| Message ID | 20230113031921.64716-3-bhe@redhat.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | mm/vmalloc.c: allow vread() to read out vm_map_ram areas | expand |
On Fri, Jan 13, 2023 at 11:19:16AM +0800, Baoquan He wrote: > 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 kinds of handling for vm_map_ram area. One is > the whole vmap_area being reserved and mapped at one time through > vm_map_area() interface; the other is the whole vmap_area with > VMAP_BLOCK_SIZE size being reserved, while mapped into split regions > with smaller size via vb_alloc(). > > To mark the area reserved through vm_map_ram(), add flags field into > struct vmap_area. Bit 0 indicates this is vm_map_ram area created > through vm_map_ram() interface, while bit 1 marks out the type of > vm_map_ram area which makes use of vmap_block to manage split regions > via vb_alloc/free(). > > This is a preparatoin for later use. > > Signed-off-by: Baoquan He <bhe@redhat.com> > --- > include/linux/vmalloc.h | 1 + > mm/vmalloc.c | 16 ++++++++++++---- > 2 files changed, 13 insertions(+), 4 deletions(-) > > 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 d6ff058ef4d0..ab4825050b5c 100644 > --- a/mm/vmalloc.c > +++ b/mm/vmalloc.c > @@ -1589,7 +1589,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) > 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) > + int node, gfp_t gfp_mask, > + unsigned long va_flags) > { > struct vmap_area *va; > unsigned long freed; > @@ -1635,6 +1636,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, > va->va_start = addr; > va->va_end = addr + size; > va->vm = NULL; > + va->flags = va_flags; > > spin_lock(&vmap_area_lock); > insert_vmap_area(va, &vmap_area_root, &vmap_area_list); > @@ -1913,6 +1915,10 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) > > #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) > > +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ > +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ > +#define VMAP_FLAGS_MASK 0x3 > + > struct vmap_block_queue { > spinlock_t lock; > struct list_head free; > @@ -1988,7 +1994,8 @@ 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); > + node, gfp_mask, > + VMAP_RAM|VMAP_BLOCK); > if (IS_ERR(va)) { > kfree(vb); > return ERR_CAST(va); > @@ -2297,7 +2304,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) > } else { > struct vmap_area *va; > va = alloc_vmap_area(size, PAGE_SIZE, > - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); > + VMALLOC_START, VMALLOC_END, > + node, GFP_KERNEL, VMAP_RAM); > if (IS_ERR(va)) > return NULL; > > @@ -2537,7 +2545,7 @@ 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); > + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); > if (IS_ERR(va)) { > kfree(area); > return NULL; > -- > 2.34.1 > Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com> -- Uladzislau Rezki
On Fri, Jan 13, 2023 at 11:19:16AM +0800, Baoquan He wrote: > 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 kinds of handling for vm_map_ram area. One is > the whole vmap_area being reserved and mapped at one time through > vm_map_area() interface; the other is the whole vmap_area with > VMAP_BLOCK_SIZE size being reserved, while mapped into split regions > with smaller size via vb_alloc(). > > To mark the area reserved through vm_map_ram(), add flags field into > struct vmap_area. Bit 0 indicates this is vm_map_ram area created > through vm_map_ram() interface, while bit 1 marks out the type of > vm_map_ram area which makes use of vmap_block to manage split regions > via vb_alloc/free(). > > This is a preparatoin for later use. > Small typo here :) > Signed-off-by: Baoquan He <bhe@redhat.com> > --- > include/linux/vmalloc.h | 1 + > mm/vmalloc.c | 16 ++++++++++++---- > 2 files changed, 13 insertions(+), 4 deletions(-) > > 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 d6ff058ef4d0..ab4825050b5c 100644 > --- a/mm/vmalloc.c > +++ b/mm/vmalloc.c > @@ -1589,7 +1589,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) > 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) > + int node, gfp_t gfp_mask, > + unsigned long va_flags) > { > struct vmap_area *va; > unsigned long freed; > @@ -1635,6 +1636,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, > va->va_start = addr; > va->va_end = addr + size; > va->vm = NULL; > + va->flags = va_flags; > > spin_lock(&vmap_area_lock); > insert_vmap_area(va, &vmap_area_root, &vmap_area_list); > @@ -1913,6 +1915,10 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) > > #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) > > +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ > +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ > +#define VMAP_FLAGS_MASK 0x3 > + > struct vmap_block_queue { > spinlock_t lock; > struct list_head free; > @@ -1988,7 +1994,8 @@ 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); > + node, gfp_mask, > + VMAP_RAM|VMAP_BLOCK); > if (IS_ERR(va)) { > kfree(vb); > return ERR_CAST(va); > @@ -2297,7 +2304,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) > } else { > struct vmap_area *va; > va = alloc_vmap_area(size, PAGE_SIZE, > - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); > + VMALLOC_START, VMALLOC_END, > + node, GFP_KERNEL, VMAP_RAM); > if (IS_ERR(va)) > return NULL; > > @@ -2537,7 +2545,7 @@ 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); > + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); > if (IS_ERR(va)) { > kfree(area); > return NULL; > -- > 2.34.1 > Other than that typo, Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com>
On 01/16/23 at 12:23pm, Lorenzo Stoakes wrote: > On Fri, Jan 13, 2023 at 11:19:16AM +0800, Baoquan He wrote: > > 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 kinds of handling for vm_map_ram area. One is > > the whole vmap_area being reserved and mapped at one time through > > vm_map_area() interface; the other is the whole vmap_area with > > VMAP_BLOCK_SIZE size being reserved, while mapped into split regions > > with smaller size via vb_alloc(). > > > > To mark the area reserved through vm_map_ram(), add flags field into > > struct vmap_area. Bit 0 indicates this is vm_map_ram area created > > through vm_map_ram() interface, while bit 1 marks out the type of > > vm_map_ram area which makes use of vmap_block to manage split regions > > via vb_alloc/free(). > > > > This is a preparatoin for later use. > > > > Small typo here :) Good catch, will fix it. > > > Signed-off-by: Baoquan He <bhe@redhat.com> > > --- > > include/linux/vmalloc.h | 1 + > > mm/vmalloc.c | 16 ++++++++++++---- > > 2 files changed, 13 insertions(+), 4 deletions(-) > > > > 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 d6ff058ef4d0..ab4825050b5c 100644 > > --- a/mm/vmalloc.c > > +++ b/mm/vmalloc.c > > @@ -1589,7 +1589,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) > > 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) > > + int node, gfp_t gfp_mask, > > + unsigned long va_flags) > > { > > struct vmap_area *va; > > unsigned long freed; > > @@ -1635,6 +1636,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, > > va->va_start = addr; > > va->va_end = addr + size; > > va->vm = NULL; > > + va->flags = va_flags; > > > > spin_lock(&vmap_area_lock); > > insert_vmap_area(va, &vmap_area_root, &vmap_area_list); > > @@ -1913,6 +1915,10 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) > > > > #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) > > > > +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ > > +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ > > +#define VMAP_FLAGS_MASK 0x3 > > + > > struct vmap_block_queue { > > spinlock_t lock; > > struct list_head free; > > @@ -1988,7 +1994,8 @@ 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); > > + node, gfp_mask, > > + VMAP_RAM|VMAP_BLOCK); > > if (IS_ERR(va)) { > > kfree(vb); > > return ERR_CAST(va); > > @@ -2297,7 +2304,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) > > } else { > > struct vmap_area *va; > > va = alloc_vmap_area(size, PAGE_SIZE, > > - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); > > + VMALLOC_START, VMALLOC_END, > > + node, GFP_KERNEL, VMAP_RAM); > > if (IS_ERR(va)) > > return NULL; > > > > @@ -2537,7 +2545,7 @@ 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); > > + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); > > if (IS_ERR(va)) { > > kfree(area); > > return NULL; > > -- > > 2.34.1 > > > > Other than that typo, > > Reviewed-by: Lorenzo Stoakes <lstoakes@gmail.com> >
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 d6ff058ef4d0..ab4825050b5c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1589,7 +1589,8 @@ preload_this_cpu_lock(spinlock_t *lock, gfp_t gfp_mask, int node) 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) + int node, gfp_t gfp_mask, + unsigned long va_flags) { struct vmap_area *va; unsigned long freed; @@ -1635,6 +1636,7 @@ static struct vmap_area *alloc_vmap_area(unsigned long size, va->va_start = addr; va->va_end = addr + size; va->vm = NULL; + va->flags = va_flags; spin_lock(&vmap_area_lock); insert_vmap_area(va, &vmap_area_root, &vmap_area_list); @@ -1913,6 +1915,10 @@ static struct vmap_area *find_unlink_vmap_area(unsigned long addr) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) +#define VMAP_RAM 0x1 /* indicates vm_map_ram area*/ +#define VMAP_BLOCK 0x2 /* mark out the vmap_block sub-type*/ +#define VMAP_FLAGS_MASK 0x3 + struct vmap_block_queue { spinlock_t lock; struct list_head free; @@ -1988,7 +1994,8 @@ 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); + node, gfp_mask, + VMAP_RAM|VMAP_BLOCK); if (IS_ERR(va)) { kfree(vb); return ERR_CAST(va); @@ -2297,7 +2304,8 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node) } else { struct vmap_area *va; va = alloc_vmap_area(size, PAGE_SIZE, - VMALLOC_START, VMALLOC_END, node, GFP_KERNEL); + VMALLOC_START, VMALLOC_END, + node, GFP_KERNEL, VMAP_RAM); if (IS_ERR(va)) return NULL; @@ -2537,7 +2545,7 @@ 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); + va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0); if (IS_ERR(va)) { kfree(area); return NULL;
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 kinds of handling for vm_map_ram area. One is the whole vmap_area being reserved and mapped at one time through vm_map_area() interface; the other is the whole vmap_area with VMAP_BLOCK_SIZE size being reserved, while mapped into split regions with smaller size via vb_alloc(). To mark the area reserved through vm_map_ram(), add flags field into struct vmap_area. Bit 0 indicates this is vm_map_ram area created through vm_map_ram() interface, while bit 1 marks out the type of vm_map_ram area which makes use of vmap_block to manage split regions via vb_alloc/free(). This is a preparatoin for later use. Signed-off-by: Baoquan He <bhe@redhat.com> --- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 16 ++++++++++++---- 2 files changed, 13 insertions(+), 4 deletions(-)