release 6.14.4
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
From a1eb9a3160dc9e3cee6abdeab8e41c2265a2d7a1 Mon Sep 17 00:00:00 2001
|
||||
From 4506de20739ac4726a258faa98609a552184d2d2 Mon Sep 17 00:00:00 2001
|
||||
From: =?UTF-8?q?Sergio=20Gonz=C3=A1lez=20Collado?=
|
||||
<sergio.collado@gmail.com>
|
||||
Date: Sun, 2 Mar 2025 23:15:18 +0100
|
||||
|
@@ -1,4 +1,4 @@
|
||||
From 1ff7499aaa4cec11be79e97c118978fd781073a6 Mon Sep 17 00:00:00 2001
|
||||
From b5a4b82efd19d0687a5582a58f6830bf714e34fc Mon Sep 17 00:00:00 2001
|
||||
From: Nathan Chancellor <nathan@kernel.org>
|
||||
Date: Tue, 18 Mar 2025 15:32:30 -0700
|
||||
Subject: x86/tools: Drop duplicate unlikely() definition in
|
||||
|
@@ -1,29 +0,0 @@
|
||||
From 72096487bfe8ebc52731c264536418c51854d999 Mon Sep 17 00:00:00 2001
|
||||
From: Alex Deucher <alexander.deucher@amd.com>
|
||||
Date: Thu, 27 Mar 2025 17:33:49 -0400
|
||||
Subject: drm/amdgpu/mes11: optimize MES pipe FW version fetching
|
||||
|
||||
Don't fetch it again if we already have it. It seems the
|
||||
don't reliably have the proper value at resume in some
|
||||
cases.
|
||||
|
||||
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4083
|
||||
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
||||
Cherry-picked-for: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/issues/121
|
||||
---
|
||||
drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 4 ++++
|
||||
1 file changed, 4 insertions(+)
|
||||
|
||||
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
|
||||
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
|
||||
@@ -899,6 +899,10 @@ static void mes_v11_0_get_fw_version(str
|
||||
{
|
||||
int pipe;
|
||||
|
||||
+ /* return early if we have already fetched these */
|
||||
+ if (adev->mes.sched_version && adev->mes.kiq_version)
|
||||
+ return;
|
||||
+
|
||||
/* get MES scheduler/KIQ versions */
|
||||
mutex_lock(&adev->srbm_mutex);
|
||||
|
@@ -1,4 +1,4 @@
|
||||
From a1dfb99dca82ff97b00ce76f8f987ade471875d1 Mon Sep 17 00:00:00 2001
|
||||
From 762de1df7e501e019c3ae273c7e5e2d4c04b303c Mon Sep 17 00:00:00 2001
|
||||
From: Jarkko Sakkinen <jarkko@kernel.org>
|
||||
Date: Mon, 7 Apr 2025 15:28:05 +0300
|
||||
Subject: tpm: Mask TPM RC in tpm2_start_auth_session()
|
@@ -1,4 +1,4 @@
|
||||
From 7b594a3c7b41db58884da466607417ca27c08a1d Mon Sep 17 00:00:00 2001
|
||||
From e3d18eed972374cfbac1e58cf109209b07c1e27e Mon Sep 17 00:00:00 2001
|
||||
From: Oleksandr Natalenko <oleksandr@natalenko.name>
|
||||
Date: Tue, 8 Apr 2025 12:02:36 +0200
|
||||
Subject: ice: mark ice_write_prof_mask_reg() as noinline
|
@@ -1,4 +1,4 @@
|
||||
From 42a4f494db975d62916c73f5d637aef9be343d70 Mon Sep 17 00:00:00 2001
|
||||
From 74c95e079dc8b3c53ade90b2070458c0c69f3fdf Mon Sep 17 00:00:00 2001
|
||||
From: Oleksandr Natalenko <oleksandr@natalenko.name>
|
||||
Date: Tue, 8 Apr 2025 19:51:44 +0200
|
||||
Subject: fixes-6.14: update tpm2_start_auth_session() fix
|
@@ -1,4 +1,4 @@
|
||||
From d3140c22ed2bc3c98dcf251659d78572e154a993 Mon Sep 17 00:00:00 2001
|
||||
From e56acee381a8e07edf1920fb58f3166f911b6e5c Mon Sep 17 00:00:00 2001
|
||||
From: Lingbo Kong <quic_lingbok@quicinc.com>
|
||||
Date: Wed, 26 Feb 2025 19:31:18 +0800
|
||||
Subject: wifi: ath12k: Abort scan before removing link interface to prevent
|
@@ -1,4 +1,4 @@
|
||||
From fa165a32074fba27286cc9d2464a647642ad6bc7 Mon Sep 17 00:00:00 2001
|
||||
From 8d0e02f81d08c7b1e082028af0f55a22e7e1dfb2 Mon Sep 17 00:00:00 2001
|
||||
From: Christian Brauner <brauner@kernel.org>
|
||||
Date: Tue, 15 Apr 2025 10:22:04 +0200
|
||||
Subject: Kconfig: switch CONFIG_SYSFS_SYCALL default to n
|
@@ -1,47 +0,0 @@
|
||||
From f1e8e30bef3757904d9e963f02ef297cd0c33240 Mon Sep 17 00:00:00 2001
|
||||
From: Alex Deucher <alexander.deucher@amd.com>
|
||||
Date: Fri, 28 Mar 2025 09:08:57 -0400
|
||||
Subject: drm/amdgpu/mes12: optimize MES pipe FW version fetching
|
||||
|
||||
Don't fetch it again if we already have it. It seems the
|
||||
registers don't reliably have the value at resume in some
|
||||
cases.
|
||||
|
||||
Fixes: 785f0f9fe742 ("drm/amdgpu: Add mes v12_0 ip block support (v4)")
|
||||
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
|
||||
---
|
||||
drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 21 ++++++++++++---------
|
||||
1 file changed, 12 insertions(+), 9 deletions(-)
|
||||
|
||||
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
|
||||
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
|
||||
@@ -1390,17 +1390,20 @@ static int mes_v12_0_queue_init(struct a
|
||||
mes_v12_0_queue_init_register(ring);
|
||||
}
|
||||
|
||||
- /* get MES scheduler/KIQ versions */
|
||||
- mutex_lock(&adev->srbm_mutex);
|
||||
- soc21_grbm_select(adev, 3, pipe, 0, 0);
|
||||
+ if (((pipe == AMDGPU_MES_SCHED_PIPE) && !adev->mes.sched_version) ||
|
||||
+ ((pipe == AMDGPU_MES_KIQ_PIPE) && !adev->mes.kiq_version)) {
|
||||
+ /* get MES scheduler/KIQ versions */
|
||||
+ mutex_lock(&adev->srbm_mutex);
|
||||
+ soc21_grbm_select(adev, 3, pipe, 0, 0);
|
||||
|
||||
- if (pipe == AMDGPU_MES_SCHED_PIPE)
|
||||
- adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
|
||||
- else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
|
||||
- adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
|
||||
+ if (pipe == AMDGPU_MES_SCHED_PIPE)
|
||||
+ adev->mes.sched_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
|
||||
+ else if (pipe == AMDGPU_MES_KIQ_PIPE && adev->enable_mes_kiq)
|
||||
+ adev->mes.kiq_version = RREG32_SOC15(GC, 0, regCP_MES_GP3_LO);
|
||||
|
||||
- soc21_grbm_select(adev, 0, 0, 0, 0);
|
||||
- mutex_unlock(&adev->srbm_mutex);
|
||||
+ soc21_grbm_select(adev, 0, 0, 0, 0);
|
||||
+ mutex_unlock(&adev->srbm_mutex);
|
||||
+ }
|
||||
|
||||
return 0;
|
||||
}
|
80
debian/patches/patchset-pf/fixes/0008-sched-eevdf-Fix-se-slice-being-set-to-U64_MAX-and-re.patch
vendored
Normal file
80
debian/patches/patchset-pf/fixes/0008-sched-eevdf-Fix-se-slice-being-set-to-U64_MAX-and-re.patch
vendored
Normal file
@@ -0,0 +1,80 @@
|
||||
From ea3ec10cacc746176a25dbd74c8d168e1c096a62 Mon Sep 17 00:00:00 2001
|
||||
From: Omar Sandoval <osandov@fb.com>
|
||||
Date: Fri, 25 Apr 2025 01:51:24 -0700
|
||||
Subject: sched/eevdf: Fix se->slice being set to U64_MAX and resulting crash
|
||||
|
||||
There is a code path in dequeue_entities() that can set the slice of a
|
||||
sched_entity to U64_MAX, which sometimes results in a crash.
|
||||
|
||||
The offending case is when dequeue_entities() is called to dequeue a
|
||||
delayed group entity, and then the entity's parent's dequeue is delayed.
|
||||
In that case:
|
||||
|
||||
1. In the if (entity_is_task(se)) else block at the beginning of
|
||||
dequeue_entities(), slice is set to
|
||||
cfs_rq_min_slice(group_cfs_rq(se)). If the entity was delayed, then
|
||||
it has no queued tasks, so cfs_rq_min_slice() returns U64_MAX.
|
||||
2. The first for_each_sched_entity() loop dequeues the entity.
|
||||
3. If the entity was its parent's only child, then the next iteration
|
||||
tries to dequeue the parent.
|
||||
4. If the parent's dequeue needs to be delayed, then it breaks from the
|
||||
first for_each_sched_entity() loop _without updating slice_.
|
||||
5. The second for_each_sched_entity() loop sets the parent's ->slice to
|
||||
the saved slice, which is still U64_MAX.
|
||||
|
||||
This throws off subsequent calculations with potentially catastrophic
|
||||
results. A manifestation we saw in production was:
|
||||
|
||||
6. In update_entity_lag(), se->slice is used to calculate limit, which
|
||||
ends up as a huge negative number.
|
||||
7. limit is used in se->vlag = clamp(vlag, -limit, limit). Because limit
|
||||
is negative, vlag > limit, so se->vlag is set to the same huge
|
||||
negative number.
|
||||
8. In place_entity(), se->vlag is scaled, which overflows and results in
|
||||
another huge (positive or negative) number.
|
||||
9. The adjusted lag is subtracted from se->vruntime, which increases or
|
||||
decreases se->vruntime by a huge number.
|
||||
10. pick_eevdf() calls entity_eligible()/vruntime_eligible(), which
|
||||
incorrectly returns false because the vruntime is so far from the
|
||||
other vruntimes on the queue, causing the
|
||||
(vruntime - cfs_rq->min_vruntime) * load calulation to overflow.
|
||||
11. Nothing appears to be eligible, so pick_eevdf() returns NULL.
|
||||
12. pick_next_entity() tries to dereference the return value of
|
||||
pick_eevdf() and crashes.
|
||||
|
||||
Dumping the cfs_rq states from the core dumps with drgn showed tell-tale
|
||||
huge vruntime ranges and bogus vlag values, and I also traced se->slice
|
||||
being set to U64_MAX on live systems (which was usually "benign" since
|
||||
the rest of the runqueue needed to be in a particular state to crash).
|
||||
|
||||
Fix it in dequeue_entities() by always setting slice from the first
|
||||
non-empty cfs_rq.
|
||||
|
||||
Fixes: aef6987d8954 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy")
|
||||
Signed-off-by: Omar Sandoval <osandov@fb.com>
|
||||
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
|
||||
Link: https://lkml.kernel.org/r/f0c2d1072be229e1bdddc73c0703919a8b00c652.1745570998.git.osandov@fb.com
|
||||
---
|
||||
kernel/sched/fair.c | 4 +---
|
||||
1 file changed, 1 insertion(+), 3 deletions(-)
|
||||
|
||||
--- a/kernel/sched/fair.c
|
||||
+++ b/kernel/sched/fair.c
|
||||
@@ -7096,9 +7096,6 @@ static int dequeue_entities(struct rq *r
|
||||
h_nr_idle = task_has_idle_policy(p);
|
||||
if (task_sleep || task_delayed || !se->sched_delayed)
|
||||
h_nr_runnable = 1;
|
||||
- } else {
|
||||
- cfs_rq = group_cfs_rq(se);
|
||||
- slice = cfs_rq_min_slice(cfs_rq);
|
||||
}
|
||||
|
||||
for_each_sched_entity(se) {
|
||||
@@ -7108,6 +7105,7 @@ static int dequeue_entities(struct rq *r
|
||||
if (p && &p->se == se)
|
||||
return -1;
|
||||
|
||||
+ slice = cfs_rq_min_slice(cfs_rq);
|
||||
break;
|
||||
}
|
||||
|
@@ -1,50 +0,0 @@
|
||||
From 81c23adad48324b73fe0993f332407c5be050bb5 Mon Sep 17 00:00:00 2001
|
||||
From: Johannes Berg <johannes.berg@intel.com>
|
||||
Date: Thu, 3 Apr 2025 11:04:37 +0000
|
||||
Subject: wifi: iwlwifi: pcie: set state to no-FW before reset handshake
|
||||
|
||||
The reset handshake attempts to kill the firmware, and it'll go
|
||||
into a pretty much dead state once we do that. However, if it
|
||||
times out, then we'll attempt to dump the firmware to be able
|
||||
to see why it didn't respond. During this dump, we cannot treat
|
||||
it as if it was still running, since we just tried to kill it,
|
||||
otherwise dumping will attempt to send a DBGC stop command. As
|
||||
this command will time out, we'll go into a reset loop.
|
||||
|
||||
For now, fix this by setting the trans->state to say firmware
|
||||
isn't running before doing the reset handshake. In the longer
|
||||
term, we should clean up the way this state is handled.
|
||||
|
||||
It's not entirely clear but it seems likely that this issue was
|
||||
introduced by my rework of the error handling, prior to that it
|
||||
would've been synchronous at that point and (I think) not have
|
||||
attempted to reset since it was already doing down.
|
||||
|
||||
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219967
|
||||
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219968
|
||||
Closes: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/issues/128
|
||||
Fixes: 7391b2a4f7db ("wifi: iwlwifi: rework firmware error handling")
|
||||
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
|
||||
Signed-off-by: Oleksandr Natalenko <oleksandr@natalenko.name>
|
||||
---
|
||||
drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c | 8 +++++++-
|
||||
1 file changed, 7 insertions(+), 1 deletion(-)
|
||||
|
||||
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
|
||||
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
|
||||
@@ -147,8 +147,14 @@ static void _iwl_trans_pcie_gen2_stop_de
|
||||
return;
|
||||
|
||||
if (trans->state >= IWL_TRANS_FW_STARTED &&
|
||||
- trans_pcie->fw_reset_handshake)
|
||||
+ trans_pcie->fw_reset_handshake) {
|
||||
+ /*
|
||||
+ * Reset handshake can dump firmware on timeout, but that
|
||||
+ * should assume that the firmware is already dead.
|
||||
+ */
|
||||
+ trans->state = IWL_TRANS_NO_FW;
|
||||
iwl_trans_pcie_fw_reset_handshake(trans);
|
||||
+ }
|
||||
|
||||
trans_pcie->is_down = true;
|
||||
|
Reference in New Issue
Block a user