September 2018 - Linux-stable-mirror

by Jaegeuk Kim

This patch fixes missing up_read call. Fixes: c9b60788fc76 ("f2fs: fix to do sanity check with block address in main area") Cc: <stable(a)vger.kernel.org> # 4.19+ Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> --- fs/f2fs/node.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 3994b44541b4..acb819b8fc42 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1541,8 +1541,10 @@ static int __write_node_page(struct page *page, bool atomic, bool *submitted, } if (__is_valid_data_blkaddr(ni.blk_addr) && - !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { + up_read(&sbi->node_write); goto redirty_out; + } if (atomic && !test_opt(sbi, NOBARRIER)) fio.op_flags |= REQ_PREFLUSH | REQ_FUA; -- 2.19.0.605.g01d371f741-goog

6 years

2
1
0 0

[PATCH 1/2] of/fdt: Allow architectures to override CONFIG_CMDLINE logic

by Paul Burton

The CONFIG_CMDLINE-related logic in early_init_dt_scan_chosen() falls back to copying CONFIG_CMDLINE into boot_command_line/data if the DT has a /chosen node but that node has no bootargs property or a bootargs property of length zero. This is problematic for the MIPS architecture because we support concatenating arguments from either the DT or the bootloader with those from CONFIG_CMDLINE, but the behaviour of early_init_dt_scan_chosen() gives us no way of knowing whether boot_command_line contains arguments from DT or already contains CONFIG_CMDLINE. This can lead to us concatenating CONFIG_CMDLINE with itself, duplicating command line arguments which can be problematic (eg. for earlycon which will attempt to register the same console twice & warn about it). Move the CONFIG_CMDLINE-related logic to a weak function that architectures can provide their own version of, such that we continue to use the existing logic for architectures where it's suitable but also allow MIPS to override this behaviour such that the architecture code knows when CONFIG_CMDLINE is used. Signed-off-by: Paul Burton <paul.burton(a)mips.com> References: https://patchwork.linux-mips.org/patch/18804/ Cc: Frank Rowand <frowand.list(a)gmail.com> Cc: Jaedon Shin <jaedon.shin(a)gmail.com> Cc: Mathieu Malaterre <malat(a)debian.org> Cc: Rob Herring <robh+dt(a)kernel.org> Cc: devicetree(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: linux-mips(a)linux-mips.org Cc: stable(a)vger.kernel.org # v4.16+ --- Marked for stable as a prerequisite of the following patch. DT maintainers: if you're OK with this it'd be great to get an ack so this can go through the mips-fixes tree. --- drivers/of/fdt.c | 55 +++++++++++++++++++++++++++++------------- include/linux/of_fdt.h | 1 + 2 files changed, 39 insertions(+), 17 deletions(-) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 800ad252cf9c..94c474315cff 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1072,6 +1072,43 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname, return 0; } +/** + * early_init_dt_fixup_cmdline_arch() - Modify a command line taken from DT + * @data: A pointer to the command line + * + * This function provides an opportunity to make modifications to command line + * arguments taken from a device tree before use, for example to concatenate + * them with arguments from other sources or replace them entirely. + * + * Modifications should be made directly to the string pointed at by @data, + * which is COMMAND_LINE_SIZE bytes in size. + * + * The default implementation supports extending or overriding the DT command + * line arguments using CONFIG_CMDLINE. Since other sources of command line + * arguments are platform-specific, architectures can provide their own + * implementation of this function to obtain their desired behaviour. + */ +void __init __weak early_init_dt_fixup_cmdline_arch(char *data) +{ + /* + * CONFIG_CMDLINE is meant to be a default in case nothing else + * managed to set the command line, unless CONFIG_CMDLINE_FORCE + * is set in which case we override whatever was found earlier. + */ +#ifdef CONFIG_CMDLINE +#if defined(CONFIG_CMDLINE_EXTEND) + strlcat(data, " ", COMMAND_LINE_SIZE); + strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#elif defined(CONFIG_CMDLINE_FORCE) + strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#else + /* No arguments from boot loader, use kernel's cmdl */ + if (!data[0]) + strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); +#endif +#endif /* CONFIG_CMDLINE */ +} + int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data) { @@ -1091,23 +1128,7 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, if (p != NULL && l > 0) strlcpy(data, p, min((int)l, COMMAND_LINE_SIZE)); - /* - * CONFIG_CMDLINE is meant to be a default in case nothing else - * managed to set the command line, unless CONFIG_CMDLINE_FORCE - * is set in which case we override whatever was found earlier. - */ -#ifdef CONFIG_CMDLINE -#if defined(CONFIG_CMDLINE_EXTEND) - strlcat(data, " ", COMMAND_LINE_SIZE); - strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#elif defined(CONFIG_CMDLINE_FORCE) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#else - /* No arguments from boot loader, use kernel's cmdl*/ - if (!((char *)data)[0]) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); -#endif -#endif /* CONFIG_CMDLINE */ + early_init_dt_fixup_cmdline_arch(data); pr_debug("Command line is: %s\n", (char*)data); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index b9cd9ebdf9b9..98935695f49d 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -80,6 +80,7 @@ extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern int early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size); extern int early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size, bool no_map); +extern void early_init_dt_fixup_cmdline_arch(char *data); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -- 2.18.0

6 years

4
8
0 0

[char-misc] mei: replace POLL* with EPOLL* for write queues.

by Tomas Winkler

Looks like during merging the bulk POLL* -> EPOLL* replacement missed the patch 'commit af336cabe083 ("mei: limit the number of queued writes")' Fix sparse warning: drivers/misc/mei/main.c:602:13: warning: restricted __poll_t degrades to integer drivers/misc/mei/main.c:605:30: warning: invalid assignment: |= drivers/misc/mei/main.c:605:30: left side has type restricted __poll_t drivers/misc/mei/main.c:605:30: right side has type int Cc: <stable(a)vger.kernel.org> #v4.17+ Fixes: 'commit af336cabe083 ("mei: limit the number of queued writes")' Signed-off-by: Tomas Winkler <tomas.winkler(a)intel.com> --- drivers/misc/mei/main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 4d77a6ae183a..87281b3695e6 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -599,10 +599,10 @@ static __poll_t mei_poll(struct file *file, poll_table *wait) mei_cl_read_start(cl, mei_cl_mtu(cl), file); } - if (req_events & (POLLOUT | POLLWRNORM)) { + if (req_events & (EPOLLOUT | EPOLLWRNORM)) { poll_wait(file, &cl->tx_wait, wait); if (cl->tx_cb_queued < dev->tx_queue_limit) - mask |= POLLOUT | POLLWRNORM; + mask |= EPOLLOUT | EPOLLWRNORM; } out: -- 2.14.4

6 years

1
0
0 0

[patch 2/6] mm: fix vma_is_anonymous() false-positives

by akpm＠linux-foundation.org

From: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Subject: mm: fix vma_is_anonymous() false-positives vma_is_anonymous() relies on ->vm_ops being NULL to detect anonymous VMA. This is unreliable as ->mmap may not set ->vm_ops. False-positive vma_is_anonymous() may lead to crashes: next ffff8801ce5e7040 prev ffff8801d20eca50 mm ffff88019c1e13c0 prot 27 anon_vma ffff88019680cdd8 vm_ops 0000000000000000 pgoff 0 file ffff8801b2ec2d00 private_data 0000000000000000 flags: 0xff(read|write|exec|shared|mayread|maywrite|mayexec|mayshare) ------------[ cut here ]------------ kernel BUG at mm/memory.c:1422! invalid opcode: 0000 [#1] SMP KASAN CPU: 0 PID: 18486 Comm: syz-executor3 Not tainted 4.18.0-rc3+ #136 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:zap_pmd_range mm/memory.c:1421 [inline] RIP: 0010:zap_pud_range mm/memory.c:1466 [inline] RIP: 0010:zap_p4d_range mm/memory.c:1487 [inline] RIP: 0010:unmap_page_range+0x1c18/0x2220 mm/memory.c:1508 Code: ff 31 ff 4c 89 e6 42 c6 04 33 f8 e8 92 dd d0 ff 4d 85 e4 0f 85 4a eb ff ff e8 54 dc d0 ff 48 8b bd 10 fc ff ff e8 82 95 fe ff <0f> 0b e8 41 dc d0 ff 0f 0b 4c 89 ad 18 fc ff ff c7 85 7c fb ff ff RSP: 0018:ffff8801b0587330 EFLAGS: 00010286 RAX: 000000000000013c RBX: 1ffff100360b0e9c RCX: ffffc90002620000 RDX: 0000000000000000 RSI: ffffffff81631851 RDI: 0000000000000001 RBP: ffff8801b05877c8 R08: ffff880199d40300 R09: ffffed003b5c4fc0 R10: ffffed003b5c4fc0 R11: ffff8801dae27e07 R12: 0000000000000000 R13: ffff88019c1e13c0 R14: dffffc0000000000 R15: 0000000020e01000 FS: 00007fca32251700(0000) GS:ffff8801dae00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f04c540d000 CR3: 00000001ac1f0000 CR4: 00000000001426f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: unmap_single_vma+0x1a0/0x310 mm/memory.c:1553 zap_page_range_single+0x3cc/0x580 mm/memory.c:1644 unmap_mapping_range_vma mm/memory.c:2792 [inline] unmap_mapping_range_tree mm/memory.c:2813 [inline] unmap_mapping_pages+0x3a7/0x5b0 mm/memory.c:2845 unmap_mapping_range+0x48/0x60 mm/memory.c:2880 truncate_pagecache+0x54/0x90 mm/truncate.c:800 truncate_setsize+0x70/0xb0 mm/truncate.c:826 simple_setattr+0xe9/0x110 fs/libfs.c:409 notify_change+0xf13/0x10f0 fs/attr.c:335 do_truncate+0x1ac/0x2b0 fs/open.c:63 do_sys_ftruncate+0x492/0x560 fs/open.c:205 __do_sys_ftruncate fs/open.c:215 [inline] __se_sys_ftruncate fs/open.c:213 [inline] __x64_sys_ftruncate+0x59/0x80 fs/open.c:213 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Reproducer: #include <stdio.h> #include <stddef.h> #include <stdint.h> #include <stdlib.h> #include <string.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/ioctl.h> #include <sys/mman.h> #include <unistd.h> #include <fcntl.h> #define KCOV_INIT_TRACE _IOR('c', 1, unsigned long) #define KCOV_ENABLE _IO('c', 100) #define KCOV_DISABLE _IO('c', 101) #define COVER_SIZE (1024<<10) #define KCOV_TRACE_PC 0 #define KCOV_TRACE_CMP 1 int main(int argc, char **argv) { int fd; unsigned long *cover; system("mount -t debugfs none /sys/kernel/debug"); fd = open("/sys/kernel/debug/kcov", O_RDWR); ioctl(fd, KCOV_INIT_TRACE, COVER_SIZE); cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long), PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); munmap(cover, COVER_SIZE * sizeof(unsigned long)); cover = mmap(NULL, COVER_SIZE * sizeof(unsigned long), PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); memset(cover, 0, COVER_SIZE * sizeof(unsigned long)); ftruncate(fd, 3UL << 20); return 0; } This can be fixed by assigning anonymous VMAs own vm_ops and not relying on it being NULL. If ->mmap() failed to set ->vm_ops, mmap_region() will set it to dummy_vm_ops. This way we will have non-NULL ->vm_ops for all VMAs. [kirill(a)shutemov.name: add comments] Link: http://lkml.kernel.org/r/20180711121521.omugjfpuuyxscjjf@kshutemo-mobl1 [kirill.shutemov(a)linux.intel.com: v2] Link: http://lkml.kernel.org/r/20180712145626.41665-2-kirill.shutemov@linux.intel… [kirill.shutemov(a)linux.intel.com: fix splat reported by Marcel] Link: http://lkml.kernel.org/r/20180716142049.ioa2irsd2d7sphn4@black.fi.intel.com Link: http://lkml.kernel.org/r/20180710134821.84709-2-kirill.shutemov@linux.intel… Signed-off-by: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Reported-by: syzbot+3f84280d52be9b7083cc(a)syzkaller.appspotmail.com Reviewed-by: Andrew Morton <akpm(a)linux-foundation.org> Cc: Dmitry Vyukov <dvyukov(a)google.com> Cc: Oleg Nesterov <oleg(a)redhat.com> Cc: Marcel Ziswiler <marcel.ziswiler(a)toradex.com> Cc: Andrea Arcangeli <aarcange(a)redhat.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- arch/arm/kernel/process.c | 1 + arch/ia64/kernel/perfmon.c | 1 + arch/ia64/mm/init.c | 2 ++ drivers/char/mem.c | 1 + fs/exec.c | 1 + fs/hugetlbfs/inode.c | 1 + include/linux/mm.h | 5 ++++- mm/khugepaged.c | 4 ++-- mm/mmap.c | 11 +++++++++++ mm/nommu.c | 9 ++++++++- mm/shmem.c | 1 + mm/util.c | 12 ++++++++++++ 12 files changed, 45 insertions(+), 4 deletions(-) diff -puN arch/arm/kernel/process.c~mm-fix-vma_is_anonymous-false-positives arch/arm/kernel/process.c --- a/arch/arm/kernel/process.c~mm-fix-vma_is_anonymous-false-positives +++ a/arch/arm/kernel/process.c @@ -334,6 +334,7 @@ static struct vm_area_struct gate_vma = .vm_start = 0xffff0000, .vm_end = 0xffff0000 + PAGE_SIZE, .vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC, + .vm_ops = &dummy_vm_ops, }; static int __init gate_vma_init(void) diff -puN arch/ia64/kernel/perfmon.c~mm-fix-vma_is_anonymous-false-positives arch/ia64/kernel/perfmon.c --- a/arch/ia64/kernel/perfmon.c~mm-fix-vma_is_anonymous-false-positives +++ a/arch/ia64/kernel/perfmon.c @@ -2292,6 +2292,7 @@ pfm_smpl_buffer_alloc(struct task_struct vma->vm_file = get_file(filp); vma->vm_flags = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP; vma->vm_page_prot = PAGE_READONLY; /* XXX may need to change */ + vma->vm_ops = &dummy_vm_ops; /* * Now we have everything we need and we can initialize diff -puN arch/ia64/mm/init.c~mm-fix-vma_is_anonymous-false-positives arch/ia64/mm/init.c --- a/arch/ia64/mm/init.c~mm-fix-vma_is_anonymous-false-positives +++ a/arch/ia64/mm/init.c @@ -122,6 +122,7 @@ ia64_init_addr_space (void) vma->vm_end = vma->vm_start + PAGE_SIZE; vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT; vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); + vma->vm_ops = &dummy_vm_ops; down_write(&current->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(&current->mm->mmap_sem); @@ -141,6 +142,7 @@ ia64_init_addr_space (void) vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT); vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vma->vm_ops = &dummy_vm_ops; down_write(&current->mm->mmap_sem); if (insert_vm_struct(current->mm, vma)) { up_write(&current->mm->mmap_sem); diff -puN drivers/char/mem.c~mm-fix-vma_is_anonymous-false-positives drivers/char/mem.c --- a/drivers/char/mem.c~mm-fix-vma_is_anonymous-false-positives +++ a/drivers/char/mem.c @@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, #endif if (vma->vm_flags & VM_SHARED) return shmem_zero_setup(vma); + vma->vm_ops = &anon_vm_ops; return 0; } diff -puN fs/exec.c~mm-fix-vma_is_anonymous-false-positives fs/exec.c --- a/fs/exec.c~mm-fix-vma_is_anonymous-false-positives +++ a/fs/exec.c @@ -307,6 +307,7 @@ static int __bprm_mm_init(struct linux_b * configured yet. */ BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); + vma->vm_ops = &anon_vm_ops; vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP; diff -puN fs/hugetlbfs/inode.c~mm-fix-vma_is_anonymous-false-positives fs/hugetlbfs/inode.c --- a/fs/hugetlbfs/inode.c~mm-fix-vma_is_anonymous-false-positives +++ a/fs/hugetlbfs/inode.c @@ -597,6 +597,7 @@ static long hugetlbfs_fallocate(struct f memset(&pseudo_vma, 0, sizeof(struct vm_area_struct)); pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; + pseudo_vma.vm_ops = &dummy_vm_ops; for (index = start; index < end; index++) { /* diff -puN include/linux/mm.h~mm-fix-vma_is_anonymous-false-positives include/linux/mm.h --- a/include/linux/mm.h~mm-fix-vma_is_anonymous-false-positives +++ a/include/linux/mm.h @@ -1536,9 +1536,12 @@ int clear_page_dirty_for_io(struct page int get_cmdline(struct task_struct *task, char *buffer, int buflen); +extern const struct vm_operations_struct anon_vm_ops; +extern const struct vm_operations_struct dummy_vm_ops; + static inline bool vma_is_anonymous(struct vm_area_struct *vma) { - return !vma->vm_ops; + return vma->vm_ops == &anon_vm_ops; } #ifdef CONFIG_SHMEM diff -puN mm/khugepaged.c~mm-fix-vma_is_anonymous-false-positives mm/khugepaged.c --- a/mm/khugepaged.c~mm-fix-vma_is_anonymous-false-positives +++ a/mm/khugepaged.c @@ -440,7 +440,7 @@ int khugepaged_enter_vma_merge(struct vm * page fault if needed. */ return 0; - if (vma->vm_ops || (vm_flags & VM_NO_KHUGEPAGED)) + if (!vma_is_anonymous(vma) || (vm_flags & VM_NO_KHUGEPAGED)) /* khugepaged not yet working on file or special mappings */ return 0; hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; @@ -831,7 +831,7 @@ static bool hugepage_vma_check(struct vm return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, HPAGE_PMD_NR); } - if (!vma->anon_vma || vma->vm_ops) + if (!vma->anon_vma || !vma_is_anonymous(vma)) return false; if (is_vma_temporary_stack(vma)) return false; diff -puN mm/mmap.c~mm-fix-vma_is_anonymous-false-positives mm/mmap.c --- a/mm/mmap.c~mm-fix-vma_is_anonymous-false-positives +++ a/mm/mmap.c @@ -561,6 +561,8 @@ static unsigned long count_vma_pages_ran void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { + WARN_ONCE(!vma->vm_ops, "missing vma->vm_ops"); + /* Update tracking information for the gap following the new vma. */ if (vma->vm_next) vma_gap_update(vma->vm_next); @@ -1762,6 +1764,11 @@ unsigned long mmap_region(struct file *f */ vma->vm_file = get_file(file); error = call_mmap(file, vma); + + /* All mappings must have ->vm_ops set */ + if (!vma->vm_ops) + vma->vm_ops = &dummy_vm_ops; + if (error) goto unmap_and_free_vma; @@ -1780,6 +1787,9 @@ unsigned long mmap_region(struct file *f error = shmem_zero_setup(vma); if (error) goto free_vma; + } else { + /* vma_is_anonymous() relies on this. */ + vma->vm_ops = &anon_vm_ops; } vma_link(mm, vma, prev, rb_link, rb_parent); @@ -2992,6 +3002,7 @@ static int do_brk_flags(unsigned long ad INIT_LIST_HEAD(&vma->anon_vma_chain); vma->vm_mm = mm; + vma->vm_ops = &anon_vm_ops; vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_pgoff = pgoff; diff -puN mm/nommu.c~mm-fix-vma_is_anonymous-false-positives mm/nommu.c --- a/mm/nommu.c~mm-fix-vma_is_anonymous-false-positives +++ a/mm/nommu.c @@ -1058,6 +1058,8 @@ static int do_mmap_shared_file(struct vm int ret; ret = call_mmap(vma->vm_file, vma); + if (!vma->vm_ops) + vma->vm_ops = &dummy_vm_ops; if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -1089,6 +1091,8 @@ static int do_mmap_private(struct vm_are */ if (capabilities & NOMMU_MAP_DIRECT) { ret = call_mmap(vma->vm_file, vma); + if (!vma->vm_ops) + vma->vm_ops = &dummy_vm_ops; if (ret == 0) { /* shouldn't return success if we're not sharing */ BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); @@ -1137,6 +1141,8 @@ static int do_mmap_private(struct vm_are fpos = vma->vm_pgoff; fpos <<= PAGE_SHIFT; + vma->vm_ops = &dummy_vm_ops; + ret = kernel_read(vma->vm_file, base, len, &fpos); if (ret < 0) goto error_free; @@ -1144,7 +1150,8 @@ static int do_mmap_private(struct vm_are /* clear the last little bit */ if (ret < len) memset(base + ret, 0, len - ret); - + } else { + vma->vm_ops = &anon_vm_ops; } return 0; diff -puN mm/shmem.c~mm-fix-vma_is_anonymous-false-positives mm/shmem.c --- a/mm/shmem.c~mm-fix-vma_is_anonymous-false-positives +++ a/mm/shmem.c @@ -1424,6 +1424,7 @@ static void shmem_pseudo_vma_init(struct /* Bias interleave by inode number to distribute better across nodes */ vma->vm_pgoff = index + info->vfs_inode.i_ino; vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index); + vma->vm_ops = &dummy_vm_ops; } static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma) diff -puN mm/util.c~mm-fix-vma_is_anonymous-false-positives mm/util.c --- a/mm/util.c~mm-fix-vma_is_anonymous-false-positives +++ a/mm/util.c @@ -20,6 +20,18 @@ #include "internal.h" +/* + * All anonymous VMAs have ->vm_ops set to anon_vm_ops. + * vma_is_anonymous() reiles on anon_vm_ops to detect anonymous VMA. + */ +const struct vm_operations_struct anon_vm_ops = {}; + +/* + * All VMAs have to have ->vm_ops set. dummy_vm_ops can be used if the VMA + * doesn't need to handle any of the operations. + */ +const struct vm_operations_struct dummy_vm_ops = {}; + static inline int is_kernel_rodata(unsigned long addr) { return addr >= (unsigned long)__start_rodata && _

6 years

4
8
0 0

ovl: hash non-dir by lower inode for fsnotify

by Mark Salyzyn

(cherry pick from commit 764baba80168ad3adafb521d2ab483ccbc49e344) Commit 31747eda41ef ("ovl: hash directory inodes for fsnotify") fixed an issue of inotify watch on directory that stops getting events after dropping dentry caches. A similar issue exists for non-dir non-upper files, for example: $ mkdir -p lower upper work merged $ touch lower/foo $ mount -t overlay -o lowerdir=lower,workdir=work,upperdir=upper none merged $ inotifywait merged/foo & $ echo 2 > /proc/sys/vm/drop_caches $ cat merged/foo inotifywait doesn't get the OPEN event, because ovl_lookup() called from 'cat' allocates a new overlay inode and does not reuse the watched inode. Fix this by hashing non-dir overlay inodes by lower real inode in the following cases that were not hashed before this change: - A non-upper overlay mount - A lower non-hardlink when index=off A helper ovl_hash_bylower() was added to put all the logic and documentation about which real inode an overlay inode is hashed by into one place. The issue dates back to initial version of overlayfs, but this patch depends on ovl_inode code that was introduced in kernel v4.13. Signed-off-by: Amir Goldstein <amir73il(a)gmail.com> Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Cc: <stable(a)vger.kernel.org> #v4.13 Signed-off-by: Mark Salyzyn <salyzyn(a)android.com> #4.14 Cc: <linux-unionfs(a)vger.kernel.org> Cc: <linux-kernel(a)vger.kernel.org> Cc: Greg KH <gregkh(a)linuxfoundation.org> --- fs/overlayfs/inode.c | 62 +++++++++++++++++++++++++++++++------------- 1 file changed, 44 insertions(+), 18 deletions(-) diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d60900b615f9..efed50304b49 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -14,6 +14,7 @@ #include <linux/posix_acl.h> #include <linux/ratelimit.h> #include "overlayfs.h" +#include "ovl_entry.h" int ovl_setattr(struct dentry *dentry, struct iattr *attr) { @@ -608,39 +609,63 @@ static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry, return true; } +/* + * Does overlay inode need to be hashed by lower inode? + */ +static bool ovl_hash_bylower(struct super_block *sb, struct dentry *upper, + struct dentry *lower, struct dentry *index) +{ + struct ovl_fs *ofs = sb->s_fs_info; + + /* No, if pure upper */ + if (!lower) + return false; + + /* Yes, if already indexed */ + if (index) + return true; + + /* Yes, if won't be copied up */ + if (!ofs->upper_mnt) + return true; + + /* No, if lower hardlink is or will be broken on copy up */ + if ((upper || !ovl_indexdir(sb)) && + !d_is_dir(lower) && d_inode(lower)->i_nlink > 1) + return false; + + /* No, if non-indexed upper with NFS export */ + if (sb->s_export_op && upper) + return false; + + /* Otherwise, hash by lower inode for fsnotify */ + return true; +} + struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry, struct dentry *index) { + struct super_block *sb = dentry->d_sb; struct dentry *lowerdentry = ovl_dentry_lower(dentry); struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL; struct inode *inode; - /* Already indexed or could be indexed on copy up? */ - bool indexed = (index || (ovl_indexdir(dentry->d_sb) && !upperdentry)); - struct dentry *origin = indexed ? lowerdentry : NULL; + bool bylower = ovl_hash_bylower(sb, upperdentry, lowerdentry, index); bool is_dir; - if (WARN_ON(upperdentry && indexed && !lowerdentry)) - return ERR_PTR(-EIO); - if (!realinode) realinode = d_inode(lowerdentry); /* - * Copy up origin (lower) may exist for non-indexed non-dir upper, but - * we must not use lower as hash key in that case. - * Hash non-dir that is or could be indexed by origin inode. - * Hash dir that is or could be merged by origin inode. - * Hash pure upper and non-indexed non-dir by upper inode. + * Copy up origin (lower) may exist for non-indexed upper, but we must + * not use lower as hash key if this is a broken hardlink. */ is_dir = S_ISDIR(realinode->i_mode); - if (is_dir) - origin = lowerdentry; - - if (upperdentry || origin) { - struct inode *key = d_inode(origin ?: upperdentry); + if (upperdentry || bylower) { + struct inode *key = d_inode(bylower ? lowerdentry : + upperdentry); unsigned int nlink = is_dir ? 1 : realinode->i_nlink; - inode = iget5_locked(dentry->d_sb, (unsigned long) key, + inode = iget5_locked(sb, (unsigned long) key, ovl_inode_test, ovl_inode_set, key); if (!inode) goto out_nomem; @@ -664,7 +689,8 @@ struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry, nlink = ovl_get_nlink(lowerdentry, upperdentry, nlink); set_nlink(inode, nlink); } else { - inode = new_inode(dentry->d_sb); + /* Lower hardlink that will be broken on copy up */ + inode = new_inode(sb); if (!inode) goto out_nomem; } -- 2.19.0.605.g01d371f741-goog

6 years

1
0
0 0

[PATCH] keys: Fix the use of the C++ keyword "private" in uapi/linux/keyctl.h

by David Howells

The keyctl_dh_params struct in uapi/linux/keyctl.h contains the symbol "private" which means that the header file will cause compilation failure if #included in to a C++ program. Further, the patch that added the same struct to the keyutils package named the symbol "priv", not "private". The previous attempt to fix this (commit 8a2336e549d3) did so by simply renaming the kernel's copy of the field to dh_private, but this then breaks existing userspace and as such has been reverted (commit 8c0f9f5b309d). [And note, to those who think that wrapping the struct in extern "C" {} will work: it won't; that only changes how symbol names are presented to the assembler and linker.]. Instead, insert an anonymous union around the "private" member and add a second member in there with the name "priv" to match the one in the keyutils package. The "private" member is then wrapped in !__cplusplus cpp-conditionals to hide it from C++. Fixes: ddbb41148724 ("KEYS: Add KEYCTL_DH_COMPUTE command") Fixes: 8a2336e549d3 ("uapi/linux/keyctl.h: don't use C++ reserved keyword as a struct member name") Signed-off-by: David Howells <dhowells(a)redhat.com> cc: Randy Dunlap <rdunlap(a)infradead.org> cc: Lubomir Rintel <lkundrak(a)v3.sk> cc: James Morris <jmorris(a)namei.org> cc: Mat Martineau <mathew.j.martineau(a)linux.intel.com> cc: Stephan Mueller <smueller(a)chronox.de> cc: Andrew Morton <akpm(a)linux-foundation.org> cc: Linus Torvalds <torvalds(a)linux-foundation.org> cc: stable(a)vger.kernel.org --- include/uapi/linux/keyctl.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index 7b8c9e19bad1..0f3cb13db8e9 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -65,7 +65,12 @@ /* keyctl structures */ struct keyctl_dh_params { - __s32 private; + union { +#ifndef __cplusplus + __s32 private; +#endif + __s32 priv; + }; __s32 prime; __s32 base; };

6 years

2
1
0 0

[PATCH] mmc: slot-gpio: Fix debounce time to use miliseconds again

by Marek Szyprowski

The debounce value passed to mmc_gpiod_request_cd() function is in microseconds, but msecs_to_jiffies() requires the value to be in miliseconds to properly calculate the delay, so adjust the value stored in cd_debounce_delay_ms context entry. Fixes: 1d71926bbd59 ("mmc: core: Fix debounce time to use microseconds") Fixes: bfd694d5e21c ("mmc: core: Add tunable delay before detecting card after card is inserted") Cc: stable(a)vger.kernel.org # v4.18+ Signed-off-by: Marek Szyprowski <m.szyprowski(a)samsung.com> --- This patch fixes eMMC card detection on Exynos5410-based Odroid XU board, broken since Linux next-20180928. --- drivers/mmc/core/slot-gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c index 2a833686784b..86803a3a04dc 100644 --- a/drivers/mmc/core/slot-gpio.c +++ b/drivers/mmc/core/slot-gpio.c @@ -271,7 +271,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id, if (debounce) { ret = gpiod_set_debounce(desc, debounce); if (ret < 0) - ctx->cd_debounce_delay_ms = debounce; + ctx->cd_debounce_delay_ms = debounce / 1000; } if (gpio_invert) -- 2.17.1

6 years

4
3
0 0

[PATCH] platform-msi: Free descriptors in platform_msi_domain_free()

by Miquel Raynal

Since the addition of platform MSI support, there were two helpers supposed to allocate/free IRQs for a device: platform_msi_domain_alloc_irqs() platform_msi_domain_free_irqs() In these helpers, IRQ descriptors are allocated in the "alloc" routine while they are freed in the "free" one. Later, two other helpers have been added to handle IRQ domains on top of MSI domains: platform_msi_domain_alloc() platform_msi_domain_free() Seen from the outside, the logic is pretty close with the former helpers and people used it with the same logic as before: a platform_msi_domain_alloc() call should be balanced with a platform_msi_domain_free() call. While this is probably what was intended to do, the platform_msi_domain_free() does not remove/free the IRQ descriptor(s) created/inserted in platform_msi_domain_alloc(). One effect of such situation is that removing a module that requested an IRQ will let one orphaned IRQ descriptor (with an allocated MSI entry) in the device descriptors list. Next time the module will be inserted back, one will observe that the allocation will happen twice in the MSI domain, one time for the remaining descriptor, one time for the new one. It also has the side effect to quickly overshoot the maximum number of allocated MSI and then prevent any module requesting an interrupt in the same domain to be inserted anymore. This situation has been met with loops of insertion/removal of the mvpp2.ko module (requesting 15 MSIs each time). Fixes: 552c494a7666 ("platform-msi: Allow creation of a MSI-based stacked irq domain") Cc: stable(a)vger.kernel.org Signed-off-by: Miquel Raynal <miquel.raynal(a)bootlin.com> --- drivers/base/platform-msi.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 60d6cc618f1c..b9d9d1729215 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -354,6 +354,20 @@ platform_msi_create_device_domain(struct device *dev, return NULL; } +static void platform_msi_domain_free_descs(struct irq_domain *domain, int virq, + int nvec) +{ + struct platform_msi_priv_data *data = domain->host_data; + struct msi_desc *desc, *tmp; + + list_for_each_entry_safe(desc, tmp, dev_to_msi_list(data->dev), list) { + if (desc->irq >= virq && desc->irq < (virq + nvec)) { + list_del(&desc->list); + free_msi_entry(desc); + } + } +} + /** * platform_msi_domain_free - Free interrupts associated with a platform-msi * domain @@ -375,6 +389,8 @@ void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_common(domain, desc->irq, 1); } + + platform_msi_domain_free_descs(domain, virq, nvec); } /** -- 2.17.1

6 years

2
4
0 0

[GIT PULL 0/6] perf/urgent fixes

by Arnaldo Carvalho de Melo

Hi Ingo, Please consider pulling, - Arnaldo Test results at the end of this message, as usual. The following changes since commit 5d05dfd13f20b01a3cd5d293058baa7d5c1583b6: Merge tag 'perf-urgent-for-mingo-4.19-20180918' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2018-09-19 13:25:35 +0200) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-urgent-for-mingo-4.19-20180928 for you to fetch changes up to 30aaba0acd1b4b6e69c45c416f2dbc9c8c5bdd50: perf python: Use -Wno-redundant-decls to build with PYTHON=python3 (2018-09-27 22:31:05 -0300) ---------------------------------------------------------------- perf/urgent fixes: - Fix the build on Clear Linux, coping with redundant declarations of function prototypes in python3 header files by adding -Wno-redundant-decls to build with PYTHON=python3 (Arnaldo Carvalho de Melo) - Fixes for processing inline frames in backtraces using DWARF based unwinding (Milian Wolff) - Cope with bad DWARF info for function names for inline frames,not trying to demangle this symbol. Problem reported with rust but reproduced as well with C++. Problem reported to the libbpf maintainers (Milian Wolff) - Fix python export to postgresql and sqlite code (Adrian Hunter) Signed-off-by: Arnaldo Carvalho de Melo <acme(a)redhat.com> ---------------------------------------------------------------- Adrian Hunter (2): perf script python: Fix export-to-postgresql.py occasional failure perf script python: Fix export-to-sqlite.py sample columns Arnaldo Carvalho de Melo (1): perf python: Use -Wno-redundant-decls to build with PYTHON=python3 Milian Wolff (3): perf report: Don't try to map ip to invalid map perf report: Use the offset address to find inline frames perf report: Don't crash on invalid inline debug information tools/perf/scripts/python/export-to-postgresql.py | 9 +++++++++ tools/perf/scripts/python/export-to-sqlite.py | 6 +++++- tools/perf/util/machine.c | 11 ++++++----- tools/perf/util/setup.py | 2 +- tools/perf/util/srcline.c | 3 +++ 5 files changed, 24 insertions(+), 7 deletions(-) Test results: The first ones are container (docker) based builds of tools/perf with and without libelf support. Where clang is available, it is also used to build perf with/without libelf, and building with LIBCLANGLLVM=1 (built-in clang) with gcc and clang when clang and its devel libraries are installed. The objtool and samples/bpf/ builds are disabled now that I'm switching from using the sources in a local volume to fetching them from a http server to build it inside the container, to make it easier to build in a container cluster. Those will come back later. Several are cross builds, the ones with -x-ARCH and the android one, and those may not have all the features built, due to lack of multi-arch devel packages, available and being used so far on just a few, like debian:experimental-x-{arm64,mipsel}. The 'perf test' one will perform a variety of tests exercising tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands with a variety of command line event specifications to then intercept the sys_perf_event syscall to check that the perf_event_attr fields are set up as expected, among a variety of other unit tests. Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/ with a variety of feature sets, exercising the build with an incomplete set of features as well as with a complete one. It is planned to have it run on each of the containers mentioned above, using some container orchestration infrastructure. Get in contact if interested in helping having this in place. The Clear Linux container is building with NO_CLANG=1, the problem preventing its use when building for python3 has been identified and the next builds will build in ClearLinux with both gcc and clang. This time around only gcc was used. # dm 1 alpine:3.4 : Ok gcc (Alpine 5.3.0) 5.3.0 2 alpine:3.5 : Ok gcc (Alpine 6.2.1) 6.2.1 20160822 3 alpine:3.6 : Ok gcc (Alpine 6.3.0) 6.3.0 4 alpine:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0 5 alpine:3.8 : Ok gcc (Alpine 6.4.0) 6.4.0 6 alpine:edge : Ok gcc (Alpine 6.4.0) 6.4.0 7 amazonlinux:1 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) 8 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180303 (Red Hat 7.3.1-5) 9 android-ndk:r12b-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 10 android-ndk:r15c-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 11 centos:5 : Ok gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55) 12 centos:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23) 13 centos:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) 14 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 8.2.1 20180502 15 debian:7 : Ok gcc (Debian 4.7.2-5) 4.7.2 16 debian:8 : Ok gcc (Debian 4.9.2-10+deb8u1) 4.9.2 17 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516 18 debian:experimental : Ok gcc (Debian 8.2.0-7) 8.2.0 19 debian:experimental-x-arm64 : Ok aarch64-linux-gnu-gcc (Debian 8.2.0-4) 8.2.0 20 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 8.1.0-12) 8.1.0 21 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 8.1.0-12) 8.1.0 22 debian:experimental-x-mipsel : Ok mipsel-linux-gnu-gcc (Debian 8.1.0-12) 8.1.0 23 fedora:20 : Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7) 24 fedora:21 : Ok gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6) 25 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 26 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 27 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) 28 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 29 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) 30 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2) 31 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6) 32 fedora:28 : Ok gcc (GCC) 8.1.1 20180712 (Red Hat 8.1.1-5) 33 fedora:rawhide : Ok gcc (GCC) 8.2.1 20180905 (Red Hat 8.2.1-3) 34 gentoo-stage3-amd64:latest : Ok gcc (Gentoo 7.3.0-r3 p1.4) 7.3.0 35 mageia:5 : Ok gcc (GCC) 4.9.2 36 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0 37 opensuse:13.2 : Ok gcc (SUSE Linux) 4.8.3 20140627 [gcc-4_8-branch revision 212064] 38 opensuse:42.1 : Ok gcc (SUSE Linux) 4.8.5 39 opensuse:42.2 : Ok gcc (SUSE Linux) 4.8.5 40 opensuse:42.3 : Ok gcc (SUSE Linux) 4.8.5 41 opensuse:tumbleweed : Ok gcc (SUSE Linux) 7.3.1 20180323 [gcc-7-branch revision 258812] 42 oraclelinux:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23.0.1) 43 oraclelinux:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28.0.1) 44 ubuntu:12.04.5 : Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 45 ubuntu:14.04.4 : Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4 46 ubuntu:14.04.4-x-linaro-arm64 : Ok aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0 47 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609 48 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 49 ubuntu:16.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 50 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 51 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 52 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 53 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 54 ubuntu:16.10 : Ok gcc (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005 55 ubuntu:17.10 : Ok gcc (Ubuntu 7.2.0-8ubuntu3.2) 7.2.0 56 ubuntu:18.04 : Ok gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 57 ubuntu:18.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-16ubuntu3) 7.3.0 58 ubuntu:18.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-16ubuntu3) 7.3.0 59 ubuntu:18.04-x-m68k : Ok m68k-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 60 ubuntu:18.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 61 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 62 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 63 ubuntu:18.04-x-riscv64 : Ok riscv64-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 64 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 65 ubuntu:18.04-x-sh4 : Ok sh4-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 66 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.3.0-16ubuntu3) 7.3.0 67 ubuntu:18.10 : Ok gcc (Ubuntu 8.2.0-4ubuntu1) 8.2.0 # # uname -a Linux jouet 4.19.0-rc4-00022-gad3273d5f1b9 #1 SMP Mon Sep 17 17:18:22 -03 2018 x86_64 x86_64 x86_64 GNU/Linux # git log --oneline -1 30aaba0acd1b perf python: Use -Wno-redundant-decls to build with PYTHON=python3 # perf version --build-options perf version 4.19.rc4.g30aaba dwarf: [ on ] # HAVE_DWARF_SUPPORT dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT glibc: [ on ] # HAVE_GLIBC_SUPPORT gtk2: [ on ] # HAVE_GTK2_SUPPORT syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT libbfd: [ on ] # HAVE_LIBBFD_SUPPORT libelf: [ on ] # HAVE_LIBELF_SUPPORT libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT libperl: [ on ] # HAVE_LIBPERL_SUPPORT libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT libslang: [ on ] # HAVE_SLANG_SUPPORT libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT zlib: [ on ] # HAVE_ZLIB_SUPPORT lzma: [ on ] # HAVE_LZMA_SUPPORT get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT bpf: [ on ] # HAVE_LIBBPF_SUPPORT # perf test 1: vmlinux symtab matches kallsyms : Ok 2: Detect openat syscall event : Ok 3: Detect openat syscall event on all cpus : Ok 4: Read samples using the mmap interface : Ok 5: Test data source output : Ok 6: Parse event definition strings : Ok 7: Simple expression parser : Ok 8: PERF_RECORD_* events & perf_sample fields : Ok 9: Parse perf pmu format : Ok 10: DSO data read : Ok 11: DSO data cache : Ok 12: DSO data reopen : Ok 13: Roundtrip evsel->name : Ok 14: Parse sched tracepoints fields : Ok 15: syscalls:sys_enter_openat event fields : Ok 16: Setup struct perf_event_attr : Ok 17: Match and link multiple hists : Ok 18: 'import perf' in python : Ok 19: Breakpoint overflow signal handler : Ok 20: Breakpoint overflow sampling : Ok 21: Breakpoint accounting : Ok 22: Number of exit events of a simple workload : Ok 23: Software clock events period values : Ok 24: Object code reading : Ok 25: Sample parsing : Ok 26: Use a dummy software event to keep tracking : Ok 27: Parse with no sample_id_all bit set : Ok 28: Filter hist entries : Ok 29: Lookup mmap thread : Ok 30: Share thread mg : Ok 31: Sort output of hist entries : Ok 32: Cumulate child hist entries : Ok 33: Track with sched_switch : Ok 34: Filter fds with revents mask in a fdarray : Ok 35: Add fd to a fdarray, making it autogrow : Ok 36: kmod_path__parse : Ok 37: Thread map : Ok 38: LLVM search and compile : 38.1: Basic BPF llvm compile : Ok 38.2: kbuild searching : Ok 38.3: Compile source for BPF prologue generation : Ok 38.4: Compile source for BPF relocation : Ok 39: Session topology : Ok 40: BPF filter : 40.1: Basic BPF filtering : Ok 40.2: BPF pinning : Ok 40.3: BPF prologue generation : Ok 40.4: BPF relocation checker : Ok 41: Synthesize thread map : Ok 42: Remove thread map : Ok 43: Synthesize cpu map : Ok 44: Synthesize stat config : Ok 45: Synthesize stat : Ok 46: Synthesize stat round : Ok 47: Synthesize attr update : Ok 48: Event times : Ok 49: Read backward ring buffer : Ok 50: Print cpu map : Ok 51: Probe SDT events : Ok 52: is_printable_array : Ok 53: Print bitmap : Ok 54: perf hooks : Ok 55: builtin clang support : Skip (not compiled in) 56: unit_number__scnprintf : Ok 57: mem2node : Ok 58: x86 rdpmc : Ok 59: Convert perf time to TSC : Ok 60: DWARF unwind : Ok 61: x86 instruction decoder - new instructions : Ok 62: x86 bp modify : Ok 63: Use vfs_getname probe to get syscall args filenames : Ok 64: Check open filename arg using perf trace + vfs_getname: Ok 65: probe libc's inet_pton & backtrace it with ping : Ok 66: Add vfs_getname probe to get syscall args filenames : Ok $ time make -C tools/perf build-test make: Entering directory '/home/acme/git/perf/tools/perf' - tarpkg: ./tests/perf-targz-src-pkg . - /home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP: make FEATURE_DUMP_COPY=/home/acme/git/perf/tools/perf/BUILD_TEST_FEATURE_DUMP feature-dump make_no_gtk2_O: make NO_GTK2=1 make_install_O: make install make_install_prefix_O: make install prefix=/tmp/krava make_tags_O: make tags make_static_O: make LDFLAGS=-static make_debug_O: make DEBUG=1 make_no_libperl_O: make NO_LIBPERL=1 make_no_libnuma_O: make NO_LIBNUMA=1 make_no_libunwind_O: make NO_LIBUNWIND=1 make_clean_all_O: make clean all make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1 make_util_pmu_bison_o_O: make util/pmu-bison.o make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1 make_no_demangle_O: make NO_DEMANGLE=1 make_no_libbpf_O: make NO_LIBBPF=1 make_help_O: make help make_no_libbionic_O: make NO_LIBBIONIC=1 make_no_libaudit_O: make NO_LIBAUDIT=1 make_perf_o_O: make perf.o make_no_auxtrace_O: make NO_AUXTRACE=1 make_util_map_o_O: make util/map.o make_with_clangllvm_O: make LIBCLANGLLVM=1 make_no_slang_O: make NO_SLANG=1 make_pure_O: make make_no_libelf_O: make NO_LIBELF=1 make_no_newt_O: make NO_NEWT=1 make_with_babeltrace_O: make LIBBABELTRACE=1 make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1 make_doc_O: make doc make_install_prefix_slash_O: make install prefix=/tmp/krava/ make_no_libpython_O: make NO_LIBPYTHON=1 make_no_backtrace_O: make NO_BACKTRACE=1 make_install_bin_O: make install-bin make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1 OK make: Leaving directory '/home/acme/git/perf/tools/perf' $

6 years

1
2
0 0

[STABLE PATCH] slub: make ->cpu_partial unsigned int

by zhong jiang

From: Alexey Dobriyan <adobriyan(a)gmail.com> /* * cpu_partial determined the maximum number of objects * kept in the per cpu partial lists of a processor. */ Can't be negative. I hit a real issue that it will result in a large number of memory leak. Because Freeing slabs are in interrupt context. So it can trigger this issue. put_cpu_partial can be interrupted more than once. due to a union struct of lru and pobjects in struct page, when other core handles page->lru list, for eaxmple, remove_partial in freeing slab code flow, It will result in pobjects being a negative value(0xdead0000). Therefore, a large number of slabs will be added to per_cpu partial list. I had posted the issue to community before. The detailed issue description is as follows. Link: https://www.spinics.net/lists/kernel/msg2870979.html After applying the patch, The issue is fixed. So the patch is a effective bugfix. It should go into stable. Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com> Acked-by: Christoph Lameter <cl(a)linux.com> Cc: Pekka Enberg <penberg(a)kernel.org> Cc: David Rientjes <rientjes(a)google.com> Cc: Joonsoo Kim <iamjoonsoo.kim(a)lge.com> Cc: stable(a)vger.kernel.org Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: zhong jiang <zhongjiang(a)huawei.com> --- include/linux/slub_def.h | 3 ++- mm/slub.c | 6 +++--- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 3388511..9b681f2 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -67,7 +67,8 @@ struct kmem_cache { int size; /* The size of an object including meta data */ int object_size; /* The size of an object without meta data */ int offset; /* Free pointer offset. */ - int cpu_partial; /* Number of per cpu partial objects to keep around */ + /* Number of per cpu partial objects to keep around */ + unsigned int cpu_partial; struct kmem_cache_order_objects oo; /* Allocation and freeing of slabs */ diff --git a/mm/slub.c b/mm/slub.c index 2284c43..c33b0e1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1661,7 +1661,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, { struct page *page, *page2; void *object = NULL; - int available = 0; + unsigned int available = 0; int objects; /* @@ -4674,10 +4674,10 @@ static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, size_t length) { - unsigned long objects; + unsigned int objects; int err; - err = kstrtoul(buf, 10, &objects); + err = kstrtouint(buf, 10, &objects); if (err) return err; if (objects && !kmem_cache_has_cpu_partial(s)) -- 1.7.12.4

6 years

3
3
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2018