aboutsummaryrefslogtreecommitdiff
path: root/drivers/char/bsr.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/char/bsr.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/char/bsr.c')
-rw-r--r--drivers/char/bsr.c348
1 files changed, 348 insertions, 0 deletions
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
new file mode 100644
index 000000000..d5f943938
--- /dev/null
+++ b/drivers/char/bsr.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* IBM POWER Barrier Synchronization Register Driver
+ *
+ * Copyright IBM Corporation 2008
+ *
+ * Author: Sonny Rao <sonnyrao@us.ibm.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/cdev.h>
+#include <linux/list.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <asm/io.h>
+
+/*
+ This driver exposes a special register which can be used for fast
+ synchronization across a large SMP machine. The hardware is exposed
+ as an array of bytes where each process will write to one of the bytes to
+ indicate it has finished the current stage and this update is broadcast to
+ all processors without having to bounce a cacheline between them. In
+ POWER5 and POWER6 there is one of these registers per SMP, but it is
+ presented in two forms; first, it is given as a whole and then as a number
+ of smaller registers which alias to parts of the single whole register.
+ This can potentially allow multiple groups of processes to each have their
+ own private synchronization device.
+
+ Note that this hardware *must* be written to using *only* single byte writes.
+ It may be read using 1, 2, 4, or 8 byte loads which must be aligned since
+ this region is treated as cache-inhibited processes should also use a
+ full sync before and after writing to the BSR to ensure all stores and
+ the BSR update have made it to all chips in the system
+*/
+
+/* This is arbitrary number, up to Power6 it's been 17 or fewer */
+#define BSR_MAX_DEVS (32)
+
+struct bsr_dev {
+ u64 bsr_addr; /* Real address */
+ u64 bsr_len; /* length of mem region we can map */
+ unsigned bsr_bytes; /* size of the BSR reg itself */
+ unsigned bsr_stride; /* interval at which BSR repeats in the page */
+ unsigned bsr_type; /* maps to enum below */
+ unsigned bsr_num; /* bsr id number for its type */
+ int bsr_minor;
+
+ struct list_head bsr_list;
+
+ dev_t bsr_dev;
+ struct cdev bsr_cdev;
+ struct device *bsr_device;
+ char bsr_name[32];
+
+};
+
+static unsigned total_bsr_devs;
+static LIST_HEAD(bsr_devs);
+static struct class *bsr_class;
+static int bsr_major;
+
+enum {
+ BSR_8 = 0,
+ BSR_16 = 1,
+ BSR_64 = 2,
+ BSR_128 = 3,
+ BSR_4096 = 4,
+ BSR_UNKNOWN = 5,
+ BSR_MAX = 6,
+};
+
+static unsigned bsr_types[BSR_MAX];
+
+static ssize_t
+bsr_size_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
+ return sprintf(buf, "%u\n", bsr_dev->bsr_bytes);
+}
+static DEVICE_ATTR_RO(bsr_size);
+
+static ssize_t
+bsr_stride_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
+ return sprintf(buf, "%u\n", bsr_dev->bsr_stride);
+}
+static DEVICE_ATTR_RO(bsr_stride);
+
+static ssize_t
+bsr_length_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
+ return sprintf(buf, "%llu\n", bsr_dev->bsr_len);
+}
+static DEVICE_ATTR_RO(bsr_length);
+
+static struct attribute *bsr_dev_attrs[] = {
+ &dev_attr_bsr_size.attr,
+ &dev_attr_bsr_stride.attr,
+ &dev_attr_bsr_length.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(bsr_dev);
+
+static int bsr_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ unsigned long size = vma->vm_end - vma->vm_start;
+ struct bsr_dev *dev = filp->private_data;
+ int ret;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ /* check for the case of a small BSR device and map one 4k page for it*/
+ if (dev->bsr_len < PAGE_SIZE && size == PAGE_SIZE)
+ ret = remap_4k_pfn(vma, vma->vm_start, dev->bsr_addr >> 12,
+ vma->vm_page_prot);
+ else if (size <= dev->bsr_len)
+ ret = io_remap_pfn_range(vma, vma->vm_start,
+ dev->bsr_addr >> PAGE_SHIFT,
+ size, vma->vm_page_prot);
+ else
+ return -EINVAL;
+
+ if (ret)
+ return -EAGAIN;
+
+ return 0;
+}
+
+static int bsr_open(struct inode *inode, struct file *filp)
+{
+ struct cdev *cdev = inode->i_cdev;
+ struct bsr_dev *dev = container_of(cdev, struct bsr_dev, bsr_cdev);
+
+ filp->private_data = dev;
+ return 0;
+}
+
+static const struct file_operations bsr_fops = {
+ .owner = THIS_MODULE,
+ .mmap = bsr_mmap,
+ .open = bsr_open,
+ .llseek = noop_llseek,
+};
+
+static void bsr_cleanup_devs(void)
+{
+ struct bsr_dev *cur, *n;
+
+ list_for_each_entry_safe(cur, n, &bsr_devs, bsr_list) {
+ if (cur->bsr_device) {
+ cdev_del(&cur->bsr_cdev);
+ device_del(cur->bsr_device);
+ }
+ list_del(&cur->bsr_list);
+ kfree(cur);
+ }
+}
+
+static int bsr_add_node(struct device_node *bn)
+{
+ int bsr_stride_len, bsr_bytes_len, num_bsr_devs;
+ const u32 *bsr_stride;
+ const u32 *bsr_bytes;
+ unsigned i;
+ int ret = -ENODEV;
+
+ bsr_stride = of_get_property(bn, "ibm,lock-stride", &bsr_stride_len);
+ bsr_bytes = of_get_property(bn, "ibm,#lock-bytes", &bsr_bytes_len);
+
+ if (!bsr_stride || !bsr_bytes ||
+ (bsr_stride_len != bsr_bytes_len)) {
+ printk(KERN_ERR "bsr of-node has missing/incorrect property\n");
+ return ret;
+ }
+
+ num_bsr_devs = bsr_bytes_len / sizeof(u32);
+
+ for (i = 0 ; i < num_bsr_devs; i++) {
+ struct bsr_dev *cur = kzalloc(sizeof(struct bsr_dev),
+ GFP_KERNEL);
+ struct resource res;
+ int result;
+
+ if (!cur) {
+ printk(KERN_ERR "Unable to alloc bsr dev\n");
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ result = of_address_to_resource(bn, i, &res);
+ if (result < 0) {
+ printk(KERN_ERR "bsr of-node has invalid reg property, skipping\n");
+ kfree(cur);
+ continue;
+ }
+
+ cur->bsr_minor = i + total_bsr_devs;
+ cur->bsr_addr = res.start;
+ cur->bsr_len = resource_size(&res);
+ cur->bsr_bytes = bsr_bytes[i];
+ cur->bsr_stride = bsr_stride[i];
+ cur->bsr_dev = MKDEV(bsr_major, i + total_bsr_devs);
+
+ /* if we have a bsr_len of > 4k and less then PAGE_SIZE (64k pages) */
+ /* we can only map 4k of it, so only advertise the 4k in sysfs */
+ if (cur->bsr_len > 4096 && cur->bsr_len < PAGE_SIZE)
+ cur->bsr_len = 4096;
+
+ switch(cur->bsr_bytes) {
+ case 8:
+ cur->bsr_type = BSR_8;
+ break;
+ case 16:
+ cur->bsr_type = BSR_16;
+ break;
+ case 64:
+ cur->bsr_type = BSR_64;
+ break;
+ case 128:
+ cur->bsr_type = BSR_128;
+ break;
+ case 4096:
+ cur->bsr_type = BSR_4096;
+ break;
+ default:
+ cur->bsr_type = BSR_UNKNOWN;
+ }
+
+ cur->bsr_num = bsr_types[cur->bsr_type];
+ snprintf(cur->bsr_name, 32, "bsr%d_%d",
+ cur->bsr_bytes, cur->bsr_num);
+
+ cdev_init(&cur->bsr_cdev, &bsr_fops);
+ result = cdev_add(&cur->bsr_cdev, cur->bsr_dev, 1);
+ if (result) {
+ kfree(cur);
+ goto out_err;
+ }
+
+ cur->bsr_device = device_create(bsr_class, NULL, cur->bsr_dev,
+ cur, "%s", cur->bsr_name);
+ if (IS_ERR(cur->bsr_device)) {
+ printk(KERN_ERR "device_create failed for %s\n",
+ cur->bsr_name);
+ cdev_del(&cur->bsr_cdev);
+ kfree(cur);
+ goto out_err;
+ }
+
+ bsr_types[cur->bsr_type] = cur->bsr_num + 1;
+ list_add_tail(&cur->bsr_list, &bsr_devs);
+ }
+
+ total_bsr_devs += num_bsr_devs;
+
+ return 0;
+
+ out_err:
+
+ bsr_cleanup_devs();
+ return ret;
+}
+
+static int bsr_create_devs(struct device_node *bn)
+{
+ int ret;
+
+ while (bn) {
+ ret = bsr_add_node(bn);
+ if (ret) {
+ of_node_put(bn);
+ return ret;
+ }
+ bn = of_find_compatible_node(bn, NULL, "ibm,bsr");
+ }
+ return 0;
+}
+
+static int __init bsr_init(void)
+{
+ struct device_node *np;
+ dev_t bsr_dev;
+ int ret = -ENODEV;
+
+ np = of_find_compatible_node(NULL, NULL, "ibm,bsr");
+ if (!np)
+ goto out_err;
+
+ bsr_class = class_create(THIS_MODULE, "bsr");
+ if (IS_ERR(bsr_class)) {
+ printk(KERN_ERR "class_create() failed for bsr_class\n");
+ ret = PTR_ERR(bsr_class);
+ goto out_err_1;
+ }
+ bsr_class->dev_groups = bsr_dev_groups;
+
+ ret = alloc_chrdev_region(&bsr_dev, 0, BSR_MAX_DEVS, "bsr");
+ bsr_major = MAJOR(bsr_dev);
+ if (ret < 0) {
+ printk(KERN_ERR "alloc_chrdev_region() failed for bsr\n");
+ goto out_err_2;
+ }
+
+ ret = bsr_create_devs(np);
+ if (ret < 0) {
+ np = NULL;
+ goto out_err_3;
+ }
+
+ return 0;
+
+ out_err_3:
+ unregister_chrdev_region(bsr_dev, BSR_MAX_DEVS);
+
+ out_err_2:
+ class_destroy(bsr_class);
+
+ out_err_1:
+ of_node_put(np);
+
+ out_err:
+
+ return ret;
+}
+
+static void __exit bsr_exit(void)
+{
+
+ bsr_cleanup_devs();
+
+ if (bsr_class)
+ class_destroy(bsr_class);
+
+ if (bsr_major)
+ unregister_chrdev_region(MKDEV(bsr_major, 0), BSR_MAX_DEVS);
+}
+
+module_init(bsr_init);
+module_exit(bsr_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sonny Rao <sonnyrao@us.ibm.com>");