* Re: [PATCH v2 0/2] implement OA2_INHERIT_CRED flag for openat2()
From: stsp @ 2024-04-23 11:02 UTC (permalink / raw)
To: Stefan Metzmacher, linux-kernel
Cc: Eric Biederman, Alexander Viro, Andy Lutomirski,
Christian Brauner, Jan Kara, Jeff Layton, Chuck Lever,
Alexander Aring, linux-fsdevel, Paolo Bonzini,
Christian Göttsche, Linux API Mailing List
In-Reply-To: <a24f8d8c-2e7e-41ff-a640-134501ba4fa2@samba.org>
23.04.2024 13:58, Stefan Metzmacher пишет:
>
> I guess this is something that should cc linux-api@vger.kernel.org ...
Done, thanks.
^ permalink raw reply
* [PATCH 2/2] openat2: add OA2_INHERIT_CRED flag
From: Stas Sergeev @ 2024-04-23 11:01 UTC (permalink / raw)
To: linux-kernel
Cc: Stas Sergeev, Stefan Metzmacher, Eric Biederman, Alexander Viro,
Andy Lutomirski, Christian Brauner, Jan Kara, Jeff Layton,
Chuck Lever, Alexander Aring, linux-fsdevel, linux-api,
Paolo Bonzini, Christian Göttsche
In-Reply-To: <20240423110148.13114-1-stsp2@yandex.ru>
This flag performs the open operation with the credentials that
were in effect when dir_fd was opened.
This allows the process to pre-open some directories and then
change eUID (and all other UIDs/GIDs) to a less-privileged user,
retaining the ability to open/create files within these directories.
Design goal:
The idea is to provide a very light-weight sandboxing, where the
process, without the use of any heavy-weight techniques like chroot
within namespaces, can restrict the access to the set of pre-opened
directories.
This patch is just a first step to such sandboxing. If things go
well, in the future the same extension can be added to more syscalls.
These should include at least unlinkat(), renameat2() and the
not-yet-upstreamed setxattrat().
Security considerations:
To avoid sandboxing escape, this patch makes sure the restricted
lookup modes are used. Namely, RESOLVE_BENEATH or RESOLVE_IN_ROOT.
To avoid leaking creds across exec, this patch requires O_CLOEXEC
flag on a directory.
Use cases:
Virtual machines that deal with untrusted code, can use that
instead of a more heavy-weighted approaches.
Currently the approach is being tested on a dosemu2 VM.
Signed-off-by: Stas Sergeev <stsp2@yandex.ru>
CC: Stefan Metzmacher <metze@samba.org>
CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Andy Lutomirski <luto@kernel.org>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Jeff Layton <jlayton@kernel.org>
CC: Chuck Lever <chuck.lever@oracle.com>
CC: Alexander Aring <alex.aring@gmail.com>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Christian Göttsche <cgzones@googlemail.com>
---
fs/internal.h | 2 +-
fs/namei.c | 30 ++++++++++++++++++++++++++++--
fs/open.c | 2 +-
include/linux/fcntl.h | 2 ++
include/uapi/linux/openat2.h | 3 +++
5 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/fs/internal.h b/fs/internal.h
index 7ca738904e34..692b53b19aad 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -169,7 +169,7 @@ static inline void sb_end_ro_state_change(struct super_block *sb)
* open.c
*/
struct open_flags {
- int open_flag;
+ u64 open_flag;
umode_t mode;
int acc_mode;
int intent;
diff --git a/fs/namei.c b/fs/namei.c
index 2fde2c320ae9..0e0f2e32ef02 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -586,6 +586,7 @@ struct nameidata {
int dfd;
vfsuid_t dir_vfsuid;
umode_t dir_mode;
+ const struct cred *dir_open_cred;
} __randomize_layout;
#define ND_ROOT_PRESET 1
@@ -695,6 +696,7 @@ static void terminate_walk(struct nameidata *nd)
nd->depth = 0;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
+ put_cred(nd->dir_open_cred);
}
/* path_put is needed afterwards regardless of success or failure */
@@ -2414,6 +2416,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
get_fs_pwd(current->fs, &nd->path);
nd->inode = nd->path.dentry->d_inode;
}
+ nd->dir_open_cred = get_current_cred();
} else {
/* Caller must check execute permissions on the starting path component */
struct fd f = fdget_raw(nd->dfd);
@@ -2437,6 +2440,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
+ nd->dir_open_cred = get_cred(f.file->f_cred);
fdput(f);
}
@@ -3794,8 +3798,28 @@ static struct file *path_openat(struct nameidata *nd,
error = do_o_path(nd, flags, file);
} else {
const char *s = path_init(nd, flags);
- file = alloc_empty_file(op->open_flag, current_cred());
- error = PTR_ERR_OR_ZERO(file);
+ const struct cred *old_cred = NULL;
+
+ error = 0;
+ if (op->open_flag & OA2_INHERIT_CRED) {
+ /* Make sure to work only with restricted
+ * look-up modes.
+ */
+ if (!(nd->flags & (LOOKUP_BENEATH | LOOKUP_IN_ROOT)))
+ error = -EPERM;
+ /* Only work with O_CLOEXEC dirs. */
+ if (!get_close_on_exec(nd->dfd))
+ error = -EPERM;
+
+ if (!error)
+ old_cred = override_creds(nd->dir_open_cred);
+ }
+ if (!error) {
+ file = alloc_empty_file(op->open_flag, current_cred());
+ error = PTR_ERR_OR_ZERO(file);
+ } else {
+ file = ERR_PTR(error);
+ }
if (!error) {
while (!(error = link_path_walk(s, nd)) &&
(s = open_last_lookups(nd, file, op)) != NULL)
@@ -3803,6 +3827,8 @@ static struct file *path_openat(struct nameidata *nd,
}
if (!error)
error = do_open(nd, file, op);
+ if (old_cred)
+ revert_creds(old_cred);
terminate_walk(nd);
if (IS_ERR(file))
return file;
diff --git a/fs/open.c b/fs/open.c
index ee8460c83c77..6be013182a35 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1225,7 +1225,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
* values before calling build_open_flags(), but openat2(2) checks all
* of its arguments.
*/
- if (flags & ~VALID_OPEN_FLAGS)
+ if (flags & ~VALID_OPENAT2_FLAGS)
return -EINVAL;
if (how->resolve & ~VALID_RESOLVE_FLAGS)
return -EINVAL;
diff --git a/include/linux/fcntl.h b/include/linux/fcntl.h
index a332e79b3207..b71f8b162102 100644
--- a/include/linux/fcntl.h
+++ b/include/linux/fcntl.h
@@ -12,6 +12,8 @@
FASYNC | O_DIRECT | O_LARGEFILE | O_DIRECTORY | O_NOFOLLOW | \
O_NOATIME | O_CLOEXEC | O_PATH | __O_TMPFILE)
+#define VALID_OPENAT2_FLAGS (VALID_OPEN_FLAGS | OA2_INHERIT_CRED)
+
/* List of all valid flags for the how->resolve argument: */
#define VALID_RESOLVE_FLAGS \
(RESOLVE_NO_XDEV | RESOLVE_NO_MAGICLINKS | RESOLVE_NO_SYMLINKS | \
diff --git a/include/uapi/linux/openat2.h b/include/uapi/linux/openat2.h
index a5feb7604948..cdd676a10b62 100644
--- a/include/uapi/linux/openat2.h
+++ b/include/uapi/linux/openat2.h
@@ -40,4 +40,7 @@ struct open_how {
return -EAGAIN if that's not
possible. */
+/* openat2-specific flags go to upper 4 bytes. */
+#define OA2_INHERIT_CRED (1ULL << 32)
+
#endif /* _UAPI_LINUX_OPENAT2_H */
--
2.44.0
^ permalink raw reply related
* [PATCH 1/2] fs: reorganize path_openat()
From: Stas Sergeev @ 2024-04-23 11:01 UTC (permalink / raw)
To: linux-kernel
Cc: Stas Sergeev, Stefan Metzmacher, Eric Biederman, Alexander Viro,
Andy Lutomirski, Christian Brauner, Jan Kara, Jeff Layton,
Chuck Lever, Alexander Aring, linux-fsdevel, linux-api,
Paolo Bonzini, Christian Göttsche
In-Reply-To: <20240423110148.13114-1-stsp2@yandex.ru>
This patch moves the call to alloc_empty_file() below the call to
path_init(). That changes is needed for the next patch, which adds
a cred override for alloc_empty_file(). The needed cred info is only
available after the call to path_init().
No functional changes are intended by that patch.
Signed-off-by: Stas Sergeev <stsp2@yandex.ru>
CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Andy Lutomirski <luto@kernel.org>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
---
fs/namei.c | 26 +++++++++++++++++---------
1 file changed, 17 insertions(+), 9 deletions(-)
diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d0..2fde2c320ae9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3782,22 +3782,30 @@ static struct file *path_openat(struct nameidata *nd,
struct file *file;
int error;
- file = alloc_empty_file(op->open_flag, current_cred());
- if (IS_ERR(file))
- return file;
-
- if (unlikely(file->f_flags & __O_TMPFILE)) {
+ if (unlikely(op->open_flag & __O_TMPFILE)) {
+ file = alloc_empty_file(op->open_flag, current_cred());
+ if (IS_ERR(file))
+ return file;
error = do_tmpfile(nd, flags, op, file);
- } else if (unlikely(file->f_flags & O_PATH)) {
+ } else if (unlikely(op->open_flag & O_PATH)) {
+ file = alloc_empty_file(op->open_flag, current_cred());
+ if (IS_ERR(file))
+ return file;
error = do_o_path(nd, flags, file);
} else {
const char *s = path_init(nd, flags);
- while (!(error = link_path_walk(s, nd)) &&
- (s = open_last_lookups(nd, file, op)) != NULL)
- ;
+ file = alloc_empty_file(op->open_flag, current_cred());
+ error = PTR_ERR_OR_ZERO(file);
+ if (!error) {
+ while (!(error = link_path_walk(s, nd)) &&
+ (s = open_last_lookups(nd, file, op)) != NULL)
+ ;
+ }
if (!error)
error = do_open(nd, file, op);
terminate_walk(nd);
+ if (IS_ERR(file))
+ return file;
}
if (likely(!error)) {
if (likely(file->f_mode & FMODE_OPENED))
--
2.44.0
^ permalink raw reply related
* [PATCH v2 0/2] implement OA2_INHERIT_CRED flag for openat2()
From: Stas Sergeev @ 2024-04-23 11:01 UTC (permalink / raw)
To: linux-kernel
Cc: Stas Sergeev, Stefan Metzmacher, Eric Biederman, Alexander Viro,
Andy Lutomirski, Christian Brauner, Jan Kara, Jeff Layton,
Chuck Lever, Alexander Aring, linux-fsdevel, linux-api,
Paolo Bonzini, Christian Göttsche
This patch-set implements the OA2_INHERIT_CRED flag for openat2() syscall.
It is needed to perform an open operation with the creds that were in
effect when the dir_fd was opened. This allows the process to pre-open
some dirs and switch eUID (and other UIDs/GIDs) to the less-privileged
user, while still retaining the possibility to open/create files within
the pre-opened directory set.
Changes in v2:
- capture full struct cred instead of just fsuid/fsgid.
Suggested by Stefan Metzmacher <metze@samba.org>
CC: Stefan Metzmacher <metze@samba.org>
CC: Eric Biederman <ebiederm@xmission.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Andy Lutomirski <luto@kernel.org>
CC: Christian Brauner <brauner@kernel.org>
CC: Jan Kara <jack@suse.cz>
CC: Jeff Layton <jlayton@kernel.org>
CC: Chuck Lever <chuck.lever@oracle.com>
CC: Alexander Aring <alex.aring@gmail.com>
CC: linux-fsdevel@vger.kernel.org
CC: linux-kernel@vger.kernel.org
CC: linux-api@vger.kernel.org
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Christian Göttsche <cgzones@googlemail.com>
Stas Sergeev (2):
fs: reorganize path_openat()
openat2: add OA2_INHERIT_CRED flag
fs/internal.h | 2 +-
fs/namei.c | 52 +++++++++++++++++++++++++++++-------
fs/open.c | 2 +-
include/linux/fcntl.h | 2 ++
include/uapi/linux/openat2.h | 3 +++
5 files changed, 50 insertions(+), 11 deletions(-)
--
2.44.0
^ permalink raw reply
* Re: [PATCH v2 0/2] implement OA2_INHERIT_CRED flag for openat2()
From: Stefan Metzmacher @ 2024-04-23 10:58 UTC (permalink / raw)
To: Stas Sergeev, linux-kernel
Cc: Eric Biederman, Alexander Viro, Andy Lutomirski,
Christian Brauner, Jan Kara, Jeff Layton, Chuck Lever,
Alexander Aring, linux-fsdevel, Paolo Bonzini,
Christian Göttsche, Linux API Mailing List
In-Reply-To: <20240423104824.10464-1-stsp2@yandex.ru>
Am 23.04.24 um 12:48 schrieb Stas Sergeev:
> This patch-set implements the OA2_INHERIT_CRED flag for openat2() syscall.
> It is needed to perform an open operation with the creds that were in
> effect when the dir_fd was opened. This allows the process to pre-open
> some dirs and switch eUID (and other UIDs/GIDs) to the less-privileged
> user, while still retaining the possibility to open/create files within
> the pre-opened directory set.
>
> Changes in v2:
> - capture full struct cred instead of just fsuid/fsgid.
> Suggested by Stefan Metzmacher <metze@samba.org>
>
> CC: Stefan Metzmacher <metze@samba.org>
> CC: Eric Biederman <ebiederm@xmission.com>
> CC: Alexander Viro <viro@zeniv.linux.org.uk>
> CC: Andy Lutomirski <luto@kernel.org>
> CC: Christian Brauner <brauner@kernel.org>
> CC: Jan Kara <jack@suse.cz>
> CC: Jeff Layton <jlayton@kernel.org>
> CC: Chuck Lever <chuck.lever@oracle.com>
> CC: Alexander Aring <alex.aring@gmail.com>
> CC: linux-fsdevel@vger.kernel.org
> CC: linux-kernel@vger.kernel.org
I guess this is something that should cc linux-api@vger.kernel.org ...
metze
^ permalink raw reply
* Re: [PATCHv3 bpf-next 0/7] uprobe: uretprobe speed up
From: Jiri Olsa @ 2024-04-22 20:25 UTC (permalink / raw)
To: Masami Hiramatsu
Cc: Steven Rostedt, Oleg Nesterov, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240423000943.478ccf1e735a63c6c1b4c66b@kernel.org>
On Tue, Apr 23, 2024 at 12:09:43AM +0900, Masami Hiramatsu wrote:
> Hi Jiri,
>
> On Sun, 21 Apr 2024 21:41:59 +0200
> Jiri Olsa <jolsa@kernel.org> wrote:
>
> > hi,
> > as part of the effort on speeding up the uprobes [0] coming with
> > return uprobe optimization by using syscall instead of the trap
> > on the uretprobe trampoline.
> >
> > The speed up depends on instruction type that uprobe is installed
> > and depends on specific HW type, please check patch 1 for details.
> >
> > Patches 1-6 are based on bpf-next/master, but path 1 and 2 are
> > apply-able on linux-trace.git tree probes/for-next branch.
> > Patch 7 is based on man-pages master.
>
> Thanks for updated! I reviewed the series and just except for the
> manpage, it looks good to me.
>
> Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
>
> for the series.
> If Linux API maintainers are OK, I can pick this in probes/for-next.
great, thanks
> (BTW, who will pick the manpage patch?)
ugh, I cc-ed linux-api but not linux-man@vger.kernel.org
I'll add that for new version
jirka
>
> Thank you,
>
> >
> > v3 changes:
> > - added source ip check if the uretprobe syscall is called from
> > trampoline and sending SIGILL to process if it's not
> > - keep x86 compat process to use standard breakpoint
> > - split syscall wiring into separate change
> > - ran ltp and syzkaller locally, no issues found [Masami]
> > - building uprobe_compat binary in selftests which breaks
> > CI atm because of missing 32-bit delve packages, I will
> > need to fix that in separate changes once this is acked
> > - added man page change
> > - there were several changes so I removed acks [Oleg Andrii]
> >
> > Also available at:
> > https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
> > uretprobe_syscall
> >
> > thanks,
> > jirka
> >
> >
> > Notes to check list items in Documentation/process/adding-syscalls.rst:
> >
> > - System Call Alternatives
> > New syscall seems like the best way in here, becase we need
> > just to quickly enter kernel with no extra arguments processing,
> > which we'd need to do if we decided to use another syscall.
> >
> > - Designing the API: Planning for Extension
> > The uretprobe syscall is very specific and most likely won't be
> > extended in the future.
> >
> > At the moment it does not take any arguments and even if it does
> > in future, it's allowed to be called only from trampoline prepared
> > by kernel, so there'll be no broken user.
> >
> > - Designing the API: Other Considerations
> > N/A because uretprobe syscall does not return reference to kernel
> > object.
> >
> > - Proposing the API
> > Wiring up of the uretprobe system call si in separate change,
> > selftests and man page changes are part of the patchset.
> >
> > - Generic System Call Implementation
> > There's no CONFIG option for the new functionality because it
> > keeps the same behaviour from the user POV.
> >
> > - x86 System Call Implementation
> > It's 64-bit syscall only.
> >
> > - Compatibility System Calls (Generic)
> > N/A uretprobe syscall has no arguments and is not supported
> > for compat processes.
> >
> > - Compatibility System Calls (x86)
> > N/A uretprobe syscall is not supported for compat processes.
> >
> > - System Calls Returning Elsewhere
> > N/A.
> >
> > - Other Details
> > N/A.
> >
> > - Testing
> > Adding new bpf selftests and ran ltp on top of this change.
> >
> > - Man Page
> > Attached.
> >
> > - Do not call System Calls in the Kernel
> > N/A.
> >
> >
> > [0] https://lore.kernel.org/bpf/ZeCXHKJ--iYYbmLj@krava/
> > ---
> > Jiri Olsa (6):
> > uprobe: Wire up uretprobe system call
> > uprobe: Add uretprobe syscall to speed up return probe
> > selftests/bpf: Add uretprobe syscall test for regs integrity
> > selftests/bpf: Add uretprobe syscall test for regs changes
> > selftests/bpf: Add uretprobe syscall call from user space test
> > selftests/bpf: Add uretprobe compat test
> >
> > arch/x86/entry/syscalls/syscall_64.tbl | 1 +
> > arch/x86/kernel/uprobes.c | 115 ++++++++++++++++++++++++++++++
> > include/linux/syscalls.h | 2 +
> > include/linux/uprobes.h | 3 +
> > include/uapi/asm-generic/unistd.h | 5 +-
> > kernel/events/uprobes.c | 24 +++++--
> > kernel/sys_ni.c | 2 +
> > tools/include/linux/compiler.h | 4 ++
> > tools/testing/selftests/bpf/.gitignore | 1 +
> > tools/testing/selftests/bpf/Makefile | 6 +-
> > tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 123 +++++++++++++++++++++++++++++++-
> > tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 362 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > tools/testing/selftests/bpf/progs/uprobe_syscall.c | 15 ++++
> > tools/testing/selftests/bpf/progs/uprobe_syscall_call.c | 15 ++++
> > tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c | 13 ++++
> > 15 files changed, 681 insertions(+), 10 deletions(-)
> > create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
> > create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall.c
> > create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
> > create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
> >
> >
> > Jiri Olsa (1):
> > man2: Add uretprobe syscall page
> >
> > man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 40 insertions(+)
> > create mode 100644 man2/uretprobe.2
>
>
> --
> Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH 7/7] man2: Add uretprobe syscall page
From: Jiri Olsa @ 2024-04-22 20:15 UTC (permalink / raw)
To: Masami Hiramatsu
Cc: Steven Rostedt, Oleg Nesterov, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240423000729.f1d58443100c3994afca0a7f@kernel.org>
On Tue, Apr 23, 2024 at 12:07:29AM +0900, Masami Hiramatsu wrote:
> On Sun, 21 Apr 2024 21:42:06 +0200
> Jiri Olsa <jolsa@kernel.org> wrote:
>
> > Adding man page for new uretprobe syscall.
> >
> > Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> > ---
> > man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
> > 1 file changed, 40 insertions(+)
> > create mode 100644 man2/uretprobe.2
> >
> > diff --git a/man2/uretprobe.2 b/man2/uretprobe.2
> > new file mode 100644
> > index 000000000000..c0343a88bb57
> > --- /dev/null
> > +++ b/man2/uretprobe.2
> > @@ -0,0 +1,40 @@
> > +.\" Copyright (C) 2024, Jiri Olsa <jolsa@kernel.org>
> > +.\"
> > +.\" SPDX-License-Identifier: Linux-man-pages-copyleft
> > +.\"
> > +.TH uretprobe 2 (date) "Linux man-pages (unreleased)"
> > +.SH NAME
> > +uretprobe \- execute pending return uprobes
> > +.SH SYNOPSIS
> > +.nf
> > +.B int uretprobe(void)
> > +.fi
> > +.SH DESCRIPTION
> > +On x86_64 architecture the kernel is using uretprobe syscall to trigger
> > +uprobe return probe consumers instead of using standard breakpoint instruction.
> > +The reason is that it's much faster to do syscall than breakpoint trap
> > +on x86_64 architecture.
>
> Do we specify the supported architecture as this? Currently it is supported
> only on x86-64, but it could be extended later, right?
yes, that's the idea, but I can't really speak other than x86 ;-)
so not sure abour other archs details
>
> This should be just noted as NOTES. Something like "This syscall is initially
> introduced on x86-64 because a syscall is faster than a breakpoint trap on it.
> But this will be extended to the architectures whose syscall is faster than
> breakpoint trap."
's/will be extended/might be will be extended/' seems better to me,
other than that it looks ok
thanks,
jirka
>
> Thank you,
>
> > +
> > +The uretprobe syscall is not supposed to be called directly by user, it's allowed
> > +to be invoked only through user space trampoline provided by kernel.
> > +When called from outside of this trampoline, the calling process will receive
> > +.BR SIGILL .
> > +
> > +.SH RETURN VALUE
> > +.BR uretprobe()
> > +return value is specific for given architecture.
> > +
> > +.SH VERSIONS
> > +This syscall is not specified in POSIX,
> > +and details of its behavior vary across systems.
> > +.SH STANDARDS
> > +None.
> > +.SH NOTES
> > +.BR uretprobe()
> > +exists only to allow the invocation of return uprobe consumers.
> > +It should
> > +.B never
> > +be called directly.
> > +Details of the arguments (if any) passed to
> > +.BR uretprobe ()
> > +and the return value are specific for given architecture.
> > --
> > 2.44.0
> >
>
>
> --
> Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCHv3 bpf-next 1/7] uprobe: Wire up uretprobe system call
From: Oleg Nesterov @ 2024-04-22 15:57 UTC (permalink / raw)
To: Jiri Olsa
Cc: Steven Rostedt, Masami Hiramatsu, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-2-jolsa@kernel.org>
On 04/21, Jiri Olsa wrote:
>
> arch/x86/entry/syscalls/syscall_64.tbl | 1 +
> include/linux/syscalls.h | 2 ++
> include/uapi/asm-generic/unistd.h | 5 ++++-
> kernel/sys_ni.c | 2 ++
> 4 files changed, 9 insertions(+), 1 deletion(-)
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
^ permalink raw reply
* Re: [PATCHv3 bpf-next 2/7] uprobe: Add uretprobe syscall to speed up return probe
From: Oleg Nesterov @ 2024-04-22 15:55 UTC (permalink / raw)
To: Jiri Olsa
Cc: Steven Rostedt, Masami Hiramatsu, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-3-jolsa@kernel.org>
On 04/21, Jiri Olsa wrote:
>
> arch/x86/kernel/uprobes.c | 115 ++++++++++++++++++++++++++++++++++++++
> include/linux/uprobes.h | 3 +
> kernel/events/uprobes.c | 24 +++++---
> 3 files changed, 135 insertions(+), 7 deletions(-)
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
^ permalink raw reply
* Re: [PATCHv3 bpf-next 0/7] uprobe: uretprobe speed up
From: Masami Hiramatsu @ 2024-04-22 15:09 UTC (permalink / raw)
To: Jiri Olsa
Cc: Steven Rostedt, Oleg Nesterov, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Hi Jiri,
On Sun, 21 Apr 2024 21:41:59 +0200
Jiri Olsa <jolsa@kernel.org> wrote:
> hi,
> as part of the effort on speeding up the uprobes [0] coming with
> return uprobe optimization by using syscall instead of the trap
> on the uretprobe trampoline.
>
> The speed up depends on instruction type that uprobe is installed
> and depends on specific HW type, please check patch 1 for details.
>
> Patches 1-6 are based on bpf-next/master, but path 1 and 2 are
> apply-able on linux-trace.git tree probes/for-next branch.
> Patch 7 is based on man-pages master.
Thanks for updated! I reviewed the series and just except for the
manpage, it looks good to me.
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
for the series.
If Linux API maintainers are OK, I can pick this in probes/for-next.
(BTW, who will pick the manpage patch?)
Thank you,
>
> v3 changes:
> - added source ip check if the uretprobe syscall is called from
> trampoline and sending SIGILL to process if it's not
> - keep x86 compat process to use standard breakpoint
> - split syscall wiring into separate change
> - ran ltp and syzkaller locally, no issues found [Masami]
> - building uprobe_compat binary in selftests which breaks
> CI atm because of missing 32-bit delve packages, I will
> need to fix that in separate changes once this is acked
> - added man page change
> - there were several changes so I removed acks [Oleg Andrii]
>
> Also available at:
> https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
> uretprobe_syscall
>
> thanks,
> jirka
>
>
> Notes to check list items in Documentation/process/adding-syscalls.rst:
>
> - System Call Alternatives
> New syscall seems like the best way in here, becase we need
> just to quickly enter kernel with no extra arguments processing,
> which we'd need to do if we decided to use another syscall.
>
> - Designing the API: Planning for Extension
> The uretprobe syscall is very specific and most likely won't be
> extended in the future.
>
> At the moment it does not take any arguments and even if it does
> in future, it's allowed to be called only from trampoline prepared
> by kernel, so there'll be no broken user.
>
> - Designing the API: Other Considerations
> N/A because uretprobe syscall does not return reference to kernel
> object.
>
> - Proposing the API
> Wiring up of the uretprobe system call si in separate change,
> selftests and man page changes are part of the patchset.
>
> - Generic System Call Implementation
> There's no CONFIG option for the new functionality because it
> keeps the same behaviour from the user POV.
>
> - x86 System Call Implementation
> It's 64-bit syscall only.
>
> - Compatibility System Calls (Generic)
> N/A uretprobe syscall has no arguments and is not supported
> for compat processes.
>
> - Compatibility System Calls (x86)
> N/A uretprobe syscall is not supported for compat processes.
>
> - System Calls Returning Elsewhere
> N/A.
>
> - Other Details
> N/A.
>
> - Testing
> Adding new bpf selftests and ran ltp on top of this change.
>
> - Man Page
> Attached.
>
> - Do not call System Calls in the Kernel
> N/A.
>
>
> [0] https://lore.kernel.org/bpf/ZeCXHKJ--iYYbmLj@krava/
> ---
> Jiri Olsa (6):
> uprobe: Wire up uretprobe system call
> uprobe: Add uretprobe syscall to speed up return probe
> selftests/bpf: Add uretprobe syscall test for regs integrity
> selftests/bpf: Add uretprobe syscall test for regs changes
> selftests/bpf: Add uretprobe syscall call from user space test
> selftests/bpf: Add uretprobe compat test
>
> arch/x86/entry/syscalls/syscall_64.tbl | 1 +
> arch/x86/kernel/uprobes.c | 115 ++++++++++++++++++++++++++++++
> include/linux/syscalls.h | 2 +
> include/linux/uprobes.h | 3 +
> include/uapi/asm-generic/unistd.h | 5 +-
> kernel/events/uprobes.c | 24 +++++--
> kernel/sys_ni.c | 2 +
> tools/include/linux/compiler.h | 4 ++
> tools/testing/selftests/bpf/.gitignore | 1 +
> tools/testing/selftests/bpf/Makefile | 6 +-
> tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 123 +++++++++++++++++++++++++++++++-
> tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 362 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> tools/testing/selftests/bpf/progs/uprobe_syscall.c | 15 ++++
> tools/testing/selftests/bpf/progs/uprobe_syscall_call.c | 15 ++++
> tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c | 13 ++++
> 15 files changed, 681 insertions(+), 10 deletions(-)
> create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
> create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall.c
> create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
> create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
>
>
> Jiri Olsa (1):
> man2: Add uretprobe syscall page
>
> man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 40 insertions(+)
> create mode 100644 man2/uretprobe.2
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* Re: [PATCH 7/7] man2: Add uretprobe syscall page
From: Masami Hiramatsu @ 2024-04-22 15:07 UTC (permalink / raw)
To: Jiri Olsa
Cc: Steven Rostedt, Oleg Nesterov, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, linux-kernel,
linux-trace-kernel, linux-api, x86, bpf, Song Liu, Yonghong Song,
John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-8-jolsa@kernel.org>
On Sun, 21 Apr 2024 21:42:06 +0200
Jiri Olsa <jolsa@kernel.org> wrote:
> Adding man page for new uretprobe syscall.
>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
> man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 40 insertions(+)
> create mode 100644 man2/uretprobe.2
>
> diff --git a/man2/uretprobe.2 b/man2/uretprobe.2
> new file mode 100644
> index 000000000000..c0343a88bb57
> --- /dev/null
> +++ b/man2/uretprobe.2
> @@ -0,0 +1,40 @@
> +.\" Copyright (C) 2024, Jiri Olsa <jolsa@kernel.org>
> +.\"
> +.\" SPDX-License-Identifier: Linux-man-pages-copyleft
> +.\"
> +.TH uretprobe 2 (date) "Linux man-pages (unreleased)"
> +.SH NAME
> +uretprobe \- execute pending return uprobes
> +.SH SYNOPSIS
> +.nf
> +.B int uretprobe(void)
> +.fi
> +.SH DESCRIPTION
> +On x86_64 architecture the kernel is using uretprobe syscall to trigger
> +uprobe return probe consumers instead of using standard breakpoint instruction.
> +The reason is that it's much faster to do syscall than breakpoint trap
> +on x86_64 architecture.
Do we specify the supported architecture as this? Currently it is supported
only on x86-64, but it could be extended later, right?
This should be just noted as NOTES. Something like "This syscall is initially
introduced on x86-64 because a syscall is faster than a breakpoint trap on it.
But this will be extended to the architectures whose syscall is faster than
breakpoint trap."
Thank you,
> +
> +The uretprobe syscall is not supposed to be called directly by user, it's allowed
> +to be invoked only through user space trampoline provided by kernel.
> +When called from outside of this trampoline, the calling process will receive
> +.BR SIGILL .
> +
> +.SH RETURN VALUE
> +.BR uretprobe()
> +return value is specific for given architecture.
> +
> +.SH VERSIONS
> +This syscall is not specified in POSIX,
> +and details of its behavior vary across systems.
> +.SH STANDARDS
> +None.
> +.SH NOTES
> +.BR uretprobe()
> +exists only to allow the invocation of return uprobe consumers.
> +It should
> +.B never
> +be called directly.
> +Details of the arguments (if any) passed to
> +.BR uretprobe ()
> +and the return value are specific for given architecture.
> --
> 2.44.0
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* [PATCH 7/7] man2: Add uretprobe syscall page
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Adding man page for new uretprobe syscall.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
create mode 100644 man2/uretprobe.2
diff --git a/man2/uretprobe.2 b/man2/uretprobe.2
new file mode 100644
index 000000000000..c0343a88bb57
--- /dev/null
+++ b/man2/uretprobe.2
@@ -0,0 +1,40 @@
+.\" Copyright (C) 2024, Jiri Olsa <jolsa@kernel.org>
+.\"
+.\" SPDX-License-Identifier: Linux-man-pages-copyleft
+.\"
+.TH uretprobe 2 (date) "Linux man-pages (unreleased)"
+.SH NAME
+uretprobe \- execute pending return uprobes
+.SH SYNOPSIS
+.nf
+.B int uretprobe(void)
+.fi
+.SH DESCRIPTION
+On x86_64 architecture the kernel is using uretprobe syscall to trigger
+uprobe return probe consumers instead of using standard breakpoint instruction.
+The reason is that it's much faster to do syscall than breakpoint trap
+on x86_64 architecture.
+
+The uretprobe syscall is not supposed to be called directly by user, it's allowed
+to be invoked only through user space trampoline provided by kernel.
+When called from outside of this trampoline, the calling process will receive
+.BR SIGILL .
+
+.SH RETURN VALUE
+.BR uretprobe()
+return value is specific for given architecture.
+
+.SH VERSIONS
+This syscall is not specified in POSIX,
+and details of its behavior vary across systems.
+.SH STANDARDS
+None.
+.SH NOTES
+.BR uretprobe()
+exists only to allow the invocation of return uprobe consumers.
+It should
+.B never
+be called directly.
+Details of the arguments (if any) passed to
+.BR uretprobe ()
+and the return value are specific for given architecture.
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 6/7] selftests/bpf: Add uretprobe compat test
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Adding test that adds return uprobe inside 32 bit task
and verify the return uprobe and attached bpf programs
get properly executed.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 6 ++-
.../selftests/bpf/prog_tests/uprobe_syscall.c | 40 +++++++++++++++++++
.../bpf/progs/uprobe_syscall_compat.c | 13 ++++++
4 files changed, 59 insertions(+), 1 deletion(-)
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index f1aebabfb017..69d71223c0dd 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -45,6 +45,7 @@ test_cpp
/veristat
/sign-file
/uprobe_multi
+/uprobe_compat
*.ko
*.tmp
xskxceiver
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index edc73f8f5aef..d170b63eca62 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -134,7 +134,7 @@ TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
xskxceiver xdp_redirect_multi xdp_synproxy veristat xdp_hw_metadata \
xdp_features bpf_test_no_cfi.ko
-TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi
+TEST_GEN_FILES += liburandom_read.so urandom_read sign-file uprobe_multi uprobe_compat
# Emit succinct information message describing current building step
# $1 - generic step name (e.g., CC, LINK, etc);
@@ -761,6 +761,10 @@ $(OUTPUT)/uprobe_multi: uprobe_multi.c
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) -O0 $(LDFLAGS) $^ $(LDLIBS) -o $@
+$(OUTPUT)/uprobe_compat:
+ $(call msg,BINARY,,$@)
+ $(Q)echo "int main() { return 0; }" | $(CC) $(CFLAGS) -xc -m32 -O0 - -o $@
+
EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
feature bpftool \
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 9233210a4c33..3770254d893b 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -11,6 +11,7 @@
#include <sys/wait.h>
#include "uprobe_syscall.skel.h"
#include "uprobe_syscall_call.skel.h"
+#include "uprobe_syscall_compat.skel.h"
__naked unsigned long uretprobe_regs_trigger(void)
{
@@ -291,6 +292,35 @@ static void test_uretprobe_syscall_call(void)
"read_trace_pipe_iter");
ASSERT_EQ(found, 0, "found");
}
+
+static void trace_pipe_compat_cb(const char *str, void *data)
+{
+ if (strstr(str, "uretprobe compat") != NULL)
+ (*(int *)data)++;
+}
+
+static void test_uretprobe_compat(void)
+{
+ struct uprobe_syscall_compat *skel = NULL;
+ int err, found = 0;
+
+ skel = uprobe_syscall_compat__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_compat__open_and_load"))
+ goto cleanup;
+
+ err = uprobe_syscall_compat__attach(skel);
+ if (!ASSERT_OK(err, "uprobe_syscall_compat__attach"))
+ goto cleanup;
+
+ system("./uprobe_compat");
+
+ ASSERT_OK(read_trace_pipe_iter(trace_pipe_compat_cb, &found, 1000),
+ "read_trace_pipe_iter");
+ ASSERT_EQ(found, 1, "found");
+
+cleanup:
+ uprobe_syscall_compat__destroy(skel);
+}
#else
static void test_uretprobe_regs_equal(void)
{
@@ -306,6 +336,11 @@ static void test_uretprobe_syscall_call(void)
{
test__skip();
}
+
+static void test_uretprobe_compat(void)
+{
+ test__skip();
+}
#endif
void test_uprobe_syscall(void)
@@ -320,3 +355,8 @@ void serial_test_uprobe_syscall_call(void)
{
test_uretprobe_syscall_call();
}
+
+void serial_test_uprobe_syscall_compat(void)
+{
+ test_uretprobe_compat();
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
new file mode 100644
index 000000000000..f8adde7f08e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("uretprobe.multi/./uprobe_compat:main")
+int uretprobe_compat(struct pt_regs *ctx)
+{
+ bpf_printk("uretprobe compat\n");
+ return 0;
+}
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 5/7] selftests/bpf: Add uretprobe syscall call from user space test
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Adding test to verify that when called from outside of the
trampoline provided by kernel, the uretprobe syscall will cause
calling process to receive SIGILL signal and the attached bpf
program is no executed.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
.../selftests/bpf/prog_tests/uprobe_syscall.c | 92 +++++++++++++++++++
.../selftests/bpf/progs/uprobe_syscall_call.c | 15 +++
2 files changed, 107 insertions(+)
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 1a50cd35205d..9233210a4c33 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -7,7 +7,10 @@
#include <unistd.h>
#include <asm/ptrace.h>
#include <linux/compiler.h>
+#include <linux/stringify.h>
+#include <sys/wait.h>
#include "uprobe_syscall.skel.h"
+#include "uprobe_syscall_call.skel.h"
__naked unsigned long uretprobe_regs_trigger(void)
{
@@ -209,6 +212,85 @@ static void test_uretprobe_regs_change(void)
}
}
+#ifndef __NR_uretprobe
+#define __NR_uretprobe 462
+#endif
+
+__naked unsigned long uretprobe_syscall_call_1(void)
+{
+ /*
+ * Pretend we are uretprobe trampoline to trigger the return
+ * probe invocation in order to verify we get SIGILL.
+ */
+ asm volatile (
+ "pushq %rax\n"
+ "pushq %rcx\n"
+ "pushq %r11\n"
+ "movq $" __stringify(__NR_uretprobe) ", %rax\n"
+ "syscall\n"
+ "popq %r11\n"
+ "popq %rcx\n"
+ "retq\n"
+ );
+}
+
+__naked unsigned long uretprobe_syscall_call(void)
+{
+ asm volatile (
+ "call uretprobe_syscall_call_1\n"
+ "retq\n"
+ );
+}
+
+static void __test_uretprobe_syscall_call(void)
+{
+ struct uprobe_syscall_call *skel = NULL;
+ int err;
+
+ skel = uprobe_syscall_call__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall_call__open_and_load"))
+ goto cleanup;
+
+ err = uprobe_syscall_call__attach(skel);
+ if (!ASSERT_OK(err, "uprobe_syscall_call__attach"))
+ goto cleanup;
+
+ uretprobe_syscall_call();
+
+cleanup:
+ uprobe_syscall_call__destroy(skel);
+}
+
+static void trace_pipe_cb(const char *str, void *data)
+{
+ if (strstr(str, "uretprobe called") != NULL)
+ (*(int *)data)++;
+}
+
+static void test_uretprobe_syscall_call(void)
+{
+ int pid, status, found = 0;
+
+ pid = fork();
+ if (!ASSERT_GE(pid, 0, "fork"))
+ return;
+
+ if (pid == 0) {
+ __test_uretprobe_syscall_call();
+ _exit(0);
+ }
+
+ waitpid(pid, &status, 0);
+
+ /* verify the child got killed with SIGILL */
+ ASSERT_EQ(WIFSIGNALED(status), 1, "WIFSIGNALED");
+ ASSERT_EQ(WTERMSIG(status), SIGILL, "WTERMSIG");
+
+ /* verify the uretprobe program wasn't called */
+ ASSERT_OK(read_trace_pipe_iter(trace_pipe_cb, &found, 1000),
+ "read_trace_pipe_iter");
+ ASSERT_EQ(found, 0, "found");
+}
#else
static void test_uretprobe_regs_equal(void)
{
@@ -219,6 +301,11 @@ static void test_uretprobe_regs_change(void)
{
test__skip();
}
+
+static void test_uretprobe_syscall_call(void)
+{
+ test__skip();
+}
#endif
void test_uprobe_syscall(void)
@@ -228,3 +315,8 @@ void test_uprobe_syscall(void)
if (test__start_subtest("uretprobe_regs_change"))
test_uretprobe_regs_change();
}
+
+void serial_test_uprobe_syscall_call(void)
+{
+ test_uretprobe_syscall_call();
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_call.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
new file mode 100644
index 000000000000..5ea03bb47198
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("uretprobe//proc/self/exe:uretprobe_syscall_call")
+int uretprobe(struct pt_regs *regs)
+{
+ bpf_printk("uretprobe called");
+ return 0;
+}
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 4/7] selftests/bpf: Add uretprobe syscall test for regs changes
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Adding test that creates uprobe consumer on uretprobe which changes some
of the registers. Making sure the changed registers are propagated to the
user space when the ureptobe syscall trampoline is used on x86_64.
To be able to do this, adding support to bpf_testmod to create uprobe via
new attribute file:
/sys/kernel/bpf_testmod_uprobe
This file is expecting file offset and creates related uprobe on current
process exe file and removes existing uprobe if offset is 0. The can be
only single uprobe at any time.
The uprobe has specific consumer that changes registers used in ureprobe
syscall trampoline and which are later checked in the test.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
.../selftests/bpf/bpf_testmod/bpf_testmod.c | 123 +++++++++++++++++-
.../selftests/bpf/prog_tests/uprobe_syscall.c | 67 ++++++++++
2 files changed, 189 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 39ad96a18123..c832cbb42e74 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -10,6 +10,7 @@
#include <linux/percpu-defs.h>
#include <linux/sysfs.h>
#include <linux/tracepoint.h>
+#include <linux/namei.h>
#include "bpf_testmod.h"
#include "bpf_testmod_kfunc.h"
@@ -343,6 +344,119 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
.write = bpf_testmod_test_write,
};
+/* bpf_testmod_uprobe sysfs attribute is so far enabled for x86_64 only,
+ * please see test_uretprobe_regs_change test
+ */
+#ifdef __x86_64__
+
+static int
+uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
+ struct pt_regs *regs)
+
+{
+ regs->ax = 0x12345678deadbeef;
+ regs->cx = 0x87654321feebdaed;
+ regs->r11 = (u64) -1;
+ return true;
+}
+
+struct testmod_uprobe {
+ struct path path;
+ loff_t offset;
+ struct uprobe_consumer consumer;
+};
+
+static DEFINE_MUTEX(testmod_uprobe_mutex);
+
+static struct testmod_uprobe uprobe = {
+ .consumer.ret_handler = uprobe_ret_handler,
+};
+
+static int testmod_register_uprobe(loff_t offset)
+{
+ int err = -EBUSY;
+
+ if (uprobe.offset)
+ return -EBUSY;
+
+ mutex_lock(&testmod_uprobe_mutex);
+
+ if (uprobe.offset)
+ goto out;
+
+ err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path);
+ if (err)
+ goto out;
+
+ err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry),
+ offset, 0, &uprobe.consumer);
+ if (err)
+ path_put(&uprobe.path);
+ else
+ uprobe.offset = offset;
+
+out:
+ mutex_unlock(&testmod_uprobe_mutex);
+ return err;
+}
+
+static void testmod_unregister_uprobe(void)
+{
+ mutex_lock(&testmod_uprobe_mutex);
+
+ if (uprobe.offset) {
+ uprobe_unregister(d_real_inode(uprobe.path.dentry),
+ uprobe.offset, &uprobe.consumer);
+ uprobe.offset = 0;
+ }
+
+ mutex_unlock(&testmod_uprobe_mutex);
+}
+
+static ssize_t
+bpf_testmod_uprobe_write(struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buf, loff_t off, size_t len)
+{
+ unsigned long offset;
+ int err;
+
+ if (kstrtoul(buf, 0, &offset))
+ return -EINVAL;
+
+ if (offset)
+ err = testmod_register_uprobe(offset);
+ else
+ testmod_unregister_uprobe();
+
+ return err ?: strlen(buf);
+}
+
+static struct bin_attribute bin_attr_bpf_testmod_uprobe_file __ro_after_init = {
+ .attr = { .name = "bpf_testmod_uprobe", .mode = 0666, },
+ .write = bpf_testmod_uprobe_write,
+};
+
+static int register_bpf_testmod_uprobe(void)
+{
+ return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+static void unregister_bpf_testmod_uprobe(void)
+{
+ testmod_unregister_uprobe();
+ sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+#else
+static int register_bpf_testmod_uprobe(void)
+{
+ return 0;
+}
+
+static void unregister_bpf_testmod_uprobe(void) { }
+#endif
+
BTF_KFUNCS_START(bpf_testmod_common_kfunc_ids)
BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
@@ -650,7 +764,13 @@ static int bpf_testmod_init(void)
return ret;
if (bpf_fentry_test1(0) < 0)
return -EINVAL;
- return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+ ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+ if (ret < 0)
+ return ret;
+ ret = register_bpf_testmod_uprobe();
+ if (ret < 0)
+ return ret;
+ return 0;
}
static void bpf_testmod_exit(void)
@@ -664,6 +784,7 @@ static void bpf_testmod_exit(void)
msleep(20);
sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+ unregister_bpf_testmod_uprobe();
}
module_init(bpf_testmod_init);
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
index 311ac19d8992..1a50cd35205d 100644
--- a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -149,15 +149,82 @@ static void test_uretprobe_regs_equal(void)
cleanup:
uprobe_syscall__destroy(skel);
}
+
+#define BPF_TESTMOD_UPROBE_TEST_FILE "/sys/kernel/bpf_testmod_uprobe"
+
+static int write_bpf_testmod_uprobe(unsigned long offset)
+{
+ size_t n, ret;
+ char buf[30];
+ int fd;
+
+ n = sprintf(buf, "%lu", offset);
+
+ fd = open(BPF_TESTMOD_UPROBE_TEST_FILE, O_WRONLY);
+ if (fd < 0)
+ return -errno;
+
+ ret = write(fd, buf, n);
+ close(fd);
+ return ret != n ? (int) ret : 0;
+}
+
+static void test_uretprobe_regs_change(void)
+{
+ struct pt_regs before = {}, after = {};
+ unsigned long *pb = (unsigned long *) &before;
+ unsigned long *pa = (unsigned long *) &after;
+ unsigned long cnt = sizeof(before)/sizeof(*pb);
+ unsigned int i, err, offset;
+
+ offset = get_uprobe_offset(uretprobe_regs_trigger);
+
+ err = write_bpf_testmod_uprobe(offset);
+ if (!ASSERT_OK(err, "register_uprobe"))
+ return;
+
+ uretprobe_regs(&before, &after);
+
+ err = write_bpf_testmod_uprobe(0);
+ if (!ASSERT_OK(err, "unregister_uprobe"))
+ return;
+
+ for (i = 0; i < cnt; i++) {
+ unsigned int offset = i * sizeof(unsigned long);
+
+ switch (offset) {
+ case offsetof(struct pt_regs, rax):
+ ASSERT_EQ(pa[i], 0x12345678deadbeef, "rax");
+ break;
+ case offsetof(struct pt_regs, rcx):
+ ASSERT_EQ(pa[i], 0x87654321feebdaed, "rcx");
+ break;
+ case offsetof(struct pt_regs, r11):
+ ASSERT_EQ(pa[i], (__u64) -1, "r11");
+ break;
+ default:
+ if (!ASSERT_EQ(pa[i], pb[i], "register before-after value check"))
+ fprintf(stdout, "failed register offset %u\n", offset);
+ }
+ }
+}
+
#else
static void test_uretprobe_regs_equal(void)
{
test__skip();
}
+
+static void test_uretprobe_regs_change(void)
+{
+ test__skip();
+}
#endif
void test_uprobe_syscall(void)
{
if (test__start_subtest("uretprobe_regs_equal"))
test_uretprobe_regs_equal();
+ if (test__start_subtest("uretprobe_regs_change"))
+ test_uretprobe_regs_change();
}
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 3/7] selftests/bpf: Add uretprobe syscall test for regs integrity
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Add uretprobe syscall test that compares register values before
and after the uretprobe is hit. It also compares the register
values seen from attached bpf program.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
tools/include/linux/compiler.h | 4 +
.../selftests/bpf/prog_tests/uprobe_syscall.c | 163 ++++++++++++++++++
.../selftests/bpf/progs/uprobe_syscall.c | 15 ++
3 files changed, 182 insertions(+)
create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall.c
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 8a63a9913495..6f7f22ac9da5 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -62,6 +62,10 @@
#define __nocf_check __attribute__((nocf_check))
#endif
+#ifndef __naked
+#define __naked __attribute__((__naked__))
+#endif
+
/* Are two types/vars the same type (ignoring qualifiers)? */
#ifndef __same_type
# define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
new file mode 100644
index 000000000000..311ac19d8992
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#ifdef __x86_64__
+
+#include <unistd.h>
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+#include "uprobe_syscall.skel.h"
+
+__naked unsigned long uretprobe_regs_trigger(void)
+{
+ asm volatile (
+ "movq $0xdeadbeef, %rax\n"
+ "ret\n"
+ );
+}
+
+__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
+{
+ asm volatile (
+ "movq %r15, 0(%rdi)\n"
+ "movq %r14, 8(%rdi)\n"
+ "movq %r13, 16(%rdi)\n"
+ "movq %r12, 24(%rdi)\n"
+ "movq %rbp, 32(%rdi)\n"
+ "movq %rbx, 40(%rdi)\n"
+ "movq %r11, 48(%rdi)\n"
+ "movq %r10, 56(%rdi)\n"
+ "movq %r9, 64(%rdi)\n"
+ "movq %r8, 72(%rdi)\n"
+ "movq %rax, 80(%rdi)\n"
+ "movq %rcx, 88(%rdi)\n"
+ "movq %rdx, 96(%rdi)\n"
+ "movq %rsi, 104(%rdi)\n"
+ "movq %rdi, 112(%rdi)\n"
+ "movq $0, 120(%rdi)\n" /* orig_rax */
+ "movq $0, 128(%rdi)\n" /* rip */
+ "movq $0, 136(%rdi)\n" /* cs */
+ "pushf\n"
+ "pop %rax\n"
+ "movq %rax, 144(%rdi)\n" /* eflags */
+ "movq %rsp, 152(%rdi)\n" /* rsp */
+ "movq $0, 160(%rdi)\n" /* ss */
+
+ /* save 2nd argument */
+ "pushq %rsi\n"
+ "call uretprobe_regs_trigger\n"
+
+ /* save return value and load 2nd argument pointer to rax */
+ "pushq %rax\n"
+ "movq 8(%rsp), %rax\n"
+
+ "movq %r15, 0(%rax)\n"
+ "movq %r14, 8(%rax)\n"
+ "movq %r13, 16(%rax)\n"
+ "movq %r12, 24(%rax)\n"
+ "movq %rbp, 32(%rax)\n"
+ "movq %rbx, 40(%rax)\n"
+ "movq %r11, 48(%rax)\n"
+ "movq %r10, 56(%rax)\n"
+ "movq %r9, 64(%rax)\n"
+ "movq %r8, 72(%rax)\n"
+ "movq %rcx, 88(%rax)\n"
+ "movq %rdx, 96(%rax)\n"
+ "movq %rsi, 104(%rax)\n"
+ "movq %rdi, 112(%rax)\n"
+ "movq $0, 120(%rax)\n" /* orig_rax */
+ "movq $0, 128(%rax)\n" /* rip */
+ "movq $0, 136(%rax)\n" /* cs */
+
+ /* restore return value and 2nd argument */
+ "pop %rax\n"
+ "pop %rsi\n"
+
+ "movq %rax, 80(%rsi)\n"
+
+ "pushf\n"
+ "pop %rax\n"
+
+ "movq %rax, 144(%rsi)\n" /* eflags */
+ "movq %rsp, 152(%rsi)\n" /* rsp */
+ "movq $0, 160(%rsi)\n" /* ss */
+ "ret\n"
+);
+}
+
+static void test_uretprobe_regs_equal(void)
+{
+ struct uprobe_syscall *skel = NULL;
+ struct pt_regs before = {}, after = {};
+ unsigned long *pb = (unsigned long *) &before;
+ unsigned long *pa = (unsigned long *) &after;
+ unsigned long *pp;
+ unsigned int i, cnt;
+ int err;
+
+ skel = uprobe_syscall__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
+ goto cleanup;
+
+ err = uprobe_syscall__attach(skel);
+ if (!ASSERT_OK(err, "uprobe_syscall__attach"))
+ goto cleanup;
+
+ uretprobe_regs(&before, &after);
+
+ pp = (unsigned long *) &skel->bss->regs;
+ cnt = sizeof(before)/sizeof(*pb);
+
+ for (i = 0; i < cnt; i++) {
+ unsigned int offset = i * sizeof(unsigned long);
+
+ /*
+ * Check register before and after uretprobe_regs_trigger call
+ * that triggers the uretprobe.
+ */
+ switch (offset) {
+ case offsetof(struct pt_regs, rax):
+ ASSERT_EQ(pa[i], 0xdeadbeef, "return value");
+ break;
+ default:
+ if (!ASSERT_EQ(pb[i], pa[i], "register before-after value check"))
+ fprintf(stdout, "failed register offset %u\n", offset);
+ }
+
+ /*
+ * Check register seen from bpf program and register after
+ * uretprobe_regs_trigger call
+ */
+ switch (offset) {
+ /*
+ * These values will be different (not set in uretprobe_regs),
+ * we don't care.
+ */
+ case offsetof(struct pt_regs, orig_rax):
+ case offsetof(struct pt_regs, rip):
+ case offsetof(struct pt_regs, cs):
+ case offsetof(struct pt_regs, rsp):
+ case offsetof(struct pt_regs, ss):
+ break;
+ default:
+ if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
+ fprintf(stdout, "failed register offset %u\n", offset);
+ }
+ }
+
+cleanup:
+ uprobe_syscall__destroy(skel);
+}
+#else
+static void test_uretprobe_regs_equal(void)
+{
+ test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+ if (test__start_subtest("uretprobe_regs_equal"))
+ test_uretprobe_regs_equal();
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
new file mode 100644
index 000000000000..8a4fa6c7ef59
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("uretprobe//proc/self/exe:uretprobe_regs_trigger")
+int uretprobe(struct pt_regs *ctx)
+{
+ __builtin_memcpy(®s, ctx, sizeof(regs));
+ return 0;
+}
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 2/7] uprobe: Add uretprobe syscall to speed up return probe
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Adding uretprobe syscall instead of trap to speed up return probe.
At the moment the uretprobe setup/path is:
- install entry uprobe
- when the uprobe is hit, it overwrites probed function's return address
on stack with address of the trampoline that contains breakpoint
instruction
- the breakpoint trap code handles the uretprobe consumers execution and
jumps back to original return address
This patch replaces the above trampoline's breakpoint instruction with new
ureprobe syscall call. This syscall does exactly the same job as the trap
with some more extra work:
- syscall trampoline must save original value for rax/r11/rcx registers
on stack - rax is set to syscall number and r11/rcx are changed and
used by syscall instruction
- the syscall code reads the original values of those registers and
restore those values in task's pt_regs area
- only caller from trampoline exposed in '[uprobes]' is allowed,
the process will receive SIGILL signal otherwise
Even with some extra work, using the uretprobes syscall shows speed
improvement (compared to using standard breakpoint):
On Intel (11th Gen Intel(R) Core(TM) i7-1165G7 @ 2.80GHz)
current:
uretprobe-nop : 1.498 ± 0.000M/s
uretprobe-push : 1.448 ± 0.001M/s
uretprobe-ret : 0.816 ± 0.001M/s
with the fix:
uretprobe-nop : 1.969 ± 0.002M/s < 31% speed up
uretprobe-push : 1.910 ± 0.000M/s < 31% speed up
uretprobe-ret : 0.934 ± 0.000M/s < 14% speed up
On Amd (AMD Ryzen 7 5700U)
current:
uretprobe-nop : 0.778 ± 0.001M/s
uretprobe-push : 0.744 ± 0.001M/s
uretprobe-ret : 0.540 ± 0.001M/s
with the fix:
uretprobe-nop : 0.860 ± 0.001M/s < 10% speed up
uretprobe-push : 0.818 ± 0.001M/s < 10% speed up
uretprobe-ret : 0.578 ± 0.000M/s < 7% speed up
The performance test spawns a thread that runs loop which triggers
uprobe with attached bpf program that increments the counter that
gets printed in results above.
The uprobe (and uretprobe) kind is determined by which instruction
is being patched with breakpoint instruction. That's also important
for uretprobes, because uprobe is installed for each uretprobe.
The performance test is part of bpf selftests:
tools/testing/selftests/bpf/run_bench_uprobes.sh
Note at the moment uretprobe syscall is supported only for native
64-bit process, compat process still uses standard breakpoint.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
arch/x86/kernel/uprobes.c | 115 ++++++++++++++++++++++++++++++++++++++
include/linux/uprobes.h | 3 +
kernel/events/uprobes.c | 24 +++++---
3 files changed, 135 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c07f6daaa22..81e6ee95784d 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -12,6 +12,7 @@
#include <linux/ptrace.h>
#include <linux/uprobes.h>
#include <linux/uaccess.h>
+#include <linux/syscalls.h>
#include <linux/kdebug.h>
#include <asm/processor.h>
@@ -308,6 +309,120 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
}
#ifdef CONFIG_X86_64
+
+asm (
+ ".pushsection .rodata\n"
+ ".global uretprobe_syscall_entry\n"
+ "uretprobe_syscall_entry:\n"
+ "pushq %rax\n"
+ "pushq %rcx\n"
+ "pushq %r11\n"
+ "movq $" __stringify(__NR_uretprobe) ", %rax\n"
+ "syscall\n"
+ ".global uretprobe_syscall_check\n"
+ "uretprobe_syscall_check:\n"
+ "popq %r11\n"
+ "popq %rcx\n"
+
+ /* The uretprobe syscall replaces stored %rax value with final
+ * return address, so we don't restore %rax in here and just
+ * call ret.
+ */
+ "retq\n"
+ ".global uretprobe_syscall_end\n"
+ "uretprobe_syscall_end:\n"
+ ".popsection\n"
+);
+
+extern u8 uretprobe_syscall_entry[];
+extern u8 uretprobe_syscall_check[];
+extern u8 uretprobe_syscall_end[];
+
+void *arch_uprobe_trampoline(unsigned long *psize)
+{
+ static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+ struct pt_regs *regs = task_pt_regs(current);
+
+ /*
+ * At the moment the uretprobe syscall trampoline is supported
+ * only for native 64-bit process, the compat process still uses
+ * standard breakpoint.
+ */
+ if (user_64bit_mode(regs)) {
+ *psize = uretprobe_syscall_end - uretprobe_syscall_entry;
+ return uretprobe_syscall_entry;
+ }
+
+ *psize = UPROBE_SWBP_INSN_SIZE;
+ return &insn;
+}
+
+static unsigned long trampoline_check_ip(void)
+{
+ unsigned long tramp = uprobe_get_trampoline_vaddr();
+
+ return tramp + (uretprobe_syscall_check - uretprobe_syscall_entry);
+}
+
+SYSCALL_DEFINE0(uretprobe)
+{
+ struct pt_regs *regs = task_pt_regs(current);
+ unsigned long err, ip, sp, r11_cx_ax[3];
+
+ if (regs->ip != trampoline_check_ip())
+ goto sigill;
+
+ err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
+ if (err)
+ goto sigill;
+
+ /* expose the "right" values of r11/cx/ax/sp to uprobe_consumer/s */
+ regs->r11 = r11_cx_ax[0];
+ regs->cx = r11_cx_ax[1];
+ regs->ax = r11_cx_ax[2];
+ regs->sp += sizeof(r11_cx_ax);
+ regs->orig_ax = -1;
+
+ ip = regs->ip;
+ sp = regs->sp;
+
+ uprobe_handle_trampoline(regs);
+
+ /*
+ * uprobe_consumer has changed sp, we can do nothing,
+ * just return via iret
+ */
+ if (regs->sp != sp)
+ return regs->ax;
+ regs->sp -= sizeof(r11_cx_ax);
+
+ /* for the case uprobe_consumer has changed r11/cx */
+ r11_cx_ax[0] = regs->r11;
+ r11_cx_ax[1] = regs->cx;
+
+ /*
+ * ax register is passed through as return value, so we can use
+ * its space on stack for ip value and jump to it through the
+ * trampoline's ret instruction
+ */
+ r11_cx_ax[2] = regs->ip;
+ regs->ip = ip;
+
+ err = copy_to_user((void __user *)regs->sp, r11_cx_ax, sizeof(r11_cx_ax));
+ if (err)
+ goto sigill;
+
+ /* ensure sysret, see do_syscall_64() */
+ regs->r11 = regs->flags;
+ regs->cx = regs->ip;
+
+ return regs->ax;
+
+sigill:
+ force_sig(SIGILL);
+ return -1;
+}
+
/*
* If arch_uprobe->insn doesn't use rip-relative addressing, return
* immediately. Otherwise, rewrite the instruction so that it accesses
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index f46e0ca0169c..b503fafb7fb3 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -138,6 +138,9 @@ extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c
extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *src, unsigned long len);
+extern void uprobe_handle_trampoline(struct pt_regs *regs);
+extern void *arch_uprobe_trampoline(unsigned long *psize);
+extern unsigned long uprobe_get_trampoline_vaddr(void);
#else /* !CONFIG_UPROBES */
struct uprobes_state {
};
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index e4834d23e1d1..c550449d66be 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1474,11 +1474,20 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
return ret;
}
+void * __weak arch_uprobe_trampoline(unsigned long *psize)
+{
+ static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+
+ *psize = UPROBE_SWBP_INSN_SIZE;
+ return &insn;
+}
+
static struct xol_area *__create_xol_area(unsigned long vaddr)
{
struct mm_struct *mm = current->mm;
- uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+ unsigned long insns_size;
struct xol_area *area;
+ void *insns;
area = kmalloc(sizeof(*area), GFP_KERNEL);
if (unlikely(!area))
@@ -1502,7 +1511,8 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
/* Reserve the 1st slot for get_trampoline_vaddr() */
set_bit(0, area->bitmap);
atomic_set(&area->slot_count, 1);
- arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);
+ insns = arch_uprobe_trampoline(&insns_size);
+ arch_uprobe_copy_ixol(area->pages[0], 0, insns, insns_size);
if (!xol_add_vma(mm, area))
return area;
@@ -1827,7 +1837,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
*
* Returns -1 in case the xol_area is not allocated.
*/
-static unsigned long get_trampoline_vaddr(void)
+unsigned long uprobe_get_trampoline_vaddr(void)
{
struct xol_area *area;
unsigned long trampoline_vaddr = -1;
@@ -1878,7 +1888,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
if (!ri)
return;
- trampoline_vaddr = get_trampoline_vaddr();
+ trampoline_vaddr = uprobe_get_trampoline_vaddr();
orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
if (orig_ret_vaddr == -1)
goto fail;
@@ -2123,7 +2133,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri)
return ri;
}
-static void handle_trampoline(struct pt_regs *regs)
+void uprobe_handle_trampoline(struct pt_regs *regs)
{
struct uprobe_task *utask;
struct return_instance *ri, *next;
@@ -2187,8 +2197,8 @@ static void handle_swbp(struct pt_regs *regs)
int is_swbp;
bp_vaddr = uprobe_get_swbp_addr(regs);
- if (bp_vaddr == get_trampoline_vaddr())
- return handle_trampoline(regs);
+ if (bp_vaddr == uprobe_get_trampoline_vaddr())
+ return uprobe_handle_trampoline(regs);
uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
if (!uprobe) {
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 1/7] uprobe: Wire up uretprobe system call
From: Jiri Olsa @ 2024-04-21 19:42 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
In-Reply-To: <20240421194206.1010934-1-jolsa@kernel.org>
Wiring up uretprobe system call, which comes in following changes.
We need to do the wiring before, because the uretprobe implementation
needs the syscall number.
Note at the moment uretprobe syscall is supported only for native
64-bit process.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
include/linux/syscalls.h | 2 ++
include/uapi/asm-generic/unistd.h | 5 ++++-
kernel/sys_ni.c | 2 ++
4 files changed, 9 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 7e8d46f4147f..af0a33ab06ee 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -383,6 +383,7 @@
459 common lsm_get_self_attr sys_lsm_get_self_attr
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
+462 64 uretprobe sys_uretprobe
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e619ac10cd23..5318e0e76799 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -972,6 +972,8 @@ asmlinkage long sys_lsm_list_modules(u64 *ids, u32 *size, u32 flags);
/* x86 */
asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
+asmlinkage long sys_uretprobe(void);
+
/* pciconfig: alpha, arm, arm64, ia64, sparc */
asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
unsigned long off, unsigned long len,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 75f00965ab15..8a747cd1d735 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -842,8 +842,11 @@ __SYSCALL(__NR_lsm_set_self_attr, sys_lsm_set_self_attr)
#define __NR_lsm_list_modules 461
__SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
+#define __NR_uretprobe 462
+__SYSCALL(__NR_uretprobe, sys_uretprobe)
+
#undef __NR_syscalls
-#define __NR_syscalls 462
+#define __NR_syscalls 463
/*
* 32 bit systems traditionally used different
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index faad00cce269..be6195e0d078 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -391,3 +391,5 @@ COND_SYSCALL(setuid16);
/* restartable sequence */
COND_SYSCALL(rseq);
+
+COND_SYSCALL(uretprobe);
--
2.44.0
^ permalink raw reply related
* [PATCHv3 bpf-next 0/7] uprobe: uretprobe speed up
From: Jiri Olsa @ 2024-04-21 19:41 UTC (permalink / raw)
To: Steven Rostedt, Masami Hiramatsu, Oleg Nesterov,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko
Cc: linux-kernel, linux-trace-kernel, linux-api, x86, bpf, Song Liu,
Yonghong Song, John Fastabend, Peter Zijlstra, Thomas Gleixner,
Borislav Petkov (AMD), Ingo Molnar, Andy Lutomirski
hi,
as part of the effort on speeding up the uprobes [0] coming with
return uprobe optimization by using syscall instead of the trap
on the uretprobe trampoline.
The speed up depends on instruction type that uprobe is installed
and depends on specific HW type, please check patch 1 for details.
Patches 1-6 are based on bpf-next/master, but path 1 and 2 are
apply-able on linux-trace.git tree probes/for-next branch.
Patch 7 is based on man-pages master.
v3 changes:
- added source ip check if the uretprobe syscall is called from
trampoline and sending SIGILL to process if it's not
- keep x86 compat process to use standard breakpoint
- split syscall wiring into separate change
- ran ltp and syzkaller locally, no issues found [Masami]
- building uprobe_compat binary in selftests which breaks
CI atm because of missing 32-bit delve packages, I will
need to fix that in separate changes once this is acked
- added man page change
- there were several changes so I removed acks [Oleg Andrii]
Also available at:
https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
uretprobe_syscall
thanks,
jirka
Notes to check list items in Documentation/process/adding-syscalls.rst:
- System Call Alternatives
New syscall seems like the best way in here, becase we need
just to quickly enter kernel with no extra arguments processing,
which we'd need to do if we decided to use another syscall.
- Designing the API: Planning for Extension
The uretprobe syscall is very specific and most likely won't be
extended in the future.
At the moment it does not take any arguments and even if it does
in future, it's allowed to be called only from trampoline prepared
by kernel, so there'll be no broken user.
- Designing the API: Other Considerations
N/A because uretprobe syscall does not return reference to kernel
object.
- Proposing the API
Wiring up of the uretprobe system call si in separate change,
selftests and man page changes are part of the patchset.
- Generic System Call Implementation
There's no CONFIG option for the new functionality because it
keeps the same behaviour from the user POV.
- x86 System Call Implementation
It's 64-bit syscall only.
- Compatibility System Calls (Generic)
N/A uretprobe syscall has no arguments and is not supported
for compat processes.
- Compatibility System Calls (x86)
N/A uretprobe syscall is not supported for compat processes.
- System Calls Returning Elsewhere
N/A.
- Other Details
N/A.
- Testing
Adding new bpf selftests and ran ltp on top of this change.
- Man Page
Attached.
- Do not call System Calls in the Kernel
N/A.
[0] https://lore.kernel.org/bpf/ZeCXHKJ--iYYbmLj@krava/
---
Jiri Olsa (6):
uprobe: Wire up uretprobe system call
uprobe: Add uretprobe syscall to speed up return probe
selftests/bpf: Add uretprobe syscall test for regs integrity
selftests/bpf: Add uretprobe syscall test for regs changes
selftests/bpf: Add uretprobe syscall call from user space test
selftests/bpf: Add uretprobe compat test
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
arch/x86/kernel/uprobes.c | 115 ++++++++++++++++++++++++++++++
include/linux/syscalls.h | 2 +
include/linux/uprobes.h | 3 +
include/uapi/asm-generic/unistd.h | 5 +-
kernel/events/uprobes.c | 24 +++++--
kernel/sys_ni.c | 2 +
tools/include/linux/compiler.h | 4 ++
tools/testing/selftests/bpf/.gitignore | 1 +
tools/testing/selftests/bpf/Makefile | 6 +-
tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c | 123 +++++++++++++++++++++++++++++++-
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c | 362 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
tools/testing/selftests/bpf/progs/uprobe_syscall.c | 15 ++++
tools/testing/selftests/bpf/progs/uprobe_syscall_call.c | 15 ++++
tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c | 13 ++++
15 files changed, 681 insertions(+), 10 deletions(-)
create mode 100644 tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall.c
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_call.c
create mode 100644 tools/testing/selftests/bpf/progs/uprobe_syscall_compat.c
Jiri Olsa (1):
man2: Add uretprobe syscall page
man2/uretprobe.2 | 40 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
create mode 100644 man2/uretprobe.2
^ permalink raw reply
* Re: [PATCH v4 00/30] NT synchronization primitive driver
From: Elizabeth Figura @ 2024-04-19 20:46 UTC (permalink / raw)
To: Peter Zijlstra
Cc: wine-devel, Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet,
Shuah Khan, linux-kernel, linux-api, André Almeida,
Wolfram Sang, Andy Lutomirski, linux-doc, linux-kselftest,
Randy Dunlap, Ingo Molnar, Will Deacon, Waiman Long, Boqun Feng
In-Reply-To: <20240419161611.GA23130@noisy.programming.kicks-ass.net>
On Friday, 19 April 2024 11:16:11 CDT Peter Zijlstra wrote:
> On Tue, Apr 16, 2024 at 05:18:56PM -0500, Elizabeth Figura wrote:
> > On Tuesday, 16 April 2024 16:18:24 CDT Elizabeth Figura wrote:
> > > On Tuesday, 16 April 2024 03:14:21 CDT Peter Zijlstra wrote:
> > > > I don't support GE has it in his builds? Last time I tried, building
> > > > Wine was a bit of a pain.
> > >
> > > It doesn't seem so. I tried to build a GE-compatible ntsync build, uploaded
> > > here (thanks Arek for hosting):
> > >
> > > https://f002.backblazeb2.com/file/wine-ntsync/ntsync-wine.tar.xz
> >
> > Oops, the initial version I uploaded had broken paths. Should be fixed now.
> >
> > (It's also broken on an unpatched kernel unless explicitly disabled with
> > WINE_DISABLE_FAST_SYNC=1. Not sure what I messed up there—it should fall back
> > cleanly—but hopefully shouldn't be too important for testing.)
>
> So I've tried using that wine build with lutris, and I can't get it to
> start EGS or anything else.
>
> I even added a printk to the ntsync driver for every open, to see if it
> gets that far, but I'm not even getting that :/
That's odd, it works for me, both as a standalone build and with
lutris...
Does /dev/ntsync exist (module is loaded) and have nonzero permissions?
I forgot to mention that's necessary, sorry.
Otherwise I can try to look at an strace, or a Wine debug log. I don't
think there's an easy way to get the latter with Lutris, but something
like `WINEDEBUG=+all ./wine winecfg 2>log` should work.
^ permalink raw reply
* Re: [PATCH v4 02/27] ntsync: Introduce NTSYNC_IOC_WAIT_ALL.
From: Peter Zijlstra @ 2024-04-19 16:28 UTC (permalink / raw)
To: Elizabeth Figura
Cc: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan,
linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Andy Lutomirski, linux-doc,
linux-kselftest, Randy Dunlap, Ingo Molnar, Will Deacon,
Waiman Long, Boqun Feng
In-Reply-To: <20240418093511.GQ40213@noisy.programming.kicks-ass.net>
On Thu, Apr 18, 2024 at 11:35:11AM +0200, Peter Zijlstra wrote:
> On Wed, Apr 17, 2024 at 03:03:05PM -0500, Elizabeth Figura wrote:
>
> > Ach. I wrote this with the idea that the race isn't meaningful, but
> > looking at it again you're right—there is a harmful race here.
> >
> > I think it should be fixable by moving the atomic_read inside the lock,
> > though.
>
> Right, I've ended up with the (as yet untested) below. I'll see if I can
> find time later to actually test things.
Latest hackery... I tried testing this but I'm not having luck using the
patched wine as per the other email.
---
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -18,6 +18,7 @@
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/mutex.h>
#include <uapi/linux/ntsync.h>
#define NTSYNC_NAME "ntsync"
@@ -43,6 +44,7 @@ enum ntsync_type {
struct ntsync_obj {
spinlock_t lock;
+ int dev_locked;
enum ntsync_type type;
@@ -132,14 +134,107 @@ struct ntsync_device {
* wait_all_lock is taken first whenever multiple objects must be locked
* at the same time.
*/
- spinlock_t wait_all_lock;
+ struct mutex wait_all_lock;
struct file *file;
};
+/*
+ * Single objects are locked using obj->lock.
+ *
+ * Multiple objects are 'locked' while holding dev->wait_all_lock to avoid lock
+ * order issues. In this case however, single objects are not locked by holding
+ * obj->lock, but by setting obj->dev_locked.
+ *
+ * This means that in order to lock a single object, the sequence is slightly
+ * more complicated than usual. Specifically it needs to check obj->dev_locked
+ * after acquiring obj->lock, if set, it needs to drop the lock and acquire
+ * dev->wait_all_lock in order to serialize against the multi-object operation.
+ */
+
+static void dev_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+ lockdep_assert_held(&dev->wait_all_lock);
+ lockdep_assert(obj->dev == dev);
+ spin_lock(&obj->lock);
+ /*
+ * By setting obj->dev_locked inside obj->lock, it is ensured that
+ * anyone holding obj->lock must see the value.
+ */
+ obj->dev_locked = 1;
+ spin_unlock(&obj->lock);
+}
+
+static void dev_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+ lockdep_assert_held(&dev->wait_all_lock);
+ lockdep_assert(obj->dev == dev);
+ spin_lock(&obj->lock);
+ obj->dev_locked = 0;
+ spin_unlock(&obj->lock);
+}
+
+static void obj_lock(struct ntsync_obj *obj)
+{
+ struct ntsync_device *dev = obj->dev;
+
+ for (;;) {
+ spin_lock(&obj->lock);
+ if (likely(!obj->dev_locked))
+ break;
+
+ spin_unlock(&obj->lock);
+ mutex_lock(&dev->wait_all_lock);
+ spin_lock(&obj->lock);
+ /*
+ * obj->dev_locked should be set and released under the same
+ * wait_all_lock section, since we now own this lock, it should
+ * be clear.
+ */
+ lockdep_assert(!obj->dev_locked);
+ spin_unlock(&obj->lock);
+ mutex_unlock(&dev->wait_all_lock);
+ }
+}
+
+static void obj_unlock(struct ntsync_obj *obj)
+{
+ spin_unlock(&obj->lock);
+}
+
+static bool ntsync_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+ bool all;
+
+ obj_lock(obj);
+ all = atomic_read(&obj->all_hint);
+ if (unlikely(all)) {
+ obj_unlock(obj);
+ mutex_lock(&dev->wait_all_lock);
+ dev_lock_obj(dev, obj);
+ }
+
+ return all;
+}
+
+static void ntsync_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj, bool all)
+{
+ if (all) {
+ dev_unlock_obj(dev, obj);
+ mutex_unlock(&dev->wait_all_lock);
+ } else {
+ obj_unlock(obj);
+ }
+}
+
+#define ntsync_assert_held(obj) \
+ lockdep_assert((lockdep_is_held(&(obj)->lock) != LOCK_STATE_NOT_HELD) || \
+ ((lockdep_is_held(&(obj)->dev->wait_all_lock) != LOCK_STATE_NOT_HELD) && \
+ (obj)->dev_locked))
+
static bool is_signaled(struct ntsync_obj *obj, __u32 owner)
{
- lockdep_assert_held(&obj->lock);
+ ntsync_assert_held(obj);
switch (obj->type) {
case NTSYNC_TYPE_SEM:
@@ -171,11 +266,11 @@ static void try_wake_all(struct ntsync_d
lockdep_assert_held(&dev->wait_all_lock);
if (locked_obj)
- lockdep_assert_held(&locked_obj->lock);
+ lockdep_assert(locked_obj->dev_locked);
for (i = 0; i < count; i++) {
if (q->entries[i].obj != locked_obj)
- spin_lock_nest_lock(&q->entries[i].obj->lock, &dev->wait_all_lock);
+ dev_lock_obj(dev, q->entries[i].obj);
}
for (i = 0; i < count; i++) {
@@ -211,7 +306,7 @@ static void try_wake_all(struct ntsync_d
for (i = 0; i < count; i++) {
if (q->entries[i].obj != locked_obj)
- spin_unlock(&q->entries[i].obj->lock);
+ dev_unlock_obj(dev, q->entries[i].obj);
}
}
@@ -220,7 +315,7 @@ static void try_wake_all_obj(struct ntsy
struct ntsync_q_entry *entry;
lockdep_assert_held(&dev->wait_all_lock);
- lockdep_assert_held(&obj->lock);
+ lockdep_assert(obj->dev_locked);
list_for_each_entry(entry, &obj->all_waiters, node)
try_wake_all(dev, entry->q, obj);
@@ -230,7 +325,8 @@ static void try_wake_any_sem(struct ntsy
{
struct ntsync_q_entry *entry;
- lockdep_assert_held(&sem->lock);
+ ntsync_assert_held(sem);
+ lockdep_assert(sem->type == NTSYNC_TYPE_SEM);
list_for_each_entry(entry, &sem->any_waiters, node) {
struct ntsync_q *q = entry->q;
@@ -250,7 +346,8 @@ static void try_wake_any_mutex(struct nt
{
struct ntsync_q_entry *entry;
- lockdep_assert_held(&mutex->lock);
+ ntsync_assert_held(mutex);
+ lockdep_assert(mutex->type == NTSYNC_TYPE_MUTEX);
list_for_each_entry(entry, &mutex->any_waiters, node) {
struct ntsync_q *q = entry->q;
@@ -276,7 +373,8 @@ static void try_wake_any_event(struct nt
{
struct ntsync_q_entry *entry;
- lockdep_assert_held(&event->lock);
+ ntsync_assert_held(event);
+ lockdep_assert(event->type == NTSYNC_TYPE_EVENT);
list_for_each_entry(entry, &event->any_waiters, node) {
struct ntsync_q *q = entry->q;
@@ -302,6 +400,7 @@ static int post_sem_state(struct ntsync_
__u32 sum;
lockdep_assert_held(&sem->lock);
+ lockdep_assert(sem->type == NTSYNC_TYPE_SEM);
if (check_add_overflow(sem->u.sem.count, count, &sum) ||
sum > sem->u.sem.max)
@@ -317,6 +416,7 @@ static int ntsync_sem_post(struct ntsync
__u32 __user *user_args = argp;
__u32 prev_count;
__u32 args;
+ bool all;
int ret;
if (copy_from_user(&args, argp, sizeof(args)))
@@ -325,30 +425,18 @@ static int ntsync_sem_post(struct ntsync
if (sem->type != NTSYNC_TYPE_SEM)
return -EINVAL;
- if (atomic_read(&sem->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&sem->lock, &dev->wait_all_lock);
-
- prev_count = sem->u.sem.count;
- ret = post_sem_state(sem, args);
- if (!ret) {
- try_wake_all_obj(dev, sem);
- try_wake_any_sem(sem);
- }
-
- spin_unlock(&sem->lock);
- spin_unlock(&dev->wait_all_lock);
- } else {
- spin_lock(&sem->lock);
+ all = ntsync_lock_obj(dev, sem);
- prev_count = sem->u.sem.count;
- ret = post_sem_state(sem, args);
- if (!ret)
- try_wake_any_sem(sem);
-
- spin_unlock(&sem->lock);
+ prev_count = sem->u.sem.count;
+ ret = post_sem_state(sem, args);
+ if (!ret) {
+ if (all)
+ try_wake_all_obj(dev, sem);
+ try_wake_any_sem(sem);
}
+ ntsync_unlock_obj(dev, sem, all);
+
if (!ret && put_user(prev_count, user_args))
ret = -EFAULT;
@@ -377,6 +465,7 @@ static int ntsync_mutex_unlock(struct nt
struct ntsync_device *dev = mutex->dev;
struct ntsync_mutex_args args;
__u32 prev_count;
+ bool all;
int ret;
if (copy_from_user(&args, argp, sizeof(args)))
@@ -387,30 +476,18 @@ static int ntsync_mutex_unlock(struct nt
if (mutex->type != NTSYNC_TYPE_MUTEX)
return -EINVAL;
- if (atomic_read(&mutex->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&mutex->lock, &dev->wait_all_lock);
-
- prev_count = mutex->u.mutex.count;
- ret = unlock_mutex_state(mutex, &args);
- if (!ret) {
- try_wake_all_obj(dev, mutex);
- try_wake_any_mutex(mutex);
- }
+ all = ntsync_lock_obj(dev, mutex);
- spin_unlock(&mutex->lock);
- spin_unlock(&dev->wait_all_lock);
- } else {
- spin_lock(&mutex->lock);
-
- prev_count = mutex->u.mutex.count;
- ret = unlock_mutex_state(mutex, &args);
- if (!ret)
- try_wake_any_mutex(mutex);
-
- spin_unlock(&mutex->lock);
+ prev_count = mutex->u.mutex.count;
+ ret = unlock_mutex_state(mutex, &args);
+ if (!ret) {
+ if (all)
+ try_wake_all_obj(dev, mutex);
+ try_wake_any_mutex(mutex);
}
+ ntsync_unlock_obj(dev, mutex, all);
+
if (!ret && put_user(prev_count, &user_args->count))
ret = -EFAULT;
@@ -438,6 +515,7 @@ static int ntsync_mutex_kill(struct ntsy
{
struct ntsync_device *dev = mutex->dev;
__u32 owner;
+ bool all;
int ret;
if (get_user(owner, (__u32 __user *)argp))
@@ -448,28 +526,17 @@ static int ntsync_mutex_kill(struct ntsy
if (mutex->type != NTSYNC_TYPE_MUTEX)
return -EINVAL;
- if (atomic_read(&mutex->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&mutex->lock, &dev->wait_all_lock);
+ all = ntsync_lock_obj(dev, mutex);
- ret = kill_mutex_state(mutex, owner);
- if (!ret) {
+ ret = kill_mutex_state(mutex, owner);
+ if (!ret) {
+ if (all)
try_wake_all_obj(dev, mutex);
- try_wake_any_mutex(mutex);
- }
-
- spin_unlock(&mutex->lock);
- spin_unlock(&dev->wait_all_lock);
- } else {
- spin_lock(&mutex->lock);
-
- ret = kill_mutex_state(mutex, owner);
- if (!ret)
- try_wake_any_mutex(mutex);
-
- spin_unlock(&mutex->lock);
+ try_wake_any_mutex(mutex);
}
+ ntsync_unlock_obj(dev, mutex, all);
+
return ret;
}
@@ -477,34 +544,22 @@ static int ntsync_event_set(struct ntsyn
{
struct ntsync_device *dev = event->dev;
__u32 prev_state;
+ bool all;
if (event->type != NTSYNC_TYPE_EVENT)
return -EINVAL;
- if (atomic_read(&event->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&event->lock, &dev->wait_all_lock);
+ all = ntsync_lock_obj(dev, event);
- prev_state = event->u.event.signaled;
- event->u.event.signaled = true;
+ prev_state = event->u.event.signaled;
+ event->u.event.signaled = true;
+ if (all)
try_wake_all_obj(dev, event);
- try_wake_any_event(event);
- if (pulse)
- event->u.event.signaled = false;
+ try_wake_any_event(event);
+ if (pulse)
+ event->u.event.signaled = false;
- spin_unlock(&event->lock);
- spin_unlock(&dev->wait_all_lock);
- } else {
- spin_lock(&event->lock);
-
- prev_state = event->u.event.signaled;
- event->u.event.signaled = true;
- try_wake_any_event(event);
- if (pulse)
- event->u.event.signaled = false;
-
- spin_unlock(&event->lock);
- }
+ ntsync_unlock_obj(dev, event, all);
if (put_user(prev_state, (__u32 __user *)argp))
return -EFAULT;
@@ -984,7 +1039,7 @@ static int ntsync_wait_all(struct ntsync
/* queue ourselves */
- spin_lock(&dev->wait_all_lock);
+ mutex_lock(&dev->wait_all_lock);
for (i = 0; i < args.count; i++) {
struct ntsync_q_entry *entry = &q->entries[i];
@@ -1004,7 +1059,7 @@ static int ntsync_wait_all(struct ntsync
try_wake_all(dev, q, NULL);
- spin_unlock(&dev->wait_all_lock);
+ mutex_unlock(&dev->wait_all_lock);
/* sleep */
@@ -1012,7 +1067,7 @@ static int ntsync_wait_all(struct ntsync
/* and finally, unqueue */
- spin_lock(&dev->wait_all_lock);
+ mutex_lock(&dev->wait_all_lock);
for (i = 0; i < args.count; i++) {
struct ntsync_q_entry *entry = &q->entries[i];
@@ -1029,7 +1084,7 @@ static int ntsync_wait_all(struct ntsync
put_obj(obj);
}
- spin_unlock(&dev->wait_all_lock);
+ mutex_unlock(&dev->wait_all_lock);
signaled = atomic_read(&q->signaled);
if (signaled != -1) {
@@ -1056,7 +1111,7 @@ static int ntsync_char_open(struct inode
if (!dev)
return -ENOMEM;
- spin_lock_init(&dev->wait_all_lock);
+ mutex_init(&dev->wait_all_lock);
file->private_data = dev;
dev->file = file;
^ permalink raw reply
* Re: [PATCH v4 00/30] NT synchronization primitive driver
From: Peter Zijlstra @ 2024-04-19 16:16 UTC (permalink / raw)
To: Elizabeth Figura
Cc: wine-devel, Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet,
Shuah Khan, linux-kernel, linux-api, André Almeida,
Wolfram Sang, Andy Lutomirski, linux-doc, linux-kselftest,
Randy Dunlap, Ingo Molnar, Will Deacon, Waiman Long, Boqun Feng
In-Reply-To: <3743440.MHq7AAxBmi@terabithia>
On Tue, Apr 16, 2024 at 05:18:56PM -0500, Elizabeth Figura wrote:
> On Tuesday, 16 April 2024 16:18:24 CDT Elizabeth Figura wrote:
> > On Tuesday, 16 April 2024 03:14:21 CDT Peter Zijlstra wrote:
> > > I don't support GE has it in his builds? Last time I tried, building
> > > Wine was a bit of a pain.
> >
> > It doesn't seem so. I tried to build a GE-compatible ntsync build, uploaded
> > here (thanks Arek for hosting):
> >
> > https://f002.backblazeb2.com/file/wine-ntsync/ntsync-wine.tar.xz
>
> Oops, the initial version I uploaded had broken paths. Should be fixed now.
>
> (It's also broken on an unpatched kernel unless explicitly disabled with
> WINE_DISABLE_FAST_SYNC=1. Not sure what I messed up there—it should fall back
> cleanly—but hopefully shouldn't be too important for testing.)
So I've tried using that wine build with lutris, and I can't get it to
start EGS or anything else.
I even added a printk to the ntsync driver for every open, to see if it
gets that far, but I'm not even getting that :/
^ permalink raw reply
* Re: [PATCH v5 2/3] VT: Add KDFONTINFO ioctl
From: Alexey Gladkov @ 2024-04-18 10:45 UTC (permalink / raw)
To: Helge Deller
Cc: Greg Kroah-Hartman, Jiri Slaby, LKML, kbd, linux-api, linux-fbdev,
linux-serial
In-Reply-To: <9019dc74-35ad-43d7-8763-cea3da93e9c1@gmx.de>
On Wed, Apr 17, 2024 at 09:31:53PM +0200, Helge Deller wrote:
> On 4/17/24 19:37, Alexey Gladkov wrote:
> > Each driver has its own restrictions on font size. There is currently no
> > way to understand what the requirements are. The new ioctl allows
> > userspace to get the minimum and maximum font size values.
> >
> > Acked-by: Helge Deller <deller@gmx.de>
> > Signed-off-by: Alexey Gladkov <legion@kernel.org>
> > ---
> > drivers/tty/vt/vt.c | 24 ++++++++++++++++++++++++
> > drivers/tty/vt/vt_ioctl.c | 13 +++++++++++++
> > include/linux/console.h | 3 +++
> > include/linux/vt_kern.h | 1 +
> > include/uapi/linux/kd.h | 14 ++++++++++++++
> > 5 files changed, 55 insertions(+)
> >
> > diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
> > index 9b5b98dfc8b4..e8db0e9ea674 100644
> > --- a/drivers/tty/vt/vt.c
> > +++ b/drivers/tty/vt/vt.c
> > @@ -4851,6 +4851,30 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op)
> > return -ENOSYS;
> > }
> >
> > +int con_font_info(struct vc_data *vc, struct console_font_info *info)
> > +{
> > + int rc;
> > +
> > + info->min_height = 0;
> > + info->max_height = max_font_height;
> > +
> > + info->min_width = 0;
> > + info->max_width = max_font_width;
> > +
> > + info->flags = KD_FONT_INFO_FLAG_LOW_SIZE | KD_FONT_INFO_FLAG_HIGH_SIZE;
> > +
> > + console_lock();
> > + if (vc->vc_mode != KD_TEXT)
> > + rc = -EINVAL;
> > + else if (vc->vc_sw->con_font_info)
> > + rc = vc->vc_sw->con_font_info(vc, info);
> > + else
> > + rc = -ENOSYS;
> > + console_unlock();
> > +
> > + return rc;
> > +}
> > +
> > /*
> > * Interface exported to selection and vcs.
> > */
> > diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
> > index 4b91072f3a4e..9a2f8081f650 100644
> > --- a/drivers/tty/vt/vt_ioctl.c
> > +++ b/drivers/tty/vt/vt_ioctl.c
> > @@ -479,6 +479,19 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd,
> > break;
> > }
> >
> > + case KDFONTINFO: {
> > + struct console_font_info fnt_info;
> > +
> > + memset(&fnt_info, 0, sizeof(fnt_info));
> > +
> > + ret = con_font_info(vc, &fnt_info);
> > + if (ret)
> > + return ret;
> > + if (copy_to_user(up, &fnt_info, sizeof(fnt_info)))
> > + return -EFAULT;
> > + break;
> > + }
> > +
> > default:
> > return -ENOIOCTLCMD;
> > }
> > diff --git a/include/linux/console.h b/include/linux/console.h
> > index 31a8f5b85f5d..4b798322aa01 100644
> > --- a/include/linux/console.h
> > +++ b/include/linux/console.h
> > @@ -21,6 +21,7 @@
> > #include <linux/vesa.h>
> >
> > struct vc_data;
> > +struct console_font_info;
> > struct console_font_op;
> > struct console_font;
> > struct module;
> > @@ -102,6 +103,8 @@ struct consw {
> > bool (*con_switch)(struct vc_data *vc);
> > bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank,
> > bool mode_switch);
> > + int (*con_font_info)(struct vc_data *vc,
> > + struct console_font_info *info);
> > int (*con_font_set)(struct vc_data *vc,
> > const struct console_font *font,
> > unsigned int vpitch, unsigned int flags);
> > diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
> > index d008c3d0a9bb..383b3a4f6113 100644
> > --- a/include/linux/vt_kern.h
> > +++ b/include/linux/vt_kern.h
> > @@ -33,6 +33,7 @@ void do_blank_screen(int entering_gfx);
> > void do_unblank_screen(int leaving_gfx);
> > void poke_blanked_console(void);
> > int con_font_op(struct vc_data *vc, struct console_font_op *op);
> > +int con_font_info(struct vc_data *vc, struct console_font_info *info);
> > int con_set_cmap(unsigned char __user *cmap);
> > int con_get_cmap(unsigned char __user *cmap);
> > void scrollback(struct vc_data *vc);
> > diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h
> > index 8ddb2219a84b..68b715ad4d5c 100644
> > --- a/include/uapi/linux/kd.h
> > +++ b/include/uapi/linux/kd.h
> > @@ -185,6 +185,20 @@ struct console_font {
> >
> > #define KD_FONT_FLAG_DONT_RECALC 1 /* Don't recalculate hw charcell size [compat] */
> >
> > +/* font information */
> > +
> > +#define KD_FONT_INFO_FLAG_LOW_SIZE _BITUL(0) /* 256 */
> > +#define KD_FONT_INFO_FLAG_HIGH_SIZE _BITUL(1) /* 512 */
>
> Do we really need those bits?
> You set a default min/max font size in con_font_info() above,
> and all drivers can override those values.
> So, there are always min/max sizes available.
These bits are not about the minimum and maximum glyph size, but about the
number of glyphs in the font.
Maybe this is an overkill, but sticon has this check:
if ((w < 6) || (h < 6) || (w > 32) || (h > 32) || (vpitch != 32)
|| (op->charcount != 256 && op->charcount != 512))
[ to be honest, I don’t know why this driver doesn’t accept a glyph of
width 4 ]
I thought it would be worth fixing the maximum number of requirements in
the drivers since I started adding a new ioctl.
> > +struct console_font_info {
> > + __u32 flags; /* KD_FONT_INFO_FLAG_* */
>
> One space too much in front of "flags" ?
No problem. I will fix.
>
> > + __u32 min_width, min_height; /* minimal font size */
> > + __u32 max_width, max_height; /* maximum font size */
> > + __u32 reserved[5]; /* This field is reserved for future use. Must be 0. */
> > +};
> > +
> > +#define KDFONTINFO _IOR(KD_IOCTL_BASE, 0x73, struct console_font_info)
> > +
> > /* note: 0x4B00-0x4B4E all have had a value at some time;
> > don't reuse for the time being */
> > /* note: 0x4B60-0x4B6D, 0x4B70-0x4B72 used above */
>
--
Rgrds, legion
^ permalink raw reply
* Re: [PATCH v5 2/3] VT: Add KDFONTINFO ioctl
From: Alexey Gladkov @ 2024-04-18 10:27 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Jiri Slaby, LKML, kbd, linux-api, linux-fbdev, linux-serial,
Helge Deller
In-Reply-To: <2024041830-feisty-gristle-5fd0@gregkh>
On Thu, Apr 18, 2024 at 08:18:33AM +0200, Greg Kroah-Hartman wrote:
> On Wed, Apr 17, 2024 at 07:37:36PM +0200, Alexey Gladkov wrote:
> > Each driver has its own restrictions on font size. There is currently no
> > way to understand what the requirements are. The new ioctl allows
> > userspace to get the minimum and maximum font size values.
>
> Is there any userspace code that uses this yet that we can point to
> here?
Yes. I have a code that uses this. It waits for this ioctl to appear in
the kernel.
https://git.kernel.org/pub/scm/linux/kernel/git/legion/kbd.git/commit/?h=kdfontinfo-v1&id=e2ad0117ca8e46cedd8668934db7b04e9054d5d7
> I know tty ioctls are woefully undocumented, but could there be some
> documentation here?
Yes, this is a big problem for this interface. The ioctl_console(2)
describes PIO_FONT/PIO_FONTX, which is no longer supported, but does not
describe KDFONTOP at all, which is exactly used by userspace.
My TODO has a task to fix this.
But I would suggest creating documentation in the kernel because life
shows that man-page is far behind what is implemented.
> >
> > Acked-by: Helge Deller <deller@gmx.de>
> > Signed-off-by: Alexey Gladkov <legion@kernel.org>
> > ---
> > drivers/tty/vt/vt.c | 24 ++++++++++++++++++++++++
> > drivers/tty/vt/vt_ioctl.c | 13 +++++++++++++
> > include/linux/console.h | 3 +++
> > include/linux/vt_kern.h | 1 +
> > include/uapi/linux/kd.h | 14 ++++++++++++++
> > 5 files changed, 55 insertions(+)
> >
> > diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
> > index 9b5b98dfc8b4..e8db0e9ea674 100644
> > --- a/drivers/tty/vt/vt.c
> > +++ b/drivers/tty/vt/vt.c
> > @@ -4851,6 +4851,30 @@ int con_font_op(struct vc_data *vc, struct console_font_op *op)
> > return -ENOSYS;
> > }
> >
> > +int con_font_info(struct vc_data *vc, struct console_font_info *info)
> > +{
> > + int rc;
> > +
> > + info->min_height = 0;
> > + info->max_height = max_font_height;
> > +
> > + info->min_width = 0;
> > + info->max_width = max_font_width;
> > +
> > + info->flags = KD_FONT_INFO_FLAG_LOW_SIZE | KD_FONT_INFO_FLAG_HIGH_SIZE;
> > +
> > + console_lock();
> > + if (vc->vc_mode != KD_TEXT)
> > + rc = -EINVAL;
> > + else if (vc->vc_sw->con_font_info)
> > + rc = vc->vc_sw->con_font_info(vc, info);
> > + else
> > + rc = -ENOSYS;
> > + console_unlock();
> > +
> > + return rc;
> > +}
> > +
> > /*
> > * Interface exported to selection and vcs.
> > */
> > diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
> > index 4b91072f3a4e..9a2f8081f650 100644
> > --- a/drivers/tty/vt/vt_ioctl.c
> > +++ b/drivers/tty/vt/vt_ioctl.c
> > @@ -479,6 +479,19 @@ static int vt_k_ioctl(struct tty_struct *tty, unsigned int cmd,
> > break;
> > }
> >
> > + case KDFONTINFO: {
> > + struct console_font_info fnt_info;
> > +
> > + memset(&fnt_info, 0, sizeof(fnt_info));
> > +
> > + ret = con_font_info(vc, &fnt_info);
>
> Shouldn't con_font_info() memset it first? No need to do it in the
> caller.
>
> > + if (ret)
> > + return ret;
> > + if (copy_to_user(up, &fnt_info, sizeof(fnt_info)))
> > + return -EFAULT;
> > + break;
> > + }
> > +
> > default:
> > return -ENOIOCTLCMD;
> > }
> > diff --git a/include/linux/console.h b/include/linux/console.h
> > index 31a8f5b85f5d..4b798322aa01 100644
> > --- a/include/linux/console.h
> > +++ b/include/linux/console.h
> > @@ -21,6 +21,7 @@
> > #include <linux/vesa.h>
> >
> > struct vc_data;
> > +struct console_font_info;
> > struct console_font_op;
> > struct console_font;
> > struct module;
> > @@ -102,6 +103,8 @@ struct consw {
> > bool (*con_switch)(struct vc_data *vc);
> > bool (*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank,
> > bool mode_switch);
> > + int (*con_font_info)(struct vc_data *vc,
> > + struct console_font_info *info);
>
> To make the names more obvious, how about:
> con_font_info_get()?
>
> > int (*con_font_set)(struct vc_data *vc,
> > const struct console_font *font,
> > unsigned int vpitch, unsigned int flags);
> > diff --git a/include/linux/vt_kern.h b/include/linux/vt_kern.h
> > index d008c3d0a9bb..383b3a4f6113 100644
> > --- a/include/linux/vt_kern.h
> > +++ b/include/linux/vt_kern.h
> > @@ -33,6 +33,7 @@ void do_blank_screen(int entering_gfx);
> > void do_unblank_screen(int leaving_gfx);
> > void poke_blanked_console(void);
> > int con_font_op(struct vc_data *vc, struct console_font_op *op);
> > +int con_font_info(struct vc_data *vc, struct console_font_info *info);
> > int con_set_cmap(unsigned char __user *cmap);
> > int con_get_cmap(unsigned char __user *cmap);
> > void scrollback(struct vc_data *vc);
> > diff --git a/include/uapi/linux/kd.h b/include/uapi/linux/kd.h
> > index 8ddb2219a84b..68b715ad4d5c 100644
> > --- a/include/uapi/linux/kd.h
> > +++ b/include/uapi/linux/kd.h
> > @@ -185,6 +185,20 @@ struct console_font {
> >
> > #define KD_FONT_FLAG_DONT_RECALC 1 /* Don't recalculate hw charcell size [compat] */
> >
> > +/* font information */
> > +
> > +#define KD_FONT_INFO_FLAG_LOW_SIZE _BITUL(0) /* 256 */
> > +#define KD_FONT_INFO_FLAG_HIGH_SIZE _BITUL(1) /* 512 */
>
> I don't understand why bit 0 and bit 1 have those comments after them.
> That's confusing (i.e. bit 0 is NOT 256...)
>
> > +
> > +struct console_font_info {
> > + __u32 flags; /* KD_FONT_INFO_FLAG_* */
>
> Why are there flags if you are only setting these 2 values? What are
> the flags for?
>
> If this is going to be a "multiplexed" type of structure, then make it a
> union? Or maybe we are totally over thinking this whole thing.
>
> All you want is the min/max font size of the console, right? So perhaps
> the whole structure is just:
>
> > + __u32 min_width, min_height; /* minimal font size */
> > + __u32 max_width, max_height; /* maximum font size */
>
> Those 4 variables? Why have anything else here at all? For any new
> thing you wish to discover, have it be a new ioctl?
>
> > + __u32 reserved[5]; /* This field is reserved for future use. Must be 0. */
>
> I understand the "must be 0" but this is a read-only structure, so
> saying "it will be set to 0" might be better?" Or something like that?
>
> > +};
> > +
> > +#define KDFONTINFO _IOR(KD_IOCTL_BASE, 0x73, struct console_font_info)
>
> As mentioned above how about KDFONTINFOGET?
>
> thanks,
>
> greg k-h
>
--
Rgrds, legion
^ permalink raw reply
* Re: [PATCH v4 02/27] ntsync: Introduce NTSYNC_IOC_WAIT_ALL.
From: Peter Zijlstra @ 2024-04-18 9:35 UTC (permalink / raw)
To: Elizabeth Figura
Cc: Arnd Bergmann, Greg Kroah-Hartman, Jonathan Corbet, Shuah Khan,
linux-kernel, linux-api, wine-devel, André Almeida,
Wolfram Sang, Arkadiusz Hiler, Andy Lutomirski, linux-doc,
linux-kselftest, Randy Dunlap, Ingo Molnar, Will Deacon,
Waiman Long, Boqun Feng
In-Reply-To: <3479054.QJadu78ljV@camazotz>
On Wed, Apr 17, 2024 at 03:03:05PM -0500, Elizabeth Figura wrote:
> Ach. I wrote this with the idea that the race isn't meaningful, but
> looking at it again you're right—there is a harmful race here.
>
> I think it should be fixable by moving the atomic_read inside the lock,
> though.
Right, I've ended up with the (as yet untested) below. I'll see if I can
find time later to actually test things.
---
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -18,6 +18,7 @@
#include <linux/sched/signal.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/mutex.h>
#include <uapi/linux/ntsync.h>
#define NTSYNC_NAME "ntsync"
@@ -43,6 +44,7 @@ enum ntsync_type {
struct ntsync_obj {
spinlock_t lock;
+ int dev_locked;
enum ntsync_type type;
@@ -132,7 +134,7 @@ struct ntsync_device {
* wait_all_lock is taken first whenever multiple objects must be locked
* at the same time.
*/
- spinlock_t wait_all_lock;
+ struct mutex wait_all_lock;
struct file *file;
};
@@ -157,6 +159,56 @@ static bool is_signaled(struct ntsync_ob
}
/*
+ * XXX write coherent comment on the locking
+ */
+
+static void dev_lock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+ lockdep_assert_held(&dev->wait_all_lock);
+ WARN_ON_ONCE(obj->dev != dev);
+ spin_lock(&obj->lock);
+ obj->dev_locked = 1;
+ spin_unlock(&obj->lock);
+}
+
+static void dev_unlock_obj(struct ntsync_device *dev, struct ntsync_obj *obj)
+{
+ lockdep_assert_held(&dev->wait_all_lock);
+ WARN_ON_ONCE(obj->dev != dev);
+ spin_lock(&obj->lock);
+ obj->dev_locked = 0;
+ spin_unlock(&obj->lock);
+}
+
+static void obj_lock(struct ntsync_obj *obj)
+{
+ struct ntsync_device *dev = obj->dev;
+
+ for (;;) {
+ spin_lock(&obj->lock);
+ if (likely(!obj->dev_locked))
+ break;
+
+ spin_unlock(&obj->lock);
+ mutex_lock(&dev->wait_all_lock);
+ spin_lock(&obj->lock);
+ /*
+ * obj->dev_locked should be set and released under the same
+ * wait_all_lock section, since we now own this lock, it should
+ * be clear.
+ */
+ WARN_ON_ONCE(obj->dev_locked);
+ spin_unlock(&obj->lock);
+ mutex_unlock(&dev->wait_all_lock);
+ }
+}
+
+static void obj_unlock(struct ntsync_obj *obj)
+{
+ spin_unlock(&obj->lock);
+}
+
+/*
* "locked_obj" is an optional pointer to an object which is already locked and
* should not be locked again. This is necessary so that changing an object's
* state and waking it can be a single atomic operation.
@@ -175,7 +227,7 @@ static void try_wake_all(struct ntsync_d
for (i = 0; i < count; i++) {
if (q->entries[i].obj != locked_obj)
- spin_lock_nest_lock(&q->entries[i].obj->lock, &dev->wait_all_lock);
+ dev_lock_obj(dev, q->entries[i].obj);
}
for (i = 0; i < count; i++) {
@@ -211,7 +263,7 @@ static void try_wake_all(struct ntsync_d
for (i = 0; i < count; i++) {
if (q->entries[i].obj != locked_obj)
- spin_unlock(&q->entries[i].obj->lock);
+ dev_unlock_obj(dev, q->entries[i].obj);
}
}
@@ -231,6 +283,7 @@ static void try_wake_any_sem(struct ntsy
struct ntsync_q_entry *entry;
lockdep_assert_held(&sem->lock);
+ WARN_ON_ONCE(sem->type != NTSYNC_TYPE_SEM);
list_for_each_entry(entry, &sem->any_waiters, node) {
struct ntsync_q *q = entry->q;
@@ -251,6 +304,7 @@ static void try_wake_any_mutex(struct nt
struct ntsync_q_entry *entry;
lockdep_assert_held(&mutex->lock);
+ WARN_ON_ONCE(mutex->type != NTSYNC_TYPE_MUTEX);
list_for_each_entry(entry, &mutex->any_waiters, node) {
struct ntsync_q *q = entry->q;
@@ -302,6 +356,7 @@ static int post_sem_state(struct ntsync_
__u32 sum;
lockdep_assert_held(&sem->lock);
+ WARN_ON_ONCE(sem->type != NTSYNC_TYPE_SEM);
if (check_add_overflow(sem->u.sem.count, count, &sum) ||
sum > sem->u.sem.max)
@@ -316,6 +371,7 @@ static int ntsync_sem_post(struct ntsync
struct ntsync_device *dev = sem->dev;
__u32 __user *user_args = argp;
__u32 prev_count;
+ bool all = false;
__u32 args;
int ret;
@@ -325,28 +381,27 @@ static int ntsync_sem_post(struct ntsync
if (sem->type != NTSYNC_TYPE_SEM)
return -EINVAL;
- if (atomic_read(&sem->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&sem->lock, &dev->wait_all_lock);
-
- prev_count = sem->u.sem.count;
- ret = post_sem_state(sem, args);
- if (!ret) {
+ obj_lock(sem);
+ all = atomic_read(&sem->all_hint);
+ if (unlikely(all)) {
+ obj_unlock(sem);
+ mutex_lock(&dev->wait_all_lock);
+ dev_lock_obj(dev, sem);
+ }
+
+ prev_count = sem->u.sem.count;
+ ret = post_sem_state(sem, args);
+ if (!ret) {
+ if (all)
try_wake_all_obj(dev, sem);
- try_wake_any_sem(sem);
- }
+ try_wake_any_sem(sem);
+ }
- spin_unlock(&sem->lock);
- spin_unlock(&dev->wait_all_lock);
+ if (all) {
+ dev_unlock_obj(dev, sem);
+ mutex_unlock(&dev->wait_all_lock);
} else {
- spin_lock(&sem->lock);
-
- prev_count = sem->u.sem.count;
- ret = post_sem_state(sem, args);
- if (!ret)
- try_wake_any_sem(sem);
-
- spin_unlock(&sem->lock);
+ obj_unlock(sem);
}
if (!ret && put_user(prev_count, user_args))
@@ -376,6 +431,7 @@ static int ntsync_mutex_unlock(struct nt
struct ntsync_mutex_args __user *user_args = argp;
struct ntsync_device *dev = mutex->dev;
struct ntsync_mutex_args args;
+ bool all = false;
__u32 prev_count;
int ret;
@@ -387,28 +443,27 @@ static int ntsync_mutex_unlock(struct nt
if (mutex->type != NTSYNC_TYPE_MUTEX)
return -EINVAL;
- if (atomic_read(&mutex->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&mutex->lock, &dev->wait_all_lock);
-
- prev_count = mutex->u.mutex.count;
- ret = unlock_mutex_state(mutex, &args);
- if (!ret) {
+ obj_lock(mutex);
+ all = atomic_read(&mutex->all_hint);
+ if (unlikely(all)) {
+ obj_unlock(mutex);
+ mutex_lock(&dev->wait_all_lock);
+ dev_lock_obj(dev, mutex);
+ }
+
+ prev_count = mutex->u.mutex.count;
+ ret = unlock_mutex_state(mutex, &args);
+ if (!ret) {
+ if (all)
try_wake_all_obj(dev, mutex);
- try_wake_any_mutex(mutex);
- }
+ try_wake_any_mutex(mutex);
+ }
- spin_unlock(&mutex->lock);
- spin_unlock(&dev->wait_all_lock);
+ if (all) {
+ dev_unlock_obj(dev, mutex);
+ mutex_unlock(&dev->wait_all_lock);
} else {
- spin_lock(&mutex->lock);
-
- prev_count = mutex->u.mutex.count;
- ret = unlock_mutex_state(mutex, &args);
- if (!ret)
- try_wake_any_mutex(mutex);
-
- spin_unlock(&mutex->lock);
+ obj_unlock(mutex);
}
if (!ret && put_user(prev_count, &user_args->count))
@@ -437,6 +492,7 @@ static int kill_mutex_state(struct ntsyn
static int ntsync_mutex_kill(struct ntsync_obj *mutex, void __user *argp)
{
struct ntsync_device *dev = mutex->dev;
+ bool all = false;
__u32 owner;
int ret;
@@ -448,26 +504,26 @@ static int ntsync_mutex_kill(struct ntsy
if (mutex->type != NTSYNC_TYPE_MUTEX)
return -EINVAL;
- if (atomic_read(&mutex->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&mutex->lock, &dev->wait_all_lock);
+ obj_lock(mutex);
+ all = atomic_read(&mutex->all_hint);
+ if (unlikely(all)) {
+ obj_unlock(mutex);
+ mutex_lock(&dev->wait_all_lock);
+ dev_lock_obj(dev, mutex);
+ }
- ret = kill_mutex_state(mutex, owner);
- if (!ret) {
+ ret = kill_mutex_state(mutex, owner);
+ if (!ret) {
+ if (all)
try_wake_all_obj(dev, mutex);
- try_wake_any_mutex(mutex);
- }
+ try_wake_any_mutex(mutex);
+ }
- spin_unlock(&mutex->lock);
- spin_unlock(&dev->wait_all_lock);
+ if (all) {
+ dev_unlock_obj(dev, mutex);
+ mutex_unlock(&dev->wait_all_lock);
} else {
- spin_lock(&mutex->lock);
-
- ret = kill_mutex_state(mutex, owner);
- if (!ret)
- try_wake_any_mutex(mutex);
-
- spin_unlock(&mutex->lock);
+ obj_unlock(mutex);
}
return ret;
@@ -477,35 +533,35 @@ static int ntsync_event_set(struct ntsyn
{
struct ntsync_device *dev = event->dev;
__u32 prev_state;
+ bool all = false;
if (event->type != NTSYNC_TYPE_EVENT)
return -EINVAL;
- if (atomic_read(&event->all_hint) > 0) {
- spin_lock(&dev->wait_all_lock);
- spin_lock_nest_lock(&event->lock, &dev->wait_all_lock);
+ obj_lock(event);
+ all = atomic_read(&event->all_hint);
+ if (unlikely(all)) {
+ obj_unlock(event);
+ mutex_lock(&dev->wait_all_lock);
+ dev_lock_obj(dev, event);
+ }
- prev_state = event->u.event.signaled;
- event->u.event.signaled = true;
+ prev_state = event->u.event.signaled;
+ event->u.event.signaled = true;
+ if (all)
try_wake_all_obj(dev, event);
- try_wake_any_event(event);
- if (pulse)
- event->u.event.signaled = false;
-
- spin_unlock(&event->lock);
- spin_unlock(&dev->wait_all_lock);
+ try_wake_any_event(event);
+ if (pulse)
+ event->u.event.signaled = false;
+
+ if (all) {
+ dev_unlock_obj(dev, event);
+ mutex_unlock(&dev->wait_all_lock);
} else {
- spin_lock(&event->lock);
-
- prev_state = event->u.event.signaled;
- event->u.event.signaled = true;
- try_wake_any_event(event);
- if (pulse)
- event->u.event.signaled = false;
-
- spin_unlock(&event->lock);
+ obj_unlock(event);
}
+
if (put_user(prev_state, (__u32 __user *)argp))
return -EFAULT;
@@ -984,7 +1040,7 @@ static int ntsync_wait_all(struct ntsync
/* queue ourselves */
- spin_lock(&dev->wait_all_lock);
+ mutex_lock(&dev->wait_all_lock);
for (i = 0; i < args.count; i++) {
struct ntsync_q_entry *entry = &q->entries[i];
@@ -1004,7 +1060,7 @@ static int ntsync_wait_all(struct ntsync
try_wake_all(dev, q, NULL);
- spin_unlock(&dev->wait_all_lock);
+ mutex_unlock(&dev->wait_all_lock);
/* sleep */
@@ -1012,7 +1068,7 @@ static int ntsync_wait_all(struct ntsync
/* and finally, unqueue */
- spin_lock(&dev->wait_all_lock);
+ mutex_lock(&dev->wait_all_lock);
for (i = 0; i < args.count; i++) {
struct ntsync_q_entry *entry = &q->entries[i];
@@ -1029,7 +1085,7 @@ static int ntsync_wait_all(struct ntsync
put_obj(obj);
}
- spin_unlock(&dev->wait_all_lock);
+ mutex_unlock(&dev->wait_all_lock);
signaled = atomic_read(&q->signaled);
if (signaled != -1) {
@@ -1056,7 +1112,7 @@ static int ntsync_char_open(struct inode
if (!dev)
return -ENOMEM;
- spin_lock_init(&dev->wait_all_lock);
+ mutex_init(&dev->wait_all_lock);
file->private_data = dev;
dev->file = file;
^ permalink raw reply
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