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, 897 insertions, 0 deletions

diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
new file mode 100644
index 000000000..cf10fa667
--- /dev/null
+++ b/drivers/md/dm-log.c
@@ -0,0 +1,897 @@
+/*
+ * Copyright (C) 2003 Sistina Software
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the LGPL.
+ */
+
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/dm-io.h>
+#include <linux/dm-dirty-log.h>
+
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "dirty region log"
+
+static LIST_HEAD(_log_types);
+static DEFINE_SPINLOCK(_lock);
+
+static struct dm_dirty_log_type *__find_dirty_log_type(const char *name)
+{
+	struct dm_dirty_log_type *log_type;
+
+	list_for_each_entry(log_type, &_log_types, list)
+		if (!strcmp(name, log_type->name))
+			return log_type;
+
+	return NULL;
+}
+
+static struct dm_dirty_log_type *_get_dirty_log_type(const char *name)
+{
+	struct dm_dirty_log_type *log_type;
+
+	spin_lock(&_lock);
+
+	log_type = __find_dirty_log_type(name);
+	if (log_type && !try_module_get(log_type->module))
+		log_type = NULL;
+
+	spin_unlock(&_lock);
+
+	return log_type;
+}
+
+/*
+ * get_type
+ * @type_name
+ *
+ * Attempt to retrieve the dm_dirty_log_type by name.  If not already
+ * available, attempt to load the appropriate module.
+ *
+ * Log modules are named "dm-log-" followed by the 'type_name'.
+ * Modules may contain multiple types.
+ * This function will first try the module "dm-log-<type_name>",
+ * then truncate 'type_name' on the last '-' and try again.
+ *
+ * For example, if type_name was "clustered-disk", it would search
+ * 'dm-log-clustered-disk' then 'dm-log-clustered'.
+ *
+ * Returns: dirty_log_type* on success, NULL on failure
+ */
+static struct dm_dirty_log_type *get_type(const char *type_name)
+{
+	char *p, *type_name_dup;
+	struct dm_dirty_log_type *log_type;
+
+	if (!type_name)
+		return NULL;
+
+	log_type = _get_dirty_log_type(type_name);
+	if (log_type)
+		return log_type;
+
+	type_name_dup = kstrdup(type_name, GFP_KERNEL);
+	if (!type_name_dup) {
+		DMWARN("No memory left to attempt log module load for \"%s\"",
+		       type_name);
+		return NULL;
+	}
+
+	while (request_module("dm-log-%s", type_name_dup) ||
+	       !(log_type = _get_dirty_log_type(type_name))) {
+		p = strrchr(type_name_dup, '-');
+		if (!p)
+			break;
+		p[0] = '\0';
+	}
+
+	if (!log_type)
+		DMWARN("Module for logging type \"%s\" not found.", type_name);
+
+	kfree(type_name_dup);
+
+	return log_type;
+}
+
+static void put_type(struct dm_dirty_log_type *type)
+{
+	if (!type)
+		return;
+
+	spin_lock(&_lock);
+	if (!__find_dirty_log_type(type->name))
+		goto out;
+
+	module_put(type->module);
+
+out:
+	spin_unlock(&_lock);
+}
+
+int dm_dirty_log_type_register(struct dm_dirty_log_type *type)
+{
+	int r = 0;
+
+	spin_lock(&_lock);
+	if (!__find_dirty_log_type(type->name))
+		list_add(&type->list, &_log_types);
+	else
+		r = -EEXIST;
+	spin_unlock(&_lock);
+
+	return r;
+}
+EXPORT_SYMBOL(dm_dirty_log_type_register);
+
+int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type)
+{
+	spin_lock(&_lock);
+
+	if (!__find_dirty_log_type(type->name)) {
+		spin_unlock(&_lock);
+		return -EINVAL;
+	}
+
+	list_del(&type->list);
+
+	spin_unlock(&_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(dm_dirty_log_type_unregister);
+
+struct dm_dirty_log *dm_dirty_log_create(const char *type_name,
+			struct dm_target *ti,
+			int (*flush_callback_fn)(struct dm_target *ti),
+			unsigned int argc, char **argv)
+{
+	struct dm_dirty_log_type *type;
+	struct dm_dirty_log *log;
+
+	log = kmalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		return NULL;
+
+	type = get_type(type_name);
+	if (!type) {
+		kfree(log);
+		return NULL;
+	}
+
+	log->flush_callback_fn = flush_callback_fn;
+	log->type = type;
+	if (type->ctr(log, ti, argc, argv)) {
+		kfree(log);
+		put_type(type);
+		return NULL;
+	}
+
+	return log;
+}
+EXPORT_SYMBOL(dm_dirty_log_create);
+
+void dm_dirty_log_destroy(struct dm_dirty_log *log)
+{
+	log->type->dtr(log);
+	put_type(log->type);
+	kfree(log);
+}
+EXPORT_SYMBOL(dm_dirty_log_destroy);
+
+/*-----------------------------------------------------------------
+ * Persistent and core logs share a lot of their implementation.
+ * FIXME: need a reload method to be called from a resume
+ *---------------------------------------------------------------*/
+/*
+ * Magic for persistent mirrors: "MiRr"
+ */
+#define MIRROR_MAGIC 0x4D695272
+
+/*
+ * The on-disk version of the metadata.
+ */
+#define MIRROR_DISK_VERSION 2
+#define LOG_OFFSET 2
+
+struct log_header_disk {
+	__le32 magic;
+
+	/*
+	 * Simple, incrementing version. no backward
+	 * compatibility.
+	 */
+	__le32 version;
+	__le64 nr_regions;
+} __packed;
+
+struct log_header_core {
+	uint32_t magic;
+	uint32_t version;
+	uint64_t nr_regions;
+};
+
+struct log_c {
+	struct dm_target *ti;
+	int touched_dirtied;
+	int touched_cleaned;
+	int flush_failed;
+	uint32_t region_size;
+	unsigned int region_count;
+	region_t sync_count;
+
+	unsigned bitset_uint32_count;
+	uint32_t *clean_bits;
+	uint32_t *sync_bits;
+	uint32_t *recovering_bits;	/* FIXME: this seems excessive */
+
+	int sync_search;
+
+	/* Resync flag */
+	enum sync {
+		DEFAULTSYNC,	/* Synchronize if necessary */
+		NOSYNC,		/* Devices known to be already in sync */
+		FORCESYNC,	/* Force a sync to happen */
+	} sync;
+
+	struct dm_io_request io_req;
+
+	/*
+	 * Disk log fields
+	 */
+	int log_dev_failed;
+	int log_dev_flush_failed;
+	struct dm_dev *log_dev;
+	struct log_header_core header;
+
+	struct dm_io_region header_location;
+	struct log_header_disk *disk_header;
+};
+
+/*
+ * The touched member needs to be updated every time we access
+ * one of the bitsets.
+ */
+static inline int log_test_bit(uint32_t *bs, unsigned bit)
+{
+	return test_bit_le(bit, bs) ? 1 : 0;
+}
+
+static inline void log_set_bit(struct log_c *l,
+			       uint32_t *bs, unsigned bit)
+{
+	__set_bit_le(bit, bs);
+	l->touched_cleaned = 1;
+}
+
+static inline void log_clear_bit(struct log_c *l,
+				 uint32_t *bs, unsigned bit)
+{
+	__clear_bit_le(bit, bs);
+	l->touched_dirtied = 1;
+}
+
+/*----------------------------------------------------------------
+ * Header IO
+ *--------------------------------------------------------------*/
+static void header_to_disk(struct log_header_core *core, struct log_header_disk *disk)
+{
+	disk->magic = cpu_to_le32(core->magic);
+	disk->version = cpu_to_le32(core->version);
+	disk->nr_regions = cpu_to_le64(core->nr_regions);
+}
+
+static void header_from_disk(struct log_header_core *core, struct log_header_disk *disk)
+{
+	core->magic = le32_to_cpu(disk->magic);
+	core->version = le32_to_cpu(disk->version);
+	core->nr_regions = le64_to_cpu(disk->nr_regions);
+}
+
+static int rw_header(struct log_c *lc, enum req_op op)
+{
+	lc->io_req.bi_opf = op;
+
+	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
+}
+
+static int flush_header(struct log_c *lc)
+{
+	struct dm_io_region null_location = {
+		.bdev = lc->header_location.bdev,
+		.sector = 0,
+		.count = 0,
+	};
+
+	lc->io_req.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+	return dm_io(&lc->io_req, 1, &null_location, NULL);
+}
+
+static int read_header(struct log_c *log)
+{
+	int r;
+
+	r = rw_header(log, REQ_OP_READ);
+	if (r)
+		return r;
+
+	header_from_disk(&log->header, log->disk_header);
+
+	/* New log required? */
+	if (log->sync != DEFAULTSYNC || log->header.magic != MIRROR_MAGIC) {
+		log->header.magic = MIRROR_MAGIC;
+		log->header.version = MIRROR_DISK_VERSION;
+		log->header.nr_regions = 0;
+	}
+
+#ifdef __LITTLE_ENDIAN
+	if (log->header.version == 1)
+		log->header.version = 2;
+#endif
+
+	if (log->header.version != MIRROR_DISK_VERSION) {
+		DMWARN("incompatible disk log version");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int _check_region_size(struct dm_target *ti, uint32_t region_size)
+{
+	if (region_size < 2 || region_size > ti->len)
+		return 0;
+
+	if (!is_power_of_2(region_size))
+		return 0;
+
+	return 1;
+}
+
+/*----------------------------------------------------------------
+ * core log constructor/destructor
+ *
+ * argv contains region_size followed optionally by [no]sync
+ *--------------------------------------------------------------*/
+#define BYTE_SHIFT 3
+static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
+			      unsigned int argc, char **argv,
+			      struct dm_dev *dev)
+{
+	enum sync sync = DEFAULTSYNC;
+
+	struct log_c *lc;
+	uint32_t region_size;
+	unsigned int region_count;
+	size_t bitset_size, buf_size;
+	int r;
+	char dummy;
+
+	if (argc < 1 || argc > 2) {
+		DMWARN("wrong number of arguments to dirty region log");
+		return -EINVAL;
+	}
+
+	if (argc > 1) {
+		if (!strcmp(argv[1], "sync"))
+			sync = FORCESYNC;
+		else if (!strcmp(argv[1], "nosync"))
+			sync = NOSYNC;
+		else {
+			DMWARN("unrecognised sync argument to "
+			       "dirty region log: %s", argv[1]);
+			return -EINVAL;
+		}
+	}
+
+	if (sscanf(argv[0], "%u%c", &region_size, &dummy) != 1 ||
+	    !_check_region_size(ti, region_size)) {
+		DMWARN("invalid region size %s", argv[0]);
+		return -EINVAL;
+	}
+
+	region_count = dm_sector_div_up(ti->len, region_size);
+
+	lc = kmalloc(sizeof(*lc), GFP_KERNEL);
+	if (!lc) {
+		DMWARN("couldn't allocate core log");
+		return -ENOMEM;
+	}
+
+	lc->ti = ti;
+	lc->touched_dirtied = 0;
+	lc->touched_cleaned = 0;
+	lc->flush_failed = 0;
+	lc->region_size = region_size;
+	lc->region_count = region_count;
+	lc->sync = sync;
+
+	/*
+	 * Work out how many "unsigned long"s we need to hold the bitset.
+	 */
+	bitset_size = dm_round_up(region_count, BITS_PER_LONG);
+	bitset_size >>= BYTE_SHIFT;
+
+	lc->bitset_uint32_count = bitset_size / sizeof(*lc->clean_bits);
+
+	/*
+	 * Disk log?
+	 */
+	if (!dev) {
+		lc->clean_bits = vmalloc(bitset_size);
+		if (!lc->clean_bits) {
+			DMWARN("couldn't allocate clean bitset");
+			kfree(lc);
+			return -ENOMEM;
+		}
+		lc->disk_header = NULL;
+	} else {
+		lc->log_dev = dev;
+		lc->log_dev_failed = 0;
+		lc->log_dev_flush_failed = 0;
+		lc->header_location.bdev = lc->log_dev->bdev;
+		lc->header_location.sector = 0;
+
+		/*
+		 * Buffer holds both header and bitset.
+		 */
+		buf_size =
+		    dm_round_up((LOG_OFFSET << SECTOR_SHIFT) + bitset_size,
+				bdev_logical_block_size(lc->header_location.
+							    bdev));
+
+		if (buf_size > bdev_nr_bytes(dev->bdev)) {
+			DMWARN("log device %s too small: need %llu bytes",
+				dev->name, (unsigned long long)buf_size);
+			kfree(lc);
+			return -EINVAL;
+		}
+
+		lc->header_location.count = buf_size >> SECTOR_SHIFT;
+
+		lc->io_req.mem.type = DM_IO_VMA;
+		lc->io_req.notify.fn = NULL;
+		lc->io_req.client = dm_io_client_create();
+		if (IS_ERR(lc->io_req.client)) {
+			r = PTR_ERR(lc->io_req.client);
+			DMWARN("couldn't allocate disk io client");
+			kfree(lc);
+			return r;
+		}
+
+		lc->disk_header = vmalloc(buf_size);
+		if (!lc->disk_header) {
+			DMWARN("couldn't allocate disk log buffer");
+			dm_io_client_destroy(lc->io_req.client);
+			kfree(lc);
+			return -ENOMEM;
+		}
+
+		lc->io_req.mem.ptr.vma = lc->disk_header;
+		lc->clean_bits = (void *)lc->disk_header +
+				 (LOG_OFFSET << SECTOR_SHIFT);
+	}
+
+	memset(lc->clean_bits, -1, bitset_size);
+
+	lc->sync_bits = vmalloc(bitset_size);
+	if (!lc->sync_bits) {
+		DMWARN("couldn't allocate sync bitset");
+		if (!dev)
+			vfree(lc->clean_bits);
+		else
+			dm_io_client_destroy(lc->io_req.client);
+		vfree(lc->disk_header);
+		kfree(lc);
+		return -ENOMEM;
+	}
+	memset(lc->sync_bits, (sync == NOSYNC) ? -1 : 0, bitset_size);
+	lc->sync_count = (sync == NOSYNC) ? region_count : 0;
+
+	lc->recovering_bits = vzalloc(bitset_size);
+	if (!lc->recovering_bits) {
+		DMWARN("couldn't allocate sync bitset");
+		vfree(lc->sync_bits);
+		if (!dev)
+			vfree(lc->clean_bits);
+		else
+			dm_io_client_destroy(lc->io_req.client);
+		vfree(lc->disk_header);
+		kfree(lc);
+		return -ENOMEM;
+	}
+	lc->sync_search = 0;
+	log->context = lc;
+
+	return 0;
+}
+
+static int core_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    unsigned int argc, char **argv)
+{
+	return create_log_context(log, ti, argc, argv, NULL);
+}
+
+static void destroy_log_context(struct log_c *lc)
+{
+	vfree(lc->sync_bits);
+	vfree(lc->recovering_bits);
+	kfree(lc);
+}
+
+static void core_dtr(struct dm_dirty_log *log)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+
+	vfree(lc->clean_bits);
+	destroy_log_context(lc);
+}
+
+/*----------------------------------------------------------------
+ * disk log constructor/destructor
+ *
+ * argv contains log_device region_size followed optionally by [no]sync
+ *--------------------------------------------------------------*/
+static int disk_ctr(struct dm_dirty_log *log, struct dm_target *ti,
+		    unsigned int argc, char **argv)
+{
+	int r;
+	struct dm_dev *dev;
+
+	if (argc < 2 || argc > 3) {
+		DMWARN("wrong number of arguments to disk dirty region log");
+		return -EINVAL;
+	}
+
+	r = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &dev);
+	if (r)
+		return r;
+
+	r = create_log_context(log, ti, argc - 1, argv + 1, dev);
+	if (r) {
+		dm_put_device(ti, dev);
+		return r;
+	}
+
+	return 0;
+}
+
+static void disk_dtr(struct dm_dirty_log *log)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+
+	dm_put_device(lc->ti, lc->log_dev);
+	vfree(lc->disk_header);
+	dm_io_client_destroy(lc->io_req.client);
+	destroy_log_context(lc);
+}
+
+static void fail_log_device(struct log_c *lc)
+{
+	if (lc->log_dev_failed)
+		return;
+
+	lc->log_dev_failed = 1;
+	dm_table_event(lc->ti->table);
+}
+
+static int disk_resume(struct dm_dirty_log *log)
+{
+	int r;
+	unsigned i;
+	struct log_c *lc = (struct log_c *) log->context;
+	size_t size = lc->bitset_uint32_count * sizeof(uint32_t);
+
+	/* read the disk header */
+	r = read_header(lc);
+	if (r) {
+		DMWARN("%s: Failed to read header on dirty region log device",
+		       lc->log_dev->name);
+		fail_log_device(lc);
+		/*
+		 * If the log device cannot be read, we must assume
+		 * all regions are out-of-sync.  If we simply return
+		 * here, the state will be uninitialized and could
+		 * lead us to return 'in-sync' status for regions
+		 * that are actually 'out-of-sync'.
+		 */
+		lc->header.nr_regions = 0;
+	}
+
+	/* set or clear any new bits -- device has grown */
+	if (lc->sync == NOSYNC)
+		for (i = lc->header.nr_regions; i < lc->region_count; i++)
+			/* FIXME: amazingly inefficient */
+			log_set_bit(lc, lc->clean_bits, i);
+	else
+		for (i = lc->header.nr_regions; i < lc->region_count; i++)
+			/* FIXME: amazingly inefficient */
+			log_clear_bit(lc, lc->clean_bits, i);
+
+	/* clear any old bits -- device has shrunk */
+	for (i = lc->region_count; i % BITS_PER_LONG; i++)
+		log_clear_bit(lc, lc->clean_bits, i);
+
+	/* copy clean across to sync */
+	memcpy(lc->sync_bits, lc->clean_bits, size);
+	lc->sync_count = memweight(lc->clean_bits,
+				lc->bitset_uint32_count * sizeof(uint32_t));
+	lc->sync_search = 0;
+
+	/* set the correct number of regions in the header */
+	lc->header.nr_regions = lc->region_count;
+
+	header_to_disk(&lc->header, lc->disk_header);
+
+	/* write the new header */
+	r = rw_header(lc, REQ_OP_WRITE);
+	if (!r) {
+		r = flush_header(lc);
+		if (r)
+			lc->log_dev_flush_failed = 1;
+	}
+	if (r) {
+		DMWARN("%s: Failed to write header on dirty region log device",
+		       lc->log_dev->name);
+		fail_log_device(lc);
+	}
+
+	return r;
+}
+
+static uint32_t core_get_region_size(struct dm_dirty_log *log)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	return lc->region_size;
+}
+
+static int core_resume(struct dm_dirty_log *log)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	lc->sync_search = 0;
+	return 0;
+}
+
+static int core_is_clean(struct dm_dirty_log *log, region_t region)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	return log_test_bit(lc->clean_bits, region);
+}
+
+static int core_in_sync(struct dm_dirty_log *log, region_t region, int block)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	return log_test_bit(lc->sync_bits, region);
+}
+
+static int core_flush(struct dm_dirty_log *log)
+{
+	/* no op */
+	return 0;
+}
+
+static int disk_flush(struct dm_dirty_log *log)
+{
+	int r, i;
+	struct log_c *lc = log->context;
+
+	/* only write if the log has changed */
+	if (!lc->touched_cleaned && !lc->touched_dirtied)
+		return 0;
+
+	if (lc->touched_cleaned && log->flush_callback_fn &&
+	    log->flush_callback_fn(lc->ti)) {
+		/*
+		 * At this point it is impossible to determine which
+		 * regions are clean and which are dirty (without
+		 * re-reading the log off disk). So mark all of them
+		 * dirty.
+		 */
+		lc->flush_failed = 1;
+		for (i = 0; i < lc->region_count; i++)
+			log_clear_bit(lc, lc->clean_bits, i);
+	}
+
+	r = rw_header(lc, REQ_OP_WRITE);
+	if (r)
+		fail_log_device(lc);
+	else {
+		if (lc->touched_dirtied) {
+			r = flush_header(lc);
+			if (r) {
+				lc->log_dev_flush_failed = 1;
+				fail_log_device(lc);
+			} else
+				lc->touched_dirtied = 0;
+		}
+		lc->touched_cleaned = 0;
+	}
+
+	return r;
+}
+
+static void core_mark_region(struct dm_dirty_log *log, region_t region)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	log_clear_bit(lc, lc->clean_bits, region);
+}
+
+static void core_clear_region(struct dm_dirty_log *log, region_t region)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+	if (likely(!lc->flush_failed))
+		log_set_bit(lc, lc->clean_bits, region);
+}
+
+static int core_get_resync_work(struct dm_dirty_log *log, region_t *region)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+
+	if (lc->sync_search >= lc->region_count)
+		return 0;
+
+	do {
+		*region = find_next_zero_bit_le(lc->sync_bits,
+					     lc->region_count,
+					     lc->sync_search);
+		lc->sync_search = *region + 1;
+
+		if (*region >= lc->region_count)
+			return 0;
+
+	} while (log_test_bit(lc->recovering_bits, *region));
+
+	log_set_bit(lc, lc->recovering_bits, *region);
+	return 1;
+}
+
+static void core_set_region_sync(struct dm_dirty_log *log, region_t region,
+				 int in_sync)
+{
+	struct log_c *lc = (struct log_c *) log->context;
+
+	log_clear_bit(lc, lc->recovering_bits, region);
+	if (in_sync) {
+		log_set_bit(lc, lc->sync_bits, region);
+                lc->sync_count++;
+        } else if (log_test_bit(lc->sync_bits, region)) {
+		lc->sync_count--;
+		log_clear_bit(lc, lc->sync_bits, region);
+	}
+}
+
+static region_t core_get_sync_count(struct dm_dirty_log *log)
+{
+        struct log_c *lc = (struct log_c *) log->context;
+
+        return lc->sync_count;
+}
+
+#define	DMEMIT_SYNC \
+	if (lc->sync != DEFAULTSYNC) \
+		DMEMIT("%ssync ", lc->sync == NOSYNC ? "no" : "")
+
+static int core_status(struct dm_dirty_log *log, status_type_t status,
+		       char *result, unsigned int maxlen)
+{
+	int sz = 0;
+	struct log_c *lc = log->context;
+
+	switch(status) {
+	case STATUSTYPE_INFO:
+		DMEMIT("1 %s", log->type->name);
+		break;
+
+	case STATUSTYPE_TABLE:
+		DMEMIT("%s %u %u ", log->type->name,
+		       lc->sync == DEFAULTSYNC ? 1 : 2, lc->region_size);
+		DMEMIT_SYNC;
+		break;
+
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
+	}
+
+	return sz;
+}
+
+static int disk_status(struct dm_dirty_log *log, status_type_t status,
+		       char *result, unsigned int maxlen)
+{
+	int sz = 0;
+	struct log_c *lc = log->context;
+
+	switch(status) {
+	case STATUSTYPE_INFO:
+		DMEMIT("3 %s %s %c", log->type->name, lc->log_dev->name,
+		       lc->log_dev_flush_failed ? 'F' :
+		       lc->log_dev_failed ? 'D' :
+		       'A');
+		break;
+
+	case STATUSTYPE_TABLE:
+		DMEMIT("%s %u %s %u ", log->type->name,
+		       lc->sync == DEFAULTSYNC ? 2 : 3, lc->log_dev->name,
+		       lc->region_size);
+		DMEMIT_SYNC;
+		break;
+
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
+	}
+
+	return sz;
+}
+
+static struct dm_dirty_log_type _core_type = {
+	.name = "core",
+	.module = THIS_MODULE,
+	.ctr = core_ctr,
+	.dtr = core_dtr,
+	.resume = core_resume,
+	.get_region_size = core_get_region_size,
+	.is_clean = core_is_clean,
+	.in_sync = core_in_sync,
+	.flush = core_flush,
+	.mark_region = core_mark_region,
+	.clear_region = core_clear_region,
+	.get_resync_work = core_get_resync_work,
+	.set_region_sync = core_set_region_sync,
+	.get_sync_count = core_get_sync_count,
+	.status = core_status,
+};
+
+static struct dm_dirty_log_type _disk_type = {
+	.name = "disk",
+	.module = THIS_MODULE,
+	.ctr = disk_ctr,
+	.dtr = disk_dtr,
+	.postsuspend = disk_flush,
+	.resume = disk_resume,
+	.get_region_size = core_get_region_size,
+	.is_clean = core_is_clean,
+	.in_sync = core_in_sync,
+	.flush = disk_flush,
+	.mark_region = core_mark_region,
+	.clear_region = core_clear_region,
+	.get_resync_work = core_get_resync_work,
+	.set_region_sync = core_set_region_sync,
+	.get_sync_count = core_get_sync_count,
+	.status = disk_status,
+};
+
+static int __init dm_dirty_log_init(void)
+{
+	int r;
+
+	r = dm_dirty_log_type_register(&_core_type);
+	if (r)
+		DMWARN("couldn't register core log");
+
+	r = dm_dirty_log_type_register(&_disk_type);
+	if (r) {
+		DMWARN("couldn't register disk type");
+		dm_dirty_log_type_unregister(&_core_type);
+	}
+
+	return r;
+}
+
+static void __exit dm_dirty_log_exit(void)
+{
+	dm_dirty_log_type_unregister(&_disk_type);
+	dm_dirty_log_type_unregister(&_core_type);
+}
+
+module_init(dm_dirty_log_init);
+module_exit(dm_dirty_log_exit);
+
+MODULE_DESCRIPTION(DM_NAME " dirty region log");
+MODULE_AUTHOR("Joe Thornber, Heinz Mauelshagen <dm-devel@redhat.com>");
+MODULE_LICENSE("GPL");