Commit 3e43e260 authored by Lorenzo Stoakes's avatar Lorenzo Stoakes Committed by Andrew Morton
Browse files

mm: perform VMA allocation, freeing, duplication in mm 

Right now these are performed in kernel/fork.c which is odd and a
violation of separation of concerns, as well as preventing us from
integrating this and related logic into userland VMA testing going
forward.

There is a fly in the ointment - nommu - mmap.c is not compiled if
CONFIG_MMU not set, and neither is vma.c.

To square the circle, let's add a new file - vma_init.c.  This will be
compiled for both CONFIG_MMU and nommu builds, and will also form part of
the VMA userland testing.

This allows us to de-duplicate code, while maintaining separation of
concerns and the ability for us to userland test this logic.

Update the VMA userland tests accordingly, additionally adding a
detach_free_vma() helper function to correctly detach VMAs before freeing
them in test code, as this change was triggering the assert for this.

[akpm@linux-foundation.org: remove stray newline, per Liam]
Link: https://lkml.kernel.org/r/f97b3a85a6da0196b28070df331b99e22b263be8.1745853549.git.lorenzo.stoakes@oracle.com


Signed-off-by: default avatarLorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: default avatarLiam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: default avatarPedro Falcato <pfalcato@suse.de>
Reviewed-by: default avatarDavid Hildenbrand <david@redhat.com>
Reviewed-by: default avatarKees Cook <kees@kernel.org>
Reviewed-by: default avatarSuren Baghdasaryan <surenb@google.com>
Reviewed-by: default avatarVlastimil Babka <vbabka@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
parent 26a8f577

MAINTAINERS

+1 −0
Original line number Diff line number Diff line
@@ -15683,6 +15683,7 @@ F: mm/mseal.c 
F:	mm/vma.c

F:	mm/vma.h

F:	mm/vma_exec.c

F:	mm/vma_init.c

F:	mm/vma_internal.h

F:	tools/testing/selftests/mm/merge.c

F:	tools/testing/vma/

kernel/fork.c

+0 −88
Original line number Diff line number Diff line
@@ -431,88 +431,9 @@ struct kmem_cache *files_cachep; 
/* SLAB cache for fs_struct structures (tsk->fs) */

struct kmem_cache *fs_cachep;



/* SLAB cache for vm_area_struct structures */

static struct kmem_cache *vm_area_cachep;



/* SLAB cache for mm_struct structures (tsk->mm) */

static struct kmem_cache *mm_cachep;



struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)

{

	struct vm_area_struct *vma;



	vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);

	if (!vma)

		return NULL;



	vma_init(vma, mm);



	return vma;

}



static void vm_area_init_from(const struct vm_area_struct *src,

			      struct vm_area_struct *dest)

{

	dest->vm_mm = src->vm_mm;

	dest->vm_ops = src->vm_ops;

	dest->vm_start = src->vm_start;

	dest->vm_end = src->vm_end;

	dest->anon_vma = src->anon_vma;

	dest->vm_pgoff = src->vm_pgoff;

	dest->vm_file = src->vm_file;

	dest->vm_private_data = src->vm_private_data;

	vm_flags_init(dest, src->vm_flags);

	memcpy(&dest->vm_page_prot, &src->vm_page_prot,

	       sizeof(dest->vm_page_prot));

	/*

	 * src->shared.rb may be modified concurrently when called from

	 * dup_mmap(), but the clone will reinitialize it.

	 */

	data_race(memcpy(&dest->shared, &src->shared, sizeof(dest->shared)));

	memcpy(&dest->vm_userfaultfd_ctx, &src->vm_userfaultfd_ctx,

	       sizeof(dest->vm_userfaultfd_ctx));

#ifdef CONFIG_ANON_VMA_NAME

	dest->anon_name = src->anon_name;

#endif

#ifdef CONFIG_SWAP

	memcpy(&dest->swap_readahead_info, &src->swap_readahead_info,

	       sizeof(dest->swap_readahead_info));

#endif

#ifndef CONFIG_MMU

	dest->vm_region = src->vm_region;

#endif

#ifdef CONFIG_NUMA

	dest->vm_policy = src->vm_policy;

#endif

}



struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)

{

	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);



	if (!new)

		return NULL;



	ASSERT_EXCLUSIVE_WRITER(orig->vm_flags);

	ASSERT_EXCLUSIVE_WRITER(orig->vm_file);

	vm_area_init_from(orig, new);

	vma_lock_init(new, true);

	INIT_LIST_HEAD(&new->anon_vma_chain);

	vma_numab_state_init(new);

	dup_anon_vma_name(orig, new);



	return new;

}



void vm_area_free(struct vm_area_struct *vma)

{

	/* The vma should be detached while being destroyed. */

	vma_assert_detached(vma);

	vma_numab_state_free(vma);

	free_anon_vma_name(vma);

	kmem_cache_free(vm_area_cachep, vma);

}



static void account_kernel_stack(struct task_struct *tsk, int account)

{

	if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -3033,11 +2954,6 @@ void __init mm_cache_init(void) 


void __init proc_caches_init(void)

{

	struct kmem_cache_args args = {

		.use_freeptr_offset = true,

		.freeptr_offset = offsetof(struct vm_area_struct, vm_freeptr),

	};



	sighand_cachep = kmem_cache_create("sighand_cache",

			sizeof(struct sighand_struct), 0,

			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3054,10 +2970,6 @@ void __init proc_caches_init(void) 
			sizeof(struct fs_struct), 0,

			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,

			NULL);

	vm_area_cachep = kmem_cache_create("vm_area_struct",

			sizeof(struct vm_area_struct), &args,

			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|

			SLAB_ACCOUNT);

	mmap_init();

	nsproxy_cache_init();

}

mm/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -55,7 +55,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ 
			   mm_init.o percpu.o slab_common.o \

			   compaction.o show_mem.o \

			   interval_tree.o list_lru.o workingset.o \

			   debug.o gup.o mmap_lock.o $(mmu-y)

			   debug.o gup.o mmap_lock.o vma_init.o $(mmu-y)



# Give 'page_alloc' its own module-parameter namespace

page-alloc-y := page_alloc.o

mm/mmap.c

+2 −1
Original line number Diff line number Diff line
@@ -1554,7 +1554,7 @@ static const struct ctl_table mmap_table[] = { 
#endif /* CONFIG_SYSCTL */



/*

 * initialise the percpu counter for VM

 * initialise the percpu counter for VM, initialise VMA state.

 */

void __init mmap_init(void)

{
@@ -1565,6 +1565,7 @@ void __init mmap_init(void) 
#ifdef CONFIG_SYSCTL

	register_sysctl_init("vm", mmap_table);

#endif

	vma_state_init();

}



/*

mm/nommu.c

+3 −1
Original line number Diff line number Diff line
@@ -399,7 +399,8 @@ static const struct ctl_table nommu_table[] = { 
};



/*

 * initialise the percpu counter for VM and region record slabs

 * initialise the percpu counter for VM and region record slabs, initialise VMA

 * state.

 */

void __init mmap_init(void)

{
@@ -409,6 +410,7 @@ void __init mmap_init(void) 
	VM_BUG_ON(ret);

	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC|SLAB_ACCOUNT);

	register_sysctl_init("vm", nommu_table);

	vma_state_init();

}



/*