fix(sway): only force a post-resume modeset when the stall is actually present

recover-output-after-resume.sh existed to work around the old ThinkPad's
/etc/modprobe.d/i915.conf, which forced PSR2 and the deepest display
C-states; the flip pending across suspend never completed, so every later
commit returned EBUSY and only a full modeset cleared it.

That file is gone and this laptop's iGPU is driven by `xe` (Panther Lake has
no i915 support at all), so the original cause cannot recur. The modeset is
now conditional on the user journal actually reporting "Atomic commit
failed"/"Page-flip failed" within the last 3 minutes.

Unconditional disable/enable + `shikanectl reload` on every resume was itself
a hazard: it is the exact sequence that re-triggers the shikane
VariantInProgress deadlock the watchdog exists to recover from.

hypridle.conf's comment no longer references the deleted i915.conf.

.config/hypr/hypridle.conf

@@ -1,34 +1,48 @@
+# Idle / lock for SWAY (wlroots), not Hyprland.
+#
+# Two things in the original Hyprland template silently did nothing under sway:
+#   * `loginctl lock-session`  -> sway implements no freedesktop login1 Session
+#                                 Lock protocol, so it is a no-op. Lock directly.
+#   * `hyprctl dispatch dpms`  -> "HYPRLAND_INSTANCE_SIGNATURE not set!".
+#                                 Use `swaymsg "output * power on|off"`.
+# Also: a hyprlock instance can outlive a sway session and then make the
+# `pidof hyprlock || hyprlock` guard a permanent no-op; the sway config kills
+# leftovers at login (`exec --no-startup-id pkill -x hyprlock`).
+
 general {
-    lock_cmd = pidof hyprlock || hyprlock       # avoid starting multiple hyprlock instances.
+    lock_cmd = pidof hyprlock || hyprlock
-    before_sleep_cmd = loginctl lock-session    # lock before suspend.
+    # pre-suspend uses swaylock: fast, sway-native, exits cleanly (no leak)
-    after_sleep_cmd = hyprctl dispatch dpms on  # to avoid having to press a key twice to turn on the display.
+    before_sleep_cmd = swaylock -f -c 000000
+    # DPMS "power on" alone does not clear a post-resume eDP page-flip stall
+    # ("Atomic commit failed: Device or resource busy" for tens of minutes).
+    # The script does a full disable/enable (forced modeset) but ONLY when the
+    # journal actually shows the stall -- it used to fire unconditionally, which
+    # risked the shikane VariantInProgress deadlock on healthy resumes. The
+    # original i915 PSR2/DC4 cause is gone; this laptop uses the `xe` driver.
+    # Lid-aware so it does not race shikane's "External Display" profile.
+    after_sleep_cmd = /home/work/.config/sway/scripts/recover-output-after-resume.sh
 }
 
 listener {
-    timeout = 150                                # 2.5min.
+    timeout = 150                                # 2.5min
-    on-timeout = brightnessctl -s set 10         # set monitor backlight to minimum, avoid 0 on OLED monitor.
+    on-timeout = brightnessctl -s set 10
-    on-resume = brightnessctl -r                 # monitor backlight restore.
+    on-resume = brightnessctl -r
 }
 
-# turn off keyboard backlight, comment out this section if you dont have a keyboard backlight.
+# keyboard backlight
-listener { 
+listener {
-    timeout = 150                                          # 2.5min.
+    timeout = 150
-    on-timeout = brightnessctl -sd rgb:kbd_backlight set 0 # turn off keyboard backlight.
+    on-timeout = brightnessctl -sd rgb:kbd_backlight set 0
-    on-resume = brightnessctl -rd rgb:kbd_backlight        # turn on keyboard backlight.
+    on-resume = brightnessctl -rd rgb:kbd_backlight
 }
 
 listener {
-    timeout = 300                                 # 5min
+    timeout = 300                                # 5min -> lock
-    on-timeout = loginctl lock-session            # lock screen when timeout has passed
+    on-timeout = pidof hyprlock || hyprlock
 }
 
 listener {
-    timeout = 330                                                     # 5.5min
+    timeout = 330                                # 5.5min -> output power off
-    on-timeout = hyprctl dispatch dpms off                            # screen off when timeout has passed
+    on-timeout = swaymsg "output * power off"
-    on-resume = hyprctl dispatch dpms on && brightnessctl -r          # screen on when activity is detected after timeout has fired.
+    on-resume = swaymsg "output * power on" && brightnessctl -r
-}
-
-listener {
-    timeout = 1800                                # 30min
-    on-timeout = systemctl suspend                # suspend pc
 }

.config/sway/scripts/recover-output-after-resume.sh

@@ -0,0 +1,60 @@
+#!/bin/sh
+# recover-output-after-resume -- clear a post-resume eDP page-flip stall.
+#
+# Symptom (see journalctl --user --since -5m | grep 'Atomic commit failed'):
+#   [wlr] backend/drm/atomic.c:82 connector eDP-1: Atomic commit failed:
+#         Device or resource busy
+#   [sway] desktop/output.c:307 Page-flip failed on output eDP-1
+# ...repeatedly for tens of minutes after a resume.
+#
+# HISTORY: this was originally a workaround for the old ThinkPad's
+# /etc/modprobe.d/i915.conf, which forced PSR2 and the deepest display C-states
+# (options i915 enable_guc=3 enable_psr=2 enable_dc=4 enable_rc6=1 -- both of
+# which taint the kernel). With PSR2 forced on, the flip pending across suspend
+# never completed, so every later commit returned EBUSY, and DPMS "power on"
+# alone did not clear it -- only a full modeset did.
+#
+# STATUS: that file is gone. This machine is a Framework Laptop 13 Pro whose
+# iGPU is driven by `xe` (Panther Lake has no i915 support at all), so the
+# original cause cannot recur. The modeset below is therefore CONDITIONAL and
+# only fires when the stall is actually present in the journal.
+#
+# Why conditional: an unconditional disable/enable plus `shikanectl reload`
+# after every resume is exactly the sequence that re-triggers the shikane
+# 1.1.1 VariantInProgress deadlock (see shikane-watchdog.sh). No point paying
+# that risk on resumes that are already healthy.
+#
+# Lid-aware on purpose: a blind `output eDP-1 enable` raced shikane's
+# "External Display" profile (which keeps eDP-1 off) and caused
+# "Atomic commit failed: Device or resource busy" churn in clamshell mode.
+# See the note in clamshell-mode.sh.
+
+set -u
+
+LID_STATE="${LID_STATE:-/proc/acpi/button/lid/LID/state}"
+OUTPUT="${OUTPUT:-eDP-1}"
+
+# Always undo the idle DPMS-off first (this is what after_sleep_cmd used to do).
+swaymsg "output * power on" 2>/dev/null
+
+# Only escalate to a modeset if the page-flip stall is actually being reported.
+# sway runs inside the user session, so its stderr is in the user journal.
+if command -v journalctl >/dev/null 2>&1; then
+    if ! journalctl --user --since '-3 min' --no-pager 2>/dev/null \
+        | grep -qE 'Atomic commit failed|Page-flip failed on output'; then
+        exit 0        # healthy resume -> do not disturb shikane
+    fi
+fi
+
+# The modeset below is lid-gated only.
+[ -r "$LID_STATE" ] || exit 0
+grep -q 'open' "$LID_STATE" || exit 0   # lid closed -> leave layout to shikane
+
+# Give the driver a moment to finish re-training the link before we modeset.
+sleep 1
+swaymsg "output $OUTPUT disable" 2>/dev/null
+sleep 1
+swaymsg "output $OUTPUT enable"  2>/dev/null
+# Re-assert the shikane profile (mode/scale/position) on top of the modeset.
+command -v shikanectl >/dev/null 2>&1 && shikanectl reload 2>/dev/null
+exit 0