* [PATCH net-next v2 1/4] selftests: net: Move some UAPI header inclusions after libc ones
From: Thomas Weißschuh @ 2026-01-20 14:10 UTC (permalink / raw)
To: Eric Dumazet, Kuniyuki Iwashima, Paolo Abeni, Willem de Bruijn,
David S. Miller, Jakub Kicinski, Simon Horman, Shuah Khan,
Matthieu Baerts, Mat Martineau, Geliang Tang,
Mickaël Salaün, Günther Noack, Alexei Starovoitov,
Daniel Borkmann, Jesper Dangaard Brouer, John Fastabend,
Stanislav Fomichev, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, KP Singh, Hao Luo,
Jiri Olsa
Cc: netdev, linux-kernel, linux-api, Arnd Bergmann, linux-kselftest,
mptcp, linux-security-module, bpf, libc-alpha,
Carlos O'Donell, Adhemerval Zanella, Rich Felker, klibc,
Florian Weimer, Thomas Weißschuh
In-Reply-To: <20260120-uapi-sockaddr-v2-0-63c319111cf6@linutronix.de>
Interleaving inclusions of UAPI headers and libc headers is problematic.
Both sets of headers define conflicting symbols. To enable their
coexistence a compatibility-mechanism is in place.
An upcoming change will define 'struct sockaddr' from linux/socket.h.
However sys/socket.h from libc does not yet handle this case and a
symbol conflict will arise.
Furthermore libc-compat.h evaluates the state of the libc
inclusions only once, at the point it is included first. If another
problematic header from libc is included later, symbol conflicts arise.
This will trigger other duplicate definitions when linux/libc-compat.h
is added to linux/socket.h
Move the inclusion of UAPI headers after the inclusion of the glibc
ones, so the libc-compat.h continues to work correctly.
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
---
tools/testing/selftests/net/af_unix/diag_uid.c | 9 +++++----
tools/testing/selftests/net/busy_poller.c | 3 ++-
tools/testing/selftests/net/mptcp/mptcp_diag.c | 11 ++++++-----
tools/testing/selftests/net/nettest.c | 4 ++--
tools/testing/selftests/net/tcp_ao/icmps-discard.c | 6 +++---
tools/testing/selftests/net/tcp_ao/lib/netlink.c | 9 +++++----
tools/testing/selftests/net/tun.c | 5 +++--
7 files changed, 26 insertions(+), 21 deletions(-)
diff --git a/tools/testing/selftests/net/af_unix/diag_uid.c b/tools/testing/selftests/net/af_unix/diag_uid.c
index da7d50cedee6..05456a205325 100644
--- a/tools/testing/selftests/net/af_unix/diag_uid.c
+++ b/tools/testing/selftests/net/af_unix/diag_uid.c
@@ -5,15 +5,16 @@
#include <sched.h>
#include <unistd.h>
-#include <linux/netlink.h>
-#include <linux/rtnetlink.h>
-#include <linux/sock_diag.h>
-#include <linux/unix_diag.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <sys/un.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+
#include "kselftest_harness.h"
FIXTURE(diag_uid)
diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c
index 3a81f9c94795..34bd8d28808a 100644
--- a/tools/testing/selftests/net/busy_poller.c
+++ b/tools/testing/selftests/net/busy_poller.c
@@ -9,7 +9,6 @@
#include <stdio.h>
#include <string.h>
#include <unistd.h>
-#include <ynl.h>
#include <arpa/inet.h>
#include <netinet/in.h>
@@ -19,6 +18,8 @@
#include <sys/socket.h>
#include <sys/types.h>
+#include <ynl.h>
+
#include <linux/genetlink.h>
#include <linux/netlink.h>
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
index 8e0b1b8d84b6..af25ebfd2915 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_diag.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -1,11 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2025, Kylin Software */
-#include <linux/sock_diag.h>
-#include <linux/rtnetlink.h>
-#include <linux/inet_diag.h>
-#include <linux/netlink.h>
-#include <linux/compiler.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <linux/tcp.h>
@@ -17,6 +12,12 @@
#include <errno.h>
#include <stdio.h>
+#include <linux/sock_diag.h>
+#include <linux/rtnetlink.h>
+#include <linux/inet_diag.h>
+#include <linux/netlink.h>
+#include <linux/compiler.h>
+
#ifndef IPPROTO_MPTCP
#define IPPROTO_MPTCP 262
#endif
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 1f5227f3d64d..71430403b50b 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -10,8 +10,6 @@
#include <sys/ioctl.h>
#include <sys/socket.h>
#include <sys/wait.h>
-#include <linux/tcp.h>
-#include <linux/udp.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netinet/in.h>
@@ -30,6 +28,8 @@
#include <errno.h>
#include <getopt.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
#include <linux/xfrm.h>
#include <linux/ipsec.h>
#include <linux/pfkeyv2.h>
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index 85c1a1e958c6..451ba89914c9 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -16,12 +16,12 @@
* Author: Dmitry Safonov <dima@arista.com>
*/
#include <inttypes.h>
-#include <linux/icmp.h>
-#include <linux/icmpv6.h>
-#include <linux/ipv6.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <sys/socket.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/ipv6.h>
#include "aolib.h"
#include "../../../../include/linux/compiler.h"
diff --git a/tools/testing/selftests/net/tcp_ao/lib/netlink.c b/tools/testing/selftests/net/tcp_ao/lib/netlink.c
index 7f108493a29a..69a05820782a 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/netlink.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/netlink.c
@@ -1,14 +1,15 @@
// SPDX-License-Identifier: GPL-2.0
/* Original from tools/testing/selftests/net/ipsec.c */
-#include <linux/netlink.h>
-#include <linux/random.h>
-#include <linux/rtnetlink.h>
-#include <linux/veth.h>
#include <net/if.h>
#include <stdint.h>
#include <string.h>
#include <sys/socket.h>
+#include <linux/netlink.h>
+#include <linux/random.h>
+#include <linux/rtnetlink.h>
+#include <linux/veth.h>
+
#include "aolib.h"
#define MAX_PAYLOAD 2048
diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
index 0efc67b0357a..e6e4c52d538e 100644
--- a/tools/testing/selftests/net/tun.c
+++ b/tools/testing/selftests/net/tun.c
@@ -8,12 +8,13 @@
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+
#include <linux/if.h>
#include <linux/if_tun.h>
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
#include "kselftest_harness.h"
--
2.52.0
^ permalink raw reply related
* [PATCH net-next v2 2/4] selftests/landlock: Move some UAPI header inclusions after libc ones
From: Thomas Weißschuh @ 2026-01-20 14:10 UTC (permalink / raw)
To: Eric Dumazet, Kuniyuki Iwashima, Paolo Abeni, Willem de Bruijn,
David S. Miller, Jakub Kicinski, Simon Horman, Shuah Khan,
Matthieu Baerts, Mat Martineau, Geliang Tang,
Mickaël Salaün, Günther Noack, Alexei Starovoitov,
Daniel Borkmann, Jesper Dangaard Brouer, John Fastabend,
Stanislav Fomichev, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, KP Singh, Hao Luo,
Jiri Olsa
Cc: netdev, linux-kernel, linux-api, Arnd Bergmann, linux-kselftest,
mptcp, linux-security-module, bpf, libc-alpha,
Carlos O'Donell, Adhemerval Zanella, Rich Felker, klibc,
Florian Weimer, Thomas Weißschuh
In-Reply-To: <20260120-uapi-sockaddr-v2-0-63c319111cf6@linutronix.de>
Interleaving inclusions of UAPI headers and libc headers is problematic.
Both sets of headers define conflicting symbols. To enable their
coexistence a compatibility-mechanism is in place.
An upcoming change will define 'struct sockaddr' from linux/socket.h.
However sys/socket.h from libc does not yet handle this case and a
symbol conflict will arise.
Move the inclusion of all UAPI headers after the inclusion of the glibc
ones, so the compatibility mechanism from the UAPI headers is used.
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
---
tools/testing/selftests/landlock/audit.h | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/tools/testing/selftests/landlock/audit.h b/tools/testing/selftests/landlock/audit.h
index 44eb433e9666..c12b16c690dc 100644
--- a/tools/testing/selftests/landlock/audit.h
+++ b/tools/testing/selftests/landlock/audit.h
@@ -7,9 +7,6 @@
#define _GNU_SOURCE
#include <errno.h>
-#include <linux/audit.h>
-#include <linux/limits.h>
-#include <linux/netlink.h>
#include <regex.h>
#include <stdbool.h>
#include <stdint.h>
@@ -20,6 +17,10 @@
#include <sys/time.h>
#include <unistd.h>
+#include <linux/audit.h>
+#include <linux/limits.h>
+#include <linux/netlink.h>
+
#include "kselftest.h"
#ifndef ARRAY_SIZE
--
2.52.0
^ permalink raw reply related
* [PATCH net-next v2 0/4] net: uapi: Provide an UAPI definition of 'struct sockaddr'
From: Thomas Weißschuh @ 2026-01-20 14:10 UTC (permalink / raw)
To: Eric Dumazet, Kuniyuki Iwashima, Paolo Abeni, Willem de Bruijn,
David S. Miller, Jakub Kicinski, Simon Horman, Shuah Khan,
Matthieu Baerts, Mat Martineau, Geliang Tang,
Mickaël Salaün, Günther Noack, Alexei Starovoitov,
Daniel Borkmann, Jesper Dangaard Brouer, John Fastabend,
Stanislav Fomichev, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, KP Singh, Hao Luo,
Jiri Olsa
Cc: netdev, linux-kernel, linux-api, Arnd Bergmann, linux-kselftest,
mptcp, linux-security-module, bpf, libc-alpha,
Carlos O'Donell, Adhemerval Zanella, Rich Felker, klibc,
Florian Weimer, Thomas Weißschuh
Various UAPI headers reference 'struct sockaddr'. Currently the
definition of this struct is pulled in from the libc header
sys/socket.h. This is problematic as it introduces a dependency
on a full userspace toolchain.
Add a definition of 'struct sockaddr' to the UAPI headers.
Before that, reorder some problematic header inclusions in the selftests.
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
---
Changes in v2:
- Fix compilation failures in BPF samples and selftests
- Link to v1: https://lore.kernel.org/r/20260105-uapi-sockaddr-v1-1-b7653aba12a5@linutronix.de
---
Thomas Weißschuh (4):
selftests: net: Move some UAPI header inclusions after libc ones
selftests/landlock: Move some UAPI header inclusions after libc ones
samples/bpf: Move some UAPI header inclusions after libc ones
net: uapi: Provide an UAPI definition of 'struct sockaddr'
include/linux/socket.h | 10 ----------
include/uapi/linux/if.h | 4 ----
include/uapi/linux/libc-compat.h | 12 ++++++++++++
include/uapi/linux/socket.h | 14 ++++++++++++++
samples/bpf/xdp_adjust_tail_user.c | 6 ++++--
samples/bpf/xdp_fwd_user.c | 7 ++++---
samples/bpf/xdp_router_ipv4_user.c | 6 +++---
samples/bpf/xdp_sample_user.c | 15 ++++++++-------
samples/bpf/xdp_tx_iptunnel_user.c | 4 ++--
tools/testing/selftests/landlock/audit.h | 7 ++++---
tools/testing/selftests/net/af_unix/diag_uid.c | 9 +++++----
tools/testing/selftests/net/busy_poller.c | 3 ++-
tools/testing/selftests/net/mptcp/mptcp_diag.c | 11 ++++++-----
tools/testing/selftests/net/nettest.c | 4 ++--
tools/testing/selftests/net/tcp_ao/icmps-discard.c | 6 +++---
tools/testing/selftests/net/tcp_ao/lib/netlink.c | 9 +++++----
tools/testing/selftests/net/tun.c | 5 +++--
17 files changed, 77 insertions(+), 55 deletions(-)
---
base-commit: 24d479d26b25bce5faea3ddd9fa8f3a6c3129ea7
change-id: 20251222-uapi-sockaddr-cf10e7624729
Best regards,
--
Thomas Weißschuh <thomas.weissschuh@linutronix.de>
^ permalink raw reply
* Re: [PATCH RESEND 09/12] mm: make vm_area_desc utilise vma_flags_t only
From: Jason Gunthorpe @ 2026-01-20 13:36 UTC (permalink / raw)
To: Lorenzo Stoakes
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module
In-Reply-To: <36abc616-471b-4c7b-82f5-db87f324d708@lucifer.local>
On Tue, Jan 20, 2026 at 09:46:05AM +0000, Lorenzo Stoakes wrote:
> On Mon, Jan 19, 2026 at 07:14:03PM -0400, Jason Gunthorpe wrote:
> > On Mon, Jan 19, 2026 at 09:19:11PM +0000, Lorenzo Stoakes wrote:
> > > +static inline bool is_shared_maywrite(vma_flags_t flags)
> > > +{
> >
> > I'm not sure it is ideal to pass this array by value? Seems like it
> > might invite some negative optimizations since now the compiler has to
> > optimze away a copy too.
>
> I really don't think so? This is inlined and thus collapses to a totally
> standard vma_flags_test_all() which passes by value anyway.
> Do you have specific examples or evidence the compiler will optimise poorly here
> on that basis as compared to pass by reference? And pass by reference would
> necessitate:
I've recently seen enough cases of older compilers and other arches
making weird choices to be a little concerened. In the above case
there is no reason not to use a const pointer (and indeed that would
be the expected idomatic kernel style), so why take chances is my
thinking.
Jason
^ permalink raw reply
* Re: [PATCH tip/locking/core 0/6] compiler-context-analysis: Scoped init guards
From: Peter Zijlstra @ 2026-01-20 10:52 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Marco Elver, Ingo Molnar, Thomas Gleixner, Will Deacon,
Boqun Feng, Waiman Long, Steven Rostedt, Bart Van Assche,
kasan-dev, llvm, linux-crypto, linux-doc, linux-security-module,
linux-kernel
In-Reply-To: <20260120072401.GA5905@lst.de>
On Tue, Jan 20, 2026 at 08:24:01AM +0100, Christoph Hellwig wrote:
> On Mon, Jan 19, 2026 at 10:05:50AM +0100, Marco Elver wrote:
> > Note: Scoped guarded initialization remains optional, and normal
> > initialization can still be used if no guarded members are being
> > initialized. Another alternative is to just disable context analysis to
> > initialize guarded members with `context_unsafe(var = init)` or adding
> > the `__context_unsafe(init)` function attribute (the latter not being
> > recommended for non-trivial functions due to lack of any checking):
>
> I still think this is doing the wrong for the regular non-scoped
> cased, and I think I finally understand what is so wrong about it.
>
> The fact that mutex_init (let's use mutexes for the example, applied
> to other primitives as well) should not automatically imply guarding
> the members for the rest of the function. Because as soon as the
> structure that contains the lock is published that is not actually
> true, and we did have quite a lot of bugs because of that in the
> past.
>
> So I think the first step is to avoid implying the safety of guarded
> member access by initialing the lock. We then need to think how to
> express they are save, which would probably require explicit annotation
> unless we can come up with a scheme that makes these accesses fine
> before the mutex_init in a magic way.
But that is exactly what these patches do!
Note that the current state of things (tip/locking/core,next) is that
mutex_init() is 'special'. And I agree with you that that is quite
horrible.
Now, these patches, specifically patch 6, removes this implied
horribleness.
The alternative is an explicit annotation -- as you suggest.
So given something like:
struct my_obj {
struct mutex mutex;
int data __guarded_by(&mutex);
...
};
tip/locking/core,next:
init_my_obj(struct my_obj *obj)
{
mutex_init(&obj->mutex); // implies obj->mutex is taken until end of function
obj->data = FOO; // OK, because &obj->mutex 'held'
...
}
And per these patches that will no longer be true. So if you apply just
patch 6, which removes this implied behaviour, you get a compile fail.
Not good!
So patches 1-5 introduces alternatives.
So your preferred solution:
hch_my_obj(struct my_obj *obj)
{
mutex_init(&obj->mutex);
mutex_lock(&obj->mutex); // actually acquires lock
obj->data = FOO;
...
}
is perfectly fine and will work. But not everybody wants this. For the
people that only need to init the data fields and don't care about the
lock state we get:
init_my_obj(struct my_obj *obj)
{
guard(mutex_init)(&obj->mutex); // initializes mutex and considers lock
// held until end of function
obj->data = FOO;
...
}
For the people that want to first init the object but then actually lock
it, we get:
use_my_obj(struct my_obj *obj)
{
scoped_guard (mutex_init, &obj->mutex) { // init mutex and 'hold' for scope
obj->data = FOO;
...
}
mutex_lock(&obj->lock);
...
}
And for the people that *reaaaaaly* hate guards, it is possible to write
something like:
ugly_my_obj(struct my_obj *obj)
{
mutex_init(&obj->mutex);
__acquire_ctx_lock(&obj->mutex);
obj->data = FOO;
...
__release_ctx_lock(&obj->mutex);
mutex_lock(&obj->lock);
...
}
And, then there is the option that C++ has:
init_my_obj(struct my_obj *obj)
__no_context_analysis // STFU!
{
mutex_init(&obj->mutex);
obj->data = FOO; // WARN; but ignored
...
}
All I can make from your email is that you must be in favour of these
patches.
^ permalink raw reply
* Re: [PATCH RESEND 00/12] mm: add bitmap VMA flag helpers and convert all mmap_prepare to use them
From: Lorenzo Stoakes @ 2026-01-20 9:48 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module
In-Reply-To: <20260119231443.GT1134360@nvidia.com>
On Mon, Jan 19, 2026 at 07:14:43PM -0400, Jason Gunthorpe wrote:
> On Mon, Jan 19, 2026 at 09:19:02PM +0000, Lorenzo Stoakes wrote:
> > We introduced the bitmap VMA type vma_flags_t in the aptly named commit
> > 9ea35a25d51b ("mm: introduce VMA flags bitmap type") in order to permit
> > future growth in VMA flags and to prevent the asinine requirement that VMA
> > flags be available to 64-bit kernels only if they happened to use a bit
> > number about 32-bits.
> >
> > This is a long-term project as there are very many users of VMA flags
> > within the kernel that need to be updated in order to utilise this new
> > type.
> >
> > In order to further this aim, this series adds a number of helper functions
> > to enable ordinary interactions with VMA flags - that is testing, setting
> > and clearing them.
> >
> > In order to make working with VMA bit numbers less cumbersome this series
> > introduces the mk_vma_flags() helper macro which generates a vma_flags_t
> > from a variadic parameter list, e.g.:
> >
> > vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT,
> > VMA_EXEC_BIT);
>
> I didn't try to check every conversion, but the whole approach looks
> nice to me and I think this design is ergonomic!
Thanks :) I have spent a _lot_ of time experimenting with different approaches
and making sure the compiler generates reasonable assembly, obviously inspired
by your suggestion that something like this was viable (I lacked faith in the
compiler doing this well previously).
I did initially have the macro be even 'cleverer' so you could do e.g.:
vma_flags_set(&flags, READ, WRITE, EXEC);
And have the macro prefix VMA_ and suffix _BIT but... a. we #define READ, WRITE
and b. it means the symbols are no longer anything to do with real symbols that
exist in the source so would be confusing.
At any rate once the conversion is complete we can drop the _BIT and make it a
little nicer.
>
> Jason
Cheers, Lorenzo
^ permalink raw reply
* Re: [PATCH RESEND 09/12] mm: make vm_area_desc utilise vma_flags_t only
From: Lorenzo Stoakes @ 2026-01-20 9:46 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module
In-Reply-To: <20260119231403.GS1134360@nvidia.com>
On Mon, Jan 19, 2026 at 07:14:03PM -0400, Jason Gunthorpe wrote:
> On Mon, Jan 19, 2026 at 09:19:11PM +0000, Lorenzo Stoakes wrote:
> > +static inline bool is_shared_maywrite(vma_flags_t flags)
> > +{
>
> I'm not sure it is ideal to pass this array by value? Seems like it
> might invite some negative optimizations since now the compiler has to
> optimze away a copy too.
I really don't think so? This is inlined and thus collapses to a totally
standard vma_flags_test_all() which passes by value anyway.
Which is in itself passing-an-array-by-value, and also inlined (though we force
the inline).
I have done a bunch of assembly generation and it has all indicated the compiler
handles this perfectly well.
It in fact is the basis of being able to pretty well like-for-like replace
vm_flags_t with vma_flags_t which makes the transition significantly better (and
allows for the mk_vma_flags() helper and associated helper macros).
Do you have specific examples or evidence the compiler will optimise poorly here
on that basis as compared to pass by reference? And pass by reference would
necessitate:
vma_flags_test_all(*flags, ...);
Or changing the whole approach? My experience generating assembly doesn't
suggest any of this is necessary.
Explicitly for this case, generating the invocation from
generic_file_readonly_mmap_prepare():
if (is_shared_maywrite(desc->vma_flags))
return -EINVAL;
Is:
notl %ecx
testb $40, %cl
je .LBB106_6 [ return -EINVAL ]
In this implementation and:
notl %ecx
testb $40, %cl
je .LBB106_6 [ return -EINVAL ]
Without my series (I am omitting movl $-22, %eax in both as this just sets up
the -EINVAL return).
i.e. exactly identical.
My experience so far is this is _always_ the case, the compiler is very adept at
optimising these kinds of things.
Thanks, Lorenzo
^ permalink raw reply
* Re: [PATCH RESEND 08/12] mm: update all remaining mmap_prepare users to use vma_flags_t
From: Lorenzo Stoakes @ 2026-01-20 9:01 UTC (permalink / raw)
To: Zi Yan
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Jann Horn, Pedro Falcato, David Howells, Paul Moore, James Morris,
Serge E . Hallyn, Yury Norov, Rasmus Villemoes, linux-sgx,
linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <34F72E48-5F22-4A20-BF32-917CDB898164@nvidia.com>
On Mon, Jan 19, 2026 at 09:59:51PM -0500, Zi Yan wrote:
> On 19 Jan 2026, at 16:19, Lorenzo Stoakes wrote:
>
> > We will be shortly removing the vm_flags_t field from vm_area_desc so we
> > need to update all mmap_prepare users to only use the dessc->vma_flags
> > field.
> >
> > This patch achieves that and makes all ancillary changes required to make
> > this possible.
> >
> > This lays the groundwork for future work to eliminate the use of vm_flags_t
> > in vm_area_desc altogether and more broadly throughout the kernel.
> >
> > While we're here, we take the opportunity to replace VM_REMAP_FLAGS with
> > VMA_REMAP_FLAGS, the vma_flags_t equivalent.
> >
> > No functional changes intended.
> >
> > Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> > ---
> > drivers/char/mem.c | 6 +++---
> > drivers/dax/device.c | 10 +++++-----
> > fs/aio.c | 2 +-
> > fs/erofs/data.c | 5 +++--
> > fs/ext4/file.c | 4 ++--
> > fs/ntfs3/file.c | 2 +-
> > fs/orangefs/file.c | 4 ++--
> > fs/ramfs/file-nommu.c | 2 +-
> > fs/resctrl/pseudo_lock.c | 2 +-
> > fs/romfs/mmap-nommu.c | 2 +-
> > fs/xfs/xfs_file.c | 4 ++--
> > fs/zonefs/file.c | 3 ++-
> > include/linux/dax.h | 4 ++--
> > include/linux/mm.h | 24 +++++++++++++++++++-----
> > kernel/relay.c | 2 +-
> > mm/memory.c | 17 ++++++++---------
> > 16 files changed, 54 insertions(+), 39 deletions(-)
> >
>
> You missed one instance in !CONFIG_DAX:
Yup of course I did... :/ the amount of testing I did here and yet there's
always some straggler that even allmodconfig somehow doesn't expose.
Let me gather up the cases first and I'll fix-patch.
Thanks, Lorenzo
>
> diff --git a/include/linux/dax.h b/include/linux/dax.h
> index 162c19fe478c..48d20b790a7d 100644
> --- a/include/linux/dax.h
> +++ b/include/linux/dax.h
> @@ -111,11 +111,11 @@ static inline void set_dax_nomc(struct dax_device *dax_dev)
> static inline void set_dax_synchronous(struct dax_device *dax_dev)
> {
> }
> -static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
> +static inline bool daxdev_mapping_supported(vma_flags_t flags,
> const struct inode *inode,
> struct dax_device *dax_dev)
> {
> - return !(vm_flags & VM_SYNC);
> + return !vma_flags_test(flags, VMA_SYNC_BIT);
> }
> static inline size_t dax_recovery_write(struct dax_device *dax_dev,
> pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
>
>
> Best Regards,
> Yan, Zi
^ permalink raw reply
* Re: [PATCH tip/locking/core 0/6] compiler-context-analysis: Scoped init guards
From: Christoph Hellwig @ 2026-01-20 7:24 UTC (permalink / raw)
To: Marco Elver
Cc: Peter Zijlstra, Ingo Molnar, Thomas Gleixner, Will Deacon,
Boqun Feng, Waiman Long, Christoph Hellwig, Steven Rostedt,
Bart Van Assche, kasan-dev, llvm, linux-crypto, linux-doc,
linux-security-module, linux-kernel
In-Reply-To: <20260119094029.1344361-1-elver@google.com>
On Mon, Jan 19, 2026 at 10:05:50AM +0100, Marco Elver wrote:
> Note: Scoped guarded initialization remains optional, and normal
> initialization can still be used if no guarded members are being
> initialized. Another alternative is to just disable context analysis to
> initialize guarded members with `context_unsafe(var = init)` or adding
> the `__context_unsafe(init)` function attribute (the latter not being
> recommended for non-trivial functions due to lack of any checking):
I still think this is doing the wrong for the regular non-scoped
cased, and I think I finally understand what is so wrong about it.
The fact that mutex_init (let's use mutexes for the example, applied
to other primitives as well) should not automatically imply guarding
the members for the rest of the function. Because as soon as the
structure that contains the lock is published that is not actually
true, and we did have quite a lot of bugs because of that in the
past.
So I think the first step is to avoid implying the safety of guarded
member access by initialing the lock. We then need to think how to
express they are save, which would probably require explicit annotation
unless we can come up with a scheme that makes these accesses fine
before the mutex_init in a magic way.
^ permalink raw reply
* Re: [PATCH RESEND 08/12] mm: update all remaining mmap_prepare users to use vma_flags_t
From: Zi Yan @ 2026-01-20 2:59 UTC (permalink / raw)
To: Lorenzo Stoakes
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Nico Pache, Ryan Roberts, Dev Jain, Barry Song, Lance Yang,
Jann Horn, Pedro Falcato, David Howells, Paul Moore, James Morris,
Serge E . Hallyn, Yury Norov, Rasmus Villemoes, linux-sgx,
linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <24317e6f6b71e8b439e672893da8d268880f7ada.1768857200.git.lorenzo.stoakes@oracle.com>
On 19 Jan 2026, at 16:19, Lorenzo Stoakes wrote:
> We will be shortly removing the vm_flags_t field from vm_area_desc so we
> need to update all mmap_prepare users to only use the dessc->vma_flags
> field.
>
> This patch achieves that and makes all ancillary changes required to make
> this possible.
>
> This lays the groundwork for future work to eliminate the use of vm_flags_t
> in vm_area_desc altogether and more broadly throughout the kernel.
>
> While we're here, we take the opportunity to replace VM_REMAP_FLAGS with
> VMA_REMAP_FLAGS, the vma_flags_t equivalent.
>
> No functional changes intended.
>
> Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> ---
> drivers/char/mem.c | 6 +++---
> drivers/dax/device.c | 10 +++++-----
> fs/aio.c | 2 +-
> fs/erofs/data.c | 5 +++--
> fs/ext4/file.c | 4 ++--
> fs/ntfs3/file.c | 2 +-
> fs/orangefs/file.c | 4 ++--
> fs/ramfs/file-nommu.c | 2 +-
> fs/resctrl/pseudo_lock.c | 2 +-
> fs/romfs/mmap-nommu.c | 2 +-
> fs/xfs/xfs_file.c | 4 ++--
> fs/zonefs/file.c | 3 ++-
> include/linux/dax.h | 4 ++--
> include/linux/mm.h | 24 +++++++++++++++++++-----
> kernel/relay.c | 2 +-
> mm/memory.c | 17 ++++++++---------
> 16 files changed, 54 insertions(+), 39 deletions(-)
>
You missed one instance in !CONFIG_DAX:
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 162c19fe478c..48d20b790a7d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -111,11 +111,11 @@ static inline void set_dax_nomc(struct dax_device *dax_dev)
static inline void set_dax_synchronous(struct dax_device *dax_dev)
{
}
-static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+static inline bool daxdev_mapping_supported(vma_flags_t flags,
const struct inode *inode,
struct dax_device *dax_dev)
{
- return !(vm_flags & VM_SYNC);
+ return !vma_flags_test(flags, VMA_SYNC_BIT);
}
static inline size_t dax_recovery_write(struct dax_device *dax_dev,
pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
Best Regards,
Yan, Zi
^ permalink raw reply related
* Re: [PATCH v2 1/1] apparmor: avoid per-cpu hold underflow in aa_get_buffer
From: John Johansen @ 2026-01-20 0:44 UTC (permalink / raw)
To: Zhengmian Hu, john, apparmor; +Cc: linux-security-module, linux-kernel
In-Reply-To: <20260120000307.369587-2-huzhengmian@gmail.com>
On 1/19/26 16:03, Zhengmian Hu wrote:
> When aa_get_buffer() pulls from the per-cpu list it unconditionally
> decrements cache->hold. If hold reaches 0 while count is still non-zero,
> the unsigned decrement wraps to UINT_MAX. This keeps hold non-zero for a
> very long time, so aa_put_buffer() never returns buffers to the global
> list, which can starve other CPUs and force repeated kmalloc(aa_g_path_max)
> allocations.
>
> Guard the decrement so hold never underflows.
>
> Signed-off-by: Zhengmian Hu <huzhengmian@gmail.com>
thanks, Acked-by: John Johansen <john.johansen@canonical.com>
I have pulled this into apparmor-next
> ---
> security/apparmor/lsm.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
> index 9b6c2f157..a6c884ba6 100644
> --- a/security/apparmor/lsm.c
> +++ b/security/apparmor/lsm.c
> @@ -1868,7 +1868,8 @@ char *aa_get_buffer(bool in_atomic)
> if (!list_empty(&cache->head)) {
> aa_buf = list_first_entry(&cache->head, union aa_buffer, list);
> list_del(&aa_buf->list);
> - cache->hold--;
> + if (cache->hold)
> + cache->hold--;
> cache->count--;
> put_cpu_ptr(&aa_local_buffers);
> return &aa_buf->buffer[0];
^ permalink raw reply
* [PATCH v2 1/1] apparmor: avoid per-cpu hold underflow in aa_get_buffer
From: Zhengmian Hu @ 2026-01-20 0:03 UTC (permalink / raw)
To: john.johansen, john, apparmor
Cc: linux-security-module, linux-kernel, Zhengmian Hu
In-Reply-To: <20260120000307.369587-1-huzhengmian@gmail.com>
When aa_get_buffer() pulls from the per-cpu list it unconditionally
decrements cache->hold. If hold reaches 0 while count is still non-zero,
the unsigned decrement wraps to UINT_MAX. This keeps hold non-zero for a
very long time, so aa_put_buffer() never returns buffers to the global
list, which can starve other CPUs and force repeated kmalloc(aa_g_path_max)
allocations.
Guard the decrement so hold never underflows.
Signed-off-by: Zhengmian Hu <huzhengmian@gmail.com>
---
security/apparmor/lsm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 9b6c2f157..a6c884ba6 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1868,7 +1868,8 @@ char *aa_get_buffer(bool in_atomic)
if (!list_empty(&cache->head)) {
aa_buf = list_first_entry(&cache->head, union aa_buffer, list);
list_del(&aa_buf->list);
- cache->hold--;
+ if (cache->hold)
+ cache->hold--;
cache->count--;
put_cpu_ptr(&aa_local_buffers);
return &aa_buf->buffer[0];
--
2.52.0
^ permalink raw reply related
* [PATCH v2 0/1] apparmor: avoid per-cpu hold underflow in aa_get_buffer
From: Zhengmian Hu @ 2026-01-20 0:03 UTC (permalink / raw)
To: john.johansen, john, apparmor
Cc: linux-security-module, linux-kernel, Zhengmian Hu
Hi all,
This series fixes a per-cpu hold counter underflow in the AppArmor buffer
cache. Under high-frequency execve workloads with AppArmor enabled, cache->hold
can wrap to UINT_MAX, preventing buffers from returning to the global list and
forcing repeated kmalloc(aa_g_path_max) allocations.
Summary:
On high-frequency execve workloads with AppArmor enabled, the per-CPU buffer
cache can enter a pathological state: aa_get_buffer() decrements hold even
when it is already zero, causing an unsigned underflow. The resulting huge
hold value prevents aa_put_buffer() from refilling the global list, which
starves other CPUs and forces repeated kmalloc(aa_g_path_max) allocations.
Because the AppArmor pool does not shrink, this accumulates into large
kmalloc-8k slab growth over time.
Repro (QEMU TCG, 4 vCPU, 1 GiB RAM, v6.16):
- Unpatched: kmalloc-8k objects grow 12->16 in 120s (run1), 16->20 in 120s (run2)
- Patched: kmalloc-8k stays at 12 for 120s
Notes:
This fix targets the observed underflow mechanism without changing the overall
AppArmor buffer pool design. Happy to provide the reproduction script and logs
on request.
Changes in v2:
- Add patch description to the commit message.
Thanks,
Zhengmian Hu
Zhengmian Hu (1):
apparmor: avoid per-cpu hold underflow in aa_get_buffer
security/apparmor/lsm.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
--
2.52.0
^ permalink raw reply
* Re: [PATCH 1/1] apparmor: avoid per-cpu hold underflow in aa_get_buffer
From: John Johansen @ 2026-01-19 23:56 UTC (permalink / raw)
To: Zhengmian Hu, john, apparmor; +Cc: linux-security-module, linux-kernel
In-Reply-To: <20260119122119.3648154-2-huzhengmian@gmail.com>
On 1/19/26 04:21, Zhengmian Hu wrote:
> Signed-off-by: Zhengmian Hu <huzhengmian@gmail.com>
Small nit, there is no patch description. I can pull that from patch [0/1] if you are okay with that, otherwise can you send in a v2?
I will pull this in once I know your preference
> ---
> security/apparmor/lsm.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
> index 9b6c2f157..a6c884ba6 100644
> --- a/security/apparmor/lsm.c
> +++ b/security/apparmor/lsm.c
> @@ -1868,7 +1868,8 @@ char *aa_get_buffer(bool in_atomic)
> if (!list_empty(&cache->head)) {
> aa_buf = list_first_entry(&cache->head, union aa_buffer, list);
> list_del(&aa_buf->list);
> - cache->hold--;
> + if (cache->hold)
> + cache->hold--;
> cache->count--;
> put_cpu_ptr(&aa_local_buffers);
> return &aa_buf->buffer[0];
^ permalink raw reply
* Re: ipv4: cipso potential BUG()
From: Paul Moore @ 2026-01-19 23:31 UTC (permalink / raw)
To: Will Rosenberg
Cc: David S. Miller, David Ahern, Eric Dumazet, Jakub Kicinski,
Paolo Abeni, Simon Horman, Huw Davies, netdev,
linux-security-module, linux-kernel
In-Reply-To: <aW6YMA11KFzSkgfw@gmail.com>
On Mon, Jan 19, 2026 at 3:46 PM Will Rosenberg <whrosenb@asu.edu> wrote:
>
> Previously, it was discussed that skb_cow() has a bug due to implicit
> integer casting that can lead to a BUG when headroom < -NET_SKB_PAD. We
> concluded that it was not worthwhile to fix the root cause and to
> instead fix the symptom found in calipso. The thread for this issue can
> be found here:
>
> https://lore.kernel.org/netdev/CAHC9VhQmR8A2vz0W-VrrhYNQ2wgCYxHbAmdgmM2yTL-uh4qiOg@mail.gmail.com/
>
> I recently reviewed the use cases of skb_cow() throughout the kernel and
> found that cipso_v4_skbuff_setattr() comes very close to triggering the
> same BUG. However, I concluded this was not triggerable. Even though
> len_delta can become negative, leading to a negative headroom passed to
> skb_cow(), we do not satisfy the condition headroom < -NET_SKB_PAD.
>
> Nonetheless, I believe cipso is using skb_cow() dangerously, but since
> the issue is not triggerable, would it still make sense to patch it?
> I figured I would throw out a quick email. Please let me know and I can
> make a similar patch for cipso if necessary.
Sometimes the easiest way to get an answer to questions like this is
to send a patch; since I would expect this particular patch to be of
limited scope and very small, I think this advice holds true here.
--
paul-moore.com
^ permalink raw reply
* Re: [PATCH RESEND 00/12] mm: add bitmap VMA flag helpers and convert all mmap_prepare to use them
From: Jason Gunthorpe @ 2026-01-19 23:14 UTC (permalink / raw)
To: Lorenzo Stoakes
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
On Mon, Jan 19, 2026 at 09:19:02PM +0000, Lorenzo Stoakes wrote:
> We introduced the bitmap VMA type vma_flags_t in the aptly named commit
> 9ea35a25d51b ("mm: introduce VMA flags bitmap type") in order to permit
> future growth in VMA flags and to prevent the asinine requirement that VMA
> flags be available to 64-bit kernels only if they happened to use a bit
> number about 32-bits.
>
> This is a long-term project as there are very many users of VMA flags
> within the kernel that need to be updated in order to utilise this new
> type.
>
> In order to further this aim, this series adds a number of helper functions
> to enable ordinary interactions with VMA flags - that is testing, setting
> and clearing them.
>
> In order to make working with VMA bit numbers less cumbersome this series
> introduces the mk_vma_flags() helper macro which generates a vma_flags_t
> from a variadic parameter list, e.g.:
>
> vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT,
> VMA_EXEC_BIT);
I didn't try to check every conversion, but the whole approach looks
nice to me and I think this design is ergonomic!
Jason
^ permalink raw reply
* Re: [PATCH v4 5/6] keys/trusted_keys: establish PKWM as a trusted source
From: Jarkko Sakkinen @ 2026-01-19 23:14 UTC (permalink / raw)
To: Srish Srinivasan
Cc: linux-integrity, keyrings, linuxppc-dev, maddy, mpe, npiggin,
christophe.leroy, James.Bottomley, zohar, nayna, rnsastry,
linux-kernel, linux-security-module
In-Reply-To: <20260115100504.488665-6-ssrish@linux.ibm.com>
On Thu, Jan 15, 2026 at 03:35:03PM +0530, Srish Srinivasan wrote:
> The wrapping key does not exist by default and is generated by the
> hypervisor as a part of PKWM initialization. This key is then persisted by
> the hypervisor and is used to wrap trusted keys. These are variable length
> symmetric keys, which in the case of PowerVM Key Wrapping Module (PKWM) are
> generated using the kernel RNG. PKWM can be used as a trust source through
> the following example keyctl commands:
>
> keyctl add trusted my_trusted_key "new 32" @u
>
> Use the wrap_flags command option to set the secure boot requirement for
> the wrapping request through the following keyctl commands
>
> case1: no secure boot requirement. (default)
> keyctl usage: keyctl add trusted my_trusted_key "new 32" @u
> OR
> keyctl add trusted my_trusted_key "new 32 wrap_flags=0x00" @u
>
> case2: secure boot required to in either audit or enforce mode. set bit 0
> keyctl usage: keyctl add trusted my_trusted_key "new 32 wrap_flags=0x01" @u
>
> case3: secure boot required to be in enforce mode. set bit 1
> keyctl usage: keyctl add trusted my_trusted_key "new 32 wrap_flags=0x02" @u
>
> NOTE:
> -> Setting the secure boot requirement is NOT a must.
> -> Only either of the secure boot requirement options should be set. Not
> both.
> -> All the other bits are required to be not set.
> -> Set the kernel parameter trusted.source=pkwm to choose PKWM as the
> backend for trusted keys implementation.
> -> CONFIG_PSERIES_PLPKS must be enabled to build PKWM.
>
> Add PKWM, which is a combination of IBM PowerVM and Power LPAR Platform
> KeyStore, as a new trust source for trusted keys.
>
> Signed-off-by: Srish Srinivasan <ssrish@linux.ibm.com>
> Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
> ---
> This version introduces a private pointer for backend specific fields and
> related changes specific to the PKWM backend, but defers migrating the TPM
> fields to this new framework. That will be done independently of this
> patch series.
> MAINTAINERS | 9 +
> include/keys/trusted-type.h | 7 +-
> include/keys/trusted_pkwm.h | 33 ++++
> security/keys/trusted-keys/Kconfig | 8 +
> security/keys/trusted-keys/Makefile | 2 +
> security/keys/trusted-keys/trusted_core.c | 6 +-
> security/keys/trusted-keys/trusted_pkwm.c | 190 ++++++++++++++++++++++
> 7 files changed, 253 insertions(+), 2 deletions(-)
> create mode 100644 include/keys/trusted_pkwm.h
> create mode 100644 security/keys/trusted-keys/trusted_pkwm.c
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index cf755238c429..c98f1811f836 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -14008,6 +14008,15 @@ S: Supported
> F: include/keys/trusted_dcp.h
> F: security/keys/trusted-keys/trusted_dcp.c
>
> +KEYS-TRUSTED-PLPKS
> +M: Srish Srinivasan <ssrish@linux.ibm.com>
> +M: Nayna Jain <nayna@linux.ibm.com>
> +L: linux-integrity@vger.kernel.org
> +L: keyrings@vger.kernel.org
> +S: Supported
> +F: include/keys/trusted_pkwm.h
> +F: security/keys/trusted-keys/trusted_pkwm.c
> +
> KEYS-TRUSTED-TEE
> M: Sumit Garg <sumit.garg@kernel.org>
> L: linux-integrity@vger.kernel.org
> diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h
> index 4eb64548a74f..03527162613f 100644
> --- a/include/keys/trusted-type.h
> +++ b/include/keys/trusted-type.h
> @@ -19,7 +19,11 @@
>
> #define MIN_KEY_SIZE 32
> #define MAX_KEY_SIZE 128
> -#define MAX_BLOB_SIZE 512
> +#if IS_ENABLED(CONFIG_TRUSTED_KEYS_PKWM)
> +#define MAX_BLOB_SIZE 1152
> +#else
> +#define MAX_BLOB_SIZE 512
> +#endif
> #define MAX_PCRINFO_SIZE 64
> #define MAX_DIGEST_SIZE 64
>
> @@ -46,6 +50,7 @@ struct trusted_key_options {
> uint32_t policydigest_len;
> unsigned char policydigest[MAX_DIGEST_SIZE];
> uint32_t policyhandle;
> + void *private;
> };
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
>
> struct trusted_key_ops {
> diff --git a/include/keys/trusted_pkwm.h b/include/keys/trusted_pkwm.h
> new file mode 100644
> index 000000000000..4035b9776394
> --- /dev/null
> +++ b/include/keys/trusted_pkwm.h
> @@ -0,0 +1,33 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef __PKWM_TRUSTED_KEY_H
> +#define __PKWM_TRUSTED_KEY_H
> +
> +#include <keys/trusted-type.h>
> +#include <linux/bitops.h>
> +#include <linux/printk.h>
> +
> +extern struct trusted_key_ops pkwm_trusted_key_ops;
> +
> +struct trusted_pkwm_options {
> + u16 wrap_flags;
> +};
> +
> +static inline void dump_options(struct trusted_key_options *o)
> +{
> + const struct trusted_pkwm_options *pkwm;
> + bool sb_audit_or_enforce_bit;
> + bool sb_enforce_bit;
> +
> + pkwm = o->private;
> + sb_audit_or_enforce_bit = pkwm->wrap_flags & BIT(0);
> + sb_enforce_bit = pkwm->wrap_flags & BIT(1);
> +
> + if (sb_audit_or_enforce_bit)
> + pr_debug("secure boot mode required: audit or enforce");
> + else if (sb_enforce_bit)
> + pr_debug("secure boot mode required: enforce");
> + else
> + pr_debug("secure boot mode required: disabled");
> +}
> +
> +#endif
> diff --git a/security/keys/trusted-keys/Kconfig b/security/keys/trusted-keys/Kconfig
> index 204a68c1429d..9e00482d886a 100644
> --- a/security/keys/trusted-keys/Kconfig
> +++ b/security/keys/trusted-keys/Kconfig
> @@ -46,6 +46,14 @@ config TRUSTED_KEYS_DCP
> help
> Enable use of NXP's DCP (Data Co-Processor) as trusted key backend.
>
> +config TRUSTED_KEYS_PKWM
> + bool "PKWM-based trusted keys"
> + depends on PSERIES_PLPKS >= TRUSTED_KEYS
> + default y
> + select HAVE_TRUSTED_KEYS
> + help
> + Enable use of IBM PowerVM Key Wrapping Module (PKWM) as a trusted key backend.
> +
> if !HAVE_TRUSTED_KEYS
> comment "No trust source selected!"
> endif
> diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile
> index f0f3b27f688b..5fc053a21dad 100644
> --- a/security/keys/trusted-keys/Makefile
> +++ b/security/keys/trusted-keys/Makefile
> @@ -16,3 +16,5 @@ trusted-$(CONFIG_TRUSTED_KEYS_TEE) += trusted_tee.o
> trusted-$(CONFIG_TRUSTED_KEYS_CAAM) += trusted_caam.o
>
> trusted-$(CONFIG_TRUSTED_KEYS_DCP) += trusted_dcp.o
> +
> +trusted-$(CONFIG_TRUSTED_KEYS_PKWM) += trusted_pkwm.o
> diff --git a/security/keys/trusted-keys/trusted_core.c b/security/keys/trusted-keys/trusted_core.c
> index b1680ee53f86..2d328de170e8 100644
> --- a/security/keys/trusted-keys/trusted_core.c
> +++ b/security/keys/trusted-keys/trusted_core.c
> @@ -12,6 +12,7 @@
> #include <keys/trusted_caam.h>
> #include <keys/trusted_dcp.h>
> #include <keys/trusted_tpm.h>
> +#include <keys/trusted_pkwm.h>
> #include <linux/capability.h>
> #include <linux/err.h>
> #include <linux/init.h>
> @@ -31,7 +32,7 @@ MODULE_PARM_DESC(rng, "Select trusted key RNG");
>
> static char *trusted_key_source;
> module_param_named(source, trusted_key_source, charp, 0);
> -MODULE_PARM_DESC(source, "Select trusted keys source (tpm, tee, caam or dcp)");
> +MODULE_PARM_DESC(source, "Select trusted keys source (tpm, tee, caam, dcp or pkwm)");
>
> static const struct trusted_key_source trusted_key_sources[] = {
> #if defined(CONFIG_TRUSTED_KEYS_TPM)
> @@ -46,6 +47,9 @@ static const struct trusted_key_source trusted_key_sources[] = {
> #if defined(CONFIG_TRUSTED_KEYS_DCP)
> { "dcp", &dcp_trusted_key_ops },
> #endif
> +#if defined(CONFIG_TRUSTED_KEYS_PKWM)
> + { "pkwm", &pkwm_trusted_key_ops },
> +#endif
> };
>
> DEFINE_STATIC_CALL_NULL(trusted_key_seal, *trusted_key_sources[0].ops->seal);
> diff --git a/security/keys/trusted-keys/trusted_pkwm.c b/security/keys/trusted-keys/trusted_pkwm.c
> new file mode 100644
> index 000000000000..4f391b77a907
> --- /dev/null
> +++ b/security/keys/trusted-keys/trusted_pkwm.c
> @@ -0,0 +1,190 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +/*
> + * Copyright (C) 2025 IBM Corporation, Srish Srinivasan <ssrish@linux.ibm.com>
> + */
> +
> +#include <keys/trusted_pkwm.h>
> +#include <keys/trusted-type.h>
> +#include <linux/build_bug.h>
> +#include <linux/key-type.h>
> +#include <linux/parser.h>
> +#include <asm/plpks.h>
> +
> +enum {
> + Opt_err,
> + Opt_wrap_flags,
> +};
> +
> +static const match_table_t key_tokens = {
> + {Opt_wrap_flags, "wrap_flags=%s"},
> + {Opt_err, NULL}
> +};
> +
> +static int getoptions(char *datablob, struct trusted_key_options *opt)
> +{
> + substring_t args[MAX_OPT_ARGS];
> + char *p = datablob;
> + int token;
> + int res;
> + u16 wrap_flags;
> + unsigned long token_mask = 0;
> + struct trusted_pkwm_options *pkwm;
> +
> + if (!datablob)
> + return 0;
> +
> + pkwm = opt->private;
> +
> + while ((p = strsep(&datablob, " \t"))) {
> + if (*p == '\0' || *p == ' ' || *p == '\t')
> + continue;
> +
> + token = match_token(p, key_tokens, args);
> + if (test_and_set_bit(token, &token_mask))
> + return -EINVAL;
> +
> + switch (token) {
> + case Opt_wrap_flags:
> + res = kstrtou16(args[0].from, 16, &wrap_flags);
> + if (res < 0 || wrap_flags > 2)
> + return -EINVAL;
> + pkwm->wrap_flags = wrap_flags;
> + break;
> + default:
> + return -EINVAL;
> + }
> + }
> + return 0;
> +}
> +
> +static struct trusted_key_options *trusted_options_alloc(void)
> +{
> + struct trusted_key_options *options;
> + struct trusted_pkwm_options *pkwm;
> +
> + options = kzalloc(sizeof(*options), GFP_KERNEL);
> +
> + if (options) {
> + pkwm = kzalloc(sizeof(*pkwm), GFP_KERNEL);
> +
> + if (!pkwm) {
> + kfree_sensitive(options);
> + options = NULL;
> + } else {
> + options->private = pkwm;
> + }
> + }
> +
> + return options;
> +}
> +
> +static int trusted_pkwm_seal(struct trusted_key_payload *p, char *datablob)
> +{
> + struct trusted_key_options *options = NULL;
> + struct trusted_pkwm_options *pkwm = NULL;
> + u8 *input_buf, *output_buf;
> + u32 output_len, input_len;
> + int rc;
> +
> + options = trusted_options_alloc();
> +
> + if (!options)
> + return -ENOMEM;
> +
> + rc = getoptions(datablob, options);
> + if (rc < 0)
> + goto out;
> + dump_options(options);
> +
> + input_len = p->key_len;
> + input_buf = kmalloc(ALIGN(input_len, 4096), GFP_KERNEL);
> + if (!input_buf) {
> + pr_err("Input buffer allocation failed. Returning -ENOMEM.");
> + rc = -ENOMEM;
> + goto out;
> + }
> +
> + memcpy(input_buf, p->key, p->key_len);
> +
> + pkwm = options->private;
> +
> + rc = plpks_wrap_object(&input_buf, input_len, pkwm->wrap_flags,
> + &output_buf, &output_len);
> + if (!rc) {
> + memcpy(p->blob, output_buf, output_len);
> + p->blob_len = output_len;
> + dump_payload(p);
> + } else {
> + pr_err("Wrapping of payload key failed: %d\n", rc);
> + }
> +
> + kfree(input_buf);
> + kfree(output_buf);
> +
> +out:
> + kfree_sensitive(options->private);
> + kfree_sensitive(options);
> + return rc;
> +}
> +
> +static int trusted_pkwm_unseal(struct trusted_key_payload *p, char *datablob)
> +{
> + u8 *input_buf, *output_buf;
> + u32 input_len, output_len;
> + int rc;
> +
> + input_len = p->blob_len;
> + input_buf = kmalloc(ALIGN(input_len, 4096), GFP_KERNEL);
> + if (!input_buf) {
> + pr_err("Input buffer allocation failed. Returning -ENOMEM.");
> + return -ENOMEM;
> + }
> +
> + memcpy(input_buf, p->blob, p->blob_len);
> +
> + rc = plpks_unwrap_object(&input_buf, input_len, &output_buf,
> + &output_len);
> + if (!rc) {
> + memcpy(p->key, output_buf, output_len);
> + p->key_len = output_len;
> + dump_payload(p);
> + } else {
> + pr_err("Unwrapping of payload failed: %d\n", rc);
> + }
> +
> + kfree(input_buf);
> + kfree(output_buf);
> +
> + return rc;
> +}
> +
> +static int trusted_pkwm_init(void)
> +{
> + int ret;
> +
> + if (!plpks_wrapping_is_supported()) {
> + pr_err("H_PKS_WRAP_OBJECT interface not supported\n");
> + return -ENODEV;
> + }
> +
> + ret = plpks_gen_wrapping_key();
> + if (ret) {
> + pr_err("Failed to generate default wrapping key\n");
> + return -EINVAL;
> + }
> +
> + return register_key_type(&key_type_trusted);
> +}
> +
> +static void trusted_pkwm_exit(void)
> +{
> + unregister_key_type(&key_type_trusted);
> +}
> +
> +struct trusted_key_ops pkwm_trusted_key_ops = {
> + .migratable = 0, /* non-migratable */
> + .init = trusted_pkwm_init,
> + .seal = trusted_pkwm_seal,
> + .unseal = trusted_pkwm_unseal,
> + .exit = trusted_pkwm_exit,
> +};
> --
> 2.47.3
>
BR, Jarkko
^ permalink raw reply
* Re: [PATCH RESEND 09/12] mm: make vm_area_desc utilise vma_flags_t only
From: Jason Gunthorpe @ 2026-01-19 23:14 UTC (permalink / raw)
To: Lorenzo Stoakes
Cc: Andrew Morton, Jarkko Sakkinen, Dave Hansen, Thomas Gleixner,
Ingo Molnar, Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module
In-Reply-To: <baac396f309264c6b3ff30465dba0fbd63f8479c.1768857200.git.lorenzo.stoakes@oracle.com>
On Mon, Jan 19, 2026 at 09:19:11PM +0000, Lorenzo Stoakes wrote:
> +static inline bool is_shared_maywrite(vma_flags_t flags)
> +{
I'm not sure it is ideal to pass this array by value? Seems like it
might invite some negative optimizations since now the compiler has to
optimze away a copy too.
Jason
^ permalink raw reply
* Re: [PATCH RESEND 00/12] mm: add bitmap VMA flag helpers and convert all mmap_prepare to use them
From: Andrew Morton @ 2026-01-19 22:31 UTC (permalink / raw)
To: Lorenzo Stoakes
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
On Mon, 19 Jan 2026 21:19:02 +0000 Lorenzo Stoakes <lorenzo.stoakes@oracle.com> wrote:
> We introduced the bitmap VMA type vma_flags_t in the aptly named commit
> 9ea35a25d51b ("mm: introduce VMA flags bitmap type") in order to permit
> future growth in VMA flags and to prevent the asinine requirement that VMA
> flags be available to 64-bit kernels only if they happened to use a bit
> number about 32-bits.
>
> This is a long-term project as there are very many users of VMA flags
> within the kernel that need to be updated in order to utilise this new
> type.
Thanks, I added this to mm.git's mm-new branch for some public exposure.
I suppressed the usual email storm.
^ permalink raw reply
* Re: [PATCH v7 0/9] Implement LANDLOCK_ADD_RULE_QUIET
From: Tingmao Wang @ 2026-01-19 22:05 UTC (permalink / raw)
To: Justin Suess; +Cc: Mickaël Salaün, linux-security-module
In-Reply-To: <b7a2444d-c3af-428f-904e-ec5a6452e513@gmail.com>
On 1/19/26 14:26, Justin Suess wrote:
> [...]
> Hey Tingmao,
>
> Thank you for your work on this patch-- I don’t have any further nits,
> this looks very clean.
>
> Do you plan to rebase/resend this series on the current mic-next branch
> at some point? It would be helpful to be able to test it alongside some
> of the other Landlock series that are in flight.>
> Feedback on the latest version of the series has been fairly quiet so far,
> and having it rebased would make cross-testing easier. I’d also rebase the
> LANDLOCK_ADD_RULE_NO_INHERIT series on top for further consideration.
Hi Justin,
Thanks for the reminder :)
I don't have any changes waiting for v8, and all the patches except one
already applies cleanly, and the one that conflicted was due to a fixed
typo, in patch 6, which git can also sort out automatically with git am
--3way:
$ b4 am '<cover.1766330134.git.m@maowtm.org>'
(ignore to suggestion to checkout the base commit - this can be
applied onto mic/next cleanly)
$ git am --3way ./v7_20251221_m_implement_landlock_add_rule_quiet.mbx
I should probably still resend at some point anyway just to make it easier
for everybody - but given this is lower priority (rightfully) than the
socket stuff, and review is not blocked anyway, I guess I will wait a bit
before spamming :D
Kind regards,
Tingmao
^ permalink raw reply
* [PATCH RESEND 10/12] tools/testing/vma: separate VMA userland tests into separate files
From: Lorenzo Stoakes @ 2026-01-19 21:19 UTC (permalink / raw)
To: Andrew Morton
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
So far the userland VMA tests have been established as a rough expression
of what's been possible.
qAdapt it into a more usable form by separating out tests and shared helper
functions.
Since we test functions that are declared statically in mm/vma.c, we make
use of the trick of #include'ing kernel C files directly.
In order for the tests to continue to function, we must therefore also
this way into the tests/ directory.
We try to keep as much shared logic actually modularised into a separate
compilation unit in shared.c, however the merge_existing() and attach_vma()
helpers rely on statically declared mm/vma.c functions so these must be
declared in main.c.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
tools/testing/vma/Makefile | 4 +-
tools/testing/vma/main.c | 55 ++++
tools/testing/vma/shared.c | 131 ++++++++
tools/testing/vma/shared.h | 114 +++++++
tools/testing/vma/{vma.c => tests/merge.c} | 332 +--------------------
tools/testing/vma/tests/mmap.c | 57 ++++
tools/testing/vma/tests/vma.c | 39 +++
tools/testing/vma/vma_internal.h | 9 -
8 files changed, 406 insertions(+), 335 deletions(-)
create mode 100644 tools/testing/vma/main.c
create mode 100644 tools/testing/vma/shared.c
create mode 100644 tools/testing/vma/shared.h
rename tools/testing/vma/{vma.c => tests/merge.c} (82%)
create mode 100644 tools/testing/vma/tests/mmap.c
create mode 100644 tools/testing/vma/tests/vma.c
diff --git a/tools/testing/vma/Makefile b/tools/testing/vma/Makefile
index 66f3831a668f..94133d9d3955 100644
--- a/tools/testing/vma/Makefile
+++ b/tools/testing/vma/Makefile
@@ -6,10 +6,10 @@ default: vma
include ../shared/shared.mk
-OFILES = $(SHARED_OFILES) vma.o maple-shim.o
+OFILES = $(SHARED_OFILES) main.o shared.o maple-shim.o
TARGETS = vma
-vma.o: vma.c vma_internal.h ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h
+main.o: main.c shared.c shared.h vma_internal.h tests/merge.c tests/mmap.c tests/vma.c ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h
vma: $(OFILES)
$(CC) $(CFLAGS) -o $@ $(OFILES) $(LDLIBS)
diff --git a/tools/testing/vma/main.c b/tools/testing/vma/main.c
new file mode 100644
index 000000000000..49b09e97a51f
--- /dev/null
+++ b/tools/testing/vma/main.c
@@ -0,0 +1,55 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "shared.h"
+/*
+ * Directly import the VMA implementation here. Our vma_internal.h wrapper
+ * provides userland-equivalent functionality for everything vma.c uses.
+ */
+#include "../../../mm/vma_init.c"
+#include "../../../mm/vma_exec.c"
+#include "../../../mm/vma.c"
+
+/* Tests are included directly so they can test static functions in mm/vma.c. */
+#include "tests/merge.c"
+#include "tests/mmap.c"
+#include "tests/vma.c"
+
+/* Helper functions which utilise static kernel functions. */
+
+struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg)
+{
+ struct vm_area_struct *vma;
+
+ vma = vma_merge_existing_range(vmg);
+ if (vma)
+ vma_assert_attached(vma);
+ return vma;
+}
+
+int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ int res;
+
+ res = vma_link(mm, vma);
+ if (!res)
+ vma_assert_attached(vma);
+ return res;
+}
+
+/* Main test running which invokes tests/ *.c runners. */
+int main(void)
+{
+ int num_tests = 0, num_fail = 0;
+
+ maple_tree_init();
+ vma_state_init();
+
+ run_merge_tests(&num_tests, &num_fail);
+ run_mmap_tests(&num_tests, &num_fail);
+ run_vma_tests(&num_tests, &num_fail);
+
+ printf("%d tests run, %d passed, %d failed.\n",
+ num_tests, num_tests - num_fail, num_fail);
+
+ return num_fail == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
+}
diff --git a/tools/testing/vma/shared.c b/tools/testing/vma/shared.c
new file mode 100644
index 000000000000..bda578cc3304
--- /dev/null
+++ b/tools/testing/vma/shared.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "shared.h"
+
+
+bool fail_prealloc;
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+const struct vm_operations_struct vma_dummy_vm_ops;
+struct anon_vma dummy_anon_vma;
+struct task_struct __current;
+
+struct vm_area_struct *alloc_vma(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff, vm_flags_t vm_flags)
+{
+ struct vm_area_struct *vma = vm_area_alloc(mm);
+
+ if (vma == NULL)
+ return NULL;
+
+ vma->vm_start = start;
+ vma->vm_end = end;
+ vma->vm_pgoff = pgoff;
+ vm_flags_reset(vma, vm_flags);
+ vma_assert_detached(vma);
+
+ return vma;
+}
+
+void detach_free_vma(struct vm_area_struct *vma)
+{
+ vma_mark_detached(vma);
+ vm_area_free(vma);
+}
+
+struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff, vm_flags_t vm_flags)
+{
+ struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vm_flags);
+
+ if (vma == NULL)
+ return NULL;
+
+ if (attach_vma(mm, vma)) {
+ detach_free_vma(vma);
+ return NULL;
+ }
+
+ /*
+ * Reset this counter which we use to track whether writes have
+ * begun. Linking to the tree will have caused this to be incremented,
+ * which means we will get a false positive otherwise.
+ */
+ vma->vm_lock_seq = UINT_MAX;
+
+ return vma;
+}
+
+void reset_dummy_anon_vma(void)
+{
+ dummy_anon_vma.was_cloned = false;
+ dummy_anon_vma.was_unlinked = false;
+}
+
+int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi)
+{
+ struct vm_area_struct *vma;
+ int count = 0;
+
+ fail_prealloc = false;
+ reset_dummy_anon_vma();
+
+ vma_iter_set(vmi, 0);
+ for_each_vma(*vmi, vma) {
+ detach_free_vma(vma);
+ count++;
+ }
+
+ mtree_destroy(&mm->mm_mt);
+ mm->map_count = 0;
+ return count;
+}
+
+bool vma_write_started(struct vm_area_struct *vma)
+{
+ int seq = vma->vm_lock_seq;
+
+ /* We reset after each check. */
+ vma->vm_lock_seq = UINT_MAX;
+
+ /* The vma_start_write() stub simply increments this value. */
+ return seq > -1;
+}
+
+void __vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc, struct anon_vma *anon_vma)
+{
+ vma->anon_vma = anon_vma;
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
+ list_add(&avc->same_vma, &vma->anon_vma_chain);
+ avc->anon_vma = vma->anon_vma;
+}
+
+void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc)
+{
+ __vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma);
+}
+
+struct task_struct *get_current(void)
+{
+ return &__current;
+}
+
+unsigned long rlimit(unsigned int limit)
+{
+ return (unsigned long)-1;
+}
+
+void vma_set_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff)
+{
+ vma->vm_start = start;
+ vma->vm_end = end;
+ vma->vm_pgoff = pgoff;
+}
diff --git a/tools/testing/vma/shared.h b/tools/testing/vma/shared.h
new file mode 100644
index 000000000000..6c64211cfa22
--- /dev/null
+++ b/tools/testing/vma/shared.h
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#pragma once
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "generated/bit-length.h"
+#include "maple-shared.h"
+#include "vma_internal.h"
+#include "../../../mm/vma.h"
+
+/* Simple test runner. Assumes local num_[fail, tests] counters. */
+#define TEST(name) \
+ do { \
+ (*num_tests)++; \
+ if (!test_##name()) { \
+ (*num_fail)++; \
+ fprintf(stderr, "Test " #name " FAILED\n"); \
+ } \
+ } while (0)
+
+#define ASSERT_TRUE(_expr) \
+ do { \
+ if (!(_expr)) { \
+ fprintf(stderr, \
+ "Assert FAILED at %s:%d:%s(): %s is FALSE.\n", \
+ __FILE__, __LINE__, __FUNCTION__, #_expr); \
+ return false; \
+ } \
+ } while (0)
+
+#define ASSERT_FALSE(_expr) ASSERT_TRUE(!(_expr))
+#define ASSERT_EQ(_val1, _val2) ASSERT_TRUE((_val1) == (_val2))
+#define ASSERT_NE(_val1, _val2) ASSERT_TRUE((_val1) != (_val2))
+
+#define IS_SET(_val, _flags) ((_val & _flags) == _flags)
+
+extern bool fail_prealloc;
+
+/* Override vma_iter_prealloc() so we can choose to fail it. */
+#define vma_iter_prealloc(vmi, vma) \
+ (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL))
+
+#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536
+
+extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
+extern unsigned long stack_guard_gap;
+
+extern const struct vm_operations_struct vma_dummy_vm_ops;
+extern struct anon_vma dummy_anon_vma;
+extern struct task_struct __current;
+
+/*
+ * Helper function which provides a wrapper around a merge existing VMA
+ * operation.
+ *
+ * Declared in main.c as uses static VMA function.
+ */
+struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg);
+
+/*
+ * Helper function to allocate a VMA and link it to the tree.
+ *
+ * Declared in main.c as uses static VMA function.
+ */
+int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma);
+
+/* Helper function providing a dummy vm_ops->close() method.*/
+static inline void dummy_close(struct vm_area_struct *)
+{
+}
+
+/* Helper function to simply allocate a VMA. */
+struct vm_area_struct *alloc_vma(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff, vm_flags_t vm_flags);
+
+/* Helper function to detach and free a VMA. */
+void detach_free_vma(struct vm_area_struct *vma);
+
+/* Helper function to allocate a VMA and link it to the tree. */
+struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff, vm_flags_t vm_flags);
+
+/*
+ * Helper function to reset the dummy anon_vma to indicate it has not been
+ * duplicated.
+ */
+void reset_dummy_anon_vma(void);
+
+/*
+ * Helper function to remove all VMAs and destroy the maple tree associated with
+ * a virtual address space. Returns a count of VMAs in the tree.
+ */
+int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi);
+
+/* Helper function to determine if VMA has had vma_start_write() performed. */
+bool vma_write_started(struct vm_area_struct *vma);
+
+void __vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc, struct anon_vma *anon_vma);
+
+/* Provide a simple dummy VMA/anon_vma dummy setup for testing. */
+void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+ struct anon_vma_chain *avc);
+
+/* Helper function to specify a VMA's range. */
+void vma_set_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end,
+ pgoff_t pgoff);
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/tests/merge.c
similarity index 82%
rename from tools/testing/vma/vma.c
rename to tools/testing/vma/tests/merge.c
index 93d21bc7e112..3708dc6945b0 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/tests/merge.c
@@ -1,132 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-or-later
-#include <stdbool.h>
-#include <stdio.h>
-#include <stdlib.h>
-
-#include "generated/bit-length.h"
-
-#include "maple-shared.h"
-#include "vma_internal.h"
-
-/* Include so header guard set. */
-#include "../../../mm/vma.h"
-
-static bool fail_prealloc;
-
-/* Then override vma_iter_prealloc() so we can choose to fail it. */
-#define vma_iter_prealloc(vmi, vma) \
- (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL))
-
-#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536
-
-unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
-unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
-
-/*
- * Directly import the VMA implementation here. Our vma_internal.h wrapper
- * provides userland-equivalent functionality for everything vma.c uses.
- */
-#include "../../../mm/vma_init.c"
-#include "../../../mm/vma_exec.c"
-#include "../../../mm/vma.c"
-
-const struct vm_operations_struct vma_dummy_vm_ops;
-static struct anon_vma dummy_anon_vma;
-
-#define ASSERT_TRUE(_expr) \
- do { \
- if (!(_expr)) { \
- fprintf(stderr, \
- "Assert FAILED at %s:%d:%s(): %s is FALSE.\n", \
- __FILE__, __LINE__, __FUNCTION__, #_expr); \
- return false; \
- } \
- } while (0)
-#define ASSERT_FALSE(_expr) ASSERT_TRUE(!(_expr))
-#define ASSERT_EQ(_val1, _val2) ASSERT_TRUE((_val1) == (_val2))
-#define ASSERT_NE(_val1, _val2) ASSERT_TRUE((_val1) != (_val2))
-
-#define IS_SET(_val, _flags) ((_val & _flags) == _flags)
-
-static struct task_struct __current;
-
-struct task_struct *get_current(void)
-{
- return &__current;
-}
-
-unsigned long rlimit(unsigned int limit)
-{
- return (unsigned long)-1;
-}
-
-/* Helper function to simply allocate a VMA. */
-static struct vm_area_struct *alloc_vma(struct mm_struct *mm,
- unsigned long start,
- unsigned long end,
- pgoff_t pgoff,
- vm_flags_t vm_flags)
-{
- struct vm_area_struct *vma = vm_area_alloc(mm);
-
- if (vma == NULL)
- return NULL;
-
- vma->vm_start = start;
- vma->vm_end = end;
- vma->vm_pgoff = pgoff;
- vm_flags_reset(vma, vm_flags);
- vma_assert_detached(vma);
-
- return vma;
-}
-
-/* Helper function to allocate a VMA and link it to the tree. */
-static int attach_vma(struct mm_struct *mm, struct vm_area_struct *vma)
-{
- int res;
-
- res = vma_link(mm, vma);
- if (!res)
- vma_assert_attached(vma);
- return res;
-}
-
-static void detach_free_vma(struct vm_area_struct *vma)
-{
- vma_mark_detached(vma);
- vm_area_free(vma);
-}
-
-/* Helper function to allocate a VMA and link it to the tree. */
-static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
- unsigned long start,
- unsigned long end,
- pgoff_t pgoff,
- vm_flags_t vm_flags)
-{
- struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vm_flags);
-
- if (vma == NULL)
- return NULL;
-
- if (attach_vma(mm, vma)) {
- detach_free_vma(vma);
- return NULL;
- }
-
- /*
- * Reset this counter which we use to track whether writes have
- * begun. Linking to the tree will have caused this to be incremented,
- * which means we will get a false positive otherwise.
- */
- vma->vm_lock_seq = UINT_MAX;
-
- return vma;
-}
-
/* Helper function which provides a wrapper around a merge new VMA operation. */
static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg)
{
@@ -146,20 +19,6 @@ static struct vm_area_struct *merge_new(struct vma_merge_struct *vmg)
return vma;
}
-/*
- * Helper function which provides a wrapper around a merge existing VMA
- * operation.
- */
-static struct vm_area_struct *merge_existing(struct vma_merge_struct *vmg)
-{
- struct vm_area_struct *vma;
-
- vma = vma_merge_existing_range(vmg);
- if (vma)
- vma_assert_attached(vma);
- return vma;
-}
-
/*
* Helper function which provides a wrapper around the expansion of an existing
* VMA.
@@ -173,8 +32,8 @@ static int expand_existing(struct vma_merge_struct *vmg)
* Helper function to reset merge state the associated VMA iterator to a
* specified new range.
*/
-static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
- unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags)
+void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
+ unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags)
{
vma_iter_set(vmg->vmi, start);
@@ -197,8 +56,8 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
/* Helper function to set both the VMG range and its anon_vma. */
static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long start,
- unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags,
- struct anon_vma *anon_vma)
+ unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags,
+ struct anon_vma *anon_vma)
{
vmg_set_range(vmg, start, end, pgoff, vm_flags);
vmg->anon_vma = anon_vma;
@@ -211,10 +70,9 @@ static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long s
* VMA, link it to the maple tree and return it.
*/
static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm,
- struct vma_merge_struct *vmg,
- unsigned long start, unsigned long end,
- pgoff_t pgoff, vm_flags_t vm_flags,
- bool *was_merged)
+ struct vma_merge_struct *vmg, unsigned long start,
+ unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags,
+ bool *was_merged)
{
struct vm_area_struct *merged;
@@ -234,72 +92,6 @@ static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm,
return alloc_and_link_vma(mm, start, end, pgoff, vm_flags);
}
-/*
- * Helper function to reset the dummy anon_vma to indicate it has not been
- * duplicated.
- */
-static void reset_dummy_anon_vma(void)
-{
- dummy_anon_vma.was_cloned = false;
- dummy_anon_vma.was_unlinked = false;
-}
-
-/*
- * Helper function to remove all VMAs and destroy the maple tree associated with
- * a virtual address space. Returns a count of VMAs in the tree.
- */
-static int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi)
-{
- struct vm_area_struct *vma;
- int count = 0;
-
- fail_prealloc = false;
- reset_dummy_anon_vma();
-
- vma_iter_set(vmi, 0);
- for_each_vma(*vmi, vma) {
- detach_free_vma(vma);
- count++;
- }
-
- mtree_destroy(&mm->mm_mt);
- mm->map_count = 0;
- return count;
-}
-
-/* Helper function to determine if VMA has had vma_start_write() performed. */
-static bool vma_write_started(struct vm_area_struct *vma)
-{
- int seq = vma->vm_lock_seq;
-
- /* We reset after each check. */
- vma->vm_lock_seq = UINT_MAX;
-
- /* The vma_start_write() stub simply increments this value. */
- return seq > -1;
-}
-
-/* Helper function providing a dummy vm_ops->close() method.*/
-static void dummy_close(struct vm_area_struct *)
-{
-}
-
-static void __vma_set_dummy_anon_vma(struct vm_area_struct *vma,
- struct anon_vma_chain *avc,
- struct anon_vma *anon_vma)
-{
- vma->anon_vma = anon_vma;
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- list_add(&avc->same_vma, &vma->anon_vma_chain);
- avc->anon_vma = vma->anon_vma;
-}
-
-static void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
- struct anon_vma_chain *avc)
-{
- __vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma);
-}
-
static bool test_simple_merge(void)
{
struct vm_area_struct *vma;
@@ -1616,39 +1408,6 @@ static bool test_merge_extend(void)
return true;
}
-static bool test_copy_vma(void)
-{
- vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
- struct mm_struct mm = {};
- bool need_locks = false;
- VMA_ITERATOR(vmi, &mm, 0);
- struct vm_area_struct *vma, *vma_new, *vma_next;
-
- /* Move backwards and do not merge. */
-
- vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
- vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks);
- ASSERT_NE(vma_new, vma);
- ASSERT_EQ(vma_new->vm_start, 0);
- ASSERT_EQ(vma_new->vm_end, 0x2000);
- ASSERT_EQ(vma_new->vm_pgoff, 0);
- vma_assert_attached(vma_new);
-
- cleanup_mm(&mm, &vmi);
-
- /* Move a VMA into position next to another and merge the two. */
-
- vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
- vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, vm_flags);
- vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks);
- vma_assert_attached(vma_new);
-
- ASSERT_EQ(vma_new, vma_next);
-
- cleanup_mm(&mm, &vmi);
- return true;
-}
-
static bool test_expand_only_mode(void)
{
vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
@@ -1689,73 +1448,8 @@ static bool test_expand_only_mode(void)
return true;
}
-static bool test_mmap_region_basic(void)
-{
- struct mm_struct mm = {};
- unsigned long addr;
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, &mm, 0);
-
- current->mm = &mm;
-
- /* Map at 0x300000, length 0x3000. */
- addr = __mmap_region(NULL, 0x300000, 0x3000,
- VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
- 0x300, NULL);
- ASSERT_EQ(addr, 0x300000);
-
- /* Map at 0x250000, length 0x3000. */
- addr = __mmap_region(NULL, 0x250000, 0x3000,
- VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
- 0x250, NULL);
- ASSERT_EQ(addr, 0x250000);
-
- /* Map at 0x303000, merging to 0x300000 of length 0x6000. */
- addr = __mmap_region(NULL, 0x303000, 0x3000,
- VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
- 0x303, NULL);
- ASSERT_EQ(addr, 0x303000);
-
- /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */
- addr = __mmap_region(NULL, 0x24d000, 0x3000,
- VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
- 0x24d, NULL);
- ASSERT_EQ(addr, 0x24d000);
-
- ASSERT_EQ(mm.map_count, 2);
-
- for_each_vma(vmi, vma) {
- if (vma->vm_start == 0x300000) {
- ASSERT_EQ(vma->vm_end, 0x306000);
- ASSERT_EQ(vma->vm_pgoff, 0x300);
- } else if (vma->vm_start == 0x24d000) {
- ASSERT_EQ(vma->vm_end, 0x253000);
- ASSERT_EQ(vma->vm_pgoff, 0x24d);
- } else {
- ASSERT_FALSE(true);
- }
- }
-
- cleanup_mm(&mm, &vmi);
- return true;
-}
-
-int main(void)
+static void run_merge_tests(int *num_tests, int *num_fail)
{
- int num_tests = 0, num_fail = 0;
-
- maple_tree_init();
- vma_state_init();
-
-#define TEST(name) \
- do { \
- num_tests++; \
- if (!test_##name()) { \
- num_fail++; \
- fprintf(stderr, "Test " #name " FAILED\n"); \
- } \
- } while (0)
-
/* Very simple tests to kick the tyres. */
TEST(simple_merge);
TEST(simple_modify);
@@ -1771,15 +1465,5 @@ int main(void)
TEST(dup_anon_vma);
TEST(vmi_prealloc_fail);
TEST(merge_extend);
- TEST(copy_vma);
TEST(expand_only_mode);
-
- TEST(mmap_region_basic);
-
-#undef TEST
-
- printf("%d tests run, %d passed, %d failed.\n",
- num_tests, num_tests - num_fail, num_fail);
-
- return num_fail == 0 ? EXIT_SUCCESS : EXIT_FAILURE;
}
diff --git a/tools/testing/vma/tests/mmap.c b/tools/testing/vma/tests/mmap.c
new file mode 100644
index 000000000000..bded4ecbe5db
--- /dev/null
+++ b/tools/testing/vma/tests/mmap.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+static bool test_mmap_region_basic(void)
+{
+ struct mm_struct mm = {};
+ unsigned long addr;
+ struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, &mm, 0);
+
+ current->mm = &mm;
+
+ /* Map at 0x300000, length 0x3000. */
+ addr = __mmap_region(NULL, 0x300000, 0x3000,
+ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+ 0x300, NULL);
+ ASSERT_EQ(addr, 0x300000);
+
+ /* Map at 0x250000, length 0x3000. */
+ addr = __mmap_region(NULL, 0x250000, 0x3000,
+ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+ 0x250, NULL);
+ ASSERT_EQ(addr, 0x250000);
+
+ /* Map at 0x303000, merging to 0x300000 of length 0x6000. */
+ addr = __mmap_region(NULL, 0x303000, 0x3000,
+ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+ 0x303, NULL);
+ ASSERT_EQ(addr, 0x303000);
+
+ /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */
+ addr = __mmap_region(NULL, 0x24d000, 0x3000,
+ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE,
+ 0x24d, NULL);
+ ASSERT_EQ(addr, 0x24d000);
+
+ ASSERT_EQ(mm.map_count, 2);
+
+ for_each_vma(vmi, vma) {
+ if (vma->vm_start == 0x300000) {
+ ASSERT_EQ(vma->vm_end, 0x306000);
+ ASSERT_EQ(vma->vm_pgoff, 0x300);
+ } else if (vma->vm_start == 0x24d000) {
+ ASSERT_EQ(vma->vm_end, 0x253000);
+ ASSERT_EQ(vma->vm_pgoff, 0x24d);
+ } else {
+ ASSERT_FALSE(true);
+ }
+ }
+
+ cleanup_mm(&mm, &vmi);
+ return true;
+}
+
+static void run_mmap_tests(int *num_tests, int *num_fail)
+{
+ TEST(mmap_region_basic);
+}
diff --git a/tools/testing/vma/tests/vma.c b/tools/testing/vma/tests/vma.c
new file mode 100644
index 000000000000..6d9775aee243
--- /dev/null
+++ b/tools/testing/vma/tests/vma.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+static bool test_copy_vma(void)
+{
+ vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+ struct mm_struct mm = {};
+ bool need_locks = false;
+ VMA_ITERATOR(vmi, &mm, 0);
+ struct vm_area_struct *vma, *vma_new, *vma_next;
+
+ /* Move backwards and do not merge. */
+
+ vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+ vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks);
+ ASSERT_NE(vma_new, vma);
+ ASSERT_EQ(vma_new->vm_start, 0);
+ ASSERT_EQ(vma_new->vm_end, 0x2000);
+ ASSERT_EQ(vma_new->vm_pgoff, 0);
+ vma_assert_attached(vma_new);
+
+ cleanup_mm(&mm, &vmi);
+
+ /* Move a VMA into position next to another and merge the two. */
+
+ vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
+ vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, vm_flags);
+ vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks);
+ vma_assert_attached(vma_new);
+
+ ASSERT_EQ(vma_new, vma_next);
+
+ cleanup_mm(&mm, &vmi);
+ return true;
+}
+
+static void run_vma_tests(int *num_tests, int *num_fail)
+{
+ TEST(copy_vma);
+}
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 8143b95dc50e..cb20382f86b9 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1127,15 +1127,6 @@ static inline void mapping_allow_writable(struct address_space *mapping)
atomic_inc(&mapping->i_mmap_writable);
}
-static inline void vma_set_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end,
- pgoff_t pgoff)
-{
- vma->vm_start = start;
- vma->vm_end = end;
- vma->vm_pgoff = pgoff;
-}
-
static inline
struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
{
--
2.52.0
^ permalink raw reply related
* [PATCH RESEND 11/12] tools/testing/vma: separate out vma_internal.h into logical headers
From: Lorenzo Stoakes @ 2026-01-19 21:19 UTC (permalink / raw)
To: Andrew Morton
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
The vma_internal.h file is becoming entirely unmanageable. It combines
duplicated kernel implementation logic that needs to be kept in-sync with
the kernel, stubbed out declarations that we simply ignore for testing
purposes and custom logic added to aid testing.
If we separate each of the three things into separate headers it makes
things far more manageable, so do so:
* include/stubs.h contains the stubbed declarations,
* include/dup.h contains the duplicated kernel declarations, and
* include/custom.h contains declarations customised for testing.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
tools/testing/vma/Makefile | 2 +-
tools/testing/vma/include/custom.h | 103 ++
tools/testing/vma/include/dup.h | 1341 +++++++++++++++++++
tools/testing/vma/include/stubs.h | 428 ++++++
tools/testing/vma/vma_internal.h | 1936 +---------------------------
5 files changed, 1885 insertions(+), 1925 deletions(-)
create mode 100644 tools/testing/vma/include/custom.h
create mode 100644 tools/testing/vma/include/dup.h
create mode 100644 tools/testing/vma/include/stubs.h
diff --git a/tools/testing/vma/Makefile b/tools/testing/vma/Makefile
index 94133d9d3955..50aa4301b3a6 100644
--- a/tools/testing/vma/Makefile
+++ b/tools/testing/vma/Makefile
@@ -9,7 +9,7 @@ include ../shared/shared.mk
OFILES = $(SHARED_OFILES) main.o shared.o maple-shim.o
TARGETS = vma
-main.o: main.c shared.c shared.h vma_internal.h tests/merge.c tests/mmap.c tests/vma.c ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h
+main.o: main.c shared.c shared.h vma_internal.h tests/merge.c tests/mmap.c tests/vma.c ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h include/custom.h include/dup.h include/stubs.h
vma: $(OFILES)
$(CC) $(CFLAGS) -o $@ $(OFILES) $(LDLIBS)
diff --git a/tools/testing/vma/include/custom.h b/tools/testing/vma/include/custom.h
new file mode 100644
index 000000000000..f567127efba9
--- /dev/null
+++ b/tools/testing/vma/include/custom.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#pragma once
+
+/*
+ * Contains declarations that exist in the kernel which have been CUSTOMISED for
+ * testing purposes to faciliate userland VMA testing.
+ */
+
+#ifdef CONFIG_MMU
+extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
+#else
+#define mmap_min_addr 0UL
+#define dac_mmap_min_addr 0UL
+#endif
+
+#define VM_WARN_ON(_expr) (WARN_ON(_expr))
+#define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr))
+#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr))
+#define VM_BUG_ON(_expr) (BUG_ON(_expr))
+#define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr))
+
+/* We hardcode this for now. */
+#define sysctl_max_map_count 0x1000000UL
+
+#define TASK_SIZE ((1ul << 47)-PAGE_SIZE)
+
+/*
+ * The shared stubs do not implement this, it amounts to an fprintf(STDERR,...)
+ * either way :)
+ */
+#define pr_warn_once pr_err
+
+#define pgtable_supports_soft_dirty() 1
+
+struct anon_vma {
+ struct anon_vma *root;
+ struct rb_root_cached rb_root;
+
+ /* Test fields. */
+ bool was_cloned;
+ bool was_unlinked;
+};
+
+static inline void unlink_anon_vmas(struct vm_area_struct *vma)
+{
+ /* For testing purposes, indicate that the anon_vma was unlinked. */
+ vma->anon_vma->was_unlinked = true;
+}
+
+static inline void vma_start_write(struct vm_area_struct *vma)
+{
+ /* Used to indicate to tests that a write operation has begun. */
+ vma->vm_lock_seq++;
+}
+
+static inline __must_check
+int vma_start_write_killable(struct vm_area_struct *vma)
+{
+ /* Used to indicate to tests that a write operation has begun. */
+ vma->vm_lock_seq++;
+ return 0;
+}
+
+static inline int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src,
+ enum vma_operation operation)
+{
+ /* For testing purposes. We indicate that an anon_vma has been cloned. */
+ if (src->anon_vma != NULL) {
+ dst->anon_vma = src->anon_vma;
+ dst->anon_vma->was_cloned = true;
+ }
+
+ return 0;
+}
+
+static inline int __anon_vma_prepare(struct vm_area_struct *vma)
+{
+ struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma));
+
+ if (!anon_vma)
+ return -ENOMEM;
+
+ anon_vma->root = anon_vma;
+ vma->anon_vma = anon_vma;
+
+ return 0;
+}
+
+static inline int anon_vma_prepare(struct vm_area_struct *vma)
+{
+ if (likely(vma->anon_vma))
+ return 0;
+
+ return __anon_vma_prepare(vma);
+}
+
+static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
+{
+ if (reset_refcnt)
+ refcount_set(&vma->vm_refcnt, 0);
+}
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
new file mode 100644
index 000000000000..3eeef4173e5b
--- /dev/null
+++ b/tools/testing/vma/include/dup.h
@@ -0,0 +1,1341 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#pragma once
+
+/* Forward declarations to avoid header cycle. */
+struct vm_area_struct;
+static inline void vma_start_write(struct vm_area_struct *vma);
+
+extern const struct vm_operations_struct vma_dummy_vm_ops;
+extern unsigned long stack_guard_gap;
+extern const struct vm_operations_struct vma_dummy_vm_ops;
+extern unsigned long rlimit(unsigned int limit);
+struct task_struct *get_current(void);
+
+#define MMF_HAS_MDWE 28
+#define current get_current()
+
+/*
+ * Define the task command name length as enum, then it can be visible to
+ * BPF programs.
+ */
+enum {
+ TASK_COMM_LEN = 16,
+};
+
+/* PARTIALLY implemented types. */
+struct mm_struct {
+ struct maple_tree mm_mt;
+ int map_count; /* number of VMAs */
+ unsigned long total_vm; /* Total pages mapped */
+ unsigned long locked_vm; /* Pages that have PG_mlocked set */
+ unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+ unsigned long stack_vm; /* VM_STACK */
+
+ unsigned long def_flags;
+
+ mm_flags_t flags; /* Must use mm_flags_* helpers to access */
+};
+struct address_space {
+ struct rb_root_cached i_mmap;
+ unsigned long flags;
+ atomic_t i_mmap_writable;
+};
+struct file_operations {
+ int (*mmap)(struct file *, struct vm_area_struct *);
+ int (*mmap_prepare)(struct vm_area_desc *);
+};
+struct file {
+ struct address_space *f_mapping;
+ const struct file_operations *f_op;
+};
+struct anon_vma_chain {
+ struct anon_vma *anon_vma;
+ struct list_head same_vma;
+};
+struct task_struct {
+ char comm[TASK_COMM_LEN];
+ pid_t pid;
+ struct mm_struct *mm;
+
+ /* Used for emulating ABI behavior of previous Linux versions: */
+ unsigned int personality;
+};
+
+struct kref {
+ refcount_t refcount;
+};
+
+struct anon_vma_name {
+ struct kref kref;
+ /* The name needs to be at the end because it is dynamically sized. */
+ char name[];
+};
+
+/*
+ * Contains declarations that are DUPLICATED from kernel source in order to
+ * faciliate userland VMA testing.
+ *
+ * These must be kept in sync with kernel source.
+ */
+
+#define VMA_LOCK_OFFSET 0x40000000
+
+typedef struct { unsigned long v; } freeptr_t;
+
+#define VM_NONE 0x00000000
+
+typedef int __bitwise vma_flag_t;
+
+#define ACCESS_PRIVATE(p, member) ((p)->member)
+
+#define DECLARE_VMA_BIT(name, bitnum) \
+ VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum)
+#define DECLARE_VMA_BIT_ALIAS(name, aliased) \
+ VMA_ ## name ## _BIT = VMA_ ## aliased ## _BIT
+enum {
+ DECLARE_VMA_BIT(READ, 0),
+ DECLARE_VMA_BIT(WRITE, 1),
+ DECLARE_VMA_BIT(EXEC, 2),
+ DECLARE_VMA_BIT(SHARED, 3),
+ /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
+ DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */
+ DECLARE_VMA_BIT(MAYWRITE, 5),
+ DECLARE_VMA_BIT(MAYEXEC, 6),
+ DECLARE_VMA_BIT(MAYSHARE, 7),
+ DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */
+#ifdef CONFIG_MMU
+ DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */
+#else
+ /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
+ DECLARE_VMA_BIT(MAYOVERLAY, 9),
+#endif /* CONFIG_MMU */
+ /* Page-ranges managed without "struct page", just pure PFN */
+ DECLARE_VMA_BIT(PFNMAP, 10),
+ DECLARE_VMA_BIT(MAYBE_GUARD, 11),
+ DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */
+ DECLARE_VMA_BIT(LOCKED, 13),
+ DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */
+ DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */
+ DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */
+ DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */
+ DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */
+ DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */
+ DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */
+ DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */
+ DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */
+ DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */
+ DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */
+ DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */
+ DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */
+ DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */
+ DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */
+ DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */
+ DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */
+ DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */
+ /* These bits are reused, we define specific uses below. */
+ DECLARE_VMA_BIT(HIGH_ARCH_0, 32),
+ DECLARE_VMA_BIT(HIGH_ARCH_1, 33),
+ DECLARE_VMA_BIT(HIGH_ARCH_2, 34),
+ DECLARE_VMA_BIT(HIGH_ARCH_3, 35),
+ DECLARE_VMA_BIT(HIGH_ARCH_4, 36),
+ DECLARE_VMA_BIT(HIGH_ARCH_5, 37),
+ DECLARE_VMA_BIT(HIGH_ARCH_6, 38),
+ /*
+ * This flag is used to connect VFIO to arch specific KVM code. It
+ * indicates that the memory under this VMA is safe for use with any
+ * non-cachable memory type inside KVM. Some VFIO devices, on some
+ * platforms, are thought to be unsafe and can cause machine crashes
+ * if KVM does not lock down the memory type.
+ */
+ DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39),
+#ifdef CONFIG_PPC32
+ DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1),
+#else
+ DECLARE_VMA_BIT(DROPPABLE, 40),
+#endif
+ DECLARE_VMA_BIT(UFFD_MINOR, 41),
+ DECLARE_VMA_BIT(SEALED, 42),
+ /* Flags that reuse flags above. */
+ DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0),
+ DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1),
+ DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2),
+ DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3),
+ DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4),
+#if defined(CONFIG_X86_USER_SHADOW_STACK)
+ /*
+ * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
+ * support core mm.
+ *
+ * These VMAs will get a single end guard page. This helps userspace
+ * protect itself from attacks. A single page is enough for current
+ * shadow stack archs (x86). See the comments near alloc_shstk() in
+ * arch/x86/kernel/shstk.c for more details on the guard size.
+ */
+ DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5),
+#elif defined(CONFIG_ARM64_GCS)
+ /*
+ * arm64's Guarded Control Stack implements similar functionality and
+ * has similar constraints to shadow stacks.
+ */
+ DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6),
+#endif
+ DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */
+ DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */
+ DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */
+ DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */
+ DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */
+ DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */
+ DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */
+ DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */
+#ifdef CONFIG_STACK_GROWSUP
+ DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP),
+ DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN),
+#else
+ DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN),
+#endif
+};
+
+#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT)
+#define VM_READ INIT_VM_FLAG(READ)
+#define VM_WRITE INIT_VM_FLAG(WRITE)
+#define VM_EXEC INIT_VM_FLAG(EXEC)
+#define VM_SHARED INIT_VM_FLAG(SHARED)
+#define VM_MAYREAD INIT_VM_FLAG(MAYREAD)
+#define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE)
+#define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC)
+#define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE)
+#define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN)
+#ifdef CONFIG_MMU
+#define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING)
+#else
+#define VM_UFFD_MISSING VM_NONE
+#define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY)
+#endif
+#define VM_PFNMAP INIT_VM_FLAG(PFNMAP)
+#define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD)
+#define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP)
+#define VM_LOCKED INIT_VM_FLAG(LOCKED)
+#define VM_IO INIT_VM_FLAG(IO)
+#define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ)
+#define VM_RAND_READ INIT_VM_FLAG(RAND_READ)
+#define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY)
+#define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND)
+#define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT)
+#define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT)
+#define VM_NORESERVE INIT_VM_FLAG(NORESERVE)
+#define VM_HUGETLB INIT_VM_FLAG(HUGETLB)
+#define VM_SYNC INIT_VM_FLAG(SYNC)
+#define VM_ARCH_1 INIT_VM_FLAG(ARCH_1)
+#define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK)
+#define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP)
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY)
+#else
+#define VM_SOFTDIRTY VM_NONE
+#endif
+#define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP)
+#define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE)
+#define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE)
+#define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE)
+#define VM_STACK INIT_VM_FLAG(STACK)
+#ifdef CONFIG_STACK_GROWS_UP
+#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY)
+#else
+#define VM_STACK_EARLY VM_NONE
+#endif
+#ifdef CONFIG_ARCH_HAS_PKEYS
+#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT)
+/* Despite the naming, these are FLAGS not bits. */
+#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0)
+#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1)
+#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2)
+#if CONFIG_ARCH_PKEY_BITS > 3
+#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3)
+#else
+#define VM_PKEY_BIT3 VM_NONE
+#endif /* CONFIG_ARCH_PKEY_BITS > 3 */
+#if CONFIG_ARCH_PKEY_BITS > 4
+#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4)
+#else
+#define VM_PKEY_BIT4 VM_NONE
+#endif /* CONFIG_ARCH_PKEY_BITS > 4 */
+#endif /* CONFIG_ARCH_HAS_PKEYS */
+#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS)
+#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK)
+#else
+#define VM_SHADOW_STACK VM_NONE
+#endif
+#if defined(CONFIG_PPC64)
+#define VM_SAO INIT_VM_FLAG(SAO)
+#elif defined(CONFIG_PARISC)
+#define VM_GROWSUP INIT_VM_FLAG(GROWSUP)
+#elif defined(CONFIG_SPARC64)
+#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI)
+#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR)
+#elif defined(CONFIG_ARM64)
+#define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI)
+#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR)
+#elif !defined(CONFIG_MMU)
+#define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY)
+#endif
+#ifndef VM_GROWSUP
+#define VM_GROWSUP VM_NONE
+#endif
+#ifdef CONFIG_ARM64_MTE
+#define VM_MTE INIT_VM_FLAG(MTE)
+#define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED)
+#else
+#define VM_MTE VM_NONE
+#define VM_MTE_ALLOWED VM_NONE
+#endif
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
+#define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR)
+#else
+#define VM_UFFD_MINOR VM_NONE
+#endif
+#ifdef CONFIG_64BIT
+#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED)
+#define VM_SEALED INIT_VM_FLAG(SEALED)
+#else
+#define VM_ALLOW_ANY_UNCACHED VM_NONE
+#define VM_SEALED VM_NONE
+#endif
+#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32)
+#define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE)
+#else
+#define VM_DROPPABLE VM_NONE
+#endif
+
+/* Bits set in the VMA until the stack is in its final location */
+#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
+
+#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
+
+/* Common data flag combinations */
+#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \
+ VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */
+#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC
+#endif
+
+#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
+#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
+#endif
+
+#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
+
+#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+
+/* VMA basic access permission flags */
+#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
+
+/*
+ * Special vmas that are non-mergable, non-mlock()able.
+ */
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
+
+#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_LOW DEFAULT_MAP_WINDOW
+#define TASK_SIZE_MAX DEFAULT_MAP_WINDOW
+#define STACK_TOP TASK_SIZE_LOW
+#define STACK_TOP_MAX TASK_SIZE_MAX
+
+/* This mask represents all the VMA flag bits used by mlock */
+#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT)
+
+#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
+
+#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
+ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#define RLIMIT_STACK 3 /* max stack size */
+#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
+
+#define CAP_IPC_LOCK 14
+
+#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD)
+
+#define VM_IGNORE_MERGE VM_STICKY
+
+#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD)
+
+#define pgprot_val(x) ((x).pgprot)
+#define __pgprot(x) ((pgprot_t) { (x) } )
+
+#define for_each_vma(__vmi, __vma) \
+ while (((__vma) = vma_next(&(__vmi))) != NULL)
+
+/* The MM code likes to work with exclusive end addresses */
+#define for_each_vma_range(__vmi, __vma, __end) \
+ while (((__vma) = vma_find(&(__vmi), (__end))) != NULL)
+
+#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
+
+#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT))
+
+#define test_and_set_bit(nr, addr) __test_and_set_bit(nr, addr)
+#define test_and_clear_bit(nr, addr) __test_and_clear_bit(nr, addr)
+
+#define AS_MM_ALL_LOCKS 2
+
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
+/*
+ * Flags for bug emulation.
+ *
+ * These occupy the top three bytes.
+ */
+enum {
+ READ_IMPLIES_EXEC = 0x0400000,
+};
+
+struct vma_iterator {
+ struct ma_state mas;
+};
+
+#define VMA_ITERATOR(name, __mm, __addr) \
+ struct vma_iterator name = { \
+ .mas = { \
+ .tree = &(__mm)->mm_mt, \
+ .index = __addr, \
+ .node = NULL, \
+ .status = ma_start, \
+ }, \
+ }
+
+#define DEFINE_MUTEX(mutexname) \
+ struct mutex mutexname = {}
+
+#define DECLARE_BITMAP(name, bits) \
+ unsigned long name[BITS_TO_LONGS(bits)]
+
+#define EMPTY_VMA_FLAGS ((vma_flags_t){ })
+
+/* What action should be taken after an .mmap_prepare call is complete? */
+enum mmap_action_type {
+ MMAP_NOTHING, /* Mapping is complete, no further action. */
+ MMAP_REMAP_PFN, /* Remap PFN range. */
+ MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
+};
+
+/*
+ * Describes an action an mmap_prepare hook can instruct to be taken to complete
+ * the mapping of a VMA. Specified in vm_area_desc.
+ */
+struct mmap_action {
+ union {
+ /* Remap range. */
+ struct {
+ unsigned long start;
+ unsigned long start_pfn;
+ unsigned long size;
+ pgprot_t pgprot;
+ } remap;
+ };
+ enum mmap_action_type type;
+
+ /*
+ * If specified, this hook is invoked after the selected action has been
+ * successfully completed. Note that the VMA write lock still held.
+ *
+ * The absolute minimum ought to be done here.
+ *
+ * Returns 0 on success, or an error code.
+ */
+ int (*success_hook)(const struct vm_area_struct *vma);
+
+ /*
+ * If specified, this hook is invoked when an error occurred when
+ * attempting the selection action.
+ *
+ * The hook can return an error code in order to filter the error, but
+ * it is not valid to clear the error here.
+ */
+ int (*error_hook)(int err);
+
+ /*
+ * This should be set in rare instances where the operation required
+ * that the rmap should not be able to access the VMA until
+ * completely set up.
+ */
+ bool hide_from_rmap_until_complete :1;
+};
+
+/* Operations which modify VMAs. */
+enum vma_operation {
+ VMA_OP_SPLIT,
+ VMA_OP_MERGE_UNFAULTED,
+ VMA_OP_REMAP,
+ VMA_OP_FORK,
+};
+
+/*
+ * Describes a VMA that is about to be mmap()'ed. Drivers may choose to
+ * manipulate mutable fields which will cause those fields to be updated in the
+ * resultant VMA.
+ *
+ * Helper functions are not required for manipulating any field.
+ */
+struct vm_area_desc {
+ /* Immutable state. */
+ const struct mm_struct *const mm;
+ struct file *const file; /* May vary from vm_file in stacked callers. */
+ unsigned long start;
+ unsigned long end;
+
+ /* Mutable fields. Populated with initial state. */
+ pgoff_t pgoff;
+ struct file *vm_file;
+ union {
+ vm_flags_t vm_flags;
+ vma_flags_t vma_flags;
+ };
+ pgprot_t page_prot;
+
+ /* Write-only fields. */
+ const struct vm_operations_struct *vm_ops;
+ void *private_data;
+
+ /* Take further action? */
+ struct mmap_action action;
+};
+
+struct vm_area_struct {
+ /* The first cache line has the info for VMA tree walking. */
+
+ union {
+ struct {
+ /* VMA covers [vm_start; vm_end) addresses within mm */
+ unsigned long vm_start;
+ unsigned long vm_end;
+ };
+ freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
+ };
+
+ struct mm_struct *vm_mm; /* The address space we belong to. */
+ pgprot_t vm_page_prot; /* Access permissions of this VMA. */
+
+ /*
+ * Flags, see mm.h.
+ * To modify use vm_flags_{init|reset|set|clear|mod} functions.
+ */
+ union {
+ const vm_flags_t vm_flags;
+ vma_flags_t flags;
+ };
+
+#ifdef CONFIG_PER_VMA_LOCK
+ /*
+ * Can only be written (using WRITE_ONCE()) while holding both:
+ * - mmap_lock (in write mode)
+ * - vm_refcnt bit at VMA_LOCK_OFFSET is set
+ * Can be read reliably while holding one of:
+ * - mmap_lock (in read or write mode)
+ * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
+ * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+ * while holding nothing (except RCU to keep the VMA struct allocated).
+ *
+ * This sequence counter is explicitly allowed to overflow; sequence
+ * counter reuse can only lead to occasional unnecessary use of the
+ * slowpath.
+ */
+ unsigned int vm_lock_seq;
+#endif
+
+ /*
+ * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
+ * list, after a COW of one of the file pages. A MAP_SHARED vma
+ * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
+ * or brk vma (with NULL file) can only be in an anon_vma list.
+ */
+ struct list_head anon_vma_chain; /* Serialized by mmap_lock &
+ * page_table_lock */
+ struct anon_vma *anon_vma; /* Serialized by page_table_lock */
+
+ /* Function pointers to deal with this struct. */
+ const struct vm_operations_struct *vm_ops;
+
+ /* Information about our backing store: */
+ unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
+ units */
+ struct file * vm_file; /* File we map to (can be NULL). */
+ void * vm_private_data; /* was vm_pte (shared mem) */
+
+#ifdef CONFIG_SWAP
+ atomic_long_t swap_readahead_info;
+#endif
+#ifndef CONFIG_MMU
+ struct vm_region *vm_region; /* NOMMU mapping region */
+#endif
+#ifdef CONFIG_NUMA
+ struct mempolicy *vm_policy; /* NUMA policy for the VMA */
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+ struct vma_numab_state *numab_state; /* NUMA Balancing state */
+#endif
+#ifdef CONFIG_PER_VMA_LOCK
+ /* Unstable RCU readers are allowed to read this. */
+ refcount_t vm_refcnt;
+#endif
+ /*
+ * For areas with an address space and backing store,
+ * linkage into the address_space->i_mmap interval tree.
+ *
+ */
+ struct {
+ struct rb_node rb;
+ unsigned long rb_subtree_last;
+ } shared;
+#ifdef CONFIG_ANON_VMA_NAME
+ /*
+ * For private and shared anonymous mappings, a pointer to a null
+ * terminated string containing the name given to the vma, or NULL if
+ * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
+ */
+ struct anon_vma_name *anon_name;
+#endif
+ struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+} __randomize_layout;
+
+struct vm_operations_struct {
+ void (*open)(struct vm_area_struct * area);
+ /**
+ * @close: Called when the VMA is being removed from the MM.
+ * Context: User context. May sleep. Caller holds mmap_lock.
+ */
+ void (*close)(struct vm_area_struct * area);
+ /* Called any time before splitting to check if it's allowed */
+ int (*may_split)(struct vm_area_struct *area, unsigned long addr);
+ int (*mremap)(struct vm_area_struct *area);
+ /*
+ * Called by mprotect() to make driver-specific permission
+ * checks before mprotect() is finalised. The VMA must not
+ * be modified. Returns 0 if mprotect() can proceed.
+ */
+ int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end, unsigned long newflags);
+ vm_fault_t (*fault)(struct vm_fault *vmf);
+ vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
+ vm_fault_t (*map_pages)(struct vm_fault *vmf,
+ pgoff_t start_pgoff, pgoff_t end_pgoff);
+ unsigned long (*pagesize)(struct vm_area_struct * area);
+
+ /* notification that a previously read-only page is about to become
+ * writable, if an error is returned it will cause a SIGBUS */
+ vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
+
+ /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
+ vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
+
+ /* called by access_process_vm when get_user_pages() fails, typically
+ * for use by special VMAs. See also generic_access_phys() for a generic
+ * implementation useful for any iomem mapping.
+ */
+ int (*access)(struct vm_area_struct *vma, unsigned long addr,
+ void *buf, int len, int write);
+
+ /* Called by the /proc/PID/maps code to ask the vma whether it
+ * has a special name. Returning non-NULL will also cause this
+ * vma to be dumped unconditionally. */
+ const char *(*name)(struct vm_area_struct *vma);
+
+#ifdef CONFIG_NUMA
+ /*
+ * set_policy() op must add a reference to any non-NULL @new mempolicy
+ * to hold the policy upon return. Caller should pass NULL @new to
+ * remove a policy and fall back to surrounding context--i.e. do not
+ * install a MPOL_DEFAULT policy, nor the task or system default
+ * mempolicy.
+ */
+ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
+
+ /*
+ * get_policy() op must add reference [mpol_get()] to any policy at
+ * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure
+ * in mm/mempolicy.c will do this automatically.
+ * get_policy() must NOT add a ref if the policy at (vma,addr) is not
+ * marked as MPOL_SHARED. vma policies are protected by the mmap_lock.
+ * If no [shared/vma] mempolicy exists at the addr, get_policy() op
+ * must return NULL--i.e., do not "fallback" to task or system default
+ * policy.
+ */
+ struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
+ unsigned long addr, pgoff_t *ilx);
+#endif
+#ifdef CONFIG_FIND_NORMAL_PAGE
+ /*
+ * Called by vm_normal_page() for special PTEs in @vma at @addr. This
+ * allows for returning a "normal" page from vm_normal_page() even
+ * though the PTE indicates that the "struct page" either does not exist
+ * or should not be touched: "special".
+ *
+ * Do not add new users: this really only works when a "normal" page
+ * was mapped, but then the PTE got changed to something weird (+
+ * marked special) that would not make pte_pfn() identify the originally
+ * inserted page.
+ */
+ struct page *(*find_normal_page)(struct vm_area_struct *vma,
+ unsigned long addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
+};
+
+struct vm_unmapped_area_info {
+#define VM_UNMAPPED_AREA_TOPDOWN 1
+ unsigned long flags;
+ unsigned long length;
+ unsigned long low_limit;
+ unsigned long high_limit;
+ unsigned long align_mask;
+ unsigned long align_offset;
+ unsigned long start_gap;
+};
+
+struct pagetable_move_control {
+ struct vm_area_struct *old; /* Source VMA. */
+ struct vm_area_struct *new; /* Destination VMA. */
+ unsigned long old_addr; /* Address from which the move begins. */
+ unsigned long old_end; /* Exclusive address at which old range ends. */
+ unsigned long new_addr; /* Address to move page tables to. */
+ unsigned long len_in; /* Bytes to remap specified by user. */
+
+ bool need_rmap_locks; /* Do rmap locks need to be taken? */
+ bool for_stack; /* Is this an early temp stack being moved? */
+};
+
+#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \
+ struct pagetable_move_control name = { \
+ .old = old_, \
+ .new = new_, \
+ .old_addr = old_addr_, \
+ .old_end = (old_addr_) + (len_), \
+ .new_addr = new_addr_, \
+ .len_in = len_, \
+ }
+
+static inline void vma_iter_invalidate(struct vma_iterator *vmi)
+{
+ mas_pause(&vmi->mas);
+}
+
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+ return __pgprot(pgprot_val(oldprot) | pgprot_val(newprot));
+}
+
+static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
+{
+ return __pgprot(vm_flags);
+}
+
+static inline bool mm_flags_test(int flag, const struct mm_struct *mm)
+{
+ return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
+}
+
+/*
+ * Copy value to the first system word of VMA flags, non-atomically.
+ *
+ * IMPORTANT: This does not overwrite bytes past the first system word. The
+ * caller must account for this.
+ */
+static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value)
+{
+ *ACCESS_PRIVATE(flags, __vma_flags) = value;
+}
+
+/*
+ * Copy value to the first system word of VMA flags ONCE, non-atomically.
+ *
+ * IMPORTANT: This does not overwrite bytes past the first system word. The
+ * caller must account for this.
+ */
+static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+ WRITE_ONCE(*bitmap, value);
+}
+
+/* Update the first system word of VMA flags setting bits, non-atomically. */
+static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+ *bitmap |= value;
+}
+
+/* Update the first system word of VMA flags clearing bits, non-atomically. */
+static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+ *bitmap &= ~value;
+}
+
+static inline void vma_flags_clear_all(vma_flags_t *flags)
+{
+ bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS);
+}
+
+static inline void vma_flag_set(vma_flags_t *flags, vma_flag_t bit)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+ __set_bit((__force int)bit, bitmap);
+}
+
+/* Use when VMA is not part of the VMA tree and needs no locking */
+static inline void vm_flags_init(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_flags_clear_all(&vma->flags);
+ vma_flags_overwrite_word(&vma->flags, flags);
+}
+
+/*
+ * Use when VMA is part of the VMA tree and modifications need coordination
+ * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
+ * it should be locked explicitly beforehand.
+ */
+static inline void vm_flags_reset(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_assert_write_locked(vma);
+ vm_flags_init(vma, flags);
+}
+
+static inline void vm_flags_reset_once(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_assert_write_locked(vma);
+ /*
+ * The user should only be interested in avoiding reordering of
+ * assignment to the first word.
+ */
+ vma_flags_clear_all(&vma->flags);
+ vma_flags_overwrite_word_once(&vma->flags, flags);
+}
+
+static inline void vm_flags_set(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_start_write(vma);
+ vma_flags_set_word(&vma->flags, flags);
+}
+
+static inline void vm_flags_clear(struct vm_area_struct *vma,
+ vm_flags_t flags)
+{
+ vma_start_write(vma);
+ vma_flags_clear_word(&vma->flags, flags);
+}
+
+static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits)
+{
+ vma_flags_t flags;
+ int i;
+
+ vma_flags_clear_all(&flags);
+ for (i = 0; i < count; i++)
+ vma_flag_set(&flags, bits[i]);
+ return flags;
+}
+
+#define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \
+ (const vma_flag_t []){__VA_ARGS__})
+
+static __always_inline bool vma_flags_test_mask(vma_flags_t flags,
+ vma_flags_t to_test)
+{
+ const unsigned long *bitmap = ACCESS_PRIVATE(&flags, __vma_flags);
+ const unsigned long *bitmap_to_test = ACCESS_PRIVATE(&to_test, __vma_flags);
+
+ return bitmap_intersects(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS);
+}
+
+#define vma_flags_test(flags, ...) \
+ vma_flags_test_mask(flags, mk_vma_flags(__VA_ARGS__))
+
+static __always_inline void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+ const unsigned long *bitmap_to_set = ACCESS_PRIVATE(&to_set, __vma_flags);
+
+ bitmap_or(bitmap, bitmap, bitmap_to_set, NUM_VMA_FLAG_BITS);
+}
+
+#define vma_flags_set(flags, ...) \
+ vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__))
+
+static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear)
+{
+ unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+ const unsigned long *bitmap_to_clear = ACCESS_PRIVATE(&to_clear, __vma_flags);
+
+ bitmap_andnot(bitmap, bitmap, bitmap_to_clear, NUM_VMA_FLAG_BITS);
+}
+
+#define vma_flags_clear(flags, ...) \
+ vma_flags_clear_mask(flags, mk_vma_flags(__VA_ARGS__))
+
+static __always_inline bool vma_flags_test_all_mask(vma_flags_t flags,
+ vma_flags_t to_test)
+{
+ const unsigned long *bitmap = ACCESS_PRIVATE(&flags, __vma_flags);
+ const unsigned long *bitmap_to_test = ACCESS_PRIVATE(&to_test, __vma_flags);
+
+ return bitmap_subset(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS);
+}
+
+#define vma_flags_test_all(flags, ...) \
+ vma_flags_test_all_mask(flags, mk_vma_flags(__VA_ARGS__))
+
+static inline void vma_set_flags_mask(struct vm_area_struct *vma,
+ vma_flags_t flags)
+{
+ vma_flags_set_mask(&vma->flags, flags);
+}
+
+#define vma_set_flags(vma, ...) \
+ vma_set_flags_mask(vma, mk_vma_flags(__VA_ARGS__))
+
+static inline bool vma_test_all_flags_mask(struct vm_area_struct *vma,
+ vma_flags_t flags)
+{
+ return vma_flags_test_all_mask(vma->flags, flags);
+}
+
+#define vma_test_all_flags(vma, ...) \
+ vma_test_all_flags_mask(vma, mk_vma_flags(__VA_ARGS__))
+
+static inline bool vma_desc_test_flags_mask(struct vm_area_desc *desc,
+ vma_flags_t flags)
+{
+ return vma_flags_test_mask(desc->vma_flags, flags);
+}
+
+#define vma_desc_test_flags(desc, ...) \
+ vma_desc_test_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
+
+static inline void vma_desc_set_flags_mask(struct vm_area_desc *desc,
+ vma_flags_t flags)
+{
+ vma_flags_set_mask(&desc->vma_flags, flags);
+}
+
+#define vma_desc_set_flags(desc, ...) \
+ vma_desc_set_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
+
+static inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc,
+ vma_flags_t flags)
+{
+ vma_flags_clear_mask(&desc->vma_flags, flags);
+}
+
+#define vma_desc_clear_flags(desc, ...) \
+ vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
+
+static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags)
+{
+ return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
+ (VM_SHARED | VM_MAYWRITE);
+}
+
+static inline bool is_shared_maywrite(vma_flags_t flags)
+{
+ return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT);
+}
+
+static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma)
+{
+ return is_shared_maywrite(vma->flags);
+}
+
+static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
+{
+ /*
+ * Uses mas_find() to get the first VMA when the iterator starts.
+ * Calling mas_next() could skip the first entry.
+ */
+ return mas_find(&vmi->mas, ULONG_MAX);
+}
+
+/*
+ * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
+ * assertions should be made either under mmap_write_lock or when the object
+ * has been isolated under mmap_write_lock, ensuring no competing writers.
+ */
+static inline void vma_assert_attached(struct vm_area_struct *vma)
+{
+ WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
+}
+
+static inline void vma_assert_detached(struct vm_area_struct *vma)
+{
+ WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
+}
+
+static inline void vma_assert_write_locked(struct vm_area_struct *);
+static inline void vma_mark_attached(struct vm_area_struct *vma)
+{
+ vma_assert_write_locked(vma);
+ vma_assert_detached(vma);
+ refcount_set_release(&vma->vm_refcnt, 1);
+}
+
+static inline void vma_mark_detached(struct vm_area_struct *vma)
+{
+ vma_assert_write_locked(vma);
+ vma_assert_attached(vma);
+ /* We are the only writer, so no need to use vma_refcount_put(). */
+ if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
+ /*
+ * Reader must have temporarily raised vm_refcnt but it will
+ * drop it without using the vma since vma is write-locked.
+ */
+ }
+}
+
+static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
+{
+ memset(vma, 0, sizeof(*vma));
+ vma->vm_mm = mm;
+ vma->vm_ops = &vma_dummy_vm_ops;
+ INIT_LIST_HEAD(&vma->anon_vma_chain);
+ vma->vm_lock_seq = UINT_MAX;
+}
+
+/*
+ * These are defined in vma.h, but sadly vm_stat_account() is referenced by
+ * kernel/fork.c, so we have to these broadly available there, and temporarily
+ * define them here to resolve the dependency cycle.
+ */
+#define is_exec_mapping(flags) \
+ ((flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC)
+
+#define is_stack_mapping(flags) \
+ (((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK))
+
+#define is_data_mapping(flags) \
+ ((flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE)
+
+static inline void vm_stat_account(struct mm_struct *mm, vm_flags_t flags,
+ long npages)
+{
+ WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages);
+
+ if (is_exec_mapping(flags))
+ mm->exec_vm += npages;
+ else if (is_stack_mapping(flags))
+ mm->stack_vm += npages;
+ else if (is_data_mapping(flags))
+ mm->data_vm += npages;
+}
+
+#undef is_exec_mapping
+#undef is_stack_mapping
+#undef is_data_mapping
+
+static inline void vm_unacct_memory(long pages)
+{
+ vm_acct_memory(-pages);
+}
+
+static inline void mapping_allow_writable(struct address_space *mapping)
+{
+ atomic_inc(&mapping->i_mmap_writable);
+}
+
+static inline
+struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
+{
+ return mas_find(&vmi->mas, max - 1);
+}
+
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+ unsigned long start, unsigned long end, gfp_t gfp)
+{
+ __mas_set_range(&vmi->mas, start, end - 1);
+ mas_store_gfp(&vmi->mas, NULL, gfp);
+ if (unlikely(mas_is_err(&vmi->mas)))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+ vma->vm_ops = NULL;
+}
+
+/* Declared in vma.h. */
+static inline void set_vma_from_desc(struct vm_area_struct *vma,
+ struct vm_area_desc *desc);
+
+static inline int __compat_vma_mmap(const struct file_operations *f_op,
+ struct file *file, struct vm_area_struct *vma)
+{
+ struct vm_area_desc desc = {
+ .mm = vma->vm_mm,
+ .file = file,
+ .start = vma->vm_start,
+ .end = vma->vm_end,
+
+ .pgoff = vma->vm_pgoff,
+ .vm_file = vma->vm_file,
+ .vm_flags = vma->vm_flags,
+ .page_prot = vma->vm_page_prot,
+
+ .action.type = MMAP_NOTHING, /* Default */
+ };
+ int err;
+
+ err = f_op->mmap_prepare(&desc);
+ if (err)
+ return err;
+
+ mmap_action_prepare(&desc.action, &desc);
+ set_vma_from_desc(vma, &desc);
+ return mmap_action_complete(&desc.action, vma);
+}
+
+static inline int compat_vma_mmap(struct file *file,
+ struct vm_area_struct *vma)
+{
+ return __compat_vma_mmap(file->f_op, file, vma);
+}
+
+
+static inline void vma_iter_init(struct vma_iterator *vmi,
+ struct mm_struct *mm, unsigned long addr)
+{
+ mas_init(&vmi->mas, &mm->mm_mt, addr);
+}
+
+static inline unsigned long vma_pages(struct vm_area_struct *vma)
+{
+ return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+}
+
+static inline void mmap_assert_locked(struct mm_struct *);
+static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
+ unsigned long start_addr,
+ unsigned long end_addr)
+{
+ unsigned long index = start_addr;
+
+ mmap_assert_locked(mm);
+ return mt_find(&mm->mm_mt, &index, end_addr - 1);
+}
+
+static inline
+struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
+{
+ return mtree_load(&mm->mm_mt, addr);
+}
+
+static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
+{
+ return mas_prev(&vmi->mas, 0);
+}
+
+static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
+{
+ mas_set(&vmi->mas, addr);
+}
+
+static inline bool vma_is_anonymous(struct vm_area_struct *vma)
+{
+ return !vma->vm_ops;
+}
+
+/* Defined in vma.h, so temporarily define here to avoid circular dependency. */
+#define vma_iter_load(vmi) \
+ mas_walk(&(vmi)->mas)
+
+static inline struct vm_area_struct *
+find_vma_prev(struct mm_struct *mm, unsigned long addr,
+ struct vm_area_struct **pprev)
+{
+ struct vm_area_struct *vma;
+ VMA_ITERATOR(vmi, mm, addr);
+
+ vma = vma_iter_load(&vmi);
+ *pprev = vma_prev(&vmi);
+ if (!vma)
+ vma = vma_next(&vmi);
+ return vma;
+}
+
+#undef vma_iter_load
+
+static inline void vma_iter_free(struct vma_iterator *vmi)
+{
+ mas_destroy(&vmi->mas);
+}
+
+static inline
+struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
+{
+ return mas_next_range(&vmi->mas, ULONG_MAX);
+}
+
+bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
+
+/* Update vma->vm_page_prot to reflect vma->vm_flags. */
+static inline void vma_set_page_prot(struct vm_area_struct *vma)
+{
+ vm_flags_t vm_flags = vma->vm_flags;
+ pgprot_t vm_page_prot;
+
+ /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
+ vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags));
+
+ if (vma_wants_writenotify(vma, vm_page_prot)) {
+ vm_flags &= ~VM_SHARED;
+ /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
+ vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags));
+ }
+ /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
+ WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
+}
+
+static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & VM_GROWSDOWN)
+ return stack_guard_gap;
+
+ /* See reasoning around the VM_SHADOW_STACK definition */
+ if (vma->vm_flags & VM_SHADOW_STACK)
+ return PAGE_SIZE;
+
+ return 0;
+}
+
+static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+{
+ unsigned long gap = stack_guard_start_gap(vma);
+ unsigned long vm_start = vma->vm_start;
+
+ vm_start -= gap;
+ if (vm_start > vma->vm_start)
+ vm_start = 0;
+ return vm_start;
+}
+
+static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+{
+ unsigned long vm_end = vma->vm_end;
+
+ if (vma->vm_flags & VM_GROWSUP) {
+ vm_end += stack_guard_gap;
+ if (vm_end < vma->vm_end)
+ vm_end = -PAGE_SIZE;
+ }
+ return vm_end;
+}
+
+static inline bool vma_is_accessible(struct vm_area_struct *vma)
+{
+ return vma->vm_flags & VM_ACCESS_FLAGS;
+}
+
+static inline bool mlock_future_ok(const struct mm_struct *mm,
+ vm_flags_t vm_flags, unsigned long bytes)
+{
+ unsigned long locked_pages, limit_pages;
+
+ if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
+ return true;
+
+ locked_pages = bytes >> PAGE_SHIFT;
+ locked_pages += mm->locked_vm;
+
+ limit_pages = rlimit(RLIMIT_MEMLOCK);
+ limit_pages >>= PAGE_SHIFT;
+
+ return locked_pages <= limit_pages;
+}
+
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
+{
+ /* If MDWE is disabled, we have nothing to deny. */
+ if (mm_flags_test(MMF_HAS_MDWE, current->mm))
+ return false;
+
+ /* If the new VMA is not executable, we have nothing to deny. */
+ if (!(new & VM_EXEC))
+ return false;
+
+ /* Under MDWE we do not accept newly writably executable VMAs... */
+ if (new & VM_WRITE)
+ return true;
+
+ /* ...nor previously non-executable VMAs becoming executable. */
+ if (!(old & VM_EXEC))
+ return true;
+
+ return false;
+}
+
+static inline int mapping_map_writable(struct address_space *mapping)
+{
+ return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
+ 0 : -EPERM;
+}
+
+/* Did the driver provide valid mmap hook configuration? */
+static inline bool can_mmap_file(struct file *file)
+{
+ bool has_mmap = file->f_op->mmap;
+ bool has_mmap_prepare = file->f_op->mmap_prepare;
+
+ /* Hooks are mutually exclusive. */
+ if (WARN_ON_ONCE(has_mmap && has_mmap_prepare))
+ return false;
+ if (!has_mmap && !has_mmap_prepare)
+ return false;
+
+ return true;
+}
+
+static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ if (file->f_op->mmap_prepare)
+ return compat_vma_mmap(file, vma);
+
+ return file->f_op->mmap(file, vma);
+}
+
+static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
+{
+ return file->f_op->mmap_prepare(desc);
+}
+
+static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ /* Changing an anonymous vma with this is illegal */
+ get_file(file);
+ swap(vma->vm_file, file);
+ fput(file);
+}
+
+struct unmap_desc {
+ struct ma_state *mas; /* the maple state point to the first vma */
+ struct vm_area_struct *first; /* The first vma */
+ unsigned long pg_start; /* The first pagetable address to free (floor) */
+ unsigned long pg_end; /* The last pagetable address to free (ceiling) */
+ unsigned long vma_start; /* The min vma address */
+ unsigned long vma_end; /* The max vma address */
+ unsigned long tree_end; /* Maximum for the vma tree search */
+ unsigned long tree_reset; /* Where to reset the vma tree walk */
+ bool mm_wr_locked; /* If the mmap write lock is held */
+};
diff --git a/tools/testing/vma/include/stubs.h b/tools/testing/vma/include/stubs.h
new file mode 100644
index 000000000000..947a3a0c2566
--- /dev/null
+++ b/tools/testing/vma/include/stubs.h
@@ -0,0 +1,428 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#pragma once
+
+/*
+ * Contains declarations that are STUBBED, that is that are rendered no-ops, in
+ * order to faciliate userland VMA testing.
+ */
+
+/* Forward declarations. */
+struct mm_struct;
+struct vm_area_struct;
+struct vm_area_desc;
+struct pagetable_move_control;
+struct mmap_action;
+struct file;
+struct anon_vma;
+struct anon_vma_chain;
+struct address_space;
+struct unmap_desc;
+
+#define __bitwise
+#define __randomize_layout
+
+#define FIRST_USER_ADDRESS 0UL
+#define USER_PGTABLES_CEILING 0UL
+
+#define vma_policy(vma) NULL
+
+#define down_write_nest_lock(sem, nest_lock)
+
+#define data_race(expr) expr
+
+#define ASSERT_EXCLUSIVE_WRITER(x)
+
+struct vm_userfaultfd_ctx {};
+struct mempolicy {};
+struct mmu_gather {};
+struct mutex {};
+struct vm_fault {};
+
+static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
+ struct list_head *uf)
+{
+}
+
+static inline unsigned long move_page_tables(struct pagetable_move_control *pmc)
+{
+ return 0;
+}
+
+static inline void free_pgd_range(struct mmu_gather *tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
+{
+}
+
+static inline int ksm_execve(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm)
+{
+}
+
+static inline void vma_numab_state_init(struct vm_area_struct *vma)
+{
+}
+
+static inline void vma_numab_state_free(struct vm_area_struct *vma)
+{
+}
+
+static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
+ struct vm_area_struct *new_vma)
+{
+}
+
+static inline void free_anon_vma_name(struct vm_area_struct *vma)
+{
+}
+
+static inline void mmap_action_prepare(struct mmap_action *action,
+ struct vm_area_desc *desc)
+{
+}
+
+static inline int mmap_action_complete(struct mmap_action *action,
+ struct vm_area_struct *vma)
+{
+ return 0;
+}
+
+static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
+{
+}
+
+static inline bool shmem_file(struct file *file)
+{
+ return false;
+}
+
+static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm,
+ const struct file *file, vm_flags_t vm_flags)
+{
+ return vm_flags;
+}
+
+static inline void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn)
+{
+}
+
+static inline int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t pgprot)
+{
+ return 0;
+}
+
+static inline int do_munmap(struct mm_struct *, unsigned long, size_t,
+ struct list_head *uf)
+{
+ return 0;
+}
+
+/* Currently stubbed but we may later wish to un-stub. */
+static inline void vm_acct_memory(long pages);
+
+static inline void mmap_assert_locked(struct mm_struct *mm)
+{
+}
+
+
+static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
+{
+}
+
+static inline void i_mmap_unlock_write(struct address_space *mapping)
+{
+}
+
+static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end,
+ struct list_head *unmaps)
+{
+ return 0;
+}
+
+static inline void mmap_write_downgrade(struct mm_struct *mm)
+{
+}
+
+static inline void mmap_read_unlock(struct mm_struct *mm)
+{
+}
+
+static inline void mmap_write_unlock(struct mm_struct *mm)
+{
+}
+
+static inline int mmap_write_lock_killable(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline bool can_modify_mm(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ return true;
+}
+
+static inline void arch_unmap(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+}
+
+static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
+{
+ return true;
+}
+
+static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
+ vm_flags_t vm_flags)
+{
+}
+
+static inline bool mapping_can_writeback(struct address_space *mapping)
+{
+ return true;
+}
+
+static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+{
+ return false;
+}
+
+static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
+{
+ return false;
+}
+
+static inline bool userfaultfd_wp(struct vm_area_struct *vma)
+{
+ return false;
+}
+
+static inline void mmap_assert_write_locked(struct mm_struct *mm)
+{
+}
+
+static inline void mutex_lock(struct mutex *lock)
+{
+}
+
+static inline void mutex_unlock(struct mutex *lock)
+{
+}
+
+static inline bool mutex_is_locked(struct mutex *lock)
+{
+ return true;
+}
+
+static inline bool signal_pending(void *p)
+{
+ return false;
+}
+
+static inline bool is_file_hugepages(struct file *file)
+{
+ return false;
+}
+
+static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
+{
+ return 0;
+}
+
+static inline bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags,
+ unsigned long npages)
+{
+ return true;
+}
+
+static inline int shmem_zero_setup(struct vm_area_struct *vma)
+{
+ return 0;
+}
+
+
+static inline void vm_acct_memory(long pages)
+{
+}
+
+static inline void vma_interval_tree_insert(struct vm_area_struct *vma,
+ struct rb_root_cached *rb)
+{
+}
+
+static inline void vma_interval_tree_remove(struct vm_area_struct *vma,
+ struct rb_root_cached *rb)
+{
+}
+
+static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
+{
+}
+
+static inline void anon_vma_interval_tree_insert(struct anon_vma_chain *avc,
+ struct rb_root_cached *rb)
+{
+}
+
+static inline void anon_vma_interval_tree_remove(struct anon_vma_chain *avc,
+ struct rb_root_cached *rb)
+{
+}
+
+static inline void uprobe_mmap(struct vm_area_struct *vma)
+{
+}
+
+static inline void uprobe_munmap(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+
+static inline void i_mmap_lock_write(struct address_space *mapping)
+{
+}
+
+static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
+{
+}
+
+static inline void vma_assert_write_locked(struct vm_area_struct *vma)
+{
+}
+
+static inline void ksm_add_vma(struct vm_area_struct *vma)
+{
+}
+
+static inline void perf_event_mmap(struct vm_area_struct *vma)
+{
+}
+
+static inline bool vma_is_dax(struct vm_area_struct *vma)
+{
+ return false;
+}
+
+static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+ return NULL;
+}
+
+static inline bool arch_validate_flags(vm_flags_t flags)
+{
+ return true;
+}
+
+static inline void vma_close(struct vm_area_struct *vma)
+{
+}
+
+static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
+{
+ return 0;
+}
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+ unsigned long addr, unsigned long len)
+{
+ return 0;
+}
+
+static inline bool capable(int cap)
+{
+ return true;
+}
+
+static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
+{
+ return NULL;
+}
+
+static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
+ struct vm_userfaultfd_ctx vm_ctx)
+{
+ return true;
+}
+
+static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
+ struct anon_vma_name *anon_name2)
+{
+ return true;
+}
+
+static inline void might_sleep(void)
+{
+}
+
+static inline void fput(struct file *file)
+{
+}
+
+static inline void mpol_put(struct mempolicy *pol)
+{
+}
+
+static inline void lru_add_drain(void)
+{
+}
+
+static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
+{
+}
+
+static inline void update_hiwater_rss(struct mm_struct *mm)
+{
+}
+
+static inline void update_hiwater_vm(struct mm_struct *mm)
+{
+}
+
+static inline void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap)
+{
+}
+
+static inline void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *unmap)
+{
+}
+
+static inline void mapping_unmap_writable(struct address_space *mapping)
+{
+}
+
+static inline void flush_dcache_mmap_lock(struct address_space *mapping)
+{
+}
+
+static inline void tlb_finish_mmu(struct mmu_gather *tlb)
+{
+}
+
+static inline struct file *get_file(struct file *f)
+{
+ return f;
+}
+
+static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
+{
+ return 0;
+}
+
+static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end,
+ struct vm_area_struct *next)
+{
+}
+
+static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {}
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index cb20382f86b9..e3ed05b57819 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -12,15 +12,11 @@
#ifndef __MM_VMA_INTERNAL_H
#define __MM_VMA_INTERNAL_H
-#define __private
-#define __bitwise
-#define __randomize_layout
+#include <stdlib.h>
#define CONFIG_MMU
#define CONFIG_PER_VMA_LOCK
-#include <stdlib.h>
-
#ifdef __CONCAT
#undef __CONCAT
#endif
@@ -35,1936 +31,28 @@
#include <linux/refcount.h>
#include <linux/slab.h>
-extern unsigned long stack_guard_gap;
-#ifdef CONFIG_MMU
-extern unsigned long mmap_min_addr;
-extern unsigned long dac_mmap_min_addr;
-#else
-#define mmap_min_addr 0UL
-#define dac_mmap_min_addr 0UL
-#endif
-
-#define ACCESS_PRIVATE(p, member) ((p)->member)
-
-#define VM_WARN_ON(_expr) (WARN_ON(_expr))
-#define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr))
-#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr))
-#define VM_BUG_ON(_expr) (BUG_ON(_expr))
-#define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr))
-
-#define MMF_HAS_MDWE 28
-
-/*
- * vm_flags in vm_area_struct, see mm_types.h.
- * When changing, update also include/trace/events/mmflags.h
- */
-
-#define VM_NONE 0x00000000
-
-/**
- * typedef vma_flag_t - specifies an individual VMA flag by bit number.
- *
- * This value is made type safe by sparse to avoid passing invalid flag values
- * around.
- */
-typedef int __bitwise vma_flag_t;
-
-#define DECLARE_VMA_BIT(name, bitnum) \
- VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum)
-#define DECLARE_VMA_BIT_ALIAS(name, aliased) \
- VMA_ ## name ## _BIT = VMA_ ## aliased ## _BIT
-enum {
- DECLARE_VMA_BIT(READ, 0),
- DECLARE_VMA_BIT(WRITE, 1),
- DECLARE_VMA_BIT(EXEC, 2),
- DECLARE_VMA_BIT(SHARED, 3),
- /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
- DECLARE_VMA_BIT(MAYREAD, 4), /* limits for mprotect() etc. */
- DECLARE_VMA_BIT(MAYWRITE, 5),
- DECLARE_VMA_BIT(MAYEXEC, 6),
- DECLARE_VMA_BIT(MAYSHARE, 7),
- DECLARE_VMA_BIT(GROWSDOWN, 8), /* general info on the segment */
-#ifdef CONFIG_MMU
- DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */
-#else
- /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
- DECLARE_VMA_BIT(MAYOVERLAY, 9),
-#endif /* CONFIG_MMU */
- /* Page-ranges managed without "struct page", just pure PFN */
- DECLARE_VMA_BIT(PFNMAP, 10),
- DECLARE_VMA_BIT(MAYBE_GUARD, 11),
- DECLARE_VMA_BIT(UFFD_WP, 12), /* wrprotect pages tracking */
- DECLARE_VMA_BIT(LOCKED, 13),
- DECLARE_VMA_BIT(IO, 14), /* Memory mapped I/O or similar */
- DECLARE_VMA_BIT(SEQ_READ, 15), /* App will access data sequentially */
- DECLARE_VMA_BIT(RAND_READ, 16), /* App will not benefit from clustered reads */
- DECLARE_VMA_BIT(DONTCOPY, 17), /* Do not copy this vma on fork */
- DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */
- DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */
- DECLARE_VMA_BIT(ACCOUNT, 20), /* Is a VM accounted object */
- DECLARE_VMA_BIT(NORESERVE, 21), /* should the VM suppress accounting */
- DECLARE_VMA_BIT(HUGETLB, 22), /* Huge TLB Page VM */
- DECLARE_VMA_BIT(SYNC, 23), /* Synchronous page faults */
- DECLARE_VMA_BIT(ARCH_1, 24), /* Architecture-specific flag */
- DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */
- DECLARE_VMA_BIT(DONTDUMP, 26), /* Do not include in the core dump */
- DECLARE_VMA_BIT(SOFTDIRTY, 27), /* NOT soft dirty clean area */
- DECLARE_VMA_BIT(MIXEDMAP, 28), /* Can contain struct page and pure PFN pages */
- DECLARE_VMA_BIT(HUGEPAGE, 29), /* MADV_HUGEPAGE marked this vma */
- DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */
- DECLARE_VMA_BIT(MERGEABLE, 31), /* KSM may merge identical pages */
- /* These bits are reused, we define specific uses below. */
- DECLARE_VMA_BIT(HIGH_ARCH_0, 32),
- DECLARE_VMA_BIT(HIGH_ARCH_1, 33),
- DECLARE_VMA_BIT(HIGH_ARCH_2, 34),
- DECLARE_VMA_BIT(HIGH_ARCH_3, 35),
- DECLARE_VMA_BIT(HIGH_ARCH_4, 36),
- DECLARE_VMA_BIT(HIGH_ARCH_5, 37),
- DECLARE_VMA_BIT(HIGH_ARCH_6, 38),
- /*
- * This flag is used to connect VFIO to arch specific KVM code. It
- * indicates that the memory under this VMA is safe for use with any
- * non-cachable memory type inside KVM. Some VFIO devices, on some
- * platforms, are thought to be unsafe and can cause machine crashes
- * if KVM does not lock down the memory type.
- */
- DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39),
-#ifdef CONFIG_PPC32
- DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1),
-#else
- DECLARE_VMA_BIT(DROPPABLE, 40),
-#endif
- DECLARE_VMA_BIT(UFFD_MINOR, 41),
- DECLARE_VMA_BIT(SEALED, 42),
- /* Flags that reuse flags above. */
- DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0),
- DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1),
- DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2),
- DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3),
- DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4),
-#if defined(CONFIG_X86_USER_SHADOW_STACK)
- /*
- * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
- * support core mm.
- *
- * These VMAs will get a single end guard page. This helps userspace
- * protect itself from attacks. A single page is enough for current
- * shadow stack archs (x86). See the comments near alloc_shstk() in
- * arch/x86/kernel/shstk.c for more details on the guard size.
- */
- DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5),
-#elif defined(CONFIG_ARM64_GCS)
- /*
- * arm64's Guarded Control Stack implements similar functionality and
- * has similar constraints to shadow stacks.
- */
- DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6),
-#endif
- DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1), /* Strong Access Ordering (powerpc) */
- DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1), /* parisc */
- DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1), /* sparc64 */
- DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1), /* arm64 */
- DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1), /* sparc64, arm64 */
- DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1), /* !CONFIG_MMU */
- DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4), /* arm64 */
- DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */
-#ifdef CONFIG_STACK_GROWSUP
- DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP),
- DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN),
-#else
- DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN),
-#endif
-};
-
-#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT)
-#define VM_READ INIT_VM_FLAG(READ)
-#define VM_WRITE INIT_VM_FLAG(WRITE)
-#define VM_EXEC INIT_VM_FLAG(EXEC)
-#define VM_SHARED INIT_VM_FLAG(SHARED)
-#define VM_MAYREAD INIT_VM_FLAG(MAYREAD)
-#define VM_MAYWRITE INIT_VM_FLAG(MAYWRITE)
-#define VM_MAYEXEC INIT_VM_FLAG(MAYEXEC)
-#define VM_MAYSHARE INIT_VM_FLAG(MAYSHARE)
-#define VM_GROWSDOWN INIT_VM_FLAG(GROWSDOWN)
-#ifdef CONFIG_MMU
-#define VM_UFFD_MISSING INIT_VM_FLAG(UFFD_MISSING)
-#else
-#define VM_UFFD_MISSING VM_NONE
-#define VM_MAYOVERLAY INIT_VM_FLAG(MAYOVERLAY)
-#endif
-#define VM_PFNMAP INIT_VM_FLAG(PFNMAP)
-#define VM_MAYBE_GUARD INIT_VM_FLAG(MAYBE_GUARD)
-#define VM_UFFD_WP INIT_VM_FLAG(UFFD_WP)
-#define VM_LOCKED INIT_VM_FLAG(LOCKED)
-#define VM_IO INIT_VM_FLAG(IO)
-#define VM_SEQ_READ INIT_VM_FLAG(SEQ_READ)
-#define VM_RAND_READ INIT_VM_FLAG(RAND_READ)
-#define VM_DONTCOPY INIT_VM_FLAG(DONTCOPY)
-#define VM_DONTEXPAND INIT_VM_FLAG(DONTEXPAND)
-#define VM_LOCKONFAULT INIT_VM_FLAG(LOCKONFAULT)
-#define VM_ACCOUNT INIT_VM_FLAG(ACCOUNT)
-#define VM_NORESERVE INIT_VM_FLAG(NORESERVE)
-#define VM_HUGETLB INIT_VM_FLAG(HUGETLB)
-#define VM_SYNC INIT_VM_FLAG(SYNC)
-#define VM_ARCH_1 INIT_VM_FLAG(ARCH_1)
-#define VM_WIPEONFORK INIT_VM_FLAG(WIPEONFORK)
-#define VM_DONTDUMP INIT_VM_FLAG(DONTDUMP)
-#ifdef CONFIG_MEM_SOFT_DIRTY
-#define VM_SOFTDIRTY INIT_VM_FLAG(SOFTDIRTY)
-#else
-#define VM_SOFTDIRTY VM_NONE
-#endif
-#define VM_MIXEDMAP INIT_VM_FLAG(MIXEDMAP)
-#define VM_HUGEPAGE INIT_VM_FLAG(HUGEPAGE)
-#define VM_NOHUGEPAGE INIT_VM_FLAG(NOHUGEPAGE)
-#define VM_MERGEABLE INIT_VM_FLAG(MERGEABLE)
-#define VM_STACK INIT_VM_FLAG(STACK)
-#ifdef CONFIG_STACK_GROWS_UP
-#define VM_STACK_EARLY INIT_VM_FLAG(STACK_EARLY)
-#else
-#define VM_STACK_EARLY VM_NONE
-#endif
-#ifdef CONFIG_ARCH_HAS_PKEYS
-#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT)
-/* Despite the naming, these are FLAGS not bits. */
-#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0)
-#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1)
-#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2)
-#if CONFIG_ARCH_PKEY_BITS > 3
-#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3)
-#else
-#define VM_PKEY_BIT3 VM_NONE
-#endif /* CONFIG_ARCH_PKEY_BITS > 3 */
-#if CONFIG_ARCH_PKEY_BITS > 4
-#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4)
-#else
-#define VM_PKEY_BIT4 VM_NONE
-#endif /* CONFIG_ARCH_PKEY_BITS > 4 */
-#endif /* CONFIG_ARCH_HAS_PKEYS */
-#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS)
-#define VM_SHADOW_STACK INIT_VM_FLAG(SHADOW_STACK)
-#else
-#define VM_SHADOW_STACK VM_NONE
-#endif
-#if defined(CONFIG_PPC64)
-#define VM_SAO INIT_VM_FLAG(SAO)
-#elif defined(CONFIG_PARISC)
-#define VM_GROWSUP INIT_VM_FLAG(GROWSUP)
-#elif defined(CONFIG_SPARC64)
-#define VM_SPARC_ADI INIT_VM_FLAG(SPARC_ADI)
-#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR)
-#elif defined(CONFIG_ARM64)
-#define VM_ARM64_BTI INIT_VM_FLAG(ARM64_BTI)
-#define VM_ARCH_CLEAR INIT_VM_FLAG(ARCH_CLEAR)
-#elif !defined(CONFIG_MMU)
-#define VM_MAPPED_COPY INIT_VM_FLAG(MAPPED_COPY)
-#endif
-#ifndef VM_GROWSUP
-#define VM_GROWSUP VM_NONE
-#endif
-#ifdef CONFIG_ARM64_MTE
-#define VM_MTE INIT_VM_FLAG(MTE)
-#define VM_MTE_ALLOWED INIT_VM_FLAG(MTE_ALLOWED)
-#else
-#define VM_MTE VM_NONE
-#define VM_MTE_ALLOWED VM_NONE
-#endif
-#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
-#define VM_UFFD_MINOR INIT_VM_FLAG(UFFD_MINOR)
-#else
-#define VM_UFFD_MINOR VM_NONE
-#endif
-#ifdef CONFIG_64BIT
-#define VM_ALLOW_ANY_UNCACHED INIT_VM_FLAG(ALLOW_ANY_UNCACHED)
-#define VM_SEALED INIT_VM_FLAG(SEALED)
-#else
-#define VM_ALLOW_ANY_UNCACHED VM_NONE
-#define VM_SEALED VM_NONE
-#endif
-#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32)
-#define VM_DROPPABLE INIT_VM_FLAG(DROPPABLE)
-#else
-#define VM_DROPPABLE VM_NONE
-#endif
-
-/* Bits set in the VMA until the stack is in its final location */
-#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
-
-#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
-
-/* Common data flag combinations */
-#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define VM_DATA_FLAGS_NON_EXEC (VM_READ | VM_WRITE | VM_MAYREAD | \
- VM_MAYWRITE | VM_MAYEXEC)
-#define VM_DATA_FLAGS_EXEC (VM_READ | VM_WRITE | VM_EXEC | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#ifndef VM_DATA_DEFAULT_FLAGS /* arch can override this */
-#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_EXEC
-#endif
-
-#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
-#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
-#endif
-
-#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
-
-#define VM_STACK_FLAGS (VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
-
-/* VMA basic access permission flags */
-#define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
-
-/*
- * Special vmas that are non-mergable, non-mlock()able.
- */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
-
-#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE)
-#define TASK_SIZE_LOW DEFAULT_MAP_WINDOW
-#define TASK_SIZE_MAX DEFAULT_MAP_WINDOW
-#define STACK_TOP TASK_SIZE_LOW
-#define STACK_TOP_MAX TASK_SIZE_MAX
-
-/* This mask represents all the VMA flag bits used by mlock */
-#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT)
-
-#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
-
-#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \
- VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#define RLIMIT_STACK 3 /* max stack size */
-#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */
-
-#define CAP_IPC_LOCK 14
-
-/*
- * Flags which should be 'sticky' on merge - that is, flags which, when one VMA
- * possesses it but the other does not, the merged VMA should nonetheless have
- * applied to it:
- *
- * VM_SOFTDIRTY - if a VMA is marked soft-dirty, that is has not had its
- * references cleared via /proc/$pid/clear_refs, any merged VMA
- * should be considered soft-dirty also as it operates at a VMA
- * granularity.
- */
-#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD)
-
/*
- * VMA flags we ignore for the purposes of merge, i.e. one VMA possessing one
- * of these flags and the other not does not preclude a merge.
- *
- * VM_STICKY - When merging VMAs, VMA flags must match, unless they are
- * 'sticky'. If any sticky flags exist in either VMA, we simply
- * set all of them on the merged VMA.
+ * DUPLICATE typedef definitions from kernel source that have to be declared
+ * ahead of all other headers.
*/
-#define VM_IGNORE_MERGE VM_STICKY
-
-/*
- * Flags which should result in page tables being copied on fork. These are
- * flags which indicate that the VMA maps page tables which cannot be
- * reconsistuted upon page fault, so necessitate page table copying upon
- *
- * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be
- * reasonably reconstructed on page fault.
- *
- * VM_UFFD_WP - Encodes metadata about an installed uffd
- * write protect handler, which cannot be
- * reconstructed on page fault.
- *
- * We always copy pgtables when dst_vma has uffd-wp
- * enabled even if it's file-backed
- * (e.g. shmem). Because when uffd-wp is enabled,
- * pgtable contains uffd-wp protection information,
- * that's something we can't retrieve from page cache,
- * and skip copying will lose those info.
- *
- * VM_MAYBE_GUARD - Could contain page guard region markers which
- * by design are a property of the page tables
- * only and thus cannot be reconstructed on page
- * fault.
- */
-#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD)
-
-#define FIRST_USER_ADDRESS 0UL
-#define USER_PGTABLES_CEILING 0UL
-
-#define vma_policy(vma) NULL
-
-#define down_write_nest_lock(sem, nest_lock)
-
-#define pgprot_val(x) ((x).pgprot)
-#define __pgprot(x) ((pgprot_t) { (x) } )
-
-#define for_each_vma(__vmi, __vma) \
- while (((__vma) = vma_next(&(__vmi))) != NULL)
-
-/* The MM code likes to work with exclusive end addresses */
-#define for_each_vma_range(__vmi, __vma, __end) \
- while (((__vma) = vma_find(&(__vmi), (__end))) != NULL)
-
-#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
-
-#define PHYS_PFN(x) ((unsigned long)((x) >> PAGE_SHIFT))
-
-#define test_and_set_bit(nr, addr) __test_and_set_bit(nr, addr)
-#define test_and_clear_bit(nr, addr) __test_and_clear_bit(nr, addr)
-
-#define TASK_SIZE ((1ul << 47)-PAGE_SIZE)
-
-#define AS_MM_ALL_LOCKS 2
-
-/* We hardcode this for now. */
-#define sysctl_max_map_count 0x1000000UL
-
-#define pgoff_t unsigned long
-typedef unsigned long pgprotval_t;
-typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
-typedef unsigned long vm_flags_t;
-typedef __bitwise unsigned int vm_fault_t;
-
-/*
- * The shared stubs do not implement this, it amounts to an fprintf(STDERR,...)
- * either way :)
- */
-#define pr_warn_once pr_err
-
-#define data_race(expr) expr
-
-#define ASSERT_EXCLUSIVE_WRITER(x)
-
-#define pgtable_supports_soft_dirty() 1
-
-/**
- * swap - swap values of @a and @b
- * @a: first value
- * @b: second value
- */
-#define swap(a, b) \
- do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
-
-struct kref {
- refcount_t refcount;
-};
-
-/*
- * Define the task command name length as enum, then it can be visible to
- * BPF programs.
- */
-enum {
- TASK_COMM_LEN = 16,
-};
-
-/*
- * Flags for bug emulation.
- *
- * These occupy the top three bytes.
- */
-enum {
- READ_IMPLIES_EXEC = 0x0400000,
-};
-
-struct task_struct {
- char comm[TASK_COMM_LEN];
- pid_t pid;
- struct mm_struct *mm;
-
- /* Used for emulating ABI behavior of previous Linux versions: */
- unsigned int personality;
-};
-
-struct task_struct *get_current(void);
-#define current get_current()
-
-struct anon_vma {
- struct anon_vma *root;
- struct rb_root_cached rb_root;
-
- /* Test fields. */
- bool was_cloned;
- bool was_unlinked;
-};
-
-struct anon_vma_chain {
- struct anon_vma *anon_vma;
- struct list_head same_vma;
-};
-
-struct anon_vma_name {
- struct kref kref;
- /* The name needs to be at the end because it is dynamically sized. */
- char name[];
-};
-
-struct vma_iterator {
- struct ma_state mas;
-};
-
-#define VMA_ITERATOR(name, __mm, __addr) \
- struct vma_iterator name = { \
- .mas = { \
- .tree = &(__mm)->mm_mt, \
- .index = __addr, \
- .node = NULL, \
- .status = ma_start, \
- }, \
- }
-
-struct address_space {
- struct rb_root_cached i_mmap;
- unsigned long flags;
- atomic_t i_mmap_writable;
-};
-
-struct vm_userfaultfd_ctx {};
-struct mempolicy {};
-struct mmu_gather {};
-struct mutex {};
-#define DEFINE_MUTEX(mutexname) \
- struct mutex mutexname = {}
-
-#define DECLARE_BITMAP(name, bits) \
- unsigned long name[BITS_TO_LONGS(bits)]
-
+#define __private
#define NUM_MM_FLAG_BITS (64)
typedef struct {
__private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS);
} mm_flags_t;
-
-/*
- * Opaque type representing current VMA (vm_area_struct) flag state. Must be
- * accessed via vma_flags_xxx() helper functions.
- */
#define NUM_VMA_FLAG_BITS BITS_PER_LONG
typedef struct {
DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS);
} __private vma_flags_t;
-#define EMPTY_VMA_FLAGS ((vma_flags_t){ })
-
-struct mm_struct {
- struct maple_tree mm_mt;
- int map_count; /* number of VMAs */
- unsigned long total_vm; /* Total pages mapped */
- unsigned long locked_vm; /* Pages that have PG_mlocked set */
- unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
- unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
- unsigned long stack_vm; /* VM_STACK */
-
- unsigned long def_flags;
-
- mm_flags_t flags; /* Must use mm_flags_* helpers to access */
-};
-
-struct vm_area_struct;
-
-
-/* What action should be taken after an .mmap_prepare call is complete? */
-enum mmap_action_type {
- MMAP_NOTHING, /* Mapping is complete, no further action. */
- MMAP_REMAP_PFN, /* Remap PFN range. */
- MMAP_IO_REMAP_PFN, /* I/O remap PFN range. */
-};
-
-/*
- * Describes an action an mmap_prepare hook can instruct to be taken to complete
- * the mapping of a VMA. Specified in vm_area_desc.
- */
-struct mmap_action {
- union {
- /* Remap range. */
- struct {
- unsigned long start;
- unsigned long start_pfn;
- unsigned long size;
- pgprot_t pgprot;
- } remap;
- };
- enum mmap_action_type type;
-
- /*
- * If specified, this hook is invoked after the selected action has been
- * successfully completed. Note that the VMA write lock still held.
- *
- * The absolute minimum ought to be done here.
- *
- * Returns 0 on success, or an error code.
- */
- int (*success_hook)(const struct vm_area_struct *vma);
-
- /*
- * If specified, this hook is invoked when an error occurred when
- * attempting the selection action.
- *
- * The hook can return an error code in order to filter the error, but
- * it is not valid to clear the error here.
- */
- int (*error_hook)(int err);
-
- /*
- * This should be set in rare instances where the operation required
- * that the rmap should not be able to access the VMA until
- * completely set up.
- */
- bool hide_from_rmap_until_complete :1;
-};
-
-/* Operations which modify VMAs. */
-enum vma_operation {
- VMA_OP_SPLIT,
- VMA_OP_MERGE_UNFAULTED,
- VMA_OP_REMAP,
- VMA_OP_FORK,
-};
-
-/*
- * Describes a VMA that is about to be mmap()'ed. Drivers may choose to
- * manipulate mutable fields which will cause those fields to be updated in the
- * resultant VMA.
- *
- * Helper functions are not required for manipulating any field.
- */
-struct vm_area_desc {
- /* Immutable state. */
- const struct mm_struct *const mm;
- struct file *const file; /* May vary from vm_file in stacked callers. */
- unsigned long start;
- unsigned long end;
-
- /* Mutable fields. Populated with initial state. */
- pgoff_t pgoff;
- struct file *vm_file;
- union {
- vm_flags_t vm_flags;
- vma_flags_t vma_flags;
- };
- pgprot_t page_prot;
-
- /* Write-only fields. */
- const struct vm_operations_struct *vm_ops;
- void *private_data;
-
- /* Take further action? */
- struct mmap_action action;
-};
-
-struct file_operations {
- int (*mmap)(struct file *, struct vm_area_struct *);
- int (*mmap_prepare)(struct vm_area_desc *);
-};
-
-struct file {
- struct address_space *f_mapping;
- const struct file_operations *f_op;
-};
-
-#define VMA_LOCK_OFFSET 0x40000000
-
-typedef struct { unsigned long v; } freeptr_t;
-
-struct vm_area_struct {
- /* The first cache line has the info for VMA tree walking. */
-
- union {
- struct {
- /* VMA covers [vm_start; vm_end) addresses within mm */
- unsigned long vm_start;
- unsigned long vm_end;
- };
- freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
- };
-
- struct mm_struct *vm_mm; /* The address space we belong to. */
- pgprot_t vm_page_prot; /* Access permissions of this VMA. */
-
- /*
- * Flags, see mm.h.
- * To modify use vm_flags_{init|reset|set|clear|mod} functions.
- */
- union {
- const vm_flags_t vm_flags;
- vma_flags_t flags;
- };
-
-#ifdef CONFIG_PER_VMA_LOCK
- /*
- * Can only be written (using WRITE_ONCE()) while holding both:
- * - mmap_lock (in write mode)
- * - vm_refcnt bit at VMA_LOCK_OFFSET is set
- * Can be read reliably while holding one of:
- * - mmap_lock (in read or write mode)
- * - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
- * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
- * while holding nothing (except RCU to keep the VMA struct allocated).
- *
- * This sequence counter is explicitly allowed to overflow; sequence
- * counter reuse can only lead to occasional unnecessary use of the
- * slowpath.
- */
- unsigned int vm_lock_seq;
-#endif
-
- /*
- * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
- * list, after a COW of one of the file pages. A MAP_SHARED vma
- * can only be in the i_mmap tree. An anonymous MAP_PRIVATE, stack
- * or brk vma (with NULL file) can only be in an anon_vma list.
- */
- struct list_head anon_vma_chain; /* Serialized by mmap_lock &
- * page_table_lock */
- struct anon_vma *anon_vma; /* Serialized by page_table_lock */
-
- /* Function pointers to deal with this struct. */
- const struct vm_operations_struct *vm_ops;
-
- /* Information about our backing store: */
- unsigned long vm_pgoff; /* Offset (within vm_file) in PAGE_SIZE
- units */
- struct file * vm_file; /* File we map to (can be NULL). */
- void * vm_private_data; /* was vm_pte (shared mem) */
-
-#ifdef CONFIG_SWAP
- atomic_long_t swap_readahead_info;
-#endif
-#ifndef CONFIG_MMU
- struct vm_region *vm_region; /* NOMMU mapping region */
-#endif
-#ifdef CONFIG_NUMA
- struct mempolicy *vm_policy; /* NUMA policy for the VMA */
-#endif
-#ifdef CONFIG_NUMA_BALANCING
- struct vma_numab_state *numab_state; /* NUMA Balancing state */
-#endif
-#ifdef CONFIG_PER_VMA_LOCK
- /* Unstable RCU readers are allowed to read this. */
- refcount_t vm_refcnt;
-#endif
- /*
- * For areas with an address space and backing store,
- * linkage into the address_space->i_mmap interval tree.
- *
- */
- struct {
- struct rb_node rb;
- unsigned long rb_subtree_last;
- } shared;
-#ifdef CONFIG_ANON_VMA_NAME
- /*
- * For private and shared anonymous mappings, a pointer to a null
- * terminated string containing the name given to the vma, or NULL if
- * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
- */
- struct anon_vma_name *anon_name;
-#endif
- struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
-} __randomize_layout;
-
-struct vm_fault {};
-
-struct vm_operations_struct {
- void (*open)(struct vm_area_struct * area);
- /**
- * @close: Called when the VMA is being removed from the MM.
- * Context: User context. May sleep. Caller holds mmap_lock.
- */
- void (*close)(struct vm_area_struct * area);
- /* Called any time before splitting to check if it's allowed */
- int (*may_split)(struct vm_area_struct *area, unsigned long addr);
- int (*mremap)(struct vm_area_struct *area);
- /*
- * Called by mprotect() to make driver-specific permission
- * checks before mprotect() is finalised. The VMA must not
- * be modified. Returns 0 if mprotect() can proceed.
- */
- int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
- unsigned long end, unsigned long newflags);
- vm_fault_t (*fault)(struct vm_fault *vmf);
- vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
- vm_fault_t (*map_pages)(struct vm_fault *vmf,
- pgoff_t start_pgoff, pgoff_t end_pgoff);
- unsigned long (*pagesize)(struct vm_area_struct * area);
-
- /* notification that a previously read-only page is about to become
- * writable, if an error is returned it will cause a SIGBUS */
- vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
-
- /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
- vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
-
- /* called by access_process_vm when get_user_pages() fails, typically
- * for use by special VMAs. See also generic_access_phys() for a generic
- * implementation useful for any iomem mapping.
- */
- int (*access)(struct vm_area_struct *vma, unsigned long addr,
- void *buf, int len, int write);
-
- /* Called by the /proc/PID/maps code to ask the vma whether it
- * has a special name. Returning non-NULL will also cause this
- * vma to be dumped unconditionally. */
- const char *(*name)(struct vm_area_struct *vma);
-
-#ifdef CONFIG_NUMA
- /*
- * set_policy() op must add a reference to any non-NULL @new mempolicy
- * to hold the policy upon return. Caller should pass NULL @new to
- * remove a policy and fall back to surrounding context--i.e. do not
- * install a MPOL_DEFAULT policy, nor the task or system default
- * mempolicy.
- */
- int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
-
- /*
- * get_policy() op must add reference [mpol_get()] to any policy at
- * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure
- * in mm/mempolicy.c will do this automatically.
- * get_policy() must NOT add a ref if the policy at (vma,addr) is not
- * marked as MPOL_SHARED. vma policies are protected by the mmap_lock.
- * If no [shared/vma] mempolicy exists at the addr, get_policy() op
- * must return NULL--i.e., do not "fallback" to task or system default
- * policy.
- */
- struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
- unsigned long addr, pgoff_t *ilx);
-#endif
-#ifdef CONFIG_FIND_NORMAL_PAGE
- /*
- * Called by vm_normal_page() for special PTEs in @vma at @addr. This
- * allows for returning a "normal" page from vm_normal_page() even
- * though the PTE indicates that the "struct page" either does not exist
- * or should not be touched: "special".
- *
- * Do not add new users: this really only works when a "normal" page
- * was mapped, but then the PTE got changed to something weird (+
- * marked special) that would not make pte_pfn() identify the originally
- * inserted page.
- */
- struct page *(*find_normal_page)(struct vm_area_struct *vma,
- unsigned long addr);
-#endif /* CONFIG_FIND_NORMAL_PAGE */
-};
-
-struct vm_unmapped_area_info {
-#define VM_UNMAPPED_AREA_TOPDOWN 1
- unsigned long flags;
- unsigned long length;
- unsigned long low_limit;
- unsigned long high_limit;
- unsigned long align_mask;
- unsigned long align_offset;
- unsigned long start_gap;
-};
-
-struct pagetable_move_control {
- struct vm_area_struct *old; /* Source VMA. */
- struct vm_area_struct *new; /* Destination VMA. */
- unsigned long old_addr; /* Address from which the move begins. */
- unsigned long old_end; /* Exclusive address at which old range ends. */
- unsigned long new_addr; /* Address to move page tables to. */
- unsigned long len_in; /* Bytes to remap specified by user. */
-
- bool need_rmap_locks; /* Do rmap locks need to be taken? */
- bool for_stack; /* Is this an early temp stack being moved? */
-};
-
-#define PAGETABLE_MOVE(name, old_, new_, old_addr_, new_addr_, len_) \
- struct pagetable_move_control name = { \
- .old = old_, \
- .new = new_, \
- .old_addr = old_addr_, \
- .old_end = (old_addr_) + (len_), \
- .new_addr = new_addr_, \
- .len_in = len_, \
- }
-
-static inline void vma_iter_invalidate(struct vma_iterator *vmi)
-{
- mas_pause(&vmi->mas);
-}
-
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
- return __pgprot(pgprot_val(oldprot) | pgprot_val(newprot));
-}
-
-static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
-{
- return __pgprot(vm_flags);
-}
-
-static inline void vma_flags_clear_all(vma_flags_t *flags)
-{
- bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS);
-}
-
-static inline void vma_flag_set(vma_flags_t *flags, vma_flag_t bit)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
-
- __set_bit((__force int)bit, bitmap);
-}
-
-static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits)
-{
- vma_flags_t flags;
- int i;
-
- vma_flags_clear_all(&flags);
- for (i = 0; i < count; i++)
- vma_flag_set(&flags, bits[i]);
- return flags;
-}
-
-#define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \
- (const vma_flag_t []){__VA_ARGS__})
-
-static __always_inline bool vma_flags_test_mask(vma_flags_t flags,
- vma_flags_t to_test)
-{
- const unsigned long *bitmap = ACCESS_PRIVATE(&flags, __vma_flags);
- const unsigned long *bitmap_to_test = ACCESS_PRIVATE(&to_test, __vma_flags);
-
- return bitmap_intersects(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS);
-}
-
-#define vma_flags_test(flags, ...) \
- vma_flags_test_mask(flags, mk_vma_flags(__VA_ARGS__))
-
-static __always_inline void vma_flags_set_mask(vma_flags_t *flags, vma_flags_t to_set)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
- const unsigned long *bitmap_to_set = ACCESS_PRIVATE(&to_set, __vma_flags);
-
- bitmap_or(bitmap, bitmap, bitmap_to_set, NUM_VMA_FLAG_BITS);
-}
-
-#define vma_flags_set(flags, ...) \
- vma_flags_set_mask(flags, mk_vma_flags(__VA_ARGS__))
-
-static __always_inline void vma_flags_clear_mask(vma_flags_t *flags, vma_flags_t to_clear)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
- const unsigned long *bitmap_to_clear = ACCESS_PRIVATE(&to_clear, __vma_flags);
-
- bitmap_andnot(bitmap, bitmap, bitmap_to_clear, NUM_VMA_FLAG_BITS);
-}
-
-#define vma_flags_clear(flags, ...) \
- vma_flags_clear_mask(flags, mk_vma_flags(__VA_ARGS__))
-
-static __always_inline bool vma_flags_test_all_mask(vma_flags_t flags,
- vma_flags_t to_test)
-{
- const unsigned long *bitmap = ACCESS_PRIVATE(&flags, __vma_flags);
- const unsigned long *bitmap_to_test = ACCESS_PRIVATE(&to_test, __vma_flags);
-
- return bitmap_subset(bitmap_to_test, bitmap, NUM_VMA_FLAG_BITS);
-}
-
-#define vma_flags_test_all(flags, ...) \
- vma_flags_test_all_mask(flags, mk_vma_flags(__VA_ARGS__))
-
-static inline void vma_set_flags_mask(struct vm_area_struct *vma,
- vma_flags_t flags)
-{
- vma_flags_set_mask(&vma->flags, flags);
-}
-
-#define vma_set_flags(vma, ...) \
- vma_set_flags_mask(vma, mk_vma_flags(__VA_ARGS__))
-
-static inline bool vma_test_all_flags_mask(struct vm_area_struct *vma,
- vma_flags_t flags)
-{
- return vma_flags_test_all_mask(vma->flags, flags);
-}
-
-#define vma_test_all_flags(vma, ...) \
- vma_test_all_flags_mask(vma, mk_vma_flags(__VA_ARGS__))
-
-static inline bool vma_desc_test_flags_mask(struct vm_area_desc *desc,
- vma_flags_t flags)
-{
- return vma_flags_test_mask(desc->vma_flags, flags);
-}
-
-#define vma_desc_test_flags(desc, ...) \
- vma_desc_test_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
-
-static inline void vma_desc_set_flags_mask(struct vm_area_desc *desc,
- vma_flags_t flags)
-{
- vma_flags_set_mask(&desc->vma_flags, flags);
-}
-
-#define vma_desc_set_flags(desc, ...) \
- vma_desc_set_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
-
-static inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc,
- vma_flags_t flags)
-{
- vma_flags_clear_mask(&desc->vma_flags, flags);
-}
-
-#define vma_desc_clear_flags(desc, ...) \
- vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
-
-static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags)
-{
- return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
- (VM_SHARED | VM_MAYWRITE);
-}
-
-static inline bool is_shared_maywrite(vma_flags_t flags)
-{
- return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT);
-}
-
-static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma)
-{
- return is_shared_maywrite(vma->flags);
-}
-
-static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
-{
- /*
- * Uses mas_find() to get the first VMA when the iterator starts.
- * Calling mas_next() could skip the first entry.
- */
- return mas_find(&vmi->mas, ULONG_MAX);
-}
-
-/*
- * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
- * assertions should be made either under mmap_write_lock or when the object
- * has been isolated under mmap_write_lock, ensuring no competing writers.
- */
-static inline void vma_assert_attached(struct vm_area_struct *vma)
-{
- WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
-}
-
-static inline void vma_assert_detached(struct vm_area_struct *vma)
-{
- WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
-}
-
-static inline void vma_assert_write_locked(struct vm_area_struct *);
-static inline void vma_mark_attached(struct vm_area_struct *vma)
-{
- vma_assert_write_locked(vma);
- vma_assert_detached(vma);
- refcount_set_release(&vma->vm_refcnt, 1);
-}
-
-static inline void vma_mark_detached(struct vm_area_struct *vma)
-{
- vma_assert_write_locked(vma);
- vma_assert_attached(vma);
- /* We are the only writer, so no need to use vma_refcount_put(). */
- if (unlikely(!refcount_dec_and_test(&vma->vm_refcnt))) {
- /*
- * Reader must have temporarily raised vm_refcnt but it will
- * drop it without using the vma since vma is write-locked.
- */
- }
-}
-
-extern const struct vm_operations_struct vma_dummy_vm_ops;
-
-extern unsigned long rlimit(unsigned int limit);
-
-static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
-{
- memset(vma, 0, sizeof(*vma));
- vma->vm_mm = mm;
- vma->vm_ops = &vma_dummy_vm_ops;
- INIT_LIST_HEAD(&vma->anon_vma_chain);
- vma->vm_lock_seq = UINT_MAX;
-}
-
-/*
- * These are defined in vma.h, but sadly vm_stat_account() is referenced by
- * kernel/fork.c, so we have to these broadly available there, and temporarily
- * define them here to resolve the dependency cycle.
- */
-
-#define is_exec_mapping(flags) \
- ((flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC)
-
-#define is_stack_mapping(flags) \
- (((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK))
-
-#define is_data_mapping(flags) \
- ((flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE)
-
-static inline void vm_stat_account(struct mm_struct *mm, vm_flags_t flags,
- long npages)
-{
- WRITE_ONCE(mm->total_vm, READ_ONCE(mm->total_vm)+npages);
-
- if (is_exec_mapping(flags))
- mm->exec_vm += npages;
- else if (is_stack_mapping(flags))
- mm->stack_vm += npages;
- else if (is_data_mapping(flags))
- mm->data_vm += npages;
-}
-
-#undef is_exec_mapping
-#undef is_stack_mapping
-#undef is_data_mapping
-
-/* Currently stubbed but we may later wish to un-stub. */
-static inline void vm_acct_memory(long pages);
-static inline void vm_unacct_memory(long pages)
-{
- vm_acct_memory(-pages);
-}
-
-static inline void mapping_allow_writable(struct address_space *mapping)
-{
- atomic_inc(&mapping->i_mmap_writable);
-}
-
-static inline
-struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
-{
- return mas_find(&vmi->mas, max - 1);
-}
-
-static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
- unsigned long start, unsigned long end, gfp_t gfp)
-{
- __mas_set_range(&vmi->mas, start, end - 1);
- mas_store_gfp(&vmi->mas, NULL, gfp);
- if (unlikely(mas_is_err(&vmi->mas)))
- return -ENOMEM;
-
- return 0;
-}
-
-static inline void mmap_assert_locked(struct mm_struct *);
-static inline struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
- unsigned long start_addr,
- unsigned long end_addr)
-{
- unsigned long index = start_addr;
-
- mmap_assert_locked(mm);
- return mt_find(&mm->mm_mt, &index, end_addr - 1);
-}
-
-static inline
-struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
-{
- return mtree_load(&mm->mm_mt, addr);
-}
-
-static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
-{
- return mas_prev(&vmi->mas, 0);
-}
-
-static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
-{
- mas_set(&vmi->mas, addr);
-}
-
-static inline bool vma_is_anonymous(struct vm_area_struct *vma)
-{
- return !vma->vm_ops;
-}
-
-/* Defined in vma.h, so temporarily define here to avoid circular dependency. */
-#define vma_iter_load(vmi) \
- mas_walk(&(vmi)->mas)
-
-static inline struct vm_area_struct *
-find_vma_prev(struct mm_struct *mm, unsigned long addr,
- struct vm_area_struct **pprev)
-{
- struct vm_area_struct *vma;
- VMA_ITERATOR(vmi, mm, addr);
-
- vma = vma_iter_load(&vmi);
- *pprev = vma_prev(&vmi);
- if (!vma)
- vma = vma_next(&vmi);
- return vma;
-}
-
-#undef vma_iter_load
-
-static inline void vma_iter_init(struct vma_iterator *vmi,
- struct mm_struct *mm, unsigned long addr)
-{
- mas_init(&vmi->mas, &mm->mm_mt, addr);
-}
-
-/* Stubbed functions. */
-
-static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
-{
- return NULL;
-}
-
-static inline bool is_mergeable_vm_userfaultfd_ctx(struct vm_area_struct *vma,
- struct vm_userfaultfd_ctx vm_ctx)
-{
- return true;
-}
-
-static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
- struct anon_vma_name *anon_name2)
-{
- return true;
-}
-
-static inline void might_sleep(void)
-{
-}
-
-static inline unsigned long vma_pages(struct vm_area_struct *vma)
-{
- return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
-}
-
-static inline void fput(struct file *file)
-{
-}
-
-static inline void mpol_put(struct mempolicy *pol)
-{
-}
-
-static inline void lru_add_drain(void)
-{
-}
-
-static inline void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
-{
-}
-
-static inline void update_hiwater_rss(struct mm_struct *mm)
-{
-}
-
-static inline void update_hiwater_vm(struct mm_struct *mm)
-{
-}
-
-struct unmap_desc;
-
-static inline void unmap_vmas(struct mmu_gather *tlb, struct unmap_desc *unmap)
-{
-}
-
-static inline void free_pgtables(struct mmu_gather *tlb, struct unmap_desc *desc)
-{
- (void)tlb;
- (void)desc;
-}
-
-static inline void mapping_unmap_writable(struct address_space *mapping)
-{
-}
-
-static inline void flush_dcache_mmap_lock(struct address_space *mapping)
-{
-}
-
-static inline void tlb_finish_mmu(struct mmu_gather *tlb)
-{
-}
-
-static inline struct file *get_file(struct file *f)
-{
- return f;
-}
-
-static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
-{
- return 0;
-}
-
-static inline int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src,
- enum vma_operation operation)
-{
- /* For testing purposes. We indicate that an anon_vma has been cloned. */
- if (src->anon_vma != NULL) {
- dst->anon_vma = src->anon_vma;
- dst->anon_vma->was_cloned = true;
- }
-
- return 0;
-}
-
-static inline void vma_start_write(struct vm_area_struct *vma)
-{
- /* Used to indicate to tests that a write operation has begun. */
- vma->vm_lock_seq++;
-}
-
-static inline __must_check
-int vma_start_write_killable(struct vm_area_struct *vma)
-{
- /* Used to indicate to tests that a write operation has begun. */
- vma->vm_lock_seq++;
- return 0;
-}
-
-static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
- unsigned long start,
- unsigned long end,
- struct vm_area_struct *next)
-{
-}
-
-static inline void hugetlb_split(struct vm_area_struct *, unsigned long) {}
-
-static inline void vma_iter_free(struct vma_iterator *vmi)
-{
- mas_destroy(&vmi->mas);
-}
-
-static inline
-struct vm_area_struct *vma_iter_next_range(struct vma_iterator *vmi)
-{
- return mas_next_range(&vmi->mas, ULONG_MAX);
-}
-
-static inline void vm_acct_memory(long pages)
-{
-}
-
-static inline void vma_interval_tree_insert(struct vm_area_struct *vma,
- struct rb_root_cached *rb)
-{
-}
-
-static inline void vma_interval_tree_remove(struct vm_area_struct *vma,
- struct rb_root_cached *rb)
-{
-}
-
-static inline void flush_dcache_mmap_unlock(struct address_space *mapping)
-{
-}
-
-static inline void anon_vma_interval_tree_insert(struct anon_vma_chain *avc,
- struct rb_root_cached *rb)
-{
-}
-
-static inline void anon_vma_interval_tree_remove(struct anon_vma_chain *avc,
- struct rb_root_cached *rb)
-{
-}
-
-static inline void uprobe_mmap(struct vm_area_struct *vma)
-{
-}
-
-static inline void uprobe_munmap(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
-}
-
-static inline void i_mmap_lock_write(struct address_space *mapping)
-{
-}
-
-static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
-{
-}
-
-static inline void vma_assert_write_locked(struct vm_area_struct *vma)
-{
-}
-
-static inline void unlink_anon_vmas(struct vm_area_struct *vma)
-{
- /* For testing purposes, indicate that the anon_vma was unlinked. */
- vma->anon_vma->was_unlinked = true;
-}
-
-static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
-{
-}
-
-static inline void i_mmap_unlock_write(struct address_space *mapping)
-{
-}
-
-static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
- unsigned long start,
- unsigned long end,
- struct list_head *unmaps)
-{
- return 0;
-}
-
-static inline void mmap_write_downgrade(struct mm_struct *mm)
-{
-}
-
-static inline void mmap_read_unlock(struct mm_struct *mm)
-{
-}
-
-static inline void mmap_write_unlock(struct mm_struct *mm)
-{
-}
-
-static inline int mmap_write_lock_killable(struct mm_struct *mm)
-{
- return 0;
-}
-
-static inline bool can_modify_mm(struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
- return true;
-}
-
-static inline void arch_unmap(struct mm_struct *mm,
- unsigned long start,
- unsigned long end)
-{
-}
-
-static inline void mmap_assert_locked(struct mm_struct *mm)
-{
-}
-
-static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
-{
- return true;
-}
-
-static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
- vm_flags_t vm_flags)
-{
-}
-
-static inline bool mapping_can_writeback(struct address_space *mapping)
-{
- return true;
-}
-
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
-{
- return false;
-}
-
-static inline bool vma_soft_dirty_enabled(struct vm_area_struct *vma)
-{
- return false;
-}
-
-static inline bool userfaultfd_wp(struct vm_area_struct *vma)
-{
- return false;
-}
-
-static inline void mmap_assert_write_locked(struct mm_struct *mm)
-{
-}
-
-static inline void mutex_lock(struct mutex *lock)
-{
-}
-
-static inline void mutex_unlock(struct mutex *lock)
-{
-}
-
-static inline bool mutex_is_locked(struct mutex *lock)
-{
- return true;
-}
-
-static inline bool signal_pending(void *p)
-{
- return false;
-}
-
-static inline bool is_file_hugepages(struct file *file)
-{
- return false;
-}
-
-static inline int security_vm_enough_memory_mm(struct mm_struct *mm, long pages)
-{
- return 0;
-}
-
-static inline bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags,
- unsigned long npages)
-{
- return true;
-}
-
-static inline int shmem_zero_setup(struct vm_area_struct *vma)
-{
- return 0;
-}
-
-static inline void vma_set_anonymous(struct vm_area_struct *vma)
-{
- vma->vm_ops = NULL;
-}
-
-static inline void ksm_add_vma(struct vm_area_struct *vma)
-{
-}
-
-static inline void perf_event_mmap(struct vm_area_struct *vma)
-{
-}
-
-static inline bool vma_is_dax(struct vm_area_struct *vma)
-{
- return false;
-}
-
-static inline struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
-{
- return NULL;
-}
-
-bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
-
-/* Update vma->vm_page_prot to reflect vma->vm_flags. */
-static inline void vma_set_page_prot(struct vm_area_struct *vma)
-{
- vm_flags_t vm_flags = vma->vm_flags;
- pgprot_t vm_page_prot;
-
- /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
- vm_page_prot = pgprot_modify(vma->vm_page_prot, vm_get_page_prot(vm_flags));
-
- if (vma_wants_writenotify(vma, vm_page_prot)) {
- vm_flags &= ~VM_SHARED;
- /* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
- vm_page_prot = pgprot_modify(vm_page_prot, vm_get_page_prot(vm_flags));
- }
- /* remove_protection_ptes reads vma->vm_page_prot without mmap_lock */
- WRITE_ONCE(vma->vm_page_prot, vm_page_prot);
-}
-
-static inline bool arch_validate_flags(vm_flags_t flags)
-{
- return true;
-}
-
-static inline void vma_close(struct vm_area_struct *vma)
-{
-}
-
-static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
-{
- return 0;
-}
-
-static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma)
-{
- if (vma->vm_flags & VM_GROWSDOWN)
- return stack_guard_gap;
-
- /* See reasoning around the VM_SHADOW_STACK definition */
- if (vma->vm_flags & VM_SHADOW_STACK)
- return PAGE_SIZE;
-
- return 0;
-}
-
-static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
-{
- unsigned long gap = stack_guard_start_gap(vma);
- unsigned long vm_start = vma->vm_start;
-
- vm_start -= gap;
- if (vm_start > vma->vm_start)
- vm_start = 0;
- return vm_start;
-}
-
-static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
-{
- unsigned long vm_end = vma->vm_end;
-
- if (vma->vm_flags & VM_GROWSUP) {
- vm_end += stack_guard_gap;
- if (vm_end < vma->vm_end)
- vm_end = -PAGE_SIZE;
- }
- return vm_end;
-}
-
-static inline int is_hugepage_only_range(struct mm_struct *mm,
- unsigned long addr, unsigned long len)
-{
- return 0;
-}
-
-static inline bool vma_is_accessible(struct vm_area_struct *vma)
-{
- return vma->vm_flags & VM_ACCESS_FLAGS;
-}
-
-static inline bool capable(int cap)
-{
- return true;
-}
-
-static inline bool mlock_future_ok(const struct mm_struct *mm,
- vm_flags_t vm_flags, unsigned long bytes)
-{
- unsigned long locked_pages, limit_pages;
-
- if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
- return true;
-
- locked_pages = bytes >> PAGE_SHIFT;
- locked_pages += mm->locked_vm;
-
- limit_pages = rlimit(RLIMIT_MEMLOCK);
- limit_pages >>= PAGE_SHIFT;
-
- return locked_pages <= limit_pages;
-}
-
-static inline int __anon_vma_prepare(struct vm_area_struct *vma)
-{
- struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma));
-
- if (!anon_vma)
- return -ENOMEM;
-
- anon_vma->root = anon_vma;
- vma->anon_vma = anon_vma;
-
- return 0;
-}
-
-static inline int anon_vma_prepare(struct vm_area_struct *vma)
-{
- if (likely(vma->anon_vma))
- return 0;
-
- return __anon_vma_prepare(vma);
-}
-
-static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
- struct list_head *uf)
-{
-}
-
-static inline bool mm_flags_test(int flag, const struct mm_struct *mm)
-{
- return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
-}
-
-/*
- * Copy value to the first system word of VMA flags, non-atomically.
- *
- * IMPORTANT: This does not overwrite bytes past the first system word. The
- * caller must account for this.
- */
-static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value)
-{
- *ACCESS_PRIVATE(flags, __vma_flags) = value;
-}
-
-/*
- * Copy value to the first system word of VMA flags ONCE, non-atomically.
- *
- * IMPORTANT: This does not overwrite bytes past the first system word. The
- * caller must account for this.
- */
-static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
-
- WRITE_ONCE(*bitmap, value);
-}
-
-/* Update the first system word of VMA flags setting bits, non-atomically. */
-static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
-
- *bitmap |= value;
-}
-
-/* Update the first system word of VMA flags clearing bits, non-atomically. */
-static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value)
-{
- unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
-
- *bitmap &= ~value;
-}
-
-
-/* Use when VMA is not part of the VMA tree and needs no locking */
-static inline void vm_flags_init(struct vm_area_struct *vma,
- vm_flags_t flags)
-{
- vma_flags_clear_all(&vma->flags);
- vma_flags_overwrite_word(&vma->flags, flags);
-}
-
-/*
- * Use when VMA is part of the VMA tree and modifications need coordination
- * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
- * it should be locked explicitly beforehand.
- */
-static inline void vm_flags_reset(struct vm_area_struct *vma,
- vm_flags_t flags)
-{
- vma_assert_write_locked(vma);
- vm_flags_init(vma, flags);
-}
-
-static inline void vm_flags_reset_once(struct vm_area_struct *vma,
- vm_flags_t flags)
-{
- vma_assert_write_locked(vma);
- /*
- * The user should only be interested in avoiding reordering of
- * assignment to the first word.
- */
- vma_flags_clear_all(&vma->flags);
- vma_flags_overwrite_word_once(&vma->flags, flags);
-}
-
-static inline void vm_flags_set(struct vm_area_struct *vma,
- vm_flags_t flags)
-{
- vma_start_write(vma);
- vma_flags_set_word(&vma->flags, flags);
-}
-
-static inline void vm_flags_clear(struct vm_area_struct *vma,
- vm_flags_t flags)
-{
- vma_start_write(vma);
- vma_flags_clear_word(&vma->flags, flags);
-}
-
-/*
- * Denies creating a writable executable mapping or gaining executable permissions.
- *
- * This denies the following:
- *
- * a) mmap(PROT_WRITE | PROT_EXEC)
- *
- * b) mmap(PROT_WRITE)
- * mprotect(PROT_EXEC)
- *
- * c) mmap(PROT_WRITE)
- * mprotect(PROT_READ)
- * mprotect(PROT_EXEC)
- *
- * But allows the following:
- *
- * d) mmap(PROT_READ | PROT_EXEC)
- * mmap(PROT_READ | PROT_EXEC | PROT_BTI)
- *
- * This is only applicable if the user has set the Memory-Deny-Write-Execute
- * (MDWE) protection mask for the current process.
- *
- * @old specifies the VMA flags the VMA originally possessed, and @new the ones
- * we propose to set.
- *
- * Return: false if proposed change is OK, true if not ok and should be denied.
- */
-static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
-{
- /* If MDWE is disabled, we have nothing to deny. */
- if (mm_flags_test(MMF_HAS_MDWE, current->mm))
- return false;
-
- /* If the new VMA is not executable, we have nothing to deny. */
- if (!(new & VM_EXEC))
- return false;
-
- /* Under MDWE we do not accept newly writably executable VMAs... */
- if (new & VM_WRITE)
- return true;
-
- /* ...nor previously non-executable VMAs becoming executable. */
- if (!(old & VM_EXEC))
- return true;
-
- return false;
-}
-
-static inline int mapping_map_writable(struct address_space *mapping)
-{
- return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
- 0 : -EPERM;
-}
-
-static inline unsigned long move_page_tables(struct pagetable_move_control *pmc)
-{
- return 0;
-}
-
-static inline void free_pgd_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end,
- unsigned long floor, unsigned long ceiling)
-{
-}
-
-static inline int ksm_execve(struct mm_struct *mm)
-{
- return 0;
-}
-
-static inline void ksm_exit(struct mm_struct *mm)
-{
-}
-
-static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
-{
- if (reset_refcnt)
- refcount_set(&vma->vm_refcnt, 0);
-}
-
-static inline void vma_numab_state_init(struct vm_area_struct *vma)
-{
-}
-
-static inline void vma_numab_state_free(struct vm_area_struct *vma)
-{
-}
-
-static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
- struct vm_area_struct *new_vma)
-{
-}
-
-static inline void free_anon_vma_name(struct vm_area_struct *vma)
-{
-}
-
-/* Declared in vma.h. */
-static inline void set_vma_from_desc(struct vm_area_struct *vma,
- struct vm_area_desc *desc);
-
-static inline void mmap_action_prepare(struct mmap_action *action,
- struct vm_area_desc *desc)
-{
-}
-
-static inline int mmap_action_complete(struct mmap_action *action,
- struct vm_area_struct *vma)
-{
- return 0;
-}
-
-static inline int __compat_vma_mmap(const struct file_operations *f_op,
- struct file *file, struct vm_area_struct *vma)
-{
- struct vm_area_desc desc = {
- .mm = vma->vm_mm,
- .file = file,
- .start = vma->vm_start,
- .end = vma->vm_end,
-
- .pgoff = vma->vm_pgoff,
- .vm_file = vma->vm_file,
- .vm_flags = vma->vm_flags,
- .page_prot = vma->vm_page_prot,
-
- .action.type = MMAP_NOTHING, /* Default */
- };
- int err;
-
- err = f_op->mmap_prepare(&desc);
- if (err)
- return err;
-
- mmap_action_prepare(&desc.action, &desc);
- set_vma_from_desc(vma, &desc);
- return mmap_action_complete(&desc.action, vma);
-}
-
-static inline int compat_vma_mmap(struct file *file,
- struct vm_area_struct *vma)
-{
- return __compat_vma_mmap(file->f_op, file, vma);
-}
-
-/* Did the driver provide valid mmap hook configuration? */
-static inline bool can_mmap_file(struct file *file)
-{
- bool has_mmap = file->f_op->mmap;
- bool has_mmap_prepare = file->f_op->mmap_prepare;
-
- /* Hooks are mutually exclusive. */
- if (WARN_ON_ONCE(has_mmap && has_mmap_prepare))
- return false;
- if (!has_mmap && !has_mmap_prepare)
- return false;
-
- return true;
-}
-
-static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
-{
- if (file->f_op->mmap_prepare)
- return compat_vma_mmap(file, vma);
-
- return file->f_op->mmap(file, vma);
-}
-
-static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
-{
- return file->f_op->mmap_prepare(desc);
-}
-
-static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
-{
-}
-
-static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
-{
- /* Changing an anonymous vma with this is illegal */
- get_file(file);
- swap(vma->vm_file, file);
- fput(file);
-}
-
-static inline bool shmem_file(struct file *file)
-{
- return false;
-}
-
-static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm,
- const struct file *file, vm_flags_t vm_flags)
-{
- return vm_flags;
-}
-
-static inline void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn)
-{
-}
-
-static inline int remap_pfn_range_complete(struct vm_area_struct *vma, unsigned long addr,
- unsigned long pfn, unsigned long size, pgprot_t pgprot)
-{
- return 0;
-}
+typedef unsigned long vm_flags_t;
+#define pgoff_t unsigned long
+typedef unsigned long pgprotval_t;
+typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
+typedef __bitwise unsigned int vm_fault_t;
-static inline int do_munmap(struct mm_struct *, unsigned long, size_t,
- struct list_head *uf)
-{
- return 0;
-}
+#include "include/stubs.h"
+#include "include/dup.h"
+#include "include/custom.h"
#endif /* __MM_VMA_INTERNAL_H */
--
2.52.0
^ permalink raw reply related
* [PATCH RESEND 12/12] tools/testing/vma: add VMA userland tests for VMA flag functions
From: Lorenzo Stoakes @ 2026-01-19 21:19 UTC (permalink / raw)
To: Andrew Morton
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
Now we have the capability to test the new helpers for the bitmap VMA flags
in userland, do so.
We also update the Makefile such that both VMA (and while we're here)
mm_struct flag sizes can be customised on build. We default to 128-bit to
enable testing of flags above word size even on 64-bit systems.
We add userland tests to ensure that we do not regress VMA flag behaviour
with the introduction when using bitmap VMA flags, nor accidentally
introduce unexpected results due to for instance higher bit values not
being correctly cleared/set.
As part of this change, make __mk_vma_flags() a custom function so we can
handle specifying invalid VMA bits. This is purposeful so we can have the
VMA tests work at lower and higher number of VMA flags without having to
duplicate code too much.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
tools/testing/vma/Makefile | 3 +
tools/testing/vma/include/custom.h | 16 ++
tools/testing/vma/include/dup.h | 11 +-
tools/testing/vma/tests/vma.c | 300 +++++++++++++++++++++++++++++
tools/testing/vma/vma_internal.h | 4 +-
5 files changed, 322 insertions(+), 12 deletions(-)
diff --git a/tools/testing/vma/Makefile b/tools/testing/vma/Makefile
index 50aa4301b3a6..e72b45dedda5 100644
--- a/tools/testing/vma/Makefile
+++ b/tools/testing/vma/Makefile
@@ -9,6 +9,9 @@ include ../shared/shared.mk
OFILES = $(SHARED_OFILES) main.o shared.o maple-shim.o
TARGETS = vma
+# These can be varied to test different sizes.
+CFLAGS += -DNUM_VMA_FLAG_BITS=128 -DNUM_MM_FLAG_BITS=128
+
main.o: main.c shared.c shared.h vma_internal.h tests/merge.c tests/mmap.c tests/vma.c ../../../mm/vma.c ../../../mm/vma_init.c ../../../mm/vma_exec.c ../../../mm/vma.h include/custom.h include/dup.h include/stubs.h
vma: $(OFILES)
diff --git a/tools/testing/vma/include/custom.h b/tools/testing/vma/include/custom.h
index f567127efba9..802a76317245 100644
--- a/tools/testing/vma/include/custom.h
+++ b/tools/testing/vma/include/custom.h
@@ -101,3 +101,19 @@ static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
if (reset_refcnt)
refcount_set(&vma->vm_refcnt, 0);
}
+
+static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits)
+{
+ vma_flags_t flags;
+ int i;
+
+ /*
+ * For testing purposes: allow invalid bit specification so we can
+ * easily test.
+ */
+ vma_flags_clear_all(&flags);
+ for (i = 0; i < count; i++)
+ if (bits[i] < NUM_VMA_FLAG_BITS)
+ vma_flag_set(&flags, bits[i]);
+ return flags;
+}
diff --git a/tools/testing/vma/include/dup.h b/tools/testing/vma/include/dup.h
index 3eeef4173e5b..f075a433b058 100644
--- a/tools/testing/vma/include/dup.h
+++ b/tools/testing/vma/include/dup.h
@@ -838,16 +838,7 @@ static inline void vm_flags_clear(struct vm_area_struct *vma,
vma_flags_clear_word(&vma->flags, flags);
}
-static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits)
-{
- vma_flags_t flags;
- int i;
-
- vma_flags_clear_all(&flags);
- for (i = 0; i < count; i++)
- vma_flag_set(&flags, bits[i]);
- return flags;
-}
+static inline vma_flags_t __mk_vma_flags(size_t count, const vma_flag_t *bits);
#define mk_vma_flags(...) __mk_vma_flags(COUNT_ARGS(__VA_ARGS__), \
(const vma_flag_t []){__VA_ARGS__})
diff --git a/tools/testing/vma/tests/vma.c b/tools/testing/vma/tests/vma.c
index 6d9775aee243..c47eeeb9d80c 100644
--- a/tools/testing/vma/tests/vma.c
+++ b/tools/testing/vma/tests/vma.c
@@ -1,5 +1,25 @@
// SPDX-License-Identifier: GPL-2.0-or-later
+static bool compare_legacy_flags(vm_flags_t legacy_flags, vma_flags_t flags)
+{
+ const unsigned long legacy_val = legacy_flags;
+ /* The lower word should contain the precise same value. */
+ const unsigned long flags_lower = flags.__vma_flags[0];
+#if NUM_VMA_FLAGS > BITS_PER_LONG
+ int i;
+
+ /* All bits in higher flag values should be zero. */
+ for (i = 1; i < NUM_VMA_FLAGS / BITS_PER_LONG; i++) {
+ if (flags.__vma_flags[i] != 0)
+ return false;
+ }
+#endif
+
+ static_assert(sizeof(legacy_flags) == sizeof(unsigned long));
+
+ return legacy_val == flags_lower;
+}
+
static bool test_copy_vma(void)
{
vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
@@ -33,7 +53,287 @@ static bool test_copy_vma(void)
return true;
}
+static bool test_vma_flags_unchanged(void)
+{
+ vma_flags_t flags = EMPTY_VMA_FLAGS;
+ vm_flags_t legacy_flags = 0;
+ int bit;
+ struct vm_area_struct vma;
+ struct vm_area_desc desc;
+
+
+ vma.flags = EMPTY_VMA_FLAGS;
+ desc.vma_flags = EMPTY_VMA_FLAGS;
+
+ for (bit = 0; bit < BITS_PER_LONG; bit++) {
+ vma_flags_t mask = mk_vma_flags(bit);
+
+ legacy_flags |= (1UL << bit);
+
+ /* Individual flags. */
+ vma_flags_set(&flags, bit);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, flags));
+
+ /* Via mask. */
+ vma_flags_set_mask(&flags, mask);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, flags));
+
+ /* Same for VMA. */
+ vma_set_flags(&vma, bit);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, vma.flags));
+ vma_set_flags_mask(&vma, mask);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, vma.flags));
+
+ /* Same for VMA descriptor. */
+ vma_desc_set_flags(&desc, bit);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, desc.vma_flags));
+ vma_desc_set_flags_mask(&desc, mask);
+ ASSERT_TRUE(compare_legacy_flags(legacy_flags, desc.vma_flags));
+ }
+
+ return true;
+}
+
+static bool test_vma_flags_cleared(void)
+{
+ const vma_flags_t empty = EMPTY_VMA_FLAGS;
+ vma_flags_t flags;
+ int i;
+
+ /* Set all bits high. */
+ memset(&flags, 1, sizeof(flags));
+ /* Try to clear. */
+ vma_flags_clear_all(&flags);
+ /* Equal to EMPTY_VMA_FLAGS? */
+ ASSERT_EQ(memcmp(&empty, &flags, sizeof(flags)), 0);
+ /* Make sure every unsigned long entry in bitmap array zero. */
+ for (i = 0; i < sizeof(flags) / BITS_PER_LONG; i++) {
+ const unsigned long val = flags.__vma_flags[i];
+
+ ASSERT_EQ(val, 0);
+ }
+
+ return true;
+}
+
+/*
+ * Assert that VMA flag functions that operate at the system word level function
+ * correctly.
+ */
+static bool test_vma_flags_word(void)
+{
+ vma_flags_t flags = EMPTY_VMA_FLAGS;
+ const vma_flags_t comparison =
+ mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT, 64, 65);
+
+ /* Set some custom high flags. */
+ vma_flags_set(&flags, 64, 65);
+ /* Now overwrite the first word. */
+ vma_flags_overwrite_word(&flags, VM_READ | VM_WRITE);
+ /* Ensure they are equal. */
+ ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0);
+
+ flags = EMPTY_VMA_FLAGS;
+ vma_flags_set(&flags, 64, 65);
+
+ /* Do the same with the _once() equivalent. */
+ vma_flags_overwrite_word_once(&flags, VM_READ | VM_WRITE);
+ ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0);
+
+ flags = EMPTY_VMA_FLAGS;
+ vma_flags_set(&flags, 64, 65);
+
+ /* Make sure we can set a word without disturbing other bits. */
+ vma_flags_set(&flags, VMA_WRITE_BIT);
+ vma_flags_set_word(&flags, VM_READ);
+ ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0);
+
+ flags = EMPTY_VMA_FLAGS;
+ vma_flags_set(&flags, 64, 65);
+
+ /* Make sure we can clear a word without disturbing other bits. */
+ vma_flags_set(&flags, VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT);
+ vma_flags_clear_word(&flags, VM_EXEC);
+ ASSERT_EQ(memcmp(&flags, &comparison, sizeof(flags)), 0);
+
+ return true;
+}
+
+/* Ensure that vma_flags_test() and friends works correctly. */
+static bool test_vma_flags_test(void)
+{
+ const vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT,
+ VMA_EXEC_BIT, 64, 65);
+ struct vm_area_struct vma;
+ struct vm_area_desc desc;
+
+ vma.flags = flags;
+ desc.vma_flags = flags;
+
+#define do_test(...) \
+ ASSERT_TRUE(vma_flags_test(flags, __VA_ARGS__)); \
+ ASSERT_TRUE(vma_desc_test_flags(&desc, __VA_ARGS__))
+
+#define do_test_all_true(...) \
+ ASSERT_TRUE(vma_flags_test_all(flags, __VA_ARGS__)); \
+ ASSERT_TRUE(vma_test_all_flags(&vma, __VA_ARGS__))
+
+#define do_test_all_false(...) \
+ ASSERT_FALSE(vma_flags_test_all(flags, __VA_ARGS__)); \
+ ASSERT_FALSE(vma_test_all_flags(&vma, __VA_ARGS__))
+
+ /*
+ * Testing for some flags that are present, some that are not - should
+ * pass. ANY flags matching should work.
+ */
+ do_test(VMA_READ_BIT, VMA_MAYREAD_BIT, VMA_SEQ_READ_BIT);
+ /* However, the ...test_all() variant should NOT pass. */
+ do_test_all_false(VMA_READ_BIT, VMA_MAYREAD_BIT, VMA_SEQ_READ_BIT);
+ /* But should pass for flags present. */
+ do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64, 65);
+ /* Also subsets... */
+ do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64);
+ do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT);
+ do_test_all_true(VMA_READ_BIT, VMA_WRITE_BIT);
+ do_test_all_true(VMA_READ_BIT);
+ /*
+ * Check _mask variant. We don't need to test extensively as macro
+ * helper is the equivalent.
+ */
+ ASSERT_TRUE(vma_flags_test_mask(flags, flags));
+ ASSERT_TRUE(vma_flags_test_all_mask(flags, flags));
+
+ /* Single bits. */
+ do_test(VMA_READ_BIT);
+ do_test(VMA_WRITE_BIT);
+ do_test(VMA_EXEC_BIT);
+#if NUM_VMA_FLAG_BITS > 64
+ do_test(64);
+ do_test(65);
+#endif
+
+ /* Two bits. */
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT);
+ do_test(VMA_READ_BIT, VMA_EXEC_BIT);
+ do_test(VMA_WRITE_BIT, VMA_EXEC_BIT);
+ /* Ordering shouldn't matter. */
+ do_test(VMA_WRITE_BIT, VMA_READ_BIT);
+ do_test(VMA_EXEC_BIT, VMA_READ_BIT);
+ do_test(VMA_EXEC_BIT, VMA_WRITE_BIT);
+#if NUM_VMA_FLAG_BITS > 64
+ do_test(VMA_READ_BIT, 64);
+ do_test(VMA_WRITE_BIT, 64);
+ do_test(64, VMA_READ_BIT);
+ do_test(64, VMA_WRITE_BIT);
+ do_test(VMA_READ_BIT, 65);
+ do_test(VMA_WRITE_BIT, 65);
+ do_test(65, VMA_READ_BIT);
+ do_test(65, VMA_WRITE_BIT);
+#endif
+ /* Three bits. */
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT);
+#if NUM_VMA_FLAG_BITS > 64
+ /* No need to consider every single permutation. */
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, 64);
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, 65);
+
+ /* Four bits. */
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64);
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 65);
+
+ /* Five bits. */
+ do_test(VMA_READ_BIT, VMA_WRITE_BIT, VMA_EXEC_BIT, 64, 65);
+#endif
+
+#undef do_test
+#undef do_test_all_true
+#undef do_test_all_false
+
+ return true;
+}
+
+/* Ensure that vma_flags_clear() and friends works correctly. */
+static bool test_vma_flags_clear(void)
+{
+ vma_flags_t flags = mk_vma_flags(VMA_READ_BIT, VMA_WRITE_BIT,
+ VMA_EXEC_BIT, 64, 65);
+ vma_flags_t mask = mk_vma_flags(VMA_EXEC_BIT, 64);
+ struct vm_area_struct vma;
+ struct vm_area_desc desc;
+
+ vma.flags = flags;
+ desc.vma_flags = flags;
+
+ /* Cursory check of _mask() variant, as the helper macros imply. */
+ vma_flags_clear_mask(&flags, mask);
+ vma_flags_clear_mask(&vma.flags, mask);
+ vma_desc_clear_flags_mask(&desc, mask);
+ ASSERT_FALSE(vma_flags_test(flags, VMA_EXEC_BIT, 64));
+ ASSERT_FALSE(vma_flags_test(vma.flags, VMA_EXEC_BIT, 64));
+ ASSERT_FALSE(vma_desc_test_flags(&desc, VMA_EXEC_BIT, 64));
+ /* Reset. */
+ vma_flags_set(&flags, VMA_EXEC_BIT, 64);
+ vma_set_flags(&vma, VMA_EXEC_BIT, 64);
+ vma_desc_set_flags(&desc, VMA_EXEC_BIT, 64);
+
+ /*
+ * Clear the flags and assert clear worked, then reset flags back to
+ * include specified flags.
+ */
+#define do_test_and_reset(...) \
+ vma_flags_clear(&flags, __VA_ARGS__); \
+ vma_flags_clear(&vma.flags, __VA_ARGS__); \
+ vma_desc_clear_flags(&desc, __VA_ARGS__); \
+ ASSERT_FALSE(vma_flags_test(flags, __VA_ARGS__)); \
+ ASSERT_FALSE(vma_flags_test(vma.flags, __VA_ARGS__)); \
+ ASSERT_FALSE(vma_desc_test_flags(&desc, __VA_ARGS__)); \
+ vma_flags_set(&flags, __VA_ARGS__); \
+ vma_set_flags(&vma, __VA_ARGS__); \
+ vma_desc_set_flags(&desc, __VA_ARGS__)
+
+ /* Single flags. */
+ do_test_and_reset(VMA_READ_BIT);
+ do_test_and_reset(VMA_WRITE_BIT);
+ do_test_and_reset(VMA_EXEC_BIT);
+ do_test_and_reset(64);
+ do_test_and_reset(65);
+
+ /* Two flags, in different orders. */
+ do_test_and_reset(VMA_READ_BIT, VMA_WRITE_BIT);
+ do_test_and_reset(VMA_READ_BIT, VMA_EXEC_BIT);
+ do_test_and_reset(VMA_READ_BIT, 64);
+ do_test_and_reset(VMA_READ_BIT, 65);
+ do_test_and_reset(VMA_WRITE_BIT, VMA_READ_BIT);
+ do_test_and_reset(VMA_WRITE_BIT, VMA_EXEC_BIT);
+ do_test_and_reset(VMA_WRITE_BIT, 64);
+ do_test_and_reset(VMA_WRITE_BIT, 65);
+ do_test_and_reset(VMA_EXEC_BIT, VMA_READ_BIT);
+ do_test_and_reset(VMA_EXEC_BIT, VMA_WRITE_BIT);
+ do_test_and_reset(VMA_EXEC_BIT, 64);
+ do_test_and_reset(VMA_EXEC_BIT, 65);
+ do_test_and_reset(64, VMA_READ_BIT);
+ do_test_and_reset(64, VMA_WRITE_BIT);
+ do_test_and_reset(64, VMA_EXEC_BIT);
+ do_test_and_reset(64, 65);
+ do_test_and_reset(65, VMA_READ_BIT);
+ do_test_and_reset(65, VMA_WRITE_BIT);
+ do_test_and_reset(65, VMA_EXEC_BIT);
+ do_test_and_reset(65, 64);
+
+ /* Three flags. */
+
+#undef do_test_some_missing
+#undef do_test_and_reset
+
+ return true;
+}
+
static void run_vma_tests(int *num_tests, int *num_fail)
{
TEST(copy_vma);
+ TEST(vma_flags_unchanged);
+ TEST(vma_flags_cleared);
+ TEST(vma_flags_word);
+ TEST(vma_flags_test);
+ TEST(vma_flags_clear);
}
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index e3ed05b57819..0e1121e2ef23 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -36,11 +36,11 @@
* ahead of all other headers.
*/
#define __private
-#define NUM_MM_FLAG_BITS (64)
+/* NUM_MM_FLAG_BITS defined by test code. */
typedef struct {
__private DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS);
} mm_flags_t;
-#define NUM_VMA_FLAG_BITS BITS_PER_LONG
+/* NUM_VMA_FLAG_BITS defined by test code. */
typedef struct {
DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS);
} __private vma_flags_t;
--
2.52.0
^ permalink raw reply related
* [PATCH RESEND 09/12] mm: make vm_area_desc utilise vma_flags_t only
From: Lorenzo Stoakes @ 2026-01-19 21:19 UTC (permalink / raw)
To: Andrew Morton
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
Now we have eliminated all uses of vm_area_desc->vm_flags, eliminate this
field, and have mmap_prepare users utilise the vma_flags_t
vm_area_desc->vma_flags field only.
As part of this change we alter is_shared_maywrite() to accept a
vma_flags_t parameter, and introduce is_shared_maywrite_vm_flags() for use
with legacy vm_flags_t flags.
We also update struct mmap_state to add a union between vma_flags and
vm_flags temporarily until the mmap logic is also converted to using
vma_flags_t.
Also update the VMA userland tests to reflect this change.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
include/linux/mm.h | 9 +++++++--
include/linux/mm_types.h | 5 +----
mm/filemap.c | 2 +-
mm/util.c | 2 +-
mm/vma.c | 11 +++++++----
mm/vma.h | 3 +--
tools/testing/vma/vma_internal.h | 9 +++++++--
7 files changed, 25 insertions(+), 16 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 32f48d5a28ce..407fcdc4831d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1293,15 +1293,20 @@ static inline bool vma_is_accessible(const struct vm_area_struct *vma)
return vma->vm_flags & VM_ACCESS_FLAGS;
}
-static inline bool is_shared_maywrite(vm_flags_t vm_flags)
+static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags)
{
return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
(VM_SHARED | VM_MAYWRITE);
}
+static inline bool is_shared_maywrite(vma_flags_t flags)
+{
+ return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT);
+}
+
static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma)
{
- return is_shared_maywrite(vma->vm_flags);
+ return is_shared_maywrite(vma->flags);
}
static inline
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index c3589bc3780e..5042374d854b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -877,10 +877,7 @@ struct vm_area_desc {
/* Mutable fields. Populated with initial state. */
pgoff_t pgoff;
struct file *vm_file;
- union {
- vm_flags_t vm_flags;
- vma_flags_t vma_flags;
- };
+ vma_flags_t vma_flags;
pgprot_t page_prot;
/* Write-only fields. */
diff --git a/mm/filemap.c b/mm/filemap.c
index ebd75684cb0a..109a4bf07366 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -4012,7 +4012,7 @@ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc)
{
- if (is_shared_maywrite(desc->vm_flags))
+ if (is_shared_maywrite(desc->vma_flags))
return -EINVAL;
return generic_file_mmap_prepare(desc);
}
diff --git a/mm/util.c b/mm/util.c
index 97cae40c0209..b05ab6f97e11 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1154,7 +1154,7 @@ int __compat_vma_mmap(const struct file_operations *f_op,
.pgoff = vma->vm_pgoff,
.vm_file = vma->vm_file,
- .vm_flags = vma->vm_flags,
+ .vma_flags = vma->flags,
.page_prot = vma->vm_page_prot,
.action.type = MMAP_NOTHING, /* Default */
diff --git a/mm/vma.c b/mm/vma.c
index 39dcd9ddd4ba..be64f781a3aa 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -15,7 +15,10 @@ struct mmap_state {
unsigned long end;
pgoff_t pgoff;
unsigned long pglen;
- vm_flags_t vm_flags;
+ union {
+ vm_flags_t vm_flags;
+ vma_flags_t vma_flags;
+ };
struct file *file;
pgprot_t page_prot;
@@ -2369,7 +2372,7 @@ static void set_desc_from_map(struct vm_area_desc *desc,
desc->pgoff = map->pgoff;
desc->vm_file = map->file;
- desc->vm_flags = map->vm_flags;
+ desc->vma_flags = map->vma_flags;
desc->page_prot = map->page_prot;
}
@@ -2650,7 +2653,7 @@ static int call_mmap_prepare(struct mmap_state *map,
map->file_doesnt_need_get = true;
map->file = desc->vm_file;
}
- map->vm_flags = desc->vm_flags;
+ map->vma_flags = desc->vma_flags;
map->page_prot = desc->page_prot;
/* User-defined fields. */
map->vm_ops = desc->vm_ops;
@@ -2823,7 +2826,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
return -EINVAL;
/* Map writable and ensure this isn't a sealed memfd. */
- if (file && is_shared_maywrite(vm_flags)) {
+ if (file && is_shared_maywrite_vm_flags(vm_flags)) {
int error = mapping_map_writable(file->f_mapping);
if (error)
diff --git a/mm/vma.h b/mm/vma.h
index bb7fa5d2bde2..062672df8a65 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -286,8 +286,7 @@ static inline void set_vma_from_desc(struct vm_area_struct *vma,
vma->vm_pgoff = desc->pgoff;
if (desc->vm_file != vma->vm_file)
vma_set_file(vma, desc->vm_file);
- if (desc->vm_flags != vma->vm_flags)
- vm_flags_set(vma, desc->vm_flags);
+ vma->flags = desc->vma_flags;
vma->vm_page_prot = desc->page_prot;
/* User-defined fields. */
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 1ac81a09feb8..8143b95dc50e 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1009,15 +1009,20 @@ static inline void vma_desc_clear_flags_mask(struct vm_area_desc *desc,
#define vma_desc_clear_flags(desc, ...) \
vma_desc_clear_flags_mask(desc, mk_vma_flags(__VA_ARGS__))
-static inline bool is_shared_maywrite(vm_flags_t vm_flags)
+static inline bool is_shared_maywrite_vm_flags(vm_flags_t vm_flags)
{
return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
(VM_SHARED | VM_MAYWRITE);
}
+static inline bool is_shared_maywrite(vma_flags_t flags)
+{
+ return vma_flags_test_all(flags, VMA_SHARED_BIT, VMA_MAYWRITE_BIT);
+}
+
static inline bool vma_is_shared_maywrite(struct vm_area_struct *vma)
{
- return is_shared_maywrite(vma->vm_flags);
+ return is_shared_maywrite(vma->flags);
}
static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi)
--
2.52.0
^ permalink raw reply related
* [PATCH RESEND 08/12] mm: update all remaining mmap_prepare users to use vma_flags_t
From: Lorenzo Stoakes @ 2026-01-19 21:19 UTC (permalink / raw)
To: Andrew Morton
Cc: Jarkko Sakkinen, Dave Hansen, Thomas Gleixner, Ingo Molnar,
Borislav Petkov, x86, H . Peter Anvin, Arnd Bergmann,
Greg Kroah-Hartman, Dan Williams, Vishal Verma, Dave Jiang,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Christian Koenig, Huang Rui, Matthew Auld,
Matthew Brost, Alexander Viro, Christian Brauner, Jan Kara,
Benjamin LaHaise, Gao Xiang, Chao Yu, Yue Hu, Jeffle Xu,
Sandeep Dhavale, Hongbo Li, Chunhai Guo, Theodore Ts'o,
Andreas Dilger, Muchun Song, Oscar Salvador, David Hildenbrand,
Konstantin Komarov, Mike Marshall, Martin Brandenburg, Tony Luck,
Reinette Chatre, Dave Martin, James Morse, Babu Moger,
Carlos Maiolino, Damien Le Moal, Naohiro Aota, Johannes Thumshirn,
Matthew Wilcox, Liam R . Howlett, Vlastimil Babka, Mike Rapoport,
Suren Baghdasaryan, Michal Hocko, Hugh Dickins, Baolin Wang,
Zi Yan, Nico Pache, Ryan Roberts, Dev Jain, Barry Song,
Lance Yang, Jann Horn, Pedro Falcato, David Howells, Paul Moore,
James Morris, Serge E . Hallyn, Yury Norov, Rasmus Villemoes,
linux-sgx, linux-kernel, nvdimm, linux-cxl, dri-devel, intel-gfx,
linux-fsdevel, linux-aio, linux-erofs, linux-ext4, linux-mm,
ntfs3, devel, linux-xfs, keyrings, linux-security-module,
Jason Gunthorpe
In-Reply-To: <cover.1768857200.git.lorenzo.stoakes@oracle.com>
We will be shortly removing the vm_flags_t field from vm_area_desc so we
need to update all mmap_prepare users to only use the dessc->vma_flags
field.
This patch achieves that and makes all ancillary changes required to make
this possible.
This lays the groundwork for future work to eliminate the use of vm_flags_t
in vm_area_desc altogether and more broadly throughout the kernel.
While we're here, we take the opportunity to replace VM_REMAP_FLAGS with
VMA_REMAP_FLAGS, the vma_flags_t equivalent.
No functional changes intended.
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
drivers/char/mem.c | 6 +++---
drivers/dax/device.c | 10 +++++-----
fs/aio.c | 2 +-
fs/erofs/data.c | 5 +++--
fs/ext4/file.c | 4 ++--
fs/ntfs3/file.c | 2 +-
fs/orangefs/file.c | 4 ++--
fs/ramfs/file-nommu.c | 2 +-
fs/resctrl/pseudo_lock.c | 2 +-
fs/romfs/mmap-nommu.c | 2 +-
fs/xfs/xfs_file.c | 4 ++--
fs/zonefs/file.c | 3 ++-
include/linux/dax.h | 4 ++--
include/linux/mm.h | 24 +++++++++++++++++++-----
kernel/relay.c | 2 +-
mm/memory.c | 17 ++++++++---------
16 files changed, 54 insertions(+), 39 deletions(-)
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 52039fae1594..702d9595a563 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -306,7 +306,7 @@ static unsigned zero_mmap_capabilities(struct file *file)
/* can't do an in-place private mapping if there's no MMU */
static inline int private_mapping_ok(struct vm_area_desc *desc)
{
- return is_nommu_shared_mapping(desc->vm_flags);
+ return is_nommu_shared_vma_flags(desc->vma_flags);
}
#else
@@ -360,7 +360,7 @@ static int mmap_mem_prepare(struct vm_area_desc *desc)
desc->vm_ops = &mmap_mem_ops;
- /* Remap-pfn-range will mark the range VM_IO. */
+ /* Remap-pfn-range will mark the range with the I/O flag. */
mmap_action_remap_full(desc, desc->pgoff);
/* We filter remap errors to -EAGAIN. */
desc->action.error_hook = mmap_filter_error;
@@ -520,7 +520,7 @@ static int mmap_zero_prepare(struct vm_area_desc *desc)
#ifndef CONFIG_MMU
return -ENOSYS;
#endif
- if (desc->vm_flags & VM_SHARED)
+ if (vma_desc_test_flags(desc, VMA_SHARED_BIT))
return shmem_zero_setup_desc(desc);
desc->action.success_hook = mmap_zero_private_success;
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 22999a402e02..4b2970d6bbee 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -13,7 +13,7 @@
#include "dax-private.h"
#include "bus.h"
-static int __check_vma(struct dev_dax *dev_dax, vm_flags_t vm_flags,
+static int __check_vma(struct dev_dax *dev_dax, vma_flags_t flags,
unsigned long start, unsigned long end, struct file *file,
const char *func)
{
@@ -24,7 +24,7 @@ static int __check_vma(struct dev_dax *dev_dax, vm_flags_t vm_flags,
return -ENXIO;
/* prevent private mappings from being established */
- if ((vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
+ if (!vma_flags_test(flags, VMA_MAYSHARE_BIT)) {
dev_info_ratelimited(dev,
"%s: %s: fail, attempted private mapping\n",
current->comm, func);
@@ -53,7 +53,7 @@ static int __check_vma(struct dev_dax *dev_dax, vm_flags_t vm_flags,
static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
const char *func)
{
- return __check_vma(dev_dax, vma->vm_flags, vma->vm_start, vma->vm_end,
+ return __check_vma(dev_dax, vma->flags, vma->vm_start, vma->vm_end,
vma->vm_file, func);
}
@@ -306,14 +306,14 @@ static int dax_mmap_prepare(struct vm_area_desc *desc)
* fault time.
*/
id = dax_read_lock();
- rc = __check_vma(dev_dax, desc->vm_flags, desc->start, desc->end, filp,
+ rc = __check_vma(dev_dax, desc->vma_flags, desc->start, desc->end, filp,
__func__);
dax_read_unlock(id);
if (rc)
return rc;
desc->vm_ops = &dax_vm_ops;
- desc->vm_flags |= VM_HUGEPAGE;
+ vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
return 0;
}
diff --git a/fs/aio.c b/fs/aio.c
index 0a23a8c0717f..59b67b8da1b2 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -394,7 +394,7 @@ static const struct vm_operations_struct aio_ring_vm_ops = {
static int aio_ring_mmap_prepare(struct vm_area_desc *desc)
{
- desc->vm_flags |= VM_DONTEXPAND;
+ vma_desc_set_flags(desc, VMA_DONTEXPAND_BIT);
desc->vm_ops = &aio_ring_vm_ops;
return 0;
}
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index bb13c4cb8455..e7bc29e764c6 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -438,11 +438,12 @@ static int erofs_file_mmap_prepare(struct vm_area_desc *desc)
if (!IS_DAX(file_inode(desc->file)))
return generic_file_readonly_mmap_prepare(desc);
- if ((desc->vm_flags & VM_SHARED) && (desc->vm_flags & VM_MAYWRITE))
+ if (vma_desc_test_flags(desc, VMA_SHARED_BIT) &&
+ vma_desc_test_flags(desc, VMA_MAYWRITE_BIT))
return -EINVAL;
desc->vm_ops = &erofs_dax_vm_ops;
- desc->vm_flags |= VM_HUGEPAGE;
+ vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
return 0;
}
#else
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 7a8b30932189..da3c208e72d1 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -822,13 +822,13 @@ static int ext4_file_mmap_prepare(struct vm_area_desc *desc)
* We don't support synchronous mappings for non-DAX files and
* for DAX files if underneath dax_device is not synchronous.
*/
- if (!daxdev_mapping_supported(desc->vm_flags, file_inode(file), dax_dev))
+ if (!daxdev_mapping_supported(desc->vma_flags, file_inode(file), dax_dev))
return -EOPNOTSUPP;
file_accessed(file);
if (IS_DAX(file_inode(file))) {
desc->vm_ops = &ext4_dax_vm_ops;
- desc->vm_flags |= VM_HUGEPAGE;
+ vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
} else {
desc->vm_ops = &ext4_file_vm_ops;
}
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 2e7b2e566ebe..2902fc6d9a85 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -347,7 +347,7 @@ static int ntfs_file_mmap_prepare(struct vm_area_desc *desc)
struct inode *inode = file_inode(file);
struct ntfs_inode *ni = ntfs_i(inode);
u64 from = ((u64)desc->pgoff << PAGE_SHIFT);
- bool rw = desc->vm_flags & VM_WRITE;
+ const bool rw = vma_desc_test_flags(desc, VMA_WRITE_BIT);
int err;
/* Avoid any operation if inode is bad. */
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index 919f99b16834..c75aa3f419b1 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -411,8 +411,8 @@ static int orangefs_file_mmap_prepare(struct vm_area_desc *desc)
"orangefs_file_mmap: called on %pD\n", file);
/* set the sequential readahead hint */
- desc->vm_flags |= VM_SEQ_READ;
- desc->vm_flags &= ~VM_RAND_READ;
+ vma_desc_set_flags(desc, VMA_SEQ_READ_BIT);
+ vma_desc_clear_flags(desc, VMA_RAND_READ_BIT);
file_accessed(file);
desc->vm_ops = &orangefs_file_vm_ops;
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 77b8ca2757e0..9b955787456e 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -264,7 +264,7 @@ static unsigned long ramfs_nommu_get_unmapped_area(struct file *file,
*/
static int ramfs_nommu_mmap_prepare(struct vm_area_desc *desc)
{
- if (!is_nommu_shared_mapping(desc->vm_flags))
+ if (!is_nommu_shared_vma_flags(desc->vma_flags))
return -ENOSYS;
file_accessed(desc->file);
diff --git a/fs/resctrl/pseudo_lock.c b/fs/resctrl/pseudo_lock.c
index 0bfc13c5b96d..e81d71abfe54 100644
--- a/fs/resctrl/pseudo_lock.c
+++ b/fs/resctrl/pseudo_lock.c
@@ -1044,7 +1044,7 @@ static int pseudo_lock_dev_mmap_prepare(struct vm_area_desc *desc)
* Ensure changes are carried directly to the memory being mapped,
* do not allow copy-on-write mapping.
*/
- if (!(desc->vm_flags & VM_SHARED)) {
+ if (!vma_desc_test_flags(desc, VMA_SHARED_BIT)) {
mutex_unlock(&rdtgroup_mutex);
return -EINVAL;
}
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index 4b77c6dc4418..0271bd8bf676 100644
--- a/fs/romfs/mmap-nommu.c
+++ b/fs/romfs/mmap-nommu.c
@@ -63,7 +63,7 @@ static unsigned long romfs_get_unmapped_area(struct file *file,
*/
static int romfs_mmap_prepare(struct vm_area_desc *desc)
{
- return is_nommu_shared_mapping(desc->vm_flags) ? 0 : -ENOSYS;
+ return is_nommu_shared_vma_flags(desc->vma_flags) ? 0 : -ENOSYS;
}
static unsigned romfs_mmap_capabilities(struct file *file)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7874cf745af3..fabea264324a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1974,14 +1974,14 @@ xfs_file_mmap_prepare(
* We don't support synchronous mappings for non-DAX files and
* for DAX files if underneath dax_device is not synchronous.
*/
- if (!daxdev_mapping_supported(desc->vm_flags, file_inode(file),
+ if (!daxdev_mapping_supported(desc->vma_flags, file_inode(file),
target->bt_daxdev))
return -EOPNOTSUPP;
file_accessed(file);
desc->vm_ops = &xfs_file_vm_ops;
if (IS_DAX(inode))
- desc->vm_flags |= VM_HUGEPAGE;
+ vma_desc_set_flags(desc, VMA_HUGEPAGE_BIT);
return 0;
}
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index c1e5e30e90a0..8a7161fc49e5 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -333,7 +333,8 @@ static int zonefs_file_mmap_prepare(struct vm_area_desc *desc)
* ordering between msync() and page cache writeback.
*/
if (zonefs_inode_is_seq(file_inode(file)) &&
- (desc->vm_flags & VM_SHARED) && (desc->vm_flags & VM_MAYWRITE))
+ vma_desc_test_flags(desc, VMA_SHARED_BIT) &&
+ vma_desc_test_flags(desc, VMA_MAYWRITE_BIT))
return -EINVAL;
file_accessed(file);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9d624f4d9df6..162c19fe478c 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -65,11 +65,11 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
/*
* Check if given mapping is supported by the file / underlying device.
*/
-static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+static inline bool daxdev_mapping_supported(vma_flags_t flags,
const struct inode *inode,
struct dax_device *dax_dev)
{
- if (!(vm_flags & VM_SYNC))
+ if (!vma_flags_test(flags, VMA_SYNC_BIT))
return true;
if (!IS_DAX(inode))
return false;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 69d8b67fe8a9..32f48d5a28ce 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -550,17 +550,18 @@ enum {
/*
* Physically remapped pages are special. Tell the
* rest of the world about it:
- * VM_IO tells people not to look at these pages
+ * IO tells people not to look at these pages
* (accesses can have side effects).
- * VM_PFNMAP tells the core MM that the base pages are just
+ * PFNMAP tells the core MM that the base pages are just
* raw PFN mappings, and do not have a "struct page" associated
* with them.
- * VM_DONTEXPAND
+ * DONTEXPAND
* Disable vma merging and expanding with mremap().
- * VM_DONTDUMP
+ * DONTDUMP
* Omit vma from core dump, even when VM_IO turned off.
*/
-#define VM_REMAP_FLAGS (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP)
+#define VMA_REMAP_FLAGS mk_vma_flags(VMA_IO_BIT, VMA_PFNMAP_BIT, \
+ VMA_DONTEXPAND_BIT, VMA_DONTDUMP_BIT)
/* This mask prevents VMA from being scanned with khugepaged */
#define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
@@ -1928,6 +1929,14 @@ static inline bool is_cow_mapping(vm_flags_t flags)
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
+static inline bool vma_desc_is_cow_mapping(struct vm_area_desc *desc)
+{
+ const vma_flags_t flags = desc->vma_flags;
+
+ return vma_flags_test(flags, VMA_MAYWRITE_BIT) &&
+ !vma_flags_test(flags, VMA_SHARED_BIT);
+}
+
#ifndef CONFIG_MMU
static inline bool is_nommu_shared_mapping(vm_flags_t flags)
{
@@ -1941,6 +1950,11 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags)
*/
return flags & (VM_MAYSHARE | VM_MAYOVERLAY);
}
+
+static inline bool is_nommu_shared_vma_flags(vma_flags_t flags)
+{
+ return vma_flags_test(flags, VMA_MAYSHARE_BIT, VMA_MAYOVERLAY_BIT);
+}
#endif
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
diff --git a/kernel/relay.c b/kernel/relay.c
index e36f6b926f7f..1c8e88259df0 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -92,7 +92,7 @@ static int relay_mmap_prepare_buf(struct rchan_buf *buf,
return -EINVAL;
desc->vm_ops = &relay_file_mmap_ops;
- desc->vm_flags |= VM_DONTEXPAND;
+ vma_desc_set_flags(desc, VMA_DONTEXPAND_BIT);
desc->private_data = buf;
return 0;
diff --git a/mm/memory.c b/mm/memory.c
index f2e9e0538874..6e5a6fc8e69e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2897,7 +2897,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
return 0;
}
-static int get_remap_pgoff(vm_flags_t vm_flags, unsigned long addr,
+static int get_remap_pgoff(bool is_cow, unsigned long addr,
unsigned long end, unsigned long vm_start, unsigned long vm_end,
unsigned long pfn, pgoff_t *vm_pgoff_p)
{
@@ -2907,7 +2907,7 @@ static int get_remap_pgoff(vm_flags_t vm_flags, unsigned long addr,
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
* See vm_normal_page() for details.
*/
- if (is_cow_mapping(vm_flags)) {
+ if (is_cow) {
if (addr != vm_start || end != vm_end)
return -EINVAL;
*vm_pgoff_p = pfn;
@@ -2928,7 +2928,7 @@ static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long ad
if (WARN_ON_ONCE(!PAGE_ALIGNED(addr)))
return -EINVAL;
- VM_WARN_ON_ONCE((vma->vm_flags & VM_REMAP_FLAGS) != VM_REMAP_FLAGS);
+ VM_WARN_ON_ONCE(!vma_test_all_flags_mask(vma, VMA_REMAP_FLAGS));
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
@@ -3052,9 +3052,9 @@ void remap_pfn_range_prepare(struct vm_area_desc *desc, unsigned long pfn)
* check it again on complete and will fail there if specified addr is
* invalid.
*/
- get_remap_pgoff(desc->vm_flags, desc->start, desc->end,
+ get_remap_pgoff(vma_desc_is_cow_mapping(desc), desc->start, desc->end,
desc->start, desc->end, pfn, &desc->pgoff);
- desc->vm_flags |= VM_REMAP_FLAGS;
+ vma_desc_set_flags_mask(desc, VMA_REMAP_FLAGS);
}
static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long addr,
@@ -3063,13 +3063,12 @@ static int remap_pfn_range_prepare_vma(struct vm_area_struct *vma, unsigned long
unsigned long end = addr + PAGE_ALIGN(size);
int err;
- err = get_remap_pgoff(vma->vm_flags, addr, end,
- vma->vm_start, vma->vm_end,
- pfn, &vma->vm_pgoff);
+ err = get_remap_pgoff(is_cow_mapping(vma->vm_flags), addr, end,
+ vma->vm_start, vma->vm_end, pfn, &vma->vm_pgoff);
if (err)
return err;
- vm_flags_set(vma, VM_REMAP_FLAGS);
+ vma_set_flags_mask(vma, VMA_REMAP_FLAGS);
return 0;
}
--
2.52.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox