| 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
| ||
|
Message-Id: <20181012060014.10242-4-jhubbard@nvidia.com>
Date: Thu, 11 Oct 2018 23:00:11 -0700
From: john.hubbard@...il.com
To: Matthew Wilcox <willy@...radead.org>,
Michal Hocko <mhocko@...nel.org>,
Christopher Lameter <cl@...ux.com>,
Jason Gunthorpe <jgg@...pe.ca>,
Dan Williams <dan.j.williams@...el.com>,
Jan Kara <jack@...e.cz>
Cc: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>,
linux-rdma <linux-rdma@...r.kernel.org>,
linux-fsdevel@...r.kernel.org, John Hubbard <jhubbard@...dia.com>,
Doug Ledford <dledford@...hat.com>,
Mike Marciniszyn <mike.marciniszyn@...el.com>,
Dennis Dalessandro <dennis.dalessandro@...el.com>,
Christian Benvenuti <benve@...co.com>
Subject: [PATCH 3/6] infiniband/mm: convert put_page() to put_user_page*()
From: John Hubbard <jhubbard@...dia.com>
For infiniband code that retains pages via get_user_pages*(),
release those pages via the new put_user_page(), or
put_user_pages*(), instead of put_page()
This is a tiny part of the second step of fixing the problem described
in [1]. The steps are:
1) Provide put_user_page*() routines, intended to be used
for releasing pages that were pinned via get_user_pages*().
2) Convert all of the call sites for get_user_pages*(), to
invoke put_user_page*(), instead of put_page(). This involves dozens of
call sites, any will take some time.
3) After (2) is complete, use get_user_pages*() and put_user_page*() to
implement tracking of these pages. This tracking will be separate from
the existing struct page refcounting.
4) Use the tracking and identification of these pages, to implement
special handling (especially in writeback paths) when the pages are
backed by a filesystem. Again, [1] provides details as to why that is
desirable.
[1] https://lwn.net/Articles/753027/ : "The Trouble with get_user_pages()"
CC: Doug Ledford <dledford@...hat.com>
CC: Jason Gunthorpe <jgg@...pe.ca>
CC: Mike Marciniszyn <mike.marciniszyn@...el.com>
CC: Dennis Dalessandro <dennis.dalessandro@...el.com>
CC: Christian Benvenuti <benve@...co.com>
CC: linux-rdma@...r.kernel.org
CC: linux-kernel@...r.kernel.org
CC: linux-mm@...ck.org
Reviewed-by: Jan Kara <jack@...e.cz>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@...el.com>
Acked-by: Jason Gunthorpe <jgg@...lanox.com>
Signed-off-by: John Hubbard <jhubbard@...dia.com>
---
drivers/infiniband/core/umem.c | 7 ++++---
drivers/infiniband/core/umem_odp.c | 2 +-
drivers/infiniband/hw/hfi1/user_pages.c | 11 ++++-------
drivers/infiniband/hw/mthca/mthca_memfree.c | 6 +++---
drivers/infiniband/hw/qib/qib_user_pages.c | 11 ++++-------
drivers/infiniband/hw/qib/qib_user_sdma.c | 6 +++---
drivers/infiniband/hw/usnic/usnic_uiom.c | 7 ++++---
7 files changed, 23 insertions(+), 27 deletions(-)
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index a41792dbae1f..7ab7a3a35eb4 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -58,9 +58,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
for_each_sg(umem->sg_head.sgl, sg, umem->npages, i) {
page = sg_page(sg);
- if (!PageDirty(page) && umem->writable && dirty)
- set_page_dirty_lock(page);
- put_page(page);
+ if (umem->writable && dirty)
+ put_user_pages_dirty_lock(&page, 1);
+ else
+ put_user_page(page);
}
sg_free_table(&umem->sg_head);
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 6ec748eccff7..6227b89cf05c 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -717,7 +717,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
ret = -EFAULT;
break;
}
- put_page(local_page_list[j]);
+ put_user_page(local_page_list[j]);
continue;
}
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
index e341e6dcc388..99ccc0483711 100644
--- a/drivers/infiniband/hw/hfi1/user_pages.c
+++ b/drivers/infiniband/hw/hfi1/user_pages.c
@@ -121,13 +121,10 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,
size_t npages, bool dirty)
{
- size_t i;
-
- for (i = 0; i < npages; i++) {
- if (dirty)
- set_page_dirty_lock(p[i]);
- put_page(p[i]);
- }
+ if (dirty)
+ put_user_pages_dirty_lock(p, npages);
+ else
+ put_user_pages(p, npages);
if (mm) { /* during close after signal, mm can be NULL */
down_write(&mm->mmap_sem);
diff --git a/drivers/infiniband/hw/mthca/mthca_memfree.c b/drivers/infiniband/hw/mthca/mthca_memfree.c
index cc9c0c8ccba3..b8b12effd009 100644
--- a/drivers/infiniband/hw/mthca/mthca_memfree.c
+++ b/drivers/infiniband/hw/mthca/mthca_memfree.c
@@ -481,7 +481,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
if (ret < 0) {
- put_page(pages[0]);
+ put_user_page(pages[0]);
goto out;
}
@@ -489,7 +489,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar,
mthca_uarc_virt(dev, uar, i));
if (ret) {
pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
- put_page(sg_page(&db_tab->page[i].mem));
+ put_user_page(sg_page(&db_tab->page[i].mem));
goto out;
}
@@ -555,7 +555,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar,
if (db_tab->page[i].uvirt) {
mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1);
pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);
- put_page(sg_page(&db_tab->page[i].mem));
+ put_user_page(sg_page(&db_tab->page[i].mem));
}
}
diff --git a/drivers/infiniband/hw/qib/qib_user_pages.c b/drivers/infiniband/hw/qib/qib_user_pages.c
index 16543d5e80c3..1a5c64c8695f 100644
--- a/drivers/infiniband/hw/qib/qib_user_pages.c
+++ b/drivers/infiniband/hw/qib/qib_user_pages.c
@@ -40,13 +40,10 @@
static void __qib_release_user_pages(struct page **p, size_t num_pages,
int dirty)
{
- size_t i;
-
- for (i = 0; i < num_pages; i++) {
- if (dirty)
- set_page_dirty_lock(p[i]);
- put_page(p[i]);
- }
+ if (dirty)
+ put_user_pages_dirty_lock(p, num_pages);
+ else
+ put_user_pages(p, num_pages);
}
/*
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index 926f3c8eba69..4a4b802b011f 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -321,7 +321,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
* the caller can ignore this page.
*/
if (put) {
- put_page(page);
+ put_user_page(page);
} else {
/* coalesce case */
kunmap(page);
@@ -635,7 +635,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
kunmap(pkt->addr[i].page);
if (pkt->addr[i].put_page)
- put_page(pkt->addr[i].page);
+ put_user_page(pkt->addr[i].page);
else
__free_page(pkt->addr[i].page);
} else if (pkt->addr[i].kvaddr) {
@@ -710,7 +710,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
/* if error, return all pages not managed by pkt */
free_pages:
while (i < j)
- put_page(pages[i++]);
+ put_user_page(pages[i++]);
done:
return ret;
diff --git a/drivers/infiniband/hw/usnic/usnic_uiom.c b/drivers/infiniband/hw/usnic/usnic_uiom.c
index 9dd39daa602b..9e3615fd05f7 100644
--- a/drivers/infiniband/hw/usnic/usnic_uiom.c
+++ b/drivers/infiniband/hw/usnic/usnic_uiom.c
@@ -89,9 +89,10 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
for_each_sg(chunk->page_list, sg, chunk->nents, i) {
page = sg_page(sg);
pa = sg_phys(sg);
- if (!PageDirty(page) && dirty)
- set_page_dirty_lock(page);
- put_page(page);
+ if (dirty)
+ put_user_pages_dirty_lock(&page, 1);
+ else
+ put_user_page(page);
usnic_dbg("pa: %pa\n", &pa);
}
kfree(chunk);
--
2.19.1
Powered by blists - more mailing lists