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

[PATCH v3] ceph: force sending a cap update msg back to MDS for revoke op

by xiubli＠redhat.com

From: Xiubo Li <xiubli(a)redhat.com> If a client sends out a cap update dropping caps with the prior 'seq' just before an incoming cap revoke request, then the client may drop the revoke because it believes it's already released the requested capabilities. This causes the MDS to wait indefinitely for the client to respond to the revoke. It's therefore always a good idea to ack the cap revoke request with the bumped up 'seq'. Currently if the cap->issued equals to the newcaps the check_caps() will do nothing, we should force flush the caps. Cc: stable(a)vger.kernel.org Link: https://tracker.ceph.com/issues/61782 Signed-off-by: Xiubo Li <xiubli(a)redhat.com> --- V3: - Move the force check earlier V2: - Improved the patch to force send the cap update only when no caps being used. fs/ceph/caps.c | 35 ++++++++++++++++++++++++----------- fs/ceph/super.h | 7 ++++--- 2 files changed, 28 insertions(+), 14 deletions(-) diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 24c31f795938..672c6611d749 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2024,6 +2024,8 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci) * CHECK_CAPS_AUTHONLY - we should only check the auth cap * CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without * further delay. + * CHECK_CAPS_FLUSH_FORCE - we should flush any caps immediately, without + * further delay. */ void ceph_check_caps(struct ceph_inode_info *ci, int flags) { @@ -2105,7 +2107,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) } doutc(cl, "%p %llx.%llx file_want %s used %s dirty %s " - "flushing %s issued %s revoking %s retain %s %s%s%s\n", + "flushing %s issued %s revoking %s retain %s %s%s%s%s\n", inode, ceph_vinop(inode), ceph_cap_string(file_wanted), ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps), ceph_cap_string(ci->i_flushing_caps), @@ -2113,7 +2115,8 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) ceph_cap_string(retain), (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "", (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "", - (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : ""); + (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "", + (flags & CHECK_CAPS_FLUSH_FORCE) ? " FLUSH_FORCE" : ""); /* * If we no longer need to hold onto old our caps, and we may @@ -2188,6 +2191,11 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags) queue_writeback = true; } + if (flags & CHECK_CAPS_FLUSH_FORCE) { + doutc(cl, "force to flush caps\n"); + goto ack; + } + if (cap == ci->i_auth_cap && (cap->issued & CEPH_CAP_FILE_WR)) { /* request larger max_size from MDS? */ @@ -3518,6 +3526,8 @@ static void handle_cap_grant(struct inode *inode, bool queue_invalidate = false; bool deleted_inode = false; bool fill_inline = false; + bool revoke_wait = false; + int flags = 0; /* * If there is at least one crypto block then we'll trust @@ -3713,16 +3723,18 @@ static void handle_cap_grant(struct inode *inode, ceph_cap_string(cap->issued), ceph_cap_string(newcaps), ceph_cap_string(revoking)); if (S_ISREG(inode->i_mode) && - (revoking & used & CEPH_CAP_FILE_BUFFER)) + (revoking & used & CEPH_CAP_FILE_BUFFER)) { writeback = true; /* initiate writeback; will delay ack */ - else if (queue_invalidate && + revoke_wait = true; + } else if (queue_invalidate && revoking == CEPH_CAP_FILE_CACHE && - (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) - ; /* do nothing yet, invalidation will be queued */ - else if (cap == ci->i_auth_cap) + (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) { + revoke_wait = true; /* do nothing yet, invalidation will be queued */ + } else if (cap == ci->i_auth_cap) { check_caps = 1; /* check auth cap only */ - else + } else { check_caps = 2; /* check all caps */ + } /* If there is new caps, try to wake up the waiters */ if (~cap->issued & newcaps) wake = true; @@ -3749,8 +3761,9 @@ static void handle_cap_grant(struct inode *inode, BUG_ON(cap->issued & ~cap->implemented); /* don't let check_caps skip sending a response to MDS for revoke msgs */ - if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { + if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) { cap->mds_wanted = 0; + flags |= CHECK_CAPS_FLUSH_FORCE; if (cap == ci->i_auth_cap) check_caps = 1; /* check auth cap only */ else @@ -3806,9 +3819,9 @@ static void handle_cap_grant(struct inode *inode, mutex_unlock(&session->s_mutex); if (check_caps == 1) - ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL); + ceph_check_caps(ci, flags | CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL); else if (check_caps == 2) - ceph_check_caps(ci, CHECK_CAPS_NOINVAL); + ceph_check_caps(ci, flags | CHECK_CAPS_NOINVAL); } /* diff --git a/fs/ceph/super.h b/fs/ceph/super.h index b0b368ed3018..831e8ec4d5da 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -200,9 +200,10 @@ struct ceph_cap { struct list_head caps_item; }; -#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */ -#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */ -#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */ +#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */ +#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */ +#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */ +#define CHECK_CAPS_FLUSH_FORCE 8 /* force flush any caps */ struct ceph_cap_flush { u64 tid; -- 2.45.1

1 year, 1 month

3
5
0 0

+ selftests-mm-add-s390-to-arch-check.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: selftests: mm: add s390 to ARCH check has been added to the -mm mm-hotfixes-unstable branch. Its filename is selftests-mm-add-s390-to-arch-check.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-hotfixes-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: Nico Pache <npache(a)redhat.com> Subject: selftests: mm: add s390 to ARCH check Date: Wed, 24 Jul 2024 15:35:17 -0600 commit 0518dbe97fe6 ("selftests/mm: fix cross compilation with LLVM") changed the env variable for the architecture from MACHINE to ARCH. This is preventing 3 required TEST_GEN_FILES from being included when cross compiling s390x and errors when trying to run the test suite. This is due to the ARCH variable already being set and the arch folder name being s390. Add "s390" to the filtered list to cover this case and have the 3 files included in the build. Link: https://lkml.kernel.org/r/20240724213517.23918-1-npache@redhat.com Fixes: 0518dbe97fe6 ("selftests/mm: fix cross compilation with LLVM") Signed-off-by: Nico Pache <npache(a)redhat.com> Cc: Mark Brown <broonie(a)kernel.org> Cc: Albert Ou <aou(a)eecs.berkeley.edu> Cc: Palmer Dabbelt <palmer(a)dabbelt.com> Cc: Paul Walmsley <paul.walmsley(a)sifive.com> Cc: Shuah Khan <shuah(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/tools/testing/selftests/mm/Makefile~selftests-mm-add-s390-to-arch-check +++ a/tools/testing/selftests/mm/Makefile @@ -110,7 +110,7 @@ endif endif -ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64)) +ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390)) TEST_GEN_FILES += va_high_addr_switch TEST_GEN_FILES += virtual_address_range TEST_GEN_FILES += write_to_hugetlbfs _ Patches currently in -mm which might be from npache(a)redhat.com are selftests-mm-add-s390-to-arch-check.patch

1 year, 1 month

1
0
0 0

+ crash-fix-x86_32-crash-memory-reserve-dead-loop-bug.patch added to mm-nonmm-unstable branch

by Andrew Morton

The patch titled Subject: crash: fix x86_32 crash memory reserve dead loop bug has been added to the -mm mm-nonmm-unstable branch. Its filename is crash-fix-x86_32-crash-memory-reserve-dead-loop-bug.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-nonmm-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: Jinjie Ruan <ruanjinjie(a)huawei.com> Subject: crash: fix x86_32 crash memory reserve dead loop bug Date: Thu, 18 Jul 2024 11:54:42 +0800 Patch series "crash: Fix x86_32 memory reserve dead loop bug", v3. Fix two bugs for x86_32 crash memory reserve, and prepare to apply generic crashkernel reservation to 32bit system. Then use generic interface to simplify crashkernel reservation for ARM32. This patch (of 3): On x86_32 Qemu machine with 1GB memory, the cmdline "crashkernel=1G,high" will cause system stall as below: ACPI: Reserving FACP table memory at [mem 0x3ffe18b8-0x3ffe192b] ACPI: Reserving DSDT table memory at [mem 0x3ffe0040-0x3ffe18b7] ACPI: Reserving FACS table memory at [mem 0x3ffe0000-0x3ffe003f] ACPI: Reserving APIC table memory at [mem 0x3ffe192c-0x3ffe19bb] ACPI: Reserving HPET table memory at [mem 0x3ffe19bc-0x3ffe19f3] ACPI: Reserving WAET table memory at [mem 0x3ffe19f4-0x3ffe1a1b] 143MB HIGHMEM available. 879MB LOWMEM available. mapped low ram: 0 - 36ffe000 low ram: 0 - 36ffe000 (stall here) The reason is that the CRASH_ADDR_LOW_MAX is equal to CRASH_ADDR_HIGH_MAX on x86_32, the first high crash kernel memory reservation will fail, then go into the "retry" loop and never came out as below. -> reserve_crashkernel_generic() and high is true -> alloc at [CRASH_ADDR_LOW_MAX, CRASH_ADDR_HIGH_MAX] fail -> alloc at [0, CRASH_ADDR_LOW_MAX] fail and repeatedly (because CRASH_ADDR_LOW_MAX = CRASH_ADDR_HIGH_MAX). Fix it by prevent crashkernel=,high from being parsed successfully on 32bit system with a architecture-defined macro. After this patch, the 'crashkernel=,high' for 32bit system can't succeed, and it has no chance to call reserve_crashkernel_generic(), therefore this issue on x86_32 is solved. Link: https://lkml.kernel.org/r/20240718035444.2977105-1-ruanjinjie@huawei.com Link: https://lkml.kernel.org/r/20240718035444.2977105-2-ruanjinjie@huawei.com Fixes: 9c08a2a139fe ("x86: kdump: use generic interface to simplify crashkernel reservation code") Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> Signed-off-by: Baoquan He <bhe(a)redhat.com> Tested-by: Jinjie Ruan <ruanjinjie(a)huawei.com> Cc: Albert Ou <aou(a)eecs.berkeley.edu> Cc: Andrew Davis <afd(a)ti.com> Cc: Arnd Bergmann <arnd(a)arndb.de> Cc: Borislav Petkov <bp(a)alien8.de> Cc: Catalin Marinas <catalin.marinas(a)arm.com> Cc: Chen Jiahao <chenjiahao16(a)huawei.com> Cc: Dave Hansen <dave.hansen(a)linux.intel.com> Cc: Dave Young <dyoung(a)redhat.com> Cc: Eric DeVolder <eric.devolder(a)oracle.com> Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: Hari Bathini <hbathini(a)linux.ibm.com> Cc: Helge Deller <deller(a)gmx.de> Cc: "H. Peter Anvin" <hpa(a)zytor.com> Cc: Ingo Molnar <mingo(a)redhat.com> Cc: Javier Martinez Canillas <javierm(a)redhat.com> Cc: Linus Walleij <linus.walleij(a)linaro.org> Cc: Palmer Dabbelt <palmer(a)dabbelt.com> Cc: Paul Walmsley <paul.walmsley(a)sifive.com> Cc: Rob Herring <robh(a)kernel.org> Cc: Russell King <linux(a)armlinux.org.uk> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Vivek Goyal <vgoyal(a)redhat.com> Cc: Will Deacon <will(a)kernel.org> Cc: Zhen Lei <thunder.leizhen(a)huawei.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/arm64/include/asm/crash_reserve.h | 2 ++ arch/riscv/include/asm/crash_reserve.h | 2 ++ arch/x86/include/asm/crash_reserve.h | 1 + kernel/crash_reserve.c | 2 +- 4 files changed, 6 insertions(+), 1 deletion(-) --- a/arch/arm64/include/asm/crash_reserve.h~crash-fix-x86_32-crash-memory-reserve-dead-loop-bug +++ a/arch/arm64/include/asm/crash_reserve.h @@ -7,4 +7,6 @@ #define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit #define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) + +#define HAVE_ARCH_CRASHKERNEL_RESERVATION_HIGH #endif --- a/arch/riscv/include/asm/crash_reserve.h~crash-fix-x86_32-crash-memory-reserve-dead-loop-bug +++ a/arch/riscv/include/asm/crash_reserve.h @@ -7,5 +7,7 @@ #define CRASH_ADDR_LOW_MAX dma32_phys_limit #define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() +#define HAVE_ARCH_CRASHKERNEL_RESERVATION_HIGH + extern phys_addr_t memblock_end_of_DRAM(void); #endif --- a/arch/x86/include/asm/crash_reserve.h~crash-fix-x86_32-crash-memory-reserve-dead-loop-bug +++ a/arch/x86/include/asm/crash_reserve.h @@ -26,6 +26,7 @@ extern unsigned long swiotlb_size_or_def #else # define CRASH_ADDR_LOW_MAX SZ_4G # define CRASH_ADDR_HIGH_MAX SZ_64T +#define HAVE_ARCH_CRASHKERNEL_RESERVATION_HIGH #endif # define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default() --- a/kernel/crash_reserve.c~crash-fix-x86_32-crash-memory-reserve-dead-loop-bug +++ a/kernel/crash_reserve.c @@ -305,7 +305,7 @@ int __init parse_crashkernel(char *cmdli /* crashkernel=X[@offset] */ ret = __parse_crashkernel(cmdline, system_ram, crash_size, crash_base, NULL); -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +#ifdef HAVE_ARCH_CRASHKERNEL_RESERVATION_HIGH /* * If non-NULL 'high' passed in and no normal crashkernel * setting detected, try parsing crashkernel=,high|low. _ Patches currently in -mm which might be from ruanjinjie(a)huawei.com are crash-fix-x86_32-crash-memory-reserve-dead-loop-bug.patch crash-fix-x86_32-crash-memory-reserve-dead-loop-bug-at-high.patch arm-use-generic-interface-to-simplify-crashkernel-reservation.patch

1 year, 1 month

2
4
0 0

+ mm-let-pte_lockptr-consume-a-pte_t-pointer.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm: let pte_lockptr() consume a pte_t pointer has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-let-pte_lockptr-consume-a-pte_t-pointer.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-hotfixes-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: David Hildenbrand <david(a)redhat.com> Subject: mm: let pte_lockptr() consume a pte_t pointer Date: Thu, 25 Jul 2024 20:39:54 +0200 Patch series "mm/hugetlb: fix hugetlb vs. core-mm PT locking". Working on another generic page table walker that tries to avoid special-casing hugetlb, I found a page table locking issue with hugetlb folios that are not mapped using a single PMD/PUD. For some hugetlb folio sizes, GUP will take different page table locks when walking the page tables than hugetlb when modifying the page tables. I did not actually try reproducing an issue, but looking at follow_pmd_mask() where we might be rereading a PMD value multiple times it's rather clear that concurrent modifications are rather unpleasant. In follow_page_pte() we might be better in that regard -- ptep_get() does a READ_ONCE() -- but who knows what else could happen concurrently in some weird corner cases (e.g., hugetlb folio getting unmapped and freed). This patch (of 2): pte_lockptr() is the only *_lockptr() function that doesn't consume what would be expected: it consumes a pmd_t pointer instead of a pte_t pointer. Let's change that. The two callers in pgtable-generic.c are easily adjusted. Adjust khugepaged.c:retract_page_tables() to simply do a pte_offset_map_nolock() to obtain the lock, even though we won't actually be traversing the page table. This makes the code more similar to the other variants and avoids other hacks to make the new pte_lockptr() version happy. pte_lockptr() users reside now only in pgtable-generic.c. Maybe, using pte_offset_map_nolock() is the right thing to do because the PTE table could have been removed in the meantime? At least it sounds more future proof if we ever have other means of page table reclaim. It's not quite clear if holding the PTE table lock is really required: what if someone else obtains the lock just after we unlock it? But we'll leave that as is for now, maybe there are good reasons. This is a preparation for adapting hugetlb page table locking logic to take the same locks as core-mm page table walkers would. Link: https://lkml.kernel.org/r/20240725183955.2268884-1-david@redhat.com Link: https://lkml.kernel.org/r/20240725183955.2268884-2-david@redhat.com Fixes: 9cb28da54643 ("mm/gup: handle hugetlb in the generic follow_page_mask code") Signed-off-by: David Hildenbrand <david(a)redhat.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Peter Xu <peterx(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm.h | 7 ++++--- mm/khugepaged.c | 21 +++++++++++++++------ mm/pgtable-generic.c | 4 ++-- 3 files changed, 21 insertions(+), 11 deletions(-) --- a/include/linux/mm.h~mm-let-pte_lockptr-consume-a-pte_t-pointer +++ a/include/linux/mm.h @@ -2915,9 +2915,10 @@ static inline spinlock_t *ptlock_ptr(str } #endif /* ALLOC_SPLIT_PTLOCKS */ -static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) +static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pte_t *pte) { - return ptlock_ptr(page_ptdesc(pmd_page(*pmd))); + /* PTE page tables don't currently exceed a single page. */ + return ptlock_ptr(virt_to_ptdesc(pte)); } static inline bool ptlock_init(struct ptdesc *ptdesc) @@ -2940,7 +2941,7 @@ static inline bool ptlock_init(struct pt /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ -static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) +static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } --- a/mm/khugepaged.c~mm-let-pte_lockptr-consume-a-pte_t-pointer +++ a/mm/khugepaged.c @@ -1697,12 +1697,13 @@ static void retract_page_tables(struct a i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; + bool retracted = false; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; - bool skipped_uffd = false; + pte_t *pte; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that @@ -1739,9 +1740,17 @@ static void retract_page_tables(struct a mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); - ptl = pte_lockptr(mm, pmd); + + /* + * No need to check the PTE table content, but we'll grab the + * PTE table lock while we zap it. + */ + pte = pte_offset_map_nolock(mm, pmd, addr, &ptl); + if (!pte) + goto unlock_pmd; if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); + pte_unmap(pte); /* * Huge page lock is still held, so normally the page table @@ -1752,20 +1761,20 @@ static void retract_page_tables(struct a * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ - if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { - skipped_uffd = true; - } else { + if (likely(!vma->anon_vma && !userfaultfd_wp(vma))) { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); + retracted = true; } if (ptl != pml) spin_unlock(ptl); +unlock_pmd: spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); - if (!skipped_uffd) { + if (retracted) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); --- a/mm/pgtable-generic.c~mm-let-pte_lockptr-consume-a-pte_t-pointer +++ a/mm/pgtable-generic.c @@ -313,7 +313,7 @@ pte_t *pte_offset_map_nolock(struct mm_s pte = __pte_offset_map(pmd, addr, &pmdval); if (likely(pte)) - *ptlp = pte_lockptr(mm, &pmdval); + *ptlp = pte_lockptr(mm, pte); return pte; } @@ -371,7 +371,7 @@ again: pte = __pte_offset_map(pmd, addr, &pmdval); if (unlikely(!pte)) return pte; - ptl = pte_lockptr(mm, &pmdval); + ptl = pte_lockptr(mm, pte); spin_lock(ptl); if (likely(pmd_same(pmdval, pmdp_get_lockless(pmd)))) { *ptlp = ptl; _ Patches currently in -mm which might be from david(a)redhat.com are mm-let-pte_lockptr-consume-a-pte_t-pointer.patch mm-hugetlb-fix-hugetlb-vs-core-mm-pt-locking.patch

1 year, 1 month

1
0
0 0

[PATCH v6 4/8] RISC-V: Scalar unaligned access emulated on hotplug CPUs

by Jesse Taube

The check_unaligned_access_emulated() function should have been called during CPU hotplug to ensure that if all CPUs had emulated unaligned accesses, the new CPU also does. This patch adds the call to check_unaligned_access_emulated() in the hotplug path. Fixes: 55e0bf49a0d0 ("RISC-V: Probe misaligned access speed in parallel") Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> Cc: stable(a)vger.kernel.org --- V5 -> V6: - New patch --- arch/riscv/kernel/unaligned_access_speed.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c index a9a6bcb02acf..b67db1fc3740 100644 --- a/arch/riscv/kernel/unaligned_access_speed.c +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -191,6 +191,7 @@ static int riscv_online_cpu(unsigned int cpu) if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN) goto exit; + check_unaligned_access_emulated(NULL); buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); if (!buf) { pr_warn("Allocation failure, not measuring misaligned performance\n"); -- 2.45.2

1 year, 1 month

2
1
0 0

[PATCH v6 3/8] RISC-V: Check scalar unaligned access on all CPUs

by Jesse Taube

Originally, the check_unaligned_access_emulated_all_cpus function only checked the boot hart. This fixes the function to check all harts. Fixes: 71c54b3d169d ("riscv: report misaligned accesses emulation to hwprobe") Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> Reviewed-by: Charlie Jenkins <charlie(a)rivosinc.com> Cc: stable(a)vger.kernel.org --- V1 -> V2: - New patch V2 -> V3: - Split patch V3 -> V4: - Re-add check for a system where a heterogeneous CPU is hotplugged into a previously homogenous system. V4 -> V5: - Change work_struct *unused to work_struct *work __always_unused V5 -> V6: - Change check_unaligned_access_emulated to extern --- arch/riscv/include/asm/cpufeature.h | 2 ++ arch/riscv/kernel/traps_misaligned.c | 14 +++++++------- 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 347805446151..3b24342c7d2a 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -8,6 +8,7 @@ #include <linux/bitmap.h> #include <linux/jump_label.h> +#include <linux/workqueue.h> #include <asm/hwcap.h> #include <asm/alternative-macros.h> #include <asm/errno.h> @@ -35,6 +36,7 @@ void riscv_user_isa_enable(void); #if defined(CONFIG_RISCV_MISALIGNED) bool check_unaligned_access_emulated_all_cpus(void); +void check_unaligned_access_emulated(struct work_struct *work __always_unused); void unaligned_emulation_finish(void); bool unaligned_ctl_available(void); DECLARE_PER_CPU(long, misaligned_access_speed); diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index b62d5a2f4541..bb09357778c5 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -526,11 +526,11 @@ int handle_misaligned_store(struct pt_regs *regs) return 0; } -static bool check_unaligned_access_emulated(int cpu) +void check_unaligned_access_emulated(struct work_struct *work __always_unused) { + int cpu = smp_processor_id(); long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); unsigned long tmp_var, tmp_val; - bool misaligned_emu_detected; *mas_ptr = RISCV_HWPROBE_MISALIGNED_UNKNOWN; @@ -538,19 +538,16 @@ static bool check_unaligned_access_emulated(int cpu) " "REG_L" %[tmp], 1(%[ptr])\n" : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); - misaligned_emu_detected = (*mas_ptr == RISCV_HWPROBE_MISALIGNED_EMULATED); /* * If unaligned_ctl is already set, this means that we detected that all * CPUS uses emulated misaligned access at boot time. If that changed * when hotplugging the new cpu, this is something we don't handle. */ - if (unlikely(unaligned_ctl && !misaligned_emu_detected)) { + if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_EMULATED))) { pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n"); while (true) cpu_relax(); } - - return misaligned_emu_detected; } bool check_unaligned_access_emulated_all_cpus(void) @@ -562,8 +559,11 @@ bool check_unaligned_access_emulated_all_cpus(void) * accesses emulated since tasks requesting such control can run on any * CPU. */ + schedule_on_each_cpu(check_unaligned_access_emulated); + for_each_online_cpu(cpu) - if (!check_unaligned_access_emulated(cpu)) + if (per_cpu(misaligned_access_speed, cpu) + != RISCV_HWPROBE_MISALIGNED_EMULATED) return false; unaligned_ctl = true; -- 2.45.2

1 year, 1 month

2
1
0 0

[PATCH wireless] wifi: mac80211: use monitor sdata with driver only if desired

by Johannes Berg

From: Johannes Berg <johannes.berg(a)intel.com> In commit 0d9c2beed116 ("wifi: mac80211: fix monitor channel with chanctx emulation") I changed mac80211 to always have an internal monitor_sdata to have something to have the chanctx bound to. However, if the driver didn't also have the WANT_MONITOR flag this would cause mac80211 to allocate it without telling the driver (which was intentional) but also use it for later APIs to the driver without it ever having known about it which was _not_ intentional. Check through the code and only use the monitor_sdata in the relevant places (TX, MU-MIMO follow settings, TX power, and interface iteration) when the WANT_MONITOR flag is set. Cc: stable(a)vger.kernel.org Fixes: 0d9c2beed116 ("wifi: mac80211: fix monitor channel with chanctx emulation") Reported-by: ZeroBeat <ZeroBeat(a)gmx.de> Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219086 Tested-by: Lorenzo Bianconi <lorenzo(a)kernel.org> Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> --- net/mac80211/cfg.c | 7 +++++-- net/mac80211/tx.c | 5 +++-- net/mac80211/util.c | 2 +- 3 files changed, 9 insertions(+), 5 deletions(-) diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 85cb71de370f..b02b84ce2130 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, /* apply all changes now - no failures allowed */ - if (monitor_sdata) + if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { @@ -3053,6 +3053,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) + return -EOPNOTSUPP; + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) @@ -3115,7 +3118,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy, if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 72a9ba8bc5fd..edba4a31844f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local, break; } sdata = rcu_dereference(local->monitor_sdata); - if (sdata) { + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; @@ -3957,7 +3957,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, break; } tx.sdata = rcu_dereference(local->monitor_sdata); - if (tx.sdata) { + if (tx.sdata && + ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { vif = &tx.sdata->vif; info->hw_queue = vif->hw_queue[skb_get_queue_mapping(skb)]; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index ced19ce7c51a..c7ad9bc5973a 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local, sdata = rcu_dereference_check(local->monitor_sdata, lockdep_is_held(&local->iflist_mtx) || lockdep_is_held(&local->hw.wiphy->mtx)); - if (sdata && + if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only || sdata->flags & IEEE80211_SDATA_IN_DRIVER)) iterator(data, sdata->vif.addr, &sdata->vif); -- 2.45.2

1 year, 1 month

2
1
0 0

[PATCH] tools/nolibc: include arch.h from string.h

by Thomas Weißschuh

string.h tests for the macros NOLIBC_ARCH_HAS_$FUNC to use the architecture-optimized function variants. However if string.h is included before arch.h header than that check does not work, leading to duplicate function definitions. Fixes: 553845eebd60 ("tools/nolibc: x86-64: Use `rep movsb` for `memcpy()` and `memmove()`") Fixes: 12108aa8c1a1 ("tools/nolibc: x86-64: Use `rep stosb` for `memset()`") Cc: stable(a)vger.kernel.org Signed-off-by: Thomas Weißschuh <linux(a)weissschuh.net> --- If nobody complains I'll apply this after v6.11-rc1 is released. --- tools/include/nolibc/string.h | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index f9ab28421e6d..9ec9c24f38c0 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -7,6 +7,7 @@ #ifndef _NOLIBC_STRING_H #define _NOLIBC_STRING_H +#include "arch.h" #include "std.h" static void *malloc(size_t len); --- base-commit: 6ca8f2e20bd1ced8a7cd12b3ae4b1ceca85cfc2b change-id: 20240725-arch-has-func-59b6c92ce935 Best regards, -- Thomas Weißschuh <linux(a)weissschuh.net>

1 year, 1 month

2
1
0 0

[PATCH 2/3] spmi: pmic-arb: Pass the correct of_node to irq_domain_add_tree

by Stephen Boyd

From: Konrad Dybcio <konrad.dybcio(a)linaro.org> Currently, irqchips for all of the subnodes (which represent a given bus master) point to the parent wrapper node. This is no bueno, as no interrupts arrive, ever (because nothing references that node). Fix that by passing a reference to the respective master's of_node. Worth noting, this is a NOP for devices with only a single master described. Signed-off-by: Konrad Dybcio <konrad.dybcio(a)linaro.org> Link: https://lore.kernel.org/r/20240522-topic-spmi_multi_master_irqfix-v2-1-7ec9… Reviewed-by: Abel Vesa <abel.vesa(a)linaro.org> Tested-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov(a)linaro.org> Fixes: 02922ccbb330 ("spmi: pmic-arb: Register controller for bus instead of arbiter") Cc: stable(a)vger.kernel.org Signed-off-by: Stephen Boyd <sboyd(a)kernel.org> --- drivers/spmi/spmi-pmic-arb.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c index f240fcc5a4e1..b6880c13163c 100644 --- a/drivers/spmi/spmi-pmic-arb.c +++ b/drivers/spmi/spmi-pmic-arb.c @@ -1737,8 +1737,7 @@ static int spmi_pmic_arb_bus_init(struct platform_device *pdev, dev_dbg(&pdev->dev, "adding irq domain for bus %d\n", bus_index); - bus->domain = irq_domain_add_tree(dev->of_node, - &pmic_arb_irq_domain_ops, bus); + bus->domain = irq_domain_add_tree(node, &pmic_arb_irq_domain_ops, bus); if (!bus->domain) { dev_err(&pdev->dev, "unable to create irq_domain\n"); return -ENOMEM; -- https://git.kernel.org/pub/scm/linux/kernel/git/clk/linux.git/ https://git.kernel.org/pub/scm/linux/kernel/git/sboyd/spmi.git

1 year, 1 month

1
0
0 0

[PATCH 6.1.y] udf: Convert udf_mkdir() to new directory iteration code

by Sergio González Collado

From: Jan Kara <jack(a)suse.cz> [ Upstream commit 00bce6f792caccefa73daeaf9bde82d24d50037f ] Convert udf_mkdir() to new directory iteration code. Signed-off-by: Jan Kara <jack(a)suse.cz> (cherry picked from commit 00bce6f792caccefa73daeaf9bde82d24d50037f) Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> Reported-by: syzbot+600a32676df180ebc4af(a)syzkaller.appspotmail.com --- fs/udf/namei.c | 48 +++++++++++++++++++++--------------------------- 1 file changed, 21 insertions(+), 27 deletions(-) diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 7c95c549dd64..a33e6d762716 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -665,8 +665,7 @@ static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; - struct udf_fileident_bh fibh; - struct fileIdentDesc cfi, *fi; + struct udf_fileident_iter iter; int err; struct udf_inode_info *dinfo = UDF_I(dir); struct udf_inode_info *iinfo; @@ -678,47 +677,42 @@ static int udf_mkdir(struct user_namespace *mnt_userns, struct inode *dir, iinfo = UDF_I(inode); inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; - fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err); - if (!fi) { - inode_dec_link_count(inode); + err = udf_fiiter_add_entry(inode, NULL, &iter); + if (err) { + clear_nlink(inode); discard_new_inode(inode); - goto out; + return err; } set_nlink(inode, 2); - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(dinfo->i_location); - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(dinfo->i_location); + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(dinfo->i_unique & 0x00000000FFFFFFFFUL); - cfi.fileCharacteristics = + iter.fi.fileCharacteristics = FID_FILE_CHAR_DIRECTORY | FID_FILE_CHAR_PARENT; - udf_write_fi(inode, &cfi, fi, &fibh, NULL, NULL); - brelse(fibh.sbh); + udf_fiiter_write_fi(&iter, NULL); + udf_fiiter_release(&iter); mark_inode_dirty(inode); - fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); - if (!fi) { + err = udf_fiiter_add_entry(dir, dentry, &iter); + if (err) { clear_nlink(inode); - mark_inode_dirty(inode); discard_new_inode(inode); - goto out; + return err; } - cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); - cfi.icb.extLocation = cpu_to_lelb(iinfo->i_location); - *(__le32 *)((struct allocDescImpUse *)cfi.icb.impUse)->impUse = + iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); + iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); + *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); - cfi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; - udf_write_fi(dir, &cfi, fi, &fibh, NULL, NULL); + iter.fi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; + udf_fiiter_write_fi(&iter, NULL); + udf_fiiter_release(&iter); inc_nlink(dir); dir->i_ctime = dir->i_mtime = current_time(dir); mark_inode_dirty(dir); d_instantiate_new(dentry, inode); - if (fibh.sbh != fibh.ebh) - brelse(fibh.ebh); - brelse(fibh.sbh); - err = 0; -out: - return err; + return 0; } static int empty_dir(struct inode *dir) -- 2.39.2

1 year, 1 month

2
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror