public inbox for stable@vger.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Philip Yang <Philip.Yang@amd.com>,
	Felix Kuehling <felix.kuehling@amd.com>,
	Alex Deucher <alexander.deucher@amd.com>,
	Sasha Levin <sashal@kernel.org>,
	Felix.Kuehling@amd.com, christian.koenig@amd.com,
	Xinhui.Pan@amd.com, airlied@gmail.com, daniel@ffwll.ch,
	amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Subject: [PATCH AUTOSEL 6.6 32/39] drm/amdkfd: svm range always mapped flag not working on APU
Date: Mon, 25 Dec 2023 19:19:22 -0500	[thread overview]
Message-ID: <20231226002021.4776-32-sashal@kernel.org> (raw)
In-Reply-To: <20231226002021.4776-1-sashal@kernel.org>

From: Philip Yang <Philip.Yang@amd.com>

[ Upstream commit ebab8c3eb6a6515dc14cd93fc29dd287709da6d3 ]

On gfx943 APU there is no VRAM and page migration, queue CWSR area, svm
range with always mapped flag, is not mapped to GPU correctly. This
works fine if retry fault on CWSR area can be recovered, but could cause
deadlock if there is another retry fault recover waiting for CWSR to
finish.

Fix this by mapping svm range with always mapped flag to GPU with ACCESS
attribute if XNACK ON.

There is side effect, because all GPUs have ACCESS attribute by default
on new svm range with XNACK on, the CWSR area will be mapped to all GPUs
after this change. This side effect will be fixed with Thunk change to
set CWSR svm range with ACCESS_IN_PLACE attribute on the GPU that user
queue is created.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 63ce30ea68915..8e368e4659fd5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1632,18 +1632,24 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
 			if (test_bit(gpuidx, prange->bitmap_access))
 				bitmap_set(ctx->bitmap, gpuidx, 1);
 		}
+
+		/*
+		 * If prange is already mapped or with always mapped flag,
+		 * update mapping on GPUs with ACCESS attribute
+		 */
+		if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
+			if (prange->mapped_to_gpu ||
+			    prange->flags & KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED)
+				bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
+		}
 	} else {
 		bitmap_or(ctx->bitmap, prange->bitmap_access,
 			  prange->bitmap_aip, MAX_GPU_INSTANCE);
 	}
 
 	if (bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-		bitmap_copy(ctx->bitmap, prange->bitmap_access, MAX_GPU_INSTANCE);
-		if (!prange->mapped_to_gpu ||
-		    bitmap_empty(ctx->bitmap, MAX_GPU_INSTANCE)) {
-			r = 0;
-			goto free_ctx;
-		}
+		r = 0;
+		goto free_ctx;
 	}
 
 	if (prange->actual_loc && !prange->ttm_res) {
-- 
2.43.0


  parent reply	other threads:[~2023-12-26  0:21 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-26  0:18 [PATCH AUTOSEL 6.6 01/39] Input: psmouse - enable Synaptics InterTouch for ThinkPad L14 G1 Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 02/39] reset: hisilicon: hi6220: fix Wvoid-pointer-to-enum-cast warning Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 03/39] Input: atkbd - skip ATKBD_CMD_GETID in translated mode Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 04/39] Input: i8042 - add nomux quirk for Acer P459-G2-M Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 05/39] Input: amimouse - convert to platform remove callback returning void Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 06/39] pinctrl: amd: Mask non-wake source pins with interrupt enabled at suspend Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 07/39] spi: cadence: revert "Add SPI transfer delays" Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 08/39] ASoC: cs35l45: Use modern pm_ops Sasha Levin
2023-12-26  0:18 ` [PATCH AUTOSEL 6.6 09/39] ASoC: cs35l45: Prevent IRQ handling when suspending/resuming Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 10/39] ASoC: cs35l45: Prevents spinning during runtime suspend Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 11/39] s390/scm: fix virtual vs physical address confusion Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 12/39] ARC: fix spare error Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 13/39] ARC: fix smatch warning Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 14/39] wifi: iwlwifi: pcie: avoid a NULL pointer dereference Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 15/39] Input: xpad - add Razer Wolverine V2 support Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 16/39] driver core: Add a guard() definition for the device_lock() Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 17/39] kselftest: alsa: fixed a print formatting warning Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 18/39] HID: nintendo: fix initializer element is not constant error Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 19/39] platform/x86: thinkpad_acpi: fix for incorrect fan reporting on some ThinkPad systems Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 20/39] platform/x86/amd/pmc: Move platform defines to header Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 21/39] platform/x86/amd/pmc: Only run IRQ1 firmware version check on Cezanne Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 22/39] platform/x86/amd/pmc: Move keyboard wakeup disablement detection to pmc-quirks Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 23/39] platform/x86/amd/pmc: Disable keyboard wakeup on AMD Framework 13 Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 24/39] ASoC: Intel: bytcr_rt5640: Add quirk for the Medion Lifetab S10346 Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 25/39] ASoC: Intel: bytcr_rt5640: Add new swapped-speakers quirk Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 26/39] ALSA: hda/realtek: Add quirks for ASUS Zenbook 2022 Models Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 27/39] dm audit: fix Kconfig so DM_AUDIT depends on BLK_DEV_DM Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 28/39] HID: nintendo: Prevent divide-by-zero on code Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 29/39] smb: client: fix potential OOB in smb2_dump_detail() Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 30/39] Revert "nvme-fc: fix race between error recovery and creating association" Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 31/39] i2c: rk3x: fix potential spinlock recursion on poll Sasha Levin
2023-12-26  0:19 ` Sasha Levin [this message]
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 33/39] drm/amd/display: Add case for dcn35 to support usb4 dmub hpd event Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 34/39] drm/amd/display: get dprefclk ss info from integration info table Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 35/39] pinctrl: cy8c95x0: Fix typo Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 36/39] pinctrl: cy8c95x0: Fix regression Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 37/39] pinctrl: cy8c95x0: Fix get_pincfg Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 38/39] posix-timers: Get rid of [COMPAT_]SYS_NI() uses Sasha Levin
2023-12-26  0:19 ` [PATCH AUTOSEL 6.6 39/39] ida: Fix crash in ida_free when the bitmap is empty Sasha Levin

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=20231226002021.4776-32-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=Philip.Yang@amd.com \
    --cc=Xinhui.Pan@amd.com \
    --cc=airlied@gmail.com \
    --cc=alexander.deucher@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.com \
    --cc=daniel@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=felix.kuehling@amd.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