Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Uladzislau Rezki <urezki@gmail.com>
Date:   Tue, 16 Jul 2019 17:58:29 +0200
To:     Pengfei Li <lpf.vector@gmail.com>
Cc:     akpm@linux-foundation.org, willy@infradead.org, urezki@gmail.com,
        rpenyaev@suse.de, peterz@infradead.org, guro@fb.com,
        rick.p.edgecombe@intel.com, rppt@linux.ibm.com,
        aryabinin@virtuozzo.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH v6 2/2] mm/vmalloc: modify struct vmap_area to reduce its
 size
Message-ID: <20190716155829.zdrzadrmwxrkfkro@pc636>
References: <20190716152656.12255-1-lpf.vector@gmail.com>
 <20190716152656.12255-3-lpf.vector@gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190716152656.12255-3-lpf.vector@gmail.com>
User-Agent: NeoMutt/20170113 (1.7.2)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Jul 16, 2019 at 11:26:56PM +0800, Pengfei Li wrote:
> Objective
> ---------
> The current implementation of struct vmap_area wasted space.
> 
> After applying this commit, sizeof(struct vmap_area) has been
> reduced from 11 words to 8 words.
> 
> Description
> -----------
> 1) Pack "subtree_max_size", "vm" and "purge_list".
> This is no problem because
>     A) "subtree_max_size" is only used when vmap_area is in
>        "free" tree
>     B) "vm" is only used when vmap_area is in "busy" tree
>     C) "purge_list" is only used when vmap_area is in
>        vmap_purge_list
> 
> 2) Eliminate "flags".
> Since only one flag VM_VM_AREA is being used, and the same
> thing can be done by judging whether "vm" is NULL, then the
> "flags" can be eliminated.
> 
> Signed-off-by: Pengfei Li <lpf.vector@gmail.com>
> Suggested-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
> ---
>  include/linux/vmalloc.h | 20 +++++++++++++-------
>  mm/vmalloc.c            | 24 ++++++++++--------------
>  2 files changed, 23 insertions(+), 21 deletions(-)
> 
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 9b21d0047710..a1334bd18ef1 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -51,15 +51,21 @@ struct vmap_area {
>  	unsigned long va_start;
>  	unsigned long va_end;
>  
> -	/*
> -	 * Largest available free size in subtree.
> -	 */
> -	unsigned long subtree_max_size;
> -	unsigned long flags;
>  	struct rb_node rb_node;         /* address sorted rbtree */
>  	struct list_head list;          /* address sorted list */
> -	struct llist_node purge_list;    /* "lazy purge" list */
> -	struct vm_struct *vm;
> +
> +	/*
> +	 * The following three variables can be packed, because
> +	 * a vmap_area object is always one of the three states:
> +	 *    1) in "free" tree (root is vmap_area_root)
> +	 *    2) in "busy" tree (root is free_vmap_area_root)
> +	 *    3) in purge list  (head is vmap_purge_list)
> +	 */
> +	union {
> +		unsigned long subtree_max_size; /* in "free" tree */
> +		struct vm_struct *vm;           /* in "busy" tree */
> +		struct llist_node purge_list;   /* in purge list */
> +	};
>  };
>  
>  /*
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 71d8040a8a0b..2f7edc0466e7 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -329,7 +329,6 @@ EXPORT_SYMBOL(vmalloc_to_pfn);
>  #define DEBUG_AUGMENT_PROPAGATE_CHECK 0
>  #define DEBUG_AUGMENT_LOWEST_MATCH_CHECK 0
>  
> -#define VM_VM_AREA	0x04
>  
>  static DEFINE_SPINLOCK(vmap_area_lock);
>  /* Export for kexec only */
> @@ -1115,7 +1114,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size,
>  
>  	va->va_start = addr;
>  	va->va_end = addr + size;
> -	va->flags = 0;
> +	va->vm = NULL;
>  	insert_vmap_area(va, &vmap_area_root, &vmap_area_list);
>  
>  	spin_unlock(&vmap_area_lock);
> @@ -1922,7 +1921,6 @@ void __init vmalloc_init(void)
>  		if (WARN_ON_ONCE(!va))
>  			continue;
>  
> -		va->flags = VM_VM_AREA;
>  		va->va_start = (unsigned long)tmp->addr;
>  		va->va_end = va->va_start + tmp->size;
>  		va->vm = tmp;
> @@ -2020,7 +2018,6 @@ static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
>  	vm->size = va->va_end - va->va_start;
>  	vm->caller = caller;
>  	va->vm = vm;
> -	va->flags |= VM_VM_AREA;
>  	spin_unlock(&vmap_area_lock);
>  }
>  
> @@ -2125,10 +2122,10 @@ struct vm_struct *find_vm_area(const void *addr)
>  	struct vmap_area *va;
>  
>  	va = find_vmap_area((unsigned long)addr);
> -	if (va && va->flags & VM_VM_AREA)
> -		return va->vm;
> +	if (!va)
> +		return NULL;
>  
> -	return NULL;
> +	return va->vm;
>  }
>  
>  /**
> @@ -2149,11 +2146,10 @@ struct vm_struct *remove_vm_area(const void *addr)
>  
>  	spin_lock(&vmap_area_lock);
>  	va = __find_vmap_area((unsigned long)addr);
> -	if (va && va->flags & VM_VM_AREA) {
> +	if (va && va->vm) {
>  		struct vm_struct *vm = va->vm;
>  
>  		va->vm = NULL;
> -		va->flags &= ~VM_VM_AREA;
>  		spin_unlock(&vmap_area_lock);
>  
>  		kasan_free_shadow(vm);
> @@ -2856,7 +2852,7 @@ long vread(char *buf, char *addr, unsigned long count)
>  		if (!count)
>  			break;
>  
> -		if (!(va->flags & VM_VM_AREA))
> +		if (!va->vm)
>  			continue;
>  
>  		vm = va->vm;
> @@ -2936,7 +2932,7 @@ long vwrite(char *buf, char *addr, unsigned long count)
>  		if (!count)
>  			break;
>  
> -		if (!(va->flags & VM_VM_AREA))
> +		if (!va->vm)
>  			continue;
>  
>  		vm = va->vm;
> @@ -3466,10 +3462,10 @@ static int s_show(struct seq_file *m, void *p)
>  	va = list_entry(p, struct vmap_area, list);
>  
>  	/*
> -	 * s_show can encounter race with remove_vm_area, !VM_VM_AREA on
> -	 * behalf of vmap area is being tear down or vm_map_ram allocation.
> +	 * s_show can encounter race with remove_vm_area, !vm on behalf
> +	 * of vmap area is being tear down or vm_map_ram allocation.
>  	 */
> -	if (!(va->flags & VM_VM_AREA)) {
> +	if (!va->vm) {
>  		seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n",
>  			(void *)va->va_start, (void *)va->va_end,
>  			va->va_end - va->va_start);
> -- 
> 2.21.0
> 

This patch depends on https://lkml.org/lkml/2019/7/16/276 and looks ok
to me, so

Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>

Thanks!

--
Vlad Rezki