From: Chris Wilson <chris(a)chris-wilson.co.uk>
If we park/unpark faster than we can respond to RPS events, we never
will process a downclock event after expiring a waitboost, and thus we
will forever restart the GPU at max clocks even if the workload switches
and doesn't justify full power.
Closes: https://gitlab.freedesktop.org/drm/intel/issues/1500
Fixes: 3e7abf814193 ("drm/i915: Extract GT render power state management")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Andi Shyti <andi.shyti(a)intel.com>
Cc: Lyude Paul <lyude(a)redhat.com>
Reviewed-by: Andi Shyti <andi.shyti(a)intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200322163225.28791-1-chris@…
Cc: <stable(a)vger.kernel.org> # v5.5+
(cherry picked from commit 21abf0bf168dffff1192e0f072af1dc74ae1ff0e)
---
drivers/gpu/drm/i915/gt/intel_rps.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index 6beaa2b4e8f7..32ccb4efb0d9 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -768,6 +768,19 @@ void intel_rps_park(struct intel_rps *rps)
intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
rps_set(rps, rps->idle_freq, false);
intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);
+
+ /*
+ * Since we will try and restart from the previously requested
+ * frequency on unparking, treat this idle point as a downclock
+ * interrupt and reduce the frequency for resume. If we park/unpark
+ * more frequently than the rps worker can run, we will not respond
+ * to any EI and never see a change in frequency.
+ *
+ * (Note we accommodate Cherryview's limitation of only using an
+ * even bin by applying it to all.)
+ */
+ rps->cur_freq =
+ max_t(int, round_down(rps->cur_freq - 1, 2), rps->min_freq);
}
void intel_rps_boost(struct i915_request *rq)
From: Chris Wilson <chris(a)chris-wilson.co.uk>
If we use a non-forcewaked write to PMINTRMSK, it does not take effect
until much later, if at all, causing a loss of RPS interrupts and no GPU
reclocking, leaving the GPU running at the wrong frequency for long
periods of time.
Reported-by: Francisco Jerez <currojerez(a)riseup.net>
Suggested-by: Francisco Jerez <currojerez(a)riseup.net>
Fixes: 35cc7f32c298 ("drm/i915/gt: Use non-forcewake writes for RPS")
Signed-off-by: Chris Wilson <chris(a)chris-wilson.co.uk>
Cc: Francisco Jerez <currojerez(a)riseup.net>
Cc: Mika Kuoppala <mika.kuoppala(a)linux.intel.com>
Cc: Andi Shyti <andi.shyti(a)intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala(a)linux.intel.com>
Reviewed-by: Andi Shyti <andi.shyti(a)intel.com>
Reviewed-by: Francisco Jerez <currojerez(a)riseup.net>
Cc: <stable(a)vger.kernel.org> # v5.6+
Link: https://patchwork.freedesktop.org/patch/msgid/20200415170318.16771-2-chris@…
(cherry picked from commit a080bd994c4023042a2b605c65fa10a25933f636)
---
drivers/gpu/drm/i915/gt/intel_rps.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
index c1a3d360de06..6beaa2b4e8f7 100644
--- a/drivers/gpu/drm/i915/gt/intel_rps.c
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -85,7 +85,8 @@ static void rps_enable_interrupts(struct intel_rps *rps)
gen6_gt_pm_enable_irq(gt, rps->pm_events);
spin_unlock_irq(>->irq_lock);
- set(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->cur_freq));
+ intel_uncore_write(gt->uncore,
+ GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq));
}
static void gen6_rps_reset_interrupts(struct intel_rps *rps)
@@ -119,7 +120,8 @@ static void rps_disable_interrupts(struct intel_rps *rps)
rps->pm_events = 0;
- set(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
+ intel_uncore_write(gt->uncore,
+ GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u));
spin_lock_irq(>->irq_lock);
gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
The patch titled
Subject: sh: include linux/time_types.h for sockios
has been added to the -mm tree. Its filename is
sh-include-linux-time_typesh-for-sockios.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/sh-include-linux-time_typesh-for-s…
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/sh-include-linux-time_typesh-for-s…
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Arnd Bergmann <arnd(a)arndb.de>
Subject: sh: include linux/time_types.h for sockios
Using the socket ioctls on arch/sh (and only there) causes build time
problems when __kernel_old_timeval/__kernel_old_timespec are not already
visible to the compiler.
Add an explict include line for the header that defines these
structures.
Link: http://lkml.kernel.org/r/20200519131327.1836482-1-arnd@arndb.de
Signed-off-by: Arnd Bergmann <arnd(a)arndb.de>
Reported-by: John Paul Adrian Glaubitz <glaubitz(a)physik.fu-berlin.de>
Tested-by: John Paul Adrian Glaubitz <glaubitz(a)physik.fu-berlin.de>
Fixes: 8c709f9a0693 ("y2038: sh: remove timeval/timespec usage from headers")
Fixes: 0768e17073dc ("net: socket: implement 64-bit timestamps")
Cc: Yoshinori Sato <ysato(a)users.sourceforge.jp>
Cc: Rich Felker <dalias(a)libc.org>
Cc: "David S. Miller" <davem(a)davemloft.net>
Cc: John Paul Adrian Glaubitz <glaubitz(a)physik.fu-berlin.de>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
arch/sh/include/uapi/asm/sockios.h | 2 ++
1 file changed, 2 insertions(+)
--- a/arch/sh/include/uapi/asm/sockios.h~sh-include-linux-time_typesh-for-sockios
+++ a/arch/sh/include/uapi/asm/sockios.h
@@ -2,6 +2,8 @@
#ifndef __ASM_SH_SOCKIOS_H
#define __ASM_SH_SOCKIOS_H
+#include <linux/time_types.h>
+
/* Socket-level I/O control calls. */
#define FIOGETOWN _IOR('f', 123, int)
#define FIOSETOWN _IOW('f', 124, int)
_
Patches currently in -mm which might be from arnd(a)arndb.de are
sh-include-linux-time_typesh-for-sockios.patch
drm-remove-drm-specific-kmap_atomic-code-fix.patch
bitops-avoid-clang-shift-count-overflow-warnings.patch
ubsan-fix-gcc-10-warnings.patch
arm64-add-support-for-folded-p4d-page-tables-fix.patch