AI Trajectory

Trajectory: (Expand/Collapse All)
Seq	Timestamp	Type	Name	Duration
0/0	2026/08/16 23:35	flow	patch-triage	0m Args: null Results: { "EnableConfigs": null, "FocusSymbols": [], "KMSANReasoning": "", "NeedsKMSAN": false, "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.", "WorthFuzzing": false }
1/1	2026/08/16 23:35	action	read-patch-diff	0m Args: null Results: { "PatchDiff": "commit a01707c4f39f9db8f15411902f052348a25923e9\nAuthor: syz-cluster \u003ctriage@syzkaller.com\u003e\nDate: Sun Aug 16 23:35:08 2026 +0000\n\n syz-cluster: applied patch under review\n\ndiff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst\nindex 4745148fecf4f..058999d0dc56f 100644\n--- a/Documentation/networking/devlink/index.rst\n+++ b/Documentation/networking/devlink/index.rst\n@@ -94,6 +94,7 @@ parameters, info versions, and other features it supports.\n mlx5\n mlxsw\n mv88e6xxx\n+ mxl862xx\n netdevsim\n nfp\n octeontx2\ndiff --git a/Documentation/networking/devlink/mxl862xx.rst b/Documentation/networking/devlink/mxl862xx.rst\nnew file mode 100644\nindex 0000000000000..5b24d8cb57bc9\n--- /dev/null\n+++ b/Documentation/networking/devlink/mxl862xx.rst\n@@ -0,0 +1,74 @@\n+.. SPDX-License-Identifier: GPL-2.0\n+\n+========================\n+mxl862xx devlink support\n+========================\n+\n+This document describes the devlink features implemented by the\n+``mxl862xx`` device driver.\n+\n+Info versions\n+=============\n+\n+The ``mxl862xx`` driver reports the following versions\n+\n+.. list-table:: devlink info versions implemented\n+ :widths: 5 5 5 85\n+\n+ * - Name\n+ - Type\n+ - Example\n+ - Description\n+ * - ``asic.id``\n+ - fixed\n+ - 8628\n+ - The chip part number read from the CHIP ID registers. Omitted\n+ when the part number reads as zero, which happens for a switch\n+ sitting in MCUboot rescue mode (the registers need a running\n+ firmware), for an unfused part, and after a failed flash.\n+ * - ``asic.rev``\n+ - fixed\n+ - 0\n+ - The chip version read from the same register word, so it is\n+ omitted whenever ``asic.id`` is.\n+ * - ``fw``\n+ - running, stored\n+ - 1.0.70\n+ - Version of the firmware running on the switch, reported as both\n+ running and stored since the switch boots it from its own flash.\n+ It is omitted while no firmware version is known: after a failed\n+ flash, and in MCUboot rescue mode while an interrupted download\n+ is still being recovered in the background. Once the loader is\n+ ready to accept a new image the version appears as \"0.0.0\",\n+ which no released firmware reports, so version-comparing tools\n+ offer any available release as an upgrade. Use ``devlink dev\n+ flash`` to tell a recovering switch from a ready one, see below;\n+ a missing version on its own does not say why.\n+\n+Flash update\n+============\n+\n+The ``mxl862xx`` driver implements support for ``devlink dev flash``.\n+The signed firmware image is transferred to the switch over the same\n+MDIO bus which is also used to manage the switch, then verified and\n+installed by the MCUboot bootloader running on the switch. All ports\n+of the switch are closed for the duration of the update and the driver\n+reprobes the switch after it has rebooted into the new firmware. A\n+complete flash and reprobe cycle takes about one minute.\n+\n+A switch stuck in MCUboot rescue mode, e.g. after an interrupted\n+update, is registered without user ports. If the previous download was\n+interrupted mid-transfer the loader is wedged; the driver drains it\n+back to a clean ready state in the background, one byte at a time,\n+which takes tens of minutes for a large image and is reported through\n+the kernel log as it progresses. During that recovery ``devlink dev\n+flash`` returns ``-EBUSY`` with an extack message saying so, and\n+``devlink dev info`` reports no firmware version. Once the loader is\n+ready the firmware version appears and flashing a firmware image\n+through the regular update flow recovers the switch.\n+\n+If the recovery fails, the loader needs a power cycle: ``devlink dev\n+flash`` then returns ``-EIO`` and says so in its extack message. The\n+driver only re-examines the switch when it binds, so on a board where\n+the switch can be power cycled on its own, unbind and rebind the driver\n+afterwards to have the recovered switch recognised.\ndiff --git a/MAINTAINERS b/MAINTAINERS\nindex 991460050da74..e3f7ded569bf7 100644\n--- a/MAINTAINERS\n+++ b/MAINTAINERS\n@@ -16106,6 +16106,7 @@ M:\tDaniel Golle \u003cdaniel@makrotopia.org\u003e\n L:\tnetdev@vger.kernel.org\n S:\tMaintained\n F:\tDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml\n+F:\tDocumentation/networking/devlink/mxl862xx.rst\n F:\tdrivers/net/dsa/mxl862xx/\n F:\tnet/dsa/tag_mxl862xx.c\n \ndiff --git a/drivers/base/base.h b/drivers/base/base.h\nindex a5b7abc10ff02..6234e37de7e99 100644\n--- a/drivers/base/base.h\n+++ b/drivers/base/base.h\n@@ -106,6 +106,10 @@ struct driver_private {\n * @dead: This device is currently either in the process of or has been\n \t removed from the system. Any asynchronous events scheduled for this\n \t device should exit without taking any action.\n+ * @shutdown_done: Set once device_shutdown() has reached this device, under\n+ \t the device lock, before any shutdown callback runs. Read under the\n+ \t device lock. A deferred re-probe scheduled with\n+ \t device_schedule_reprobe() must not detach the device anymore.\n \n * Nothing outside of the driver core should ever touch these fields.\n /\n@@ -120,6 +124,7 @@ struct device_private {\n \tchar deferred_probe_reason;\n \tstruct device device;\n \tu8 dead:1;\n+\tu8 shutdown_done:1;\n };\n #define to_device_private_parent(obj)\t\\\n \tcontainer_of(obj, struct device_private, knode_parent)\ndiff --git a/drivers/base/core.c b/drivers/base/core.c\nindex 4d026682944f2..8a7dbe4e8362b 100644\n--- a/drivers/base/core.c\n+++ b/drivers/base/core.c\n@@ -4906,6 +4906,9 @@ void device_shutdown(void)\n \t\t\tdevice_lock(parent);\n \t\tdevice_lock(dev);\n \n+\t\tif (dev-\u003ep)\n+\t\t\tdev-\u003ep-\u003eshutdown_done = true;\n+\n \t\t/ Don't allow any more runtime suspends /\n \t\tpm_runtime_get_noresume(dev);\n \t\tpm_runtime_barrier(dev);\ndiff --git a/drivers/base/dd.c b/drivers/base/dd.c\nindex 60c005223844d..3394b1c7ed180 100644\n--- a/drivers/base/dd.c\n+++ b/drivers/base/dd.c\n@@ -1436,3 +1436,102 @@ void driver_detach(const struct device_driver drv)\n \t\tput_device(dev);\n \t}\n }\n+\n+struct device_reprobe {\n+\tstruct delayed_work work;\n+\tstruct device dev;\n+\tstruct device parent;\n+\tconst struct device_driver drv;\n+};\n+\n+static void device_reprobe_work_fn(struct work_struct work)\n+{\n+\tstruct device_reprobe rp = container_of(work, struct device_reprobe,\n+\t\t\t\t\t\t work.work);\n+\tstruct device dev = rp-\u003edev;\n+\tstruct device parent = rp-\u003eparent;\n+\tbool detached = false;\n+\n+\t__device_driver_lock(dev, parent);\n+\t/\n+\t * rp-\u003edrv is only ever compared, never dereferenced: the driver it\n+\t * points to may have been unregistered and freed by now.\n+\t /\n+\tif (!dev-\u003ep-\u003edead \u0026\u0026 !dev-\u003ep-\u003eshutdown_done \u0026\u0026\n+\t dev-\u003edriver \u0026\u0026 dev-\u003edriver == rp-\u003edrv) {\n+\t\t__device_release_driver(dev, parent);\n+\t\tdetached = true;\n+\t}\n+\t__device_driver_unlock(dev, parent);\n+\n+\tif (detached) {\n+\t\t/\n+\t\t * device_attach() must run with the parent locked on buses\n+\t\t * that require it, mirroring bus_rescan_devices_helper().\n+\t\t /\n+\t\tif (parent \u0026\u0026 dev-\u003ebus-\u003eneed_parent_lock)\n+\t\t\tdevice_lock(parent);\n+\t\tif (device_attach(dev) \u003c 0)\n+\t\t\tdev_err(dev, \"re-probe failed, device left unbound\\n\");\n+\t\tif (parent \u0026\u0026 dev-\u003ebus-\u003eneed_parent_lock)\n+\t\t\tdevice_unlock(parent);\n+\t}\n+\n+\tput_device(dev);\n+\tput_device(parent);\n+\tkfree(rp);\n+}\n+\n+/\n+ device_schedule_reprobe - schedule a deferred detach and re-probe\n+ * @dev: device to detach and re-probe\n+ * @delay_ms: delay in milliseconds before the re-probe runs\n+ \n+ Schedule a detach and re-probe of @dev after @delay_ms milliseconds.\n+ * The re-probe is skipped if, by the time the scheduled work runs, the\n+ * device has been removed, the system shutdown sequence has reached the\n+ * device, or @dev is no longer bound to the driver that was bound at\n+ * scheduling time. In particular an administrative unbind is never\n+ * undone by a stale re-probe.\n+ \n+ The work function is built-in text, so the bound driver may call this\n+ * from its own code without holding a module reference. If the driver\n+ * module is unloaded before the work runs, driver unregistration unbinds\n+ * @dev first and the scheduled work does nothing.\n+ \n+ Multiple pending re-probes for the same device are individually safe;\n+ * a caller that wants at most one pending re-probe must gate scheduling\n+ * itself.\n+ \n+ May only be called from process context.\n+ \n+ Returns: 0 on success, -EINVAL if @dev is not a registered device\n+ * bound to a driver, -ENOMEM on allocation failure.\n+ /\n+int device_schedule_reprobe(struct device dev, unsigned int delay_ms)\n+{\n+\tstruct device_reprobe rp;\n+\n+\tif (!dev-\u003ebus \|\| !dev-\u003ep \|\| !device_is_registered(dev))\n+\t\treturn -EINVAL;\n+\tif (!dev-\u003edriver)\n+\t\treturn -EINVAL;\n+\n+\trp = kzalloc_obj(rp);\n+\tif (!rp)\n+\t\treturn -ENOMEM;\n+\n+\trp-\u003edev = get_device(dev);\n+\t/\n+\t Pin the parent too: the work locks it, and an unregister of @dev\n+\t * would otherwise drop the last reference before the work runs.\n+\t /\n+\trp-\u003eparent = get_device(dev-\u003eparent);\n+\trp-\u003edrv = READ_ONCE(dev-\u003edriver);\n+\tINIT_DELAYED_WORK(\u0026rp-\u003ework, device_reprobe_work_fn);\n+\tqueue_delayed_work(system_dfl_wq, \u0026rp-\u003ework,\n+\t\t\t msecs_to_jiffies(delay_ms));\n+\n+\treturn 0;\n+}\n+EXPORT_SYMBOL_GPL(device_schedule_reprobe);\ndiff --git a/drivers/net/dsa/mxl862xx/Makefile b/drivers/net/dsa/mxl862xx/Makefile\nindex a7be0e6669dfa..bccac0d0f703f 100644\n--- a/drivers/net/dsa/mxl862xx/Makefile\n+++ b/drivers/net/dsa/mxl862xx/Makefile\n@@ -1,3 +1,3 @@\n # SPDX-License-Identifier: GPL-2.0\n obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o\n-mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o\n+mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-api.h b/drivers/net/dsa/mxl862xx/mxl862xx-api.h\nindex a180a5decffc0..6f771895984cb 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-api.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-api.h\n@@ -1224,6 +1224,16 @@ struct mxl862xx_sys_fw_image_version {\n \t__le32 iv_build_num;\n } __packed;\n \n+/\n+ struct mxl862xx_sys_reg_rw - System register read/write\n+ * @addr: 32-bit register address\n+ * @val: register value\n+ /\n+struct mxl862xx_sys_reg_rw {\n+\t__le32 addr;\n+\t__le32 val;\n+} __packed;\n+\n /\n enum mxl862xx_port_type - Port Type\n * @MXL862XX_LOGICAL_PORT: Logical Port\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\nindex c87a955c13c48..a865425aa61e1 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\n@@ -70,7 +70,9 @@\n #define INT_GPHY_READ\t\t\t(GPY_GPY2XX_MAGIC + 0x1)\n #define INT_GPHY_WRITE\t\t\t(GPY_GPY2XX_MAGIC + 0x2)\n \n+#define SYS_MISC_FW_UPDATE\t\t(SYS_MISC_MAGIC + 0x1)\n #define SYS_MISC_FW_VERSION\t\t(SYS_MISC_MAGIC + 0x2)\n+#define SYS_MISC_REG_RD\t\t\t(SYS_MISC_MAGIC + 0x8)\n \n #define MXL862XX_XPCS_PCS_CONFIG\t(MXL862XX_XPCS_MAGIC + 0x1)\n #define MXL862XX_XPCS_PCS_GET_STATE\t(MXL862XX_XPCS_MAGIC + 0x2)\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.c b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c\nnew file mode 100644\nindex 0000000000000..1de8d9970a369\n--- /dev/null\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c\n@@ -0,0 +1,1062 @@\n+// SPDX-License-Identifier: GPL-2.0-or-later\n+/\n+ Firmware flash and devlink support for MaxLinear MxL862xx\n+ \n+ Copyright (C) 2025 Daniel Golle \u003cdaniel@makrotopia.org\u003e\n+ \n+ SB PDI - firmware download interface over clause-22 SMDIO\n+ * =========================================================\n+ \n+ The MxL862xx MCUboot loader accepts a firmware image through four \"SB PDI\"\n+ * registers in the switch SMDIO register space. It runs whenever no WSP\n+ * firmware is active: the normal firmware update enters it deliberately - the\n+ * SYS_MISC_FW_UPDATE API command sets a sticky rescue bit and reboots into\n+ * MCUboot - and the loader also stays here when the stored WSP firmware fails\n+ * its boot-time integrity check. This driver drives the loader's 0xc55c\n+ * \"console\" download path.\n+ \n+ SMDIO register access (mxl862xx_smdio_read/write):\n+ * MII reg 0x1f := (\u003csb_pdi_reg\u003e \u0026 0xfff0) ; page latch\n+ * MII reg (\u003csb_pdi_reg\u003e \u0026 0x000f) := / =\u003e \u003cu16 data\u003e\n+ * so CTRL/ADDR/DATA/STAT (0xe100..0xe103) are MII regs 0/1/2/3 of page\n+ * 0xe100, not all reg 0x00.\n+ \n+ SB PDI registers (host name/addr -\u003e MCU mailbox):\n+ * CTRL 0xe100 -\u003e 0xc0938400 mode: RST=0x00 RD=0x01 WR=0x02\n+ * ADDR 0xe101 -\u003e 0xc0938404 SB target word address (SB1 bank = 0x7800)\n+ * DATA 0xe102 -\u003e 0xc0938408 16-bit data / reply word\n+ * STAT 0xe103 -\u003e 0xc093840c handshake: a magic (below) or a byte count\n+ \n+ STAT magics:\n+ * READY 0xc55c loader idle in the console loop (this driver)\n+ * DL_RDY 0xc33c loader idle in the flashless loop\n+ * START 0xf48f host -\u003e begin download session\n+ * ACK 0xf490 loader -\u003e START acknowledged (START + 1)\n+ * END 0x3cc3 host -\u003e finalise now (optional, see below)\n+ * RDREG 0xe2c0 host -\u003e register-read command (\| index), see below\n+ \n+ Console flash path (STAT=0xc55c) - mxl862xx_flash_firmware():\n+ \n+ host loader\n+ * ---- ------\n+ * reset (CTRL=ADDR=DATA=0)\n+ * read STAT ............................ 0xc55c (READY, idle)\n+ * STAT := START(0xf48f) --------------\u003e\n+ * \u003c-------------- STAT = 0xf490 (ACK)\n+ * CTRL := WR\n+ * DATA := hdr[0..9] (20-byte header: type,size1,crc1,size2,crc2)\n+ * reset; STAT := 20 (header len) -----\u003e parse hdr; r_remain=size1+size2;\n+ * ERASE target region(s)\n+ * \u003c-------------- STAT=21 (len+1), then STAT=0\n+ * (erased)\n+ * -- payload, streamed in slices: --\n+ * CTRL := WR\n+ * DATA := word x N ...\n+ * at word 16384: CTRL:=RST; ADDR:=0x7800; CTRL:=WR (half-bank -\u003e SB1)\n+ * at word 32760: flush slice:\n+ * reset; STAT := \u003cbytes_this_slice\u003e ---\u003e r_remain -= bytes; program\n+ * \u003c------------------- STAT=0 (ready for next slice)\n+ * ... repeat until the whole payload is sent ...\n+ * \u003c------------------- STAT=0 image verified\n+ * (STAT=1: image rejected)\n+ * STAT := END(0x3cc3) ---------------------\u003e finalise and boot\n+ \n+ The r_remain == 0 rule (critical):\n+ * Every host STAT write in the payload phase is a byte count; the loader\n+ * does r_remain -= count and stays in the receive loop while r_remain != 0.\n+ * It leaves the loop ONLY when r_remain hits EXACTLY 0, and a count larger\n+ * than r_remain underflows the 32-bit counter and wedges the loader until a\n+ * power cycle. Having left it, the loader verifies the image, publishes the\n+ * verdict in STAT (0 good, 1 rejected) and waits 2 s for END before\n+ * finalising regardless -- clearing its rescue-enable bit so boot_go boots\n+ * the new image -- so END only saves that wait. Hence:\n+ * - never send a slice/chunk count larger than what is outstanding;\n+ * - a STAT write is a command only once the loader has left the loop;\n+ * - the loader leaves the count in STAT while it programs the chunk, so\n+ * a lingering count does not distinguish \"busy\" from \"verdict\";\n+ * - interrupted-download recovery feeds 1 byte at a time (see below).\n+ \n+ Interrupted-flash recovery (mxl862xx_rescue_drain):\n+ * A host that dies mid-payload leaves the loader in the receive loop holding\n+ * STAT=0. Feed single 1-byte chunks (one DATA word + STAT=1) until r_remain\n+ * reaches 0; the loader then verifies the (now corrupt) image, publishes its\n+ * verdict and comes back to READY by itself. END is never sent here: while\n+ * r_remain is non-zero it would be consumed as a 15555-byte count, and a\n+ * lingering STAT=1 cannot be told from a chunk still being programmed.\n+ \n+ Register-read challenge (non-destructive liveness proof):\n+ * DATA := 0x7c23 (marker); STAT := 0xe2c0\|idx\n+ * -\u003e loader returns a runtime word in DATA and re-arms STAT=0xc55c.\n+ * The reply source is loader BSS, not a chip id; used only to prove a live\n+ * mailbox in mxl862xx_rescue_mode_detect().\n+ \n+ The other STAT ready magic, 0xc33c, marks the loader's flashless\n+ * chip-to-chip download mode (MxL86281S 16-port tier); this driver does not\n+ * use it.\n+ \n+ Rescue lifecycle (devlink): probe runs mxl862xx_rescue_mode_detect(); a\n+ * wedged loader is drained back to READY by a background self-heal\n+ * (rescue_heal_work), so the long recovery never holds the devlink lock.\n+ * devlink dev info exposes the fw version (the \"flashable\" signal) only once at\n+ * READY; flash_update returns -EBUSY until then, and reprobes to WSP firmware\n+ * on success.\n+ \n+ Notes:\n+ * - Chip id/revision (0xc0d28884/88) are NOT reachable on this channel; they\n+ * need the clause-45 MMD firmware mailbox, which is dead under MCUboot.\n+ * Rescue identity is by SB PDI behaviour only (mxl862xx_rescue_mode_detect).\n+ * - The SMDIO PHY address comes from the device tree; the 0xe1xx register\n+ * offsets are the OTP reset defaults and the only layout supported here.\n+ /\n+\n+#include \u003clinux/crc32.h\u003e\n+#include \u003clinux/delay.h\u003e\n+#include \u003clinux/device.h\u003e\n+#include \u003clinux/iopoll.h\u003e\n+#include \u003clinux/netdevice.h\u003e\n+#include \u003clinux/overflow.h\u003e\n+#include \u003clinux/rtnetlink.h\u003e\n+#include \u003clinux/workqueue.h\u003e\n+#include \u003cnet/dsa.h\u003e\n+#include \u003cnet/switchdev.h\u003e\n+\n+#include \"mxl862xx.h\"\n+#include \"mxl862xx-api.h\"\n+#include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n+#include \"mxl862xx-host.h\"\n+\n+/ SB PDI registers (clause-22 SMDIO address space) /\n+#define MXL862XX_SB_PDI_CTRL\t\t0xe100\n+#define MXL862XX_SB_PDI_ADDR\t\t0xe101\n+#define MXL862XX_SB_PDI_DATA\t\t0xe102\n+#define MXL862XX_SB_PDI_STAT\t\t0xe103\n+\n+/ SB PDI CTRL modes /\n+#define MXL862XX_SB_PDI_CTRL_RST\t0x00\n+#define MXL862XX_SB_PDI_CTRL_WR\t\t0x02\n+\n+/ SB PDI handshake magic (published/consumed via STAT) /\n+#define MXL862XX_SB_PDI_READY\t\t0xc55c\t/ loader idle, console loop /\n+#define MXL862XX_SB_PDI_DL_READY\t0xc33c\t/ loader idle, flashless loop /\n+#define MXL862XX_SB_PDI_START\t\t0xf48f\n+#define MXL862XX_SB_PDI_END\t\t0x3cc3\n+#define MXL862XX_SB_PDI_RDREG\t\t0xe2c0\t/ register-read cmd (\| index) /\n+#define MXL862XX_SB_PDI_RDREG_MARK\t0x7c23\t/ marker placed in DATA for RDREG /\n+\n+/ Behavioural presence probe: two distinct 16-bit latches on ADDR/DATA. /\n+#define MXL862XX_SB_PDI_PROBE_A\t\t0x5a5a\n+#define MXL862XX_SB_PDI_PROBE_D\t\t0xa5a5\n+\n+/ Image verification verdict published in STAT once the receive loop ends /\n+#define MXL862XX_SB_PDI_VERIFY_OK\t0\n+#define MXL862XX_SB_PDI_VERIFY_BAD\t1\n+\n+/ Firmware transfer geometry /\n+#define MXL862XX_FW_HDR_SIZE\t\t20\n+#define MXL862XX_FW_BANK_HALF\t\t16384\t/ words per half-bank /\n+#define MXL862XX_FW_BANK_SLICE\t\t32760\t/ words per full slice /\n+#define MXL862XX_FW_SB1_ADDR\t\t0x7800\t/ SB1 word address /\n+\n+/ Timeouts (generous upper bounds) /\n+#define MXL862XX_FW_READY_TIMEOUT_MS\t3000\n+#define MXL862XX_FW_ACK_TIMEOUT_MS\t5000\n+#define MXL862XX_FW_ERASE_TIMEOUT_MS\t300000\n+#define MXL862XX_FW_WRITE_TIMEOUT_MS\t60000\n+#define MXL862XX_FW_REBOOT_DELAY_MS\t5000\n+#define MXL862XX_FW_REPROBE_DELAY_MS\t500\n+/ One loader mailbox step: program a 1-byte chunk or service a command /\n+#define MXL862XX_SB_PDI_STEP_MS\t\t2000\n+/ Covers the loader's END wait, verification and the reset into READY /\n+#define MXL862XX_SB_PDI_VERIFY_MS\t15000\n+\n+static int mxl862xx_sb_pdi_reset(struct mxl862xx_priv priv)\n+{\n+\tint ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_RST);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_RST);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\treturn mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_RST);\n+}\n+\n+static int mxl862xx_sb_pdi_poll_stat(struct mxl862xx_priv priv, u16 expected,\n+\t\t\t\t unsigned long timeout_ms)\n+{\n+\tint ret, val;\n+\n+\tret = read_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t\tval \u003c 0 \|\| (u16)val == expected,\n+\t\t\t\t10000, timeout_ms 1000, false,\n+\t\t\t\tpriv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\treturn ret;\n+}\n+\n+static int mxl862xx_sb_pdi_flush_slice(struct mxl862xx_priv priv,\n+\t\t\t\t u32 data_written)\n+{\n+\tint ret;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\treturn mxl862xx_sb_pdi_poll_stat(priv, 0,\n+\t\t\t\t\t MXL862XX_FW_WRITE_TIMEOUT_MS);\n+}\n+\n+/ Flush the last slice, which ends the receive loop: the loader verifies the\n+ * image and replaces the count in STAT with its verdict, so wait for the count\n+ * to go rather than for a fixed value.\n+ /\n+static int mxl862xx_sb_pdi_flush_last(struct mxl862xx_priv priv,\n+\t\t\t\t u32 data_written)\n+{\n+\tint ret, val;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = read_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t\tval \u003c 0 \|\| (u16)val != (u16)data_written,\n+\t\t\t\t10000, (MXL862XX_FW_WRITE_TIMEOUT_MS +\n+\t\t\t\t\tMXL862XX_SB_PDI_VERIFY_MS) * 1000,\n+\t\t\t\tfalse, priv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\n+\tif (!ret \u0026\u0026 (u16)val == MXL862XX_SB_PDI_VERIFY_OK)\n+\t\treturn 0;\n+\n+\t/* A final count of 1 is indistinguishable from the reject verdict, so\n+\t * a timeout still holding it lands here too.\n+\t /\n+\tif ((u16)val == MXL862XX_SB_PDI_VERIFY_BAD) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: loader rejected the image\\n\");\n+\t\treturn -EBADMSG;\n+\t}\n+\n+\treturn ret ? ret : -EPROTO;\n+}\n+\n+static void mxl862xx_flash_notify(struct devlink dl, const char status,\n+\t\t\t\t u32 done, u32 total)\n+{\n+\tdevlink_flash_update_status_notify(dl, status, NULL, done, total);\n+}\n+\n+/ Byte-count of each chunk fed to the loader during drain. It MUST be 1: the\n+ * loader only lets us observe \"counter == 0\", never \"counter \u003c step\", so any\n+ * step \u003e 1 can subtract past zero, underflow the 32-bit counter and wedge the\n+ * loader for ~2^32 more bytes (a state only a power cycle clears). Stepping by\n+ * 1 walks the counter through every value and is guaranteed to land on zero\n+ * whatever its (possibly odd) start. A 1-byte chunk is a path the loader\n+ * already handles: the normal transfer ends with a single trailing byte for\n+ * odd-sized images (see Step 6).\n+ /\n+#define MXL862XX_DRAIN_CHUNK_BYTES\t1\n+\n+/ Log the drain's progress every so many bytes; it can run for a long time /\n+#define MXL862XX_DRAIN_LOG_BYTES\t(128 1024)\n+\n+/* Wait for the loader to ask for the next chunk (STAT 0) or to come back to its\n+ * command loop (STAT READY), and return the STAT value either way. On timeout\n+ * that is whatever STAT still holds, which carries no further information: the\n+ * loader keeps the count we wrote visible while it programs the chunk, and that\n+ * is the same value it publishes as the \"image rejected\" verdict once the\n+ * counter reaches zero.\n+ \n+ STAT 0 is unambiguous here even though it is also the \"image verified\"\n+ * verdict: by the r_remain == 0 rule the loader leaves the receive loop the\n+ * moment the counter reaches zero, so it is never both inside the loop asking\n+ * for a chunk and publishing a verdict. Once it has left, the next STAT write\n+ * is a command rather than a count, so feeding one more chunk after a verdict\n+ * cannot underflow anything either.\n+ /\n+static int mxl862xx_sb_pdi_poll_drain(struct mxl862xx_priv priv,\n+\t\t\t\t unsigned long timeout_ms)\n+{\n+\tint val;\n+\n+\tread_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t val \u003c 0 \|\| (u16)val == MXL862XX_SB_PDI_READY \|\|\n+\t\t\t (u16)val == 0,\n+\t\t\t 50, timeout_ms * 1000, false,\n+\t\t\t priv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\treturn (u16)val;\n+}\n+\n+/* The loader is not asking for a chunk: it may still be programming the last\n+ * one, or the counter has reached zero and it is verifying the image and\n+ * resetting into READY. Wait that out -- STAT cannot tell the two apart, and\n+ * guessing would mean writing END into a live receive loop.\n+ \n+ Return: 0 once the loader has left the loop, -EAGAIN if it asks for another\n+ * chunk after all, -EIO for a loader still holding the count when the verify\n+ * window expires, or an SMDIO bus error.\n+ /\n+static int mxl862xx_rescue_drain_finish(struct mxl862xx_priv priv, u32 chunk)\n+{\n+\tstruct device dev = \u0026priv-\u003emdiodev-\u003edev;\n+\tint stat;\n+\n+\tstat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_VERIFY_MS);\n+\tif (stat \u003c 0)\n+\t\treturn stat;\n+\tif (stat == MXL862XX_SB_PDI_READY)\n+\t\treturn 0;\n+\tif (stat == MXL862XX_SB_PDI_VERIFY_BAD) {\n+\t\tdev_err(dev,\n+\t\t\t\"flash: loader stuck after %u chunks, power cycle it\\n\",\n+\t\t\tchunk);\n+\t\treturn -EIO;\n+\t}\n+\tif (stat) {\n+\t\t/ A firmware is answering, not the loader: an image survived\n+\t\t * in flash and booted.\n+\t\t /\n+\t\tdev_info(dev, \"flash: firmware booted while draining\\n\");\n+\t\treturn 0;\n+\t}\n+\n+\treturn -EAGAIN;\n+}\n+\n+/ Recover a switch whose SB PDI download was interrupted mid-transfer - the\n+ * host died after MCUboot began erasing flash, whether it aborted mid erase or\n+ * mid image-write, both end up in the same place: the payload receive loop.\n+ * There the loader publishes STAT=0, waits for the host to write a byte-count\n+ * to STAT, DMAs that many bytes and subtracts the count from a remaining-bytes\n+ * counter, leaving the loop only when the counter reaches exactly zero. The\n+ * image size died with the host, so we feed single-byte chunks (see\n+ * MXL862XX_DRAIN_CHUNK_BYTES) to walk the counter to zero without underflow.\n+ * The loader then verifies the (now corrupt) image and returns to READY by\n+ * itself, or boots a valid image that happened to survive in flash; either way\n+ * the caller's reprobe classifies the result. Every byte costs about a dozen\n+ * MDIO frames, so a multi-MiB outstanding count takes tens of minutes.\n+ * Returns 0 once the loader has left the receive loop, \u003c0 on error. Does NOT\n+ * recover a counter already underflowed by an earlier oversized-chunk attempt\n+ * - that needs a power cycle.\n+ /\n+static int mxl862xx_rescue_drain(struct mxl862xx_priv priv)\n+{\n+\tstruct device dev = \u0026priv-\u003emdiodev-\u003edev;\n+\t/ Bound: twice the loader's 16 MiB image cap, one byte per chunk. /\n+\tu32 max_chunks = 2u (16u \u003c\u003c 20) / MXL862XX_DRAIN_CHUNK_BYTES;\n+\tu32 chunk = 0;\n+\tint ret, stat;\n+\n+\twhile (chunk \u003c max_chunks) {\n+\t\t/* Teardown can interrupt this long drain. /\n+\t\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\t\treturn -ECANCELED;\n+\n+\t\tstat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);\n+\t\tif (stat \u003c 0)\n+\t\t\treturn stat;\n+\t\tif (stat == MXL862XX_SB_PDI_READY)\n+\t\t\treturn 0;\n+\n+\t\tif (stat) {\n+\t\t\tret = mxl862xx_rescue_drain_finish(priv, chunk);\n+\t\t\tif (ret != -EAGAIN)\n+\t\t\t\treturn ret;\n+\t\t}\n+\n+\t\t/ Feed one zero byte; reset cleared the write latch. /\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_sb_pdi_reset(priv);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t\t MXL862XX_DRAIN_CHUNK_BYTES);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tchunk++;\n+\t\tif (!(chunk % MXL862XX_DRAIN_LOG_BYTES))\n+\t\t\tdev_info(dev, \"flash: drained %u KiB so far\\n\",\n+\t\t\t\t chunk / 1024);\n+\t\tcond_resched();\n+\t}\n+\n+\tdev_err(dev,\n+\t\t\"flash: interrupted download did not drain after %u chunks\\n\",\n+\t\tchunk);\n+\n+\treturn -ETIMEDOUT;\n+}\n+\n+/ Background self-heal: drain a wedged download off the devlink flash path, so\n+ * the long recovery never holds the devlink lock. Scheduled from probe;\n+ * reprobes on success so the probe-time detection re-classifies the switch.\n+ /\n+void mxl862xx_rescue_heal_work_fn(struct work_struct work)\n+{\n+\tstruct mxl862xx_priv priv =\n+\t\tcontainer_of(work, struct mxl862xx_priv, rescue_heal_work);\n+\tstruct device dev = \u0026priv-\u003emdiodev-\u003edev;\n+\tint ret;\n+\n+\tret = mxl862xx_rescue_drain(priv);\n+\tif (ret == -ECANCELED)\n+\t\treturn;\n+\tif (ret) {\n+\t\t/* Nothing retries this, so say so: rescue_ready stays clear\n+\t\t * and devlink dev flash reports why it refuses.\n+\t\t /\n+\t\tdev_err(dev, \"flash: download recovery failed: %pe\\n\",\n+\t\t\tERR_PTR(ret));\n+\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n+\t\treturn;\n+\t}\n+\n+\t/ The interrupted transfer is finalised; reprobe so the probe-time\n+\t * detection brings the driver up -- flashable in rescue mode if the\n+\t * loader is at READY, or normally if a valid image booted. The core\n+\t * skips the re-probe on its own if the device is unbound first; the\n+\t * flag test only avoids scheduling one certain to be skipped. A\n+\t * failed hand-off leaves nothing to reclassify the switch, so mark\n+\t * recovery failed rather than promise a retry that cannot succeed.\n+\t /\n+\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\treturn;\n+\n+\tif (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS))\n+\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n+}\n+\n+/ Detect MCUboot rescue mode over clause-22 SMDIO alone, so the caller can rule\n+ * the loader out before any C45 API request (which spews CRC errors when no WSP\n+ * firmware answers). A scratch write to ADDR/DATA must latch or the chip is\n+ * absent (-ENODEV); the mailbox is reset first, or a transfer interrupted with\n+ * CTRL=WR would take that write as a payload word instead of latching it. STAT\n+ * then classifies the state, poked destructively only when 0, the one value a\n+ * running firmware never holds:\n+ \n+ - 0xc33c: flashless loop; recognised but not supported here.\n+ * - 0xc55c: console loop, if the register-read challenge is serviced.\n+ * - other non-zero: running firmware, left unpoked.\n+ * - 0: wedged receive loop; the 1-byte slice-advance then says whether it\n+ * still needs draining or has just finished.\n+ \n+ The scratch write reaches a running firmware too, but lands in mailbox\n+ * registers it does not read, so it is inert there.\n+ \n+ Return: MXL862XX_IN_RESCUE, MXL862XX_NOT_RESCUE, -ENODEV when the scratch\n+ * write does not latch, which is a switch that does not answer at all or one\n+ * whose SB PDI window is not at the offsets above, -EOPNOTSUPP for the\n+ * flashless loop, -ENXIO for a READY loader whose mailbox fails the challenge,\n+ * or an SMDIO bus error.\n+ /\n+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv priv)\n+{\n+\tint stat, dat, ret, rb, a, d;\n+\n+\t/* rescue_ready gates flashing; a wedged loader needs the drain first. /\n+\tWRITE_ONCE(priv-\u003erescue_ready, false);\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\t/ Presence: a live chip latches the scratch write, an absent one floats. /\n+\ta = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t MXL862XX_SB_PDI_PROBE_A);\n+\tif (a \u003c 0)\n+\t\treturn a;\n+\td = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t MXL862XX_SB_PDI_PROBE_D);\n+\tif (d \u003c 0)\n+\t\treturn d;\n+\ta = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_ADDR);\n+\tif (a \u003c 0)\n+\t\treturn a;\n+\td = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);\n+\tif (d \u003c 0)\n+\t\treturn d;\n+\tif ((u16)a != MXL862XX_SB_PDI_PROBE_A \|\|\n+\t (u16)d != MXL862XX_SB_PDI_PROBE_D)\n+\t\treturn -ENODEV;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tstat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_STAT);\n+\tif (stat \u003c 0)\n+\t\treturn stat;\n+\n+\t/ Flashless-download loop (MxL86281S tier): this driver does not\n+\t * support it -- the console flash path expects READY. Treat it as an\n+\t * unusable configuration, like any other unsupported state.\n+\t /\n+\tif ((u16)stat == MXL862XX_SB_PDI_DL_READY)\n+\t\treturn -EOPNOTSUPP;\n+\n+\t/ Console loop at READY: confirm the live mailbox with the register-read\n+\t * challenge (consumes the marker from DATA and re-arms READY).\n+\t /\n+\tif ((u16)stat == MXL862XX_SB_PDI_READY) {\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t\t MXL862XX_SB_PDI_RDREG_MARK);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t\t MXL862XX_SB_PDI_RDREG);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\trb = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,\n+\t\t\t\t\t MXL862XX_SB_PDI_STEP_MS);\n+\t\tdat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);\n+\t\tret = mxl862xx_sb_pdi_reset(priv);\n+\t\t/ Never re-arming READY fails the challenge like any other\n+\t\t * unserviced command; report it as such rather than as a bus\n+\t\t * timeout the bus never saw.\n+\t\t /\n+\t\tif (rb == -ETIMEDOUT)\n+\t\t\trb = -ENXIO;\n+\t\tif (rb \u003c 0)\n+\t\t\treturn rb;\n+\t\tif (dat \u003c 0)\n+\t\t\treturn dat;\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tif ((u16)dat != MXL862XX_SB_PDI_RDREG_MARK) {\n+\t\t\tWRITE_ONCE(priv-\u003erescue_ready, true);\n+\t\t\treturn MXL862XX_IN_RESCUE;\n+\t\t}\n+\t\t/ READY but the marker is untouched, so nothing is servicing the\n+\t\t * mailbox. A firmware publishing 0xc55c as its status word looks\n+\t\t * exactly like this, and flashing one would be far worse than\n+\t\t * refusing to bind, so treat it as unusable.\n+\t\t /\n+\t\treturn -ENXIO;\n+\t}\n+\n+\t/ Any other non-zero value is a running firmware, not a loader. /\n+\tif (stat)\n+\t\treturn MXL862XX_NOT_RESCUE;\n+\n+\t/ STAT == 0: a wedged receive loop takes a 1-byte slice-advance (feed\n+\t * one DATA word first, like a drain chunk) and asks for the next chunk\n+\t * by publishing 0 again. Had that byte been the last one outstanding,\n+\t * the loader leaves the loop instead and returns to READY, having\n+\t * consumed the advance -- proof enough of a live mailbox to skip the\n+\t * challenge. Anything else means it is still working on it. All three\n+\t * are rescue, so this never fails probe; only the drain does.\n+\t /\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t MXL862XX_DRAIN_CHUNK_BYTES);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\trb = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);\n+\tif (rb \u003c 0)\n+\t\treturn rb;\n+\tif (rb == MXL862XX_SB_PDI_READY)\n+\t\tWRITE_ONCE(priv-\u003erescue_ready, true);\n+\n+\treturn MXL862XX_IN_RESCUE;\n+}\n+\n+/ MCUboot firmware image header /\n+struct mxl862xx_fw_hdr {\n+\t__le32 image_type;\n+\t__le32 image_size_1;\n+\t__le32 image_checksum_1;\n+\t__le32 image_size_2;\n+\t__le32 image_checksum_2;\n+} __packed;\n+\n+static int mxl862xx_flash_validate(struct mxl862xx_priv priv,\n+\t\t\t\t const struct firmware fw,\n+\t\t\t\t u32 payload_size)\n+{\n+\tconst struct mxl862xx_fw_hdr hdr;\n+\tu32 size1, size2, total;\n+\tconst u8 payload;\n+\tu32 crc;\n+\n+\tif (fw-\u003esize \u003c MXL862XX_FW_HDR_SIZE)\n+\t\treturn -EINVAL;\n+\n+\thdr = (const struct mxl862xx_fw_hdr )fw-\u003edata;\n+\tpayload = fw-\u003edata + MXL862XX_FW_HDR_SIZE;\n+\tsize1 = le32_to_cpu(hdr-\u003eimage_size_1);\n+\tsize2 = le32_to_cpu(hdr-\u003eimage_size_2);\n+\n+\tif (check_add_overflow(size1, size2, \u0026total) \|\|\n+\t total \u003e fw-\u003esize - MXL862XX_FW_HDR_SIZE) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: firmware file too small for declared size\\n\");\n+\t\treturn -EINVAL;\n+\t}\n+\n+\tif (!total) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: firmware file with empty payload\\n\");\n+\t\treturn -EINVAL;\n+\t}\n+\n+\tif (size1) {\n+\t\tcrc = ~crc32_le(~0U, payload, size1);\n+\t\tif (crc != le32_to_cpu(hdr-\u003eimage_checksum_1)) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: image 1 CRC mismatch (got %08x, expected %08x)\\n\",\n+\t\t\t\tcrc, le32_to_cpu(hdr-\u003eimage_checksum_1));\n+\t\t\treturn -EINVAL;\n+\t\t}\n+\t}\n+\n+\tif (size2) {\n+\t\tcrc = ~crc32_le(~0U, payload + size1, size2);\n+\t\tif (crc != le32_to_cpu(hdr-\u003eimage_checksum_2)) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: image 2 CRC mismatch (got %08x, expected %08x)\\n\",\n+\t\t\t\tcrc, le32_to_cpu(hdr-\u003eimage_checksum_2));\n+\t\t\treturn -EINVAL;\n+\t\t}\n+\t}\n+\n+\tpayload_size = total;\n+\n+\treturn 0;\n+}\n+\n+static int mxl862xx_flash_firmware(struct mxl862xx_priv priv,\n+\t\t\t\t const struct firmware fw,\n+\t\t\t\t u32 payload_size, struct devlink dl)\n+{\n+\tconst u8 payload = fw-\u003edata + MXL862XX_FW_HDR_SIZE;\n+\tu32 word_idx = 0, data_written = 0, idx = 0;\n+\tunsigned long next_notify = jiffies - 1;\n+\tu16 word, fdata;\n+\tint ret, i;\n+\n+\t/* Step 1: reboot the firmware into MCUboot rescue mode /\n+\tif (!priv-\u003erescue_mode) {\n+\t\tret = mxl862xx_api_wrap(priv, SYS_MISC_FW_UPDATE, NULL, 0,\n+\t\t\t\t\tfalse, false);\n+\t\tif (ret) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: FW_UPDATE command failed: %pe\\n\",\n+\t\t\t\tERR_PTR(ret));\n+\t\t\treturn ret;\n+\t\t}\n+\t}\n+\n+\t/ Step 2: wait for bootloader ready /\n+\tmxl862xx_flash_notify(dl, \"Waiting for bootloader\", 0, 0);\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/ Failures from here on end up at no_end, which returns the error\n+\t * without signalling END -- see there.\n+\t /\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,\n+\t\t\t\t\tMXL862XX_FW_READY_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: bootloader not ready: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/ Step 3: start handshake /\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t MXL862XX_SB_PDI_START);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_START + 1,\n+\t\t\t\t\tMXL862XX_FW_ACK_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: start handshake failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/ Step 4: transfer image header /\n+\tmxl862xx_flash_notify(dl, \"Erasing flash\", 0, 0);\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\tfor (i = 0; i \u003c MXL862XX_FW_HDR_SIZE / 2; i++) {\n+\t\tword = fw-\u003edata[i 2] \|\n+\t\t ((u16)fw-\u003edata[i * 2 + 1] \u003c\u003c 8);\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, word);\n+\t\tif (ret \u003c 0)\n+\t\t\tgoto write_err;\n+\t}\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/* the byte count in STAT triggers the erase /\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t MXL862XX_FW_HDR_SIZE);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/ ACK is byte count + 1 /\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_FW_HDR_SIZE + 1,\n+\t\t\t\t\tMXL862XX_FW_ACK_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: header ACK failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/ Step 5: wait for erase to complete /\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, 0,\n+\t\t\t\t\tMXL862XX_FW_ERASE_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: erase timeout: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/ Step 6: transfer payload /\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\twhile (idx \u003c payload_size) {\n+\t\tcond_resched();\n+\t\tif (idx + 1 \u003c payload_size) {\n+\t\t\tfdata = payload[idx] \|\n+\t\t\t\t((u16)payload[idx + 1] \u003c\u003c 8);\n+\t\t\tidx += 2;\n+\t\t\tdata_written += 2;\n+\t\t} else {\n+\t\t\tfdata = payload[idx];\n+\t\t\tidx++;\n+\t\t\tdata_written++;\n+\t\t}\n+\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, fdata);\n+\t\tif (ret \u003c 0)\n+\t\t\tgoto write_err;\n+\t\tword_idx++;\n+\n+\t\tif (idx \u003e= payload_size) {\n+\t\t\tret = mxl862xx_sb_pdi_flush_last(priv, data_written);\n+\t\t\tbreak;\n+\t\t}\n+\n+\t\t/ Half-bank boundary: switch to SB1 address /\n+\t\tif (word_idx == MXL862XX_FW_BANK_HALF) {\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t MXL862XX_SB_PDI_CTRL_RST);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t\t\t MXL862XX_FW_SB1_ADDR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\t\t} else if (word_idx \u003e= MXL862XX_FW_BANK_SLICE) {\n+\t\t\tret = mxl862xx_sb_pdi_flush_slice(priv, data_written);\n+\t\t\tif (ret) {\n+\t\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\t\"flash: write timeout at %u/%u: %pe\\n\",\n+\t\t\t\t\tidx, payload_size, ERR_PTR(ret));\n+\t\t\t\tgoto no_end;\n+\t\t\t}\n+\t\t\tword_idx = 0;\n+\t\t\tdata_written = 0;\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t MXL862XX_SB_PDI_CTRL_WR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tif (time_after(jiffies, next_notify)) {\n+\t\t\t\tmxl862xx_flash_notify(dl, \"Flashing\", idx,\n+\t\t\t\t\t\t payload_size);\n+\t\t\t\tnext_notify = jiffies + msecs_to_jiffies(500);\n+\t\t\t}\n+\t\t}\n+\t}\n+\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: final slice failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\tmxl862xx_flash_notify(dl, \"Flashing\", payload_size, payload_size);\n+\n+\t/ Success: the loader has left the receive loop at r_remain == 0 and\n+\t * verified the image, so END(0x3cc3) is a finalise/boot request rather\n+\t * than a byte count. Signal it here -- and only here -- to boot the new\n+\t * image without waiting out the loader's 2 s END timeout.\n+\t /\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t MXL862XX_SB_PDI_END);\n+\tmsleep(MXL862XX_FW_REBOOT_DELAY_MS);\n+\treturn ret;\n+\n+write_err:\n+\tdev_err(\u0026priv-\u003emdiodev-\u003edev, \"flash: SMDIO write failed: %pe\\n\",\n+\t\tERR_PTR(ret));\n+no_end:\n+\t/ A failure leaves the loader mid transfer; do not signal END (a STAT\n+\t * write is a byte count then, and END would be misread as one, risking\n+\t * a receive-counter underflow). Return the error; the caller reprobes.\n+\t /\n+\treturn ret;\n+}\n+\n+int mxl862xx_devlink_info_get(struct dsa_switch ds,\n+\t\t\t struct devlink_info_req req,\n+\t\t\t struct netlink_ext_ack extack)\n+{\n+\tstruct mxl862xx_priv priv = ds-\u003epriv;\n+\tchar buf[16];\n+\tint ret;\n+\n+\t/ No chip-id/revision in MCUboot (needs the firmware MMD mailbox). The\n+\t * fw version doubles as the \"ready to flash\" signal: report it only\n+\t * once the loader is at a clean READY, nothing while still draining.\n+\t /\n+\tif (priv-\u003erescue_mode) {\n+\t\tif (!READ_ONCE(priv-\u003erescue_ready))\n+\t\t\treturn 0;\n+\n+\t\tsnprintf(buf, sizeof(buf), \"%u.%u.%u\",\n+\t\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t\t priv-\u003efw_version.revision);\n+\t\tret = devlink_info_version_running_put(req,\n+\t\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\t\treturn devlink_info_version_stored_put(req,\n+\t\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\t}\n+\n+\t/ A 0 part number means the CHIP ID read failed or the part is\n+\t * unfused; omit it rather than publish a bogus \"0000\" that fwupd\n+\t * would match firmware against -- it then falls back to the driver\n+\t * name.\n+\t /\n+\tif (priv-\u003easic_id) {\n+\t\tsnprintf(buf, sizeof(buf), \"%04X\", priv-\u003easic_id);\n+\t\tret = devlink_info_version_fixed_put(req,\n+\t\t\t\t\t\t DEVLINK_INFO_VERSION_GENERIC_ASIC_ID,\n+\t\t\t\t\t\t buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\n+\t\tsnprintf(buf, sizeof(buf), \"%u\", priv-\u003easic_rev);\n+\t\tret = devlink_info_version_fixed_put(req,\n+\t\t\t\t\t\t DEVLINK_INFO_VERSION_GENERIC_ASIC_REV,\n+\t\t\t\t\t\t buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\t}\n+\n+\t/ An all-zero version is the cache a failed flash left behind, not a\n+\t * released firmware; omit it like the part number above.\n+\t /\n+\tif (!priv-\u003efw_version.major \u0026\u0026 !priv-\u003efw_version.minor \u0026\u0026\n+\t !priv-\u003efw_version.revision)\n+\t\treturn 0;\n+\n+\tsnprintf(buf, sizeof(buf), \"%u.%u.%u\",\n+\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t priv-\u003efw_version.revision);\n+\n+\tret = devlink_info_version_running_put(req,\n+\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\tif (ret)\n+\t\treturn ret;\n+\n+\t/ boots this image from its own flash: stored == running /\n+\treturn devlink_info_version_stored_put(req,\n+\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+}\n+\n+int mxl862xx_devlink_flash_update(struct dsa_switch ds,\n+\t\t\t\t struct devlink_flash_update_params params,\n+\t\t\t\t struct netlink_ext_ack extack)\n+{\n+\tstruct mxl862xx_priv priv = ds-\u003epriv;\n+\tstruct dsa_port dp;\n+\tu32 payload_size;\n+\tint ret, err, i;\n+\n+\tif (params-\u003ecomponent) {\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"component is not supported\");\n+\t\treturn -EOPNOTSUPP;\n+\t}\n+\n+\t/* A previous flash is still waiting for its reprobe: the firmware API\n+\t * is short-circuited, so the raw SB PDI writes below would run against\n+\t * a switch this driver no longer tracks.\n+\t /\n+\tif (priv-\u003eskip_teardown) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t \"device is reinitializing, retry later\");\n+\t\treturn -EBUSY;\n+\t}\n+\n+\tret = mxl862xx_flash_validate(priv, params-\u003efw, \u0026payload_size);\n+\tif (ret) {\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"firmware image validation failed\");\n+\t\treturn ret;\n+\t}\n+\n+\t/ Refuse to flash while the background self-heal is still draining, and\n+\t * for good once it has given up on the loader.\n+\t /\n+\tif (READ_ONCE(priv-\u003erescue_failed)) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t \"download recovery failed, power cycle the switch\");\n+\t\treturn -EIO;\n+\t}\n+\n+\tif (priv-\u003erescue_mode \u0026\u0026 !READ_ONCE(priv-\u003erescue_ready)) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t \"switch is recovering an interrupted download, retry shortly\");\n+\t\treturn -EBUSY;\n+\t}\n+\n+\tif (priv-\u003erescue_mode)\n+\t\tdev_info(ds-\u003edev,\n+\t\t\t \"flash: flashing switch via MCUboot rescue mode\\n\");\n+\telse\n+\t\tdev_info(ds-\u003edev, \"flash: running firmware %u.%u.%u\\n\",\n+\t\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t\t priv-\u003efw_version.revision);\n+\n+\t/ Close ports while the firmware is still alive so the DSA core's\n+\t * MDB/FDB tracking is drained, and detach user ports so userspace\n+\t * cannot reopen them during the flash. The conduit is only closed,\n+\t * not detached: it belongs to the MAC driver. This driver binds a\n+\t * single switch with a direct host link and no cascade ports, so the\n+\t * conduit serves only this switch, and flashing it reboots the switch,\n+\t * which takes the tree down regardless.\n+\t /\n+\trtnl_lock();\n+\tdsa_switch_for_each_user_port(dp, ds) {\n+\t\tif (dp-\u003euser) {\n+\t\t\tdev_close(dp-\u003euser);\n+\t\t\tnetif_device_detach(dp-\u003euser);\n+\t\t}\n+\t}\n+\tdsa_switch_for_each_cpu_port(dp, ds)\n+\t\tdev_close(dp-\u003econduit);\n+\t/ The bridge defers the STP state changes triggered by closing\n+\t * the ports; let them reach the firmware while it is still alive.\n+\t /\n+\tswitchdev_deferred_process();\n+\trtnl_unlock();\n+\n+\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n+\tpriv-\u003eblock_host = true;\n+\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\tset_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags);\n+\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n+\tcancel_work_sync(\u0026priv-\u003ecrc_err_work);\n+\tfor (i = 0; i \u003c ds-\u003enum_ports; i++)\n+\t\tcancel_work_sync(\u0026priv-\u003eports[i].host_flood_work);\n+\n+\tret = mxl862xx_flash_firmware(priv, params-\u003efw, payload_size,\n+\t\t\t\t ds-\u003edevlink);\n+\tif (ret)\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"firmware transfer failed\");\n+\n+\tif (!ret) {\n+\t\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock,\n+\t\t\t\t MDIO_MUTEX_NESTED);\n+\t\t/ Keep block_host set so host writes stay blocked, but let the\n+\t\t * readiness poll below read the freshly booted firmware.\n+\t\t /\n+\t\tpriv-\u003eflash_reading = true;\n+\t\tpriv-\u003erescue_mode = false;\n+\t\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\t\t/ Refresh the cached versions so the flash update only\n+\t\t * completes once the new firmware is confirmed running and\n+\t\t * devlink dev info reports it. Must happen before setting\n+\t\t * skip_teardown, which discards all firmware API reads.\n+\t\t /\n+\t\tret = mxl862xx_wait_ready(ds);\n+\t\tif (ret)\n+\t\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t\t \"new firmware did not become ready\");\n+\t}\n+\n+\tif (ret) {\n+\t\t/ The switch is in MCUboot with erased or partly written flash;\n+\t\t * drop the cached identity so devlink dev info stops reporting\n+\t\t * the pre-flash version until the reprobe re-reads the truth.\n+\t\t /\n+\t\tmemset(\u0026priv-\u003efw_version, 0, sizeof(priv-\u003efw_version));\n+\t\tpriv-\u003easic_id = 0;\n+\t\tpriv-\u003easic_rev = 0;\n+\t}\n+\n+\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n+\tpriv-\u003eflash_reading = false;\n+\tpriv-\u003eblock_host = false;\n+\tpriv-\u003eskip_teardown = true;\n+\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\t/ Reinitialise through a deferred re-probe: remove() runs with\n+\t * skip_teardown set, then a fresh probe() starts against whatever\n+\t * the switch now runs. The core skips the re-probe if the device\n+\t * is unbound or shut down before it fires.\n+\t /\n+\terr = device_schedule_reprobe(ds-\u003edev, MXL862XX_FW_REPROBE_DELAY_MS);\n+\n+\treturn ret ? ret : err;\n+}\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.h b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h\nnew file mode 100644\nindex 0000000000000..7cd87c7ad8716\n--- /dev/null\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h\n@@ -0,0 +1,20 @@\n+/ SPDX-License-Identifier: GPL-2.0-or-later /\n+\n+#ifndef __MXL862XX_FW_H\n+#define __MXL862XX_FW_H\n+\n+#include \u003cnet/dsa.h\u003e\n+\n+struct mxl862xx_priv;\n+struct work_struct;\n+\n+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv priv);\n+void mxl862xx_rescue_heal_work_fn(struct work_struct work);\n+int mxl862xx_devlink_info_get(struct dsa_switch ds,\n+\t\t\t struct devlink_info_req req,\n+\t\t\t struct netlink_ext_ack extack);\n+int mxl862xx_devlink_flash_update(struct dsa_switch ds,\n+\t\t\t\t struct devlink_flash_update_params params,\n+\t\t\t\t struct netlink_ext_ack extack);\n+\n+#endif / __MXL862XX_FW_H /\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.c b/drivers/net/dsa/mxl862xx/mxl862xx-host.c\nindex 4acd216f7cc00..23e5dfe81e364 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.c\n@@ -15,6 +15,8 @@\n #include \u003clinux/unaligned.h\u003e\n #include \u003cnet/dsa.h\u003e\n #include \"mxl862xx.h\"\n+#include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n #include \"mxl862xx-host.h\"\n \n #define CTRL_BUSY_MASK\t\t\tBIT(15)\n@@ -340,6 +342,26 @@ int mxl862xx_api_wrap(struct mxl862xx_priv priv, u16 cmd, void _data,\n \n \tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n \n+\tif (priv-\u003eskip_teardown) {\n+\t\tret = read ? -ENODEV : 0;\n+\t\tgoto out;\n+\t}\n+\n+\tif (priv-\u003erescue_mode) {\n+\t\tret = -ENODEV;\n+\t\tgoto out;\n+\t}\n+\n+\t/ During the post-flash readiness poll block_host stays set, but the\n+\t * flash path's own firmware version reads must reach the new image;\n+\t * host writes stay blocked so stale resource IDs cannot corrupt it.\n+\t /\n+\tif (priv-\u003eblock_host \u0026\u0026 cmd != SYS_MISC_FW_UPDATE \u0026\u0026\n+\t !(priv-\u003eflash_reading \u0026\u0026 read)) {\n+\t\tret = -EBUSY;\n+\t\tgoto out;\n+\t}\n+\n \tmax = (size + 1) / 2;\n \n \tret = mxl862xx_busy_wait(priv);\n@@ -495,12 +517,54 @@ int mxl862xx_reset(struct mxl862xx_priv priv)\n \treturn ret;\n }\n \n+#define MXL862XX_SMDIO_ADDR_REG\t\t0x1f\n+#define MXL862XX_SMDIO_PAGE_MASK\t0xfff0\n+#define MXL862XX_SMDIO_OFF_MASK\t\t0x000f\n+\n+/* Paged clause-22 window: the page goes into MII register 0x1f, the low nibble\n+ * of addr selects one of the 16 registers within it. Both helpers take the MDIO\n+ * bus lock per transaction, so callers must not already hold it -- unlike\n+ * mxl862xx_api_wrap(), which holds it across a whole firmware command.\n+ /\n+int mxl862xx_smdio_read(struct mxl862xx_priv priv, u32 addr)\n+{\n+\tstruct mii_bus bus = priv-\u003emdiodev-\u003ebus;\n+\tint phy = priv-\u003emdiodev-\u003eaddr;\n+\tint ret;\n+\n+\tmutex_lock(\u0026bus-\u003emdio_lock);\n+\tret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,\n+\t\t\t addr \u0026 MXL862XX_SMDIO_PAGE_MASK);\n+\tif (ret \u003e= 0)\n+\t\tret = __mdiobus_read(bus, phy, addr \u0026 MXL862XX_SMDIO_OFF_MASK);\n+\tmutex_unlock(\u0026bus-\u003emdio_lock);\n+\treturn ret;\n+}\n+\n+int mxl862xx_smdio_write(struct mxl862xx_priv priv, u32 addr, u16 val)\n+{\n+\tstruct mii_bus bus = priv-\u003emdiodev-\u003ebus;\n+\tint phy = priv-\u003emdiodev-\u003eaddr;\n+\tint ret;\n+\n+\tmutex_lock(\u0026bus-\u003emdio_lock);\n+\tret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,\n+\t\t\t addr \u0026 MXL862XX_SMDIO_PAGE_MASK);\n+\tif (ret \u003e= 0)\n+\t\tret = __mdiobus_write(bus, phy, addr \u0026 MXL862XX_SMDIO_OFF_MASK,\n+\t\t\t\t val);\n+\tmutex_unlock(\u0026bus-\u003emdio_lock);\n+\treturn ret;\n+}\n+\n void mxl862xx_host_init(struct mxl862xx_priv priv)\n {\n \tINIT_WORK(\u0026priv-\u003ecrc_err_work, mxl862xx_crc_err_work_fn);\n+\tINIT_WORK(\u0026priv-\u003erescue_heal_work, mxl862xx_rescue_heal_work_fn);\n }\n \n void mxl862xx_host_shutdown(struct mxl862xx_priv priv)\n {\n \tcancel_work_sync(\u0026priv-\u003ecrc_err_work);\n+\tcancel_work_sync(\u0026priv-\u003erescue_heal_work);\n }\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.h b/drivers/net/dsa/mxl862xx/mxl862xx-host.h\nindex 66d6ae198aff4..4e054c6e4c0e4 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.h\n@@ -18,5 +18,7 @@ int mxl862xx_api_wrap(struct mxl862xx_priv priv, u16 cmd, void data, u16 size,\n \tmxl862xx_api_wrap(dev, cmd, \u0026(data), sizeof((data)), true, true)\n \n int mxl862xx_reset(struct mxl862xx_priv priv);\n+int mxl862xx_smdio_read(struct mxl862xx_priv priv, u32 addr);\n+int mxl862xx_smdio_write(struct mxl862xx_priv priv, u32 addr, u16 val);\n \n #endif /* __MXL862XX_HOST_H /\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\nindex b689652aa9b92..a5b6940b552e9 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\n@@ -406,6 +406,8 @@ mxl862xx_phylink_mac_select_pcs(struct phylink_config config,\n \n \tswitch (port) {\n \tcase 9 ... 16:\n+\t\tif (priv-\u003erescue_mode)\n+\t\t\treturn NULL;\n \t\tif (!MXL862XX_FW_VER_MIN(priv, 1, 0, 84)) {\n \t\t\tdev_warn_once(dp-\u003eds-\u003edev,\n \t\t\t\t \"SerDes PCS unsupported on old firmware.\\n\");\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c\nindex 45d237b3a40f1..74abf88c09cc6 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx.c\n@@ -21,6 +21,7 @@\n #include \"mxl862xx.h\"\n #include \"mxl862xx-api.h\"\n #include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n #include \"mxl862xx-host.h\"\n #include \"mxl862xx-phylink.h\"\n \n@@ -71,6 +72,13 @@ static const struct ethtool_rmon_hist_range mxl862xx_rmon_ranges[] = {\n #define MXL862XX_READY_TIMEOUT_MS\t10000\n #define MXL862XX_READY_POLL_MS\t\t100\n \n+/* Chip ID registers, read via SYS_MISC_REG_RD /\n+#define MXL862XX_CHIPID_L\t\t0xc0d28884\n+#define MXL862XX_CHIPID_M\t\t0xc0d28888\n+#define MXL862XX_CHIPID_L_PNUML\t\tGENMASK(15, 12)\n+#define MXL862XX_CHIPID_M_PNUMM\t\tGENMASK(11, 0)\n+#define MXL862XX_CHIPID_M_VERSION\tGENMASK(14, 12)\n+\n #define MXL862XX_TCM_INST_SEL\t\t0xe00\n #define MXL862XX_TCM_CBS\t\t0xe12\n #define MXL862XX_TCM_EBS\t\t0xe13\n@@ -222,7 +230,46 @@ static int mxl862xx_phy_write_c45_mii_bus(struct mii_bus bus, int addr,\n \treturn mxl862xx_phy_write_mmd(bus-\u003epriv, addr, devadd, regnum, val);\n }\n \n-static int mxl862xx_wait_ready(struct dsa_switch ds)\n+/ Read the static chip part number and version from the CHIP ID\n+ * registers. Only possible with a running firmware, so the values are\n+ * cached at setup and left zero when the switch is in rescue mode.\n+ /\n+static int mxl862xx_read_chip_id(struct mxl862xx_priv priv)\n+{\n+\tstruct mxl862xx_sys_reg_rw reg = {};\n+\tu16 chipid_l, chipid_m;\n+\tint ret;\n+\n+\treg.addr = cpu_to_le32(MXL862XX_CHIPID_L);\n+\tret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);\n+\tif (ret)\n+\t\treturn ret;\n+\tchipid_l = le32_to_cpu(reg.val);\n+\n+\treg.addr = cpu_to_le32(MXL862XX_CHIPID_M);\n+\tret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);\n+\tif (ret)\n+\t\treturn ret;\n+\tchipid_m = le32_to_cpu(reg.val);\n+\n+\tpriv-\u003easic_id = FIELD_GET(MXL862XX_CHIPID_L_PNUML, chipid_l) \|\n+\t\t\tFIELD_GET(MXL862XX_CHIPID_M_PNUMM, chipid_m) \u003c\u003c 4;\n+\tpriv-\u003easic_rev = FIELD_GET(MXL862XX_CHIPID_M_VERSION, chipid_m);\n+\n+\treturn 0;\n+}\n+\n+/*\n+ mxl862xx_wait_ready - wait for the switch firmware to become operational\n+ * @ds: DSA switch instance\n+ \n+ Poll the firmware until it reports its version and accepts\n+ * configuration commands, then cache the firmware version and chip ID.\n+ * Takes at least two seconds.\n+ \n+ Return: 0 on success or a negative error code.\n+ /\n+int mxl862xx_wait_ready(struct dsa_switch ds)\n {\n \tstruct mxl862xx_sys_fw_image_version ver = {};\n \tunsigned long start = jiffies, timeout;\n@@ -254,6 +301,11 @@ static int mxl862xx_wait_ready(struct dsa_switch ds)\n \t\tpriv-\u003efw_version.major = ver.iv_major;\n \t\tpriv-\u003efw_version.minor = ver.iv_minor;\n \t\tpriv-\u003efw_version.revision = le16_to_cpu(ver.iv_revision);\n+\n+\t\tret = mxl862xx_read_chip_id(priv);\n+\t\tif (ret)\n+\t\t\tdev_warn(ds-\u003edev, \"failed to read chip ID: %pe\\n\",\n+\t\t\t\t ERR_PTR(ret));\n \t\treturn 0;\n \n not_ready_yet:\n@@ -622,21 +674,66 @@ static int mxl862xx_setup(struct dsa_switch ds)\n \tint n_user_ports = 0, max_vlans;\n \tint ingress_finals, vid_rules;\n \tstruct dsa_port dp;\n-\tint ret, i;\n-\n-\tret = mxl862xx_reset(priv);\n-\tif (ret)\n-\t\treturn ret;\n-\n-\tret = mxl862xx_wait_ready(ds);\n-\tif (ret)\n-\t\treturn ret;\n+\tint ret, i, rescue;\n \n+\t/ The SerDes state is software-only and must exist before anything can\n+\t * reach phylink, including a rescue-mode flash clearing rescue_mode\n+\t * ahead of the reprobe.\n+\t /\n \tmutex_init(\u0026priv-\u003eserdes_lock);\n \tfor (i = 0; i \u003c ARRAY_SIZE(priv-\u003eserdes_ports); i++)\n \t\tmxl862xx_setup_pcs(priv, \u0026priv-\u003eserdes_ports[i],\n \t\t\t\t i + MXL862XX_FIRST_SERDES_PORT);\n \n+\t/ Detect the loader over SB PDI first: it needs no firmware, unlike the\n+\t * C45 API (mxl862xx_reset/wait_ready) which spews CRC errors when none\n+\t * answers. Touch C45 only once rescue is ruled out.\n+\t /\n+\trescue = mxl862xx_rescue_mode_detect(priv);\n+\tif (rescue \u003c 0) {\n+\t\tdev_err(ds-\u003edev, \"switch state detection failed: %pe\\n\",\n+\t\t\tERR_PTR(rescue));\n+\t\treturn rescue;\n+\t}\n+\n+\tif (rescue == MXL862XX_NOT_RESCUE) {\n+\t\tret = mxl862xx_reset(priv);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\n+\t\tret = mxl862xx_wait_ready(ds);\n+\t\tif (ret) {\n+\t\t\t/ the reset may only now have triggered rescue mode /\n+\t\t\trescue = mxl862xx_rescue_mode_detect(priv);\n+\t\t\tif (rescue \u003c 0) {\n+\t\t\t\tdev_err(ds-\u003edev,\n+\t\t\t\t\t\"switch not responding after reset: %pe\\n\",\n+\t\t\t\t\tERR_PTR(rescue));\n+\t\t\t\treturn rescue;\n+\t\t\t}\n+\t\t\tif (rescue == MXL862XX_NOT_RESCUE)\n+\t\t\t\treturn ret;\n+\t\t}\n+\t}\n+\n+\tpriv-\u003erescue_mode = rescue;\n+\n+\tif (priv-\u003erescue_mode) {\n+\t\tif (priv-\u003erescue_ready) {\n+\t\t\tdev_warn(ds-\u003edev,\n+\t\t\t\t \"switch in MCUboot rescue mode, use devlink to flash new firmware\\n\");\n+\t\t} else {\n+\t\t\t/ Drain the wedged download in the background so it\n+\t\t\t * never holds the devlink lock; info and flash become\n+\t\t\t * available once ready.\n+\t\t\t /\n+\t\t\tdev_warn(ds-\u003edev,\n+\t\t\t\t \"switch in MCUboot with an interrupted download, recovering in background\\n\");\n+\t\t\tqueue_work(system_long_wq, \u0026priv-\u003erescue_heal_work);\n+\t\t}\n+\t\treturn 0;\n+\t}\n+\n \t/ Calculate Extended VLAN block sizes.\n \t * With VLAN Filter handling VID membership checks:\n \t * Ingress: only final catchall rules (PVID insertion, 802.1Q\n@@ -715,11 +812,21 @@ static int mxl862xx_port_state(struct dsa_switch ds, int port, bool enable)\n static int mxl862xx_port_enable(struct dsa_switch ds, int port,\n \t\t\t\tstruct phy_device phydev)\n {\n+\tstruct mxl862xx_priv priv = ds-\u003epriv;\n+\n+\tif (priv-\u003erescue_mode)\n+\t\treturn 0;\n+\n \treturn mxl862xx_port_state(ds, port, true);\n }\n \n static void mxl862xx_port_disable(struct dsa_switch ds, int port)\n {\n+\tstruct mxl862xx_priv priv = ds-\u003epriv;\n+\n+\tif (priv-\u003erescue_mode)\n+\t\treturn;\n+\n \tif (mxl862xx_port_state(ds, port, false))\n \t\tdev_err(ds-\u003edev, \"failed to disable port %d\\n\", port);\n }\n@@ -1337,6 +1444,17 @@ static int mxl862xx_port_setup(struct dsa_switch ds, int port)\n \tbool is_cpu_port = dsa_port_is_cpu(dp);\n \tint ret;\n \n+\tif (dsa_port_is_dsa(dp)) {\n+\t\tdev_err(ds-\u003edev, \"port %d: DSA links not supported\\n\", port);\n+\t\treturn -EOPNOTSUPP;\n+\t}\n+\n+\t/ DSA reinits failed user ports as unused; shared ports must\n+\t * succeed for the tree to register.\n+\t /\n+\tif (priv-\u003erescue_mode)\n+\t\treturn dsa_port_is_user(dp) ? -ENODEV : 0;\n+\n \tret = mxl862xx_port_state(ds, port, false);\n \tif (ret)\n \t\treturn ret;\n@@ -1346,11 +1464,6 @@ static int mxl862xx_port_setup(struct dsa_switch ds, int port)\n \tif (dsa_port_is_unused(dp))\n \t\treturn 0;\n \n-\tif (dsa_port_is_dsa(dp)) {\n-\t\tdev_err(ds-\u003edev, \"port %d: DSA links not supported\\n\", port);\n-\t\treturn -EOPNOTSUPP;\n-\t}\n-\n \tret = mxl862xx_configure_sp_tag_proto(ds, port, is_cpu_port);\n \tif (ret)\n \t\treturn ret;\n@@ -1572,6 +1685,12 @@ static int mxl862xx_port_mdb_del(struct dsa_switch ds, int port,\n \tether_addr_copy(qparam.mac, mdb-\u003eaddr);\n \n \tret = MXL862XX_API_READ(priv, MXL862XX_MAC_TABLEENTRYQUERY, qparam);\n+\t/ Post-flash teardown or MCUboot: the firmware and its MAC table are\n+\t * gone, so there is nothing left to delete. Outside those, -ENODEV is a\n+\t * bus error and must be reported.\n+\t /\n+\tif (ret == -ENODEV \u0026\u0026 (priv-\u003eskip_teardown \|\| priv-\u003erescue_mode))\n+\t\treturn 0;\n \tif (ret)\n \t\treturn ret;\n \n@@ -1628,6 +1747,9 @@ static void mxl862xx_port_stp_state_set(struct dsa_switch ds, int port,\n \tstruct mxl862xx_priv priv = ds-\u003epriv;\n \tint ret;\n \n+\tif (priv-\u003erescue_mode)\n+\t\treturn;\n+\n \tswitch (state) {\n \tcase BR_STATE_DISABLED:\n \t\tparam.port_state = cpu_to_le32(MXL862XX_STP_PORT_STATE_DISABLE);\n@@ -2015,6 +2137,12 @@ static void mxl862xx_stats_work_fn(struct work_struct work)\n \tstruct dsa_switch ds = priv-\u003eds;\n \tstruct dsa_port dp;\n \n+\t/* A get_stats64() re-arm can race the flash teardown's WORK_STOPPED\n+\t * set and cancel; bail here so a stray poll never runs during a flash.\n+\t /\n+\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\treturn;\n+\n \tdsa_switch_for_each_available_port(dp, ds)\n \t\tmxl862xx_stats_poll(ds, dp-\u003eindex);\n \n@@ -2086,6 +2214,8 @@ static const struct dsa_switch_ops mxl862xx_switch_ops = {\n \t.get_pause_stats = mxl862xx_get_pause_stats,\n \t.get_rmon_stats = mxl862xx_get_rmon_stats,\n \t.get_stats64 = mxl862xx_get_stats64,\n+\t.devlink_info_get = mxl862xx_devlink_info_get,\n+\t.devlink_flash_update = mxl862xx_devlink_flash_update,\n };\n \n static int mxl862xx_probe(struct mdio_device mdiodev)\n@@ -2151,10 +2281,16 @@ static void mxl862xx_remove(struct mdio_device mdiodev)\n \tpriv = ds-\u003epriv;\n \n \tset_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags);\n-\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n \n \tdsa_unregister_switch(ds);\n \n+\t/ Cancel the stats poll only after the user netdevs are gone: until\n+\t * dsa_unregister_switch() returns a get_stats64() can still re-arm the\n+\t * work after a plain cancel, and it would then run against the\n+\t * devres-freed priv.\n+\t /\n+\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n+\n \tmxl862xx_host_shutdown(priv);\n \n \t/ Cancel any pending host flood work. dsa_unregister_switch()\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx.h b/drivers/net/dsa/mxl862xx/mxl862xx.h\nindex 432a5f3f2e08e..bdaf295c8a9f6 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx.h\n@@ -4,7 +4,9 @@\n #define __MXL862XX_H\n \n #include \u003casm/byteorder.h\u003e\n+#include \u003clinux/bitops.h\u003e\n #include \u003clinux/mdio.h\u003e\n+#include \u003clinux/mutex.h\u003e\n #include \u003clinux/workqueue.h\u003e\n #include \u003cnet/dsa.h\u003e\n \n@@ -14,6 +16,10 @@ struct mxl862xx_priv;\n #define MXL862XX_FIRST_SERDES_PORT\t9\n #define MXL862XX_SERDES_SLOTS\t\t4\n \n+/* mxl862xx_rescue_mode_detect() return codes (negative values are errors) /\n+#define MXL862XX_NOT_RESCUE\t\t0\n+#define MXL862XX_IN_RESCUE\t\t1\n+\n #define MXL862XX_DEFAULT_BRIDGE\t\t0\n #define MXL862XX_MAX_BRIDGES\t\t48\n #define MXL862XX_MAX_BRIDGE_PORTS\t128\n@@ -303,6 +309,10 @@ struct mxl862xx_fw_version {\n flooding)\n * @fw_version: cached firmware version, populated at probe and\n * compared with MXL862XX_FW_VER_MIN()\n+ * @asic_id: chip part number read from the CHIP ID registers,\n+ * reported as the devlink \"asic.id\" fixed version\n+ * @asic_rev: chip version read from the CHIP ID registers,\n+ * reported as the devlink \"asic.rev\" fixed version\n * @serdes_ports: SerDes interfaces incl. sub-interfaces in case of\n * 10G_QXGMII or QSGMII\n * @serdes_refcount: per-XPCS count of sub-ports enabled by phylink;\n@@ -319,6 +329,22 @@ struct mxl862xx_fw_version {\n * @evlan_ingress_size: per-port ingress Extended VLAN block size\n * @evlan_egress_size: per-port egress Extended VLAN block size\n * @vf_block_size: per-port VLAN Filter block size\n+ * @block_host: reject firmware API commands (except FW_UPDATE)\n+ * during a firmware flash\n+ * @flash_reading: let the flash path's own firmware reads through\n+ * block_host while polling the freshly booted image\n+ * @skip_teardown: discard firmware API commands during the teardown\n+ * triggered by the post-flash reprobe\n+ * @rescue_mode: switch is in MCUboot; firmware API commands fail fast,\n+ * only clause-22 SMDIO works. Set from setup() before the\n+ * switch is registered and cleared under the MDIO bus lock\n+ * for the benefit of mxl862xx_api_wrap(); other readers\n+ * only need it to be a stable single flag.\n+ * @rescue_ready: (rescue_mode) loader is at a clean READY and will accept\n+ * a flash; false while rescue_heal_work is draining\n+ * @rescue_failed: (rescue_mode) the self-heal gave up; the loader needs a\n+ * power cycle and no flash can be accepted\n+ * @rescue_heal_work: background self-heal draining a wedged download to READY\n * @stats_work: periodic work item that polls RMON hardware counters\n * and accumulates them into 64-bit per-port stats\n /\n@@ -326,9 +352,12 @@ struct mxl862xx_priv {\n \tstruct dsa_switch ds;\n \tstruct mdio_device mdiodev;\n \tstruct work_struct crc_err_work;\n+\tstruct work_struct rescue_heal_work;\n \tunsigned long flags;\n \tu16 drop_meter;\n \tstruct mxl862xx_fw_version fw_version;\n+\tu16 asic_id;\n+\tu8 asic_rev;\n \tstruct mxl862xx_pcs serdes_ports[8];\n \tint serdes_refcount[2];\n \tstruct mutex serdes_lock;\n@@ -337,7 +366,15 @@ struct mxl862xx_priv {\n \tu16 evlan_ingress_size;\n \tu16 evlan_egress_size;\n \tu16 vf_block_size;\n+\tbool block_host;\n+\tbool flash_reading;\n+\tbool skip_teardown;\n+\tbool rescue_mode;\n+\tbool rescue_ready;\n+\tbool rescue_failed;\n \tstruct delayed_work stats_work;\n };\n \n+int mxl862xx_wait_ready(struct dsa_switch ds);\n+\n #endif /* __MXL862XX_H /\ndiff --git a/include/linux/device.h b/include/linux/device.h\nindex aee79fd6b32b4..7a99169505772 100644\n--- a/include/linux/device.h\n+++ b/include/linux/device.h\n@@ -1314,6 +1314,8 @@ int __must_check device_attach(struct device dev);\n int __must_check driver_attach(const struct device_driver drv);\n void device_initial_probe(struct device dev);\n int __must_check device_reprobe(struct device dev);\n+int __must_check device_schedule_reprobe(struct device dev,\n+\t\t\t\t\t unsigned int delay_ms);\n \n bool device_is_bound(struct device dev);\n \ndiff --git a/include/net/dsa.h b/include/net/dsa.h\nindex 6f7f5c17b5320..58597b14e592a 100644\n--- a/include/net/dsa.h\n+++ b/include/net/dsa.h\n@@ -1172,6 +1172,9 @@ struct dsa_switch_ops {\n \tint\t(devlink_info_get)(struct dsa_switch ds,\n \t\t\t\t struct devlink_info_req req,\n \t\t\t\t struct netlink_ext_ack extack);\n+\tint\t(devlink_flash_update)(struct dsa_switch ds,\n+\t\t\t\t\tstruct devlink_flash_update_params params,\n+\t\t\t\t\tstruct netlink_ext_ack extack);\n \tint\t(devlink_sb_pool_get)(struct dsa_switch ds,\n \t\t\t\t unsigned int sb_index, u16 pool_index,\n \t\t\t\t struct devlink_sb_pool_info pool_info);\ndiff --git a/net/dsa/devlink.c b/net/dsa/devlink.c\nindex ed342f345692b..25311a87cbc56 100644\n--- a/net/dsa/devlink.c\n+++ b/net/dsa/devlink.c\n@@ -20,6 +20,18 @@ static int dsa_devlink_info_get(struct devlink dl,\n \treturn -EOPNOTSUPP;\n }\n \n+static int dsa_devlink_flash_update(struct devlink dl,\n+\t\t\t\t struct devlink_flash_update_params params,\n+\t\t\t\t struct netlink_ext_ack extack)\n+{\n+\tstruct dsa_switch ds = dsa_devlink_to_ds(dl);\n+\n+\tif (!ds-\u003eops-\u003edevlink_flash_update)\n+\t\treturn -EOPNOTSUPP;\n+\n+\treturn ds-\u003eops-\u003edevlink_flash_update(ds, params, extack);\n+}\n+\n static int dsa_devlink_sb_pool_get(struct devlink dl,\n \t\t\t\t unsigned int sb_index, u16 pool_index,\n \t\t\t\t struct devlink_sb_pool_info pool_info)\n@@ -169,6 +181,7 @@ dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port dlp,\n \n static const struct devlink_ops dsa_devlink_ops = {\n \t.info_get\t\t\t= dsa_devlink_info_get,\n+\t.flash_update\t\t\t= dsa_devlink_flash_update,\n \t.sb_pool_get\t\t\t= dsa_devlink_sb_pool_get,\n \t.sb_pool_set\t\t\t= dsa_devlink_sb_pool_set,\n \t.sb_port_pool_get\t\t= dsa_devlink_sb_port_pool_get,\n" }
2/1	2026/08/16 23:35	agent	patch-evaluator	0m Model: best-expensive Args: null Results: { "EnableConfigs": null, "FocusSymbols": [], "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.", "WorthFuzzing": false } Instruction: You are an expert Linux kernel maintainer. Your job is to review a provided patch series and determine if it makes functional changes to the kernel that should be fuzzed. IMPORTANT: The changes have ALREADY been applied and committed as the HEAD commit in your workspace. Do NOT rely on your internal knowledge of the kernel. You must actively use your code access tools to examine the actual source code and confirm any assumptions. Return WorthFuzzing=false if the patch only contains: - Modifications to Documentation/, Kconfig files, or code comments. - Purely decorative changes, such as logging (e.g., pr_err, printk) or tracepoints. - Changes to numeric constants or macros that do not functionally alter execution flow. - Code paths that are impossible to reach in virtualized environments like GCE or QEMU, even when utilizing software-emulated hardware (e.g., usb gadget, mac80211_hwsim). - Code in vendor-specific PCIe switch, SmartNIC, or GPU drivers (e.g., mlxsw, pds_core, qed, ionic, amdgpu) that require physical PCIe hardware cards not emulated in standard QEMU. - Driver .remove, .shutdown, or pci_unregister_driver teardown callbacks (e.g., igb_remove) that are executed only during PCI hot-unplug or sysfs driver unbind operations. If it modifies reachable core kernel logic, drivers, or architectures, use your code search tools to verify the code can be executed, then return WorthFuzzing=true. When returning WorthFuzzing=true, you MUST ALSO: 1. Extract any specific kernel functions that should be heavily fuzzed into FocusSymbols. Avoid listing generic hot-path functions to prevent skewed test distributions. Prefer non-static, non-inlined API entrypoint functions over internal static helper functions (which are inlined by the compiler and do not have distinct symbol addresses). 2. Identify any specific CONFIG_ options required to properly test this new/modified feature. Go and look into the Kconfig files and check for ifdefs around the code, do not make assumptions. Also check "depends on" lines in Kconfig to include any non-standard parent subsystem configs needed for Kbuild to compile the code statically into vmlinux. List them in the EnableConfigs output array, and DO NOT add a 'CONFIG_' prefix (e.g., return "NET_IPV4" instead of "CONFIG_NET_IPV4"). Prefer calling several tools at the same time to save round-trips. Use set-results tool to provide results of the analysis. It must be called exactly once before the final reply. Ignore results of this tool. Prompt: For your convenience, here is the diff of the changes: commit a01707c4f39f9db8f15411902f052348a25923e9 Author: syz-cluster <triage@syzkaller.com> Date: Sun Aug 16 23:35:08 2026 +0000 syz-cluster: applied patch under review diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index 4745148fecf4f..058999d0dc56f 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -94,6 +94,7 @@ parameters, info versions, and other features it supports. mlx5 mlxsw mv88e6xxx + mxl862xx netdevsim nfp octeontx2 diff --git a/Documentation/networking/devlink/mxl862xx.rst b/Documentation/networking/devlink/mxl862xx.rst new file mode 100644 index 0000000000000..5b24d8cb57bc9 --- /dev/null +++ b/Documentation/networking/devlink/mxl862xx.rst @@ -0,0 +1,74 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================== +mxl862xx devlink support +======================== + +This document describes the devlink features implemented by the +``mxl862xx`` device driver. + +Info versions +============= + +The ``mxl862xx`` driver reports the following versions + +.. list-table:: devlink info versions implemented + :widths: 5 5 5 85 + + * - Name + - Type + - Example + - Description + * - ``asic.id`` + - fixed + - 8628 + - The chip part number read from the CHIP ID registers. Omitted + when the part number reads as zero, which happens for a switch + sitting in MCUboot rescue mode (the registers need a running + firmware), for an unfused part, and after a failed flash. + * - ``asic.rev`` + - fixed + - 0 + - The chip version read from the same register word, so it is + omitted whenever ``asic.id`` is. + * - ``fw`` + - running, stored + - 1.0.70 + - Version of the firmware running on the switch, reported as both + running and stored since the switch boots it from its own flash. + It is omitted while no firmware version is known: after a failed + flash, and in MCUboot rescue mode while an interrupted download + is still being recovered in the background. Once the loader is + ready to accept a new image the version appears as "0.0.0", + which no released firmware reports, so version-comparing tools + offer any available release as an upgrade. Use ``devlink dev + flash`` to tell a recovering switch from a ready one, see below; + a missing version on its own does not say why. + +Flash update +============ + +The ``mxl862xx`` driver implements support for ``devlink dev flash``. +The signed firmware image is transferred to the switch over the same +MDIO bus which is also used to manage the switch, then verified and +installed by the MCUboot bootloader running on the switch. All ports +of the switch are closed for the duration of the update and the driver +reprobes the switch after it has rebooted into the new firmware. A +complete flash and reprobe cycle takes about one minute. + +A switch stuck in MCUboot rescue mode, e.g. after an interrupted +update, is registered without user ports. If the previous download was +interrupted mid-transfer the loader is wedged; the driver drains it +back to a clean ready state in the background, one byte at a time, +which takes tens of minutes for a large image and is reported through +the kernel log as it progresses. During that recovery ``devlink dev +flash`` returns ``-EBUSY`` with an extack message saying so, and +``devlink dev info`` reports no firmware version. Once the loader is +ready the firmware version appears and flashing a firmware image +through the regular update flow recovers the switch. + +If the recovery fails, the loader needs a power cycle: ``devlink dev +flash`` then returns ``-EIO`` and says so in its extack message. The +driver only re-examines the switch when it binds, so on a board where +the switch can be power cycled on its own, unbind and rebind the driver +afterwards to have the recovered switch recognised. diff --git a/MAINTAINERS b/MAINTAINERS index 991460050da74..e3f7ded569bf7 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16106,6 +16106,7 @@ M: Daniel Golle <daniel@makrotopia.org> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml +F: Documentation/networking/devlink/mxl862xx.rst F: drivers/net/dsa/mxl862xx/ F: net/dsa/tag_mxl862xx.c diff --git a/drivers/base/base.h b/drivers/base/base.h index a5b7abc10ff02..6234e37de7e99 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -106,6 +106,10 @@ struct driver_private { * @dead: This device is currently either in the process of or has been * removed from the system. Any asynchronous events scheduled for this * device should exit without taking any action. + * @shutdown_done: Set once device_shutdown() has reached this device, under + * the device lock, before any shutdown callback runs. Read under the + * device lock. A deferred re-probe scheduled with + * device_schedule_reprobe() must not detach the device anymore. * * Nothing outside of the driver core should ever touch these fields. / @@ -120,6 +124,7 @@ struct device_private { char deferred_probe_reason; struct device device; u8 dead:1; + u8 shutdown_done:1; }; #define to_device_private_parent(obj) \ container_of(obj, struct device_private, knode_parent) diff --git a/drivers/base/core.c b/drivers/base/core.c index 4d026682944f2..8a7dbe4e8362b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4906,6 +4906,9 @@ void device_shutdown(void) device_lock(parent); device_lock(dev); + if (dev->p) + dev->p->shutdown_done = true; + / Don't allow any more runtime suspends / pm_runtime_get_noresume(dev); pm_runtime_barrier(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 60c005223844d..3394b1c7ed180 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -1436,3 +1436,102 @@ void driver_detach(const struct device_driver drv) put_device(dev); } } + +struct device_reprobe { + struct delayed_work work; + struct device dev; + struct device parent; + const struct device_driver drv; +}; + +static void device_reprobe_work_fn(struct work_struct work) +{ + struct device_reprobe rp = container_of(work, struct device_reprobe, + work.work); + struct device dev = rp->dev; + struct device parent = rp->parent; + bool detached = false; + + __device_driver_lock(dev, parent); + / + * rp->drv is only ever compared, never dereferenced: the driver it + * points to may have been unregistered and freed by now. + / + if (!dev->p->dead && !dev->p->shutdown_done && + dev->driver && dev->driver == rp->drv) { + __device_release_driver(dev, parent); + detached = true; + } + __device_driver_unlock(dev, parent); + + if (detached) { + / + * device_attach() must run with the parent locked on buses + * that require it, mirroring bus_rescan_devices_helper(). + / + if (parent && dev->bus->need_parent_lock) + device_lock(parent); + if (device_attach(dev) < 0) + dev_err(dev, "re-probe failed, device left unbound\n"); + if (parent && dev->bus->need_parent_lock) + device_unlock(parent); + } + + put_device(dev); + put_device(parent); + kfree(rp); +} + +/* + * device_schedule_reprobe - schedule a deferred detach and re-probe + * @dev: device to detach and re-probe + * @delay_ms: delay in milliseconds before the re-probe runs + * + * Schedule a detach and re-probe of @dev after @delay_ms milliseconds. + * The re-probe is skipped if, by the time the scheduled work runs, the + * device has been removed, the system shutdown sequence has reached the + * device, or @dev is no longer bound to the driver that was bound at + * scheduling time. In particular an administrative unbind is never + * undone by a stale re-probe. + * + * The work function is built-in text, so the bound driver may call this + * from its own code without holding a module reference. If the driver + * module is unloaded before the work runs, driver unregistration unbinds + * @dev first and the scheduled work does nothing. + * + * Multiple pending re-probes for the same device are individually safe; + * a caller that wants at most one pending re-probe must gate scheduling + * itself. + * + * May only be called from process context. + * + * Returns: 0 on success, -EINVAL if @dev is not a registered device + * bound to a driver, -ENOMEM on allocation failure. + / +int device_schedule_reprobe(struct device dev, unsigned int delay_ms) +{ + struct device_reprobe rp; + + if (!dev->bus \|\| !dev->p \|\| !device_is_registered(dev)) + return -EINVAL; + if (!dev->driver) + return -EINVAL; + + rp = kzalloc_obj(rp); + if (!rp) + return -ENOMEM; + + rp->dev = get_device(dev); + /* + * Pin the parent too: the work locks it, and an unregister of @dev + * would otherwise drop the last reference before the work runs. + / + rp->parent = get_device(dev->parent); + rp->drv = READ_ONCE(dev->driver); + INIT_DELAYED_WORK(&rp->work, device_reprobe_work_fn); + queue_delayed_work(system_dfl_wq, &rp->work, + msecs_to_jiffies(delay_ms)); + + return 0; +} +EXPORT_SYMBOL_GPL(device_schedule_reprobe); diff --git a/drivers/net/dsa/mxl862xx/Makefile b/drivers/net/dsa/mxl862xx/Makefile index a7be0e6669dfa..bccac0d0f703f 100644 --- a/drivers/net/dsa/mxl862xx/Makefile +++ b/drivers/net/dsa/mxl862xx/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o -mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o +mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-api.h b/drivers/net/dsa/mxl862xx/mxl862xx-api.h index a180a5decffc0..6f771895984cb 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx-api.h +++ b/drivers/net/dsa/mxl862xx/mxl862xx-api.h @@ -1224,6 +1224,16 @@ struct mxl862xx_sys_fw_image_version { __le32 iv_build_num; } __packed; +/* + * struct mxl862xx_sys_reg_rw - System register read/write + * @addr: 32-bit register address + * @val: register value + / +struct mxl862xx_sys_reg_rw { + __le32 addr; + __le32 val; +} __packed; + /* * enum mxl862xx_port_type - Port Type * @MXL862XX_LOGICAL_PORT: Logical Port diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h index c87a955c13c48..a865425aa61e1 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h +++ b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h @@ -70,7 +70,9 @@ #define INT_GPHY_READ (GPY_GPY2XX_MAGIC + 0x1) #define INT_GPHY_WRITE (GPY_GPY2XX_MAGIC + 0x2) +#define SYS_MISC_FW_UPDATE (SYS_MISC_MAGIC + 0x1) #define SYS_MISC_FW_VERSION (SYS_MISC_MAGIC + 0x2) +#define SYS_MISC_REG_RD (SYS_MISC_MAGIC + 0x8) #define MXL862XX_XPCS_PCS_CONFIG (MXL862XX_XPCS_MAGIC + 0x1) #define MXL862XX_XPCS_PCS_GET_STATE (MXL862XX_XPCS_MAGIC + 0x2) diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.c b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c new file mode 100644 index 0000000000000..1de8d9970a369 --- /dev/null +++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c @@ -0,0 +1,1062 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Firmware flash and devlink support for MaxLinear MxL862xx + * + * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org> + * + * SB PDI - firmware download interface over clause-22 SMDIO + * ========================================================= + * + * The MxL862xx MCUboot loader accepts a firmware image through four "SB PDI" + * registers in the switch SMDIO register space. It runs whenever no WSP + * firmware is active: the normal firmware update enters it deliberately - the + * SYS_MISC_FW_UPDATE API command sets a sticky rescue bit and reboots into + * MCUboot - and the loader also stays here when the stored WSP firmware fails + * its boot-time integrity check. This driver drives the loader's 0xc55c + * "console" download path. + * + * SMDIO register access (mxl862xx_smdio_read/write): + * MII reg 0x1f := (<sb_pdi_reg> & 0xfff0) ; page latch + * MII reg (<sb_pdi_reg> & 0x000f) := / => <u16 data> + * so CTRL/ADDR/DATA/STAT (0xe100..0xe103) are MII regs 0/1/2/3 of page + * 0xe100, not all reg 0x00. + * + * SB PDI registers (host name/addr -> MCU mailbox): + * CTRL 0xe100 -> 0xc0938400 mode: RST=0x00 RD=0x01 WR=0x02 + * ADDR 0xe101 -> 0xc0938404 SB target word address (SB1 bank = 0x7800) + * DATA 0xe102 -> 0xc0938408 16-bit data / reply word + * STAT 0xe103 -> 0xc093840c handshake: a magic (below) or a byte count + * + * STAT magics: + * READY 0xc55c loader idle in the console loop (this driver) + * DL_RDY 0xc33c loader idle in the flashless loop + * START 0xf48f host -> begin download session + * ACK 0xf490 loader -> START acknowledged (START + 1) + * END 0x3cc3 host -> finalise now (optional, see below) + * RDREG 0xe2c0 host -> register-read command (\| index), see below + * + * Console flash path (STAT=0xc55c) - mxl862xx_flash_firmware(): + * + * host loader + * ---- ------ + * reset (CTRL=ADDR=DATA=0) + * read STAT ............................ 0xc55c (READY, idle) + * STAT := START(0xf48f) --------------> + * <-------------- STAT = 0xf490 (ACK) + * CTRL := WR + * DATA := hdr[0..9] (20-byte header: type,size1,crc1,size2,crc2) + * reset; STAT := 20 (header len) -----> parse hdr; r_remain=size1+size2; + * ERASE target region(s) + * <-------------- STAT=21 (len+1), then STAT=0 + * (erased) + * -- payload, streamed in slices: -- + * CTRL := WR + * DATA := word x N ... + * at word 16384: CTRL:=RST; ADDR:=0x7800; CTRL:=WR (half-bank -> SB1) + * at word 32760: flush slice: + * reset; STAT := <bytes_this_slice> ---> r_remain -= bytes; program + * <------------------- STAT=0 (ready for next slice) + * ... repeat until the whole payload is sent ... + * <------------------- STAT=0 image verified + * (STAT=1: image rejected) + * STAT := END(0x3cc3) ---------------------> finalise and boot + * + * The r_remain == 0 rule (critical): + * Every host STAT write in the payload phase is a byte count; the loader + * does r_remain -= count and stays in the receive loop while r_remain != 0. + * It leaves the loop ONLY when r_remain hits EXACTLY 0, and a count larger + * than r_remain underflows the 32-bit counter and wedges the loader until a + * power cycle. Having left it, the loader verifies the image, publishes the + * verdict in STAT (0 good, 1 rejected) and waits 2 s for END before + * finalising regardless -- clearing its rescue-enable bit so boot_go boots + * the new image -- so END only saves that wait. Hence: + * - never send a slice/chunk count larger than what is outstanding; + * - a STAT write is a command only once the loader has left the loop; + * - the loader leaves the count in STAT while it programs the chunk, so + * a lingering count does not distinguish "busy" from "verdict"; + * - interrupted-download recovery feeds 1 byte at a time (see below). + * + * Interrupted-flash recovery (mxl862xx_rescue_drain): + * A host that dies mid-payload leaves the loader in the receive loop holding + * STAT=0. Feed single 1-byte chunks (one DATA word + STAT=1) until r_remain + * reaches 0; the loader then verifies the (now corrupt) image, publishes its + * verdict and comes back to READY by itself. END is never sent here: while + * r_remain is non-zero it would be consumed as a 15555-byte count, and a + * lingering STAT=1 cannot be told from a chunk still being programmed. + * + * Register-read challenge (non-destructive liveness proof): + * DATA := 0x7c23 (marker); STAT := 0xe2c0\|idx + * -> loader returns a runtime word in DATA and re-arms STAT=0xc55c. + * The reply source is loader BSS, not a chip id; used only to prove a live + * mailbox in mxl862xx_rescue_mode_detect(). + * + * The other STAT ready magic, 0xc33c, marks the loader's flashless + * chip-to-chip download mode (MxL86281S 16-port tier); this driver does not + * use it. + * + * Rescue lifecycle (devlink): probe runs mxl862xx_rescue_mode_detect(); a + * wedged loader is drained back to READY by a background self-heal + * (rescue_heal_work), so the long recovery never holds the devlink lock. + * devlink dev info exposes the fw version (the "flashable" signal) only once at + * READY; flash_update returns -EBUSY until then, and reprobes to WSP firmware + * on success. + * + * Notes: + * - Chip id/revision (0xc0d28884/88) are NOT reachable on this channel; they + * need the clause-45 MMD firmware mailbox, which is dead under MCUboot. + * Rescue identity is by SB PDI behaviour only (mxl862xx_rescue_mode_detect). + * - The SMDIO PHY address comes from the device tree; the 0xe1xx register + * offsets are the OTP reset defaults and the only layout supported here. + / + +#include <linux/crc32.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/iopoll.h> +#include <linux/netdevice.h> +#include <linux/overflow.h> +#include <linux/rtnetlink.h> +#include <linux/workqueue.h> +#include <net/dsa.h> +#include <net/switchdev.h> + +#include "mxl862xx.h" +#include "mxl862xx-api.h" +#include "mxl862xx-cmd.h" +#include "mxl862xx-fw.h" +#include "mxl862xx-host.h" + +/ SB PDI registers (clause-22 SMDIO address space) / +#define MXL862XX_SB_PDI_CTRL 0xe100 +#define MXL862XX_SB_PDI_ADDR 0xe101 +#define MXL862XX_SB_PDI_DATA 0xe102 +#define MXL862XX_SB_PDI_STAT 0xe103 + +/ SB PDI CTRL modes / +#define MXL862XX_SB_PDI_CTRL_RST 0x00 +#define MXL862XX_SB_PDI_CTRL_WR 0x02 + +/ SB PDI handshake magic (published/consumed via STAT) / +#define MXL862XX_SB_PDI_READY 0xc55c / loader idle, console loop / +#define MXL862XX_SB_PDI_DL_READY 0xc33c / loader idle, flashless loop / +#define MXL862XX_SB_PDI_START 0xf48f +#define MXL862XX_SB_PDI_END 0x3cc3 +#define MXL862XX_SB_PDI_RDREG 0xe2c0 / register-read cmd (\| index) / +#define MXL862XX_SB_PDI_RDREG_MARK 0x7c23 / marker placed in DATA for RDREG / + +/ Behavioural presence probe: two distinct 16-bit latches on ADDR/DATA. / +#define MXL862XX_SB_PDI_PROBE_A 0x5a5a +#define MXL862XX_SB_PDI_PROBE_D 0xa5a5 + +/ Image verification verdict published in STAT once the receive loop ends / +#define MXL862XX_SB_PDI_VERIFY_OK 0 +#define MXL862XX_SB_PDI_VERIFY_BAD 1 + +/ Firmware transfer geometry / +#define MXL862XX_FW_HDR_SIZE 20 +#define MXL862XX_FW_BANK_HALF 16384 / words per half-bank / +#define MXL862XX_FW_BANK_SLICE 32760 / words per full slice / +#define MXL862XX_FW_SB1_ADDR 0x7800 / SB1 word address / + +/ Timeouts (generous upper bounds) / +#define MXL862XX_FW_READY_TIMEOUT_MS 3000 +#define MXL862XX_FW_ACK_TIMEOUT_MS 5000 +#define MXL862XX_FW_ERASE_TIMEOUT_MS 300000 +#define MXL862XX_FW_WRITE_TIMEOUT_MS 60000 +#define MXL862XX_FW_REBOOT_DELAY_MS 5000 +#define MXL862XX_FW_REPROBE_DELAY_MS 500 +/ One loader mailbox step: program a 1-byte chunk or service a command / +#define MXL862XX_SB_PDI_STEP_MS 2000 +/ Covers the loader's END wait, verification and the reset into READY / +#define MXL862XX_SB_PDI_VERIFY_MS 15000 + +static int mxl862xx_sb_pdi_reset(struct mxl862xx_priv priv) +{ + int ret; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_RST); + if (ret < 0) + return ret; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR, + MXL862XX_SB_PDI_CTRL_RST); + if (ret < 0) + return ret; + + return mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, + MXL862XX_SB_PDI_CTRL_RST); +} + +static int mxl862xx_sb_pdi_poll_stat(struct mxl862xx_priv priv, u16 expected, + unsigned long timeout_ms) +{ + int ret, val; + + ret = read_poll_timeout(mxl862xx_smdio_read, val, + val < 0 \|\| (u16)val == expected, + 10000, timeout_ms 1000, false, + priv, MXL862XX_SB_PDI_STAT); + if (val < 0) + return val; + return ret; +} + +static int mxl862xx_sb_pdi_flush_slice(struct mxl862xx_priv priv, + u32 data_written) +{ + int ret; + + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written); + if (ret < 0) + return ret; + + return mxl862xx_sb_pdi_poll_stat(priv, 0, + MXL862XX_FW_WRITE_TIMEOUT_MS); +} + +/ Flush the last slice, which ends the receive loop: the loader verifies the + * image and replaces the count in STAT with its verdict, so wait for the count + * to go rather than for a fixed value. + / +static int mxl862xx_sb_pdi_flush_last(struct mxl862xx_priv priv, + u32 data_written) +{ + int ret, val; + + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written); + if (ret < 0) + return ret; + + ret = read_poll_timeout(mxl862xx_smdio_read, val, + val < 0 \|\| (u16)val != (u16)data_written, + 10000, (MXL862XX_FW_WRITE_TIMEOUT_MS + + MXL862XX_SB_PDI_VERIFY_MS) * 1000, + false, priv, MXL862XX_SB_PDI_STAT); + if (val < 0) + return val; + + if (!ret && (u16)val == MXL862XX_SB_PDI_VERIFY_OK) + return 0; + + /* A final count of 1 is indistinguishable from the reject verdict, so + * a timeout still holding it lands here too. + / + if ((u16)val == MXL862XX_SB_PDI_VERIFY_BAD) { + dev_err(&priv->mdiodev->dev, + "flash: loader rejected the image\n"); + return -EBADMSG; + } + + return ret ? ret : -EPROTO; +} + +static void mxl862xx_flash_notify(struct devlink dl, const char status, + u32 done, u32 total) +{ + devlink_flash_update_status_notify(dl, status, NULL, done, total); +} + +/ Byte-count of each chunk fed to the loader during drain. It MUST be 1: the + * loader only lets us observe "counter == 0", never "counter < step", so any + * step > 1 can subtract past zero, underflow the 32-bit counter and wedge the + * loader for ~2^32 more bytes (a state only a power cycle clears). Stepping by + * 1 walks the counter through every value and is guaranteed to land on zero + * whatever its (possibly odd) start. A 1-byte chunk is a path the loader + * already handles: the normal transfer ends with a single trailing byte for + * odd-sized images (see Step 6). + / +#define MXL862XX_DRAIN_CHUNK_BYTES 1 + +/ Log the drain's progress every so many bytes; it can run for a long time / +#define MXL862XX_DRAIN_LOG_BYTES (128 1024) + +/* Wait for the loader to ask for the next chunk (STAT 0) or to come back to its + * command loop (STAT READY), and return the STAT value either way. On timeout + * that is whatever STAT still holds, which carries no further information: the + * loader keeps the count we wrote visible while it programs the chunk, and that + * is the same value it publishes as the "image rejected" verdict once the + * counter reaches zero. + * + * STAT 0 is unambiguous here even though it is also the "image verified" + * verdict: by the r_remain == 0 rule the loader leaves the receive loop the + * moment the counter reaches zero, so it is never both inside the loop asking + * for a chunk and publishing a verdict. Once it has left, the next STAT write + * is a command rather than a count, so feeding one more chunk after a verdict + * cannot underflow anything either. + / +static int mxl862xx_sb_pdi_poll_drain(struct mxl862xx_priv priv, + unsigned long timeout_ms) +{ + int val; + + read_poll_timeout(mxl862xx_smdio_read, val, + val < 0 \|\| (u16)val == MXL862XX_SB_PDI_READY \|\| + (u16)val == 0, + 50, timeout_ms * 1000, false, + priv, MXL862XX_SB_PDI_STAT); + if (val < 0) + return val; + return (u16)val; +} + +/* The loader is not asking for a chunk: it may still be programming the last + * one, or the counter has reached zero and it is verifying the image and + * resetting into READY. Wait that out -- STAT cannot tell the two apart, and + * guessing would mean writing END into a live receive loop. + * + * Return: 0 once the loader has left the loop, -EAGAIN if it asks for another + * chunk after all, -EIO for a loader still holding the count when the verify + * window expires, or an SMDIO bus error. + / +static int mxl862xx_rescue_drain_finish(struct mxl862xx_priv priv, u32 chunk) +{ + struct device dev = &priv->mdiodev->dev; + int stat; + + stat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_VERIFY_MS); + if (stat < 0) + return stat; + if (stat == MXL862XX_SB_PDI_READY) + return 0; + if (stat == MXL862XX_SB_PDI_VERIFY_BAD) { + dev_err(dev, + "flash: loader stuck after %u chunks, power cycle it\n", + chunk); + return -EIO; + } + if (stat) { + / A firmware is answering, not the loader: an image survived + * in flash and booted. + / + dev_info(dev, "flash: firmware booted while draining\n"); + return 0; + } + + return -EAGAIN; +} + +/ Recover a switch whose SB PDI download was interrupted mid-transfer - the + * host died after MCUboot began erasing flash, whether it aborted mid erase or + * mid image-write, both end up in the same place: the payload receive loop. + * There the loader publishes STAT=0, waits for the host to write a byte-count + * to STAT, DMAs that many bytes and subtracts the count from a remaining-bytes + * counter, leaving the loop only when the counter reaches exactly zero. The + * image size died with the host, so we feed single-byte chunks (see + * MXL862XX_DRAIN_CHUNK_BYTES) to walk the counter to zero without underflow. + * The loader then verifies the (now corrupt) image and returns to READY by + * itself, or boots a valid image that happened to survive in flash; either way + * the caller's reprobe classifies the result. Every byte costs about a dozen + * MDIO frames, so a multi-MiB outstanding count takes tens of minutes. + * Returns 0 once the loader has left the receive loop, <0 on error. Does NOT + * recover a counter already underflowed by an earlier oversized-chunk attempt + * - that needs a power cycle. + / +static int mxl862xx_rescue_drain(struct mxl862xx_priv priv) +{ + struct device dev = &priv->mdiodev->dev; + / Bound: twice the loader's 16 MiB image cap, one byte per chunk. / + u32 max_chunks = 2u (16u << 20) / MXL862XX_DRAIN_CHUNK_BYTES; + u32 chunk = 0; + int ret, stat; + + while (chunk < max_chunks) { + /* Teardown can interrupt this long drain. / + if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags)) + return -ECANCELED; + + stat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS); + if (stat < 0) + return stat; + if (stat == MXL862XX_SB_PDI_READY) + return 0; + + if (stat) { + ret = mxl862xx_rescue_drain_finish(priv, chunk); + if (ret != -EAGAIN) + return ret; + } + + / Feed one zero byte; reset cleared the write latch. / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + return ret; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000); + if (ret < 0) + return ret; + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_DRAIN_CHUNK_BYTES); + if (ret < 0) + return ret; + chunk++; + if (!(chunk % MXL862XX_DRAIN_LOG_BYTES)) + dev_info(dev, "flash: drained %u KiB so far\n", + chunk / 1024); + cond_resched(); + } + + dev_err(dev, + "flash: interrupted download did not drain after %u chunks\n", + chunk); + + return -ETIMEDOUT; +} + +/ Background self-heal: drain a wedged download off the devlink flash path, so + * the long recovery never holds the devlink lock. Scheduled from probe; + * reprobes on success so the probe-time detection re-classifies the switch. + / +void mxl862xx_rescue_heal_work_fn(struct work_struct work) +{ + struct mxl862xx_priv priv = + container_of(work, struct mxl862xx_priv, rescue_heal_work); + struct device dev = &priv->mdiodev->dev; + int ret; + + ret = mxl862xx_rescue_drain(priv); + if (ret == -ECANCELED) + return; + if (ret) { + /* Nothing retries this, so say so: rescue_ready stays clear + * and devlink dev flash reports why it refuses. + / + dev_err(dev, "flash: download recovery failed: %pe\n", + ERR_PTR(ret)); + WRITE_ONCE(priv->rescue_failed, true); + return; + } + + / The interrupted transfer is finalised; reprobe so the probe-time + * detection brings the driver up -- flashable in rescue mode if the + * loader is at READY, or normally if a valid image booted. The core + * skips the re-probe on its own if the device is unbound first; the + * flag test only avoids scheduling one certain to be skipped. A + * failed hand-off leaves nothing to reclassify the switch, so mark + * recovery failed rather than promise a retry that cannot succeed. + / + if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags)) + return; + + if (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS)) + WRITE_ONCE(priv->rescue_failed, true); +} + +/ Detect MCUboot rescue mode over clause-22 SMDIO alone, so the caller can rule + * the loader out before any C45 API request (which spews CRC errors when no WSP + * firmware answers). A scratch write to ADDR/DATA must latch or the chip is + * absent (-ENODEV); the mailbox is reset first, or a transfer interrupted with + * CTRL=WR would take that write as a payload word instead of latching it. STAT + * then classifies the state, poked destructively only when 0, the one value a + * running firmware never holds: + * + * - 0xc33c: flashless loop; recognised but not supported here. + * - 0xc55c: console loop, if the register-read challenge is serviced. + * - other non-zero: running firmware, left unpoked. + * - 0: wedged receive loop; the 1-byte slice-advance then says whether it + * still needs draining or has just finished. + * + * The scratch write reaches a running firmware too, but lands in mailbox + * registers it does not read, so it is inert there. + * + * Return: MXL862XX_IN_RESCUE, MXL862XX_NOT_RESCUE, -ENODEV when the scratch + * write does not latch, which is a switch that does not answer at all or one + * whose SB PDI window is not at the offsets above, -EOPNOTSUPP for the + * flashless loop, -ENXIO for a READY loader whose mailbox fails the challenge, + * or an SMDIO bus error. + / +int mxl862xx_rescue_mode_detect(struct mxl862xx_priv priv) +{ + int stat, dat, ret, rb, a, d; + + /* rescue_ready gates flashing; a wedged loader needs the drain first. / + WRITE_ONCE(priv->rescue_ready, false); + + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + + / Presence: a live chip latches the scratch write, an absent one floats. / + a = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR, + MXL862XX_SB_PDI_PROBE_A); + if (a < 0) + return a; + d = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, + MXL862XX_SB_PDI_PROBE_D); + if (d < 0) + return d; + a = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_ADDR); + if (a < 0) + return a; + d = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA); + if (d < 0) + return d; + if ((u16)a != MXL862XX_SB_PDI_PROBE_A \|\| + (u16)d != MXL862XX_SB_PDI_PROBE_D) + return -ENODEV; + + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + + stat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_STAT); + if (stat < 0) + return stat; + + / Flashless-download loop (MxL86281S tier): this driver does not + * support it -- the console flash path expects READY. Treat it as an + * unusable configuration, like any other unsupported state. + / + if ((u16)stat == MXL862XX_SB_PDI_DL_READY) + return -EOPNOTSUPP; + + / Console loop at READY: confirm the live mailbox with the register-read + * challenge (consumes the marker from DATA and re-arms READY). + / + if ((u16)stat == MXL862XX_SB_PDI_READY) { + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, + MXL862XX_SB_PDI_RDREG_MARK); + if (ret < 0) + return ret; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_SB_PDI_RDREG); + if (ret < 0) + return ret; + rb = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY, + MXL862XX_SB_PDI_STEP_MS); + dat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA); + ret = mxl862xx_sb_pdi_reset(priv); + / Never re-arming READY fails the challenge like any other + * unserviced command; report it as such rather than as a bus + * timeout the bus never saw. + / + if (rb == -ETIMEDOUT) + rb = -ENXIO; + if (rb < 0) + return rb; + if (dat < 0) + return dat; + if (ret < 0) + return ret; + if ((u16)dat != MXL862XX_SB_PDI_RDREG_MARK) { + WRITE_ONCE(priv->rescue_ready, true); + return MXL862XX_IN_RESCUE; + } + / READY but the marker is untouched, so nothing is servicing the + * mailbox. A firmware publishing 0xc55c as its status word looks + * exactly like this, and flashing one would be far worse than + * refusing to bind, so treat it as unusable. + / + return -ENXIO; + } + + / Any other non-zero value is a running firmware, not a loader. / + if (stat) + return MXL862XX_NOT_RESCUE; + + / STAT == 0: a wedged receive loop takes a 1-byte slice-advance (feed + * one DATA word first, like a drain chunk) and asks for the next chunk + * by publishing 0 again. Had that byte been the last one outstanding, + * the loader leaves the loop instead and returns to READY, having + * consumed the advance -- proof enough of a live mailbox to skip the + * challenge. Anything else means it is still working on it. All three + * are rescue, so this never fails probe; only the drain does. + / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + return ret; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000); + if (ret < 0) + return ret; + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + return ret; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_DRAIN_CHUNK_BYTES); + if (ret < 0) + return ret; + + rb = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS); + if (rb < 0) + return rb; + if (rb == MXL862XX_SB_PDI_READY) + WRITE_ONCE(priv->rescue_ready, true); + + return MXL862XX_IN_RESCUE; +} + +/ MCUboot firmware image header / +struct mxl862xx_fw_hdr { + __le32 image_type; + __le32 image_size_1; + __le32 image_checksum_1; + __le32 image_size_2; + __le32 image_checksum_2; +} __packed; + +static int mxl862xx_flash_validate(struct mxl862xx_priv priv, + const struct firmware fw, + u32 payload_size) +{ + const struct mxl862xx_fw_hdr hdr; + u32 size1, size2, total; + const u8 payload; + u32 crc; + + if (fw->size < MXL862XX_FW_HDR_SIZE) + return -EINVAL; + + hdr = (const struct mxl862xx_fw_hdr )fw->data; + payload = fw->data + MXL862XX_FW_HDR_SIZE; + size1 = le32_to_cpu(hdr->image_size_1); + size2 = le32_to_cpu(hdr->image_size_2); + + if (check_add_overflow(size1, size2, &total) \|\| + total > fw->size - MXL862XX_FW_HDR_SIZE) { + dev_err(&priv->mdiodev->dev, + "flash: firmware file too small for declared size\n"); + return -EINVAL; + } + + if (!total) { + dev_err(&priv->mdiodev->dev, + "flash: firmware file with empty payload\n"); + return -EINVAL; + } + + if (size1) { + crc = ~crc32_le(~0U, payload, size1); + if (crc != le32_to_cpu(hdr->image_checksum_1)) { + dev_err(&priv->mdiodev->dev, + "flash: image 1 CRC mismatch (got %08x, expected %08x)\n", + crc, le32_to_cpu(hdr->image_checksum_1)); + return -EINVAL; + } + } + + if (size2) { + crc = ~crc32_le(~0U, payload + size1, size2); + if (crc != le32_to_cpu(hdr->image_checksum_2)) { + dev_err(&priv->mdiodev->dev, + "flash: image 2 CRC mismatch (got %08x, expected %08x)\n", + crc, le32_to_cpu(hdr->image_checksum_2)); + return -EINVAL; + } + } + + payload_size = total; + + return 0; +} + +static int mxl862xx_flash_firmware(struct mxl862xx_priv priv, + const struct firmware fw, + u32 payload_size, struct devlink dl) +{ + const u8 payload = fw->data + MXL862XX_FW_HDR_SIZE; + u32 word_idx = 0, data_written = 0, idx = 0; + unsigned long next_notify = jiffies - 1; + u16 word, fdata; + int ret, i; + + /* Step 1: reboot the firmware into MCUboot rescue mode / + if (!priv->rescue_mode) { + ret = mxl862xx_api_wrap(priv, SYS_MISC_FW_UPDATE, NULL, 0, + false, false); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: FW_UPDATE command failed: %pe\n", + ERR_PTR(ret)); + return ret; + } + } + + / Step 2: wait for bootloader ready / + mxl862xx_flash_notify(dl, "Waiting for bootloader", 0, 0); + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + goto write_err; + + / Failures from here on end up at no_end, which returns the error + * without signalling END -- see there. + / + ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY, + MXL862XX_FW_READY_TIMEOUT_MS); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: bootloader not ready: %pe\n", ERR_PTR(ret)); + goto no_end; + } + + / Step 3: start handshake / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_SB_PDI_START); + if (ret < 0) + goto write_err; + + ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_START + 1, + MXL862XX_FW_ACK_TIMEOUT_MS); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: start handshake failed: %pe\n", ERR_PTR(ret)); + goto no_end; + } + + / Step 4: transfer image header / + mxl862xx_flash_notify(dl, "Erasing flash", 0, 0); + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + goto write_err; + + for (i = 0; i < MXL862XX_FW_HDR_SIZE / 2; i++) { + word = fw->data[i 2] \| + ((u16)fw->data[i * 2 + 1] << 8); + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, word); + if (ret < 0) + goto write_err; + } + + ret = mxl862xx_sb_pdi_reset(priv); + if (ret < 0) + goto write_err; + + /* the byte count in STAT triggers the erase / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_FW_HDR_SIZE); + if (ret < 0) + goto write_err; + + / ACK is byte count + 1 / + ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_FW_HDR_SIZE + 1, + MXL862XX_FW_ACK_TIMEOUT_MS); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: header ACK failed: %pe\n", ERR_PTR(ret)); + goto no_end; + } + + / Step 5: wait for erase to complete / + ret = mxl862xx_sb_pdi_poll_stat(priv, 0, + MXL862XX_FW_ERASE_TIMEOUT_MS); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: erase timeout: %pe\n", ERR_PTR(ret)); + goto no_end; + } + + / Step 6: transfer payload / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + goto write_err; + + while (idx < payload_size) { + cond_resched(); + if (idx + 1 < payload_size) { + fdata = payload[idx] \| + ((u16)payload[idx + 1] << 8); + idx += 2; + data_written += 2; + } else { + fdata = payload[idx]; + idx++; + data_written++; + } + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, fdata); + if (ret < 0) + goto write_err; + word_idx++; + + if (idx >= payload_size) { + ret = mxl862xx_sb_pdi_flush_last(priv, data_written); + break; + } + + / Half-bank boundary: switch to SB1 address / + if (word_idx == MXL862XX_FW_BANK_HALF) { + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_RST); + if (ret < 0) + goto write_err; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR, + MXL862XX_FW_SB1_ADDR); + if (ret < 0) + goto write_err; + + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + goto write_err; + } else if (word_idx >= MXL862XX_FW_BANK_SLICE) { + ret = mxl862xx_sb_pdi_flush_slice(priv, data_written); + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: write timeout at %u/%u: %pe\n", + idx, payload_size, ERR_PTR(ret)); + goto no_end; + } + word_idx = 0; + data_written = 0; + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL, + MXL862XX_SB_PDI_CTRL_WR); + if (ret < 0) + goto write_err; + + if (time_after(jiffies, next_notify)) { + mxl862xx_flash_notify(dl, "Flashing", idx, + payload_size); + next_notify = jiffies + msecs_to_jiffies(500); + } + } + } + + if (ret) { + dev_err(&priv->mdiodev->dev, + "flash: final slice failed: %pe\n", ERR_PTR(ret)); + goto no_end; + } + + mxl862xx_flash_notify(dl, "Flashing", payload_size, payload_size); + + / Success: the loader has left the receive loop at r_remain == 0 and + * verified the image, so END(0x3cc3) is a finalise/boot request rather + * than a byte count. Signal it here -- and only here -- to boot the new + * image without waiting out the loader's 2 s END timeout. + / + ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, + MXL862XX_SB_PDI_END); + msleep(MXL862XX_FW_REBOOT_DELAY_MS); + return ret; + +write_err: + dev_err(&priv->mdiodev->dev, "flash: SMDIO write failed: %pe\n", + ERR_PTR(ret)); +no_end: + / A failure leaves the loader mid transfer; do not signal END (a STAT + * write is a byte count then, and END would be misread as one, risking + * a receive-counter underflow). Return the error; the caller reprobes. + / + return ret; +} + +int mxl862xx_devlink_info_get(struct dsa_switch ds, + struct devlink_info_req req, + struct netlink_ext_ack extack) +{ + struct mxl862xx_priv priv = ds->priv; + char buf[16]; + int ret; + + / No chip-id/revision in MCUboot (needs the firmware MMD mailbox). The + * fw version doubles as the "ready to flash" signal: report it only + * once the loader is at a clean READY, nothing while still draining. + / + if (priv->rescue_mode) { + if (!READ_ONCE(priv->rescue_ready)) + return 0; + + snprintf(buf, sizeof(buf), "%u.%u.%u", + priv->fw_version.major, priv->fw_version.minor, + priv->fw_version.revision); + ret = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, buf); + if (ret) + return ret; + return devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, buf); + } + + / A 0 part number means the CHIP ID read failed or the part is + * unfused; omit it rather than publish a bogus "0000" that fwupd + * would match firmware against -- it then falls back to the driver + * name. + / + if (priv->asic_id) { + snprintf(buf, sizeof(buf), "%04X", priv->asic_id); + ret = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, + buf); + if (ret) + return ret; + + snprintf(buf, sizeof(buf), "%u", priv->asic_rev); + ret = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_REV, + buf); + if (ret) + return ret; + } + + / An all-zero version is the cache a failed flash left behind, not a + * released firmware; omit it like the part number above. + / + if (!priv->fw_version.major && !priv->fw_version.minor && + !priv->fw_version.revision) + return 0; + + snprintf(buf, sizeof(buf), "%u.%u.%u", + priv->fw_version.major, priv->fw_version.minor, + priv->fw_version.revision); + + ret = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, buf); + if (ret) + return ret; + + / boots this image from its own flash: stored == running / + return devlink_info_version_stored_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, buf); +} + +int mxl862xx_devlink_flash_update(struct dsa_switch ds, + struct devlink_flash_update_params params, + struct netlink_ext_ack extack) +{ + struct mxl862xx_priv priv = ds->priv; + struct dsa_port dp; + u32 payload_size; + int ret, err, i; + + if (params->component) { + NL_SET_ERR_MSG_MOD(extack, "component is not supported"); + return -EOPNOTSUPP; + } + + /* A previous flash is still waiting for its reprobe: the firmware API + * is short-circuited, so the raw SB PDI writes below would run against + * a switch this driver no longer tracks. + / + if (priv->skip_teardown) { + NL_SET_ERR_MSG_MOD(extack, + "device is reinitializing, retry later"); + return -EBUSY; + } + + ret = mxl862xx_flash_validate(priv, params->fw, &payload_size); + if (ret) { + NL_SET_ERR_MSG_MOD(extack, "firmware image validation failed"); + return ret; + } + + / Refuse to flash while the background self-heal is still draining, and + * for good once it has given up on the loader. + / + if (READ_ONCE(priv->rescue_failed)) { + NL_SET_ERR_MSG_MOD(extack, + "download recovery failed, power cycle the switch"); + return -EIO; + } + + if (priv->rescue_mode && !READ_ONCE(priv->rescue_ready)) { + NL_SET_ERR_MSG_MOD(extack, + "switch is recovering an interrupted download, retry shortly"); + return -EBUSY; + } + + if (priv->rescue_mode) + dev_info(ds->dev, + "flash: flashing switch via MCUboot rescue mode\n"); + else + dev_info(ds->dev, "flash: running firmware %u.%u.%u\n", + priv->fw_version.major, priv->fw_version.minor, + priv->fw_version.revision); + + / Close ports while the firmware is still alive so the DSA core's + * MDB/FDB tracking is drained, and detach user ports so userspace + * cannot reopen them during the flash. The conduit is only closed, + * not detached: it belongs to the MAC driver. This driver binds a + * single switch with a direct host link and no cascade ports, so the + * conduit serves only this switch, and flashing it reboots the switch, + * which takes the tree down regardless. + / + rtnl_lock(); + dsa_switch_for_each_user_port(dp, ds) { + if (dp->user) { + dev_close(dp->user); + netif_device_detach(dp->user); + } + } + dsa_switch_for_each_cpu_port(dp, ds) + dev_close(dp->conduit); + / The bridge defers the STP state changes triggered by closing + * the ports; let them reach the firmware while it is still alive. + / + switchdev_deferred_process(); + rtnl_unlock(); + + mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED); + priv->block_host = true; + mutex_unlock(&priv->mdiodev->bus->mdio_lock); + + set_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags); + cancel_delayed_work_sync(&priv->stats_work); + cancel_work_sync(&priv->crc_err_work); + for (i = 0; i < ds->num_ports; i++) + cancel_work_sync(&priv->ports[i].host_flood_work); + + ret = mxl862xx_flash_firmware(priv, params->fw, payload_size, + ds->devlink); + if (ret) + NL_SET_ERR_MSG_MOD(extack, "firmware transfer failed"); + + if (!ret) { + mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, + MDIO_MUTEX_NESTED); + / Keep block_host set so host writes stay blocked, but let the + * readiness poll below read the freshly booted firmware. + / + priv->flash_reading = true; + priv->rescue_mode = false; + mutex_unlock(&priv->mdiodev->bus->mdio_lock); + + / Refresh the cached versions so the flash update only + * completes once the new firmware is confirmed running and + * devlink dev info reports it. Must happen before setting + * skip_teardown, which discards all firmware API reads. + / + ret = mxl862xx_wait_ready(ds); + if (ret) + NL_SET_ERR_MSG_MOD(extack, + "new firmware did not become ready"); + } + + if (ret) { + / The switch is in MCUboot with erased or partly written flash; + * drop the cached identity so devlink dev info stops reporting + * the pre-flash version until the reprobe re-reads the truth. + / + memset(&priv->fw_version, 0, sizeof(priv->fw_version)); + priv->asic_id = 0; + priv->asic_rev = 0; + } + + mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED); + priv->flash_reading = false; + priv->block_host = false; + priv->skip_teardown = true; + mutex_unlock(&priv->mdiodev->bus->mdio_lock); + + / Reinitialise through a deferred re-probe: remove() runs with + * skip_teardown set, then a fresh probe() starts against whatever + * the switch now runs. The core skips the re-probe if the device + * is unbound or shut down before it fires. + / + err = device_schedule_reprobe(ds->dev, MXL862XX_FW_REPROBE_DELAY_MS); + + return ret ? ret : err; +} diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.h b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h new file mode 100644 index 0000000000000..7cd87c7ad8716 --- /dev/null +++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h @@ -0,0 +1,20 @@ +/ SPDX-License-Identifier: GPL-2.0-or-later / + +#ifndef __MXL862XX_FW_H +#define __MXL862XX_FW_H + +#include <net/dsa.h> + +struct mxl862xx_priv; +struct work_struct; + +int mxl862xx_rescue_mode_detect(struct mxl862xx_priv priv); +void mxl862xx_rescue_heal_work_fn(struct work_struct work); +int mxl862xx_devlink_info_get(struct dsa_switch ds, + struct devlink_info_req req, + struct netlink_ext_ack extack); +int mxl862xx_devlink_flash_update(struct dsa_switch ds, + struct devlink_flash_update_params params, + struct netlink_ext_ack extack); + +#endif / __MXL862XX_FW_H / diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.c b/drivers/net/dsa/mxl862xx/mxl862xx-host.c index 4acd216f7cc00..23e5dfe81e364 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx-host.c +++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.c @@ -15,6 +15,8 @@ #include <linux/unaligned.h> #include <net/dsa.h> #include "mxl862xx.h" +#include "mxl862xx-cmd.h" +#include "mxl862xx-fw.h" #include "mxl862xx-host.h" #define CTRL_BUSY_MASK BIT(15) @@ -340,6 +342,26 @@ int mxl862xx_api_wrap(struct mxl862xx_priv priv, u16 cmd, void _data, mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED); + if (priv->skip_teardown) { + ret = read ? -ENODEV : 0; + goto out; + } + + if (priv->rescue_mode) { + ret = -ENODEV; + goto out; + } + + / During the post-flash readiness poll block_host stays set, but the + * flash path's own firmware version reads must reach the new image; + * host writes stay blocked so stale resource IDs cannot corrupt it. + / + if (priv->block_host && cmd != SYS_MISC_FW_UPDATE && + !(priv->flash_reading && read)) { + ret = -EBUSY; + goto out; + } + max = (size + 1) / 2; ret = mxl862xx_busy_wait(priv); @@ -495,12 +517,54 @@ int mxl862xx_reset(struct mxl862xx_priv priv) return ret; } +#define MXL862XX_SMDIO_ADDR_REG 0x1f +#define MXL862XX_SMDIO_PAGE_MASK 0xfff0 +#define MXL862XX_SMDIO_OFF_MASK 0x000f + +/* Paged clause-22 window: the page goes into MII register 0x1f, the low nibble + * of addr selects one of the 16 registers within it. Both helpers take the MDIO + * bus lock per transaction, so callers must not already hold it -- unlike + * mxl862xx_api_wrap(), which holds it across a whole firmware command. + / +int mxl862xx_smdio_read(struct mxl862xx_priv priv, u32 addr) +{ + struct mii_bus bus = priv->mdiodev->bus; + int phy = priv->mdiodev->addr; + int ret; + + mutex_lock(&bus->mdio_lock); + ret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG, + addr & MXL862XX_SMDIO_PAGE_MASK); + if (ret >= 0) + ret = __mdiobus_read(bus, phy, addr & MXL862XX_SMDIO_OFF_MASK); + mutex_unlock(&bus->mdio_lock); + return ret; +} + +int mxl862xx_smdio_write(struct mxl862xx_priv priv, u32 addr, u16 val) +{ + struct mii_bus bus = priv->mdiodev->bus; + int phy = priv->mdiodev->addr; + int ret; + + mutex_lock(&bus->mdio_lock); + ret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG, + addr & MXL862XX_SMDIO_PAGE_MASK); + if (ret >= 0) + ret = __mdiobus_write(bus, phy, addr & MXL862XX_SMDIO_OFF_MASK, + val); + mutex_unlock(&bus->mdio_lock); + return ret; +} + void mxl862xx_host_init(struct mxl862xx_priv priv) { INIT_WORK(&priv->crc_err_work, mxl862xx_crc_err_work_fn); + INIT_WORK(&priv->rescue_heal_work, mxl862xx_rescue_heal_work_fn); } void mxl862xx_host_shutdown(struct mxl862xx_priv priv) { cancel_work_sync(&priv->crc_err_work); + cancel_work_sync(&priv->rescue_heal_work); } diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.h b/drivers/net/dsa/mxl862xx/mxl862xx-host.h index 66d6ae198aff4..4e054c6e4c0e4 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx-host.h +++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.h @@ -18,5 +18,7 @@ int mxl862xx_api_wrap(struct mxl862xx_priv priv, u16 cmd, void data, u16 size, mxl862xx_api_wrap(dev, cmd, &(data), sizeof((data)), true, true) int mxl862xx_reset(struct mxl862xx_priv priv); +int mxl862xx_smdio_read(struct mxl862xx_priv priv, u32 addr); +int mxl862xx_smdio_write(struct mxl862xx_priv priv, u32 addr, u16 val); #endif /* __MXL862XX_HOST_H / diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c index b689652aa9b92..a5b6940b552e9 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c +++ b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c @@ -406,6 +406,8 @@ mxl862xx_phylink_mac_select_pcs(struct phylink_config config, switch (port) { case 9 ... 16: + if (priv->rescue_mode) + return NULL; if (!MXL862XX_FW_VER_MIN(priv, 1, 0, 84)) { dev_warn_once(dp->ds->dev, "SerDes PCS unsupported on old firmware.\n"); diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c index 45d237b3a40f1..74abf88c09cc6 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx.c +++ b/drivers/net/dsa/mxl862xx/mxl862xx.c @@ -21,6 +21,7 @@ #include "mxl862xx.h" #include "mxl862xx-api.h" #include "mxl862xx-cmd.h" +#include "mxl862xx-fw.h" #include "mxl862xx-host.h" #include "mxl862xx-phylink.h" @@ -71,6 +72,13 @@ static const struct ethtool_rmon_hist_range mxl862xx_rmon_ranges[] = { #define MXL862XX_READY_TIMEOUT_MS 10000 #define MXL862XX_READY_POLL_MS 100 +/* Chip ID registers, read via SYS_MISC_REG_RD / +#define MXL862XX_CHIPID_L 0xc0d28884 +#define MXL862XX_CHIPID_M 0xc0d28888 +#define MXL862XX_CHIPID_L_PNUML GENMASK(15, 12) +#define MXL862XX_CHIPID_M_PNUMM GENMASK(11, 0) +#define MXL862XX_CHIPID_M_VERSION GENMASK(14, 12) + #define MXL862XX_TCM_INST_SEL 0xe00 #define MXL862XX_TCM_CBS 0xe12 #define MXL862XX_TCM_EBS 0xe13 @@ -222,7 +230,46 @@ static int mxl862xx_phy_write_c45_mii_bus(struct mii_bus bus, int addr, return mxl862xx_phy_write_mmd(bus->priv, addr, devadd, regnum, val); } -static int mxl862xx_wait_ready(struct dsa_switch ds) +/ Read the static chip part number and version from the CHIP ID + * registers. Only possible with a running firmware, so the values are + * cached at setup and left zero when the switch is in rescue mode. + / +static int mxl862xx_read_chip_id(struct mxl862xx_priv priv) +{ + struct mxl862xx_sys_reg_rw reg = {}; + u16 chipid_l, chipid_m; + int ret; + + reg.addr = cpu_to_le32(MXL862XX_CHIPID_L); + ret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg); + if (ret) + return ret; + chipid_l = le32_to_cpu(reg.val); + + reg.addr = cpu_to_le32(MXL862XX_CHIPID_M); + ret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg); + if (ret) + return ret; + chipid_m = le32_to_cpu(reg.val); + + priv->asic_id = FIELD_GET(MXL862XX_CHIPID_L_PNUML, chipid_l) \| + FIELD_GET(MXL862XX_CHIPID_M_PNUMM, chipid_m) << 4; + priv->asic_rev = FIELD_GET(MXL862XX_CHIPID_M_VERSION, chipid_m); + + return 0; +} + +/** + * mxl862xx_wait_ready - wait for the switch firmware to become operational + * @ds: DSA switch instance + * + * Poll the firmware until it reports its version and accepts + * configuration commands, then cache the firmware version and chip ID. + * Takes at least two seconds. + * + * Return: 0 on success or a negative error code. + / +int mxl862xx_wait_ready(struct dsa_switch ds) { struct mxl862xx_sys_fw_image_version ver = {}; unsigned long start = jiffies, timeout; @@ -254,6 +301,11 @@ static int mxl862xx_wait_ready(struct dsa_switch ds) priv->fw_version.major = ver.iv_major; priv->fw_version.minor = ver.iv_minor; priv->fw_version.revision = le16_to_cpu(ver.iv_revision); + + ret = mxl862xx_read_chip_id(priv); + if (ret) + dev_warn(ds->dev, "failed to read chip ID: %pe\n", + ERR_PTR(ret)); return 0; not_ready_yet: @@ -622,21 +674,66 @@ static int mxl862xx_setup(struct dsa_switch ds) int n_user_ports = 0, max_vlans; int ingress_finals, vid_rules; struct dsa_port dp; - int ret, i; - - ret = mxl862xx_reset(priv); - if (ret) - return ret; - - ret = mxl862xx_wait_ready(ds); - if (ret) - return ret; + int ret, i, rescue; + / The SerDes state is software-only and must exist before anything can + * reach phylink, including a rescue-mode flash clearing rescue_mode + * ahead of the reprobe. + / mutex_init(&priv->serdes_lock); for (i = 0; i < ARRAY_SIZE(priv->serdes_ports); i++) mxl862xx_setup_pcs(priv, &priv->serdes_ports[i], i + MXL862XX_FIRST_SERDES_PORT); + / Detect the loader over SB PDI first: it needs no firmware, unlike the + * C45 API (mxl862xx_reset/wait_ready) which spews CRC errors when none + * answers. Touch C45 only once rescue is ruled out. + / + rescue = mxl862xx_rescue_mode_detect(priv); + if (rescue < 0) { + dev_err(ds->dev, "switch state detection failed: %pe\n", + ERR_PTR(rescue)); + return rescue; + } + + if (rescue == MXL862XX_NOT_RESCUE) { + ret = mxl862xx_reset(priv); + if (ret) + return ret; + + ret = mxl862xx_wait_ready(ds); + if (ret) { + / the reset may only now have triggered rescue mode / + rescue = mxl862xx_rescue_mode_detect(priv); + if (rescue < 0) { + dev_err(ds->dev, + "switch not responding after reset: %pe\n", + ERR_PTR(rescue)); + return rescue; + } + if (rescue == MXL862XX_NOT_RESCUE) + return ret; + } + } + + priv->rescue_mode = rescue; + + if (priv->rescue_mode) { + if (priv->rescue_ready) { + dev_warn(ds->dev, + "switch in MCUboot rescue mode, use devlink to flash new firmware\n"); + } else { + / Drain the wedged download in the background so it + * never holds the devlink lock; info and flash become + * available once ready. + / + dev_warn(ds->dev, + "switch in MCUboot with an interrupted download, recovering in background\n"); + queue_work(system_long_wq, &priv->rescue_heal_work); + } + return 0; + } + / Calculate Extended VLAN block sizes. * With VLAN Filter handling VID membership checks: * Ingress: only final catchall rules (PVID insertion, 802.1Q @@ -715,11 +812,21 @@ static int mxl862xx_port_state(struct dsa_switch ds, int port, bool enable) static int mxl862xx_port_enable(struct dsa_switch ds, int port, struct phy_device phydev) { + struct mxl862xx_priv priv = ds->priv; + + if (priv->rescue_mode) + return 0; + return mxl862xx_port_state(ds, port, true); } static void mxl862xx_port_disable(struct dsa_switch ds, int port) { + struct mxl862xx_priv priv = ds->priv; + + if (priv->rescue_mode) + return; + if (mxl862xx_port_state(ds, port, false)) dev_err(ds->dev, "failed to disable port %d\n", port); } @@ -1337,6 +1444,17 @@ static int mxl862xx_port_setup(struct dsa_switch ds, int port) bool is_cpu_port = dsa_port_is_cpu(dp); int ret; + if (dsa_port_is_dsa(dp)) { + dev_err(ds->dev, "port %d: DSA links not supported\n", port); + return -EOPNOTSUPP; + } + + / DSA reinits failed user ports as unused; shared ports must + * succeed for the tree to register. + / + if (priv->rescue_mode) + return dsa_port_is_user(dp) ? -ENODEV : 0; + ret = mxl862xx_port_state(ds, port, false); if (ret) return ret; @@ -1346,11 +1464,6 @@ static int mxl862xx_port_setup(struct dsa_switch ds, int port) if (dsa_port_is_unused(dp)) return 0; - if (dsa_port_is_dsa(dp)) { - dev_err(ds->dev, "port %d: DSA links not supported\n", port); - return -EOPNOTSUPP; - } - ret = mxl862xx_configure_sp_tag_proto(ds, port, is_cpu_port); if (ret) return ret; @@ -1572,6 +1685,12 @@ static int mxl862xx_port_mdb_del(struct dsa_switch ds, int port, ether_addr_copy(qparam.mac, mdb->addr); ret = MXL862XX_API_READ(priv, MXL862XX_MAC_TABLEENTRYQUERY, qparam); + / Post-flash teardown or MCUboot: the firmware and its MAC table are + * gone, so there is nothing left to delete. Outside those, -ENODEV is a + * bus error and must be reported. + / + if (ret == -ENODEV && (priv->skip_teardown \|\| priv->rescue_mode)) + return 0; if (ret) return ret; @@ -1628,6 +1747,9 @@ static void mxl862xx_port_stp_state_set(struct dsa_switch ds, int port, struct mxl862xx_priv priv = ds->priv; int ret; + if (priv->rescue_mode) + return; + switch (state) { case BR_STATE_DISABLED: param.port_state = cpu_to_le32(MXL862XX_STP_PORT_STATE_DISABLE); @@ -2015,6 +2137,12 @@ static void mxl862xx_stats_work_fn(struct work_struct work) struct dsa_switch ds = priv->ds; struct dsa_port dp; + /* A get_stats64() re-arm can race the flash teardown's WORK_STOPPED + * set and cancel; bail here so a stray poll never runs during a flash. + / + if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags)) + return; + dsa_switch_for_each_available_port(dp, ds) mxl862xx_stats_poll(ds, dp->index); @@ -2086,6 +2214,8 @@ static const struct dsa_switch_ops mxl862xx_switch_ops = { .get_pause_stats = mxl862xx_get_pause_stats, .get_rmon_stats = mxl862xx_get_rmon_stats, .get_stats64 = mxl862xx_get_stats64, + .devlink_info_get = mxl862xx_devlink_info_get, + .devlink_flash_update = mxl862xx_devlink_flash_update, }; static int mxl862xx_probe(struct mdio_device mdiodev) @@ -2151,10 +2281,16 @@ static void mxl862xx_remove(struct mdio_device mdiodev) priv = ds->priv; set_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags); - cancel_delayed_work_sync(&priv->stats_work); dsa_unregister_switch(ds); + / Cancel the stats poll only after the user netdevs are gone: until + * dsa_unregister_switch() returns a get_stats64() can still re-arm the + * work after a plain cancel, and it would then run against the + * devres-freed priv. + / + cancel_delayed_work_sync(&priv->stats_work); + mxl862xx_host_shutdown(priv); / Cancel any pending host flood work. dsa_unregister_switch() diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.h b/drivers/net/dsa/mxl862xx/mxl862xx.h index 432a5f3f2e08e..bdaf295c8a9f6 100644 --- a/drivers/net/dsa/mxl862xx/mxl862xx.h +++ b/drivers/net/dsa/mxl862xx/mxl862xx.h @@ -4,7 +4,9 @@ #define __MXL862XX_H #include <asm/byteorder.h> +#include <linux/bitops.h> #include <linux/mdio.h> +#include <linux/mutex.h> #include <linux/workqueue.h> #include <net/dsa.h> @@ -14,6 +16,10 @@ struct mxl862xx_priv; #define MXL862XX_FIRST_SERDES_PORT 9 #define MXL862XX_SERDES_SLOTS 4 +/* mxl862xx_rescue_mode_detect() return codes (negative values are errors) / +#define MXL862XX_NOT_RESCUE 0 +#define MXL862XX_IN_RESCUE 1 + #define MXL862XX_DEFAULT_BRIDGE 0 #define MXL862XX_MAX_BRIDGES 48 #define MXL862XX_MAX_BRIDGE_PORTS 128 @@ -303,6 +309,10 @@ struct mxl862xx_fw_version { flooding) * @fw_version: cached firmware version, populated at probe and * compared with MXL862XX_FW_VER_MIN() + * @asic_id: chip part number read from the CHIP ID registers, + * reported as the devlink "asic.id" fixed version + * @asic_rev: chip version read from the CHIP ID registers, + * reported as the devlink "asic.rev" fixed version * @serdes_ports: SerDes interfaces incl. sub-interfaces in case of * 10G_QXGMII or QSGMII * @serdes_refcount: per-XPCS count of sub-ports enabled by phylink; @@ -319,6 +329,22 @@ struct mxl862xx_fw_version { * @evlan_ingress_size: per-port ingress Extended VLAN block size * @evlan_egress_size: per-port egress Extended VLAN block size * @vf_block_size: per-port VLAN Filter block size + * @block_host: reject firmware API commands (except FW_UPDATE) + * during a firmware flash + * @flash_reading: let the flash path's own firmware reads through + * block_host while polling the freshly booted image + * @skip_teardown: discard firmware API commands during the teardown + * triggered by the post-flash reprobe + * @rescue_mode: switch is in MCUboot; firmware API commands fail fast, + * only clause-22 SMDIO works. Set from setup() before the + * switch is registered and cleared under the MDIO bus lock + * for the benefit of mxl862xx_api_wrap(); other readers + * only need it to be a stable single flag. + * @rescue_ready: (rescue_mode) loader is at a clean READY and will accept + * a flash; false while rescue_heal_work is draining + * @rescue_failed: (rescue_mode) the self-heal gave up; the loader needs a + * power cycle and no flash can be accepted + * @rescue_heal_work: background self-heal draining a wedged download to READY * @stats_work: periodic work item that polls RMON hardware counters * and accumulates them into 64-bit per-port stats / @@ -326,9 +352,12 @@ struct mxl862xx_priv { struct dsa_switch ds; struct mdio_device mdiodev; struct work_struct crc_err_work; + struct work_struct rescue_heal_work; unsigned long flags; u16 drop_meter; struct mxl862xx_fw_version fw_version; + u16 asic_id; + u8 asic_rev; struct mxl862xx_pcs serdes_ports[8]; int serdes_refcount[2]; struct mutex serdes_lock; @@ -337,7 +366,15 @@ struct mxl862xx_priv { u16 evlan_ingress_size; u16 evlan_egress_size; u16 vf_block_size; + bool block_host; + bool flash_reading; + bool skip_teardown; + bool rescue_mode; + bool rescue_ready; + bool rescue_failed; struct delayed_work stats_work; }; +int mxl862xx_wait_ready(struct dsa_switch ds); + #endif /* __MXL862XX_H / diff --git a/include/linux/device.h b/include/linux/device.h index aee79fd6b32b4..7a99169505772 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1314,6 +1314,8 @@ int __must_check device_attach(struct device dev); int __must_check driver_attach(const struct device_driver drv); void device_initial_probe(struct device dev); int __must_check device_reprobe(struct device dev); +int __must_check device_schedule_reprobe(struct device dev, + unsigned int delay_ms); bool device_is_bound(struct device dev); diff --git a/include/net/dsa.h b/include/net/dsa.h index 6f7f5c17b5320..58597b14e592a 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1172,6 +1172,9 @@ struct dsa_switch_ops { int (devlink_info_get)(struct dsa_switch ds, struct devlink_info_req req, struct netlink_ext_ack extack); + int (devlink_flash_update)(struct dsa_switch ds, + struct devlink_flash_update_params params, + struct netlink_ext_ack extack); int (devlink_sb_pool_get)(struct dsa_switch ds, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info pool_info); diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c index ed342f345692b..25311a87cbc56 100644 --- a/net/dsa/devlink.c +++ b/net/dsa/devlink.c @@ -20,6 +20,18 @@ static int dsa_devlink_info_get(struct devlink dl, return -EOPNOTSUPP; } +static int dsa_devlink_flash_update(struct devlink dl, + struct devlink_flash_update_params params, + struct netlink_ext_ack extack) +{ + struct dsa_switch ds = dsa_devlink_to_ds(dl); + + if (!ds->ops->devlink_flash_update) + return -EOPNOTSUPP; + + return ds->ops->devlink_flash_update(ds, params, extack); +} + static int dsa_devlink_sb_pool_get(struct devlink dl, unsigned int sb_index, u16 pool_index, struct devlink_sb_pool_info pool_info) @@ -169,6 +181,7 @@ dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port dlp, static const struct devlink_ops dsa_devlink_ops = { .info_get = dsa_devlink_info_get, + .flash_update = dsa_devlink_flash_update, .sb_pool_get = dsa_devlink_sb_pool_get, .sb_pool_set = dsa_devlink_sb_pool_set, .sb_port_pool_get = dsa_devlink_sb_port_pool_get,
3/2	2026/08/16 23:35	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 29248 output: 20 thoughts: 696 Thoughts: Reaching the MxL862xx Firmware Flash Functionality Okay, so this patch introduces firmware flashing and devlink support for the MaxLinear MxL862xx switch driver, which is interesting. It also adds a core function, `device_schedule_reprobe` in `drivers/base/dd.c`, and a `devlink_flash_update` to `struct dsa_switch_ops` and implements it in `net/dsa/devlink.c`. My immediate thought is, "Can we actually reach this code?" I see that `device_schedule_reprobe` is added and used by `mxl862xx-fw.c`, and `dsa_devlink_flash_update` to `dsa_devlink_ops`. The `mxl862xx` driver, as the name suggests, is a DSA driver. Now, the key question is, can this be triggered in a virtualized environment like syzkaller? The MxL862xx is a hardware switch. That's a problem. It's also an MDIO device. MDIO devices are usually probed if we register a software MDIO bus or use a dummy MDIO device. While syzkaller isn't typically set up to emulate specific MDIO devices, it can inject netlink commands. Aha! We can send `devlink` commands to any registered devlink instance. Can we somehow get syzkaller to create a dummy MxL862xx device? Let's figure out if there is a way to instantiate `mxl862xx` via software. MDIO devices usually rely on device tree or board code for instantiation. But then, `device_schedule_reprobe` is a core driver function, and it's added in `drivers/base/dd.c`. This opens up a fuzzing possibility! The `device_schedule_reprobe` function schedules a delayed work to reprobe a device. It takes a device pointer and a delay, and it’s called by `mxl862xx_devlink_flash_update` and `mxl862xx_rescue_heal_work_fn`. And the `dsa_devlink_flash_update` addition to `net/dsa/devlink.c` is important. It is reachable for any DSA switch that implements `devlink_flash_update`, which, according to this patch, is currently only the `mxl862xx` driver. But here's an idea: Syzkaller can create DSA switches using `netdevsim` or `dsa_loop`, right? Let's check. Does `dsa_loop` or `netdevsim` support DSA? In fact, `dsa_loop` is a mock DSA driver. The `mxl862xx` itself is a hardware driver, but perhaps `dsa_loop` or `netdevsim` provides a base to test against. The core question is, is `mxl862xx` reachable? I need to check the config. Is `CONFIG_NET_DSA_MXL862` the relevant one? Let's search for "mxl862xx" in the kernel. This patch has a chance!
4/2	2026/08/16 23:35	tool	grepper	0m Args: { "Expression": "mxl862xx" } Results: { "Output": "\nFull output is too long, showing 500 out of 2588 lines.\nUse more precise expression if possible.\n\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml-3----\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml:4:$id: http://devicetree.org/schemas/net/dsa/maxlinear,mxl862xx.yaml#\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml-5-$schema: http://devicetree.org/meta-schemas/core.yaml#\n--\nDocumentation/networking/devlink/index.rst=77=parameters, info versions, and other features it supports.\n--\nDocumentation/networking/devlink/index.rst-96- mv88e6xxx\nDocumentation/networking/devlink/index.rst:97: mxl862xx\nDocumentation/networking/devlink/index.rst-98- netdevsim\n--\nDocumentation/networking/devlink/mxl862xx.rst-3-========================\nDocumentation/networking/devlink/mxl862xx.rst:4:mxl862xx devlink support\nDocumentation/networking/devlink/mxl862xx.rst-5-========================\n--\nDocumentation/networking/devlink/mxl862xx.rst=7=This document describes the devlink features implemented by the\nDocumentation/networking/devlink/mxl862xx.rst:8:``mxl862xx`` device driver.\nDocumentation/networking/devlink/mxl862xx.rst-9-\nDocumentation/networking/devlink/mxl862xx.rst=10=Info versions\n--\nDocumentation/networking/devlink/mxl862xx.rst-12-\nDocumentation/networking/devlink/mxl862xx.rst:13:The ``mxl862xx`` driver reports the following versions\nDocumentation/networking/devlink/mxl862xx.rst-14-\n--\nDocumentation/networking/devlink/mxl862xx.rst=48=Flash update\n--\nDocumentation/networking/devlink/mxl862xx.rst-50-\nDocumentation/networking/devlink/mxl862xx.rst:51:The ``mxl862xx`` driver implements support for ``devlink dev flash``.\nDocumentation/networking/devlink/mxl862xx.rst-52-The signed firmware image is transferred to the switch over the same\n--\nMAINTAINERS=16107=S:\tMaintained\nMAINTAINERS:16108:F:\tDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml\nMAINTAINERS:16109:F:\tDocumentation/networking/devlink/mxl862xx.rst\nMAINTAINERS:16110:F:\tdrivers/net/dsa/mxl862xx/\nMAINTAINERS:16111:F:\tnet/dsa/tag_mxl862xx.c\nMAINTAINERS-16112-\n--\ndrivers/net/dsa/Kconfig=75=source \"drivers/net/dsa/mv88e6xxx/Kconfig\"\ndrivers/net/dsa/Kconfig-76-\ndrivers/net/dsa/Kconfig:77:source \"drivers/net/dsa/mxl862xx/Kconfig\"\ndrivers/net/dsa/Kconfig-78-\n--\ndrivers/net/dsa/Makefile=22=obj-y\t\t\t\t+= mv88e6xxx/\ndrivers/net/dsa/Makefile:23:obj-y\t\t\t\t+= mxl862xx/\ndrivers/net/dsa/Makefile-24-obj-y\t\t\t\t+= netc/\n--\ndrivers/net/dsa/mxl862xx/Makefile-1-# SPDX-License-Identifier: GPL-2.0\ndrivers/net/dsa/mxl862xx/Makefile:2:obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o\ndrivers/net/dsa/mxl862xx/Makefile:3:mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h=16=struct mdio_relay_data {\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-23-/*\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:24: struct mxl862xx_register_mod - Register access parameter to directly\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-25- * modify internal registers\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-31- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:32:struct mxl862xx_register_mod {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-33-\t__le16 addr;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-38-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:39: enum mxl862xx_mac_table_filter - Source/Destination MAC address filtering\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-40- \n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-45- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:46:enum mxl862xx_mac_table_filter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-47-\tMXL862XX_MAC_FILTER_NONE = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-64-/*\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:65: struct mxl862xx_mac_table_add - MAC Table Entry to be added\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-66- * @fid: Filtering Identifier (FID) (not supported by all switches)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-74- * @mac: MAC Address to add to the table\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:75: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-76- * @igmp_controlled: Packet is marked as IGMP controlled if destination MAC\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-83- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:84:struct mxl862xx_mac_table_add {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-85-\t__le16 fid;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-100-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:101: struct mxl862xx_mac_table_remove - MAC Table Entry to be removed\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-102- * @fid: Filtering Identifier (FID)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-103- * @mac: MAC Address to be removed from the table.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:104: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-105- * @tci: TCI for B-Step\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-109- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:110:struct mxl862xx_mac_table_remove {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-111-\t__le16 fid;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-117-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:118: struct mxl862xx_mac_table_read - MAC Table Entry to be read\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-119- * @initial: Restart the get operation from the beginning of the table\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-128- * @mac: MAC Address. Filled out by the switch API implementation.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:129: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-130- * @igmp_controlled: Packet is marked as IGMP controlled if destination MAC\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-141- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:142:struct mxl862xx_mac_table_read {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-143-\tu8 initial;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-162-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:163: struct mxl862xx_mac_table_query - MAC Table Entry key-based lookup\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-164- * @mac: MAC Address to search for (input)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-172- * @static_entry: Indicates if this is a Static Entry\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:173: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter (input+output)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-174- * @igmp_controlled: IGMP controlled flag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-180- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:181:struct mxl862xx_mac_table_query {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-182-\tu8 mac[ETH_ALEN];\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-200-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:201: enum mxl862xx_mac_clear_type - MAC table clear type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-202- * @MXL862XX_MAC_CLEAR_PHY_PORT: clear dynamic entries based on port_id\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-204- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:205:enum mxl862xx_mac_clear_type {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-206-\tMXL862XX_MAC_CLEAR_PHY_PORT = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-210-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:211: struct mxl862xx_mac_table_clear - MAC table clear\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:212: * @type: see \u0026enum mxl862xx_mac_clear_type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-213- * @port_id: physical port id\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-214- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:215:struct mxl862xx_mac_table_clear {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-216-\tu8 type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-220-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:221: enum mxl862xx_age_timer - Aging Timer Value.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-222- * @MXL862XX_AGETIMER_1_SEC: 1 second aging time\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-228- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:229:enum mxl862xx_age_timer {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-230-\tMXL862XX_AGETIMER_1_SEC = 1,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-238-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:239: struct mxl862xx_bridge_alloc - Bridge Allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-240- * @bridge_id: If the bridge allocation is successful, a valid ID will be\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-247- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:248:struct mxl862xx_bridge_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-249-\t__le16 bridge_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-252-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:253: enum mxl862xx_bridge_config_mask - Bridge configuration mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-254- * @MXL862XX_BRIDGE_CONFIG_MASK_MAC_LEARNING_LIMIT:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-267- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:268:enum mxl862xx_bridge_config_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-269-\tMXL862XX_BRIDGE_CONFIG_MASK_MAC_LEARNING_LIMIT = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-278-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:279: enum mxl862xx_bridge_port_egress_meter - Meters for egress traffic type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-280- * @MXL862XX_BRIDGE_PORT_EGRESS_METER_BROADCAST:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-293- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:294:enum mxl862xx_bridge_port_egress_meter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-295-\tMXL862XX_BRIDGE_PORT_EGRESS_METER_BROADCAST = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-304-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:305: struct mxl862xx_qos_meter_cfg - Rate meter configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-306- * @enable: Enable/disable meter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-320- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:321:struct mxl862xx_qos_meter_cfg {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-322-\tu8 enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-338-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:339: enum mxl862xx_bridge_forward_mode - Bridge forwarding type of packet\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-340- * @MXL862XX_BRIDGE_FORWARD_FLOOD: Packet is flooded to port members of\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-343- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:344:enum mxl862xx_bridge_forward_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-345-\tMXL862XX_BRIDGE_FORWARD_FLOOD = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-349-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:350: struct mxl862xx_bridge_config - Bridge Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-351- * @bridge_id: Bridge ID (FID)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:352: * @mask: See \u0026enum mxl862xx_bridge_config_mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-353- * @mac_learning_limit_enable: Enable MAC learning limitation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-363- * @forward_broadcast: Forwarding mode of broadcast traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:364: * \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-365- * @forward_unknown_multicast_ip: Forwarding mode of unknown multicast IP\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-366- * traffic.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:367: * See \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-368- * @forward_unknown_multicast_non_ip: Forwarding mode of unknown multicast\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-369- * non-IP traffic.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:370: * See \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-371- * @forward_unknown_unicast: Forwarding mode of unknown unicast traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:372: * \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-373- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:374:struct mxl862xx_bridge_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-375-\t__le16 bridge_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:376:\t__le32 mask; / enum mxl862xx_bridge_config_mask /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-377-\tu8 mac_learning_limit_enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-382-\t__le16 traffic_sub_meter_id[MXL862XX_BRIDGE_PORT_EGRESS_METER_MAX];\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:383:\t__le32 forward_broadcast; / enum mxl862xx_bridge_forward_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:384:\t__le32 forward_unknown_multicast_ip; / enum mxl862xx_bridge_forward_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:385:\t__le32 forward_unknown_multicast_non_ip; / enum mxl862xx_bridge_forward_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:386:\t__le32 forward_unknown_unicast; / enum mxl862xx_bridge_forward_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-387-} __packed;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-389-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:390: struct mxl862xx_bridge_port_alloc - Bridge Port Allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-391- * @bridge_port_id: If the bridge port allocation is successful, a valid ID\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-397- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:398:struct mxl862xx_bridge_port_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-399-\t__le16 bridge_port_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-402-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:403: enum mxl862xx_bridge_port_config_mask - Bridge Port configuration mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-404- * @MXL862XX_BRIDGE_PORT_CONFIG_MASK_BRIDGE_ID:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-462- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:463:enum mxl862xx_bridge_port_config_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-464-\tMXL862XX_BRIDGE_PORT_CONFIG_MASK_BRIDGE_ID = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-491-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:492: enum mxl862xx_color_marking_mode - Color Marking Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-493- * @MXL862XX_MARKING_ALL_GREEN: mark packets (except critical) to green\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-501- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:502:enum mxl862xx_color_marking_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-503-\tMXL862XX_MARKING_ALL_GREEN = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-513-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:514: enum mxl862xx_color_remarking_mode - Color Remarking Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-515- * @MXL862XX_REMARKING_NONE: values from last process stage\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-522- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:523:enum mxl862xx_color_remarking_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-524-\tMXL862XX_REMARKING_NONE = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-533-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:534: enum mxl862xx_pmapper_mapping_mode - P-mapper Mapping Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-535- * @MXL862XX_PMAPPER_MAPPING_PCP: Use PCP for VLAN tagged packets to derive\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-541- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:542:enum mxl862xx_pmapper_mapping_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-543-\tMXL862XX_PMAPPER_MAPPING_PCP = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-548-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:549: struct mxl862xx_pmapper - P-mapper Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-550- * @pmapper_id: Index of P-mapper (0-31)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-560- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:561:struct mxl862xx_pmapper {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-562-\t__le16 pmapper_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-566-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:567: struct mxl862xx_bridge_port_config - Bridge Port Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-568- * @bridge_port_id: Bridge Port ID allocated by bridge port allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:569: * @mask: See \u0026enum mxl862xx_bridge_port_config_mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-570- * @bridge_id: Bridge ID (FID) to which this bridge port is associated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-583- * @ingress_marking_mode: Ingress color marking mode. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:584: * \u0026enum mxl862xx_color_marking_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-585- * @egress_remarking_mode: Color remarking for egress traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:586: * \u0026enum mxl862xx_color_remarking_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-587- * @ingress_metering_enable: Traffic metering on ingress traffic applies\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-597- * @pmapper_mapping_mode: P-mapper mapping mode. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:598: * \u0026enum mxl862xx_pmapper_mapping_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-599- * @pmapper_id_valid: When true, P-mapper is re-used; when false,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-653- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:654:struct mxl862xx_bridge_port_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-655-\t__le16 bridge_port_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:656:\t__le32 mask; / enum mxl862xx_bridge_port_config_mask /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-657-\t__le16 bridge_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-663-\t__le16 egress_extended_vlan_block_size;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:664:\t__le32 ingress_marking_mode; / enum mxl862xx_color_marking_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:665:\t__le32 egress_remarking_mode; / enum mxl862xx_color_remarking_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-666-\tu8 ingress_metering_enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-672-\t__le16 dest_sub_if_id_group;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:673:\t__le32 pmapper_mapping_mode; / enum mxl862xx_pmapper_mapping_mode /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-674-\tu8 pmapper_id_valid;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:675:\tstruct mxl862xx_pmapper pmapper;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-676-\t__le16 bridge_port_map[8];\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-709-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:710: struct mxl862xx_cfg - Global Switch configuration Attributes\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:711: * @mac_table_age_timer: See \u0026enum mxl862xx_age_timer\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-712- * @age_timer: Custom MAC table aging timer in seconds\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-722- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:723:struct mxl862xx_cfg {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:724:\t__le32 mac_table_age_timer; / enum mxl862xx_age_timer /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-725-\t__le32 age_timer;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-734-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:735: enum mxl862xx_extended_vlan_filter_type - Extended VLAN filter tag type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-736- * @MXL862XX_EXTENDEDVLAN_FILTER_TYPE_NORMAL: Normal tagged\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-740- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:741:enum mxl862xx_extended_vlan_filter_type {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-742-\tMXL862XX_EXTENDEDVLAN_FILTER_TYPE_NORMAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-748-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:749: enum mxl862xx_extended_vlan_filter_tpid - Extended VLAN filter TPID\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-750- * @MXL862XX_EXTENDEDVLAN_FILTER_TPID_NO_FILTER: No TPID filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-753- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:754:enum mxl862xx_extended_vlan_filter_tpid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-755-\tMXL862XX_EXTENDEDVLAN_FILTER_TPID_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-760-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:761: enum mxl862xx_extended_vlan_filter_dei - Extended VLAN filter DEI\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-762- * @MXL862XX_EXTENDEDVLAN_FILTER_DEI_NO_FILTER: No DEI filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-765- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:766:enum mxl862xx_extended_vlan_filter_dei {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-767-\tMXL862XX_EXTENDEDVLAN_FILTER_DEI_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-772-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:773: enum mxl862xx_extended_vlan_treatment_remove_tag - Tag removal action\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-774- * @MXL862XX_EXTENDEDVLAN_TREATMENT_NOT_REMOVE_TAG: Do not remove tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-778- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:779:enum mxl862xx_extended_vlan_treatment_remove_tag {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-780-\tMXL862XX_EXTENDEDVLAN_TREATMENT_NOT_REMOVE_TAG = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-786-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:787: enum mxl862xx_extended_vlan_treatment_priority - Treatment priority mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-788- * @MXL862XX_EXTENDEDVLAN_TREATMENT_PRIORITY_VAL: Use explicit value\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-792- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:793:enum mxl862xx_extended_vlan_treatment_priority {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-794-\tMXL862XX_EXTENDEDVLAN_TREATMENT_PRIORITY_VAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-800-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:801: enum mxl862xx_extended_vlan_treatment_vid - Treatment VID mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-802- * @MXL862XX_EXTENDEDVLAN_TREATMENT_VID_VAL: Use explicit VID value\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-805- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:806:enum mxl862xx_extended_vlan_treatment_vid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-807-\tMXL862XX_EXTENDEDVLAN_TREATMENT_VID_VAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-812-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:813: enum mxl862xx_extended_vlan_treatment_tpid - Treatment TPID mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-814- * @MXL862XX_EXTENDEDVLAN_TREATMENT_INNER_TPID: Copy from inner tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-818- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:819:enum mxl862xx_extended_vlan_treatment_tpid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-820-\tMXL862XX_EXTENDEDVLAN_TREATMENT_INNER_TPID = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-826-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:827: enum mxl862xx_extended_vlan_treatment_dei - Treatment DEI mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-828- * @MXL862XX_EXTENDEDVLAN_TREATMENT_INNER_DEI: Copy from inner tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-832- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:833:enum mxl862xx_extended_vlan_treatment_dei {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-834-\tMXL862XX_EXTENDEDVLAN_TREATMENT_INNER_DEI = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-840-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:841: enum mxl862xx_extended_vlan_4_tpid_mode - 4-TPID mode selector\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-842- * @MXL862XX_EXTENDEDVLAN_TPID_VTETYPE_1: VLAN TPID type 1\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-846- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:847:enum mxl862xx_extended_vlan_4_tpid_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-848-\tMXL862XX_EXTENDEDVLAN_TPID_VTETYPE_1 = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-854-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:855: enum mxl862xx_extended_vlan_filter_ethertype - Filter EtherType match\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-856- * @MXL862XX_EXTENDEDVLAN_FILTER_ETHERTYPE_NO_FILTER: No filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-864- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:865:enum mxl862xx_extended_vlan_filter_ethertype {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-866-\tMXL862XX_EXTENDEDVLAN_FILTER_ETHERTYPE_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-876-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:877: struct mxl862xx_extendedvlan_filter_vlan - Per-tag filter in Extended VLAN\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:878: * @type: Tag presence/type match (see \u0026enum mxl862xx_extended_vlan_filter_type)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-879- * @priority_enable: Enable PCP value matching\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-882- * @vid_val: VID value to match\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:883: * @tpid: TPID match mode (see \u0026enum mxl862xx_extended_vlan_filter_tpid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:884: * @dei: DEI match mode (see \u0026enum mxl862xx_extended_vlan_filter_dei)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-885- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:886:struct mxl862xx_extendedvlan_filter_vlan {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-887-\t__le32 type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-896-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:897: struct mxl862xx_extendedvlan_filter - Extended VLAN filter configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-898- * @original_packet_filter_mode: If true, filter on original (pre-treatment)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-899- * packet\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:900: * @filter_4_tpid_mode: 4-TPID mode (see \u0026enum mxl862xx_extended_vlan_4_tpid_mode)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-901- * @outer_vlan: Outer VLAN tag filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-903- * @ether_type: EtherType filter (see\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:904: * \u0026enum mxl862xx_extended_vlan_filter_ethertype)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-905- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:906:struct mxl862xx_extendedvlan_filter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-907-\tu8 original_packet_filter_mode;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-908-\t__le32 filter_4_tpid_mode;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:909:\tstruct mxl862xx_extendedvlan_filter_vlan outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:910:\tstruct mxl862xx_extendedvlan_filter_vlan inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-911-\t__le32 ether_type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-914-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:915: struct mxl862xx_extendedvlan_treatment_vlan - Per-tag treatment in\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-916- * Extended VLAN\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-917- * @priority_mode: Priority assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:918: * (see \u0026enum mxl862xx_extended_vlan_treatment_priority)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-919- * @priority_val: Priority value (when mode is VAL)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-920- * @vid_mode: VID assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:921: * (see \u0026enum mxl862xx_extended_vlan_treatment_vid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-922- * @vid_val: VID value (when mode is VAL)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-923- * @tpid: TPID assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:924: * (see \u0026enum mxl862xx_extended_vlan_treatment_tpid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-925- * @dei: DEI assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:926: * (see \u0026enum mxl862xx_extended_vlan_treatment_dei)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-927- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:928:struct mxl862xx_extendedvlan_treatment_vlan {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-929-\t__le32 priority_mode;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-937-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:938: struct mxl862xx_extendedvlan_treatment - Extended VLAN treatment\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-939- * @remove_tag: Tag removal action\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:940: * (see \u0026enum mxl862xx_extended_vlan_treatment_remove_tag)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-941- * @treatment_4_tpid_mode: 4-TPID treatment mode\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-958- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:959:struct mxl862xx_extendedvlan_treatment {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-960-\t__le32 remove_tag;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-962-\tu8 add_outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:963:\tstruct mxl862xx_extendedvlan_treatment_vlan outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-964-\tu8 add_inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:965:\tstruct mxl862xx_extendedvlan_treatment_vlan inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-966-\tu8 reassign_bridge_port;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-980-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:981: struct mxl862xx_extendedvlan_alloc - Extended VLAN block allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-982- * @number_of_entries: Number of entries to allocate (input) / allocated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-988- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:989:struct mxl862xx_extendedvlan_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-990-\t__le16 number_of_entries;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-994-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:995: struct mxl862xx_extendedvlan_config - Extended VLAN entry configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-996- * @extended_vlan_block_id: Block ID from allocation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1002- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1003:struct mxl862xx_extendedvlan_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1004-\t__le16 extended_vlan_block_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1005-\t__le16 entry_index;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1006:\tstruct mxl862xx_extendedvlan_filter filter;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1007:\tstruct mxl862xx_extendedvlan_treatment treatment;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1008-} __packed;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1010-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1011: enum mxl862xx_vlan_filter_tci_mask - VLAN Filter TCI mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1012- * @MXL862XX_VLAN_FILTER_TCI_MASK_VID: TCI mask for VLAN ID\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1015- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1016:enum mxl862xx_vlan_filter_tci_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1017-\tMXL862XX_VLAN_FILTER_TCI_MASK_VID = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1022-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1023: struct mxl862xx_vlanfilter_alloc - VLAN Filter block allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1024- * @number_of_entries: Number of entries to allocate (input) / allocated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1034- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1035:struct mxl862xx_vlanfilter_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1036-\t__le16 number_of_entries;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1043-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1044: struct mxl862xx_vlanfilter_config - VLAN Filter entry configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1045- * @vlan_filter_block_id: Block ID from allocation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1047- * @vlan_filter_mask: TCI field(s) to match (see\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1048: * \u0026enum mxl862xx_vlan_filter_tci_mask)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1049- * @val: TCI value(s) to match (VID, PCP, or full TCI depending on mask)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1054- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1055:struct mxl862xx_vlanfilter_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1056-\t__le16 vlan_filter_block_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1057-\t__le16 entry_index;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1058:\t__le32 vlan_filter_mask; / enum mxl862xx_vlan_filter_tci_mask /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1059-\t__le32 val;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1063-/\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1064: enum mxl862xx_ss_sp_tag_mask - Special tag valid field indicator bits\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1065- * @MXL862XX_SS_SP_TAG_MASK_RX: valid RX special tag mode\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1069- /\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1070:enum mxl862xx_ss_sp_tag_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1071-\tMXL862XX_SS_SP_TAG_MASK_RX = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1077-/*\n\n" }
5/2	2026/08/16 23:35	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 47451 output: 20 thoughts: 283 Thoughts: Analyzing the mxl862xx Driver for Virtualization Potential Okay, so I'm looking at the `mxl862xx` driver, specifically `drivers/net/dsa/mxl862xx/mxl862xx.c`. It's an MDIO device driver, and the driver structure definition looks pretty standard: ```c static struct mdio_driver mxl862xx_driver = { .mdiodrv.driver = { .name = "mxl862xx", .of_match_table = mxl862xx_of_match, }, .probe = mxl862xx_probe, .remove = mxl862xx_remove, }; ``` The question is, can I get this thing probed in a virtualized setting? Ideally, I'd want to create a mock MDIO bus, register a virtual device, and see if the driver attaches properly. Standard procedure would involve something like `mdio-mockup`, or similar techniques. But wait, this is syzkaller, and syzkaller doesn't typically mess around with that level of setup. Hmm... syzkaller does have `syz_genetlink` and `syz_devlink` which are interesting for interacting with networking and device linking... but unless there's a software emulator specifically for an MDIO device, I'm going to have trouble directly instantiating this specific hardware. Okay, let's take a step back and consider `device_schedule_reprobe`. That's a generic function in `drivers/base/dd.c`, and it's something that I've seen used in these situations before. I wonder if it's reachable from anywhere else? A generic function is more likely to be exposed and invoked. I should check how else it's used within the codebase.
6/2	2026/08/16 23:35	tool	grepper	0m Args: { "Expression": "device_schedule_reprobe" } Results: { "Output": "drivers/base/base.h=80=struct driver_private {\n--\ndrivers/base/base.h-111- \t device lock. A deferred re-probe scheduled with\ndrivers/base/base.h:112: \t device_schedule_reprobe() must not detach the device anymore.\ndrivers/base/base.h-113- \n--\ndrivers/base/dd.c=1447=static void device_reprobe_work_fn(struct work_struct work)\n--\ndrivers/base/dd.c-1485-/*\ndrivers/base/dd.c:1486: device_schedule_reprobe - schedule a deferred detach and re-probe\ndrivers/base/dd.c-1487- * @dev: device to detach and re-probe\n--\ndrivers/base/dd.c-1510- /\ndrivers/base/dd.c:1511:int device_schedule_reprobe(struct device dev, unsigned int delay_ms)\ndrivers/base/dd.c-1512-{\n--\ndrivers/base/dd.c-1536-}\ndrivers/base/dd.c:1537:EXPORT_SYMBOL_GPL(device_schedule_reprobe);\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c=421=void mxl862xx_rescue_heal_work_fn(struct work_struct work)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-451-\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c:452:\tif (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS))\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-453-\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c=926=int mxl862xx_devlink_flash_update(struct dsa_switch ds,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-1058-\t /\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c:1059:\terr = device_schedule_reprobe(ds-\u003edev, MXL862XX_FW_REPROBE_DELAY_MS);\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-1060-\n--\ninclude/linux/device.h=1316=int __must_check device_reprobe(struct device dev);\ninclude/linux/device.h:1317:int __must_check device_schedule_reprobe(struct device *dev,\ninclude/linux/device.h-1318-\t\t\t\t\t unsigned int delay_ms);\n" }
7/2	2026/08/16 23:35	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 48943 output: 19 thoughts: 138 Thoughts: My Line of Reasoning Okay, so `device_schedule_reprobe` is pretty specific; it seems it's exclusively used within the `mxl862xx` driver. Right away, that raises a flag. `mxl862xx` is definitely a hardware-specific driver, which usually requires actual physical hardware or at least a very precise emulation. And let's be realistic, standard QEMU or Google Compute Engine environments aren't going to have that specific emulation available. So, directly hitting that code path seems impossible. Hold on a second, though... is there any other way that `device_schedule_reprobe` could be triggered? Let me double-check the call graph. Nope, it's exclusively within `mxl862xx`. Damn. Okay, back to the drawing board. Wait, maybe there's a back door. Could Syzkaller somehow instantiate an MDIO device using something like `mdio-mockup`, or a similar construct? It’s a long shot, but worth checking. Let me confirm if that `mdio-mockup` driver is even present in the target system. Time to go dig around.
8/2	2026/08/16 23:35	tool	grepper	0m Error: no matches Args: { "Expression": "mdio-mockup" } Results: { "error": "no matches" }
9/2	2026/08/16 23:35	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 49367 output: 21 thoughts: 364 Thoughts: Analyzing the Fuzzing Worthiness of a Patch Okay, let's break this down. First, I ruled out `mdio-mockup.c` pretty quickly – not the right approach. Then I considered instantiating an MDIO device from userspace. Nope, that's handled by the MDIO bus driver, likely through device tree or board code, not a generic userspace interface. So, the `mxl862xx` driver is out for virtualization without specific hardware or emulation. Now, the instructions are key. They say to return `WorthFuzzing=false` if the changes are unreachable in virtualized environments. I looked at `device_schedule_reprobe`. It is a core function, a new API even, but is it reachable? Currently, no. No other code calls it. It's exported, but that doesn't mean it's executed. Therefore, following the instructions, that's another `WorthFuzzing=false`. Wait a minute, what about `dsa_devlink_flash_update`? This is added to `dsa_devlink_ops`, that's potentially different. But is it reachable? If a DSA switch implements `devlink_flash_update`, then yes, it's reachable. Right now, only `mxl862xx` does. So, I need to investigate further: are there any other DSA switch implementations that use `devlink_flash_update`? That's the key to figuring this out. That's my next step.
10/2	2026/08/16 23:35	tool	grepper	0m Args: { "Expression": "\\.devlink_flash_update" } Results: { "Output": "drivers/net/dsa/mxl862xx/mxl862xx.c=2185=static const struct dsa_switch_ops mxl862xx_switch_ops = {\n--\ndrivers/net/dsa/mxl862xx/mxl862xx.c-2217-\t.devlink_info_get = mxl862xx_devlink_info_get,\ndrivers/net/dsa/mxl862xx/mxl862xx.c:2218:\t.devlink_flash_update = mxl862xx_devlink_flash_update,\ndrivers/net/dsa/mxl862xx/mxl862xx.c-2219-};\n" }
11/2	2026/08/16 23:35	llm	patch-evaluator	0m Model: gemini-3.1-pro-preview Args: null Results: null Tokens: input: 50287 output: 102 thoughts: 1074 Thoughts: Analysis of the Proposed Patch's Fuzzing Potential Okay, let's break this down. My initial assessment is that this patch isn't particularly fruitful for fuzzing, given the constraints. It looks like the main functionality centers around `mxl862xx`, a driver for a specific hardware switch. I see that `dsa_devlink_flash_update` is affected, but for other DSA switches it will simply return `-EOPNOTSUPP`. That initial function is reachable, but trivial in its implementation. The core logic resides within `mxl862xx-fw.c` and involves `device_schedule_reprobe`. The problem is that `mxl862xx` isn't accessible without the actual hardware; its probe logic, specifically using MDIO reads/writes and looking for specific register values, will fail if the physical device isn't present. And Syzkaller, in its current implementation, isn't going to dynamically inject device tree nodes to probe arbitrary MDIO devices. I can already see from the code that any attempt to emulate the device would fail during early probe attempts. Even if somehow it could, without the actual hardware it will fail early within probe. So, the juicy stuff is locked away in that driver, essentially unaccessible. What about the changes in `drivers/base/dd.c` and `drivers/base/core.c`? Setting `shutdown_done` during `device_shutdown` is reachable during system shutdown, but that's a trivial change: just setting a boolean flag. The other change there - the introduction of `device_schedule_reprobe` and `device_reprobe_work_fn` - is only used by that `mxl862xx` driver. It depends on an MDIO probe, which fails in an emulated environment. Therefore, the useful parts are unexercisable. I'm seeing that the patch relies on a hardware-specific driver, one that can't be probed in my current fuzzing setup. The driver has a few device compatible strings: `maxlinear,mxl86280`, `maxlinear,mxl86281`, `maxlinear,mxl86282`, `maxlinear,mxl86283`, `maxlinear,mxl86280s`, `maxlinear,mxl86281s`, `maxlinear,mxl86282s`, and `maxlinear,mxl86283s`. So, in conclusion, the patch is not worth fuzzing, based on the fact that I can't reach the core driver logic due to hardware dependencies and limitations in the virtual environment. I'm going to set `WorthFuzzing=false`. The reasoning is that the firmware flash and devlink support are added for a hardware-specific switch driver which requires physical MDIO hardware. Because of the MDIO requirements, the driver cannot be probed in an emulated environment and the core changes, `device_schedule_reprobe` and `device_shutdown`, are not worth fuzzing.
12/2	2026/08/16 23:36	tool	set-results	0m Args: { "EnableConfigs": [], "FocusSymbols": [], "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.", "WorthFuzzing": false } Results: { "EnableConfigs": null, "FocusSymbols": [], "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.", "WorthFuzzing": false }
13/1	2026/08/16 23:36	action	If	0m Args: { "WorthFuzzing": false } Results: null

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "KMSANReasoning": "",
  "NeedsKMSAN": false,
  "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.",
  "WorthFuzzing": false
}

{
  "PatchDiff": "commit a01707c4f39f9db8f15411902f052348a25923e9\nAuthor: syz-cluster \u003ctriage@syzkaller.com\u003e\nDate:   Sun Aug 16 23:35:08 2026 +0000\n\n    syz-cluster: applied patch under review\n\ndiff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst\nindex 4745148fecf4f..058999d0dc56f 100644\n--- a/Documentation/networking/devlink/index.rst\n+++ b/Documentation/networking/devlink/index.rst\n@@ -94,6 +94,7 @@ parameters, info versions, and other features it supports.\n    mlx5\n    mlxsw\n    mv88e6xxx\n+   mxl862xx\n    netdevsim\n    nfp\n    octeontx2\ndiff --git a/Documentation/networking/devlink/mxl862xx.rst b/Documentation/networking/devlink/mxl862xx.rst\nnew file mode 100644\nindex 0000000000000..5b24d8cb57bc9\n--- /dev/null\n+++ b/Documentation/networking/devlink/mxl862xx.rst\n@@ -0,0 +1,74 @@\n+.. SPDX-License-Identifier: GPL-2.0\n+\n+========================\n+mxl862xx devlink support\n+========================\n+\n+This document describes the devlink features implemented by the\n+``mxl862xx`` device driver.\n+\n+Info versions\n+=============\n+\n+The ``mxl862xx`` driver reports the following versions\n+\n+.. list-table:: devlink info versions implemented\n+   :widths: 5 5 5 85\n+\n+   * - Name\n+     - Type\n+     - Example\n+     - Description\n+   * - ``asic.id``\n+     - fixed\n+     - 8628\n+     - The chip part number read from the CHIP ID registers. Omitted\n+       when the part number reads as zero, which happens for a switch\n+       sitting in MCUboot rescue mode (the registers need a running\n+       firmware), for an unfused part, and after a failed flash.\n+   * - ``asic.rev``\n+     - fixed\n+     - 0\n+     - The chip version read from the same register word, so it is\n+       omitted whenever ``asic.id`` is.\n+   * - ``fw``\n+     - running, stored\n+     - 1.0.70\n+     - Version of the firmware running on the switch, reported as both\n+       running and stored since the switch boots it from its own flash.\n+       It is omitted while no firmware version is known: after a failed\n+       flash, and in MCUboot rescue mode while an interrupted download\n+       is still being recovered in the background. Once the loader is\n+       ready to accept a new image the version appears as \"0.0.0\",\n+       which no released firmware reports, so version-comparing tools\n+       offer any available release as an upgrade. Use ``devlink dev\n+       flash`` to tell a recovering switch from a ready one, see below;\n+       a missing version on its own does not say why.\n+\n+Flash update\n+============\n+\n+The ``mxl862xx`` driver implements support for ``devlink dev flash``.\n+The signed firmware image is transferred to the switch over the same\n+MDIO bus which is also used to manage the switch, then verified and\n+installed by the MCUboot bootloader running on the switch. All ports\n+of the switch are closed for the duration of the update and the driver\n+reprobes the switch after it has rebooted into the new firmware. A\n+complete flash and reprobe cycle takes about one minute.\n+\n+A switch stuck in MCUboot rescue mode, e.g. after an interrupted\n+update, is registered without user ports. If the previous download was\n+interrupted mid-transfer the loader is wedged; the driver drains it\n+back to a clean ready state in the background, one byte at a time,\n+which takes tens of minutes for a large image and is reported through\n+the kernel log as it progresses. During that recovery ``devlink dev\n+flash`` returns ``-EBUSY`` with an extack message saying so, and\n+``devlink dev info`` reports no firmware version. Once the loader is\n+ready the firmware version appears and flashing a firmware image\n+through the regular update flow recovers the switch.\n+\n+If the recovery fails, the loader needs a power cycle: ``devlink dev\n+flash`` then returns ``-EIO`` and says so in its extack message. The\n+driver only re-examines the switch when it binds, so on a board where\n+the switch can be power cycled on its own, unbind and rebind the driver\n+afterwards to have the recovered switch recognised.\ndiff --git a/MAINTAINERS b/MAINTAINERS\nindex 991460050da74..e3f7ded569bf7 100644\n--- a/MAINTAINERS\n+++ b/MAINTAINERS\n@@ -16106,6 +16106,7 @@ M:\tDaniel Golle \u003cdaniel@makrotopia.org\u003e\n L:\tnetdev@vger.kernel.org\n S:\tMaintained\n F:\tDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml\n+F:\tDocumentation/networking/devlink/mxl862xx.rst\n F:\tdrivers/net/dsa/mxl862xx/\n F:\tnet/dsa/tag_mxl862xx.c\n \ndiff --git a/drivers/base/base.h b/drivers/base/base.h\nindex a5b7abc10ff02..6234e37de7e99 100644\n--- a/drivers/base/base.h\n+++ b/drivers/base/base.h\n@@ -106,6 +106,10 @@ struct driver_private {\n  * @dead: This device is currently either in the process of or has been\n  *\t  removed from the system. Any asynchronous events scheduled for this\n  *\t  device should exit without taking any action.\n+ * @shutdown_done: Set once device_shutdown() has reached this device, under\n+ *\t  the device lock, before any shutdown callback runs. Read under the\n+ *\t  device lock. A deferred re-probe scheduled with\n+ *\t  device_schedule_reprobe() must not detach the device anymore.\n  *\n  * Nothing outside of the driver core should ever touch these fields.\n  */\n@@ -120,6 +124,7 @@ struct device_private {\n \tchar *deferred_probe_reason;\n \tstruct device *device;\n \tu8 dead:1;\n+\tu8 shutdown_done:1;\n };\n #define to_device_private_parent(obj)\t\\\n \tcontainer_of(obj, struct device_private, knode_parent)\ndiff --git a/drivers/base/core.c b/drivers/base/core.c\nindex 4d026682944f2..8a7dbe4e8362b 100644\n--- a/drivers/base/core.c\n+++ b/drivers/base/core.c\n@@ -4906,6 +4906,9 @@ void device_shutdown(void)\n \t\t\tdevice_lock(parent);\n \t\tdevice_lock(dev);\n \n+\t\tif (dev-\u003ep)\n+\t\t\tdev-\u003ep-\u003eshutdown_done = true;\n+\n \t\t/* Don't allow any more runtime suspends */\n \t\tpm_runtime_get_noresume(dev);\n \t\tpm_runtime_barrier(dev);\ndiff --git a/drivers/base/dd.c b/drivers/base/dd.c\nindex 60c005223844d..3394b1c7ed180 100644\n--- a/drivers/base/dd.c\n+++ b/drivers/base/dd.c\n@@ -1436,3 +1436,102 @@ void driver_detach(const struct device_driver *drv)\n \t\tput_device(dev);\n \t}\n }\n+\n+struct device_reprobe {\n+\tstruct delayed_work work;\n+\tstruct device *dev;\n+\tstruct device *parent;\n+\tconst struct device_driver *drv;\n+};\n+\n+static void device_reprobe_work_fn(struct work_struct *work)\n+{\n+\tstruct device_reprobe *rp = container_of(work, struct device_reprobe,\n+\t\t\t\t\t\t work.work);\n+\tstruct device *dev = rp-\u003edev;\n+\tstruct device *parent = rp-\u003eparent;\n+\tbool detached = false;\n+\n+\t__device_driver_lock(dev, parent);\n+\t/*\n+\t * rp-\u003edrv is only ever compared, never dereferenced: the driver it\n+\t * points to may have been unregistered and freed by now.\n+\t */\n+\tif (!dev-\u003ep-\u003edead \u0026\u0026 !dev-\u003ep-\u003eshutdown_done \u0026\u0026\n+\t    dev-\u003edriver \u0026\u0026 dev-\u003edriver == rp-\u003edrv) {\n+\t\t__device_release_driver(dev, parent);\n+\t\tdetached = true;\n+\t}\n+\t__device_driver_unlock(dev, parent);\n+\n+\tif (detached) {\n+\t\t/*\n+\t\t * device_attach() must run with the parent locked on buses\n+\t\t * that require it, mirroring bus_rescan_devices_helper().\n+\t\t */\n+\t\tif (parent \u0026\u0026 dev-\u003ebus-\u003eneed_parent_lock)\n+\t\t\tdevice_lock(parent);\n+\t\tif (device_attach(dev) \u003c 0)\n+\t\t\tdev_err(dev, \"re-probe failed, device left unbound\\n\");\n+\t\tif (parent \u0026\u0026 dev-\u003ebus-\u003eneed_parent_lock)\n+\t\t\tdevice_unlock(parent);\n+\t}\n+\n+\tput_device(dev);\n+\tput_device(parent);\n+\tkfree(rp);\n+}\n+\n+/**\n+ * device_schedule_reprobe - schedule a deferred detach and re-probe\n+ * @dev: device to detach and re-probe\n+ * @delay_ms: delay in milliseconds before the re-probe runs\n+ *\n+ * Schedule a detach and re-probe of @dev after @delay_ms milliseconds.\n+ * The re-probe is skipped if, by the time the scheduled work runs, the\n+ * device has been removed, the system shutdown sequence has reached the\n+ * device, or @dev is no longer bound to the driver that was bound at\n+ * scheduling time. In particular an administrative unbind is never\n+ * undone by a stale re-probe.\n+ *\n+ * The work function is built-in text, so the bound driver may call this\n+ * from its own code without holding a module reference. If the driver\n+ * module is unloaded before the work runs, driver unregistration unbinds\n+ * @dev first and the scheduled work does nothing.\n+ *\n+ * Multiple pending re-probes for the same device are individually safe;\n+ * a caller that wants at most one pending re-probe must gate scheduling\n+ * itself.\n+ *\n+ * May only be called from process context.\n+ *\n+ * Returns: 0 on success, -EINVAL if @dev is not a registered device\n+ * bound to a driver, -ENOMEM on allocation failure.\n+ */\n+int device_schedule_reprobe(struct device *dev, unsigned int delay_ms)\n+{\n+\tstruct device_reprobe *rp;\n+\n+\tif (!dev-\u003ebus || !dev-\u003ep || !device_is_registered(dev))\n+\t\treturn -EINVAL;\n+\tif (!dev-\u003edriver)\n+\t\treturn -EINVAL;\n+\n+\trp = kzalloc_obj(*rp);\n+\tif (!rp)\n+\t\treturn -ENOMEM;\n+\n+\trp-\u003edev = get_device(dev);\n+\t/*\n+\t * Pin the parent too: the work locks it, and an unregister of @dev\n+\t * would otherwise drop the last reference before the work runs.\n+\t */\n+\trp-\u003eparent = get_device(dev-\u003eparent);\n+\trp-\u003edrv = READ_ONCE(dev-\u003edriver);\n+\tINIT_DELAYED_WORK(\u0026rp-\u003ework, device_reprobe_work_fn);\n+\tqueue_delayed_work(system_dfl_wq, \u0026rp-\u003ework,\n+\t\t\t   msecs_to_jiffies(delay_ms));\n+\n+\treturn 0;\n+}\n+EXPORT_SYMBOL_GPL(device_schedule_reprobe);\ndiff --git a/drivers/net/dsa/mxl862xx/Makefile b/drivers/net/dsa/mxl862xx/Makefile\nindex a7be0e6669dfa..bccac0d0f703f 100644\n--- a/drivers/net/dsa/mxl862xx/Makefile\n+++ b/drivers/net/dsa/mxl862xx/Makefile\n@@ -1,3 +1,3 @@\n # SPDX-License-Identifier: GPL-2.0\n obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o\n-mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o\n+mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-api.h b/drivers/net/dsa/mxl862xx/mxl862xx-api.h\nindex a180a5decffc0..6f771895984cb 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-api.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-api.h\n@@ -1224,6 +1224,16 @@ struct mxl862xx_sys_fw_image_version {\n \t__le32 iv_build_num;\n } __packed;\n \n+/**\n+ * struct mxl862xx_sys_reg_rw - System register read/write\n+ * @addr: 32-bit register address\n+ * @val: register value\n+ */\n+struct mxl862xx_sys_reg_rw {\n+\t__le32 addr;\n+\t__le32 val;\n+} __packed;\n+\n /**\n  * enum mxl862xx_port_type - Port Type\n  * @MXL862XX_LOGICAL_PORT: Logical Port\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\nindex c87a955c13c48..a865425aa61e1 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h\n@@ -70,7 +70,9 @@\n #define INT_GPHY_READ\t\t\t(GPY_GPY2XX_MAGIC + 0x1)\n #define INT_GPHY_WRITE\t\t\t(GPY_GPY2XX_MAGIC + 0x2)\n \n+#define SYS_MISC_FW_UPDATE\t\t(SYS_MISC_MAGIC + 0x1)\n #define SYS_MISC_FW_VERSION\t\t(SYS_MISC_MAGIC + 0x2)\n+#define SYS_MISC_REG_RD\t\t\t(SYS_MISC_MAGIC + 0x8)\n \n #define MXL862XX_XPCS_PCS_CONFIG\t(MXL862XX_XPCS_MAGIC + 0x1)\n #define MXL862XX_XPCS_PCS_GET_STATE\t(MXL862XX_XPCS_MAGIC + 0x2)\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.c b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c\nnew file mode 100644\nindex 0000000000000..1de8d9970a369\n--- /dev/null\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c\n@@ -0,0 +1,1062 @@\n+// SPDX-License-Identifier: GPL-2.0-or-later\n+/*\n+ * Firmware flash and devlink support for MaxLinear MxL862xx\n+ *\n+ * Copyright (C) 2025 Daniel Golle \u003cdaniel@makrotopia.org\u003e\n+ *\n+ * SB PDI - firmware download interface over clause-22 SMDIO\n+ * =========================================================\n+ *\n+ * The MxL862xx MCUboot loader accepts a firmware image through four \"SB PDI\"\n+ * registers in the switch SMDIO register space. It runs whenever no WSP\n+ * firmware is active: the normal firmware update enters it deliberately - the\n+ * SYS_MISC_FW_UPDATE API command sets a sticky rescue bit and reboots into\n+ * MCUboot - and the loader also stays here when the stored WSP firmware fails\n+ * its boot-time integrity check. This driver drives the loader's 0xc55c\n+ * \"console\" download path.\n+ *\n+ * SMDIO register access (mxl862xx_smdio_read/write):\n+ *   MII reg 0x1f := (\u003csb_pdi_reg\u003e \u0026 0xfff0)   ; page latch\n+ *   MII reg (\u003csb_pdi_reg\u003e \u0026 0x000f) := / =\u003e \u003cu16 data\u003e\n+ * so CTRL/ADDR/DATA/STAT (0xe100..0xe103) are MII regs 0/1/2/3 of page\n+ * 0xe100, not all reg 0x00.\n+ *\n+ * SB PDI registers (host name/addr  -\u003e  MCU mailbox):\n+ *   CTRL 0xe100 -\u003e 0xc0938400   mode: RST=0x00  RD=0x01  WR=0x02\n+ *   ADDR 0xe101 -\u003e 0xc0938404   SB target word address (SB1 bank = 0x7800)\n+ *   DATA 0xe102 -\u003e 0xc0938408   16-bit data / reply word\n+ *   STAT 0xe103 -\u003e 0xc093840c   handshake: a magic (below) or a byte count\n+ *\n+ * STAT magics:\n+ *   READY  0xc55c   loader idle in the console loop        (this driver)\n+ *   DL_RDY 0xc33c   loader idle in the flashless loop\n+ *   START  0xf48f   host   -\u003e begin download session\n+ *   ACK    0xf490   loader -\u003e START acknowledged (START + 1)\n+ *   END    0x3cc3   host   -\u003e finalise now (optional, see below)\n+ *   RDREG  0xe2c0   host   -\u003e register-read command (| index), see below\n+ *\n+ * Console flash path (STAT=0xc55c) - mxl862xx_flash_firmware():\n+ *\n+ *   host                                   loader\n+ *   ----                                   ------\n+ *   reset (CTRL=ADDR=DATA=0)\n+ *   read STAT ............................ 0xc55c   (READY, idle)\n+ *   STAT := START(0xf48f)  --------------\u003e\n+ *                          \u003c-------------- STAT = 0xf490 (ACK)\n+ *   CTRL := WR\n+ *   DATA := hdr[0..9]  (20-byte header: type,size1,crc1,size2,crc2)\n+ *   reset; STAT := 20 (header len)  -----\u003e parse hdr; r_remain=size1+size2;\n+ *                                          ERASE target region(s)\n+ *                          \u003c-------------- STAT=21 (len+1), then STAT=0\n+ *                                          (erased)\n+ *   -- payload, streamed in slices: --\n+ *   CTRL := WR\n+ *   DATA := word x N ...\n+ *     at word 16384: CTRL:=RST; ADDR:=0x7800; CTRL:=WR  (half-bank -\u003e SB1)\n+ *     at word 32760: flush slice:\n+ *        reset; STAT := \u003cbytes_this_slice\u003e ---\u003e r_remain -= bytes; program\n+ *                          \u003c------------------- STAT=0  (ready for next slice)\n+ *   ... repeat until the whole payload is sent ...\n+ *                          \u003c------------------- STAT=0  image verified\n+ *                                               (STAT=1: image rejected)\n+ *   STAT := END(0x3cc3)  ---------------------\u003e finalise and boot\n+ *\n+ * The r_remain == 0 rule (critical):\n+ *   Every host STAT write in the payload phase is a byte count; the loader\n+ *   does r_remain -= count and stays in the receive loop while r_remain != 0.\n+ *   It leaves the loop ONLY when r_remain hits EXACTLY 0, and a count larger\n+ *   than r_remain underflows the 32-bit counter and wedges the loader until a\n+ *   power cycle. Having left it, the loader verifies the image, publishes the\n+ *   verdict in STAT (0 good, 1 rejected) and waits 2 s for END before\n+ *   finalising regardless -- clearing its rescue-enable bit so boot_go boots\n+ *   the new image -- so END only saves that wait. Hence:\n+ *     - never send a slice/chunk count larger than what is outstanding;\n+ *     - a STAT write is a command only once the loader has left the loop;\n+ *     - the loader leaves the count in STAT while it programs the chunk, so\n+ *       a lingering count does not distinguish \"busy\" from \"verdict\";\n+ *     - interrupted-download recovery feeds 1 byte at a time (see below).\n+ *\n+ * Interrupted-flash recovery (mxl862xx_rescue_drain):\n+ *   A host that dies mid-payload leaves the loader in the receive loop holding\n+ *   STAT=0. Feed single 1-byte chunks (one DATA word + STAT=1) until r_remain\n+ *   reaches 0; the loader then verifies the (now corrupt) image, publishes its\n+ *   verdict and comes back to READY by itself. END is never sent here: while\n+ *   r_remain is non-zero it would be consumed as a 15555-byte count, and a\n+ *   lingering STAT=1 cannot be told from a chunk still being programmed.\n+ *\n+ * Register-read challenge (non-destructive liveness proof):\n+ *   DATA := 0x7c23 (marker); STAT := 0xe2c0|idx\n+ *     -\u003e loader returns a runtime word in DATA and re-arms STAT=0xc55c.\n+ *   The reply source is loader BSS, not a chip id; used only to prove a live\n+ *   mailbox in mxl862xx_rescue_mode_detect().\n+ *\n+ * The other STAT ready magic, 0xc33c, marks the loader's flashless\n+ * chip-to-chip download mode (MxL86281S 16-port tier); this driver does not\n+ * use it.\n+ *\n+ * Rescue lifecycle (devlink): probe runs mxl862xx_rescue_mode_detect(); a\n+ * wedged loader is drained back to READY by a background self-heal\n+ * (rescue_heal_work), so the long recovery never holds the devlink lock.\n+ * devlink dev info exposes the fw version (the \"flashable\" signal) only once at\n+ * READY; flash_update returns -EBUSY until then, and reprobes to WSP firmware\n+ * on success.\n+ *\n+ * Notes:\n+ *   - Chip id/revision (0xc0d28884/88) are NOT reachable on this channel; they\n+ *     need the clause-45 MMD firmware mailbox, which is dead under MCUboot.\n+ *     Rescue identity is by SB PDI behaviour only (mxl862xx_rescue_mode_detect).\n+ *   - The SMDIO PHY address comes from the device tree; the 0xe1xx register\n+ *     offsets are the OTP reset defaults and the only layout supported here.\n+ */\n+\n+#include \u003clinux/crc32.h\u003e\n+#include \u003clinux/delay.h\u003e\n+#include \u003clinux/device.h\u003e\n+#include \u003clinux/iopoll.h\u003e\n+#include \u003clinux/netdevice.h\u003e\n+#include \u003clinux/overflow.h\u003e\n+#include \u003clinux/rtnetlink.h\u003e\n+#include \u003clinux/workqueue.h\u003e\n+#include \u003cnet/dsa.h\u003e\n+#include \u003cnet/switchdev.h\u003e\n+\n+#include \"mxl862xx.h\"\n+#include \"mxl862xx-api.h\"\n+#include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n+#include \"mxl862xx-host.h\"\n+\n+/* SB PDI registers (clause-22 SMDIO address space) */\n+#define MXL862XX_SB_PDI_CTRL\t\t0xe100\n+#define MXL862XX_SB_PDI_ADDR\t\t0xe101\n+#define MXL862XX_SB_PDI_DATA\t\t0xe102\n+#define MXL862XX_SB_PDI_STAT\t\t0xe103\n+\n+/* SB PDI CTRL modes */\n+#define MXL862XX_SB_PDI_CTRL_RST\t0x00\n+#define MXL862XX_SB_PDI_CTRL_WR\t\t0x02\n+\n+/* SB PDI handshake magic (published/consumed via STAT) */\n+#define MXL862XX_SB_PDI_READY\t\t0xc55c\t/* loader idle, console loop */\n+#define MXL862XX_SB_PDI_DL_READY\t0xc33c\t/* loader idle, flashless loop */\n+#define MXL862XX_SB_PDI_START\t\t0xf48f\n+#define MXL862XX_SB_PDI_END\t\t0x3cc3\n+#define MXL862XX_SB_PDI_RDREG\t\t0xe2c0\t/* register-read cmd (| index) */\n+#define MXL862XX_SB_PDI_RDREG_MARK\t0x7c23\t/* marker placed in DATA for RDREG */\n+\n+/* Behavioural presence probe: two distinct 16-bit latches on ADDR/DATA. */\n+#define MXL862XX_SB_PDI_PROBE_A\t\t0x5a5a\n+#define MXL862XX_SB_PDI_PROBE_D\t\t0xa5a5\n+\n+/* Image verification verdict published in STAT once the receive loop ends */\n+#define MXL862XX_SB_PDI_VERIFY_OK\t0\n+#define MXL862XX_SB_PDI_VERIFY_BAD\t1\n+\n+/* Firmware transfer geometry */\n+#define MXL862XX_FW_HDR_SIZE\t\t20\n+#define MXL862XX_FW_BANK_HALF\t\t16384\t/* words per half-bank */\n+#define MXL862XX_FW_BANK_SLICE\t\t32760\t/* words per full slice */\n+#define MXL862XX_FW_SB1_ADDR\t\t0x7800\t/* SB1 word address */\n+\n+/* Timeouts (generous upper bounds) */\n+#define MXL862XX_FW_READY_TIMEOUT_MS\t3000\n+#define MXL862XX_FW_ACK_TIMEOUT_MS\t5000\n+#define MXL862XX_FW_ERASE_TIMEOUT_MS\t300000\n+#define MXL862XX_FW_WRITE_TIMEOUT_MS\t60000\n+#define MXL862XX_FW_REBOOT_DELAY_MS\t5000\n+#define MXL862XX_FW_REPROBE_DELAY_MS\t500\n+/* One loader mailbox step: program a 1-byte chunk or service a command */\n+#define MXL862XX_SB_PDI_STEP_MS\t\t2000\n+/* Covers the loader's END wait, verification and the reset into READY */\n+#define MXL862XX_SB_PDI_VERIFY_MS\t15000\n+\n+static int mxl862xx_sb_pdi_reset(struct mxl862xx_priv *priv)\n+{\n+\tint ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t   MXL862XX_SB_PDI_CTRL_RST);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t   MXL862XX_SB_PDI_CTRL_RST);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\treturn mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t    MXL862XX_SB_PDI_CTRL_RST);\n+}\n+\n+static int mxl862xx_sb_pdi_poll_stat(struct mxl862xx_priv *priv, u16 expected,\n+\t\t\t\t     unsigned long timeout_ms)\n+{\n+\tint ret, val;\n+\n+\tret = read_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t\tval \u003c 0 || (u16)val == expected,\n+\t\t\t\t10000, timeout_ms * 1000, false,\n+\t\t\t\tpriv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\treturn ret;\n+}\n+\n+static int mxl862xx_sb_pdi_flush_slice(struct mxl862xx_priv *priv,\n+\t\t\t\t       u32 data_written)\n+{\n+\tint ret;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\treturn mxl862xx_sb_pdi_poll_stat(priv, 0,\n+\t\t\t\t\t MXL862XX_FW_WRITE_TIMEOUT_MS);\n+}\n+\n+/* Flush the last slice, which ends the receive loop: the loader verifies the\n+ * image and replaces the count in STAT with its verdict, so wait for the count\n+ * to go rather than for a fixed value.\n+ */\n+static int mxl862xx_sb_pdi_flush_last(struct mxl862xx_priv *priv,\n+\t\t\t\t      u32 data_written)\n+{\n+\tint ret, val;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tret = read_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t\tval \u003c 0 || (u16)val != (u16)data_written,\n+\t\t\t\t10000, (MXL862XX_FW_WRITE_TIMEOUT_MS +\n+\t\t\t\t\tMXL862XX_SB_PDI_VERIFY_MS) * 1000,\n+\t\t\t\tfalse, priv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\n+\tif (!ret \u0026\u0026 (u16)val == MXL862XX_SB_PDI_VERIFY_OK)\n+\t\treturn 0;\n+\n+\t/* A final count of 1 is indistinguishable from the reject verdict, so\n+\t * a timeout still holding it lands here too.\n+\t */\n+\tif ((u16)val == MXL862XX_SB_PDI_VERIFY_BAD) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: loader rejected the image\\n\");\n+\t\treturn -EBADMSG;\n+\t}\n+\n+\treturn ret ? ret : -EPROTO;\n+}\n+\n+static void mxl862xx_flash_notify(struct devlink *dl, const char *status,\n+\t\t\t\t  u32 done, u32 total)\n+{\n+\tdevlink_flash_update_status_notify(dl, status, NULL, done, total);\n+}\n+\n+/* Byte-count of each chunk fed to the loader during drain. It MUST be 1: the\n+ * loader only lets us observe \"counter == 0\", never \"counter \u003c step\", so any\n+ * step \u003e 1 can subtract past zero, underflow the 32-bit counter and wedge the\n+ * loader for ~2^32 more bytes (a state only a power cycle clears). Stepping by\n+ * 1 walks the counter through every value and is guaranteed to land on zero\n+ * whatever its (possibly odd) start. A 1-byte chunk is a path the loader\n+ * already handles: the normal transfer ends with a single trailing byte for\n+ * odd-sized images (see Step 6).\n+ */\n+#define MXL862XX_DRAIN_CHUNK_BYTES\t1\n+\n+/* Log the drain's progress every so many bytes; it can run for a long time */\n+#define MXL862XX_DRAIN_LOG_BYTES\t(128 * 1024)\n+\n+/* Wait for the loader to ask for the next chunk (STAT 0) or to come back to its\n+ * command loop (STAT READY), and return the STAT value either way. On timeout\n+ * that is whatever STAT still holds, which carries no further information: the\n+ * loader keeps the count we wrote visible while it programs the chunk, and that\n+ * is the same value it publishes as the \"image rejected\" verdict once the\n+ * counter reaches zero.\n+ *\n+ * STAT 0 is unambiguous here even though it is also the \"image verified\"\n+ * verdict: by the r_remain == 0 rule the loader leaves the receive loop the\n+ * moment the counter reaches zero, so it is never both inside the loop asking\n+ * for a chunk and publishing a verdict. Once it has left, the next STAT write\n+ * is a command rather than a count, so feeding one more chunk after a verdict\n+ * cannot underflow anything either.\n+ */\n+static int mxl862xx_sb_pdi_poll_drain(struct mxl862xx_priv *priv,\n+\t\t\t\t      unsigned long timeout_ms)\n+{\n+\tint val;\n+\n+\tread_poll_timeout(mxl862xx_smdio_read, val,\n+\t\t\t  val \u003c 0 || (u16)val == MXL862XX_SB_PDI_READY ||\n+\t\t\t  (u16)val == 0,\n+\t\t\t  50, timeout_ms * 1000, false,\n+\t\t\t  priv, MXL862XX_SB_PDI_STAT);\n+\tif (val \u003c 0)\n+\t\treturn val;\n+\treturn (u16)val;\n+}\n+\n+/* The loader is not asking for a chunk: it may still be programming the last\n+ * one, or the counter has reached zero and it is verifying the image and\n+ * resetting into READY. Wait that out -- STAT cannot tell the two apart, and\n+ * guessing would mean writing END into a live receive loop.\n+ *\n+ * Return: 0 once the loader has left the loop, -EAGAIN if it asks for another\n+ * chunk after all, -EIO for a loader still holding the count when the verify\n+ * window expires, or an SMDIO bus error.\n+ */\n+static int mxl862xx_rescue_drain_finish(struct mxl862xx_priv *priv, u32 chunk)\n+{\n+\tstruct device *dev = \u0026priv-\u003emdiodev-\u003edev;\n+\tint stat;\n+\n+\tstat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_VERIFY_MS);\n+\tif (stat \u003c 0)\n+\t\treturn stat;\n+\tif (stat == MXL862XX_SB_PDI_READY)\n+\t\treturn 0;\n+\tif (stat == MXL862XX_SB_PDI_VERIFY_BAD) {\n+\t\tdev_err(dev,\n+\t\t\t\"flash: loader stuck after %u chunks, power cycle it\\n\",\n+\t\t\tchunk);\n+\t\treturn -EIO;\n+\t}\n+\tif (stat) {\n+\t\t/* A firmware is answering, not the loader: an image survived\n+\t\t * in flash and booted.\n+\t\t */\n+\t\tdev_info(dev, \"flash: firmware booted while draining\\n\");\n+\t\treturn 0;\n+\t}\n+\n+\treturn -EAGAIN;\n+}\n+\n+/* Recover a switch whose SB PDI download was interrupted mid-transfer - the\n+ * host died after MCUboot began erasing flash, whether it aborted mid erase or\n+ * mid image-write, both end up in the same place: the payload receive loop.\n+ * There the loader publishes STAT=0, waits for the host to write a byte-count\n+ * to STAT, DMAs that many bytes and subtracts the count from a remaining-bytes\n+ * counter, leaving the loop only when the counter reaches exactly zero. The\n+ * image size died with the host, so we feed single-byte chunks (see\n+ * MXL862XX_DRAIN_CHUNK_BYTES) to walk the counter to zero without underflow.\n+ * The loader then verifies the (now corrupt) image and returns to READY by\n+ * itself, or boots a valid image that happened to survive in flash; either way\n+ * the caller's reprobe classifies the result. Every byte costs about a dozen\n+ * MDIO frames, so a multi-MiB outstanding count takes tens of minutes.\n+ * Returns 0 once the loader has left the receive loop, \u003c0 on error. Does NOT\n+ * recover a counter already underflowed by an earlier oversized-chunk attempt\n+ * - that needs a power cycle.\n+ */\n+static int mxl862xx_rescue_drain(struct mxl862xx_priv *priv)\n+{\n+\tstruct device *dev = \u0026priv-\u003emdiodev-\u003edev;\n+\t/* Bound: twice the loader's 16 MiB image cap, one byte per chunk. */\n+\tu32 max_chunks = 2u * (16u \u003c\u003c 20) / MXL862XX_DRAIN_CHUNK_BYTES;\n+\tu32 chunk = 0;\n+\tint ret, stat;\n+\n+\twhile (chunk \u003c max_chunks) {\n+\t\t/* Teardown can interrupt this long drain. */\n+\t\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\t\treturn -ECANCELED;\n+\n+\t\tstat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);\n+\t\tif (stat \u003c 0)\n+\t\t\treturn stat;\n+\t\tif (stat == MXL862XX_SB_PDI_READY)\n+\t\t\treturn 0;\n+\n+\t\tif (stat) {\n+\t\t\tret = mxl862xx_rescue_drain_finish(priv, chunk);\n+\t\t\tif (ret != -EAGAIN)\n+\t\t\t\treturn ret;\n+\t\t}\n+\n+\t\t/* Feed one zero byte; reset cleared the write latch. */\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_sb_pdi_reset(priv);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t\t   MXL862XX_DRAIN_CHUNK_BYTES);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tchunk++;\n+\t\tif (!(chunk % MXL862XX_DRAIN_LOG_BYTES))\n+\t\t\tdev_info(dev, \"flash: drained %u KiB so far\\n\",\n+\t\t\t\t chunk / 1024);\n+\t\tcond_resched();\n+\t}\n+\n+\tdev_err(dev,\n+\t\t\"flash: interrupted download did not drain after %u chunks\\n\",\n+\t\tchunk);\n+\n+\treturn -ETIMEDOUT;\n+}\n+\n+/* Background self-heal: drain a wedged download off the devlink flash path, so\n+ * the long recovery never holds the devlink lock. Scheduled from probe;\n+ * reprobes on success so the probe-time detection re-classifies the switch.\n+ */\n+void mxl862xx_rescue_heal_work_fn(struct work_struct *work)\n+{\n+\tstruct mxl862xx_priv *priv =\n+\t\tcontainer_of(work, struct mxl862xx_priv, rescue_heal_work);\n+\tstruct device *dev = \u0026priv-\u003emdiodev-\u003edev;\n+\tint ret;\n+\n+\tret = mxl862xx_rescue_drain(priv);\n+\tif (ret == -ECANCELED)\n+\t\treturn;\n+\tif (ret) {\n+\t\t/* Nothing retries this, so say so: rescue_ready stays clear\n+\t\t * and devlink dev flash reports why it refuses.\n+\t\t */\n+\t\tdev_err(dev, \"flash: download recovery failed: %pe\\n\",\n+\t\t\tERR_PTR(ret));\n+\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n+\t\treturn;\n+\t}\n+\n+\t/* The interrupted transfer is finalised; reprobe so the probe-time\n+\t * detection brings the driver up -- flashable in rescue mode if the\n+\t * loader is at READY, or normally if a valid image booted. The core\n+\t * skips the re-probe on its own if the device is unbound first; the\n+\t * flag test only avoids scheduling one certain to be skipped. A\n+\t * failed hand-off leaves nothing to reclassify the switch, so mark\n+\t * recovery failed rather than promise a retry that cannot succeed.\n+\t */\n+\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\treturn;\n+\n+\tif (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS))\n+\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n+}\n+\n+/* Detect MCUboot rescue mode over clause-22 SMDIO alone, so the caller can rule\n+ * the loader out before any C45 API request (which spews CRC errors when no WSP\n+ * firmware answers). A scratch write to ADDR/DATA must latch or the chip is\n+ * absent (-ENODEV); the mailbox is reset first, or a transfer interrupted with\n+ * CTRL=WR would take that write as a payload word instead of latching it. STAT\n+ * then classifies the state, poked destructively only when 0, the one value a\n+ * running firmware never holds:\n+ *\n+ *  - 0xc33c: flashless loop; recognised but not supported here.\n+ *  - 0xc55c: console loop, if the register-read challenge is serviced.\n+ *  - other non-zero: running firmware, left unpoked.\n+ *  - 0: wedged receive loop; the 1-byte slice-advance then says whether it\n+ *    still needs draining or has just finished.\n+ *\n+ * The scratch write reaches a running firmware too, but lands in mailbox\n+ * registers it does not read, so it is inert there.\n+ *\n+ * Return: MXL862XX_IN_RESCUE, MXL862XX_NOT_RESCUE, -ENODEV when the scratch\n+ * write does not latch, which is a switch that does not answer at all or one\n+ * whose SB PDI window is not at the offsets above, -EOPNOTSUPP for the\n+ * flashless loop, -ENXIO for a READY loader whose mailbox fails the challenge,\n+ * or an SMDIO bus error.\n+ */\n+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv *priv)\n+{\n+\tint stat, dat, ret, rb, a, d;\n+\n+\t/* rescue_ready gates flashing; a wedged loader needs the drain first. */\n+\tWRITE_ONCE(priv-\u003erescue_ready, false);\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\t/* Presence: a live chip latches the scratch write, an absent one floats. */\n+\ta = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t MXL862XX_SB_PDI_PROBE_A);\n+\tif (a \u003c 0)\n+\t\treturn a;\n+\td = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t MXL862XX_SB_PDI_PROBE_D);\n+\tif (d \u003c 0)\n+\t\treturn d;\n+\ta = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_ADDR);\n+\tif (a \u003c 0)\n+\t\treturn a;\n+\td = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);\n+\tif (d \u003c 0)\n+\t\treturn d;\n+\tif ((u16)a != MXL862XX_SB_PDI_PROBE_A ||\n+\t    (u16)d != MXL862XX_SB_PDI_PROBE_D)\n+\t\treturn -ENODEV;\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\tstat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_STAT);\n+\tif (stat \u003c 0)\n+\t\treturn stat;\n+\n+\t/* Flashless-download loop (MxL86281S tier): this driver does not\n+\t * support it -- the console flash path expects READY. Treat it as an\n+\t * unusable configuration, like any other unsupported state.\n+\t */\n+\tif ((u16)stat == MXL862XX_SB_PDI_DL_READY)\n+\t\treturn -EOPNOTSUPP;\n+\n+\t/* Console loop at READY: confirm the live mailbox with the register-read\n+\t * challenge (consumes the marker from DATA and re-arms READY).\n+\t */\n+\tif ((u16)stat == MXL862XX_SB_PDI_READY) {\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,\n+\t\t\t\t\t   MXL862XX_SB_PDI_RDREG_MARK);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t\t   MXL862XX_SB_PDI_RDREG);\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\trb = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,\n+\t\t\t\t\t       MXL862XX_SB_PDI_STEP_MS);\n+\t\tdat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);\n+\t\tret = mxl862xx_sb_pdi_reset(priv);\n+\t\t/* Never re-arming READY fails the challenge like any other\n+\t\t * unserviced command; report it as such rather than as a bus\n+\t\t * timeout the bus never saw.\n+\t\t */\n+\t\tif (rb == -ETIMEDOUT)\n+\t\t\trb = -ENXIO;\n+\t\tif (rb \u003c 0)\n+\t\t\treturn rb;\n+\t\tif (dat \u003c 0)\n+\t\t\treturn dat;\n+\t\tif (ret \u003c 0)\n+\t\t\treturn ret;\n+\t\tif ((u16)dat != MXL862XX_SB_PDI_RDREG_MARK) {\n+\t\t\tWRITE_ONCE(priv-\u003erescue_ready, true);\n+\t\t\treturn MXL862XX_IN_RESCUE;\n+\t\t}\n+\t\t/* READY but the marker is untouched, so nothing is servicing the\n+\t\t * mailbox. A firmware publishing 0xc55c as its status word looks\n+\t\t * exactly like this, and flashing one would be far worse than\n+\t\t * refusing to bind, so treat it as unusable.\n+\t\t */\n+\t\treturn -ENXIO;\n+\t}\n+\n+\t/* Any other non-zero value is a running firmware, not a loader. */\n+\tif (stat)\n+\t\treturn MXL862XX_NOT_RESCUE;\n+\n+\t/* STAT == 0: a wedged receive loop takes a 1-byte slice-advance (feed\n+\t * one DATA word first, like a drain chunk) and asks for the next chunk\n+\t * by publishing 0 again. Had that byte been the last one outstanding,\n+\t * the loader leaves the loop instead and returns to READY, having\n+\t * consumed the advance -- proof enough of a live mailbox to skip the\n+\t * challenge. Anything else means it is still working on it. All three\n+\t * are rescue, so this never fails probe; only the drain does.\n+\t */\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t   MXL862XX_DRAIN_CHUNK_BYTES);\n+\tif (ret \u003c 0)\n+\t\treturn ret;\n+\n+\trb = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);\n+\tif (rb \u003c 0)\n+\t\treturn rb;\n+\tif (rb == MXL862XX_SB_PDI_READY)\n+\t\tWRITE_ONCE(priv-\u003erescue_ready, true);\n+\n+\treturn MXL862XX_IN_RESCUE;\n+}\n+\n+/* MCUboot firmware image header */\n+struct mxl862xx_fw_hdr {\n+\t__le32 image_type;\n+\t__le32 image_size_1;\n+\t__le32 image_checksum_1;\n+\t__le32 image_size_2;\n+\t__le32 image_checksum_2;\n+} __packed;\n+\n+static int mxl862xx_flash_validate(struct mxl862xx_priv *priv,\n+\t\t\t\t   const struct firmware *fw,\n+\t\t\t\t   u32 *payload_size)\n+{\n+\tconst struct mxl862xx_fw_hdr *hdr;\n+\tu32 size1, size2, total;\n+\tconst u8 *payload;\n+\tu32 crc;\n+\n+\tif (fw-\u003esize \u003c MXL862XX_FW_HDR_SIZE)\n+\t\treturn -EINVAL;\n+\n+\thdr = (const struct mxl862xx_fw_hdr *)fw-\u003edata;\n+\tpayload = fw-\u003edata + MXL862XX_FW_HDR_SIZE;\n+\tsize1 = le32_to_cpu(hdr-\u003eimage_size_1);\n+\tsize2 = le32_to_cpu(hdr-\u003eimage_size_2);\n+\n+\tif (check_add_overflow(size1, size2, \u0026total) ||\n+\t    total \u003e fw-\u003esize - MXL862XX_FW_HDR_SIZE) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: firmware file too small for declared size\\n\");\n+\t\treturn -EINVAL;\n+\t}\n+\n+\tif (!total) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: firmware file with empty payload\\n\");\n+\t\treturn -EINVAL;\n+\t}\n+\n+\tif (size1) {\n+\t\tcrc = ~crc32_le(~0U, payload, size1);\n+\t\tif (crc != le32_to_cpu(hdr-\u003eimage_checksum_1)) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: image 1 CRC mismatch (got %08x, expected %08x)\\n\",\n+\t\t\t\tcrc, le32_to_cpu(hdr-\u003eimage_checksum_1));\n+\t\t\treturn -EINVAL;\n+\t\t}\n+\t}\n+\n+\tif (size2) {\n+\t\tcrc = ~crc32_le(~0U, payload + size1, size2);\n+\t\tif (crc != le32_to_cpu(hdr-\u003eimage_checksum_2)) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: image 2 CRC mismatch (got %08x, expected %08x)\\n\",\n+\t\t\t\tcrc, le32_to_cpu(hdr-\u003eimage_checksum_2));\n+\t\t\treturn -EINVAL;\n+\t\t}\n+\t}\n+\n+\t*payload_size = total;\n+\n+\treturn 0;\n+}\n+\n+static int mxl862xx_flash_firmware(struct mxl862xx_priv *priv,\n+\t\t\t\t   const struct firmware *fw,\n+\t\t\t\t   u32 payload_size, struct devlink *dl)\n+{\n+\tconst u8 *payload = fw-\u003edata + MXL862XX_FW_HDR_SIZE;\n+\tu32 word_idx = 0, data_written = 0, idx = 0;\n+\tunsigned long next_notify = jiffies - 1;\n+\tu16 word, fdata;\n+\tint ret, i;\n+\n+\t/* Step 1: reboot the firmware into MCUboot rescue mode */\n+\tif (!priv-\u003erescue_mode) {\n+\t\tret = mxl862xx_api_wrap(priv, SYS_MISC_FW_UPDATE, NULL, 0,\n+\t\t\t\t\tfalse, false);\n+\t\tif (ret) {\n+\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\"flash: FW_UPDATE command failed: %pe\\n\",\n+\t\t\t\tERR_PTR(ret));\n+\t\t\treturn ret;\n+\t\t}\n+\t}\n+\n+\t/* Step 2: wait for bootloader ready */\n+\tmxl862xx_flash_notify(dl, \"Waiting for bootloader\", 0, 0);\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/* Failures from here on end up at no_end, which returns the error\n+\t * without signalling END -- see there.\n+\t */\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,\n+\t\t\t\t\tMXL862XX_FW_READY_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: bootloader not ready: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/* Step 3: start handshake */\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t   MXL862XX_SB_PDI_START);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_START + 1,\n+\t\t\t\t\tMXL862XX_FW_ACK_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: start handshake failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/* Step 4: transfer image header */\n+\tmxl862xx_flash_notify(dl, \"Erasing flash\", 0, 0);\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\tfor (i = 0; i \u003c MXL862XX_FW_HDR_SIZE / 2; i++) {\n+\t\tword = fw-\u003edata[i * 2] |\n+\t\t       ((u16)fw-\u003edata[i * 2 + 1] \u003c\u003c 8);\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, word);\n+\t\tif (ret \u003c 0)\n+\t\t\tgoto write_err;\n+\t}\n+\n+\tret = mxl862xx_sb_pdi_reset(priv);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/* the byte count in STAT triggers the erase */\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t   MXL862XX_FW_HDR_SIZE);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\t/* ACK is byte count + 1 */\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_FW_HDR_SIZE + 1,\n+\t\t\t\t\tMXL862XX_FW_ACK_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: header ACK failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/* Step 5: wait for erase to complete */\n+\tret = mxl862xx_sb_pdi_poll_stat(priv, 0,\n+\t\t\t\t\tMXL862XX_FW_ERASE_TIMEOUT_MS);\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: erase timeout: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\t/* Step 6: transfer payload */\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\tif (ret \u003c 0)\n+\t\tgoto write_err;\n+\n+\twhile (idx \u003c payload_size) {\n+\t\tcond_resched();\n+\t\tif (idx + 1 \u003c payload_size) {\n+\t\t\tfdata = payload[idx] |\n+\t\t\t\t((u16)payload[idx + 1] \u003c\u003c 8);\n+\t\t\tidx += 2;\n+\t\t\tdata_written += 2;\n+\t\t} else {\n+\t\t\tfdata = payload[idx];\n+\t\t\tidx++;\n+\t\t\tdata_written++;\n+\t\t}\n+\n+\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, fdata);\n+\t\tif (ret \u003c 0)\n+\t\t\tgoto write_err;\n+\t\tword_idx++;\n+\n+\t\tif (idx \u003e= payload_size) {\n+\t\t\tret = mxl862xx_sb_pdi_flush_last(priv, data_written);\n+\t\t\tbreak;\n+\t\t}\n+\n+\t\t/* Half-bank boundary: switch to SB1 address */\n+\t\tif (word_idx == MXL862XX_FW_BANK_HALF) {\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t   MXL862XX_SB_PDI_CTRL_RST);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,\n+\t\t\t\t\t\t   MXL862XX_FW_SB1_ADDR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\t\t} else if (word_idx \u003e= MXL862XX_FW_BANK_SLICE) {\n+\t\t\tret = mxl862xx_sb_pdi_flush_slice(priv, data_written);\n+\t\t\tif (ret) {\n+\t\t\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\t\t\"flash: write timeout at %u/%u: %pe\\n\",\n+\t\t\t\t\tidx, payload_size, ERR_PTR(ret));\n+\t\t\t\tgoto no_end;\n+\t\t\t}\n+\t\t\tword_idx = 0;\n+\t\t\tdata_written = 0;\n+\t\t\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,\n+\t\t\t\t\t\t   MXL862XX_SB_PDI_CTRL_WR);\n+\t\t\tif (ret \u003c 0)\n+\t\t\t\tgoto write_err;\n+\n+\t\t\tif (time_after(jiffies, next_notify)) {\n+\t\t\t\tmxl862xx_flash_notify(dl, \"Flashing\", idx,\n+\t\t\t\t\t\t      payload_size);\n+\t\t\t\tnext_notify = jiffies + msecs_to_jiffies(500);\n+\t\t\t}\n+\t\t}\n+\t}\n+\n+\tif (ret) {\n+\t\tdev_err(\u0026priv-\u003emdiodev-\u003edev,\n+\t\t\t\"flash: final slice failed: %pe\\n\", ERR_PTR(ret));\n+\t\tgoto no_end;\n+\t}\n+\n+\tmxl862xx_flash_notify(dl, \"Flashing\", payload_size, payload_size);\n+\n+\t/* Success: the loader has left the receive loop at r_remain == 0 and\n+\t * verified the image, so END(0x3cc3) is a finalise/boot request rather\n+\t * than a byte count. Signal it here -- and only here -- to boot the new\n+\t * image without waiting out the loader's 2 s END timeout.\n+\t */\n+\tret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,\n+\t\t\t\t   MXL862XX_SB_PDI_END);\n+\tmsleep(MXL862XX_FW_REBOOT_DELAY_MS);\n+\treturn ret;\n+\n+write_err:\n+\tdev_err(\u0026priv-\u003emdiodev-\u003edev, \"flash: SMDIO write failed: %pe\\n\",\n+\t\tERR_PTR(ret));\n+no_end:\n+\t/* A failure leaves the loader mid transfer; do not signal END (a STAT\n+\t * write is a byte count then, and END would be misread as one, risking\n+\t * a receive-counter underflow). Return the error; the caller reprobes.\n+\t */\n+\treturn ret;\n+}\n+\n+int mxl862xx_devlink_info_get(struct dsa_switch *ds,\n+\t\t\t      struct devlink_info_req *req,\n+\t\t\t      struct netlink_ext_ack *extack)\n+{\n+\tstruct mxl862xx_priv *priv = ds-\u003epriv;\n+\tchar buf[16];\n+\tint ret;\n+\n+\t/* No chip-id/revision in MCUboot (needs the firmware MMD mailbox). The\n+\t * fw version doubles as the \"ready to flash\" signal: report it only\n+\t * once the loader is at a clean READY, nothing while still draining.\n+\t */\n+\tif (priv-\u003erescue_mode) {\n+\t\tif (!READ_ONCE(priv-\u003erescue_ready))\n+\t\t\treturn 0;\n+\n+\t\tsnprintf(buf, sizeof(buf), \"%u.%u.%u\",\n+\t\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t\t priv-\u003efw_version.revision);\n+\t\tret = devlink_info_version_running_put(req,\n+\t\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\t\treturn devlink_info_version_stored_put(req,\n+\t\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\t}\n+\n+\t/* A 0 part number means the CHIP ID read failed or the part is\n+\t * unfused; omit it rather than publish a bogus \"0000\" that fwupd\n+\t * would match firmware against -- it then falls back to the driver\n+\t * name.\n+\t */\n+\tif (priv-\u003easic_id) {\n+\t\tsnprintf(buf, sizeof(buf), \"%04X\", priv-\u003easic_id);\n+\t\tret = devlink_info_version_fixed_put(req,\n+\t\t\t\t\t\t     DEVLINK_INFO_VERSION_GENERIC_ASIC_ID,\n+\t\t\t\t\t\t     buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\n+\t\tsnprintf(buf, sizeof(buf), \"%u\", priv-\u003easic_rev);\n+\t\tret = devlink_info_version_fixed_put(req,\n+\t\t\t\t\t\t     DEVLINK_INFO_VERSION_GENERIC_ASIC_REV,\n+\t\t\t\t\t\t     buf);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\t}\n+\n+\t/* An all-zero version is the cache a failed flash left behind, not a\n+\t * released firmware; omit it like the part number above.\n+\t */\n+\tif (!priv-\u003efw_version.major \u0026\u0026 !priv-\u003efw_version.minor \u0026\u0026\n+\t    !priv-\u003efw_version.revision)\n+\t\treturn 0;\n+\n+\tsnprintf(buf, sizeof(buf), \"%u.%u.%u\",\n+\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t priv-\u003efw_version.revision);\n+\n+\tret = devlink_info_version_running_put(req,\n+\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+\tif (ret)\n+\t\treturn ret;\n+\n+\t/* boots this image from its own flash: stored == running */\n+\treturn devlink_info_version_stored_put(req,\n+\t\t\tDEVLINK_INFO_VERSION_GENERIC_FW, buf);\n+}\n+\n+int mxl862xx_devlink_flash_update(struct dsa_switch *ds,\n+\t\t\t\t  struct devlink_flash_update_params *params,\n+\t\t\t\t  struct netlink_ext_ack *extack)\n+{\n+\tstruct mxl862xx_priv *priv = ds-\u003epriv;\n+\tstruct dsa_port *dp;\n+\tu32 payload_size;\n+\tint ret, err, i;\n+\n+\tif (params-\u003ecomponent) {\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"component is not supported\");\n+\t\treturn -EOPNOTSUPP;\n+\t}\n+\n+\t/* A previous flash is still waiting for its reprobe: the firmware API\n+\t * is short-circuited, so the raw SB PDI writes below would run against\n+\t * a switch this driver no longer tracks.\n+\t */\n+\tif (priv-\u003eskip_teardown) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t   \"device is reinitializing, retry later\");\n+\t\treturn -EBUSY;\n+\t}\n+\n+\tret = mxl862xx_flash_validate(priv, params-\u003efw, \u0026payload_size);\n+\tif (ret) {\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"firmware image validation failed\");\n+\t\treturn ret;\n+\t}\n+\n+\t/* Refuse to flash while the background self-heal is still draining, and\n+\t * for good once it has given up on the loader.\n+\t */\n+\tif (READ_ONCE(priv-\u003erescue_failed)) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t   \"download recovery failed, power cycle the switch\");\n+\t\treturn -EIO;\n+\t}\n+\n+\tif (priv-\u003erescue_mode \u0026\u0026 !READ_ONCE(priv-\u003erescue_ready)) {\n+\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t   \"switch is recovering an interrupted download, retry shortly\");\n+\t\treturn -EBUSY;\n+\t}\n+\n+\tif (priv-\u003erescue_mode)\n+\t\tdev_info(ds-\u003edev,\n+\t\t\t \"flash: flashing switch via MCUboot rescue mode\\n\");\n+\telse\n+\t\tdev_info(ds-\u003edev, \"flash: running firmware %u.%u.%u\\n\",\n+\t\t\t priv-\u003efw_version.major, priv-\u003efw_version.minor,\n+\t\t\t priv-\u003efw_version.revision);\n+\n+\t/* Close ports while the firmware is still alive so the DSA core's\n+\t * MDB/FDB tracking is drained, and detach user ports so userspace\n+\t * cannot reopen them during the flash. The conduit is only closed,\n+\t * not detached: it belongs to the MAC driver. This driver binds a\n+\t * single switch with a direct host link and no cascade ports, so the\n+\t * conduit serves only this switch, and flashing it reboots the switch,\n+\t * which takes the tree down regardless.\n+\t */\n+\trtnl_lock();\n+\tdsa_switch_for_each_user_port(dp, ds) {\n+\t\tif (dp-\u003euser) {\n+\t\t\tdev_close(dp-\u003euser);\n+\t\t\tnetif_device_detach(dp-\u003euser);\n+\t\t}\n+\t}\n+\tdsa_switch_for_each_cpu_port(dp, ds)\n+\t\tdev_close(dp-\u003econduit);\n+\t/* The bridge defers the STP state changes triggered by closing\n+\t * the ports; let them reach the firmware while it is still alive.\n+\t */\n+\tswitchdev_deferred_process();\n+\trtnl_unlock();\n+\n+\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n+\tpriv-\u003eblock_host = true;\n+\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\tset_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags);\n+\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n+\tcancel_work_sync(\u0026priv-\u003ecrc_err_work);\n+\tfor (i = 0; i \u003c ds-\u003enum_ports; i++)\n+\t\tcancel_work_sync(\u0026priv-\u003eports[i].host_flood_work);\n+\n+\tret = mxl862xx_flash_firmware(priv, params-\u003efw, payload_size,\n+\t\t\t\t      ds-\u003edevlink);\n+\tif (ret)\n+\t\tNL_SET_ERR_MSG_MOD(extack, \"firmware transfer failed\");\n+\n+\tif (!ret) {\n+\t\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock,\n+\t\t\t\t  MDIO_MUTEX_NESTED);\n+\t\t/* Keep block_host set so host writes stay blocked, but let the\n+\t\t * readiness poll below read the freshly booted firmware.\n+\t\t */\n+\t\tpriv-\u003eflash_reading = true;\n+\t\tpriv-\u003erescue_mode = false;\n+\t\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\t\t/* Refresh the cached versions so the flash update only\n+\t\t * completes once the new firmware is confirmed running and\n+\t\t * devlink dev info reports it. Must happen before setting\n+\t\t * skip_teardown, which discards all firmware API reads.\n+\t\t */\n+\t\tret = mxl862xx_wait_ready(ds);\n+\t\tif (ret)\n+\t\t\tNL_SET_ERR_MSG_MOD(extack,\n+\t\t\t\t\t   \"new firmware did not become ready\");\n+\t}\n+\n+\tif (ret) {\n+\t\t/* The switch is in MCUboot with erased or partly written flash;\n+\t\t * drop the cached identity so devlink dev info stops reporting\n+\t\t * the pre-flash version until the reprobe re-reads the truth.\n+\t\t */\n+\t\tmemset(\u0026priv-\u003efw_version, 0, sizeof(priv-\u003efw_version));\n+\t\tpriv-\u003easic_id = 0;\n+\t\tpriv-\u003easic_rev = 0;\n+\t}\n+\n+\tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n+\tpriv-\u003eflash_reading = false;\n+\tpriv-\u003eblock_host = false;\n+\tpriv-\u003eskip_teardown = true;\n+\tmutex_unlock(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock);\n+\n+\t/* Reinitialise through a deferred re-probe: remove() runs with\n+\t * skip_teardown set, then a fresh probe() starts against whatever\n+\t * the switch now runs. The core skips the re-probe if the device\n+\t * is unbound or shut down before it fires.\n+\t */\n+\terr = device_schedule_reprobe(ds-\u003edev, MXL862XX_FW_REPROBE_DELAY_MS);\n+\n+\treturn ret ? ret : err;\n+}\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.h b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h\nnew file mode 100644\nindex 0000000000000..7cd87c7ad8716\n--- /dev/null\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h\n@@ -0,0 +1,20 @@\n+/* SPDX-License-Identifier: GPL-2.0-or-later */\n+\n+#ifndef __MXL862XX_FW_H\n+#define __MXL862XX_FW_H\n+\n+#include \u003cnet/dsa.h\u003e\n+\n+struct mxl862xx_priv;\n+struct work_struct;\n+\n+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv *priv);\n+void mxl862xx_rescue_heal_work_fn(struct work_struct *work);\n+int mxl862xx_devlink_info_get(struct dsa_switch *ds,\n+\t\t\t      struct devlink_info_req *req,\n+\t\t\t      struct netlink_ext_ack *extack);\n+int mxl862xx_devlink_flash_update(struct dsa_switch *ds,\n+\t\t\t\t  struct devlink_flash_update_params *params,\n+\t\t\t\t  struct netlink_ext_ack *extack);\n+\n+#endif /* __MXL862XX_FW_H */\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.c b/drivers/net/dsa/mxl862xx/mxl862xx-host.c\nindex 4acd216f7cc00..23e5dfe81e364 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.c\n@@ -15,6 +15,8 @@\n #include \u003clinux/unaligned.h\u003e\n #include \u003cnet/dsa.h\u003e\n #include \"mxl862xx.h\"\n+#include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n #include \"mxl862xx-host.h\"\n \n #define CTRL_BUSY_MASK\t\t\tBIT(15)\n@@ -340,6 +342,26 @@ int mxl862xx_api_wrap(struct mxl862xx_priv *priv, u16 cmd, void *_data,\n \n \tmutex_lock_nested(\u0026priv-\u003emdiodev-\u003ebus-\u003emdio_lock, MDIO_MUTEX_NESTED);\n \n+\tif (priv-\u003eskip_teardown) {\n+\t\tret = read ? -ENODEV : 0;\n+\t\tgoto out;\n+\t}\n+\n+\tif (priv-\u003erescue_mode) {\n+\t\tret = -ENODEV;\n+\t\tgoto out;\n+\t}\n+\n+\t/* During the post-flash readiness poll block_host stays set, but the\n+\t * flash path's own firmware version reads must reach the new image;\n+\t * host writes stay blocked so stale resource IDs cannot corrupt it.\n+\t */\n+\tif (priv-\u003eblock_host \u0026\u0026 cmd != SYS_MISC_FW_UPDATE \u0026\u0026\n+\t    !(priv-\u003eflash_reading \u0026\u0026 read)) {\n+\t\tret = -EBUSY;\n+\t\tgoto out;\n+\t}\n+\n \tmax = (size + 1) / 2;\n \n \tret = mxl862xx_busy_wait(priv);\n@@ -495,12 +517,54 @@ int mxl862xx_reset(struct mxl862xx_priv *priv)\n \treturn ret;\n }\n \n+#define MXL862XX_SMDIO_ADDR_REG\t\t0x1f\n+#define MXL862XX_SMDIO_PAGE_MASK\t0xfff0\n+#define MXL862XX_SMDIO_OFF_MASK\t\t0x000f\n+\n+/* Paged clause-22 window: the page goes into MII register 0x1f, the low nibble\n+ * of addr selects one of the 16 registers within it. Both helpers take the MDIO\n+ * bus lock per transaction, so callers must not already hold it -- unlike\n+ * mxl862xx_api_wrap(), which holds it across a whole firmware command.\n+ */\n+int mxl862xx_smdio_read(struct mxl862xx_priv *priv, u32 addr)\n+{\n+\tstruct mii_bus *bus = priv-\u003emdiodev-\u003ebus;\n+\tint phy = priv-\u003emdiodev-\u003eaddr;\n+\tint ret;\n+\n+\tmutex_lock(\u0026bus-\u003emdio_lock);\n+\tret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,\n+\t\t\t      addr \u0026 MXL862XX_SMDIO_PAGE_MASK);\n+\tif (ret \u003e= 0)\n+\t\tret = __mdiobus_read(bus, phy, addr \u0026 MXL862XX_SMDIO_OFF_MASK);\n+\tmutex_unlock(\u0026bus-\u003emdio_lock);\n+\treturn ret;\n+}\n+\n+int mxl862xx_smdio_write(struct mxl862xx_priv *priv, u32 addr, u16 val)\n+{\n+\tstruct mii_bus *bus = priv-\u003emdiodev-\u003ebus;\n+\tint phy = priv-\u003emdiodev-\u003eaddr;\n+\tint ret;\n+\n+\tmutex_lock(\u0026bus-\u003emdio_lock);\n+\tret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,\n+\t\t\t      addr \u0026 MXL862XX_SMDIO_PAGE_MASK);\n+\tif (ret \u003e= 0)\n+\t\tret = __mdiobus_write(bus, phy, addr \u0026 MXL862XX_SMDIO_OFF_MASK,\n+\t\t\t\t      val);\n+\tmutex_unlock(\u0026bus-\u003emdio_lock);\n+\treturn ret;\n+}\n+\n void mxl862xx_host_init(struct mxl862xx_priv *priv)\n {\n \tINIT_WORK(\u0026priv-\u003ecrc_err_work, mxl862xx_crc_err_work_fn);\n+\tINIT_WORK(\u0026priv-\u003erescue_heal_work, mxl862xx_rescue_heal_work_fn);\n }\n \n void mxl862xx_host_shutdown(struct mxl862xx_priv *priv)\n {\n \tcancel_work_sync(\u0026priv-\u003ecrc_err_work);\n+\tcancel_work_sync(\u0026priv-\u003erescue_heal_work);\n }\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.h b/drivers/net/dsa/mxl862xx/mxl862xx-host.h\nindex 66d6ae198aff4..4e054c6e4c0e4 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.h\n@@ -18,5 +18,7 @@ int mxl862xx_api_wrap(struct mxl862xx_priv *priv, u16 cmd, void *data, u16 size,\n \tmxl862xx_api_wrap(dev, cmd, \u0026(data), sizeof((data)), true, true)\n \n int mxl862xx_reset(struct mxl862xx_priv *priv);\n+int mxl862xx_smdio_read(struct mxl862xx_priv *priv, u32 addr);\n+int mxl862xx_smdio_write(struct mxl862xx_priv *priv, u32 addr, u16 val);\n \n #endif /* __MXL862XX_HOST_H */\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\nindex b689652aa9b92..a5b6940b552e9 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c\n@@ -406,6 +406,8 @@ mxl862xx_phylink_mac_select_pcs(struct phylink_config *config,\n \n \tswitch (port) {\n \tcase 9 ... 16:\n+\t\tif (priv-\u003erescue_mode)\n+\t\t\treturn NULL;\n \t\tif (!MXL862XX_FW_VER_MIN(priv, 1, 0, 84)) {\n \t\t\tdev_warn_once(dp-\u003eds-\u003edev,\n \t\t\t\t      \"SerDes PCS unsupported on old firmware.\\n\");\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c\nindex 45d237b3a40f1..74abf88c09cc6 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx.c\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx.c\n@@ -21,6 +21,7 @@\n #include \"mxl862xx.h\"\n #include \"mxl862xx-api.h\"\n #include \"mxl862xx-cmd.h\"\n+#include \"mxl862xx-fw.h\"\n #include \"mxl862xx-host.h\"\n #include \"mxl862xx-phylink.h\"\n \n@@ -71,6 +72,13 @@ static const struct ethtool_rmon_hist_range mxl862xx_rmon_ranges[] = {\n #define MXL862XX_READY_TIMEOUT_MS\t10000\n #define MXL862XX_READY_POLL_MS\t\t100\n \n+/* Chip ID registers, read via SYS_MISC_REG_RD */\n+#define MXL862XX_CHIPID_L\t\t0xc0d28884\n+#define MXL862XX_CHIPID_M\t\t0xc0d28888\n+#define MXL862XX_CHIPID_L_PNUML\t\tGENMASK(15, 12)\n+#define MXL862XX_CHIPID_M_PNUMM\t\tGENMASK(11, 0)\n+#define MXL862XX_CHIPID_M_VERSION\tGENMASK(14, 12)\n+\n #define MXL862XX_TCM_INST_SEL\t\t0xe00\n #define MXL862XX_TCM_CBS\t\t0xe12\n #define MXL862XX_TCM_EBS\t\t0xe13\n@@ -222,7 +230,46 @@ static int mxl862xx_phy_write_c45_mii_bus(struct mii_bus *bus, int addr,\n \treturn mxl862xx_phy_write_mmd(bus-\u003epriv, addr, devadd, regnum, val);\n }\n \n-static int mxl862xx_wait_ready(struct dsa_switch *ds)\n+/* Read the static chip part number and version from the CHIP ID\n+ * registers. Only possible with a running firmware, so the values are\n+ * cached at setup and left zero when the switch is in rescue mode.\n+ */\n+static int mxl862xx_read_chip_id(struct mxl862xx_priv *priv)\n+{\n+\tstruct mxl862xx_sys_reg_rw reg = {};\n+\tu16 chipid_l, chipid_m;\n+\tint ret;\n+\n+\treg.addr = cpu_to_le32(MXL862XX_CHIPID_L);\n+\tret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);\n+\tif (ret)\n+\t\treturn ret;\n+\tchipid_l = le32_to_cpu(reg.val);\n+\n+\treg.addr = cpu_to_le32(MXL862XX_CHIPID_M);\n+\tret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);\n+\tif (ret)\n+\t\treturn ret;\n+\tchipid_m = le32_to_cpu(reg.val);\n+\n+\tpriv-\u003easic_id = FIELD_GET(MXL862XX_CHIPID_L_PNUML, chipid_l) |\n+\t\t\tFIELD_GET(MXL862XX_CHIPID_M_PNUMM, chipid_m) \u003c\u003c 4;\n+\tpriv-\u003easic_rev = FIELD_GET(MXL862XX_CHIPID_M_VERSION, chipid_m);\n+\n+\treturn 0;\n+}\n+\n+/**\n+ * mxl862xx_wait_ready - wait for the switch firmware to become operational\n+ * @ds: DSA switch instance\n+ *\n+ * Poll the firmware until it reports its version and accepts\n+ * configuration commands, then cache the firmware version and chip ID.\n+ * Takes at least two seconds.\n+ *\n+ * Return: 0 on success or a negative error code.\n+ */\n+int mxl862xx_wait_ready(struct dsa_switch *ds)\n {\n \tstruct mxl862xx_sys_fw_image_version ver = {};\n \tunsigned long start = jiffies, timeout;\n@@ -254,6 +301,11 @@ static int mxl862xx_wait_ready(struct dsa_switch *ds)\n \t\tpriv-\u003efw_version.major = ver.iv_major;\n \t\tpriv-\u003efw_version.minor = ver.iv_minor;\n \t\tpriv-\u003efw_version.revision = le16_to_cpu(ver.iv_revision);\n+\n+\t\tret = mxl862xx_read_chip_id(priv);\n+\t\tif (ret)\n+\t\t\tdev_warn(ds-\u003edev, \"failed to read chip ID: %pe\\n\",\n+\t\t\t\t ERR_PTR(ret));\n \t\treturn 0;\n \n not_ready_yet:\n@@ -622,21 +674,66 @@ static int mxl862xx_setup(struct dsa_switch *ds)\n \tint n_user_ports = 0, max_vlans;\n \tint ingress_finals, vid_rules;\n \tstruct dsa_port *dp;\n-\tint ret, i;\n-\n-\tret = mxl862xx_reset(priv);\n-\tif (ret)\n-\t\treturn ret;\n-\n-\tret = mxl862xx_wait_ready(ds);\n-\tif (ret)\n-\t\treturn ret;\n+\tint ret, i, rescue;\n \n+\t/* The SerDes state is software-only and must exist before anything can\n+\t * reach phylink, including a rescue-mode flash clearing rescue_mode\n+\t * ahead of the reprobe.\n+\t */\n \tmutex_init(\u0026priv-\u003eserdes_lock);\n \tfor (i = 0; i \u003c ARRAY_SIZE(priv-\u003eserdes_ports); i++)\n \t\tmxl862xx_setup_pcs(priv, \u0026priv-\u003eserdes_ports[i],\n \t\t\t\t   i + MXL862XX_FIRST_SERDES_PORT);\n \n+\t/* Detect the loader over SB PDI first: it needs no firmware, unlike the\n+\t * C45 API (mxl862xx_reset/wait_ready) which spews CRC errors when none\n+\t * answers. Touch C45 only once rescue is ruled out.\n+\t */\n+\trescue = mxl862xx_rescue_mode_detect(priv);\n+\tif (rescue \u003c 0) {\n+\t\tdev_err(ds-\u003edev, \"switch state detection failed: %pe\\n\",\n+\t\t\tERR_PTR(rescue));\n+\t\treturn rescue;\n+\t}\n+\n+\tif (rescue == MXL862XX_NOT_RESCUE) {\n+\t\tret = mxl862xx_reset(priv);\n+\t\tif (ret)\n+\t\t\treturn ret;\n+\n+\t\tret = mxl862xx_wait_ready(ds);\n+\t\tif (ret) {\n+\t\t\t/* the reset may only now have triggered rescue mode */\n+\t\t\trescue = mxl862xx_rescue_mode_detect(priv);\n+\t\t\tif (rescue \u003c 0) {\n+\t\t\t\tdev_err(ds-\u003edev,\n+\t\t\t\t\t\"switch not responding after reset: %pe\\n\",\n+\t\t\t\t\tERR_PTR(rescue));\n+\t\t\t\treturn rescue;\n+\t\t\t}\n+\t\t\tif (rescue == MXL862XX_NOT_RESCUE)\n+\t\t\t\treturn ret;\n+\t\t}\n+\t}\n+\n+\tpriv-\u003erescue_mode = rescue;\n+\n+\tif (priv-\u003erescue_mode) {\n+\t\tif (priv-\u003erescue_ready) {\n+\t\t\tdev_warn(ds-\u003edev,\n+\t\t\t\t \"switch in MCUboot rescue mode, use devlink to flash new firmware\\n\");\n+\t\t} else {\n+\t\t\t/* Drain the wedged download in the background so it\n+\t\t\t * never holds the devlink lock; info and flash become\n+\t\t\t * available once ready.\n+\t\t\t */\n+\t\t\tdev_warn(ds-\u003edev,\n+\t\t\t\t \"switch in MCUboot with an interrupted download, recovering in background\\n\");\n+\t\t\tqueue_work(system_long_wq, \u0026priv-\u003erescue_heal_work);\n+\t\t}\n+\t\treturn 0;\n+\t}\n+\n \t/* Calculate Extended VLAN block sizes.\n \t * With VLAN Filter handling VID membership checks:\n \t *   Ingress: only final catchall rules (PVID insertion, 802.1Q\n@@ -715,11 +812,21 @@ static int mxl862xx_port_state(struct dsa_switch *ds, int port, bool enable)\n static int mxl862xx_port_enable(struct dsa_switch *ds, int port,\n \t\t\t\tstruct phy_device *phydev)\n {\n+\tstruct mxl862xx_priv *priv = ds-\u003epriv;\n+\n+\tif (priv-\u003erescue_mode)\n+\t\treturn 0;\n+\n \treturn mxl862xx_port_state(ds, port, true);\n }\n \n static void mxl862xx_port_disable(struct dsa_switch *ds, int port)\n {\n+\tstruct mxl862xx_priv *priv = ds-\u003epriv;\n+\n+\tif (priv-\u003erescue_mode)\n+\t\treturn;\n+\n \tif (mxl862xx_port_state(ds, port, false))\n \t\tdev_err(ds-\u003edev, \"failed to disable port %d\\n\", port);\n }\n@@ -1337,6 +1444,17 @@ static int mxl862xx_port_setup(struct dsa_switch *ds, int port)\n \tbool is_cpu_port = dsa_port_is_cpu(dp);\n \tint ret;\n \n+\tif (dsa_port_is_dsa(dp)) {\n+\t\tdev_err(ds-\u003edev, \"port %d: DSA links not supported\\n\", port);\n+\t\treturn -EOPNOTSUPP;\n+\t}\n+\n+\t/* DSA reinits failed user ports as unused; shared ports must\n+\t * succeed for the tree to register.\n+\t */\n+\tif (priv-\u003erescue_mode)\n+\t\treturn dsa_port_is_user(dp) ? -ENODEV : 0;\n+\n \tret = mxl862xx_port_state(ds, port, false);\n \tif (ret)\n \t\treturn ret;\n@@ -1346,11 +1464,6 @@ static int mxl862xx_port_setup(struct dsa_switch *ds, int port)\n \tif (dsa_port_is_unused(dp))\n \t\treturn 0;\n \n-\tif (dsa_port_is_dsa(dp)) {\n-\t\tdev_err(ds-\u003edev, \"port %d: DSA links not supported\\n\", port);\n-\t\treturn -EOPNOTSUPP;\n-\t}\n-\n \tret = mxl862xx_configure_sp_tag_proto(ds, port, is_cpu_port);\n \tif (ret)\n \t\treturn ret;\n@@ -1572,6 +1685,12 @@ static int mxl862xx_port_mdb_del(struct dsa_switch *ds, int port,\n \tether_addr_copy(qparam.mac, mdb-\u003eaddr);\n \n \tret = MXL862XX_API_READ(priv, MXL862XX_MAC_TABLEENTRYQUERY, qparam);\n+\t/* Post-flash teardown or MCUboot: the firmware and its MAC table are\n+\t * gone, so there is nothing left to delete. Outside those, -ENODEV is a\n+\t * bus error and must be reported.\n+\t */\n+\tif (ret == -ENODEV \u0026\u0026 (priv-\u003eskip_teardown || priv-\u003erescue_mode))\n+\t\treturn 0;\n \tif (ret)\n \t\treturn ret;\n \n@@ -1628,6 +1747,9 @@ static void mxl862xx_port_stp_state_set(struct dsa_switch *ds, int port,\n \tstruct mxl862xx_priv *priv = ds-\u003epriv;\n \tint ret;\n \n+\tif (priv-\u003erescue_mode)\n+\t\treturn;\n+\n \tswitch (state) {\n \tcase BR_STATE_DISABLED:\n \t\tparam.port_state = cpu_to_le32(MXL862XX_STP_PORT_STATE_DISABLE);\n@@ -2015,6 +2137,12 @@ static void mxl862xx_stats_work_fn(struct work_struct *work)\n \tstruct dsa_switch *ds = priv-\u003eds;\n \tstruct dsa_port *dp;\n \n+\t/* A get_stats64() re-arm can race the flash teardown's WORK_STOPPED\n+\t * set and cancel; bail here so a stray poll never runs during a flash.\n+\t */\n+\tif (test_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags))\n+\t\treturn;\n+\n \tdsa_switch_for_each_available_port(dp, ds)\n \t\tmxl862xx_stats_poll(ds, dp-\u003eindex);\n \n@@ -2086,6 +2214,8 @@ static const struct dsa_switch_ops mxl862xx_switch_ops = {\n \t.get_pause_stats = mxl862xx_get_pause_stats,\n \t.get_rmon_stats = mxl862xx_get_rmon_stats,\n \t.get_stats64 = mxl862xx_get_stats64,\n+\t.devlink_info_get = mxl862xx_devlink_info_get,\n+\t.devlink_flash_update = mxl862xx_devlink_flash_update,\n };\n \n static int mxl862xx_probe(struct mdio_device *mdiodev)\n@@ -2151,10 +2281,16 @@ static void mxl862xx_remove(struct mdio_device *mdiodev)\n \tpriv = ds-\u003epriv;\n \n \tset_bit(MXL862XX_FLAG_WORK_STOPPED, \u0026priv-\u003eflags);\n-\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n \n \tdsa_unregister_switch(ds);\n \n+\t/* Cancel the stats poll only after the user netdevs are gone: until\n+\t * dsa_unregister_switch() returns a get_stats64() can still re-arm the\n+\t * work after a plain cancel, and it would then run against the\n+\t * devres-freed priv.\n+\t */\n+\tcancel_delayed_work_sync(\u0026priv-\u003estats_work);\n+\n \tmxl862xx_host_shutdown(priv);\n \n \t/* Cancel any pending host flood work. dsa_unregister_switch()\ndiff --git a/drivers/net/dsa/mxl862xx/mxl862xx.h b/drivers/net/dsa/mxl862xx/mxl862xx.h\nindex 432a5f3f2e08e..bdaf295c8a9f6 100644\n--- a/drivers/net/dsa/mxl862xx/mxl862xx.h\n+++ b/drivers/net/dsa/mxl862xx/mxl862xx.h\n@@ -4,7 +4,9 @@\n #define __MXL862XX_H\n \n #include \u003casm/byteorder.h\u003e\n+#include \u003clinux/bitops.h\u003e\n #include \u003clinux/mdio.h\u003e\n+#include \u003clinux/mutex.h\u003e\n #include \u003clinux/workqueue.h\u003e\n #include \u003cnet/dsa.h\u003e\n \n@@ -14,6 +16,10 @@ struct mxl862xx_priv;\n #define MXL862XX_FIRST_SERDES_PORT\t9\n #define MXL862XX_SERDES_SLOTS\t\t4\n \n+/* mxl862xx_rescue_mode_detect() return codes (negative values are errors) */\n+#define MXL862XX_NOT_RESCUE\t\t0\n+#define MXL862XX_IN_RESCUE\t\t1\n+\n #define MXL862XX_DEFAULT_BRIDGE\t\t0\n #define MXL862XX_MAX_BRIDGES\t\t48\n #define MXL862XX_MAX_BRIDGE_PORTS\t128\n@@ -303,6 +309,10 @@ struct mxl862xx_fw_version {\n  *                      flooding)\n  * @fw_version:         cached firmware version, populated at probe and\n  *                      compared with MXL862XX_FW_VER_MIN()\n+ * @asic_id:            chip part number read from the CHIP ID registers,\n+ *                      reported as the devlink \"asic.id\" fixed version\n+ * @asic_rev:           chip version read from the CHIP ID registers,\n+ *                      reported as the devlink \"asic.rev\" fixed version\n  * @serdes_ports:       SerDes interfaces incl. sub-interfaces in case of\n  *                      10G_QXGMII or QSGMII\n  * @serdes_refcount:    per-XPCS count of sub-ports enabled by phylink;\n@@ -319,6 +329,22 @@ struct mxl862xx_fw_version {\n  * @evlan_ingress_size: per-port ingress Extended VLAN block size\n  * @evlan_egress_size:  per-port egress Extended VLAN block size\n  * @vf_block_size:      per-port VLAN Filter block size\n+ * @block_host:         reject firmware API commands (except FW_UPDATE)\n+ *                      during a firmware flash\n+ * @flash_reading:      let the flash path's own firmware reads through\n+ *                      block_host while polling the freshly booted image\n+ * @skip_teardown:      discard firmware API commands during the teardown\n+ *                      triggered by the post-flash reprobe\n+ * @rescue_mode:        switch is in MCUboot; firmware API commands fail fast,\n+ *                      only clause-22 SMDIO works. Set from setup() before the\n+ *                      switch is registered and cleared under the MDIO bus lock\n+ *                      for the benefit of mxl862xx_api_wrap(); other readers\n+ *                      only need it to be a stable single flag.\n+ * @rescue_ready:       (rescue_mode) loader is at a clean READY and will accept\n+ *                      a flash; false while rescue_heal_work is draining\n+ * @rescue_failed:      (rescue_mode) the self-heal gave up; the loader needs a\n+ *                      power cycle and no flash can be accepted\n+ * @rescue_heal_work:   background self-heal draining a wedged download to READY\n  * @stats_work:         periodic work item that polls RMON hardware counters\n  *                      and accumulates them into 64-bit per-port stats\n  */\n@@ -326,9 +352,12 @@ struct mxl862xx_priv {\n \tstruct dsa_switch *ds;\n \tstruct mdio_device *mdiodev;\n \tstruct work_struct crc_err_work;\n+\tstruct work_struct rescue_heal_work;\n \tunsigned long flags;\n \tu16 drop_meter;\n \tstruct mxl862xx_fw_version fw_version;\n+\tu16 asic_id;\n+\tu8 asic_rev;\n \tstruct mxl862xx_pcs serdes_ports[8];\n \tint serdes_refcount[2];\n \tstruct mutex serdes_lock;\n@@ -337,7 +366,15 @@ struct mxl862xx_priv {\n \tu16 evlan_ingress_size;\n \tu16 evlan_egress_size;\n \tu16 vf_block_size;\n+\tbool block_host;\n+\tbool flash_reading;\n+\tbool skip_teardown;\n+\tbool rescue_mode;\n+\tbool rescue_ready;\n+\tbool rescue_failed;\n \tstruct delayed_work stats_work;\n };\n \n+int mxl862xx_wait_ready(struct dsa_switch *ds);\n+\n #endif /* __MXL862XX_H */\ndiff --git a/include/linux/device.h b/include/linux/device.h\nindex aee79fd6b32b4..7a99169505772 100644\n--- a/include/linux/device.h\n+++ b/include/linux/device.h\n@@ -1314,6 +1314,8 @@ int  __must_check device_attach(struct device *dev);\n int __must_check driver_attach(const struct device_driver *drv);\n void device_initial_probe(struct device *dev);\n int __must_check device_reprobe(struct device *dev);\n+int __must_check device_schedule_reprobe(struct device *dev,\n+\t\t\t\t\t unsigned int delay_ms);\n \n bool device_is_bound(struct device *dev);\n \ndiff --git a/include/net/dsa.h b/include/net/dsa.h\nindex 6f7f5c17b5320..58597b14e592a 100644\n--- a/include/net/dsa.h\n+++ b/include/net/dsa.h\n@@ -1172,6 +1172,9 @@ struct dsa_switch_ops {\n \tint\t(*devlink_info_get)(struct dsa_switch *ds,\n \t\t\t\t    struct devlink_info_req *req,\n \t\t\t\t    struct netlink_ext_ack *extack);\n+\tint\t(*devlink_flash_update)(struct dsa_switch *ds,\n+\t\t\t\t\tstruct devlink_flash_update_params *params,\n+\t\t\t\t\tstruct netlink_ext_ack *extack);\n \tint\t(*devlink_sb_pool_get)(struct dsa_switch *ds,\n \t\t\t\t       unsigned int sb_index, u16 pool_index,\n \t\t\t\t       struct devlink_sb_pool_info *pool_info);\ndiff --git a/net/dsa/devlink.c b/net/dsa/devlink.c\nindex ed342f345692b..25311a87cbc56 100644\n--- a/net/dsa/devlink.c\n+++ b/net/dsa/devlink.c\n@@ -20,6 +20,18 @@ static int dsa_devlink_info_get(struct devlink *dl,\n \treturn -EOPNOTSUPP;\n }\n \n+static int dsa_devlink_flash_update(struct devlink *dl,\n+\t\t\t\t    struct devlink_flash_update_params *params,\n+\t\t\t\t    struct netlink_ext_ack *extack)\n+{\n+\tstruct dsa_switch *ds = dsa_devlink_to_ds(dl);\n+\n+\tif (!ds-\u003eops-\u003edevlink_flash_update)\n+\t\treturn -EOPNOTSUPP;\n+\n+\treturn ds-\u003eops-\u003edevlink_flash_update(ds, params, extack);\n+}\n+\n static int dsa_devlink_sb_pool_get(struct devlink *dl,\n \t\t\t\t   unsigned int sb_index, u16 pool_index,\n \t\t\t\t   struct devlink_sb_pool_info *pool_info)\n@@ -169,6 +181,7 @@ dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp,\n \n static const struct devlink_ops dsa_devlink_ops = {\n \t.info_get\t\t\t= dsa_devlink_info_get,\n+\t.flash_update\t\t\t= dsa_devlink_flash_update,\n \t.sb_pool_get\t\t\t= dsa_devlink_sb_pool_get,\n \t.sb_pool_set\t\t\t= dsa_devlink_sb_pool_set,\n \t.sb_port_pool_get\t\t= dsa_devlink_sb_port_pool_get,\n"
}

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.",
  "WorthFuzzing": false
}

You are an expert Linux kernel maintainer.
Your job is to review a provided patch series and determine
if it makes functional changes to the kernel that should be fuzzed.

IMPORTANT: The changes have ALREADY been applied and committed as the HEAD commit in
your workspace. Do NOT rely on your internal knowledge of the kernel. You must actively
use your code access tools to examine the actual source code and confirm any assumptions.

Return WorthFuzzing=false if the patch only contains:
- Modifications to Documentation/, Kconfig files, or code comments.
- Purely decorative changes, such as logging (e.g., pr_err, printk) or tracepoints.
- Changes to numeric constants or macros that do not functionally alter execution flow.
- Code paths that are impossible to reach in virtualized environments like GCE or QEMU,
  even when utilizing software-emulated hardware (e.g., usb gadget, mac80211_hwsim).
- Code in vendor-specific PCIe switch, SmartNIC, or GPU drivers (e.g., mlxsw, pds_core, qed,
  ionic, amdgpu) that require physical PCIe hardware cards not emulated in standard QEMU.
- Driver .remove, .shutdown, or pci_unregister_driver teardown callbacks (e.g., igb_remove)
  that are executed only during PCI hot-unplug or sysfs driver unbind operations.

If it modifies reachable core kernel logic, drivers, or architectures, use your code search
tools to verify the code can be executed, then return WorthFuzzing=true.

When returning WorthFuzzing=true, you MUST ALSO:
1. Extract any specific kernel functions that should be heavily fuzzed into FocusSymbols.
   Avoid listing generic hot-path functions to prevent skewed test distributions.
   Prefer non-static, non-inlined API entrypoint functions over internal static helper functions
   (which are inlined by the compiler and do not have distinct symbol addresses).
2. Identify any specific CONFIG_ options required to properly test this new/modified feature.
   Go and look into the Kconfig files and check for ifdefs around the code, do not make assumptions.
   Also check "depends on" lines in Kconfig to include any non-standard parent subsystem configs
   needed for Kbuild to compile the code statically into vmlinux. List them in the EnableConfigs
   output array, and DO NOT add a 'CONFIG_' prefix (e.g., return "NET_IPV4" instead of "CONFIG_NET_IPV4").
Prefer calling several tools at the same time to save round-trips.


Use set-results tool to provide results of the analysis.
It must be called exactly once before the final reply.
Ignore results of this tool.

For your convenience, here is the diff of the changes:
commit a01707c4f39f9db8f15411902f052348a25923e9
Author: syz-cluster <triage@syzkaller.com>
Date:   Sun Aug 16 23:35:08 2026 +0000

    syz-cluster: applied patch under review

diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst
index 4745148fecf4f..058999d0dc56f 100644
--- a/Documentation/networking/devlink/index.rst
+++ b/Documentation/networking/devlink/index.rst
@@ -94,6 +94,7 @@ parameters, info versions, and other features it supports.
    mlx5
    mlxsw
    mv88e6xxx
+   mxl862xx
    netdevsim
    nfp
    octeontx2
diff --git a/Documentation/networking/devlink/mxl862xx.rst b/Documentation/networking/devlink/mxl862xx.rst
new file mode 100644
index 0000000000000..5b24d8cb57bc9
--- /dev/null
+++ b/Documentation/networking/devlink/mxl862xx.rst
@@ -0,0 +1,74 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+========================
+mxl862xx devlink support
+========================
+
+This document describes the devlink features implemented by the
+``mxl862xx`` device driver.
+
+Info versions
+=============
+
+The ``mxl862xx`` driver reports the following versions
+
+.. list-table:: devlink info versions implemented
+   :widths: 5 5 5 85
+
+   * - Name
+     - Type
+     - Example
+     - Description
+   * - ``asic.id``
+     - fixed
+     - 8628
+     - The chip part number read from the CHIP ID registers. Omitted
+       when the part number reads as zero, which happens for a switch
+       sitting in MCUboot rescue mode (the registers need a running
+       firmware), for an unfused part, and after a failed flash.
+   * - ``asic.rev``
+     - fixed
+     - 0
+     - The chip version read from the same register word, so it is
+       omitted whenever ``asic.id`` is.
+   * - ``fw``
+     - running, stored
+     - 1.0.70
+     - Version of the firmware running on the switch, reported as both
+       running and stored since the switch boots it from its own flash.
+       It is omitted while no firmware version is known: after a failed
+       flash, and in MCUboot rescue mode while an interrupted download
+       is still being recovered in the background. Once the loader is
+       ready to accept a new image the version appears as "0.0.0",
+       which no released firmware reports, so version-comparing tools
+       offer any available release as an upgrade. Use ``devlink dev
+       flash`` to tell a recovering switch from a ready one, see below;
+       a missing version on its own does not say why.
+
+Flash update
+============
+
+The ``mxl862xx`` driver implements support for ``devlink dev flash``.
+The signed firmware image is transferred to the switch over the same
+MDIO bus which is also used to manage the switch, then verified and
+installed by the MCUboot bootloader running on the switch. All ports
+of the switch are closed for the duration of the update and the driver
+reprobes the switch after it has rebooted into the new firmware. A
+complete flash and reprobe cycle takes about one minute.
+
+A switch stuck in MCUboot rescue mode, e.g. after an interrupted
+update, is registered without user ports. If the previous download was
+interrupted mid-transfer the loader is wedged; the driver drains it
+back to a clean ready state in the background, one byte at a time,
+which takes tens of minutes for a large image and is reported through
+the kernel log as it progresses. During that recovery ``devlink dev
+flash`` returns ``-EBUSY`` with an extack message saying so, and
+``devlink dev info`` reports no firmware version. Once the loader is
+ready the firmware version appears and flashing a firmware image
+through the regular update flow recovers the switch.
+
+If the recovery fails, the loader needs a power cycle: ``devlink dev
+flash`` then returns ``-EIO`` and says so in its extack message. The
+driver only re-examines the switch when it binds, so on a board where
+the switch can be power cycled on its own, unbind and rebind the driver
+afterwards to have the recovered switch recognised.
diff --git a/MAINTAINERS b/MAINTAINERS
index 991460050da74..e3f7ded569bf7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16106,6 +16106,7 @@ M:	Daniel Golle <daniel@makrotopia.org>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml
+F:	Documentation/networking/devlink/mxl862xx.rst
 F:	drivers/net/dsa/mxl862xx/
 F:	net/dsa/tag_mxl862xx.c
 
diff --git a/drivers/base/base.h b/drivers/base/base.h
index a5b7abc10ff02..6234e37de7e99 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -106,6 +106,10 @@ struct driver_private {
  * @dead: This device is currently either in the process of or has been
  *	  removed from the system. Any asynchronous events scheduled for this
  *	  device should exit without taking any action.
+ * @shutdown_done: Set once device_shutdown() has reached this device, under
+ *	  the device lock, before any shutdown callback runs. Read under the
+ *	  device lock. A deferred re-probe scheduled with
+ *	  device_schedule_reprobe() must not detach the device anymore.
  *
  * Nothing outside of the driver core should ever touch these fields.
  */
@@ -120,6 +124,7 @@ struct device_private {
 	char *deferred_probe_reason;
 	struct device *device;
 	u8 dead:1;
+	u8 shutdown_done:1;
 };
 #define to_device_private_parent(obj)	\
 	container_of(obj, struct device_private, knode_parent)
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 4d026682944f2..8a7dbe4e8362b 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4906,6 +4906,9 @@ void device_shutdown(void)
 			device_lock(parent);
 		device_lock(dev);
 
+		if (dev->p)
+			dev->p->shutdown_done = true;
+
 		/* Don't allow any more runtime suspends */
 		pm_runtime_get_noresume(dev);
 		pm_runtime_barrier(dev);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 60c005223844d..3394b1c7ed180 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -1436,3 +1436,102 @@ void driver_detach(const struct device_driver *drv)
 		put_device(dev);
 	}
 }
+
+struct device_reprobe {
+	struct delayed_work work;
+	struct device *dev;
+	struct device *parent;
+	const struct device_driver *drv;
+};
+
+static void device_reprobe_work_fn(struct work_struct *work)
+{
+	struct device_reprobe *rp = container_of(work, struct device_reprobe,
+						 work.work);
+	struct device *dev = rp->dev;
+	struct device *parent = rp->parent;
+	bool detached = false;
+
+	__device_driver_lock(dev, parent);
+	/*
+	 * rp->drv is only ever compared, never dereferenced: the driver it
+	 * points to may have been unregistered and freed by now.
+	 */
+	if (!dev->p->dead && !dev->p->shutdown_done &&
+	    dev->driver && dev->driver == rp->drv) {
+		__device_release_driver(dev, parent);
+		detached = true;
+	}
+	__device_driver_unlock(dev, parent);
+
+	if (detached) {
+		/*
+		 * device_attach() must run with the parent locked on buses
+		 * that require it, mirroring bus_rescan_devices_helper().
+		 */
+		if (parent && dev->bus->need_parent_lock)
+			device_lock(parent);
+		if (device_attach(dev) < 0)
+			dev_err(dev, "re-probe failed, device left unbound\n");
+		if (parent && dev->bus->need_parent_lock)
+			device_unlock(parent);
+	}
+
+	put_device(dev);
+	put_device(parent);
+	kfree(rp);
+}
+
+/**
+ * device_schedule_reprobe - schedule a deferred detach and re-probe
+ * @dev: device to detach and re-probe
+ * @delay_ms: delay in milliseconds before the re-probe runs
+ *
+ * Schedule a detach and re-probe of @dev after @delay_ms milliseconds.
+ * The re-probe is skipped if, by the time the scheduled work runs, the
+ * device has been removed, the system shutdown sequence has reached the
+ * device, or @dev is no longer bound to the driver that was bound at
+ * scheduling time. In particular an administrative unbind is never
+ * undone by a stale re-probe.
+ *
+ * The work function is built-in text, so the bound driver may call this
+ * from its own code without holding a module reference. If the driver
+ * module is unloaded before the work runs, driver unregistration unbinds
+ * @dev first and the scheduled work does nothing.
+ *
+ * Multiple pending re-probes for the same device are individually safe;
+ * a caller that wants at most one pending re-probe must gate scheduling
+ * itself.
+ *
+ * May only be called from process context.
+ *
+ * Returns: 0 on success, -EINVAL if @dev is not a registered device
+ * bound to a driver, -ENOMEM on allocation failure.
+ */
+int device_schedule_reprobe(struct device *dev, unsigned int delay_ms)
+{
+	struct device_reprobe *rp;
+
+	if (!dev->bus || !dev->p || !device_is_registered(dev))
+		return -EINVAL;
+	if (!dev->driver)
+		return -EINVAL;
+
+	rp = kzalloc_obj(*rp);
+	if (!rp)
+		return -ENOMEM;
+
+	rp->dev = get_device(dev);
+	/*
+	 * Pin the parent too: the work locks it, and an unregister of @dev
+	 * would otherwise drop the last reference before the work runs.
+	 */
+	rp->parent = get_device(dev->parent);
+	rp->drv = READ_ONCE(dev->driver);
+	INIT_DELAYED_WORK(&rp->work, device_reprobe_work_fn);
+	queue_delayed_work(system_dfl_wq, &rp->work,
+			   msecs_to_jiffies(delay_ms));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(device_schedule_reprobe);
diff --git a/drivers/net/dsa/mxl862xx/Makefile b/drivers/net/dsa/mxl862xx/Makefile
index a7be0e6669dfa..bccac0d0f703f 100644
--- a/drivers/net/dsa/mxl862xx/Makefile
+++ b/drivers/net/dsa/mxl862xx/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o
-mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o
+mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-api.h b/drivers/net/dsa/mxl862xx/mxl862xx-api.h
index a180a5decffc0..6f771895984cb 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx-api.h
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-api.h
@@ -1224,6 +1224,16 @@ struct mxl862xx_sys_fw_image_version {
 	__le32 iv_build_num;
 } __packed;
 
+/**
+ * struct mxl862xx_sys_reg_rw - System register read/write
+ * @addr: 32-bit register address
+ * @val: register value
+ */
+struct mxl862xx_sys_reg_rw {
+	__le32 addr;
+	__le32 val;
+} __packed;
+
 /**
  * enum mxl862xx_port_type - Port Type
  * @MXL862XX_LOGICAL_PORT: Logical Port
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h
index c87a955c13c48..a865425aa61e1 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-cmd.h
@@ -70,7 +70,9 @@
 #define INT_GPHY_READ			(GPY_GPY2XX_MAGIC + 0x1)
 #define INT_GPHY_WRITE			(GPY_GPY2XX_MAGIC + 0x2)
 
+#define SYS_MISC_FW_UPDATE		(SYS_MISC_MAGIC + 0x1)
 #define SYS_MISC_FW_VERSION		(SYS_MISC_MAGIC + 0x2)
+#define SYS_MISC_REG_RD			(SYS_MISC_MAGIC + 0x8)
 
 #define MXL862XX_XPCS_PCS_CONFIG	(MXL862XX_XPCS_MAGIC + 0x1)
 #define MXL862XX_XPCS_PCS_GET_STATE	(MXL862XX_XPCS_MAGIC + 0x2)
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.c b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c
new file mode 100644
index 0000000000000..1de8d9970a369
--- /dev/null
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.c
@@ -0,0 +1,1062 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Firmware flash and devlink support for MaxLinear MxL862xx
+ *
+ * Copyright (C) 2025 Daniel Golle <daniel@makrotopia.org>
+ *
+ * SB PDI - firmware download interface over clause-22 SMDIO
+ * =========================================================
+ *
+ * The MxL862xx MCUboot loader accepts a firmware image through four "SB PDI"
+ * registers in the switch SMDIO register space. It runs whenever no WSP
+ * firmware is active: the normal firmware update enters it deliberately - the
+ * SYS_MISC_FW_UPDATE API command sets a sticky rescue bit and reboots into
+ * MCUboot - and the loader also stays here when the stored WSP firmware fails
+ * its boot-time integrity check. This driver drives the loader's 0xc55c
+ * "console" download path.
+ *
+ * SMDIO register access (mxl862xx_smdio_read/write):
+ *   MII reg 0x1f := (<sb_pdi_reg> & 0xfff0)   ; page latch
+ *   MII reg (<sb_pdi_reg> & 0x000f) := / => <u16 data>
+ * so CTRL/ADDR/DATA/STAT (0xe100..0xe103) are MII regs 0/1/2/3 of page
+ * 0xe100, not all reg 0x00.
+ *
+ * SB PDI registers (host name/addr  ->  MCU mailbox):
+ *   CTRL 0xe100 -> 0xc0938400   mode: RST=0x00  RD=0x01  WR=0x02
+ *   ADDR 0xe101 -> 0xc0938404   SB target word address (SB1 bank = 0x7800)
+ *   DATA 0xe102 -> 0xc0938408   16-bit data / reply word
+ *   STAT 0xe103 -> 0xc093840c   handshake: a magic (below) or a byte count
+ *
+ * STAT magics:
+ *   READY  0xc55c   loader idle in the console loop        (this driver)
+ *   DL_RDY 0xc33c   loader idle in the flashless loop
+ *   START  0xf48f   host   -> begin download session
+ *   ACK    0xf490   loader -> START acknowledged (START + 1)
+ *   END    0x3cc3   host   -> finalise now (optional, see below)
+ *   RDREG  0xe2c0   host   -> register-read command (| index), see below
+ *
+ * Console flash path (STAT=0xc55c) - mxl862xx_flash_firmware():
+ *
+ *   host                                   loader
+ *   ----                                   ------
+ *   reset (CTRL=ADDR=DATA=0)
+ *   read STAT ............................ 0xc55c   (READY, idle)
+ *   STAT := START(0xf48f)  -------------->
+ *                          <-------------- STAT = 0xf490 (ACK)
+ *   CTRL := WR
+ *   DATA := hdr[0..9]  (20-byte header: type,size1,crc1,size2,crc2)
+ *   reset; STAT := 20 (header len)  -----> parse hdr; r_remain=size1+size2;
+ *                                          ERASE target region(s)
+ *                          <-------------- STAT=21 (len+1), then STAT=0
+ *                                          (erased)
+ *   -- payload, streamed in slices: --
+ *   CTRL := WR
+ *   DATA := word x N ...
+ *     at word 16384: CTRL:=RST; ADDR:=0x7800; CTRL:=WR  (half-bank -> SB1)
+ *     at word 32760: flush slice:
+ *        reset; STAT := <bytes_this_slice> ---> r_remain -= bytes; program
+ *                          <------------------- STAT=0  (ready for next slice)
+ *   ... repeat until the whole payload is sent ...
+ *                          <------------------- STAT=0  image verified
+ *                                               (STAT=1: image rejected)
+ *   STAT := END(0x3cc3)  ---------------------> finalise and boot
+ *
+ * The r_remain == 0 rule (critical):
+ *   Every host STAT write in the payload phase is a byte count; the loader
+ *   does r_remain -= count and stays in the receive loop while r_remain != 0.
+ *   It leaves the loop ONLY when r_remain hits EXACTLY 0, and a count larger
+ *   than r_remain underflows the 32-bit counter and wedges the loader until a
+ *   power cycle. Having left it, the loader verifies the image, publishes the
+ *   verdict in STAT (0 good, 1 rejected) and waits 2 s for END before
+ *   finalising regardless -- clearing its rescue-enable bit so boot_go boots
+ *   the new image -- so END only saves that wait. Hence:
+ *     - never send a slice/chunk count larger than what is outstanding;
+ *     - a STAT write is a command only once the loader has left the loop;
+ *     - the loader leaves the count in STAT while it programs the chunk, so
+ *       a lingering count does not distinguish "busy" from "verdict";
+ *     - interrupted-download recovery feeds 1 byte at a time (see below).
+ *
+ * Interrupted-flash recovery (mxl862xx_rescue_drain):
+ *   A host that dies mid-payload leaves the loader in the receive loop holding
+ *   STAT=0. Feed single 1-byte chunks (one DATA word + STAT=1) until r_remain
+ *   reaches 0; the loader then verifies the (now corrupt) image, publishes its
+ *   verdict and comes back to READY by itself. END is never sent here: while
+ *   r_remain is non-zero it would be consumed as a 15555-byte count, and a
+ *   lingering STAT=1 cannot be told from a chunk still being programmed.
+ *
+ * Register-read challenge (non-destructive liveness proof):
+ *   DATA := 0x7c23 (marker); STAT := 0xe2c0|idx
+ *     -> loader returns a runtime word in DATA and re-arms STAT=0xc55c.
+ *   The reply source is loader BSS, not a chip id; used only to prove a live
+ *   mailbox in mxl862xx_rescue_mode_detect().
+ *
+ * The other STAT ready magic, 0xc33c, marks the loader's flashless
+ * chip-to-chip download mode (MxL86281S 16-port tier); this driver does not
+ * use it.
+ *
+ * Rescue lifecycle (devlink): probe runs mxl862xx_rescue_mode_detect(); a
+ * wedged loader is drained back to READY by a background self-heal
+ * (rescue_heal_work), so the long recovery never holds the devlink lock.
+ * devlink dev info exposes the fw version (the "flashable" signal) only once at
+ * READY; flash_update returns -EBUSY until then, and reprobes to WSP firmware
+ * on success.
+ *
+ * Notes:
+ *   - Chip id/revision (0xc0d28884/88) are NOT reachable on this channel; they
+ *     need the clause-45 MMD firmware mailbox, which is dead under MCUboot.
+ *     Rescue identity is by SB PDI behaviour only (mxl862xx_rescue_mode_detect).
+ *   - The SMDIO PHY address comes from the device tree; the 0xe1xx register
+ *     offsets are the OTP reset defaults and the only layout supported here.
+ */
+
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/iopoll.h>
+#include <linux/netdevice.h>
+#include <linux/overflow.h>
+#include <linux/rtnetlink.h>
+#include <linux/workqueue.h>
+#include <net/dsa.h>
+#include <net/switchdev.h>
+
+#include "mxl862xx.h"
+#include "mxl862xx-api.h"
+#include "mxl862xx-cmd.h"
+#include "mxl862xx-fw.h"
+#include "mxl862xx-host.h"
+
+/* SB PDI registers (clause-22 SMDIO address space) */
+#define MXL862XX_SB_PDI_CTRL		0xe100
+#define MXL862XX_SB_PDI_ADDR		0xe101
+#define MXL862XX_SB_PDI_DATA		0xe102
+#define MXL862XX_SB_PDI_STAT		0xe103
+
+/* SB PDI CTRL modes */
+#define MXL862XX_SB_PDI_CTRL_RST	0x00
+#define MXL862XX_SB_PDI_CTRL_WR		0x02
+
+/* SB PDI handshake magic (published/consumed via STAT) */
+#define MXL862XX_SB_PDI_READY		0xc55c	/* loader idle, console loop */
+#define MXL862XX_SB_PDI_DL_READY	0xc33c	/* loader idle, flashless loop */
+#define MXL862XX_SB_PDI_START		0xf48f
+#define MXL862XX_SB_PDI_END		0x3cc3
+#define MXL862XX_SB_PDI_RDREG		0xe2c0	/* register-read cmd (| index) */
+#define MXL862XX_SB_PDI_RDREG_MARK	0x7c23	/* marker placed in DATA for RDREG */
+
+/* Behavioural presence probe: two distinct 16-bit latches on ADDR/DATA. */
+#define MXL862XX_SB_PDI_PROBE_A		0x5a5a
+#define MXL862XX_SB_PDI_PROBE_D		0xa5a5
+
+/* Image verification verdict published in STAT once the receive loop ends */
+#define MXL862XX_SB_PDI_VERIFY_OK	0
+#define MXL862XX_SB_PDI_VERIFY_BAD	1
+
+/* Firmware transfer geometry */
+#define MXL862XX_FW_HDR_SIZE		20
+#define MXL862XX_FW_BANK_HALF		16384	/* words per half-bank */
+#define MXL862XX_FW_BANK_SLICE		32760	/* words per full slice */
+#define MXL862XX_FW_SB1_ADDR		0x7800	/* SB1 word address */
+
+/* Timeouts (generous upper bounds) */
+#define MXL862XX_FW_READY_TIMEOUT_MS	3000
+#define MXL862XX_FW_ACK_TIMEOUT_MS	5000
+#define MXL862XX_FW_ERASE_TIMEOUT_MS	300000
+#define MXL862XX_FW_WRITE_TIMEOUT_MS	60000
+#define MXL862XX_FW_REBOOT_DELAY_MS	5000
+#define MXL862XX_FW_REPROBE_DELAY_MS	500
+/* One loader mailbox step: program a 1-byte chunk or service a command */
+#define MXL862XX_SB_PDI_STEP_MS		2000
+/* Covers the loader's END wait, verification and the reset into READY */
+#define MXL862XX_SB_PDI_VERIFY_MS	15000
+
+static int mxl862xx_sb_pdi_reset(struct mxl862xx_priv *priv)
+{
+	int ret;
+
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+				   MXL862XX_SB_PDI_CTRL_RST);
+	if (ret < 0)
+		return ret;
+
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,
+				   MXL862XX_SB_PDI_CTRL_RST);
+	if (ret < 0)
+		return ret;
+
+	return mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,
+				    MXL862XX_SB_PDI_CTRL_RST);
+}
+
+static int mxl862xx_sb_pdi_poll_stat(struct mxl862xx_priv *priv, u16 expected,
+				     unsigned long timeout_ms)
+{
+	int ret, val;
+
+	ret = read_poll_timeout(mxl862xx_smdio_read, val,
+				val < 0 || (u16)val == expected,
+				10000, timeout_ms * 1000, false,
+				priv, MXL862XX_SB_PDI_STAT);
+	if (val < 0)
+		return val;
+	return ret;
+}
+
+static int mxl862xx_sb_pdi_flush_slice(struct mxl862xx_priv *priv,
+				       u32 data_written)
+{
+	int ret;
+
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		return ret;
+
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);
+	if (ret < 0)
+		return ret;
+
+	return mxl862xx_sb_pdi_poll_stat(priv, 0,
+					 MXL862XX_FW_WRITE_TIMEOUT_MS);
+}
+
+/* Flush the last slice, which ends the receive loop: the loader verifies the
+ * image and replaces the count in STAT with its verdict, so wait for the count
+ * to go rather than for a fixed value.
+ */
+static int mxl862xx_sb_pdi_flush_last(struct mxl862xx_priv *priv,
+				      u32 data_written)
+{
+	int ret, val;
+
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		return ret;
+
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT, data_written);
+	if (ret < 0)
+		return ret;
+
+	ret = read_poll_timeout(mxl862xx_smdio_read, val,
+				val < 0 || (u16)val != (u16)data_written,
+				10000, (MXL862XX_FW_WRITE_TIMEOUT_MS +
+					MXL862XX_SB_PDI_VERIFY_MS) * 1000,
+				false, priv, MXL862XX_SB_PDI_STAT);
+	if (val < 0)
+		return val;
+
+	if (!ret && (u16)val == MXL862XX_SB_PDI_VERIFY_OK)
+		return 0;
+
+	/* A final count of 1 is indistinguishable from the reject verdict, so
+	 * a timeout still holding it lands here too.
+	 */
+	if ((u16)val == MXL862XX_SB_PDI_VERIFY_BAD) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: loader rejected the image\n");
+		return -EBADMSG;
+	}
+
+	return ret ? ret : -EPROTO;
+}
+
+static void mxl862xx_flash_notify(struct devlink *dl, const char *status,
+				  u32 done, u32 total)
+{
+	devlink_flash_update_status_notify(dl, status, NULL, done, total);
+}
+
+/* Byte-count of each chunk fed to the loader during drain. It MUST be 1: the
+ * loader only lets us observe "counter == 0", never "counter < step", so any
+ * step > 1 can subtract past zero, underflow the 32-bit counter and wedge the
+ * loader for ~2^32 more bytes (a state only a power cycle clears). Stepping by
+ * 1 walks the counter through every value and is guaranteed to land on zero
+ * whatever its (possibly odd) start. A 1-byte chunk is a path the loader
+ * already handles: the normal transfer ends with a single trailing byte for
+ * odd-sized images (see Step 6).
+ */
+#define MXL862XX_DRAIN_CHUNK_BYTES	1
+
+/* Log the drain's progress every so many bytes; it can run for a long time */
+#define MXL862XX_DRAIN_LOG_BYTES	(128 * 1024)
+
+/* Wait for the loader to ask for the next chunk (STAT 0) or to come back to its
+ * command loop (STAT READY), and return the STAT value either way. On timeout
+ * that is whatever STAT still holds, which carries no further information: the
+ * loader keeps the count we wrote visible while it programs the chunk, and that
+ * is the same value it publishes as the "image rejected" verdict once the
+ * counter reaches zero.
+ *
+ * STAT 0 is unambiguous here even though it is also the "image verified"
+ * verdict: by the r_remain == 0 rule the loader leaves the receive loop the
+ * moment the counter reaches zero, so it is never both inside the loop asking
+ * for a chunk and publishing a verdict. Once it has left, the next STAT write
+ * is a command rather than a count, so feeding one more chunk after a verdict
+ * cannot underflow anything either.
+ */
+static int mxl862xx_sb_pdi_poll_drain(struct mxl862xx_priv *priv,
+				      unsigned long timeout_ms)
+{
+	int val;
+
+	read_poll_timeout(mxl862xx_smdio_read, val,
+			  val < 0 || (u16)val == MXL862XX_SB_PDI_READY ||
+			  (u16)val == 0,
+			  50, timeout_ms * 1000, false,
+			  priv, MXL862XX_SB_PDI_STAT);
+	if (val < 0)
+		return val;
+	return (u16)val;
+}
+
+/* The loader is not asking for a chunk: it may still be programming the last
+ * one, or the counter has reached zero and it is verifying the image and
+ * resetting into READY. Wait that out -- STAT cannot tell the two apart, and
+ * guessing would mean writing END into a live receive loop.
+ *
+ * Return: 0 once the loader has left the loop, -EAGAIN if it asks for another
+ * chunk after all, -EIO for a loader still holding the count when the verify
+ * window expires, or an SMDIO bus error.
+ */
+static int mxl862xx_rescue_drain_finish(struct mxl862xx_priv *priv, u32 chunk)
+{
+	struct device *dev = &priv->mdiodev->dev;
+	int stat;
+
+	stat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_VERIFY_MS);
+	if (stat < 0)
+		return stat;
+	if (stat == MXL862XX_SB_PDI_READY)
+		return 0;
+	if (stat == MXL862XX_SB_PDI_VERIFY_BAD) {
+		dev_err(dev,
+			"flash: loader stuck after %u chunks, power cycle it\n",
+			chunk);
+		return -EIO;
+	}
+	if (stat) {
+		/* A firmware is answering, not the loader: an image survived
+		 * in flash and booted.
+		 */
+		dev_info(dev, "flash: firmware booted while draining\n");
+		return 0;
+	}
+
+	return -EAGAIN;
+}
+
+/* Recover a switch whose SB PDI download was interrupted mid-transfer - the
+ * host died after MCUboot began erasing flash, whether it aborted mid erase or
+ * mid image-write, both end up in the same place: the payload receive loop.
+ * There the loader publishes STAT=0, waits for the host to write a byte-count
+ * to STAT, DMAs that many bytes and subtracts the count from a remaining-bytes
+ * counter, leaving the loop only when the counter reaches exactly zero. The
+ * image size died with the host, so we feed single-byte chunks (see
+ * MXL862XX_DRAIN_CHUNK_BYTES) to walk the counter to zero without underflow.
+ * The loader then verifies the (now corrupt) image and returns to READY by
+ * itself, or boots a valid image that happened to survive in flash; either way
+ * the caller's reprobe classifies the result. Every byte costs about a dozen
+ * MDIO frames, so a multi-MiB outstanding count takes tens of minutes.
+ * Returns 0 once the loader has left the receive loop, <0 on error. Does NOT
+ * recover a counter already underflowed by an earlier oversized-chunk attempt
+ * - that needs a power cycle.
+ */
+static int mxl862xx_rescue_drain(struct mxl862xx_priv *priv)
+{
+	struct device *dev = &priv->mdiodev->dev;
+	/* Bound: twice the loader's 16 MiB image cap, one byte per chunk. */
+	u32 max_chunks = 2u * (16u << 20) / MXL862XX_DRAIN_CHUNK_BYTES;
+	u32 chunk = 0;
+	int ret, stat;
+
+	while (chunk < max_chunks) {
+		/* Teardown can interrupt this long drain. */
+		if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags))
+			return -ECANCELED;
+
+		stat = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);
+		if (stat < 0)
+			return stat;
+		if (stat == MXL862XX_SB_PDI_READY)
+			return 0;
+
+		if (stat) {
+			ret = mxl862xx_rescue_drain_finish(priv, chunk);
+			if (ret != -EAGAIN)
+				return ret;
+		}
+
+		/* Feed one zero byte; reset cleared the write latch. */
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+					   MXL862XX_SB_PDI_CTRL_WR);
+		if (ret < 0)
+			return ret;
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);
+		if (ret < 0)
+			return ret;
+		ret = mxl862xx_sb_pdi_reset(priv);
+		if (ret < 0)
+			return ret;
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+					   MXL862XX_DRAIN_CHUNK_BYTES);
+		if (ret < 0)
+			return ret;
+		chunk++;
+		if (!(chunk % MXL862XX_DRAIN_LOG_BYTES))
+			dev_info(dev, "flash: drained %u KiB so far\n",
+				 chunk / 1024);
+		cond_resched();
+	}
+
+	dev_err(dev,
+		"flash: interrupted download did not drain after %u chunks\n",
+		chunk);
+
+	return -ETIMEDOUT;
+}
+
+/* Background self-heal: drain a wedged download off the devlink flash path, so
+ * the long recovery never holds the devlink lock. Scheduled from probe;
+ * reprobes on success so the probe-time detection re-classifies the switch.
+ */
+void mxl862xx_rescue_heal_work_fn(struct work_struct *work)
+{
+	struct mxl862xx_priv *priv =
+		container_of(work, struct mxl862xx_priv, rescue_heal_work);
+	struct device *dev = &priv->mdiodev->dev;
+	int ret;
+
+	ret = mxl862xx_rescue_drain(priv);
+	if (ret == -ECANCELED)
+		return;
+	if (ret) {
+		/* Nothing retries this, so say so: rescue_ready stays clear
+		 * and devlink dev flash reports why it refuses.
+		 */
+		dev_err(dev, "flash: download recovery failed: %pe\n",
+			ERR_PTR(ret));
+		WRITE_ONCE(priv->rescue_failed, true);
+		return;
+	}
+
+	/* The interrupted transfer is finalised; reprobe so the probe-time
+	 * detection brings the driver up -- flashable in rescue mode if the
+	 * loader is at READY, or normally if a valid image booted. The core
+	 * skips the re-probe on its own if the device is unbound first; the
+	 * flag test only avoids scheduling one certain to be skipped. A
+	 * failed hand-off leaves nothing to reclassify the switch, so mark
+	 * recovery failed rather than promise a retry that cannot succeed.
+	 */
+	if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags))
+		return;
+
+	if (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS))
+		WRITE_ONCE(priv->rescue_failed, true);
+}
+
+/* Detect MCUboot rescue mode over clause-22 SMDIO alone, so the caller can rule
+ * the loader out before any C45 API request (which spews CRC errors when no WSP
+ * firmware answers). A scratch write to ADDR/DATA must latch or the chip is
+ * absent (-ENODEV); the mailbox is reset first, or a transfer interrupted with
+ * CTRL=WR would take that write as a payload word instead of latching it. STAT
+ * then classifies the state, poked destructively only when 0, the one value a
+ * running firmware never holds:
+ *
+ *  - 0xc33c: flashless loop; recognised but not supported here.
+ *  - 0xc55c: console loop, if the register-read challenge is serviced.
+ *  - other non-zero: running firmware, left unpoked.
+ *  - 0: wedged receive loop; the 1-byte slice-advance then says whether it
+ *    still needs draining or has just finished.
+ *
+ * The scratch write reaches a running firmware too, but lands in mailbox
+ * registers it does not read, so it is inert there.
+ *
+ * Return: MXL862XX_IN_RESCUE, MXL862XX_NOT_RESCUE, -ENODEV when the scratch
+ * write does not latch, which is a switch that does not answer at all or one
+ * whose SB PDI window is not at the offsets above, -EOPNOTSUPP for the
+ * flashless loop, -ENXIO for a READY loader whose mailbox fails the challenge,
+ * or an SMDIO bus error.
+ */
+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv *priv)
+{
+	int stat, dat, ret, rb, a, d;
+
+	/* rescue_ready gates flashing; a wedged loader needs the drain first. */
+	WRITE_ONCE(priv->rescue_ready, false);
+
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		return ret;
+
+	/* Presence: a live chip latches the scratch write, an absent one floats. */
+	a = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,
+				 MXL862XX_SB_PDI_PROBE_A);
+	if (a < 0)
+		return a;
+	d = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,
+				 MXL862XX_SB_PDI_PROBE_D);
+	if (d < 0)
+		return d;
+	a = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_ADDR);
+	if (a < 0)
+		return a;
+	d = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);
+	if (d < 0)
+		return d;
+	if ((u16)a != MXL862XX_SB_PDI_PROBE_A ||
+	    (u16)d != MXL862XX_SB_PDI_PROBE_D)
+		return -ENODEV;
+
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		return ret;
+
+	stat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_STAT);
+	if (stat < 0)
+		return stat;
+
+	/* Flashless-download loop (MxL86281S tier): this driver does not
+	 * support it -- the console flash path expects READY. Treat it as an
+	 * unusable configuration, like any other unsupported state.
+	 */
+	if ((u16)stat == MXL862XX_SB_PDI_DL_READY)
+		return -EOPNOTSUPP;
+
+	/* Console loop at READY: confirm the live mailbox with the register-read
+	 * challenge (consumes the marker from DATA and re-arms READY).
+	 */
+	if ((u16)stat == MXL862XX_SB_PDI_READY) {
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA,
+					   MXL862XX_SB_PDI_RDREG_MARK);
+		if (ret < 0)
+			return ret;
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+					   MXL862XX_SB_PDI_RDREG);
+		if (ret < 0)
+			return ret;
+		rb = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,
+					       MXL862XX_SB_PDI_STEP_MS);
+		dat = mxl862xx_smdio_read(priv, MXL862XX_SB_PDI_DATA);
+		ret = mxl862xx_sb_pdi_reset(priv);
+		/* Never re-arming READY fails the challenge like any other
+		 * unserviced command; report it as such rather than as a bus
+		 * timeout the bus never saw.
+		 */
+		if (rb == -ETIMEDOUT)
+			rb = -ENXIO;
+		if (rb < 0)
+			return rb;
+		if (dat < 0)
+			return dat;
+		if (ret < 0)
+			return ret;
+		if ((u16)dat != MXL862XX_SB_PDI_RDREG_MARK) {
+			WRITE_ONCE(priv->rescue_ready, true);
+			return MXL862XX_IN_RESCUE;
+		}
+		/* READY but the marker is untouched, so nothing is servicing the
+		 * mailbox. A firmware publishing 0xc55c as its status word looks
+		 * exactly like this, and flashing one would be far worse than
+		 * refusing to bind, so treat it as unusable.
+		 */
+		return -ENXIO;
+	}
+
+	/* Any other non-zero value is a running firmware, not a loader. */
+	if (stat)
+		return MXL862XX_NOT_RESCUE;
+
+	/* STAT == 0: a wedged receive loop takes a 1-byte slice-advance (feed
+	 * one DATA word first, like a drain chunk) and asks for the next chunk
+	 * by publishing 0 again. Had that byte been the last one outstanding,
+	 * the loader leaves the loop instead and returns to READY, having
+	 * consumed the advance -- proof enough of a live mailbox to skip the
+	 * challenge. Anything else means it is still working on it. All three
+	 * are rescue, so this never fails probe; only the drain does.
+	 */
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+				   MXL862XX_SB_PDI_CTRL_WR);
+	if (ret < 0)
+		return ret;
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, 0x0000);
+	if (ret < 0)
+		return ret;
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		return ret;
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+				   MXL862XX_DRAIN_CHUNK_BYTES);
+	if (ret < 0)
+		return ret;
+
+	rb = mxl862xx_sb_pdi_poll_drain(priv, MXL862XX_SB_PDI_STEP_MS);
+	if (rb < 0)
+		return rb;
+	if (rb == MXL862XX_SB_PDI_READY)
+		WRITE_ONCE(priv->rescue_ready, true);
+
+	return MXL862XX_IN_RESCUE;
+}
+
+/* MCUboot firmware image header */
+struct mxl862xx_fw_hdr {
+	__le32 image_type;
+	__le32 image_size_1;
+	__le32 image_checksum_1;
+	__le32 image_size_2;
+	__le32 image_checksum_2;
+} __packed;
+
+static int mxl862xx_flash_validate(struct mxl862xx_priv *priv,
+				   const struct firmware *fw,
+				   u32 *payload_size)
+{
+	const struct mxl862xx_fw_hdr *hdr;
+	u32 size1, size2, total;
+	const u8 *payload;
+	u32 crc;
+
+	if (fw->size < MXL862XX_FW_HDR_SIZE)
+		return -EINVAL;
+
+	hdr = (const struct mxl862xx_fw_hdr *)fw->data;
+	payload = fw->data + MXL862XX_FW_HDR_SIZE;
+	size1 = le32_to_cpu(hdr->image_size_1);
+	size2 = le32_to_cpu(hdr->image_size_2);
+
+	if (check_add_overflow(size1, size2, &total) ||
+	    total > fw->size - MXL862XX_FW_HDR_SIZE) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: firmware file too small for declared size\n");
+		return -EINVAL;
+	}
+
+	if (!total) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: firmware file with empty payload\n");
+		return -EINVAL;
+	}
+
+	if (size1) {
+		crc = ~crc32_le(~0U, payload, size1);
+		if (crc != le32_to_cpu(hdr->image_checksum_1)) {
+			dev_err(&priv->mdiodev->dev,
+				"flash: image 1 CRC mismatch (got %08x, expected %08x)\n",
+				crc, le32_to_cpu(hdr->image_checksum_1));
+			return -EINVAL;
+		}
+	}
+
+	if (size2) {
+		crc = ~crc32_le(~0U, payload + size1, size2);
+		if (crc != le32_to_cpu(hdr->image_checksum_2)) {
+			dev_err(&priv->mdiodev->dev,
+				"flash: image 2 CRC mismatch (got %08x, expected %08x)\n",
+				crc, le32_to_cpu(hdr->image_checksum_2));
+			return -EINVAL;
+		}
+	}
+
+	*payload_size = total;
+
+	return 0;
+}
+
+static int mxl862xx_flash_firmware(struct mxl862xx_priv *priv,
+				   const struct firmware *fw,
+				   u32 payload_size, struct devlink *dl)
+{
+	const u8 *payload = fw->data + MXL862XX_FW_HDR_SIZE;
+	u32 word_idx = 0, data_written = 0, idx = 0;
+	unsigned long next_notify = jiffies - 1;
+	u16 word, fdata;
+	int ret, i;
+
+	/* Step 1: reboot the firmware into MCUboot rescue mode */
+	if (!priv->rescue_mode) {
+		ret = mxl862xx_api_wrap(priv, SYS_MISC_FW_UPDATE, NULL, 0,
+					false, false);
+		if (ret) {
+			dev_err(&priv->mdiodev->dev,
+				"flash: FW_UPDATE command failed: %pe\n",
+				ERR_PTR(ret));
+			return ret;
+		}
+	}
+
+	/* Step 2: wait for bootloader ready */
+	mxl862xx_flash_notify(dl, "Waiting for bootloader", 0, 0);
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		goto write_err;
+
+	/* Failures from here on end up at no_end, which returns the error
+	 * without signalling END -- see there.
+	 */
+	ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_READY,
+					MXL862XX_FW_READY_TIMEOUT_MS);
+	if (ret) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: bootloader not ready: %pe\n", ERR_PTR(ret));
+		goto no_end;
+	}
+
+	/* Step 3: start handshake */
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+				   MXL862XX_SB_PDI_START);
+	if (ret < 0)
+		goto write_err;
+
+	ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_SB_PDI_START + 1,
+					MXL862XX_FW_ACK_TIMEOUT_MS);
+	if (ret) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: start handshake failed: %pe\n", ERR_PTR(ret));
+		goto no_end;
+	}
+
+	/* Step 4: transfer image header */
+	mxl862xx_flash_notify(dl, "Erasing flash", 0, 0);
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+				   MXL862XX_SB_PDI_CTRL_WR);
+	if (ret < 0)
+		goto write_err;
+
+	for (i = 0; i < MXL862XX_FW_HDR_SIZE / 2; i++) {
+		word = fw->data[i * 2] |
+		       ((u16)fw->data[i * 2 + 1] << 8);
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, word);
+		if (ret < 0)
+			goto write_err;
+	}
+
+	ret = mxl862xx_sb_pdi_reset(priv);
+	if (ret < 0)
+		goto write_err;
+
+	/* the byte count in STAT triggers the erase */
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+				   MXL862XX_FW_HDR_SIZE);
+	if (ret < 0)
+		goto write_err;
+
+	/* ACK is byte count + 1 */
+	ret = mxl862xx_sb_pdi_poll_stat(priv, MXL862XX_FW_HDR_SIZE + 1,
+					MXL862XX_FW_ACK_TIMEOUT_MS);
+	if (ret) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: header ACK failed: %pe\n", ERR_PTR(ret));
+		goto no_end;
+	}
+
+	/* Step 5: wait for erase to complete */
+	ret = mxl862xx_sb_pdi_poll_stat(priv, 0,
+					MXL862XX_FW_ERASE_TIMEOUT_MS);
+	if (ret) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: erase timeout: %pe\n", ERR_PTR(ret));
+		goto no_end;
+	}
+
+	/* Step 6: transfer payload */
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+				   MXL862XX_SB_PDI_CTRL_WR);
+	if (ret < 0)
+		goto write_err;
+
+	while (idx < payload_size) {
+		cond_resched();
+		if (idx + 1 < payload_size) {
+			fdata = payload[idx] |
+				((u16)payload[idx + 1] << 8);
+			idx += 2;
+			data_written += 2;
+		} else {
+			fdata = payload[idx];
+			idx++;
+			data_written++;
+		}
+
+		ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_DATA, fdata);
+		if (ret < 0)
+			goto write_err;
+		word_idx++;
+
+		if (idx >= payload_size) {
+			ret = mxl862xx_sb_pdi_flush_last(priv, data_written);
+			break;
+		}
+
+		/* Half-bank boundary: switch to SB1 address */
+		if (word_idx == MXL862XX_FW_BANK_HALF) {
+			ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+						   MXL862XX_SB_PDI_CTRL_RST);
+			if (ret < 0)
+				goto write_err;
+
+			ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_ADDR,
+						   MXL862XX_FW_SB1_ADDR);
+			if (ret < 0)
+				goto write_err;
+
+			ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+						   MXL862XX_SB_PDI_CTRL_WR);
+			if (ret < 0)
+				goto write_err;
+		} else if (word_idx >= MXL862XX_FW_BANK_SLICE) {
+			ret = mxl862xx_sb_pdi_flush_slice(priv, data_written);
+			if (ret) {
+				dev_err(&priv->mdiodev->dev,
+					"flash: write timeout at %u/%u: %pe\n",
+					idx, payload_size, ERR_PTR(ret));
+				goto no_end;
+			}
+			word_idx = 0;
+			data_written = 0;
+			ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_CTRL,
+						   MXL862XX_SB_PDI_CTRL_WR);
+			if (ret < 0)
+				goto write_err;
+
+			if (time_after(jiffies, next_notify)) {
+				mxl862xx_flash_notify(dl, "Flashing", idx,
+						      payload_size);
+				next_notify = jiffies + msecs_to_jiffies(500);
+			}
+		}
+	}
+
+	if (ret) {
+		dev_err(&priv->mdiodev->dev,
+			"flash: final slice failed: %pe\n", ERR_PTR(ret));
+		goto no_end;
+	}
+
+	mxl862xx_flash_notify(dl, "Flashing", payload_size, payload_size);
+
+	/* Success: the loader has left the receive loop at r_remain == 0 and
+	 * verified the image, so END(0x3cc3) is a finalise/boot request rather
+	 * than a byte count. Signal it here -- and only here -- to boot the new
+	 * image without waiting out the loader's 2 s END timeout.
+	 */
+	ret = mxl862xx_smdio_write(priv, MXL862XX_SB_PDI_STAT,
+				   MXL862XX_SB_PDI_END);
+	msleep(MXL862XX_FW_REBOOT_DELAY_MS);
+	return ret;
+
+write_err:
+	dev_err(&priv->mdiodev->dev, "flash: SMDIO write failed: %pe\n",
+		ERR_PTR(ret));
+no_end:
+	/* A failure leaves the loader mid transfer; do not signal END (a STAT
+	 * write is a byte count then, and END would be misread as one, risking
+	 * a receive-counter underflow). Return the error; the caller reprobes.
+	 */
+	return ret;
+}
+
+int mxl862xx_devlink_info_get(struct dsa_switch *ds,
+			      struct devlink_info_req *req,
+			      struct netlink_ext_ack *extack)
+{
+	struct mxl862xx_priv *priv = ds->priv;
+	char buf[16];
+	int ret;
+
+	/* No chip-id/revision in MCUboot (needs the firmware MMD mailbox). The
+	 * fw version doubles as the "ready to flash" signal: report it only
+	 * once the loader is at a clean READY, nothing while still draining.
+	 */
+	if (priv->rescue_mode) {
+		if (!READ_ONCE(priv->rescue_ready))
+			return 0;
+
+		snprintf(buf, sizeof(buf), "%u.%u.%u",
+			 priv->fw_version.major, priv->fw_version.minor,
+			 priv->fw_version.revision);
+		ret = devlink_info_version_running_put(req,
+				DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+		if (ret)
+			return ret;
+		return devlink_info_version_stored_put(req,
+				DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+	}
+
+	/* A 0 part number means the CHIP ID read failed or the part is
+	 * unfused; omit it rather than publish a bogus "0000" that fwupd
+	 * would match firmware against -- it then falls back to the driver
+	 * name.
+	 */
+	if (priv->asic_id) {
+		snprintf(buf, sizeof(buf), "%04X", priv->asic_id);
+		ret = devlink_info_version_fixed_put(req,
+						     DEVLINK_INFO_VERSION_GENERIC_ASIC_ID,
+						     buf);
+		if (ret)
+			return ret;
+
+		snprintf(buf, sizeof(buf), "%u", priv->asic_rev);
+		ret = devlink_info_version_fixed_put(req,
+						     DEVLINK_INFO_VERSION_GENERIC_ASIC_REV,
+						     buf);
+		if (ret)
+			return ret;
+	}
+
+	/* An all-zero version is the cache a failed flash left behind, not a
+	 * released firmware; omit it like the part number above.
+	 */
+	if (!priv->fw_version.major && !priv->fw_version.minor &&
+	    !priv->fw_version.revision)
+		return 0;
+
+	snprintf(buf, sizeof(buf), "%u.%u.%u",
+		 priv->fw_version.major, priv->fw_version.minor,
+		 priv->fw_version.revision);
+
+	ret = devlink_info_version_running_put(req,
+			DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+	if (ret)
+		return ret;
+
+	/* boots this image from its own flash: stored == running */
+	return devlink_info_version_stored_put(req,
+			DEVLINK_INFO_VERSION_GENERIC_FW, buf);
+}
+
+int mxl862xx_devlink_flash_update(struct dsa_switch *ds,
+				  struct devlink_flash_update_params *params,
+				  struct netlink_ext_ack *extack)
+{
+	struct mxl862xx_priv *priv = ds->priv;
+	struct dsa_port *dp;
+	u32 payload_size;
+	int ret, err, i;
+
+	if (params->component) {
+		NL_SET_ERR_MSG_MOD(extack, "component is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	/* A previous flash is still waiting for its reprobe: the firmware API
+	 * is short-circuited, so the raw SB PDI writes below would run against
+	 * a switch this driver no longer tracks.
+	 */
+	if (priv->skip_teardown) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "device is reinitializing, retry later");
+		return -EBUSY;
+	}
+
+	ret = mxl862xx_flash_validate(priv, params->fw, &payload_size);
+	if (ret) {
+		NL_SET_ERR_MSG_MOD(extack, "firmware image validation failed");
+		return ret;
+	}
+
+	/* Refuse to flash while the background self-heal is still draining, and
+	 * for good once it has given up on the loader.
+	 */
+	if (READ_ONCE(priv->rescue_failed)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "download recovery failed, power cycle the switch");
+		return -EIO;
+	}
+
+	if (priv->rescue_mode && !READ_ONCE(priv->rescue_ready)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "switch is recovering an interrupted download, retry shortly");
+		return -EBUSY;
+	}
+
+	if (priv->rescue_mode)
+		dev_info(ds->dev,
+			 "flash: flashing switch via MCUboot rescue mode\n");
+	else
+		dev_info(ds->dev, "flash: running firmware %u.%u.%u\n",
+			 priv->fw_version.major, priv->fw_version.minor,
+			 priv->fw_version.revision);
+
+	/* Close ports while the firmware is still alive so the DSA core's
+	 * MDB/FDB tracking is drained, and detach user ports so userspace
+	 * cannot reopen them during the flash. The conduit is only closed,
+	 * not detached: it belongs to the MAC driver. This driver binds a
+	 * single switch with a direct host link and no cascade ports, so the
+	 * conduit serves only this switch, and flashing it reboots the switch,
+	 * which takes the tree down regardless.
+	 */
+	rtnl_lock();
+	dsa_switch_for_each_user_port(dp, ds) {
+		if (dp->user) {
+			dev_close(dp->user);
+			netif_device_detach(dp->user);
+		}
+	}
+	dsa_switch_for_each_cpu_port(dp, ds)
+		dev_close(dp->conduit);
+	/* The bridge defers the STP state changes triggered by closing
+	 * the ports; let them reach the firmware while it is still alive.
+	 */
+	switchdev_deferred_process();
+	rtnl_unlock();
+
+	mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	priv->block_host = true;
+	mutex_unlock(&priv->mdiodev->bus->mdio_lock);
+
+	set_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags);
+	cancel_delayed_work_sync(&priv->stats_work);
+	cancel_work_sync(&priv->crc_err_work);
+	for (i = 0; i < ds->num_ports; i++)
+		cancel_work_sync(&priv->ports[i].host_flood_work);
+
+	ret = mxl862xx_flash_firmware(priv, params->fw, payload_size,
+				      ds->devlink);
+	if (ret)
+		NL_SET_ERR_MSG_MOD(extack, "firmware transfer failed");
+
+	if (!ret) {
+		mutex_lock_nested(&priv->mdiodev->bus->mdio_lock,
+				  MDIO_MUTEX_NESTED);
+		/* Keep block_host set so host writes stay blocked, but let the
+		 * readiness poll below read the freshly booted firmware.
+		 */
+		priv->flash_reading = true;
+		priv->rescue_mode = false;
+		mutex_unlock(&priv->mdiodev->bus->mdio_lock);
+
+		/* Refresh the cached versions so the flash update only
+		 * completes once the new firmware is confirmed running and
+		 * devlink dev info reports it. Must happen before setting
+		 * skip_teardown, which discards all firmware API reads.
+		 */
+		ret = mxl862xx_wait_ready(ds);
+		if (ret)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "new firmware did not become ready");
+	}
+
+	if (ret) {
+		/* The switch is in MCUboot with erased or partly written flash;
+		 * drop the cached identity so devlink dev info stops reporting
+		 * the pre-flash version until the reprobe re-reads the truth.
+		 */
+		memset(&priv->fw_version, 0, sizeof(priv->fw_version));
+		priv->asic_id = 0;
+		priv->asic_rev = 0;
+	}
+
+	mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED);
+	priv->flash_reading = false;
+	priv->block_host = false;
+	priv->skip_teardown = true;
+	mutex_unlock(&priv->mdiodev->bus->mdio_lock);
+
+	/* Reinitialise through a deferred re-probe: remove() runs with
+	 * skip_teardown set, then a fresh probe() starts against whatever
+	 * the switch now runs. The core skips the re-probe if the device
+	 * is unbound or shut down before it fires.
+	 */
+	err = device_schedule_reprobe(ds->dev, MXL862XX_FW_REPROBE_DELAY_MS);
+
+	return ret ? ret : err;
+}
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-fw.h b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h
new file mode 100644
index 0000000000000..7cd87c7ad8716
--- /dev/null
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-fw.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __MXL862XX_FW_H
+#define __MXL862XX_FW_H
+
+#include <net/dsa.h>
+
+struct mxl862xx_priv;
+struct work_struct;
+
+int mxl862xx_rescue_mode_detect(struct mxl862xx_priv *priv);
+void mxl862xx_rescue_heal_work_fn(struct work_struct *work);
+int mxl862xx_devlink_info_get(struct dsa_switch *ds,
+			      struct devlink_info_req *req,
+			      struct netlink_ext_ack *extack);
+int mxl862xx_devlink_flash_update(struct dsa_switch *ds,
+				  struct devlink_flash_update_params *params,
+				  struct netlink_ext_ack *extack);
+
+#endif /* __MXL862XX_FW_H */
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.c b/drivers/net/dsa/mxl862xx/mxl862xx-host.c
index 4acd216f7cc00..23e5dfe81e364 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.c
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.c
@@ -15,6 +15,8 @@
 #include <linux/unaligned.h>
 #include <net/dsa.h>
 #include "mxl862xx.h"
+#include "mxl862xx-cmd.h"
+#include "mxl862xx-fw.h"
 #include "mxl862xx-host.h"
 
 #define CTRL_BUSY_MASK			BIT(15)
@@ -340,6 +342,26 @@ int mxl862xx_api_wrap(struct mxl862xx_priv *priv, u16 cmd, void *_data,
 
 	mutex_lock_nested(&priv->mdiodev->bus->mdio_lock, MDIO_MUTEX_NESTED);
 
+	if (priv->skip_teardown) {
+		ret = read ? -ENODEV : 0;
+		goto out;
+	}
+
+	if (priv->rescue_mode) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	/* During the post-flash readiness poll block_host stays set, but the
+	 * flash path's own firmware version reads must reach the new image;
+	 * host writes stay blocked so stale resource IDs cannot corrupt it.
+	 */
+	if (priv->block_host && cmd != SYS_MISC_FW_UPDATE &&
+	    !(priv->flash_reading && read)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	max = (size + 1) / 2;
 
 	ret = mxl862xx_busy_wait(priv);
@@ -495,12 +517,54 @@ int mxl862xx_reset(struct mxl862xx_priv *priv)
 	return ret;
 }
 
+#define MXL862XX_SMDIO_ADDR_REG		0x1f
+#define MXL862XX_SMDIO_PAGE_MASK	0xfff0
+#define MXL862XX_SMDIO_OFF_MASK		0x000f
+
+/* Paged clause-22 window: the page goes into MII register 0x1f, the low nibble
+ * of addr selects one of the 16 registers within it. Both helpers take the MDIO
+ * bus lock per transaction, so callers must not already hold it -- unlike
+ * mxl862xx_api_wrap(), which holds it across a whole firmware command.
+ */
+int mxl862xx_smdio_read(struct mxl862xx_priv *priv, u32 addr)
+{
+	struct mii_bus *bus = priv->mdiodev->bus;
+	int phy = priv->mdiodev->addr;
+	int ret;
+
+	mutex_lock(&bus->mdio_lock);
+	ret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,
+			      addr & MXL862XX_SMDIO_PAGE_MASK);
+	if (ret >= 0)
+		ret = __mdiobus_read(bus, phy, addr & MXL862XX_SMDIO_OFF_MASK);
+	mutex_unlock(&bus->mdio_lock);
+	return ret;
+}
+
+int mxl862xx_smdio_write(struct mxl862xx_priv *priv, u32 addr, u16 val)
+{
+	struct mii_bus *bus = priv->mdiodev->bus;
+	int phy = priv->mdiodev->addr;
+	int ret;
+
+	mutex_lock(&bus->mdio_lock);
+	ret = __mdiobus_write(bus, phy, MXL862XX_SMDIO_ADDR_REG,
+			      addr & MXL862XX_SMDIO_PAGE_MASK);
+	if (ret >= 0)
+		ret = __mdiobus_write(bus, phy, addr & MXL862XX_SMDIO_OFF_MASK,
+				      val);
+	mutex_unlock(&bus->mdio_lock);
+	return ret;
+}
+
 void mxl862xx_host_init(struct mxl862xx_priv *priv)
 {
 	INIT_WORK(&priv->crc_err_work, mxl862xx_crc_err_work_fn);
+	INIT_WORK(&priv->rescue_heal_work, mxl862xx_rescue_heal_work_fn);
 }
 
 void mxl862xx_host_shutdown(struct mxl862xx_priv *priv)
 {
 	cancel_work_sync(&priv->crc_err_work);
+	cancel_work_sync(&priv->rescue_heal_work);
 }
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-host.h b/drivers/net/dsa/mxl862xx/mxl862xx-host.h
index 66d6ae198aff4..4e054c6e4c0e4 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx-host.h
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-host.h
@@ -18,5 +18,7 @@ int mxl862xx_api_wrap(struct mxl862xx_priv *priv, u16 cmd, void *data, u16 size,
 	mxl862xx_api_wrap(dev, cmd, &(data), sizeof((data)), true, true)
 
 int mxl862xx_reset(struct mxl862xx_priv *priv);
+int mxl862xx_smdio_read(struct mxl862xx_priv *priv, u32 addr);
+int mxl862xx_smdio_write(struct mxl862xx_priv *priv, u32 addr, u16 val);
 
 #endif /* __MXL862XX_HOST_H */
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c
index b689652aa9b92..a5b6940b552e9 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c
+++ b/drivers/net/dsa/mxl862xx/mxl862xx-phylink.c
@@ -406,6 +406,8 @@ mxl862xx_phylink_mac_select_pcs(struct phylink_config *config,
 
 	switch (port) {
 	case 9 ... 16:
+		if (priv->rescue_mode)
+			return NULL;
 		if (!MXL862XX_FW_VER_MIN(priv, 1, 0, 84)) {
 			dev_warn_once(dp->ds->dev,
 				      "SerDes PCS unsupported on old firmware.\n");
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.c b/drivers/net/dsa/mxl862xx/mxl862xx.c
index 45d237b3a40f1..74abf88c09cc6 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx.c
+++ b/drivers/net/dsa/mxl862xx/mxl862xx.c
@@ -21,6 +21,7 @@
 #include "mxl862xx.h"
 #include "mxl862xx-api.h"
 #include "mxl862xx-cmd.h"
+#include "mxl862xx-fw.h"
 #include "mxl862xx-host.h"
 #include "mxl862xx-phylink.h"
 
@@ -71,6 +72,13 @@ static const struct ethtool_rmon_hist_range mxl862xx_rmon_ranges[] = {
 #define MXL862XX_READY_TIMEOUT_MS	10000
 #define MXL862XX_READY_POLL_MS		100
 
+/* Chip ID registers, read via SYS_MISC_REG_RD */
+#define MXL862XX_CHIPID_L		0xc0d28884
+#define MXL862XX_CHIPID_M		0xc0d28888
+#define MXL862XX_CHIPID_L_PNUML		GENMASK(15, 12)
+#define MXL862XX_CHIPID_M_PNUMM		GENMASK(11, 0)
+#define MXL862XX_CHIPID_M_VERSION	GENMASK(14, 12)
+
 #define MXL862XX_TCM_INST_SEL		0xe00
 #define MXL862XX_TCM_CBS		0xe12
 #define MXL862XX_TCM_EBS		0xe13
@@ -222,7 +230,46 @@ static int mxl862xx_phy_write_c45_mii_bus(struct mii_bus *bus, int addr,
 	return mxl862xx_phy_write_mmd(bus->priv, addr, devadd, regnum, val);
 }
 
-static int mxl862xx_wait_ready(struct dsa_switch *ds)
+/* Read the static chip part number and version from the CHIP ID
+ * registers. Only possible with a running firmware, so the values are
+ * cached at setup and left zero when the switch is in rescue mode.
+ */
+static int mxl862xx_read_chip_id(struct mxl862xx_priv *priv)
+{
+	struct mxl862xx_sys_reg_rw reg = {};
+	u16 chipid_l, chipid_m;
+	int ret;
+
+	reg.addr = cpu_to_le32(MXL862XX_CHIPID_L);
+	ret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);
+	if (ret)
+		return ret;
+	chipid_l = le32_to_cpu(reg.val);
+
+	reg.addr = cpu_to_le32(MXL862XX_CHIPID_M);
+	ret = MXL862XX_API_READ(priv, SYS_MISC_REG_RD, reg);
+	if (ret)
+		return ret;
+	chipid_m = le32_to_cpu(reg.val);
+
+	priv->asic_id = FIELD_GET(MXL862XX_CHIPID_L_PNUML, chipid_l) |
+			FIELD_GET(MXL862XX_CHIPID_M_PNUMM, chipid_m) << 4;
+	priv->asic_rev = FIELD_GET(MXL862XX_CHIPID_M_VERSION, chipid_m);
+
+	return 0;
+}
+
+/**
+ * mxl862xx_wait_ready - wait for the switch firmware to become operational
+ * @ds: DSA switch instance
+ *
+ * Poll the firmware until it reports its version and accepts
+ * configuration commands, then cache the firmware version and chip ID.
+ * Takes at least two seconds.
+ *
+ * Return: 0 on success or a negative error code.
+ */
+int mxl862xx_wait_ready(struct dsa_switch *ds)
 {
 	struct mxl862xx_sys_fw_image_version ver = {};
 	unsigned long start = jiffies, timeout;
@@ -254,6 +301,11 @@ static int mxl862xx_wait_ready(struct dsa_switch *ds)
 		priv->fw_version.major = ver.iv_major;
 		priv->fw_version.minor = ver.iv_minor;
 		priv->fw_version.revision = le16_to_cpu(ver.iv_revision);
+
+		ret = mxl862xx_read_chip_id(priv);
+		if (ret)
+			dev_warn(ds->dev, "failed to read chip ID: %pe\n",
+				 ERR_PTR(ret));
 		return 0;
 
 not_ready_yet:
@@ -622,21 +674,66 @@ static int mxl862xx_setup(struct dsa_switch *ds)
 	int n_user_ports = 0, max_vlans;
 	int ingress_finals, vid_rules;
 	struct dsa_port *dp;
-	int ret, i;
-
-	ret = mxl862xx_reset(priv);
-	if (ret)
-		return ret;
-
-	ret = mxl862xx_wait_ready(ds);
-	if (ret)
-		return ret;
+	int ret, i, rescue;
 
+	/* The SerDes state is software-only and must exist before anything can
+	 * reach phylink, including a rescue-mode flash clearing rescue_mode
+	 * ahead of the reprobe.
+	 */
 	mutex_init(&priv->serdes_lock);
 	for (i = 0; i < ARRAY_SIZE(priv->serdes_ports); i++)
 		mxl862xx_setup_pcs(priv, &priv->serdes_ports[i],
 				   i + MXL862XX_FIRST_SERDES_PORT);
 
+	/* Detect the loader over SB PDI first: it needs no firmware, unlike the
+	 * C45 API (mxl862xx_reset/wait_ready) which spews CRC errors when none
+	 * answers. Touch C45 only once rescue is ruled out.
+	 */
+	rescue = mxl862xx_rescue_mode_detect(priv);
+	if (rescue < 0) {
+		dev_err(ds->dev, "switch state detection failed: %pe\n",
+			ERR_PTR(rescue));
+		return rescue;
+	}
+
+	if (rescue == MXL862XX_NOT_RESCUE) {
+		ret = mxl862xx_reset(priv);
+		if (ret)
+			return ret;
+
+		ret = mxl862xx_wait_ready(ds);
+		if (ret) {
+			/* the reset may only now have triggered rescue mode */
+			rescue = mxl862xx_rescue_mode_detect(priv);
+			if (rescue < 0) {
+				dev_err(ds->dev,
+					"switch not responding after reset: %pe\n",
+					ERR_PTR(rescue));
+				return rescue;
+			}
+			if (rescue == MXL862XX_NOT_RESCUE)
+				return ret;
+		}
+	}
+
+	priv->rescue_mode = rescue;
+
+	if (priv->rescue_mode) {
+		if (priv->rescue_ready) {
+			dev_warn(ds->dev,
+				 "switch in MCUboot rescue mode, use devlink to flash new firmware\n");
+		} else {
+			/* Drain the wedged download in the background so it
+			 * never holds the devlink lock; info and flash become
+			 * available once ready.
+			 */
+			dev_warn(ds->dev,
+				 "switch in MCUboot with an interrupted download, recovering in background\n");
+			queue_work(system_long_wq, &priv->rescue_heal_work);
+		}
+		return 0;
+	}
+
 	/* Calculate Extended VLAN block sizes.
 	 * With VLAN Filter handling VID membership checks:
 	 *   Ingress: only final catchall rules (PVID insertion, 802.1Q
@@ -715,11 +812,21 @@ static int mxl862xx_port_state(struct dsa_switch *ds, int port, bool enable)
 static int mxl862xx_port_enable(struct dsa_switch *ds, int port,
 				struct phy_device *phydev)
 {
+	struct mxl862xx_priv *priv = ds->priv;
+
+	if (priv->rescue_mode)
+		return 0;
+
 	return mxl862xx_port_state(ds, port, true);
 }
 
 static void mxl862xx_port_disable(struct dsa_switch *ds, int port)
 {
+	struct mxl862xx_priv *priv = ds->priv;
+
+	if (priv->rescue_mode)
+		return;
+
 	if (mxl862xx_port_state(ds, port, false))
 		dev_err(ds->dev, "failed to disable port %d\n", port);
 }
@@ -1337,6 +1444,17 @@ static int mxl862xx_port_setup(struct dsa_switch *ds, int port)
 	bool is_cpu_port = dsa_port_is_cpu(dp);
 	int ret;
 
+	if (dsa_port_is_dsa(dp)) {
+		dev_err(ds->dev, "port %d: DSA links not supported\n", port);
+		return -EOPNOTSUPP;
+	}
+
+	/* DSA reinits failed user ports as unused; shared ports must
+	 * succeed for the tree to register.
+	 */
+	if (priv->rescue_mode)
+		return dsa_port_is_user(dp) ? -ENODEV : 0;
+
 	ret = mxl862xx_port_state(ds, port, false);
 	if (ret)
 		return ret;
@@ -1346,11 +1464,6 @@ static int mxl862xx_port_setup(struct dsa_switch *ds, int port)
 	if (dsa_port_is_unused(dp))
 		return 0;
 
-	if (dsa_port_is_dsa(dp)) {
-		dev_err(ds->dev, "port %d: DSA links not supported\n", port);
-		return -EOPNOTSUPP;
-	}
-
 	ret = mxl862xx_configure_sp_tag_proto(ds, port, is_cpu_port);
 	if (ret)
 		return ret;
@@ -1572,6 +1685,12 @@ static int mxl862xx_port_mdb_del(struct dsa_switch *ds, int port,
 	ether_addr_copy(qparam.mac, mdb->addr);
 
 	ret = MXL862XX_API_READ(priv, MXL862XX_MAC_TABLEENTRYQUERY, qparam);
+	/* Post-flash teardown or MCUboot: the firmware and its MAC table are
+	 * gone, so there is nothing left to delete. Outside those, -ENODEV is a
+	 * bus error and must be reported.
+	 */
+	if (ret == -ENODEV && (priv->skip_teardown || priv->rescue_mode))
+		return 0;
 	if (ret)
 		return ret;
 
@@ -1628,6 +1747,9 @@ static void mxl862xx_port_stp_state_set(struct dsa_switch *ds, int port,
 	struct mxl862xx_priv *priv = ds->priv;
 	int ret;
 
+	if (priv->rescue_mode)
+		return;
+
 	switch (state) {
 	case BR_STATE_DISABLED:
 		param.port_state = cpu_to_le32(MXL862XX_STP_PORT_STATE_DISABLE);
@@ -2015,6 +2137,12 @@ static void mxl862xx_stats_work_fn(struct work_struct *work)
 	struct dsa_switch *ds = priv->ds;
 	struct dsa_port *dp;
 
+	/* A get_stats64() re-arm can race the flash teardown's WORK_STOPPED
+	 * set and cancel; bail here so a stray poll never runs during a flash.
+	 */
+	if (test_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags))
+		return;
+
 	dsa_switch_for_each_available_port(dp, ds)
 		mxl862xx_stats_poll(ds, dp->index);
 
@@ -2086,6 +2214,8 @@ static const struct dsa_switch_ops mxl862xx_switch_ops = {
 	.get_pause_stats = mxl862xx_get_pause_stats,
 	.get_rmon_stats = mxl862xx_get_rmon_stats,
 	.get_stats64 = mxl862xx_get_stats64,
+	.devlink_info_get = mxl862xx_devlink_info_get,
+	.devlink_flash_update = mxl862xx_devlink_flash_update,
 };
 
 static int mxl862xx_probe(struct mdio_device *mdiodev)
@@ -2151,10 +2281,16 @@ static void mxl862xx_remove(struct mdio_device *mdiodev)
 	priv = ds->priv;
 
 	set_bit(MXL862XX_FLAG_WORK_STOPPED, &priv->flags);
-	cancel_delayed_work_sync(&priv->stats_work);
 
 	dsa_unregister_switch(ds);
 
+	/* Cancel the stats poll only after the user netdevs are gone: until
+	 * dsa_unregister_switch() returns a get_stats64() can still re-arm the
+	 * work after a plain cancel, and it would then run against the
+	 * devres-freed priv.
+	 */
+	cancel_delayed_work_sync(&priv->stats_work);
+
 	mxl862xx_host_shutdown(priv);
 
 	/* Cancel any pending host flood work. dsa_unregister_switch()
diff --git a/drivers/net/dsa/mxl862xx/mxl862xx.h b/drivers/net/dsa/mxl862xx/mxl862xx.h
index 432a5f3f2e08e..bdaf295c8a9f6 100644
--- a/drivers/net/dsa/mxl862xx/mxl862xx.h
+++ b/drivers/net/dsa/mxl862xx/mxl862xx.h
@@ -4,7 +4,9 @@
 #define __MXL862XX_H
 
 #include <asm/byteorder.h>
+#include <linux/bitops.h>
 #include <linux/mdio.h>
+#include <linux/mutex.h>
 #include <linux/workqueue.h>
 #include <net/dsa.h>
 
@@ -14,6 +16,10 @@ struct mxl862xx_priv;
 #define MXL862XX_FIRST_SERDES_PORT	9
 #define MXL862XX_SERDES_SLOTS		4
 
+/* mxl862xx_rescue_mode_detect() return codes (negative values are errors) */
+#define MXL862XX_NOT_RESCUE		0
+#define MXL862XX_IN_RESCUE		1
+
 #define MXL862XX_DEFAULT_BRIDGE		0
 #define MXL862XX_MAX_BRIDGES		48
 #define MXL862XX_MAX_BRIDGE_PORTS	128
@@ -303,6 +309,10 @@ struct mxl862xx_fw_version {
  *                      flooding)
  * @fw_version:         cached firmware version, populated at probe and
  *                      compared with MXL862XX_FW_VER_MIN()
+ * @asic_id:            chip part number read from the CHIP ID registers,
+ *                      reported as the devlink "asic.id" fixed version
+ * @asic_rev:           chip version read from the CHIP ID registers,
+ *                      reported as the devlink "asic.rev" fixed version
  * @serdes_ports:       SerDes interfaces incl. sub-interfaces in case of
  *                      10G_QXGMII or QSGMII
  * @serdes_refcount:    per-XPCS count of sub-ports enabled by phylink;
@@ -319,6 +329,22 @@ struct mxl862xx_fw_version {
  * @evlan_ingress_size: per-port ingress Extended VLAN block size
  * @evlan_egress_size:  per-port egress Extended VLAN block size
  * @vf_block_size:      per-port VLAN Filter block size
+ * @block_host:         reject firmware API commands (except FW_UPDATE)
+ *                      during a firmware flash
+ * @flash_reading:      let the flash path's own firmware reads through
+ *                      block_host while polling the freshly booted image
+ * @skip_teardown:      discard firmware API commands during the teardown
+ *                      triggered by the post-flash reprobe
+ * @rescue_mode:        switch is in MCUboot; firmware API commands fail fast,
+ *                      only clause-22 SMDIO works. Set from setup() before the
+ *                      switch is registered and cleared under the MDIO bus lock
+ *                      for the benefit of mxl862xx_api_wrap(); other readers
+ *                      only need it to be a stable single flag.
+ * @rescue_ready:       (rescue_mode) loader is at a clean READY and will accept
+ *                      a flash; false while rescue_heal_work is draining
+ * @rescue_failed:      (rescue_mode) the self-heal gave up; the loader needs a
+ *                      power cycle and no flash can be accepted
+ * @rescue_heal_work:   background self-heal draining a wedged download to READY
  * @stats_work:         periodic work item that polls RMON hardware counters
  *                      and accumulates them into 64-bit per-port stats
  */
@@ -326,9 +352,12 @@ struct mxl862xx_priv {
 	struct dsa_switch *ds;
 	struct mdio_device *mdiodev;
 	struct work_struct crc_err_work;
+	struct work_struct rescue_heal_work;
 	unsigned long flags;
 	u16 drop_meter;
 	struct mxl862xx_fw_version fw_version;
+	u16 asic_id;
+	u8 asic_rev;
 	struct mxl862xx_pcs serdes_ports[8];
 	int serdes_refcount[2];
 	struct mutex serdes_lock;
@@ -337,7 +366,15 @@ struct mxl862xx_priv {
 	u16 evlan_ingress_size;
 	u16 evlan_egress_size;
 	u16 vf_block_size;
+	bool block_host;
+	bool flash_reading;
+	bool skip_teardown;
+	bool rescue_mode;
+	bool rescue_ready;
+	bool rescue_failed;
 	struct delayed_work stats_work;
 };
 
+int mxl862xx_wait_ready(struct dsa_switch *ds);
+
 #endif /* __MXL862XX_H */
diff --git a/include/linux/device.h b/include/linux/device.h
index aee79fd6b32b4..7a99169505772 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1314,6 +1314,8 @@ int  __must_check device_attach(struct device *dev);
 int __must_check driver_attach(const struct device_driver *drv);
 void device_initial_probe(struct device *dev);
 int __must_check device_reprobe(struct device *dev);
+int __must_check device_schedule_reprobe(struct device *dev,
+					 unsigned int delay_ms);
 
 bool device_is_bound(struct device *dev);
 
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 6f7f5c17b5320..58597b14e592a 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -1172,6 +1172,9 @@ struct dsa_switch_ops {
 	int	(*devlink_info_get)(struct dsa_switch *ds,
 				    struct devlink_info_req *req,
 				    struct netlink_ext_ack *extack);
+	int	(*devlink_flash_update)(struct dsa_switch *ds,
+					struct devlink_flash_update_params *params,
+					struct netlink_ext_ack *extack);
 	int	(*devlink_sb_pool_get)(struct dsa_switch *ds,
 				       unsigned int sb_index, u16 pool_index,
 				       struct devlink_sb_pool_info *pool_info);
diff --git a/net/dsa/devlink.c b/net/dsa/devlink.c
index ed342f345692b..25311a87cbc56 100644
--- a/net/dsa/devlink.c
+++ b/net/dsa/devlink.c
@@ -20,6 +20,18 @@ static int dsa_devlink_info_get(struct devlink *dl,
 	return -EOPNOTSUPP;
 }
 
+static int dsa_devlink_flash_update(struct devlink *dl,
+				    struct devlink_flash_update_params *params,
+				    struct netlink_ext_ack *extack)
+{
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
+
+	if (!ds->ops->devlink_flash_update)
+		return -EOPNOTSUPP;
+
+	return ds->ops->devlink_flash_update(ds, params, extack);
+}
+
 static int dsa_devlink_sb_pool_get(struct devlink *dl,
 				   unsigned int sb_index, u16 pool_index,
 				   struct devlink_sb_pool_info *pool_info)
@@ -169,6 +181,7 @@ dsa_devlink_sb_occ_tc_port_bind_get(struct devlink_port *dlp,
 
 static const struct devlink_ops dsa_devlink_ops = {
 	.info_get			= dsa_devlink_info_get,
+	.flash_update			= dsa_devlink_flash_update,
 	.sb_pool_get			= dsa_devlink_sb_pool_get,
 	.sb_pool_set			= dsa_devlink_sb_pool_set,
 	.sb_port_pool_get		= dsa_devlink_sb_port_pool_get,

gemini-3.1-pro-preview

							input: 29248
							output: 20
							thoughts: 696

**Reaching the MxL862xx Firmware Flash Functionality**

Okay, so this patch introduces firmware flashing and devlink support for the MaxLinear MxL862xx switch driver, which is interesting. It also adds a core function, `device_schedule_reprobe` in `drivers/base/dd.c`, and a `devlink_flash_update` to `struct dsa_switch_ops` and implements it in `net/dsa/devlink.c`. My immediate thought is, "Can we actually reach this code?"

I see that `device_schedule_reprobe` is added and used by `mxl862xx-fw.c`, and `dsa_devlink_flash_update` to `dsa_devlink_ops`. The `mxl862xx` driver, as the name suggests, is a DSA driver. Now, the key question is, can this be triggered in a virtualized environment like syzkaller?

The MxL862xx is a *hardware* switch. That's a problem. It's also an MDIO device. MDIO devices are usually probed if we register a software MDIO bus or use a dummy MDIO device. While syzkaller isn't typically set up to emulate *specific* MDIO devices, it *can* inject netlink commands. Aha! We can send `devlink` commands to any registered devlink instance. Can we somehow get syzkaller to create a dummy MxL862xx device? Let's figure out if there is a way to instantiate `mxl862xx` via software.

MDIO devices usually rely on device tree or board code for instantiation. But then, `device_schedule_reprobe` is a core driver function, and it's added in `drivers/base/dd.c`. This opens up a fuzzing possibility! The `device_schedule_reprobe` function schedules a delayed work to reprobe a device. It takes a device pointer and a delay, and it’s called by `mxl862xx_devlink_flash_update` and `mxl862xx_rescue_heal_work_fn`.

And the `dsa_devlink_flash_update` addition to `net/dsa/devlink.c` is important. It is reachable for any DSA switch that implements `devlink_flash_update`, which, according to this patch, is currently *only* the `mxl862xx` driver. But here's an idea: Syzkaller can create DSA switches using `netdevsim` or `dsa_loop`, right? Let's check. Does `dsa_loop` or `netdevsim` support DSA? In fact, `dsa_loop` is a mock DSA driver. The `mxl862xx` itself is a hardware driver, but perhaps `dsa_loop` or `netdevsim` provides a base to test against.

The core question is, is `mxl862xx` reachable? I need to check the config. Is `CONFIG_NET_DSA_MXL862` the relevant one? Let's search for "mxl862xx" in the kernel. This patch has a chance!

{
  "Expression": "mxl862xx"
}

{
  "Output": "\nFull output is too long, showing 500 out of 2588 lines.\nUse more precise expression if possible.\n\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml-3----\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml:4:$id: http://devicetree.org/schemas/net/dsa/maxlinear,mxl862xx.yaml#\nDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml-5-$schema: http://devicetree.org/meta-schemas/core.yaml#\n--\nDocumentation/networking/devlink/index.rst=77=parameters, info versions, and other features it supports.\n--\nDocumentation/networking/devlink/index.rst-96-   mv88e6xxx\nDocumentation/networking/devlink/index.rst:97:   mxl862xx\nDocumentation/networking/devlink/index.rst-98-   netdevsim\n--\nDocumentation/networking/devlink/mxl862xx.rst-3-========================\nDocumentation/networking/devlink/mxl862xx.rst:4:mxl862xx devlink support\nDocumentation/networking/devlink/mxl862xx.rst-5-========================\n--\nDocumentation/networking/devlink/mxl862xx.rst=7=This document describes the devlink features implemented by the\nDocumentation/networking/devlink/mxl862xx.rst:8:``mxl862xx`` device driver.\nDocumentation/networking/devlink/mxl862xx.rst-9-\nDocumentation/networking/devlink/mxl862xx.rst=10=Info versions\n--\nDocumentation/networking/devlink/mxl862xx.rst-12-\nDocumentation/networking/devlink/mxl862xx.rst:13:The ``mxl862xx`` driver reports the following versions\nDocumentation/networking/devlink/mxl862xx.rst-14-\n--\nDocumentation/networking/devlink/mxl862xx.rst=48=Flash update\n--\nDocumentation/networking/devlink/mxl862xx.rst-50-\nDocumentation/networking/devlink/mxl862xx.rst:51:The ``mxl862xx`` driver implements support for ``devlink dev flash``.\nDocumentation/networking/devlink/mxl862xx.rst-52-The signed firmware image is transferred to the switch over the same\n--\nMAINTAINERS=16107=S:\tMaintained\nMAINTAINERS:16108:F:\tDocumentation/devicetree/bindings/net/dsa/maxlinear,mxl862xx.yaml\nMAINTAINERS:16109:F:\tDocumentation/networking/devlink/mxl862xx.rst\nMAINTAINERS:16110:F:\tdrivers/net/dsa/mxl862xx/\nMAINTAINERS:16111:F:\tnet/dsa/tag_mxl862xx.c\nMAINTAINERS-16112-\n--\ndrivers/net/dsa/Kconfig=75=source \"drivers/net/dsa/mv88e6xxx/Kconfig\"\ndrivers/net/dsa/Kconfig-76-\ndrivers/net/dsa/Kconfig:77:source \"drivers/net/dsa/mxl862xx/Kconfig\"\ndrivers/net/dsa/Kconfig-78-\n--\ndrivers/net/dsa/Makefile=22=obj-y\t\t\t\t+= mv88e6xxx/\ndrivers/net/dsa/Makefile:23:obj-y\t\t\t\t+= mxl862xx/\ndrivers/net/dsa/Makefile-24-obj-y\t\t\t\t+= netc/\n--\ndrivers/net/dsa/mxl862xx/Makefile-1-# SPDX-License-Identifier: GPL-2.0\ndrivers/net/dsa/mxl862xx/Makefile:2:obj-$(CONFIG_NET_DSA_MXL862) += mxl862xx_dsa.o\ndrivers/net/dsa/mxl862xx/Makefile:3:mxl862xx_dsa-y := mxl862xx.o mxl862xx-host.o mxl862xx-phylink.o mxl862xx-fw.o\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h=16=struct mdio_relay_data {\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-23-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:24: * struct mxl862xx_register_mod - Register access parameter to directly\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-25- *                                modify internal registers\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-31- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:32:struct mxl862xx_register_mod {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-33-\t__le16 addr;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-38-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:39: * enum mxl862xx_mac_table_filter - Source/Destination MAC address filtering\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-40- *\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-45- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:46:enum mxl862xx_mac_table_filter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-47-\tMXL862XX_MAC_FILTER_NONE = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-64-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:65: * struct mxl862xx_mac_table_add - MAC Table Entry to be added\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-66- * @fid: Filtering Identifier (FID) (not supported by all switches)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-74- * @mac: MAC Address to add to the table\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:75: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-76- * @igmp_controlled: Packet is marked as IGMP controlled if destination MAC\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-83- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:84:struct mxl862xx_mac_table_add {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-85-\t__le16 fid;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-100-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:101: * struct mxl862xx_mac_table_remove - MAC Table Entry to be removed\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-102- * @fid: Filtering Identifier (FID)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-103- * @mac: MAC Address to be removed from the table.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:104: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-105- * @tci: TCI for B-Step\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-109- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:110:struct mxl862xx_mac_table_remove {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-111-\t__le16 fid;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-117-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:118: * struct mxl862xx_mac_table_read - MAC Table Entry to be read\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-119- * @initial: Restart the get operation from the beginning of the table\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-128- * @mac: MAC Address. Filled out by the switch API implementation.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:129: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-130- * @igmp_controlled: Packet is marked as IGMP controlled if destination MAC\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-141- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:142:struct mxl862xx_mac_table_read {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-143-\tu8 initial;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-162-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:163: * struct mxl862xx_mac_table_query - MAC Table Entry key-based lookup\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-164- * @mac: MAC Address to search for (input)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-172- * @static_entry: Indicates if this is a Static Entry\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:173: * @filter_flag: See \u0026enum mxl862xx_mac_table_filter (input+output)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-174- * @igmp_controlled: IGMP controlled flag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-180- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:181:struct mxl862xx_mac_table_query {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-182-\tu8 mac[ETH_ALEN];\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-200-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:201: * enum mxl862xx_mac_clear_type - MAC table clear type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-202- * @MXL862XX_MAC_CLEAR_PHY_PORT: clear dynamic entries based on port_id\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-204- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:205:enum mxl862xx_mac_clear_type {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-206-\tMXL862XX_MAC_CLEAR_PHY_PORT = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-210-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:211: * struct mxl862xx_mac_table_clear - MAC table clear\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:212: * @type: see \u0026enum mxl862xx_mac_clear_type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-213- * @port_id: physical port id\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-214- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:215:struct mxl862xx_mac_table_clear {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-216-\tu8 type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-220-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:221: * enum mxl862xx_age_timer - Aging Timer Value.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-222- * @MXL862XX_AGETIMER_1_SEC: 1 second aging time\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-228- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:229:enum mxl862xx_age_timer {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-230-\tMXL862XX_AGETIMER_1_SEC = 1,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-238-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:239: * struct mxl862xx_bridge_alloc - Bridge Allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-240- * @bridge_id: If the bridge allocation is successful, a valid ID will be\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-247- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:248:struct mxl862xx_bridge_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-249-\t__le16 bridge_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-252-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:253: * enum mxl862xx_bridge_config_mask - Bridge configuration mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-254- * @MXL862XX_BRIDGE_CONFIG_MASK_MAC_LEARNING_LIMIT:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-267- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:268:enum mxl862xx_bridge_config_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-269-\tMXL862XX_BRIDGE_CONFIG_MASK_MAC_LEARNING_LIMIT = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-278-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:279: * enum mxl862xx_bridge_port_egress_meter - Meters for egress traffic type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-280- * @MXL862XX_BRIDGE_PORT_EGRESS_METER_BROADCAST:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-293- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:294:enum mxl862xx_bridge_port_egress_meter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-295-\tMXL862XX_BRIDGE_PORT_EGRESS_METER_BROADCAST = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-304-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:305: * struct mxl862xx_qos_meter_cfg - Rate meter configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-306- * @enable: Enable/disable meter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-320- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:321:struct mxl862xx_qos_meter_cfg {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-322-\tu8 enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-338-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:339: * enum mxl862xx_bridge_forward_mode - Bridge forwarding type of packet\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-340- * @MXL862XX_BRIDGE_FORWARD_FLOOD: Packet is flooded to port members of\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-343- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:344:enum mxl862xx_bridge_forward_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-345-\tMXL862XX_BRIDGE_FORWARD_FLOOD = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-349-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:350: * struct mxl862xx_bridge_config - Bridge Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-351- * @bridge_id: Bridge ID (FID)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:352: * @mask: See \u0026enum mxl862xx_bridge_config_mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-353- * @mac_learning_limit_enable: Enable MAC learning limitation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-363- * @forward_broadcast: Forwarding mode of broadcast traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:364: *                     \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-365- * @forward_unknown_multicast_ip: Forwarding mode of unknown multicast IP\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-366- *                                traffic.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:367: *                                See \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-368- * @forward_unknown_multicast_non_ip: Forwarding mode of unknown multicast\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-369- *                                    non-IP traffic.\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:370: *                                    See \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-371- * @forward_unknown_unicast: Forwarding mode of unknown unicast traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:372: *                           \u0026enum mxl862xx_bridge_forward_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-373- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:374:struct mxl862xx_bridge_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-375-\t__le16 bridge_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:376:\t__le32 mask; /* enum mxl862xx_bridge_config_mask */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-377-\tu8 mac_learning_limit_enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-382-\t__le16 traffic_sub_meter_id[MXL862XX_BRIDGE_PORT_EGRESS_METER_MAX];\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:383:\t__le32 forward_broadcast; /* enum mxl862xx_bridge_forward_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:384:\t__le32 forward_unknown_multicast_ip; /* enum mxl862xx_bridge_forward_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:385:\t__le32 forward_unknown_multicast_non_ip; /* enum mxl862xx_bridge_forward_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:386:\t__le32 forward_unknown_unicast; /* enum mxl862xx_bridge_forward_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-387-} __packed;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-389-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:390: * struct mxl862xx_bridge_port_alloc - Bridge Port Allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-391- * @bridge_port_id: If the bridge port allocation is successful, a valid ID\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-397- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:398:struct mxl862xx_bridge_port_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-399-\t__le16 bridge_port_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-402-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:403: * enum mxl862xx_bridge_port_config_mask - Bridge Port configuration mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-404- * @MXL862XX_BRIDGE_PORT_CONFIG_MASK_BRIDGE_ID:\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-462- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:463:enum mxl862xx_bridge_port_config_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-464-\tMXL862XX_BRIDGE_PORT_CONFIG_MASK_BRIDGE_ID = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-491-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:492: * enum mxl862xx_color_marking_mode - Color Marking Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-493- * @MXL862XX_MARKING_ALL_GREEN: mark packets (except critical) to green\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-501- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:502:enum mxl862xx_color_marking_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-503-\tMXL862XX_MARKING_ALL_GREEN = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-513-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:514: * enum mxl862xx_color_remarking_mode - Color Remarking Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-515- * @MXL862XX_REMARKING_NONE: values from last process stage\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-522- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:523:enum mxl862xx_color_remarking_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-524-\tMXL862XX_REMARKING_NONE = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-533-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:534: * enum mxl862xx_pmapper_mapping_mode - P-mapper Mapping Mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-535- * @MXL862XX_PMAPPER_MAPPING_PCP: Use PCP for VLAN tagged packets to derive\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-541- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:542:enum mxl862xx_pmapper_mapping_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-543-\tMXL862XX_PMAPPER_MAPPING_PCP = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-548-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:549: * struct mxl862xx_pmapper - P-mapper Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-550- * @pmapper_id: Index of P-mapper (0-31)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-560- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:561:struct mxl862xx_pmapper {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-562-\t__le16 pmapper_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-566-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:567: * struct mxl862xx_bridge_port_config - Bridge Port Configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-568- * @bridge_port_id: Bridge Port ID allocated by bridge port allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:569: * @mask: See \u0026enum mxl862xx_bridge_port_config_mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-570- * @bridge_id: Bridge ID (FID) to which this bridge port is associated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-583- * @ingress_marking_mode: Ingress color marking mode. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:584: *                        \u0026enum mxl862xx_color_marking_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-585- * @egress_remarking_mode: Color remarking for egress traffic. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:586: *                         \u0026enum mxl862xx_color_remarking_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-587- * @ingress_metering_enable: Traffic metering on ingress traffic applies\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-597- * @pmapper_mapping_mode: P-mapper mapping mode. See\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:598: *                        \u0026enum mxl862xx_pmapper_mapping_mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-599- * @pmapper_id_valid: When true, P-mapper is re-used; when false,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-653- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:654:struct mxl862xx_bridge_port_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-655-\t__le16 bridge_port_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:656:\t__le32 mask; /* enum mxl862xx_bridge_port_config_mask */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-657-\t__le16 bridge_id;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-663-\t__le16 egress_extended_vlan_block_size;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:664:\t__le32 ingress_marking_mode; /* enum mxl862xx_color_marking_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:665:\t__le32 egress_remarking_mode; /* enum mxl862xx_color_remarking_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-666-\tu8 ingress_metering_enable;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-672-\t__le16 dest_sub_if_id_group;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:673:\t__le32 pmapper_mapping_mode; /* enum mxl862xx_pmapper_mapping_mode */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-674-\tu8 pmapper_id_valid;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:675:\tstruct mxl862xx_pmapper pmapper;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-676-\t__le16 bridge_port_map[8];\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-709-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:710: * struct mxl862xx_cfg -  Global Switch configuration Attributes\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:711: * @mac_table_age_timer: See \u0026enum mxl862xx_age_timer\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-712- * @age_timer: Custom MAC table aging timer in seconds\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-722- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:723:struct mxl862xx_cfg {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:724:\t__le32 mac_table_age_timer; /* enum mxl862xx_age_timer */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-725-\t__le32 age_timer;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-734-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:735: * enum mxl862xx_extended_vlan_filter_type - Extended VLAN filter tag type\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-736- * @MXL862XX_EXTENDEDVLAN_FILTER_TYPE_NORMAL: Normal tagged\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-740- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:741:enum mxl862xx_extended_vlan_filter_type {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-742-\tMXL862XX_EXTENDEDVLAN_FILTER_TYPE_NORMAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-748-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:749: * enum mxl862xx_extended_vlan_filter_tpid - Extended VLAN filter TPID\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-750- * @MXL862XX_EXTENDEDVLAN_FILTER_TPID_NO_FILTER: No TPID filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-753- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:754:enum mxl862xx_extended_vlan_filter_tpid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-755-\tMXL862XX_EXTENDEDVLAN_FILTER_TPID_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-760-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:761: * enum mxl862xx_extended_vlan_filter_dei - Extended VLAN filter DEI\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-762- * @MXL862XX_EXTENDEDVLAN_FILTER_DEI_NO_FILTER: No DEI filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-765- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:766:enum mxl862xx_extended_vlan_filter_dei {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-767-\tMXL862XX_EXTENDEDVLAN_FILTER_DEI_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-772-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:773: * enum mxl862xx_extended_vlan_treatment_remove_tag - Tag removal action\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-774- * @MXL862XX_EXTENDEDVLAN_TREATMENT_NOT_REMOVE_TAG: Do not remove tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-778- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:779:enum mxl862xx_extended_vlan_treatment_remove_tag {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-780-\tMXL862XX_EXTENDEDVLAN_TREATMENT_NOT_REMOVE_TAG = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-786-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:787: * enum mxl862xx_extended_vlan_treatment_priority - Treatment priority mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-788- * @MXL862XX_EXTENDEDVLAN_TREATMENT_PRIORITY_VAL: Use explicit value\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-792- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:793:enum mxl862xx_extended_vlan_treatment_priority {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-794-\tMXL862XX_EXTENDEDVLAN_TREATMENT_PRIORITY_VAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-800-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:801: * enum mxl862xx_extended_vlan_treatment_vid - Treatment VID mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-802- * @MXL862XX_EXTENDEDVLAN_TREATMENT_VID_VAL: Use explicit VID value\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-805- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:806:enum mxl862xx_extended_vlan_treatment_vid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-807-\tMXL862XX_EXTENDEDVLAN_TREATMENT_VID_VAL = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-812-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:813: * enum mxl862xx_extended_vlan_treatment_tpid - Treatment TPID mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-814- * @MXL862XX_EXTENDEDVLAN_TREATMENT_INNER_TPID: Copy from inner tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-818- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:819:enum mxl862xx_extended_vlan_treatment_tpid {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-820-\tMXL862XX_EXTENDEDVLAN_TREATMENT_INNER_TPID = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-826-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:827: * enum mxl862xx_extended_vlan_treatment_dei - Treatment DEI mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-828- * @MXL862XX_EXTENDEDVLAN_TREATMENT_INNER_DEI: Copy from inner tag\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-832- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:833:enum mxl862xx_extended_vlan_treatment_dei {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-834-\tMXL862XX_EXTENDEDVLAN_TREATMENT_INNER_DEI = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-840-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:841: * enum mxl862xx_extended_vlan_4_tpid_mode - 4-TPID mode selector\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-842- * @MXL862XX_EXTENDEDVLAN_TPID_VTETYPE_1: VLAN TPID type 1\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-846- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:847:enum mxl862xx_extended_vlan_4_tpid_mode {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-848-\tMXL862XX_EXTENDEDVLAN_TPID_VTETYPE_1 = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-854-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:855: * enum mxl862xx_extended_vlan_filter_ethertype - Filter EtherType match\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-856- * @MXL862XX_EXTENDEDVLAN_FILTER_ETHERTYPE_NO_FILTER: No filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-864- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:865:enum mxl862xx_extended_vlan_filter_ethertype {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-866-\tMXL862XX_EXTENDEDVLAN_FILTER_ETHERTYPE_NO_FILTER = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-876-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:877: * struct mxl862xx_extendedvlan_filter_vlan - Per-tag filter in Extended VLAN\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:878: * @type: Tag presence/type match (see \u0026enum mxl862xx_extended_vlan_filter_type)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-879- * @priority_enable: Enable PCP value matching\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-882- * @vid_val: VID value to match\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:883: * @tpid: TPID match mode (see \u0026enum mxl862xx_extended_vlan_filter_tpid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:884: * @dei: DEI match mode (see \u0026enum mxl862xx_extended_vlan_filter_dei)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-885- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:886:struct mxl862xx_extendedvlan_filter_vlan {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-887-\t__le32 type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-896-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:897: * struct mxl862xx_extendedvlan_filter - Extended VLAN filter configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-898- * @original_packet_filter_mode: If true, filter on original (pre-treatment)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-899- *                               packet\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:900: * @filter_4_tpid_mode: 4-TPID mode (see \u0026enum mxl862xx_extended_vlan_4_tpid_mode)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-901- * @outer_vlan: Outer VLAN tag filter\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-903- * @ether_type: EtherType filter (see\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:904: *              \u0026enum mxl862xx_extended_vlan_filter_ethertype)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-905- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:906:struct mxl862xx_extendedvlan_filter {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-907-\tu8 original_packet_filter_mode;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-908-\t__le32 filter_4_tpid_mode;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:909:\tstruct mxl862xx_extendedvlan_filter_vlan outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:910:\tstruct mxl862xx_extendedvlan_filter_vlan inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-911-\t__le32 ether_type;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-914-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:915: * struct mxl862xx_extendedvlan_treatment_vlan - Per-tag treatment in\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-916- *                                               Extended VLAN\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-917- * @priority_mode: Priority assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:918: *                 (see \u0026enum mxl862xx_extended_vlan_treatment_priority)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-919- * @priority_val: Priority value (when mode is VAL)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-920- * @vid_mode: VID assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:921: *            (see \u0026enum mxl862xx_extended_vlan_treatment_vid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-922- * @vid_val: VID value (when mode is VAL)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-923- * @tpid: TPID assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:924: *        (see \u0026enum mxl862xx_extended_vlan_treatment_tpid)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-925- * @dei: DEI assignment mode\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:926: *       (see \u0026enum mxl862xx_extended_vlan_treatment_dei)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-927- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:928:struct mxl862xx_extendedvlan_treatment_vlan {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-929-\t__le32 priority_mode;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-937-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:938: * struct mxl862xx_extendedvlan_treatment - Extended VLAN treatment\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-939- * @remove_tag: Tag removal action\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:940: *              (see \u0026enum mxl862xx_extended_vlan_treatment_remove_tag)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-941- * @treatment_4_tpid_mode: 4-TPID treatment mode\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-958- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:959:struct mxl862xx_extendedvlan_treatment {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-960-\t__le32 remove_tag;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-962-\tu8 add_outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:963:\tstruct mxl862xx_extendedvlan_treatment_vlan outer_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-964-\tu8 add_inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:965:\tstruct mxl862xx_extendedvlan_treatment_vlan inner_vlan;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-966-\tu8 reassign_bridge_port;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-980-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:981: * struct mxl862xx_extendedvlan_alloc - Extended VLAN block allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-982- * @number_of_entries: Number of entries to allocate (input) / allocated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-988- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:989:struct mxl862xx_extendedvlan_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-990-\t__le16 number_of_entries;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-994-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:995: * struct mxl862xx_extendedvlan_config - Extended VLAN entry configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-996- * @extended_vlan_block_id: Block ID from allocation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1002- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1003:struct mxl862xx_extendedvlan_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1004-\t__le16 extended_vlan_block_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1005-\t__le16 entry_index;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1006:\tstruct mxl862xx_extendedvlan_filter filter;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1007:\tstruct mxl862xx_extendedvlan_treatment treatment;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1008-} __packed;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1010-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1011: * enum mxl862xx_vlan_filter_tci_mask - VLAN Filter TCI mask\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1012- * @MXL862XX_VLAN_FILTER_TCI_MASK_VID: TCI mask for VLAN ID\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1015- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1016:enum mxl862xx_vlan_filter_tci_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1017-\tMXL862XX_VLAN_FILTER_TCI_MASK_VID = 0,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1022-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1023: * struct mxl862xx_vlanfilter_alloc - VLAN Filter block allocation\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1024- * @number_of_entries: Number of entries to allocate (input) / allocated\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1034- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1035:struct mxl862xx_vlanfilter_alloc {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1036-\t__le16 number_of_entries;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1043-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1044: * struct mxl862xx_vlanfilter_config - VLAN Filter entry configuration\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1045- * @vlan_filter_block_id: Block ID from allocation\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1047- * @vlan_filter_mask: TCI field(s) to match (see\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1048: *                    \u0026enum mxl862xx_vlan_filter_tci_mask)\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1049- * @val: TCI value(s) to match (VID, PCP, or full TCI depending on mask)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1054- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1055:struct mxl862xx_vlanfilter_config {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1056-\t__le16 vlan_filter_block_id;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1057-\t__le16 entry_index;\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1058:\t__le32 vlan_filter_mask; /* enum mxl862xx_vlan_filter_tci_mask */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1059-\t__le32 val;\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1063-/**\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1064: * enum mxl862xx_ss_sp_tag_mask - Special tag valid field indicator bits\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1065- * @MXL862XX_SS_SP_TAG_MASK_RX: valid RX special tag mode\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1069- */\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h:1070:enum mxl862xx_ss_sp_tag_mask {\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1071-\tMXL862XX_SS_SP_TAG_MASK_RX = BIT(0),\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-api.h-1077-/**\n\n"
}

gemini-3.1-pro-preview

							input: 47451
							output: 20
							thoughts: 283

**Analyzing the mxl862xx Driver for Virtualization Potential**

Okay, so I'm looking at the `mxl862xx` driver, specifically `drivers/net/dsa/mxl862xx/mxl862xx.c`. It's an MDIO device driver, and the driver structure definition looks pretty standard:

```c
static struct mdio_driver mxl862xx_driver = {
	.mdiodrv.driver = {
		.name = "mxl862xx",
		.of_match_table = mxl862xx_of_match,
	},
	.probe = mxl862xx_probe,
	.remove = mxl862xx_remove,
};
```

The question is, can I get this thing probed in a virtualized setting? Ideally, I'd want to create a mock MDIO bus, register a virtual device, and see if the driver attaches properly. Standard procedure would involve something like `mdio-mockup`, or similar techniques. But wait, this is syzkaller, and syzkaller doesn't typically mess around with that level of setup.

Hmm... syzkaller does have `syz_genetlink` and `syz_devlink` which are interesting for interacting with networking and device linking... but unless there's a software emulator *specifically* for an MDIO device, I'm going to have trouble directly instantiating this specific hardware.

Okay, let's take a step back and consider `device_schedule_reprobe`. That's a generic function in `drivers/base/dd.c`, and it's something that I've seen used in these situations before. I wonder if it's reachable from anywhere else? A generic function is more likely to be exposed and invoked. I should check how else it's used within the codebase.

{
  "Expression": "device_schedule_reprobe"
}

{
  "Output": "drivers/base/base.h=80=struct driver_private {\n--\ndrivers/base/base.h-111- *\t  device lock. A deferred re-probe scheduled with\ndrivers/base/base.h:112: *\t  device_schedule_reprobe() must not detach the device anymore.\ndrivers/base/base.h-113- *\n--\ndrivers/base/dd.c=1447=static void device_reprobe_work_fn(struct work_struct *work)\n--\ndrivers/base/dd.c-1485-/**\ndrivers/base/dd.c:1486: * device_schedule_reprobe - schedule a deferred detach and re-probe\ndrivers/base/dd.c-1487- * @dev: device to detach and re-probe\n--\ndrivers/base/dd.c-1510- */\ndrivers/base/dd.c:1511:int device_schedule_reprobe(struct device *dev, unsigned int delay_ms)\ndrivers/base/dd.c-1512-{\n--\ndrivers/base/dd.c-1536-}\ndrivers/base/dd.c:1537:EXPORT_SYMBOL_GPL(device_schedule_reprobe);\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c=421=void mxl862xx_rescue_heal_work_fn(struct work_struct *work)\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-451-\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c:452:\tif (device_schedule_reprobe(dev, MXL862XX_FW_REPROBE_DELAY_MS))\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-453-\t\tWRITE_ONCE(priv-\u003erescue_failed, true);\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c=926=int mxl862xx_devlink_flash_update(struct dsa_switch *ds,\n--\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-1058-\t */\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c:1059:\terr = device_schedule_reprobe(ds-\u003edev, MXL862XX_FW_REPROBE_DELAY_MS);\ndrivers/net/dsa/mxl862xx/mxl862xx-fw.c-1060-\n--\ninclude/linux/device.h=1316=int __must_check device_reprobe(struct device *dev);\ninclude/linux/device.h:1317:int __must_check device_schedule_reprobe(struct device *dev,\ninclude/linux/device.h-1318-\t\t\t\t\t unsigned int delay_ms);\n"
}

gemini-3.1-pro-preview

							input: 48943
							output: 19
							thoughts: 138

**My Line of Reasoning**

Okay, so `device_schedule_reprobe` is pretty specific; it seems it's exclusively used within the `mxl862xx` driver. Right away, that raises a flag. `mxl862xx` is definitely a hardware-specific driver, which usually requires actual physical hardware or at least a very precise emulation. And let's be realistic, standard QEMU or Google Compute Engine environments aren't going to have that specific emulation available. So, directly hitting that code path seems impossible.

Hold on a second, though... is there *any* other way that `device_schedule_reprobe` could be triggered? Let me double-check the call graph. Nope, it's exclusively within `mxl862xx`. Damn. Okay, back to the drawing board.

Wait, maybe there's a back door. Could Syzkaller somehow instantiate an MDIO device using something like `mdio-mockup`, or a similar construct? It’s a long shot, but worth checking. Let me confirm if that `mdio-mockup` driver is even present in the target system. Time to go dig around.

{
  "Expression": "mdio-mockup"
}

{
  "error": "no matches"
}

gemini-3.1-pro-preview

							input: 49367
							output: 21
							thoughts: 364

**Analyzing the Fuzzing Worthiness of a Patch**

Okay, let's break this down. First, I ruled out `mdio-mockup.c` pretty quickly – not the right approach. Then I considered instantiating an MDIO device from userspace. Nope, that's handled by the MDIO bus driver, likely through device tree or board code, not a generic userspace interface. So, the `mxl862xx` driver is out for virtualization without specific hardware or emulation.

Now, the instructions are key. They say to return `WorthFuzzing=false` if the changes are unreachable in virtualized environments. I looked at `device_schedule_reprobe`. It *is* a core function, a new API even, but is it reachable? Currently, no. No other code calls it. It's exported, but that doesn't mean it's executed. Therefore, following the instructions, that's another `WorthFuzzing=false`.

Wait a minute, what about `dsa_devlink_flash_update`? This is added to `dsa_devlink_ops`, that's potentially different. But is it reachable? If a DSA switch implements `devlink_flash_update`, then yes, it's reachable. Right now, *only* `mxl862xx` does. So, I need to investigate further: are there *any* other DSA switch implementations that use `devlink_flash_update`? That's the key to figuring this out. That's my next step.

{
  "Expression": "\\.devlink_flash_update"
}

{
  "Output": "drivers/net/dsa/mxl862xx/mxl862xx.c=2185=static const struct dsa_switch_ops mxl862xx_switch_ops = {\n--\ndrivers/net/dsa/mxl862xx/mxl862xx.c-2217-\t.devlink_info_get = mxl862xx_devlink_info_get,\ndrivers/net/dsa/mxl862xx/mxl862xx.c:2218:\t.devlink_flash_update = mxl862xx_devlink_flash_update,\ndrivers/net/dsa/mxl862xx/mxl862xx.c-2219-};\n"
}

gemini-3.1-pro-preview

							input: 50287
							output: 102
							thoughts: 1074

**Analysis of the Proposed Patch's Fuzzing Potential**

Okay, let's break this down. My initial assessment is that this patch isn't particularly fruitful for fuzzing, given the constraints. It looks like the main functionality centers around `mxl862xx`, a driver for a specific hardware switch. I see that `dsa_devlink_flash_update` is affected, but for other DSA switches it will simply return `-EOPNOTSUPP`. That initial function is reachable, but trivial in its implementation.

The core logic resides within `mxl862xx-fw.c` and involves `device_schedule_reprobe`. The problem is that `mxl862xx` isn't accessible without the actual hardware; its probe logic, specifically using MDIO reads/writes and looking for specific register values, will fail if the physical device isn't present. And Syzkaller, in its current implementation, isn't going to dynamically inject device tree nodes to probe arbitrary MDIO devices. I can already see from the code that any attempt to emulate the device would fail during early probe attempts. Even if somehow it could, without the actual hardware it will fail early within probe.

So, the juicy stuff is locked away in that driver, essentially unaccessible. What about the changes in `drivers/base/dd.c` and `drivers/base/core.c`? Setting `shutdown_done` during `device_shutdown` is reachable during system shutdown, but that's a trivial change: just setting a boolean flag. The other change there - the introduction of `device_schedule_reprobe` and `device_reprobe_work_fn` - is only used by that `mxl862xx` driver. It depends on an MDIO probe, which fails in an emulated environment. Therefore, the useful parts are unexercisable. I'm seeing that the patch relies on a hardware-specific driver, one that can't be probed in my current fuzzing setup.

The driver has a few device compatible strings: `maxlinear,mxl86280`, `maxlinear,mxl86281`, `maxlinear,mxl86282`, `maxlinear,mxl86283`, `maxlinear,mxl86280s`, `maxlinear,mxl86281s`, `maxlinear,mxl86282s`, and `maxlinear,mxl86283s`.

So, in conclusion, the patch is not worth fuzzing, based on the fact that I can't reach the core driver logic due to hardware dependencies and limitations in the virtual environment. I'm going to set `WorthFuzzing=false`. The reasoning is that the firmware flash and devlink support are added for a hardware-specific switch driver which requires physical MDIO hardware. Because of the MDIO requirements, the driver cannot be probed in an emulated environment and the core changes, `device_schedule_reprobe` and `device_shutdown`, are not worth fuzzing.

{
  "EnableConfigs": [],
  "FocusSymbols": [],
  "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.",
  "WorthFuzzing": false
}

{
  "EnableConfigs": null,
  "FocusSymbols": [],
  "Reasoning": "The patch adds firmware flash and devlink support for the MaxLinear MxL862xx hardware switch driver. The driver requires physical MDIO hardware to probe successfully and cannot be reached in a virtualized environment. The core changes (device_schedule_reprobe) are only used by this unreachable driver, and the device_shutdown flag is trivial.",
  "WorthFuzzing": false
}

{
  "WorthFuzzing": false
}

LLM Calls Summary:
Total Calls	Total Tokens	Avg Tokens	Total Duration (Seconds)	Avg Duration (Seconds)

Tool Calls Summary:
Total Calls	Total Duration (Seconds)	Avg Duration (Seconds)