diff options
author | Stephen Rothwell <sfr@canb.auug.org.au> | 2019-10-31 16:42:01 +1100 |
---|---|---|
committer | Stephen Rothwell <sfr@canb.auug.org.au> | 2019-10-31 16:42:01 +1100 |
commit | cbf83a411543bc3296abee873842ee8ff2a3e6b7 (patch) | |
tree | fc725a3d1dc0c6ba65fdf2b1092a96d43ecbb76b | |
parent | d8d78c852ef4217d0fc3810614fa3c32b98ef9ed (diff) | |
parent | 080dba92bc46ec72ffa03ba2a00079c7cdcce509 (diff) |
Merge branch 'akpm-current/current'
117 files changed, 5395 insertions, 1384 deletions
diff --git a/.gitattributes b/.gitattributes index 89c411b5ce6b..4b32eaa9571e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,2 +1,4 @@ *.c diff=cpp *.h diff=cpp +*.dtsi diff=dts +*.dts diff=dts diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 6e0da29e55f1..614179dc79a9 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -45,6 +45,7 @@ show up in /proc/sys/kernel: - hung_task_timeout_secs - hung_task_check_interval_secs - hung_task_warnings +- hung_task_interval_warnings - hyperv_record_panic_msg - kexec_load_disabled - kptr_restrict @@ -383,14 +384,29 @@ Possible values to set are in range {0..LONG_MAX/HZ}. hung_task_warnings: =================== -The maximum number of warnings to report. During a check interval -if a hung task is detected, this value is decreased by 1. +The maximum number of warnings to report. If after timeout a hung +task is present, this value is decreased by 1 every check interval, +producing a warning. When this value reaches 0, no more warnings will be reported. This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. -1: report an infinite number of warnings. +hung_task_interval_warnings: +=================== + +The same as hung_task_warnings, but set the number of interval +warnings to be issued about detected hung tasks during check +interval. That will produce warnings *before* the timeout happens. +If a hung task is detected during check interval, this value is +decreased by 1. When this value reaches 0, only timeout warnings +will be reported. +This file shows up if CONFIG_DETECT_HUNG_TASK is enabled. + +-1: report an infinite number of check interval warnings. + + hyperv_record_panic_msg: ======================== diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 1adbb8a371c7..fe43f4b30907 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1873,12 +1873,16 @@ There are some more advanced barrier functions: (*) smp_mb__before_atomic(); (*) smp_mb__after_atomic(); - These are for use with atomic (such as add, subtract, increment and - decrement) functions that don't return a value, especially when used for - reference counting. These functions do not imply memory barriers. - - These are also used for atomic bitop functions that do not return a - value (such as set_bit and clear_bit). + These are for use with atomic RMW functions that do not imply memory + barriers, but where the code needs a memory barrier. Examples for atomic + RMW functions that do not imply are memory barrier are e.g. add, + subtract, (failed) conditional operations, _relaxed functions, + but not atomic_read or atomic_set. A common example where a memory + barrier may be required is when atomic ops are used for reference + counting. + + These are also used for atomic RMW bitop functions that do not imply a + memory barrier (such as set_bit and clear_bit). As an example, consider a piece of code that marks an object as being dead and then decrements the object's reference count: diff --git a/Documentation/process/deprecated.rst b/Documentation/process/deprecated.rst index 179f2a5625a0..a0ffdc8daef3 100644 --- a/Documentation/process/deprecated.rst +++ b/Documentation/process/deprecated.rst @@ -84,7 +84,7 @@ buffer. This could result in linear overflows beyond the end of the buffer, leading to all kinds of misbehaviors. While `CONFIG_FORTIFY_SOURCE=y` and various compiler flags help reduce the risk of using this function, there is no good reason to add new uses of -this function. The safe replacement is :c:func:`strscpy`. +this function. The safe replacement is stracpy() or strscpy(). strncpy() on NUL-terminated strings ----------------------------------- @@ -93,9 +93,9 @@ will be NUL terminated. This can lead to various linear read overflows and other misbehavior due to the missing termination. It also NUL-pads the destination buffer if the source contents are shorter than the destination buffer size, which may be a needless performance penalty for callers using -only NUL-terminated strings. The safe replacement is :c:func:`strscpy`. -(Users of :c:func:`strscpy` still needing NUL-padding will need an -explicit :c:func:`memset` added.) +only NUL-terminated strings. In this case, the safe replacement is +stracpy() or strscpy(). If, however, the destination buffer still needs +NUL-padding, the safe replacement is stracpy_pad(). If a caller is using non-NUL-terminated strings, :c:func:`strncpy()` can still be used, but destinations should be marked with the `__nonstring @@ -107,7 +107,7 @@ strlcpy() :c:func:`strlcpy` reads the entire source buffer first, possibly exceeding the given limit of bytes to copy. This is inefficient and can lead to linear read overflows if a source string is not NUL-terminated. The -safe replacement is :c:func:`strscpy`. +safe replacement is stracpy() or strscpy(). Variable Length Arrays (VLAs) ----------------------------- diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index ea14a8bfc691..9019ed9f9c94 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -33,7 +33,6 @@ #define _ASM_ARC_PGTABLE_H #include <linux/bits.h> -#define __ARCH_USE_5LEVEL_HACK #include <asm-generic/pgtable-nopmd.h> #include <asm/page.h> #include <asm/mmu.h> /* to propagate CONFIG_ARC_MMU_VER <n> */ diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 3861543b66a0..fb86bc3e9b35 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -30,6 +30,7 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address) * with the 'reference' page table. */ pgd_t *pgd, *pgd_k; + p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; @@ -39,8 +40,13 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address) if (!pgd_present(*pgd_k)) goto bad_area; - pud = pud_offset(pgd, address); - pud_k = pud_offset(pgd_k, address); + p4d = p4d_offset(pgd, address); + p4d_k = p4d_offset(pgd_k, address); + if (!p4d_present(*p4d_k)) + goto bad_area; + + pud = pud_offset(p4d, address); + pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) goto bad_area; diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index a4856bfaedf3..fc8849e4f72e 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -111,12 +111,14 @@ EXPORT_SYMBOL(__kunmap_atomic); static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr) { pgd_t *pgd_k; + p4d_t *p4d_k; pud_t *pud_k; pmd_t *pmd_k; pte_t *pte_k; pgd_k = pgd_offset_k(kvaddr); - pud_k = pud_offset(pgd_k, kvaddr); + p4d_k = p4d_offset(pgd_k, kvaddr); + pud_k = pud_offset(p4d_k, kvaddr); pmd_k = pmd_offset(pud_k, kvaddr); pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 60c929f3683b..d10247fab0fd 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1069,7 +1069,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; /* * FIXME: Cleanup page tables (also in arch_add_memory() in case @@ -1078,7 +1077,6 @@ void arch_remove_memory(int nid, u64 start, u64 size, * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be * unlocked yet. */ - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index bf9df2625bc8..a6dd80a2c939 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -689,9 +689,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index be941d382c8d..97e5922cb52e 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -130,10 +130,9 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); int ret; - __remove_pages(page_zone(page), start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index a124f19f7b3c..c1d96e588152 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -291,10 +291,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); vmem_remove_mapping(start, size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index dfdbaa50946e..d1b1ff2be17a 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -434,9 +434,7 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = PFN_DOWN(start); unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 930edeb41ec3..0a74407ef92e 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -865,10 +865,8 @@ void arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct zone *zone; - zone = page_zone(pfn_to_page(start_pfn)); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); } #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a6b5c653727b..b8541d77452c 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1212,10 +1212,8 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size, { unsigned long start_pfn = start >> PAGE_SHIFT; unsigned long nr_pages = size >> PAGE_SHIFT; - struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap); - struct zone *zone = page_zone(page); - __remove_pages(zone, start_pfn, nr_pages, altmap); + __remove_pages(start_pfn, nr_pages, altmap); kernel_physical_mapping_remove(start, start + size); } #endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 55907c27075b..a757d9ed88a7 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -538,12 +538,7 @@ static ssize_t soft_offline_page_store(struct device *dev, if (kstrtoull(buf, 0, &pfn) < 0) return -EINVAL; pfn >>= PAGE_SHIFT; - if (!pfn_valid(pfn)) - return -ENXIO; - /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ - if (!pfn_to_online_page(pfn)) - return -EIO; - ret = soft_offline_page(pfn_to_page(pfn), 0); + ret = soft_offline_page(pfn, 0); return ret == 0 ? count : ret; } diff --git a/drivers/base/node.c b/drivers/base/node.c index 296546ffed6c..98a31bafc8a2 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -496,20 +496,17 @@ static ssize_t node_read_vmstat(struct device *dev, int n = 0; for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", vmstat_text[i], + n += sprintf(buf+n, "%s %lu\n", zone_stat_name(i), sum_zone_node_page_state(nid, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", numa_stat_name(i), sum_zone_numa_state(nid, i)); #endif for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) - n += sprintf(buf+n, "%s %lu\n", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], + n += sprintf(buf+n, "%s %lu\n", node_stat_name(i), node_page_state(pgdat, i)); return n; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 34bd73526afd..da6ced15c6c5 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -680,9 +680,7 @@ static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg) __ClearPageOffline(pg); /* This frame is currently backed; online the page. */ - __online_page_set_limits(pg); - __online_page_increment_counters(pg); - __online_page_free(pg); + generic_online_page(pg, 0); lockdep_assert_held(&dm_device.ha_lock); dm_device.num_pages_onlined++; diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 5bae515c8e25..4f2e78a5e4db 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -374,7 +374,6 @@ static void xen_online_page(struct page *page, unsigned int order) mutex_lock(&balloon_mutex); for (i = 0; i < size; i++) { p = pfn_to_page(start_pfn + i); - __online_page_set_limits(p); balloon_append(p); } mutex_unlock(&balloon_mutex); @@ -1287,12 +1287,9 @@ static long read_events(struct kioctx *ctx, long min_nr, long nr, * the ringbuffer empty. So in practice we should be ok, but it's * something to be aware of when touching this code. */ - if (until == 0) - aio_read_events(ctx, min_nr, nr, event, &ret); - else - wait_event_interruptible_hrtimeout(ctx->wait, - aio_read_events(ctx, min_nr, nr, event, &ret), - until); + wait_event_interruptible_hrtimeout(ctx->wait, + aio_read_events(ctx, min_nr, nr, event, &ret), + until); return ret; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index c5642bcb6b46..54f21926940e 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -404,6 +404,17 @@ static unsigned long total_mapping_size(const struct elf_phdr *cmds, int nr) ELF_PAGESTART(cmds[first_idx].p_vaddr); } +static int elf_read(struct file *file, void *buf, size_t len, loff_t pos) +{ + ssize_t rv; + + rv = kernel_read(file, buf, len, &pos); + if (unlikely(rv != len)) { + return (rv < 0) ? rv : -EIO; + } + return 0; +} + /** * load_elf_phdrs() - load ELF program headers * @elf_ex: ELF header of the binary whose program headers should be loaded @@ -418,7 +429,6 @@ static struct elf_phdr *load_elf_phdrs(const struct elfhdr *elf_ex, { struct elf_phdr *elf_phdata = NULL; int retval, err = -1; - loff_t pos = elf_ex->e_phoff; unsigned int size; /* @@ -439,9 +449,9 @@ static struct elf_phdr *load_elf_phdrs(const struct elfhdr *elf_ex, goto out; /* Read in the program headers */ - retval = kernel_read(elf_file, elf_phdata, size, &pos); - if (retval != size) { - err = (retval < 0) ? retval : -EIO; + retval = elf_read(elf_file, elf_phdata, size, elf_ex->e_phoff); + if (retval < 0) { + err = retval; goto out; } @@ -544,7 +554,7 @@ static inline int make_prot(u32 p_flags) an ELF header */ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, - struct file *interpreter, unsigned long *interp_map_addr, + struct file *interpreter, unsigned long no_base, struct elf_phdr *interp_elf_phdata) { struct elf_phdr *eppnt; @@ -590,8 +600,6 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, map_addr = elf_map(interpreter, load_addr + vaddr, eppnt, elf_prot, elf_type, total_size); total_size = 0; - if (!*interp_map_addr) - *interp_map_addr = map_addr; error = map_addr; if (BAD_ADDR(map_addr)) goto out; @@ -722,7 +730,6 @@ static int load_elf_binary(struct linux_binprm *bprm) elf_ppnt = elf_phdata; for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { char *elf_interpreter; - loff_t pos; if (elf_ppnt->p_type != PT_INTERP) continue; @@ -740,14 +747,10 @@ static int load_elf_binary(struct linux_binprm *bprm) if (!elf_interpreter) goto out_free_ph; - pos = elf_ppnt->p_offset; - retval = kernel_read(bprm->file, elf_interpreter, - elf_ppnt->p_filesz, &pos); - if (retval != elf_ppnt->p_filesz) { - if (retval >= 0) - retval = -EIO; + retval = elf_read(bprm->file, elf_interpreter, elf_ppnt->p_filesz, + elf_ppnt->p_offset); + if (retval < 0) goto out_free_interp; - } /* make sure path is NULL terminated */ retval = -ENOEXEC; if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0') @@ -766,14 +769,10 @@ static int load_elf_binary(struct linux_binprm *bprm) would_dump(bprm, interpreter); /* Get the exec headers */ - pos = 0; - retval = kernel_read(interpreter, &loc->interp_elf_ex, - sizeof(loc->interp_elf_ex), &pos); - if (retval != sizeof(loc->interp_elf_ex)) { - if (retval >= 0) - retval = -EIO; + retval = elf_read(interpreter, &loc->interp_elf_ex, + sizeof(loc->interp_elf_ex), 0); + if (retval < 0) goto out_free_dentry; - } break; @@ -1054,11 +1053,8 @@ out_free_interp: } if (interpreter) { - unsigned long interp_map_addr = 0; - elf_entry = load_elf_interp(&loc->interp_elf_ex, interpreter, - &interp_map_addr, load_bias, interp_elf_phdata); if (!IS_ERR((void *)elf_entry)) { /* @@ -1179,11 +1175,10 @@ static int load_elf_library(struct file *file) unsigned long elf_bss, bss, len; int retval, error, i, j; struct elfhdr elf_ex; - loff_t pos = 0; error = -ENOEXEC; - retval = kernel_read(file, &elf_ex, sizeof(elf_ex), &pos); - if (retval != sizeof(elf_ex)) + retval = elf_read(file, &elf_ex, sizeof(elf_ex), 0); + if (retval < 0) goto out; if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0) @@ -1208,9 +1203,8 @@ static int load_elf_library(struct file *file) eppnt = elf_phdata; error = -ENOEXEC; - pos = elf_ex.e_phoff; - retval = kernel_read(file, eppnt, j, &pos); - if (retval != j) + retval = elf_read(file, eppnt, j, elf_ex.e_phoff); + if (retval < 0) goto out_free_ph; for (j = 0, i = 0; i<elf_ex.e_phnum; i++) diff --git a/fs/buffer.c b/fs/buffer.c index 86a38b979323..131d39ec7d31 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -956,10 +956,20 @@ grow_dev_page(struct block_device *bdev, sector_t block, end_block = init_page_buffers(page, bdev, (sector_t)index << sizebits, size); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x01; +#endif goto done; } - if (!try_to_free_buffers(page)) + if (!try_to_free_buffers(page)) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x02; +#endif goto failed; + } +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x04; +#endif } /* @@ -979,6 +989,9 @@ grow_dev_page(struct block_device *bdev, sector_t block, spin_unlock(&inode->i_mapping->private_lock); done: ret = (block < end_block) ? 1 : -ENXIO; +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x08; +#endif failed: unlock_page(page); put_page(page); @@ -1034,6 +1047,12 @@ __getblk_slow(struct block_device *bdev, sector_t block, return NULL; } +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_stamp = jiffies; + current->getblk_executed = 0; + current->getblk_bh_count = 0; + current->getblk_bh_state = 0; +#endif for (;;) { struct buffer_head *bh; int ret; @@ -1045,6 +1064,24 @@ __getblk_slow(struct block_device *bdev, sector_t block, ret = grow_buffers(bdev, block, size, gfp); if (ret < 0) return NULL; + +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + if (!time_after(jiffies, current->getblk_stamp + 3 * HZ)) + continue; + printk(KERN_ERR "%s(%u): getblk(): executed=%x bh_count=%d bh_state=%lx bdev_super_blocksize=%ld size=%u bdev_super_blocksize_bits=%d bdev_inode_blkbits=%d\n", + current->comm, current->pid, current->getblk_executed, + current->getblk_bh_count, current->getblk_bh_state, + IS_ERR_OR_NULL(bdev->bd_super) ? -1L : + bdev->bd_super->s_blocksize, size, + IS_ERR_OR_NULL(bdev->bd_super) ? -1 : + bdev->bd_super->s_blocksize_bits, + IS_ERR_OR_NULL(bdev->bd_inode) ? -1 : + bdev->bd_inode->i_blkbits); + current->getblk_executed = 0; + current->getblk_bh_count = 0; + current->getblk_bh_state = 0; + current->getblk_stamp = jiffies; +#endif } } @@ -3223,6 +3260,11 @@ EXPORT_SYMBOL(sync_dirty_buffer); */ static inline int buffer_busy(struct buffer_head *bh) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x80; + current->getblk_bh_count = atomic_read(&bh->b_count); + current->getblk_bh_state = bh->b_state; +#endif return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } @@ -3261,11 +3303,18 @@ int try_to_free_buffers(struct page *page) int ret = 0; BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) + if (PageWriteback(page)) { +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x10; +#endif return 0; + } if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(page, &buffers_to_free); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x20; +#endif goto out; } @@ -3289,6 +3338,9 @@ int try_to_free_buffers(struct page *page) if (ret) cancel_dirty_page(page); spin_unlock(&mapping->private_lock); +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + current->getblk_executed |= 0x40; +#endif out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index c4159bcc05d9..67a395039268 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -551,28 +551,23 @@ out_unlock: */ #ifdef CONFIG_DEBUG_LOCK_ALLOC -static struct nested_calls poll_safewake_ncalls; - -static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests) -{ - unsigned long flags; - wait_queue_head_t *wqueue = (wait_queue_head_t *)cookie; - - spin_lock_irqsave_nested(&wqueue->lock, flags, call_nests + 1); - wake_up_locked_poll(wqueue, EPOLLIN); - spin_unlock_irqrestore(&wqueue->lock, flags); - - return 0; -} +static DEFINE_PER_CPU(int, wakeup_nest); static void ep_poll_safewake(wait_queue_head_t *wq) { - int this_cpu = get_cpu(); - - ep_call_nested(&poll_safewake_ncalls, - ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + unsigned long flags; + int subclass; - put_cpu(); + local_irq_save(flags); + preempt_disable(); + subclass = __this_cpu_read(wakeup_nest); + spin_lock_nested(&wq->lock, subclass + 1); + __this_cpu_inc(wakeup_nest); + wake_up_locked_poll(wq, POLLIN); + __this_cpu_dec(wakeup_nest); + spin_unlock(&wq->lock); + local_irq_restore(flags); + preempt_enable(); } #else @@ -671,7 +666,6 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, void *priv, int depth, bool ep_locked) { __poll_t res; - int pwake = 0; struct epitem *epi, *nepi; LIST_HEAD(txlist); @@ -738,26 +732,11 @@ static __poll_t ep_scan_ready_list(struct eventpoll *ep, */ list_splice(&txlist, &ep->rdllist); __pm_relax(ep->ws); - - if (!list_empty(&ep->rdllist)) { - /* - * Wake up (if active) both the eventpoll wait list and - * the ->poll() wait list (delayed after we release the lock). - */ - if (waitqueue_active(&ep->wq)) - wake_up(&ep->wq); - if (waitqueue_active(&ep->poll_wait)) - pwake++; - } write_unlock_irq(&ep->lock); if (!ep_locked) mutex_unlock(&ep->mtx); - /* We have to call this outside the lock */ - if (pwake) - ep_poll_safewake(&ep->poll_wait); - return res; } @@ -2370,11 +2349,6 @@ static int __init eventpoll_init(void) */ ep_nested_calls_init(&poll_loop_ncalls); -#ifdef CONFIG_DEBUG_LOCK_ALLOC - /* Initialize the structure used to perform safe poll wait head wake ups */ - ep_nested_calls_init(&poll_safewake_ncalls); -#endif - /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a478df035651..b9561bbf1dd9 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -440,7 +440,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, u32 hash; index = page->index; - hash = hugetlb_fault_mutex_hash(h, mapping, index, 0); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* @@ -644,7 +644,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ - hash = hugetlb_fault_mutex_hash(h, mapping, index, addr); + hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c index 3e7da392aa6f..bb981ec76456 100644 --- a/fs/ocfs2/acl.c +++ b/fs/ocfs2/acl.c @@ -327,8 +327,8 @@ int ocfs2_acl_chmod(struct inode *inode, struct buffer_head *bh) down_read(&OCFS2_I(inode)->ip_xattr_sem); acl = ocfs2_get_acl_nolock(inode, ACL_TYPE_ACCESS, bh); up_read(&OCFS2_I(inode)->ip_xattr_sem); - if (IS_ERR(acl) || !acl) - return PTR_ERR(acl); + if (IS_ERR_OR_NULL(acl)) + return PTR_ERR_OR_ZERO(acl); ret = __posix_acl_chmod(&acl, GFP_KERNEL, inode->i_mode); if (ret) return ret; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 53939bf9d7d2..9876db52913a 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos) return 0; } -static int ocfs2_prepare_inode_for_refcount(struct inode *inode, - struct file *file, - loff_t pos, size_t count, - int *meta_level) +static int ocfs2_inode_lock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int overwrite_io, + int write_sem, + int wait) { - int ret; - struct buffer_head *di_bh = NULL; - u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; - u32 clusters = - ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + int ret = 0; - ret = ocfs2_inode_lock(inode, &di_bh, 1); - if (ret) { - mlog_errno(ret); + if (wait) + ret = ocfs2_inode_lock(inode, NULL, meta_level); + else + ret = ocfs2_try_inode_lock(inode, + overwrite_io ? NULL : di_bh, meta_level); + if (ret < 0) goto out; + + if (wait) { + if (write_sem) + down_write(&OCFS2_I(inode)->ip_alloc_sem); + else + down_read(&OCFS2_I(inode)->ip_alloc_sem); + } else { + if (write_sem) + ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem); + else + ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem); + + if (!ret) { + ret = -EAGAIN; + goto out_unlock; + } } - *meta_level = 1; + return ret; - ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); - if (ret) - mlog_errno(ret); +out_unlock: + brelse(*di_bh); + ocfs2_inode_unlock(inode, meta_level); out: - brelse(di_bh); return ret; } +static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode, + struct buffer_head **di_bh, + int meta_level, + int write_sem) +{ + if (write_sem) + up_write(&OCFS2_I(inode)->ip_alloc_sem); + else + up_read(&OCFS2_I(inode)->ip_alloc_sem); + + brelse(*di_bh); + *di_bh = NULL; + + if (meta_level >= 0) + ocfs2_inode_unlock(inode, meta_level); +} + static int ocfs2_prepare_inode_for_write(struct file *file, loff_t pos, size_t count, int wait) { int ret = 0, meta_level = 0, overwrite_io = 0; + int write_sem = 0; struct dentry *dentry = file->f_path.dentry; struct inode *inode = d_inode(dentry); struct buffer_head *di_bh = NULL; + u32 cpos; + u32 clusters; /* * We start with a read level meta lock and only jump to an ex * if we need to make modifications here. */ for(;;) { - if (wait) - ret = ocfs2_inode_lock(inode, NULL, meta_level); - else - ret = ocfs2_try_inode_lock(inode, - overwrite_io ? NULL : &di_bh, meta_level); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + write_sem, + wait); if (ret < 0) { - meta_level = -1; if (ret != -EAGAIN) mlog_errno(ret); goto out; @@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file, */ if (!wait && !overwrite_io) { overwrite_io = 1; - if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) { - ret = -EAGAIN; - goto out_unlock; - } ret = ocfs2_overwrite_io(inode, di_bh, pos, count); - brelse(di_bh); - di_bh = NULL; - up_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret < 0) { if (ret != -EAGAIN) mlog_errno(ret); @@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file, * set inode->i_size at the end of a write. */ if (should_remove_suid(dentry)) { if (meta_level == 0) { - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); meta_level = 1; continue; } @@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file, ret = ocfs2_check_range_for_refcount(inode, pos, count); if (ret == 1) { - ocfs2_inode_unlock(inode, meta_level); - meta_level = -1; - - ret = ocfs2_prepare_inode_for_refcount(inode, - file, - pos, - count, - &meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); + ret = ocfs2_inode_lock_for_extent_tree(inode, + &di_bh, + meta_level, + overwrite_io, + 1, + wait); + write_sem = 1; + if (ret < 0) { + if (ret != -EAGAIN) + mlog_errno(ret); + goto out; + } + + cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits; + clusters = + ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos; + ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX); } if (ret < 0) { - mlog_errno(ret); + if (ret != -EAGAIN) + mlog_errno(ret); goto out_unlock; } @@ -2219,10 +2265,10 @@ out_unlock: trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno, pos, count, wait); - brelse(di_bh); - - if (meta_level >= 0) - ocfs2_inode_unlock(inode, meta_level); + ocfs2_inode_unlock_for_extent_tree(inode, + &di_bh, + meta_level, + write_sem); out: return ret; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 64e9ee1b129e..074e9585c699 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -138,8 +138,12 @@ static int proc_getattr(const struct path *path, struct kstat *stat, { struct inode *inode = d_inode(path->dentry); struct proc_dir_entry *de = PDE(inode); - if (de && de->nlink) - set_nlink(inode, de->nlink); + if (de) { + nlink_t nlink = READ_ONCE(de->nlink); + if (nlink > 0) { + set_nlink(inode, nlink); + } + } generic_fillattr(inode, stat); return 0; @@ -159,7 +163,6 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, { const char *cp = name, *next; struct proc_dir_entry *de; - unsigned int len; de = *ret; if (!de) @@ -170,13 +173,12 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret, if (!next) break; - len = next - cp; - de = pde_subdir_find(de, cp, len); + de = pde_subdir_find(de, cp, next - cp); if (!de) { WARN(1, "name '%s'\n", name); return -ENOENT; } - cp += len + 1; + cp = next + 1; } *residual = cp; *ret = de; @@ -362,6 +364,7 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, write_unlock(&proc_subdir_lock); goto out_free_inum; } + dir->nlink++; write_unlock(&proc_subdir_lock); return dp; @@ -472,10 +475,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, ent->data = data; ent->proc_fops = &proc_dir_operations; ent->proc_iops = &proc_dir_inode_operations; - parent->nlink++; ent = proc_register(parent, ent); - if (!ent) - parent->nlink--; } return ent; } @@ -505,10 +505,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) ent->data = NULL; ent->proc_fops = NULL; ent->proc_iops = NULL; - parent->nlink++; ent = proc_register(parent, ent); - if (!ent) - parent->nlink--; } return ent; } @@ -666,8 +663,12 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) len = strlen(fn); de = pde_subdir_find(parent, fn, len); - if (de) + if (de) { rb_erase(&de->subdir_node, &parent->subdir); + if (S_ISDIR(de->mode)) { + parent->nlink--; + } + } write_unlock(&proc_subdir_lock); if (!de) { WARN(1, "name '%s'\n", name); @@ -676,9 +677,6 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent) proc_entry_rundown(de); - if (S_ISDIR(de->mode)) - parent->nlink--; - de->nlink = 0; WARN(pde_subdir_first(de), "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n", __func__, de->parent->name, de->name, pde_subdir_first(de)->name); @@ -714,13 +712,12 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent) de = next; continue; } - write_unlock(&proc_subdir_lock); - - proc_entry_rundown(de); next = de->parent; if (S_ISDIR(de->mode)) next->nlink--; - de->nlink = 0; + write_unlock(&proc_subdir_lock); + + proc_entry_rundown(de); if (de == root) break; pde_put(de); diff --git a/fs/proc/internal.h b/fs/proc/internal.h index cd0c8d5ce9a1..0f3b557c9b77 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -197,8 +197,8 @@ extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, lof * inode.c */ struct pde_opener { - struct file *file; struct list_head lh; + struct file *file; bool closing; struct completion *c; } __randomize_layout; diff --git a/fs/proc/page.c b/fs/proc/page.c index 7c952ee732e6..e40dbfe1168e 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -97,7 +97,10 @@ u64 stable_page_flags(struct page *page) * it differentiates a memory hole from a page with no flags */ if (!page) - return 1 << KPF_NOPAGE; + return BIT_ULL(KPF_NOPAGE); + + if (pfn_zone_device_reserved(page_to_pfn(page))) + return BIT_ULL(KPF_RESERVED); k = page->flags; u = 0; @@ -109,22 +112,22 @@ u64 stable_page_flags(struct page *page) * simple test in page_mapped() is not enough. */ if (!PageSlab(page) && page_mapped(page)) - u |= 1 << KPF_MMAP; + u |= BIT_ULL(KPF_MMAP); if (PageAnon(page)) - u |= 1 << KPF_ANON; + u |= BIT_ULL(KPF_ANON); if (PageKsm(page)) - u |= 1 << KPF_KSM; + u |= BIT_ULL(KPF_KSM); /* * compound pages: export both head/tail info * they together define a compound page's start/end pos and order */ if (PageHead(page)) - u |= 1 << KPF_COMPOUND_HEAD; + u |= BIT_ULL(KPF_COMPOUND_HEAD); if (PageTail(page)) - u |= 1 << KPF_COMPOUND_TAIL; + u |= BIT_ULL(KPF_COMPOUND_TAIL); if (PageHuge(page)) - u |= 1 << KPF_HUGE; + u |= BIT_ULL(KPF_HUGE); /* * PageTransCompound can be true for non-huge compound pages (slab * pages or pages allocated by drivers with __GFP_COMP) because it @@ -135,14 +138,13 @@ u64 stable_page_flags(struct page *page) struct page *head = compound_head(page); if (PageLRU(head) || PageAnon(head)) - u |= 1 << KPF_THP; + u |= BIT_ULL(KPF_THP); else if (is_huge_zero_page(head)) { - u |= 1 << KPF_ZERO_PAGE; - u |= 1 << KPF_THP; + u |= BIT_ULL(KPF_ZERO_PAGE); + u |= BIT_ULL(KPF_THP); } } else if (is_zero_pfn(page_to_pfn(page))) - u |= 1 << KPF_ZERO_PAGE; - + u |= BIT_ULL(KPF_ZERO_PAGE); /* * Caveats on high order pages: page->_refcount will only be set @@ -150,23 +152,23 @@ u64 stable_page_flags(struct page *page) * SLOB won't set PG_slab at all on compound pages. */ if (PageBuddy(page)) - u |= 1 << KPF_BUDDY; + u |= BIT_ULL(KPF_BUDDY); else if (page_count(page) == 0 && is_free_buddy_page(page)) - u |= 1 << KPF_BUDDY; + u |= BIT_ULL(KPF_BUDDY); if (PageOffline(page)) - u |= 1 << KPF_OFFLINE; + u |= BIT_ULL(KPF_OFFLINE); if (PageTable(page)) - u |= 1 << KPF_PGTABLE; + u |= BIT_ULL(KPF_PGTABLE); if (page_is_idle(page)) - u |= 1 << KPF_IDLE; + u |= BIT_ULL(KPF_IDLE); u |= kpf_copy_bit(k, KPF_LOCKED, PG_locked); u |= kpf_copy_bit(k, KPF_SLAB, PG_slab); if (PageTail(page) && PageSlab(compound_head(page))) - u |= 1 << KPF_SLAB; + u |= BIT_ULL(KPF_SLAB); u |= kpf_copy_bit(k, KPF_ERROR, PG_error); u |= kpf_copy_bit(k, KPF_DIRTY, PG_dirty); @@ -179,7 +181,7 @@ u64 stable_page_flags(struct page *page) u |= kpf_copy_bit(k, KPF_RECLAIM, PG_reclaim); if (PageSwapCache(page)) - u |= 1 << KPF_SWAPCACHE; + u |= BIT_ULL(KPF_SWAPCACHE); u |= kpf_copy_bit(k, KPF_SWAPBACKED, PG_swapbacked); u |= kpf_copy_bit(k, KPF_UNEVICTABLE, PG_unevictable); diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index d82636e8eb65..35624ca2a2f9 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -147,6 +147,17 @@ static int ramfs_symlink(struct inode * dir, struct dentry *dentry, const char * return error; } +static int ramfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + + inode = ramfs_get_inode(dir->i_sb, dir, mode, 0); + if (!inode) + return -ENOSPC; + d_tmpfile(dentry, inode); + return 0; +} + static const struct inode_operations ramfs_dir_inode_operations = { .create = ramfs_create, .lookup = simple_lookup, @@ -157,6 +168,7 @@ static const struct inode_operations ramfs_dir_inode_operations = { .rmdir = simple_rmdir, .mknod = ramfs_mknod, .rename = simple_rename, + .tmpfile = ramfs_tmpfile, }; /* diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d7f54e535294..f18e6e828b21 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1460,7 +1460,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, start = vma->vm_start; vma_end = min(end, vma->vm_end); - new_flags = (vma->vm_flags & ~vm_flags) | vm_flags; + new_flags = (vma->vm_flags & + ~(VM_UFFD_MISSING|VM_UFFD_WP)) | vm_flags; prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index e3667c9a33a5..c86cf7cb4bba 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -30,7 +30,6 @@ #undef pud_free_tlb #define pud_free_tlb(tlb, x, addr) do { } while (0) #define pud_free(mm, x) do { } while (0) -#define __pud_free_tlb(tlb, x, addr) do { } while (0) #undef pud_addr_end #define pud_addr_end(addr, end) (end) diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index f6947da70d71..4c74b1c1d13b 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -51,7 +51,6 @@ static inline int p4d_present(p4d_t p4d) #undef p4d_free_tlb #define p4d_free_tlb(tlb, x, addr) do { } while (0) #define p4d_free(mm, x) do { } while (0) -#define __p4d_free_tlb(tlb, x, addr) do { } while (0) #undef p4d_addr_end #define p4d_addr_end(addr, end) (end) diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index aebab905e6cd..ce2cbb3c380f 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -50,7 +50,7 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) */ #define p4d_alloc_one(mm, address) NULL #define p4d_free(mm, x) do { } while (0) -#define __p4d_free_tlb(tlb, x, a) do { } while (0) +#define p4d_free_tlb(tlb, x, a) do { } while (0) #undef p4d_addr_end #define p4d_addr_end(addr, end) (end) diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index b85b8271a73d..0d9b28cba16d 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -60,7 +60,7 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address) static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) { } -#define __pmd_free_tlb(tlb, x, a) do { } while (0) +#define pmd_free_tlb(tlb, x, a) do { } while (0) #undef pmd_addr_end #define pmd_addr_end(addr, end) (end) diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index c77a1d301155..d3776cb494c0 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -59,7 +59,7 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) */ #define pud_alloc_one(mm, address) NULL #define pud_free(mm, x) do { } while (0) -#define __pud_free_tlb(tlb, x, a) do { } while (0) +#define pud_free_tlb(tlb, x, a) do { } while (0) #undef pud_addr_end #define pud_addr_end(addr, end) (end) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 818691846c90..9cdcbc7c0b7b 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -558,8 +558,19 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) * Do the tests inline, but report and clear the bad entry in mm/memory.c. */ void pgd_clear_bad(pgd_t *); + +#ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *); +#else +#define p4d_clear_bad(p4d) do { } while (0) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *); +#else +#define pud_clear_bad(p4d) do { } while (0) +#endif + void pmd_clear_bad(pmd_t *); static inline int pgd_none_or_clear_bad(pgd_t *pgd) diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 04c0644006fd..05dddc17522b 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -584,7 +584,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm } while (0) #endif -#ifndef __ARCH_HAS_4LEVEL_HACK #ifndef pud_free_tlb #define pud_free_tlb(tlb, pudp, address) \ do { \ @@ -594,9 +593,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif -#endif -#ifndef __ARCH_HAS_5LEVEL_HACK #ifndef p4d_free_tlb #define p4d_free_tlb(tlb, pudp, address) \ do { \ @@ -605,7 +602,6 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif -#endif #endif /* CONFIG_MMU */ diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h index 0fe5426f2bdc..e3a0be2c90ad 100644 --- a/include/linux/build_bug.h +++ b/include/linux/build_bug.h @@ -9,11 +9,11 @@ #else /* __CHECKER__ */ /* * Force a compilation error if condition is true, but also produce a - * result (of value 0 and type size_t), so the expression can be used + * result (of value 0 and type int), so the expression can be used * e.g. in a structure initializer (or where-ever else comma expressions * aren't permitted). */ -#define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:(-!!(e)); })) +#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); }))) #endif /* __CHECKER__ */ /* Force a compilation error if a constant expression is not a power of 2 */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 61f2f6ff9467..e5b817cb86e7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -612,6 +612,8 @@ static inline bool pm_suspended_storage(void) /* The below functions must be run on a range from a single zone. */ extern int alloc_contig_range(unsigned long start, unsigned long end, unsigned migratetype, gfp_t gfp_mask); +extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask); #endif void free_contig_range(unsigned long pfn, unsigned int nr_pages); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 53fc34f930d0..4c5a16be7912 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -105,8 +105,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason); void free_huge_page(struct page *page); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address); +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f491690d54c6..b38bbefabfab 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -358,6 +358,9 @@ static inline phys_addr_t memblock_phys_alloc(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE); } +void *memblock_alloc_exact_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ae703ea3ef48..e82928deea88 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -58,7 +58,6 @@ enum mem_cgroup_protection { struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; - int priority; unsigned int generation; }; @@ -112,7 +111,7 @@ struct memcg_shrinker_map { }; /* - * per-zone information in memory controller. + * per-node information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; @@ -126,7 +125,7 @@ struct mem_cgroup_per_node { unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; - struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + struct mem_cgroup_reclaim_iter iter; struct memcg_shrinker_map __rcu *shrinker_map; @@ -399,8 +398,7 @@ mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @node or a given - * @memcg and @zone. This can be the node lruvec, if the memory controller - * is disabled. + * @memcg. This can be the node lruvec, if the memory controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, struct mem_cgroup *memcg) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index f46ea71b4ffd..384ffb3d69ab 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -102,13 +102,10 @@ extern unsigned long __offline_isolated_pages(unsigned long start_pfn, typedef void (*online_page_callback_t)(struct page *page, unsigned int order); +extern void generic_online_page(struct page *page, unsigned int order); extern int set_online_page_callback(online_page_callback_t callback); extern int restore_online_page_callback(online_page_callback_t callback); -extern void __online_page_set_limits(struct page *page); -extern void __online_page_increment_counters(struct page *page); -extern void __online_page_free(struct page *page); - extern int try_online_node(int nid); extern int arch_add_memory(int nid, u64 start, u64 size, @@ -125,8 +122,8 @@ static inline bool movable_node_is_enabled(void) extern void arch_remove_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap); -extern void __remove_pages(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages, struct vmem_altmap *altmap); +extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages, + struct vmem_altmap *altmap); /* reasonably generic interface to expand the physical pages */ extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, @@ -345,6 +342,9 @@ extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource); extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); +extern void remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern int sparse_add_section(int nid, unsigned long pfn, unsigned long nr_pages, struct vmem_altmap *altmap); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 6fefb09af7c3..c676e33205d3 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -123,6 +123,7 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) } #ifdef CONFIG_ZONE_DEVICE +bool pfn_zone_device_reserved(unsigned long pfn); void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap); @@ -133,6 +134,11 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); #else +static inline bool pfn_zone_device_reserved(unsigned long pfn) +{ + return false; +} + static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) { diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..82e4aaa8bef9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1648,19 +1648,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return (unsigned long)val; } +void mm_trace_rss_stat(int member, long count); + static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { - atomic_long_add(value, &mm->rss_stat.count[member]); + long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { - atomic_long_inc(&mm->rss_stat.count[member]); + long count = atomic_long_inc_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { - atomic_long_dec(&mm->rss_stat.count[member]); + long count = atomic_long_dec_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(member, count); } /* Optimized variant when page is already known not to be PageAnon */ @@ -2219,9 +2227,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); -extern void zone_pcp_update(struct zone *zone); -extern void zone_pcp_reset(struct zone *zone); - /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; @@ -2786,7 +2791,7 @@ extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages __read_mostly; -extern int soft_offline_page(struct page *page, int flags); +extern int soft_offline_page(unsigned long pfn, int flags); /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b0a36d1580b6..d4ca03b93373 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1079,7 +1079,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, /** * for_each_zone_zonelist_nodemask - helper macro to iterate over valid zones in a zonelist at or below a given zone index and within a nodemask * @zone - The current zone in the iterator - * @z - The current pointer within zonelist->zones being iterated + * @z - The current pointer within zonelist->_zonerefs being iterated * @zlist - The zonelist being iterated * @highidx - The zone index of the highest zone to return * @nodemask - Nodemask allowed by the allocator diff --git a/include/linux/notifier.h b/include/linux/notifier.h index 0096a05395e3..018947611483 100644 --- a/include/linux/notifier.h +++ b/include/linux/notifier.h @@ -150,10 +150,6 @@ extern int raw_notifier_chain_register(struct raw_notifier_head *nh, extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); -extern int blocking_notifier_chain_cond_register( - struct blocking_notifier_head *nh, - struct notifier_block *nb); - extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index f91cb8898ff0..3b8e5c5f7e1f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -610,27 +610,6 @@ static inline int PageTransCompound(struct page *page) } /* - * PageTransCompoundMap is the same as PageTransCompound, but it also - * guarantees the primary MMU has the entire compound page mapped - * through pmd_trans_huge, which in turn guarantees the secondary MMUs - * can also map the entire compound page. This allows the secondary - * MMUs to call get_user_pages() only once for each compound page and - * to immediately map the entire compound page with a single secondary - * MMU fault. If there will be a pmd split later, the secondary MMUs - * will get an update through the MMU notifier invalidation through - * split_huge_pmd(). - * - * Unlike PageTransCompound, this is safe to be called only while - * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false - * positives. - */ -static inline int PageTransCompoundMap(struct page *page) -{ - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; -} - -/* * PageTransTail returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known * that hugetlbfs pages aren't involved. @@ -681,6 +660,39 @@ static inline int TestClearPageDoubleMap(struct page *page) return test_and_clear_bit(PG_double_map, &page[1].flags); } +/* + * PageTransCompoundMap is the same as PageTransCompound, but it also + * guarantees the primary MMU has the entire compound page mapped + * through pmd_trans_huge, which in turn guarantees the secondary MMUs + * can also map the entire compound page. This allows the secondary + * MMUs to call get_user_pages() only once for each compound page and + * to immediately map the entire compound page with a single secondary + * MMU fault. If there will be a pmd split later, the secondary MMUs + * will get an update through the MMU notifier invalidation through + * split_huge_pmd(). + * + * Unlike PageTransCompound, this is safe to be called only while + * split_huge_pmd() cannot run from under us, like if protected by the + * MMU notifier, otherwise it may result in page->_mapcount check false + * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so checking PageDoubleMap flag to rule + * this out. + */ +static inline int PageTransCompoundMap(struct page *page) +{ + bool pmd_mapped; + + if (PageAnon(page)) + pmd_mapped = atomic_read(&page->_mapcount) < 0; + else + pmd_mapped = atomic_read(&page->_mapcount) >= 0 && + !PageDoubleMap(compound_head(page)); + + return PageTransCompound(page) && pmd_mapped; +} #else TESTPAGEFLAG_FALSE(TransHuge) TESTPAGEFLAG_FALSE(TransCompound) diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 1099c2fee20f..6861df759fad 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -30,7 +30,7 @@ static inline bool is_migrate_isolate(int migratetype) } #endif -#define SKIP_HWPOISON 0x1 +#define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 bool has_unmovable_pages(struct zone *zone, struct page *page, int count, @@ -58,7 +58,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, * Test all pages in [start_pfn, end_pfn) are isolated or not. */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages); + int isol_flags); struct page *alloc_migrate_target(struct page *page, unsigned long private); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index a705aa2d03f9..0640be56dcbd 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -58,8 +58,8 @@ extern int remove_proc_subtree(const char *, struct proc_dir_entry *); struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct seq_operations *ops, unsigned int state_size, void *data); -#define proc_create_net(name, mode, parent, state_size, ops) \ - proc_create_net_data(name, mode, parent, state_size, ops, NULL) +#define proc_create_net(name, mode, parent, ops, state_size) \ + proc_create_net_data(name, mode, parent, ops, state_size, NULL) struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, struct proc_dir_entry *parent, int (*show)(struct seq_file *, void *), void *data); diff --git a/include/linux/sched.h b/include/linux/sched.h index f72984f94a5c..d6c80e7991df 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -905,6 +905,7 @@ struct task_struct { #ifdef CONFIG_DETECT_HUNG_TASK unsigned long last_switch_count; unsigned long last_switch_time; + unsigned long killed_time; #endif /* Filesystem information: */ struct fs_struct *fs; @@ -1251,6 +1252,7 @@ struct task_struct { #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; #endif + struct list_head oom_victim_list; #ifdef CONFIG_VMAP_STACK struct vm_struct *stack_vm_area; #endif @@ -1271,6 +1273,13 @@ struct task_struct { unsigned long prev_lowest_stack; #endif +#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT + unsigned long getblk_stamp; + unsigned int getblk_executed; + unsigned int getblk_bh_count; + unsigned long getblk_bh_state; +#endif + /* * New fields for task_struct should be added above here, so that * they are included in the randomized portion of task_struct. diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index d4f6215ee03f..89f55e914673 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -12,6 +12,7 @@ extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; extern unsigned long sysctl_hung_task_check_interval_secs; extern int sysctl_hung_task_warnings; +extern int sysctl_hung_task_interval_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/include/linux/slab.h b/include/linux/slab.h index 6d52953dbdf0..270f03ee3f83 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -561,26 +561,6 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -/* - * Determine size used for the nth kmalloc cache. - * return size or 0 if a kmalloc cache for that - * size does not exist - */ -static __always_inline unsigned int kmalloc_size(unsigned int n) -{ -#ifndef CONFIG_SLOB - if (n > 2) - return 1U << n; - - if (n == 1 && KMALLOC_MIN_SIZE <= 32) - return 96; - - if (n == 2 && KMALLOC_MIN_SIZE <= 64) - return 192; -#endif - return 0; -} - static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB diff --git a/include/linux/string.h b/include/linux/string.h index b6ccdc2c7f02..f516cec5277c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -35,6 +35,51 @@ ssize_t strscpy(char *, const char *, size_t); /* Wraps calls to strscpy()/memset(), no arch specific code required */ ssize_t strscpy_pad(char *dest, const char *src, size_t count); +/** + * stracpy - Copy a C-string into an array of char/u8/s8 or equivalent + * @dest: Where to copy the string, must be an array of char and not a pointer + * @src: String to copy, may be a pointer or const char array + * + * Helper for strscpy(). + * Copies a maximum of sizeof(@dest) bytes of @src with %NUL termination. + * + * Returns: + * * The number of characters copied (not including the trailing %NUL) + * * -E2BIG if @dest is a zero size array or @src was truncated. + */ +#define stracpy(dest, src) \ +({ \ + size_t count = ARRAY_SIZE(dest); \ + BUILD_BUG_ON(!(__same_type(dest, char[]) || \ + __same_type(dest, unsigned char[]) || \ + __same_type(dest, signed char[]))); \ + \ + strscpy(dest, src, count); \ +}) + +/** + * stracpy_pad - Copy a C-string into an array of char/u8/s8 with %NUL padding + * @dest: Where to copy the string, must be an array of char and not a pointer + * @src: String to copy, may be a pointer or const char array + * + * Helper for strscpy_pad(). + * Copies a maximum of sizeof(@dest) bytes of @src with %NUL termination + * and zero-pads the remaining size of @dest + * + * Returns: + * * The number of characters copied (not including the trailing %NUL) + * * -E2BIG if @dest is a zero size array or @src was truncated. + */ +#define stracpy_pad(dest, src) \ +({ \ + size_t count = ARRAY_SIZE(dest); \ + BUILD_BUG_ON(!(__same_type(dest, char[]) || \ + __same_type(dest, unsigned char[]) || \ + __same_type(dest, signed char[]))); \ + \ + strscpy_pad(dest, src, count); \ +}) + #ifndef __HAVE_ARCH_STRCAT extern char * strcat(char *, const char *); #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6df477329b76..02fa84493f23 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -120,8 +120,7 @@ static inline void *proc_sys_poll_event(struct ctl_table_poll *poll) struct ctl_table_poll name = __CTL_TABLE_POLL_INITIALIZER(name) /* A sysctl table is an array of struct ctl_table: */ -struct ctl_table -{ +struct ctl_table { const char *procname; /* Text ID for /proc/sys, or zero */ void *data; int maxlen; @@ -140,8 +139,7 @@ struct ctl_node { /* struct ctl_table_header is used to maintain dynamic lists of struct ctl_table trees. */ -struct ctl_table_header -{ +struct ctl_table_header { union { struct { struct ctl_table *ctl_table; diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 659a4400517b..e93e249a4e9b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -147,6 +147,8 @@ check_copy_size(const void *addr, size_t bytes, bool is_source) __bad_copy_to(); return false; } + if (WARN_ON_ONCE(bytes > INT_MAX)) + return false; check_object_size(addr, bytes, is_source); return true; } diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index bdeda4b079fe..292485f3d24d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -31,6 +31,12 @@ struct reclaim_stat { unsigned nr_unmap_fail; }; +enum writeback_stat_item { + NR_DIRTY_THRESHOLD, + NR_DIRTY_BG_THRESHOLD, + NR_VM_WRITEBACK_STAT_ITEMS, +}; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. @@ -381,4 +387,48 @@ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, extern const char * const vmstat_text[]; +static inline const char *zone_stat_name(enum zone_stat_item item) +{ + return vmstat_text[item]; +} + +#ifdef CONFIG_NUMA +static inline const char *numa_stat_name(enum numa_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + item]; +} +#endif /* CONFIG_NUMA */ + +static inline const char *node_stat_name(enum node_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + item]; +} + +static inline const char *lru_list_name(enum lru_list lru) +{ + return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" +} + +static inline const char *writeback_stat_name(enum writeback_stat_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + item]; +} + +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) +static inline const char *vm_event_name(enum vm_event_item item) +{ + return vmstat_text[NR_VM_ZONE_STAT_ITEMS + + NR_VM_NUMA_STAT_ITEMS + + NR_VM_NODE_STAT_ITEMS + + NR_VM_WRITEBACK_STAT_ITEMS + + item]; +} +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ + #endif /* _LINUX_VMSTAT_H */ diff --git a/include/linux/wait.h b/include/linux/wait.h index 3eb7cae8206c..3647d1008d88 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -540,7 +540,7 @@ do { \ ({ \ int __ret = 0; \ might_sleep(); \ - if (!(condition)) \ + if (!(condition) && (timeout)) \ __ret = __wait_event_hrtimeout(wq_head, condition, timeout, \ TASK_UNINTERRUPTIBLE); \ __ret; \ @@ -566,7 +566,7 @@ do { \ ({ \ long __ret = 0; \ might_sleep(); \ - if (!(condition)) \ + if (!(condition) && (timeout)) \ __ret = __wait_event_hrtimeout(wq, condition, timeout, \ TASK_INTERRUPTIBLE); \ __ret; \ diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 69e8bb8963db..5a0666bfcf85 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -316,6 +316,27 @@ TRACE_EVENT(mm_page_alloc_extfrag, __entry->change_ownership) ); +TRACE_EVENT(rss_stat, + + TP_PROTO(int member, + long count), + + TP_ARGS(member, count), + + TP_STRUCT__entry( + __field(int, member) + __field(long, size) + ), + + TP_fast_assign( + __entry->member = member; + __entry->size = (count << PAGE_SHIFT); + ), + + TP_printk("member=%d size=%ldB", + __entry->member, + __entry->size) + ); #endif /* _TRACE_KMEM_H */ /* This part must be outside protection */ diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index a5ab2973e8dc..c37e2280e6dd 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -127,18 +127,43 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_b ); #ifdef CONFIG_MEMCG -DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin, +DECLARE_EVENT_CLASS(mm_vmscan_memcg_reclaim_begin_template, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags), - TP_ARGS(order, gfp_flags) + TP_ARGS(cgroup_ino, order, gfp_flags), + + TP_STRUCT__entry( + __field(unsigned int, cgroup_ino) + __field(int, order) + __field(gfp_t, gfp_flags) + ), + + TP_fast_assign( + __entry->cgroup_ino = cgroup_ino; + __entry->order = order; + __entry->gfp_flags = gfp_flags; + ), + + TP_printk("cgroup_ino=%u order=%d gfp_flags=%s", + __entry->cgroup_ino, __entry->order, + show_gfp_flags(__entry->gfp_flags)) ); -DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin, +DEFINE_EVENT(mm_vmscan_memcg_reclaim_begin_template, + mm_vmscan_memcg_reclaim_begin, - TP_PROTO(int order, gfp_t gfp_flags), + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags), - TP_ARGS(order, gfp_flags) + TP_ARGS(cgroup_ino, order, gfp_flags) +); + +DEFINE_EVENT(mm_vmscan_memcg_reclaim_begin_template, + mm_vmscan_memcg_softlimit_reclaim_begin, + + TP_PROTO(unsigned int cgroup_ino, int order, gfp_t gfp_flags), + + TP_ARGS(cgroup_ino, order, gfp_flags) ); #endif /* CONFIG_MEMCG */ @@ -167,18 +192,40 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end ); #ifdef CONFIG_MEMCG -DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end, +DECLARE_EVENT_CLASS(mm_vmscan_memcg_reclaim_end_template, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed), - TP_ARGS(nr_reclaimed) + TP_ARGS(cgroup_ino, nr_reclaimed), + + TP_STRUCT__entry( + __field(unsigned int, cgroup_ino) + __field(unsigned long, nr_reclaimed) + ), + + TP_fast_assign( + __entry->cgroup_ino = cgroup_ino; + __entry->nr_reclaimed = nr_reclaimed; + ), + + TP_printk("cgroup_ino=%u nr_reclaimed=%lu", + __entry->cgroup_ino, __entry->nr_reclaimed) ); -DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end, +DEFINE_EVENT(mm_vmscan_memcg_reclaim_end_template, + mm_vmscan_memcg_reclaim_end, - TP_PROTO(unsigned long nr_reclaimed), + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed), - TP_ARGS(nr_reclaimed) + TP_ARGS(cgroup_ino, nr_reclaimed) +); + +DEFINE_EVENT(mm_vmscan_memcg_reclaim_end_template, + mm_vmscan_memcg_softlimit_reclaim_end, + + TP_PROTO(unsigned int cgroup_ino, unsigned long nr_reclaimed), + + TP_ARGS(cgroup_ino, nr_reclaimed) ); #endif /* CONFIG_MEMCG */ diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 3d920ff15c80..49a05ba3000d 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -63,6 +63,66 @@ struct posix_msg_tree_node { int priority; }; +/* + * Locking: + * + * Accesses to a message queue are synchronized by acquiring info->lock. + * + * There are two notable exceptions: + * - The actual wakeup of a sleeping task is performed using the wake_q + * framework. info->lock is already released when wake_up_q is called. + * - The exit codepaths after sleeping check ext_wait_queue->state without + * any locks. If it is STATE_READY, then the syscall is completed without + * acquiring info->lock. + * + * MQ_BARRIER: + * To achieve proper release/acquire memory barrier pairing, the state is set to + * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed + * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used. + * + * This prevents the following races: + * + * 1) With the simple wake_q_add(), the task could be gone already before + * the increase of the reference happens + * Thread A + * Thread B + * WRITE_ONCE(wait.state, STATE_NONE); + * schedule_hrtimeout() + * wake_q_add(A) + * if (cmpxchg()) // success + * ->state = STATE_READY (reordered) + * <timeout returns> + * if (wait.state == STATE_READY) return; + * sysret to user space + * sys_exit() + * get_task_struct() // UaF + * + * Solution: Use wake_q_add_safe() and perform the get_task_struct() before + * the smp_store_release() that does ->state = STATE_READY. + * + * 2) Without proper _release/_acquire barriers, the woken up task + * could read stale data + * + * Thread A + * Thread B + * do_mq_timedreceive + * WRITE_ONCE(wait.state, STATE_NONE); + * schedule_hrtimeout() + * state = STATE_READY; + * <timeout returns> + * if (wait.state == STATE_READY) return; + * msg_ptr = wait.msg; // Access to stale data! + * receiver->msg = message; (reordered) + * + * Solution: use _release and _acquire barriers. + * + * 3) There is intentionally no barrier when setting current->state + * to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the + * release memory barrier, and the wakeup is triggered when holding + * info->lock, i.e. spin_lock(&info->lock) provided a pairing + * acquire memory barrier. + */ + struct ext_wait_queue { /* queue of sleeping tasks */ struct task_struct *task; struct list_head list; @@ -646,18 +706,23 @@ static int wq_sleep(struct mqueue_inode_info *info, int sr, wq_add(info, sr, ewp); for (;;) { + /* memory barrier not required, we hold info->lock */ __set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&info->lock); time = schedule_hrtimeout_range_clock(timeout, 0, HRTIMER_MODE_ABS, CLOCK_REALTIME); - if (ewp->state == STATE_READY) { + if (READ_ONCE(ewp->state) == STATE_READY) { + /* see MQ_BARRIER for purpose/pairing */ + smp_acquire__after_ctrl_dep(); retval = 0; goto out; } spin_lock(&info->lock); - if (ewp->state == STATE_READY) { + + /* we hold info->lock, so no memory barrier required */ + if (READ_ONCE(ewp->state) == STATE_READY) { retval = 0; goto out_unlock; } @@ -918,6 +983,18 @@ out_name: * The same algorithm is used for senders. */ +static inline void __pipelined_op(struct wake_q_head *wake_q, + struct mqueue_inode_info *info, + struct ext_wait_queue *this) +{ + list_del(&this->list); + get_task_struct(this->task); + + /* see MQ_BARRIER for purpose/pairing */ + smp_store_release(&this->state, STATE_READY); + wake_q_add_safe(wake_q, this->task); +} + /* pipelined_send() - send a message directly to the task waiting in * sys_mq_timedreceive() (without inserting message into a queue). */ @@ -927,17 +1004,7 @@ static inline void pipelined_send(struct wake_q_head *wake_q, struct ext_wait_queue *receiver) { receiver->msg = message; - list_del(&receiver->list); - wake_q_add(wake_q, receiver->task); - /* - * Rely on the implicit cmpxchg barrier from wake_q_add such - * that we can ensure that updating receiver->state is the last - * write operation: As once set, the receiver can continue, - * and if we don't have the reference count from the wake_q, - * yet, at that point we can later have a use-after-free - * condition and bogus wakeup. - */ - receiver->state = STATE_READY; + __pipelined_op(wake_q, info, receiver); } /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() @@ -955,9 +1022,7 @@ static inline void pipelined_receive(struct wake_q_head *wake_q, if (msg_insert(sender->msg, info)) return; - list_del(&sender->list); - wake_q_add(wake_q, sender->task); - sender->state = STATE_READY; + __pipelined_op(wake_q, info, sender); } static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, @@ -1044,7 +1109,9 @@ static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, } else { wait.task = current; wait.msg = (void *) msg_ptr; - wait.state = STATE_NONE; + + /* memory barrier not required, we hold info->lock */ + WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, SEND, timeout, &wait); /* * wq_sleep must be called with info->lock held, and @@ -1147,7 +1214,9 @@ static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, ret = -EAGAIN; } else { wait.task = current; - wait.state = STATE_NONE; + + /* memory barrier not required, we hold info->lock */ + WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, RECV, timeout, &wait); msg_ptr = wait.msg; } diff --git a/ipc/msg.c b/ipc/msg.c index 8dec945fa030..22ed09ded601 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -61,6 +61,16 @@ struct msg_queue { struct list_head q_senders; } __randomize_layout; +/* + * MSG_BARRIER Locking: + * + * Similar to the optimization used in ipc/mqueue.c, one syscall return path + * does not acquire any locks when it sees that a message exists in + * msg_receiver.r_msg. Therefore r_msg is set using smp_store_release() + * and accessed using READ_ONCE()+smp_acquire__after_ctrl_dep(). In addition, + * wake_q_add_safe() is used. See ipc/mqueue.c for more details + */ + /* one msg_receiver structure for each sleeping receiver */ struct msg_receiver { struct list_head r_list; @@ -184,6 +194,10 @@ static inline void ss_add(struct msg_queue *msq, { mss->tsk = current; mss->msgsz = msgsz; + /* + * No memory barrier required: we did ipc_lock_object(), + * and the waker obtains that lock before calling wake_q_add(). + */ __set_current_state(TASK_INTERRUPTIBLE); list_add_tail(&mss->list, &msq->q_senders); } @@ -237,8 +251,11 @@ static void expunge_all(struct msg_queue *msq, int res, struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { - wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, ERR_PTR(res)); + get_task_struct(msr->r_tsk); + + /* see MSG_BARRIER for purpose/pairing */ + smp_store_release(&msr->r_msg, ERR_PTR(res)); + wake_q_add_safe(wake_q, msr->r_tsk); } } @@ -377,7 +394,7 @@ copy_msqid_from_user(struct msqid64_ds *out, void __user *buf, int version) * NOTE: no locks must be held, the rwsem is taken inside this function. */ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, - struct msqid64_ds *msqid64) + struct ipc64_perm *perm, int msg_qbytes) { struct kern_ipc_perm *ipcp; struct msg_queue *msq; @@ -387,7 +404,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, rcu_read_lock(); ipcp = ipcctl_obtain_check(ns, &msg_ids(ns), msqid, cmd, - &msqid64->msg_perm, msqid64->msg_qbytes); + perm, msg_qbytes); if (IS_ERR(ipcp)) { err = PTR_ERR(ipcp); goto out_unlock1; @@ -409,18 +426,18 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd, { DEFINE_WAKE_Q(wake_q); - if (msqid64->msg_qbytes > ns->msg_ctlmnb && + if (msg_qbytes > ns->msg_ctlmnb && !capable(CAP_SYS_RESOURCE)) { err = -EPERM; goto out_unlock1; } ipc_lock_object(&msq->q_perm); - err = ipc_update_perm(&msqid64->msg_perm, ipcp); + err = ipc_update_perm(perm, ipcp); if (err) goto out_unlock0; - msq->q_qbytes = msqid64->msg_qbytes; + msq->q_qbytes = msg_qbytes; msq->q_ctime = ktime_get_real_seconds(); /* @@ -601,9 +618,9 @@ static long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf, int ver case IPC_SET: if (copy_msqid_from_user(&msqid64, buf, version)) return -EFAULT; - /* fallthru */ + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: - return msgctl_down(ns, msqid, cmd, &msqid64); + return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } @@ -735,9 +752,9 @@ static long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr, int versio case IPC_SET: if (copy_compat_msqid_from_user(&msqid64, uptr, version)) return -EFAULT; - /* fallthru */ + return msgctl_down(ns, msqid, cmd, &msqid64.msg_perm, msqid64.msg_qbytes); case IPC_RMID: - return msgctl_down(ns, msqid, cmd, &msqid64); + return msgctl_down(ns, msqid, cmd, NULL, 0); default: return -EINVAL; } @@ -798,13 +815,17 @@ static inline int pipelined_send(struct msg_queue *msq, struct msg_msg *msg, list_del(&msr->r_list); if (msr->r_maxsize < msg->m_ts) { wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, ERR_PTR(-E2BIG)); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, ERR_PTR(-E2BIG)); } else { ipc_update_pid(&msq->q_lrpid, task_pid(msr->r_tsk)); msq->q_rtime = ktime_get_real_seconds(); wake_q_add(wake_q, msr->r_tsk); - WRITE_ONCE(msr->r_msg, msg); + + /* See expunge_all regarding memory barrier */ + smp_store_release(&msr->r_msg, msg); return 1; } } @@ -1154,7 +1175,11 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in msr_d.r_maxsize = INT_MAX; else msr_d.r_maxsize = bufsz; - msr_d.r_msg = ERR_PTR(-EAGAIN); + + /* memory barrier not require due to ipc_lock_object() */ + WRITE_ONCE(msr_d.r_msg, ERR_PTR(-EAGAIN)); + + /* memory barrier not required, we own ipc_lock_object() */ __set_current_state(TASK_INTERRUPTIBLE); ipc_unlock_object(&msq->q_perm); @@ -1183,8 +1208,12 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in * signal) it will either see the message and continue ... */ msg = READ_ONCE(msr_d.r_msg); - if (msg != ERR_PTR(-EAGAIN)) + if (msg != ERR_PTR(-EAGAIN)) { + /* see MSG_BARRIER for purpose/pairing */ + smp_acquire__after_ctrl_dep(); + goto out_unlock1; + } /* * ... or see -EAGAIN, acquire the lock to check the message @@ -1192,7 +1221,7 @@ static long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, in */ ipc_lock_object(&msq->q_perm); - msg = msr_d.r_msg; + msg = READ_ONCE(msr_d.r_msg); if (msg != ERR_PTR(-EAGAIN)) goto out_unlock0; diff --git a/ipc/sem.c b/ipc/sem.c index ec97a7072413..4f4303f32077 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -205,15 +205,38 @@ static int sysvipc_sem_proc_show(struct seq_file *s, void *it); * * Memory ordering: * Most ordering is enforced by using spin_lock() and spin_unlock(). - * The special case is use_global_lock: + * + * Exceptions: + * 1) use_global_lock: (SEM_BARRIER_1) * Setting it from non-zero to 0 is a RELEASE, this is ensured by - * using smp_store_release(). + * using smp_store_release(): Immediately after setting it to 0, + * a simple op can start. * Testing if it is non-zero is an ACQUIRE, this is ensured by using * smp_load_acquire(). * Setting it from 0 to non-zero must be ordered with regards to * this smp_load_acquire(), this is guaranteed because the smp_load_acquire() * is inside a spin_lock() and after a write from 0 to non-zero a * spin_lock()+spin_unlock() is done. + * + * 2) queue.status: (SEM_BARRIER_2) + * Initialization is done while holding sem_lock(), so no further barrier is + * required. + * Setting it to a result code is a RELEASE, this is ensured by both a + * smp_store_release() (for case a) and while holding sem_lock() + * (for case b). + * The AQUIRE when reading the result code without holding sem_lock() is + * achieved by using READ_ONCE() + smp_acquire__after_ctrl_dep(). + * (case a above). + * Reading the result code while holding sem_lock() needs no further barriers, + * the locks inside sem_lock() enforce ordering (case b above) + * + * 3) current->state: + * current->state is set to TASK_INTERRUPTIBLE while holding sem_lock(). + * The wakeup is handled using the wake_q infrastructure. wake_q wakeups may + * happen immediately after calling wake_q_add. As wake_q_add_safe() is called + * when holding sem_lock(), no further barriers are required. + * + * See also ipc/mqueue.c for more details on the covered races. */ #define sc_semmsl sem_ctls[0] @@ -344,12 +367,8 @@ static void complexmode_tryleave(struct sem_array *sma) return; } if (sma->use_global_lock == 1) { - /* - * Immediately after setting use_global_lock to 0, - * a simple op can start. Thus: all memory writes - * performed by the current operation must be visible - * before we set use_global_lock to 0. - */ + + /* See SEM_BARRIER_1 for purpose/pairing */ smp_store_release(&sma->use_global_lock, 0); } else { sma->use_global_lock--; @@ -400,7 +419,7 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops, */ spin_lock(&sem->lock); - /* pairs with smp_store_release() */ + /* see SEM_BARRIER_1 for purpose/pairing */ if (!smp_load_acquire(&sma->use_global_lock)) { /* fast path successful! */ return sops->sem_num; @@ -766,15 +785,12 @@ would_block: static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, struct wake_q_head *wake_q) { - wake_q_add(wake_q, q->sleeper); - /* - * Rely on the above implicit barrier, such that we can - * ensure that we hold reference to the task before setting - * q->status. Otherwise we could race with do_exit if the - * task is awoken by an external event before calling - * wake_up_process(). - */ - WRITE_ONCE(q->status, error); + get_task_struct(q->sleeper); + + /* see SEM_BARRIER_2 for purpuse/pairing */ + smp_store_release(&q->status, error); + + wake_q_add_safe(wake_q, q->sleeper); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) @@ -2148,9 +2164,11 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, } do { + /* memory ordering ensured by the lock in sem_lock() */ WRITE_ONCE(queue.status, -EINTR); queue.sleeper = current; + /* memory ordering is ensured by the lock in sem_lock() */ __set_current_state(TASK_INTERRUPTIBLE); sem_unlock(sma, locknum); rcu_read_unlock(); @@ -2173,13 +2191,8 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, */ error = READ_ONCE(queue.status); if (error != -EINTR) { - /* - * User space could assume that semop() is a memory - * barrier: Without the mb(), the cpu could - * speculatively read in userspace stale data that was - * overwritten by the previous owner of the semaphore. - */ - smp_mb(); + /* see SEM_BARRIER_2 for purpose/pairing */ + smp_acquire__after_ctrl_dep(); goto out_free; } @@ -2189,6 +2202,9 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops, if (!ipc_valid_object(&sma->sem_perm)) goto out_unlock_free; + /* + * No necessity for any barrier: We are protect by sem_lock() + */ error = READ_ONCE(queue.status); /* diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c74761004ee5..ece7e13f6e4a 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1457,7 +1457,7 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) /* Try to map as high as possible, this is only a hint. */ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0); - if (area->vaddr & ~PAGE_MASK) { + if (IS_ERR_VALUE(area->vaddr)) { ret = area->vaddr; goto fail; } diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 14a625c16cb3..f1443abb31f1 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -49,6 +49,7 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_ unsigned long __read_mostly sysctl_hung_task_check_interval_secs; int __read_mostly sysctl_hung_task_warnings = 10; +int __read_mostly sysctl_hung_task_interval_warnings; static int __read_mostly did_panic; static bool hung_task_show_lock; @@ -85,6 +86,34 @@ static struct notifier_block panic_block = { .notifier_call = hung_task_panic, }; +static void hung_task_warning(struct task_struct *t, bool timeout) +{ + const char *loglevel = timeout ? KERN_ERR : KERN_INFO; + const char *path; + int *warnings; + + if (timeout) { + warnings = &sysctl_hung_task_warnings; + path = "hung_task_timeout_secs"; + } else { + warnings = &sysctl_hung_task_interval_warnings; + path = "hung_task_interval_secs"; + } + + if (*warnings > 0) + --*warnings; + + printk("%sINFO: task %s:%d blocked for more than %ld seconds.\n", + loglevel, t->comm, t->pid, (jiffies - t->last_switch_time) / HZ); + printk("%s %s %s %.*s\n", + loglevel, print_tainted(), init_utsname()->release, + (int)strcspn(init_utsname()->version, " "), + init_utsname()->version); + printk("%s\"echo 0 > /proc/sys/kernel/%s\" disables this message.\n", + loglevel, path); + sched_show_task(t); +} + static void check_hung_task(struct task_struct *t, unsigned long timeout) { unsigned long switch_count = t->nvcsw + t->nivcsw; @@ -109,6 +138,9 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) t->last_switch_time = jiffies; return; } + if (sysctl_hung_task_interval_warnings) + hung_task_warning(t, false); + if (time_is_after_jiffies(t->last_switch_time + timeout * HZ)) return; @@ -120,28 +152,57 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) hung_task_call_panic = true; } - /* - * Ok, the task did not get scheduled for more than 2 minutes, - * complain: - */ if (sysctl_hung_task_warnings) { - if (sysctl_hung_task_warnings > 0) - sysctl_hung_task_warnings--; - pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", - t->comm, t->pid, (jiffies - t->last_switch_time) / HZ); - pr_err(" %s %s %.*s\n", - print_tainted(), init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" - " disables this message.\n"); - sched_show_task(t); + /* Don't print warings twice */ + if (!sysctl_hung_task_interval_warnings) + hung_task_warning(t, true); hung_task_show_lock = true; } touch_nmi_watchdog(); } +static void check_killed_task(struct task_struct *t, unsigned long timeout) +{ + unsigned long stamp = t->killed_time; + + /* + * Ensure the task is not frozen. + * Also, skip vfork and any other user process that freezer should skip. + */ + if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP))) + return; + /* + * Skip threads which are already inside do_exit(), for exit_mm() etc. + * might take many seconds. + */ + if (t->flags & PF_EXITING) + return; + if (!stamp) { + stamp = jiffies; + if (!stamp) + stamp++; + t->killed_time = stamp; + return; + } + if (time_is_after_jiffies(stamp + timeout * HZ)) + return; + trace_sched_process_hang(t); + if (sysctl_hung_task_panic) { + console_verbose(); + hung_task_call_panic = true; + } + /* + * This thread failed to terminate for more than + * sysctl_hung_task_timeout_secs seconds, complain: + */ + pr_err("INFO: task %s:%d can't die for more than %ld seconds.\n", + t->comm, t->pid, (jiffies - stamp) / HZ); + sched_show_task(t); + hung_task_show_lock = true; + touch_nmi_watchdog(); +} + /* * To avoid extending the RCU grace period for an unbounded amount of time, * periodically exit the critical section and enter a new one. @@ -193,6 +254,9 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) goto unlock; last_break = jiffies; } + /* Check threads which are about to terminate. */ + if (unlikely(fatal_signal_pending(t))) + check_killed_task(t, timeout); /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ if (t->state == TASK_UNINTERRUPTIBLE) check_hung_task(t, timeout); diff --git a/kernel/notifier.c b/kernel/notifier.c index d9f5081d578d..63d7501ac638 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -23,22 +23,10 @@ static int notifier_chain_register(struct notifier_block **nl, struct notifier_block *n) { while ((*nl) != NULL) { - WARN_ONCE(((*nl) == n), "double register detected"); - if (n->priority > (*nl)->priority) - break; - nl = &((*nl)->next); - } - n->next = *nl; - rcu_assign_pointer(*nl, n); - return 0; -} - -static int notifier_chain_cond_register(struct notifier_block **nl, - struct notifier_block *n) -{ - while ((*nl) != NULL) { - if ((*nl) == n) + if (unlikely((*nl) == n)) { + WARN(1, "double register detected"); return 0; + } if (n->priority > (*nl)->priority) break; nl = &((*nl)->next); @@ -233,29 +221,6 @@ int blocking_notifier_chain_register(struct blocking_notifier_head *nh, EXPORT_SYMBOL_GPL(blocking_notifier_chain_register); /** - * blocking_notifier_chain_cond_register - Cond add notifier to a blocking notifier chain - * @nh: Pointer to head of the blocking notifier chain - * @n: New entry in notifier chain - * - * Adds a notifier to a blocking notifier chain, only if not already - * present in the chain. - * Must be called in process context. - * - * Currently always returns zero. - */ -int blocking_notifier_chain_cond_register(struct blocking_notifier_head *nh, - struct notifier_block *n) -{ - int ret; - - down_write(&nh->rwsem); - ret = notifier_chain_cond_register(&nh->head, n); - up_write(&nh->rwsem); - return ret; -} -EXPORT_SYMBOL_GPL(blocking_notifier_chain_cond_register); - -/** * blocking_notifier_chain_unregister - Remove notifier from a blocking notifier chain * @nh: Pointer to head of the blocking notifier chain * @n: Entry to remove from notifier chain diff --git a/kernel/profile.c b/kernel/profile.c index af7c94bf5fa1..4b144b02ca5d 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -336,7 +336,7 @@ static int profile_dead_cpu(unsigned int cpu) struct page *page; int i; - if (prof_cpu_mask != NULL) + if (cpumask_available(prof_cpu_mask)) cpumask_clear_cpu(cpu, prof_cpu_mask); for (i = 0; i < 2; i++) { @@ -373,7 +373,7 @@ static int profile_prepare_cpu(unsigned int cpu) static int profile_online_cpu(unsigned int cpu) { - if (prof_cpu_mask != NULL) + if (cpumask_available(prof_cpu_mask)) cpumask_set_cpu(cpu, prof_cpu_mask); return 0; @@ -403,7 +403,7 @@ void profile_tick(int type) { struct pt_regs *regs = get_irq_regs(); - if (!user_mode(regs) && prof_cpu_mask != NULL && + if (!user_mode(regs) && cpumask_available(prof_cpu_mask) && cpumask_test_cpu(smp_processor_id(), prof_cpu_mask)) profile_hit(type, (void *)profile_pc(regs)); } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b6f2f35d0bcf..31ece1120aa4 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1148,6 +1148,14 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &neg_one, }, + { + .procname = "hung_task_interval_warnings", + .data = &sysctl_hung_task_interval_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &neg_one, + }, #endif #ifdef CONFIG_RT_MUTEXES { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 27ff08ce03e9..83a804d58e2f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2147,6 +2147,12 @@ config IO_STRICT_DEVMEM If in doubt, say Y. +config DEBUG_AID_FOR_SYZBOT + bool "Additional debug code for syzbot" + default n + help + This option is intended for testing by syzbot. + source "arch/$(SRCARCH)/Kconfig.debug" endmenu # Kernel hacking diff --git a/lib/math/rational.c b/lib/math/rational.c index ba7443677c90..31fb27db2deb 100644 --- a/lib/math/rational.c +++ b/lib/math/rational.c @@ -3,6 +3,7 @@ * rational fractions * * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <oskar@scara.com> + * Copyright (C) 2019 Trent Piepho <tpiepho@gmail.com> * * helper functions when coping with rational numbers */ @@ -10,6 +11,7 @@ #include <linux/rational.h> #include <linux/compiler.h> #include <linux/export.h> +#include <linux/kernel.h> /* * calculate best rational approximation for a given fraction @@ -33,30 +35,65 @@ void rational_best_approximation( unsigned long max_numerator, unsigned long max_denominator, unsigned long *best_numerator, unsigned long *best_denominator) { - unsigned long n, d, n0, d0, n1, d1; + /* n/d is the starting rational, which is continually + * decreased each iteration using the Euclidean algorithm. + * + * dp is the value of d from the prior iteration. + * + * n2/d2, n1/d1, and n0/d0 are our successively more accurate + * approximations of the rational. They are, respectively, + * the current, previous, and two prior iterations of it. + * + * a is current term of the continued fraction. + */ + unsigned long n, d, n0, d0, n1, d1, n2, d2; n = given_numerator; d = given_denominator; n0 = d1 = 0; n1 = d0 = 1; + for (;;) { - unsigned long t, a; - if ((n1 > max_numerator) || (d1 > max_denominator)) { - n1 = n0; - d1 = d0; - break; - } + unsigned long dp, a; + if (d == 0) break; - t = d; + /* Find next term in continued fraction, 'a', via + * Euclidean algorithm. + */ + dp = d; a = n / d; d = n % d; - n = t; - t = n0 + a * n1; + n = dp; + + /* Calculate the current rational approximation (aka + * convergent), n2/d2, using the term just found and + * the two prior approximations. + */ + n2 = n0 + a * n1; + d2 = d0 + a * d1; + + /* If the current convergent exceeds the maxes, then + * return either the previous convergent or the + * largest semi-convergent, the final term of which is + * found below as 't'. + */ + if ((n2 > max_numerator) || (d2 > max_denominator)) { + unsigned long t = min((max_numerator - n0) / n1, + (max_denominator - d0) / d1); + + /* This tests if the semi-convergent is closer + * than the previous convergent. + */ + if (2u * t > a || (2u * t == a && d0 * dp > d1 * d)) { + n1 = n0 + t * n1; + d1 = d0 + t * d1; + } + break; + } n0 = n1; - n1 = t; - t = d0 + a * d1; + n1 = n2; d0 = d1; - d1 = t; + d1 = d2; } *best_numerator = n1; *best_denominator = d1; diff --git a/lib/ubsan.c b/lib/ubsan.c index 0c4681118fcd..f007a406f89c 100644 --- a/lib/ubsan.c +++ b/lib/ubsan.c @@ -140,25 +140,21 @@ static void val_to_string(char *str, size_t size, struct type_descriptor *type, } } -static DEFINE_SPINLOCK(report_lock); - -static void ubsan_prologue(struct source_location *location, - unsigned long *flags) +static void ubsan_prologue(struct source_location *location) { current->in_ubsan++; - spin_lock_irqsave(&report_lock, *flags); pr_err("========================================" "========================================\n"); print_source_location("UBSAN: Undefined behaviour in", location); } -static void ubsan_epilogue(unsigned long *flags) +static void ubsan_epilogue(void) { dump_stack(); pr_err("========================================" "========================================\n"); - spin_unlock_irqrestore(&report_lock, *flags); + current->in_ubsan--; } @@ -167,14 +163,13 @@ static void handle_overflow(struct overflow_data *data, void *lhs, { struct type_descriptor *type = data->type; - unsigned long flags; char lhs_val_str[VALUE_LENGTH]; char rhs_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(lhs_val_str, sizeof(lhs_val_str), type, lhs); val_to_string(rhs_val_str, sizeof(rhs_val_str), type, rhs); @@ -186,7 +181,7 @@ static void handle_overflow(struct overflow_data *data, void *lhs, rhs_val_str, type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } void __ubsan_handle_add_overflow(struct overflow_data *data, @@ -214,20 +209,19 @@ EXPORT_SYMBOL(__ubsan_handle_mul_overflow); void __ubsan_handle_negate_overflow(struct overflow_data *data, void *old_val) { - unsigned long flags; char old_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(old_val_str, sizeof(old_val_str), data->type, old_val); pr_err("negation of %s cannot be represented in type %s:\n", old_val_str, data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_negate_overflow); @@ -235,13 +229,12 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow); void __ubsan_handle_divrem_overflow(struct overflow_data *data, void *lhs, void *rhs) { - unsigned long flags; char rhs_val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(rhs_val_str, sizeof(rhs_val_str), data->type, rhs); @@ -251,58 +244,52 @@ void __ubsan_handle_divrem_overflow(struct overflow_data *data, else pr_err("division by zero\n"); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_divrem_overflow); static void handle_null_ptr_deref(struct type_mismatch_data_common *data) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s null pointer of type %s\n", type_check_kinds[data->type_check_kind], data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void handle_misaligned_access(struct type_mismatch_data_common *data, unsigned long ptr) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s misaligned address %p for type %s\n", type_check_kinds[data->type_check_kind], (void *)ptr, data->type->type_name); pr_err("which requires %ld byte alignment\n", data->alignment); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void handle_object_size_mismatch(struct type_mismatch_data_common *data, unsigned long ptr) { - unsigned long flags; - if (suppress_report(data->location)) return; - ubsan_prologue(data->location, &flags); + ubsan_prologue(data->location); pr_err("%s address %p with insufficient space\n", type_check_kinds[data->type_check_kind], (void *) ptr); pr_err("for an object of type %s\n", data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data, @@ -351,25 +338,23 @@ EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1); void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index) { - unsigned long flags; char index_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(index_str, sizeof(index_str), data->index_type, index); pr_err("index %s is out of range for type %s\n", index_str, data->array_type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_out_of_bounds); void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, void *lhs, void *rhs) { - unsigned long flags; struct type_descriptor *rhs_type = data->rhs_type; struct type_descriptor *lhs_type = data->lhs_type; char rhs_str[VALUE_LENGTH]; @@ -379,7 +364,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, if (suppress_report(&data->location)) goto out; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(rhs_str, sizeof(rhs_str), rhs_type, rhs); val_to_string(lhs_str, sizeof(lhs_str), lhs_type, lhs); @@ -402,7 +387,7 @@ void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data, lhs_str, rhs_str, lhs_type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); out: user_access_restore(ua_flags); } @@ -411,11 +396,9 @@ EXPORT_SYMBOL(__ubsan_handle_shift_out_of_bounds); void __ubsan_handle_builtin_unreachable(struct unreachable_data *data) { - unsigned long flags; - - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); pr_err("calling __builtin_unreachable()\n"); - ubsan_epilogue(&flags); + ubsan_epilogue(); panic("can't return from __builtin_unreachable()"); } EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); @@ -423,19 +406,18 @@ EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable); void __ubsan_handle_load_invalid_value(struct invalid_value_data *data, void *val) { - unsigned long flags; char val_str[VALUE_LENGTH]; if (suppress_report(&data->location)) return; - ubsan_prologue(&data->location, &flags); + ubsan_prologue(&data->location); val_to_string(val_str, sizeof(val_str), data->type, val); pr_err("load of value %s is not a valid value for type %s\n", val_str, data->type->type_name); - ubsan_epilogue(&flags); + ubsan_epilogue(); } EXPORT_SYMBOL(__ubsan_handle_load_invalid_value); @@ -95,13 +95,11 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, static int __init cma_activate_area(struct cma *cma) { - int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long); unsigned long base_pfn = cma->base_pfn, pfn = base_pfn; unsigned i = cma->count >> pageblock_order; struct zone *zone; - cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - + cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL); if (!cma->bitmap) { cma->count = 0; return -ENOMEM; @@ -139,7 +137,7 @@ static int __init cma_activate_area(struct cma *cma) not_in_zone: pr_err("CMA area %s could not be activated\n", cma->name); - kfree(cma->bitmap); + bitmap_free(cma->bitmap); cma->count = 0; return -EINVAL; } diff --git a/mm/filemap.c b/mm/filemap.c index 85b7d087eb45..1f5731768222 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2329,27 +2329,6 @@ EXPORT_SYMBOL(generic_file_read_iter); #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) -static struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, - struct file *fpin) -{ - int flags = vmf->flags; - - if (fpin) - return fpin; - - /* - * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or - * anything, so we only pin the file and drop the mmap_sem if only - * FAULT_FLAG_ALLOW_RETRY is set. - */ - if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == - FAULT_FLAG_ALLOW_RETRY) { - fpin = get_file(vmf->vma->vm_file); - up_read(&vmf->vma->vm_mm->mmap_sem); - } - return fpin; -} - /* * lock_page_maybe_drop_mmap - lock the page, possibly dropping the mmap_sem * @vmf - the vm_fault for this fault. @@ -1443,6 +1443,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk, bool drain_allow = true; bool migrate_allow = true; LIST_HEAD(cma_page_list); + long ret = nr_pages; check_again: for (i = 0; i < nr_pages;) { @@ -1504,17 +1505,18 @@ check_again: * again migrating any new CMA pages which we failed to isolate * earlier. */ - nr_pages = __get_user_pages_locked(tsk, mm, start, nr_pages, + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, pages, vmas, NULL, gup_flags); - if ((nr_pages > 0) && migrate_allow) { + if ((ret > 0) && migrate_allow) { + nr_pages = ret; drain_allow = true; goto check_again; } } - return nr_pages; + return ret; } #else static long check_and_migrate_cma_pages(struct task_struct *tsk, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 13cc93785006..b68c13e564d1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -686,20 +686,18 @@ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) } /* Caller must hold page table lock. */ -static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, +static void set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct page *zero_page) { pmd_t entry; - if (!pmd_none(*pmd)) - return false; + entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); if (pgtable) pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); mm_inc_nr_ptes(mm); - return true; } vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b45a95363a84..a5c2c880af27 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -244,16 +244,66 @@ struct file_region { long to; }; +/* Must be called with resv->lock held. Calling this with count_only == true + * will count the number of pages to be added but will not modify the linked + * list. + */ +static long add_reservation_in_range(struct resv_map *resv, long f, long t, + bool count_only) +{ + long chg = 0; + struct list_head *head = &resv->regions; + struct file_region *rg = NULL, *trg = NULL, *nrg = NULL; + + /* Locate the region we are before or in. */ + list_for_each_entry(rg, head, link) + if (f <= rg->to) + break; + + /* Round our left edge to the current segment if it encloses us. */ + if (f > rg->from) + f = rg->from; + + chg = t - f; + + /* Check for and consume any regions we now overlap with. */ + nrg = rg; + list_for_each_entry_safe(rg, trg, rg->link.prev, link) { + if (&rg->link == head) + break; + if (rg->from > t) + break; + + /* We overlap with this area, if it extends further than + * us then we must extend ourselves. Account for its + * existing reservation. + */ + if (rg->to > t) { + chg += rg->to - t; + t = rg->to; + } + chg -= rg->to - rg->from; + + if (!count_only && rg != nrg) { + list_del(&rg->link); + kfree(rg); + } + } + + if (!count_only) { + nrg->from = f; + nrg->to = t; + } + + return chg; +} + /* * Add the huge page range represented by [f, t) to the reserve - * map. In the normal case, existing regions will be expanded - * to accommodate the specified range. Sufficient regions should - * exist for expansion due to the previous call to region_chg - * with the same range. However, it is possible that region_del - * could have been called after region_chg and modifed the map - * in such a way that no region exists to be expanded. In this - * case, pull a region descriptor from the cache associated with - * the map and use that for the new range. + * map. Existing regions will be expanded to accommodate the specified + * range, or a region will be taken from the cache. Sufficient regions + * must exist in the cache due to the previous call to region_chg with + * the same range. * * Return the number of new huge pages added to the map. This * number is greater than or equal to zero. @@ -261,7 +311,7 @@ struct file_region { static long region_add(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; - struct file_region *rg, *nrg, *trg; + struct file_region *rg, *nrg; long add = 0; spin_lock(&resv->lock); @@ -272,9 +322,8 @@ static long region_add(struct resv_map *resv, long f, long t) /* * If no region exists which can be expanded to include the - * specified range, the list must have been modified by an - * interleving call to region_del(). Pull a region descriptor - * from the cache and use it for this range. + * specified range, pull a region descriptor from the cache + * and use it for this range. */ if (&rg->link == head || t < rg->from) { VM_BUG_ON(resv->region_cache_count <= 0); @@ -292,38 +341,7 @@ static long region_add(struct resv_map *resv, long f, long t) goto out_locked; } - /* Round our left edge to the current segment if it encloses us. */ - if (f > rg->from) - f = rg->from; - - /* Check for and consume any regions we now overlap with. */ - nrg = rg; - list_for_each_entry_safe(rg, trg, rg->link.prev, link) { - if (&rg->link == head) - break; - if (rg->from > t) - break; - - /* If this area reaches higher then extend our area to - * include it completely. If this is not the first area - * which we intend to reuse, free it. */ - if (rg->to > t) - t = rg->to; - if (rg != nrg) { - /* Decrement return value by the deleted range. - * Another range will span this area so that by - * end of routine add will be >= zero - */ - add -= (rg->to - rg->from); - list_del(&rg->link); - kfree(rg); - } - } - - add += (nrg->from - f); /* Added to beginning of region */ - nrg->from = f; - add += t - nrg->to; /* Added to end of region */ - nrg->to = t; + add = add_reservation_in_range(resv, f, t, false); out_locked: resv->adds_in_progress--; @@ -339,15 +357,9 @@ out_locked: * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the - * map. However, if the existing regions in the map can not - * be expanded to represent the new range, a new file_region - * structure is added to the map as a placeholder. This is - * so that the subsequent region_add call will have all the - * regions it needs and will not fail. - * - * Upon entry, region_chg will also examine the cache of region descriptors - * associated with the map. If there are not enough descriptors cached, one - * will be allocated for the in progress add operation. + * map. A new file_region structure is added to the cache + * as a placeholder, so that the subsequent region_add + * call will have all the regions it needs and will not fail. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to @@ -356,11 +368,8 @@ out_locked: */ static long region_chg(struct resv_map *resv, long f, long t) { - struct list_head *head = &resv->regions; - struct file_region *rg, *nrg = NULL; long chg = 0; -retry: spin_lock(&resv->lock); retry_locked: resv->adds_in_progress++; @@ -378,10 +387,8 @@ retry_locked: spin_unlock(&resv->lock); trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) { - kfree(nrg); + if (!trg) return -ENOMEM; - } spin_lock(&resv->lock); list_add(&trg->link, &resv->region_cache); @@ -389,61 +396,8 @@ retry_locked: goto retry_locked; } - /* Locate the region we are before or in. */ - list_for_each_entry(rg, head, link) - if (f <= rg->to) - break; + chg = add_reservation_in_range(resv, f, t, true); - /* If we are below the current region then a new region is required. - * Subtle, allocate a new region at the position but make it zero - * size such that we can guarantee to record the reservation. */ - if (&rg->link == head || t < rg->from) { - if (!nrg) { - resv->adds_in_progress--; - spin_unlock(&resv->lock); - nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); - if (!nrg) - return -ENOMEM; - - nrg->from = f; - nrg->to = f; - INIT_LIST_HEAD(&nrg->link); - goto retry; - } - - list_add(&nrg->link, rg->link.prev); - chg = t - f; - goto out_nrg; - } - - /* Round our left edge to the current segment if it encloses us. */ - if (f > rg->from) - f = rg->from; - chg = t - f; - - /* Check for and consume any regions we now overlap with. */ - list_for_each_entry(rg, rg->link.prev, link) { - if (&rg->link == head) - break; - if (rg->from > t) - goto out; - - /* We overlap with this area, if it extends further than - * us then we must extend ourselves. Account for its - * existing reservation. */ - if (rg->to > t) { - chg += rg->to - t; - t = rg->to; - } - chg -= rg->to - rg->from; - } - -out: - spin_unlock(&resv->lock); - /* We already know we raced and no longer need the new region */ - kfree(nrg); - return chg; -out_nrg: spin_unlock(&resv->lock); return chg; } @@ -1069,85 +1023,12 @@ static void free_gigantic_page(struct page *page, unsigned int order) } #ifdef CONFIG_CONTIG_ALLOC -static int __alloc_gigantic_page(unsigned long start_pfn, - unsigned long nr_pages, gfp_t gfp_mask) -{ - unsigned long end_pfn = start_pfn + nr_pages; - return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - gfp_mask); -} - -static bool pfn_range_valid_gigantic(struct zone *z, - unsigned long start_pfn, unsigned long nr_pages) -{ - unsigned long i, end_pfn = start_pfn + nr_pages; - struct page *page; - - for (i = start_pfn; i < end_pfn; i++) { - page = pfn_to_online_page(i); - if (!page) - return false; - - if (page_zone(page) != z) - return false; - - if (PageReserved(page)) - return false; - - if (page_count(page) > 0) - return false; - - if (PageHuge(page)) - return false; - } - - return true; -} - -static bool zone_spans_last_pfn(const struct zone *zone, - unsigned long start_pfn, unsigned long nr_pages) -{ - unsigned long last_pfn = start_pfn + nr_pages - 1; - return zone_spans_pfn(zone, last_pfn); -} - static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { - unsigned int order = huge_page_order(h); - unsigned long nr_pages = 1 << order; - unsigned long ret, pfn, flags; - struct zonelist *zonelist; - struct zone *zone; - struct zoneref *z; - - zonelist = node_zonelist(nid, gfp_mask); - for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) { - spin_lock_irqsave(&zone->lock, flags); - - pfn = ALIGN(zone->zone_start_pfn, nr_pages); - while (zone_spans_last_pfn(zone, pfn, nr_pages)) { - if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) { - /* - * We release the zone lock here because - * alloc_contig_range() will also lock the zone - * at some point. If there's an allocation - * spinning on this lock, it may win the race - * and cause alloc_contig_range() to fail... - */ - spin_unlock_irqrestore(&zone->lock, flags); - ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask); - if (!ret) - return pfn_to_page(pfn); - spin_lock_irqsave(&zone->lock, flags); - } - pfn += nr_pages; - } - - spin_unlock_irqrestore(&zone->lock, flags); - } + unsigned long nr_pages = 1UL << huge_page_order(h); - return NULL; + return alloc_contig_pages(nr_pages, gfp_mask, nid, nodemask); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid); @@ -3915,7 +3796,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -4042,8 +3923,7 @@ backout_unlocked: } #ifdef CONFIG_SMP -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; @@ -4051,7 +3931,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, key[0] = (unsigned long) mapping; key[1] = idx; - hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); + hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } @@ -4060,8 +3940,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, * For uniprocesor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ -u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) +u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } @@ -4105,7 +3984,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); @@ -4459,6 +4338,21 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } } + + /* + * If subpage information not requested, update counters + * and skip the same_page loop below. + */ + if (!pages && !vmas && !pfn_offset && + (vaddr + huge_page_size(h) < vma->vm_end) && + (remainder >= pages_per_huge_page(h))) { + vaddr += huge_page_size(h); + remainder -= pages_per_huge_page(h); + i += pages_per_huge_page(h); + spin_unlock(ptl); + continue; + } + same_page: if (pages) { pages[i] = mem_map_offset(page, pfn_offset); diff --git a/mm/internal.h b/mm/internal.h index 0d5f720c75ab..3cf20ab3ca01 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -165,6 +165,9 @@ extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern int user_min_free_kbytes; +extern void zone_pcp_update(struct zone *zone); +extern void zone_pcp_reset(struct zone *zone); + #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* @@ -290,7 +293,8 @@ static inline bool is_data_mapping(vm_flags_t flags) /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev, struct rb_node *rb_parent); + struct vm_area_struct *prev); +void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU extern long populate_vma_page_range(struct vm_area_struct *vma, @@ -362,6 +366,27 @@ vma_address(struct page *page, struct vm_area_struct *vma) return max(start, vma->vm_start); } +static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, + struct file *fpin) +{ + int flags = vmf->flags; + + if (fpin) + return fpin; + + /* + * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or + * anything, so we only pin the file and drop the mmap_sem if only + * FAULT_FLAG_ALLOW_RETRY is set. + */ + if ((flags & (FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT)) == + FAULT_FLAG_ALLOW_RETRY) { + fpin = get_file(vmf->vma->vm_file); + up_read(&vmf->vma->vm_mm->mmap_sem); + } + return fpin; +} + #else /* !CONFIG_MMU */ static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a1b4b484ac5..cd480dce92c6 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1601,17 +1601,6 @@ static void collapse_file(struct mm_struct *mm, result = SCAN_FAIL; goto xa_unlocked; } - } else if (!PageUptodate(page)) { - xas_unlock_irq(&xas); - wait_on_page_locked(page); - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto xa_unlocked; - } - get_page(page); - } else if (PageDirty(page)) { - result = SCAN_FAIL; - goto xa_locked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); @@ -1626,7 +1615,12 @@ static void collapse_file(struct mm_struct *mm, * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageUptodate(page), page); + + /* double check the page is up to date */ + if (unlikely(!PageUptodate(page))) { + result = SCAN_FAIL; + goto out_unlock; + } /* * If file was truncated then extended, or hole-punched, before @@ -1642,6 +1636,24 @@ static void collapse_file(struct mm_struct *mm, goto out_unlock; } + if (!is_shmem && PageDirty(page)) { + /* + * khugepaged only works on read-only fd, so this + * page is dirty because it hasn't been flushed + * since first write. There won't be new dirty + * pages. + * + * Trigger async flush here and hope the writeback + * is done when khugepaged revisits this page. + * + * This is a one-off situation. We are not forcing + * writeback in loop. + */ + filemap_flush(mapping); + result = SCAN_FAIL; + goto out_unlock; + } + if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; diff --git a/mm/madvise.c b/mm/madvise.c index 2be9f3fdb05e..99dd06fecfa9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -887,7 +887,7 @@ static int madvise_inject_error(int behavior, pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); - ret = soft_offline_page(page, MF_COUNT_INCREASED); + ret = soft_offline_page(pfn, MF_COUNT_INCREASED); if (ret) return ret; continue; diff --git a/mm/memblock.c b/mm/memblock.c index c4b16cae2bc9..1f84be7d2b7d 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1323,12 +1323,13 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, * @start: the lower bound of the memory region to allocate (phys address) * @end: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes * * The allocation is performed from memory region limited by * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE. * - * If the specified node can not hold the requested memory the - * allocation falls back to any node in the system + * If the specified node can not hold the requested memory and @exact_nid + * is false, the allocation falls back to any node in the system * * For systems with memory mirroring, the allocation is attempted first * from the regions with mirroring enabled and then retried from any @@ -1342,7 +1343,8 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, */ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, - phys_addr_t end, int nid) + phys_addr_t end, int nid, + bool exact_nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t found; @@ -1362,7 +1364,7 @@ again: if (found && !memblock_reserve(found, size)) goto done; - if (nid != NUMA_NO_NODE) { + if (nid != NUMA_NO_NODE && !exact_nid) { found = memblock_find_in_range_node(size, align, start, end, NUMA_NO_NODE, flags); @@ -1410,7 +1412,8 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t start, phys_addr_t end) { - return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE); + return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, + false); } /** @@ -1429,7 +1432,7 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { return memblock_alloc_range_nid(size, align, 0, - MEMBLOCK_ALLOC_ACCESSIBLE, nid); + MEMBLOCK_ALLOC_ACCESSIBLE, nid, false); } /** @@ -1439,6 +1442,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * @min_addr: the lower bound of the memory region to allocate (phys address) * @max_addr: the upper bound of the memory region to allocate (phys address) * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * @exact_nid: control the allocation fall back to other nodes * * Allocates memory block using memblock_alloc_range_nid() and * converts the returned physical address to virtual. @@ -1454,7 +1458,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, - int nid) + int nid, bool exact_nid) { phys_addr_t alloc; @@ -1469,11 +1473,13 @@ static void * __init memblock_alloc_internal( if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; - alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid); + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid, + exact_nid); /* retry allocation without lower limit */ if (!alloc && min_addr) - alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid); + alloc = memblock_alloc_range_nid(size, align, 0, max_addr, nid, + exact_nid); if (!alloc) return NULL; @@ -1482,6 +1488,43 @@ static void * __init memblock_alloc_internal( } /** + * memblock_alloc_exact_nid_raw - allocate boot memory block on the exact node + * without zeroing memory + * @size: size of memory block to be allocated in bytes + * @align: alignment of the region and block's size + * @min_addr: the lower bound of the memory region from where the allocation + * is preferred (phys address) + * @max_addr: the upper bound of the memory region from where the allocation + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to + * allocate only from memory limited by memblock.current_limit value + * @nid: nid of the free area to find, %NUMA_NO_NODE for any node + * + * Public function, provides additional debug information (including caller + * info), if enabled. Does not zero allocated memory. + * + * Return: + * Virtual address of allocated memory block on success, NULL on failure. + */ +void * __init memblock_alloc_exact_nid_raw( + phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid) +{ + void *ptr; + + memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, nid, &min_addr, + &max_addr, (void *)_RET_IP_); + + ptr = memblock_alloc_internal(size, align, + min_addr, max_addr, nid, true); + if (ptr && size > 0) + page_init_poison(ptr, size); + + return ptr; +} + +/** * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes @@ -1512,7 +1555,7 @@ void * __init memblock_alloc_try_nid_raw( &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid); + min_addr, max_addr, nid, false); if (ptr && size > 0) page_init_poison(ptr, size); @@ -1547,7 +1590,7 @@ void * __init memblock_alloc_try_nid( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid); + min_addr, max_addr, nid, false); if (ptr) memset(ptr, 0, size); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4b3865a1e4c1..ea085877c548 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -98,14 +98,6 @@ static bool do_memsw_account(void) return !cgroup_subsys_on_dfl(memory_cgrp_subsys) && do_swap_account; } -static const char *const mem_cgroup_lru_names[] = { - "inactive_anon", - "active_anon", - "inactive_file", - "active_file", - "unevictable", -}; - #define THRESHOLDS_EVENTS_TARGET 128 #define SOFTLIMIT_EVENTS_TARGET 1024 #define NUMAINFO_EVENTS_TARGET 1024 @@ -1052,7 +1044,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup_per_node *mz; mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id); - iter = &mz->iter[reclaim->priority]; + iter = &mz->iter; if (prev && reclaim->generation != iter->generation) goto out_unlock; @@ -1152,15 +1144,11 @@ static void __invalidate_reclaim_iterators(struct mem_cgroup *from, struct mem_cgroup_reclaim_iter *iter; struct mem_cgroup_per_node *mz; int nid; - int i; for_each_node(nid) { mz = mem_cgroup_nodeinfo(from, nid); - for (i = 0; i <= DEF_PRIORITY; i++) { - iter = &mz->iter[i]; - cmpxchg(&iter->position, - dead_memcg, NULL); - } + iter = &mz->iter; + cmpxchg(&iter->position, dead_memcg, NULL); } } @@ -1438,7 +1426,7 @@ static char *memory_stat_format(struct mem_cgroup *memcg) PAGE_SIZE); for (i = 0; i < NR_LRU_LISTS; i++) - seq_buf_printf(&s, "%s %llu\n", mem_cgroup_lru_names[i], + seq_buf_printf(&s, "%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -1451,8 +1439,10 @@ static char *memory_stat_format(struct mem_cgroup *memcg) /* Accumulated memory events */ - seq_buf_printf(&s, "pgfault %lu\n", memcg_events(memcg, PGFAULT)); - seq_buf_printf(&s, "pgmajfault %lu\n", memcg_events(memcg, PGMAJFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT), + memcg_events(memcg, PGFAULT)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT), + memcg_events(memcg, PGMAJFAULT)); seq_buf_printf(&s, "workingset_refault %lu\n", memcg_page_state(memcg, WORKINGSET_REFAULT)); @@ -1461,22 +1451,27 @@ static char *memory_stat_format(struct mem_cgroup *memcg) seq_buf_printf(&s, "workingset_nodereclaim %lu\n", memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); - seq_buf_printf(&s, "pgrefill %lu\n", memcg_events(memcg, PGREFILL)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGREFILL), + memcg_events(memcg, PGREFILL)); seq_buf_printf(&s, "pgscan %lu\n", memcg_events(memcg, PGSCAN_KSWAPD) + memcg_events(memcg, PGSCAN_DIRECT)); seq_buf_printf(&s, "pgsteal %lu\n", memcg_events(memcg, PGSTEAL_KSWAPD) + memcg_events(memcg, PGSTEAL_DIRECT)); - seq_buf_printf(&s, "pgactivate %lu\n", memcg_events(memcg, PGACTIVATE)); - seq_buf_printf(&s, "pgdeactivate %lu\n", memcg_events(memcg, PGDEACTIVATE)); - seq_buf_printf(&s, "pglazyfree %lu\n", memcg_events(memcg, PGLAZYFREE)); - seq_buf_printf(&s, "pglazyfreed %lu\n", memcg_events(memcg, PGLAZYFREED)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE), + memcg_events(memcg, PGACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE), + memcg_events(memcg, PGDEACTIVATE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE), + memcg_events(memcg, PGLAZYFREE)); + seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED), + memcg_events(memcg, PGLAZYFREED)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE - seq_buf_printf(&s, "thp_fault_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC), memcg_events(memcg, THP_FAULT_ALLOC)); - seq_buf_printf(&s, "thp_collapse_alloc %lu\n", + seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC), memcg_events(memcg, THP_COLLAPSE_ALLOC)); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -1705,7 +1700,6 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg, unsigned long nr_scanned; struct mem_cgroup_reclaim_cookie reclaim = { .pgdat = pgdat, - .priority = 0, }; excess = soft_limit_excess(root_memcg); @@ -3849,13 +3843,6 @@ static const unsigned int memcg1_events[] = { PGMAJFAULT, }; -static const char *const memcg1_event_names[] = { - "pgpgin", - "pgpgout", - "pgfault", - "pgmajfault", -}; - static int memcg_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_seq(m); @@ -3864,7 +3851,6 @@ static int memcg_stat_show(struct seq_file *m, void *v) unsigned int i; BUILD_BUG_ON(ARRAY_SIZE(memcg1_stat_names) != ARRAY_SIZE(memcg1_stats)); - BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) { if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account()) @@ -3875,11 +3861,11 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "%s %lu\n", memcg1_event_names[i], + seq_printf(m, "%s %lu\n", vm_event_name(memcg1_events[i]), memcg_events_local(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "%s %lu\n", mem_cgroup_lru_names[i], + seq_printf(m, "%s %lu\n", lru_list_name(i), memcg_page_state_local(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -3904,11 +3890,12 @@ static int memcg_stat_show(struct seq_file *m, void *v) } for (i = 0; i < ARRAY_SIZE(memcg1_events); i++) - seq_printf(m, "total_%s %llu\n", memcg1_event_names[i], + seq_printf(m, "total_%s %llu\n", + vm_event_name(memcg1_events[i]), (u64)memcg_events(memcg, memcg1_events[i])); for (i = 0; i < NR_LRU_LISTS; i++) - seq_printf(m, "total_%s %llu\n", mem_cgroup_lru_names[i], + seq_printf(m, "total_%s %llu\n", lru_list_name(i), (u64)memcg_page_state(memcg, NR_LRU_BASE + i) * PAGE_SIZE); @@ -5014,12 +5001,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - /* - * Flush percpu vmstats and vmevents to guarantee the value correctness - * on parent's and all ancestor levels. - */ - memcg_flush_percpu_vmstats(memcg, false); - memcg_flush_percpu_vmevents(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->vmstats_percpu); @@ -5030,6 +5011,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) static void mem_cgroup_free(struct mem_cgroup *memcg) { memcg_wb_domain_exit(memcg); + /* + * Flush percpu vmstats and vmevents to guarantee the value correctness + * on parent's and all ancestor levels. + */ + memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } @@ -6087,7 +6074,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); - unsigned long nr_pages; + unsigned int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; + bool drained = false; unsigned long high; int err; @@ -6098,12 +6086,29 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, memcg->high = high; - nr_pages = page_counter_read(&memcg->memory); - if (nr_pages > high) - try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, true); + for (;;) { + unsigned long nr_pages = page_counter_read(&memcg->memory); + unsigned long reclaimed; + + if (nr_pages <= high) + break; + + if (signal_pending(current)) + break; + + if (!drained) { + drain_all_stock(memcg); + drained = true; + continue; + } + + reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, + GFP_KERNEL, true); + + if (!reclaimed && !nr_retries--) + break; + } - memcg_wb_domain_size_changed(memcg); return nbytes; } @@ -6135,10 +6140,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_pages <= max) break; - if (signal_pending(current)) { - err = -EINTR; + if (signal_pending(current)) break; - } if (!drained) { drain_all_stock(memcg); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3151c87dff73..af2712004a4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -303,25 +303,19 @@ static unsigned long dev_pagemap_mapping_shift(struct page *page, /* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. - * TBD would GFP_NOIO be enough? */ static void add_to_kill(struct task_struct *tsk, struct page *p, struct vm_area_struct *vma, - struct list_head *to_kill, - struct to_kill **tkc) + struct list_head *to_kill) { struct to_kill *tk; - if (*tkc) { - tk = *tkc; - *tkc = NULL; - } else { - tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); - if (!tk) { - pr_err("Memory failure: Out of memory while machine check handling\n"); - return; - } + tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC); + if (!tk) { + pr_err("Memory failure: Out of memory while machine check handling\n"); + return; } + tk->addr = page_address_in_vma(p, vma); if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(p, vma); @@ -345,6 +339,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, kfree(tk); return; } + get_task_struct(tsk); tk->tsk = tsk; list_add_tail(&tk->nd, to_kill); @@ -436,7 +431,7 @@ static struct task_struct *task_early_kill(struct task_struct *tsk, * Collect processes when the error hit an anonymous page. */ static void collect_procs_anon(struct page *page, struct list_head *to_kill, - struct to_kill **tkc, int force_early) + int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -461,7 +456,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, if (!page_mapped_in_vma(page, vma)) continue; if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill, tkc); + add_to_kill(t, page, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -472,7 +467,7 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, * Collect processes when the error hit a file mapped page. */ static void collect_procs_file(struct page *page, struct list_head *to_kill, - struct to_kill **tkc, int force_early) + int force_early) { struct vm_area_struct *vma; struct task_struct *tsk; @@ -496,7 +491,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, * to be informed of all such data corruptions. */ if (vma->vm_mm == t->mm) - add_to_kill(t, page, vma, to_kill, tkc); + add_to_kill(t, page, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -505,26 +500,17 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill, /* * Collect the processes who have the corrupted page mapped to kill. - * This is done in two steps for locking reasons. - * First preallocate one tokill structure outside the spin locks, - * so that we can kill at least one process reasonably reliable. */ static void collect_procs(struct page *page, struct list_head *tokill, int force_early) { - struct to_kill *tk; - if (!page->mapping) return; - tk = kmalloc(sizeof(struct to_kill), GFP_NOIO); - if (!tk) - return; if (PageAnon(page)) - collect_procs_anon(page, tokill, &tk, force_early); + collect_procs_anon(page, tokill, force_early); else - collect_procs_file(page, tokill, &tk, force_early); - kfree(tk); + collect_procs_file(page, tokill, force_early); } static const char *action_name[] = { @@ -1490,7 +1476,7 @@ static void memory_failure_work_func(struct work_struct *work) if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) - soft_offline_page(pfn_to_page(entry.pfn), entry.flags); + soft_offline_page(entry.pfn, entry.flags); else memory_failure(entry.pfn, entry.flags); } @@ -1871,7 +1857,7 @@ static int soft_offline_free_page(struct page *page) /** * soft_offline_page - Soft offline a page. - * @page: page to offline + * @pfn: pfn to soft-offline * @flags: flags. Same as memory_failure(). * * Returns 0 on success, otherwise negated errno. @@ -1891,18 +1877,17 @@ static int soft_offline_free_page(struct page *page) * This is not a 100% solution for all memory, but tries to be * ``good enough'' for the majority of memory. */ -int soft_offline_page(struct page *page, int flags) +int soft_offline_page(unsigned long pfn, int flags) { int ret; - unsigned long pfn = page_to_pfn(page); + struct page *page; - if (is_zone_device_page(page)) { - pr_debug_ratelimited("soft_offline: %#lx page is device page\n", - pfn); - if (flags & MF_COUNT_INCREASED) - put_page(page); + if (!pfn_valid(pfn)) + return -ENXIO; + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + page = pfn_to_online_page(pfn); + if (!page) return -EIO; - } if (PageHWPoison(page)) { pr_info("soft offline: %#lx page already poisoned\n", pfn); diff --git a/mm/memory.c b/mm/memory.c index b6a5d6a08438..7596d625ebd1 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -72,6 +72,8 @@ #include <linux/oom.h> #include <linux/numa.h> +#include <trace/events/kmem.h> + #include <asm/io.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> @@ -152,6 +154,10 @@ static int __init init_zero_pfn(void) } core_initcall(init_zero_pfn); +void mm_trace_rss_stat(int member, long count) +{ + trace_rss_stat(member, count); +} #if defined(SPLIT_RSS_COUNTING) @@ -2289,10 +2295,11 @@ static vm_fault_t do_page_mkwrite(struct vm_fault *vmf) * * The function expects the page to be locked and unlocks it. */ -static void fault_dirty_shared_page(struct vm_area_struct *vma, - struct page *page) +static vm_fault_t fault_dirty_shared_page(struct vm_fault *vmf) { + struct vm_area_struct *vma = vmf->vma; struct address_space *mapping; + struct page *page = vmf->page; bool dirtied; bool page_mkwrite = vma->vm_ops && vma->vm_ops->page_mkwrite; @@ -2307,16 +2314,30 @@ static void fault_dirty_shared_page(struct vm_area_struct *vma, mapping = page_rmapping(page); unlock_page(page); + if (!page_mkwrite) + file_update_time(vma->vm_file); + + /* + * Throttle page dirtying rate down to writeback speed. + * + * mapping may be NULL here because some device drivers do not + * set page.mapping but still dirty their pages + * + * Drop the mmap_sem before waiting on IO, if we can. The file + * is pinning the mapping, as per above. + */ if ((dirtied || page_mkwrite) && mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ + struct file *fpin; + + fpin = maybe_unlock_mmap_for_io(vmf, NULL); balance_dirty_pages_ratelimited(mapping); + if (fpin) { + fput(fpin); + return VM_FAULT_RETRY; + } } - if (!page_mkwrite) - file_update_time(vma->vm_file); + return 0; } /* @@ -2571,6 +2592,7 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) __releases(vmf->ptl) { struct vm_area_struct *vma = vmf->vma; + vm_fault_t ret = VM_FAULT_WRITE; get_page(vmf->page); @@ -2594,10 +2616,10 @@ static vm_fault_t wp_page_shared(struct vm_fault *vmf) wp_page_reuse(vmf); lock_page(vmf->page); } - fault_dirty_shared_page(vma, vmf->page); + ret |= fault_dirty_shared_page(vmf); put_page(vmf->page); - return VM_FAULT_WRITE; + return ret; } /* @@ -3083,7 +3105,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) /* * The memory barrier inside __SetPageUptodate makes sure that - * preceeding stores to the page contents become visible before + * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); @@ -3641,7 +3663,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) return ret; } - fault_dirty_shared_page(vma, vmf->page); + ret |= fault_dirty_shared_page(vmf); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index df570e5c71cc..561371ead39a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -49,8 +49,6 @@ * and restore_online_page_callback() for generic callback restore. */ -static void generic_online_page(struct page *page, unsigned int order); - static online_page_callback_t online_page_callback = generic_online_page; static DEFINE_MUTEX(online_page_callback_lock); @@ -278,6 +276,22 @@ static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, return 0; } +static int check_hotplug_memory_addressable(unsigned long pfn, + unsigned long nr_pages) +{ + const u64 max_addr = PFN_PHYS(pfn + nr_pages) - 1; + + if (max_addr >> MAX_PHYSMEM_BITS) { + const u64 max_allowed = (1ull << (MAX_PHYSMEM_BITS + 1)) - 1; + WARN(1, + "Hotplugged memory exceeds maximum addressable address, range=%#llx-%#llx, maximum=%#llx\n", + (u64)PFN_PHYS(pfn), max_addr, max_allowed); + return -E2BIG; + } + + return 0; +} + /* * Reasonably generic function for adding memory. It is * expected that archs that support memory hotplug will @@ -291,6 +305,10 @@ int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages, unsigned long nr, start_sec, end_sec; struct vmem_altmap *altmap = restrictions->altmap; + err = check_hotplug_memory_addressable(pfn, nr_pages); + if (err) + return err; + if (altmap) { /* * Validate altmap is within bounds of the total request @@ -331,13 +349,13 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(start_pfn))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) continue; - if (zone && zone != page_zone(pfn_to_page(start_pfn))) + if (zone != page_zone(pfn_to_page(start_pfn))) continue; return start_pfn; @@ -356,13 +374,13 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) continue; - if (zone && zone != page_zone(pfn_to_page(pfn))) + if (zone != page_zone(pfn_to_page(pfn))) continue; return pfn; @@ -374,14 +392,11 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { - unsigned long zone_start_pfn = zone->zone_start_pfn; - unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */ - unsigned long zone_end_pfn = z; unsigned long pfn; int nid = zone_to_nid(zone); zone_span_writelock(zone); - if (zone_start_pfn == start_pfn) { + if (zone->zone_start_pfn == start_pfn) { /* * If the section is smallest section in the zone, it need * shrink zone->zone_start_pfn and zone->zone_spanned_pages. @@ -389,50 +404,30 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, * for shrinking zone. */ pfn = find_smallest_section_pfn(nid, zone, end_pfn, - zone_end_pfn); + zone_end_pfn(zone)); if (pfn) { + zone->spanned_pages = zone_end_pfn(zone) - pfn; zone->zone_start_pfn = pfn; - zone->spanned_pages = zone_end_pfn - pfn; + } else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; } - } else if (zone_end_pfn == end_pfn) { + } else if (zone_end_pfn(zone) == end_pfn) { /* * If the section is biggest section in the zone, it need * shrink zone->spanned_pages. * In this case, we find second biggest valid mem_section for * shrinking zone. */ - pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn, + pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn, start_pfn); if (pfn) - zone->spanned_pages = pfn - zone_start_pfn + 1; - } - - /* - * The section is not biggest or smallest mem_section in the zone, it - * only creates a hole in the zone. So in this case, we need not - * change the zone. But perhaps, the zone has only hole data. Thus - * it check the zone has only hole or not. - */ - pfn = zone_start_pfn; - for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) - continue; - - if (page_zone(pfn_to_page(pfn)) != zone) - continue; - - /* Skip range to be removed */ - if (pfn >= start_pfn && pfn < end_pfn) - continue; - - /* If we find valid section, we have nothing to do */ - zone_span_writeunlock(zone); - return; + zone->spanned_pages = pfn - zone->zone_start_pfn + 1; + else { + zone->zone_start_pfn = 0; + zone->spanned_pages = 0; + } } - - /* The zone has no valid section */ - zone->zone_start_pfn = 0; - zone->spanned_pages = 0; zone_span_writeunlock(zone); } @@ -457,34 +452,50 @@ static void update_pgdat_span(struct pglist_data *pgdat) pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } -static void __remove_zone(struct zone *zone, unsigned long start_pfn, - unsigned long nr_pages) +void __ref remove_pfn_range_from_zone(struct zone *zone, + unsigned long start_pfn, + unsigned long nr_pages) { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; + /* Poison struct pages because they are now uninitialized again. */ + page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages); + +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + + clear_zone_contiguous(zone); + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); + + set_zone_contiguous(zone); } -static void __remove_section(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, unsigned long map_offset, - struct vmem_altmap *altmap) +static void __remove_section(unsigned long pfn, unsigned long nr_pages, + unsigned long map_offset, + struct vmem_altmap *altmap) { struct mem_section *ms = __nr_to_section(pfn_to_section_nr(pfn)); if (WARN_ON_ONCE(!valid_section(ms))) return; - __remove_zone(zone, pfn, nr_pages); sparse_remove_section(ms, pfn, nr_pages, map_offset, altmap); } /** - * __remove_pages() - remove sections of pages from a zone - * @zone: zone from which pages need to be removed + * __remove_pages() - remove sections of pages * @pfn: starting pageframe (must be aligned to start of a section) * @nr_pages: number of pages to remove (must be multiple of section size) * @altmap: alternative device page map or %NULL if default memmap is used @@ -494,34 +505,25 @@ static void __remove_section(struct zone *zone, unsigned long pfn, * sure that pages are marked reserved and zones are adjust properly by * calling offline_pages(). */ -void __remove_pages(struct zone *zone, unsigned long pfn, - unsigned long nr_pages, struct vmem_altmap *altmap) +void __remove_pages(unsigned long pfn, unsigned long nr_pages, + struct vmem_altmap *altmap) { + const unsigned long end_pfn = pfn + nr_pages; + unsigned long cur_nr_pages; unsigned long map_offset = 0; - unsigned long nr, start_sec, end_sec; map_offset = vmem_altmap_offset(altmap); - clear_zone_contiguous(zone); - if (check_pfn_span(pfn, nr_pages, "remove")) return; - start_sec = pfn_to_section_nr(pfn); - end_sec = pfn_to_section_nr(pfn + nr_pages - 1); - for (nr = start_sec; nr <= end_sec; nr++) { - unsigned long pfns; - + for (; pfn < end_pfn; pfn += cur_nr_pages) { cond_resched(); - pfns = min(nr_pages, PAGES_PER_SECTION - - (pfn & ~PAGE_SECTION_MASK)); - __remove_section(zone, pfn, pfns, map_offset, altmap); - pfn += pfns; - nr_pages -= pfns; + /* Select all remaining pages up to the next section boundary */ + cur_nr_pages = min(end_pfn - pfn, -(pfn | PAGE_SECTION_MASK)); + __remove_section(pfn, cur_nr_pages, map_offset, altmap); map_offset = 0; } - - set_zone_contiguous(zone); } int set_online_page_callback(online_page_callback_t callback) @@ -562,24 +564,7 @@ int restore_online_page_callback(online_page_callback_t callback) } EXPORT_SYMBOL_GPL(restore_online_page_callback); -void __online_page_set_limits(struct page *page) -{ -} -EXPORT_SYMBOL_GPL(__online_page_set_limits); - -void __online_page_increment_counters(struct page *page) -{ - adjust_managed_page_count(page, 1); -} -EXPORT_SYMBOL_GPL(__online_page_increment_counters); - -void __online_page_free(struct page *page) -{ - __free_reserved_page(page); -} -EXPORT_SYMBOL_GPL(__online_page_free); - -static void generic_online_page(struct page *page, unsigned int order) +void generic_online_page(struct page *page, unsigned int order) { kernel_map_pages(page, 1 << order, 1); __free_pages_core(page, order); @@ -589,6 +574,7 @@ static void generic_online_page(struct page *page, unsigned int order) totalhigh_pages_add(1UL << order); #endif } +EXPORT_SYMBOL_GPL(generic_online_page); static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages, void *arg) @@ -849,6 +835,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + remove_pfn_range_from_zone(zone, pfn, nr_pages); mem_hotplug_done(); return ret; } @@ -1162,7 +1149,8 @@ static bool is_pageblock_removable_nolock(unsigned long pfn) if (!zone_spans_pfn(zone, pfn)) return false; - return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, SKIP_HWPOISON); + return !has_unmovable_pages(zone, page, 0, MIGRATE_MOVABLE, + MEMORY_OFFLINE); } /* Checks if this range of memory is likely to be hot-removable. */ @@ -1359,9 +1347,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) return ret; } -/* - * remove from free_area[] and mark all as Reserved. - */ +/* Mark all sections offline and remove all free pages from the buddy. */ static int offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages, void *data) @@ -1379,7 +1365,8 @@ static int check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages, void *data) { - return test_pages_isolated(start_pfn, start_pfn + nr_pages, true); + return test_pages_isolated(start_pfn, start_pfn + nr_pages, + MEMORY_OFFLINE); } static int __init cmdline_parse_movable_node(char *p) @@ -1490,7 +1477,7 @@ static int __ref __offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - SKIP_HWPOISON | REPORT_FAILURE); + MEMORY_OFFLINE | REPORT_FAILURE); if (ret < 0) { reason = "failure to isolate range"; goto failed_removal; @@ -1584,6 +1571,7 @@ static int __ref __offline_pages(unsigned long start_pfn, writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + remove_pfn_range_from_zone(zone, start_pfn, nr_pages); mem_hotplug_done(); return 0; @@ -1721,13 +1709,13 @@ static int __ref try_remove_memory(int nid, u64 start, u64 size) /* remove memmap entry */ firmware_map_remove(start, start + size, "System RAM"); - memblock_free(start, size); - memblock_remove(start, size); /* remove memory block devices before removing memory */ remove_memory_block_devices(start, size); arch_remove_memory(nid, start, size, NULL); + memblock_free(start, size); + memblock_remove(start, size); __release_memory_resource(start, size); try_offline_node(nid); diff --git a/mm/memremap.c b/mm/memremap.c index 03ccbdfeb697..022e78e68ea0 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -55,8 +55,16 @@ static void pgmap_array_delete(struct resource *res) static unsigned long pfn_first(struct dev_pagemap *pgmap) { - return PHYS_PFN(pgmap->res.start) + - vmem_altmap_offset(pgmap_altmap(pgmap)); + const struct resource *res = &pgmap->res; + struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned long pfn; + + if (altmap) + pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + else + pfn = PHYS_PFN(res->start); + + return pfn; } static unsigned long pfn_end(struct dev_pagemap *pgmap) @@ -73,6 +81,26 @@ static unsigned long pfn_next(unsigned long pfn) return pfn + 1; } +/* + * This returns true if the page is reserved by ZONE_DEVICE driver. + */ +bool pfn_zone_device_reserved(unsigned long pfn) +{ + struct dev_pagemap *pgmap; + struct vmem_altmap *altmap; + bool ret = false; + + pgmap = get_dev_pagemap(pfn, NULL); + if (!pgmap) + return ret; + altmap = pgmap_altmap(pgmap); + if (altmap && pfn < (altmap->base_pfn + altmap->reserve)) + ret = true; + put_dev_pagemap(pgmap); + + return ret; +} + #define for_each_device_pfn(pfn, map) \ for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn)) @@ -119,8 +147,10 @@ void memunmap_pages(struct dev_pagemap *pgmap) nid = page_to_nid(first_page); mem_hotplug_begin(); + remove_pfn_range_from_zone(page_zone(first_page), PHYS_PFN(res->start), + PHYS_PFN(resource_size(res))); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + __remove_pages(PHYS_PFN(res->start), PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), diff --git a/mm/mmap.c b/mm/mmap.c index a7d8c84d19b7..d5ca73facd5d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -641,7 +641,7 @@ __vma_link(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node **rb_link, struct rb_node *rb_parent) { - __vma_link_list(mm, vma, prev, rb_parent); + __vma_link_list(mm, vma, prev); __vma_link_rb(mm, vma, rb_link, rb_parent); } @@ -684,37 +684,14 @@ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) static __always_inline void __vma_unlink_common(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev, - bool has_prev, struct vm_area_struct *ignore) { - struct vm_area_struct *next; - vma_rb_erase_ignore(vma, &mm->mm_rb, ignore); - next = vma->vm_next; - if (has_prev) - prev->vm_next = next; - else { - prev = vma->vm_prev; - if (prev) - prev->vm_next = next; - else - mm->mmap = next; - } - if (next) - next->vm_prev = prev; - + __vma_unlink_list(mm, vma); /* Kill the cache */ vmacache_invalidate(mm); } -static inline void __vma_unlink_prev(struct mm_struct *mm, - struct vm_area_struct *vma, - struct vm_area_struct *prev) -{ - __vma_unlink_common(mm, vma, prev, true, vma); -} - /* * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that * is already present in an i_mmap tree without adjusting the tree. @@ -769,8 +746,6 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, remove_next = 1 + (end > next->vm_end); VM_WARN_ON(remove_next == 2 && end != next->vm_next->vm_end); - VM_WARN_ON(remove_next == 1 && - end != next->vm_end); /* trim end to next, for case 6 first pass */ end = next->vm_end; } @@ -889,7 +864,7 @@ again: * us to remove next before dropping the locks. */ if (remove_next != 3) - __vma_unlink_prev(mm, next, vma); + __vma_unlink_common(mm, next, next); else /* * vma is not before next if they've been @@ -900,7 +875,7 @@ again: * "next" (which is stored in post-swap() * "vma"). */ - __vma_unlink_common(mm, next, NULL, false, vma); + __vma_unlink_common(mm, next, vma); if (file) __remove_shared_vm_struct(next, file, mapping); } else if (insert) { @@ -1442,7 +1417,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, * that it represents a valid section of the address space. */ addr = get_unmapped_area(file, addr, len, pgoff, flags); - if (offset_in_page(addr)) + if (IS_ERR_VALUE(addr)) return addr; if (flags & MAP_FIXED_NOREPLACE) { @@ -1884,6 +1859,22 @@ unacct_error: return error; } +static inline unsigned long gap_start_offset(struct vm_unmapped_area_info *info, + unsigned long addr) +{ + /* get gap_start offset to adjust gap address to the + * desired alignment + */ + return (info->align_offset - addr) & info->align_mask; +} + +static inline unsigned long gap_end_offset(struct vm_unmapped_area_info *info, + unsigned long addr) +{ + /* get gap_end offset to adjust gap address to the desired alignment */ + return (addr - info->align_offset) & info->align_mask; +} + unsigned long unmapped_area(struct vm_unmapped_area_info *info) { /* @@ -1898,10 +1889,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; - /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask; - if (length < info->length) - return -ENOMEM; + length = info->length; /* Adjust search limits by the desired length */ if (info->high_limit < length) @@ -1933,6 +1921,7 @@ unsigned long unmapped_area(struct vm_unmapped_area_info *info) } gap_start = vma->vm_prev ? vm_end_gap(vma->vm_prev) : 0; + gap_start += gap_start_offset(info, gap_start); check_current: /* Check if current node has a suitable gap */ if (gap_start > high_limit) @@ -1961,6 +1950,7 @@ check_current: struct vm_area_struct, vm_rb); if (prev == vma->vm_rb.rb_left) { gap_start = vm_end_gap(vma->vm_prev); + gap_start += gap_start_offset(info, gap_start); gap_end = vm_start_gap(vma); goto check_current; } @@ -1970,17 +1960,17 @@ check_current: check_highest: /* Check highest gap, which does not precede any rbtree node */ gap_start = mm->highest_vm_end; + gap_start += gap_start_offset(info, gap_start); gap_end = ULONG_MAX; /* Only for VM_BUG_ON below */ if (gap_start > high_limit) return -ENOMEM; found: /* We found a suitable gap. Clip it with the original low_limit. */ - if (gap_start < info->low_limit) + if (gap_start < info->low_limit) { gap_start = info->low_limit; - - /* Adjust gap address to the desired alignment */ - gap_start += (info->align_offset - gap_start) & info->align_mask; + gap_start += gap_start_offset(info, gap_start); + } VM_BUG_ON(gap_start + info->length > info->high_limit); VM_BUG_ON(gap_start + info->length > gap_end); @@ -1993,16 +1983,14 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) struct vm_area_struct *vma; unsigned long length, low_limit, high_limit, gap_start, gap_end; - /* Adjust search length to account for worst case alignment overhead */ - length = info->length + info->align_mask; - if (length < info->length) - return -ENOMEM; + length = info->length; /* * Adjust search limits by the desired length. * See implementation comment at top of unmapped_area(). */ gap_end = info->high_limit; + gap_end -= gap_end_offset(info, gap_end); if (gap_end < length) return -ENOMEM; high_limit = gap_end - length; @@ -2039,6 +2027,7 @@ unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info) check_current: /* Check if current node has a suitable gap */ gap_end = vm_start_gap(vma); + gap_end -= gap_end_offset(info, gap_end); if (gap_end < low_limit) return -ENOMEM; if (gap_start <= high_limit && @@ -2073,13 +2062,14 @@ check_current: found: /* We found a suitable gap. Clip it with the original high_limit. */ - if (gap_end > info->high_limit) + if (gap_end > info->high_limit) { gap_end = info->high_limit; + gap_end -= gap_end_offset(info, gap_end); + } found_highest: /* Compute highest gap address at the desired alignment */ gap_end -= info->length; - gap_end -= (gap_end - info->align_offset) & info->align_mask; VM_BUG_ON(gap_end < info->low_limit); VM_BUG_ON(gap_end < gap_start); @@ -3006,15 +2996,16 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla struct rb_node **rb_link, *rb_parent; pgoff_t pgoff = addr >> PAGE_SHIFT; int error; + unsigned long mapped_addr; /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; - error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); - if (offset_in_page(error)) - return error; + mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); + if (IS_ERR_VALUE(mapped_addr)) + return mapped_addr; error = mlock_future_check(mm, mm->def_flags, len); if (error) diff --git a/mm/mremap.c b/mm/mremap.c index 1fc8a29fbe3f..122938dcec15 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -558,7 +558,7 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len, ret = get_unmapped_area(vma->vm_file, new_addr, new_len, vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); - if (offset_in_page(ret)) + if (IS_ERR_VALUE(ret)) goto out1; ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf, @@ -706,7 +706,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT), map_flags); - if (offset_in_page(new_addr)) { + if (IS_ERR_VALUE(new_addr)) { ret = new_addr; goto out; } diff --git a/mm/nommu.c b/mm/nommu.c index 99b7ec318824..21ddf689d4fa 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -637,7 +637,7 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) if (rb_prev) prev = rb_entry(rb_prev, struct vm_area_struct, vm_rb); - __vma_link_list(mm, vma, prev, parent); + __vma_link_list(mm, vma, prev); } /* @@ -673,13 +673,7 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) /* remove from the MM's tree and list */ rb_erase(&vma->vm_rb, &mm->mm_rb); - if (vma->vm_prev) - vma->vm_prev->vm_next = vma->vm_next; - else - mm->mmap = vma->vm_next; - - if (vma->vm_next) - vma->vm_next->vm_prev = vma->vm_prev; + __vma_unlink_list(mm, vma); } /* diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 71e3acea7817..314ce1a3cf25 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -377,36 +377,13 @@ static void select_bad_process(struct oom_control *oc) } } -static int dump_task(struct task_struct *p, void *arg) -{ - struct oom_control *oc = arg; - struct task_struct *task; - - if (oom_unkillable_task(p)) - return 0; - - /* p may not have freeable memory in nodemask */ - if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) - return 0; - task = find_lock_task_mm(p); - if (!task) { - /* - * This is a kthread or all of p's threads have already - * detached their mm's. There's no need to report - * them; they can't be oom killed anyway. - */ - return 0; +static int add_candidate_task(struct task_struct *p, void *arg) +{ + if (!oom_unkillable_task(p)) { + get_task_struct(p); + list_add_tail(&p->oom_victim_list, (struct list_head *) arg); } - - pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", - task->pid, from_kuid(&init_user_ns, task_uid(task)), - task->tgid, task->mm->total_vm, get_mm_rss(task->mm), - mm_pgtables_bytes(task->mm), - get_mm_counter(task->mm, MM_SWAPENTS), - task->signal->oom_score_adj, task->comm); - task_unlock(task); - return 0; } @@ -422,19 +399,41 @@ static int dump_task(struct task_struct *p, void *arg) */ static void dump_tasks(struct oom_control *oc) { - pr_info("Tasks state (memory values in pages):\n"); - pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); + LIST_HEAD(list); + struct task_struct *p; + struct task_struct *t; if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); + mem_cgroup_scan_tasks(oc->memcg, add_candidate_task, &list); else { - struct task_struct *p; - rcu_read_lock(); for_each_process(p) - dump_task(p, oc); + add_candidate_task(p, &list); rcu_read_unlock(); } + pr_info("Tasks state (memory values in pages):\n"); + pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); + list_for_each_entry(p, &list, oom_victim_list) { + cond_resched(); + /* p may not have freeable memory in nodemask */ + if (!is_memcg_oom(oc) && !oom_cpuset_eligible(p, oc)) + continue; + /* All of p's threads might have already detached their mm's. */ + t = find_lock_task_mm(p); + if (!t) + continue; + pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n", + t->pid, from_kuid(&init_user_ns, task_uid(t)), + t->tgid, t->mm->total_vm, get_mm_rss(t->mm), + mm_pgtables_bytes(t->mm), + get_mm_counter(t->mm, MM_SWAPENTS), + t->signal->oom_score_adj, t->comm); + task_unlock(t); + } + list_for_each_entry_safe(p, t, &list, oom_victim_list) { + list_del(&p->oom_victim_list); + put_task_struct(p); + } } static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ecc3dbad606b..12f3ce09d33d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -5944,10 +5952,10 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, #ifdef CONFIG_ZONE_DEVICE void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, - unsigned long size, + unsigned long nr_pages, struct dev_pagemap *pgmap) { - unsigned long pfn, end_pfn = start_pfn + size; + unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); unsigned long zone_idx = zone_idx(zone); @@ -5964,7 +5972,7 @@ void __ref memmap_init_zone_device(struct zone *zone, */ if (altmap) { start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - size = end_pfn - start_pfn; + nr_pages = end_pfn - start_pfn; } for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -6011,7 +6019,7 @@ void __ref memmap_init_zone_device(struct zone *zone, } pr_info("%s initialised %lu pages in %ums\n", __func__, - size, jiffies_to_msecs(jiffies - start)); + nr_pages, jiffies_to_msecs(jiffies - start)); } #endif @@ -7985,6 +7993,15 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, return 0; } +static void __zone_pcp_update(struct zone *zone) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); +} + /* * percpu_pagelist_fraction - changes the pcp->high for each zone on each * cpu. It is the fraction of total pages in each zone that a hot per cpu @@ -8016,13 +8033,8 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) goto out; - for_each_populated_zone(zone) { - unsigned int cpu; - - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); - } + for_each_populated_zone(zone) + __zone_pcp_update(zone); out: mutex_unlock(&pcp_batch_high_lock); return ret; @@ -8258,7 +8270,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * The HWPoisoned page may be not in buddy system, and * page_count() is not 0. */ - if ((flags & SKIP_HWPOISON) && PageHWPoison(page)) + if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) continue; if (__PageMovable(page)) @@ -8474,7 +8486,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, } /* Make sure the range is really isolated. */ - if (test_pages_isolated(outer_start, end, false)) { + if (test_pages_isolated(outer_start, end, 0)) { pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", __func__, outer_start, end); ret = -EBUSY; @@ -8499,6 +8511,107 @@ done: pfn_max_align_up(end), migratetype); return ret; } + +static int __alloc_contig_pages(unsigned long start_pfn, + unsigned long nr_pages, gfp_t gfp_mask) +{ + unsigned long end_pfn = start_pfn + nr_pages; + + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); +} + +static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + page = pfn_to_online_page(i); + if (!page) + return false; + + if (page_zone(page) != z) + return false; + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + + return zone_spans_pfn(zone, last_pfn); +} + +/** + * alloc_contig_pages() -- tries to find and allocate contiguous range of pages + * @nr_pages: Number of contiguous pages to allocate + * @gfp_mask: GFP mask to limit search and used during compaction + * @nid: Target node + * @nodemask: Mask for other possible nodes + * + * This routine is a wrapper around alloc_contig_range(). It scans over zones + * on an applicable zonelist to find a contiguous pfn range which can then be + * tried for allocation with alloc_contig_range(). This routine is intended + * for allocation requests which can not be fulfilled with the buddy allocator. + * + * The allocated memory is always aligned to a page boundary. If nr_pages is a + * power of two then the alignment is guaranteed to be to the given nr_pages + * (e.g. 1GB request would be aligned to 1GB). + * + * Allocated pages can be freed with free_contig_range() or by manually calling + * __free_page() on each allocated page. + * + * Return: pointer to contiguous pages on success, or NULL if not successful. + */ +struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long ret, pfn, flags; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + spin_lock_irqsave(&zone->lock, flags); + + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_contig(zone, pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_contig_pages(pfn, nr_pages, + gfp_mask); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&zone->lock, flags); + } + pfn += nr_pages; + } + spin_unlock_irqrestore(&zone->lock, flags); + } + return NULL; +} #endif /* CONFIG_CONTIG_ALLOC */ void free_contig_range(unsigned long pfn, unsigned int nr_pages) @@ -8514,21 +8627,16 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. */ void __meminit zone_pcp_update(struct zone *zone) { - unsigned cpu; mutex_lock(&pcp_batch_high_lock); - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); + __zone_pcp_update(zone); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { @@ -8559,7 +8667,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - unsigned int order, i; + unsigned int order; unsigned long pfn; unsigned long flags; unsigned long offlined_pages = 0; @@ -8587,7 +8695,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) */ if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { pfn++; - SetPageReserved(page); offlined_pages++; continue; } @@ -8601,8 +8708,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) pfn, 1 << order, end_pfn); #endif del_page_from_free_area(page, &zone->free_area[order]); - for (i = 0; i < (1 << order); i++) - SetPageReserved((page+i)); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); diff --git a/mm/page_io.c b/mm/page_io.c index 24ee600f9131..83db25aee6f1 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -22,6 +22,7 @@ #include <linux/writeback.h> #include <linux/frontswap.h> #include <linux/blkdev.h> +#include <linux/psi.h> #include <linux/uio.h> #include <linux/sched/task.h> #include <asm/pgtable.h> @@ -354,10 +355,19 @@ int swap_readpage(struct page *page, bool synchronous) struct swap_info_struct *sis = page_swap_info(page); blk_qc_t qc; struct gendisk *disk; + unsigned long pflags; VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageUptodate(page), page); + + /* + * Count submission time as memory stall. When the device is congested, + * or the submitting cgroup IO-throttled, submission can be a + * significant part of overall IO time. + */ + psi_memstall_enter(&pflags); + if (frontswap_load(page) == 0) { SetPageUptodate(page); unlock_page(page); @@ -371,7 +381,7 @@ int swap_readpage(struct page *page, bool synchronous) ret = mapping->a_ops->readpage(swap_file, page); if (!ret) count_vm_event(PSWPIN); - return ret; + goto out; } ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); @@ -382,7 +392,7 @@ int swap_readpage(struct page *page, bool synchronous) } count_vm_event(PSWPIN); - return 0; + goto out; } ret = 0; @@ -418,6 +428,7 @@ int swap_readpage(struct page *page, bool synchronous) bio_put(bio); out: + psi_memstall_leave(&pflags); return ret; } diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 89c19c0feadb..04ee1663cdbe 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -168,7 +168,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * @migratetype: Migrate type to set in error recovery. * @flags: The following flags are allowed (they can be combined in * a bit mask) - * SKIP_HWPOISON - ignore hwpoison pages + * MEMORY_OFFLINE - isolate to offline (!allocate) memory + * e.g., skip over PageHWPoison() pages * REPORT_FAILURE - report details about the failure to * isolate the range * @@ -257,7 +258,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, */ static unsigned long __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages) + int flags) { struct page *page; @@ -274,7 +275,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, * simple way to verify that as VM_BUG_ON(), though. */ pfn += 1 << page_order(page); - else if (skip_hwpoisoned_pages && PageHWPoison(page)) + else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) /* A HWPoisoned page cannot be also PageBuddy */ pfn++; else @@ -286,7 +287,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn, /* Caller should ensure that requested range is in a single zone */ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, - bool skip_hwpoisoned_pages) + int isol_flags) { unsigned long pfn, flags; struct page *page; @@ -308,8 +309,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, /* Check all pages are free or marked as ISOLATED */ zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); - pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, - skip_hwpoisoned_pages); + pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags); spin_unlock_irqrestore(&zone->lock, flags); trace_test_pages_isolated(start_pfn, end_pfn, pfn); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 532c29276fce..3d7c01e76efc 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -24,18 +24,27 @@ void pgd_clear_bad(pgd_t *pgd) pgd_clear(pgd); } +#ifndef __PAGETABLE_P4D_FOLDED void p4d_clear_bad(p4d_t *p4d) { p4d_ERROR(*p4d); p4d_clear(p4d); } +#endif +#ifndef __PAGETABLE_PUD_FOLDED void pud_clear_bad(pud_t *pud) { pud_ERROR(*pud); pud_clear(pud); } +#endif +/* + * Note that the pmd variant below can't be stub'ed out just as for p4d/pud + * above. pmd folding is special and typically pmd_* macros refer to upper + * level even when folded + */ void pmd_clear_bad(pmd_t *pmd) { pmd_ERROR(*pmd); diff --git a/mm/rmap.c b/mm/rmap.c index 0c7b2a9400d4..2487c9dd9649 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -251,18 +251,37 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. * - * If dst->anon_vma is NULL this function tries to find and reuse existing - * anon_vma which has no vmas and only one child anon_vma. This prevents - * degradation of anon_vma hierarchy to endless linear chain in case of - * constantly forking task. On the other hand, an anon_vma with more than one - * child isn't reused even if there was no alive vma, thus rmap walker has a - * good chance of avoiding scanning the whole hierarchy when it searches where - * page is mapped. + * anon_vma_clone() is called by __vma_split(), __split_vma(), copy_vma() and + * anon_vma_fork(). The first three want an exact copy of src, while the last + * one, anon_vma_fork(), may try to reuse an existing anon_vma to prevent + * endless growth of anon_vma. Since dst->anon_vma is set to NULL before call, + * we can identify this case by checking (!dst->anon_vma && src->anon_vma). + * + * If (!dst->anon_vma && src->anon_vma) is true, this function tries to find + * and reuse existing anon_vma which has no vmas and only one child anon_vma. + * This prevents degradation of anon_vma hierarchy to endless linear chain in + * case of constantly forking task. On the other hand, an anon_vma with more + * than one child isn't reused even if there was no alive vma, thus rmap + * walker has a good chance of avoiding scanning the whole hierarchy when it + * searches where page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { struct anon_vma_chain *avc, *pavc; struct anon_vma *root = NULL; + struct vm_area_struct *prev = dst->vm_prev, *pprev = src->vm_prev; + + /* + * If parent share anon_vma with its vm_prev, keep this sharing in in + * child. + * + * 1. Parent has vm_prev, which implies we have vm_prev. + * 2. Parent and its vm_prev have the same anon_vma. + */ + if (!dst->anon_vma && src->anon_vma && + pprev && pprev->anon_vma == src->anon_vma) + dst->anon_vma = prev->anon_vma; + list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) { struct anon_vma *anon_vma; @@ -287,8 +306,8 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) * will always reuse it. Root anon_vma is never reused: * it has self-parent reference and at least one child. */ - if (!dst->anon_vma && anon_vma != src->anon_vma && - anon_vma->degree < 2) + if (!dst->anon_vma && src->anon_vma && + anon_vma != src->anon_vma && anon_vma->degree < 2) dst->anon_vma = anon_vma; } if (dst->anon_vma) @@ -458,9 +477,10 @@ void __init anon_vma_init(void) * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * - * Since anon_vma's slab is DESTROY_BY_RCU and we know from page_remove_rmap() - * that the anon_vma pointer from page->mapping is valid if there is a - * mapcount, we can dereference the anon_vma after observing those. + * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from + * page_remove_rmap() that the anon_vma pointer from page->mapping is valid + * if there is a mapcount, we can dereference the anon_vma after observing + * those. */ struct anon_vma *page_get_anon_vma(struct page *page) { @@ -1273,12 +1293,20 @@ static void page_remove_anon_compound_rmap(struct page *page) if (TestClearPageDoubleMap(page)) { /* * Subpages can be mapped with PTEs too. Check how many of - * themi are still mapped. + * them are still mapped. */ for (i = 0, nr = 0; i < HPAGE_PMD_NR; i++) { if (atomic_add_negative(-1, &page[i]._mapcount)) nr++; } + + /* + * Queue the page for deferred split if at least one small + * page of the compound page is unmapped, but at least one + * small page is still mapped. + */ + if (nr && nr < HPAGE_PMD_NR) + deferred_split_huge_page(page); } else { nr = HPAGE_PMD_NR; } @@ -1286,10 +1314,8 @@ static void page_remove_anon_compound_rmap(struct page *page) if (unlikely(PageMlocked(page))) clear_page_mlock(page); - if (nr) { + if (nr) __mod_node_page_state(page_pgdat(page), NR_ANON_MAPPED, -nr); - deferred_split_huge_page(page); - } } /** diff --git a/mm/shmem.c b/mm/shmem.c index 220be9fa2c41..447fd575587c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2022,16 +2022,14 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) shmem_falloc->waitq && vmf->pgoff >= shmem_falloc->start && vmf->pgoff < shmem_falloc->next) { + struct file *fpin; wait_queue_head_t *shmem_falloc_waitq; DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function); ret = VM_FAULT_NOPAGE; - if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) && - !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) { - /* It's polite to up mmap_sem if we can */ - up_read(&vma->vm_mm->mmap_sem); + fpin = maybe_unlock_mmap_for_io(vmf, NULL); + if (fpin) ret = VM_FAULT_RETRY; - } shmem_falloc_waitq = shmem_falloc->waitq; prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait, @@ -2049,6 +2047,9 @@ static vm_fault_t shmem_fault(struct vm_fault *vmf) spin_lock(&inode->i_lock); finish_wait(shmem_falloc_waitq, &shmem_fault_wait); spin_unlock(&inode->i_lock); + + if (fpin) + fput(fpin); return ret; } spin_unlock(&inode->i_lock); @@ -3928,7 +3929,7 @@ out2: static ssize_t shmem_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - int values[] = { + static const int values[] = { SHMEM_HUGE_ALWAYS, SHMEM_HUGE_WITHIN_SIZE, SHMEM_HUGE_ADVISE, diff --git a/mm/slab.c b/mm/slab.c index 66e5d8032bae..f1e1840af533 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1247,9 +1247,10 @@ void __init kmem_cache_init(void) * structures first. Without this, further allocations will bug. */ kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache( - kmalloc_info[INDEX_NODE].name, - kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS, - 0, kmalloc_size(INDEX_NODE)); + kmalloc_info[INDEX_NODE].name[KMALLOC_NORMAL], + kmalloc_info[INDEX_NODE].size, + ARCH_KMALLOC_FLAGS, 0, + kmalloc_info[INDEX_NODE].size); slab_state = PARTIAL_NODE; setup_kmalloc_cache_index_table(); diff --git a/mm/slab.h b/mm/slab.h index 68e455f2b698..3eb29ae75743 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -139,7 +139,7 @@ extern struct kmem_cache *kmem_cache; /* A table of kmalloc cache names and sizes */ extern const struct kmalloc_info_struct { - const char *name; + const char *name[NR_KMALLOC_TYPES]; unsigned int size; } kmalloc_info[]; diff --git a/mm/slab_common.c b/mm/slab_common.c index f9fb27b4c843..8afa188f6e20 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1139,26 +1139,56 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) return kmalloc_caches[kmalloc_type(flags)][index]; } +#ifdef CONFIG_ZONE_DMA +#define INIT_KMALLOC_INFO(__size, __short_size) \ +{ \ + .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ + .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + .name[KMALLOC_DMA] = "dma-kmalloc-" #__short_size, \ + .size = __size, \ +} +#else +#define INIT_KMALLOC_INFO(__size, __short_size) \ +{ \ + .name[KMALLOC_NORMAL] = "kmalloc-" #__short_size, \ + .name[KMALLOC_RECLAIM] = "kmalloc-rcl-" #__short_size, \ + .size = __size, \ +} +#endif + /* * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is * kmalloc-67108864. */ const struct kmalloc_info_struct kmalloc_info[] __initconst = { - {NULL, 0}, {"kmalloc-96", 96}, - {"kmalloc-192", 192}, {"kmalloc-8", 8}, - {"kmalloc-16", 16}, {"kmalloc-32", 32}, - {"kmalloc-64", 64}, {"kmalloc-128", 128}, - {"kmalloc-256", 256}, {"kmalloc-512", 512}, - {"kmalloc-1k", 1024}, {"kmalloc-2k", 2048}, - {"kmalloc-4k", 4096}, {"kmalloc-8k", 8192}, - {"kmalloc-16k", 16384}, {"kmalloc-32k", 32768}, - {"kmalloc-64k", 65536}, {"kmalloc-128k", 131072}, - {"kmalloc-256k", 262144}, {"kmalloc-512k", 524288}, - {"kmalloc-1M", 1048576}, {"kmalloc-2M", 2097152}, - {"kmalloc-4M", 4194304}, {"kmalloc-8M", 8388608}, - {"kmalloc-16M", 16777216}, {"kmalloc-32M", 33554432}, - {"kmalloc-64M", 67108864} + INIT_KMALLOC_INFO(0, 0), + INIT_KMALLOC_INFO(96, 96), + INIT_KMALLOC_INFO(192, 192), + INIT_KMALLOC_INFO(8, 8), + INIT_KMALLOC_INFO(16, 16), + INIT_KMALLOC_INFO(32, 32), + INIT_KMALLOC_INFO(64, 64), + INIT_KMALLOC_INFO(128, 128), + INIT_KMALLOC_INFO(256, 256), + INIT_KMALLOC_INFO(512, 512), + INIT_KMALLOC_INFO(1024, 1k), + INIT_KMALLOC_INFO(2048, 2k), + INIT_KMALLOC_INFO(4096, 4k), + INIT_KMALLOC_INFO(8192, 8k), + INIT_KMALLOC_INFO(16384, 16k), + INIT_KMALLOC_INFO(32768, 32k), + INIT_KMALLOC_INFO(65536, 64k), + INIT_KMALLOC_INFO(131072, 128k), + INIT_KMALLOC_INFO(262144, 256k), + INIT_KMALLOC_INFO(524288, 512k), + INIT_KMALLOC_INFO(1048576, 1M), + INIT_KMALLOC_INFO(2097152, 2M), + INIT_KMALLOC_INFO(4194304, 4M), + INIT_KMALLOC_INFO(8388608, 8M), + INIT_KMALLOC_INFO(16777216, 16M), + INIT_KMALLOC_INFO(33554432, 32M), + INIT_KMALLOC_INFO(67108864, 64M) }; /* @@ -1208,36 +1238,14 @@ void __init setup_kmalloc_cache_index_table(void) } } -static const char * -kmalloc_cache_name(const char *prefix, unsigned int size) -{ - - static const char units[3] = "\0kM"; - int idx = 0; - - while (size >= 1024 && (size % 1024 == 0)) { - size /= 1024; - idx++; - } - - return kasprintf(GFP_NOWAIT, "%s-%u%c", prefix, size, units[idx]); -} - static void __init -new_kmalloc_cache(int idx, int type, slab_flags_t flags) +new_kmalloc_cache(int idx, enum kmalloc_cache_type type, slab_flags_t flags) { - const char *name; - - if (type == KMALLOC_RECLAIM) { + if (type == KMALLOC_RECLAIM) flags |= SLAB_RECLAIM_ACCOUNT; - name = kmalloc_cache_name("kmalloc-rcl", - kmalloc_info[idx].size); - BUG_ON(!name); - } else { - name = kmalloc_info[idx].name; - } - kmalloc_caches[type][idx] = create_kmalloc_cache(name, + kmalloc_caches[type][idx] = create_kmalloc_cache( + kmalloc_info[idx].name[type], kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); } @@ -1249,7 +1257,8 @@ new_kmalloc_cache(int idx, int type, slab_flags_t flags) */ void __init create_kmalloc_caches(slab_flags_t flags) { - int i, type; + int i; + enum kmalloc_cache_type type; for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { @@ -1278,12 +1287,10 @@ void __init create_kmalloc_caches(slab_flags_t flags) struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; if (s) { - unsigned int size = kmalloc_size(i); - const char *n = kmalloc_cache_name("dma-kmalloc", size); - - BUG_ON(!n); kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( - n, size, SLAB_CACHE_DMA | flags, 0, 0); + kmalloc_info[i].name[KMALLOC_DMA], + kmalloc_info[i].size, + SLAB_CACHE_DMA | flags, 0, 0); } } #endif diff --git a/mm/slub.c b/mm/slub.c index b25c807a111f..249e4c8be66a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -93,9 +93,7 @@ * minimal so we rely on the page allocators per cpu caches for * fast frees and allocs. * - * Overloading of page flags that are otherwise used for LRU management. - * - * PageActive The slab is frozen and exempt from list processing. + * page->frozen The slab is frozen and exempt from list processing. * This means that the slab is dedicated to a purpose * such as satisfying allocations for a specific * processor. Objects may be freed in the slab while @@ -111,7 +109,7 @@ * free objects in addition to the regular freelist * that requires the slab lock. * - * PageError Slab requires special handling due to debug + * SLAB_DEBUG_FLAGS Slab requires special handling due to debug * options set. This moves slab handling out of * the fast path and disables lockless freelists. */ @@ -736,6 +734,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, { u8 *fault; u8 *end; + u8 *addr = page_address(page); metadata_access_enable(); fault = memchr_inv(start, value, bytes); @@ -748,8 +747,9 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, end--; slab_bug(s, "%s overwritten", what); - pr_err("INFO: 0x%p-0x%p. First byte 0x%x instead of 0x%x\n", - fault, end - 1, fault[0], value); + pr_err("INFO: 0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n", + fault, end - 1, fault - addr, + fault[0], value); print_trailer(s, page, object); restore_bytes(s, what, value, fault, end); @@ -844,7 +844,8 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) while (end > fault && end[-1] == POISON_INUSE) end--; - slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1); + slab_err(s, page, "Padding overwritten. 0x%p-0x%p @offset=%tu", + fault, end - 1, fault - start); print_section(KERN_ERR, "Padding ", pad, remainder); restore_bytes(s, "slab padding", POISON_INUSE, fault, end); diff --git a/mm/sparse.c b/mm/sparse.c index f6891c1992b1..a04c754ec99c 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -483,7 +483,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) phys_addr_t addr = __pa(MAX_DMA_ADDRESS); WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */ sparsemap_buf = - memblock_alloc_try_nid_raw(size, PAGE_SIZE, + memblock_alloc_exact_nid_raw(size, PAGE_SIZE, addr, MEMBLOCK_ALLOC_ACCESSIBLE, nid); sparsemap_buf_end = sparsemap_buf + size; diff --git a/mm/swap.c b/mm/swap.c index 38c3fa4308e2..5341ae93861f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -373,9 +373,16 @@ static void __lru_cache_activate_page(struct page *page) void mark_page_accessed(struct page *page) { page = compound_head(page); - if (!PageActive(page) && !PageUnevictable(page) && - PageReferenced(page)) { + if (!PageReferenced(page)) { + SetPageReferenced(page); + } else if (PageUnevictable(page)) { + /* + * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, + * this list is never rotated or maintained, so marking an + * evictable page accessed has no effect. + */ + } else if (!PageActive(page)) { /* * If the page is on the LRU, queue it for activation via * activate_page_pvecs. Otherwise, assume the page is on a @@ -389,8 +396,6 @@ void mark_page_accessed(struct page *page) ClearPageReferenced(page); if (page_is_file_cache(page)) workingset_activation(page); - } else if (!PageReferenced(page)) { - SetPageReferenced(page); } if (page_is_idle(page)) clear_page_idle(page); @@ -708,9 +713,10 @@ static void lru_add_drain_per_cpu(struct work_struct *dummy) */ void lru_add_drain_all(void) { + static seqcount_t seqcount = SEQCNT_ZERO(seqcount); static DEFINE_MUTEX(lock); static struct cpumask has_work; - int cpu; + int cpu, seq; /* * Make sure nobody triggers this path before mm_percpu_wq is fully @@ -719,7 +725,19 @@ void lru_add_drain_all(void) if (WARN_ON(!mm_percpu_wq)) return; + seq = raw_read_seqcount_latch(&seqcount); + mutex_lock(&lock); + + /* + * Piggyback on drain started and finished while we waited for lock: + * all pages pended at the time of our enter were drained from vectors. + */ + if (__read_seqcount_retry(&seqcount, seq)) + goto done; + + raw_write_seqcount_latch(&seqcount); + cpumask_clear(&has_work); for_each_online_cpu(cpu) { @@ -740,6 +758,7 @@ void lru_add_drain_all(void) for_each_cpu(cpu, &has_work) flush_work(&per_cpu(lru_add_drain_work, cpu)); +done: mutex_unlock(&lock); } #else diff --git a/mm/swapfile.c b/mm/swapfile.c index dab43523afdd..bb3261d45b6a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2887,6 +2887,13 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; + /* + * Zoned block devices contain zones that have a sequential + * write only restriction. Hence zoned block devices are not + * suitable for swapping. Disallow them here. + */ + if (blk_queue_is_zoned(p->bdev->bd_queue)) + return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c7ae74ce5ff3..1b0d7abad1d4 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -18,6 +18,36 @@ #include <asm/tlbflush.h> #include "internal.h" +static __always_inline +struct vm_area_struct *find_dst_vma(struct mm_struct *dst_mm, + unsigned long dst_start, + unsigned long len) +{ + /* + * Make sure that the dst range is both valid and fully within a + * single existing vma. + */ + struct vm_area_struct *dst_vma; + + dst_vma = find_vma(dst_mm, dst_start); + if (!dst_vma) + return NULL; + + if (dst_start < dst_vma->vm_start || + dst_start + len > dst_vma->vm_end) + return NULL; + + /* + * Check the vma is registered in uffd, this is required to + * enforce the VM_MAYWRITE check done at uffd registration + * time. + */ + if (!dst_vma->vm_userfaultfd_ctx.ctx) + return NULL; + + return dst_vma; +} + static int mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, @@ -60,7 +90,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, /* * The memory barrier inside __SetPageUptodate makes sure that - * preceeding stores to the page contents become visible before + * preceding stores to the page contents become visible before * the set_pte_at() write. */ __SetPageUptodate(page); @@ -184,7 +214,6 @@ static __always_inline ssize_t __mcopy_atomic_hugetlb(struct mm_struct *dst_mm, unsigned long src_addr, dst_addr; long copied; struct page *page; - struct hstate *h; unsigned long vma_hpagesize; pgoff_t idx; u32 hash; @@ -221,20 +250,9 @@ retry: */ if (!dst_vma) { err = -ENOENT; - dst_vma = find_vma(dst_mm, dst_start); + dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) goto out_unlock; - /* - * Check the vma is registered in uffd, this is - * required to enforce the VM_MAYWRITE check done at - * uffd registration time. - */ - if (!dst_vma->vm_userfaultfd_ctx.ctx) - goto out_unlock; - - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) - goto out_unlock; err = -EINVAL; if (vma_hpagesize != vma_kernel_pagesize(dst_vma)) @@ -243,10 +261,6 @@ retry: vm_shared = dst_vma->vm_flags & VM_SHARED; } - if (WARN_ON(dst_addr & (vma_hpagesize - 1) || - (len - copied) & (vma_hpagesize - 1))) - goto out_unlock; - /* * If not shared, ensure the dst_vma has a anon_vma. */ @@ -256,24 +270,21 @@ retry: goto out_unlock; } - h = hstate_vma(dst_vma); - while (src_addr < src_start + len) { pte_t dst_pteval; BUG_ON(dst_addr >= dst_start + len); - VM_BUG_ON(dst_addr & ~huge_page_mask(h)); /* * Serialize via hugetlb_fault_mutex */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx, dst_addr); + hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; - dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); + dst_pte = huge_pte_alloc(dst_mm, dst_addr, vma_hpagesize); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out_unlock; @@ -300,7 +311,8 @@ retry: err = copy_huge_page_from_user(page, (const void __user *)src_addr, - pages_per_huge_page(h), true); + vma_hpagesize / PAGE_SIZE, + true); if (unlikely(err)) { err = -EFAULT; goto out; @@ -475,20 +487,9 @@ retry: * both valid and fully within a single existing vma. */ err = -ENOENT; - dst_vma = find_vma(dst_mm, dst_start); + dst_vma = find_dst_vma(dst_mm, dst_start, len); if (!dst_vma) goto out_unlock; - /* - * Check the vma is registered in uffd, this is required to - * enforce the VM_MAYWRITE check done at uffd registration - * time. - */ - if (!dst_vma->vm_userfaultfd_ctx.ctx) - goto out_unlock; - - if (dst_start < dst_vma->vm_start || - dst_start + len > dst_vma->vm_end) - goto out_unlock; err = -EINVAL; /* diff --git a/mm/util.c b/mm/util.c index 3ad6db9a722e..988d11e6c17c 100644 --- a/mm/util.c +++ b/mm/util.c @@ -271,7 +271,7 @@ void *memdup_user_nul(const void __user *src, size_t len) EXPORT_SYMBOL(memdup_user_nul); void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, - struct vm_area_struct *prev, struct rb_node *rb_parent) + struct vm_area_struct *prev) { struct vm_area_struct *next; @@ -280,18 +280,28 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, next = prev->vm_next; prev->vm_next = vma; } else { + next = mm->mmap; mm->mmap = vma; - if (rb_parent) - next = rb_entry(rb_parent, - struct vm_area_struct, vm_rb); - else - next = NULL; } vma->vm_next = next; if (next) next->vm_prev = vma; } +void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma) +{ + struct vm_area_struct *prev, *next; + + next = vma->vm_next; + prev = vma->vm_prev; + if (prev) + prev->vm_next = next; + else + mm->mmap = next; + if (next) + next->vm_prev = prev; +} + /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a3c70e275f4e..f48f64c8d200 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -331,6 +331,7 @@ EXPORT_SYMBOL(vmalloc_to_pfn); static DEFINE_SPINLOCK(vmap_area_lock); +static DEFINE_SPINLOCK(free_vmap_area_lock); /* Export for kexec only */ LIST_HEAD(vmap_area_list); static LLIST_HEAD(vmap_purge_list); @@ -968,6 +969,19 @@ adjust_va_to_fit_type(struct vmap_area *va, * There are a few exceptions though, as an example it is * a first allocation (early boot up) when we have "one" * big free space that has to be split. + * + * Also we can hit this path in case of regular "vmap" + * allocations, if "this" current CPU was not preloaded. + * See the comment in alloc_vmap_area() why. If so, then + * GFP_NOWAIT is used instead to get an extra object for + * split purpose. That is rare and most time does not + * occur. + * + * What happens if an allocation gets failed. Basically, + * an "overflow" path is triggered to purge lazily freed + * areas to free some memory, then, the "retry" path is + * triggered to repeat one more time. See more details + * in alloc_vmap_area() function. */ lva = kmem_cache_alloc(vmap_area_cachep, GFP_NOWAIT); if (!lva) @@ -1063,9 +1077,9 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, return ERR_PTR(-EBUSY); might_sleep(); + gfp_mask = gfp_mask & GFP_RECLAIM_MASK; - va = kmem_cache_alloc_node(vmap_area_cachep, - gfp_mask & GFP_RECLAIM_MASK, node); + va = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); if (unlikely(!va)) return ERR_PTR(-ENOMEM); @@ -1073,49 +1087,55 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, * Only scan the relevant parts containing pointers to other objects * to avoid false negatives. */ - kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask & GFP_RECLAIM_MASK); + kmemleak_scan_area(&va->rb_node, SIZE_MAX, gfp_mask); retry: /* - * Preload this CPU with one extra vmap_area object to ensure - * that we have it available when fit type of free area is - * NE_FIT_TYPE. + * Preload this CPU with one extra vmap_area object. It is used + * when fit type of free area is NE_FIT_TYPE. Please note, it + * does not guarantee that an allocation occurs on a CPU that + * is preloaded, instead we minimize the case when it is not. + * It can happen because of cpu migration, because there is a + * race until the below spinlock is taken. * * The preload is done in non-atomic context, thus it allows us * to use more permissive allocation masks to be more stable under - * low memory condition and high memory pressure. + * low memory condition and high memory pressure. In rare case, + * if not preloaded, GFP_NOWAIT is used. * - * Even if it fails we do not really care about that. Just proceed - * as it is. "overflow" path will refill the cache we allocate from. + * Set "pva" to NULL here, because of "retry" path. */ - preempt_disable(); - if (!__this_cpu_read(ne_fit_preload_node)) { - preempt_enable(); - pva = kmem_cache_alloc_node(vmap_area_cachep, GFP_KERNEL, node); - preempt_disable(); - - if (__this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) { - if (pva) - kmem_cache_free(vmap_area_cachep, pva); - } - } + pva = NULL; - spin_lock(&vmap_area_lock); - preempt_enable(); + if (!this_cpu_read(ne_fit_preload_node)) + /* + * Even if it fails we do not really care about that. + * Just proceed as it is. If needed "overflow" path + * will refill the cache we allocate from. + */ + pva = kmem_cache_alloc_node(vmap_area_cachep, gfp_mask, node); + + spin_lock(&free_vmap_area_lock); + + if (pva && __this_cpu_cmpxchg(ne_fit_preload_node, NULL, pva)) + kmem_cache_free(vmap_area_cachep, pva); /* * If an allocation fails, the "vend" address is * returned. Therefore trigger the overflow path. */ addr = __alloc_vmap_area(size, align, vstart, vend); + spin_unlock(&free_vmap_area_lock); + if (unlikely(addr == vend)) goto overflow; va->va_start = addr; va->va_end = addr + size; va->vm = NULL; - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); + spin_lock(&vmap_area_lock); + insert_vmap_area(va, &vmap_area_root, &vmap_area_list); spin_unlock(&vmap_area_lock); BUG_ON(!IS_ALIGNED(va->va_start, align)); @@ -1125,7 +1145,6 @@ retry: return va; overflow: - spin_unlock(&vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = 1; @@ -1161,28 +1180,25 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier); -static void __free_vmap_area(struct vmap_area *va) +/* + * Free a region of KVA allocated by alloc_vmap_area + */ +static void free_vmap_area(struct vmap_area *va) { /* * Remove from the busy tree/list. */ + spin_lock(&vmap_area_lock); unlink_va(va, &vmap_area_root); + spin_unlock(&vmap_area_lock); /* - * Merge VA with its neighbors, otherwise just add it. + * Insert/Merge it back to the free tree/list. */ + spin_lock(&free_vmap_area_lock); merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list); -} - -/* - * Free a region of KVA allocated by alloc_vmap_area - */ -static void free_vmap_area(struct vmap_area *va) -{ - spin_lock(&vmap_area_lock); - __free_vmap_area(va); - spin_unlock(&vmap_area_lock); + spin_unlock(&free_vmap_area_lock); } /* @@ -1275,7 +1291,7 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) flush_tlb_kernel_range(start, end); resched_threshold = lazy_max_pages() << 1; - spin_lock(&vmap_area_lock); + spin_lock(&free_vmap_area_lock); llist_for_each_entry_safe(va, n_va, valist, purge_list) { unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT; @@ -1290,9 +1306,9 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) atomic_long_sub(nr, &vmap_lazy_nr); if (atomic_long_read(&vmap_lazy_nr) < resched_threshold) - cond_resched_lock(&vmap_area_lock); + cond_resched_lock(&free_vmap_area_lock); } - spin_unlock(&vmap_area_lock); + spin_unlock(&free_vmap_area_lock); return true; } @@ -2014,15 +2030,21 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages) } EXPORT_SYMBOL_GPL(map_vm_area); -static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, const void *caller) +static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, + struct vmap_area *va, unsigned long flags, const void *caller) { - spin_lock(&vmap_area_lock); vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; +} + +static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, const void *caller) +{ + spin_lock(&vmap_area_lock); + setup_vmalloc_vm_locked(vm, va, flags, caller); spin_unlock(&vmap_area_lock); } @@ -2440,7 +2462,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } area->pages[i] = page; - if (gfpflags_allow_blocking(gfp_mask|highmem_mask)) + if (gfpflags_allow_blocking(gfp_mask)) cond_resched(); } atomic_long_add(area->nr_pages, &nr_vmalloc_pages); @@ -3262,7 +3284,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, goto err_free; } retry: - spin_lock(&vmap_area_lock); + spin_lock(&free_vmap_area_lock); /* start scanning - we scan from the top, begin with the last area */ area = term_area = last_area; @@ -3344,29 +3366,38 @@ retry: va = vas[area]; va->va_start = start; va->va_end = start + size; - - insert_vmap_area(va, &vmap_area_root, &vmap_area_list); } - spin_unlock(&vmap_area_lock); + spin_unlock(&free_vmap_area_lock); /* insert all vm's */ - for (area = 0; area < nr_vms; area++) - setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, + spin_lock(&vmap_area_lock); + for (area = 0; area < nr_vms; area++) { + insert_vmap_area(vas[area], &vmap_area_root, &vmap_area_list); + + setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); + } + spin_unlock(&vmap_area_lock); kfree(vas); return vms; recovery: - /* Remove previously inserted areas. */ + /* + * Remove previously allocated areas. There is no + * need in removing these areas from the busy tree, + * because they are inserted only on the final step + * and when pcpu_get_vm_areas() is success. + */ while (area--) { - __free_vmap_area(vas[area]); + merge_or_add_vmap_area(vas[area], + &free_vmap_area_root, &free_vmap_area_list); vas[area] = NULL; } overflow: - spin_unlock(&vmap_area_lock); + spin_unlock(&free_vmap_area_lock); if (!purged) { purge_vmap_area_lazy(); purged = true; @@ -3417,9 +3448,12 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) + __acquires(&vmap_purge_lock) __acquires(&vmap_area_lock) { + mutex_lock(&vmap_purge_lock); spin_lock(&vmap_area_lock); + return seq_list_start(&vmap_area_list, *pos); } @@ -3429,8 +3463,10 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos) } static void s_stop(struct seq_file *m, void *p) + __releases(&vmap_purge_lock) __releases(&vmap_area_lock) { + mutex_unlock(&vmap_purge_lock); spin_unlock(&vmap_area_lock); } diff --git a/mm/vmscan.c b/mm/vmscan.c index ee4eecc7e1c2..1154b3a2b637 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -775,7 +775,7 @@ static inline int is_page_cache_freeable(struct page *page) return page_count(page) - page_has_private(page) == 1 + page_cache_pins; } -static int may_write_to_inode(struct inode *inode, struct scan_control *sc) +static int may_write_to_inode(struct inode *inode) { if (current->flags & PF_SWAPWRITE) return 1; @@ -823,8 +823,7 @@ typedef enum { * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ -static pageout_t pageout(struct page *page, struct address_space *mapping, - struct scan_control *sc) +static pageout_t pageout(struct page *page, struct address_space *mapping) { /* * If the page is dirty, only perform writeback if that write @@ -860,7 +859,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_inode(mapping->host, sc)) + if (!may_write_to_inode(mapping->host)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -1394,7 +1393,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, * starts and then write it out here. */ try_to_unmap_flush_dirty(); - switch (pageout(page, mapping, sc)) { + switch (pageout(page, mapping)) { case PAGE_KEEP: goto keep_locked; case PAGE_ACTIVATE: @@ -2302,8 +2301,7 @@ enum scan_balance { * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, - struct scan_control *sc, unsigned long *nr, - unsigned long *lru_pages) + struct scan_control *sc, unsigned long *nr) { int swappiness = mem_cgroup_swappiness(memcg); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; @@ -2454,7 +2452,6 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fraction[1] = fp; denominator = ap + fp + 1; out: - *lru_pages = 0; for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; @@ -2549,7 +2546,6 @@ out: BUG(); } - *lru_pages += lruvec_size; nr[lru] = scan; } } @@ -2558,7 +2554,7 @@ out: * This is a basic per-node page freer. Used by both kswapd and direct reclaim. */ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memcg, - struct scan_control *sc, unsigned long *lru_pages) + struct scan_control *sc) { struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg); unsigned long nr[NR_LRU_LISTS]; @@ -2570,7 +2566,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc struct blk_plug plug; bool scan_adjusted; - get_scan_count(lruvec, memcg, sc, nr, lru_pages); + get_scan_count(lruvec, memcg, sc, nr); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); @@ -2758,7 +2754,6 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) do { struct mem_cgroup *root = sc->target_mem_cgroup; - unsigned long node_lru_pages = 0; struct mem_cgroup *memcg; memset(&sc->nr, 0, sizeof(sc->nr)); @@ -2768,7 +2763,6 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) memcg = mem_cgroup_iter(root, NULL, NULL); do { - unsigned long lru_pages; unsigned long reclaimed; unsigned long scanned; @@ -2805,8 +2799,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; - shrink_node_memcg(pgdat, memcg, sc, &lru_pages); - node_lru_pages += lru_pages; + shrink_node_memcg(pgdat, memcg, sc); shrink_slab(sc->gfp_mask, pgdat->node_id, memcg, sc->priority); @@ -3317,15 +3310,16 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, .reclaim_idx = MAX_NR_ZONES - 1, .may_swap = !noswap, }; - unsigned long lru_pages; WARN_ON_ONCE(!current->reclaim_state); sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK); - trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order, - sc.gfp_mask); + trace_mm_vmscan_memcg_softlimit_reclaim_begin( + cgroup_ino(memcg->css.cgroup), + sc.order, + sc.gfp_mask); /* * NOTE: Although we can get the priority field, using it @@ -3334,9 +3328,11 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_node_memcg(pgdat, memcg, &sc, &lru_pages); + shrink_node_memcg(pgdat, memcg, &sc); - trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); + trace_mm_vmscan_memcg_softlimit_reclaim_end( + cgroup_ino(memcg->css.cgroup), + sc.nr_reclaimed); *nr_scanned = sc.nr_scanned; @@ -3375,7 +3371,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; - trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask); + trace_mm_vmscan_memcg_reclaim_begin( + cgroup_ino(memcg->css.cgroup), + 0, sc.gfp_mask); psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); @@ -3385,7 +3383,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); - trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); + trace_mm_vmscan_memcg_reclaim_end( + cgroup_ino(memcg->css.cgroup), + nr_reclaimed); set_task_reclaim_state(current, NULL); return nr_reclaimed; diff --git a/mm/vmstat.c b/mm/vmstat.c index 6afc892a148a..c37e07a73c30 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1084,7 +1084,8 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) +#if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || \ + defined(CONFIG_NUMA) || defined(CONFIG_MEMCG) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", #else @@ -1134,7 +1135,7 @@ const char * const vmstat_text[] = { "numa_other", #endif - /* Node-based counters */ + /* enum node_stat_item counters */ "nr_inactive_anon", "nr_active_anon", "nr_inactive_file", @@ -1172,7 +1173,7 @@ const char * const vmstat_text[] = { "nr_dirty_threshold", "nr_dirty_background_threshold", -#ifdef CONFIG_VM_EVENT_COUNTERS +#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG) /* enum vm_event_item counters */ "pgpgin", "pgpgout", @@ -1291,9 +1292,9 @@ const char * const vmstat_text[] = { "swap_ra", "swap_ra_hit", #endif -#endif /* CONFIG_VM_EVENTS_COUNTERS */ +#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */ }; -#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */ #if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ defined(CONFIG_PROC_FS) @@ -1373,23 +1374,54 @@ static void pagetypeinfo_showfree_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { int order, mtype; + unsigned long nfree[MAX_ORDER][MIGRATE_TYPES]; - for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { - seq_printf(m, "Node %4d, zone %8s, type %12s ", - pgdat->node_id, - zone->name, - migratetype_names[mtype]); - for (order = 0; order < MAX_ORDER; ++order) { + lockdep_assert_held(&zone->lock); + lockdep_assert_irqs_disabled(); + + /* + * MIGRATE_MOVABLE is usually the largest one in large memory + * systems. We skip iterating that list. Instead, we compute it by + * subtracting the total of the rests from free_area->nr_free. + */ + for (order = 0; order < MAX_ORDER; ++order) { + unsigned long nr_total = 0; + struct free_area *area = &(zone->free_area[order]); + + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { unsigned long freecount = 0; - struct free_area *area; struct list_head *curr; - area = &(zone->free_area[order]); - + if (mtype == MIGRATE_MOVABLE) + continue; list_for_each(curr, &area->free_list[mtype]) freecount++; - seq_printf(m, "%6lu ", freecount); + nfree[order][mtype] = freecount; + nr_total += freecount; + } + nfree[order][MIGRATE_MOVABLE] = area->nr_free - nr_total; + + /* + * If we have already iterated more than 64k of list + * entries, we might have hold the zone lock for too long. + * Temporarily release the lock and reschedule before + * continuing so that other lock waiters have a chance + * to run. + */ + if (nr_total > (1 << 16)) { + spin_unlock_irq(&zone->lock); + cond_resched(); + spin_lock_irq(&zone->lock); } + } + + for (mtype = 0; mtype < MIGRATE_TYPES; mtype++) { + seq_printf(m, "Node %4d, zone %8s, type %12s ", + pgdat->node_id, + zone->name, + migratetype_names[mtype]); + for (order = 0; order < MAX_ORDER; ++order) + seq_printf(m, "%6lu ", nfree[order][mtype]); seq_putc(m, '\n'); } } @@ -1547,10 +1579,8 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, if (is_zone_first_populated(pgdat, zone)) { seq_printf(m, "\n per-node stats"); for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) { - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS + - NR_VM_NUMA_STAT_ITEMS], - node_page_state(pgdat, i)); + seq_printf(m, "\n %-12s %lu", node_stat_name(i), + node_page_state(pgdat, i)); } } seq_printf(m, @@ -1583,14 +1613,13 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, } for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", vmstat_text[i], - zone_page_state(zone, i)); + seq_printf(m, "\n %-12s %lu", zone_stat_name(i), + zone_page_state(zone, i)); #ifdef CONFIG_NUMA for (i = 0; i < NR_VM_NUMA_STAT_ITEMS; i++) - seq_printf(m, "\n %-12s %lu", - vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], - zone_numa_state_snapshot(zone, i)); + seq_printf(m, "\n %-12s %lu", numa_stat_name(i), + zone_numa_state_snapshot(zone, i)); #endif seq_printf(m, "\n pagesets"); @@ -1641,31 +1670,23 @@ static const struct seq_operations zoneinfo_op = { .show = zoneinfo_show, }; -enum writeback_stat_item { - NR_DIRTY_THRESHOLD, - NR_DIRTY_BG_THRESHOLD, - NR_VM_WRITEBACK_STAT_ITEMS, -}; +#define NR_VMSTAT_ITEMS (NR_VM_ZONE_STAT_ITEMS + \ + NR_VM_NUMA_STAT_ITEMS + \ + NR_VM_NODE_STAT_ITEMS + \ + NR_VM_WRITEBACK_STAT_ITEMS + \ + (IS_ENABLED(CONFIG_VM_EVENT_COUNTERS) ? \ + NR_VM_EVENT_ITEMS : 0)) static void *vmstat_start(struct seq_file *m, loff_t *pos) { unsigned long *v; - int i, stat_items_size; + int i; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; - stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NUMA_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_NODE_STAT_ITEMS * sizeof(unsigned long) + - NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long); - -#ifdef CONFIG_VM_EVENT_COUNTERS - stat_items_size += sizeof(struct vm_event_state); -#endif - BUILD_BUG_ON(stat_items_size != - ARRAY_SIZE(vmstat_text) * sizeof(unsigned long)); - v = kmalloc(stat_items_size, GFP_KERNEL); + BUILD_BUG_ON(ARRAY_SIZE(vmstat_text) < NR_VMSTAT_ITEMS); + v = kmalloc_array(NR_VMSTAT_ITEMS, sizeof(unsigned long), GFP_KERNEL); m->private = v; if (!v) return ERR_PTR(-ENOMEM); @@ -1698,7 +1719,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos) { (*pos)++; - if (*pos >= ARRAY_SIZE(vmstat_text)) + if (*pos >= NR_VMSTAT_ITEMS) return NULL; return (unsigned long *)m->private + *pos; } @@ -1764,7 +1785,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_zone_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i], val); + __func__, zone_stat_name(i), val); err = -EINVAL; } } @@ -1773,7 +1794,7 @@ int vmstat_refresh(struct ctl_table *table, int write, val = atomic_long_read(&vm_numa_stat[i]); if (val < 0) { pr_warn("%s: %s %ld\n", - __func__, vmstat_text[i + NR_VM_ZONE_STAT_ITEMS], val); + __func__, numa_stat_name(i), val); err = -EINVAL; } } diff --git a/mm/z3fold.c b/mm/z3fold.c index 6d3d3f698ebb..d48d0ec3bcdd 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -41,6 +41,7 @@ #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/spinlock.h> +#include <linux/rwlock.h> #include <linux/zpool.h> #include <linux/magic.h> @@ -90,6 +91,7 @@ struct z3fold_buddy_slots { */ unsigned long slot[BUDDY_MASK + 1]; unsigned long pool; /* back link + flags */ + rwlock_t lock; }; #define HANDLE_FLAG_MASK (0x03) @@ -124,6 +126,7 @@ struct z3fold_header { unsigned short start_middle; unsigned short first_num:2; unsigned short mapped_count:2; + unsigned short foreign_handles:2; }; /** @@ -178,6 +181,19 @@ enum z3fold_page_flags { PAGE_CLAIMED, /* by either reclaim or free */ }; +/* + * handle flags, go under HANDLE_FLAG_MASK + */ +enum z3fold_handle_flags { + HANDLES_ORPHANED = 0, +}; + +/* + * Forward declarations + */ +static struct z3fold_header *__z3fold_alloc(struct z3fold_pool *, size_t, bool); +static void compact_page_work(struct work_struct *w); + /***************** * Helpers *****************/ @@ -191,8 +207,6 @@ static int size_to_chunks(size_t size) #define for_each_unbuddied_list(_iter, _begin) \ for ((_iter) = (_begin); (_iter) < NCHUNKS; (_iter)++) -static void compact_page_work(struct work_struct *w); - static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool, gfp_t gfp) { @@ -204,6 +218,7 @@ static inline struct z3fold_buddy_slots *alloc_slots(struct z3fold_pool *pool, if (slots) { memset(slots->slot, 0, sizeof(slots->slot)); slots->pool = (unsigned long)pool; + rwlock_init(&slots->lock); } return slots; @@ -219,27 +234,108 @@ static inline struct z3fold_buddy_slots *handle_to_slots(unsigned long handle) return (struct z3fold_buddy_slots *)(handle & ~(SLOTS_ALIGN - 1)); } +/* Lock a z3fold page */ +static inline void z3fold_page_lock(struct z3fold_header *zhdr) +{ + spin_lock(&zhdr->page_lock); +} + +/* Try to lock a z3fold page */ +static inline int z3fold_page_trylock(struct z3fold_header *zhdr) +{ + return spin_trylock(&zhdr->page_lock); +} + +/* Unlock a z3fold page */ +static inline void z3fold_page_unlock(struct z3fold_header *zhdr) +{ + spin_unlock(&zhdr->page_lock); +} + + +static inline struct z3fold_header *__get_z3fold_header(unsigned long handle, + bool lock) +{ + struct z3fold_buddy_slots *slots; + struct z3fold_header *zhdr; + int locked = 0; + + if (!(handle & (1 << PAGE_HEADLESS))) { + slots = handle_to_slots(handle); + do { + unsigned long addr; + + read_lock(&slots->lock); + addr = *(unsigned long *)handle; + zhdr = (struct z3fold_header *)(addr & PAGE_MASK); + if (lock) + locked = z3fold_page_trylock(zhdr); + read_unlock(&slots->lock); + if (locked) + break; + cpu_relax(); + } while (lock); + } else { + zhdr = (struct z3fold_header *)(handle & PAGE_MASK); + } + + return zhdr; +} + +/* Returns the z3fold page where a given handle is stored */ +static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h) +{ + return __get_z3fold_header(h, false); +} + +/* return locked z3fold page if it's not headless */ +static inline struct z3fold_header *get_z3fold_header(unsigned long h) +{ + return __get_z3fold_header(h, true); +} + +static inline void put_z3fold_header(struct z3fold_header *zhdr) +{ + struct page *page = virt_to_page(zhdr); + + if (!test_bit(PAGE_HEADLESS, &page->private)) + z3fold_page_unlock(zhdr); +} + static inline void free_handle(unsigned long handle) { struct z3fold_buddy_slots *slots; + struct z3fold_header *zhdr; int i; bool is_free; if (handle & (1 << PAGE_HEADLESS)) return; - WARN_ON(*(unsigned long *)handle == 0); - *(unsigned long *)handle = 0; + if (WARN_ON(*(unsigned long *)handle == 0)) + return; + + zhdr = handle_to_z3fold_header(handle); slots = handle_to_slots(handle); + write_lock(&slots->lock); + *(unsigned long *)handle = 0; + write_unlock(&slots->lock); + if (zhdr->slots == slots) + return; /* simple case, nothing else to do */ + + /* we are freeing a foreign handle if we are here */ + zhdr->foreign_handles--; is_free = true; + read_lock(&slots->lock); for (i = 0; i <= BUDDY_MASK; i++) { if (slots->slot[i]) { is_free = false; break; } } + read_unlock(&slots->lock); - if (is_free) { + if (is_free && test_and_clear_bit(HANDLES_ORPHANED, &slots->pool)) { struct z3fold_pool *pool = slots_to_pool(slots); kmem_cache_free(pool->c_handle, slots); @@ -322,6 +418,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, bool headless, zhdr->first_num = 0; zhdr->start_middle = 0; zhdr->cpu = -1; + zhdr->foreign_handles = 0; zhdr->slots = slots; zhdr->pool = pool; INIT_LIST_HEAD(&zhdr->buddy); @@ -341,24 +438,6 @@ static void free_z3fold_page(struct page *page, bool headless) __free_page(page); } -/* Lock a z3fold page */ -static inline void z3fold_page_lock(struct z3fold_header *zhdr) -{ - spin_lock(&zhdr->page_lock); -} - -/* Try to lock a z3fold page */ -static inline int z3fold_page_trylock(struct z3fold_header *zhdr) -{ - return spin_trylock(&zhdr->page_lock); -} - -/* Unlock a z3fold page */ -static inline void z3fold_page_unlock(struct z3fold_header *zhdr) -{ - spin_unlock(&zhdr->page_lock); -} - /* Helper function to build the index */ static inline int __idx(struct z3fold_header *zhdr, enum buddy bud) { @@ -389,7 +468,9 @@ static unsigned long __encode_handle(struct z3fold_header *zhdr, if (bud == LAST) h |= (zhdr->last_chunks << BUDDY_SHIFT); + write_lock(&slots->lock); slots->slot[idx] = h; + write_unlock(&slots->lock); return (unsigned long)&slots->slot[idx]; } @@ -398,17 +479,6 @@ static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) return __encode_handle(zhdr, zhdr->slots, bud); } -/* Returns the z3fold page where a given handle is stored */ -static inline struct z3fold_header *handle_to_z3fold_header(unsigned long h) -{ - unsigned long addr = h; - - if (!(addr & (1 << PAGE_HEADLESS))) - addr = *(unsigned long *)h; - - return (struct z3fold_header *)(addr & PAGE_MASK); -} - /* only for LAST bud, returns zero otherwise */ static unsigned short handle_to_chunks(unsigned long handle) { @@ -442,6 +512,8 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) { struct page *page = virt_to_page(zhdr); struct z3fold_pool *pool = zhdr_to_pool(zhdr); + bool is_free = true; + int i; WARN_ON(!list_empty(&zhdr->buddy)); set_bit(PAGE_STALE, &page->private); @@ -450,8 +522,25 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) if (!list_empty(&page->lru)) list_del_init(&page->lru); spin_unlock(&pool->lock); + + /* If there are no foreign handles, free the handles array */ + read_lock(&zhdr->slots->lock); + for (i = 0; i <= BUDDY_MASK; i++) { + if (zhdr->slots->slot[i]) { + is_free = false; + break; + } + } + read_unlock(&zhdr->slots->lock); + + if (is_free) + kmem_cache_free(pool->c_handle, zhdr->slots); + else + set_bit(HANDLES_ORPHANED, &zhdr->slots->pool); + if (locked) z3fold_page_unlock(zhdr); + spin_lock(&pool->stale_lock); list_add(&zhdr->buddy, &pool->stale); queue_work(pool->release_wq, &pool->work); @@ -479,6 +568,7 @@ static void release_z3fold_page_locked_list(struct kref *ref) struct z3fold_header *zhdr = container_of(ref, struct z3fold_header, refcount); struct z3fold_pool *pool = zhdr_to_pool(zhdr); + spin_lock(&pool->lock); list_del_init(&zhdr->buddy); spin_unlock(&pool->lock); @@ -559,6 +649,113 @@ static inline void *mchunk_memmove(struct z3fold_header *zhdr, zhdr->middle_chunks << CHUNK_SHIFT); } +static inline bool buddy_single(struct z3fold_header *zhdr) +{ + return !((zhdr->first_chunks && zhdr->middle_chunks) || + (zhdr->first_chunks && zhdr->last_chunks) || + (zhdr->middle_chunks && zhdr->last_chunks)); +} + +static struct z3fold_header *compact_single_buddy(struct z3fold_header *zhdr) +{ + struct z3fold_pool *pool = zhdr_to_pool(zhdr); + void *p = zhdr; + unsigned long old_handle = 0; + size_t sz = 0; + struct z3fold_header *new_zhdr = NULL; + int first_idx = __idx(zhdr, FIRST); + int middle_idx = __idx(zhdr, MIDDLE); + int last_idx = __idx(zhdr, LAST); + + /* + * No need to protect slots here -- all the slots are "local" and + * the page lock is already taken + */ + if (zhdr->first_chunks && zhdr->slots->slot[first_idx]) { + p += ZHDR_SIZE_ALIGNED; + sz = zhdr->first_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[first_idx]; + } else if (zhdr->middle_chunks && zhdr->slots->slot[middle_idx]) { + p += zhdr->start_middle << CHUNK_SHIFT; + sz = zhdr->middle_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[middle_idx]; + } else if (zhdr->last_chunks && zhdr->slots->slot[last_idx]) { + p += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + sz = zhdr->last_chunks << CHUNK_SHIFT; + old_handle = (unsigned long)&zhdr->slots->slot[last_idx]; + } + + if (sz > 0) { + enum buddy new_bud = HEADLESS; + short chunks = size_to_chunks(sz); + void *q; + + new_zhdr = __z3fold_alloc(pool, sz, false); + if (!new_zhdr) + return NULL; + + if (WARN_ON(new_zhdr == zhdr)) + goto out_fail; + + if (new_zhdr->first_chunks == 0) { + if (new_zhdr->middle_chunks != 0 && + chunks >= new_zhdr->start_middle) { + new_bud = LAST; + } else { + new_bud = FIRST; + } + } else if (new_zhdr->last_chunks == 0) { + new_bud = LAST; + } else if (new_zhdr->middle_chunks == 0) { + new_bud = MIDDLE; + } + q = new_zhdr; + switch (new_bud) { + case FIRST: + new_zhdr->first_chunks = chunks; + q += ZHDR_SIZE_ALIGNED; + break; + case MIDDLE: + new_zhdr->middle_chunks = chunks; + new_zhdr->start_middle = + new_zhdr->first_chunks + ZHDR_CHUNKS; + q += new_zhdr->start_middle << CHUNK_SHIFT; + break; + case LAST: + new_zhdr->last_chunks = chunks; + q += PAGE_SIZE - (new_zhdr->last_chunks << CHUNK_SHIFT); + break; + default: + goto out_fail; + } + new_zhdr->foreign_handles++; + memcpy(q, p, sz); + write_lock(&zhdr->slots->lock); + *(unsigned long *)old_handle = (unsigned long)new_zhdr + + __idx(new_zhdr, new_bud); + if (new_bud == LAST) + *(unsigned long *)old_handle |= + (new_zhdr->last_chunks << BUDDY_SHIFT); + write_unlock(&zhdr->slots->lock); + add_to_unbuddied(pool, new_zhdr); + z3fold_page_unlock(new_zhdr); + } + + return new_zhdr; + +out_fail: + if (new_zhdr) { + if (kref_put(&new_zhdr->refcount, release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else { + add_to_unbuddied(pool, new_zhdr); + z3fold_page_unlock(new_zhdr); + } + } + return NULL; + +} + #define BIG_CHUNK_GAP 3 /* Has to be called with lock held */ static int z3fold_compact_page(struct z3fold_header *zhdr) @@ -638,6 +835,15 @@ static void do_compact_page(struct z3fold_header *zhdr, bool locked) return; } + if (!zhdr->foreign_handles && buddy_single(zhdr) && + compact_single_buddy(zhdr)) { + if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) + atomic64_dec(&pool->pages_nr); + else + z3fold_page_unlock(zhdr); + return; + } + z3fold_compact_page(zhdr); add_to_unbuddied(pool, zhdr); z3fold_page_unlock(zhdr); @@ -690,7 +896,8 @@ lookup: spin_unlock(&pool->lock); page = virt_to_page(zhdr); - if (test_bit(NEEDS_COMPACTING, &page->private)) { + if (test_bit(NEEDS_COMPACTING, &page->private) || + test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); zhdr = NULL; put_cpu_ptr(pool->unbuddied); @@ -734,7 +941,8 @@ lookup: spin_unlock(&pool->lock); page = virt_to_page(zhdr); - if (test_bit(NEEDS_COMPACTING, &page->private)) { + if (test_bit(NEEDS_COMPACTING, &page->private) || + test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); zhdr = NULL; if (can_sleep) @@ -1000,7 +1208,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) enum buddy bud; bool page_claimed; - zhdr = handle_to_z3fold_header(handle); + zhdr = get_z3fold_header(handle); page = virt_to_page(zhdr); page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); @@ -1014,6 +1222,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) spin_lock(&pool->lock); list_del(&page->lru); spin_unlock(&pool->lock); + put_z3fold_header(zhdr); free_z3fold_page(page, true); atomic64_dec(&pool->pages_nr); } @@ -1021,7 +1230,6 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) } /* Non-headless case */ - z3fold_page_lock(zhdr); bud = handle_to_buddy(handle); switch (bud) { @@ -1037,11 +1245,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) default: pr_err("%s: unknown bud %d\n", __func__, bud); WARN_ON(1); - z3fold_page_unlock(zhdr); + put_z3fold_header(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); return; } - free_handle(handle); if (kref_put(&zhdr->refcount, release_z3fold_page_locked_list)) { atomic64_dec(&pool->pages_nr); return; @@ -1051,9 +1259,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) z3fold_page_unlock(zhdr); return; } + free_handle(handle); if (unlikely(PageIsolated(page)) || test_and_set_bit(NEEDS_COMPACTING, &page->private)) { - z3fold_page_unlock(zhdr); + put_z3fold_header(zhdr); clear_bit(PAGE_CLAIMED, &page->private); return; } @@ -1063,14 +1272,14 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) spin_unlock(&pool->lock); zhdr->cpu = -1; kref_get(&zhdr->refcount); - do_compact_page(zhdr, true); clear_bit(PAGE_CLAIMED, &page->private); + do_compact_page(zhdr, true); return; } kref_get(&zhdr->refcount); - queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); clear_bit(PAGE_CLAIMED, &page->private); - z3fold_page_unlock(zhdr); + queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + put_z3fold_header(zhdr); } /** @@ -1111,11 +1320,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) */ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) { - int i, ret = 0; + int i, ret = -1; struct z3fold_header *zhdr = NULL; struct page *page = NULL; struct list_head *pos; - struct z3fold_buddy_slots slots; unsigned long first_handle = 0, middle_handle = 0, last_handle = 0; spin_lock(&pool->lock); @@ -1153,6 +1361,12 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) zhdr = NULL; continue; /* can't evict at this point */ } + if (zhdr->foreign_handles) { + clear_bit(PAGE_CLAIMED, &page->private); + z3fold_page_unlock(zhdr); + zhdr = NULL; + continue; /* can't evict such page */ + } kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; @@ -1176,39 +1390,38 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) last_handle = 0; middle_handle = 0; if (zhdr->first_chunks) - first_handle = __encode_handle(zhdr, &slots, - FIRST); + first_handle = encode_handle(zhdr, FIRST); if (zhdr->middle_chunks) - middle_handle = __encode_handle(zhdr, &slots, - MIDDLE); + middle_handle = encode_handle(zhdr, MIDDLE); if (zhdr->last_chunks) - last_handle = __encode_handle(zhdr, &slots, - LAST); + last_handle = encode_handle(zhdr, LAST); /* * it's safe to unlock here because we hold a * reference to this page */ z3fold_page_unlock(zhdr); } else { - first_handle = __encode_handle(zhdr, &slots, HEADLESS); + first_handle = encode_handle(zhdr, HEADLESS); last_handle = middle_handle = 0; } - /* Issue the eviction callback(s) */ if (middle_handle) { ret = pool->ops->evict(pool, middle_handle); if (ret) goto next; + free_handle(middle_handle); } if (first_handle) { ret = pool->ops->evict(pool, first_handle); if (ret) goto next; + free_handle(first_handle); } if (last_handle) { ret = pool->ops->evict(pool, last_handle); if (ret) goto next; + free_handle(last_handle); } next: if (test_bit(PAGE_HEADLESS, &page->private)) { @@ -1264,14 +1477,13 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) void *addr; enum buddy buddy; - zhdr = handle_to_z3fold_header(handle); + zhdr = get_z3fold_header(handle); addr = zhdr; page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) goto out; - z3fold_page_lock(zhdr); buddy = handle_to_buddy(handle); switch (buddy) { case FIRST: @@ -1293,8 +1505,8 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) if (addr) zhdr->mapped_count++; - z3fold_page_unlock(zhdr); out: + put_z3fold_header(zhdr); return addr; } @@ -1309,18 +1521,17 @@ static void z3fold_unmap(struct z3fold_pool *pool, unsigned long handle) struct page *page; enum buddy buddy; - zhdr = handle_to_z3fold_header(handle); + zhdr = get_z3fold_header(handle); page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) return; - z3fold_page_lock(zhdr); buddy = handle_to_buddy(handle); if (buddy == MIDDLE) clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); zhdr->mapped_count--; - z3fold_page_unlock(zhdr); + put_z3fold_header(zhdr); } /** @@ -1352,19 +1563,21 @@ static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode) test_bit(PAGE_STALE, &page->private)) goto out; + if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) + goto out; + pool = zhdr_to_pool(zhdr); + spin_lock(&pool->lock); + if (!list_empty(&zhdr->buddy)) + list_del_init(&zhdr->buddy); + if (!list_empty(&page->lru)) + list_del_init(&page->lru); + spin_unlock(&pool->lock); + + kref_get(&zhdr->refcount); + z3fold_page_unlock(zhdr); + return true; - if (zhdr->mapped_count == 0) { - kref_get(&zhdr->refcount); - if (!list_empty(&zhdr->buddy)) - list_del_init(&zhdr->buddy); - spin_lock(&pool->lock); - if (!list_empty(&page->lru)) - list_del(&page->lru); - spin_unlock(&pool->lock); - z3fold_page_unlock(zhdr); - return true; - } out: z3fold_page_unlock(zhdr); return false; @@ -1387,7 +1600,7 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa if (!z3fold_page_trylock(zhdr)) { return -EAGAIN; } - if (zhdr->mapped_count != 0) { + if (zhdr->mapped_count != 0 || zhdr->foreign_handles != 0) { z3fold_page_unlock(zhdr); return -EBUSY; } diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index b71a39ded930..39e14d5edaf1 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -51,7 +51,7 @@ static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { - return blocking_notifier_chain_cond_register(&rpc_pipefs_notifier_list, nb); + return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index e9995b880f84..a85d719df1f4 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -607,6 +607,20 @@ foreach my $entry (keys %deprecated_apis) { } $deprecated_apis_search = "(?:${deprecated_apis_search})"; +our %deprecated_string_apis = ( + "strcpy" => "stracpy or strscpy", + "strlcpy" => "stracpy or strscpy", + "strncpy" => "stracpy or strscpy - for non-NUL-terminated uses, strncpy dest should be __nonstring", +); + +#Create a search pattern for all these strings apis to speed up a loop below +our $deprecated_string_apis_search = ""; +foreach my $entry (keys %deprecated_string_apis) { + $deprecated_string_apis_search .= '|' if ($deprecated_string_apis_search ne ""); + $deprecated_string_apis_search .= $entry; +} +$deprecated_string_apis_search = "(?:${deprecated_string_apis_search})"; + our $mode_perms_world_writable = qr{ S_IWUGO | S_IWOTH | @@ -5038,8 +5052,9 @@ sub process { $var =~ /[A-Z][a-z]|[a-z][A-Z]/ && #Ignore Page<foo> variants $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ && -#Ignore SI style variants like nS, mV and dB (ie: max_uV, regulator_min_uA_show) - $var !~ /^(?:[a-z_]*?)_?[a-z][A-Z](?:_[a-z_]+)?$/ && +#Ignore SI style variants like nS, mV and dB +#(ie: max_uV, regulator_min_uA_show, RANGE_mA_VALUE) + $var !~ /^(?:[a-z0-9_]*|[A-Z0-9_]*)?_?[a-z][A-Z](?:_[a-z0-9_]+|_[A-Z0-9_]+)?$/ && #Ignore some three character SI units explicitly, like MiB and KHz $var !~ /^(?:[a-z_]*?)_?(?:[KMGT]iB|[KMGT]?Hz)(?:_[a-z_]+)?$/) { while ($var =~ m{($Ident)}g) { @@ -6484,6 +6499,16 @@ sub process { "Deprecated use of '$deprecated_api', prefer '$new_api' instead\n" . $herecurr); } +# check for string deprecated apis + if ($line =~ /\b($deprecated_string_apis_search)\b\s*\(/) { + my $deprecated_string_api = $1; + my $new_api = $deprecated_string_apis{$deprecated_string_api}; + my $msg_level = \&WARN; + $msg_level = \&CHK if ($file); + &{$msg_level}("DEPRECATED_API", + "Deprecated use of '$deprecated_string_api', prefer '$new_api' instead\n" . $herecurr); + } + # check for various structs that are normally const (ops, kgdb, device_tree) # and avoid what seem like struct definitions 'struct foo {' if ($line !~ /\bconst\b/ && diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 5ef59214c555..34085d146fa2 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -26,6 +26,7 @@ my $email = 1; my $email_usename = 1; my $email_maintainer = 1; my $email_reviewer = 1; +my $email_fixes = 1; my $email_list = 1; my $email_moderated_list = 1; my $email_subscriber_list = 0; @@ -249,6 +250,7 @@ if (!GetOptions( 'r!' => \$email_reviewer, 'n!' => \$email_usename, 'l!' => \$email_list, + 'fixes!' => \$email_fixes, 'moderated!' => \$email_moderated_list, 's!' => \$email_subscriber_list, 'multiline!' => \$output_multiline, @@ -503,6 +505,7 @@ sub read_mailmap { ## use the filenames on the command line or find the filenames in the patchfiles my @files = (); +my @fixes = (); # If a patch description includes Fixes: lines my @range = (); my @keyword_tvi = (); my @file_emails = (); @@ -568,6 +571,8 @@ foreach my $file (@ARGV) { my $filename2 = $2; push(@files, $filename1); push(@files, $filename2); + } elsif (m/^Fixes:\s+([0-9a-fA-F]{6,40})/) { + push(@fixes, $1) if ($email_fixes); } elsif (m/^\+\+\+\s+(\S+)/ or m/^---\s+(\S+)/) { my $filename = $1; $filename =~ s@^[^/]*/@@; @@ -598,6 +603,7 @@ foreach my $file (@ARGV) { } @file_emails = uniq(@file_emails); +@fixes = uniq(@fixes); my %email_hash_name; my %email_hash_address; @@ -612,7 +618,6 @@ my %deduplicate_name_hash = (); my %deduplicate_address_hash = (); my @maintainers = get_maintainers(); - if (@maintainers) { @maintainers = merge_email(@maintainers); output(@maintainers); @@ -927,6 +932,10 @@ sub get_maintainers { } } + foreach my $fix (@fixes) { + vcs_add_commit_signers($fix, "blamed_fixes"); + } + foreach my $email (@email_to, @list_to) { $email->[0] = deduplicate_email($email->[0]); } @@ -1031,6 +1040,7 @@ MAINTAINER field selection options: --roles => show roles (status:subsystem, git-signer, list, etc...) --rolestats => show roles and statistics (commits/total_commits, %) --file-emails => add email addresses found in -f file (default: 0 (off)) + --fixes => for patches, add signatures of commits with 'Fixes: <commit>' (default: 1 (on)) --scm => print SCM tree(s) if any --status => print status if any --subsystem => print subsystem name if any @@ -1730,6 +1740,32 @@ sub vcs_is_hg { return $vcs_used == 2; } +sub vcs_add_commit_signers { + return if (!vcs_exists()); + + my ($commit, $desc) = @_; + my $commit_count = 0; + my $commit_authors_ref; + my $commit_signers_ref; + my $stats_ref; + my @commit_authors = (); + my @commit_signers = (); + my $cmd; + + $cmd = $VCS_cmds{"find_commit_signers_cmd"}; + $cmd =~ s/(\$\w+)/$1/eeg; #substitute variables in $cmd + + ($commit_count, $commit_signers_ref, $commit_authors_ref, $stats_ref) = vcs_find_signers($cmd, ""); + @commit_authors = @{$commit_authors_ref} if defined $commit_authors_ref; + @commit_signers = @{$commit_signers_ref} if defined $commit_signers_ref; + + foreach my $signer (@commit_signers) { + $signer = deduplicate_email($signer); + } + + vcs_assign($desc, 1, @commit_signers); +} + sub interactive_get_maintainers { my ($list_ref) = @_; my @list = @$list_ref; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 2c6f7994a0aa..d65f59669f7c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -12,6 +12,7 @@ TARGETS += efivarfs TARGETS += exec TARGETS += filesystems TARGETS += filesystems/binderfs +TARGETS += filesystems/epoll TARGETS += firmware TARGETS += ftrace TARGETS += futex diff --git a/tools/testing/selftests/filesystems/epoll/.gitignore b/tools/testing/selftests/filesystems/epoll/.gitignore new file mode 100644 index 000000000000..9ae8db44ec14 --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/.gitignore @@ -0,0 +1 @@ +epoll_wakeup_test diff --git a/tools/testing/selftests/filesystems/epoll/Makefile b/tools/testing/selftests/filesystems/epoll/Makefile new file mode 100644 index 000000000000..e62f3d4f68da --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +LDFLAGS += -lpthread +TEST_GEN_PROGS := epoll_wakeup_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c new file mode 100644 index 000000000000..37a04dab56f0 --- /dev/null +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -0,0 +1,3074 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <poll.h> +#include <unistd.h> +#include <signal.h> +#include <pthread.h> +#include <sys/epoll.h> +#include <sys/socket.h> +#include "../../kselftest_harness.h" + +struct epoll_mtcontext +{ + int efd[3]; + int sfd[4]; + int count; + + pthread_t main; + pthread_t waiter; +}; + +static void signal_handler(int signum) +{ +} + +static void kill_timeout(struct epoll_mtcontext *ctx) +{ + usleep(1000000); + pthread_kill(ctx->main, SIGUSR1); + pthread_kill(ctx->waiter, SIGUSR1); +} + +static void *waiter_entry1a(void *data) +{ + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry1ap(void *data) +{ + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx->count, 1); + } + + return NULL; +} + +static void *waiter_entry1o(void *data) +{ + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry1op(void *data) +{ + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx->count, 1); + } + + return NULL; +} + +static void *waiter_entry2a(void *data) +{ + struct epoll_event events[2]; + struct epoll_mtcontext *ctx = data; + + if (epoll_wait(ctx->efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx->count, 1); + + return NULL; +} + +static void *waiter_entry2ap(void *data) +{ + struct pollfd pfd; + struct epoll_event events[2]; + struct epoll_mtcontext *ctx = data; + + pfd.fd = ctx->efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx->efd[0], events, 2, 0) > 0) + __sync_fetch_and_add(&ctx->count, 1); + } + + return NULL; +} + +static void *emitter_entry1(void *data) +{ + struct epoll_mtcontext *ctx = data; + + usleep(100000); + write(ctx->sfd[1], "w", 1); + + kill_timeout(ctx); + + return NULL; +} + +static void *emitter_entry2(void *data) +{ + struct epoll_mtcontext *ctx = data; + + usleep(100000); + write(ctx->sfd[1], "w", 1); + write(ctx->sfd[3], "w", 1); + + kill_timeout(ctx); + + return NULL; +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * s0 + */ +TEST(epoll1) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * s0 + */ +TEST(epoll2) +{ + int efd; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, &e, 1, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll3) +{ + int efd; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll4) +{ + int efd; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * s0 + */ +TEST(epoll5) +{ + int efd; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * s0 + */ +TEST(epoll6) +{ + int efd; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 1); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + ASSERT_EQ(poll(&pfd, 1, 0), 0); + ASSERT_EQ(epoll_wait(efd, &e, 1, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ + +TEST(epoll7) +{ + int efd; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll8) +{ + int efd; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd = epoll_create(1); + ASSERT_GE(efd, 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd, EPOLL_CTL_ADD, sfd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 2); + + pfd.fd = efd; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd, events, 2, 0), 0); + + close(efd); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * s0 + */ +TEST(epoll9) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * s0 + */ +TEST(epoll10) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll11) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry2a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll12) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * s0 + */ +TEST(epoll13) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * s0 + */ +TEST(epoll14) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (lt) / \ (lt) + * s0 s2 + */ +TEST(epoll15) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry2ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 2, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (et) / \ (et) + * s0 s2 + */ +TEST(epoll16) +{ + pthread_t emitter; + struct epoll_event events[2]; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[0], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.sfd[2], events), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], events, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll17) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll18) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll19) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll20) +{ + int efd[2]; + int sfd[2]; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll21) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll22) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll23) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 + * | (p) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll24) +{ + int efd[2]; + int sfd[2]; + struct pollfd pfd; + struct epoll_event e; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, sfd), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], &e), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], &e, 1, 0), 0); + + close(efd[0]); + close(efd[1]); + close(sfd[0]); + close(sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll25) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll26) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll27) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll28) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll29) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll30) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll31) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * | (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll32) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 1); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll33) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll34) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll35) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll36) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll37) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll38) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx.count, 2); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll39) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (ew) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll40) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1o, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_or(&ctx.count, 2); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll41) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll42) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll43) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (ew) | | (p) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll44) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (lt) + * s0 + */ +TEST(epoll45) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (lt) + * e1 + * | (et) + * s0 + */ +TEST(epoll46) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (et) + * e1 + * | (lt) + * s0 + */ +TEST(epoll47) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + pfd.fd = ctx.efd[1]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[1], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 t1 + * (p) | | (p) + * | e0 + * \ / (et) + * e1 + * | (et) + * s0 + */ +TEST(epoll48) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, ctx.sfd), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1op, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry1, &ctx), 0); + + if (epoll_wait(ctx.efd[1], &e, 1, -1) > 0) + __sync_fetch_and_or(&ctx.count, 2); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_TRUE((ctx.count == 2) || (ctx.count == 3)); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); +} + +/* + * t0 + * | (ew) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll49) +{ + int efd[3]; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (ew) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll50) +{ + int efd[3]; + int sfd[4]; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 0); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll51) +{ + int efd[3]; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 + * | (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll52) +{ + int efd[3]; + int sfd[4]; + struct pollfd pfd; + struct epoll_event events[2]; + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &sfd[2]), 0); + + efd[0] = epoll_create(1); + ASSERT_GE(efd[0], 0); + + efd[1] = epoll_create(1); + ASSERT_GE(efd[1], 0); + + efd[2] = epoll_create(1); + ASSERT_GE(efd[2], 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[1], EPOLL_CTL_ADD, sfd[0], events), 0); + + events[0].events = EPOLLIN; + ASSERT_EQ(epoll_ctl(efd[2], EPOLL_CTL_ADD, sfd[2], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[1], events), 0); + + events[0].events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(efd[0], EPOLL_CTL_ADD, efd[2], events), 0); + + ASSERT_EQ(write(sfd[1], "w", 1), 1); + ASSERT_EQ(write(sfd[3], "w", 1), 1); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 1); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 2); + + pfd.fd = efd[0]; + pfd.events = POLLIN; + EXPECT_EQ(poll(&pfd, 1, 0), 0); + EXPECT_EQ(epoll_wait(efd[0], events, 2, 0), 0); + + close(efd[0]); + close(efd[1]); + close(efd[2]); + close(sfd[0]); + close(sfd[1]); + close(sfd[2]); + close(sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll53) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (ew) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll54) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1a, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll55) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (ew) \ / (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll56) +{ + pthread_t emitter; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + if (epoll_wait(ctx.efd[0], &e, 1, -1) > 0) + __sync_fetch_and_add(&ctx.count, 1); + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (p) \ / (p) + * e0 + * (lt) / \ (lt) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll57) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + pfd.fd = ctx.efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +/* + * t0 t1 + * (p) \ / (p) + * e0 + * (et) / \ (et) + * e1 e2 + * (lt) | | (lt) + * s0 s2 + */ +TEST(epoll58) +{ + pthread_t emitter; + struct pollfd pfd; + struct epoll_event e; + struct epoll_mtcontext ctx = { 0 }; + + signal(SIGUSR1, signal_handler); + + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[0]), 0); + ASSERT_EQ(socketpair(AF_UNIX, SOCK_STREAM, 0, &ctx.sfd[2]), 0); + + ctx.efd[0] = epoll_create(1); + ASSERT_GE(ctx.efd[0], 0); + + ctx.efd[1] = epoll_create(1); + ASSERT_GE(ctx.efd[1], 0); + + ctx.efd[2] = epoll_create(1); + ASSERT_GE(ctx.efd[2], 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[1], EPOLL_CTL_ADD, ctx.sfd[0], &e), 0); + + e.events = EPOLLIN; + ASSERT_EQ(epoll_ctl(ctx.efd[2], EPOLL_CTL_ADD, ctx.sfd[2], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[1], &e), 0); + + e.events = EPOLLIN | EPOLLET; + ASSERT_EQ(epoll_ctl(ctx.efd[0], EPOLL_CTL_ADD, ctx.efd[2], &e), 0); + + ctx.main = pthread_self(); + ASSERT_EQ(pthread_create(&ctx.waiter, NULL, waiter_entry1ap, &ctx), 0); + ASSERT_EQ(pthread_create(&emitter, NULL, emitter_entry2, &ctx), 0); + + pfd.fd = ctx.efd[0]; + pfd.events = POLLIN; + if (poll(&pfd, 1, -1) > 0) { + if (epoll_wait(ctx.efd[0], &e, 1, 0) > 0) + __sync_fetch_and_add(&ctx.count, 1); + } + + ASSERT_EQ(pthread_join(ctx.waiter, NULL), 0); + EXPECT_EQ(ctx.count, 2); + + if (pthread_tryjoin_np(emitter, NULL) < 0) { + pthread_kill(emitter, SIGUSR1); + pthread_join(emitter, NULL); + } + + close(ctx.efd[0]); + close(ctx.efd[1]); + close(ctx.efd[2]); + close(ctx.sfd[0]); + close(ctx.sfd[1]); + close(ctx.sfd[2]); + close(ctx.sfd[3]); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config index 1c0d76cb5adf..93b90a9b1eeb 100644 --- a/tools/testing/selftests/vm/config +++ b/tools/testing/selftests/vm/config @@ -1,2 +1,3 @@ CONFIG_SYSVIPC=y CONFIG_USERFAULTFD=y +CONFIG_TEST_VMALLOC=m diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index cb3fc09645c4..485cf06ef013 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -71,7 +71,7 @@ int main(int argc, char **argv) flags |= MAP_SHARED; break; case 'H': - flags |= MAP_HUGETLB; + flags |= (MAP_HUGETLB | MAP_ANONYMOUS); break; default: return -1; |