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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240805082106.65847-1-jasowang@redhat.com>
Date: Mon,  5 Aug 2024 16:21:06 +0800
From: Jason Wang <jasowang@...hat.com>
To: mst@...hat.com,
	jasowang@...hat.com,
	xuanzhuo@...ux.alibaba.com,
	eperezma@...hat.com
Cc: maxime.coquelin@...hat.com,
	xieyongji@...edance.com,
	virtualization@...ts.linux.dev,
	linux-kernel@...r.kernel.org,
	21cnbao@...il.com,
	penguin-kernel@...ove.sakura.ne.jp,
	linux-mm@...ck.org,
	akpm@...ux-foundation.org
Subject: [PATCH] vduse: avoid using __GFP_NOFAIL

Barry said [1]:

"""
mm doesn't support non-blockable __GFP_NOFAIL allocation. Because
__GFP_NOFAIL without direct reclamation may just result in a busy
loop within non-sleepable contexts.
""“

Unfortuantely, we do that under read lock. A possible way to fix that
is to move the pages allocation out of the lock into the caller, but
having to allocate a huge number of pages and auxiliary page array
seems to be problematic as well per Tetsuon [2]:

"""
You should implement proper error handling instead of using
__GFP_NOFAIL if count can become large.
"""

So I choose another way, which does not release kernel bounce pages
when user tries to register usersapce bounce pages. Then we don't need
to do allocation in the path which is not expected to be fail (e.g in
the release). We pay this for more memory usage but further
optimizations could be done on top.

[1] https://lore.kernel.org/all/CACGkMEtcOJAA96SF9B8m-nZ1X04-XZr+nq8ZQ2saLnUdfOGOLg@mail.gmail.com/T/#m3caef86a66ea6318ef94f9976ddb3a0ccfe6fcf8
[2] https://lore.kernel.org/all/CACGkMEtcOJAA96SF9B8m-nZ1X04-XZr+nq8ZQ2saLnUdfOGOLg@mail.gmail.com/T/#m7ad10eaba48ade5abf2d572f24e185d9fb146480

Fixes: 6c77ed22880d ("vduse: Support using userspace pages as bounce buffer")
Signed-off-by: Jason Wang <jasowang@...hat.com>
---
 drivers/vdpa/vdpa_user/iova_domain.c | 18 ++++++++++--------
 drivers/vdpa/vdpa_user/iova_domain.h |  1 +
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c
index 791d38d6284c..933d2f7cd49a 100644
--- a/drivers/vdpa/vdpa_user/iova_domain.c
+++ b/drivers/vdpa/vdpa_user/iova_domain.c
@@ -162,6 +162,7 @@ static void vduse_domain_bounce(struct vduse_iova_domain *domain,
 				enum dma_data_direction dir)
 {
 	struct vduse_bounce_map *map;
+	struct page *page;
 	unsigned int offset;
 	void *addr;
 	size_t sz;
@@ -178,7 +179,10 @@ static void vduse_domain_bounce(struct vduse_iova_domain *domain,
 			    map->orig_phys == INVALID_PHYS_ADDR))
 			return;
 
-		addr = kmap_local_page(map->bounce_page);
+		page = domain->user_bounce_pages ?
+		       map->user_bounce_page : map->bounce_page;
+
+		addr = kmap_local_page(page);
 		do_bounce(map->orig_phys + offset, addr + offset, sz, dir);
 		kunmap_local(addr);
 		size -= sz;
@@ -270,9 +274,8 @@ int vduse_domain_add_user_bounce_pages(struct vduse_iova_domain *domain,
 				memcpy_to_page(pages[i], 0,
 					       page_address(map->bounce_page),
 					       PAGE_SIZE);
-			__free_page(map->bounce_page);
 		}
-		map->bounce_page = pages[i];
+		map->user_bounce_page = pages[i];
 		get_page(pages[i]);
 	}
 	domain->user_bounce_pages = true;
@@ -297,17 +300,16 @@ void vduse_domain_remove_user_bounce_pages(struct vduse_iova_domain *domain)
 		struct page *page = NULL;
 
 		map = &domain->bounce_maps[i];
-		if (WARN_ON(!map->bounce_page))
+		if (WARN_ON(!map->user_bounce_page))
 			continue;
 
 		/* Copy user page to kernel page if it's in use */
 		if (map->orig_phys != INVALID_PHYS_ADDR) {
-			page = alloc_page(GFP_ATOMIC | __GFP_NOFAIL);
+			page = map->bounce_page;
 			memcpy_from_page(page_address(page),
-					 map->bounce_page, 0, PAGE_SIZE);
+					 map->user_bounce_page, 0, PAGE_SIZE);
 		}
-		put_page(map->bounce_page);
-		map->bounce_page = page;
+		put_page(map->user_bounce_page);
 	}
 	domain->user_bounce_pages = false;
 out:
diff --git a/drivers/vdpa/vdpa_user/iova_domain.h b/drivers/vdpa/vdpa_user/iova_domain.h
index f92f22a7267d..7f3f0928ec78 100644
--- a/drivers/vdpa/vdpa_user/iova_domain.h
+++ b/drivers/vdpa/vdpa_user/iova_domain.h
@@ -21,6 +21,7 @@
 
 struct vduse_bounce_map {
 	struct page *bounce_page;
+	struct page *user_bounce_page;
 	u64 orig_phys;
 };
 
-- 
2.31.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ