- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 95567729173e62e0e60a1f8ad9eb2e1320a8ccac # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051236-dense-economy-c808@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 95567729173e62e0e60a1f8ad9eb2e1320a8ccac Mon Sep 17 00:00:00 2001 From: Peter Xu <peterx(a)redhat.com> Date: Thu, 24 Apr 2025 17:57:28 -0400 Subject: [PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN race While discussing some userfaultfd relevant issues recently, Andrea noticed a potential ABI breakage with -EAGAIN on almost all userfaultfd ioctl()s. Quote from Andrea, explaining how -EAGAIN was processed, and how this should fix it (taking example of UFFDIO_COPY ioctl): The "mmap_changing" and "stale pmd" conditions are already reported as -EAGAIN written in the copy field, this does not change it. This change removes the subnormal case that left copy.copy uninitialized and required apps to explicitly set the copy field to get deterministic behavior (which is a requirement contrary to the documentation in both the manpage and source code). In turn there's no alteration to backwards compatibility as result of this change because userland will find the copy field consistently set to -EAGAIN, and not anymore sometime -EAGAIN and sometime uninitialized. Even then the change only can make a difference to non cooperative users of userfaultfd, so when UFFD_FEATURE_EVENT_* is enabled, which is not true for the vast majority of apps using userfaultfd or this unintended uninitialized field may have been noticed sooner. Meanwhile, since this bug existed for years, it also almost affects all ioctl()s that was introduced later. Besides UFFDIO_ZEROPAGE, these also get affected in the same way: - UFFDIO_CONTINUE - UFFDIO_POISON - UFFDIO_MOVE This patch should have fixed all of them. Link: https://lkml.kernel.org/r/20250424215729.194656-2-peterx@redhat.com Fixes: df2cc96e7701 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Fixes: fc71884a5f59 ("mm: userfaultfd: add new UFFDIO_POISON ioctl") Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Andrea Arcangeli <aarcange(a)redhat.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 95567729173e62e0e60a1f8ad9eb2e1320a8ccac # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051235-unusual-viewer-d8fa@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 95567729173e62e0e60a1f8ad9eb2e1320a8ccac Mon Sep 17 00:00:00 2001 From: Peter Xu <peterx(a)redhat.com> Date: Thu, 24 Apr 2025 17:57:28 -0400 Subject: [PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN race While discussing some userfaultfd relevant issues recently, Andrea noticed a potential ABI breakage with -EAGAIN on almost all userfaultfd ioctl()s. Quote from Andrea, explaining how -EAGAIN was processed, and how this should fix it (taking example of UFFDIO_COPY ioctl): The "mmap_changing" and "stale pmd" conditions are already reported as -EAGAIN written in the copy field, this does not change it. This change removes the subnormal case that left copy.copy uninitialized and required apps to explicitly set the copy field to get deterministic behavior (which is a requirement contrary to the documentation in both the manpage and source code). In turn there's no alteration to backwards compatibility as result of this change because userland will find the copy field consistently set to -EAGAIN, and not anymore sometime -EAGAIN and sometime uninitialized. Even then the change only can make a difference to non cooperative users of userfaultfd, so when UFFD_FEATURE_EVENT_* is enabled, which is not true for the vast majority of apps using userfaultfd or this unintended uninitialized field may have been noticed sooner. Meanwhile, since this bug existed for years, it also almost affects all ioctl()s that was introduced later. Besides UFFDIO_ZEROPAGE, these also get affected in the same way: - UFFDIO_CONTINUE - UFFDIO_POISON - UFFDIO_MOVE This patch should have fixed all of them. Link: https://lkml.kernel.org/r/20250424215729.194656-2-peterx@redhat.com Fixes: df2cc96e7701 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Fixes: fc71884a5f59 ("mm: userfaultfd: add new UFFDIO_POISON ioctl") Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Andrea Arcangeli <aarcange(a)redhat.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 95567729173e62e0e60a1f8ad9eb2e1320a8ccac # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051234-legwarmer-usable-d2c7@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 95567729173e62e0e60a1f8ad9eb2e1320a8ccac Mon Sep 17 00:00:00 2001 From: Peter Xu <peterx(a)redhat.com> Date: Thu, 24 Apr 2025 17:57:28 -0400 Subject: [PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN race While discussing some userfaultfd relevant issues recently, Andrea noticed a potential ABI breakage with -EAGAIN on almost all userfaultfd ioctl()s. Quote from Andrea, explaining how -EAGAIN was processed, and how this should fix it (taking example of UFFDIO_COPY ioctl): The "mmap_changing" and "stale pmd" conditions are already reported as -EAGAIN written in the copy field, this does not change it. This change removes the subnormal case that left copy.copy uninitialized and required apps to explicitly set the copy field to get deterministic behavior (which is a requirement contrary to the documentation in both the manpage and source code). In turn there's no alteration to backwards compatibility as result of this change because userland will find the copy field consistently set to -EAGAIN, and not anymore sometime -EAGAIN and sometime uninitialized. Even then the change only can make a difference to non cooperative users of userfaultfd, so when UFFD_FEATURE_EVENT_* is enabled, which is not true for the vast majority of apps using userfaultfd or this unintended uninitialized field may have been noticed sooner. Meanwhile, since this bug existed for years, it also almost affects all ioctl()s that was introduced later. Besides UFFDIO_ZEROPAGE, these also get affected in the same way: - UFFDIO_CONTINUE - UFFDIO_POISON - UFFDIO_MOVE This patch should have fixed all of them. Link: https://lkml.kernel.org/r/20250424215729.194656-2-peterx@redhat.com Fixes: df2cc96e7701 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Fixes: fc71884a5f59 ("mm: userfaultfd: add new UFFDIO_POISON ioctl") Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Andrea Arcangeli <aarcange(a)redhat.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 95567729173e62e0e60a1f8ad9eb2e1320a8ccac # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051228-laurel-hypnoses-428f@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 95567729173e62e0e60a1f8ad9eb2e1320a8ccac Mon Sep 17 00:00:00 2001 From: Peter Xu <peterx(a)redhat.com> Date: Thu, 24 Apr 2025 17:57:28 -0400 Subject: [PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN race While discussing some userfaultfd relevant issues recently, Andrea noticed a potential ABI breakage with -EAGAIN on almost all userfaultfd ioctl()s. Quote from Andrea, explaining how -EAGAIN was processed, and how this should fix it (taking example of UFFDIO_COPY ioctl): The "mmap_changing" and "stale pmd" conditions are already reported as -EAGAIN written in the copy field, this does not change it. This change removes the subnormal case that left copy.copy uninitialized and required apps to explicitly set the copy field to get deterministic behavior (which is a requirement contrary to the documentation in both the manpage and source code). In turn there's no alteration to backwards compatibility as result of this change because userland will find the copy field consistently set to -EAGAIN, and not anymore sometime -EAGAIN and sometime uninitialized. Even then the change only can make a difference to non cooperative users of userfaultfd, so when UFFD_FEATURE_EVENT_* is enabled, which is not true for the vast majority of apps using userfaultfd or this unintended uninitialized field may have been noticed sooner. Meanwhile, since this bug existed for years, it also almost affects all ioctl()s that was introduced later. Besides UFFDIO_ZEROPAGE, these also get affected in the same way: - UFFDIO_CONTINUE - UFFDIO_POISON - UFFDIO_MOVE This patch should have fixed all of them. Link: https://lkml.kernel.org/r/20250424215729.194656-2-peterx@redhat.com Fixes: df2cc96e7701 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Fixes: fc71884a5f59 ("mm: userfaultfd: add new UFFDIO_POISON ioctl") Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Andrea Arcangeli <aarcange(a)redhat.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 95567729173e62e0e60a1f8ad9eb2e1320a8ccac # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051227-malt-universe-29e7@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 95567729173e62e0e60a1f8ad9eb2e1320a8ccac Mon Sep 17 00:00:00 2001 From: Peter Xu <peterx(a)redhat.com> Date: Thu, 24 Apr 2025 17:57:28 -0400 Subject: [PATCH] mm/userfaultfd: fix uninitialized output field for -EAGAIN race While discussing some userfaultfd relevant issues recently, Andrea noticed a potential ABI breakage with -EAGAIN on almost all userfaultfd ioctl()s. Quote from Andrea, explaining how -EAGAIN was processed, and how this should fix it (taking example of UFFDIO_COPY ioctl): The "mmap_changing" and "stale pmd" conditions are already reported as -EAGAIN written in the copy field, this does not change it. This change removes the subnormal case that left copy.copy uninitialized and required apps to explicitly set the copy field to get deterministic behavior (which is a requirement contrary to the documentation in both the manpage and source code). In turn there's no alteration to backwards compatibility as result of this change because userland will find the copy field consistently set to -EAGAIN, and not anymore sometime -EAGAIN and sometime uninitialized. Even then the change only can make a difference to non cooperative users of userfaultfd, so when UFFD_FEATURE_EVENT_* is enabled, which is not true for the vast majority of apps using userfaultfd or this unintended uninitialized field may have been noticed sooner. Meanwhile, since this bug existed for years, it also almost affects all ioctl()s that was introduced later. Besides UFFDIO_ZEROPAGE, these also get affected in the same way: - UFFDIO_CONTINUE - UFFDIO_POISON - UFFDIO_MOVE This patch should have fixed all of them. Link: https://lkml.kernel.org/r/20250424215729.194656-2-peterx@redhat.com Fixes: df2cc96e7701 ("userfaultfd: prevent non-cooperative events vs mcopy_atomic races") Fixes: f619147104c8 ("userfaultfd: add UFFDIO_CONTINUE ioctl") Fixes: fc71884a5f59 ("mm: userfaultfd: add new UFFDIO_POISON ioctl") Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI") Signed-off-by: Peter Xu <peterx(a)redhat.com> Reported-by: Andrea Arcangeli <aarcange(a)redhat.com> Suggested-by: Andrea Arcangeli <aarcange(a)redhat.com> Reviewed-by: David Hildenbrand <david(a)redhat.com> Cc: Mike Rapoport <rppt(a)kernel.org> Cc: Axel Rasmussen <axelrasmussen(a)google.com> Cc: Suren Baghdasaryan <surenb(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */

4 months, 1 week

1
0
0 0

Re: Patch "s390/entry: Fix last breaking event handling in case of stack corruption" has been added to the 6.6-stable tree

by Heiko Carstens

On Sun, May 11, 2025 at 01:59:02PM -0400, Sasha Levin wrote: > This is a note to let you know that I've just added the patch titled > > s390/entry: Fix last breaking event handling in case of stack corruption > > to the 6.6-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum… > > The filename of the patch is: > s390-entry-fix-last-breaking-event-handling-in-case-.patch > and it can be found in the queue-6.6 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable(a)vger.kernel.org> know about it. This patch shouldn't be applied as it is to 6.6, 6.1, and 5.15 stable kernels, since it won't compile. I'll provide a slightly modified variant.

4 months, 1 week

2
1
0 0

FAILED: patch "[PATCH] staging: axis-fifo: Correct handling of tx_fifo_depth for" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 2ca34b508774aaa590fc3698a54204706ecca4ba # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051209-visible-hassle-6995@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 2ca34b508774aaa590fc3698a54204706ecca4ba Mon Sep 17 00:00:00 2001 From: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> Date: Fri, 18 Apr 2025 21:29:37 -0400 Subject: [PATCH] staging: axis-fifo: Correct handling of tx_fifo_depth for size validation Remove erroneous subtraction of 4 from the total FIFO depth read from device tree. The stored depth is for checking against total capacity, not initial vacancy. This prevented writes near the FIFO's full size. The check performed just before data transfer, which uses live reads of the TDFV register to determine current vacancy, correctly handles the initial Depth - 4 hardware state and subsequent FIFO fullness. Fixes: 4a965c5f89de ("staging: add driver for Xilinx AXI-Stream FIFO v4.1 IP core") Cc: stable(a)vger.kernel.org Signed-off-by: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> Link: https://lore.kernel.org/r/20250419012937.674924-1-gshahrouzi@gmail.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 7540c20090c7..04b3dc3cfe7c 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -775,9 +775,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo) goto end; } - /* IP sets TDFV to fifo depth - 4 so we will do the same */ - fifo->tx_fifo_depth -= 4; - ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo); if (ret) { dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n");

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] staging: axis-fifo: Remove hardware resets for user errors" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x c6e8d85fafa7193613db37da29c0e8d6e2515b13 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051251-pardon-stellar-d13f@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From c6e8d85fafa7193613db37da29c0e8d6e2515b13 Mon Sep 17 00:00:00 2001 From: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> Date: Fri, 18 Apr 2025 20:43:06 -0400 Subject: [PATCH] staging: axis-fifo: Remove hardware resets for user errors The axis-fifo driver performs a full hardware reset (via reset_ip_core()) in several error paths within the read and write functions. This reset flushes both TX and RX FIFOs and resets the AXI-Stream links. Allow the user to handle the error without causing hardware disruption or data loss in other FIFO paths. Fixes: 4a965c5f89de ("staging: add driver for Xilinx AXI-Stream FIFO v4.1 IP core") Cc: stable(a)vger.kernel.org Signed-off-by: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> Link: https://lore.kernel.org/r/20250419004306.669605-1-gshahrouzi@gmail.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 04b3dc3cfe7c..351f983ef914 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET); if (!bytes_available) { - dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet of length 0\n"); ret = -EIO; goto end_unlock; } if (bytes_available > len) { - dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n", + dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n", bytes_available, len); - reset_ip_core(fifo); ret = -EINVAL; goto end_unlock; } @@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, /* this probably can't happen unless IP * registers were previously mishandled */ - dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n"); ret = -EIO; goto end_unlock; } @@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, if (copy_to_user(buf + copied * sizeof(u32), tmp_buf, copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf, if (copy_from_user(tmp_buf, buf + copied * sizeof(u32), copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; }

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x f31fe8165d365379d858c53bef43254c7d6d1cfd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051213-regretful-conceded-2379@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f31fe8165d365379d858c53bef43254c7d6d1cfd Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Fri, 2 May 2025 13:18:10 +0530 Subject: [PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer On regular bootup, devices get registered to VMBus first, so when uio_hv_generic driver for a particular device type is probed, the device is already initialized and added, so sysfs creation in hv_uio_probe() works fine. However, when the device is removed and brought back, the channel gets rescinded and the device again gets registered to VMBus. However this time, the uio_hv_generic driver is already registered to probe for that device and in this case sysfs creation is tried before the device's kobject gets initialized completely. Fix this by moving the core logic of sysfs creation of ring buffer, from uio_hv_generic to HyperV's VMBus driver, where the rest of the sysfs attributes for the channels are defined. While doing that, make use of attribute groups and macros, instead of creating sysfs directly, to ensure better error handling and code flow. Problematic path: vmbus_process_offer (A new offer comes for the VMBus device) vmbus_add_channel_work vmbus_device_register |-> device_register | |... | |-> hv_uio_probe | |... | |-> sysfs_create_bin_file (leads to a warning as | the primary channel's kobject, which is used to | create the sysfs file, is not yet initialized) |-> kset_create_and_add |-> vmbus_add_channel_kobj (initialization of the primary channel's kobject happens later) Above code flow is sequential and the warning is always reproducible in this path. Fixes: 9ab877a6ccf8 ("uio_hv_generic: make ring buffer attribute for primary channel") Cc: stable(a)kernel.org Suggested-by: Saurabh Sengar <ssengar(a)linux.microsoft.com> Suggested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Tested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Link: https://lore.kernel.org/r/20250502074811.2022-2-namjain@linux.microsoft.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..0f16a83cc2d6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,27 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .size = 2 * SZ_2M, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1842,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1867,24 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1892,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..d6ffe01962c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \

4 months, 1 week

1
0
0 0

FAILED: patch "[PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x f31fe8165d365379d858c53bef43254c7d6d1cfd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025051212-blah-famine-0e8e@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f31fe8165d365379d858c53bef43254c7d6d1cfd Mon Sep 17 00:00:00 2001 From: Naman Jain <namjain(a)linux.microsoft.com> Date: Fri, 2 May 2025 13:18:10 +0530 Subject: [PATCH] uio_hv_generic: Fix sysfs creation path for ring buffer On regular bootup, devices get registered to VMBus first, so when uio_hv_generic driver for a particular device type is probed, the device is already initialized and added, so sysfs creation in hv_uio_probe() works fine. However, when the device is removed and brought back, the channel gets rescinded and the device again gets registered to VMBus. However this time, the uio_hv_generic driver is already registered to probe for that device and in this case sysfs creation is tried before the device's kobject gets initialized completely. Fix this by moving the core logic of sysfs creation of ring buffer, from uio_hv_generic to HyperV's VMBus driver, where the rest of the sysfs attributes for the channels are defined. While doing that, make use of attribute groups and macros, instead of creating sysfs directly, to ensure better error handling and code flow. Problematic path: vmbus_process_offer (A new offer comes for the VMBus device) vmbus_add_channel_work vmbus_device_register |-> device_register | |... | |-> hv_uio_probe | |... | |-> sysfs_create_bin_file (leads to a warning as | the primary channel's kobject, which is used to | create the sysfs file, is not yet initialized) |-> kset_create_and_add |-> vmbus_add_channel_kobj (initialization of the primary channel's kobject happens later) Above code flow is sequential and the warning is always reproducible in this path. Fixes: 9ab877a6ccf8 ("uio_hv_generic: make ring buffer attribute for primary channel") Cc: stable(a)kernel.org Suggested-by: Saurabh Sengar <ssengar(a)linux.microsoft.com> Suggested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Michael Kelley <mhklinux(a)outlook.com> Tested-by: Michael Kelley <mhklinux(a)outlook.com> Reviewed-by: Dexuan Cui <decui(a)microsoft.com> Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com> Link: https://lore.kernel.org/r/20250502074811.2022-2-namjain@linux.microsoft.com Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..0f16a83cc2d6 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,27 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .size = 2 * SZ_2M, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1842,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1867,24 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1892,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..d6ffe01962c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \

4 months, 1 week

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror