diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-25 15:10:33 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-05-25 15:10:33 -0700 |
commit | 9b62e02e63363f5678d5598ee7372064301587f7 (patch) | |
tree | 1f79f1b1506b579e0721d6a522d90809f5360b47 | |
parent | a0db36ed571397df9a3f507ee19913a74d4b97a5 (diff) | |
parent | 90e823498881fb8a91d83e9a8eed87c8c3ff2176 (diff) |
Merge tag 'mm-hotfixes-stable-2024-05-25-09-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull misc fixes from Andrew Morton:
"16 hotfixes, 11 of which are cc:stable.
A few nilfs2 fixes, the remainder are for MM: a couple of selftests
fixes, various singletons fixing various issues in various parts"
* tag 'mm-hotfixes-stable-2024-05-25-09-13' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
mm/ksm: fix possible UAF of stable_node
mm/memory-failure: fix handling of dissolved but not taken off from buddy pages
mm: /proc/pid/smaps_rollup: avoid skipping vma after getting mmap_lock again
nilfs2: fix potential hang in nilfs_detach_log_writer()
nilfs2: fix unexpected freezing of nilfs_segctor_sync()
nilfs2: fix use-after-free of timer for log writer thread
selftests/mm: fix build warnings on ppc64
arm64: patching: fix handling of execmem addresses
selftests/mm: compaction_test: fix bogus test success and reduce probability of OOM-killer invocation
selftests/mm: compaction_test: fix incorrect write of zero to nr_hugepages
selftests/mm: compaction_test: fix bogus test success on Aarch64
mailmap: update email address for Satya Priya
mm/huge_memory: don't unpoison huge_zero_folio
kasan, fortify: properly rename memintrinsics
lib: add version into /proc/allocinfo output
mm/vmalloc: fix vmalloc which may return null if called with __GFP_NOFAIL
-rw-r--r-- | .mailmap | 2 | ||||
-rw-r--r-- | Documentation/filesystems/proc.rst | 5 | ||||
-rw-r--r-- | arch/arm64/kernel/patching.c | 2 | ||||
-rw-r--r-- | fs/nilfs2/segment.c | 63 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 9 | ||||
-rw-r--r-- | include/linux/fortify-string.h | 22 | ||||
-rw-r--r-- | lib/alloc_tag.c | 47 | ||||
-rw-r--r-- | mm/ksm.c | 3 | ||||
-rw-r--r-- | mm/memory-failure.c | 11 | ||||
-rw-r--r-- | mm/vmalloc.c | 5 | ||||
-rw-r--r-- | tools/testing/selftests/mm/compaction_test.c | 85 | ||||
-rw-r--r-- | tools/testing/selftests/mm/gup_test.c | 1 | ||||
-rw-r--r-- | tools/testing/selftests/mm/uffd-common.h | 1 |
13 files changed, 187 insertions, 69 deletions
@@ -572,7 +572,7 @@ Sarangdhar Joshi <spjoshi@codeaurora.org> Sascha Hauer <s.hauer@pengutronix.de> Sahitya Tummala <quic_stummala@quicinc.com> <stummala@codeaurora.org> Sathishkumar Muruganandam <quic_murugana@quicinc.com> <murugana@codeaurora.org> -Satya Priya <quic_c_skakit@quicinc.com> <skakit@codeaurora.org> +Satya Priya <quic_skakitap@quicinc.com> <quic_c_skakit@quicinc.com> <skakit@codeaurora.org> S.Çağlar Onur <caglar@pardus.org.tr> Sayali Lokhande <quic_sayalil@quicinc.com> <sayalil@codeaurora.org> Sean Christopherson <seanjc@google.com> <sean.j.christopherson@intel.com> diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 4d97258a7954..7c3a565ffbef 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -961,13 +961,14 @@ Provides information about memory allocations at all locations in the code base. Each allocation in the code is identified by its source file, line number, module (if originates from a loadable module) and the function calling the allocation. The number of bytes allocated and number of calls at each -location are reported. +location are reported. The first line indicates the version of the file, the +second line is the header listing fields in the file. Example output. :: - > sort -rn /proc/allocinfo + > tail -n +3 /proc/allocinfo | sort -rn 127664128 31168 mm/page_ext.c:270 func:alloc_page_ext 56373248 4737 mm/slub.c:2259 func:alloc_slab_page 14880768 3633 mm/readahead.c:247 func:page_cache_ra_unbounded diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 255534930368..945df74005c7 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -36,7 +36,7 @@ static void __kprobes *patch_map(void *addr, int fixmap) if (image) page = phys_to_page(__pa_symbol(addr)); - else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + else if (IS_ENABLED(CONFIG_EXECMEM)) page = vmalloc_to_page(addr); else return addr; diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 6be7dd423fbd..60d4f59f7665 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -2118,8 +2118,10 @@ static void nilfs_segctor_start_timer(struct nilfs_sc_info *sci) { spin_lock(&sci->sc_state_lock); if (!(sci->sc_state & NILFS_SEGCTOR_COMMIT)) { - sci->sc_timer.expires = jiffies + sci->sc_interval; - add_timer(&sci->sc_timer); + if (sci->sc_task) { + sci->sc_timer.expires = jiffies + sci->sc_interval; + add_timer(&sci->sc_timer); + } sci->sc_state |= NILFS_SEGCTOR_COMMIT; } spin_unlock(&sci->sc_state_lock); @@ -2166,19 +2168,36 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) struct nilfs_segctor_wait_request wait_req; int err = 0; - spin_lock(&sci->sc_state_lock); init_wait(&wait_req.wq); wait_req.err = 0; atomic_set(&wait_req.done, 0); + init_waitqueue_entry(&wait_req.wq, current); + + /* + * To prevent a race issue where completion notifications from the + * log writer thread are missed, increment the request sequence count + * "sc_seq_request" and insert a wait queue entry using the current + * sequence number into the "sc_wait_request" queue at the same time + * within the lock section of "sc_state_lock". + */ + spin_lock(&sci->sc_state_lock); wait_req.seq = ++sci->sc_seq_request; + add_wait_queue(&sci->sc_wait_request, &wait_req.wq); spin_unlock(&sci->sc_state_lock); - init_waitqueue_entry(&wait_req.wq, current); - add_wait_queue(&sci->sc_wait_request, &wait_req.wq); - set_current_state(TASK_INTERRUPTIBLE); wake_up(&sci->sc_wait_daemon); for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + /* + * Synchronize only while the log writer thread is alive. + * Leave flushing out after the log writer thread exits to + * the cleanup work in nilfs_segctor_destroy(). + */ + if (!sci->sc_task) + break; + if (atomic_read(&wait_req.done)) { err = wait_req.err; break; @@ -2194,7 +2213,7 @@ static int nilfs_segctor_sync(struct nilfs_sc_info *sci) return err; } -static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) +static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err, bool force) { struct nilfs_segctor_wait_request *wrq, *n; unsigned long flags; @@ -2202,7 +2221,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err) spin_lock_irqsave(&sci->sc_wait_request.lock, flags); list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) { if (!atomic_read(&wrq->done) && - nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) { + (force || nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq))) { wrq->err = err; atomic_set(&wrq->done, 1); } @@ -2320,10 +2339,21 @@ int nilfs_construct_dsync_segment(struct super_block *sb, struct inode *inode, */ static void nilfs_segctor_accept(struct nilfs_sc_info *sci) { + bool thread_is_alive; + spin_lock(&sci->sc_state_lock); sci->sc_seq_accepted = sci->sc_seq_request; + thread_is_alive = (bool)sci->sc_task; spin_unlock(&sci->sc_state_lock); - del_timer_sync(&sci->sc_timer); + + /* + * This function does not race with the log writer thread's + * termination. Therefore, deleting sc_timer, which should not be + * done after the log writer thread exits, can be done safely outside + * the area protected by sc_state_lock. + */ + if (thread_is_alive) + del_timer_sync(&sci->sc_timer); } /** @@ -2340,7 +2370,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) if (mode == SC_LSEG_SR) { sci->sc_state &= ~NILFS_SEGCTOR_COMMIT; sci->sc_seq_done = sci->sc_seq_accepted; - nilfs_segctor_wakeup(sci, err); + nilfs_segctor_wakeup(sci, err, false); sci->sc_flush_request = 0; } else { if (mode == SC_FLUSH_FILE) @@ -2349,7 +2379,7 @@ static void nilfs_segctor_notify(struct nilfs_sc_info *sci, int mode, int err) sci->sc_flush_request &= ~FLUSH_DAT_BIT; /* re-enable timer if checkpoint creation was not done */ - if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && + if ((sci->sc_state & NILFS_SEGCTOR_COMMIT) && sci->sc_task && time_before(jiffies, sci->sc_timer.expires)) add_timer(&sci->sc_timer); } @@ -2539,6 +2569,7 @@ static int nilfs_segctor_thread(void *arg) int timeout = 0; sci->sc_timer_task = current; + timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); /* start sync. */ sci->sc_task = current; @@ -2606,6 +2637,7 @@ static int nilfs_segctor_thread(void *arg) end_thread: /* end sync. */ sci->sc_task = NULL; + timer_shutdown_sync(&sci->sc_timer); wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ spin_unlock(&sci->sc_state_lock); return 0; @@ -2669,7 +2701,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb, INIT_LIST_HEAD(&sci->sc_gc_inodes); INIT_LIST_HEAD(&sci->sc_iput_queue); INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func); - timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0); sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT; sci->sc_mjcp_freq = HZ * NILFS_SC_DEFAULT_SR_FREQ; @@ -2723,6 +2754,13 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) || sci->sc_seq_request != sci->sc_seq_done); spin_unlock(&sci->sc_state_lock); + /* + * Forcibly wake up tasks waiting in nilfs_segctor_sync(), which can + * be called from delayed iput() via nilfs_evict_inode() and can race + * with the above log writer thread termination. + */ + nilfs_segctor_wakeup(sci, 0, true); + if (flush_work(&sci->sc_iput_work)) flag = true; @@ -2748,7 +2786,6 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci) down_write(&nilfs->ns_segctor_sem); - timer_shutdown_sync(&sci->sc_timer); kfree(sci); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e5a5f015ff03..f8d35f993fe5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -970,12 +970,17 @@ static int show_smaps_rollup(struct seq_file *m, void *v) break; /* Case 1 and 2 above */ - if (vma->vm_start >= last_vma_end) + if (vma->vm_start >= last_vma_end) { + smap_gather_stats(vma, &mss, 0); + last_vma_end = vma->vm_end; continue; + } /* Case 4 above */ - if (vma->vm_end > last_vma_end) + if (vma->vm_end > last_vma_end) { smap_gather_stats(vma, &mss, last_vma_end); + last_vma_end = vma->vm_end; + } } } for_each_vma(vmi, vma); diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index d658ae729a02..7e0f340bf363 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -75,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning(" __ret; \ }) -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) +#if defined(__SANITIZE_ADDRESS__) + +#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); +#elif defined(CONFIG_KASAN_GENERIC) +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy); +#else /* CONFIG_KASAN_SW_TAGS */ +extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset); +extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove); +extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy); +#endif + extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); -extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy); -extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove); -extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset); extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat); extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy); extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen); extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat); extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy); + #else #if defined(__SANITIZE_MEMORY__) @@ -110,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #define __underlying_strlen __builtin_strlen #define __underlying_strncat __builtin_strncat #define __underlying_strncpy __builtin_strncpy + #endif /** diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 531dbe2f5456..11ed973ac359 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -16,47 +16,60 @@ EXPORT_SYMBOL(_shared_alloc_tag); DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, mem_alloc_profiling_key); +struct allocinfo_private { + struct codetag_iterator iter; + bool print_header; +}; + static void *allocinfo_start(struct seq_file *m, loff_t *pos) { - struct codetag_iterator *iter; + struct allocinfo_private *priv; struct codetag *ct; loff_t node = *pos; - iter = kzalloc(sizeof(*iter), GFP_KERNEL); - m->private = iter; - if (!iter) + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + m->private = priv; + if (!priv) return NULL; + priv->print_header = (node == 0); codetag_lock_module_list(alloc_tag_cttype, true); - *iter = codetag_get_ct_iter(alloc_tag_cttype); - while ((ct = codetag_next_ct(iter)) != NULL && node) + priv->iter = codetag_get_ct_iter(alloc_tag_cttype); + while ((ct = codetag_next_ct(&priv->iter)) != NULL && node) node--; - return ct ? iter : NULL; + return ct ? priv : NULL; } static void *allocinfo_next(struct seq_file *m, void *arg, loff_t *pos) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; - struct codetag *ct = codetag_next_ct(iter); + struct allocinfo_private *priv = (struct allocinfo_private *)arg; + struct codetag *ct = codetag_next_ct(&priv->iter); (*pos)++; if (!ct) return NULL; - return iter; + return priv; } static void allocinfo_stop(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)m->private; + struct allocinfo_private *priv = (struct allocinfo_private *)m->private; - if (iter) { + if (priv) { codetag_lock_module_list(alloc_tag_cttype, false); - kfree(iter); + kfree(priv); } } +static void print_allocinfo_header(struct seq_buf *buf) +{ + /* Output format version, so we can change it. */ + seq_buf_printf(buf, "allocinfo - version: 1.0\n"); + seq_buf_printf(buf, "# <size> <calls> <tag info>\n"); +} + static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) { struct alloc_tag *tag = ct_to_alloc_tag(ct); @@ -71,13 +84,17 @@ static void alloc_tag_to_text(struct seq_buf *out, struct codetag *ct) static int allocinfo_show(struct seq_file *m, void *arg) { - struct codetag_iterator *iter = (struct codetag_iterator *)arg; + struct allocinfo_private *priv = (struct allocinfo_private *)arg; char *bufp; size_t n = seq_get_buf(m, &bufp); struct seq_buf buf; seq_buf_init(&buf, bufp, n); - alloc_tag_to_text(&buf, iter->ct); + if (priv->print_header) { + print_allocinfo_header(&buf); + priv->print_header = false; + } + alloc_tag_to_text(&buf, priv->iter.ct); seq_commit(m, seq_buf_used(&buf)); return 0; } @@ -2153,7 +2153,6 @@ again: INIT_HLIST_HEAD(&stable_node_dup->hlist); stable_node_dup->kpfn = kpfn; - folio_set_stable_node(kfolio, stable_node_dup); stable_node_dup->rmap_hlist_len = 0; DO_NUMA(stable_node_dup->nid = nid); if (!need_chain) { @@ -2172,6 +2171,8 @@ again: stable_node_chain_add_dup(stable_node_dup, stable_node); } + folio_set_stable_node(kfolio, stable_node_dup); + return stable_node_dup; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 16ada4fb02b7..d3c830e817e3 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1221,7 +1221,7 @@ static int me_huge_page(struct page_state *ps, struct page *p) * subpages. */ folio_put(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2091,7 +2091,7 @@ retry: */ if (res == 0) { folio_unlock(folio); - if (__page_handle_poison(p) >= 0) { + if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { @@ -2546,6 +2546,13 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } + if (is_huge_zero_folio(folio)) { + unpoison_pr_info("Unpoison: huge zero page is not supported %#lx\n", + pfn, &unpoison_rs); + ret = -EOPNOTSUPP; + goto unlock_mutex; + } + if (!PageHWPoison(p)) { unpoison_pr_info("Unpoison: Page was already unpoisoned %#lx\n", pfn, &unpoison_rs); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 6641be0ca80b..5d3aa2dc88a8 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3498,7 +3498,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, { unsigned int nr_allocated = 0; gfp_t alloc_gfp = gfp; - bool nofail = false; + bool nofail = gfp & __GFP_NOFAIL; struct page *page; int i; @@ -3555,12 +3555,11 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * and compaction etc. */ alloc_gfp &= ~__GFP_NOFAIL; - nofail = true; } /* High-order pages or fallback path if "bulk" fails. */ while (nr_allocated < nr_pages) { - if (fatal_signal_pending(current)) + if (!nofail && fatal_signal_pending(current)) break; if (nid == NUMA_NO_NODE) diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 4f42eb7d7636..e140558e6f53 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -82,12 +82,16 @@ int prereq(void) return -1; } -int check_compaction(unsigned long mem_free, unsigned int hugepage_size) +int check_compaction(unsigned long mem_free, unsigned long hugepage_size, + unsigned long initial_nr_hugepages) { + unsigned long nr_hugepages_ul; int fd, ret = -1; int compaction_index = 0; - char initial_nr_hugepages[10] = {0}; - char nr_hugepages[10] = {0}; + char nr_hugepages[20] = {0}; + char init_nr_hugepages[20] = {0}; + + sprintf(init_nr_hugepages, "%lu", initial_nr_hugepages); /* We want to test with 80% of available memory. Else, OOM killer comes in to play */ @@ -101,21 +105,6 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) goto out; } - if (read(fd, initial_nr_hugepages, sizeof(initial_nr_hugepages)) <= 0) { - ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - /* Start with the initial condition of 0 huge pages*/ - if (write(fd, "0", sizeof(char)) != sizeof(char)) { - ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); - goto close_fd; - } - - lseek(fd, 0, SEEK_SET); - /* Request a large number of huge pages. The Kernel will allocate as much as it can */ if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { @@ -134,22 +123,27 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) /* We should have been able to request at least 1/3 rd of the memory in huge pages */ - compaction_index = mem_free/(atoi(nr_hugepages) * hugepage_size); + nr_hugepages_ul = strtoul(nr_hugepages, NULL, 10); + if (!nr_hugepages_ul) { + ksft_print_msg("ERROR: No memory is available as huge pages\n"); + goto close_fd; + } + compaction_index = mem_free/(nr_hugepages_ul * hugepage_size); lseek(fd, 0, SEEK_SET); - if (write(fd, initial_nr_hugepages, strlen(initial_nr_hugepages)) - != strlen(initial_nr_hugepages)) { + if (write(fd, init_nr_hugepages, strlen(init_nr_hugepages)) + != strlen(init_nr_hugepages)) { ksft_print_msg("Failed to write value to /proc/sys/vm/nr_hugepages: %s\n", strerror(errno)); goto close_fd; } - ksft_print_msg("Number of huge pages allocated = %d\n", - atoi(nr_hugepages)); + ksft_print_msg("Number of huge pages allocated = %lu\n", + nr_hugepages_ul); if (compaction_index > 3) { - ksft_print_msg("ERROR: Less that 1/%d of memory is available\n" + ksft_print_msg("ERROR: Less than 1/%d of memory is available\n" "as huge pages\n", compaction_index); goto close_fd; } @@ -163,6 +157,41 @@ int check_compaction(unsigned long mem_free, unsigned int hugepage_size) return ret; } +int set_zero_hugepages(unsigned long *initial_nr_hugepages) +{ + int fd, ret = -1; + char nr_hugepages[20] = {0}; + + fd = open("/proc/sys/vm/nr_hugepages", O_RDWR | O_NONBLOCK); + if (fd < 0) { + ksft_print_msg("Failed to open /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto out; + } + if (read(fd, nr_hugepages, sizeof(nr_hugepages)) <= 0) { + ksft_print_msg("Failed to read from /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + lseek(fd, 0, SEEK_SET); + + /* Start with the initial condition of 0 huge pages */ + if (write(fd, "0", sizeof(char)) != sizeof(char)) { + ksft_print_msg("Failed to write 0 to /proc/sys/vm/nr_hugepages: %s\n", + strerror(errno)); + goto close_fd; + } + + *initial_nr_hugepages = strtoul(nr_hugepages, NULL, 10); + ret = 0; + + close_fd: + close(fd); + + out: + return ret; +} int main(int argc, char **argv) { @@ -173,6 +202,7 @@ int main(int argc, char **argv) unsigned long mem_free = 0; unsigned long hugepage_size = 0; long mem_fragmentable_MB = 0; + unsigned long initial_nr_hugepages; ksft_print_header(); @@ -181,6 +211,10 @@ int main(int argc, char **argv) ksft_set_plan(1); + /* Start the test without hugepages reducing mem_free */ + if (set_zero_hugepages(&initial_nr_hugepages)) + ksft_exit_fail(); + lim.rlim_cur = RLIM_INFINITY; lim.rlim_max = RLIM_INFINITY; if (setrlimit(RLIMIT_MEMLOCK, &lim)) @@ -224,7 +258,8 @@ int main(int argc, char **argv) entry = entry->next; } - if (check_compaction(mem_free, hugepage_size) == 0) + if (check_compaction(mem_free, hugepage_size, + initial_nr_hugepages) == 0) ksft_exit_pass(); ksft_exit_fail(); diff --git a/tools/testing/selftests/mm/gup_test.c b/tools/testing/selftests/mm/gup_test.c index bd335cf9bc0e..bdeaac67ff9a 100644 --- a/tools/testing/selftests/mm/gup_test.c +++ b/tools/testing/selftests/mm/gup_test.c @@ -1,3 +1,4 @@ +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <fcntl.h> #include <errno.h> #include <stdio.h> diff --git a/tools/testing/selftests/mm/uffd-common.h b/tools/testing/selftests/mm/uffd-common.h index cc5629c3d2aa..a70ae10b5f62 100644 --- a/tools/testing/selftests/mm/uffd-common.h +++ b/tools/testing/selftests/mm/uffd-common.h @@ -8,6 +8,7 @@ #define __UFFD_COMMON_H__ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ // Use ll64 #include <stdio.h> #include <errno.h> #include <unistd.h> |