From 799c10559d60f159ab2232203f222f18fa3c4a5f Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 15 Oct 2010 11:09:28 -0700 Subject: [PATCH 1/2] De-pessimize rds_page_copy_user Don't try to "optimize" rds_page_copy_user() by using kmap_atomic() and the unsafe atomic user mode accessor functions. It's actually slower than the straightforward code on any reasonable modern CPU. Back when the code was written (although probably not by the time it was actually merged, though), 32-bit x86 may have been the dominant architecture. And there kmap_atomic() can be a lot faster than kmap() (unless you have very good locality, in which case the virtual address caching by kmap() can overcome all the downsides). But these days, x86-64 may not be more populous, but it's getting there (and if you care about performance, it's definitely already there - you'd have upgraded your CPU's already in the last few years). And on x86-64, the non-kmap_atomic() version is faster, simply because the code is simpler and doesn't have the "re-try page fault" case. People with old hardware are not likely to care about RDS anyway, and the optimization for the 32-bit case is simply buggy, since it doesn't verify the user addresses properly. Reported-by: Dan Rosenberg Acked-by: Andrew Morton Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- net/rds/page.c | 27 +++++++-------------------- 1 file changed, 7 insertions(+), 20 deletions(-) diff --git a/net/rds/page.c b/net/rds/page.c index 595a952d4b17..1dfbfea12e9b 100644 --- a/net/rds/page.c +++ b/net/rds/page.c @@ -57,30 +57,17 @@ int rds_page_copy_user(struct page *page, unsigned long offset, unsigned long ret; void *addr; - if (to_user) + addr = kmap(page); + if (to_user) { rds_stats_add(s_copy_to_user, bytes); - else + ret = copy_to_user(ptr, addr + offset, bytes); + } else { rds_stats_add(s_copy_from_user, bytes); - - addr = kmap_atomic(page, KM_USER0); - if (to_user) - ret = __copy_to_user_inatomic(ptr, addr + offset, bytes); - else - ret = __copy_from_user_inatomic(addr + offset, ptr, bytes); - kunmap_atomic(addr, KM_USER0); - - if (ret) { - addr = kmap(page); - if (to_user) - ret = copy_to_user(ptr, addr + offset, bytes); - else - ret = copy_from_user(addr + offset, ptr, bytes); - kunmap(page); - if (ret) - return -EFAULT; + ret = copy_from_user(addr + offset, ptr, bytes); } + kunmap(page); - return 0; + return ret ? -EFAULT : 0; } EXPORT_SYMBOL_GPL(rds_page_copy_user); From 3e645d6b485446c54c6745c5e2cf5c528fe4deec Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 15 Oct 2010 11:12:38 -0700 Subject: [PATCH 2/2] v4l1: fix 32-bit compat microcode loading translation The compat code for the VIDIOCSMICROCODE ioctl is totally buggered. It's only used by the VIDEO_STRADIS driver, and that one is scheduled to staging and eventually removed unless somebody steps up to maintain it (at which point it should use request_firmware() rather than some magic ioctl). So we'll get rid of it eventually. But in the meantime, the compatibility ioctl code is broken, and this tries to get it to at least limp along (even if Mauro suggested just deleting it entirely, which may be the right thing to do - I don't think the compatibility translation code has ever worked unless you were very lucky). Reported-by: Kees Cook Cc: Mauro Carvalho Chehab Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- drivers/media/video/v4l2-compat-ioctl32.c | 32 +++++++++++++++-------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/media/video/v4l2-compat-ioctl32.c b/drivers/media/video/v4l2-compat-ioctl32.c index 073f01390cdd..86294ed35c9b 100644 --- a/drivers/media/video/v4l2-compat-ioctl32.c +++ b/drivers/media/video/v4l2-compat-ioctl32.c @@ -193,17 +193,24 @@ static int put_video_window32(struct video_window *kp, struct video_window32 __u struct video_code32 { char loadwhat[16]; /* name or tag of file being passed */ compat_int_t datasize; - unsigned char *data; + compat_uptr_t data; }; -static int get_microcode32(struct video_code *kp, struct video_code32 __user *up) +static struct video_code __user *get_microcode32(struct video_code32 *kp) { - if (!access_ok(VERIFY_READ, up, sizeof(struct video_code32)) || - copy_from_user(kp->loadwhat, up->loadwhat, sizeof(up->loadwhat)) || - get_user(kp->datasize, &up->datasize) || - copy_from_user(kp->data, up->data, up->datasize)) - return -EFAULT; - return 0; + struct video_code __user *up; + + up = compat_alloc_user_space(sizeof(*up)); + + /* + * NOTE! We don't actually care if these fail. If the + * user address is invalid, the native ioctl will do + * the error handling for us + */ + (void) copy_to_user(up->loadwhat, kp->loadwhat, sizeof(up->loadwhat)); + (void) put_user(kp->datasize, &up->datasize); + (void) put_user(compat_ptr(kp->data), &up->data); + return up; } #define VIDIOCGTUNER32 _IOWR('v', 4, struct video_tuner32) @@ -739,7 +746,7 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar struct video_tuner vt; struct video_buffer vb; struct video_window vw; - struct video_code vc; + struct video_code32 vc; struct video_audio va; #endif struct v4l2_format v2f; @@ -818,8 +825,11 @@ static long do_video_ioctl(struct file *file, unsigned int cmd, unsigned long ar break; case VIDIOCSMICROCODE: - err = get_microcode32(&karg.vc, up); - compatible_arg = 0; + /* Copy the 32-bit "video_code32" to kernel space */ + if (copy_from_user(&karg.vc, up, sizeof(karg.vc))) + return -EFAULT; + /* Convert the 32-bit version to a 64-bit version in user space */ + up = get_microcode32(&karg.vc); break; case VIDIOCSFREQ: