From: ZhangPeng zhangpeng362@huawei.com
Backport vmalloc 2 bugfix for OLK-6.6.
Uladzislau Rezki (Sony) (1): mm: vmalloc: fix lockdep warning
rulinhuang (1): mm/vmalloc: eliminated the lock contention from twice to once
mm/vmalloc.c | 123 +++++++++++++++++++++++++++------------------------ 1 file changed, 65 insertions(+), 58 deletions(-)
From: rulinhuang rulin.huang@intel.com
mainline inclusion from mainline-v6.10-rc1 commit aaab830ad887629156ef17097c2ad24ce6fb8177 category: performance bugzilla: https://gitee.com/openeuler/kernel/issues/IAI0KD CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
When allocating a new memory area where the mapping address range is known, it is observed that the vmap_node->busy.lock is acquired twice.
The first acquisition occurs in the alloc_vmap_area() function when inserting the vm area into the vm mapping red-black tree. The second acquisition occurs in the setup_vmalloc_vm() function when updating the properties of the vm, such as flags and address, etc.
Combine these two operations together in alloc_vmap_area(), which improves scalability when the vmap_node->busy.lock is contended. By doing so, the need to acquire the lock twice can also be eliminated to once.
With the above change, tested on intel sapphire rapids platform(224 vcpu), a 4% performance improvement is gained on stress-ng/pthread(https://github.com/ColinIanKing/stress-ng), which is the stress test of thread creations.
Link: https://lkml.kernel.org/r/20240307021440.64967-1-rulin.huang@intel.com Co-developed-by: "Chen, Tim C" tim.c.chen@intel.com Signed-off-by: "Chen, Tim C" tim.c.chen@intel.com Co-developed-by: "King, Colin" colin.king@intel.com Signed-off-by: "King, Colin" colin.king@intel.com Signed-off-by: rulinhuang rulin.huang@intel.com Reviewed-by: Baoquan He bhe@redhat.com Reviewed-by: Uladzislau Rezki (Sony) urezki@gmail.com Cc: Tim Chen tim.c.chen@linux.intel.com Cc: Christoph Hellwig hch@infradead.org Cc: Lorenzo Stoakes lstoakes@gmail.com Cc: Wangyang Guo wangyang.guo@intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: ZhangPeng zhangpeng362@huawei.com --- mm/vmalloc.c | 50 ++++++++++++++++++++++---------------------------- 1 file changed, 22 insertions(+), 28 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 099ba16f81dc..5a2cdcfaa9fb 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1913,15 +1913,26 @@ node_alloc(unsigned long size, unsigned long align, return va; }
+static inline void setup_vmalloc_vm(struct vm_struct *vm, + struct vmap_area *va, unsigned long flags, const void *caller) +{ + vm->flags = flags; + vm->addr = (void *)va->va_start; + vm->size = va->va_end - va->va_start; + vm->caller = caller; + va->vm = vm; +} + /* * Allocate a region of KVA of the specified size and alignment, within the - * vstart and vend. + * vstart and vend. If vm is passed in, the two will also be bound. */ static struct vmap_area *alloc_vmap_area(unsigned long size, unsigned long align, unsigned long vstart, unsigned long vend, int node, gfp_t gfp_mask, - unsigned long va_flags) + unsigned long va_flags, struct vm_struct *vm, + unsigned long flags, const void *caller) { struct vmap_node *vn; struct vmap_area *va; @@ -1984,6 +1995,9 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, va->vm = NULL; va->flags = (va_flags | vn_id);
+ if (vm) + setup_vmalloc_vm(vm, va, flags, caller); + vn = addr_to_node(va->va_start);
spin_lock(&vn->busy.lock); @@ -2570,7 +2584,8 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask) va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE, VMALLOC_START, VMALLOC_END, node, gfp_mask, - VMAP_RAM|VMAP_BLOCK); + VMAP_RAM|VMAP_BLOCK, NULL, + 0, NULL); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); @@ -2935,7 +2950,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, VMALLOC_START, VMALLOC_END, - node, GFP_KERNEL, VMAP_RAM); + node, GFP_KERNEL, VMAP_RAM, + NULL, 0, NULL); if (IS_ERR(va)) return NULL;
@@ -3038,26 +3054,6 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align) kasan_populate_early_vm_area_shadow(vm->addr, vm->size); }
-static inline void setup_vmalloc_vm_locked(struct vm_struct *vm, - struct vmap_area *va, unsigned long flags, const void *caller) -{ - vm->flags = flags; - vm->addr = (void *)va->va_start; - vm->size = va->va_end - va->va_start; - vm->caller = caller; - va->vm = vm; -} - -static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, - unsigned long flags, const void *caller) -{ - struct vmap_node *vn = addr_to_node(va->va_start); - - spin_lock(&vn->busy.lock); - setup_vmalloc_vm_locked(vm, va, flags, caller); - spin_unlock(&vn->busy.lock); -} - static void clear_vm_uninitialized_flag(struct vm_struct *vm) { /* @@ -3094,14 +3090,12 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (!(flags & VM_NO_GUARD)) size += PAGE_SIZE;
- va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area, flags, caller); if (IS_ERR(va)) { kfree(area); return NULL; }
- setup_vmalloc_vm(area, va, flags, caller); - /* * Mark pages for non-VM_ALLOC mappings as accessible. Do it now as a * best-effort approach, as they can be mapped outside of vmalloc code. @@ -4680,7 +4674,7 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
spin_lock(&vn->busy.lock); insert_vmap_area(vas[area], &vn->busy.root, &vn->busy.head); - setup_vmalloc_vm_locked(vms[area], vas[area], VM_ALLOC, + setup_vmalloc_vm(vms[area], vas[area], VM_ALLOC, pcpu_get_vm_areas); spin_unlock(&vn->busy.lock); }
From: "Uladzislau Rezki (Sony)" urezki@gmail.com
mainline inclusion from mainline-v6.9-rc3 commit fc2c22693c608125bbce174c1952eb4db2f8d07f category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAI0KD CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
A lockdep reports a possible deadlock in the find_vmap_area_exceed_addr_lock() function:
============================================ WARNING: possible recursive locking detected 6.9.0-rc1-00060-ged3ccc57b108-dirty #6140 Not tainted -------------------------------------------- drgn/455 is trying to acquire lock: ffff0000c00131d0 (&vn->busy.lock/1){+.+.}-{2:2}, at: find_vmap_area_exceed_addr_lock+0x64/0x124
but task is already holding lock: ffff0000c0011878 (&vn->busy.lock/1){+.+.}-{2:2}, at: find_vmap_area_exceed_addr_lock+0x64/0x124
other info that might help us debug this: Possible unsafe locking scenario:
CPU0 ---- lock(&vn->busy.lock/1); lock(&vn->busy.lock/1);
*** DEADLOCK ***
indeed it can happen if the find_vmap_area_exceed_addr_lock() gets called concurrently because it tries to acquire two nodes locks. It was done to prevent removing a lowest VA found on a previous step.
To address this a lowest VA is found first without holding a node lock where it resides. As a last step we check if a VA still there because it can go away, if removed, proceed with next lowest.
[akpm@linux-foundation.org: fix comment typos, per Baoquan] Link: https://lkml.kernel.org/r/20240328140330.4747-1-urezki@gmail.com Fixes: 53becf32aec1 ("mm: vmalloc: support multiple nodes in vread_iter") Signed-off-by: Uladzislau Rezki (Sony) urezki@gmail.com Tested-by: Jens Axboe axboe@kernel.dk Tested-by: Omar Sandoval osandov@fb.com Reported-by: Jens Axboe axboe@kernel.dk Cc: Baoquan He bhe@redhat.com Cc: Christoph Hellwig hch@infradead.org Cc: Dave Chinner david@fromorbit.com Cc: Lorenzo Stoakes lstoakes@gmail.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Oleksiy Avramchenko oleksiy.avramchenko@sony.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: ZhangPeng zhangpeng362@huawei.com --- mm/vmalloc.c | 73 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 30 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 5a2cdcfaa9fb..d7ffe8ef8d87 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -989,6 +989,27 @@ unsigned long vmalloc_nr_pages(void) return atomic_long_read(&nr_vmalloc_pages); }
+static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) +{ + struct rb_node *n = root->rb_node; + + addr = (unsigned long)kasan_reset_tag((void *)addr); + + while (n) { + struct vmap_area *va; + + va = rb_entry(n, struct vmap_area, rb_node); + if (addr < va->va_start) + n = n->rb_left; + else if (addr >= va->va_end) + n = n->rb_right; + else + return va; + } + + return NULL; +} + /* Look up the first VA which satisfies addr < va_end, NULL if none. */ static struct vmap_area * __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) @@ -1025,47 +1046,39 @@ __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root) static struct vmap_node * find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va) { - struct vmap_node *vn, *va_node = NULL; - struct vmap_area *va_lowest; + unsigned long va_start_lowest; + struct vmap_node *vn; int i;
- for (i = 0; i < nr_vmap_nodes; i++) { +repeat: + for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) { vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock); - va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root); - if (va_lowest) { - if (!va_node || va_lowest->va_start < (*va)->va_start) { - if (va_node) - spin_unlock(&va_node->busy.lock); - - *va = va_lowest; - va_node = vn; - continue; - } - } + *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root); + + if (*va) + if (!va_start_lowest || (*va)->va_start < va_start_lowest) + va_start_lowest = (*va)->va_start; spin_unlock(&vn->busy.lock); }
- return va_node; -} - -static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root) -{ - struct rb_node *n = root->rb_node; + /* + * Check if found VA exists, it might have gone away. In this case we + * repeat the search because a VA has been removed concurrently and we + * need to proceed to the next one, which is a rare case. + */ + if (va_start_lowest) { + vn = addr_to_node(va_start_lowest);
- addr = (unsigned long)kasan_reset_tag((void *)addr); + spin_lock(&vn->busy.lock); + *va = __find_vmap_area(va_start_lowest, &vn->busy.root);
- while (n) { - struct vmap_area *va; + if (*va) + return vn;
- va = rb_entry(n, struct vmap_area, rb_node); - if (addr < va->va_start) - n = n->rb_left; - else if (addr >= va->va_end) - n = n->rb_right; - else - return va; + spin_unlock(&vn->busy.lock); + goto repeat; }
return NULL;
反馈: 您发送到kernel@openeuler.org的补丁/补丁集,已成功转换为PR! PR链接地址: https://gitee.com/openeuler/kernel/pulls/10729 邮件列表地址:https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/4...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/10729 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/4...