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().
  ...

1 files changed, 548 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
new file mode 100644
index 000000000..a973905af
--- /dev/null
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -0,0 +1,548 @@
+/*
+ * Copyright (c) 2012 Intel Corporation. All rights reserved.
+ * Copyright (c) 2006 - 2012 QLogic Corporation. All rights reserved.
+ * Copyright (c) 2006 PathScale, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/fs.h>
+#include <linux/fs_context.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+
+#include "qib.h"
+
+#define QIBFS_MAGIC 0x726a77
+
+static struct super_block *qib_super;
+
+#define private2dd(file) (file_inode(file)->i_private)
+
+static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
+		       umode_t mode, const struct file_operations *fops,
+		       void *data)
+{
+	int error;
+	struct inode *inode = new_inode(dir->i_sb);
+
+	if (!inode) {
+		error = -EPERM;
+		goto bail;
+	}
+
+	inode->i_ino = get_next_ino();
+	inode->i_mode = mode;
+	inode->i_uid = GLOBAL_ROOT_UID;
+	inode->i_gid = GLOBAL_ROOT_GID;
+	inode->i_blocks = 0;
+	inode->i_atime = current_time(inode);
+	inode->i_mtime = inode->i_atime;
+	inode->i_ctime = inode->i_atime;
+	inode->i_private = data;
+	if (S_ISDIR(mode)) {
+		inode->i_op = &simple_dir_inode_operations;
+		inc_nlink(inode);
+		inc_nlink(dir);
+	}
+
+	inode->i_fop = fops;
+
+	d_instantiate(dentry, inode);
+	error = 0;
+
+bail:
+	return error;
+}
+
+static int create_file(const char *name, umode_t mode,
+		       struct dentry *parent, struct dentry **dentry,
+		       const struct file_operations *fops, void *data)
+{
+	int error;
+
+	inode_lock(d_inode(parent));
+	*dentry = lookup_one_len(name, parent, strlen(name));
+	if (!IS_ERR(*dentry))
+		error = qibfs_mknod(d_inode(parent), *dentry,
+				    mode, fops, data);
+	else
+		error = PTR_ERR(*dentry);
+	inode_unlock(d_inode(parent));
+
+	return error;
+}
+
+static ssize_t driver_stats_read(struct file *file, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	qib_stats.sps_ints = qib_sps_ints();
+	return simple_read_from_buffer(buf, count, ppos, &qib_stats,
+				       sizeof(qib_stats));
+}
+
+/*
+ * driver stats field names, one line per stat, single string.  Used by
+ * programs like ipathstats to print the stats in a way which works for
+ * different versions of drivers, without changing program source.
+ * if qlogic_ib_stats changes, this needs to change.  Names need to be
+ * 12 chars or less (w/o newline), for proper display by ipathstats utility.
+ */
+static const char qib_statnames[] =
+	"KernIntr\n"
+	"ErrorIntr\n"
+	"Tx_Errs\n"
+	"Rcv_Errs\n"
+	"H/W_Errs\n"
+	"NoPIOBufs\n"
+	"CtxtsOpen\n"
+	"RcvLen_Errs\n"
+	"EgrBufFull\n"
+	"EgrHdrFull\n"
+	;
+
+static ssize_t driver_names_read(struct file *file, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, count, ppos, qib_statnames,
+		sizeof(qib_statnames) - 1); /* no null */
+}
+
+static const struct file_operations driver_ops[] = {
+	{ .read = driver_stats_read, .llseek = generic_file_llseek, },
+	{ .read = driver_names_read, .llseek = generic_file_llseek, },
+};
+
+/* read the per-device counters */
+static ssize_t dev_counters_read(struct file *file, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	u64 *counters;
+	size_t avail;
+	struct qib_devdata *dd = private2dd(file);
+
+	avail = dd->f_read_cntrs(dd, *ppos, NULL, &counters);
+	return simple_read_from_buffer(buf, count, ppos, counters, avail);
+}
+
+/* read the per-device counters */
+static ssize_t dev_names_read(struct file *file, char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	char *names;
+	size_t avail;
+	struct qib_devdata *dd = private2dd(file);
+
+	avail = dd->f_read_cntrs(dd, *ppos, &names, NULL);
+	return simple_read_from_buffer(buf, count, ppos, names, avail);
+}
+
+static const struct file_operations cntr_ops[] = {
+	{ .read = dev_counters_read, .llseek = generic_file_llseek, },
+	{ .read = dev_names_read, .llseek = generic_file_llseek, },
+};
+
+/*
+ * Could use file_inode(file)->i_ino to figure out which file,
+ * instead of separate routine for each, but for now, this works...
+ */
+
+/* read the per-port names (same for each port) */
+static ssize_t portnames_read(struct file *file, char __user *buf,
+			      size_t count, loff_t *ppos)
+{
+	char *names;
+	size_t avail;
+	struct qib_devdata *dd = private2dd(file);
+
+	avail = dd->f_read_portcntrs(dd, *ppos, 0, &names, NULL);
+	return simple_read_from_buffer(buf, count, ppos, names, avail);
+}
+
+/* read the per-port counters for port 1 (pidx 0) */
+static ssize_t portcntrs_1_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	u64 *counters;
+	size_t avail;
+	struct qib_devdata *dd = private2dd(file);
+
+	avail = dd->f_read_portcntrs(dd, *ppos, 0, NULL, &counters);
+	return simple_read_from_buffer(buf, count, ppos, counters, avail);
+}
+
+/* read the per-port counters for port 2 (pidx 1) */
+static ssize_t portcntrs_2_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	u64 *counters;
+	size_t avail;
+	struct qib_devdata *dd = private2dd(file);
+
+	avail = dd->f_read_portcntrs(dd, *ppos, 1, NULL, &counters);
+	return simple_read_from_buffer(buf, count, ppos, counters, avail);
+}
+
+static const struct file_operations portcntr_ops[] = {
+	{ .read = portnames_read, .llseek = generic_file_llseek, },
+	{ .read = portcntrs_1_read, .llseek = generic_file_llseek, },
+	{ .read = portcntrs_2_read, .llseek = generic_file_llseek, },
+};
+
+/*
+ * read the per-port QSFP data for port 1 (pidx 0)
+ */
+static ssize_t qsfp_1_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct qib_devdata *dd = private2dd(file);
+	char *tmp;
+	int ret;
+
+	tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	ret = qib_qsfp_dump(dd->pport, tmp, PAGE_SIZE);
+	if (ret > 0)
+		ret = simple_read_from_buffer(buf, count, ppos, tmp, ret);
+	kfree(tmp);
+	return ret;
+}
+
+/*
+ * read the per-port QSFP data for port 2 (pidx 1)
+ */
+static ssize_t qsfp_2_read(struct file *file, char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct qib_devdata *dd = private2dd(file);
+	char *tmp;
+	int ret;
+
+	if (dd->num_pports < 2)
+		return -ENODEV;
+
+	tmp = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!tmp)
+		return -ENOMEM;
+
+	ret = qib_qsfp_dump(dd->pport + 1, tmp, PAGE_SIZE);
+	if (ret > 0)
+		ret = simple_read_from_buffer(buf, count, ppos, tmp, ret);
+	kfree(tmp);
+	return ret;
+}
+
+static const struct file_operations qsfp_ops[] = {
+	{ .read = qsfp_1_read, .llseek = generic_file_llseek, },
+	{ .read = qsfp_2_read, .llseek = generic_file_llseek, },
+};
+
+static ssize_t flash_read(struct file *file, char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	struct qib_devdata *dd;
+	ssize_t ret;
+	loff_t pos;
+	char *tmp;
+
+	pos = *ppos;
+
+	if (pos < 0) {
+		ret = -EINVAL;
+		goto bail;
+	}
+
+	if (pos >= sizeof(struct qib_flash)) {
+		ret = 0;
+		goto bail;
+	}
+
+	if (count > sizeof(struct qib_flash) - pos)
+		count = sizeof(struct qib_flash) - pos;
+
+	tmp = kmalloc(count, GFP_KERNEL);
+	if (!tmp) {
+		ret = -ENOMEM;
+		goto bail;
+	}
+
+	dd = private2dd(file);
+	if (qib_eeprom_read(dd, pos, tmp, count)) {
+		qib_dev_err(dd, "failed to read from flash\n");
+		ret = -ENXIO;
+		goto bail_tmp;
+	}
+
+	if (copy_to_user(buf, tmp, count)) {
+		ret = -EFAULT;
+		goto bail_tmp;
+	}
+
+	*ppos = pos + count;
+	ret = count;
+
+bail_tmp:
+	kfree(tmp);
+
+bail:
+	return ret;
+}
+
+static ssize_t flash_write(struct file *file, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct qib_devdata *dd;
+	ssize_t ret;
+	loff_t pos;
+	char *tmp;
+
+	pos = *ppos;
+
+	if (pos != 0 || count != sizeof(struct qib_flash))
+		return -EINVAL;
+
+	tmp = memdup_user(buf, count);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
+
+	dd = private2dd(file);
+	if (qib_eeprom_write(dd, pos, tmp, count)) {
+		ret = -ENXIO;
+		qib_dev_err(dd, "failed to write to flash\n");
+		goto bail_tmp;
+	}
+
+	*ppos = pos + count;
+	ret = count;
+
+bail_tmp:
+	kfree(tmp);
+	return ret;
+}
+
+static const struct file_operations flash_ops = {
+	.read = flash_read,
+	.write = flash_write,
+	.llseek = default_llseek,
+};
+
+static int add_cntr_files(struct super_block *sb, struct qib_devdata *dd)
+{
+	struct dentry *dir, *tmp;
+	char unit[10];
+	int ret, i;
+
+	/* create the per-unit directory */
+	snprintf(unit, sizeof(unit), "%u", dd->unit);
+	ret = create_file(unit, S_IFDIR|S_IRUGO|S_IXUGO, sb->s_root, &dir,
+			  &simple_dir_operations, dd);
+	if (ret) {
+		pr_err("create_file(%s) failed: %d\n", unit, ret);
+		goto bail;
+	}
+
+	/* create the files in the new directory */
+	ret = create_file("counters", S_IFREG|S_IRUGO, dir, &tmp,
+			  &cntr_ops[0], dd);
+	if (ret) {
+		pr_err("create_file(%s/counters) failed: %d\n",
+		       unit, ret);
+		goto bail;
+	}
+	ret = create_file("counter_names", S_IFREG|S_IRUGO, dir, &tmp,
+			  &cntr_ops[1], dd);
+	if (ret) {
+		pr_err("create_file(%s/counter_names) failed: %d\n",
+		       unit, ret);
+		goto bail;
+	}
+	ret = create_file("portcounter_names", S_IFREG|S_IRUGO, dir, &tmp,
+			  &portcntr_ops[0], dd);
+	if (ret) {
+		pr_err("create_file(%s/%s) failed: %d\n",
+		       unit, "portcounter_names", ret);
+		goto bail;
+	}
+	for (i = 1; i <= dd->num_pports; i++) {
+		char fname[24];
+
+		sprintf(fname, "port%dcounters", i);
+		/* create the files in the new directory */
+		ret = create_file(fname, S_IFREG|S_IRUGO, dir, &tmp,
+				  &portcntr_ops[i], dd);
+		if (ret) {
+			pr_err("create_file(%s/%s) failed: %d\n",
+				unit, fname, ret);
+			goto bail;
+		}
+		if (!(dd->flags & QIB_HAS_QSFP))
+			continue;
+		sprintf(fname, "qsfp%d", i);
+		ret = create_file(fname, S_IFREG|S_IRUGO, dir, &tmp,
+				  &qsfp_ops[i - 1], dd);
+		if (ret) {
+			pr_err("create_file(%s/%s) failed: %d\n",
+				unit, fname, ret);
+			goto bail;
+		}
+	}
+
+	ret = create_file("flash", S_IFREG|S_IWUSR|S_IRUGO, dir, &tmp,
+			  &flash_ops, dd);
+	if (ret)
+		pr_err("create_file(%s/flash) failed: %d\n",
+			unit, ret);
+bail:
+	return ret;
+}
+
+static int remove_device_files(struct super_block *sb,
+			       struct qib_devdata *dd)
+{
+	struct dentry *dir;
+	char unit[10];
+
+	snprintf(unit, sizeof(unit), "%u", dd->unit);
+	dir = lookup_one_len_unlocked(unit, sb->s_root, strlen(unit));
+
+	if (IS_ERR(dir)) {
+		pr_err("Lookup of %s failed\n", unit);
+		return PTR_ERR(dir);
+	}
+	simple_recursive_removal(dir, NULL);
+	return 0;
+}
+
+/*
+ * This fills everything in when the fs is mounted, to handle umount/mount
+ * after device init.  The direct add_cntr_files() call handles adding
+ * them from the init code, when the fs is already mounted.
+ */
+static int qibfs_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct qib_devdata *dd;
+	unsigned long index;
+	int ret;
+
+	static const struct tree_descr files[] = {
+		[2] = {"driver_stats", &driver_ops[0], S_IRUGO},
+		[3] = {"driver_stats_names", &driver_ops[1], S_IRUGO},
+		{""},
+	};
+
+	ret = simple_fill_super(sb, QIBFS_MAGIC, files);
+	if (ret) {
+		pr_err("simple_fill_super failed: %d\n", ret);
+		goto bail;
+	}
+
+	xa_for_each(&qib_dev_table, index, dd) {
+		ret = add_cntr_files(sb, dd);
+		if (ret)
+			goto bail;
+	}
+
+bail:
+	return ret;
+}
+
+static int qibfs_get_tree(struct fs_context *fc)
+{
+	int ret = get_tree_single(fc, qibfs_fill_super);
+	if (ret == 0)
+		qib_super = fc->root->d_sb;
+	return ret;
+}
+
+static const struct fs_context_operations qibfs_context_ops = {
+	.get_tree	= qibfs_get_tree,
+};
+
+static int qibfs_init_fs_context(struct fs_context *fc)
+{
+	fc->ops = &qibfs_context_ops;
+	return 0;
+}
+
+static void qibfs_kill_super(struct super_block *s)
+{
+	kill_litter_super(s);
+	qib_super = NULL;
+}
+
+int qibfs_add(struct qib_devdata *dd)
+{
+	int ret;
+
+	/*
+	 * On first unit initialized, qib_super will not yet exist
+	 * because nobody has yet tried to mount the filesystem, so
+	 * we can't consider that to be an error; if an error occurs
+	 * during the mount, that will get a complaint, so this is OK.
+	 * add_cntr_files() for all units is done at mount from
+	 * qibfs_fill_super(), so one way or another, everything works.
+	 */
+	if (qib_super == NULL)
+		ret = 0;
+	else
+		ret = add_cntr_files(qib_super, dd);
+	return ret;
+}
+
+int qibfs_remove(struct qib_devdata *dd)
+{
+	int ret = 0;
+
+	if (qib_super)
+		ret = remove_device_files(qib_super, dd);
+
+	return ret;
+}
+
+static struct file_system_type qibfs_fs_type = {
+	.owner =        THIS_MODULE,
+	.name =         "ipathfs",
+	.init_fs_context = qibfs_init_fs_context,
+	.kill_sb =      qibfs_kill_super,
+};
+MODULE_ALIAS_FS("ipathfs");
+
+int __init qib_init_qibfs(void)
+{
+	return register_filesystem(&qibfs_fs_type);
+}
+
+int __exit qib_exit_qibfs(void)
+{
+	return unregister_filesystem(&qibfs_fs_type);
+}