Compare commits

..

1 Commits

Author SHA1 Message Date
test0r 4604958033 bes2600: recover wedged firmware via mmc_hw_reset on link break
When the LMAC active monitor detects 'link break between lmac and host'
(the hw_buf_used==pending watchdog in bes2600_bh_lmac_active_monitor),
bes2600_chrdev_wifi_force_close(hw_priv, true) is invoked to tear the
device down and prepare for a fresh probe. On the wifi_force_close_work
side this calls bes2600_chrdev_do_system_close() which dispatches
sbus_ops->power_switch(0).

On PineTab2 (RK3566 + BES2600WM over SDIO) this recovery path is a
no-op:

  * bes2600_sdio_power_down() writes a SYSTEM_CLOSE host-int message,
    clears MMC_CAP_NONREMOVABLE, and schedules sdio_scan_work, which is
    the literal one-line stub bes_warn("...this function does
    nothing\n").
  * bes2600_sdio_on() (the eventual power_switch(1) counterpart)
    toggles pdata->powerup, which is NULL on PineTab2 because the
    wifi-reset GPIO is owned by sdio_pwrseq, not the bes2600 device
    tree node (see arch/arm64/boot/dts/rockchip/rk3566-pinetab2.dtsi:
    'The reset pin is claimed by sdio_mmcseq, It is better to move it
    to U-Boot so the OS can use it.').

Net result: the chip is never reset. The function drivers are not
removed (the SDIO core has no signal that the card is gone), the
firmware stays wedged, and a subsequent rmmod bes2600 leaves the SDIO
function in a half-torn-down state. modprobe bes2600 then fails with
'probe with driver bes2600_wlan failed with error -123' (-ENOMEDIUM)
on both functions (:1 wifi, :2 BT-companion) until a full system
reboot.

Observed on PineTab2 (linux-pinetab2 6.19.10-danctnix1-1) after ~150
minutes of background-scan rejects (wsm_generic_confirm 0x0007,
[SCAN] Scan failed (-22)) accumulating until the LMAC stopped
acknowledging TX buffers (hw_buf_used:24 pending:24). Reproducible
under sustained scan pressure.

Add a sbus operation bus_reset() that the recovery path can call when
power_switch() has no effective chip-reset signal of its own. Provide
an SDIO implementation that calls mmc_hw_reset(self->func->card),
which on a multi-function SDIO card (PineTab2 binds func 1 for WLAN
and func 2 for the BT-companion path) takes the remove-and-rescan
path: mmc_sdio_hw_reset() marks the card removed and schedules
mmc_rescan, which tears down the bound function drivers and re-detects
the card on the next sweep, in turn reinvoking bes2600_sdio_probe().
With a single function probed it instead invokes mmc_power_cycle()
directly, which on PineTab2 toggles the wifi-reset GPIO via
sdio_pwrseq.

Add bes2600_chrdev_do_bus_reset() as the chrdev-side helper. It
invokes the bus op and then waits on probe_done_wq for the SDIO
remove() callback to clear sbus_priv, mirroring the wait pattern
already used by bes2600_chrdev_do_system_close() so that a subsequent
bes2600_switch_wifi(true) sees a clean state and can wait on the
fresh probe.

Wire it into bes2600_chrdev_wifi_force_close_work(): when halt_dev is
set (the hard-exception path used by both
bes2600_bh_lmac_active_monitor and bes2600_bh_mcu_active_monitor) and
the underlying bus implements bus_reset, take the new recovery path;
otherwise fall back to the legacy power_switch(0) sequence so this
patch is a no-op on USB or any other future bus that does not provide
bus_reset.

mmc_hw_reset() is exported by the MMC core and is the canonical
recovery primitive; calling it without holding the SDIO host claim is
correct because the multi-func remove-and-rescan path acquires the
host claim via the mmc workqueue, and the single-func mmc_power_cycle
path does not require the host claim.

No DT change is required: this works against the existing PineTab2
DTS, where the wifi-reset GPIO and the optional sdio_pwrkey GPIO (on
v2.0 boards) are both already configured as MMC pwrseq resets.

Signed-off-by: Markus Fritsche <fritsche.markus@gmail.com>
2026-04-26 22:32:29 +02:00
11 changed files with 23 additions and 473 deletions
-21
View File
@@ -511,9 +511,6 @@ struct bes2600_common {
struct list_head coex_event_list;
spinlock_t coex_event_lock;
/* Connection-loss-storm fast-recover (Trigger A). See sta.c. */
struct work_struct connection_loss_storm_recover_work;
/* member for low power */
struct bes2600_pwr_t bes_power;
@@ -599,11 +596,6 @@ struct bes2600_vif {
unsigned long rx_timestamp;
u32 cipherType;
/* Decrypt-storm fast-recover (Trigger B). See txrx.c. */
unsigned long decrypt_storm_window_start;
unsigned int decrypt_storm_count;
unsigned int decrypt_storm_recoveries;
struct work_struct decrypt_storm_recover_work;
/* AP powersave */
u32 link_id_map;
@@ -630,10 +622,6 @@ struct bes2600_vif {
/* CQM Implementation */
struct delayed_work bss_loss_work;
struct delayed_work connection_loss_work;
/* Connection-loss-storm fast-recover (Trigger A). See sta.c. */
unsigned long connection_loss_storm_window_start;
unsigned int connection_loss_storm_count;
unsigned int connection_loss_storm_recoveries;
struct work_struct tx_failure_work;
int delayed_link_loss;
spinlock_t bss_loss_lock;
@@ -868,13 +856,4 @@ int bes2600_btusb_setup_pipes(struct sbus_priv *sbus_priv);
void bes2600_btusb_uninit(struct usb_interface *interface);
#endif
/* Decrypt-storm fast-recover helpers — see txrx.c. */
void bes2600_decrypt_storm_init(struct bes2600_vif *priv);
void bes2600_decrypt_storm_account(struct bes2600_vif *priv);
/* Connection-loss-storm fast-recover helpers — see sta.c. */
void bes2600_connection_loss_storm_init(struct bes2600_vif *priv);
bool bes2600_connection_loss_storm_account(struct bes2600_vif *priv);
void bes2600_connection_loss_storm_recover(struct work_struct *work);
#endif /* BES2600_H */
+3 -36
View File
@@ -1389,14 +1389,7 @@ static void bes2600_gpio_wakeup_mcu(struct sbus_priv *self, int flag)
/* error check */
if((self->gpio_wakup_flags & BIT(flag)) != 0) {
/*
* Multiple subsystems holding wake is the steady-state case
* (e.g. WIFI + BT both want MCU awake). Demoted from bes_err
* to bes_devel since it isn't an error - the GPIO is already
* asserted high and the subsystem is now also tracked.
*/
bes_devel("repeat set gpio_wake_flag, sub_sys:%d\n", flag);
self->gpio_wakup_flags |= BIT(flag);
bes_err( "repeat set gpio_wake_flag, sub_sys:%d", flag);
mutex_unlock(&self->io_mutex);
return;
}
@@ -1428,11 +1421,7 @@ static void bes2600_gpio_allow_mcu_sleep(struct sbus_priv *self, int flag)
/* error check */
if((self->gpio_wakup_flags & BIT(flag)) == 0) {
/*
* Mirror of the wake path: a clear when the bit is already
* clear is racy bookkeeping, not a hardware error.
*/
bes_devel("repeat clear gpio_wake_flag, sub_sys:%d\n", flag);
bes_err( "repeat clear gpio_wake_flag, sub_sys:%d", flag);
mutex_unlock(&self->io_mutex);
return;
}
@@ -1810,32 +1799,10 @@ static void bes2600_sdio_halt_device(struct sbus_priv *self)
*/
static int bes2600_sdio_bus_reset(struct sbus_priv *self)
{
struct mmc_host *host;
int ret;
if (!self || !self->func || !self->func->card)
return -EINVAL;
host = self->func->card->host;
ret = mmc_hw_reset(self->func->card);
/*
* On multi-function SDIO cards (BES2600 has WLAN func 1 + BT
* companion func 2), mmc_sdio_hw_reset() removes the card and
* returns 1 to signal "remove happened, caller must trigger
* rescan". The kernel does NOT auto-rescan in this case;
* single-function cards take the rescan path inline and return 0.
* Treat any non-negative return as success and force a rescan if
* mmc_hw_reset signalled the multi-function path - otherwise the
* card stays removed indefinitely after a wedge recovery,
* leaving wifi (and the BT companion) silent until reboot.
*/
if (ret > 0) {
bes_info("multi-func mmc_hw_reset removed card; scheduling rescan\n");
mmc_detect_change(host, 0);
ret = 0;
}
return ret;
return mmc_hw_reset(self->func->card);
}
static bool bes2600_sdio_wakeup_source(struct sbus_priv *self)
-12
View File
@@ -484,18 +484,6 @@ int bes2600_chrdev_do_bus_reset(const struct sbus_ops *sbus_ops, struct sbus_pri
return 0;
}
/*
* Trigger bes2600_chrdev_do_bus_reset() against the file-global
* bes2600_cdev. Used by host-side recovery paths outside this
* compilation unit (e.g. sta.c connection-loss-storm fast-recover) so
* those callers do not need to reach the static bes2600_cdev directly.
*/
int bes2600_chrdev_trigger_bus_reset(void)
{
return bes2600_chrdev_do_bus_reset(bes2600_cdev.sbus_ops,
bes2600_cdev.sbus_priv);
}
bool bes2600_chrdev_is_wifi_opened(void)
{
bool wifi_opened = false;
-1
View File
@@ -61,7 +61,6 @@ struct sbus_priv *bes2600_chrdev_get_sbus_priv_data(void);
int bes2600_chrdev_check_system_close(void);
int bes2600_chrdev_do_system_close(const struct sbus_ops *sbus_ops, struct sbus_priv *priv);
int bes2600_chrdev_do_bus_reset(const struct sbus_ops *sbus_ops, struct sbus_priv *priv);
int bes2600_chrdev_trigger_bus_reset(void);
void bes2600_chrdev_wakeup_bt(void);
void bes2600_chrdev_wifi_force_close(struct bes2600_common *hw_priv, bool halt_dev);
void bes2600_chrdev_usb_remove(struct bes2600_common *hw_priv);
+10 -196
View File
@@ -467,45 +467,6 @@ static void bes2600_pwr_device_enter_lp_mode(struct bes2600_common *hw_priv)
bes_devel("device enter sleep\n");
}
/*
* Number of consecutive bes2600_pwr_enter_lp_mode timeouts (with zero
* PM_INDICATIONs received) before we conclude the firmware does not
* honor host-driven PSM and switch to a sticky skip path.
*/
#define BES2600_PM_UNSUPPORTED_THRESHOLD 3
/*
* Latch pm_unsupported = true and force chip_pm_state = ACTIVE so the
* c6.2 wake-side skip branch covers bes2600_pwr_device_exit_lp_mode.
* Called after BES2600_PM_UNSUPPORTED_THRESHOLD consecutive enter_lp_mode
* timeouts with zero PM_INDICATIONs.
*/
static void bes2600_pwr_latch_pm_unsupported(struct bes2600_common *hw_priv)
{
bes_warn("PSM not honored (%u timeouts), switching to skip mode\n",
hw_priv->bes_power.pm_consecutive_timeouts);
hw_priv->bes_power.pm_unsupported = true;
atomic_set(&hw_priv->bes_power.chip_pm_state,
BES2600_CHIP_PM_ACTIVE);
/*
* Hold the MCU wake-flag bit permanently. Without this, every
* sdio_rx_work invocation hits bes2600_gpio_wakeup_mcu(SDIO_RX)
* when gpio_wakup_flags == 0, drives the GPIO high and msleeps
* 10 ms per RX. With ~50 RX/s of beacons + multicast that's
* ~50%% of the bes_sdio workqueue thread blocked in msleep,
* which directly caps RX throughput. Holding the MCU bit makes
* those calls bit-only bookkeeping (gpio_wakeup = (flags == 0)
* stays false, no GPIO toggle, no msleep). The bit is never
* cleared once pm_unsupported is set because
* bes2600_pwr_device_enter_lp_mode is unreachable under the
* early-return.
*/
if (hw_priv->sbus_ops->gpio_wake)
hw_priv->sbus_ops->gpio_wake(hw_priv->sbus_priv,
GPIO_WAKE_FLAG_MCU);
}
static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
{
int i = 0;
@@ -515,17 +476,6 @@ static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
char ip_str[20];
unsigned long status = 0;
/*
* Sticky early-return when we've previously concluded the firmware
* doesn't honor PSM. Each attempt would otherwise burn 5s on a
* doomed wait_for_completion_timeout and produce a noisy three-line
* cascade in dmesg every time power_down_work retries (every
* ~10s). The chip stays in active mode, which on this firmware is
* the de-facto state anyway.
*/
if (hw_priv->bes_power.pm_unsupported)
return -EOPNOTSUPP;
/* set interface low power configuration */
bes2600_for_each_vif(hw_priv, priv, i) {
#ifdef P2P_MULTIVIF
@@ -574,17 +524,7 @@ static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
bes_devel("%s, psMode:%s, fastPsmIdlePeriod:%d apPsmChangePeriod:%d minAutoPsPollPeriod:%d\n",
__func__, bes2600_get_ps_mode_str(priv->powersave_mode.pmMode), priv->powersave_mode.fastPsmIdlePeriod,
priv->powersave_mode.apPsmChangePeriod, priv->powersave_mode.minAutoPsPollPeriod);
/*
* Reinit BEFORE the WSM goes out, so a stale
* indication from a previous cycle cannot have
* primed pm_enter_cmpl. From here until the
* indication callback's cmpxchg(1->0) on
* pm_set_in_process, only the indication for
* THIS request can complete the wait.
*/
reinit_completion(&hw_priv->bes_power.pm_enter_cmpl);
atomic_set(&hw_priv->bes_power.pm_set_in_process, 1);
ret = bes2600_set_pm(priv, &priv->powersave_mode);
if (ret) {
atomic_set(&hw_priv->bes_power.pm_set_in_process, 0);
@@ -595,36 +535,11 @@ static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
/* wait power save mode changed indication */
status = wait_for_completion_timeout(&hw_priv->bes_power.pm_enter_cmpl, 5 * HZ);
atomic_set(&hw_priv->bes_power.pm_set_in_process, 0);
reinit_completion(&hw_priv->bes_power.pm_enter_cmpl);
if (!status) {
/*
* The indication callback only fires
* complete() when it observes
* pm_set_in_process == 1; cmpxchg it
* to 0 here so a late indication
* cannot prime the next wait.
*
* If we win the cmpxchg, this is a
* real timeout: the firmware's PS
* state is unknown to us. Mark it as
* such so the next wake path can
* probe before assuming the chip is
* still active.
*
* If we lose the cmpxchg, the
* indication arrived between the
* wait timing out and us getting
* here; treat as success.
*/
if (atomic_cmpxchg(&hw_priv->bes_power.pm_set_in_process,
1, 0) == 1) {
bes_devel("%s, wait pm ind timeout\n", __func__);
atomic_set(&hw_priv->bes_power.chip_pm_state,
BES2600_CHIP_PM_UNKNOWN);
timeouts++;
if (++hw_priv->bes_power.pm_consecutive_timeouts
>= BES2600_PM_UNSUPPORTED_THRESHOLD)
bes2600_pwr_latch_pm_unsupported(hw_priv);
}
}
} else {
bes_devel("skip enter lp mode\n");
@@ -639,35 +554,10 @@ static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
* in an inconsistent state that cascades into SDIO TX errors on
* the BES2600.
*/
if (timeouts == 0) {
if (timeouts == 0)
bes2600_pwr_device_enter_lp_mode(hw_priv);
} else {
/*
* device_enter_lp_mode() was skipped (one or more VIFs
* timed out waiting for the firmware indication) so its
* gpio_sleep(MCU) - which drops the wake-flag bit and, if
* no other subsystem holds the wake, drives the GPIO low -
* never ran. Without it the bit stays asserted, and the
* next bes2600_pwr_device_exit_lp_mode() calls
* gpio_wake(MCU) into a "bit already set" no-op: the GPIO
* never re-edges, sbus_active() exhausts its 200x2ms
* MCU_WAKEUP_READY budget against an unwoken chip, and
* the first TX after idle stalls for several seconds.
*
* Drop the MCU wake-flag bit explicitly here so the next
* wake injects a real GPIO edge. gpio_allow_mcu_sleep
* preserves multi-subsystem semantics: it only drives the
* GPIO low when no other subsystem still holds wake; if
* BT or another holder is keeping the chip awake, the
* GPIO stays high and the bit clear here is purely
* bookkeeping (so the next gpio_wake doesn't no-op).
*/
if (!hw_priv->bes_power.pm_unsupported &&
hw_priv->sbus_ops->gpio_sleep)
hw_priv->sbus_ops->gpio_sleep(hw_priv->sbus_priv,
GPIO_WAKE_FLAG_MCU);
else
ret = -ETIMEDOUT;
}
return ret;
}
@@ -675,61 +565,19 @@ static int bes2600_pwr_enter_lp_mode(struct bes2600_common *hw_priv)
static void bes2600_pwr_device_exit_lp_mode(struct bes2600_common *hw_priv)
{
int ret = 0;
enum bes2600_chip_pm_state state;
struct wsm_operational_mode mode = {
.power_mode = wsm_power_mode_active,
.disableMoreFlagUsage = true,
};
/*
* Consult chip_pm_state set by bes2600_pwr_notify_ps_changed().
* If we last saw the firmware confirm ACTIVE, skip ONLY the
* gpio_wake + sbus_active wake handshake - the GPIO is already
* asserted high and the SDIO MCU subsystem is already running,
* so another sbus_active() round-trip just hits its 200x2ms
* timeout because the firmware has nothing to do.
*
* wsm_set_operational_mode() below is NOT part of the wake
* handshake; it is the operational-mode setter the firmware
* tracks per call. Skipping it leaves the chip's SDIO state
* machine without a fresh operational-mode update, which on
* PineTab2 wedges the bus (-EBUSY on next sdio_rx_work read)
* within a few seconds of probe completion. So it must run
* unconditionally.
*/
state = atomic_read(&hw_priv->bes_power.chip_pm_state);
if (state == BES2600_CHIP_PM_ACTIVE) {
bes_devel("device_exit_lp_mode: chip already ACTIVE, skipping wake handshake\n");
} else {
bes_devel("host lock lmac\n");
if (hw_priv->sbus_ops->gpio_wake)
hw_priv->sbus_ops->gpio_wake(hw_priv->sbus_priv,
GPIO_WAKE_FLAG_MCU);
if(hw_priv->sbus_ops->gpio_wake)
hw_priv->sbus_ops->gpio_wake(hw_priv->sbus_priv, GPIO_WAKE_FLAG_MCU);
if (hw_priv->sbus_ops->sbus_active) {
ret = hw_priv->sbus_ops->sbus_active(hw_priv->sbus_priv,
SUBSYSTEM_MCU);
if (ret) {
/*
* MCU_WAKEUP_READY did not arrive within
* the SDIO handshake window. Record state
* as UNKNOWN so the next exit_lp_mode call
* also runs the full wake sequence (no
* skip), but still send operational_mode
* below to match pre-c6 behaviour - the
* WSM may succeed even if the SDIO active
* confirm was lost, and if it fails too,
* we just emit a second devel-level error.
* Repeated UNKNOWN is the signal for the
* LMAC active-monitor to eventually
* escalate to bus_reset (c5.2's
* mmc_hw_reset path).
*/
if(hw_priv->sbus_ops->sbus_active) {
ret = hw_priv->sbus_ops->sbus_active(hw_priv->sbus_priv, SUBSYSTEM_MCU);
if (ret)
bes_err("%s, active mcu fail\n", __func__);
atomic_set(&hw_priv->bes_power.chip_pm_state,
BES2600_CHIP_PM_UNKNOWN);
}
}
}
ret = wsm_set_operational_mode(hw_priv, &mode, 0);
@@ -985,9 +833,6 @@ void bes2600_pwr_init(struct bes2600_common *hw_priv)
hw_priv->bes_power.power_up_task = NULL;
mutex_init(&hw_priv->bes_power.pwr_mutex);
atomic_set(&hw_priv->bes_power.dev_state, 0);
atomic_set(&hw_priv->bes_power.chip_pm_state, BES2600_CHIP_PM_UNKNOWN);
hw_priv->bes_power.pm_unsupported = false;
hw_priv->bes_power.pm_consecutive_timeouts = 0;
init_completion(&hw_priv->bes_power.pm_enter_cmpl);
sema_init(&hw_priv->bes_power.sync_lock, 1);
device_set_wakeup_capable(hw_priv->pdev, true);
@@ -1368,40 +1213,9 @@ int bes2600_pwr_clear_busy_event(struct bes2600_common *hw_priv, u32 event)
void bes2600_pwr_notify_ps_changed(struct bes2600_common *hw_priv, u8 psmode)
{
/*
* The firmware sends a PM-changed indication for every transition,
* including ones we didn't ask for (firmware-internal coex moves,
* idle-driven aging). Update chip_pm_state unconditionally so the
* wake path can use it, but only fire pm_enter_cmpl when a host-
* initiated set_pm is actually in flight - otherwise a stale
* indication can prime a future wait against a freshly
* reinit_completion()'ed state.
*/
/*
* Any PM indication, whatever its psmode, proves the firmware is
* actually emitting them. Reset the consecutive-timeout counter
* so a transient stall doesn't permanently disable PSM, and clear
* pm_unsupported if a previous run had latched it.
*/
hw_priv->bes_power.pm_consecutive_timeouts = 0;
if (hw_priv->bes_power.pm_unsupported) {
bes_warn("PM indication arrived after pm_unsupported was set; re-enabling PSM transitions\n");
hw_priv->bes_power.pm_unsupported = false;
}
if ((psmode & 0x01) != WSM_PSM_ACTIVE) {
atomic_set(&hw_priv->bes_power.chip_pm_state,
BES2600_CHIP_PM_LP);
if (atomic_cmpxchg(&hw_priv->bes_power.pm_set_in_process,
1, 0) == 1) {
if((psmode & 0x01) != WSM_PSM_ACTIVE) {
bes_devel("complete pm_enter_cmpl\n");
complete(&hw_priv->bes_power.pm_enter_cmpl);
} else {
bes_devel("PM ind (LP) without pending wait; state recorded\n");
}
} else {
atomic_set(&hw_priv->bes_power.chip_pm_state,
BES2600_CHIP_PM_ACTIVE);
}
}
-24
View File
@@ -64,20 +64,6 @@ enum power_down_state
POWER_DOWN_STATE_UNLOCKED,
};
/*
* Confirmed PM state of the firmware-side chip. Tracks what the host
* has *seen* the firmware acknowledge, not what the host has
* requested. UNKNOWN means a host-initiated transition timed out
* before the firmware indication arrived; the next wake path should
* treat it as "we don't know" and probe before issuing GPIO/SDIO
* wakeup ops.
*/
enum bes2600_chip_pm_state {
BES2600_CHIP_PM_ACTIVE = 0,
BES2600_CHIP_PM_LP,
BES2600_CHIP_PM_UNKNOWN,
};
typedef void (*bes_pwr_enter_lp_cb)(struct bes2600_common *hw_priv);
typedef void (*bes_pwr_exit_lp_cb)(struct bes2600_common *hw_priv);
@@ -120,16 +106,6 @@ struct bes2600_pwr_t
bool ap_lp_bad;
struct bes2600_pwr_event_t pwr_events[BES2600_DELAY_EVENT_NUM];
atomic_t pm_set_in_process;
atomic_t chip_pm_state;
/*
* Sticky flag set after BES2600_PM_UNSUPPORTED_THRESHOLD
* consecutive enter_lp_mode timeouts with zero PM_INDICATIONs
* received from firmware. Indicates this chip's firmware does
* not honor host-driven PSM transitions; further attempts are
* skipped to avoid the 5s timeout cascade.
*/
bool pm_unsupported;
unsigned int pm_consecutive_timeouts;
};
#ifdef CONFIG_BES2600_WOWLAN
-4
View File
@@ -542,10 +542,6 @@ static int bes2600_status_show_priv(struct seq_file *seq, void *v)
priv->listening ? " (listening)" : "");
seq_printf(seq, "Assoc: %s\n",
bes2600_debug_join_status[priv->join_status]);
seq_printf(seq, "DecryptStormRecoveries: %u\n",
priv->decrypt_storm_recoveries);
seq_printf(seq, "ConnectionLossStormRecoveries: %u\n",
priv->connection_loss_storm_recoveries);
if (priv->rx_filter.promiscuous)
seq_puts(seq, "Filter: promisc\n");
else if (priv->rx_filter.fcs)
-2
View File
@@ -484,8 +484,6 @@ static struct ieee80211_hw *bes2600_init_common(size_t hw_priv_data_len)
spin_lock_init(&hw_priv->rtsvalue_lock);
INIT_WORK(&hw_priv->dynamic_opt_txrx_work, bes2600_dynamic_opt_txrx_work);
INIT_WORK(&hw_priv->tx_policy_upload_work, tx_policy_upload_work);
INIT_WORK(&hw_priv->connection_loss_storm_recover_work,
bes2600_connection_loss_storm_recover);
spin_lock_init(&hw_priv->event_queue_lock);
INIT_LIST_HEAD(&hw_priv->event_queue);
INIT_WORK(&hw_priv->event_handler, bes2600_event_handler);
+2 -15
View File
@@ -22,17 +22,9 @@
* After this many consecutive WSM scan rejections from firmware, stop
* issuing new scans for BES2600_SCAN_BACKOFF_JIFFIES and let the state
* that's rejecting them (coex window, firmware-internal busy) clear.
*
* The backoff has to be at least as long as the natural mac80211 scan-
* retry cadence, otherwise the next attempt lands outside the window
* and bypasses the defer guard. Observed in the wild on PineTab2:
* roam-evaluation bursts at ~12 s cadence, idle background scans at
* ~5 min cadence. 30 s catches the burst and leaves the slow case
* alone (the firmware-policy state has had minutes to clear by then
* anyway).
*/
#define BES2600_SCAN_REJECT_THRESHOLD 3
#define BES2600_SCAN_BACKOFF_JIFFIES (30 * HZ)
#define BES2600_SCAN_BACKOFF_JIFFIES (10 * HZ)
static void bes2600_scan_restart_delayed(struct bes2600_vif *priv);
@@ -48,9 +40,7 @@ static void bes2600_scan_restart_delayed(struct bes2600_vif *priv);
* 2. We already saw >= BES2600_SCAN_REJECT_THRESHOLD consecutive
* rejections on recent scan attempts and the backoff window has
* not yet elapsed. Whatever was rejecting them is likely still
* rejecting them; give it time. If the backoff has elapsed without
* a fresh reject refreshing it, the burst is over and we reset the
* count so an isolated reject doesn't immediately re-trip.
* rejecting them; give it time.
*
* Returns true if the caller should abandon the scan iteration.
*/
@@ -61,9 +51,6 @@ static bool bes2600_scan_should_defer(struct bes2600_common *hw_priv)
return true;
#endif
if (time_after(jiffies, hw_priv->scan.backoff_until))
hw_priv->scan.reject_count = 0;
if (hw_priv->scan.reject_count >= BES2600_SCAN_REJECT_THRESHOLD &&
time_before(jiffies, hw_priv->scan.backoff_until))
return true;
+2 -82
View File
@@ -266,7 +266,6 @@ void bes2600_stop(struct ieee80211_hw *dev, bool suspend)
cancel_work_sync(&hw_priv->coex_work);
coex_stop(hw_priv);
#endif
cancel_work_sync(&hw_priv->connection_loss_storm_recover_work);
bes2600_wifi_stop(hw_priv);
@@ -449,7 +448,6 @@ void bes2600_remove_interface(struct ieee80211_hw *dev,
cancel_delayed_work_sync(&priv->join_timeout);
cancel_delayed_work_sync(&priv->set_cts_work);
cancel_delayed_work_sync(&priv->pending_offchanneltx_work);
cancel_work_sync(&priv->decrypt_storm_recover_work);
del_timer_sync(&priv->mcast_timeout);
/* TODO:COMBO: May be reset of these variables "delayed_link_loss and
@@ -1660,70 +1658,6 @@ report:
spin_unlock(&priv->bss_loss_lock);
}
/*
* Connection-loss-storm fast-recover (Trigger A).
*
* bes2600_connection_loss_work below is the driver's own decision-point
* to give up on a BSS (after bss-loss detection accumulates beyond
* tolerance) and tell mac80211 via ieee80211_connection_loss(). On the
* deployed pinetab2 stack a single ieee80211_connection_loss() event
* sometimes triggers a userspace reauth blackhole (assoc-comeback
* timeouts followed by AP unprotected-deauth-reason-6) that ends only
* via cross-channel/cross-SSID fallback and can take 80+ s. Receipts at
* https://git.reauktion.de/marfrit/besser, notes/phase4-2026-05-07.md.
*
* When N connection-loss decisions land within WINDOW on the same vif,
* skip the ieee80211_connection_loss() path and trigger a chip-level
* bus_reset (the c5.2-introduced bes2600_chrdev_do_bus_reset). The chip
* is removed and re-probed; userspace re-associates from a fresh state,
* dodging the assoc-comeback loop.
*
* Threshold (3 / 60 s) is chosen well above the steady-state per-vif
* connection-loss rate observed in the patch-A Phase-7 rep
* (0.86/h under sustained load), so a true storm is required.
*
* The recover work_struct lives on bes2600_common (hw_priv) so that
* scheduling it does not race with vif teardown after bus_reset frees
* the per-vif state.
*/
#define BES2600_CONNECTION_LOSS_STORM_THRESHOLD 3
#define BES2600_CONNECTION_LOSS_STORM_WINDOW_MS 60000
void bes2600_connection_loss_storm_recover(struct work_struct *work)
{
bes_warn("[bes2600] connection-loss-storm fast-recover: bus_reset\n");
bes2600_chrdev_trigger_bus_reset();
/*
* After bes2600_chrdev_do_bus_reset() returns, the SDIO core has
* scheduled a remove + rescan; per-vif state may already be gone.
* Do not dereference any per-vif pointer here.
*/
}
void bes2600_connection_loss_storm_init(struct bes2600_vif *priv)
{
priv->connection_loss_storm_window_start = 0;
priv->connection_loss_storm_count = 0;
priv->connection_loss_storm_recoveries = 0;
}
bool bes2600_connection_loss_storm_account(struct bes2600_vif *priv)
{
unsigned long now = jiffies;
unsigned long window =
msecs_to_jiffies(BES2600_CONNECTION_LOSS_STORM_WINDOW_MS);
if (priv->connection_loss_storm_window_start == 0 ||
time_after(now, priv->connection_loss_storm_window_start + window)) {
priv->connection_loss_storm_window_start = now;
priv->connection_loss_storm_count = 1;
return false;
}
return ++priv->connection_loss_storm_count >=
BES2600_CONNECTION_LOSS_STORM_THRESHOLD;
}
void bes2600_connection_loss_work(struct work_struct *work)
{
struct bes2600_vif *priv =
@@ -1733,21 +1667,9 @@ void bes2600_connection_loss_work(struct work_struct *work)
bes_devel("[CQM] Reporting connection loss.\n");
bes2600_pwr_clear_busy_event(priv->hw_priv, BES_PWR_LOCK_ON_BSS_LOST);
if (bes2600_connection_loss_storm_account(priv)) {
bes_warn("[bes2600] connection-loss storm: %u in %u s, scheduling bus reset\n",
priv->connection_loss_storm_count,
BES2600_CONNECTION_LOSS_STORM_WINDOW_MS / 1000);
priv->connection_loss_storm_count = 0;
priv->connection_loss_storm_recoveries++;
schedule_work(&hw_priv->connection_loss_storm_recover_work);
/* bus_reset will tear the chip down; skip the mac80211 path. */
return;
}
if (bes2600_suspend_status_get(hw_priv))
if(bes2600_suspend_status_get(hw_priv)) {
bes2600_pending_unjoin_set(hw_priv, priv->if_id);
else
} else
ieee80211_connection_loss(priv->vif);
#ifdef WIFI_BT_COEXIST_EPTA_ENABLE
// set disconnected in BSS_CHANGED_ASSOC
@@ -2697,8 +2619,6 @@ int bes2600_vif_setup(struct bes2600_vif *priv)
/* Setup per vif workitems and locks */
spin_lock_init(&priv->vif_lock);
bes2600_decrypt_storm_init(priv);
bes2600_connection_loss_storm_init(priv);
INIT_WORK(&priv->join_work, bes2600_join_work);
INIT_DELAYED_WORK(&priv->join_timeout, bes2600_join_timeout);
INIT_WORK(&priv->unjoin_work, bes2600_unjoin_work);
-74
View File
@@ -25,78 +25,6 @@
#define BES2600_INVALID_RATE_ID (0xFF)
/*
* Decrypt-storm fast-recover (Trigger B).
*
* When the BES2600 firmware reports WSM_STATUS_DECRYPTFAILURE for a
* burst of received frames (typically because the host's PTK or GTK
* has fallen out of sync with the AP), the AP eventually concludes that
* the STA is not authenticated and emits an unprotected deauth-reason-6
* ("Class 2 frame received from non-authenticated station"). On the
* deployed pinetab2 + bes2600 stack this AP-initiated deauth has been
* observed to leave the link blackholed for up to 109 s before
* userspace finds a different SSID/channel to recover on. (Receipts at
* https://git.reauktion.de/marfrit/besser, notes/phase5-2026-05-06.md.)
*
* Recovery here pre-empts the AP: when we see THRESHOLD decrypt
* failures within WINDOW, we ask mac80211 for a clean reassoc via
* ieee80211_connection_loss(), which causes immediate disassociation
* and lets userspace auto-reconnect with fresh keys.
*
* mac80211 contract: ieee80211_connection_loss() may be called
* regardless of IEEE80211_HW_CONNECTION_MONITOR; it causes immediate
* disassociation without driver-side recovery attempts. See
* include/net/mac80211.h for the canonical doc-comment.
*
* The threshold is set well above the steady-state per-vif
* decrypt-fail rate observed in measurement (~1/min even under
* sustained 1 MB/s load), so a true storm is required to trip it.
*/
#define BES2600_DECRYPT_STORM_THRESHOLD 5
#define BES2600_DECRYPT_STORM_WINDOW_MS 5000
static void bes2600_decrypt_storm_recover_work(struct work_struct *work)
{
struct bes2600_vif *priv = container_of(work, struct bes2600_vif,
decrypt_storm_recover_work);
if (!priv->vif)
return;
bes_warn("[bes2600] decrypt-storm fast-recover: forcing reassoc\n");
ieee80211_connection_loss(priv->vif);
priv->decrypt_storm_recoveries++;
}
void bes2600_decrypt_storm_init(struct bes2600_vif *priv)
{
INIT_WORK(&priv->decrypt_storm_recover_work,
bes2600_decrypt_storm_recover_work);
priv->decrypt_storm_window_start = 0;
priv->decrypt_storm_count = 0;
priv->decrypt_storm_recoveries = 0;
}
void bes2600_decrypt_storm_account(struct bes2600_vif *priv)
{
unsigned long now = jiffies;
unsigned long window = msecs_to_jiffies(BES2600_DECRYPT_STORM_WINDOW_MS);
if (priv->decrypt_storm_window_start == 0 ||
time_after(now, priv->decrypt_storm_window_start + window)) {
priv->decrypt_storm_window_start = now;
priv->decrypt_storm_count = 1;
return;
}
if (++priv->decrypt_storm_count >= BES2600_DECRYPT_STORM_THRESHOLD) {
priv->decrypt_storm_count = 0;
/* Skew the window so we don't re-fire on the same storm. */
priv->decrypt_storm_window_start = now + window;
schedule_work(&priv->decrypt_storm_recover_work);
}
}
#ifdef CONFIG_BES2600_TESTMODE
#include "bes_nl80211_testmode_msg.h"
#endif /* CONFIG_BES2600_TESTMODE */
@@ -1744,8 +1672,6 @@ void bes2600_rx_cb(struct bes2600_vif *priv,
goto drop;
} else {
bes_warn("[RX] Receive failure: %d.\n", arg->status);
if (arg->status == WSM_STATUS_DECRYPTFAILURE)
bes2600_decrypt_storm_account(priv);
goto drop;
}
}