Giant pushdown for read/write/pread/pwrite syscalls.

kern/kern_descrip.c:
Aquire Giant in fdrop_locked when file refcount hits zero, this removes
the requirement for the caller to own Giant for the most part.

kern/kern_ktrace.c:
Aquire Giant in ktrgenio, simplifies locking in upper read/write syscalls.

kern/vfs_bio.c:
Aquire Giant in bwillwrite if needed.

kern/sys_generic.c
Giant pushdown, remove Giant for:
   read, pread, write and pwrite.
readv and writev aren't done yet because of the possible malloc calls
for iov to uio processing.

kern/sys_socket.c
Grab giant in the socket fo_read/write functions.

kern/vfs_vnops.c
Grab giant in the vnode fo_read/write functions.

6 files changed, 26 insertions, 11 deletions

diff --git a/sys/kern/kern_descrip.c b/sys/kern/kern_descrip.c
index 5fed676..50bcc3a 100644
--- a/sys/kern/kern_descrip.c
+++ b/sys/kern/kern_descrip.c
@@ -1716,6 +1716,7 @@ fdrop_locked(fp, td)
 		FILE_UNLOCK(fp);
 		return (0);
 	}
+	mtx_lock(&Giant);
 	if (fp->f_count < 0)
 		panic("fdrop: count < 0");
 	if ((fp->f_flag & FHASLOCK) && fp->f_type == DTYPE_VNODE) {
@@ -1733,6 +1734,7 @@ fdrop_locked(fp, td)
 	else
 		error = 0;
 	ffree(fp);
+	mtx_unlock(&Giant);
 	return (error);
 }
 
diff --git a/sys/kern/kern_ktrace.c b/sys/kern/kern_ktrace.c
index 75372d8..c66108f 100644
--- a/sys/kern/kern_ktrace.c
+++ b/sys/kern/kern_ktrace.c
@@ -181,6 +181,8 @@ ktrgenio(vp, fd, rw, uio, error)
 
 	if (error)
 		return;
+
+	mtx_lock(&Giant);
 	/*
 	 * don't let p_tracep get ripped out from under us
 	 */
@@ -200,6 +202,7 @@ ktrgenio(vp, fd, rw, uio, error)
 		vrele(vp);
 	FREE(kth, M_KTRACE);
 	p->p_traceflag &= ~KTRFAC_ACTIVE;
+	mtx_unlock(&Giant);
 }
 
 void
diff --git a/sys/kern/sys_generic.c b/sys/kern/sys_generic.c
index dff12a1..16fdcf8 100644
--- a/sys/kern/sys_generic.c
+++ b/sys/kern/sys_generic.c
@@ -102,13 +102,11 @@ read(td, uap)
 	struct file *fp;
 	int error;
 
-	mtx_lock(&Giant);
 	if ((error = fget_read(td, uap->fd, &fp)) == 0) {
 		error = dofileread(td, fp, uap->fd, uap->buf,
 			    uap->nbyte, (off_t)-1, 0);
 		fdrop(fp, td);
 	}
-	mtx_unlock(&Giant);
 	return(error);
 }
 
@@ -137,7 +135,6 @@ pread(td, uap)
 
 	if ((error = fget_read(td, uap->fd, &fp)) != 0)
 		return (error);
-	mtx_lock(&Giant);
 	if (fp->f_type != DTYPE_VNODE) {
 		error = ESPIPE;
 	} else {
@@ -145,7 +142,6 @@ pread(td, uap)
 			    uap->offset, FOF_OFFSET);
 	}
 	fdrop(fp, td);
-	mtx_unlock(&Giant);
 	return(error);
 }
 
@@ -332,7 +328,6 @@ write(td, uap)
 	struct file *fp;
 	int error;
 
-	mtx_lock(&Giant);
 	if ((error = fget_write(td, uap->fd, &fp)) == 0) {
 		error = dofilewrite(td, fp, uap->fd, uap->buf, uap->nbyte,
 			    (off_t)-1, 0);
@@ -340,7 +335,6 @@ write(td, uap)
 	} else {
 		error = EBADF;	/* XXX this can't be right */
 	}
-	mtx_unlock(&Giant);
 	return(error);
 }
 
@@ -368,7 +362,6 @@ pwrite(td, uap)
 	int error;
 
 	if ((error = fget_write(td, uap->fd, &fp)) == 0) {
-		mtx_lock(&Giant);
 		if (fp->f_type == DTYPE_VNODE) {
 			error = dofilewrite(td, fp, uap->fd, uap->buf,
 				    uap->nbyte, uap->offset, FOF_OFFSET);
@@ -376,7 +369,6 @@ pwrite(td, uap)
 			error = ESPIPE;
 		}
 		fdrop(fp, td);
-		mtx_unlock(&Giant);
 	} else {
 		error = EBADF;	/* this can't be right */
 	}
diff --git a/sys/kern/sys_socket.c b/sys/kern/sys_socket.c
index 13f4000..c8a6198 100644
--- a/sys/kern/sys_socket.c
+++ b/sys/kern/sys_socket.c
@@ -65,7 +65,12 @@ soo_read(fp, uio, cred, flags, td)
 	int flags;
 {
 	struct socket *so = (struct socket *)fp->f_data;
-	return so->so_proto->pr_usrreqs->pru_soreceive(so, 0, uio, 0, 0, 0);
+	int error;
+
+	mtx_lock(&Giant);
+	error = so->so_proto->pr_usrreqs->pru_soreceive(so, 0, uio, 0, 0, 0);
+	mtx_unlock(&Giant);
+	return (error);
 }
 
 /* ARGSUSED */
@@ -78,8 +83,13 @@ soo_write(fp, uio, cred, flags, td)
 	int flags;
 {
 	struct socket *so = (struct socket *)fp->f_data;
-	return so->so_proto->pr_usrreqs->pru_sosend(so, 0, uio, 0, 0, 0,
+	int error;
+
+	mtx_lock(&Giant);
+	error = so->so_proto->pr_usrreqs->pru_sosend(so, 0, uio, 0, 0, 0,
 						    uio->uio_td);
+	mtx_unlock(&Giant);
+	return (error);
 }
 
 int
diff --git a/sys/kern/vfs_bio.c b/sys/kern/vfs_bio.c
index 70d3a92..bf4970d 100644
--- a/sys/kern/vfs_bio.c
+++ b/sys/kern/vfs_bio.c
@@ -1079,6 +1079,7 @@ bwillwrite(void)
 	if (numdirtybuffers >= hidirtybuffers) {
 		int s;
 
+		mtx_lock(&Giant);
 		s = splbio();
 		while (numdirtybuffers >= hidirtybuffers) {
 			bd_wakeup(1);
@@ -1086,6 +1087,7 @@ bwillwrite(void)
 			tsleep(&needsbuffer, (PRIBIO + 4), "flswai", 0);
 		}
 		splx(s);
+		mtx_unlock(&Giant);
 	}
 }
 
diff --git a/sys/kern/vfs_vnops.c b/sys/kern/vfs_vnops.c
index 336086c..4f1556a 100644
--- a/sys/kern/vfs_vnops.c
+++ b/sys/kern/vfs_vnops.c
@@ -443,6 +443,7 @@ vn_read(fp, uio, cred, flags, td)
 	struct vnode *vp;
 	int error, ioflag;
 
+	mtx_lock(&Giant);
 	KASSERT(uio->uio_td == td, ("uio_td %p is not td %p",
 	    uio->uio_td, td));
 	vp = (struct vnode *)fp->f_data;
@@ -463,6 +464,7 @@ vn_read(fp, uio, cred, flags, td)
 		fp->f_offset = uio->uio_offset;
 	fp->f_nextoff = uio->uio_offset;
 	VOP_UNLOCK(vp, 0, td);
+	mtx_unlock(&Giant);
 	return (error);
 }
 
@@ -481,6 +483,7 @@ vn_write(fp, uio, cred, flags, td)
 	struct mount *mp;
 	int error, ioflag;
 
+	mtx_lock(&Giant);
 	KASSERT(uio->uio_td == td, ("uio_td %p is not td %p",
 	    uio->uio_td, td));
 	vp = (struct vnode *)fp->f_data;
@@ -498,8 +501,10 @@ vn_write(fp, uio, cred, flags, td)
 		ioflag |= IO_SYNC;
 	mp = NULL;
 	if (vp->v_type != VCHR &&
-	    (error = vn_start_write(vp, &mp, V_WAIT | PCATCH)) != 0)
+	    (error = vn_start_write(vp, &mp, V_WAIT | PCATCH)) != 0) {
+		mtx_unlock(&Giant);
 		return (error);
+	}
 	VOP_LEASE(vp, td, cred, LEASE_WRITE);
 	vn_lock(vp, LK_EXCLUSIVE | LK_RETRY, td);
 	if ((flags & FOF_OFFSET) == 0)
@@ -511,6 +516,7 @@ vn_write(fp, uio, cred, flags, td)
 	fp->f_nextoff = uio->uio_offset;
 	VOP_UNLOCK(vp, 0, td);
 	vn_finished_write(mp);
+	mtx_unlock(&Giant);
 	return (error);
 }