Date: Mon, 25 Aug 2014 11:10:56 +0200 From: Mateusz Guzik <mjguzik@gmail.com> To: Konstantin Belousov <kostikbel@gmail.com> Cc: freebsd-hackers@freebsd.org Subject: Re: atomic_load_acq_int in sequential_heuristic Message-ID: <20140825091056.GC14344@dft-labs.eu> In-Reply-To: <20140825083539.GB2737@kib.kiev.ua> References: <20140824115729.GC2045@dft-labs.eu> <20140824162331.GW2737@kib.kiev.ua> <20140824164236.GX2737@kib.kiev.ua> <20140825005659.GA14344@dft-labs.eu> <20140825073404.GZ2737@kib.kiev.ua> <20140825081526.GB14344@dft-labs.eu> <20140825083539.GB2737@kib.kiev.ua>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Aug 25, 2014 at 11:35:39AM +0300, Konstantin Belousov wrote: > > + atomic_set_int(&fp->f_flag, FHASLOCK); > You misspelled FRDAHEAD as FHASLOCK, below as well. > Was this tested ? > Oops, damn copy-pasto. Sorry. > > + VOP_UNLOCK(vp, 0); > > } else { > > - do { > > - new = old = fp->f_flag; > > - new &= ~FRDAHEAD; > > - } while (!atomic_cmpset_rel_int(&fp->f_flag, old, new)); > > + atomic_clear_int(&fp->f_flag, FHASLOCK); > So what about extending the vnode lock to cover the flag reset ? > Sure. So this time I tested it properly and found out it is impossible to disable the hint. The test is: -1 is truncated and then read from intptr_t which yields a big positive number instead. Other users in the function use int tmp to work around this issue. diff --git a/sys/kern/kern_descrip.c b/sys/kern/kern_descrip.c index 7abdca0..774f647 100644 --- a/sys/kern/kern_descrip.c +++ b/sys/kern/kern_descrip.c @@ -760,7 +760,8 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg) error = EBADF; break; } - if (arg >= 0) { + tmp = arg; + if (tmp >= 0) { vp = fp->f_vnode; error = vn_lock(vp, LK_SHARED); if (error != 0) { @@ -769,7 +770,7 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg) } bsize = fp->f_vnode->v_mount->mnt_stat.f_iosize; VOP_UNLOCK(vp, 0); - fp->f_seqcount = (arg + bsize - 1) / bsize; + fp->f_seqcount = (tmp + bsize - 1) / bsize; do { new = old = fp->f_flag; new |= FRDAHEAD; Then the patch in question: diff --git a/sys/kern/kern_descrip.c b/sys/kern/kern_descrip.c index 774f647..4efadb0 100644 --- a/sys/kern/kern_descrip.c +++ b/sys/kern/kern_descrip.c @@ -476,7 +476,6 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg) struct vnode *vp; cap_rights_t rights; int error, flg, tmp; - u_int old, new; uint64_t bsize; off_t foffset; @@ -760,27 +759,25 @@ kern_fcntl(struct thread *td, int fd, int cmd, intptr_t arg) error = EBADF; break; } + vp = fp->f_vnode; + /* + * Exclusive lock synchronizes against + * sequential_heuristic(). + */ + error = vn_lock(vp, LK_EXCLUSIVE); + if (error != 0) { + fdrop(fp, td); + break; + } tmp = arg; if (tmp >= 0) { - vp = fp->f_vnode; - error = vn_lock(vp, LK_SHARED); - if (error != 0) { - fdrop(fp, td); - break; - } bsize = fp->f_vnode->v_mount->mnt_stat.f_iosize; - VOP_UNLOCK(vp, 0); fp->f_seqcount = (tmp + bsize - 1) / bsize; - do { - new = old = fp->f_flag; - new |= FRDAHEAD; - } while (!atomic_cmpset_rel_int(&fp->f_flag, old, new)); + atomic_set_int(&fp->f_flag, FRDAHEAD); } else { - do { - new = old = fp->f_flag; - new &= ~FRDAHEAD; - } while (!atomic_cmpset_rel_int(&fp->f_flag, old, new)); + atomic_clear_int(&fp->f_flag, FRDAHEAD); } + VOP_UNLOCK(vp, 0); fdrop(fp, td); break; diff --git a/sys/kern/vfs_vnops.c b/sys/kern/vfs_vnops.c index f1d19ac..98823f3 100644 --- a/sys/kern/vfs_vnops.c +++ b/sys/kern/vfs_vnops.c @@ -438,7 +438,8 @@ static int sequential_heuristic(struct uio *uio, struct file *fp) { - if (atomic_load_acq_int(&(fp->f_flag)) & FRDAHEAD) + ASSERT_VOP_LOCKED(fp->f_vnode, __func__); + if (fp->f_flag & FRDAHEAD) return (fp->f_seqcount << IO_SEQSHIFT); /* -- Mateusz Guzik <mjguzik gmail.com>
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20140825091056.GC14344>