| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sun, 11 Sep 2022 23:28:50 -0600
From: Jim Cromie <jim.cromie@...il.com>
To: jbaron@...mai.com, gregkh@...uxfoundation.org,
dri-devel@...ts.freedesktop.org, amd-gfx@...ts.freedesktop.org,
intel-gvt-dev@...ts.freedesktop.org,
intel-gfx@...ts.freedesktop.org, linux-kernel@...r.kernel.org
Cc: daniel.vetter@...ll.ch, seanpaul@...omium.org, robdclark@...il.com,
linux@...musvillemoes.dk, joe@...ches.com,
Jim Cromie <jim.cromie@...il.com>
Subject: [PATCH v7 7/9] drm_print: optimize drm_debug_enabled for jump-label
When CONFIG_DRM_USE_DYNAMIC_DEBUG=y, the drm.debug API (a macro stack,
calling _+drm_*dbg() eventually) invokes a dyndbg Factory macro to
create a descriptor for each callsite, thus making them individually
>control-able.
In this case, the calls to _drm_*dbg are unreachable unless the
callsite is enabled. So those calls can short-circuit their early
do-nothing returns. Provide and use __drm_debug_enabled(), to do this
when config'd, or the _raw flags-check otherwize.
And since dyndbg is in use, lets also instrument the remaining users
of drm_debug_enabled, by wrapping the _raw in a macro with a:
pr_debug("todo: is this frequent enough to optimize ?\n");
For CONFIG_DRM_USE_DYNAMIC_DEBUG=n, do no site instrumenting at all,
since JUMP_LABEL might be off, and we don't want to make work.
With drm, amdgpu, i915, nouveau loaded, heres remaining uses of
drm_debug_enabled(), which costs ~1.5kb data to control the
pr_debug("todo:..")s.
Some of those uses might be ok to use __drm_debug_enabled() by
inspection, others might warrant conversion to use dyndbg Factory
macros, and that would want callrate data to estimate the savings
possible. TBH, any remaining savings are probably small; drm.debug
covers the vast bulk of the uses. Maybe "vblank" is the exception.
:#> grep todo /proc/dynamic_debug/control | wc
21 168 2357
:#> grep todo /proc/dynamic_debug/control
drivers/gpu/drm/drm_edid_load.c:178 [drm]edid_load =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/drm_vblank.c:410 [drm]drm_crtc_accurate_vblank_count =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/drm_vblank.c:787 [drm]drm_crtc_vblank_helper_get_vblank_timestamp_internal =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/drm_vblank.c:1491 [drm]drm_vblank_restore =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/drm_vblank.c:1433 [drm]drm_vblank_enable =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/drm_plane.c:2168 [drm]drm_mode_setplane =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/display/drm_dp_mst_topology.c:1359 [drm_display_helper]drm_dp_mst_wait_tx_reply =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/display/drm_dp_mst_topology.c:2864 [drm_display_helper]process_single_tx_qlock =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/display/drm_dp_mst_topology.c:2909 [drm_display_helper]drm_dp_queue_down_tx =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/display/drm_dp_mst_topology.c:1686 [drm_display_helper]drm_dp_mst_update_slots =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_dp.c:1111 [i915]intel_dp_print_rates =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_backlight.c:5434 [i915]cnp_enable_backlight =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_backlight.c:5459 [i915]intel_backlight_device_register =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_opregion.c:43 [i915]intel_opregion_notify_encoder =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_opregion.c:53 [i915]asle_set_backlight =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_bios.c:1088 [i915]intel_bios_is_dsi_present =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/display/intel_display_debugfs.c:6153 [i915]i915_drrs_ctl_set =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/intel_pcode.c:26 [i915]snb_pcode_read =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/i915/i915_getparam.c:785 [i915]i915_getparam_ioctl =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c:282 [amdgpu]vcn_v2_5_process_interrupt =_ "todo: maybe avoid via dyndbg\n"
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c:433 [amdgpu]vcn_v2_0_process_interrupt =_ "todo: maybe avoid via dyndbg\n"
:#>
Signed-off-by: Jim Cromie <jim.cromie@...il.com>
---
- simplify drm-debug-enabled choices, @DanVet
---
drivers/gpu/drm/drm_print.c | 4 ++--
include/drm/drm_print.h | 21 ++++++++++++++++++++-
2 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 29a29949ad0b..cb203d63b286 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -285,7 +285,7 @@ void __drm_dev_dbg(const struct device *dev, enum drm_debug_category category,
struct va_format vaf;
va_list args;
- if (!drm_debug_enabled(category))
+ if (!__drm_debug_enabled(category))
return;
va_start(args, format);
@@ -308,7 +308,7 @@ void ___drm_dbg(enum drm_debug_category category, const char *format, ...)
struct va_format vaf;
va_list args;
- if (!drm_debug_enabled(category))
+ if (!__drm_debug_enabled(category))
return;
va_start(args, format);
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index dfdd81c3287c..9af57d3df259 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -321,11 +321,30 @@ enum drm_debug_category {
DRM_UT_DRMRES
};
-static inline bool drm_debug_enabled(enum drm_debug_category category)
+static inline bool drm_debug_enabled_raw(enum drm_debug_category category)
{
return unlikely(__drm_debug & BIT(category));
}
+#define drm_debug_enabled_instrumented(category) \
+ ({ \
+ pr_debug("todo: is this frequent enough to optimize ?\n"); \
+ drm_debug_enabled_raw(category); \
+ })
+
+#if defined(CONFIG_DRM_USE_DYNAMIC_DEBUG)
+/*
+ * the drm.debug API uses dyndbg, so each drm_*dbg macro/callsite gets
+ * a descriptor, and only enabled callsites are reachable. They use
+ * the private macro to avoid re-testing the enable-bit.
+ */
+#define __drm_debug_enabled(category) true
+#define drm_debug_enabled(category) drm_debug_enabled_instrumented(category)
+#else
+#define __drm_debug_enabled(category) drm_debug_enabled_raw(category)
+#define drm_debug_enabled(category) drm_debug_enabled_raw(category)
+#endif
+
/*
* struct device based logging
*
--
2.37.3
Powered by blists - more mailing lists