From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org, Ben Skeggs <bskeggs@redhat.com>
Subject: [PATCH 4.19 34/44] drm/nouveau/kms/nv50-: also flush fb writes when rewinding push buffer
Date: Tue, 18 Dec 2018 17:39:46 +0100 [thread overview]
Message-ID: <20181218163931.437726462@linuxfoundation.org> (raw)
In-Reply-To: <20181218163927.119623235@linuxfoundation.org>
4.19-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ben Skeggs <bskeggs@redhat.com>
commit 970a5ee41c72df46e3b0f307528c7d8ef7734a2e upstream.
Should hopefully fix a regression some people have been seeing since EVO
push buffers were moved to VRAM by default on Pascal GPUs.
Fixes: d00ddd9da ("drm/nouveau/kms/nv50-: allocate push buffers in vidmem on pascal")
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
Cc: <stable@vger.kernel.org> # 4.19+
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/gpu/drm/nouveau/dispnv50/disp.c | 29 ++++++++++++++++++-----------
1 file changed, 18 insertions(+), 11 deletions(-)
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -197,6 +197,22 @@ nv50_dmac_create(struct nvif_device *dev
/******************************************************************************
* EVO channel helpers
*****************************************************************************/
+static void
+evo_flush(struct nv50_dmac *dmac)
+{
+ /* Push buffer fetches are not coherent with BAR1, we need to ensure
+ * writes have been flushed right through to VRAM before writing PUT.
+ */
+ if (dmac->push.type & NVIF_MEM_VRAM) {
+ struct nvif_device *device = dmac->base.device;
+ nvif_wr32(&device->object, 0x070000, 0x00000001);
+ nvif_msec(device, 2000,
+ if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002))
+ break;
+ );
+ }
+}
+
u32 *
evo_wait(struct nv50_dmac *evoc, int nr)
{
@@ -207,6 +223,7 @@ evo_wait(struct nv50_dmac *evoc, int nr)
mutex_lock(&dmac->lock);
if (put + nr >= (PAGE_SIZE / 4) - 8) {
dmac->ptr[put] = 0x20000000;
+ evo_flush(dmac);
nvif_wr32(&dmac->base.user, 0x0000, 0x00000000);
if (nvif_msec(device, 2000,
@@ -229,17 +246,7 @@ evo_kick(u32 *push, struct nv50_dmac *ev
{
struct nv50_dmac *dmac = evoc;
- /* Push buffer fetches are not coherent with BAR1, we need to ensure
- * writes have been flushed right through to VRAM before writing PUT.
- */
- if (dmac->push.type & NVIF_MEM_VRAM) {
- struct nvif_device *device = dmac->base.device;
- nvif_wr32(&device->object, 0x070000, 0x00000001);
- nvif_msec(device, 2000,
- if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002))
- break;
- );
- }
+ evo_flush(dmac);
nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
mutex_unlock(&dmac->lock);
next prev parent reply other threads:[~2018-12-18 16:42 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-18 16:39 [PATCH 4.19 00/44] 4.19.11-stable review Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 01/44] sched/pelt: Fix warning and clean up IRQ PELT config Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 02/44] scsi: raid_attrs: fix unused variable warning Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 03/44] staging: olpc_dcon: add a missing dependency Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 04/44] slimbus: ngd: mark PM functions as __maybe_unused Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 05/44] i2c: aspeed: fix build warning Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 06/44] ARM: dts: qcom-apq8064-arrow-sd-600eval fix graph_endpoint warning Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 07/44] drm/msm: fix address space warning Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 08/44] pinctrl: sunxi: a83t: Fix IRQ offset typo for PH11 Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 09/44] aio: fix spectre gadget in lookup_ioctx Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 10/44] scripts/spdxcheck.py: always open files in binary mode Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 11/44] fs/iomap.c: get/put the page in iomap_page_create/release() Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 12/44] userfaultfd: check VM_MAYWRITE was set after verifying the uffd is registered Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 13/44] arm64: dma-mapping: Fix FORCE_CONTIGUOUS buffer clearing Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 14/44] block/bio: Do not zero user pages Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 15/44] ovl: fix decode of dir file handle with multi lower layers Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 16/44] ovl: fix missing override creds in link of a metacopy upper Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 17/44] MMC: OMAP: fix broken MMC on OMAP15XX/OMAP5910/OMAP310 Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 18/44] mmc: core: use mrq->sbc when sending CMD23 for RPMB Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 19/44] mmc: sdhci-omap: Fix DCRC error handling during tuning Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 20/44] mmc: sdhci: fix the timeout check window for clock and reset Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 21/44] fuse: continue to send FUSE_RELEASEDIR when FUSE_OPEN returns ENOSYS Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 22/44] ARM: mmp/mmp2: fix cpu_is_mmp2() on mmp2-dt Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 23/44] ARM: dts: bcm2837: Fix polarity of wifi reset GPIOs Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 24/44] dm thin: send event about thin-pool state change _after_ making it Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 25/44] dm cache metadata: verify cache has blocks in blocks_are_clean_separate_dirty() Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 26/44] dm: call blk_queue_split() to impose device limits on bios Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 27/44] tracing: Fix memory leak in create_filter() Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 28/44] tracing: Fix memory leak in set_trigger_filter() Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 29/44] tracing: Fix memory leak of instance function hash filters Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 30/44] media: vb2: dont call __vb2_queue_cancel if vb2_start_streaming failed Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 31/44] powerpc/msi: Fix NULL pointer access in teardown code Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 32/44] powerpc: Look for "stdout-path" when setting up legacy consoles Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 33/44] drm/nouveau/kms: Fix memory leak in nv50_mstm_del() Greg Kroah-Hartman
2018-12-18 16:39 ` Greg Kroah-Hartman [this message]
2018-12-18 16:39 ` [PATCH 4.19 35/44] Revert "drm/rockchip: Allow driver to be shutdown on reboot/kexec" Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 36/44] drm/i915/gvt: Fix tiled memory decoding bug on BDW Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 37/44] drm/i915/execlists: Apply a full mb before execution for Braswell Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 38/44] drm/amdgpu/powerplay: Apply avfs cks-off voltages on VI Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 39/44] drm/amdkfd: add new vega10 pci ids Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 40/44] drm/amdgpu: add some additional " Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 41/44] drm/amdgpu: update smu firmware images for VI variants (v2) Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 42/44] drm/amdgpu: update SMC firmware image for polaris10 variants Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 43/44] dm zoned: Fix target BIO completion handling Greg Kroah-Hartman
2018-12-18 16:39 ` [PATCH 4.19 44/44] x86/build: Fix compiler support check for CONFIG_RETPOLINE Greg Kroah-Hartman
2018-12-18 20:26 ` [PATCH 4.19 00/44] 4.19.11-stable review shuah
2018-12-19 13:19 ` Greg Kroah-Hartman
2018-12-18 21:10 ` Dan Rue
2018-12-19 13:19 ` Greg Kroah-Hartman
2018-12-19 15:01 ` Harsh Shandilya
2018-12-19 15:14 ` Greg Kroah-Hartman
2018-12-19 17:23 ` Guenter Roeck
2018-12-19 18:37 ` Greg Kroah-Hartman
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181218163931.437726462@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=bskeggs@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).