Alternate ath9k and ath10k radio reset for deaf nodes (#857)

* A scan, especially if we have to do both active and passive, essentially mutes
the radio to AREDN traffic for 10-20 seconds, which isn't good. If the radio is completely
deaf then it doesn't matter, but particularly on the 9K radios we do this when
things are looking a bit dodgy, though not deaf. 
* Provide hook to reset ath9k from userspace.  This hook is attributed to:
Linus Lüssing <ll@simonwunderlich.de>
* User /sys reset hooks rather than iw scan

files/usr/local/bin/mgr/rssi_monitor_ath10k.lua

@@ -33,10 +33,9 @@
 
 --]]
 
-local periodic_scan_time = 300 -- 5 minutes
+local periodic_scan_tick = 5
 
 local wifiiface
-local last_scan_time = 0
 
 function rssi_monitor_10k()
     if not string.match(get_ifname("wifi"), "^wlan") then
@@ -67,9 +66,13 @@ if not file_exists(logfile) then
     io.open(logfile, "w+"):close()
 end
 
-local last_station_count = 0
+local station_zero = 0
 local log = aredn.log.open(logfile, 16000)
 
+local function reset_network()
+    write_all("/sys/kernel/debug/ieee80211/" .. phy .. "/ath10k/simulate_fw_crash", "hw-restart")
+end
+
 function run_monitor_10k()
 
     local station_count = 0
@@ -79,15 +82,16 @@ function run_monitor_10k()
         station_count = station_count + 1
     end
 
-    if station_count == 0 and (last_station_count ~= 0 or nixio.sysinfo().uptime > periodic_scan_time + last_scan_time) then
-         -- reset
-         last_scan_time = nixio.sysinfo().uptime
-         os.execute("/usr/sbin/iw " .. wifiiface .. " scan > /dev/null 2>&1")
-         os.execute("/usr/sbin/iw " .. wifiiface .. " scan passive > /dev/null 2>&1")
-         log:write("No stations detected")
-         log:flush()
+    if station_count ~= 0 then
+        station_zero = periodic_scan_tick - 1
+    else
+        station_zero = station_zero + 1
+        if math.mod(station_zero, periodic_scan_tick) == 0 then
+            reset_network()
+            log:write("No stations detected")
+            log:flush()
+        end
     end
-    last_station_count = station_count
 end
 
 return rssi_monitor_10k

files/usr/local/bin/mgr/rssi_monitor_ath9k.lua

@@ -75,9 +75,14 @@ if not file_exists(logfile) then
     io.open(logfile, "w+"):close()
 end
 
-local last_station_count = 0
+local station_zero = 0
+local periodic_scan_tick = 5
 local log = aredn.log.open(logfile, 16000)
 
+local function reset_network()
+    write_all("/sys/kernel/debug/ieee80211/" .. phy .. "/ath9k/reset", "1")
+end
+
 function run_monitor_9k()
 
     local now = nixio.sysinfo().uptime
@@ -105,13 +110,6 @@ function run_monitor_9k()
         end
     end
     local amac = nil
-
-    -- avoid node going deaf while trying to obtain 'normal' statistics of neighbor strength
-    -- in first few minutes after boot
-    if now > 119 and now < 750 then
-        os.execute("/usr/sbin/iw " .. wifiiface .. " scan > /dev/null 2>&1")
-    end
-
     local station_count = 0
     local rssi = get_rssi(wifiiface)
     for mac, info in pairs(rssi)
@@ -166,9 +164,7 @@ function run_monitor_9k()
     end
 
     if amac then
-        -- reset
-        os.execute("/usr/sbin/iw " .. wifiiface .. " scan > /dev/null 2>&1")
-        os.execute("/usr/sbin/iw " .. wifiiface .. " scan passive > /dev/null 2>&1")
+        reset_network()
         wait_for_ticks(5)
         -- update time
         now = nixio.sysinfo().uptime
@@ -202,13 +198,18 @@ function run_monitor_9k()
                 rssih.num = rssih.num + 1
             end
         end
-    elseif station_count == 0 and last_station_count ~= 0 then
-         -- reset
-         os.execute("/usr/sbin/iw " .. wifiiface .. " scan > /dev/null 2>&1")
-         wait_for_ticks(5)
-         log:write("No stations detected")
+    else
+        if station_count ~= 0 then
+            station_zero = periodic_scan_tick - 1
+        else
+            station_zero = station_zero + 1
+            if math.mod(station_zero, periodic_scan_tick) == 0 then
+                reset_network()
+                wait_for_ticks(5)
+                log:write("No stations detected")
+            end
+        end
     end
-    last_station_count = station_count
 
     local f = io.open(datfile, "w")
     if f then

files/usr/local/bin/mgr/station_monitor.lua

@@ -51,7 +51,6 @@ local log = aredn.log.open(logfile, 8000)
 
 function rejoin_network()
     os.execute(IW .. " " .. wifiiface .. " ibss leave")
-    nixio.nanosleep(1, 0)
     os.execute(IW .. " " .. wifiiface .. " ibss join " .. ssid .. " " .. frequency .. " fixed-freq")
     log:write("Rejoining network")
     log:flush()

patches/701-ath9k-reset.patch

@@ -0,0 +1,99 @@
+--- /dev/null
++++ b/package/kernel/mac80211/patches/ath/301-ath-reset.patch
+@@ -0,0 +1,96 @@
++diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
++index 4c81b1d7f417..fb7a2952d0ce 100644
++--- a/drivers/net/wireless/ath/ath9k/debug.c
+++++ b/drivers/net/wireless/ath/ath9k/debug.c
++@@ -749,9 +749,9 @@  static int read_file_misc(struct seq_file *file, void *data)
++ 
++ static int read_file_reset(struct seq_file *file, void *data)
++ {
++-	struct ieee80211_hw *hw = dev_get_drvdata(file->private);
++-	struct ath_softc *sc = hw->priv;
+++	struct ath_softc *sc = file->private;
++ 	static const char * const reset_cause[__RESET_TYPE_MAX] = {
+++		[RESET_TYPE_USER] = "User reset",
++ 		[RESET_TYPE_BB_HANG] = "Baseband Hang",
++ 		[RESET_TYPE_BB_WATCHDOG] = "Baseband Watchdog",
++ 		[RESET_TYPE_FATAL_INT] = "Fatal HW Error",
++@@ -779,6 +779,55 @@  static int read_file_reset(struct seq_file *file, void *data)
++ 	return 0;
++ }
++ 
+++static int open_file_reset(struct inode *inode, struct file *f)
+++{
+++	return single_open(f, read_file_reset, inode->i_private);
+++}
+++
+++static ssize_t write_file_reset(struct file *file,
+++				const char __user *user_buf,
+++				size_t count, loff_t *ppos)
+++{
+++	struct ath_softc *sc = file_inode(file)->i_private;
+++	struct ath_hw *ah = sc->sc_ah;
+++	struct ath_common *common = ath9k_hw_common(ah);
+++	unsigned long val;
+++	char buf[32];
+++	ssize_t len;
+++
+++	len = min(count, sizeof(buf) - 1);
+++	if (copy_from_user(buf, user_buf, len))
+++		return -EFAULT;
+++
+++	buf[len] = '\0';
+++	if (kstrtoul(buf, 0, &val))
+++		return -EINVAL;
+++
+++	if (val != 1)
+++		return -EINVAL;
+++
+++	/* avoid rearming hw_reset_work on shutdown */
+++	mutex_lock(&sc->mutex);
+++	if (test_bit(ATH_OP_INVALID, &common->op_flags)) {
+++		mutex_unlock(&sc->mutex);
+++		return -EBUSY;
+++	}
+++
+++	ath9k_queue_reset(sc, RESET_TYPE_USER);
+++	mutex_unlock(&sc->mutex);
+++
+++	return count;
+++}
+++
+++static const struct file_operations fops_reset = {
+++	.read = seq_read,
+++	.write = write_file_reset,
+++	.open = open_file_reset,
+++	.owner = THIS_MODULE,
+++	.llseek = seq_lseek,
+++	.release = single_release,
+++};
+++
++ void ath_debug_stat_tx(struct ath_softc *sc, struct ath_buf *bf,
++ 		       struct ath_tx_status *ts, struct ath_txq *txq,
++ 		       unsigned int flags)
++@@ -1393,8 +1442,8 @@  int ath9k_init_debug(struct ath_hw *ah)
++ 				    read_file_queues);
++ 	debugfs_create_devm_seqfile(sc->dev, "misc", sc->debug.debugfs_phy,
++ 				    read_file_misc);
++-	debugfs_create_devm_seqfile(sc->dev, "reset", sc->debug.debugfs_phy,
++-				    read_file_reset);
+++	debugfs_create_file("reset", 0600, sc->debug.debugfs_phy,
+++			    sc, &fops_reset);
++ 
++ 	ath9k_cmn_debug_recv(sc->debug.debugfs_phy, &sc->debug.stats.rxstats);
++ 	ath9k_cmn_debug_phy_err(sc->debug.debugfs_phy, &sc->debug.stats.rxstats);
++diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h
++index 33826aa13687..389459c04d14 100644
++--- a/drivers/net/wireless/ath/ath9k/debug.h
+++++ b/drivers/net/wireless/ath/ath9k/debug.h
++@@ -39,6 +39,7 @@  struct fft_sample_tlv;
++ #endif
++ 
++ enum ath_reset_type {
+++	RESET_TYPE_USER,
++ 	RESET_TYPE_BB_HANG,
++ 	RESET_TYPE_BB_WATCHDOG,
++ 	RESET_TYPE_FATAL_INT,
++

patches/series

@@ -2,6 +2,7 @@
 001-ath79-cpe220v3-sysupgrade-supported.patch
 001-ath79-reverse-wpad-basic-wolfssl.patch
 006-rocket-m-flash-fix.patch
+701-ath9k-reset.patch
 701-extended-spectrum.patch
 702-enable-country-hx.patch
 703-fix-dnsmasq.patch