b7cb382190
This effectively reverts commit16c243e99d
("udmabuf: Add support for mapping hugepages (v4)"). Recently, Junxiao Chang found a BUG with page map counting as described here [1]. This issue pointed out that the udmabuf driver was making direct use of subpages of hugetlb pages. This is not a good idea, and no other mm code attempts such use. In addition to the mapcount issue, this also causes issues with hugetlb vmemmap optimization and page poisoning. For now, remove hugetlb support. If udmabuf wants to be used on hugetlb mappings, it should be changed to only use complete hugetlb pages. This will require different alignment and size requirements on the UDMABUF_CREATE API. [1] https://lore.kernel.org/linux-mm/20230512072036.1027784-1-junxiao.chang@intel.com/ Link: https://lkml.kernel.org/r/20230608204927.88711-1-mike.kravetz@oracle.com Fixes:16c243e99d
("udmabuf: Add support for mapping hugepages (v4)") Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Acked-by: Vivek Kasireddy <vivek.kasireddy@intel.com> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Dongwon Kim <dongwon.kim@intel.com> Cc: James Houghton <jthoughton@google.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Junxiao Chang <junxiao.chang@intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
398 lines
8.8 KiB
C
398 lines
8.8 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/cred.h>
|
|
#include <linux/device.h>
|
|
#include <linux/dma-buf.h>
|
|
#include <linux/dma-resv.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/init.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/memfd.h>
|
|
#include <linux/miscdevice.h>
|
|
#include <linux/module.h>
|
|
#include <linux/shmem_fs.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/udmabuf.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/iosys-map.h>
|
|
|
|
static int list_limit = 1024;
|
|
module_param(list_limit, int, 0644);
|
|
MODULE_PARM_DESC(list_limit, "udmabuf_create_list->count limit. Default is 1024.");
|
|
|
|
static int size_limit_mb = 64;
|
|
module_param(size_limit_mb, int, 0644);
|
|
MODULE_PARM_DESC(size_limit_mb, "Max size of a dmabuf, in megabytes. Default is 64.");
|
|
|
|
struct udmabuf {
|
|
pgoff_t pagecount;
|
|
struct page **pages;
|
|
struct sg_table *sg;
|
|
struct miscdevice *device;
|
|
};
|
|
|
|
static vm_fault_t udmabuf_vm_fault(struct vm_fault *vmf)
|
|
{
|
|
struct vm_area_struct *vma = vmf->vma;
|
|
struct udmabuf *ubuf = vma->vm_private_data;
|
|
pgoff_t pgoff = vmf->pgoff;
|
|
|
|
if (pgoff >= ubuf->pagecount)
|
|
return VM_FAULT_SIGBUS;
|
|
vmf->page = ubuf->pages[pgoff];
|
|
get_page(vmf->page);
|
|
return 0;
|
|
}
|
|
|
|
static const struct vm_operations_struct udmabuf_vm_ops = {
|
|
.fault = udmabuf_vm_fault,
|
|
};
|
|
|
|
static int mmap_udmabuf(struct dma_buf *buf, struct vm_area_struct *vma)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
|
|
dma_resv_assert_held(buf->resv);
|
|
|
|
if ((vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) == 0)
|
|
return -EINVAL;
|
|
|
|
vma->vm_ops = &udmabuf_vm_ops;
|
|
vma->vm_private_data = ubuf;
|
|
return 0;
|
|
}
|
|
|
|
static int vmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
void *vaddr;
|
|
|
|
dma_resv_assert_held(buf->resv);
|
|
|
|
vaddr = vm_map_ram(ubuf->pages, ubuf->pagecount, -1);
|
|
if (!vaddr)
|
|
return -EINVAL;
|
|
|
|
iosys_map_set_vaddr(map, vaddr);
|
|
return 0;
|
|
}
|
|
|
|
static void vunmap_udmabuf(struct dma_buf *buf, struct iosys_map *map)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
|
|
dma_resv_assert_held(buf->resv);
|
|
|
|
vm_unmap_ram(map->vaddr, ubuf->pagecount);
|
|
}
|
|
|
|
static struct sg_table *get_sg_table(struct device *dev, struct dma_buf *buf,
|
|
enum dma_data_direction direction)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
struct sg_table *sg;
|
|
int ret;
|
|
|
|
sg = kzalloc(sizeof(*sg), GFP_KERNEL);
|
|
if (!sg)
|
|
return ERR_PTR(-ENOMEM);
|
|
ret = sg_alloc_table_from_pages(sg, ubuf->pages, ubuf->pagecount,
|
|
0, ubuf->pagecount << PAGE_SHIFT,
|
|
GFP_KERNEL);
|
|
if (ret < 0)
|
|
goto err;
|
|
ret = dma_map_sgtable(dev, sg, direction, 0);
|
|
if (ret < 0)
|
|
goto err;
|
|
return sg;
|
|
|
|
err:
|
|
sg_free_table(sg);
|
|
kfree(sg);
|
|
return ERR_PTR(ret);
|
|
}
|
|
|
|
static void put_sg_table(struct device *dev, struct sg_table *sg,
|
|
enum dma_data_direction direction)
|
|
{
|
|
dma_unmap_sgtable(dev, sg, direction, 0);
|
|
sg_free_table(sg);
|
|
kfree(sg);
|
|
}
|
|
|
|
static struct sg_table *map_udmabuf(struct dma_buf_attachment *at,
|
|
enum dma_data_direction direction)
|
|
{
|
|
return get_sg_table(at->dev, at->dmabuf, direction);
|
|
}
|
|
|
|
static void unmap_udmabuf(struct dma_buf_attachment *at,
|
|
struct sg_table *sg,
|
|
enum dma_data_direction direction)
|
|
{
|
|
return put_sg_table(at->dev, sg, direction);
|
|
}
|
|
|
|
static void release_udmabuf(struct dma_buf *buf)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
struct device *dev = ubuf->device->this_device;
|
|
pgoff_t pg;
|
|
|
|
if (ubuf->sg)
|
|
put_sg_table(dev, ubuf->sg, DMA_BIDIRECTIONAL);
|
|
|
|
for (pg = 0; pg < ubuf->pagecount; pg++)
|
|
put_page(ubuf->pages[pg]);
|
|
kfree(ubuf->pages);
|
|
kfree(ubuf);
|
|
}
|
|
|
|
static int begin_cpu_udmabuf(struct dma_buf *buf,
|
|
enum dma_data_direction direction)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
struct device *dev = ubuf->device->this_device;
|
|
int ret = 0;
|
|
|
|
if (!ubuf->sg) {
|
|
ubuf->sg = get_sg_table(dev, buf, direction);
|
|
if (IS_ERR(ubuf->sg)) {
|
|
ret = PTR_ERR(ubuf->sg);
|
|
ubuf->sg = NULL;
|
|
}
|
|
} else {
|
|
dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
|
|
direction);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int end_cpu_udmabuf(struct dma_buf *buf,
|
|
enum dma_data_direction direction)
|
|
{
|
|
struct udmabuf *ubuf = buf->priv;
|
|
struct device *dev = ubuf->device->this_device;
|
|
|
|
if (!ubuf->sg)
|
|
return -EINVAL;
|
|
|
|
dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
|
|
return 0;
|
|
}
|
|
|
|
static const struct dma_buf_ops udmabuf_ops = {
|
|
.cache_sgt_mapping = true,
|
|
.map_dma_buf = map_udmabuf,
|
|
.unmap_dma_buf = unmap_udmabuf,
|
|
.release = release_udmabuf,
|
|
.mmap = mmap_udmabuf,
|
|
.vmap = vmap_udmabuf,
|
|
.vunmap = vunmap_udmabuf,
|
|
.begin_cpu_access = begin_cpu_udmabuf,
|
|
.end_cpu_access = end_cpu_udmabuf,
|
|
};
|
|
|
|
#define SEALS_WANTED (F_SEAL_SHRINK)
|
|
#define SEALS_DENIED (F_SEAL_WRITE)
|
|
|
|
static long udmabuf_create(struct miscdevice *device,
|
|
struct udmabuf_create_list *head,
|
|
struct udmabuf_create_item *list)
|
|
{
|
|
DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
|
|
struct file *memfd = NULL;
|
|
struct address_space *mapping = NULL;
|
|
struct udmabuf *ubuf;
|
|
struct dma_buf *buf;
|
|
pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
|
|
struct page *page;
|
|
int seals, ret = -EINVAL;
|
|
u32 i, flags;
|
|
|
|
ubuf = kzalloc(sizeof(*ubuf), GFP_KERNEL);
|
|
if (!ubuf)
|
|
return -ENOMEM;
|
|
|
|
pglimit = (size_limit_mb * 1024 * 1024) >> PAGE_SHIFT;
|
|
for (i = 0; i < head->count; i++) {
|
|
if (!IS_ALIGNED(list[i].offset, PAGE_SIZE))
|
|
goto err;
|
|
if (!IS_ALIGNED(list[i].size, PAGE_SIZE))
|
|
goto err;
|
|
ubuf->pagecount += list[i].size >> PAGE_SHIFT;
|
|
if (ubuf->pagecount > pglimit)
|
|
goto err;
|
|
}
|
|
|
|
if (!ubuf->pagecount)
|
|
goto err;
|
|
|
|
ubuf->pages = kmalloc_array(ubuf->pagecount, sizeof(*ubuf->pages),
|
|
GFP_KERNEL);
|
|
if (!ubuf->pages) {
|
|
ret = -ENOMEM;
|
|
goto err;
|
|
}
|
|
|
|
pgbuf = 0;
|
|
for (i = 0; i < head->count; i++) {
|
|
ret = -EBADFD;
|
|
memfd = fget(list[i].memfd);
|
|
if (!memfd)
|
|
goto err;
|
|
mapping = memfd->f_mapping;
|
|
if (!shmem_mapping(mapping))
|
|
goto err;
|
|
seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
|
|
if (seals == -EINVAL)
|
|
goto err;
|
|
ret = -EINVAL;
|
|
if ((seals & SEALS_WANTED) != SEALS_WANTED ||
|
|
(seals & SEALS_DENIED) != 0)
|
|
goto err;
|
|
pgoff = list[i].offset >> PAGE_SHIFT;
|
|
pgcnt = list[i].size >> PAGE_SHIFT;
|
|
for (pgidx = 0; pgidx < pgcnt; pgidx++) {
|
|
page = shmem_read_mapping_page(mapping, pgoff + pgidx);
|
|
if (IS_ERR(page)) {
|
|
ret = PTR_ERR(page);
|
|
goto err;
|
|
}
|
|
ubuf->pages[pgbuf++] = page;
|
|
}
|
|
fput(memfd);
|
|
memfd = NULL;
|
|
}
|
|
|
|
exp_info.ops = &udmabuf_ops;
|
|
exp_info.size = ubuf->pagecount << PAGE_SHIFT;
|
|
exp_info.priv = ubuf;
|
|
exp_info.flags = O_RDWR;
|
|
|
|
ubuf->device = device;
|
|
buf = dma_buf_export(&exp_info);
|
|
if (IS_ERR(buf)) {
|
|
ret = PTR_ERR(buf);
|
|
goto err;
|
|
}
|
|
|
|
flags = 0;
|
|
if (head->flags & UDMABUF_FLAGS_CLOEXEC)
|
|
flags |= O_CLOEXEC;
|
|
return dma_buf_fd(buf, flags);
|
|
|
|
err:
|
|
while (pgbuf > 0)
|
|
put_page(ubuf->pages[--pgbuf]);
|
|
if (memfd)
|
|
fput(memfd);
|
|
kfree(ubuf->pages);
|
|
kfree(ubuf);
|
|
return ret;
|
|
}
|
|
|
|
static long udmabuf_ioctl_create(struct file *filp, unsigned long arg)
|
|
{
|
|
struct udmabuf_create create;
|
|
struct udmabuf_create_list head;
|
|
struct udmabuf_create_item list;
|
|
|
|
if (copy_from_user(&create, (void __user *)arg,
|
|
sizeof(create)))
|
|
return -EFAULT;
|
|
|
|
head.flags = create.flags;
|
|
head.count = 1;
|
|
list.memfd = create.memfd;
|
|
list.offset = create.offset;
|
|
list.size = create.size;
|
|
|
|
return udmabuf_create(filp->private_data, &head, &list);
|
|
}
|
|
|
|
static long udmabuf_ioctl_create_list(struct file *filp, unsigned long arg)
|
|
{
|
|
struct udmabuf_create_list head;
|
|
struct udmabuf_create_item *list;
|
|
int ret = -EINVAL;
|
|
u32 lsize;
|
|
|
|
if (copy_from_user(&head, (void __user *)arg, sizeof(head)))
|
|
return -EFAULT;
|
|
if (head.count > list_limit)
|
|
return -EINVAL;
|
|
lsize = sizeof(struct udmabuf_create_item) * head.count;
|
|
list = memdup_user((void __user *)(arg + sizeof(head)), lsize);
|
|
if (IS_ERR(list))
|
|
return PTR_ERR(list);
|
|
|
|
ret = udmabuf_create(filp->private_data, &head, list);
|
|
kfree(list);
|
|
return ret;
|
|
}
|
|
|
|
static long udmabuf_ioctl(struct file *filp, unsigned int ioctl,
|
|
unsigned long arg)
|
|
{
|
|
long ret;
|
|
|
|
switch (ioctl) {
|
|
case UDMABUF_CREATE:
|
|
ret = udmabuf_ioctl_create(filp, arg);
|
|
break;
|
|
case UDMABUF_CREATE_LIST:
|
|
ret = udmabuf_ioctl_create_list(filp, arg);
|
|
break;
|
|
default:
|
|
ret = -ENOTTY;
|
|
break;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static const struct file_operations udmabuf_fops = {
|
|
.owner = THIS_MODULE,
|
|
.unlocked_ioctl = udmabuf_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = udmabuf_ioctl,
|
|
#endif
|
|
};
|
|
|
|
static struct miscdevice udmabuf_misc = {
|
|
.minor = MISC_DYNAMIC_MINOR,
|
|
.name = "udmabuf",
|
|
.fops = &udmabuf_fops,
|
|
};
|
|
|
|
static int __init udmabuf_dev_init(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = misc_register(&udmabuf_misc);
|
|
if (ret < 0) {
|
|
pr_err("Could not initialize udmabuf device\n");
|
|
return ret;
|
|
}
|
|
|
|
ret = dma_coerce_mask_and_coherent(udmabuf_misc.this_device,
|
|
DMA_BIT_MASK(64));
|
|
if (ret < 0) {
|
|
pr_err("Could not setup DMA mask for udmabuf device\n");
|
|
misc_deregister(&udmabuf_misc);
|
|
return ret;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void __exit udmabuf_dev_exit(void)
|
|
{
|
|
misc_deregister(&udmabuf_misc);
|
|
}
|
|
|
|
module_init(udmabuf_dev_init)
|
|
module_exit(udmabuf_dev_exit)
|
|
|
|
MODULE_AUTHOR("Gerd Hoffmann <kraxel@redhat.com>");
|