Commit 58b99a00 authored by rulinhuang's avatar rulinhuang Committed by Peng Zhang
Browse files

mm/vmalloc: eliminated the lock contention from twice to once 

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/?id=aaab830ad887629156ef17097c2ad24ce6fb8177

--------------------------------

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: default avatar"Chen, Tim C" <tim.c.chen@intel.com>
Signed-off-by: default avatar"Chen, Tim C" <tim.c.chen@intel.com>
Co-developed-by: default avatar"King, Colin" <colin.king@intel.com>
Signed-off-by: default avatar"King, Colin" <colin.king@intel.com>
Signed-off-by: default avatarrulinhuang <rulin.huang@intel.com>
Reviewed-by: default avatarBaoquan He <bhe@redhat.com>
Reviewed-by: default avatarUladzislau 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarZhangPeng <zhangpeng362@huawei.com>
parent d59a335b

mm/vmalloc.c

+22 −28
Original line number Diff line number Diff line
@@ -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);

	}