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, 830 insertions, 0 deletions

diff --git a/drivers/mtd/rfd_ftl.c b/drivers/mtd/rfd_ftl.c
new file mode 100644
index 000000000..c546f8c5f
--- /dev/null
+++ b/drivers/mtd/rfd_ftl.c
@@ -0,0 +1,830 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * rfd_ftl.c -- resident flash disk (flash translation layer)
+ *
+ * Copyright © 2005  Sean Young <sean@mess.org>
+ *
+ * This type of flash translation layer (FTL) is used by the Embedded BIOS
+ * by General Software. It is known as the Resident Flash Disk (RFD), see:
+ *
+ *	http://www.gensw.com/pages/prod/bios/rfd.htm
+ *
+ * based on ftl.c
+ */
+
+#include <linux/hdreg.h>
+#include <linux/init.h>
+#include <linux/mtd/blktrans.h>
+#include <linux/mtd/mtd.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+
+#include <asm/types.h>
+
+static int block_size = 0;
+module_param(block_size, int, 0);
+MODULE_PARM_DESC(block_size, "Block size to use by RFD, defaults to erase unit size");
+
+#define PREFIX "rfd_ftl: "
+
+/* This major has been assigned by device@lanana.org */
+#ifndef RFD_FTL_MAJOR
+#define RFD_FTL_MAJOR		256
+#endif
+
+/* Maximum number of partitions in an FTL region */
+#define PART_BITS		4
+
+/* An erase unit should start with this value */
+#define RFD_MAGIC		0x9193
+
+/* the second value is 0xffff or 0xffc8; function unknown */
+
+/* the third value is always 0xffff, ignored */
+
+/* next is an array of mapping for each corresponding sector */
+#define HEADER_MAP_OFFSET	3
+#define SECTOR_DELETED		0x0000
+#define SECTOR_ZERO		0xfffe
+#define SECTOR_FREE		0xffff
+
+#define SECTOR_SIZE		512
+
+#define SECTORS_PER_TRACK	63
+
+struct block {
+	enum {
+		BLOCK_OK,
+		BLOCK_ERASING,
+		BLOCK_ERASED,
+		BLOCK_UNUSED,
+		BLOCK_FAILED
+	} state;
+	int free_sectors;
+	int used_sectors;
+	int erases;
+	u_long offset;
+};
+
+struct partition {
+	struct mtd_blktrans_dev mbd;
+
+	u_int block_size;		/* size of erase unit */
+	u_int total_blocks;		/* number of erase units */
+	u_int header_sectors_per_block;	/* header sectors in erase unit */
+	u_int data_sectors_per_block;	/* data sectors in erase unit */
+	u_int sector_count;		/* sectors in translated disk */
+	u_int header_size;		/* bytes in header sector */
+	int reserved_block;		/* block next up for reclaim */
+	int current_block;		/* block to write to */
+	u16 *header_cache;		/* cached header */
+
+	int is_reclaiming;
+	int cylinders;
+	int errors;
+	u_long *sector_map;
+	struct block *blocks;
+};
+
+static int rfd_ftl_writesect(struct mtd_blktrans_dev *dev, u_long sector, char *buf);
+
+static int build_block_map(struct partition *part, int block_no)
+{
+	struct block *block = &part->blocks[block_no];
+	int i;
+
+	block->offset = part->block_size * block_no;
+
+	if (le16_to_cpu(part->header_cache[0]) != RFD_MAGIC) {
+		block->state = BLOCK_UNUSED;
+		return -ENOENT;
+	}
+
+	block->state = BLOCK_OK;
+
+	for (i=0; i<part->data_sectors_per_block; i++) {
+		u16 entry;
+
+		entry = le16_to_cpu(part->header_cache[HEADER_MAP_OFFSET + i]);
+
+		if (entry == SECTOR_DELETED)
+			continue;
+
+		if (entry == SECTOR_FREE) {
+			block->free_sectors++;
+			continue;
+		}
+
+		if (entry == SECTOR_ZERO)
+			entry = 0;
+
+		if (entry >= part->sector_count) {
+			printk(KERN_WARNING PREFIX
+				"'%s': unit #%d: entry %d corrupt, "
+				"sector %d out of range\n",
+				part->mbd.mtd->name, block_no, i, entry);
+			continue;
+		}
+
+		if (part->sector_map[entry] != -1) {
+			printk(KERN_WARNING PREFIX
+				"'%s': more than one entry for sector %d\n",
+				part->mbd.mtd->name, entry);
+			part->errors = 1;
+			continue;
+		}
+
+		part->sector_map[entry] = block->offset +
+			(i + part->header_sectors_per_block) * SECTOR_SIZE;
+
+		block->used_sectors++;
+	}
+
+	if (block->free_sectors == part->data_sectors_per_block)
+		part->reserved_block = block_no;
+
+	return 0;
+}
+
+static int scan_header(struct partition *part)
+{
+	int sectors_per_block;
+	int i, rc = -ENOMEM;
+	int blocks_found;
+	size_t retlen;
+
+	sectors_per_block = part->block_size / SECTOR_SIZE;
+	part->total_blocks = (u32)part->mbd.mtd->size / part->block_size;
+
+	if (part->total_blocks < 2)
+		return -ENOENT;
+
+	/* each erase block has three bytes header, followed by the map */
+	part->header_sectors_per_block =
+			((HEADER_MAP_OFFSET + sectors_per_block) *
+			sizeof(u16) + SECTOR_SIZE - 1) / SECTOR_SIZE;
+
+	part->data_sectors_per_block = sectors_per_block -
+			part->header_sectors_per_block;
+
+	part->header_size = (HEADER_MAP_OFFSET +
+			part->data_sectors_per_block) * sizeof(u16);
+
+	part->cylinders = (part->data_sectors_per_block *
+			(part->total_blocks - 1) - 1) / SECTORS_PER_TRACK;
+
+	part->sector_count = part->cylinders * SECTORS_PER_TRACK;
+
+	part->current_block = -1;
+	part->reserved_block = -1;
+	part->is_reclaiming = 0;
+
+	part->header_cache = kmalloc(part->header_size, GFP_KERNEL);
+	if (!part->header_cache)
+		goto err;
+
+	part->blocks = kcalloc(part->total_blocks, sizeof(struct block),
+			GFP_KERNEL);
+	if (!part->blocks)
+		goto err;
+
+	part->sector_map = vmalloc(array_size(sizeof(u_long),
+					      part->sector_count));
+	if (!part->sector_map)
+		goto err;
+
+	for (i=0; i<part->sector_count; i++)
+		part->sector_map[i] = -1;
+
+	for (i=0, blocks_found=0; i<part->total_blocks; i++) {
+		rc = mtd_read(part->mbd.mtd, i * part->block_size,
+			      part->header_size, &retlen,
+			      (u_char *)part->header_cache);
+
+		if (!rc && retlen != part->header_size)
+			rc = -EIO;
+
+		if (rc)
+			goto err;
+
+		if (!build_block_map(part, i))
+			blocks_found++;
+	}
+
+	if (blocks_found == 0) {
+		printk(KERN_NOTICE PREFIX "no RFD magic found in '%s'\n",
+				part->mbd.mtd->name);
+		rc = -ENOENT;
+		goto err;
+	}
+
+	if (part->reserved_block == -1) {
+		printk(KERN_WARNING PREFIX "'%s': no empty erase unit found\n",
+				part->mbd.mtd->name);
+
+		part->errors = 1;
+	}
+
+	return 0;
+
+err:
+	vfree(part->sector_map);
+	kfree(part->header_cache);
+	kfree(part->blocks);
+
+	return rc;
+}
+
+static int rfd_ftl_readsect(struct mtd_blktrans_dev *dev, u_long sector, char *buf)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+	u_long addr;
+	size_t retlen;
+	int rc;
+
+	if (sector >= part->sector_count)
+		return -EIO;
+
+	addr = part->sector_map[sector];
+	if (addr != -1) {
+		rc = mtd_read(part->mbd.mtd, addr, SECTOR_SIZE, &retlen,
+			      (u_char *)buf);
+		if (!rc && retlen != SECTOR_SIZE)
+			rc = -EIO;
+
+		if (rc) {
+			printk(KERN_WARNING PREFIX "error reading '%s' at "
+				"0x%lx\n", part->mbd.mtd->name, addr);
+			return rc;
+		}
+	} else
+		memset(buf, 0, SECTOR_SIZE);
+
+	return 0;
+}
+
+static int erase_block(struct partition *part, int block)
+{
+	struct erase_info *erase;
+	int rc;
+
+	erase = kmalloc(sizeof(struct erase_info), GFP_KERNEL);
+	if (!erase)
+		return -ENOMEM;
+
+	erase->addr = part->blocks[block].offset;
+	erase->len = part->block_size;
+
+	part->blocks[block].state = BLOCK_ERASING;
+	part->blocks[block].free_sectors = 0;
+
+	rc = mtd_erase(part->mbd.mtd, erase);
+	if (rc) {
+		printk(KERN_ERR PREFIX "erase of region %llx,%llx on '%s' "
+				"failed\n", (unsigned long long)erase->addr,
+				(unsigned long long)erase->len, part->mbd.mtd->name);
+		part->blocks[block].state = BLOCK_FAILED;
+		part->blocks[block].free_sectors = 0;
+		part->blocks[block].used_sectors = 0;
+	} else {
+		u16 magic = cpu_to_le16(RFD_MAGIC);
+		size_t retlen;
+
+		part->blocks[block].state = BLOCK_ERASED;
+		part->blocks[block].free_sectors = part->data_sectors_per_block;
+		part->blocks[block].used_sectors = 0;
+		part->blocks[block].erases++;
+
+		rc = mtd_write(part->mbd.mtd, part->blocks[block].offset,
+			       sizeof(magic), &retlen, (u_char *)&magic);
+		if (!rc && retlen != sizeof(magic))
+			rc = -EIO;
+
+		if (rc) {
+			pr_err(PREFIX "'%s': unable to write RFD header at 0x%lx\n",
+			       part->mbd.mtd->name, part->blocks[block].offset);
+			part->blocks[block].state = BLOCK_FAILED;
+		} else {
+			part->blocks[block].state = BLOCK_OK;
+		}
+	}
+
+	kfree(erase);
+
+	return rc;
+}
+
+static int move_block_contents(struct partition *part, int block_no, u_long *old_sector)
+{
+	void *sector_data;
+	u16 *map;
+	size_t retlen;
+	int i, rc = -ENOMEM;
+
+	part->is_reclaiming = 1;
+
+	sector_data = kmalloc(SECTOR_SIZE, GFP_KERNEL);
+	if (!sector_data)
+		goto err3;
+
+	map = kmalloc(part->header_size, GFP_KERNEL);
+	if (!map)
+		goto err2;
+
+	rc = mtd_read(part->mbd.mtd, part->blocks[block_no].offset,
+		      part->header_size, &retlen, (u_char *)map);
+
+	if (!rc && retlen != part->header_size)
+		rc = -EIO;
+
+	if (rc) {
+		printk(KERN_ERR PREFIX "error reading '%s' at "
+			"0x%lx\n", part->mbd.mtd->name,
+			part->blocks[block_no].offset);
+
+		goto err;
+	}
+
+	for (i=0; i<part->data_sectors_per_block; i++) {
+		u16 entry = le16_to_cpu(map[HEADER_MAP_OFFSET + i]);
+		u_long addr;
+
+
+		if (entry == SECTOR_FREE || entry == SECTOR_DELETED)
+			continue;
+
+		if (entry == SECTOR_ZERO)
+			entry = 0;
+
+		/* already warned about and ignored in build_block_map() */
+		if (entry >= part->sector_count)
+			continue;
+
+		addr = part->blocks[block_no].offset +
+			(i + part->header_sectors_per_block) * SECTOR_SIZE;
+
+		if (*old_sector == addr) {
+			*old_sector = -1;
+			if (!part->blocks[block_no].used_sectors--) {
+				rc = erase_block(part, block_no);
+				break;
+			}
+			continue;
+		}
+		rc = mtd_read(part->mbd.mtd, addr, SECTOR_SIZE, &retlen,
+			      sector_data);
+
+		if (!rc && retlen != SECTOR_SIZE)
+			rc = -EIO;
+
+		if (rc) {
+			printk(KERN_ERR PREFIX "'%s': Unable to "
+				"read sector for relocation\n",
+				part->mbd.mtd->name);
+
+			goto err;
+		}
+
+		rc = rfd_ftl_writesect((struct mtd_blktrans_dev*)part,
+				entry, sector_data);
+
+		if (rc)
+			goto err;
+	}
+
+err:
+	kfree(map);
+err2:
+	kfree(sector_data);
+err3:
+	part->is_reclaiming = 0;
+
+	return rc;
+}
+
+static int reclaim_block(struct partition *part, u_long *old_sector)
+{
+	int block, best_block, score, old_sector_block;
+	int rc;
+
+	/* we have a race if sync doesn't exist */
+	mtd_sync(part->mbd.mtd);
+
+	score = 0x7fffffff; /* MAX_INT */
+	best_block = -1;
+	if (*old_sector != -1)
+		old_sector_block = *old_sector / part->block_size;
+	else
+		old_sector_block = -1;
+
+	for (block=0; block<part->total_blocks; block++) {
+		int this_score;
+
+		if (block == part->reserved_block)
+			continue;
+
+		/*
+		 * Postpone reclaiming if there is a free sector as
+		 * more removed sectors is more efficient (have to move
+		 * less).
+		 */
+		if (part->blocks[block].free_sectors)
+			return 0;
+
+		this_score = part->blocks[block].used_sectors;
+
+		if (block == old_sector_block)
+			this_score--;
+		else {
+			/* no point in moving a full block */
+			if (part->blocks[block].used_sectors ==
+					part->data_sectors_per_block)
+				continue;
+		}
+
+		this_score += part->blocks[block].erases;
+
+		if (this_score < score) {
+			best_block = block;
+			score = this_score;
+		}
+	}
+
+	if (best_block == -1)
+		return -ENOSPC;
+
+	part->current_block = -1;
+	part->reserved_block = best_block;
+
+	pr_debug("reclaim_block: reclaiming block #%d with %d used "
+		 "%d free sectors\n", best_block,
+		 part->blocks[best_block].used_sectors,
+		 part->blocks[best_block].free_sectors);
+
+	if (part->blocks[best_block].used_sectors)
+		rc = move_block_contents(part, best_block, old_sector);
+	else
+		rc = erase_block(part, best_block);
+
+	return rc;
+}
+
+/*
+ * IMPROVE: It would be best to choose the block with the most deleted sectors,
+ * because if we fill that one up first it'll have the most chance of having
+ * the least live sectors at reclaim.
+ */
+static int find_free_block(struct partition *part)
+{
+	int block, stop;
+
+	block = part->current_block == -1 ?
+			jiffies % part->total_blocks : part->current_block;
+	stop = block;
+
+	do {
+		if (part->blocks[block].free_sectors &&
+				block != part->reserved_block)
+			return block;
+
+		if (part->blocks[block].state == BLOCK_UNUSED)
+			erase_block(part, block);
+
+		if (++block >= part->total_blocks)
+			block = 0;
+
+	} while (block != stop);
+
+	return -1;
+}
+
+static int find_writable_block(struct partition *part, u_long *old_sector)
+{
+	int rc, block;
+	size_t retlen;
+
+	block = find_free_block(part);
+
+	if (block == -1) {
+		if (!part->is_reclaiming) {
+			rc = reclaim_block(part, old_sector);
+			if (rc)
+				goto err;
+
+			block = find_free_block(part);
+		}
+
+		if (block == -1) {
+			rc = -ENOSPC;
+			goto err;
+		}
+	}
+
+	rc = mtd_read(part->mbd.mtd, part->blocks[block].offset,
+		      part->header_size, &retlen,
+		      (u_char *)part->header_cache);
+
+	if (!rc && retlen != part->header_size)
+		rc = -EIO;
+
+	if (rc) {
+		printk(KERN_ERR PREFIX "'%s': unable to read header at "
+				"0x%lx\n", part->mbd.mtd->name,
+				part->blocks[block].offset);
+		goto err;
+	}
+
+	part->current_block = block;
+
+err:
+	return rc;
+}
+
+static int mark_sector_deleted(struct partition *part, u_long old_addr)
+{
+	int block, offset, rc;
+	u_long addr;
+	size_t retlen;
+	u16 del = cpu_to_le16(SECTOR_DELETED);
+
+	block = old_addr / part->block_size;
+	offset = (old_addr % part->block_size) / SECTOR_SIZE -
+		part->header_sectors_per_block;
+
+	addr = part->blocks[block].offset +
+			(HEADER_MAP_OFFSET + offset) * sizeof(u16);
+	rc = mtd_write(part->mbd.mtd, addr, sizeof(del), &retlen,
+		       (u_char *)&del);
+
+	if (!rc && retlen != sizeof(del))
+		rc = -EIO;
+
+	if (rc) {
+		printk(KERN_ERR PREFIX "error writing '%s' at "
+			"0x%lx\n", part->mbd.mtd->name, addr);
+		goto err;
+	}
+	if (block == part->current_block)
+		part->header_cache[offset + HEADER_MAP_OFFSET] = del;
+
+	part->blocks[block].used_sectors--;
+
+	if (!part->blocks[block].used_sectors &&
+	    !part->blocks[block].free_sectors)
+		rc = erase_block(part, block);
+
+err:
+	return rc;
+}
+
+static int find_free_sector(const struct partition *part, const struct block *block)
+{
+	int i, stop;
+
+	i = stop = part->data_sectors_per_block - block->free_sectors;
+
+	do {
+		if (le16_to_cpu(part->header_cache[HEADER_MAP_OFFSET + i])
+				== SECTOR_FREE)
+			return i;
+
+		if (++i == part->data_sectors_per_block)
+			i = 0;
+	}
+	while(i != stop);
+
+	return -1;
+}
+
+static int do_writesect(struct mtd_blktrans_dev *dev, u_long sector, char *buf, ulong *old_addr)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+	struct block *block;
+	u_long addr;
+	int i;
+	int rc;
+	size_t retlen;
+	u16 entry;
+
+	if (part->current_block == -1 ||
+		!part->blocks[part->current_block].free_sectors) {
+
+		rc = find_writable_block(part, old_addr);
+		if (rc)
+			goto err;
+	}
+
+	block = &part->blocks[part->current_block];
+
+	i = find_free_sector(part, block);
+
+	if (i < 0) {
+		rc = -ENOSPC;
+		goto err;
+	}
+
+	addr = (i + part->header_sectors_per_block) * SECTOR_SIZE +
+		block->offset;
+	rc = mtd_write(part->mbd.mtd, addr, SECTOR_SIZE, &retlen,
+		       (u_char *)buf);
+
+	if (!rc && retlen != SECTOR_SIZE)
+		rc = -EIO;
+
+	if (rc) {
+		printk(KERN_ERR PREFIX "error writing '%s' at 0x%lx\n",
+				part->mbd.mtd->name, addr);
+		goto err;
+	}
+
+	part->sector_map[sector] = addr;
+
+	entry = cpu_to_le16(sector == 0 ? SECTOR_ZERO : sector);
+
+	part->header_cache[i + HEADER_MAP_OFFSET] = entry;
+
+	addr = block->offset + (HEADER_MAP_OFFSET + i) * sizeof(u16);
+	rc = mtd_write(part->mbd.mtd, addr, sizeof(entry), &retlen,
+		       (u_char *)&entry);
+
+	if (!rc && retlen != sizeof(entry))
+		rc = -EIO;
+
+	if (rc) {
+		printk(KERN_ERR PREFIX "error writing '%s' at 0x%lx\n",
+				part->mbd.mtd->name, addr);
+		goto err;
+	}
+	block->used_sectors++;
+	block->free_sectors--;
+
+err:
+	return rc;
+}
+
+static int rfd_ftl_writesect(struct mtd_blktrans_dev *dev, u_long sector, char *buf)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+	u_long old_addr;
+	int i;
+	int rc = 0;
+
+	pr_debug("rfd_ftl_writesect(sector=0x%lx)\n", sector);
+
+	if (part->reserved_block == -1) {
+		rc = -EACCES;
+		goto err;
+	}
+
+	if (sector >= part->sector_count) {
+		rc = -EIO;
+		goto err;
+	}
+
+	old_addr = part->sector_map[sector];
+
+	for (i=0; i<SECTOR_SIZE; i++) {
+		if (!buf[i])
+			continue;
+
+		rc = do_writesect(dev, sector, buf, &old_addr);
+		if (rc)
+			goto err;
+		break;
+	}
+
+	if (i == SECTOR_SIZE)
+		part->sector_map[sector] = -1;
+
+	if (old_addr != -1)
+		rc = mark_sector_deleted(part, old_addr);
+
+err:
+	return rc;
+}
+
+static int rfd_ftl_discardsect(struct mtd_blktrans_dev *dev,
+			       unsigned long sector, unsigned int nr_sects)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+	u_long addr;
+	int rc;
+
+	while (nr_sects) {
+		if (sector >= part->sector_count)
+			return -EIO;
+
+		addr = part->sector_map[sector];
+
+		if (addr != -1) {
+			rc = mark_sector_deleted(part, addr);
+			if (rc)
+				return rc;
+
+			part->sector_map[sector] = -1;
+		}
+
+		sector++;
+		nr_sects--;
+	}
+
+	return 0;
+}
+
+static int rfd_ftl_getgeo(struct mtd_blktrans_dev *dev, struct hd_geometry *geo)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+
+	geo->heads = 1;
+	geo->sectors = SECTORS_PER_TRACK;
+	geo->cylinders = part->cylinders;
+
+	return 0;
+}
+
+static void rfd_ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd)
+{
+	struct partition *part;
+
+	if ((mtd->type != MTD_NORFLASH && mtd->type != MTD_RAM) ||
+	    mtd->size > UINT_MAX)
+		return;
+
+	part = kzalloc(sizeof(struct partition), GFP_KERNEL);
+	if (!part)
+		return;
+
+	part->mbd.mtd = mtd;
+
+	if (block_size)
+		part->block_size = block_size;
+	else {
+		if (!mtd->erasesize) {
+			printk(KERN_WARNING PREFIX "please provide block_size");
+			goto out;
+		} else
+			part->block_size = mtd->erasesize;
+	}
+
+	if (scan_header(part) == 0) {
+		part->mbd.size = part->sector_count;
+		part->mbd.tr = tr;
+		part->mbd.devnum = -1;
+		if (!(mtd->flags & MTD_WRITEABLE))
+			part->mbd.readonly = 1;
+		else if (part->errors) {
+			printk(KERN_WARNING PREFIX "'%s': errors found, "
+					"setting read-only\n", mtd->name);
+			part->mbd.readonly = 1;
+		}
+
+		printk(KERN_INFO PREFIX "name: '%s' type: %d flags %x\n",
+				mtd->name, mtd->type, mtd->flags);
+
+		if (!add_mtd_blktrans_dev(&part->mbd))
+			return;
+	}
+out:
+	kfree(part);
+}
+
+static void rfd_ftl_remove_dev(struct mtd_blktrans_dev *dev)
+{
+	struct partition *part = container_of(dev, struct partition, mbd);
+	int i;
+
+	for (i=0; i<part->total_blocks; i++) {
+		pr_debug("rfd_ftl_remove_dev:'%s': erase unit #%02d: %d erases\n",
+			part->mbd.mtd->name, i, part->blocks[i].erases);
+	}
+
+	vfree(part->sector_map);
+	kfree(part->header_cache);
+	kfree(part->blocks);
+	del_mtd_blktrans_dev(&part->mbd);
+}
+
+static struct mtd_blktrans_ops rfd_ftl_tr = {
+	.name		= "rfd",
+	.major		= RFD_FTL_MAJOR,
+	.part_bits	= PART_BITS,
+	.blksize 	= SECTOR_SIZE,
+
+	.readsect	= rfd_ftl_readsect,
+	.writesect	= rfd_ftl_writesect,
+	.discard	= rfd_ftl_discardsect,
+	.getgeo		= rfd_ftl_getgeo,
+	.add_mtd	= rfd_ftl_add_mtd,
+	.remove_dev	= rfd_ftl_remove_dev,
+	.owner		= THIS_MODULE,
+};
+
+module_mtd_blktrans(rfd_ftl_tr);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Sean Young <sean@mess.org>");
+MODULE_DESCRIPTION("Support code for RFD Flash Translation Layer, "
+		"used by General Software's Embedded BIOS");
+