On Tue, Jan 30, 2024 at 9:28 AM Liam R. Howlett <Liam.Howlett@xxxxxxxxxx> wrote: > > * Mike Rapoport <rppt@xxxxxxxxxx> [240130 03:55]: > > On Mon, Jan 29, 2024 at 10:46:27PM -0500, Liam R. Howlett wrote: > > > * Lokesh Gidra <lokeshgidra@xxxxxxxxxx> [240129 17:35]: > > > > On Mon, Jan 29, 2024 at 1:00 PM Liam R. Howlett <Liam.Howlett@xxxxxxxxxx> wrote: > > > > > > > > > > * Lokesh Gidra <lokeshgidra@xxxxxxxxxx> [240129 14:35]: > > > > > > Increments and loads to mmap_changing are always in mmap_lock > > > > > > critical section. > > > > > > > > > > Read or write? > > > > > > > > > It's write-mode when incrementing (except in case of > > > > userfaultfd_remove() where it's done in read-mode) and loads are in > > > > mmap_lock (read-mode). I'll clarify this in the next version. > > > > > > > > > > > This ensures that if userspace requests event > > > > > > notification for non-cooperative operations (e.g. mremap), userfaultfd > > > > > > operations don't occur concurrently. > > > > > > > > > > > > This can be achieved by using a separate read-write semaphore in > > > > > > userfaultfd_ctx such that increments are done in write-mode and loads > > > > > > in read-mode, thereby eliminating the dependency on mmap_lock for this > > > > > > purpose. > > > > > > > > > > > > This is a preparatory step before we replace mmap_lock usage with > > > > > > per-vma locks in fill/move ioctls. > > > > > > > > > > > > Signed-off-by: Lokesh Gidra <lokeshgidra@xxxxxxxxxx> > > > > > > --- > > > > > > fs/userfaultfd.c | 40 ++++++++++++---------- > > > > > > include/linux/userfaultfd_k.h | 31 ++++++++++-------- > > > > > > mm/userfaultfd.c | 62 ++++++++++++++++++++--------------- > > > > > > 3 files changed, 75 insertions(+), 58 deletions(-) > > > > > > > > > > > > diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c > > > > > > index 58331b83d648..c00a021bcce4 100644 > > > > > > --- a/fs/userfaultfd.c > > > > > > +++ b/fs/userfaultfd.c > > > > > > @@ -685,12 +685,15 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) > > > > > > ctx->flags = octx->flags; > > > > > > ctx->features = octx->features; > > > > > > ctx->released = false; > > > > > > + init_rwsem(&ctx->map_changing_lock); > > > > > > atomic_set(&ctx->mmap_changing, 0); > > > > > > ctx->mm = vma->vm_mm; > > > > > > mmgrab(ctx->mm); > > > > > > > > > > > > userfaultfd_ctx_get(octx); > > > > > > + down_write(&octx->map_changing_lock); > > > > > > atomic_inc(&octx->mmap_changing); > > > > > > + up_write(&octx->map_changing_lock); > > > > > > On init, I don't think taking the lock is strictly necessary - unless > > > there is a way to access it before this increment? Not that it would > > > cost much. > > > > It's fork, the lock is for the context of the parent process and there > > could be uffdio ops running in parallel on its VM. > > Is this necessary then? We are getting the octx from another mm but the > mm is locked for forking. Why does it matter if there are readers of > the octx? > > I assume, currently, there is no way the userfaultfd ctx can > be altered under mmap_lock held for writing. I would think it matters if > there are writers (which, I presume are blocked by the mmap_lock for > now?) Shouldn't we hold the write lock for the entire dup process, I > mean, if we remove the userfaultfd from the mmap_lock, we cannot let the > structure being duplicated change half way through the dup process? > > I must be missing something with where this is headed? > AFAIU, the purpose of mmap_changing is to serialize uffdio operations with non-cooperative events if and when such events are being monitored by userspace (in case you missed, in all the cases of writes to mmap_changing, we only do it if that non-cooperative event has been requested by the user). As you pointed out there are no correctness concerns as far as userfaultfd operations are concerned. But these events are essential for the uffd monitor's functioning. For example: say the uffd monitor wants to be notified for REMAP operations while doing uffdio_copy operations. When COPY ioctls start failing with -EAGAIN and uffdio_copy.copy == 0, then it knows it must be due to mremap(), in which case it waits for the REMAP event notification before attempting COPY again. But there are few things that I didn't get after going through the history of non-cooperative events. Hopefully Mike (or someone else familiar) can clarify: IIUC, the idea behind non-cooperative events was to block uffdio operations from happening *before* the page tables are manipulated by the event (like mremap), and that the uffdio ops are resumed after the event notification is received by the monitor. If so then: 1) Why in the case of REMAP prep() is done after page-tables are moved? Shouldn't it be done before? All other non-cooperative operations do the prep() before. 2) UFFD_FEATURE_EVENT_REMOVE only notifies user space. It is not consistently blocking uffdio operations (as both sides are acquiring mmap_lock in read-mode) when remove operation is taking place. I can understand this was intentionally left as is in the interest of not acquiring mmap_lock in write-mode during madvise. But is only getting the notification any useful? Can we say this patch fixes it? And in that case shouldn't I split userfaultfd_remove() into two functions (like other non-cooperative operations)? 3) Based on [1] I see how mmap_changing helps in eliminating duplicate work (background copy) by uffd monitor, but didn't get if there is a correctness aspect too that I'm missing? I concur with Amit's point in [1] that getting -EEXIST when setting up the pte will avoid memory corruption, no? [1] https://lore.kernel.org/lkml/20201206093703.GY123287@xxxxxxxxxxxxx/ > > > > > > > You could use the first bit of the atomic_inc as indication of a write. > > > > > So if the mmap_changing is even, then there are no writers. If it > > > > > didn't change and it's even then you know no modification has happened > > > > > (or it overflowed and hit the same number which would be rare, but > > > > > maybe okay?). > > > > > > > > This is already achievable, right? If mmap_changing is >0 then we know > > > > there are writers. The problem is that we want writers (like mremap > > > > operations) to block as long as there is a userfaultfd operation (also > > > > reader of mmap_changing) going on. Please note that I'm inferring this > > > > from current implementation. > > > > > > > > AFAIU, mmap_changing isn't required for correctness, because all > > > > operations are happening under the right mode of mmap_lock. It's used > > > > to ensure that while a non-cooperative operations is happening, if the > > > > user has asked it to be notified, then no other userfaultfd operations > > > > should take place until the user gets the event notification. > > > > > > I think it is needed, mmap_changing is read before the mmap_lock is > > > taken, then compared after the mmap_lock is taken (both read mode) to > > > ensure nothing has changed. > > > > mmap_changing is required to ensure that no uffdio operation runs in > > parallel with operations that modify the memory map, like fork, mremap, > > munmap and some of madvise calls. > > And we do need the writers to block if there is an uffdio operation going > > on, so I think an rwsem is the right way to protect mmap_chaniging. > > > > > > > > @@ -783,7 +788,9 @@ bool userfaultfd_remove(struct vm_area_struct *vma, > > > > > > return true; > > > > > > > > > > > > userfaultfd_ctx_get(ctx); > > > > > > + down_write(&ctx->map_changing_lock); > > > > > > atomic_inc(&ctx->mmap_changing); > > > > > > + up_write(&ctx->map_changing_lock); > > > > > > mmap_read_unlock(mm); > > > > > > > > > > > > msg_init(&ewq.msg); > > > > > > If this happens in read mode, then why are you waiting for the readers > > > to leave? Can't you just increment the atomic? It's fine happening in > > > read mode today, so it should be fine with this new rwsem. > > > > It's been a while and the details are blurred now, but if I remember > > correctly, having this in read mode forced non-cooperative uffd monitor to > > be single threaded. If a monitor runs, say uffdio_copy, and in parallel a > > thread in the monitored process does MADV_DONTNEED, the latter will wait > > for userfaultfd_remove notification to be processed in the monitor and drop > > the VMA contents only afterwards. If a non-cooperative monitor would > > process notification in parallel with uffdio ops, MADV_DONTNEED could > > continue and race with uffdio_copy, so read mode wouldn't be enough. > > > > Right now this function won't stop to wait for readers to exit the > critical section, but with this change there will be a pause (since the > down_write() will need to wait for the readers with the read lock). So > this is adding a delay in this call path that isn't necessary (?) nor > existed before. If you have non-cooperative uffd monitors, then you > will have to wait for them to finish to mark the uffd as being removed, > where as before it was a fire & forget, this is now a wait to tell. > I think a lot will be clearer once we get a response to my questions above. IMHO not only this write-lock is needed here, we need to fix userfaultfd_remove() by splitting it into userfaultfd_remove_prep() and userfaultfd_remove_complete() (like all other non-cooperative operations) as well. This patch enables us to do that as we remove mmap_changing's dependency on mmap_lock for synchronization. > > > There was no much sense to make MADV_DONTNEED take mmap_lock in write mode > > just for this, but now taking the rwsem in write mode here sounds > > reasonable. > > > > I see why there was no need for a mmap_lock in write mode, but I think > taking the new rwsem in write mode is unnecessary. > > Basically, I see this as a signal to new readers to abort, but we don't > need to wait for current readers to finish before this one increments > the atomic. > > Unless I missed something, I don't think you want to take the write lock > here. What I understood from the history of mmap_changing is that the intention was to enable informing the uffd monitor about the correct state of which pages are filled and which aren't. Going through this thread was very helpful [2] [2] https://lore.kernel.org/lkml/1527061324-19949-1-git-send-email-rppt@xxxxxxxxxxxxxxxxxx/ > > Thanks, > Liam
