| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 16 Jun 2022 16:52:12 -0700
From: Nicolin Chen <nicolinc@...dia.com>
To: <kwankhede@...dia.com>, <corbet@....net>, <hca@...ux.ibm.com>,
<gor@...ux.ibm.com>, <agordeev@...ux.ibm.com>,
<borntraeger@...ux.ibm.com>, <svens@...ux.ibm.com>,
<zhenyuw@...ux.intel.com>, <zhi.a.wang@...el.com>,
<jani.nikula@...ux.intel.com>, <joonas.lahtinen@...ux.intel.com>,
<rodrigo.vivi@...el.com>, <tvrtko.ursulin@...ux.intel.com>,
<airlied@...ux.ie>, <daniel@...ll.ch>, <farman@...ux.ibm.com>,
<mjrosato@...ux.ibm.com>, <pasic@...ux.ibm.com>,
<vneethv@...ux.ibm.com>, <oberpar@...ux.ibm.com>,
<freude@...ux.ibm.com>, <akrowiak@...ux.ibm.com>,
<jjherne@...ux.ibm.com>, <alex.williamson@...hat.com>,
<cohuck@...hat.com>, <jgg@...dia.com>, <kevin.tian@...el.com>
CC: <jchrist@...ux.ibm.com>, <kvm@...r.kernel.org>,
<linux-doc@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-s390@...r.kernel.org>,
<intel-gvt-dev@...ts.freedesktop.org>,
<intel-gfx@...ts.freedesktop.org>,
<dri-devel@...ts.freedesktop.org>
Subject: [RFT][PATCH v1 6/6] vfio: Replace phys_pfn with phys_page for vfio_pin_pages()
Most of the callers of vfio_pin_pages() want "struct page *" and the
low-level mm code to pin pages returns a list of "struct page *" too.
So there's no gain in converting "struct page *" to PFN in between.
Replace the output parameter phys_pfn list with a phys_page list, to
simplify callers. This also allows us to replace the vfio_iommu_type1
implementation with a more efficient one.
For now, also update vfio_iommu_type1 to fit this new parameter too.
Signed-off-by: Nicolin Chen <nicolinc@...dia.com>
---
.../driver-api/vfio-mediated-device.rst | 2 +-
drivers/gpu/drm/i915/gvt/kvmgt.c | 19 ++++++-------------
drivers/s390/cio/vfio_ccw_cp.c | 19 +++++++++----------
drivers/s390/crypto/vfio_ap_ops.c | 7 ++++---
drivers/vfio/vfio.c | 8 ++++----
drivers/vfio/vfio.h | 2 +-
drivers/vfio/vfio_iommu_type1.c | 19 +++++++++++--------
include/linux/vfio.h | 2 +-
8 files changed, 37 insertions(+), 41 deletions(-)
diff --git a/Documentation/driver-api/vfio-mediated-device.rst b/Documentation/driver-api/vfio-mediated-device.rst
index d28f8bcbfbc6..070e51bb0bb6 100644
--- a/Documentation/driver-api/vfio-mediated-device.rst
+++ b/Documentation/driver-api/vfio-mediated-device.rst
@@ -263,7 +263,7 @@ The following APIs are provided for translating user pfn to host pfn in a VFIO
driver::
int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
- int npage, int prot, unsigned long *phys_pfn);
+ int npage, int prot, struct page **phys_page);
int vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova,
int npage);
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index c9bdc3901f1e..669432999676 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -243,7 +243,7 @@ static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
unsigned long size, struct page **page)
{
- unsigned long base_pfn = 0;
+ struct page *base_page = NULL;
int total_pages;
int npage;
int ret;
@@ -255,26 +255,19 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
*/
for (npage = 0; npage < total_pages; npage++) {
unsigned long cur_iova = (gfn + npage) << PAGE_SHIFT;
- unsigned long pfn;
+ struct page *cur_page;
ret = vfio_pin_pages(&vgpu->vfio_device, cur_iova, 1,
- IOMMU_READ | IOMMU_WRITE, &pfn);
+ IOMMU_READ | IOMMU_WRITE, &cur_page);
if (ret != 1) {
gvt_vgpu_err("vfio_pin_pages failed for iova 0x%lx, ret %d\n",
cur_iova, ret);
goto err;
}
- if (!pfn_valid(pfn)) {
- gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
- npage++;
- ret = -EFAULT;
- goto err;
- }
-
if (npage == 0)
- base_pfn = pfn;
- else if (base_pfn + npage != pfn) {
+ base_page = cur_page;
+ else if (base_page + npage != cur_page) {
gvt_vgpu_err("The pages are not continuous\n");
ret = -EINVAL;
npage++;
@@ -282,7 +275,7 @@ static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
}
}
- *page = pfn_to_page(base_pfn);
+ *page = base_page;
return 0;
err:
gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 12cbe66721af..92be288dff74 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -24,8 +24,8 @@ struct pfn_array {
unsigned long pa_iova;
/* Array that stores PFNs of the pages need to pin. */
unsigned long *pa_iova_pfn;
- /* Array that receives PFNs of the pages pinned. */
- unsigned long *pa_pfn;
+ /* Array that receives the pinned pages. */
+ struct page **pa_page;
/* Number of pages pinned from @pa_iova. */
int pa_nr;
};
@@ -73,19 +73,19 @@ static int pfn_array_alloc(struct pfn_array *pa, u64 iova, unsigned int len)
pa->pa_iova_pfn = kcalloc(pa->pa_nr,
sizeof(*pa->pa_iova_pfn) +
- sizeof(*pa->pa_pfn),
+ sizeof(*pa->pa_page),
GFP_KERNEL);
if (unlikely(!pa->pa_iova_pfn)) {
pa->pa_nr = 0;
return -ENOMEM;
}
- pa->pa_pfn = pa->pa_iova_pfn + pa->pa_nr;
+ pa->pa_page = (struct page **)pa->pa_iova_pfn + pa->pa_nr;
pa->pa_iova_pfn[0] = pa->pa_iova >> PAGE_SHIFT;
- pa->pa_pfn[0] = -1ULL;
+ pa->pa_page[0] = NULL;
for (i = 1; i < pa->pa_nr; i++) {
pa->pa_iova_pfn[i] = pa->pa_iova_pfn[i - 1] + 1;
- pa->pa_pfn[i] = -1ULL;
+ pa->pa_page[i] = NULL;
}
return 0;
@@ -147,7 +147,7 @@ static int pfn_array_pin(struct pfn_array *pa, struct vfio_device *vdev)
ret = vfio_pin_pages(vdev, *first << PAGE_SHIFT, npage,
IOMMU_READ | IOMMU_WRITE,
- &pa->pa_pfn[pinned]);
+ &pa->pa_page[pinned]);
if (ret < 0) {
goto err_out;
} else if (ret > 0 && ret != npage) {
@@ -200,7 +200,7 @@ static inline void pfn_array_idal_create_words(
*/
for (i = 0; i < pa->pa_nr; i++)
- idaws[i] = pa->pa_pfn[i] << PAGE_SHIFT;
+ idaws[i] = page_to_phys(pa->pa_page[i]);
/* Adjust the first IDAW, since it may not start on a page boundary */
idaws[0] += pa->pa_iova & (PAGE_SIZE - 1);
@@ -251,8 +251,7 @@ static long copy_from_iova(struct vfio_device *vdev, void *to, u64 iova,
l = n;
for (i = 0; i < pa.pa_nr; i++) {
- struct page *page = pfn_to_page(pa.pa_pfn[i]);
- void *from = kmap_local_page(page);
+ void *from = kmap_local_page(pa.pa_page[i]);
m = PAGE_SIZE;
if (i == 0) {
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 8a2018ab3cf0..e73bdb57bc90 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -243,9 +243,10 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
struct ap_qirq_ctrl aqic_gisa = {};
struct ap_queue_status status = {};
struct kvm_s390_gisa *gisa;
+ struct page *h_page;
int nisc;
struct kvm *kvm;
- unsigned long g_pfn, h_pfn;
+ unsigned long g_pfn;
phys_addr_t h_nib;
int ret;
@@ -259,7 +260,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
}
ret = vfio_pin_pages(&q->matrix_mdev->vdev, g_pfn << PAGE_SHIFT, 1,
- IOMMU_READ | IOMMU_WRITE, &h_pfn);
+ IOMMU_READ | IOMMU_WRITE, &h_page);
switch (ret) {
case 1:
break;
@@ -275,7 +276,7 @@ static struct ap_queue_status vfio_ap_irq_enable(struct vfio_ap_queue *q,
kvm = q->matrix_mdev->kvm;
gisa = kvm->arch.gisa_int.origin;
- h_nib = (h_pfn << PAGE_SHIFT) | (nib & ~PAGE_MASK);
+ h_nib = page_to_phys(h_page) | (nib & ~PAGE_MASK);
aqic_gisa.gisc = isc;
nisc = kvm_s390_gisc_register(kvm, isc);
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index e8dbb0122e20..7eee8048e231 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -1917,18 +1917,18 @@ EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
* @npage [in] : count of pages to be pinned. This count should not
* be greater VFIO_PIN_PAGES_MAX_ENTRIES.
* @prot [in] : protection flags
- * @phys_pfn[out]: array of host PFNs
+ * @phys_page[out]: array of host pages
* Return error or number of pages pinned.
*/
int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
- int npage, int prot, unsigned long *phys_pfn)
+ int npage, int prot, struct page **phys_page)
{
struct vfio_container *container;
struct vfio_group *group = device->group;
struct vfio_iommu_driver *driver;
int ret;
- if (!phys_pfn || !npage || !vfio_assert_device_open(device))
+ if (!phys_page || !npage || !vfio_assert_device_open(device))
return -EINVAL;
if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
@@ -1943,7 +1943,7 @@ int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
if (likely(driver && driver->ops->pin_pages))
ret = driver->ops->pin_pages(container->iommu_data,
group->iommu_group, iova,
- npage, prot, phys_pfn);
+ npage, prot, phys_page);
else
ret = -ENOTTY;
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index 6bd5304ee0b7..758a0a91a066 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -52,7 +52,7 @@ struct vfio_iommu_driver_ops {
struct iommu_group *group,
dma_addr_t user_iova,
int npage, int prot,
- unsigned long *phys_pfn);
+ struct page **phys_page);
int (*unpin_pages)(void *iommu_data,
dma_addr_t user_iova, int npage);
int (*register_notifier)(void *iommu_data,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index d027ed8441a9..841b1803e313 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -830,7 +830,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
struct iommu_group *iommu_group,
dma_addr_t user_iova,
int npage, int prot,
- unsigned long *phys_pfn)
+ struct page **phys_page)
{
struct vfio_iommu *iommu = iommu_data;
struct vfio_iommu_group *group;
@@ -840,7 +840,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
bool do_accounting;
dma_addr_t iova;
- if (!iommu || !phys_pfn)
+ if (!iommu || !phys_page)
return -EINVAL;
/* Supported for v2 version only */
@@ -879,6 +879,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
do_accounting = list_empty(&iommu->domain_list);
for (i = 0; i < npage; i++) {
+ unsigned long phys_pfn;
struct vfio_pfn *vpfn;
iova = user_iova + PAGE_SIZE * i;
@@ -895,23 +896,25 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
vpfn = vfio_iova_get_vfio_pfn(dma, iova);
if (vpfn) {
- phys_pfn[i] = vpfn->pfn;
+ phys_page[i] = pfn_to_page(vpfn->pfn);
continue;
}
remote_vaddr = dma->vaddr + (iova - dma->iova);
- ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn[i],
+ ret = vfio_pin_page_external(dma, remote_vaddr, &phys_pfn,
do_accounting);
if (ret)
goto pin_unwind;
- ret = vfio_add_to_pfn_list(dma, iova, phys_pfn[i]);
+ ret = vfio_add_to_pfn_list(dma, iova, phys_pfn);
if (ret) {
- if (put_pfn(phys_pfn[i], dma->prot) && do_accounting)
+ if (put_pfn(phys_pfn, dma->prot) && do_accounting)
vfio_lock_acct(dma, -1, true);
goto pin_unwind;
}
+ phys_page[i] = pfn_to_page(phys_pfn);
+
if (iommu->dirty_page_tracking) {
unsigned long pgshift = __ffs(iommu->pgsize_bitmap);
@@ -934,14 +937,14 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
goto pin_done;
pin_unwind:
- phys_pfn[i] = 0;
+ phys_page[i] = NULL;
for (j = 0; j < i; j++) {
dma_addr_t iova;
iova = user_iova + PAGE_SIZE * j;
dma = vfio_find_dma(iommu, iova, PAGE_SIZE);
vfio_unpin_page_external(dma, iova, do_accounting);
- phys_pfn[j] = 0;
+ phys_page[j] = NULL;
}
pin_done:
mutex_unlock(&iommu->lock);
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 99c3bf52c4da..7bc18802bf39 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -148,7 +148,7 @@ extern bool vfio_file_has_dev(struct file *file, struct vfio_device *device);
#define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long))
extern int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
- int npage, int prot, unsigned long *phys_pfn);
+ int npage, int prot, struct page **phys_page);
extern int vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova,
int npage);
extern int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova,
--
2.17.1
Powered by blists - more mailing lists