From 2b97cf76289a4fcae66d7959b0d74a87207d7068 Mon Sep 17 00:00:00 2001 From: Hao Jia Date: Sat, 6 Aug 2022 20:05:08 +0800 Subject: sched/psi: Zero the memory of struct psi_group After commit 5f69a6577bc3 ("psi: dont alloc memory for psi by default"), the memory used by struct psi_group is no longer allocated and zeroed in cgroup_create(). Since the memory of struct psi_group is not zeroed, the data in this memory is random, which will lead to inaccurate psi statistics when creating a new cgroup. So we use kzlloc() to allocate and zero the struct psi_group and remove the redundant zeroing in group_init(). Steps to reproduce: 1. Use cgroup v2 and enable CONFIG_PSI 2. Create a new cgroup, and query psi statistics mkdir /sys/fs/cgroup/test cat /sys/fs/cgroup/test/cpu.pressure some avg10=0.00 avg60=0.00 avg300=47927752200.00 total=12884901 full avg10=561815124.00 avg60=125835394188.00 avg300=1077090462000.00 total=10273561772 cat /sys/fs/cgroup/test/io.pressure some avg10=1040093132823.95 avg60=1203770351379.21 avg300=3862252669559.46 total=4294967296 full avg10=921884564601.39 avg60=0.00 avg300=1984507298.35 total=442381631 cat /sys/fs/cgroup/test/memory.pressure some avg10=232476085778.11 avg60=0.00 avg300=0.00 total=0 full avg10=0.00 avg60=0.00 avg300=2585658472280.57 total=12884901 Fixes: commit 5f69a6577bc3 ("psi: dont alloc memory for psi by default") Signed-off-by: Hao Jia Reviewed-by: Ingo Molnar Acked-by: Johannes Weiner Signed-off-by: Tejun Heo --- kernel/sched/psi.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index ec66b40bdd40..5ee615a59fe1 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -190,12 +190,8 @@ static void group_init(struct psi_group *group) /* Init trigger-related members */ mutex_init(&group->trigger_lock); INIT_LIST_HEAD(&group->triggers); - memset(group->nr_triggers, 0, sizeof(group->nr_triggers)); - group->poll_states = 0; group->poll_min_period = U32_MAX; - memset(group->polling_total, 0, sizeof(group->polling_total)); group->polling_next_update = ULLONG_MAX; - group->polling_until = 0; init_waitqueue_head(&group->poll_wait); timer_setup(&group->poll_timer, poll_timer_fn, 0); rcu_assign_pointer(group->poll_task, NULL); @@ -957,7 +953,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) if (static_branch_likely(&psi_disabled)) return 0; - cgroup->psi = kmalloc(sizeof(struct psi_group), GFP_KERNEL); + cgroup->psi = kzalloc(sizeof(struct psi_group), GFP_KERNEL); if (!cgroup->psi) return -ENOMEM; -- cgit v1.2.3 From 76b079ef4cc954fc2c2e0333a01855b0b2b6bdee Mon Sep 17 00:00:00 2001 From: Hao Jia Date: Sat, 6 Aug 2022 20:05:09 +0800 Subject: sched/psi: Remove unused parameter nbytes of psi_trigger_create() psi_trigger_create()'s 'nbytes' parameter is not used, so we can remove it. Signed-off-by: Hao Jia Reviewed-by: Ingo Molnar Acked-by: Johannes Weiner Signed-off-by: Tejun Heo --- include/linux/psi.h | 2 +- kernel/cgroup/cgroup.c | 2 +- kernel/sched/psi.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/sched') diff --git a/include/linux/psi.h b/include/linux/psi.h index 89784763d19e..dd74411ac21d 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -27,7 +27,7 @@ void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res); + char *buf, enum psi_res res); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index ffaccd6373f1..df7df5843b4f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3698,7 +3698,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_ino(cgrp) == 1 ? &psi_system : cgrp->psi; - new = psi_trigger_create(psi, buf, nbytes, res); + new = psi_trigger_create(psi, buf, res); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 5ee615a59fe1..ecb4b4ff4ce0 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1087,7 +1087,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) } struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, size_t nbytes, enum psi_res res) + char *buf, enum psi_res res) { struct psi_trigger *t; enum psi_states state; @@ -1316,7 +1316,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, nbytes, res); + new = psi_trigger_create(&psi_system, buf, res); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); -- cgit v1.2.3 From 8238b4579866b7c1bb99883cfe102a43db5506ff Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Fri, 26 Aug 2022 09:17:08 -0400 Subject: wait_on_bit: add an acquire memory barrier There are several places in the kernel where wait_on_bit is not followed by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read). On architectures with weak memory ordering, it may happen that memory accesses that follow wait_on_bit are reordered before wait_on_bit and they may return invalid data. Fix this class of bugs by introducing a new function "test_bit_acquire" that works like test_bit, but has acquire memory ordering semantics. Signed-off-by: Mikulas Patocka Acked-by: Will Deacon Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds --- Documentation/atomic_bitops.txt | 10 ++++------ arch/x86/include/asm/bitops.h | 21 +++++++++++++++++++++ include/asm-generic/bitops/generic-non-atomic.h | 14 ++++++++++++++ .../asm-generic/bitops/instrumented-non-atomic.h | 12 ++++++++++++ include/asm-generic/bitops/non-atomic.h | 1 + .../bitops/non-instrumented-non-atomic.h | 1 + include/linux/bitops.h | 1 + include/linux/buffer_head.h | 2 +- include/linux/wait_bit.h | 8 ++++---- kernel/sched/wait_bit.c | 2 +- 10 files changed, 60 insertions(+), 12 deletions(-) (limited to 'kernel/sched') diff --git a/Documentation/atomic_bitops.txt b/Documentation/atomic_bitops.txt index d8b101c97031..edea4656c5c0 100644 --- a/Documentation/atomic_bitops.txt +++ b/Documentation/atomic_bitops.txt @@ -58,13 +58,11 @@ Like with atomic_t, the rule of thumb is: - RMW operations that have a return value are fully ordered. - - RMW operations that are conditional are unordered on FAILURE, - otherwise the above rules apply. In the case of test_and_set_bit_lock(), - if the bit in memory is unchanged by the operation then it is deemed to have - failed. + - RMW operations that are conditional are fully ordered. -Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics and -clear_bit_unlock() which has RELEASE semantics. +Except for a successful test_and_set_bit_lock() which has ACQUIRE semantics, +clear_bit_unlock() which has RELEASE semantics and test_bit_acquire which has +ACQUIRE semantics. Since a platform only has a single means of achieving atomic operations the same barriers as for atomic_t are used, see atomic_t.txt. diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 973c6bd17f98..0fe9de58af31 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -207,6 +207,20 @@ static __always_inline bool constant_test_bit(long nr, const volatile unsigned l (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } +static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + CC_SET(nz) + : CC_OUT(nz) (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + :"memory"); + + return oldbit; +} + static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) { bool oldbit; @@ -226,6 +240,13 @@ arch_test_bit(unsigned long nr, const volatile unsigned long *addr) variable_test_bit(nr, addr); } +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + /** * __ffs - find first set bit in word * @word: The word to search diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h index 3d5ebd24652b..564a8c675d85 100644 --- a/include/asm-generic/bitops/generic-non-atomic.h +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -4,6 +4,7 @@ #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H #include +#include #ifndef _LINUX_BITOPS_H #error only can be included directly @@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr) return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } +/** + * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1))); +} + /* * const_*() definitions provide good compile-time optimizations when * the passed arguments can be resolved at compile time. @@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr) #define const___test_and_set_bit generic___test_and_set_bit #define const___test_and_clear_bit generic___test_and_clear_bit #define const___test_and_change_bit generic___test_and_change_bit +#define const_test_bit_acquire generic_test_bit_acquire /** * const_test_bit - Determine whether a bit is set diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 988a3bbfba34..2b238b161a62 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volatile unsigned long *addr) return arch_test_bit(nr, addr); } +/** + * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_bit_acquire(nr, addr); +} + #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h index 5c37ced343ae..71f8d54a5195 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -13,6 +13,7 @@ #define arch___test_and_change_bit generic___test_and_change_bit #define arch_test_bit generic_test_bit +#define arch_test_bit_acquire generic_test_bit_acquire #include diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h index bdb9b1ffaee9..0ddc78dfc358 100644 --- a/include/asm-generic/bitops/non-instrumented-non-atomic.h +++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h @@ -12,5 +12,6 @@ #define ___test_and_change_bit arch___test_and_change_bit #define _test_bit arch_test_bit +#define _test_bit_acquire arch_test_bit_acquire #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index cf9bf65039f2..3b89c64bcfd8 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w); #define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) #define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) #define test_bit(nr, addr) bitop(_test_bit, nr, addr) +#define test_bit_acquire(nr, addr) bitop(_test_bit_acquire, nr, addr) /* * Include this here because some architectures need generic_ffs/fls in diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index def8b8d30ccc..089c9ade4325 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -156,7 +156,7 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh) * make it consistent with folio_test_uptodate * pairs with smp_mb__before_atomic in set_buffer_uptodate */ - return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0; + return test_bit_acquire(BH_Uptodate, &bh->b_state); } #define bh_offset(bh) ((unsigned long)(bh)->b_data & ~PAGE_MASK) diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h index 7dec36aecbd9..7725b7579b78 100644 --- a/include/linux/wait_bit.h +++ b/include/linux/wait_bit.h @@ -71,7 +71,7 @@ static inline int wait_on_bit(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait, @@ -96,7 +96,7 @@ static inline int wait_on_bit_io(unsigned long *word, int bit, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, bit_wait_io, @@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode, unsigned long timeout) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit_timeout(word, bit, bit_wait_timeout, @@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action, unsigned mode) { might_sleep(); - if (!test_bit(bit, word)) + if (!test_bit_acquire(bit, word)) return 0; return out_of_line_wait_on_bit(word, bit, action, mode); } diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c index d4788f810b55..0b1cd985dc27 100644 --- a/kernel/sched/wait_bit.c +++ b/kernel/sched/wait_bit.c @@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_ prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode); if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) ret = (*action)(&wbq_entry->key, mode); - } while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); + } while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret); finish_wait(wq_head, &wbq_entry->wq_entry); -- cgit v1.2.3 From c2e406596571659451f4b95e37ddfd5a8ef1d0dc Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Sep 2022 14:31:07 +0200 Subject: sched/debug: fix dentry leak in update_sched_domain_debugfs Kuyo reports that the pattern of using debugfs_remove(debugfs_lookup()) leaks a dentry and with a hotplug stress test, the machine eventually runs out of memory. Fix this up by using the newly created debugfs_lookup_and_remove() call instead which properly handles the dentry reference counting logic. Cc: Major Chen Cc: stable Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Juri Lelli Cc: Vincent Guittot Cc: Dietmar Eggemann Cc: Steven Rostedt Cc: Ben Segall Cc: Mel Gorman Cc: Daniel Bristot de Oliveira Cc: Valentin Schneider Cc: Matthias Brugger Reported-by: Kuyo Chang Tested-by: Kuyo Chang Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20220902123107.109274-2-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- kernel/sched/debug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/sched') diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index bb3d63bdf4ae..667876da8382 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -416,7 +416,7 @@ void update_sched_domain_debugfs(void) char buf[32]; snprintf(buf, sizeof(buf), "cpu%d", cpu); - debugfs_remove(debugfs_lookup(buf, sd_dentry)); + debugfs_lookup_and_remove(buf, sd_dentry); d_cpu = debugfs_create_dir(buf, sd_dentry); i = 0; -- cgit v1.2.3