[PATCH 5.10 166/235] wifi: brcmfmac: drain bus_reset work on device removal

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

5.10-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Fan Wu <fanwu01@zju.edu.cn>

[ Upstream commit 43b25879f004c98defa2776bedc6ca4763c51945 ]

brcmf_fw_crashed() and the debugfs "reset" entry both schedule
drvr->bus_reset, whose callback recovers drvr through container_of()
and dereferences it.  The removal path frees drvr (brcmf_free ->
wiphy_free) without draining the work, so a bus_reset callback pending
or running during removal can outlive drvr.

Cancellation cannot live in brcmf_detach() or brcmf_free(): the work
callback reaches teardown through the bus .reset op (PCIe
brcmf_pcie_reset -> brcmf_detach; SDIO brcmf_sdio_bus_reset ->
brcmf_sdiod_remove -> brcmf_free), so cancelling there would wait for
the running work and deadlock.

Add a per-bus mutex (bus_reset_lock) and route all arming through
brcmf_bus_schedule_reset(), which under the lock skips when the bus is
marked removing.  Each bus remove entry calls
brcmf_bus_cancel_reset_work(), which under the same lock sets removing
and cancels the work.  Holding the mutex across cancel_work_sync() makes
the set-removing + drain step atomic.  Every producer reaches the arming
path from process context -- the PCIe firmware-halt notification runs in
the threaded IRQ handler (brcmf_pcie_isr_thread) and the SDIO hostmail
path runs from the data workqueue -- so the mutex is taken only in
sleepable contexts.  Where applicable the remove entry first stops the
firmware-crash producer: on PCIe mask the mailbox and synchronize_irq;
on SDIO unregister the bus interrupt and cancel the data worker, which
also reports firmware halts through brcmf_fw_crashed().  The mutex is
initialized at bus allocation.  The SDIO suspend power-off path frees
drvr through the same brcmf_sdiod_remove() and takes the same lock;
resume re-allows the work only on a successful re-probe.

Also guard brcmf_fw_crashed() against a NULL bus_if/drvr: it can fire
before brcmf_attach() wires up drvr, and it dereferences drvr
(bphy_err/brcmf_dev_coredump) before reaching the arming gate.

The bus_reset work is shared across buses, so the drain is applied to
every remove path: PCIe (the .reset op introduced by the Fixes commit),
SDIO (arms the same work through brcmf_fw_crashed()), and USB (via the
debugfs "reset" entry).  cancel_work_sync() drains a running or pending
bus_reset work item before removal frees drvr, and patch 1/2 makes the
scratch-buffer release safe when reset teardown has already released
those DMA buffers.

This patch fixes the lifetime of the bus_reset work item itself.  It does
not attempt to address the separate, pre-existing lifetime of the
asynchronous firmware completion started by the PCIe reset path.  That
callback needs its own lifetime/ownership protocol and is being tracked
separately.

This issue was found by an in-house static analysis tool.

Fixes: 4684997d9eea ("brcmfmac: reset PCIe bus on a firmware crash")
Cc: stable@vger.kernel.org
Signed-off-by: Fan Wu <fanwu01@zju.edu.cn>
Assisted-by: Codex:gpt-5.6
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20260718024353.3147201-3-fanwu01@zju.edu.cn
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c |   13 ++++
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h    |    6 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c   |   45 +++++++++++++-
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c   |    6 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c   |    6 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h   |    1 
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c    |    3 
 7 files changed, 77 insertions(+), 3 deletions(-)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -1042,6 +1042,7 @@ static int brcmf_ops_sdio_probe(struct s
 	bus_if = kzalloc(sizeof(struct brcmf_bus), GFP_KERNEL);
 	if (!bus_if)
 		return -ENOMEM;
+	mutex_init(&bus_if->bus_reset_lock);
 	sdiodev = kzalloc(sizeof(struct brcmf_sdio_dev), GFP_KERNEL);
 	if (!sdiodev) {
 		kfree(bus_if);
@@ -1101,6 +1102,14 @@ static void brcmf_ops_sdio_remove(struct
 		if (func->num != 1)
 			return;
 
+		/* Drain bus_reset before the shared brcmf_sdiod_remove()
+		 * teardown, which the SDIO reset callback also reaches.  The
+		 * data worker can arm bus_reset via brcmf_fw_crashed(); cancel
+		 * it first.
+		 */
+		brcmf_sdio_cancel_datawork(sdiodev->bus);
+		brcmf_bus_cancel_reset_work(bus_if);
+
 		/* only proceed with rest of cleanup if func 1 */
 		brcmf_sdiod_remove(sdiodev);
 
@@ -1162,6 +1171,8 @@ static int brcmf_ops_sdio_suspend(struct
 	} else {
 		/* power will be cut so remove device, probe again in resume */
 		brcmf_sdiod_intr_unregister(sdiodev);
+		brcmf_sdio_cancel_datawork(sdiodev->bus);
+		brcmf_bus_cancel_reset_work(bus_if);
 		ret = brcmf_sdiod_remove(sdiodev);
 		if (ret)
 			brcmf_err("Failed to remove device on suspend\n");
@@ -1187,6 +1198,8 @@ static int brcmf_ops_sdio_resume(struct
 		ret = brcmf_sdiod_probe(sdiodev);
 		if (ret)
 			brcmf_err("Failed to probe device on resume\n");
+		else
+			brcmf_bus_allow_reset_work(bus_if);
 	} else {
 		if (sdiodev->wowl_enabled &&
 		    sdiodev->settings->bus.sdio.oob_irq_supported)
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bus.h
@@ -6,6 +6,7 @@
 #ifndef BRCMFMAC_BUS_H
 #define BRCMFMAC_BUS_H
 
+#include <linux/mutex.h>
 #include "debug.h"
 
 /* IDs of the 6 default common rings of msgbuf protocol */
@@ -149,11 +150,16 @@ struct brcmf_bus {
 	u32 chiprev;
 	bool always_use_fws_queue;
 	bool wowl_supported;
+	bool removing;		/* device removal in progress; quiesce async work */
+	struct mutex bus_reset_lock;
 
 	const struct brcmf_bus_ops *ops;
 	struct brcmf_bus_msgbuf *msgbuf;
 };
 
+void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if);
+void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if);
+
 /*
  * callback wrappers
  */
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -1166,6 +1166,35 @@ static int brcmf_revinfo_read(struct seq
 	return 0;
 }
 
+/*
+ * Serialize arming from debugfs reset and brcmf_fw_crashed() against
+ * teardown.  The remove path sets ->removing and drains the work while
+ * holding bus_reset_lock, so a racing armer is either drained or skips it.
+ */
+static void brcmf_bus_schedule_reset(struct brcmf_bus *bus_if)
+{
+	mutex_lock(&bus_if->bus_reset_lock);
+	if (bus_if->drvr && bus_if->drvr->bus_reset.func && !bus_if->removing)
+		schedule_work(&bus_if->drvr->bus_reset);
+	mutex_unlock(&bus_if->bus_reset_lock);
+}
+
+void brcmf_bus_cancel_reset_work(struct brcmf_bus *bus_if)
+{
+	mutex_lock(&bus_if->bus_reset_lock);
+	bus_if->removing = true;
+	if (bus_if->drvr)
+		cancel_work_sync(&bus_if->drvr->bus_reset);
+	mutex_unlock(&bus_if->bus_reset_lock);
+}
+
+void brcmf_bus_allow_reset_work(struct brcmf_bus *bus_if)
+{
+	mutex_lock(&bus_if->bus_reset_lock);
+	bus_if->removing = false;
+	mutex_unlock(&bus_if->bus_reset_lock);
+}
+
 static void brcmf_core_bus_reset(struct work_struct *work)
 {
 	struct brcmf_pub *drvr = container_of(work, struct brcmf_pub,
@@ -1186,7 +1215,7 @@ static ssize_t bus_reset_write(struct fi
 	if (value != 1)
 		return -EINVAL;
 
-	schedule_work(&drvr->bus_reset);
+	brcmf_bus_schedule_reset(drvr->bus_if);
 
 	return count;
 }
@@ -1404,13 +1433,23 @@ void brcmf_dev_coredump(struct device *d
 void brcmf_fw_crashed(struct device *dev)
 {
 	struct brcmf_bus *bus_if = dev_get_drvdata(dev);
-	struct brcmf_pub *drvr = bus_if->drvr;
+	struct brcmf_pub *drvr;
+
+	/* May fire before brcmf_attach() wires up drvr, or after removal
+	 * has cleared it; guard the derefs below (and the arming gate in
+	 * brcmf_bus_schedule_reset() already checks drvr/->removing).
+	 */
+	if (!bus_if)
+		return;
+	drvr = bus_if->drvr;
+	if (!drvr)
+		return;
 
 	bphy_err(drvr, "Firmware has halted or crashed\n");
 
 	brcmf_dev_coredump(dev);
 
-	schedule_work(&drvr->bus_reset);
+	brcmf_bus_schedule_reset(bus_if);
 }
 
 void brcmf_detach(struct device *dev)
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c
@@ -1892,6 +1892,7 @@ brcmf_pcie_probe(struct pci_dev *pdev, c
 		ret = -ENOMEM;
 		goto fail;
 	}
+	mutex_init(&bus->bus_reset_lock);
 	bus->msgbuf = kzalloc(sizeof(*bus->msgbuf), GFP_KERNEL);
 	if (!bus->msgbuf) {
 		ret = -ENOMEM;
@@ -1963,6 +1964,11 @@ brcmf_pcie_remove(struct pci_dev *pdev)
 	if (devinfo->ci)
 		brcmf_pcie_intr_disable(devinfo);
 
+	if (devinfo->irq_allocated)
+		synchronize_irq(pdev->irq);
+
+	brcmf_bus_cancel_reset_work(bus);
+
 	brcmf_detach(&pdev->dev);
 	brcmf_free(&pdev->dev);
 
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4530,6 +4530,12 @@ fail:
 	return NULL;
 }
 
+void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus)
+{
+	if (bus)
+		cancel_work_sync(&bus->datawork);
+}
+
 /* Detach and free everything */
 void brcmf_sdio_remove(struct brcmf_sdio *bus)
 {
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.h
@@ -373,6 +373,7 @@ int brcmf_sdiod_remove(struct brcmf_sdio
 struct brcmf_sdio *brcmf_sdio_probe(struct brcmf_sdio_dev *sdiodev);
 void brcmf_sdio_remove(struct brcmf_sdio *bus);
 void brcmf_sdio_isr(struct brcmf_sdio *bus, bool in_isr);
+void brcmf_sdio_cancel_datawork(struct brcmf_sdio *bus);
 
 void brcmf_sdio_wd_timer(struct brcmf_sdio *bus, bool active);
 void brcmf_sdio_wowl_config(struct device *dev, bool enabled);
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c
@@ -1273,6 +1273,7 @@ static int brcmf_usb_probe_cb(struct brc
 		ret = -ENOMEM;
 		goto fail;
 	}
+	mutex_init(&bus->bus_reset_lock);
 
 	bus->dev = dev;
 	bus_pub->bus = bus;
@@ -1338,6 +1339,8 @@ brcmf_usb_disconnect_cb(struct brcmf_usb
 		return;
 	brcmf_dbg(USB, "Enter, bus_pub %p\n", devinfo);
 
+	brcmf_bus_cancel_reset_work(devinfo->bus_pub.bus);
+
 	brcmf_detach(devinfo->dev);
 	brcmf_free(devinfo->dev);
 	kfree(devinfo->bus_pub.bus);