- Linux-stable-mirror - lists.linaro.org

[PATCH 5/5] drm/tests: shmem: Hold reservation lock around purge

by Thomas Zimmermann

Acquire and release the GEM object's reservation lock around calls to the object's purge operation. The tests use drm_gem_shmem_purge_locked(), which led to errors such as show below. [ 58.709128] WARNING: CPU: 1 PID: 1354 at drivers/gpu/drm/drm_gem_shmem_helper.c:515 drm_gem_shmem_purge_locked+0x51c/0x740 Only export the new helper drm_gem_shmem_purge() for Kunit tests. This is not an interface for regular drivers. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: 954907f7147d ("drm/shmem-helper: Refactor locked/unlocked functions") Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v6.16+ --- drivers/gpu/drm/drm_gem_shmem_helper.c | 15 +++++++++++++++ drivers/gpu/drm/tests/drm_gem_shmem_test.c | 4 +++- include/drm/drm_gem_shmem_helper.h | 1 + 3 files changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 4ffcf6ed46f5..dfc24392cb61 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -939,6 +939,21 @@ int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv) return ret; } EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_madvise); + +int drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem) +{ + struct drm_gem_object *obj = &shmem->base; + int ret; + + ret = dma_resv_lock_interruptible(obj->resv, NULL); + if (ret) + return ret; + drm_gem_shmem_purge_locked(shmem); + dma_resv_unlock(obj->resv); + + return 0; +} +EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_purge); #endif MODULE_DESCRIPTION("DRM SHMEM memory-management helpers"); diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index d639848e3c8e..4b459f21acfd 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -340,7 +340,9 @@ static void drm_gem_shmem_test_purge(struct kunit *test) ret = drm_gem_shmem_is_purgeable(shmem); KUNIT_EXPECT_TRUE(test, ret); - drm_gem_shmem_purge_locked(shmem); + ret = drm_gem_shmem_purge(shmem); + KUNIT_ASSERT_EQ(test, ret, 0); + KUNIT_EXPECT_NULL(test, shmem->pages); KUNIT_EXPECT_NULL(test, shmem->sgt); KUNIT_EXPECT_EQ(test, shmem->madv, -1); diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 3dd93e2df709..8d56970d7eed 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -311,6 +311,7 @@ struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev, int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); +int drm_gem_shmem_purge(struct drm_gem_shmem_object *shmem); #endif #endif /* __DRM_GEM_SHMEM_HELPER_H__ */ -- 2.52.0

5 days

2
1
0 0

[PATCH 4/5] drm/tests: shmem: Hold reservation lock around madvise

by Thomas Zimmermann

Acquire and release the GEM object's reservation lock around calls to the object's madvide operation. The tests use drm_gem_shmem_madvise_locked(), which led to errors such as show below. [ 58.339389] WARNING: CPU: 1 PID: 1352 at drivers/gpu/drm/drm_gem_shmem_helper.c:499 drm_gem_shmem_madvise_locked+0xde/0x140 Only export the new helper drm_gem_shmem_madvise() for Kunit tests. This is not an interface for regular drivers. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: 954907f7147d ("drm/shmem-helper: Refactor locked/unlocked functions") Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v6.16+ --- drivers/gpu/drm/drm_gem_shmem_helper.c | 15 +++++++++++++++ drivers/gpu/drm/tests/drm_gem_shmem_test.c | 8 ++++---- include/drm/drm_gem_shmem_helper.h | 1 + 3 files changed, 20 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 06ef4e5adb7d..4ffcf6ed46f5 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -924,6 +924,21 @@ void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map * dma_resv_unlock(obj->resv); } EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_vunmap); + +int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv) +{ + struct drm_gem_object *obj = &shmem->base; + int ret; + + ret = dma_resv_lock_interruptible(obj->resv, NULL); + if (ret) + return ret; + ret = drm_gem_shmem_madvise_locked(shmem, madv); + dma_resv_unlock(obj->resv); + + return ret; +} +EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_madvise); #endif MODULE_DESCRIPTION("DRM SHMEM memory-management helpers"); diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index 3e7c6f20fbcc..d639848e3c8e 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -292,17 +292,17 @@ static void drm_gem_shmem_test_madvise(struct kunit *test) ret = kunit_add_action_or_reset(test, drm_gem_shmem_free_wrapper, shmem); KUNIT_ASSERT_EQ(test, ret, 0); - ret = drm_gem_shmem_madvise_locked(shmem, 1); + ret = drm_gem_shmem_madvise(shmem, 1); KUNIT_EXPECT_TRUE(test, ret); KUNIT_ASSERT_EQ(test, shmem->madv, 1); /* Set madv to a negative value */ - ret = drm_gem_shmem_madvise_locked(shmem, -1); + ret = drm_gem_shmem_madvise(shmem, -1); KUNIT_EXPECT_FALSE(test, ret); KUNIT_ASSERT_EQ(test, shmem->madv, -1); /* Check that madv cannot be set back to a positive value */ - ret = drm_gem_shmem_madvise_locked(shmem, 0); + ret = drm_gem_shmem_madvise(shmem, 0); KUNIT_EXPECT_FALSE(test, ret); KUNIT_ASSERT_EQ(test, shmem->madv, -1); } @@ -330,7 +330,7 @@ static void drm_gem_shmem_test_purge(struct kunit *test) ret = drm_gem_shmem_is_purgeable(shmem); KUNIT_EXPECT_FALSE(test, ret); - ret = drm_gem_shmem_madvise_locked(shmem, 1); + ret = drm_gem_shmem_madvise(shmem, 1); KUNIT_EXPECT_TRUE(test, ret); /* The scatter/gather table will be freed by drm_gem_shmem_free */ diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 6924ee226655..3dd93e2df709 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -310,6 +310,7 @@ struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev, #if IS_ENABLED(CONFIG_KUNIT) int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); +int drm_gem_shmem_madvise(struct drm_gem_shmem_object *shmem, int madv); #endif #endif /* __DRM_GEM_SHMEM_HELPER_H__ */ -- 2.52.0

5 days

2
1
0 0

[PATCH 3/5] drm/tests: shmem: Hold reservation lock around vmap/vunmap

by Thomas Zimmermann

Acquire and release the GEM object's reservation lock around vmap and vunmap operations. The tests use vmap_locked, which led to errors such as show below. [ 122.292030] WARNING: CPU: 3 PID: 1413 at drivers/gpu/drm/drm_gem_shmem_helper.c:390 drm_gem_shmem_vmap_locked+0x3a3/0x6f0 [ 122.468066] WARNING: CPU: 3 PID: 1413 at drivers/gpu/drm/drm_gem_shmem_helper.c:293 drm_gem_shmem_pin_locked+0x1fe/0x350 [ 122.563504] WARNING: CPU: 3 PID: 1413 at drivers/gpu/drm/drm_gem_shmem_helper.c:234 drm_gem_shmem_get_pages_locked+0x23c/0x370 [ 122.662248] WARNING: CPU: 2 PID: 1413 at drivers/gpu/drm/drm_gem_shmem_helper.c:452 drm_gem_shmem_vunmap_locked+0x101/0x330 Only export the new vmap/vunmap helpers for Kunit tests. These are not interfaces for regular drivers. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: 954907f7147d ("drm/shmem-helper: Refactor locked/unlocked functions") Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v6.16+ --- drivers/gpu/drm/drm_gem_shmem_helper.c | 33 ++++++++++++++++++++++ drivers/gpu/drm/tests/drm_gem_shmem_test.c | 6 ++-- include/drm/drm_gem_shmem_helper.h | 9 ++++++ 3 files changed, 46 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index dc94a27710e5..06ef4e5adb7d 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -15,6 +15,8 @@ #include <asm/set_memory.h> #endif +#include <kunit/visibility.h> + #include <drm/drm.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> @@ -893,6 +895,37 @@ struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev, } EXPORT_SYMBOL_GPL(drm_gem_shmem_prime_import_no_map); +/* + * Kunit helpers + */ + +#if IS_ENABLED(CONFIG_KUNIT) +int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map) +{ + struct drm_gem_object *obj = &shmem->base; + int ret; + + ret = dma_resv_lock_interruptible(obj->resv, NULL); + if (ret) + return ret; + ret = drm_gem_shmem_vmap_locked(shmem, map); + dma_resv_unlock(obj->resv); + + return ret; +} +EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_vmap); + +void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map) +{ + struct drm_gem_object *obj = &shmem->base; + + dma_resv_lock_interruptible(obj->resv, NULL); + drm_gem_shmem_vunmap_locked(shmem, map); + dma_resv_unlock(obj->resv); +} +EXPORT_SYMBOL_IF_KUNIT(drm_gem_shmem_vunmap); +#endif + MODULE_DESCRIPTION("DRM SHMEM memory-management helpers"); MODULE_IMPORT_NS("DMA_BUF"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index 1d50bab51ef3..3e7c6f20fbcc 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -19,6 +19,8 @@ #include <drm/drm_gem_shmem_helper.h> #include <drm/drm_kunit_helpers.h> +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); + #define TEST_SIZE SZ_1M #define TEST_BYTE 0xae @@ -176,7 +178,7 @@ static void drm_gem_shmem_test_vmap(struct kunit *test) ret = kunit_add_action_or_reset(test, drm_gem_shmem_free_wrapper, shmem); KUNIT_ASSERT_EQ(test, ret, 0); - ret = drm_gem_shmem_vmap_locked(shmem, &map); + ret = drm_gem_shmem_vmap(shmem, &map); KUNIT_ASSERT_EQ(test, ret, 0); KUNIT_ASSERT_NOT_NULL(test, shmem->vaddr); KUNIT_ASSERT_FALSE(test, iosys_map_is_null(&map)); @@ -186,7 +188,7 @@ static void drm_gem_shmem_test_vmap(struct kunit *test) for (i = 0; i < TEST_SIZE; i++) KUNIT_EXPECT_EQ(test, iosys_map_rd(&map, i, u8), TEST_BYTE); - drm_gem_shmem_vunmap_locked(shmem, &map); + drm_gem_shmem_vunmap(shmem, &map); KUNIT_EXPECT_NULL(test, shmem->vaddr); KUNIT_EXPECT_EQ(test, refcount_read(&shmem->vmap_use_count), 0); } diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h index 589f7bfe7506..6924ee226655 100644 --- a/include/drm/drm_gem_shmem_helper.h +++ b/include/drm/drm_gem_shmem_helper.h @@ -303,4 +303,13 @@ struct drm_gem_object *drm_gem_shmem_prime_import_no_map(struct drm_device *dev, .gem_prime_import = drm_gem_shmem_prime_import_no_map, \ .dumb_create = drm_gem_shmem_dumb_create +/* + * Kunit helpers + */ + +#if IS_ENABLED(CONFIG_KUNIT) +int drm_gem_shmem_vmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); +void drm_gem_shmem_vunmap(struct drm_gem_shmem_object *shmem, struct iosys_map *map); +#endif + #endif /* __DRM_GEM_SHMEM_HELPER_H__ */ -- 2.52.0

5 days

2
1
0 0

[PATCH 2/5] drm/tests: shmem: Add clean-up action to unpin pages

by Thomas Zimmermann

Automatically unpin pages on cleanup. The test currently fails with the error [ 58.246263] drm-kunit-mock-device drm_gem_shmem_test_get_sg_table.drm-kunit-mock-device: [drm] drm_WARN_ON(refcount_read(&shmem->pages_pin_count)) while cleaning up the GEM object. The pin count has to be zero at this point. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: d586b535f144 ("drm/shmem-helper: Add and use pages_pin_count") Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v6.16+ --- drivers/gpu/drm/tests/drm_gem_shmem_test.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index 872881ec9c30..1d50bab51ef3 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -34,6 +34,9 @@ KUNIT_DEFINE_ACTION_WRAPPER(sg_free_table_wrapper, sg_free_table, KUNIT_DEFINE_ACTION_WRAPPER(drm_gem_shmem_free_wrapper, drm_gem_shmem_free, struct drm_gem_shmem_object *); +KUNIT_DEFINE_ACTION_WRAPPER(drm_gem_shmem_unpin_wrapper, drm_gem_shmem_unpin, + struct drm_gem_shmem_object *); + /* * Test creating a shmem GEM object backed by shmem buffer. The test * case succeeds if the GEM object is successfully allocated with the @@ -212,6 +215,9 @@ static void drm_gem_shmem_test_get_sg_table(struct kunit *test) ret = drm_gem_shmem_pin(shmem); KUNIT_ASSERT_EQ(test, ret, 0); + ret = kunit_add_action_or_reset(test, drm_gem_shmem_unpin_wrapper, shmem); + KUNIT_ASSERT_EQ(test, ret, 0); + sgt = drm_gem_shmem_get_sg_table(shmem); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, sgt); KUNIT_EXPECT_NULL(test, shmem->sgt); -- 2.52.0

5 days

2
1
0 0

[PATCH 1/5] drm/tests: shmem: Swap names of export tests

by Thomas Zimmermann

GEM SHMEM has 2 helpers for exporting S/G tables. Swap the names of the rsp. tests, so that each matches the helper it tests. Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: 93032ae634d4 ("drm/test: add a test suite for GEM objects backed by shmem") Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/tests/drm_gem_shmem_test.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c index 68f2c3162354..872881ec9c30 100644 --- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c +++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c @@ -194,7 +194,7 @@ static void drm_gem_shmem_test_vmap(struct kunit *test) * scatter/gather table large enough to accommodate the backing memory * is successfully exported. */ -static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test) +static void drm_gem_shmem_test_get_sg_table(struct kunit *test) { struct drm_device *drm_dev = test->priv; struct drm_gem_shmem_object *shmem; @@ -236,7 +236,7 @@ static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test) * backing pages are pinned and a scatter/gather table large enough to * accommodate the backing memory is successfully exported. */ -static void drm_gem_shmem_test_get_sg_table(struct kunit *test) +static void drm_gem_shmem_test_get_pages_sgt(struct kunit *test) { struct drm_device *drm_dev = test->priv; struct drm_gem_shmem_object *shmem; @@ -366,8 +366,8 @@ static struct kunit_case drm_gem_shmem_test_cases[] = { KUNIT_CASE(drm_gem_shmem_test_obj_create_private), KUNIT_CASE(drm_gem_shmem_test_pin_pages), KUNIT_CASE(drm_gem_shmem_test_vmap), - KUNIT_CASE(drm_gem_shmem_test_get_pages_sgt), KUNIT_CASE(drm_gem_shmem_test_get_sg_table), + KUNIT_CASE(drm_gem_shmem_test_get_pages_sgt), KUNIT_CASE(drm_gem_shmem_test_madvise), KUNIT_CASE(drm_gem_shmem_test_purge), {} -- 2.52.0

5 days

2
1
0 0

[PATCH v2 RESEND] coresight: etm-perf: Fix reference count leak in etm_setup_aux

by Ma Ke

In etm_setup_aux(), when a user sink is obtained via coresight_get_sink_by_id(), it increments the reference count of the sink device. However, if the sink is used in path building, the path holds a reference, but the initial reference from coresight_get_sink_by_id() is not released, causing a reference count leak. We should release the initial reference after the path is built. Found by code review. Cc: stable(a)vger.kernel.org Fixes: 0e6c20517596 ("coresight: etm-perf: Allow an event to use different sinks") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- Changes in v2: - modified the patch as suggestions. --- drivers/hwtracing/coresight/coresight-etm-perf.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 17afa0f4cdee..56d012ab6d3a 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -454,6 +454,11 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, goto err; out: + if (user_sink) { + put_device(&user_sink->dev); + user_sink = NULL; + } + return event_data; err: -- 2.17.1

5 days, 1 hour

5
9
0 0

[PATCH v6 03/24] drm/pagemap, drm/xe: Ensure that the devmem allocation is idle before use

by Thomas Hellström

In situations where no system memory is migrated to devmem, and in upcoming patches where another GPU is performing the migration to the newly allocated devmem buffer, there is nothing to ensure any ongoing clear to the devmem allocation or async eviction from the devmem allocation is complete. Address that by passing a struct dma_fence down to the copy functions, and ensure it is waited for before migration is marked complete. v3: - New patch. v4: - Update the logic used for determining when to wait for the pre_migrate_fence. - Update the logic used for determining when to warn for the pre_migrate_fence since the scheduler fences apparently can signal out-of-order. v5: - Fix a UAF (CI) - Remove references to source P2P migration (Himal) - Put the pre_migrate_fence after migration. v6: - Pipeline the pre_migrate_fence dependency (Matt Brost) Fixes: c5b3eb5a906c ("drm/xe: Add GPUSVM device memory copy vfunc functions") Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.15+ Signed-off-by: Thomas Hellström <thomas.hellstrom(a)linux.intel.com> Reviewed-by: Matthew Brost <matthew.brost(a)intel.com> --- drivers/gpu/drm/drm_pagemap.c | 17 +++++++++--- drivers/gpu/drm/xe/xe_migrate.c | 25 +++++++++++++---- drivers/gpu/drm/xe/xe_migrate.h | 6 ++-- drivers/gpu/drm/xe/xe_svm.c | 49 +++++++++++++++++++++++++-------- include/drm/drm_pagemap.h | 17 ++++++++++-- 5 files changed, 88 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/drm_pagemap.c b/drivers/gpu/drm/drm_pagemap.c index 4cf8f54e5a27..ac3832f85190 100644 --- a/drivers/gpu/drm/drm_pagemap.c +++ b/drivers/gpu/drm/drm_pagemap.c @@ -3,6 +3,7 @@ * Copyright © 2024-2025 Intel Corporation */ +#include <linux/dma-fence.h> #include <linux/dma-mapping.h> #include <linux/migrate.h> #include <linux/pagemap.h> @@ -408,10 +409,14 @@ int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, drm_pagemap_get_devmem_page(page, zdd); } - err = ops->copy_to_devmem(pages, pagemap_addr, npages); + err = ops->copy_to_devmem(pages, pagemap_addr, npages, + devmem_allocation->pre_migrate_fence); if (err) goto err_finalize; + dma_fence_put(devmem_allocation->pre_migrate_fence); + devmem_allocation->pre_migrate_fence = NULL; + /* Upon success bind devmem allocation to range and zdd */ devmem_allocation->timeslice_expiration = get_jiffies_64() + msecs_to_jiffies(timeslice_ms); @@ -596,7 +601,7 @@ int drm_pagemap_evict_to_ram(struct drm_pagemap_devmem *devmem_allocation) for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -719,7 +724,7 @@ static int __drm_pagemap_migrate_to_ram(struct vm_area_struct *vas, for (i = 0; i < npages; ++i) pages[i] = migrate_pfn_to_page(migrate.src[i]); - err = ops->copy_to_ram(pages, pagemap_addr, npages); + err = ops->copy_to_ram(pages, pagemap_addr, npages, NULL); if (err) goto err_finalize; @@ -800,11 +805,14 @@ EXPORT_SYMBOL_GPL(drm_pagemap_pagemap_ops_get); * @ops: Pointer to the operations structure for GPU SVM device memory * @dpagemap: The struct drm_pagemap we're allocating from. * @size: Size of device memory allocation + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size) + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence) { init_completion(&devmem_allocation->detached); devmem_allocation->dev = dev; @@ -812,6 +820,7 @@ void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, devmem_allocation->ops = ops; devmem_allocation->dpagemap = dpagemap; devmem_allocation->size = size; + devmem_allocation->pre_migrate_fence = pre_migrate_fence; } EXPORT_SYMBOL_GPL(drm_pagemap_devmem_init); diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index f3b66b55acfb..284b575346ee 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -2113,6 +2113,7 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, unsigned long sram_offset, struct drm_pagemap_addr *sram_addr, u64 vram_addr, + struct dma_fence *deps, const enum xe_migrate_copy_dir dir) { struct xe_gt *gt = m->tile->primary_gt; @@ -2201,6 +2202,14 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, xe_sched_job_add_migrate_flush(job, MI_INVALIDATE_TLB); + if (deps && !dma_fence_is_signaled(deps)) { + dma_fence_get(deps); + err = drm_sched_job_add_dependency(&job->drm, deps); + if (err) + dma_fence_wait(deps, false); + err = 0; + } + mutex_lock(&m->job_mutex); xe_sched_job_arm(job); fence = dma_fence_get(&job->drm.s_fence->finished); @@ -2226,6 +2235,8 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, * @npages: Number of pages to migrate. * @src_addr: Array of DMA information (source of migrate) * @dst_addr: Device physical address of VRAM (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from an array dma addresses to a VRAM device physical address * @@ -2235,10 +2246,11 @@ static struct dma_fence *xe_migrate_vram(struct xe_migrate *m, struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr) + u64 dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, src_addr, dst_addr, - XE_MIGRATE_COPY_TO_VRAM); + deps, XE_MIGRATE_COPY_TO_VRAM); } /** @@ -2247,6 +2259,8 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, * @npages: Number of pages to migrate. * @src_addr: Device physical address of VRAM (source of migrate) * @dst_addr: Array of DMA information (destination of migrate) + * @deps: struct dma_fence representing the dependencies that need + * to be signaled before migration. * * Copy from a VRAM device physical address to an array dma addresses * @@ -2256,10 +2270,11 @@ struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr) + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps) { return xe_migrate_vram(m, npages * PAGE_SIZE, 0, dst_addr, src_addr, - XE_MIGRATE_COPY_TO_SRAM); + deps, XE_MIGRATE_COPY_TO_SRAM); } static void xe_migrate_dma_unmap(struct xe_device *xe, @@ -2435,7 +2450,7 @@ int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, __fence = xe_migrate_vram(m, current_bytes, (unsigned long)buf & ~PAGE_MASK, &pagemap_addr[current_page], - vram_addr, write ? + vram_addr, NULL, write ? XE_MIGRATE_COPY_TO_VRAM : XE_MIGRATE_COPY_TO_SRAM); if (IS_ERR(__fence)) { diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 464c05dde1ba..1522afb37dcf 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -116,12 +116,14 @@ int xe_migrate_init(struct xe_migrate *m); struct dma_fence *xe_migrate_to_vram(struct xe_migrate *m, unsigned long npages, struct drm_pagemap_addr *src_addr, - u64 dst_addr); + u64 dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_from_vram(struct xe_migrate *m, unsigned long npages, u64 src_addr, - struct drm_pagemap_addr *dst_addr); + struct drm_pagemap_addr *dst_addr, + struct dma_fence *deps); struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct xe_bo *src_bo, diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index bab8e6cbe53d..14a027b3ee6b 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -472,7 +472,8 @@ static void xe_svm_copy_us_stats_incr(struct xe_gt *gt, static int xe_svm_copy(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages, const enum xe_svm_copy_dir dir) + unsigned long npages, const enum xe_svm_copy_dir dir, + struct dma_fence *pre_migrate_fence) { struct xe_vram_region *vr = NULL; struct xe_gt *gt = NULL; @@ -561,7 +562,8 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_from_vram(vr->migrate, i - pos + incr, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld", @@ -570,13 +572,14 @@ static int xe_svm_copy(struct page **pages, __fence = xe_migrate_to_vram(vr->migrate, i - pos + incr, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -599,20 +602,22 @@ static int xe_svm_copy(struct page **pages, vram_addr, (u64)pagemap_addr[pos].addr, 1); __fence = xe_migrate_from_vram(vr->migrate, 1, vram_addr, - &pagemap_addr[pos]); + &pagemap_addr[pos], + pre_migrate_fence); } else { vm_dbg(&xe->drm, "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d", (u64)pagemap_addr[pos].addr, vram_addr, 1); __fence = xe_migrate_to_vram(vr->migrate, 1, &pagemap_addr[pos], - vram_addr); + vram_addr, + pre_migrate_fence); } if (IS_ERR(__fence)) { err = PTR_ERR(__fence); goto err_out; } - + pre_migrate_fence = NULL; dma_fence_put(fence); fence = __fence; } @@ -625,6 +630,8 @@ static int xe_svm_copy(struct page **pages, dma_fence_wait(fence, false); dma_fence_put(fence); } + if (pre_migrate_fence) + dma_fence_wait(pre_migrate_fence, false); /* * XXX: We can't derive the GT here (or anywhere in this functions, but @@ -641,16 +648,20 @@ static int xe_svm_copy(struct page **pages, static int xe_svm_copy_to_devmem(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_VRAM, + pre_migrate_fence); } static int xe_svm_copy_to_ram(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages) + unsigned long npages, + struct dma_fence *pre_migrate_fence) { - return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM); + return xe_svm_copy(pages, pagemap_addr, npages, XE_SVM_COPY_TO_SRAM, + pre_migrate_fence); } static struct xe_bo *to_xe_bo(struct drm_pagemap_devmem *devmem_allocation) @@ -663,6 +674,7 @@ static void xe_svm_devmem_release(struct drm_pagemap_devmem *devmem_allocation) struct xe_bo *bo = to_xe_bo(devmem_allocation); struct xe_device *xe = xe_bo_device(bo); + dma_fence_put(devmem_allocation->pre_migrate_fence); xe_bo_put_async(bo); xe_pm_runtime_put(xe); } @@ -857,6 +869,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long timeslice_ms) { struct xe_vram_region *vr = container_of(dpagemap, typeof(*vr), dpagemap); + struct dma_fence *pre_migrate_fence = NULL; struct xe_device *xe = vr->xe; struct device *dev = xe->drm.dev; struct drm_buddy_block *block; @@ -883,8 +896,20 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, break; } + /* Ensure that any clearing or async eviction will complete before migration. */ + if (!dma_resv_test_signaled(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL)) { + err = dma_resv_get_singleton(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + &pre_migrate_fence); + if (err) + dma_resv_wait_timeout(bo->ttm.base.resv, DMA_RESV_USAGE_KERNEL, + false, MAX_SCHEDULE_TIMEOUT); + else if (pre_migrate_fence) + dma_fence_enable_sw_signaling(pre_migrate_fence); + } + drm_pagemap_devmem_init(&bo->devmem_allocation, dev, mm, - &dpagemap_devmem_ops, dpagemap, end - start); + &dpagemap_devmem_ops, dpagemap, end - start, + pre_migrate_fence); blocks = &to_xe_ttm_vram_mgr_resource(bo->ttm.resource)->blocks; list_for_each_entry(block, blocks, link) diff --git a/include/drm/drm_pagemap.h b/include/drm/drm_pagemap.h index f6e7e234c089..70a7991f784f 100644 --- a/include/drm/drm_pagemap.h +++ b/include/drm/drm_pagemap.h @@ -8,6 +8,7 @@ #define NR_PAGES(order) (1U << (order)) +struct dma_fence; struct drm_pagemap; struct drm_pagemap_zdd; struct device; @@ -174,6 +175,8 @@ struct drm_pagemap_devmem_ops { * @pages: Pointer to array of device memory pages (destination) * @pagemap_addr: Pointer to array of DMA information (source) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to device memory. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -183,13 +186,16 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_devmem)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); /** * @copy_to_ram: Copy to system RAM (required for migration) * @pages: Pointer to array of device memory pages (source) * @pagemap_addr: Pointer to array of DMA information (destination) * @npages: Number of pages to copy + * @pre_migrate_fence: dma-fence to wait for before migration start. + * May be NULL. * * Copy pages to system RAM. If the order of a @pagemap_addr entry * is greater than 0, the entry is populated but subsequent entries @@ -199,7 +205,8 @@ struct drm_pagemap_devmem_ops { */ int (*copy_to_ram)(struct page **pages, struct drm_pagemap_addr *pagemap_addr, - unsigned long npages); + unsigned long npages, + struct dma_fence *pre_migrate_fence); }; /** @@ -212,6 +219,8 @@ struct drm_pagemap_devmem_ops { * @dpagemap: The struct drm_pagemap of the pages this allocation belongs to. * @size: Size of device memory allocation * @timeslice_expiration: Timeslice expiration in jiffies + * @pre_migrate_fence: Fence to wait for or pipeline behind before migration starts. + * (May be NULL). */ struct drm_pagemap_devmem { struct device *dev; @@ -221,6 +230,7 @@ struct drm_pagemap_devmem { struct drm_pagemap *dpagemap; size_t size; u64 timeslice_expiration; + struct dma_fence *pre_migrate_fence; }; int drm_pagemap_migrate_to_devmem(struct drm_pagemap_devmem *devmem_allocation, @@ -238,7 +248,8 @@ struct drm_pagemap *drm_pagemap_page_to_dpagemap(struct page *page); void drm_pagemap_devmem_init(struct drm_pagemap_devmem *devmem_allocation, struct device *dev, struct mm_struct *mm, const struct drm_pagemap_devmem_ops *ops, - struct drm_pagemap *dpagemap, size_t size); + struct drm_pagemap *dpagemap, size_t size, + struct dma_fence *pre_migrate_fence); int drm_pagemap_populate_mm(struct drm_pagemap *dpagemap, unsigned long start, unsigned long end, -- 2.51.1

5 days, 2 hours

1
0
0 0

[PATCH v6 01/24] drm/xe/svm: Fix a debug printout

by Thomas Hellström

Avoid spamming the log with drm_info(). Use drm_dbg() instead. Fixes: cc795e041034 ("drm/xe/svm: Make xe_svm_range_needs_migrate_to_vram() public") Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.17+ Signed-off-by: Thomas Hellström <thomas.hellstrom(a)linux.intel.com> Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray(a)intel.com> --- drivers/gpu/drm/xe/xe_svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c index 93550c7c84ac..bab8e6cbe53d 100644 --- a/drivers/gpu/drm/xe/xe_svm.c +++ b/drivers/gpu/drm/xe/xe_svm.c @@ -937,7 +937,7 @@ bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range, struct xe_vm xe_assert(vm->xe, IS_DGFX(vm->xe)); if (xe_svm_range_in_vram(range)) { - drm_info(&vm->xe->drm, "Range is already in VRAM\n"); + drm_dbg(&vm->xe->drm, "Range is already in VRAM\n"); return false; } -- 2.51.1

5 days, 2 hours

1
0
0 0

[PATCH 6.12 1/1] sched/rt: Fix race in push_rt_task

by Rajani Kantha

From: Harshit Agarwal <harshit(a)nutanix.com> [ Upstream commit 690e47d1403e90b7f2366f03b52ed3304194c793 ] Overview ======== When a CPU chooses to call push_rt_task and picks a task to push to another CPU's runqueue then it will call find_lock_lowest_rq method which would take a double lock on both CPUs' runqueues. If one of the locks aren't readily available, it may lead to dropping the current runqueue lock and reacquiring both the locks at once. During this window it is possible that the task is already migrated and is running on some other CPU. These cases are already handled. However, if the task is migrated and has already been executed and another CPU is now trying to wake it up (ttwu) such that it is queued again on the runqeue (on_rq is 1) and also if the task was run by the same CPU, then the current checks will pass even though the task was migrated out and is no longer in the pushable tasks list. Crashes ======= This bug resulted in quite a few flavors of crashes triggering kernel panics with various crash signatures such as assert failures, page faults, null pointer dereferences, and queue corruption errors all coming from scheduler itself. Some of the crashes: -> kernel BUG at kernel/sched/rt.c:1616! BUG_ON(idx >= MAX_RT_PRIO) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? pick_next_task_rt+0x6e/0x1d0 ? do_error_trap+0x64/0xa0 ? pick_next_task_rt+0x6e/0x1d0 ? exc_invalid_op+0x4c/0x60 ? pick_next_task_rt+0x6e/0x1d0 ? asm_exc_invalid_op+0x12/0x20 ? pick_next_task_rt+0x6e/0x1d0 __schedule+0x5cb/0x790 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: kernel NULL pointer dereference, address: 00000000000000c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? __warn+0x8a/0xe0 ? exc_page_fault+0x3d6/0x520 ? asm_exc_page_fault+0x1e/0x30 ? pick_next_task_rt+0xb5/0x1d0 ? pick_next_task_rt+0x8c/0x1d0 __schedule+0x583/0x7e0 ? update_ts_time_stats+0x55/0x70 schedule_idle+0x1e/0x40 do_idle+0x15e/0x200 cpu_startup_entry+0x19/0x20 start_secondary+0x117/0x160 secondary_startup_64_no_verify+0xb0/0xbb -> BUG: unable to handle page fault for address: ffff9464daea5900 kernel BUG at kernel/sched/rt.c:1861! BUG_ON(rq->cpu != task_cpu(p)) -> kernel BUG at kernel/sched/rt.c:1055! BUG_ON(!rq->nr_running) Call Trace: ? __die_body+0x1a/0x60 ? die+0x2a/0x50 ? do_trap+0x85/0x100 ? dequeue_top_rt_rq+0xa2/0xb0 ? do_error_trap+0x64/0xa0 ? dequeue_top_rt_rq+0xa2/0xb0 ? exc_invalid_op+0x4c/0x60 ? dequeue_top_rt_rq+0xa2/0xb0 ? asm_exc_invalid_op+0x12/0x20 ? dequeue_top_rt_rq+0xa2/0xb0 dequeue_rt_entity+0x1f/0x70 dequeue_task_rt+0x2d/0x70 __schedule+0x1a8/0x7e0 ? blk_finish_plug+0x25/0x40 schedule+0x3c/0xb0 futex_wait_queue_me+0xb6/0x120 futex_wait+0xd9/0x240 do_futex+0x344/0xa90 ? get_mm_exe_file+0x30/0x60 ? audit_exe_compare+0x58/0x70 ? audit_filter_rules.constprop.26+0x65e/0x1220 __x64_sys_futex+0x148/0x1f0 do_syscall_64+0x30/0x80 entry_SYSCALL_64_after_hwframe+0x62/0xc7 -> BUG: unable to handle page fault for address: ffff8cf3608bc2c0 Call Trace: ? __die_body+0x1a/0x60 ? no_context+0x183/0x350 ? spurious_kernel_fault+0x171/0x1c0 ? exc_page_fault+0x3b6/0x520 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? asm_exc_page_fault+0x1e/0x30 ? _cond_resched+0x15/0x30 ? futex_wait_queue_me+0xc8/0x120 ? futex_wait+0xd9/0x240 ? try_to_wake_up+0x1b8/0x490 ? futex_wake+0x78/0x160 ? do_futex+0xcd/0xa90 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? plist_del+0x6a/0xd0 ? plist_check_list+0x15/0x40 ? plist_check_list+0x2e/0x40 ? dequeue_pushable_task+0x20/0x70 ? __schedule+0x382/0x7e0 ? asm_sysvec_reschedule_ipi+0xa/0x20 ? schedule+0x3c/0xb0 ? exit_to_user_mode_prepare+0x9e/0x150 ? irqentry_exit_to_user_mode+0x5/0x30 ? asm_sysvec_reschedule_ipi+0x12/0x20 Above are some of the common examples of the crashes that were observed due to this issue. Details ======= Let's look at the following scenario to understand this race. 1) CPU A enters push_rt_task a) CPU A has chosen next_task = task p. b) CPU A calls find_lock_lowest_rq(Task p, CPU Z’s rq). c) CPU A identifies CPU X as a destination CPU (X < Z). d) CPU A enters double_lock_balance(CPU Z’s rq, CPU X’s rq). e) Since X is lower than Z, CPU A unlocks CPU Z’s rq. Someone else has locked CPU X’s rq, and thus, CPU A must wait. 2) At CPU Z a) Previous task has completed execution and thus, CPU Z enters schedule, locks its own rq after CPU A releases it. b) CPU Z dequeues previous task and begins executing task p. c) CPU Z unlocks its rq. d) Task p yields the CPU (ex. by doing IO or waiting to acquire a lock) which triggers the schedule function on CPU Z. e) CPU Z enters schedule again, locks its own rq, and dequeues task p. f) As part of dequeue, it sets p.on_rq = 0 and unlocks its rq. 3) At CPU B a) CPU B enters try_to_wake_up with input task p. b) Since CPU Z dequeued task p, p.on_rq = 0, and CPU B updates B.state = WAKING. c) CPU B via select_task_rq determines CPU Y as the target CPU. 4) The race a) CPU A acquires CPU X’s lock and relocks CPU Z. b) CPU A reads task p.cpu = Z and incorrectly concludes task p is still on CPU Z. c) CPU A failed to notice task p had been dequeued from CPU Z while CPU A was waiting for locks in double_lock_balance. If CPU A knew that task p had been dequeued, it would return NULL forcing push_rt_task to give up the task p's migration. d) CPU B updates task p.cpu = Y and calls ttwu_queue. e) CPU B locks Ys rq. CPU B enqueues task p onto Y and sets task p.on_rq = 1. f) CPU B unlocks CPU Y, triggering memory synchronization. g) CPU A reads task p.on_rq = 1, cementing its assumption that task p has not migrated. h) CPU A decides to migrate p to CPU X. This leads to A dequeuing p from Y's queue and various crashes down the line. Solution ======== The solution here is fairly simple. After obtaining the lock (at 4a), the check is enhanced to make sure that the task is still at the head of the pushable tasks list. If not, then it is anyway not suitable for being pushed out. Testing ======= The fix is tested on a cluster of 3 nodes, where the panics due to this are hit every couple of days. A fix similar to this was deployed on such cluster and was stable for more than 30 days. Co-developed-by: Jon Kohler <jon(a)nutanix.com> Signed-off-by: Jon Kohler <jon(a)nutanix.com> Co-developed-by: Gauri Patwardhan <gauri.patwardhan(a)nutanix.com> Signed-off-by: Gauri Patwardhan <gauri.patwardhan(a)nutanix.com> Co-developed-by: Rahul Chunduru <rahul.chunduru(a)nutanix.com> Signed-off-by: Rahul Chunduru <rahul.chunduru(a)nutanix.com> Signed-off-by: Harshit Agarwal <harshit(a)nutanix.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Reviewed-by: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Reviewed-by: Phil Auld <pauld(a)redhat.com> Tested-by: Will Ton <william.ton(a)nutanix.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20250225180553.167995-1-harshit@nutanix.com Signed-off-by: Rajani Kantha <681739313(a)139.com> --- kernel/sched/rt.c | 52 +++++++++++++++++++++++------------------------ 1 file changed, 25 insertions(+), 27 deletions(-) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 6ad6717084ed..c437a1502623 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1895,6 +1895,26 @@ static int find_lowest_rq(struct task_struct *task) return -1; } +static struct task_struct *pick_next_pushable_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_tasks(rq)) + return NULL; + + p = plist_first_entry(&rq->rt.pushable_tasks, + struct task_struct, pushable_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!task_on_rq_queued(p)); + BUG_ON(!rt_task(p)); + + return p; +} + /* Will lock the rq it finds */ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) { @@ -1925,18 +1945,16 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) /* * We had to unlock the run queue. In * the mean time, task could have - * migrated already or had its affinity changed. - * Also make sure that it wasn't scheduled on its rq. + * migrated already or had its affinity changed, + * therefore check if the task is still at the + * head of the pushable tasks list. * It is possible the task was scheduled, set * "migrate_disabled" and then got preempted, so we must * check the task migration disable flag here too. */ - if (unlikely(task_rq(task) != rq || + if (unlikely(is_migration_disabled(task) || !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) || - task_on_cpu(rq, task) || - !rt_task(task) || - is_migration_disabled(task) || - !task_on_rq_queued(task))) { + task != pick_next_pushable_task(rq))) { double_unlock_balance(rq, lowest_rq); lowest_rq = NULL; @@ -1956,26 +1974,6 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) return lowest_rq; } -static struct task_struct *pick_next_pushable_task(struct rq *rq) -{ - struct task_struct *p; - - if (!has_pushable_tasks(rq)) - return NULL; - - p = plist_first_entry(&rq->rt.pushable_tasks, - struct task_struct, pushable_tasks); - - BUG_ON(rq->cpu != task_cpu(p)); - BUG_ON(task_current(rq, p)); - BUG_ON(p->nr_cpus_allowed <= 1); - - BUG_ON(!task_on_rq_queued(p)); - BUG_ON(!rt_task(p)); - - return p; -} - /* * If the current CPU has more than one RT task, see if the non * running task can migrate over to a CPU that is running a task -- 2.17.1

5 days, 2 hours

1
1
0 0

[PATCH] mfd: omap-usb-host: fix OF populate on driver rebind

by Johan Hovold

Since commit c6e126de43e7 ("of: Keep track of populated platform devices") child devices will not be created by of_platform_populate() if the devices had previously been deregistered individually so that the OF_POPULATED flag is still set in the corresponding OF nodes. Switch to using of_platform_depopulate() instead of open coding so that the child devices are created if the driver is rebound. Fixes: c6e126de43e7 ("of: Keep track of populated platform devices") Cc: stable(a)vger.kernel.org # 3.16 Signed-off-by: Johan Hovold <johan(a)kernel.org> --- drivers/mfd/omap-usb-host.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mfd/omap-usb-host.c b/drivers/mfd/omap-usb-host.c index a77b6fc790f2..4d29a6e2ed87 100644 --- a/drivers/mfd/omap-usb-host.c +++ b/drivers/mfd/omap-usb-host.c @@ -819,8 +819,10 @@ static void usbhs_omap_remove(struct platform_device *pdev) { pm_runtime_disable(&pdev->dev); - /* remove children */ - device_for_each_child(&pdev->dev, NULL, usbhs_omap_remove_child); + if (pdev->dev.of_node) + of_platform_depopulate(&pdev->dev); + else + device_for_each_child(&pdev->dev, NULL, usbhs_omap_remove_child); } static const struct dev_pm_ops usbhsomap_dev_pm_ops = { -- 2.51.2

5 days, 2 hours

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror