February 2025 - Linux-stable-mirror

+ mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon: avoid applying DAMOS action to same entity multiple times has been added to the -mm mm-unstable branch. Its filename is mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon: avoid applying DAMOS action to same entity multiple times Date: Fri, 7 Feb 2025 13:20:33 -0800 'paddr' DAMON operations set can apply a DAMOS scheme's action to a large folio multiple times in single DAMOS-regions-walk if the folio is laid on multiple DAMON regions. Add a field for DAMOS scheme object that can be used by the underlying ops to know what was the last entity that the scheme's action has applied. The core layer unsets the field when each DAMOS-regions-walk is done for the given scheme. And update 'paddr' ops to use the infrastructure to avoid the problem. Link: https://lkml.kernel.org/r/20250207212033.45269-3-sj@kernel.org Fixes: 57223ac29584 ("mm/damon/paddr: support the pageout scheme") Signed-off-by: SeongJae Park <sj(a)kernel.org> Reported-by: Usama Arif <usamaarif642(a)gmail.com> Closes: https://lore.kernel.org/20250203225604.44742-3-usamaarif642@gmail.com Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/damon.h | 11 +++++++++++ mm/damon/core.c | 1 + mm/damon/paddr.c | 39 +++++++++++++++++++++++++++------------ 3 files changed, 39 insertions(+), 12 deletions(-) --- a/include/linux/damon.h~mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times +++ a/include/linux/damon.h @@ -432,6 +432,7 @@ struct damos_access_pattern { * @wmarks: Watermarks for automated (in)activation of this scheme. * @target_nid: Destination node if @action is "migrate_{hot,cold}". * @filters: Additional set of &struct damos_filter for &action. + * @last_applied: Last @action applied ops-managing entity. * @stat: Statistics of this scheme. * @list: List head for siblings. * @@ -454,6 +455,15 @@ struct damos_access_pattern { * implementation could check pages of the region and skip &action to respect * &filters * + * The minimum entity that @action can be applied depends on the underlying + * &struct damon_operations. Since it may not be aligned with the core layer + * abstract, namely &struct damon_region, &struct damon_operations could apply + * @action to same entity multiple times. Large folios that underlying on + * multiple &struct damon region objects could be such examples. The &struct + * damon_operations can use @last_applied to avoid that. DAMOS core logic + * unsets @last_applied when each regions walking for applying the scheme is + * finished. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -477,6 +487,7 @@ struct damos { int target_nid; }; struct list_head filters; + void *last_applied; struct damos_stat stat; struct list_head list; }; --- a/mm/damon/core.c~mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times +++ a/mm/damon/core.c @@ -1851,6 +1851,7 @@ static void kdamond_apply_schemes(struct s->next_apply_sis = c->passed_sample_intervals + (s->apply_interval_us ? s->apply_interval_us : c->attrs.aggr_interval) / sample_interval; + s->last_applied = NULL; } } --- a/mm/damon/paddr.c~mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times +++ a/mm/damon/paddr.c @@ -243,6 +243,17 @@ static bool damos_pa_filter_out(struct d return false; } +static bool damon_pa_invalid_damos_folio(struct folio *folio, struct damos *s) +{ + if (!folio) + return true; + if (folio == s->last_applied) { + folio_put(folio); + return true; + } + return false; +} + static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s, unsigned long *sz_filter_passed) { @@ -250,6 +261,7 @@ static unsigned long damon_pa_pageout(st LIST_HEAD(folio_list); bool install_young_filter = true; struct damos_filter *filter; + struct folio *folio; /* check access in page level again by default */ damos_for_each_filter(filter, s) { @@ -268,9 +280,8 @@ static unsigned long damon_pa_pageout(st addr = r->ar.start; while (addr < r->ar.end) { - struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - - if (!folio) { + folio = damon_get_folio(PHYS_PFN(addr)); + if (damon_pa_invalid_damos_folio(folio, s)) { addr += PAGE_SIZE; continue; } @@ -296,6 +307,7 @@ put_folio: damos_destroy_filter(filter); applied = reclaim_pages(&folio_list); cond_resched(); + s->last_applied = folio; return applied * PAGE_SIZE; } @@ -304,12 +316,12 @@ static inline unsigned long damon_pa_mar unsigned long *sz_filter_passed) { unsigned long addr, applied = 0; + struct folio *folio; addr = r->ar.start; while (addr < r->ar.end) { - struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - - if (!folio) { + folio = damon_get_folio(PHYS_PFN(addr)); + if (damon_pa_invalid_damos_folio(folio, s)) { addr += PAGE_SIZE; continue; } @@ -328,6 +340,7 @@ put_folio: addr += folio_size(folio); folio_put(folio); } + s->last_applied = folio; return applied * PAGE_SIZE; } @@ -471,12 +484,12 @@ static unsigned long damon_pa_migrate(st { unsigned long addr, applied; LIST_HEAD(folio_list); + struct folio *folio; addr = r->ar.start; while (addr < r->ar.end) { - struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - - if (!folio) { + folio = damon_get_folio(PHYS_PFN(addr)); + if (damon_pa_invalid_damos_folio(folio, s)) { addr += PAGE_SIZE; continue; } @@ -495,6 +508,7 @@ put_folio: } applied = damon_pa_migrate_pages(&folio_list, s->target_nid); cond_resched(); + s->last_applied = folio; return applied * PAGE_SIZE; } @@ -512,15 +526,15 @@ static unsigned long damon_pa_stat(struc { unsigned long addr; LIST_HEAD(folio_list); + struct folio *folio; if (!damon_pa_scheme_has_filter(s)) return 0; addr = r->ar.start; while (addr < r->ar.end) { - struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - - if (!folio) { + folio = damon_get_folio(PHYS_PFN(addr)); + if (damon_pa_invalid_damos_folio(folio, s)) { addr += PAGE_SIZE; continue; } @@ -530,6 +544,7 @@ static unsigned long damon_pa_stat(struc addr += folio_size(folio); folio_put(folio); } + s->last_applied = folio; return 0; } _ Patches currently in -mm which might be from sj(a)kernel.org are mm-madvise-split-out-mmap-locking-operations-for-madvise.patch mm-madvise-split-out-madvise-input-validity-check.patch mm-madvise-split-out-madvise-behavior-execution.patch mm-madvise-remove-redundant-mmap_lock-operations-from-process_madvise.patch mm-damon-avoid-applying-damos-action-to-same-entity-multiple-times.patch

6 months, 1 week

1
0
0 0

+ mm-damon-ops-have-damon_get_folio-return-folio-even-for-tail-pages.patch added to mm-unstable branch

by Andrew Morton

The patch titled Subject: mm/damon/ops: have damon_get_folio return folio even for tail pages has been added to the -mm mm-unstable branch. Its filename is mm-damon-ops-have-damon_get_folio-return-folio-even-for-tail-pages.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Usama Arif <usamaarif642(a)gmail.com> Subject: mm/damon/ops: have damon_get_folio return folio even for tail pages Date: Fri, 7 Feb 2025 13:20:32 -0800 Patch series "mm/damon/paddr: fix large folios access and schemes handling". DAMON operations set for physical address space, namely 'paddr', treats tail pages as unaccessed always. It can also apply DAMOS action to a large folio multiple times within single DAMOS' regions walking. As a result, the monitoring output has poor quality and DAMOS works in unexpected ways when large folios are being used. Fix those. The patches were parts of Usama's hugepage_size DAMOS filter patch series[1]. The first fix has collected from there with a slight commit message change for the subject prefix. The second fix is re-written by SJ and posted as an RFC before this series. The second one also got a slight commit message change for the subject prefix. [1] https://lore.kernel.org/20250203225604.44742-1-usamaarif642@gmail.com [2] https://lore.kernel.org/20250206231103.38298-1-sj@kernel.org This patch (of 2): This effectively adds support for large folios in damon for paddr, as damon_pa_mkold/young won't get a null folio from this function and won't ignore it, hence access will be checked and reported. This also means that larger folios will be considered for different DAMOS actions like pageout, prioritization and migration. As these DAMOS actions will consider larger folios, iterate through the region at folio_size and not PAGE_SIZE intervals. This should not have an affect on vaddr, as damon_young_pmd_entry considers pmd entries. Link: https://lkml.kernel.org/r/20250207212033.45269-1-sj@kernel.org Link: https://lkml.kernel.org/r/20250207212033.45269-2-sj@kernel.org Fixes: a28397beb55b ("mm/damon: implement primitives for physical address space monitoring") Signed-off-by: Usama Arif <usamaarif642(a)gmail.com> Signed-off-by: SeongJae Park <sj(a)kernel.org> Reviewed-by: SeongJae Park <sj(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/damon/ops-common.c | 2 +- mm/damon/paddr.c | 24 ++++++++++++++++++------ 2 files changed, 19 insertions(+), 7 deletions(-) --- a/mm/damon/ops-common.c~mm-damon-ops-have-damon_get_folio-return-folio-even-for-tail-pages +++ a/mm/damon/ops-common.c @@ -24,7 +24,7 @@ struct folio *damon_get_folio(unsigned l struct page *page = pfn_to_online_page(pfn); struct folio *folio; - if (!page || PageTail(page)) + if (!page) return NULL; folio = page_folio(page); --- a/mm/damon/paddr.c~mm-damon-ops-have-damon_get_folio-return-folio-even-for-tail-pages +++ a/mm/damon/paddr.c @@ -266,11 +266,14 @@ static unsigned long damon_pa_pageout(st damos_add_filter(s, filter); } - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -286,6 +289,7 @@ static unsigned long damon_pa_pageout(st else list_add(&folio->lru, &folio_list); put_folio: + addr += folio_size(folio); folio_put(folio); } if (install_young_filter) @@ -301,11 +305,14 @@ static inline unsigned long damon_pa_mar { unsigned long addr, applied = 0; - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -318,6 +325,7 @@ static inline unsigned long damon_pa_mar folio_deactivate(folio); applied += folio_nr_pages(folio); put_folio: + addr += folio_size(folio); folio_put(folio); } return applied * PAGE_SIZE; @@ -464,11 +472,14 @@ static unsigned long damon_pa_migrate(st unsigned long addr, applied; LIST_HEAD(folio_list); - for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + addr = r->ar.start; + while (addr < r->ar.end) { struct folio *folio = damon_get_folio(PHYS_PFN(addr)); - if (!folio) + if (!folio) { + addr += PAGE_SIZE; continue; + } if (damos_pa_filter_out(s, folio)) goto put_folio; @@ -479,6 +490,7 @@ static unsigned long damon_pa_migrate(st goto put_folio; list_add(&folio->lru, &folio_list); put_folio: + addr += folio_size(folio); folio_put(folio); } applied = damon_pa_migrate_pages(&folio_list, s->target_nid); _ Patches currently in -mm which might be from usamaarif642(a)gmail.com are mm-damon-ops-have-damon_get_folio-return-folio-even-for-tail-pages.patch

6 months, 1 week

1
0
0 0

[PATCH v3 0/2] rust: lockdep: Fix soundness issue affecting LockClassKeys

by Mitchell Levy

This series is aimed at fixing a soundness issue with how dynamically allocated LockClassKeys are handled. Currently, LockClassKeys can be used without being Pin'd, which can break lockdep since it relies on address stability. Similarly, these keys are not automatically (de)registered with lockdep. At the suggestion of Alice Ryhl, this series includes a patch for -stable kernels that disables dynamically allocated keys. This prevents backported patches from using the unsound implementation. Currently, this series requires that all dynamically allocated LockClassKeys have a lifetime of 'static (i.e., they must be leaked after allocation). This is because Lock does not currently keep a reference to the LockClassKey, instead passing it to C via FFI. This causes a problem because the rust compiler would allow creating a 'static Lock with a 'a LockClassKey (with 'a < 'static) while C would expect the LockClassKey to live as long as the lock. This problem represents an avenue for future work. --- Changes in v3: - Rebased on rust-next - Fixed clippy/compiler warninings (Thanks Boqun Feng) - Link to v2: https://lore.kernel.org/r/20241219-rust-lockdep-v2-0-f65308fbc5ca@gmail.com Changes in v2: - Dropped formatting change that's already fixed upstream (Thanks Dirk Behme). - Moved safety comment to the right point in the patch series (Thanks Dirk Behme and Boqun Feng). - Added an example of dynamic LockClassKey usage (Thanks Boqun Feng). - Link to v1: https://lore.kernel.org/r/20241004-rust-lockdep-v1-0-e9a5c45721fc@gmail.com Changes from RFC: - Split into two commits so that dynamically allocated LockClassKeys are removed from stable kernels. (Thanks Alice Ryhl) - Extract calls to C lockdep functions into helpers so things build properly when LOCKDEP=n. (Thanks Benno Lossin) - Remove extraneous `get_ref()` calls. (Thanks Benno Lossin) - Provide better documentation for `new_dynamic()`. (Thanks Benno Lossin) - Ran rustfmt to fix formatting and some extraneous changes. (Thanks Alice Ryhl and Benno Lossin) - Link to RFC: https://lore.kernel.org/r/20240905-rust-lockdep-v1-1-d2c9c21aa8b2@gmail.com --- Mitchell Levy (2): rust: lockdep: Remove support for dynamically allocated LockClassKeys rust: lockdep: Use Pin for all LockClassKey usages rust/helpers/helpers.c | 1 + rust/helpers/sync.c | 13 +++++++++ rust/kernel/sync.rs | 63 ++++++++++++++++++++++++++++++++++------- rust/kernel/sync/condvar.rs | 5 ++-- rust/kernel/sync/lock.rs | 9 ++---- rust/kernel/sync/lock/global.rs | 5 ++-- rust/kernel/sync/poll.rs | 2 +- rust/kernel/workqueue.rs | 2 +- 8 files changed, 77 insertions(+), 23 deletions(-) --- base-commit: ceff0757f5dafb5be5205988171809c877b1d3e3 change-id: 20240905-rust-lockdep-d3e30521c8ba Best regards, -- Mitchell Levy <levymitchell0(a)gmail.com>

6 months, 1 week

3
4
0 0

[PATCH v4 3/5] arm64: errata: Add KRYO 2XX/3XX/4XX silver cores to Spectre BHB safe list

by Douglas Anderson

Qualcomm has confirmed that, much like Cortex A53 and A55, KRYO 2XX/3XX/4XX silver cores are unaffected by Spectre BHB. Add them to the safe list. Fixes: 558c303c9734 ("arm64: Mitigate spectre style branch history side channels") Cc: stable(a)vger.kernel.org Cc: Scott Bauer <sbauer(a)quicinc.com> Signed-off-by: Douglas Anderson <dianders(a)chromium.org> --- Changes in v4: - Re-added KRYO 2XX/3XX/4XX silver patch after Qualcomm confirmed. Changes in v3: - Removed KRYO 2XX/3XX/4XX silver patch. Changes in v2: - New arch/arm64/kernel/proton-pack.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 17aa836fe46d..89405be53d8f 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -854,6 +854,9 @@ static bool is_spectre_bhb_safe(int scope) MIDR_ALL_VERSIONS(MIDR_CORTEX_A510), MIDR_ALL_VERSIONS(MIDR_CORTEX_A520), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_2XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), {}, }; static bool all_safe = true; -- 2.47.1.613.gc27f4b7a9f-goog

6 months, 1 week

2
1
0 0

[PATCH v4 1/5] arm64: errata: Add QCOM_KRYO_4XX_GOLD to the spectre_bhb_k24_list

by Douglas Anderson

Qualcomm Kryo 400-series Gold cores have a derivative of an ARM Cortex A76 in them. Since A76 needs Spectre mitigation via looping then the Kyro 400-series Gold cores also need Spectre mitigation via looping. Qualcomm has confirmed that the proper "k" value for Kryo 400-series Gold cores is 24. Fixes: 558c303c9734 ("arm64: Mitigate spectre style branch history side channels") Cc: stable(a)vger.kernel.org Cc: Scott Bauer <sbauer(a)quicinc.com> Signed-off-by: Douglas Anderson <dianders(a)chromium.org> --- Changes in v4: - Re-added QCOM_KRYO_4XX_GOLD k24 patch after Qualcomm confirmed. Changes in v3: - Removed QCOM_KRYO_4XX_GOLD k24 patch. Changes in v2: - Slight change to wording and notes of KRYO_4XX_GOLD patch arch/arm64/kernel/proton-pack.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index da53722f95d4..e149efadff20 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -866,6 +866,7 @@ u8 spectre_bhb_loop_affected(int scope) MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_GOLD), {}, }; static const struct midr_range spectre_bhb_k11_list[] = { -- 2.47.1.613.gc27f4b7a9f-goog

6 months, 1 week

2
1
0 0

[PATCH 6.6 00/24] xfs backports for 6.6.y (from 6.12)

by Catherine Hoang

Hello, This series contains backports for 6.6 from the 6.12 release. This patchset has gone through xfs testing and review. Andrew Kreimer (1): xfs: fix a typo Brian Foster (2): xfs: skip background cowblock trims on inodes open for write xfs: don't free cowblocks from under dirty pagecache on unshare Chi Zhiling (1): xfs: Reduce unnecessary searches when searching for the best extents Christoph Hellwig (15): xfs: assert a valid limit in xfs_rtfind_forw xfs: merge xfs_attr_leaf_try_add into xfs_attr_leaf_addname xfs: return bool from xfs_attr3_leaf_add xfs: distinguish extra split from real ENOSPC from xfs_attr3_leaf_split xfs: distinguish extra split from real ENOSPC from xfs_attr_node_try_addname xfs: fold xfs_bmap_alloc_userdata into xfs_bmapi_allocate xfs: don't ifdef around the exact minlen allocations xfs: call xfs_bmap_exact_minlen_extent_alloc from xfs_bmap_btalloc xfs: support lowmode allocations in xfs_bmap_exact_minlen_extent_alloc xfs: pass the exact range to initialize to xfs_initialize_perag xfs: update the file system geometry after recoverying superblock buffers xfs: error out when a superblock buffer update reduces the agcount xfs: don't use __GFP_RETRY_MAYFAIL in xfs_initialize_perag xfs: update the pag for the last AG at recovery time xfs: streamline xfs_filestream_pick_ag Darrick J. Wong (2): xfs: validate inumber in xfs_iget xfs: fix a sloppy memory handling bug in xfs_iroot_realloc Ojaswin Mujoo (1): xfs: Check for delayed allocations before setting extsize Uros Bizjak (1): xfs: Use try_cmpxchg() in xlog_cil_insert_pcp_aggregate() Zhang Zekun (1): xfs: Remove empty declartion in header file fs/xfs/libxfs/xfs_ag.c | 47 ++++---- fs/xfs/libxfs/xfs_ag.h | 6 +- fs/xfs/libxfs/xfs_alloc.c | 9 +- fs/xfs/libxfs/xfs_alloc.h | 4 +- fs/xfs/libxfs/xfs_attr.c | 190 ++++++++++++++------------------- fs/xfs/libxfs/xfs_attr_leaf.c | 40 +++---- fs/xfs/libxfs/xfs_attr_leaf.h | 2 +- fs/xfs/libxfs/xfs_bmap.c | 140 ++++++++---------------- fs/xfs/libxfs/xfs_da_btree.c | 5 +- fs/xfs/libxfs/xfs_inode_fork.c | 10 +- fs/xfs/libxfs/xfs_rtbitmap.c | 2 + fs/xfs/xfs_buf_item_recover.c | 70 ++++++++++++ fs/xfs/xfs_filestream.c | 96 ++++++++--------- fs/xfs/xfs_fsops.c | 18 ++-- fs/xfs/xfs_icache.c | 39 ++++--- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_inode.h | 5 + fs/xfs/xfs_ioctl.c | 4 +- fs/xfs/xfs_log.h | 1 - fs/xfs/xfs_log_cil.c | 11 +- fs/xfs/xfs_log_recover.c | 9 +- fs/xfs/xfs_mount.c | 4 +- fs/xfs/xfs_reflink.c | 3 + fs/xfs/xfs_reflink.h | 19 ++++ 24 files changed, 375 insertions(+), 361 deletions(-) -- 2.39.3

6 months, 1 week

2
25
0 0

[PATCH 5.4 5.10 5.15 0/3] nilfs2: protect busy buffer heads from being force-cleared

by Ryusuke Konishi

Please apply this series to the stable trees indicated by the subject prefix. This series makes it possible to backport the latter two patches (fixing some syzbot issues and a use-after-free issue) that could not be backported as-is. To achieve this, one dependent patch (patch 1/3) is included, and each patch is tailored to avoid extensive page/folio conversion. Both adjustments are specific to nilfs2 and do not include tree-wide changes. It has also been tested against the latest versions of each tree. Thanks, Ryusuke Konishi Ryusuke Konishi (3): nilfs2: do not output warnings when clearing dirty buffers nilfs2: do not force clear folio if buffer is referenced nilfs2: protect access to buffers with no active references fs/nilfs2/inode.c | 4 ++-- fs/nilfs2/mdt.c | 6 ++--- fs/nilfs2/page.c | 55 ++++++++++++++++++++++++++------------------- fs/nilfs2/page.h | 4 ++-- fs/nilfs2/segment.c | 4 +++- 5 files changed, 42 insertions(+), 31 deletions(-) -- 2.43.5

6 months, 1 week

2
4
0 0

[PATCH 5.10 1/2] Revert "btrfs: avoid monopolizing a core when activating a swap file"

by Koichiro Den

This reverts commit a1c3a19446a440c68e80e9c34c5f308ff58aac88. The backport for linux-5.10.y, commit a1c3a19446a4 ("btrfs: avoid monopolizing a core when activating a swap file"), inserted cond_resched() in the wrong location. Revert it now; a subsequent commit will re-backport the original patch. Fixes: a1c3a19446a4 ("btrfs: avoid monopolizing a core when activating a swap file") # linux-5.10.y Signed-off-by: Koichiro Den <koichiro.den(a)canonical.com> --- fs/btrfs/inode.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 560c4f2a1833..45c1732a9677 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7127,8 +7127,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, ret = -EAGAIN; goto out; } - - cond_resched(); } btrfs_release_path(path); -- 2.45.2

6 months, 1 week

2
2
0 0

[PATCH 5.4 1/2] Revert "btrfs: avoid monopolizing a core when activating a swap file"

by Koichiro Den

This reverts commit 3d770d44dd5c6316913b003790998404636ec2a8. The backport for linux-5.4.y, commit 3d770d44dd5c ("btrfs: avoid monopolizing a core when activating a swap file"), inserted cond_resched() in the wrong location. Revert it now; a subsequent commit will re-backport the original patch. Fixes: 3d770d44dd5c ("btrfs: avoid monopolizing a core when activating a swap file") # linux-5.4.y Signed-off-by: Koichiro Den <koichiro.den(a)canonical.com> --- fs/btrfs/inode.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d9a581f46f13..cd72409ccc94 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7679,8 +7679,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, ret = -EAGAIN; goto out; } - - cond_resched(); } btrfs_release_path(path); -- 2.45.2

6 months, 1 week

2
2
0 0

FAILED: patch "[PATCH] pps: Fix a use-after-free" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x c79a39dc8d060b9e64e8b0fa9d245d44befeefbe # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025020420-subtly-blaming-0ded@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From c79a39dc8d060b9e64e8b0fa9d245d44befeefbe Mon Sep 17 00:00:00 2001 From: Calvin Owens <calvin(a)wbinvd.org> Date: Mon, 11 Nov 2024 20:13:29 -0800 Subject: [PATCH] pps: Fix a use-after-free On a board running ntpd and gpsd, I'm seeing a consistent use-after-free in sys_exit() from gpsd when rebooting: pps pps1: removed ------------[ cut here ]------------ kobject: '(null)' (00000000db4bec24): is not initialized, yet kobject_put() is being called. WARNING: CPU: 2 PID: 440 at lib/kobject.c:734 kobject_put+0x120/0x150 CPU: 2 UID: 299 PID: 440 Comm: gpsd Not tainted 6.11.0-rc6-00308-gb31c44928842 #1 Hardware name: Raspberry Pi 4 Model B Rev 1.1 (DT) pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : kobject_put+0x120/0x150 lr : kobject_put+0x120/0x150 sp : ffffffc0803d3ae0 x29: ffffffc0803d3ae0 x28: ffffff8042dc9738 x27: 0000000000000001 x26: 0000000000000000 x25: ffffff8042dc9040 x24: ffffff8042dc9440 x23: ffffff80402a4620 x22: ffffff8042ef4bd0 x21: ffffff80405cb600 x20: 000000000008001b x19: ffffff8040b3b6e0 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 696e6920746f6e20 x14: 7369203a29343263 x13: 205d303434542020 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000000000 Call trace: kobject_put+0x120/0x150 cdev_put+0x20/0x3c __fput+0x2c4/0x2d8 ____fput+0x1c/0x38 task_work_run+0x70/0xfc do_exit+0x2a0/0x924 do_group_exit+0x34/0x90 get_signal+0x7fc/0x8c0 do_signal+0x128/0x13b4 do_notify_resume+0xdc/0x160 el0_svc+0xd4/0xf8 el0t_64_sync_handler+0x140/0x14c el0t_64_sync+0x190/0x194 ---[ end trace 0000000000000000 ]--- ...followed by more symptoms of corruption, with similar stacks: refcount_t: underflow; use-after-free. kernel BUG at lib/list_debug.c:62! Kernel panic - not syncing: Oops - BUG: Fatal exception This happens because pps_device_destruct() frees the pps_device with the embedded cdev immediately after calling cdev_del(), but, as the comment above cdev_del() notes, fops for previously opened cdevs are still callable even after cdev_del() returns. I think this bug has always been there: I can't explain why it suddenly started happening every time I reboot this particular board. In commit d953e0e837e6 ("pps: Fix a use-after free bug when unregistering a source."), George Spelvin suggested removing the embedded cdev. That seems like the simplest way to fix this, so I've implemented his suggestion, using __register_chrdev() with pps_idr becoming the source of truth for which minor corresponds to which device. But now that pps_idr defines userspace visibility instead of cdev_add(), we need to be sure the pps->dev refcount can't reach zero while userspace can still find it again. So, the idr_remove() call moves to pps_unregister_cdev(), and pps_idr now holds a reference to pps->dev. pps_core: source serial1 got cdev (251:1) <...> pps pps1: removed pps_core: unregistering pps1 pps_core: deallocating pps1 Fixes: d953e0e837e6 ("pps: Fix a use-after free bug when unregistering a source.") Cc: stable(a)vger.kernel.org Signed-off-by: Calvin Owens <calvin(a)wbinvd.org> Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com> Link: https://lore.kernel.org/r/a17975fd5ae99385791929e563f72564edbcf28f.17313837… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c index 634c3b2f8c26..f77b19884f05 100644 --- a/drivers/pps/clients/pps-gpio.c +++ b/drivers/pps/clients/pps-gpio.c @@ -214,8 +214,8 @@ static int pps_gpio_probe(struct platform_device *pdev) return -EINVAL; } - dev_info(data->pps->dev, "Registered IRQ %d as PPS source\n", - data->irq); + dev_dbg(&data->pps->dev, "Registered IRQ %d as PPS source\n", + data->irq); return 0; } diff --git a/drivers/pps/clients/pps-ktimer.c b/drivers/pps/clients/pps-ktimer.c index d33106bd7a29..2f465549b843 100644 --- a/drivers/pps/clients/pps-ktimer.c +++ b/drivers/pps/clients/pps-ktimer.c @@ -56,7 +56,7 @@ static struct pps_source_info pps_ktimer_info = { static void __exit pps_ktimer_exit(void) { - dev_info(pps->dev, "ktimer PPS source unregistered\n"); + dev_dbg(&pps->dev, "ktimer PPS source unregistered\n"); del_timer_sync(&ktimer); pps_unregister_source(pps); @@ -74,7 +74,7 @@ static int __init pps_ktimer_init(void) timer_setup(&ktimer, pps_ktimer_event, 0); mod_timer(&ktimer, jiffies + HZ); - dev_info(pps->dev, "ktimer PPS source registered\n"); + dev_dbg(&pps->dev, "ktimer PPS source registered\n"); return 0; } diff --git a/drivers/pps/clients/pps-ldisc.c b/drivers/pps/clients/pps-ldisc.c index 443d6bae19d1..fa5660f3c4b7 100644 --- a/drivers/pps/clients/pps-ldisc.c +++ b/drivers/pps/clients/pps-ldisc.c @@ -32,7 +32,7 @@ static void pps_tty_dcd_change(struct tty_struct *tty, bool active) pps_event(pps, &ts, active ? PPS_CAPTUREASSERT : PPS_CAPTURECLEAR, NULL); - dev_dbg(pps->dev, "PPS %s at %lu\n", + dev_dbg(&pps->dev, "PPS %s at %lu\n", active ? "assert" : "clear", jiffies); } @@ -69,7 +69,7 @@ static int pps_tty_open(struct tty_struct *tty) goto err_unregister; } - dev_info(pps->dev, "source \"%s\" added\n", info.path); + dev_dbg(&pps->dev, "source \"%s\" added\n", info.path); return 0; @@ -89,7 +89,7 @@ static void pps_tty_close(struct tty_struct *tty) if (WARN_ON(!pps)) return; - dev_info(pps->dev, "removed\n"); + dev_info(&pps->dev, "removed\n"); pps_unregister_source(pps); } diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c index abaffb4e1c1c..24db06750297 100644 --- a/drivers/pps/clients/pps_parport.c +++ b/drivers/pps/clients/pps_parport.c @@ -81,7 +81,7 @@ static void parport_irq(void *handle) /* check the signal (no signal means the pulse is lost this time) */ if (!signal_is_set(port)) { local_irq_restore(flags); - dev_err(dev->pps->dev, "lost the signal\n"); + dev_err(&dev->pps->dev, "lost the signal\n"); goto out_assert; } @@ -98,7 +98,7 @@ static void parport_irq(void *handle) /* timeout */ dev->cw_err++; if (dev->cw_err >= CLEAR_WAIT_MAX_ERRORS) { - dev_err(dev->pps->dev, "disabled clear edge capture after %d" + dev_err(&dev->pps->dev, "disabled clear edge capture after %d" " timeouts\n", dev->cw_err); dev->cw = 0; dev->cw_err = 0; diff --git a/drivers/pps/kapi.c b/drivers/pps/kapi.c index d9d566f70ed1..92d1b62ea239 100644 --- a/drivers/pps/kapi.c +++ b/drivers/pps/kapi.c @@ -41,7 +41,7 @@ static void pps_add_offset(struct pps_ktime *ts, struct pps_ktime *offset) static void pps_echo_client_default(struct pps_device *pps, int event, void *data) { - dev_info(pps->dev, "echo %s %s\n", + dev_info(&pps->dev, "echo %s %s\n", event & PPS_CAPTUREASSERT ? "assert" : "", event & PPS_CAPTURECLEAR ? "clear" : ""); } @@ -112,7 +112,7 @@ struct pps_device *pps_register_source(struct pps_source_info *info, goto kfree_pps; } - dev_info(pps->dev, "new PPS source %s\n", info->name); + dev_dbg(&pps->dev, "new PPS source %s\n", info->name); return pps; @@ -166,7 +166,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* check event type */ BUG_ON((event & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR)) == 0); - dev_dbg(pps->dev, "PPS event at %lld.%09ld\n", + dev_dbg(&pps->dev, "PPS event at %lld.%09ld\n", (s64)ts->ts_real.tv_sec, ts->ts_real.tv_nsec); timespec_to_pps_ktime(&ts_real, ts->ts_real); @@ -188,7 +188,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* Save the time stamp */ pps->assert_tu = ts_real; pps->assert_sequence++; - dev_dbg(pps->dev, "capture assert seq #%u\n", + dev_dbg(&pps->dev, "capture assert seq #%u\n", pps->assert_sequence); captured = ~0; @@ -202,7 +202,7 @@ void pps_event(struct pps_device *pps, struct pps_event_time *ts, int event, /* Save the time stamp */ pps->clear_tu = ts_real; pps->clear_sequence++; - dev_dbg(pps->dev, "capture clear seq #%u\n", + dev_dbg(&pps->dev, "capture clear seq #%u\n", pps->clear_sequence); captured = ~0; diff --git a/drivers/pps/kc.c b/drivers/pps/kc.c index 50dc59af45be..fbd23295afd7 100644 --- a/drivers/pps/kc.c +++ b/drivers/pps/kc.c @@ -43,11 +43,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args) pps_kc_hardpps_mode = 0; pps_kc_hardpps_dev = NULL; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "unbound kernel" + dev_info(&pps->dev, "unbound kernel" " consumer\n"); } else { spin_unlock_irq(&pps_kc_hardpps_lock); - dev_err(pps->dev, "selected kernel consumer" + dev_err(&pps->dev, "selected kernel consumer" " is not bound\n"); return -EINVAL; } @@ -57,11 +57,11 @@ int pps_kc_bind(struct pps_device *pps, struct pps_bind_args *bind_args) pps_kc_hardpps_mode = bind_args->edge; pps_kc_hardpps_dev = pps; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "bound kernel consumer: " + dev_info(&pps->dev, "bound kernel consumer: " "edge=0x%x\n", bind_args->edge); } else { spin_unlock_irq(&pps_kc_hardpps_lock); - dev_err(pps->dev, "another kernel consumer" + dev_err(&pps->dev, "another kernel consumer" " is already bound\n"); return -EINVAL; } @@ -83,7 +83,7 @@ void pps_kc_remove(struct pps_device *pps) pps_kc_hardpps_mode = 0; pps_kc_hardpps_dev = NULL; spin_unlock_irq(&pps_kc_hardpps_lock); - dev_info(pps->dev, "unbound kernel consumer" + dev_info(&pps->dev, "unbound kernel consumer" " on device removal\n"); } else spin_unlock_irq(&pps_kc_hardpps_lock); diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c index 25d47907db17..6a02245ea35f 100644 --- a/drivers/pps/pps.c +++ b/drivers/pps/pps.c @@ -25,7 +25,7 @@ * Local variables */ -static dev_t pps_devt; +static int pps_major; static struct class *pps_class; static DEFINE_MUTEX(pps_idr_lock); @@ -62,7 +62,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata) else { unsigned long ticks; - dev_dbg(pps->dev, "timeout %lld.%09d\n", + dev_dbg(&pps->dev, "timeout %lld.%09d\n", (long long) fdata->timeout.sec, fdata->timeout.nsec); ticks = fdata->timeout.sec * HZ; @@ -80,7 +80,7 @@ static int pps_cdev_pps_fetch(struct pps_device *pps, struct pps_fdata *fdata) /* Check for pending signals */ if (err == -ERESTARTSYS) { - dev_dbg(pps->dev, "pending signal caught\n"); + dev_dbg(&pps->dev, "pending signal caught\n"); return -EINTR; } @@ -98,7 +98,7 @@ static long pps_cdev_ioctl(struct file *file, switch (cmd) { case PPS_GETPARAMS: - dev_dbg(pps->dev, "PPS_GETPARAMS\n"); + dev_dbg(&pps->dev, "PPS_GETPARAMS\n"); spin_lock_irq(&pps->lock); @@ -114,7 +114,7 @@ static long pps_cdev_ioctl(struct file *file, break; case PPS_SETPARAMS: - dev_dbg(pps->dev, "PPS_SETPARAMS\n"); + dev_dbg(&pps->dev, "PPS_SETPARAMS\n"); /* Check the capabilities */ if (!capable(CAP_SYS_TIME)) @@ -124,14 +124,14 @@ static long pps_cdev_ioctl(struct file *file, if (err) return -EFAULT; if (!(params.mode & (PPS_CAPTUREASSERT | PPS_CAPTURECLEAR))) { - dev_dbg(pps->dev, "capture mode unspecified (%x)\n", + dev_dbg(&pps->dev, "capture mode unspecified (%x)\n", params.mode); return -EINVAL; } /* Check for supported capabilities */ if ((params.mode & ~pps->info.mode) != 0) { - dev_dbg(pps->dev, "unsupported capabilities (%x)\n", + dev_dbg(&pps->dev, "unsupported capabilities (%x)\n", params.mode); return -EINVAL; } @@ -144,7 +144,7 @@ static long pps_cdev_ioctl(struct file *file, /* Restore the read only parameters */ if ((params.mode & (PPS_TSFMT_TSPEC | PPS_TSFMT_NTPFP)) == 0) { /* section 3.3 of RFC 2783 interpreted */ - dev_dbg(pps->dev, "time format unspecified (%x)\n", + dev_dbg(&pps->dev, "time format unspecified (%x)\n", params.mode); pps->params.mode |= PPS_TSFMT_TSPEC; } @@ -165,7 +165,7 @@ static long pps_cdev_ioctl(struct file *file, break; case PPS_GETCAP: - dev_dbg(pps->dev, "PPS_GETCAP\n"); + dev_dbg(&pps->dev, "PPS_GETCAP\n"); err = put_user(pps->info.mode, iuarg); if (err) @@ -176,7 +176,7 @@ static long pps_cdev_ioctl(struct file *file, case PPS_FETCH: { struct pps_fdata fdata; - dev_dbg(pps->dev, "PPS_FETCH\n"); + dev_dbg(&pps->dev, "PPS_FETCH\n"); err = copy_from_user(&fdata, uarg, sizeof(struct pps_fdata)); if (err) @@ -206,7 +206,7 @@ static long pps_cdev_ioctl(struct file *file, case PPS_KC_BIND: { struct pps_bind_args bind_args; - dev_dbg(pps->dev, "PPS_KC_BIND\n"); + dev_dbg(&pps->dev, "PPS_KC_BIND\n"); /* Check the capabilities */ if (!capable(CAP_SYS_TIME)) @@ -218,7 +218,7 @@ static long pps_cdev_ioctl(struct file *file, /* Check for supported capabilities */ if ((bind_args.edge & ~pps->info.mode) != 0) { - dev_err(pps->dev, "unsupported capabilities (%x)\n", + dev_err(&pps->dev, "unsupported capabilities (%x)\n", bind_args.edge); return -EINVAL; } @@ -227,7 +227,7 @@ static long pps_cdev_ioctl(struct file *file, if (bind_args.tsformat != PPS_TSFMT_TSPEC || (bind_args.edge & ~PPS_CAPTUREBOTH) != 0 || bind_args.consumer != PPS_KC_HARDPPS) { - dev_err(pps->dev, "invalid kernel consumer bind" + dev_err(&pps->dev, "invalid kernel consumer bind" " parameters (%x)\n", bind_args.edge); return -EINVAL; } @@ -259,7 +259,7 @@ static long pps_cdev_compat_ioctl(struct file *file, struct pps_fdata fdata; int err; - dev_dbg(pps->dev, "PPS_FETCH\n"); + dev_dbg(&pps->dev, "PPS_FETCH\n"); err = copy_from_user(&compat, uarg, sizeof(struct pps_fdata_compat)); if (err) @@ -296,20 +296,36 @@ static long pps_cdev_compat_ioctl(struct file *file, #define pps_cdev_compat_ioctl NULL #endif +static struct pps_device *pps_idr_get(unsigned long id) +{ + struct pps_device *pps; + + mutex_lock(&pps_idr_lock); + pps = idr_find(&pps_idr, id); + if (pps) + get_device(&pps->dev); + + mutex_unlock(&pps_idr_lock); + return pps; +} + static int pps_cdev_open(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); + struct pps_device *pps = pps_idr_get(iminor(inode)); + + if (!pps) + return -ENODEV; + file->private_data = pps; - kobject_get(&pps->dev->kobj); return 0; } static int pps_cdev_release(struct inode *inode, struct file *file) { - struct pps_device *pps = container_of(inode->i_cdev, - struct pps_device, cdev); - kobject_put(&pps->dev->kobj); + struct pps_device *pps = file->private_data; + + WARN_ON(pps->id != iminor(inode)); + put_device(&pps->dev); return 0; } @@ -331,22 +347,13 @@ static void pps_device_destruct(struct device *dev) { struct pps_device *pps = dev_get_drvdata(dev); - cdev_del(&pps->cdev); - - /* Now we can release the ID for re-use */ pr_debug("deallocating pps%d\n", pps->id); - mutex_lock(&pps_idr_lock); - idr_remove(&pps_idr, pps->id); - mutex_unlock(&pps_idr_lock); - - kfree(dev); kfree(pps); } int pps_register_cdev(struct pps_device *pps) { int err; - dev_t devt; mutex_lock(&pps_idr_lock); /* @@ -363,40 +370,29 @@ int pps_register_cdev(struct pps_device *pps) goto out_unlock; } pps->id = err; - mutex_unlock(&pps_idr_lock); - devt = MKDEV(MAJOR(pps_devt), pps->id); - - cdev_init(&pps->cdev, &pps_cdev_fops); - pps->cdev.owner = pps->info.owner; - - err = cdev_add(&pps->cdev, devt, 1); - if (err) { - pr_err("%s: failed to add char device %d:%d\n", - pps->info.name, MAJOR(pps_devt), pps->id); + pps->dev.class = pps_class; + pps->dev.parent = pps->info.dev; + pps->dev.devt = MKDEV(pps_major, pps->id); + dev_set_drvdata(&pps->dev, pps); + dev_set_name(&pps->dev, "pps%d", pps->id); + err = device_register(&pps->dev); + if (err) goto free_idr; - } - pps->dev = device_create(pps_class, pps->info.dev, devt, pps, - "pps%d", pps->id); - if (IS_ERR(pps->dev)) { - err = PTR_ERR(pps->dev); - goto del_cdev; - } /* Override the release function with our own */ - pps->dev->release = pps_device_destruct; + pps->dev.release = pps_device_destruct; - pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, - MAJOR(pps_devt), pps->id); + pr_debug("source %s got cdev (%d:%d)\n", pps->info.name, pps_major, + pps->id); + get_device(&pps->dev); + mutex_unlock(&pps_idr_lock); return 0; -del_cdev: - cdev_del(&pps->cdev); - free_idr: - mutex_lock(&pps_idr_lock); idr_remove(&pps_idr, pps->id); + put_device(&pps->dev); out_unlock: mutex_unlock(&pps_idr_lock); return err; @@ -406,7 +402,13 @@ void pps_unregister_cdev(struct pps_device *pps) { pr_debug("unregistering pps%d\n", pps->id); pps->lookup_cookie = NULL; - device_destroy(pps_class, pps->dev->devt); + device_destroy(pps_class, pps->dev.devt); + + /* Now we can release the ID for re-use */ + mutex_lock(&pps_idr_lock); + idr_remove(&pps_idr, pps->id); + put_device(&pps->dev); + mutex_unlock(&pps_idr_lock); } /* @@ -426,6 +428,11 @@ void pps_unregister_cdev(struct pps_device *pps) * so that it will not be used again, even if the pps device cannot * be removed from the idr due to pending references holding the minor * number in use. + * + * Since pps_idr holds a reference to the device, the returned + * pps_device is guaranteed to be valid until pps_unregister_cdev() is + * called on it. But after calling pps_unregister_cdev(), it may be + * freed at any time. */ struct pps_device *pps_lookup_dev(void const *cookie) { @@ -448,13 +455,11 @@ EXPORT_SYMBOL(pps_lookup_dev); static void __exit pps_exit(void) { class_destroy(pps_class); - unregister_chrdev_region(pps_devt, PPS_MAX_SOURCES); + __unregister_chrdev(pps_major, 0, PPS_MAX_SOURCES, "pps"); } static int __init pps_init(void) { - int err; - pps_class = class_create("pps"); if (IS_ERR(pps_class)) { pr_err("failed to allocate class\n"); @@ -462,8 +467,9 @@ static int __init pps_init(void) } pps_class->dev_groups = pps_groups; - err = alloc_chrdev_region(&pps_devt, 0, PPS_MAX_SOURCES, "pps"); - if (err < 0) { + pps_major = __register_chrdev(0, 0, PPS_MAX_SOURCES, "pps", + &pps_cdev_fops); + if (pps_major < 0) { pr_err("failed to allocate char device region\n"); goto remove_class; } @@ -476,8 +482,7 @@ static int __init pps_init(void) remove_class: class_destroy(pps_class); - - return err; + return pps_major; } subsys_initcall(pps_init); diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 5feecaadde8e..120db96d9e95 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4420,7 +4420,7 @@ ptp_ocp_complete(struct ptp_ocp *bp) pps = pps_lookup_dev(bp->ptp); if (pps) - ptp_ocp_symlink(bp, pps->dev, "pps"); + ptp_ocp_symlink(bp, &pps->dev, "pps"); ptp_ocp_debugfs_add_device(bp); diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h index 78c8ac4951b5..c7abce28ed29 100644 --- a/include/linux/pps_kernel.h +++ b/include/linux/pps_kernel.h @@ -56,8 +56,7 @@ struct pps_device { unsigned int id; /* PPS source unique ID */ void const *lookup_cookie; /* For pps_lookup_dev() only */ - struct cdev cdev; - struct device *dev; + struct device dev; struct fasync_struct *async_queue; /* fasync method */ spinlock_t lock; };

6 months, 1 week

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror February 2025