Re: [PATCH man-pages] Add rseq manpage
From: Mathieu Desnoyers
Date: Mon Mar 04 2019 - 13:02:38 EST
----- On Feb 28, 2019, at 3:42 AM, Michael Kerrisk mtk.manpages@xxxxxxxxx wrote:
> On 12/6/18 3:42 PM, Mathieu Desnoyers wrote:
>> [ Michael, rseq(2) was merged into 4.18. Can you have a look at this
>> patch which adds rseq documentation to the man-pages project ? ]
> Hi Matthieu
>
> Sorry for the long delay. I've merged this page into a private
> branch and have done quite a lot of editing. I have many
> questions :-).
No worries, thanks for looking into it!
>
> In the first instance, I think it is probably best to have
> a free-form text discussion rather than firing patches
> back and forward. Could you take a look at the questions below
> and respond?
Sure,
>
> Thanks,
>
> Michael
>
>
> RSEQ(2) Linux Programmer's Manual RSEQ(2)
>
> NAME
> rseq - Restartable sequences and CPU number cache
>
> SYNOPSIS
> #include <linux/rseq.h>
>
> int rseq(struct rseq *rseq, uint32_t rseq_len, int flags, uint32_t sig);
>
> DESCRIPTION
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âImagine you are someone who is pretty new to this â
> âidea... What is notably lacking from this page is â
> âan overview explaining: â
> â â
> â * What a restartable sequence actually is. â
> â â
> â * An outline of the steps to perform when using â
> â restartable sequences / rseq(2). â
> â â
> âI.e., something along the lines of Jon Corbet's â
> âhttps://lwn.net/Articles/697979/. Can you come up â
> âwith something? (Part of it might be at the start of â
> âthis page, and the rest in NOTES; it need not be all â
> âin one place.) â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
We recently published a blog post about rseq, which might contain just the
right level of information we are looking for here:
https://www.efficios.com/blog/2019/02/08/linux-restartable-sequences/
Could something along the following lines work ?
"A restartable sequence is a sequence of instructions guaranteed to be
executed atomically with respect to other threads and signal handlers on the
current CPU. If its execution does not complete atomically, the kernel changes
the execution flow by jumping to an abort handler defined by user-space for
that restartable sequence.
Using restartable sequences requires to register a __rseq_abi thread-local storage
data structure (struct rseq) through the rseq(2) system call. Only one __rseq_abi
can be registered per thread, so user-space libraries and applications must follow
a user-space ABI defining how to share this resource. The ABI defining how to share
this resource between applications and libraries is defined by the C library.
The __rseq_abi contains a rseq_cs field which points to the currently executing
critical section. For each thread, a single rseq critical section can run at any
given point. Each critical section need to be implemented in assembly."
> The rseq() ABI accelerates user-space operations on per-CPU data by
> defining a shared data structure ABI between each user-space thread and
> the kernel.
>
> It allows user-space to perform update operations on per-CPU data withâ
> out requiring heavy-weight atomic operations.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the following para: "a hardware execution conâ â
> âtext"? What is the contrast being drawn here? It â
> âwould be good to state it more explicitly. â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Here I'm trying to clarify what we mean by "CPU" in this document. We define
a CPU as having its own number returned by sched_getcpu(), which I think is
sometimes referred to as "logical cpu". This is the current hyperthread on
the current core, on the current "physical CPU", in the current socket.
> The term CPU used in this documentation refers to a hardware execution
> context.
>
> Restartable sequences are atomic with respect to preemption (making it
> atomic with respect to other threads running on the same CPU), as well
> as signal delivery (user-space execution contexts nested over the same
> thread). They either complete atomically with respect to preemption on
> the current CPU and signal delivery, or they are aborted.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the preceding sentence, we need a definition of â
> â"current CPU". â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Not sure how to word it. If a thread or signal handler execution context can
possibly run and issue, for instance, "sched_getcpu()" between the beginning
and the end of the critical section and get the same logical CPU number as the
current thread, then we are guaranteed to abort. Of course, sched_getcpu() is
just one way to get the CPU number, considering that we can also read it
from the __rseq_abi cpu_id and cpu_id_start fields.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the following, does "It is" means "Restartable â
> âsequences are"? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> It is suited for update operations on per-CPU data.
Yes.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the following, does "It is" means "Restartable â
> âsequences are"? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
"Restartable sequences can be..."
> It can be used on data structures shared between threads within a
> process, and on data structures shared between threads across different
> processes.
>
> Some examples of operations that can be accelerated or improved by this
> ABI:
>
> Â Memory allocator per-CPU free-lists
>
> Â Querying the current CPU number
>
> Â Incrementing per-CPU counters
>
> Â Modifying data protected by per-CPU spinlocks
>
> Â Inserting/removing elements in per-CPU linked-lists
>
> Â Writing/reading per-CPU ring buffers content
>
> Â Accurately reading performance monitoring unit counters with respect
> to thread migration
>
> Restartable sequences must not perform system calls. Doing so may
> result in termination of the process by a segmentation fault.
>
> The rseq argument is a pointer to the thread-local rseq structure to be
> shared between kernel and user-space. The layout of this structure is
> shown below.
>
> The rseq_len argument is the size of the struct rseq to register.
>
> The flags argument is 0 for registration, or RSEQ_FLAG_UNREGISTER for
> unregistration.
>
> The sig argument is the 32-bit signature to be expected before the
> abort handler code.
>
> The rseq structure
> The struct rseq is aligned on a 32-byte boundary. This structure is
> extensible. Its size is passed as parameter to the rseq() system call.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âBelow, I added the structure definition (in abbreviâ â
> âated form). Is there any reason not to do this? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
It seems appropriate.
>
> struct rseq {
> __u32 cpu_id_start;
> __u32 cpu_id;
> union {
> __u64 ptr64;
> #ifdef __LP64__
> __u64 ptr;
> #else
> ....
> #endif
> } rseq_cs;
> __u32 flags;
> } __attribute__((aligned(4 * sizeof(__u64))));
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the text below, I think it would be helpful to â
> âexplicitly note which of these fields are set by the â
> âkernel (on return from the reseq() call) and which â
> âare set by the caller (before calling rseq()). Is â
> âthe following correct: â
> â â
> â cpu_id_start - initialized by caller to possible â
> â CPU number (e.g., 0), updated by kernel â
> â on return â
"initialized by caller to possible CPU number (e.g., 0), updated
by the kernel on return, and updated by the kernel on return after
thread migration to a different CPU"
> â â
> â cpu_id - initialized to -1 by caller, â
> â updated by kernel on return â
"initialized to -1 by caller, updated by the kernel on return, and
updated by the kernel on return after thread migration to a different
CPU"
> â â
> â rseq_cs - initialized by caller, either to NULL â
> â or a pointer to an 'rseq_cs' structure â
> â that is initialized by the caller â
"initialized by caller to NULL, then, after returning from successful
registration, updated to a pointer to an "rseq_cs" structure by user-space.
Set to NULL by the kernel when it restarts a rseq critical section,
when it preempts or deliver a signal outside of the range targeted by the
rseq_cs. Set to NULL by user-space before reclaiming memory that
contains the targeted struct rseq_cs."
> â â
> â flags - initialized by caller, used by kernel â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
>
> The structure fields are as follows:
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the following paragraph, and in later places, I â
> âchanged "current thread" to "calling thread". Okay? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Yes.
>
> cpu_id_start
> Optimistic cache of the CPU number on which the calling thread
> is running. The value in this field is guaranteed to always be
> a possible CPU number, even when rseq is not initialized. The
> value it contains should always be confirmed by reading the
> cpu_id field.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âWhat does the last sentence mean? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
It means the caller thread can always use __rseq_abi.cpu_id_start to index an
array of per-cpu data and this won't cause an out-of-bound access on load, but it
does not mean it really contains the current CPU number. For instance, if rseq
registration failed, it will contain "0".
Therefore, it's fine to use cpu_is_start to fetch per-cpu data, but the cpu_id
field should be used to compare the cpu_is_start value, so the case where rseq
is not registered is caught. In that case, cpu_id_start=0, but cpu_id=-1 or -2,
which differ, and therefore the critical section needs to jump to the abort
handler.
>
> This field is an optimistic cache in the sense that it is always
> guaranteed to hold a valid CPU number in the range [0..(nr_posâ
> sible_cpus - 1)]. It can therefore be loaded by user-space and
> used as an offset in per-CPU data structures without having to
> check whether its value is within the valid bounds compared to
> the number of possible CPUs in the system.
>
> For user-space applications executed on a kernel without rseq
> support, the cpu_id_start field stays initialized at 0, which is
> indeed a valid CPU number. It is therefore valid to use it as
> an offset in per-CPU data structures, and only validate whether
> it's actually the current CPU number by comparing it with the
> cpu_id field within the rseq critical section.
>
> If the kernel does not provide rseq support, that cpu_id field
> stays initialized at -1, so the comparison always fails, as
> intended. It is then up to user-space to use a fall-back mechaâ
> nism, considering that rseq is not available.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âThe last sentence is rather difficult to grok. Can â
> âwe say some more here? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Perhaps we could use the explanation I've written above in my reply ?
>
> cpu_id Cache of the CPU number on which the calling thread is running.
> -1 if uninitialized.
>
> rseq_cs
> The rseq_cs field is a pointer to a struct rseq_cs (described
> below). It is NULL when no rseq assembly block critical section
> is active for the calling thread. Setting it to point to a
> critical section descriptor (struct rseq_cs) marks the beginning
> of the critical section.
>
> flags Flags indicating the restart behavior for the calling thread.
> This is mainly used for debugging purposes. Can be either:
>
> RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
Inhibit instruction sequence block restart on preemption for this thread.
>
> RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
Inhibit instruction sequence block restart on signal delivery for this thread.
Restart on signal can only be inhibited when restart on preemption and restart
on migration are inhibited too, else it will terminate the offending process with
a segmentation fault.
>
> RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
Inhibit instruction sequence block restart on migration for this thread.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âEach of the above values needs an explanation. â
> â â
> âIs it correct that only one of the values may be â
> âspecified in 'flags'? I ask because in the 'rseq_cs' â
> âstructure below, the 'flags' field is a bit mask â
> âwhere any combination of these flags may be ORed â
> âtogether. â
> â â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Those are also masks and can be ORed.
>
> The rseq_cs structure
> The struct rseq_cs is aligned on a 32-byte boundary and has a fixed
> size of 32 bytes.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âBelow, I added the structure definition (in abbreviâ â
> âated form). Is there any reason not to do this? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
It's fine.
>
> struct rseq_cs {
> __u32 version;
> __u32 flags;
> __u64 start_ip;
> __u64 post_commit_offset;
> __u64 abort_ip;
> } __attribute__((aligned(4 * sizeof(__u64))));
>
> The structure fields are as follows:
>
> version
> Version of this structure.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âWhat does 'version' need to be initialized to? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Currently version needs to be 0. Eventually, if we implement support for new flags to rseq(),
we could add feature flags which register support for newer versions of struct rseq_cs.
>
> flags Flags indicating the restart behavior of this structure. Can be
> a combination of:
>
> RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
Inhibit instruction sequence block restart on preemption for this thread.
>
> RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
Inhibit instruction sequence block restart on signal delivery for this thread.
Restart on signal can only be inhibited when restart on preemption and restart
on migration are inhibited too, else it will terminate the offending process with
a segmentation fault.
>
> RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
Inhibit instruction sequence block restart on migration for this thread.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âEach of the above values needs an explanation. â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
>
> start_ip
> Instruction pointer address of the first instruction of the
> sequence of consecutive assembly instructions.
>
> post_commit_offset
> Offset (from start_ip address) of the address after the last
> instruction of the sequence of consecutive assembly instrucâ
> tions.
>
> abort_ip
> Instruction pointer address where to move the execution flow in
> case of abort of the sequence of consecutive assembly instrucâ
> tions.
>
> NOTES
> A single library per process should keep the rseq structure in a
> thread-local storage variable. The cpu_id field should be initialized
> to -1, and the cpu_id_start field should be initialized to a possible
> CPU value (typically 0).
The part above is not quite right. All applications/libraries wishing to register
rseq must follow the ABI specified by the C library. It can be defined within more
that a single application/library, but in the end only one symbol will be chosen
for the process's global symbol table.
>
> Each thread is responsible for registering and unregistering its rseq
> structure. No more than one rseq structure address can be registered
> per thread at a given time.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the following paragraph, what is the difference â
> âbetween "freed" and "reclaim"? I'm supposing they â
> âmean the same thing, but it's not clear. And if they â
> âdo mean the same thing, then the first two sentences â
> âappear to contain contradictory information. â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
The mean the same thing, and they are subtly not contradictory.
The first states that memory of a _registered_ rseq object must not
be freed before the thread exits.
The second states that memory of a rseq object must not be freed before
it is unregistered or the thread exits.
Do you have an alternative wording in mind to make this clearer ?
>
> Memory of a registered rseq object must not be freed before the thread
> exits. Reclaim of rseq object's memory must only be done after either
> an explicit rseq unregistration is performed or after the thread exits.
> Keep in mind that the implementation of the Thread-Local Storage (C
> language __thread) lifetime does not guarantee existence of the TLS
> area up until the thread exits.
>
> In a typical usage scenario, the thread registering the rseq structure
> will be performing loads and stores from/to that structure. It is howâ
> ever also allowed to read that structure from other threads. The rseq
> field updates performed by the kernel provide relaxed atomicity semanâ
> tics, which guarantee that other threads performing relaxed atomic
> reads of the CPU number cache will always observe a consistent value.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIn the preceding paragraph, can we reasonably add â
> âsome words to explain "relaxed atomicity semantics" â
> âand "relaxed atomic reads"? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
Not sure how to word this exactly, but here it means the stores and loads need
to be done atomically, but don't require nor provide any ordering guarantees
with respect to other loads/stores (no memory barriers).
>
> RETURN VALUE
> A return value of 0 indicates success. On error, -1 is returned, and
> errno is set appropriately.
>
> ERRORS
> EBUSY Restartable sequence is already registered for this thread.
>
> EFAULT rseq is an invalid address.
>
> EINVAL Either flags contains an invalid value, or rseq contains an
> address which is not appropriately aligned, or rseq_len contains
> a size that does not match the size received on registration.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âThe last case "rseq_len contains a size that does â
> ânot match the size received on registration" can â
> âoccur only on RSEQ_FLAG_UNREGISTER, tight? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
>
> ENOSYS The rseq() system call is not implemented by this kernel.
>
> EPERM The sig argument on unregistration does not match the signature
> received on registration.
>
> VERSIONS
> The rseq() system call was added in Linux 4.18.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âWhat is the current state of library support? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
After going through a few RFC rounds, it's been posted as non-rfc a
few weeks ago. It is pending review from glibc maintainers. I currently
aim for inclusion of the rseq TLS registration by glibc for glibc 2.30:
https://sourceware.org/ml/libc-alpha/2019-02/msg00317.html
https://sourceware.org/ml/libc-alpha/2019-02/msg00320.html
https://sourceware.org/ml/libc-alpha/2019-02/msg00319.html
https://sourceware.org/ml/libc-alpha/2019-02/msg00318.html
https://sourceware.org/ml/libc-alpha/2019-02/msg00321.html
Note that the C library will define a user-space ABI which states how
applications/libraries wishing to register the rseq TLS need to behave so they
are compatible with the C library when it gets updated to a new version providing
rseq registration support. It seems like an important point to document,
perhaps even here in the rseq(2) man page.
>
> CONFORMING TO
> rseq() is Linux-specific.
>
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âFIXME â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
> âIs there any example code that can reasonably be â
> âincluded in this manual page? Or some example code â
> âthat can be referred to? â
> âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
>
The per-cpu counter example we have here seems compact enough:
https://www.efficios.com/blog/2019/02/08/linux-restartable-sequences/
Thanks,
Mathieu
> SEE ALSO
> sched_getcpu(3), membarrier(2)
>
> --
> Michael Kerrisk
> Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
> Linux/UNIX System Programming Training: http://man7.org/training/
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com