4a55c0474a
It is not that hard to trigger lockdep splats by calling printk from under zone->lock. Most of them are false positives caused by lock chains introduced early in the boot process and they do not cause any real problems (although most of the early boot lock dependencies could happen after boot as well). There are some console drivers which do allocate from the printk context as well and those should be fixed. In any case, false positives are not that trivial to workaround and it is far from optimal to lose lockdep functionality for something that is a non-issue. So change has_unmovable_pages() so that it no longer calls dump_page() itself - instead it returns a "struct page *" of the unmovable page back to the caller so that in the case of a has_unmovable_pages() failure, the caller can call dump_page() after releasing zone->lock. Also, make dump_page() is able to report a CMA page as well, so the reason string from has_unmovable_pages() can be removed. Even though has_unmovable_pages doesn't hold any reference to the returned page this should be reasonably safe for the purpose of reporting the page (dump_page) because it cannot be hotremoved in the context of memory unplug. The state of the page might change but that is the case even with the existing code as zone->lock only plays role for free pages. While at it, remove a similar but unnecessary debug-only printk() as well. A sample of one of those lockdep splats is, WARNING: possible circular locking dependency detected ------------------------------------------------------ test.sh/8653 is trying to acquire lock: ffffffff865a4460 (console_owner){-.-.}, at: console_unlock+0x207/0x750 but task is already holding lock: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&(&zone->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock+0x2f/0x40 rmqueue_bulk.constprop.21+0xb6/0x1160 get_page_from_freelist+0x898/0x22c0 __alloc_pages_nodemask+0x2f3/0x1cd0 alloc_pages_current+0x9c/0x110 allocate_slab+0x4c6/0x19c0 new_slab+0x46/0x70 ___slab_alloc+0x58b/0x960 __slab_alloc+0x43/0x70 __kmalloc+0x3ad/0x4b0 __tty_buffer_request_room+0x100/0x250 tty_insert_flip_string_fixed_flag+0x67/0x110 pty_write+0xa2/0xf0 n_tty_write+0x36b/0x7b0 tty_write+0x284/0x4c0 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 redirected_tty_write+0x6a/0xc0 do_iter_write+0x248/0x2a0 vfs_writev+0x106/0x1e0 do_writev+0xd4/0x180 __x64_sys_writev+0x45/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #2 (&(&port->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 tty_port_tty_get+0x20/0x60 tty_port_default_wakeup+0xf/0x30 tty_port_tty_wakeup+0x39/0x40 uart_write_wakeup+0x2a/0x40 serial8250_tx_chars+0x22e/0x440 serial8250_handle_irq.part.8+0x14a/0x170 serial8250_default_handle_irq+0x5c/0x90 serial8250_interrupt+0xa6/0x130 __handle_irq_event_percpu+0x78/0x4f0 handle_irq_event_percpu+0x70/0x100 handle_irq_event+0x5a/0x8b handle_edge_irq+0x117/0x370 do_IRQ+0x9e/0x1e0 ret_from_intr+0x0/0x2a cpuidle_enter_state+0x156/0x8e0 cpuidle_enter+0x41/0x70 call_cpuidle+0x5e/0x90 do_idle+0x333/0x370 cpu_startup_entry+0x1d/0x1f start_secondary+0x290/0x330 secondary_startup_64+0xb6/0xc0 -> #1 (&port_lock_key){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 serial8250_console_write+0x3e4/0x450 univ8250_console_write+0x4b/0x60 console_unlock+0x501/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 -> #0 (console_owner){-.-.}: check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Chain exists of: console_owner --> &(&port->lock)->rlock --> &(&zone->lock)->rlock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&zone->lock)->rlock); lock(&(&port->lock)->rlock); lock(&(&zone->lock)->rlock); lock(console_owner); *** DEADLOCK *** 9 locks held by test.sh/8653: #0: ffff88839ba7d408 (sb_writers#4){.+.+}, at: vfs_write+0x25f/0x290 #1: ffff888277618880 (&of->mutex){+.+.}, at: kernfs_fop_write+0x128/0x240 #2: ffff8898131fc218 (kn->count#115){.+.+}, at: kernfs_fop_write+0x138/0x240 #3: ffffffff86962a80 (device_hotplug_lock){+.+.}, at: lock_device_hotplug_sysfs+0x16/0x50 #4: ffff8884374f4990 (&dev->mutex){....}, at: device_offline+0x70/0x110 #5: ffffffff86515250 (cpu_hotplug_lock.rw_sem){++++}, at: __offline_pages+0xbf/0xa10 #6: ffffffff867405f0 (mem_hotplug_lock.rw_sem){++++}, at: percpu_down_write+0x87/0x2f0 #7: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 #8: ffffffff865a4920 (console_lock){+.+.}, at: vprintk_emit+0x100/0x340 stack backtrace: Hardware name: HPE ProLiant DL560 Gen10/ProLiant DL560 Gen10, BIOS U34 05/21/2019 Call Trace: dump_stack+0x86/0xca print_circular_bug.cold.31+0x243/0x26e check_noncircular+0x29e/0x2e0 check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: http://lkml.kernel.org/r/20200117181200.20299-1-cai@lca.pw Signed-off-by: Qian Cai <cai@lca.pw> Reviewed-by: David Hildenbrand <david@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
254 lines
6.4 KiB
C
254 lines
6.4 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* mm/debug.c
|
|
*
|
|
* mm/ specific debug routines.
|
|
*
|
|
*/
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/trace_events.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <trace/events/mmflags.h>
|
|
#include <linux/migrate.h>
|
|
#include <linux/page_owner.h>
|
|
#include <linux/ctype.h>
|
|
|
|
#include "internal.h"
|
|
|
|
const char *migrate_reason_names[MR_TYPES] = {
|
|
"compaction",
|
|
"memory_failure",
|
|
"memory_hotplug",
|
|
"syscall_or_cpuset",
|
|
"mempolicy_mbind",
|
|
"numa_misplaced",
|
|
"cma",
|
|
};
|
|
|
|
const struct trace_print_flags pageflag_names[] = {
|
|
__def_pageflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
const struct trace_print_flags gfpflag_names[] = {
|
|
__def_gfpflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
const struct trace_print_flags vmaflag_names[] = {
|
|
__def_vmaflag_names,
|
|
{0, NULL}
|
|
};
|
|
|
|
void __dump_page(struct page *page, const char *reason)
|
|
{
|
|
struct address_space *mapping;
|
|
bool page_poisoned = PagePoisoned(page);
|
|
/*
|
|
* Accessing the pageblock without the zone lock. It could change to
|
|
* "isolate" again in the meantime, but since we are just dumping the
|
|
* state for debugging, it should be fine to accept a bit of
|
|
* inaccuracy here due to racing.
|
|
*/
|
|
bool page_cma = is_migrate_cma_page(page);
|
|
int mapcount;
|
|
char *type = "";
|
|
|
|
/*
|
|
* If struct page is poisoned don't access Page*() functions as that
|
|
* leads to recursive loop. Page*() check for poisoned pages, and calls
|
|
* dump_page() when detected.
|
|
*/
|
|
if (page_poisoned) {
|
|
pr_warn("page:%px is uninitialized and poisoned", page);
|
|
goto hex_only;
|
|
}
|
|
|
|
mapping = page_mapping(page);
|
|
|
|
/*
|
|
* Avoid VM_BUG_ON() in page_mapcount().
|
|
* page->_mapcount space in struct page is used by sl[aou]b pages to
|
|
* encode own info.
|
|
*/
|
|
mapcount = PageSlab(page) ? 0 : page_mapcount(page);
|
|
|
|
if (PageCompound(page))
|
|
pr_warn("page:%px refcount:%d mapcount:%d mapping:%px "
|
|
"index:%#lx compound_mapcount: %d\n",
|
|
page, page_ref_count(page), mapcount,
|
|
page->mapping, page_to_pgoff(page),
|
|
compound_mapcount(page));
|
|
else
|
|
pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx\n",
|
|
page, page_ref_count(page), mapcount,
|
|
page->mapping, page_to_pgoff(page));
|
|
if (PageKsm(page))
|
|
type = "ksm ";
|
|
else if (PageAnon(page))
|
|
type = "anon ";
|
|
else if (mapping) {
|
|
if (mapping->host && mapping->host->i_dentry.first) {
|
|
struct dentry *dentry;
|
|
dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
|
|
pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry);
|
|
} else
|
|
pr_warn("%ps\n", mapping->a_ops);
|
|
}
|
|
BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
|
|
|
|
pr_warn("%sflags: %#lx(%pGp)%s\n", type, page->flags, &page->flags,
|
|
page_cma ? " CMA" : "");
|
|
|
|
hex_only:
|
|
print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
|
|
sizeof(unsigned long), page,
|
|
sizeof(struct page), false);
|
|
|
|
if (reason)
|
|
pr_warn("page dumped because: %s\n", reason);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
if (!page_poisoned && page->mem_cgroup)
|
|
pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup);
|
|
#endif
|
|
}
|
|
|
|
void dump_page(struct page *page, const char *reason)
|
|
{
|
|
__dump_page(page, reason);
|
|
dump_page_owner(page);
|
|
}
|
|
EXPORT_SYMBOL(dump_page);
|
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
|
|
void dump_vma(const struct vm_area_struct *vma)
|
|
{
|
|
pr_emerg("vma %px start %px end %px\n"
|
|
"next %px prev %px mm %px\n"
|
|
"prot %lx anon_vma %px vm_ops %px\n"
|
|
"pgoff %lx file %px private_data %px\n"
|
|
"flags: %#lx(%pGv)\n",
|
|
vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
|
|
vma->vm_prev, vma->vm_mm,
|
|
(unsigned long)pgprot_val(vma->vm_page_prot),
|
|
vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
|
|
vma->vm_file, vma->vm_private_data,
|
|
vma->vm_flags, &vma->vm_flags);
|
|
}
|
|
EXPORT_SYMBOL(dump_vma);
|
|
|
|
void dump_mm(const struct mm_struct *mm)
|
|
{
|
|
pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n"
|
|
#ifdef CONFIG_MMU
|
|
"get_unmapped_area %px\n"
|
|
#endif
|
|
"mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n"
|
|
"pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
|
|
"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
|
|
"pinned_vm %llx data_vm %lx exec_vm %lx stack_vm %lx\n"
|
|
"start_code %lx end_code %lx start_data %lx end_data %lx\n"
|
|
"start_brk %lx brk %lx start_stack %lx\n"
|
|
"arg_start %lx arg_end %lx env_start %lx env_end %lx\n"
|
|
"binfmt %px flags %lx core_state %px\n"
|
|
#ifdef CONFIG_AIO
|
|
"ioctx_table %px\n"
|
|
#endif
|
|
#ifdef CONFIG_MEMCG
|
|
"owner %px "
|
|
#endif
|
|
"exe_file %px\n"
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
"notifier_subscriptions %px\n"
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
"numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n"
|
|
#endif
|
|
"tlb_flush_pending %d\n"
|
|
"def_flags: %#lx(%pGv)\n",
|
|
|
|
mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size,
|
|
#ifdef CONFIG_MMU
|
|
mm->get_unmapped_area,
|
|
#endif
|
|
mm->mmap_base, mm->mmap_legacy_base, mm->highest_vm_end,
|
|
mm->pgd, atomic_read(&mm->mm_users),
|
|
atomic_read(&mm->mm_count),
|
|
mm_pgtables_bytes(mm),
|
|
mm->map_count,
|
|
mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
|
|
(u64)atomic64_read(&mm->pinned_vm),
|
|
mm->data_vm, mm->exec_vm, mm->stack_vm,
|
|
mm->start_code, mm->end_code, mm->start_data, mm->end_data,
|
|
mm->start_brk, mm->brk, mm->start_stack,
|
|
mm->arg_start, mm->arg_end, mm->env_start, mm->env_end,
|
|
mm->binfmt, mm->flags, mm->core_state,
|
|
#ifdef CONFIG_AIO
|
|
mm->ioctx_table,
|
|
#endif
|
|
#ifdef CONFIG_MEMCG
|
|
mm->owner,
|
|
#endif
|
|
mm->exe_file,
|
|
#ifdef CONFIG_MMU_NOTIFIER
|
|
mm->notifier_subscriptions,
|
|
#endif
|
|
#ifdef CONFIG_NUMA_BALANCING
|
|
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
|
|
#endif
|
|
atomic_read(&mm->tlb_flush_pending),
|
|
mm->def_flags, &mm->def_flags
|
|
);
|
|
}
|
|
|
|
static bool page_init_poisoning __read_mostly = true;
|
|
|
|
static int __init setup_vm_debug(char *str)
|
|
{
|
|
bool __page_init_poisoning = true;
|
|
|
|
/*
|
|
* Calling vm_debug with no arguments is equivalent to requesting
|
|
* to enable all debugging options we can control.
|
|
*/
|
|
if (*str++ != '=' || !*str)
|
|
goto out;
|
|
|
|
__page_init_poisoning = false;
|
|
if (*str == '-')
|
|
goto out;
|
|
|
|
while (*str) {
|
|
switch (tolower(*str)) {
|
|
case'p':
|
|
__page_init_poisoning = true;
|
|
break;
|
|
default:
|
|
pr_err("vm_debug option '%c' unknown. skipped\n",
|
|
*str);
|
|
}
|
|
|
|
str++;
|
|
}
|
|
out:
|
|
if (page_init_poisoning && !__page_init_poisoning)
|
|
pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n");
|
|
|
|
page_init_poisoning = __page_init_poisoning;
|
|
|
|
return 1;
|
|
}
|
|
__setup("vm_debug", setup_vm_debug);
|
|
|
|
void page_init_poison(struct page *page, size_t size)
|
|
{
|
|
if (page_init_poisoning)
|
|
memset(page, PAGE_POISON_PATTERN, size);
|
|
}
|
|
EXPORT_SYMBOL_GPL(page_init_poison);
|
|
#endif /* CONFIG_DEBUG_VM */
|