> Through vmalloc API, a virtual kernel area is reserved for physical
> address mapping. And vmap_area is used to track them, while vm_struct
> is allocated to associate with the vmap_area to store more information
> and passed out.
>
> However, area reserved via vm_map_ram() is an exception. It doesn't have
> vm_struct to associate with vmap_area. And we can't recognize the
> vmap_area with '->vm == NULL' as a vm_map_ram() area because the normal
> freeing path will set va->vm = NULL before unmapping, please see
> function remove_vm_area().
>
> Meanwhile, there are two types of vm_map_ram area. One is the whole
> vmap_area being reserved and mapped at one time; the other is the
> whole vmap_area with VMAP_BLOCK_SIZE size being reserved, while mapped
> into split regions with smaller size several times via vb_alloc().
>
> To mark the area reserved through vm_map_ram(), add flags field into
> struct vmap_area. Bit 0 indicates whether it's a vm_map_ram area,
> while bit 1 indicates whether it's a vmap_block type of vm_map_ram
> area.
>
> This is a preparatoin for later use.
>
> Signed-off-by: Baoquan He <bhe@xxxxxxxxxx>
> ---
> include/linux/vmalloc.h | 1 +
> mm/vmalloc.c | 18 +++++++++++++++++-
> 2 files changed, 18 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index 096d48aa3437..69250efa03d1 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -76,6 +76,7 @@ struct vmap_area {
> unsigned long subtree_max_size; /* in "free" tree */
> struct vm_struct *vm; /* in "busy" tree */
> };
> + unsigned long flags; /* mark type of vm_map_ram area */
> };
>
> /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 5d3fd3e6fe09..d6f376060d83 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -1815,6 +1815,7 @@ static void free_vmap_area_noflush(struct vmap_area *va)
>
> spin_lock(&vmap_area_lock);
> unlink_va(va, &vmap_area_root);
> + va->flags = 0;
> spin_unlock(&vmap_area_lock);
>
This is not a good place to set flags to zero. It looks to me like
corner and kind of specific.
> nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
> @@ -1887,6 +1888,10 @@ struct vmap_area *find_vmap_area(unsigned long addr)
>
> #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE)
>
> +#define VMAP_RAM 0x1
> +#define VMAP_BLOCK 0x2
> +#define VMAP_FLAGS_MASK 0x3
> +
> struct vmap_block_queue {
> spinlock_t lock;
> struct list_head free;
> @@ -1967,6 +1972,9 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
> kfree(vb);
> return ERR_CAST(va);
> }
> + spin_lock(&vmap_area_lock);
> + va->flags = VMAP_RAM|VMAP_BLOCK;
> + spin_unlock(&vmap_area_lock);
>
The per-cpu code was created as a fast per-cpu allocator because of high
vmalloc lock contention. If possible we should avoid of locking of the
vmap_area_lock. Because it has a high contention.
>
> vaddr = vmap_block_vaddr(va->va_start, 0);
> spin_lock_init(&vb->lock);
> @@ -2229,8 +2237,12 @@ void vm_unmap_ram(const void *mem, unsigned int count)
> return;
> }
>
> - va = find_vmap_area(addr);
> + spin_lock(&vmap_area_lock);
> + va = __find_vmap_area((unsigned long)addr, &vmap_area_root);
> BUG_ON(!va);
> + if (va)
> + va->flags &= ~VMAP_RAM;
> + spin_unlock(&vmap_area_lock);
> debug_check_no_locks_freed((void *)va->va_start,
> (va->va_end - va->va_start));
> free_unmap_vmap_area(va);
> @@ -2269,6 +2281,10 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node)
> if (IS_ERR(va))
> return NULL;
>
> + spin_lock(&vmap_area_lock);
> + va->flags = VMAP_RAM;
> + spin_unlock(&vmap_area_lock);
> +
>
Same here.
--
Uladzislau Rezki
