September 2024 - Linux-stable-mirror

[merged mm-nonmm-stable] scripts-gdb-add-iteration-function-for-rbtree.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: scripts/gdb: add iteration function for rbtree has been removed from the -mm tree. Its filename was scripts-gdb-add-iteration-function-for-rbtree.patch This patch was dropped because it was merged into the mm-nonmm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kuan-Ying Lee <kuan-ying.lee(a)canonical.com> Subject: scripts/gdb: add iteration function for rbtree Date: Tue, 23 Jul 2024 14:48:58 +0800 Add inorder iteration function for rbtree usage. This is a preparation patch for the next patch to fix the gdb mounts issue. Link: https://lkml.kernel.org/r/20240723064902.124154-3-kuan-ying.lee@canonical.c… Fixes: 2eea9ce4310d ("mounts: keep list of mounts in an rbtree") Signed-off-by: Kuan-Ying Lee <kuan-ying.lee(a)canonical.com> Cc: Jan Kiszka <jan.kiszka(a)siemens.com> Cc: Kieran Bingham <kbingham(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- scripts/gdb/linux/rbtree.py | 12 ++++++++++++ 1 file changed, 12 insertions(+) --- a/scripts/gdb/linux/rbtree.py~scripts-gdb-add-iteration-function-for-rbtree +++ a/scripts/gdb/linux/rbtree.py @@ -9,6 +9,18 @@ from linux import utils rb_root_type = utils.CachedType("struct rb_root") rb_node_type = utils.CachedType("struct rb_node") +def rb_inorder_for_each(root): + def inorder(node): + if node: + yield from inorder(node['rb_left']) + yield node + yield from inorder(node['rb_right']) + + yield from inorder(root['rb_node']) + +def rb_inorder_for_each_entry(root, gdbtype, member): + for node in rb_inorder_for_each(root): + yield utils.container_of(node, gdbtype, member) def rb_first(root): if root.type == rb_root_type.get_type(): _ Patches currently in -mm which might be from kuan-ying.lee(a)canonical.com are

3 months, 3 weeks

1
0
0 0

[merged mm-nonmm-stable] scripts-gdb-fix-timerlist-parsing-issue.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: scripts/gdb: fix timerlist parsing issue has been removed from the -mm tree. Its filename was scripts-gdb-fix-timerlist-parsing-issue.patch This patch was dropped because it was merged into the mm-nonmm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Kuan-Ying Lee <kuan-ying.lee(a)canonical.com> Subject: scripts/gdb: fix timerlist parsing issue Date: Tue, 23 Jul 2024 14:48:57 +0800 Patch series "Fix some GDB command error and add some GDB commands", v3. Fix some GDB command errors and add some useful GDB commands. This patch (of 5): Commit 7988e5ae2be7 ("tick: Split nohz and highres features from nohz_mode") and commit 7988e5ae2be7 ("tick: Split nohz and highres features from nohz_mode") move 'tick_stopped' and 'nohz_mode' to flags field which will break the gdb lx-mounts command: (gdb) lx-timerlist Python Exception <class 'gdb.error'>: There is no member named nohz_mode. Error occurred in Python: There is no member named nohz_mode. (gdb) lx-timerlist Python Exception <class 'gdb.error'>: There is no member named tick_stopped. Error occurred in Python: There is no member named tick_stopped. We move 'tick_stopped' and 'nohz_mode' to flags field instead. Link: https://lkml.kernel.org/r/20240723064902.124154-1-kuan-ying.lee@canonical.c… Link: https://lkml.kernel.org/r/20240723064902.124154-2-kuan-ying.lee@canonical.c… Fixes: a478ffb2ae23 ("tick: Move individual bit features to debuggable mask accesses") Fixes: 7988e5ae2be7 ("tick: Split nohz and highres features from nohz_mode") Signed-off-by: Kuan-Ying Lee <kuan-ying.lee(a)canonical.com> Cc: Jan Kiszka <jan.kiszka(a)siemens.com> Cc: Kieran Bingham <kbingham(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- scripts/gdb/linux/timerlist.py | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) --- a/scripts/gdb/linux/timerlist.py~scripts-gdb-fix-timerlist-parsing-issue +++ a/scripts/gdb/linux/timerlist.py @@ -87,21 +87,22 @@ def print_cpu(hrtimer_bases, cpu, max_cl text += "\n" if constants.LX_CONFIG_TICK_ONESHOT: - fmts = [(" .{} : {}", 'nohz_mode'), - (" .{} : {} nsecs", 'last_tick'), - (" .{} : {}", 'tick_stopped'), - (" .{} : {}", 'idle_jiffies'), - (" .{} : {}", 'idle_calls'), - (" .{} : {}", 'idle_sleeps'), - (" .{} : {} nsecs", 'idle_entrytime'), - (" .{} : {} nsecs", 'idle_waketime'), - (" .{} : {} nsecs", 'idle_exittime'), - (" .{} : {} nsecs", 'idle_sleeptime'), - (" .{}: {} nsecs", 'iowait_sleeptime'), - (" .{} : {}", 'last_jiffies'), - (" .{} : {}", 'next_timer'), - (" .{} : {} nsecs", 'idle_expires')] - text += "\n".join([s.format(f, ts[f]) for s, f in fmts]) + TS_FLAG_STOPPED = 1 << 1 + TS_FLAG_NOHZ = 1 << 4 + text += f" .{'nohz':15s}: {int(bool(ts['flags'] & TS_FLAG_NOHZ))}\n" + text += f" .{'last_tick':15s}: {ts['last_tick']}\n" + text += f" .{'tick_stopped':15s}: {int(bool(ts['flags'] & TS_FLAG_STOPPED))}\n" + text += f" .{'idle_jiffies':15s}: {ts['idle_jiffies']}\n" + text += f" .{'idle_calls':15s}: {ts['idle_calls']}\n" + text += f" .{'idle_sleeps':15s}: {ts['idle_sleeps']}\n" + text += f" .{'idle_entrytime':15s}: {ts['idle_entrytime']} nsecs\n" + text += f" .{'idle_waketime':15s}: {ts['idle_waketime']} nsecs\n" + text += f" .{'idle_exittime':15s}: {ts['idle_exittime']} nsecs\n" + text += f" .{'idle_sleeptime':15s}: {ts['idle_sleeptime']} nsecs\n" + text += f" .{'iowait_sleeptime':15s}: {ts['iowait_sleeptime']} nsecs\n" + text += f" .{'last_jiffies':15s}: {ts['last_jiffies']}\n" + text += f" .{'next_timer':15s}: {ts['next_timer']}\n" + text += f" .{'idle_expires':15s}: {ts['idle_expires']} nsecs\n" text += "\njiffies: {}\n".format(jiffies) text += "\n" _ Patches currently in -mm which might be from kuan-ying.lee(a)canonical.com are

3 months, 3 weeks

1
0
0 0

[merged mm-nonmm-stable] ocfs2-fix-the-la-space-leak-when-unmounting-an-ocfs2-volume.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: ocfs2: fix the la space leak when unmounting an ocfs2 volume has been removed from the -mm tree. Its filename was ocfs2-fix-the-la-space-leak-when-unmounting-an-ocfs2-volume.patch This patch was dropped because it was merged into the mm-nonmm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Heming Zhao <heming.zhao(a)suse.com> Subject: ocfs2: fix the la space leak when unmounting an ocfs2 volume Date: Fri, 19 Jul 2024 19:43:10 +0800 This bug has existed since the initial OCFS2 code. The code logic in ocfs2_sync_local_to_main() is wrong, as it ignores the last contiguous free bits, which causes an OCFS2 volume to lose the last free clusters of LA window on each umount command. Link: https://lkml.kernel.org/r/20240719114310.14245-1-heming.zhao@suse.com Signed-off-by: Heming Zhao <heming.zhao(a)suse.com> Reviewed-by: Su Yue <glass.su(a)suse.com> Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Jun Piao <piaojun(a)huawei.com> Cc: Heming Zhao <heming.zhao(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- fs/ocfs2/localalloc.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) --- a/fs/ocfs2/localalloc.c~ocfs2-fix-the-la-space-leak-when-unmounting-an-ocfs2-volume +++ a/fs/ocfs2/localalloc.c @@ -1002,6 +1002,25 @@ static int ocfs2_sync_local_to_main(stru start = bit_off + 1; } + /* clear the contiguous bits until the end boundary */ + if (count) { + blkno = la_start_blk + + ocfs2_clusters_to_blocks(osb->sb, + start - count); + + trace_ocfs2_sync_local_to_main_free( + count, start - count, + (unsigned long long)la_start_blk, + (unsigned long long)blkno); + + status = ocfs2_release_clusters(handle, + main_bm_inode, + main_bm_bh, blkno, + count); + if (status < 0) + mlog_errno(status); + } + bail: if (status) mlog_errno(status); _ Patches currently in -mm which might be from heming.zhao(a)suse.com are

3 months, 3 weeks

1
0
0 0

[merged mm-stable] mm-hugetlb_vmemmap-batch-hvo-work-when-demoting.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/hugetlb_vmemmap: batch HVO work when demoting has been removed from the -mm tree. Its filename was mm-hugetlb_vmemmap-batch-hvo-work-when-demoting.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/hugetlb_vmemmap: batch HVO work when demoting Date: Mon, 12 Aug 2024 16:48:23 -0600 Batch the HVO work, including de-HVO of the source and HVO of the destination hugeTLB folios, to speed up demotion. After commit bd225530a4c7 ("mm/hugetlb_vmemmap: fix race with speculative PFN walkers"), each request of HVO or de-HVO, batched or not, invokes synchronize_rcu() once. For example, when not batched, demoting one 1GB hugeTLB folio to 512 2MB hugeTLB folios invokes synchronize_rcu() 513 times (1 de-HVO plus 512 HVO requests), whereas when batched, only twice (1 de-HVO plus 1 HVO request). And the performance difference between the two cases is significant, e.g., echo 2048kB >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote_size time echo 100 >/sys/kernel/mm/hugepages/hugepages-1048576kB/demote Before this patch: real 8m58.158s user 0m0.009s sys 0m5.900s After this patch: real 0m0.900s user 0m0.000s sys 0m0.851s Note that this patch changes the behavior of the `demote` interface when de-HVO fails. Before, the interface aborts immediately upon failure; now, it tries to finish an entire batch, meaning it can make extra progress if the rest of the batch contains folios that do not need to de-HVO. Link: https://lkml.kernel.org/r/20240812224823.3914837-1-yuzhao@google.com Fixes: bd225530a4c7 ("mm/hugetlb_vmemmap: fix race with speculative PFN walkers") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reviewed-by: Muchun Song <muchun.song(a)linux.dev> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 156 ++++++++++++++++++++++++++++--------------------- 1 file changed, 92 insertions(+), 64 deletions(-) --- a/mm/hugetlb.c~mm-hugetlb_vmemmap-batch-hvo-work-when-demoting +++ a/mm/hugetlb.c @@ -3921,101 +3921,125 @@ out: return 0; } -static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio) +static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, + struct list_head *src_list) { - int i, nid = folio_nid(folio); - struct hstate *target_hstate; - struct page *subpage; - struct folio *inner_folio; - int rc = 0; + long rc; + struct folio *folio, *next; + LIST_HEAD(dst_list); + LIST_HEAD(ret_list); - target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order); - - remove_hugetlb_folio(h, folio, false); - spin_unlock_irq(&hugetlb_lock); - - /* - * If vmemmap already existed for folio, the remove routine above would - * have cleared the hugetlb folio flag. Hence the folio is technically - * no longer a hugetlb folio. hugetlb_vmemmap_restore_folio can only be - * passed hugetlb folios and will BUG otherwise. - */ - if (folio_test_hugetlb(folio)) { - rc = hugetlb_vmemmap_restore_folio(h, folio); - if (rc) { - /* Allocation of vmemmmap failed, we can not demote folio */ - spin_lock_irq(&hugetlb_lock); - add_hugetlb_folio(h, folio, false); - return rc; - } - } - - /* - * Use destroy_compound_hugetlb_folio_for_demote for all huge page - * sizes as it will not ref count folios. - */ - destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h)); + rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list); + list_splice_init(&ret_list, src_list); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * - * Note that we already hold h->resize_lock. To prevent deadlock, + * Note that we already hold src->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ - mutex_lock(&target_hstate->resize_lock); - for (i = 0; i < pages_per_huge_page(h); - i += pages_per_huge_page(target_hstate)) { - subpage = folio_page(folio, i); - inner_folio = page_folio(subpage); - if (hstate_is_gigantic(target_hstate)) - prep_compound_gigantic_folio_for_demote(inner_folio, - target_hstate->order); - else - prep_compound_page(subpage, target_hstate->order); - folio_change_private(inner_folio, NULL); - prep_new_hugetlb_folio(target_hstate, inner_folio, nid); - free_huge_folio(inner_folio); + mutex_lock(&dst->resize_lock); + + list_for_each_entry_safe(folio, next, src_list, lru) { + int i; + + if (folio_test_hugetlb_vmemmap_optimized(folio)) + continue; + + list_del(&folio->lru); + /* + * Use destroy_compound_hugetlb_folio_for_demote for all huge page + * sizes as it will not ref count folios. + */ + destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(src)); + + for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { + struct page *page = folio_page(folio, i); + + if (hstate_is_gigantic(dst)) + prep_compound_gigantic_folio_for_demote(page_folio(page), + dst->order); + else + prep_compound_page(page, dst->order); + set_page_private(page, 0); + + init_new_hugetlb_folio(dst, page_folio(page)); + list_add(&page->lru, &dst_list); + } } - mutex_unlock(&target_hstate->resize_lock); - spin_lock_irq(&hugetlb_lock); + prep_and_add_allocated_folios(dst, &dst_list); - /* - * Not absolutely necessary, but for consistency update max_huge_pages - * based on pool changes for the demoted page. - */ - h->max_huge_pages--; - target_hstate->max_huge_pages += - pages_per_huge_page(h) / pages_per_huge_page(target_hstate); + mutex_unlock(&dst->resize_lock); return rc; } -static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) +static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed, + unsigned long nr_to_demote) __must_hold(&hugetlb_lock) { int nr_nodes, node; - struct folio *folio; + struct hstate *dst; + long rc = 0; + long nr_demoted = 0; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ - if (!h->demote_order) { + if (!src->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } + dst = size_to_hstate(PAGE_SIZE << src->demote_order); - for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { - list_for_each_entry(folio, &h->hugepage_freelists[node], lru) { + for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) { + LIST_HEAD(list); + struct folio *folio, *next; + + list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; - return demote_free_hugetlb_folio(h, folio); + + remove_hugetlb_folio(src, folio, false); + list_add(&folio->lru, &list); + + if (++nr_demoted == nr_to_demote) + break; + } + + spin_unlock_irq(&hugetlb_lock); + + rc = demote_free_hugetlb_folios(src, dst, &list); + + spin_lock_irq(&hugetlb_lock); + + list_for_each_entry_safe(folio, next, &list, lru) { + list_del(&folio->lru); + add_hugetlb_folio(src, folio, false); + + nr_demoted--; } + + if (rc < 0 || nr_demoted == nr_to_demote) + break; } /* + * Not absolutely necessary, but for consistency update max_huge_pages + * based on pool changes for the demoted page. + */ + src->max_huge_pages -= nr_demoted; + dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst)); + + if (rc < 0) + return rc; + + if (nr_demoted) + return nr_demoted; + /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ @@ -4249,6 +4273,8 @@ static ssize_t demote_store(struct kobje spin_lock_irq(&hugetlb_lock); while (nr_demote) { + long rc; + /* * Check for available pages to demote each time thorough the * loop as demote_pool_huge_page will drop hugetlb_lock. @@ -4261,11 +4287,13 @@ static ssize_t demote_store(struct kobje if (!nr_available) break; - err = demote_pool_huge_page(h, n_mask); - if (err) + rc = demote_pool_huge_page(h, n_mask, nr_demote); + if (rc < 0) { + err = rc; break; + } - nr_demote--; + nr_demote -= rc; } spin_unlock_irq(&hugetlb_lock); _ Patches currently in -mm which might be from yuzhao(a)google.com are mm-contig_alloc-support-__gfp_comp.patch mm-cma-add-cma_allocfree_folio.patch mm-cma-add-cma_allocfree_folio-fix.patch mm-hugetlb-use-__gfp_comp-for-gigantic-folios.patch mm-free-zapped-tail-pages-when-splitting-isolated-thp.patch mm-remap-unused-subpages-to-shared-zeropage-when-splitting-isolated-thp.patch

3 months, 3 weeks

1
0
0 0

[merged mm-stable] selftest-mm-mseal-fix-test_seal_mremap_move_dontunmap_anyaddr.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: selftest mm/mseal: fix test_seal_mremap_move_dontunmap_anyaddr has been removed from the -mm tree. Its filename was selftest-mm-mseal-fix-test_seal_mremap_move_dontunmap_anyaddr.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Jeff Xu <jeffxu(a)chromium.org> Subject: selftest mm/mseal: fix test_seal_mremap_move_dontunmap_anyaddr Date: Wed, 7 Aug 2024 21:23:20 +0000 the syscall remap accepts following: mremap(src, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, dst) when the src is sealed, the call will fail with error code: EPERM Previously, the test uses hard-coded 0xdeaddead as dst, and it will fail on the system with newer glibc installed. This patch removes test's dependency on glibc for mremap(), also fix the test and remove the hardcoded address. Link: https://lkml.kernel.org/r/20240807212320.2831848-1-jeffxu@chromium.org Fixes: 4926c7a52de7 ("selftest mm/mseal memory sealing") Signed-off-by: Jeff Xu <jeffxu(a)chromium.org> Reported-by: Pedro Falcato <pedro.falcato(a)gmail.com> Cc: Dave Hansen <dave.hansen(a)intel.com> Cc: Liam R. Howlett <Liam.Howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Michael Ellerman <mpe(a)ellerman.id.au> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/mm/mseal_test.c | 57 +++++++++++++--------- 1 file changed, 36 insertions(+), 21 deletions(-) --- a/tools/testing/selftests/mm/mseal_test.c~selftest-mm-mseal-fix-test_seal_mremap_move_dontunmap_anyaddr +++ a/tools/testing/selftests/mm/mseal_test.c @@ -110,6 +110,16 @@ static int sys_madvise(void *start, size return sret; } +static void *sys_mremap(void *addr, size_t old_len, size_t new_len, + unsigned long flags, void *new_addr) +{ + void *sret; + + errno = 0; + sret = (void *) syscall(__NR_mremap, addr, old_len, new_len, flags, new_addr); + return sret; +} + static int sys_pkey_alloc(unsigned long flags, unsigned long init_val) { int ret = syscall(__NR_pkey_alloc, flags, init_val); @@ -1115,12 +1125,12 @@ static void test_seal_mremap_shrink(bool } /* shrink from 4 pages to 2 pages. */ - ret2 = mremap(ptr, size, 2 * page_size, 0, 0); + ret2 = sys_mremap(ptr, size, 2 * page_size, 0, 0); if (seal) { - FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); + FAIL_TEST_IF_FALSE(ret2 == (void *) MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); } else { - FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); + FAIL_TEST_IF_FALSE(ret2 != (void *) MAP_FAILED); } @@ -1147,7 +1157,7 @@ static void test_seal_mremap_expand(bool } /* expand from 2 page to 4 pages. */ - ret2 = mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); + ret2 = sys_mremap(ptr, 2 * page_size, 4 * page_size, 0, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1180,7 +1190,7 @@ static void test_seal_mremap_move(bool s } /* move from ptr to fixed address. */ - ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newPtr); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1299,7 +1309,7 @@ static void test_seal_mremap_shrink_fixe } /* mremap to move and shrink to fixed address */ - ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + ret2 = sys_mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); @@ -1330,7 +1340,7 @@ static void test_seal_mremap_expand_fixe } /* mremap to move and expand to fixed address */ - ret2 = mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, + ret2 = sys_mremap(ptr, page_size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); @@ -1361,7 +1371,7 @@ static void test_seal_mremap_move_fixed( } /* mremap to move to fixed address */ - ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_FIXED, newAddr); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); @@ -1390,14 +1400,13 @@ static void test_seal_mremap_move_fixed_ /* * MREMAP_FIXED can move the mapping to zero address */ - ret2 = mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, + ret2 = sys_mremap(ptr, size, 2 * page_size, MREMAP_MAYMOVE | MREMAP_FIXED, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); } else { FAIL_TEST_IF_FALSE(ret2 == 0); - } REPORT_TEST_PASS(); @@ -1420,13 +1429,13 @@ static void test_seal_mremap_move_dontun } /* mremap to move, and don't unmap src addr. */ - ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, 0); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); } else { + /* kernel will allocate a new address */ FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); - } REPORT_TEST_PASS(); @@ -1434,7 +1443,7 @@ static void test_seal_mremap_move_dontun static void test_seal_mremap_move_dontunmap_anyaddr(bool seal) { - void *ptr; + void *ptr, *ptr2; unsigned long page_size = getpagesize(); unsigned long size = 4 * page_size; int ret; @@ -1449,24 +1458,30 @@ static void test_seal_mremap_move_dontun } /* - * The 0xdeaddead should not have effect on dest addr - * when MREMAP_DONTUNMAP is set. + * The new address is any address that not allocated. + * use allocate/free to similate that. + */ + setup_single_address(size, &ptr2); + FAIL_TEST_IF_FALSE(ptr2 != (void *)-1); + ret = sys_munmap(ptr2, size); + FAIL_TEST_IF_FALSE(!ret); + + /* + * remap to any address. */ - ret2 = mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, - 0xdeaddead); + ret2 = sys_mremap(ptr, size, size, MREMAP_MAYMOVE | MREMAP_DONTUNMAP, + (void *) ptr2); if (seal) { FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED); FAIL_TEST_IF_FALSE(errno == EPERM); } else { - FAIL_TEST_IF_FALSE(ret2 != MAP_FAILED); - FAIL_TEST_IF_FALSE((long)ret2 != 0xdeaddead); - + /* remap success and return ptr2 */ + FAIL_TEST_IF_FALSE(ret2 == ptr2); } REPORT_TEST_PASS(); } - static void test_seal_merge_and_split(void) { void *ptr; _ Patches currently in -mm which might be from jeffxu(a)chromium.org are

3 months, 3 weeks

1
0
0 0

[merged mm-stable] mm-only-enforce-minimum-stack-gap-size-if-its-sensible.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: only enforce minimum stack gap size if it's sensible has been removed from the -mm tree. Its filename was mm-only-enforce-minimum-stack-gap-size-if-its-sensible.patch This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: David Gow <davidgow(a)google.com> Subject: mm: only enforce minimum stack gap size if it's sensible Date: Sat, 3 Aug 2024 15:46:41 +0800 The generic mmap_base code tries to leave a gap between the top of the stack and the mmap base address, but enforces a minimum gap size (MIN_GAP) of 128MB, which is too large on some setups. In particular, on arm tasks without ADDR_LIMIT_32BIT, the STACK_TOP value is less than 128MB, so it's impossible to fit such a gap in. Only enforce this minimum if MIN_GAP < MAX_GAP, as we'd prefer to honour MAX_GAP, which is defined proportionally, so scales better and always leaves us with both _some_ stack space and some room for mmap. This fixes the usercopy KUnit test suite on 32-bit arm, as it doesn't set any personality flags so gets the default (in this case 26-bit) task size. This test can be run with: ./tools/testing/kunit/kunit.py run --arch arm usercopy --make_options LLVM=1 Link: https://lkml.kernel.org/r/20240803074642.1849623-2-davidgow@google.com Fixes: dba79c3df4a2 ("arm: use generic mmap top-down layout and brk randomization") Signed-off-by: David Gow <davidgow(a)google.com> Reviewed-by: Kees Cook <kees(a)kernel.org> Cc: Alexandre Ghiti <alex(a)ghiti.fr> Cc: Linus Walleij <linus.walleij(a)linaro.org> Cc: Luis Chamberlain <mcgrof(a)kernel.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Russell King <linux(a)armlinux.org.uk> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) --- a/mm/util.c~mm-only-enforce-minimum-stack-gap-size-if-its-sensible +++ a/mm/util.c @@ -463,7 +463,7 @@ static unsigned long mmap_base(unsigned if (gap + pad > gap) gap += pad; - if (gap < MIN_GAP) + if (gap < MIN_GAP && MIN_GAP < MAX_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; _ Patches currently in -mm which might be from davidgow(a)google.com are

3 months, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] alloc_tag-fix-allocation-tag-reporting-when-config_modules=n.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: alloc_tag: fix allocation tag reporting when CONFIG_MODULES=n has been removed from the -mm tree. Its filename was alloc_tag-fix-allocation-tag-reporting-when-config_modules=n.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Suren Baghdasaryan <surenb(a)google.com> Subject: alloc_tag: fix allocation tag reporting when CONFIG_MODULES=n Date: Wed, 28 Aug 2024 16:15:36 -0700 codetag_module_init() is used to initialize sections containing allocation tags. This function is used to initialize module sections as well as core kernel sections, in which case the module parameter is set to NULL. This function has to be called even when CONFIG_MODULES=n to initialize core kernel allocation tag sections. When CONFIG_MODULES=n, this function is a NOP, which is wrong. This leads to /proc/allocinfo reported as empty. Fix this by making it independent of CONFIG_MODULES. Link: https://lkml.kernel.org/r/20240828231536.1770519-1-surenb@google.com Fixes: 916cc5167cc6 ("lib: code tagging framework") Signed-off-by: Suren Baghdasaryan <surenb(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Kees Cook <keescook(a)chromium.org> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Pasha Tatashin <pasha.tatashin(a)soleen.com> Cc: Sourav Panda <souravpanda(a)google.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> [6.10+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- lib/codetag.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) --- a/lib/codetag.c~alloc_tag-fix-allocation-tag-reporting-when-config_modules=n +++ a/lib/codetag.c @@ -125,7 +125,6 @@ static inline size_t range_size(const st cttype->desc.tag_size; } -#ifdef CONFIG_MODULES static void *get_symbol(struct module *mod, const char *prefix, const char *name) { DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN); @@ -155,6 +154,15 @@ static struct codetag_range get_section_ }; } +static const char *get_mod_name(__maybe_unused struct module *mod) +{ +#ifdef CONFIG_MODULES + if (mod) + return mod->name; +#endif + return "(built-in)"; +} + static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { struct codetag_range range; @@ -164,8 +172,7 @@ static int codetag_module_init(struct co range = get_section_range(mod, cttype->desc.section); if (!range.start || !range.stop) { pr_warn("Failed to load code tags of type %s from the module %s\n", - cttype->desc.section, - mod ? mod->name : "(built-in)"); + cttype->desc.section, get_mod_name(mod)); return -EINVAL; } @@ -199,6 +206,7 @@ static int codetag_module_init(struct co return 0; } +#ifdef CONFIG_MODULES void codetag_load_module(struct module *mod) { struct codetag_type *cttype; @@ -248,9 +256,6 @@ bool codetag_unload_module(struct module return unload_ok; } - -#else /* CONFIG_MODULES */ -static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; } #endif /* CONFIG_MODULES */ struct codetag_type * _ Patches currently in -mm which might be from surenb(a)google.com are

3 months, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] mm-vmalloc-optimize-vmap_lazy_nr-arithmetic-when-purging-each-vmap_area.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm: vmalloc: optimize vmap_lazy_nr arithmetic when purging each vmap_area has been removed from the -mm tree. Its filename was mm-vmalloc-optimize-vmap_lazy_nr-arithmetic-when-purging-each-vmap_area.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Adrian Huang <ahuang12(a)lenovo.com> Subject: mm: vmalloc: optimize vmap_lazy_nr arithmetic when purging each vmap_area Date: Thu, 29 Aug 2024 21:06:33 +0800 When running the vmalloc stress on a 448-core system, observe the average latency of purge_vmap_node() is about 2 seconds by using the eBPF/bcc 'funclatency.py' tool [1]. # /your-git-repo/bcc/tools/funclatency.py -u purge_vmap_node & pid1=$! && sleep 8 && modprobe test_vmalloc nr_threads=$(nproc) run_test_mask=0x7; kill -SIGINT $pid1 usecs : count distribution 0 -> 1 : 0 | | 2 -> 3 : 29 | | 4 -> 7 : 19 | | 8 -> 15 : 56 | | 16 -> 31 : 483 |**** | 32 -> 63 : 1548 |************ | 64 -> 127 : 2634 |********************* | 128 -> 255 : 2535 |********************* | 256 -> 511 : 1776 |************** | 512 -> 1023 : 1015 |******** | 1024 -> 2047 : 573 |**** | 2048 -> 4095 : 488 |**** | 4096 -> 8191 : 1091 |********* | 8192 -> 16383 : 3078 |************************* | 16384 -> 32767 : 4821 |****************************************| 32768 -> 65535 : 3318 |*************************** | 65536 -> 131071 : 1718 |************** | 131072 -> 262143 : 2220 |****************** | 262144 -> 524287 : 1147 |********* | 524288 -> 1048575 : 1179 |********* | 1048576 -> 2097151 : 822 |****** | 2097152 -> 4194303 : 906 |******* | 4194304 -> 8388607 : 2148 |***************** | 8388608 -> 16777215 : 4497 |************************************* | 16777216 -> 33554431 : 289 |** | avg = 2041714 usecs, total: 78381401772 usecs, count: 38390 The worst case is over 16-33 seconds, so soft lockup is triggered [2]. [Root Cause] 1) Each purge_list has the long list. The following shows the number of vmap_area is purged. crash> p vmap_nodes vmap_nodes = $27 = (struct vmap_node *) 0xff2de5a900100000 crash> vmap_node 0xff2de5a900100000 128 | grep nr_purged nr_purged = 663070 ... nr_purged = 821670 nr_purged = 692214 nr_purged = 726808 ... 2) atomic_long_sub() employs the 'lock' prefix to ensure the atomic operation when purging each vmap_area. However, the iteration is over 600000 vmap_area (See 'nr_purged' above). Here is objdump output: $ objdump -D vmlinux ffffffff813e8c80 <purge_vmap_node>: ... ffffffff813e8d70: f0 48 29 2d 68 0c bb lock sub %rbp,0x2bb0c68(%rip) ... Quote from "Instruction tables" pdf file [3]: Instructions with a LOCK prefix have a long latency that depends on cache organization and possibly RAM speed. If there are multiple processors or cores or direct memory access (DMA) devices, then all locked instructions will lock a cache line for exclusive access, which may involve RAM access. A LOCK prefix typically costs more than a hundred clock cycles, even on single-processor systems. That's why the latency of purge_vmap_node() dramatically increases on a many-core system: One core is busy on purging each vmap_area of the *long* purge_list and executing atomic_long_sub() for each vmap_area, while other cores free vmalloc allocations and execute atomic_long_add_return() in free_vmap_area_noflush(). [Solution] Employ a local variable to record the total purged pages, and execute atomic_long_sub() after the traversal of the purge_list is done. The experiment result shows the latency improvement is 99%. [Experiment Result] 1) System Configuration: Three servers (with HT-enabled) are tested. * 72-core server: 3rd Gen Intel Xeon Scalable Processor*1 * 192-core server: 5th Gen Intel Xeon Scalable Processor*2 * 448-core server: AMD Zen 4 Processor*2 2) Kernel Config * CONFIG_KASAN is disabled 3) The data in column "w/o patch" and "w/ patch" * Unit: micro seconds (us) * Each data is the average of 3-time measurements System w/o patch (us) w/ patch (us) Improvement (%) --------------- -------------- ------------- ------------- 72-core server 2194 14 99.36% 192-core server 143799 1139 99.21% 448-core server 1992122 6883 99.65% [1] https://github.com/iovisor/bcc/blob/master/tools/funclatency.py [2] https://gist.github.com/AdrianHuang/37c15f67b45407b83c2d32f918656c12 [3] https://www.agner.org/optimize/instruction_tables.pdf Link: https://lkml.kernel.org/r/20240829130633.2184-1-ahuang12@lenovo.com Signed-off-by: Adrian Huang <ahuang12(a)lenovo.com> Reviewed-by: Uladzislau Rezki (Sony) <urezki(a)gmail.com> Cc: Christoph Hellwig <hch(a)infradead.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmalloc.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) --- a/mm/vmalloc.c~mm-vmalloc-optimize-vmap_lazy_nr-arithmetic-when-purging-each-vmap_area +++ a/mm/vmalloc.c @@ -2191,6 +2191,7 @@ static void purge_vmap_node(struct work_ { struct vmap_node *vn = container_of(work, struct vmap_node, purge_work); + unsigned long nr_purged_pages = 0; struct vmap_area *va, *n_va; LIST_HEAD(local_list); @@ -2208,7 +2209,7 @@ static void purge_vmap_node(struct work_ kasan_release_vmalloc(orig_start, orig_end, va->va_start, va->va_end); - atomic_long_sub(nr, &vmap_lazy_nr); + nr_purged_pages += nr; vn->nr_purged++; if (is_vn_id_valid(vn_id) && !vn->skip_populate) @@ -2219,6 +2220,8 @@ static void purge_vmap_node(struct work_ list_add(&va->list, &local_list); } + atomic_long_sub(nr_purged_pages, &vmap_lazy_nr); + reclaim_list_global(&local_list); } _ Patches currently in -mm which might be from ahuang12(a)lenovo.com are mm-vmalloc-combine-all-tlb-flush-operations-of-kasan-shadow-virtual-address-into-one-operation.patch

3 months, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] codetag-debug-mark-codetags-for-poisoned-page-as-empty.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: codetag: debug: mark codetags for poisoned page as empty has been removed from the -mm tree. Its filename was codetag-debug-mark-codetags-for-poisoned-page-as-empty.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Hao Ge <gehao(a)kylinos.cn> Subject: codetag: debug: mark codetags for poisoned page as empty Date: Mon, 26 Aug 2024 00:36:49 +0800 When PG_hwpoison pages are freed they are treated differently in free_pages_prepare() and instead of being released they are isolated. Page allocation tag counters are decremented at this point since the page is considered not in use. Later on when such pages are released by unpoison_memory(), the allocation tag counters will be decremented again and the following warning gets reported: [ 113.930443][ T3282] ------------[ cut here ]------------ [ 113.931105][ T3282] alloc_tag was not set [ 113.931576][ T3282] WARNING: CPU: 2 PID: 3282 at ./include/linux/alloc_tag.h:130 pgalloc_tag_sub.part.66+0x154/0x164 [ 113.932866][ T3282] Modules linked in: hwpoison_inject fuse ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute ip6table_nat ip6table_man4 [ 113.941638][ T3282] CPU: 2 UID: 0 PID: 3282 Comm: madvise11 Kdump: loaded Tainted: G W 6.11.0-rc4-dirty #18 [ 113.943003][ T3282] Tainted: [W]=WARN [ 113.943453][ T3282] Hardware name: QEMU KVM Virtual Machine, BIOS unknown 2/2/2022 [ 113.944378][ T3282] pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 113.945319][ T3282] pc : pgalloc_tag_sub.part.66+0x154/0x164 [ 113.946016][ T3282] lr : pgalloc_tag_sub.part.66+0x154/0x164 [ 113.946706][ T3282] sp : ffff800087093a10 [ 113.947197][ T3282] x29: ffff800087093a10 x28: ffff0000d7a9d400 x27: ffff80008249f0a0 [ 113.948165][ T3282] x26: 0000000000000000 x25: ffff80008249f2b0 x24: 0000000000000000 [ 113.949134][ T3282] x23: 0000000000000001 x22: 0000000000000001 x21: 0000000000000000 [ 113.950597][ T3282] x20: ffff0000c08fcad8 x19: ffff80008251e000 x18: ffffffffffffffff [ 113.952207][ T3282] x17: 0000000000000000 x16: 0000000000000000 x15: ffff800081746210 [ 113.953161][ T3282] x14: 0000000000000000 x13: 205d323832335420 x12: 5b5d353031313339 [ 113.954120][ T3282] x11: ffff800087093500 x10: 000000000000005d x9 : 00000000ffffffd0 [ 113.955078][ T3282] x8 : 7f7f7f7f7f7f7f7f x7 : ffff80008236ba90 x6 : c0000000ffff7fff [ 113.956036][ T3282] x5 : ffff000b34bf4dc8 x4 : ffff8000820aba90 x3 : 0000000000000001 [ 113.956994][ T3282] x2 : ffff800ab320f000 x1 : 841d1e35ac932e00 x0 : 0000000000000000 [ 113.957962][ T3282] Call trace: [ 113.958350][ T3282] pgalloc_tag_sub.part.66+0x154/0x164 [ 113.959000][ T3282] pgalloc_tag_sub+0x14/0x1c [ 113.959539][ T3282] free_unref_page+0xf4/0x4b8 [ 113.960096][ T3282] __folio_put+0xd4/0x120 [ 113.960614][ T3282] folio_put+0x24/0x50 [ 113.961103][ T3282] unpoison_memory+0x4f0/0x5b0 [ 113.961678][ T3282] hwpoison_unpoison+0x30/0x48 [hwpoison_inject] [ 113.962436][ T3282] simple_attr_write_xsigned.isra.34+0xec/0x1cc [ 113.963183][ T3282] simple_attr_write+0x38/0x48 [ 113.963750][ T3282] debugfs_attr_write+0x54/0x80 [ 113.964330][ T3282] full_proxy_write+0x68/0x98 [ 113.964880][ T3282] vfs_write+0xdc/0x4d0 [ 113.965372][ T3282] ksys_write+0x78/0x100 [ 113.965875][ T3282] __arm64_sys_write+0x24/0x30 [ 113.966440][ T3282] invoke_syscall+0x7c/0x104 [ 113.966984][ T3282] el0_svc_common.constprop.1+0x88/0x104 [ 113.967652][ T3282] do_el0_svc+0x2c/0x38 [ 113.968893][ T3282] el0_svc+0x3c/0x1b8 [ 113.969379][ T3282] el0t_64_sync_handler+0x98/0xbc [ 113.969980][ T3282] el0t_64_sync+0x19c/0x1a0 [ 113.970511][ T3282] ---[ end trace 0000000000000000 ]--- To fix this, clear the page tag reference after the page got isolated and accounted for. Link: https://lkml.kernel.org/r/20240825163649.33294-1-hao.ge@linux.dev Fixes: d224eb0287fb ("codetag: debug: mark codetags for reserved pages as empty") Signed-off-by: Hao Ge <gehao(a)kylinos.cn> Reviewed-by: Miaohe Lin <linmiaohe(a)huawei.com> Acked-by: Suren Baghdasaryan <surenb(a)google.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Hao Ge <gehao(a)kylinos.cn> Cc: Kent Overstreet <kent.overstreet(a)linux.dev> Cc: Naoya Horiguchi <nao.horiguchi(a)gmail.com> Cc: Pasha Tatashin <pasha.tatashin(a)soleen.com> Cc: <stable(a)vger.kernel.org> [6.10+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/page_alloc.c | 7 +++++++ 1 file changed, 7 insertions(+) --- a/mm/page_alloc.c~codetag-debug-mark-codetags-for-poisoned-page-as-empty +++ a/mm/page_alloc.c @@ -1054,6 +1054,13 @@ __always_inline bool free_pages_prepare( reset_page_owner(page, order); page_table_check_free(page, order); pgalloc_tag_sub(page, 1 << order); + + /* + * The page is isolated and accounted for. + * Mark the codetag as empty to avoid accounting error + * when the page is freed by unpoison_memory(). + */ + clear_page_tag_ref(page); return false; } _ Patches currently in -mm which might be from gehao(a)kylinos.cn are mm-cma-change-the-addition-of-totalcma_pages-in-the-cma_init_reserved_mem.patch

3 months, 3 weeks

1
0
0 0

[merged mm-hotfixes-stable] revert-mm-skip-cma-pages-when-they-are-not-available.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: Revert "mm: skip CMA pages when they are not available" has been removed from the -mm tree. Its filename was revert-mm-skip-cma-pages-when-they-are-not-available.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Usama Arif <usamaarif642(a)gmail.com> Subject: Revert "mm: skip CMA pages when they are not available" Date: Wed, 21 Aug 2024 20:26:07 +0100 This reverts commit 5da226dbfce3 ("mm: skip CMA pages when they are not available") and b7108d66318a ("Multi-gen LRU: skip CMA pages when they are not eligible"). lruvec->lru_lock is highly contended and is held when calling isolate_lru_folios. If the lru has a large number of CMA folios consecutively, while the allocation type requested is not MIGRATE_MOVABLE, isolate_lru_folios can hold the lock for a very long time while it skips those. For FIO workload, ~150million order=0 folios were skipped to isolate a few ZONE_DMA folios [1]. This can cause lockups [1] and high memory pressure for extended periods of time [2]. Remove skipping CMA for MGLRU as well, as it was introduced in sort_folio for the same resaon as 5da226dbfce3a2f44978c2c7cf88166e69a6788b. [1] https://lore.kernel.org/all/CAOUHufbkhMZYz20aM_3rHZ3OcK4m2puji2FGpUpn_-DevG… [2] https://lore.kernel.org/all/ZrssOrcJIDy8hacI@gmail.com/ [usamaarif642(a)gmail.com: also revert b7108d66318a, per Johannes] Link: https://lkml.kernel.org/r/9060a32d-b2d7-48c0-8626-1db535653c54@gmail.com Link: https://lkml.kernel.org/r/357ac325-4c61-497a-92a3-bdbd230d5ec9@gmail.com Link: https://lkml.kernel.org/r/9060a32d-b2d7-48c0-8626-1db535653c54@gmail.com Fixes: 5da226dbfce3 ("mm: skip CMA pages when they are not available") Signed-off-by: Usama Arif <usamaarif642(a)gmail.com> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> Cc: Bharata B Rao <bharata(a)amd.com> Cc: Breno Leitao <leitao(a)debian.org> Cc: David Hildenbrand <david(a)redhat.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Rik van Riel <riel(a)surriel.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: Yu Zhao <yuzhao(a)google.com> Cc: Zhaoyang Huang <huangzhaoyang(a)gmail.com> Cc: Zhaoyang Huang <zhaoyang.huang(a)unisoc.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 24 ++---------------------- 1 file changed, 2 insertions(+), 22 deletions(-) --- a/mm/vmscan.c~revert-mm-skip-cma-pages-when-they-are-not-available +++ a/mm/vmscan.c @@ -1604,25 +1604,6 @@ static __always_inline void update_lru_s } -#ifdef CONFIG_CMA -/* - * It is waste of effort to scan and reclaim CMA pages if it is not available - * for current allocation context. Kswapd can not be enrolled as it can not - * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL - */ -static bool skip_cma(struct folio *folio, struct scan_control *sc) -{ - return !current_is_kswapd() && - gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE && - folio_migratetype(folio) == MIGRATE_CMA; -} -#else -static bool skip_cma(struct folio *folio, struct scan_control *sc) -{ - return false; -} -#endif - /* * Isolating page from the lruvec to fill in @dst list by nr_to_scan times. * @@ -1669,8 +1650,7 @@ static unsigned long isolate_lru_folios( nr_pages = folio_nr_pages(folio); total_scan += nr_pages; - if (folio_zonenum(folio) > sc->reclaim_idx || - skip_cma(folio, sc)) { + if (folio_zonenum(folio) > sc->reclaim_idx) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; goto move; @@ -4320,7 +4300,7 @@ static bool sort_folio(struct lruvec *lr } /* ineligible */ - if (zone > sc->reclaim_idx || skip_cma(folio, sc)) { + if (zone > sc->reclaim_idx) { gen = folio_inc_gen(lruvec, folio, false); list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]); return true; _ Patches currently in -mm which might be from usamaarif642(a)gmail.com are mm-store-zero-pages-to-be-swapped-out-in-a-bitmap.patch mm-remove-code-to-handle-same-filled-pages.patch mm-introduce-a-pageflag-for-partially-mapped-folios.patch mm-split-underused-thps.patch mm-add-sysfs-entry-to-disable-splitting-underused-thps.patch

3 months, 3 weeks

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2024