From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Jonathan Kim <jonathan.kim@amd.com>,
Amber Lin <amber.lin@amd.com>,
Alex Deucher <alexander.deucher@amd.com>,
Sasha Levin <sashal@kernel.org>,
amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Subject: [PATCH AUTOSEL 5.10 032/100] drm/amdgpu: mask the xgmi number of hops reported from psp to kfd
Date: Mon, 3 May 2021 12:37:21 -0400 [thread overview]
Message-ID: <20210503163829.2852775-32-sashal@kernel.org> (raw)
In-Reply-To: <20210503163829.2852775-1-sashal@kernel.org>
From: Jonathan Kim <jonathan.kim@amd.com>
[ Upstream commit 4ac5617c4b7d0f0a8f879997f8ceaa14636d7554 ]
The psp supplies the link type in the upper 2 bits of the psp xgmi node
information num_hops field. With a new link type, Aldebaran has these
bits set to a non-zero value (1 = xGMI3) so the KFD topology will report
the incorrect IO link weights without proper masking.
The actual number of hops is located in the 3 least significant bits of
this field so mask if off accordingly before passing it to the KFD.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Reviewed-by: Amber Lin <amber.lin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 1162913c8bf4..0526dec1d736 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -465,15 +465,22 @@ int amdgpu_xgmi_update_topology(struct amdgpu_hive_info *hive, struct amdgpu_dev
}
+/*
+ * NOTE psp_xgmi_node_info.num_hops layout is as follows:
+ * num_hops[7:6] = link type (0 = xGMI2, 1 = xGMI3, 2/3 = reserved)
+ * num_hops[5:3] = reserved
+ * num_hops[2:0] = number of hops
+ */
int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
struct amdgpu_device *peer_adev)
{
struct psp_xgmi_topology_info *top = &adev->psp.xgmi_context.top_info;
+ uint8_t num_hops_mask = 0x7;
int i;
for (i = 0 ; i < top->num_nodes; ++i)
if (top->nodes[i].node_id == peer_adev->gmc.xgmi.node_id)
- return top->nodes[i].num_hops;
+ return top->nodes[i].num_hops & num_hops_mask;
return -EINVAL;
}
--
2.30.2
next prev parent reply other threads:[~2021-05-03 16:46 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-03 16:36 [PATCH AUTOSEL 5.10 001/100] drm: Added orientation quirk for OneGX1 Pro Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 002/100] drm/qxl: do not run release if qxl failed to init Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 003/100] drm/qxl: release shadow on shutdown Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 004/100] drm/ast: Fix invalid usage of AST_MAX_HWC_WIDTH in cursor atomic_check Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 005/100] drm/amd/display: changing sr exit latency Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 006/100] drm/ast: fix memory leak when unload the driver Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 007/100] drm/amd/display: Check for DSC support instead of ASIC revision Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 008/100] drm/amd/display: Don't optimize bandwidth before disabling planes Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 009/100] drm/amdgpu/display: buffer INTERRUPT_LOW_IRQ_CONTEXT interrupt work Sasha Levin
2021-05-03 16:36 ` [PATCH AUTOSEL 5.10 010/100] drm/amd/display/dc/dce/dce_aux: Remove duplicate line causing 'field overwritten' issue Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 011/100] scsi: lpfc: Fix incorrect dbde assignment when building target abts wqe Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 012/100] scsi: lpfc: Fix pt2pt connection does not recover after LOGO Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 013/100] drm/amdgpu: Fix some unload driver issues Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 014/100] sched/pelt: Fix task util_est update filtering Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 015/100] kvfree_rcu: Use same set of GFP flags as does single-argument Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 016/100] scsi: target: pscsi: Fix warning in pscsi_complete_cmd() Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 017/100] media: ite-cir: check for receive overflow Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 018/100] media: drivers: media: pci: sta2x11: fix Kconfig dependency on GPIOLIB Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 019/100] media: imx: capture: Return -EPIPE from __capture_legacy_try_fmt() Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 020/100] atomisp: don't let it go past pipes array Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 021/100] power: supply: bq27xxx: fix power_avg for newer ICs Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 022/100] extcon: arizona: Fix some issues when HPDET IRQ fires after the jack has been unplugged Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 023/100] extcon: arizona: Fix various races on driver unbind Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 024/100] media: media/saa7164: fix saa7164_encoder_register() memory leak bugs Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 025/100] media: gspca/sq905.c: fix uninitialized variable Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 026/100] media: pci: saa7164: Rudimentary spelling fixes in the file saa7164-types.h Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 027/100] power: supply: Use IRQF_ONESHOT Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 028/100] backlight: qcom-wled: Use sink_addr for sync toggle Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 029/100] backlight: qcom-wled: Fix FSC update issue for WLED5 Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 030/100] drm/bridge/analogix/anx78xx: Setup encoder before registering connector Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 031/100] drm/bridge/analogix/anx78xx: Cleanup on error in anx78xx_bridge_attach() Sasha Levin
2021-05-03 16:37 ` Sasha Levin [this message]
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 033/100] drm/amdkfd: Fix UBSAN shift-out-of-bounds warning Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 034/100] drm/amdgpu : Fix asic reset regression issue introduce by 8f211fe8ac7c4f Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 035/100] drm/amd/pm: fix workload mismatch on vega10 Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 036/100] drm/amd/display: Fix UBSAN warning for not a valid value for type '_Bool' Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 037/100] drm/amd/display: DCHUB underflow counter increasing in some scenarios Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 038/100] drm/amd/display: fix dml prefetch validation Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 039/100] scsi: qla2xxx: Always check the return value of qla24xx_get_isp_stats() Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 040/100] drm/vkms: fix misuse of WARN_ON Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 041/100] scsi: qla2xxx: Fix use after free in bsg Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 042/100] mmc: sdhci-esdhc-imx: validate pinctrl before use it Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 043/100] mmc: sdhci-pci: Add PCI IDs for Intel LKF Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 044/100] mmc: sdhci-brcmstb: Remove CQE quirk Sasha Levin
2021-05-03 16:37 ` [PATCH AUTOSEL 5.10 045/100] ata: ahci: Disable SXS for Hisilicon Kunpeng920 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=20210503163829.2852775-32-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=alexander.deucher@amd.com \
--cc=amber.lin@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=jonathan.kim@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