd_btt->initial_offset = SZ_4K;
+ nd_btt->version_major = 1;
+ nd_btt->version_minor = 1;
+ if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb), 0))
+ return -ENXIO;
+ if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
+ return -ENODEV;
+ if ((le16_to_cpu(btt_sb->version_major) != 1) ||
+ (le16_to_cpu(btt_sb->version_minor) != 1))
+ return -ENODEV;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(nd_btt_version);
+
+static int __nd_btt_probe(struct nd_btt *nd_btt,
+ struct nd_namespace_common *ndns, struct btt_sb *btt_sb)
+{
+ int rc;
+
+ if (!btt_sb || !ndns || !nd_btt)
+ return -ENODEV;
+
+ if (nvdimm_namespace_capacity(ndns) < SZ_16M)
+ return -ENXIO;
+
+ rc = nd_btt_version(nd_btt, ndns, btt_sb);
+ if (rc < 0)
+ return rc;
+
+ nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize);
+ nd_btt->uuid = kmemdup(&btt_sb->uuid, sizeof(uuid_t), GFP_KERNEL);
+ if (!nd_btt->uuid)
+ return -ENOMEM;
+
+ nd_device_register(&nd_btt->dev);
+
+ return 0;
+}
+
+int nd_btt_probe(struct device *dev, struct nd_namespace_common *ndns)
+{
+ int rc;
+ struct device *btt_dev;
+ struct btt_sb *btt_sb;
+ struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+
+ if (ndns->force_raw)
+ return -ENODEV;
+
+ switch (ndns->claim_class) {
+ case NVDIMM_CCLASS_NONE:
+ case NVDIMM_CCLASS_BTT:
+ case NVDIMM_CCLASS_BTT2:
+ break;
+ default:
+ return -ENODEV;
+ }
+
+ nvdimm_bus_lock(&ndns->dev);
+ btt_dev = __nd_btt_create(nd_region, 0, NULL, ndns);
+ nvdimm_bus_unlock(&ndns->dev);
+ if (!btt_dev)
+ return -ENOMEM;
+ btt_sb = devm_kzalloc(dev, sizeof(*btt_sb), GFP_KERNEL);
+ rc = __nd_btt_probe(to_nd_btt(btt_dev), ndns, btt_sb);
+ dev_dbg(dev, "btt: %s\n", rc == 0 ? dev_name(btt_dev) : "<none>");
+ if (rc < 0) {
+ struct nd_btt *nd_btt = to_nd_btt(btt_dev);
+
+ nd_detach_ndns(btt_dev, &nd_btt->ndns);
+ put_device(btt_dev);
+ }
+
+ return rc;
+}
+EXPORT_SYMBOL(nd_btt_probe);