From 1723058eab19de741b80ac8ad25bfe2a00e02987 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 1 Feb 2019 14:19:57 -0800 Subject: [PATCH 01/24] mm, memory_hotplug: don't bail out in do_migrate_range() prematurely do_migrate_range() takes a memory range and tries to isolate the pages to put them into a list. This list will be later on used in migrate_pages() to know the pages we need to migrate. Currently, if we fail to isolate a single page, we put all already isolated pages back to their LRU and we bail out from the function. This is quite suboptimal, as this will force us to start over again because scan_movable_pages will give us the same range. If there is no chance that we can isolate that page, we will loop here forever. Issue debugged in [1] has proved that. During the debugging of that issue, it was noticed that if do_migrate_ranges() fails to isolate a single page, we will just discard the work we have done so far and bail out, which means that scan_movable_pages() will find again the same set of pages. Instead, we can just skip the error, keep isolating as much pages as possible and then proceed with the call to migrate_pages(). This will allow us to do as much work as possible at once. [1] https://lkml.org/lkml/2018/12/6/324 Michal said: : I still think that this doesn't give us a whole picture. Looping for : ever is a bug. Failing the isolation is quite possible and it should : be a ephemeral condition (e.g. a race with freeing the page or : somebody else isolating the page for whatever reason). And here comes : the disadvantage of the current implementation. We simply throw : everything on the floor just because of a ephemeral condition. The : racy page_count check is quite dubious to prevent from that. Link: http://lkml.kernel.org/r/20181211135312.27034-1-osalvador@suse.de Signed-off-by: Oscar Salvador Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Dan Williams Cc: Jan Kara Cc: Kirill A. Shutemov Cc: William Kucharski Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b9a667d36c554..d7b7d221c284a 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1344,7 +1344,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; - int not_managed = 0; int ret = 0; LIST_HEAD(source); @@ -1392,7 +1391,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) else ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ - put_page(page); list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + @@ -1401,22 +1399,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } else { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); - put_page(page); - /* Because we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) { - not_managed++; - ret = -EBUSY; - break; - } } + put_page(page); } if (!list_empty(&source)) { - if (not_managed) { - putback_movable_pages(&source); - goto out; - } - /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); @@ -1429,7 +1415,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } -out: + return ret; } From 1fde6f21d90f8ba5da3cb9c54ca991ed72696c43 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Fri, 1 Feb 2019 14:20:01 -0800 Subject: [PATCH 02/24] proc: fix /proc/net/* after setns(2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit /proc entries under /proc/net/* can't be cached into dcache because setns(2) can change current net namespace. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: avoid vim miscolorization] [adobriyan@gmail.com: write test, add dummy ->d_revalidate hook: necessary if /proc/net/* is pinned at setns time] Link: http://lkml.kernel.org/r/20190108192350.GA12034@avx2 Link: http://lkml.kernel.org/r/20190107162336.GA9239@avx2 Fixes: 1da4d377f943fe4194ffb9fb9c26cc58fad4dd24 ("proc: revalidate misc dentries") Signed-off-by: Alexey Dobriyan Reported-by: Mateusz Stępień Reported-by: Ahmad Fatoum Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/generic.c | 4 +- fs/proc/internal.h | 1 + fs/proc/proc_net.c | 20 +++ tools/testing/selftests/proc/.gitignore | 1 + tools/testing/selftests/proc/Makefile | 1 + tools/testing/selftests/proc/setns-dcache.c | 129 ++++++++++++++++++++ 6 files changed, 155 insertions(+), 1 deletion(-) create mode 100644 tools/testing/selftests/proc/setns-dcache.c diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ae109429a883..e39bac94dead0 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_misc_dentry_ops); + d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); @@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + ent->proc_dops = &proc_misc_dentry_ops; + out: return ent; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51ee..95b14196f2842 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -44,6 +44,7 @@ struct proc_dir_entry { struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d5e0fcb3439e9..a7b12435519e0 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +static const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + +static void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} + static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; return proc_register(parent, p); @@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; p->write = write; diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 82121a81681f7..29bac5ef9a93d 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,4 +10,5 @@ /proc-uptime-002 /read /self +/setns-dcache /thread-self diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index 1c12c34cf85d8..434d033ee0677 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001 TEST_GEN_PROGS += proc-uptime-002 TEST_GEN_PROGS += read TEST_GEN_PROGS += self +TEST_GEN_PROGS += setns-dcache TEST_GEN_PROGS += thread-self include ../lib.mk diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c new file mode 100644 index 0000000000000..60ab197a73fc9 --- /dev/null +++ b/tools/testing/selftests/proc/setns-dcache.c @@ -0,0 +1,129 @@ +/* + * Copyright © 2019 Alexey Dobriyan + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +/* + * Test that setns(CLONE_NEWNET) points to new /proc/net content even + * if old one is in dcache. + * + * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled. + */ +#undef NDEBUG +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static pid_t pid = -1; + +static void f(void) +{ + if (pid > 0) { + kill(pid, SIGTERM); + } +} + +int main(void) +{ + int fd[2]; + char _ = 0; + int nsfd; + + atexit(f); + + /* Check for priviledges and syscall availability straight away. */ + if (unshare(CLONE_NEWNET) == -1) { + if (errno == ENOSYS || errno == EPERM) { + return 4; + } + return 1; + } + /* Distinguisher between two otherwise empty net namespaces. */ + if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) { + return 1; + } + + if (pipe(fd) == -1) { + return 1; + } + + pid = fork(); + if (pid == -1) { + return 1; + } + + if (pid == 0) { + if (unshare(CLONE_NEWNET) == -1) { + return 1; + } + + if (write(fd[1], &_, 1) != 1) { + return 1; + } + + pause(); + + return 0; + } + + if (read(fd[0], &_, 1) != 1) { + return 1; + } + + { + char buf[64]; + snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid); + nsfd = open(buf, O_RDONLY); + if (nsfd == -1) { + return 1; + } + } + + /* Reliably pin dentry into dcache. */ + (void)open("/proc/net/unix", O_RDONLY); + + if (setns(nsfd, CLONE_NEWNET) == -1) { + return 1; + } + + kill(pid, SIGTERM); + pid = 0; + + { + char buf[4096]; + ssize_t rv; + int fd; + + fd = open("/proc/net/unix", O_RDONLY); + if (fd == -1) { + return 1; + } + +#define S "Num RefCount Protocol Flags Type St Inode Path\n" + rv = read(fd, buf, sizeof(buf)); + + assert(rv == strlen(S)); + assert(memcmp(buf, S, strlen(S)) == 0); + } + + return 0; +} From 36c0f7f0f89984bb21e6d0f92d776faf7be73096 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 1 Feb 2019 14:20:12 -0800 Subject: [PATCH 03/24] arch: unexport asm/shmparam.h for all architectures Most architectures do not export shmparam.h to user-space. $ find arch -name shmparam.h | sort arch/alpha/include/asm/shmparam.h arch/arc/include/asm/shmparam.h arch/arm64/include/asm/shmparam.h arch/arm/include/asm/shmparam.h arch/csky/include/asm/shmparam.h arch/ia64/include/asm/shmparam.h arch/mips/include/asm/shmparam.h arch/nds32/include/asm/shmparam.h arch/nios2/include/asm/shmparam.h arch/parisc/include/asm/shmparam.h arch/powerpc/include/asm/shmparam.h arch/s390/include/asm/shmparam.h arch/sh/include/asm/shmparam.h arch/sparc/include/asm/shmparam.h arch/x86/include/asm/shmparam.h arch/xtensa/include/asm/shmparam.h Strangely, some users of the asm-generic wrapper export shmparam.h $ git grep 'generic-y += shmparam.h' arch/c6x/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/h8300/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/hexagon/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/m68k/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/microblaze/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/openrisc/include/uapi/asm/Kbuild:generic-y += shmparam.h arch/riscv/include/asm/Kbuild:generic-y += shmparam.h arch/unicore32/include/uapi/asm/Kbuild:generic-y += shmparam.h The newly added riscv correctly creates the asm-generic wrapper in the kernel space, but the others (c6x, h8300, hexagon, m68k, microblaze, openrisc, unicore32) create the one in the uapi directory. Digging into the git history, now I guess fcc8487d477a ("uapi: export all headers under uapi directories") was the misconversion. Prior to that commit, no architecture exported to shmparam.h As its commit description said, that commit exported shmparam.h for c6x, h8300, hexagon, m68k, openrisc, unicore32. 83f0124ad81e ("microblaze: remove asm-generic wrapper headers") accidentally exported shmparam.h for microblaze. This commit unexports shmparam.h for those architectures. There is no more reason to export include/uapi/asm-generic/shmparam.h, so it has been moved to include/asm-generic/shmparam.h Link: http://lkml.kernel.org/r/1546904307-11124-1-git-send-email-yamada.masahiro@socionext.com Signed-off-by: Masahiro Yamada Acked-by: Stafford Horne Cc: Geert Uytterhoeven Cc: Michal Simek Cc: Yoshinori Sato Cc: Richard Kuo Cc: Guan Xuetao Cc: Nicolas Dichtel Cc: Arnd Bergmann Cc: Aurelien Jacquiot Cc: Greentime Hu Cc: Guo Ren Cc: Palmer Dabbelt Cc: Stefan Kristiansson Cc: Mark Salter Cc: Albert Ou Cc: Jonas Bonn Cc: Vincent Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/c6x/include/asm/Kbuild | 1 + arch/c6x/include/uapi/asm/Kbuild | 1 - arch/h8300/include/asm/Kbuild | 1 + arch/h8300/include/uapi/asm/Kbuild | 1 - arch/hexagon/include/asm/Kbuild | 1 + arch/hexagon/include/uapi/asm/Kbuild | 1 - arch/m68k/include/asm/Kbuild | 1 + arch/m68k/include/uapi/asm/Kbuild | 1 - arch/microblaze/include/asm/Kbuild | 1 + arch/microblaze/include/uapi/asm/Kbuild | 1 - arch/openrisc/include/asm/Kbuild | 1 + arch/openrisc/include/uapi/asm/Kbuild | 1 - arch/unicore32/include/asm/Kbuild | 1 + arch/unicore32/include/uapi/asm/Kbuild | 1 - 14 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 33a2c94fed0de..63b4a17051822 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += pgalloc.h generic-y += preempt.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 6c6f6301012ef..0febf1a07c30a 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index cd400d353d182..961c1dc064e16 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -40,6 +40,7 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += spinlock.h generic-y += timex.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 6c6f6301012ef..0febf1a07c30a 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 47c4da3d64a4e..b25fd42aa0f47 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index 61d955c1747a7..c1b06dcf6cf8e 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -1,4 +1,3 @@ include include/uapi/asm-generic/Kbuild.asm -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 9f1dd26903e33..95f8f631c4df0 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h +generic-y += shmparam.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index b8b3525271faf..960bf1e4be530 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 9c7d1d25bf3db..791cc8d54d0a9 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -26,6 +26,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += serial.h +generic-y += shmparam.h generic-y += syscalls.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 28823e3db8253..97823ec46e97c 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index eb87cd8327c89..1f04844b6b82d 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -34,6 +34,7 @@ generic-y += qrwlock_types.h generic-y += qrwlock.h generic-y += sections.h generic-y += segment.h +generic-y += shmparam.h generic-y += string.h generic-y += switch_to.h generic-y += topology.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 6c6f6301012ef..0febf1a07c30a 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1372553dc0a9a..1d1544b6ca74c 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -28,6 +28,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += syscalls.h generic-y += topology.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 6c6f6301012ef..0febf1a07c30a 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h From 1ac25013fb9e4ed595cd608a406191e93520881e Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 1 Feb 2019 14:20:16 -0800 Subject: [PATCH 04/24] mm/hugetlb.c: teach follow_hugetlb_page() to handle FOLL_NOWAIT hugetlb needs the same fix as faultin_nopage (which was applied in commit 96312e61282a ("mm/gup.c: teach get_user_pages_unlocked to handle FOLL_NOWAIT")) or KVM hangs because it thinks the mmap_sem was already released by hugetlb_fault() if it returned VM_FAULT_RETRY, but it wasn't in the FOLL_NOWAIT case. Link: http://lkml.kernel.org/r/20190109020203.26669-2-aarcange@redhat.com Fixes: ce53053ce378 ("kvm: switch get_user_page_nowait() to get_user_pages_unlocked()") Signed-off-by: Andrea Arcangeli Tested-by: "Dr. David Alan Gilbert" Reported-by: "Dr. David Alan Gilbert" Reviewed-by: Mike Kravetz Reviewed-by: Peter Xu Cc: Mike Rapoport Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index df2e7dd5ff17f..afef61656c1e1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4268,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; *nr_pages = 0; /* From a8e911d13540487942d53137c156bd7707f66e5d Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:20 -0800 Subject: [PATCH 05/24] x86_64: increase stack size for KASAN_EXTRA If the kernel is configured with KASAN_EXTRA, the stack size is increasted significantly because this option sets "-fstack-reuse" to "none" in GCC [1]. As a result, it triggers stack overrun quite often with 32k stack size compiled using GCC 8. For example, this reproducer https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/syscalls/madvise/madvise06.c triggers a "corrupted stack end detected inside scheduler" very reliably with CONFIG_SCHED_STACK_END_CHECK enabled. There are just too many functions that could have a large stack with KASAN_EXTRA due to large local variables that have been called over and over again without being able to reuse the stacks. Some noticiable ones are size 7648 shrink_page_list 3584 xfs_rmap_convert 3312 migrate_page_move_mapping 3312 dev_ethtool 3200 migrate_misplaced_transhuge_page 3168 copy_process There are other 49 functions are over 2k in size while compiling kernel with "-Wframe-larger-than=" even with a related minimal config on this machine. Hence, it is too much work to change Makefiles for each object to compile without "-fsanitize-address-use-after-scope" individually. [1] https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81715#c23 Although there is a patch in GCC 9 to help the situation, GCC 9 probably won't be released in a few months and then it probably take another 6-month to 1-year for all major distros to include it as a default. Hence, the stack usage with KASAN_EXTRA can be revisited again in 2020 when GCC 9 is everywhere. Until then, this patch will help users avoid stack overrun. This has already been fixed for arm64 for the same reason via 6e8830674ea ("arm64: kasan: Increase stack size for KASAN_EXTRA"). Link: http://lkml.kernel.org/r/20190109215209.2903-1-cai@lca.pw Signed-off-by: Qian Cai Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/page_64_types.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8f657286d599a..0ce558a8150d3 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif From 8fb335e078378c8426fabeed1ebee1fbf915690c Mon Sep 17 00:00:00 2001 From: Andrei Vagin Date: Fri, 1 Feb 2019 14:20:24 -0800 Subject: [PATCH 06/24] kernel/exit.c: release ptraced tasks before zap_pid_ns_processes Currently, exit_ptrace() adds all ptraced tasks in a dead list, then zap_pid_ns_processes() waits on all tasks in a current pidns, and only then are tasks from the dead list released. zap_pid_ns_processes() can get stuck on waiting tasks from the dead list. In this case, we will have one unkillable process with one or more dead children. Thanks to Oleg for the advice to release tasks in find_child_reaper(). Link: http://lkml.kernel.org/r/20190110175200.12442-1-avagin@gmail.com Fixes: 7c8bd2322c7f ("exit: ptrace: shift "reap dead" code from exit_ptrace() to forget_original_parent()") Signed-off-by: Andrei Vagin Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/exit.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/kernel/exit.c b/kernel/exit.c index 3fb7be0019644..2639a30a8aa5d 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p) return NULL; } -static struct task_struct *find_child_reaper(struct task_struct *father) +static struct task_struct *find_child_reaper(struct task_struct *father, + struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; + struct task_struct *p, *n; if (likely(reaper != father)) return reaper; @@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father) panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } + + list_for_each_entry_safe(p, n, dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } + zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); @@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father, exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ - reaper = find_child_reaper(father); + reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; From 80409c65e2c6cd1540045ee01fc55e50d95e0983 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Feb 2019 14:20:27 -0800 Subject: [PATCH 07/24] mm: migrate: make buffer_migrate_page_norefs() actually succeed Currently, buffer_migrate_page_norefs() was constantly failing because buffer_migrate_lock_buffers() grabbed reference on each buffer. In fact, there's no reason for buffer_migrate_lock_buffers() to grab any buffer references as the page is locked during all our operation and thus nobody can reclaim buffers from the page. So remove grabbing of buffer references which also makes buffer_migrate_page_norefs() succeed. Link: http://lkml.kernel.org/r/20190116131217.7226-1-jack@suse.cz Fixes: 89cb0888ca14 "mm: migrate: provide buffer_migrate_page_norefs()" Signed-off-by: Jan Kara Cc: Sergey Senozhatsky Cc: Pavel Machek Cc: Mel Gorman Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: David Rientjes Cc: Michal Hocko Cc: Zi Yan Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index a16b15090df3b..712b231a73769 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { - get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; @@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { - get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; - put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } return false; @@ -818,7 +814,6 @@ static int __buffer_migrate_page(struct address_space *mapping, bh = head; do { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } while (bh != head); From 9bcdeb51bd7d2ae9fe65ea4d60643d2aeef5bfe3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 1 Feb 2019 14:20:31 -0800 Subject: [PATCH 08/24] oom, oom_reaper: do not enqueue same task twice Arkadiusz reported that enabling memcg's group oom killing causes strange memcg statistics where there is no task in a memcg despite the number of tasks in that memcg is not 0. It turned out that there is a bug in wake_oom_reaper() which allows enqueuing same task twice which makes impossible to decrease the number of tasks in that memcg due to a refcount leak. This bug existed since the OOM reaper became invokable from task_will_free_mem(current) path in out_of_memory() in Linux 4.7, T1@P1 |T2@P1 |T3@P1 |OOM reaper ----------+----------+----------+------------ # Processing an OOM victim in a different memcg domain. try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) try_charge() mem_cgroup_out_of_memory() mutex_lock(&oom_lock) out_of_memory() oom_kill_process(P1) do_send_sig_info(SIGKILL, @P1) mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T2@P1) wake_oom_reaper(T2@P1) # T2@P1 is enqueued. mutex_unlock(&oom_lock) out_of_memory() mark_oom_victim(T1@P1) wake_oom_reaper(T1@P1) # T1@P1 is enqueued again due to oom_reaper_list == T2@P1 && T1@P1->oom_reaper_list == NULL. mutex_unlock(&oom_lock) # Completed processing an OOM victim in a different memcg domain. spin_lock(&oom_reaper_lock) # T1P1 is dequeued. spin_unlock(&oom_reaper_lock) but memcg's group oom killing made it easier to trigger this bug by calling wake_oom_reaper() on the same task from one out_of_memory() request. Fix this bug using an approach used by commit 855b018325737f76 ("oom, oom_reaper: disable oom_reaper for oom_kill_allocating_task"). As a side effect of this patch, this patch also avoids enqueuing multiple threads sharing memory via task_will_free_mem(current) path. Link: http://lkml.kernel.org/r/e865a044-2c10-9858-f4ef-254bc71d6cc2@i-love.sakura.ne.jp Link: http://lkml.kernel.org/r/5ee34fc6-1485-34f8-8790-903ddabaa809@i-love.sakura.ne.jp Fixes: af8e15cc85a25315 ("oom, oom_reaper: do not enqueue task if it is on the oom_reaper_list head") Signed-off-by: Tetsuo Handa Reported-by: Arkadiusz Miskiewicz Tested-by: Arkadiusz Miskiewicz Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Tejun Heo Cc: Aleksa Sarai Cc: Jay Kamat Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/coredump.h | 1 + mm/oom_kill.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f4..ecdc6542070f1 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a8..059e617a18472 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); From efad4e475c312456edb3c789d0996d12ed744c13 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Feb 2019 14:20:34 -0800 Subject: [PATCH 09/24] mm, memory_hotplug: is_mem_section_removable do not pass the end of a zone Patch series "mm, memory_hotplug: fix uninitialized pages fallouts", v2. Mikhail Zaslonko has posted fixes for the two bugs quite some time ago [1]. I have pushed back on those fixes because I believed that it is much better to plug the problem at the initialization time rather than play whack-a-mole all over the hotplug code and find all the places which expect the full memory section to be initialized. We have ended up with commit 2830bf6f05fb ("mm, memory_hotplug: initialize struct pages for the full memory section") merged and cause a regression [2][3]. The reason is that there might be memory layouts when two NUMA nodes share the same memory section so the merged fix is simply incorrect. In order to plug this hole we really have to be zone range aware in those handlers. I have split up the original patch into two. One is unchanged (patch 2) and I took a different approach for `removable' crash. [1] http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com [2] https://bugzilla.redhat.com/show_bug.cgi?id=1666948 [3] http://lkml.kernel.org/r/20190125163938.GA20411@dhcp22.suse.cz This patch (of 2): Mikhail has reported the following VM_BUG_ON triggered when reading sysfs removable state of a memory block: page:000003d08300c000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: is_mem_section_removable+0xb4/0x190 show_mem_removable+0x9a/0xd8 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: is_mem_section_removable+0xb4/0x190 Kernel panic - not syncing: Fatal exception: panic_on_oops The reason is that the memory block spans the zone boundary and we are stumbling over an unitialized struct page. Fix this by enforcing zone range in is_mem_section_removable so that we never run away from a zone. Link: http://lkml.kernel.org/r/20190128144506.15603-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Mikhail Zaslonko Debugged-by: Mikhail Zaslonko Tested-by: Gerald Schaefer Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Cc: Pavel Tatashin Cc: Heiko Carstens Cc: Martin Schwidefsky Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index d7b7d221c284a..91e6fef4cf9f5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { From 24feb47c5fa5b825efb0151f28906dfdad027e61 Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Fri, 1 Feb 2019 14:20:38 -0800 Subject: [PATCH 10/24] mm, memory_hotplug: test_pages_in_a_zone do not pass the end of zone If memory end is not aligned with the sparse memory section boundary, the mapping of such a section is only partly initialized. This may lead to VM_BUG_ON due to uninitialized struct pages access from test_pages_in_a_zone() function triggered by memory_hotplug sysfs handlers. Here are the the panic examples: CONFIG_DEBUG_VM_PGFLAGS=y kernel parameter mem=2050M -------------------------- page:000003d082008000 is uninitialized and poisoned page dumped because: VM_BUG_ON_PAGE(PagePoisoned(p)) Call Trace: test_pages_in_a_zone+0xde/0x160 show_valid_zones+0x5c/0x190 dev_attr_show+0x34/0x70 sysfs_kf_seq_show+0xc8/0x148 seq_read+0x204/0x480 __vfs_read+0x32/0x178 vfs_read+0x82/0x138 ksys_read+0x5a/0xb0 system_call+0xdc/0x2d8 Last Breaking-Event-Address: test_pages_in_a_zone+0xde/0x160 Kernel panic - not syncing: Fatal exception: panic_on_oops Fix this by checking whether the pfn to check is within the zone. [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Link: http://lkml.kernel.org/r/20190128144506.15603-3-mhocko@kernel.org [mhocko@suse.com: separated this change from http://lkml.kernel.org/r/20181105150401.97287-2-zaslonko@linux.ibm.com] Signed-off-by: Michal Hocko Signed-off-by: Mikhail Zaslonko Tested-by: Mikhail Gavrilov Reviewed-by: Oscar Salvador Tested-by: Gerald Schaefer Cc: Heiko Carstens Cc: Martin Schwidefsky Cc: Mikhail Gavrilov Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 91e6fef4cf9f5..ecc5ee04e3016 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1274,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; From 1b69ac6b40ebd85eed73e4dbccde2a36961ab990 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:20:42 -0800 Subject: [PATCH 11/24] psi: fix aggregation idle shut-off psi has provisions to shut off the periodic aggregation worker when there is a period of no task activity - and thus no data that needs aggregating. However, while developing psi monitoring, Suren noticed that the aggregation clock currently won't stay shut off for good. Debugging this revealed a flaw in the idle design: an aggregation run will see no task activity and decide to go to sleep; shortly thereafter, the kworker thread that executed the aggregation will go idle and cause a scheduling change, during which the psi callback will kick the !pending worker again. This will ping-pong forever, and is equivalent to having no shut-off logic at all (but with more code!) Fix this by exempting aggregation workers from psi's clock waking logic when the state change is them going to sleep. To do this, tag workers with the last work function they executed, and if in psi we see a worker going to sleep after aggregating psi data, we will not reschedule the aggregation work item. What if the worker is also executing other items before or after? Any psi state times that were incurred by work items preceding the aggregation work will have been collected from the per-cpu buckets during the aggregation itself. If there are work items following the aggregation work, the worker's last_func tag will be overwritten and the aggregator will be kept alive to process this genuine new activity. If the aggregation work is the last thing the worker does, and we decide to go idle, the brief period of non-idle time incurred between the aggregation run and the kworker's dequeue will be stranded in the per-cpu buckets until the clock is woken by later activity. But that should not be a problem. The buckets can hold 4s worth of time, and future activity will wake the clock with a 2s delay, giving us 2s worth of data we can leave behind when disabling aggregation. If it takes a worker more than two seconds to go idle after it finishes its last work item, we likely have bigger problems in the system, and won't notice one sample that was averaged with a bogus per-CPU weight. Link: http://lkml.kernel.org/r/20190116193501.1910-1-hannes@cmpxchg.org Fixes: eb414681d5a0 ("psi: pressure stall information for CPU, memory, and IO") Signed-off-by: Johannes Weiner Reported-by: Suren Baghdasaryan Acked-by: Tejun Heo Cc: Peter Zijlstra Cc: Lai Jiangshan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/psi.c | 21 +++++++++++++++++---- kernel/workqueue.c | 23 +++++++++++++++++++++++ kernel/workqueue_internal.h | 6 +++++- 3 files changed, 45 insertions(+), 5 deletions(-) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3fbc938..c3484785b1795 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */ +#include "../workqueue_internal.h" #include #include #include @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++; write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); } static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL; if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } } void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 392be4b252f69..fc5d23d752a57 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -909,6 +909,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) return to_wakeup ? to_wakeup->task : NULL; } +/** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self @@ -2184,6 +2204,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 66fbb5a9e633b..cb68b03ca89aa 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -53,6 +53,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ From eeb0efd071d821a88da3fbd35f2d478f40d3b2ea Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 1 Feb 2019 14:20:47 -0800 Subject: [PATCH 12/24] mm,memory_hotplug: fix scan_movable_pages() for gigantic hugepages This is the same sort of error we saw in commit 17e2e7d7e1b8 ("mm, page_alloc: fix has_unmovable_pages for HugePages"). Gigantic hugepages cross several memblocks, so it can be that the page we get in scan_movable_pages() is a page-tail belonging to a 1G-hugepage. If that happens, page_hstate()->size_to_hstate() will return NULL, and we will blow up in hugepage_migration_supported(). The splat is as follows: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 #PF error: [normal kernel read fault] PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 1 PID: 1350 Comm: bash Tainted: G E 5.0.0-rc1-mm1-1-default+ #27 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 RIP: 0010:__offline_pages+0x6ae/0x900 Call Trace: memory_subsys_offline+0x42/0x60 device_offline+0x80/0xa0 state_store+0xab/0xc0 kernfs_fop_write+0x102/0x180 __vfs_write+0x26/0x190 vfs_write+0xad/0x1b0 ksys_write+0x42/0x90 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Modules linked in: af_packet(E) xt_tcpudp(E) ipt_REJECT(E) xt_conntrack(E) nf_conntrack(E) nf_defrag_ipv4(E) ip_set(E) nfnetlink(E) ebtable_nat(E) ebtable_broute(E) bridge(E) stp(E) llc(E) iptable_mangle(E) iptable_raw(E) iptable_security(E) ebtable_filter(E) ebtables(E) iptable_filter(E) ip_tables(E) x_tables(E) kvm_intel(E) kvm(E) irqbypass(E) crct10dif_pclmul(E) crc32_pclmul(E) ghash_clmulni_intel(E) bochs_drm(E) ttm(E) aesni_intel(E) drm_kms_helper(E) aes_x86_64(E) crypto_simd(E) cryptd(E) glue_helper(E) drm(E) virtio_net(E) syscopyarea(E) sysfillrect(E) net_failover(E) sysimgblt(E) pcspkr(E) failover(E) i2c_piix4(E) fb_sys_fops(E) parport_pc(E) parport(E) button(E) btrfs(E) libcrc32c(E) xor(E) zstd_decompress(E) zstd_compress(E) xxhash(E) raid6_pq(E) sd_mod(E) ata_generic(E) ata_piix(E) ahci(E) libahci(E) libata(E) crc32c_intel(E) serio_raw(E) virtio_pci(E) virtio_ring(E) virtio(E) sg(E) scsi_mod(E) autofs4(E) [akpm@linux-foundation.org: fix brace layout, per David. Reduce indentation] Link: http://lkml.kernel.org/r/20190122154407.18417-1-osalvador@suse.de Signed-off-by: Oscar Salvador Reviewed-by: Anthony Yznaga Acked-by: Michal Hocko Reviewed-by: David Hildenbrand Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 36 ++++++++++++++++++++---------------- 1 file changed, 20 insertions(+), 16 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ecc5ee04e3016..a0130633a6e1b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1305,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; - struct page *page; + for (pfn = start; pfn < end; pfn++) { - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageLRU(page)) - return pfn; - if (__PageMovable(page)) - return pfn; - if (PageHuge(page)) { - if (hugepage_migration_supported(page_hstate(page)) && - page_huge_active(page)) - return pfn; - else - pfn = round_up(pfn + 1, - 1 << compound_order(page)) - 1; - } - } + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + return pfn; + if (__PageMovable(page)) + return pfn; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (hugepage_migration_supported(page_hstate(head)) && + page_huge_active(head)) + return pfn; + skip = (1 << compound_order(head)) - (page - head); + pfn += skip - 1; } return 0; } From b13bc35193d9e7a8c050a24928ca5c9e7c9a009b Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 1 Feb 2019 14:20:51 -0800 Subject: [PATCH 13/24] mm/hotplug: invalid PFNs from pfn_to_online_page() On an arm64 ThunderX2 server, the first kmemleak scan would crash [1] with CONFIG_DEBUG_VM_PGFLAGS=y due to page_to_nid() found a pfn that is not directly mapped (MEMBLOCK_NOMAP). Hence, the page->flags is uninitialized. This is due to the commit 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") starts to use pfn_to_online_page() instead of pfn_valid(). However, in the CONFIG_MEMORY_HOTPLUG=y case, pfn_to_online_page() does not call memblock_is_map_memory() while pfn_valid() does. Historically, the commit 68709f45385a ("arm64: only consider memblocks with NOMAP cleared for linear mapping") causes pages marked as nomap being no long reassigned to the new zone in memmap_init_zone() by calling __init_single_page(). Since the commit 2d070eab2e82 ("mm: consider zone which is not fully populated to have holes") introduced pfn_to_online_page() and was designed to return a valid pfn only, but it is clearly broken on arm64. Therefore, let pfn_to_online_page() call pfn_valid_within(), so it can handle nomap thanks to the commit f52bb98f5ade ("arm64: mm: always enable CONFIG_HOLES_IN_ZONE"), while it will be optimized away on architectures where have no HOLES_IN_ZONE. [1] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000006 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 Internal error: Oops: 96000005 [#1] SMP CPU: 60 PID: 1408 Comm: kmemleak Not tainted 5.0.0-rc2+ #8 pstate: 60400009 (nZCv daif +PAN -UAO) pc : page_mapping+0x24/0x144 lr : __dump_page+0x34/0x3dc sp : ffff00003a5cfd10 x29: ffff00003a5cfd10 x28: 000000000000802f x27: 0000000000000000 x26: 0000000000277d00 x25: ffff000010791f56 x24: ffff7fe000000000 x23: ffff000010772f8b x22: ffff00001125f670 x21: ffff000011311000 x20: ffff000010772f8b x19: fffffffffffffffe x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff802698b19600 x13: ffff802698b1a200 x12: ffff802698b16f00 x11: ffff802698b1a400 x10: 0000000000001400 x9 : 0000000000000001 x8 : ffff00001121a000 x7 : 0000000000000000 x6 : ffff0000102c53b8 x5 : 0000000000000000 x4 : 0000000000000003 x3 : 0000000000000100 x2 : 0000000000000000 x1 : ffff000010772f8b x0 : ffffffffffffffff Process kmemleak (pid: 1408, stack limit = 0x(____ptrval____)) Call trace: page_mapping+0x24/0x144 __dump_page+0x34/0x3dc dump_page+0x28/0x4c kmemleak_scan+0x4ac/0x680 kmemleak_scan_thread+0xb4/0xdc kthread+0x12c/0x13c ret_from_fork+0x10/0x18 Code: d503201f f9400660 36000040 d1000413 (f9400661) ---[ end trace 4d4bd7f573490c8e ]--- Kernel panic - not syncing: Fatal exception SMP: stopping secondary CPUs Kernel Offset: disabled CPU features: 0x002,20000c38 Memory Limit: none ---[ end Kernel panic - not syncing: Fatal exception ]--- Link: http://lkml.kernel.org/r/20190122132916.28360-1-cai@lca.pw Fixes: 9f1eb38e0e11 ("mm, kmemleak: little optimization while scanning") Signed-off-by: Qian Cai Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Catalin Marinas Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0f..368267c1b71b1 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* From cefc7ef3c87d02fc9307835868ff721ea12cc597 Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 1 Feb 2019 14:20:54 -0800 Subject: [PATCH 14/24] mm, oom: fix use-after-free in oom_kill_process Syzbot instance running on upstream kernel found a use-after-free bug in oom_kill_process. On further inspection it seems like the process selected to be oom-killed has exited even before reaching read_lock(&tasklist_lock) in oom_kill_process(). More specifically the tsk->usage is 1 which is due to get_task_struct() in oom_evaluate_task() and the put_task_struct within for_each_thread() frees the tsk and for_each_thread() tries to access the tsk. The easiest fix is to do get/put across the for_each_thread() on the selected task. Now the next question is should we continue with the oom-kill as the previously selected task has exited? However before adding more complexity and heuristics, let's answer why we even look at the children of oom-kill selected task? The select_bad_process() has already selected the worst process in the system/memcg. Due to race, the selected process might not be the worst at the kill time but does that matter? The userspace can use the oom_score_adj interface to prefer children to be killed before the parent. I looked at the history but it seems like this is there before git history. Link: http://lkml.kernel.org/r/20190121215850.221745-1-shakeelb@google.com Reported-by: syzbot+7fbbfa368521945f0e3d@syzkaller.appspotmail.com Fixes: 6b0c81b3be11 ("mm, oom: reduce dependency on tasklist_lock") Signed-off-by: Shakeel Butt Reviewed-by: Roman Gushchin Acked-by: Michal Hocko Cc: David Rientjes Cc: Johannes Weiner Cc: Tetsuo Handa Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 059e617a18472..26ea8636758f8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * still freeing memory. */ read_lock(&tasklist_lock); + + /* + * The task 'p' might have already exited before reaching here. The + * put_task_struct() will free task_struct 'p' while the loop still try + * to access the field of 'p', so, get an extra reference. + */ + get_task_struct(p); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } } } + put_task_struct(p); read_unlock(&tasklist_lock); /* From db7ddeab3ce5d64c9696e70d61f45ea9909cd196 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 1 Feb 2019 14:20:58 -0800 Subject: [PATCH 15/24] lib/test_kmod.c: potential double free in error handling There is a copy and paste bug so we set "config->test_driver" to NULL twice instead of setting "config->test_fs". Smatch complains that it leads to a double free: lib/test_kmod.c:840 __kmod_config_init() warn: 'config->test_fs' double freed Link: http://lkml.kernel.org/r/20190121140011.GA14283@kadam Fixes: d9c6a72d6fa2 ("kmod: add test driver to stress test the module loader") Signed-off-by: Dan Carpenter Acked-by: Luis Chamberlain Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/test_kmod.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/test_kmod.c b/lib/test_kmod.c index d82d022111e0e..9cf77628fc913 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) From 980768338488921b15c2f01d67f0324a48ef8625 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jonathan=20Neusch=C3=A4fer?= Date: Fri, 1 Feb 2019 14:21:01 -0800 Subject: [PATCH 16/24] init/Kconfig: fix grammar by moving a closing parenthesis MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Link: http://lkml.kernel.org/r/20190129150813.15785-1-j.neuschaefer@gmx.net Signed-off-by: Jonathan Neuschäfer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/init/Kconfig b/init/Kconfig index 513fa544a134c..354146666d972 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -825,7 +825,7 @@ config CGROUP_PIDS PIDs controller is designed to stop this from happening. It should be noted that organisational operations (such as attaching - to a cgroup hierarchy will *not* be blocked by the PIDs controller), + to a cgroup hierarchy) will *not* be blocked by the PIDs controller, since the PIDs limit only affects a process's ability to fork, not to attach to a cgroup. From 0d0c8de8788b6c441ea01365612de7efc20cc682 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Fri, 1 Feb 2019 14:21:05 -0800 Subject: [PATCH 17/24] kasan: mark file common so ftrace doesn't trace it When option CONFIG_KASAN is enabled toghether with ftrace, function ftrace_graph_caller() gets in to a recursion, via functions kasan_check_read() and kasan_check_write(). Breakpoint 2, ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:179 179 mcount_get_pc x0 // function's pc (gdb) bt #0 ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:179 #1 0xffffff90101406c8 in ftrace_caller () at ../arch/arm64/kernel/entry-ftrace.S:151 #2 0xffffff90106fd084 in kasan_check_write (p=0xffffffc06c170878, size=4) at ../mm/kasan/common.c:105 #3 0xffffff90104a2464 in atomic_add_return (v=, i=) at ./include/generated/atomic-instrumented.h:71 #4 atomic_inc_return (v=) at ./include/generated/atomic-fallback.h:284 #5 trace_graph_entry (trace=0xffffffc03f5ff380) at ../kernel/trace/trace_functions_graph.c:441 #6 0xffffff9010481774 in trace_graph_entry_watchdog (trace=) at ../kernel/trace/trace_selftest.c:741 #7 0xffffff90104a185c in function_graph_enter (ret=, func=, frame_pointer=18446743799894897728, retp=) at ../kernel/trace/trace_functions_graph.c:196 #8 0xffffff9010140628 in prepare_ftrace_return (self_addr=18446743592948977792, parent=0xffffffc03f5ff418, frame_pointer=18446743799894897728) at ../arch/arm64/kernel/ftrace.c:231 #9 0xffffff90101406f4 in ftrace_graph_caller () at ../arch/arm64/kernel/entry-ftrace.S:182 Backtrace stopped: previous frame identical to this frame (corrupt stack?) (gdb) Rework so that the kasan implementation isn't traced. Link: http://lkml.kernel.org/r/20181212183447.15890-1-anders.roxell@linaro.org Signed-off-by: Anders Roxell Acked-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Acked-by: Steven Rostedt (VMware) Cc: Andrey Ryabinin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/Makefile | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 0a14fcff70ed7..e2bb06c1b45e9 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n UBSAN_SANITIZE_tags.o := n KCOV_INSTRUMENT := n +CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 From 6376360ecbe525a9c17b3d081dfd88ba3e4ed65b Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 1 Feb 2019 14:21:08 -0800 Subject: [PATCH 18/24] mm: hwpoison: use do_send_sig_info() instead of force_sig() Currently memory_failure() is racy against process's exiting, which results in kernel crash by null pointer dereference. The root cause is that memory_failure() uses force_sig() to forcibly kill asynchronous (meaning not in the current context) processes. As discussed in thread https://lkml.org/lkml/2010/6/8/236 years ago for OOM fixes, this is not a right thing to do. OOM solves this issue by using do_send_sig_info() as done in commit d2d393099de2 ("signal: oom_kill_task: use SEND_SIG_FORCED instead of force_sig()"), so this patch is suggesting to do the same for hwpoison. do_send_sig_info() properly accesses to siglock with lock_task_sighand(), so is free from the reported race. I confirmed that the reported bug reproduces with inserting some delay in kill_procs(), and it never reproduces with this patch. Note that memory_failure() can send another type of signal using force_sig_mceerr(), and the reported race shouldn't happen on it because force_sig_mceerr() is called only for synchronous processes (i.e. BUS_MCEERR_AR happens only when some process accesses to the corrupted memory.) Link: http://lkml.kernel.org/r/20190116093046.GA29835@hori1.linux.bs1.fc.nec.co.jp Signed-off-by: Naoya Horiguchi Reported-by: Jane Chu Reviewed-by: Dan Williams Reviewed-by: William Kucharski Cc: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory-failure.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7c72f2a95785e..831be5ff5f4df 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); - force_sig(SIGKILL, tk->tsk); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* From e3df4c6e4836ce93cd5cf92d9cbdeaf4439a0241 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 1 Feb 2019 14:21:12 -0800 Subject: [PATCH 19/24] mm, memory_hotplug: __offline_pages fix wrong locking Jan has noticed that we do double unlock on some failure paths when offlining a page range. This is indeed the case when test_pages_in_a_zone respp. start_isolate_page_range fail. This was an omission when forward porting the debugging patch from an older kernel. Fix the issue by dropping mem_hotplug_done from the failure condition and keeping the single unlock in the catch all failure path. Link: http://lkml.kernel.org/r/20190115120307.22768-1-mhocko@kernel.org Fixes: 7960509329c2 ("mm, memory_hotplug: print reason for the offlining failure") Signed-off-by: Michal Hocko Reported-by: Jan Kara Reviewed-by: Jan Kara Tested-by: Jan Kara Reviewed-by: Oscar Salvador Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a0130633a6e1b..124e794867c56 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1570,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { - mem_hotplug_done(); ret = -EINVAL; reason = "multizone range"; goto failed_removal; @@ -1585,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); if (ret) { - mem_hotplug_done(); reason = "failure to isolate range"; goto failed_removal; } From 7b2489d37e1e355228f7c55724f77580e1dec22a Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 1 Feb 2019 14:21:15 -0800 Subject: [PATCH 20/24] psi: clarify the Kconfig text for the default-disable option The current help text caused some confusion in online forums about whether or not to default-enable or default-disable psi in vendor kernels. This is because it doesn't communicate the reason for why we made this setting configurable in the first place: that the overhead is non-zero in an artificial scheduler stress test. Since this isn't representative of real workloads, and the effect was not measurable in scheduler-heavy real world applications such as the webservers and memcache installations at Facebook, it's fair to point out that this is a pretty cautious option to select. Link: http://lkml.kernel.org/r/20190129233617.16767-1-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/init/Kconfig b/init/Kconfig index 354146666d972..c9386a365eea2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -512,6 +512,17 @@ config PSI_DEFAULT_DISABLED per default but can be enabled through passing psi=1 on the kernel commandline during boot. + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION From e0a352fabce61f730341d119fbedf71ffdb8663f Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 1 Feb 2019 14:21:19 -0800 Subject: [PATCH 21/24] mm: migrate: don't rely on __PageMovable() of newpage after unlocking it We had a race in the old balloon compaction code before b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature") refactored it that became visible after backporting 195a8c43e93d ("virtio-balloon: deflate via a page list") without the refactoring. The bug existed from commit d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") till b1123ea6d3b3 ("mm: balloon: use general non-lru movable page feature"). d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") was backported to 3.12, so the broken kernels are stable kernels [3.12 - 4.7]. There was a subtle race between dropping the page lock of the newpage in __unmap_and_move() and checking for __is_movable_balloon_page(newpage). Just after dropping this page lock, virtio-balloon could go ahead and deflate the newpage, effectively dequeueing it and clearing PageBalloon, in turn making __is_movable_balloon_page(newpage) fail. This resulted in dropping the reference of the newpage via putback_lru_page(newpage) instead of put_page(newpage), leading to page->lru getting modified and a !LRU page ending up in the LRU lists. With 195a8c43e93d ("virtio-balloon: deflate via a page list") backported, one would suddenly get corrupted lists in release_pages_balloon(): - WARNING: CPU: 13 PID: 6586 at lib/list_debug.c:59 __list_del_entry+0xa1/0xd0 - list_del corruption. prev->next should be ffffe253961090a0, but was dead000000000100 Nowadays this race is no longer possible, but it is hidden behind very ugly handling of __ClearPageMovable() and __PageMovable(). __ClearPageMovable() will not make __PageMovable() fail, only PageMovable(). So the new check (__PageMovable(newpage)) will still hold even after newpage was dequeued by virtio-balloon. If anybody would ever change that special handling, the BUG would be introduced again. So instead, make it explicit and use the information of the original isolated page before migration. This patch can be backported fairly easy to stable kernels (in contrast to the refactoring). Link: http://lkml.kernel.org/r/20190129233217.10747-1-david@redhat.com Fixes: d6d86c0a7f8d ("mm/balloon_compaction: redesign ballooned pages management") Signed-off-by: David Hildenbrand Reported-by: Vratislav Bendel Acked-by: Michal Hocko Acked-by: Rafael Aquini Cc: Mel Gorman Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Naoya Horiguchi Cc: Jan Kara Cc: Andrea Arcangeli Cc: Dominik Brodowski Cc: Matthew Wilcox Cc: Vratislav Bendel Cc: Rafael Aquini Cc: Konstantin Khlebnikov Cc: Minchan Kim Cc: [3.12 - 4.7] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 712b231a73769..d4fd680be3b0f 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1130,10 +1130,13 @@ static int __unmap_and_move(struct page *page, struct page *newpage, * If migration is successful, decrease refcount of the newpage * which will not free the page because new page owner increased * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(__PageMovable(newpage))) + if (unlikely(!is_lru)) put_page(newpage); else putback_lru_page(newpage); From c27d82f52f75fc9d8d9d40d120d2a96fdeeada5e Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 1 Feb 2019 14:21:23 -0800 Subject: [PATCH 22/24] fs/drop_caches.c: avoid softlockups in drop_pagecache_sb() When superblock has lots of inodes without any pagecache (like is the case for /proc), drop_pagecache_sb() will iterate through all of them without dropping sb->s_inode_list_lock which can lead to softlockups (one of our customers hit this). Fix the problem by going to the slow path and doing cond_resched() in case the process needs rescheduling. Link: http://lkml.kernel.org/r/20190114085343.15011-1-jack@suse.cz Signed-off-by: Jan Kara Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/drop_caches.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f0..d31b6c72b4764 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; From 63ce5f552beb9bdb41546b3a26c4374758b21815 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Fri, 1 Feb 2019 14:21:26 -0800 Subject: [PATCH 23/24] autofs: drop dentry reference only when it is never used autofs_expire_run() calls dput(dentry) to drop the reference count of dentry. However, dentry is read via autofs_dentry_ino(dentry) after that. This may result in a use-free-bug. The patch drops the reference count of dentry only when it is never used. Link: http://lkml.kernel.org/r/154725122396.11260.16053424107144453867.stgit@pluto-themaw-net Signed-off-by: Pan Bian Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/expire.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index d441244b79df9..28d9c2b1b3bb3 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } From f585b283e3f025754c45bbe7533fc6e5c4643700 Mon Sep 17 00:00:00 2001 From: Ian Kent Date: Fri, 1 Feb 2019 14:21:29 -0800 Subject: [PATCH 24/24] autofs: fix error return in autofs_fill_super() In autofs_fill_super() on error of get inode/make root dentry the return should be ENOMEM as this is the only failure case of the called functions. Link: http://lkml.kernel.org/r/154725123240.11260.796773942606871359.stgit@pluto-themaw-net Signed-off-by: Ian Kent Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/autofs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 0e8ea2d9a2bba..078992eee299d 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino;