vfio Updates for v3.11
Largely hugepage support for vfio/type1 iommu and surrounding cleanups and fixes. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (GNU/Linux) iQIcBAABAgAGBQJR2uNvAAoJECObm247sIsiJRYQAJK15MfXgJq2PtBABNvFUAOG nqUvLgBgM5Ow1NI0Rzh9jkNohNqCvXDFGaWXXnsaX83hIpi59GFK31W2E3SiFCj3 xISA9SUnm7Kjt9LAF6HTNz805zBkshIOk4MCx6HlezVWSRlWwT3rZzI4dI2fMvl8 iPRk1Ion3QSQui99HWfXv/rtezAIzgZqsFqPC6DjWRfN7LcdEtKtcQwnrSb5GGY9 3TIRY9IRYTSfJ2yjSz5f5258JxoDG5sR8dTMkgG2Gm92iGvGcPGpzQWPzVc4t+TO PdTqtv9ftEyAJKsYTFjPIod8XbzJBa1FSPadVAIfwF0JCDcsSFjoWGp+RzMQQSF8 MK3VsnQ/pqJfs2nJHDQbWbKu0qWYPntvOCdojZ4679ceDTd0t515npfYeDQuX8yU fAA5rB46mDXjyxikTP574NdnkcGjbAj7EOCp7s+WTsVPGQQ3mId/3fQw0Wg7bE6v jaJqdRj70SNTRHs8DFLQhvSZgpef4RzepE4sRBZqzY4vWd4riNcAC3Got+F2rQy3 X4hcHHU/5LGLoGMxOJQmuBfKVM8RAgikq6w2RfttVMLeKCknKtJ29OnotKilvILh W8nAOGxRnkmONFfHakNJtLl5tQJ4FQXc2cG8OeIIhHgheJjUxL72/zv8bBxOo7rY jUBjtZ5riQXc/ck4FEGI =9+Jh -----END PGP SIGNATURE----- Merge tag 'vfio-v3.11' of git://github.com/awilliam/linux-vfio Pull vfio updates from Alex Williamson: "Largely hugepage support for vfio/type1 iommu and surrounding cleanups and fixes" * tag 'vfio-v3.11' of git://github.com/awilliam/linux-vfio: vfio/type1: Fix leak on error path vfio: Limit group opens vfio/type1: Fix missed frees and zero sized removes vfio: fix documentation vfio: Provide module option to disable vfio_iommu_type1 hugepage support vfio: hugepage support for vfio_iommu_type1 vfio: Convert type1 iommu to use rbtree
This commit is contained in:
Linus Torvalds
commit
15a49b9a90
|
|
@ -172,12 +172,12 @@ group and can access them as follows:
|
|||
struct vfio_device_info device_info = { .argsz = sizeof(device_info) };
|
||||
|
||||
/* Create a new container */
|
||||
container = open("/dev/vfio/vfio, O_RDWR);
|
||||
container = open("/dev/vfio/vfio", O_RDWR);
|
||||
|
||||
if (ioctl(container, VFIO_GET_API_VERSION) != VFIO_API_VERSION)
|
||||
/* Unknown API version */
|
||||
|
||||
if (!ioctl(container, VFIO_CHECK_EXTENSION, VFIO_X86_IOMMU))
|
||||
if (!ioctl(container, VFIO_CHECK_EXTENSION, VFIO_TYPE1_IOMMU))
|
||||
/* Doesn't support the IOMMU driver we want. */
|
||||
|
||||
/* Open the group */
|
||||
|
|
@ -193,7 +193,7 @@ group and can access them as follows:
|
|||
ioctl(group, VFIO_GROUP_SET_CONTAINER, &container);
|
||||
|
||||
/* Enable the IOMMU model we want */
|
||||
ioctl(container, VFIO_SET_IOMMU, VFIO_X86_IOMMU)
|
||||
ioctl(container, VFIO_SET_IOMMU, VFIO_TYPE1_IOMMU)
|
||||
|
||||
/* Get addition IOMMU info */
|
||||
ioctl(container, VFIO_IOMMU_GET_INFO, &iommu_info);
|
||||
|
|
|
|||
|
|
@ -76,6 +76,7 @@ struct vfio_group {
|
|||
struct notifier_block nb;
|
||||
struct list_head vfio_next;
|
||||
struct list_head container_next;
|
||||
atomic_t opened;
|
||||
};
|
||||
|
||||
struct vfio_device {
|
||||
|
|
@ -206,6 +207,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group)
|
|||
INIT_LIST_HEAD(&group->device_list);
|
||||
mutex_init(&group->device_lock);
|
||||
atomic_set(&group->container_users, 0);
|
||||
atomic_set(&group->opened, 0);
|
||||
group->iommu_group = iommu_group;
|
||||
|
||||
group->nb.notifier_call = vfio_iommu_group_notifier;
|
||||
|
|
@ -1236,12 +1238,22 @@ static long vfio_group_fops_compat_ioctl(struct file *filep,
|
|||
static int vfio_group_fops_open(struct inode *inode, struct file *filep)
|
||||
{
|
||||
struct vfio_group *group;
|
||||
int opened;
|
||||
|
||||
group = vfio_group_get_from_minor(iminor(inode));
|
||||
if (!group)
|
||||
return -ENODEV;
|
||||
|
||||
/* Do we need multiple instances of the group open? Seems not. */
|
||||
opened = atomic_cmpxchg(&group->opened, 0, 1);
|
||||
if (opened) {
|
||||
vfio_group_put(group);
|
||||
return -EBUSY;
|
||||
}
|
||||
|
||||
/* Is something still in use from a previous open? */
|
||||
if (group->container) {
|
||||
atomic_dec(&group->opened);
|
||||
vfio_group_put(group);
|
||||
return -EBUSY;
|
||||
}
|
||||
|
|
@ -1259,6 +1271,8 @@ static int vfio_group_fops_release(struct inode *inode, struct file *filep)
|
|||
|
||||
vfio_group_try_dissolve_container(group);
|
||||
|
||||
atomic_dec(&group->opened);
|
||||
|
||||
vfio_group_put(group);
|
||||
|
||||
return 0;
|
||||
|
|
|
|||
|
|
@ -31,6 +31,7 @@
|
|||
#include <linux/module.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/pci.h> /* pci_bus_type */
|
||||
#include <linux/rbtree.h>
|
||||
#include <linux/sched.h>
|
||||
#include <linux/slab.h>
|
||||
#include <linux/uaccess.h>
|
||||
|
|
@ -47,19 +48,25 @@ module_param_named(allow_unsafe_interrupts,
|
|||
MODULE_PARM_DESC(allow_unsafe_interrupts,
|
||||
"Enable VFIO IOMMU support for on platforms without interrupt remapping support.");
|
||||
|
||||
static bool disable_hugepages;
|
||||
module_param_named(disable_hugepages,
|
||||
disable_hugepages, bool, S_IRUGO | S_IWUSR);
|
||||
MODULE_PARM_DESC(disable_hugepages,
|
||||
"Disable VFIO IOMMU support for IOMMU hugepages.");
|
||||
|
||||
struct vfio_iommu {
|
||||
struct iommu_domain *domain;
|
||||
struct mutex lock;
|
||||
struct list_head dma_list;
|
||||
struct rb_root dma_list;
|
||||
struct list_head group_list;
|
||||
bool cache;
|
||||
};
|
||||
|
||||
struct vfio_dma {
|
||||
struct list_head next;
|
||||
struct rb_node node;
|
||||
dma_addr_t iova; /* Device address */
|
||||
unsigned long vaddr; /* Process virtual addr */
|
||||
long npage; /* Number of pages */
|
||||
size_t size; /* Map size (bytes) */
|
||||
int prot; /* IOMMU_READ/WRITE */
|
||||
};
|
||||
|
||||
|
|
@ -73,7 +80,48 @@ struct vfio_group {
|
|||
* into DMA'ble space using the IOMMU
|
||||
*/
|
||||
|
||||
#define NPAGE_TO_SIZE(npage) ((size_t)(npage) << PAGE_SHIFT)
|
||||
static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
|
||||
dma_addr_t start, size_t size)
|
||||
{
|
||||
struct rb_node *node = iommu->dma_list.rb_node;
|
||||
|
||||
while (node) {
|
||||
struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
|
||||
|
||||
if (start + size <= dma->iova)
|
||||
node = node->rb_left;
|
||||
else if (start >= dma->iova + dma->size)
|
||||
node = node->rb_right;
|
||||
else
|
||||
return dma;
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static void vfio_insert_dma(struct vfio_iommu *iommu, struct vfio_dma *new)
|
||||
{
|
||||
struct rb_node **link = &iommu->dma_list.rb_node, *parent = NULL;
|
||||
struct vfio_dma *dma;
|
||||
|
||||
while (*link) {
|
||||
parent = *link;
|
||||
dma = rb_entry(parent, struct vfio_dma, node);
|
||||
|
||||
if (new->iova + new->size <= dma->iova)
|
||||
link = &(*link)->rb_left;
|
||||
else
|
||||
link = &(*link)->rb_right;
|
||||
}
|
||||
|
||||
rb_link_node(&new->node, parent, link);
|
||||
rb_insert_color(&new->node, &iommu->dma_list);
|
||||
}
|
||||
|
||||
static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *old)
|
||||
{
|
||||
rb_erase(&old->node, &iommu->dma_list);
|
||||
}
|
||||
|
||||
struct vwork {
|
||||
struct mm_struct *mm;
|
||||
|
|
@ -100,8 +148,8 @@ static void vfio_lock_acct(long npage)
|
|||
struct vwork *vwork;
|
||||
struct mm_struct *mm;
|
||||
|
||||
if (!current->mm)
|
||||
return; /* process exited */
|
||||
if (!current->mm || !npage)
|
||||
return; /* process exited or nothing to do */
|
||||
|
||||
if (down_write_trylock(¤t->mm->mmap_sem)) {
|
||||
current->mm->locked_vm += npage;
|
||||
|
|
@ -173,33 +221,6 @@ static int put_pfn(unsigned long pfn, int prot)
|
|||
return 0;
|
||||
}
|
||||
|
||||
/* Unmap DMA region */
|
||||
static long __vfio_dma_do_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
|
||||
long npage, int prot)
|
||||
{
|
||||
long i, unlocked = 0;
|
||||
|
||||
for (i = 0; i < npage; i++, iova += PAGE_SIZE) {
|
||||
unsigned long pfn;
|
||||
|
||||
pfn = iommu_iova_to_phys(iommu->domain, iova) >> PAGE_SHIFT;
|
||||
if (pfn) {
|
||||
iommu_unmap(iommu->domain, iova, PAGE_SIZE);
|
||||
unlocked += put_pfn(pfn, prot);
|
||||
}
|
||||
}
|
||||
return unlocked;
|
||||
}
|
||||
|
||||
static void vfio_dma_unmap(struct vfio_iommu *iommu, dma_addr_t iova,
|
||||
long npage, int prot)
|
||||
{
|
||||
long unlocked;
|
||||
|
||||
unlocked = __vfio_dma_do_unmap(iommu, iova, npage, prot);
|
||||
vfio_lock_acct(-unlocked);
|
||||
}
|
||||
|
||||
static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
|
||||
{
|
||||
struct page *page[1];
|
||||
|
|
@ -226,198 +247,306 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn)
|
|||
return ret;
|
||||
}
|
||||
|
||||
/* Map DMA region */
|
||||
static int __vfio_dma_map(struct vfio_iommu *iommu, dma_addr_t iova,
|
||||
unsigned long vaddr, long npage, int prot)
|
||||
/*
|
||||
* Attempt to pin pages. We really don't want to track all the pfns and
|
||||
* the iommu can only map chunks of consecutive pfns anyway, so get the
|
||||
* first page and all consecutive pages with the same locking.
|
||||
*/
|
||||
static long vfio_pin_pages(unsigned long vaddr, long npage,
|
||||
int prot, unsigned long *pfn_base)
|
||||
{
|
||||
dma_addr_t start = iova;
|
||||
long i, locked = 0;
|
||||
int ret;
|
||||
unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
|
||||
bool lock_cap = capable(CAP_IPC_LOCK);
|
||||
long ret, i;
|
||||
|
||||
/* Verify that pages are not already mapped */
|
||||
for (i = 0; i < npage; i++, iova += PAGE_SIZE)
|
||||
if (iommu_iova_to_phys(iommu->domain, iova))
|
||||
return -EBUSY;
|
||||
if (!current->mm)
|
||||
return -ENODEV;
|
||||
|
||||
iova = start;
|
||||
ret = vaddr_get_pfn(vaddr, prot, pfn_base);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
if (iommu->cache)
|
||||
prot |= IOMMU_CACHE;
|
||||
if (is_invalid_reserved_pfn(*pfn_base))
|
||||
return 1;
|
||||
|
||||
/*
|
||||
* XXX We break mappings into pages and use get_user_pages_fast to
|
||||
* pin the pages in memory. It's been suggested that mlock might
|
||||
* provide a more efficient mechanism, but nothing prevents the
|
||||
* user from munlocking the pages, which could then allow the user
|
||||
* access to random host memory. We also have no guarantee from the
|
||||
* IOMMU API that the iommu driver can unmap sub-pages of previous
|
||||
* mappings. This means we might lose an entire range if a single
|
||||
* page within it is unmapped. Single page mappings are inefficient,
|
||||
* but provide the most flexibility for now.
|
||||
*/
|
||||
for (i = 0; i < npage; i++, iova += PAGE_SIZE, vaddr += PAGE_SIZE) {
|
||||
if (!lock_cap && current->mm->locked_vm + 1 > limit) {
|
||||
put_pfn(*pfn_base, prot);
|
||||
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n", __func__,
|
||||
limit << PAGE_SHIFT);
|
||||
return -ENOMEM;
|
||||
}
|
||||
|
||||
if (unlikely(disable_hugepages)) {
|
||||
vfio_lock_acct(1);
|
||||
return 1;
|
||||
}
|
||||
|
||||
/* Lock all the consecutive pages from pfn_base */
|
||||
for (i = 1, vaddr += PAGE_SIZE; i < npage; i++, vaddr += PAGE_SIZE) {
|
||||
unsigned long pfn = 0;
|
||||
|
||||
ret = vaddr_get_pfn(vaddr, prot, &pfn);
|
||||
if (ret) {
|
||||
__vfio_dma_do_unmap(iommu, start, i, prot);
|
||||
return ret;
|
||||
if (ret)
|
||||
break;
|
||||
|
||||
if (pfn != *pfn_base + i || is_invalid_reserved_pfn(pfn)) {
|
||||
put_pfn(pfn, prot);
|
||||
break;
|
||||
}
|
||||
|
||||
/*
|
||||
* Only add actual locked pages to accounting
|
||||
* XXX We're effectively marking a page locked for every
|
||||
* IOVA page even though it's possible the user could be
|
||||
* backing multiple IOVAs with the same vaddr. This over-
|
||||
* penalizes the user process, but we currently have no
|
||||
* easy way to do this properly.
|
||||
*/
|
||||
if (!is_invalid_reserved_pfn(pfn))
|
||||
locked++;
|
||||
|
||||
ret = iommu_map(iommu->domain, iova,
|
||||
(phys_addr_t)pfn << PAGE_SHIFT,
|
||||
PAGE_SIZE, prot);
|
||||
if (ret) {
|
||||
/* Back out mappings on error */
|
||||
if (!lock_cap && current->mm->locked_vm + i + 1 > limit) {
|
||||
put_pfn(pfn, prot);
|
||||
__vfio_dma_do_unmap(iommu, start, i, prot);
|
||||
return ret;
|
||||
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
|
||||
__func__, limit << PAGE_SHIFT);
|
||||
break;
|
||||
}
|
||||
}
|
||||
vfio_lock_acct(locked);
|
||||
|
||||
vfio_lock_acct(i);
|
||||
|
||||
return i;
|
||||
}
|
||||
|
||||
static long vfio_unpin_pages(unsigned long pfn, long npage,
|
||||
int prot, bool do_accounting)
|
||||
{
|
||||
unsigned long unlocked = 0;
|
||||
long i;
|
||||
|
||||
for (i = 0; i < npage; i++)
|
||||
unlocked += put_pfn(pfn++, prot);
|
||||
|
||||
if (do_accounting)
|
||||
vfio_lock_acct(-unlocked);
|
||||
|
||||
return unlocked;
|
||||
}
|
||||
|
||||
static int vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
|
||||
dma_addr_t iova, size_t *size)
|
||||
{
|
||||
dma_addr_t start = iova, end = iova + *size;
|
||||
long unlocked = 0;
|
||||
|
||||
while (iova < end) {
|
||||
size_t unmapped;
|
||||
phys_addr_t phys;
|
||||
|
||||
/*
|
||||
* We use the IOMMU to track the physical address. This
|
||||
* saves us from having a lot more entries in our mapping
|
||||
* tree. The downside is that we don't track the size
|
||||
* used to do the mapping. We request unmap of a single
|
||||
* page, but expect IOMMUs that support large pages to
|
||||
* unmap a larger chunk.
|
||||
*/
|
||||
phys = iommu_iova_to_phys(iommu->domain, iova);
|
||||
if (WARN_ON(!phys)) {
|
||||
iova += PAGE_SIZE;
|
||||
continue;
|
||||
}
|
||||
|
||||
unmapped = iommu_unmap(iommu->domain, iova, PAGE_SIZE);
|
||||
if (!unmapped)
|
||||
break;
|
||||
|
||||
unlocked += vfio_unpin_pages(phys >> PAGE_SHIFT,
|
||||
unmapped >> PAGE_SHIFT,
|
||||
dma->prot, false);
|
||||
iova += unmapped;
|
||||
}
|
||||
|
||||
vfio_lock_acct(-unlocked);
|
||||
|
||||
*size = iova - start;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static inline bool ranges_overlap(dma_addr_t start1, size_t size1,
|
||||
dma_addr_t start2, size_t size2)
|
||||
{
|
||||
if (start1 < start2)
|
||||
return (start2 - start1 < size1);
|
||||
else if (start2 < start1)
|
||||
return (start1 - start2 < size2);
|
||||
return (size1 > 0 && size2 > 0);
|
||||
}
|
||||
|
||||
static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu,
|
||||
dma_addr_t start, size_t size)
|
||||
{
|
||||
struct vfio_dma *dma;
|
||||
|
||||
list_for_each_entry(dma, &iommu->dma_list, next) {
|
||||
if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
|
||||
start, size))
|
||||
return dma;
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static long vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start,
|
||||
size_t size, struct vfio_dma *dma)
|
||||
static int vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start,
|
||||
size_t *size, struct vfio_dma *dma)
|
||||
{
|
||||
size_t offset, overlap, tmp;
|
||||
struct vfio_dma *split;
|
||||
long npage_lo, npage_hi;
|
||||
int ret;
|
||||
|
||||
/* Existing dma region is completely covered, unmap all */
|
||||
if (start <= dma->iova &&
|
||||
start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
|
||||
vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
|
||||
list_del(&dma->next);
|
||||
npage_lo = dma->npage;
|
||||
if (!*size)
|
||||
return 0;
|
||||
|
||||
/*
|
||||
* Existing dma region is completely covered, unmap all. This is
|
||||
* the likely case since userspace tends to map and unmap buffers
|
||||
* in one shot rather than multiple mappings within a buffer.
|
||||
*/
|
||||
if (likely(start <= dma->iova &&
|
||||
start + *size >= dma->iova + dma->size)) {
|
||||
*size = dma->size;
|
||||
ret = vfio_unmap_unpin(iommu, dma, dma->iova, size);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
/*
|
||||
* Did we remove more than we have? Should never happen
|
||||
* since a vfio_dma is contiguous in iova and vaddr.
|
||||
*/
|
||||
WARN_ON(*size != dma->size);
|
||||
|
||||
vfio_remove_dma(iommu, dma);
|
||||
kfree(dma);
|
||||
return npage_lo;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Overlap low address of existing range */
|
||||
if (start <= dma->iova) {
|
||||
size_t overlap;
|
||||
overlap = start + *size - dma->iova;
|
||||
ret = vfio_unmap_unpin(iommu, dma, dma->iova, &overlap);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
overlap = start + size - dma->iova;
|
||||
npage_lo = overlap >> PAGE_SHIFT;
|
||||
vfio_remove_dma(iommu, dma);
|
||||
|
||||
vfio_dma_unmap(iommu, dma->iova, npage_lo, dma->prot);
|
||||
dma->iova += overlap;
|
||||
dma->vaddr += overlap;
|
||||
dma->npage -= npage_lo;
|
||||
return npage_lo;
|
||||
/*
|
||||
* Check, we may have removed to whole vfio_dma. If not
|
||||
* fixup and re-insert.
|
||||
*/
|
||||
if (overlap < dma->size) {
|
||||
dma->iova += overlap;
|
||||
dma->vaddr += overlap;
|
||||
dma->size -= overlap;
|
||||
vfio_insert_dma(iommu, dma);
|
||||
} else
|
||||
kfree(dma);
|
||||
|
||||
*size = overlap;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Overlap high address of existing range */
|
||||
if (start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) {
|
||||
size_t overlap;
|
||||
if (start + *size >= dma->iova + dma->size) {
|
||||
offset = start - dma->iova;
|
||||
overlap = dma->size - offset;
|
||||
|
||||
overlap = dma->iova + NPAGE_TO_SIZE(dma->npage) - start;
|
||||
npage_hi = overlap >> PAGE_SHIFT;
|
||||
ret = vfio_unmap_unpin(iommu, dma, start, &overlap);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
vfio_dma_unmap(iommu, start, npage_hi, dma->prot);
|
||||
dma->npage -= npage_hi;
|
||||
return npage_hi;
|
||||
dma->size -= overlap;
|
||||
*size = overlap;
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* Split existing */
|
||||
npage_lo = (start - dma->iova) >> PAGE_SHIFT;
|
||||
npage_hi = dma->npage - (size >> PAGE_SHIFT) - npage_lo;
|
||||
|
||||
split = kzalloc(sizeof *split, GFP_KERNEL);
|
||||
/*
|
||||
* Allocate our tracking structure early even though it may not
|
||||
* be used. An Allocation failure later loses track of pages and
|
||||
* is more difficult to unwind.
|
||||
*/
|
||||
split = kzalloc(sizeof(*split), GFP_KERNEL);
|
||||
if (!split)
|
||||
return -ENOMEM;
|
||||
|
||||
vfio_dma_unmap(iommu, start, size >> PAGE_SHIFT, dma->prot);
|
||||
offset = start - dma->iova;
|
||||
|
||||
dma->npage = npage_lo;
|
||||
ret = vfio_unmap_unpin(iommu, dma, start, size);
|
||||
if (ret || !*size) {
|
||||
kfree(split);
|
||||
return ret;
|
||||
}
|
||||
|
||||
split->npage = npage_hi;
|
||||
split->iova = start + size;
|
||||
split->vaddr = dma->vaddr + NPAGE_TO_SIZE(npage_lo) + size;
|
||||
split->prot = dma->prot;
|
||||
list_add(&split->next, &iommu->dma_list);
|
||||
return size >> PAGE_SHIFT;
|
||||
tmp = dma->size;
|
||||
|
||||
/* Resize the lower vfio_dma in place, before the below insert */
|
||||
dma->size = offset;
|
||||
|
||||
/* Insert new for remainder, assuming it didn't all get unmapped */
|
||||
if (likely(offset + *size < tmp)) {
|
||||
split->size = tmp - offset - *size;
|
||||
split->iova = dma->iova + offset + *size;
|
||||
split->vaddr = dma->vaddr + offset + *size;
|
||||
split->prot = dma->prot;
|
||||
vfio_insert_dma(iommu, split);
|
||||
} else
|
||||
kfree(split);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
|
||||
struct vfio_iommu_type1_dma_unmap *unmap)
|
||||
{
|
||||
long ret = 0, npage = unmap->size >> PAGE_SHIFT;
|
||||
struct vfio_dma *dma, *tmp;
|
||||
uint64_t mask;
|
||||
struct vfio_dma *dma;
|
||||
size_t unmapped = 0, size;
|
||||
int ret = 0;
|
||||
|
||||
mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
|
||||
|
||||
if (unmap->iova & mask)
|
||||
return -EINVAL;
|
||||
if (unmap->size & mask)
|
||||
if (!unmap->size || unmap->size & mask)
|
||||
return -EINVAL;
|
||||
|
||||
/* XXX We still break these down into PAGE_SIZE */
|
||||
WARN_ON(mask & PAGE_MASK);
|
||||
|
||||
mutex_lock(&iommu->lock);
|
||||
|
||||
list_for_each_entry_safe(dma, tmp, &iommu->dma_list, next) {
|
||||
if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage),
|
||||
unmap->iova, unmap->size)) {
|
||||
ret = vfio_remove_dma_overlap(iommu, unmap->iova,
|
||||
unmap->size, dma);
|
||||
if (ret > 0)
|
||||
npage -= ret;
|
||||
if (ret < 0 || npage == 0)
|
||||
break;
|
||||
}
|
||||
while ((dma = vfio_find_dma(iommu, unmap->iova, unmap->size))) {
|
||||
size = unmap->size;
|
||||
ret = vfio_remove_dma_overlap(iommu, unmap->iova, &size, dma);
|
||||
if (ret || !size)
|
||||
break;
|
||||
unmapped += size;
|
||||
}
|
||||
|
||||
mutex_unlock(&iommu->lock);
|
||||
return ret > 0 ? 0 : (int)ret;
|
||||
|
||||
/*
|
||||
* We may unmap more than requested, update the unmap struct so
|
||||
* userspace can know.
|
||||
*/
|
||||
unmap->size = unmapped;
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
/*
|
||||
* Turns out AMD IOMMU has a page table bug where it won't map large pages
|
||||
* to a region that previously mapped smaller pages. This should be fixed
|
||||
* soon, so this is just a temporary workaround to break mappings down into
|
||||
* PAGE_SIZE. Better to map smaller pages than nothing.
|
||||
*/
|
||||
static int map_try_harder(struct vfio_iommu *iommu, dma_addr_t iova,
|
||||
unsigned long pfn, long npage, int prot)
|
||||
{
|
||||
long i;
|
||||
int ret;
|
||||
|
||||
for (i = 0; i < npage; i++, pfn++, iova += PAGE_SIZE) {
|
||||
ret = iommu_map(iommu->domain, iova,
|
||||
(phys_addr_t)pfn << PAGE_SHIFT,
|
||||
PAGE_SIZE, prot);
|
||||
if (ret)
|
||||
break;
|
||||
}
|
||||
|
||||
for (; i < npage && i > 0; i--, iova -= PAGE_SIZE)
|
||||
iommu_unmap(iommu->domain, iova, PAGE_SIZE);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
static int vfio_dma_do_map(struct vfio_iommu *iommu,
|
||||
struct vfio_iommu_type1_dma_map *map)
|
||||
{
|
||||
struct vfio_dma *dma, *pdma = NULL;
|
||||
dma_addr_t iova = map->iova;
|
||||
unsigned long locked, lock_limit, vaddr = map->vaddr;
|
||||
dma_addr_t end, iova;
|
||||
unsigned long vaddr = map->vaddr;
|
||||
size_t size = map->size;
|
||||
long npage;
|
||||
int ret = 0, prot = 0;
|
||||
uint64_t mask;
|
||||
long npage;
|
||||
|
||||
end = map->iova + map->size;
|
||||
|
||||
mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1;
|
||||
|
||||
|
|
@ -430,104 +559,144 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
|
|||
if (!prot)
|
||||
return -EINVAL; /* No READ/WRITE? */
|
||||
|
||||
if (iommu->cache)
|
||||
prot |= IOMMU_CACHE;
|
||||
|
||||
if (vaddr & mask)
|
||||
return -EINVAL;
|
||||
if (iova & mask)
|
||||
if (map->iova & mask)
|
||||
return -EINVAL;
|
||||
if (size & mask)
|
||||
if (!map->size || map->size & mask)
|
||||
return -EINVAL;
|
||||
|
||||
/* XXX We still break these down into PAGE_SIZE */
|
||||
WARN_ON(mask & PAGE_MASK);
|
||||
|
||||
/* Don't allow IOVA wrap */
|
||||
if (iova + size && iova + size < iova)
|
||||
if (end && end < map->iova)
|
||||
return -EINVAL;
|
||||
|
||||
/* Don't allow virtual address wrap */
|
||||
if (vaddr + size && vaddr + size < vaddr)
|
||||
return -EINVAL;
|
||||
|
||||
npage = size >> PAGE_SHIFT;
|
||||
if (!npage)
|
||||
if (vaddr + map->size && vaddr + map->size < vaddr)
|
||||
return -EINVAL;
|
||||
|
||||
mutex_lock(&iommu->lock);
|
||||
|
||||
if (vfio_find_dma(iommu, iova, size)) {
|
||||
ret = -EBUSY;
|
||||
goto out_lock;
|
||||
if (vfio_find_dma(iommu, map->iova, map->size)) {
|
||||
mutex_unlock(&iommu->lock);
|
||||
return -EEXIST;
|
||||
}
|
||||
|
||||
/* account for locked pages */
|
||||
locked = current->mm->locked_vm + npage;
|
||||
lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
|
||||
if (locked > lock_limit && !capable(CAP_IPC_LOCK)) {
|
||||
pr_warn("%s: RLIMIT_MEMLOCK (%ld) exceeded\n",
|
||||
__func__, rlimit(RLIMIT_MEMLOCK));
|
||||
ret = -ENOMEM;
|
||||
goto out_lock;
|
||||
}
|
||||
for (iova = map->iova; iova < end; iova += size, vaddr += size) {
|
||||
struct vfio_dma *dma = NULL;
|
||||
unsigned long pfn;
|
||||
long i;
|
||||
|
||||
ret = __vfio_dma_map(iommu, iova, vaddr, npage, prot);
|
||||
if (ret)
|
||||
goto out_lock;
|
||||
|
||||
/* Check if we abut a region below - nothing below 0 */
|
||||
if (iova) {
|
||||
dma = vfio_find_dma(iommu, iova - 1, 1);
|
||||
if (dma && dma->prot == prot &&
|
||||
dma->vaddr + NPAGE_TO_SIZE(dma->npage) == vaddr) {
|
||||
|
||||
dma->npage += npage;
|
||||
iova = dma->iova;
|
||||
vaddr = dma->vaddr;
|
||||
npage = dma->npage;
|
||||
size = NPAGE_TO_SIZE(npage);
|
||||
|
||||
pdma = dma;
|
||||
/* Pin a contiguous chunk of memory */
|
||||
npage = vfio_pin_pages(vaddr, (end - iova) >> PAGE_SHIFT,
|
||||
prot, &pfn);
|
||||
if (npage <= 0) {
|
||||
WARN_ON(!npage);
|
||||
ret = (int)npage;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
/* Check if we abut a region above - nothing above ~0 + 1 */
|
||||
if (iova + size) {
|
||||
dma = vfio_find_dma(iommu, iova + size, 1);
|
||||
if (dma && dma->prot == prot &&
|
||||
dma->vaddr == vaddr + size) {
|
||||
/* Verify pages are not already mapped */
|
||||
for (i = 0; i < npage; i++) {
|
||||
if (iommu_iova_to_phys(iommu->domain,
|
||||
iova + (i << PAGE_SHIFT))) {
|
||||
vfio_unpin_pages(pfn, npage, prot, true);
|
||||
ret = -EBUSY;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
dma->npage += npage;
|
||||
ret = iommu_map(iommu->domain, iova,
|
||||
(phys_addr_t)pfn << PAGE_SHIFT,
|
||||
npage << PAGE_SHIFT, prot);
|
||||
if (ret) {
|
||||
if (ret != -EBUSY ||
|
||||
map_try_harder(iommu, iova, pfn, npage, prot)) {
|
||||
vfio_unpin_pages(pfn, npage, prot, true);
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
size = npage << PAGE_SHIFT;
|
||||
|
||||
/*
|
||||
* Check if we abut a region below - nothing below 0.
|
||||
* This is the most likely case when mapping chunks of
|
||||
* physically contiguous regions within a virtual address
|
||||
* range. Update the abutting entry in place since iova
|
||||
* doesn't change.
|
||||
*/
|
||||
if (likely(iova)) {
|
||||
struct vfio_dma *tmp;
|
||||
tmp = vfio_find_dma(iommu, iova - 1, 1);
|
||||
if (tmp && tmp->prot == prot &&
|
||||
tmp->vaddr + tmp->size == vaddr) {
|
||||
tmp->size += size;
|
||||
iova = tmp->iova;
|
||||
size = tmp->size;
|
||||
vaddr = tmp->vaddr;
|
||||
dma = tmp;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Check if we abut a region above - nothing above ~0 + 1.
|
||||
* If we abut above and below, remove and free. If only
|
||||
* abut above, remove, modify, reinsert.
|
||||
*/
|
||||
if (likely(iova + size)) {
|
||||
struct vfio_dma *tmp;
|
||||
tmp = vfio_find_dma(iommu, iova + size, 1);
|
||||
if (tmp && tmp->prot == prot &&
|
||||
tmp->vaddr == vaddr + size) {
|
||||
vfio_remove_dma(iommu, tmp);
|
||||
if (dma) {
|
||||
dma->size += tmp->size;
|
||||
kfree(tmp);
|
||||
} else {
|
||||
size += tmp->size;
|
||||
tmp->size = size;
|
||||
tmp->iova = iova;
|
||||
tmp->vaddr = vaddr;
|
||||
vfio_insert_dma(iommu, tmp);
|
||||
dma = tmp;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (!dma) {
|
||||
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
|
||||
if (!dma) {
|
||||
iommu_unmap(iommu->domain, iova, size);
|
||||
vfio_unpin_pages(pfn, npage, prot, true);
|
||||
ret = -ENOMEM;
|
||||
break;
|
||||
}
|
||||
|
||||
dma->size = size;
|
||||
dma->iova = iova;
|
||||
dma->vaddr = vaddr;
|
||||
|
||||
/*
|
||||
* If merged above and below, remove previously
|
||||
* merged entry. New entry covers it.
|
||||
*/
|
||||
if (pdma) {
|
||||
list_del(&pdma->next);
|
||||
kfree(pdma);
|
||||
}
|
||||
pdma = dma;
|
||||
dma->prot = prot;
|
||||
vfio_insert_dma(iommu, dma);
|
||||
}
|
||||
}
|
||||
|
||||
/* Isolated, new region */
|
||||
if (!pdma) {
|
||||
dma = kzalloc(sizeof *dma, GFP_KERNEL);
|
||||
if (!dma) {
|
||||
ret = -ENOMEM;
|
||||
vfio_dma_unmap(iommu, iova, npage, prot);
|
||||
goto out_lock;
|
||||
if (ret) {
|
||||
struct vfio_dma *tmp;
|
||||
iova = map->iova;
|
||||
size = map->size;
|
||||
while ((tmp = vfio_find_dma(iommu, iova, size))) {
|
||||
int r = vfio_remove_dma_overlap(iommu, iova,
|
||||
&size, tmp);
|
||||
if (WARN_ON(r || !size))
|
||||
break;
|
||||
}
|
||||
|
||||
dma->npage = npage;
|
||||
dma->iova = iova;
|
||||
dma->vaddr = vaddr;
|
||||
dma->prot = prot;
|
||||
list_add(&dma->next, &iommu->dma_list);
|
||||
}
|
||||
|
||||
out_lock:
|
||||
mutex_unlock(&iommu->lock);
|
||||
return ret;
|
||||
}
|
||||
|
|
@ -606,7 +775,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
|
|||
return ERR_PTR(-ENOMEM);
|
||||
|
||||
INIT_LIST_HEAD(&iommu->group_list);
|
||||
INIT_LIST_HEAD(&iommu->dma_list);
|
||||
iommu->dma_list = RB_ROOT;
|
||||
mutex_init(&iommu->lock);
|
||||
|
||||
/*
|
||||
|
|
@ -640,7 +809,7 @@ static void vfio_iommu_type1_release(void *iommu_data)
|
|||
{
|
||||
struct vfio_iommu *iommu = iommu_data;
|
||||
struct vfio_group *group, *group_tmp;
|
||||
struct vfio_dma *dma, *dma_tmp;
|
||||
struct rb_node *node;
|
||||
|
||||
list_for_each_entry_safe(group, group_tmp, &iommu->group_list, next) {
|
||||
iommu_detach_group(iommu->domain, group->iommu_group);
|
||||
|
|
@ -648,10 +817,12 @@ static void vfio_iommu_type1_release(void *iommu_data)
|
|||
kfree(group);
|
||||
}
|
||||
|
||||
list_for_each_entry_safe(dma, dma_tmp, &iommu->dma_list, next) {
|
||||
vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot);
|
||||
list_del(&dma->next);
|
||||
kfree(dma);
|
||||
while ((node = rb_first(&iommu->dma_list))) {
|
||||
struct vfio_dma *dma = rb_entry(node, struct vfio_dma, node);
|
||||
size_t size = dma->size;
|
||||
vfio_remove_dma_overlap(iommu, dma->iova, &size, dma);
|
||||
if (WARN_ON(!size))
|
||||
break;
|
||||
}
|
||||
|
||||
iommu_domain_free(iommu->domain);
|
||||
|
|
@ -706,6 +877,7 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
|
|||
|
||||
} else if (cmd == VFIO_IOMMU_UNMAP_DMA) {
|
||||
struct vfio_iommu_type1_dma_unmap unmap;
|
||||
long ret;
|
||||
|
||||
minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size);
|
||||
|
||||
|
|
@ -715,7 +887,11 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
|
|||
if (unmap.argsz < minsz || unmap.flags)
|
||||
return -EINVAL;
|
||||
|
||||
return vfio_dma_do_unmap(iommu, &unmap);
|
||||
ret = vfio_dma_do_unmap(iommu, &unmap);
|
||||
if (ret)
|
||||
return ret;
|
||||
|
||||
return copy_to_user((void __user *)arg, &unmap, minsz);
|
||||
}
|
||||
|
||||
return -ENOTTY;
|
||||
|
|
|
|||
|
|
@ -362,10 +362,14 @@ struct vfio_iommu_type1_dma_map {
|
|||
#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13)
|
||||
|
||||
/**
|
||||
* VFIO_IOMMU_UNMAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 14, struct vfio_dma_unmap)
|
||||
* VFIO_IOMMU_UNMAP_DMA - _IOWR(VFIO_TYPE, VFIO_BASE + 14,
|
||||
* struct vfio_dma_unmap)
|
||||
*
|
||||
* Unmap IO virtual addresses using the provided struct vfio_dma_unmap.
|
||||
* Caller sets argsz.
|
||||
* Caller sets argsz. The actual unmapped size is returned in the size
|
||||
* field. No guarantee is made to the user that arbitrary unmaps of iova
|
||||
* or size different from those used in the original mapping call will
|
||||
* succeed.
|
||||
*/
|
||||
struct vfio_iommu_type1_dma_unmap {
|
||||
__u32 argsz;
|
||||
|
|
|
|||
Loading…
Reference in New Issue