January 2025 - Linux-stable-mirror

[PATCH 6.1.y] ext4: fix access to uninitialised lock in fc replay path

by Imkanmod Khan

From: "Luis Henriques (SUSE)" <luis.henriques(a)linux.dev> [ commit 23dfdb56581ad92a9967bcd720c8c23356af74c1 upstream ] The following kernel trace can be triggered with fstest generic/629 when executed against a filesystem with fast-commit feature enabled: INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 0 PID: 866 Comm: mount Not tainted 6.10.0+ #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x66/0x90 register_lock_class+0x759/0x7d0 __lock_acquire+0x85/0x2630 ? __find_get_block+0xb4/0x380 lock_acquire+0xd1/0x2d0 ? __ext4_journal_get_write_access+0xd5/0x160 _raw_spin_lock+0x33/0x40 ? __ext4_journal_get_write_access+0xd5/0x160 __ext4_journal_get_write_access+0xd5/0x160 ext4_reserve_inode_write+0x61/0xb0 __ext4_mark_inode_dirty+0x79/0x270 ? ext4_ext_replay_set_iblocks+0x2f8/0x450 ext4_ext_replay_set_iblocks+0x330/0x450 ext4_fc_replay+0x14c8/0x1540 ? jread+0x88/0x2e0 ? rcu_is_watching+0x11/0x40 do_one_pass+0x447/0xd00 jbd2_journal_recover+0x139/0x1b0 jbd2_journal_load+0x96/0x390 ext4_load_and_init_journal+0x253/0xd40 ext4_fill_super+0x2cc6/0x3180 ... In the replay path there's an attempt to lock sbi->s_bdev_wb_lock in function ext4_check_bdev_write_error(). Unfortunately, at this point this spinlock has not been initialized yet. Moving it's initialization to an earlier point in __ext4_fill_super() fixes this splat. Signed-off-by: Luis Henriques (SUSE) <luis.henriques(a)linux.dev> Link: https://patch.msgid.link/20240718094356.7863-1-luis.henriques@linux.dev Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Imkanmod Khan <imkanmodkhan(a)gmail.com> --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0b2591c07166..53f1deb049ec 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5264,6 +5264,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); + spin_lock_init(&sbi->s_bdev_wb_lock); + ext4_fast_commit_init(sb); sb->s_root = NULL; @@ -5514,7 +5516,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ - spin_lock_init(&sbi->s_bdev_wb_lock); errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, &sbi->s_bdev_wb_err); sb->s_bdev->bd_super = sb; -- 2.25.1

4 months, 1 week

2
1
0 0

[PATCH 6.6.y] ext4: fix access to uninitialised lock in fc replay path

by Imkanmod Khan

From: "Luis Henriques (SUSE)" <luis.henriques(a)linux.dev> [ commit 23dfdb56581ad92a9967bcd720c8c23356af74c1 upstream ] The following kernel trace can be triggered with fstest generic/629 when executed against a filesystem with fast-commit feature enabled: INFO: trying to register non-static key. The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator. CPU: 0 PID: 866 Comm: mount Not tainted 6.10.0+ #11 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.2-3-gd478f380-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x66/0x90 register_lock_class+0x759/0x7d0 __lock_acquire+0x85/0x2630 ? __find_get_block+0xb4/0x380 lock_acquire+0xd1/0x2d0 ? __ext4_journal_get_write_access+0xd5/0x160 _raw_spin_lock+0x33/0x40 ? __ext4_journal_get_write_access+0xd5/0x160 __ext4_journal_get_write_access+0xd5/0x160 ext4_reserve_inode_write+0x61/0xb0 __ext4_mark_inode_dirty+0x79/0x270 ? ext4_ext_replay_set_iblocks+0x2f8/0x450 ext4_ext_replay_set_iblocks+0x330/0x450 ext4_fc_replay+0x14c8/0x1540 ? jread+0x88/0x2e0 ? rcu_is_watching+0x11/0x40 do_one_pass+0x447/0xd00 jbd2_journal_recover+0x139/0x1b0 jbd2_journal_load+0x96/0x390 ext4_load_and_init_journal+0x253/0xd40 ext4_fill_super+0x2cc6/0x3180 ... In the replay path there's an attempt to lock sbi->s_bdev_wb_lock in function ext4_check_bdev_write_error(). Unfortunately, at this point this spinlock has not been initialized yet. Moving it's initialization to an earlier point in __ext4_fill_super() fixes this splat. Signed-off-by: Luis Henriques (SUSE) <luis.henriques(a)linux.dev> Link: https://patch.msgid.link/20240718094356.7863-1-luis.henriques@linux.dev Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Cc: stable(a)kernel.org Signed-off-by: Imkanmod Khan <imkanmodkhan(a)gmail.com> --- fs/ext4/super.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 71ced0ada9a2..f019ce64eba4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5366,6 +5366,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */ mutex_init(&sbi->s_orphan_lock); + spin_lock_init(&sbi->s_bdev_wb_lock); + ext4_fast_commit_init(sb); sb->s_root = NULL; @@ -5586,7 +5588,6 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) * Save the original bdev mapping's wb_err value which could be * used to detect the metadata async write error. */ - spin_lock_init(&sbi->s_bdev_wb_lock); errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, &sbi->s_bdev_wb_err); EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; -- 2.25.1

4 months, 1 week

2
1
0 0

[PATCH AUTOSEL 6.1 1/2] RDMA/efa: Reset device on probe failure

by Sasha Levin

From: Michael Margolin <mrgolin(a)amazon.com> [ Upstream commit 123c13f10ed3627ba112172d8bd122a72cae226d ] Make sure the device is being reset on driver exit whatever the reason is, to keep the device aligned and allow it to close shared resources (e.g. admin queue). Reviewed-by: Firas Jahjah <firasj(a)amazon.com> Reviewed-by: Yonatan Nachum <ynachum(a)amazon.com> Signed-off-by: Michael Margolin <mrgolin(a)amazon.com> Link: https://patch.msgid.link/20241225131548.15155-1-mrgolin@amazon.com Reviewed-by: Gal Pressman <gal.pressman(a)linux.dev> Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/infiniband/hw/efa/efa_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index 15ee920811187..924940ca9de0a 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -452,7 +452,6 @@ static void efa_ib_device_remove(struct efa_dev *dev) ibdev_info(&dev->ibdev, "Unregister ib device\n"); ib_unregister_device(&dev->ibdev); efa_destroy_eqs(dev); - efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL); efa_release_doorbell_bar(dev); } @@ -623,12 +622,14 @@ static struct efa_dev *efa_probe_device(struct pci_dev *pdev) return ERR_PTR(err); } -static void efa_remove_device(struct pci_dev *pdev) +static void efa_remove_device(struct pci_dev *pdev, + enum efa_regs_reset_reason_types reset_reason) { struct efa_dev *dev = pci_get_drvdata(pdev); struct efa_com_dev *edev; edev = &dev->edev; + efa_com_dev_reset(edev, reset_reason); efa_com_admin_destroy(edev); efa_free_irq(dev, &dev->admin_irq); efa_disable_msix(dev); @@ -656,7 +657,7 @@ static int efa_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_remove_device: - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_INIT_ERR); return err; } @@ -665,7 +666,7 @@ static void efa_remove(struct pci_dev *pdev) struct efa_dev *dev = pci_get_drvdata(pdev); efa_ib_device_remove(dev); - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_NORMAL); } static struct pci_driver efa_pci_driver = { -- 2.39.5

4 months, 1 week

1
1
0 0

[PATCH AUTOSEL 6.6 1/3] RDMA/efa: Reset device on probe failure

by Sasha Levin

From: Michael Margolin <mrgolin(a)amazon.com> [ Upstream commit 123c13f10ed3627ba112172d8bd122a72cae226d ] Make sure the device is being reset on driver exit whatever the reason is, to keep the device aligned and allow it to close shared resources (e.g. admin queue). Reviewed-by: Firas Jahjah <firasj(a)amazon.com> Reviewed-by: Yonatan Nachum <ynachum(a)amazon.com> Signed-off-by: Michael Margolin <mrgolin(a)amazon.com> Link: https://patch.msgid.link/20241225131548.15155-1-mrgolin@amazon.com Reviewed-by: Gal Pressman <gal.pressman(a)linux.dev> Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/infiniband/hw/efa/efa_main.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index 15ee920811187..924940ca9de0a 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -452,7 +452,6 @@ static void efa_ib_device_remove(struct efa_dev *dev) ibdev_info(&dev->ibdev, "Unregister ib device\n"); ib_unregister_device(&dev->ibdev); efa_destroy_eqs(dev); - efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_NORMAL); efa_release_doorbell_bar(dev); } @@ -623,12 +622,14 @@ static struct efa_dev *efa_probe_device(struct pci_dev *pdev) return ERR_PTR(err); } -static void efa_remove_device(struct pci_dev *pdev) +static void efa_remove_device(struct pci_dev *pdev, + enum efa_regs_reset_reason_types reset_reason) { struct efa_dev *dev = pci_get_drvdata(pdev); struct efa_com_dev *edev; edev = &dev->edev; + efa_com_dev_reset(edev, reset_reason); efa_com_admin_destroy(edev); efa_free_irq(dev, &dev->admin_irq); efa_disable_msix(dev); @@ -656,7 +657,7 @@ static int efa_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_remove_device: - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_INIT_ERR); return err; } @@ -665,7 +666,7 @@ static void efa_remove(struct pci_dev *pdev) struct efa_dev *dev = pci_get_drvdata(pdev); efa_ib_device_remove(dev); - efa_remove_device(pdev); + efa_remove_device(pdev, EFA_REGS_RESET_NORMAL); } static struct pci_driver efa_pci_driver = { -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 6.12 1/7] soc: qcom: pd-mapper: Add X1P42100

by Sasha Levin

From: Konrad Dybcio <konrad.dybcio(a)oss.qualcomm.com> [ Upstream commit e7282bf8a0e9bb8a4cb1be406674ff7bb7b264f2 ] X1P42100 is a cousin of X1E80100, and hence can make use of the latter's configuration. Do so. Signed-off-by: Konrad Dybcio <konrad.dybcio(a)oss.qualcomm.com> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Link: https://lore.kernel.org/r/20241221-topic-x1p4_soc-v1-3-55347831d73c@oss.qua… Signed-off-by: Bjorn Andersson <andersson(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/soc/qcom/qcom_pd_mapper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soc/qcom/qcom_pd_mapper.c b/drivers/soc/qcom/qcom_pd_mapper.c index 6e30f08761aa4..50aa54996901f 100644 --- a/drivers/soc/qcom/qcom_pd_mapper.c +++ b/drivers/soc/qcom/qcom_pd_mapper.c @@ -561,6 +561,7 @@ static const struct of_device_id qcom_pdm_domains[] __maybe_unused = { { .compatible = "qcom,sm8550", .data = sm8550_domains, }, { .compatible = "qcom,sm8650", .data = sm8550_domains, }, { .compatible = "qcom,x1e80100", .data = x1e80100_domains, }, + { .compatible = "qcom,x1p42100", .data = x1e80100_domains, }, {}, }; -- 2.39.5

4 months, 1 week

1
6
0 0

[PATCH AUTOSEL 6.12 01/31] drm/virtio: New fence for every plane update

by Sasha Levin

From: Dongwon Kim <dongwon.kim(a)intel.com> [ Upstream commit d3c55b8ab6fe5fa2e7ab02efd36d09c39ee5022f ] Having a fence linked to a virtio_gpu_framebuffer in the plane update sequence would cause conflict when several planes referencing the same framebuffer (e.g. Xorg screen covering multi-displays configured for an extended mode) and those planes are updated concurrently. So it is needed to allocate a fence for every plane state instead of the framebuffer. Signed-off-by: Dongwon Kim <dongwon.kim(a)intel.com> [dmitry.osipenko(a)collabora.com: rebase, fix up, edit commit message] Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Acked-by: Vivek Kasireddy <vivek.kasireddy(a)intel.com> Reviewed-by: Rob Clark <robdclark(a)gmail.com> Link: https://patchwork.freedesktop.org/patch/msgid/20241020230803.247419-2-dmitr… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/virtio/virtgpu_drv.h | 7 ++++ drivers/gpu/drm/virtio/virtgpu_plane.c | 58 +++++++++++++++++--------- 2 files changed, 46 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 64c236169db88..5dc8eeaf7123c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -194,6 +194,13 @@ struct virtio_gpu_framebuffer { #define to_virtio_gpu_framebuffer(x) \ container_of(x, struct virtio_gpu_framebuffer, base) +struct virtio_gpu_plane_state { + struct drm_plane_state base; + struct virtio_gpu_fence *fence; +}; +#define to_virtio_gpu_plane_state(x) \ + container_of(x, struct virtio_gpu_plane_state, base) + struct virtio_gpu_queue { struct virtqueue *vq; spinlock_t qlock; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index a72a2dbda031c..7acd38b962c62 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -66,11 +66,28 @@ uint32_t virtio_gpu_translate_format(uint32_t drm_fourcc) return format; } +static struct +drm_plane_state *virtio_gpu_plane_duplicate_state(struct drm_plane *plane) +{ + struct virtio_gpu_plane_state *new; + + if (WARN_ON(!plane->state)) + return NULL; + + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return NULL; + + __drm_atomic_helper_plane_duplicate_state(plane, &new->base); + + return &new->base; +} + static const struct drm_plane_funcs virtio_gpu_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, .reset = drm_atomic_helper_plane_reset, - .atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state, + .atomic_duplicate_state = virtio_gpu_plane_duplicate_state, .atomic_destroy_state = drm_atomic_helper_plane_destroy_state, }; @@ -138,11 +155,13 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); - if (vgfb->fence) { + if (vgplane_st->fence) { struct virtio_gpu_object_array *objs; objs = virtio_gpu_array_alloc(1); @@ -151,13 +170,11 @@ static void virtio_gpu_resource_flush(struct drm_plane *plane, virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); virtio_gpu_array_lock_resv(objs); virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, - width, height, objs, vgfb->fence); + width, height, objs, + vgplane_st->fence); virtio_gpu_notify(vgdev); - - dma_fence_wait_timeout(&vgfb->fence->f, true, + dma_fence_wait_timeout(&vgplane_st->fence->f, true, msecs_to_jiffies(50)); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; } else { virtio_gpu_cmd_resource_flush(vgdev, bo->hw_res_handle, x, y, width, height, NULL, NULL); @@ -247,20 +264,23 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, struct drm_device *dev = plane->dev; struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo; if (!new_state->fb) return 0; vgfb = to_virtio_gpu_framebuffer(new_state->fb); + vgplane_st = to_virtio_gpu_plane_state(new_state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); if (!bo || (plane->type == DRM_PLANE_TYPE_PRIMARY && !bo->guest_blob)) return 0; - if (bo->dumb && (plane->state->fb != new_state->fb)) { - vgfb->fence = virtio_gpu_fence_alloc(vgdev, vgdev->fence_drv.context, + if (bo->dumb) { + vgplane_st->fence = virtio_gpu_fence_alloc(vgdev, + vgdev->fence_drv.context, 0); - if (!vgfb->fence) + if (!vgplane_st->fence) return -ENOMEM; } @@ -270,15 +290,15 @@ static int virtio_gpu_plane_prepare_fb(struct drm_plane *plane, static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, struct drm_plane_state *state) { - struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; if (!state->fb) return; - vgfb = to_virtio_gpu_framebuffer(state->fb); - if (vgfb->fence) { - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + vgplane_st = to_virtio_gpu_plane_state(state); + if (vgplane_st->fence) { + dma_fence_put(&vgplane_st->fence->f); + vgplane_st->fence = NULL; } } @@ -291,6 +311,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_output *output = NULL; struct virtio_gpu_framebuffer *vgfb; + struct virtio_gpu_plane_state *vgplane_st; struct virtio_gpu_object *bo = NULL; uint32_t handle; @@ -303,6 +324,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (plane->state->fb) { vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgplane_st = to_virtio_gpu_plane_state(plane->state); bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]); handle = bo->hw_res_handle; } else { @@ -322,11 +344,9 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, (vgdev, 0, plane->state->crtc_w, plane->state->crtc_h, - 0, 0, objs, vgfb->fence); + 0, 0, objs, vgplane_st->fence); virtio_gpu_notify(vgdev); - dma_fence_wait(&vgfb->fence->f, true); - dma_fence_put(&vgfb->fence->f); - vgfb->fence = NULL; + dma_fence_wait(&vgplane_st->fence->f, true); } if (plane->state->fb != old_state->fb) { -- 2.39.5

4 months, 1 week

2
31
0 0

[PATCH AUTOSEL 5.4] tool api fs: Correctly encode errno for read/write open failures

by Sasha Levin

From: Ian Rogers <irogers(a)google.com> [ Upstream commit 05be17eed774aaf56f6b1e12714325ca3a266c04 ] Switch from returning -1 to -errno so that callers can determine types of failure. Reviewed-by: Namhyung Kim <namhyung(a)kernel.org> Signed-off-by: Ian Rogers <irogers(a)google.com> Acked-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Athira Rajeev <atrajeev(a)linux.vnet.ibm.com> Cc: Ben Gainey <ben.gainey(a)arm.com> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Dominique Martinet <asmadeus(a)codewreck.org> Cc: Ilkka Koskinen <ilkka(a)os.amperecomputing.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: James Clark <james.clark(a)linaro.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Kan Liang <kan.liang(a)linux.intel.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paran Lee <p4ranlee(a)gmail.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Steinar H. Gunderson <sesse(a)google.com> Cc: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Cc: Thomas Falcon <thomas.falcon(a)intel.com> Cc: Weilin Wang <weilin.wang(a)intel.com> Cc: Yang Jihong <yangjihong(a)bytedance.com> Cc: Yang Li <yang.lee(a)linux.alibaba.com> Cc: Ze Gao <zegao2021(a)gmail.com> Cc: Zixian Cai <fzczx123(a)gmail.com> Cc: zhaimingbing <zhaimingbing(a)cmss.chinamobile.com> Link: https://lore.kernel.org/r/20241118225345.889810-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/lib/api/fs/fs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 4cc69675c2a9a..234c882f9029c 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -323,7 +323,7 @@ int filename__read_int(const char *filename, int *value) int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = atoi(line); @@ -341,7 +341,7 @@ static int filename__read_ull_base(const char *filename, int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = strtoull(line, NULL, base); @@ -428,7 +428,7 @@ int filename__write_int(const char *filename, int value) char buf[64]; if (fd < 0) - return err; + return -errno; sprintf(buf, "%d", value); if (write(fd, buf, sizeof(buf)) == sizeof(buf)) -- 2.39.5

4 months, 1 week

1
0
0 0

[PATCH AUTOSEL 5.10 1/2] tool api fs: Correctly encode errno for read/write open failures

by Sasha Levin

From: Ian Rogers <irogers(a)google.com> [ Upstream commit 05be17eed774aaf56f6b1e12714325ca3a266c04 ] Switch from returning -1 to -errno so that callers can determine types of failure. Reviewed-by: Namhyung Kim <namhyung(a)kernel.org> Signed-off-by: Ian Rogers <irogers(a)google.com> Acked-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Athira Rajeev <atrajeev(a)linux.vnet.ibm.com> Cc: Ben Gainey <ben.gainey(a)arm.com> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Dominique Martinet <asmadeus(a)codewreck.org> Cc: Ilkka Koskinen <ilkka(a)os.amperecomputing.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: James Clark <james.clark(a)linaro.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Kan Liang <kan.liang(a)linux.intel.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paran Lee <p4ranlee(a)gmail.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Steinar H. Gunderson <sesse(a)google.com> Cc: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Cc: Thomas Falcon <thomas.falcon(a)intel.com> Cc: Weilin Wang <weilin.wang(a)intel.com> Cc: Yang Jihong <yangjihong(a)bytedance.com> Cc: Yang Li <yang.lee(a)linux.alibaba.com> Cc: Ze Gao <zegao2021(a)gmail.com> Cc: Zixian Cai <fzczx123(a)gmail.com> Cc: zhaimingbing <zhaimingbing(a)cmss.chinamobile.com> Link: https://lore.kernel.org/r/20241118225345.889810-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/lib/api/fs/fs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 82f53d81a7a78..a0a6a907315f0 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -323,7 +323,7 @@ int filename__read_int(const char *filename, int *value) int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = atoi(line); @@ -341,7 +341,7 @@ static int filename__read_ull_base(const char *filename, int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = strtoull(line, NULL, base); @@ -428,7 +428,7 @@ int filename__write_int(const char *filename, int value) char buf[64]; if (fd < 0) - return err; + return -errno; sprintf(buf, "%d", value); if (write(fd, buf, sizeof(buf)) == sizeof(buf)) -- 2.39.5

4 months, 1 week

1
1
0 0

[PATCH AUTOSEL 5.15 1/3] tool api fs: Correctly encode errno for read/write open failures

by Sasha Levin

From: Ian Rogers <irogers(a)google.com> [ Upstream commit 05be17eed774aaf56f6b1e12714325ca3a266c04 ] Switch from returning -1 to -errno so that callers can determine types of failure. Reviewed-by: Namhyung Kim <namhyung(a)kernel.org> Signed-off-by: Ian Rogers <irogers(a)google.com> Acked-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Cc: Adrian Hunter <adrian.hunter(a)intel.com> Cc: Alexander Shishkin <alexander.shishkin(a)linux.intel.com> Cc: Andi Kleen <ak(a)linux.intel.com> Cc: Athira Rajeev <atrajeev(a)linux.vnet.ibm.com> Cc: Ben Gainey <ben.gainey(a)arm.com> Cc: Colin Ian King <colin.i.king(a)gmail.com> Cc: Dominique Martinet <asmadeus(a)codewreck.org> Cc: Ilkka Koskinen <ilkka(a)os.amperecomputing.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: James Clark <james.clark(a)linaro.org> Cc: Jiri Olsa <jolsa(a)kernel.org> Cc: Kan Liang <kan.liang(a)linux.intel.com> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Oliver Upton <oliver.upton(a)linux.dev> Cc: Paran Lee <p4ranlee(a)gmail.com> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Steinar H. Gunderson <sesse(a)google.com> Cc: Steven Rostedt (VMware) <rostedt(a)goodmis.org> Cc: Thomas Falcon <thomas.falcon(a)intel.com> Cc: Weilin Wang <weilin.wang(a)intel.com> Cc: Yang Jihong <yangjihong(a)bytedance.com> Cc: Yang Li <yang.lee(a)linux.alibaba.com> Cc: Ze Gao <zegao2021(a)gmail.com> Cc: Zixian Cai <fzczx123(a)gmail.com> Cc: zhaimingbing <zhaimingbing(a)cmss.chinamobile.com> Link: https://lore.kernel.org/r/20241118225345.889810-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- tools/lib/api/fs/fs.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c index 82f53d81a7a78..a0a6a907315f0 100644 --- a/tools/lib/api/fs/fs.c +++ b/tools/lib/api/fs/fs.c @@ -323,7 +323,7 @@ int filename__read_int(const char *filename, int *value) int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = atoi(line); @@ -341,7 +341,7 @@ static int filename__read_ull_base(const char *filename, int fd = open(filename, O_RDONLY), err = -1; if (fd < 0) - return -1; + return -errno; if (read(fd, line, sizeof(line)) > 0) { *value = strtoull(line, NULL, base); @@ -428,7 +428,7 @@ int filename__write_int(const char *filename, int value) char buf[64]; if (fd < 0) - return err; + return -errno; sprintf(buf, "%d", value); if (write(fd, buf, sizeof(buf)) == sizeof(buf)) -- 2.39.5

4 months, 1 week

1
2
0 0

[PATCH AUTOSEL 6.1 1/8] x86/kexec: Allocate PGD for x86_64 transition page tables separately

by Sasha Levin

From: David Woodhouse <dwmw(a)amazon.co.uk> [ Upstream commit 4b5bc2ec9a239bce261ffeafdd63571134102323 ] Now that the following fix: d0ceea662d45 ("x86/mm: Add _PAGE_NOPTISHADOW bit to avoid updating userspace page tables") stops kernel_ident_mapping_init() from scribbling over the end of a 4KiB PGD by assuming the following 4KiB will be a userspace PGD, there's no good reason for the kexec PGD to be part of a single 8KiB allocation with the control_code_page. ( It's not clear that that was the reason for x86_64 kexec doing it that way in the first place either; there were no comments to that effect and it seems to have been the case even before PTI came along. It looks like it was just a happy accident which prevented memory corruption on kexec. ) Either way, it definitely isn't needed now. Just allocate the PGD separately on x86_64, like i386 already does. Signed-off-by: David Woodhouse <dwmw(a)amazon.co.uk> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Cc: Baoquan He <bhe(a)redhat.com> Cc: Vivek Goyal <vgoyal(a)redhat.com> Cc: Dave Young <dyoung(a)redhat.com> Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Ard Biesheuvel <ardb(a)kernel.org> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Link: https://lore.kernel.org/r/20241205153343.3275139-6-dwmw2@infradead.org Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- arch/x86/include/asm/kexec.h | 18 +++++++++--- arch/x86/kernel/machine_kexec_64.c | 45 ++++++++++++++++-------------- 2 files changed, 38 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index 256eee99afc8f..e2e1ec99c9998 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -16,6 +16,7 @@ # define PAGES_NR 4 #endif +# define KEXEC_CONTROL_PAGE_SIZE 4096 # define KEXEC_CONTROL_CODE_MAX_SIZE 2048 #ifndef __ASSEMBLY__ @@ -44,7 +45,6 @@ struct kimage; /* Maximum address we can use for the control code buffer */ # define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE -# define KEXEC_CONTROL_PAGE_SIZE 4096 /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_386 @@ -59,9 +59,6 @@ struct kimage; /* Maximum address we can use for the control pages */ # define KEXEC_CONTROL_MEMORY_LIMIT (MAXMEM-1) -/* Allocate one page for the pdp and the second for the code */ -# define KEXEC_CONTROL_PAGE_SIZE (4096UL + 4096UL) - /* The native architecture */ # define KEXEC_ARCH KEXEC_ARCH_X86_64 #endif @@ -146,6 +143,19 @@ struct kimage_arch { }; #else struct kimage_arch { + /* + * This is a kimage control page, as it must not overlap with either + * source or destination address ranges. + */ + pgd_t *pgd; + /* + * The virtual mapping of the control code page itself is used only + * during the transition, while the current kernel's pages are all + * in place. Thus the intermediate page table pages used to map it + * are not control pages, but instead just normal pages obtained + * with get_zeroed_page(). And have to be tracked (below) so that + * they can be freed. + */ p4d_t *p4d; pud_t *pud; pmd_t *pmd; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 24b6eaacc81eb..5d61a342871b5 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -149,7 +149,8 @@ static void free_transition_pgtable(struct kimage *image) image->arch.pte = NULL; } -static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) +static int init_transition_pgtable(struct kimage *image, pgd_t *pgd, + unsigned long control_page) { pgprot_t prot = PAGE_KERNEL_EXEC_NOENC; unsigned long vaddr, paddr; @@ -160,7 +161,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd) pte_t *pte; vaddr = (unsigned long)relocate_kernel; - paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE); + paddr = control_page; pgd += pgd_index(vaddr); if (!pgd_present(*pgd)) { p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL); @@ -219,7 +220,7 @@ static void *alloc_pgt_page(void *data) return p; } -static int init_pgtable(struct kimage *image, unsigned long start_pgtable) +static int init_pgtable(struct kimage *image, unsigned long control_page) { struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, @@ -228,12 +229,12 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) .kernpg_flag = _KERNPG_TABLE_NOENC, }; unsigned long mstart, mend; - pgd_t *level4p; int result; int i; - level4p = (pgd_t *)__va(start_pgtable); - clear_page(level4p); + image->arch.pgd = alloc_pgt_page(image); + if (!image->arch.pgd) + return -ENOMEM; if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { info.page_flag |= _PAGE_ENC; @@ -247,8 +248,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = pfn_mapped[i].start << PAGE_SHIFT; mend = pfn_mapped[i].end << PAGE_SHIFT; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; } @@ -263,8 +264,8 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) mstart = image->segment[i].mem; mend = mstart + image->segment[i].memsz; - result = kernel_ident_mapping_init(&info, - level4p, mstart, mend); + result = kernel_ident_mapping_init(&info, image->arch.pgd, + mstart, mend); if (result) return result; @@ -274,15 +275,19 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable) * Prepare EFI systab and ACPI tables for kexec kernel since they are * not covered by pfn_mapped. */ - result = map_efi_systab(&info, level4p); + result = map_efi_systab(&info, image->arch.pgd); if (result) return result; - result = map_acpi_tables(&info, level4p); + result = map_acpi_tables(&info, image->arch.pgd); if (result) return result; - return init_transition_pgtable(image, level4p); + /* + * This must be last because the intermediate page table pages it + * allocates will not be control pages and may overlap the image. + */ + return init_transition_pgtable(image, image->arch.pgd, control_page); } static void load_segments(void) @@ -299,14 +304,14 @@ static void load_segments(void) int machine_kexec_prepare(struct kimage *image) { - unsigned long start_pgtable; + unsigned long control_page; int result; /* Calculate the offsets */ - start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT; + control_page = page_to_pfn(image->control_code_page) << PAGE_SHIFT; /* Setup the identity mapped 64bit page table */ - result = init_pgtable(image, start_pgtable); + result = init_pgtable(image, control_page); if (result) return result; @@ -353,13 +358,12 @@ void machine_kexec(struct kimage *image) #endif } - control_page = page_address(image->control_code_page) + PAGE_SIZE; + control_page = page_address(image->control_code_page); __memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page); page_list[VA_CONTROL_PAGE] = (unsigned long)control_page; - page_list[PA_TABLE_PAGE] = - (unsigned long)__pa(page_address(image->control_code_page)); + page_list[PA_TABLE_PAGE] = (unsigned long)__pa(image->arch.pgd); if (image->type == KEXEC_TYPE_DEFAULT) page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) @@ -578,8 +582,7 @@ static void kexec_mark_crashkres(bool protect) /* Don't touch the control code page used in crash_kexec().*/ control = PFN_PHYS(page_to_pfn(kexec_crash_image->control_code_page)); - /* Control code page is located in the 2nd page. */ - kexec_mark_range(crashk_res.start, control + PAGE_SIZE - 1, protect); + kexec_mark_range(crashk_res.start, control - 1, protect); control += KEXEC_CONTROL_PAGE_SIZE; kexec_mark_range(control, crashk_res.end, protect); } -- 2.39.5

4 months, 1 week

1
7
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror January 2025