A change to KPI of vm_pager_get_pages() and underlying VOP_GETPAGES().

o With new KPI consumers can request contiguous ranges of pages, and
  unlike before, all pages will be kept busied on return, like it was
  done before with the 'reqpage' only. Now the reqpage goes away. With
  new interface it is easier to implement code protected from race
  conditions.

  Such arrayed requests for now should be preceeded by a call to
  vm_pager_haspage() to make sure that request is possible. This
  could be improved later, making vm_pager_haspage() obsolete.

  Strenghtening the promises on the business of the array of pages
  allows us to remove such hacks as swp_pager_free_nrpage() and
  vm_pager_free_nonreq().

o New KPI accepts two integer pointers that may optionally point at
  values for read ahead and read behind, that a pager may do, if it
  can. These pages are completely owned by pager, and not controlled
  by the caller.

  This shifts the UFS-specific readahead logic from vm_fault.c, which
  should be file system agnostic, into vnode_pager.c. It also removes
  one VOP_BMAP() request per hard fault.

Discussed with:	kib, alc, jeff, scottl
Sponsored by:	Nginx, Inc.
Sponsored by:	Netflix

1 files changed, 13 insertions, 6 deletions

diff --git a/share/man/man9/VOP_GETPAGES.9 b/share/man/man9/VOP_GETPAGES.9
index 2cc5b7a..4625d9b 100644
--- a/share/man/man9/VOP_GETPAGES.9
+++ b/share/man/man9/VOP_GETPAGES.9
@@ -29,7 +29,7 @@
 .\"
 .\" $FreeBSD$
 .\"
-.Dd September 12, 2014
+.Dd December 16, 2015
 .Dt VOP_GETPAGES 9
 .Os
 .Sh NAME
@@ -41,7 +41,7 @@
 .In sys/vnode.h
 .In vm/vm.h
 .Ft int
-.Fn VOP_GETPAGES "struct vnode *vp" "vm_page_t *ma" "int count" "int reqpage"
+.Fn VOP_GETPAGES "struct vnode *vp" "vm_page_t *ma" "int count" "int *rbehind" "int *rahead"
 .Ft int
 .Fn VOP_PUTPAGES "struct vnode *vp" "vm_page_t *ma" "int count" "int sync" "int *rtvals"
 .Sh DESCRIPTION
@@ -63,7 +63,7 @@ locks are held.
 Both methods return in the same state on both success and error returns.
 .Pp
 The arguments are:
-.Bl -tag -width reqpage
+.Bl -tag -width rbehind
 .It Fa vp
 The file to access.
 .It Fa ma
@@ -78,9 +78,16 @@ if the write should be synchronous.
 An array of VM system result codes indicating the status of each
 page written by
 .Fn VOP_PUTPAGES .
-.It Fa reqpage
-The index in the page array of the requested page; i.e., the one page which
-the implementation of this method must handle.
+.It Fa rbehind
+Optional pointer to integer specifying number of pages to be read behind, if
+possible.
+If the filesystem supports that feature, number of actually read pages is
+reported back, otherwise zero is returned.
+.It Fa rahead
+Optional pointer to integer specifying number of pages to be read ahead, if
+possible.
+If the filesystem supports that feature, number of actually read pages is
+reported back, otherwise zero is returned.
 .El
 .Pp
 The status of the