From: "Timur Kristóf" <timur.kristof@gmail.com>
To: amd-gfx@lists.freedesktop.org,
"Alex Deucher" <alexander.deucher@amd.com>,
christian.koenig@amd.com, "Marek Olšák" <maraeo@gmail.com>,
"Natalie Vock" <natalie.vock@gmx.de>,
"Melissa Wen" <mwen@igalia.com>
Cc: "Timur Kristóf" <timur.kristof@gmail.com>
Subject: [PATCH 2/6] drm/amdgpu/gfxhub: Enable retry fault interrupts when needed
Date: Wed, 13 May 2026 18:30:39 +0200 [thread overview]
Message-ID: <20260513163043.8725-3-timur.kristof@gmail.com> (raw)
In-Reply-To: <20260513163043.8725-1-timur.kristof@gmail.com>
Enable retry fault interrupts when retrying page faults is
enabled in amdgpu (ie. amdgpu.noretry=0).
Needs to be done for each GFXHUB version at once,
because none of them actually enabled this interrupt.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
---
drivers/gpu/drm/amd/amdgpu/gfxhub_v11_5_0.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v12_0.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v12_1.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c | 5 +++++
drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c | 5 +++++
9 files changed, 45 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v11_5_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v11_5_0.c
index f845ba698b40..8fdf66ad265c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v11_5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v11_5_0.c
@@ -456,6 +456,11 @@ static void gfxhub_v11_5_0_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v11_5_0_vmhub_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_0.c
index ba78b5a1a7cd..84344c67013a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_0.c
@@ -461,6 +461,11 @@ static void gfxhub_v12_0_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v12_0_vmhub_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_1.c
index 3544eb42dca6..e505aaf8b447 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v12_1.c
@@ -648,6 +648,11 @@ static void gfxhub_v12_1_xcc_set_fault_enable_default(struct amdgpu_device *adev
CRASH_ON_RETRY_FAULT, 1);
WREG32_SOC15(GC, GET_INST(GC, i),
regGCVM_L2_PROTECTION_FAULT_CNTL_HI32, tmp);
+
+ tmp = RREG32_SOC15(GC, GET_INST(GC, i), regGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, GET_INST(GC, i), regGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index a7bfc9f41d0e..c8a615147904 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -410,6 +410,11 @@ static void gfxhub_v1_0_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, VM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, mmVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static void gfxhub_v1_0_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 6c03bf9f1ae8..afc8c6a6f1bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -523,6 +523,11 @@ static void gfxhub_v1_2_xcc_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, GET_INST(GC, i), regVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, GET_INST(GC, i), regVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, VM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, GET_INST(GC, i), regVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 793faf62cb07..a27bb37b2a11 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -425,6 +425,11 @@ static void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v2_0_vmhub_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
index aceb8447feac..db56f7a61d61 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c
@@ -456,6 +456,11 @@ static void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v2_1_vmhub_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c
index 631f99e3741a..97585c7b879c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0.c
@@ -453,6 +453,11 @@ static void gfxhub_v3_0_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v3_0_vmhub_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c
index 8a87410ce016..72f24372a4e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v3_0_3.c
@@ -441,6 +441,11 @@ static void gfxhub_v3_0_3_set_fault_enable_default(struct amdgpu_device *adev,
CRASH_ON_RETRY_FAULT, 1);
}
WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL, tmp);
+
+ tmp = RREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2);
+ tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL2,
+ ENABLE_RETRY_FAULT_INTERRUPT, value && !adev->gmc.noretry);
+ WREG32_SOC15(GC, 0, regGCVM_L2_PROTECTION_FAULT_CNTL2, tmp);
}
static const struct amdgpu_vmhub_funcs gfxhub_v3_0_3_vmhub_funcs = {
--
2.54.0
next prev parent reply other threads:[~2026-05-13 16:30 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-05-13 16:30 [PATCH 0/6] drm/amdgpu: Improve retry fault handling Timur Kristóf
2026-05-13 16:30 ` [PATCH 1/6] drm/amdgpu: Use gmc->noretry instead of amdgpu_noretry directly Timur Kristóf
2026-05-13 16:30 ` Timur Kristóf [this message]
2026-05-13 16:30 ` [PATCH 3/6] drm/amdgpu/gfxhub: Program CRASH_ON_*_FAULT bits to 0 as needed Timur Kristóf
2026-05-13 16:30 ` [PATCH 4/6] drm/amdgpu/gmc: Don't compare page fault timestamps with other interrupts Timur Kristóf
2026-05-13 16:30 ` [PATCH 5/6] drm/amdgpu/ih: Add retry_cam_ack IH function pointer Timur Kristóf
2026-05-13 16:30 ` [PATCH 6/6] drm/amdgpu: Enable retry CAM on Navi 3 dGPUs Timur Kristóf
2026-05-13 16:36 ` [PATCH 0/6] drm/amdgpu: Improve retry fault handling Alex Deucher
2026-05-13 16:43 ` Timur Kristóf
2026-05-13 17:28 ` Shetaia, Amir
2026-05-13 17:32 ` Deucher, Alexander
2026-05-13 17:51 ` Timur Kristóf
2026-05-13 20:32 ` Shetaia, Amir
2026-05-13 22:12 ` Timur Kristóf
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=20260513163043.8725-3-timur.kristof@gmail.com \
--to=timur.kristof@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=maraeo@gmail.com \
--cc=mwen@igalia.com \
--cc=natalie.vock@gmx.de \
/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