Date: Tue, 10 Apr 2012 10:44:42 +0000 (UTC) From: Konstantin Belousov <kib@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-stable@freebsd.org, svn-src-stable-8@freebsd.org Subject: svn commit: r234094 - in stable/8/sys: i386/conf vm Message-ID: <201204101044.q3AAigCn020197@svn.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: kib Date: Tue Apr 10 10:44:41 2012 New Revision: 234094 URL: http://svn.freebsd.org/changeset/base/234094 Log: MFC r233100: In vm_object_page_clean(), do not clean OBJ_MIGHTBEDIRTY object flag if the filesystem performed short write and we are skipping the page due to this. Propogate write error from the pager back to the callers of vm_pageout_flush(). Report the failure to write a page from the requested range as the FALSE return value from vm_object_page_clean(), and propagate it back to msync(2) to return EIO to usermode. While there, convert the clearobjflags variable in the vm_object_page_clean() and arguments of the helper functions to boolean. PR: kern/165927 Tested by: David Wolfskill Modified: stable/8/sys/vm/vm_contig.c stable/8/sys/vm/vm_map.c stable/8/sys/vm/vm_mmap.c stable/8/sys/vm/vm_object.c stable/8/sys/vm/vm_object.h stable/8/sys/vm/vm_pageout.c stable/8/sys/vm/vm_pageout.h Directory Properties: stable/8/sys/ (props changed) stable/8/sys/amd64/include/xen/ (props changed) stable/8/sys/boot/ (props changed) stable/8/sys/cddl/contrib/opensolaris/ (props changed) stable/8/sys/contrib/dev/acpica/ (props changed) stable/8/sys/contrib/pf/ (props changed) stable/8/sys/dev/e1000/ (props changed) stable/8/sys/i386/conf/XENHVM (props changed) Modified: stable/8/sys/vm/vm_contig.c ============================================================================== --- stable/8/sys/vm/vm_contig.c Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_contig.c Tue Apr 10 10:44:41 2012 (r234094) @@ -135,7 +135,8 @@ vm_contig_launder_page(vm_page_t m, vm_p } else if (object->type == OBJT_SWAP || object->type == OBJT_DEFAULT) { m_tmp = m; - vm_pageout_flush(&m_tmp, 1, VM_PAGER_PUT_SYNC, 0, NULL); + vm_pageout_flush(&m_tmp, 1, VM_PAGER_PUT_SYNC, 0, + NULL, NULL); VM_OBJECT_UNLOCK(object); return (0); } Modified: stable/8/sys/vm/vm_map.c ============================================================================== --- stable/8/sys/vm/vm_map.c Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_map.c Tue Apr 10 10:44:41 2012 (r234094) @@ -2573,6 +2573,7 @@ vm_map_sync( vm_object_t object; vm_ooffset_t offset; unsigned int last_timestamp; + boolean_t failed; vm_map_lock_read(map); VM_MAP_RANGE_CHECK(map, start, end); @@ -2602,6 +2603,7 @@ vm_map_sync( if (invalidate) pmap_remove(map->pmap, start, end); + failed = FALSE; /* * Make a second pass, cleaning/uncaching pages from the indicated @@ -2630,7 +2632,8 @@ vm_map_sync( vm_object_reference(object); last_timestamp = map->timestamp; vm_map_unlock_read(map); - vm_object_sync(object, offset, size, syncio, invalidate); + if (!vm_object_sync(object, offset, size, syncio, invalidate)) + failed = TRUE; start += size; vm_object_deallocate(object); vm_map_lock_read(map); @@ -2640,7 +2643,7 @@ vm_map_sync( } vm_map_unlock_read(map); - return (KERN_SUCCESS); + return (failed ? KERN_FAILURE : KERN_SUCCESS); } /* Modified: stable/8/sys/vm/vm_mmap.c ============================================================================== --- stable/8/sys/vm/vm_mmap.c Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_mmap.c Tue Apr 10 10:44:41 2012 (r234094) @@ -487,6 +487,8 @@ msync(td, uap) return (EINVAL); /* Sun returns ENOMEM? */ case KERN_INVALID_ARGUMENT: return (EBUSY); + case KERN_FAILURE: + return (EIO); default: return (EINVAL); } Modified: stable/8/sys/vm/vm_object.c ============================================================================== --- stable/8/sys/vm/vm_object.c Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_object.c Tue Apr 10 10:44:41 2012 (r234094) @@ -105,9 +105,10 @@ SYSCTL_INT(_vm, OID_AUTO, old_msync, CTL "Use old (insecure) msync behavior"); static int vm_object_page_collect_flush(vm_object_t object, vm_page_t p, - int pagerflags, int flags, int *clearobjflags); + int pagerflags, int flags, boolean_t *clearobjflags, + boolean_t *eio); static boolean_t vm_object_page_remove_write(vm_page_t p, int flags, - int *clearobjflags); + boolean_t *clearobjflags); static void vm_object_qcollapse(vm_object_t object); static void vm_object_vndeallocate(vm_object_t object); @@ -772,7 +773,7 @@ vm_object_terminate(vm_object_t object) } static boolean_t -vm_object_page_remove_write(vm_page_t p, int flags, int *clearobjflags) +vm_object_page_remove_write(vm_page_t p, int flags, boolean_t *clearobjflags) { /* @@ -781,7 +782,7 @@ vm_object_page_remove_write(vm_page_t p, * cleared in this case so we do not have to set them. */ if ((flags & OBJPC_NOSYNC) != 0 && (p->oflags & VPO_NOSYNC) != 0) { - *clearobjflags = 0; + *clearobjflags = FALSE; return (FALSE); } else { pmap_remove_write(p); @@ -803,20 +804,24 @@ vm_object_page_remove_write(vm_page_t p, * Odd semantics: if start == end, we clean everything. * * The object must be locked. + * + * Returns FALSE if some page from the range was not written, as + * reported by the pager, and TRUE otherwise. */ -void +boolean_t vm_object_page_clean(vm_object_t object, vm_pindex_t start, vm_pindex_t end, int flags) { vm_page_t np, p; vm_pindex_t pi, tend; - int clearobjflags, curgeneration, n, pagerflags; + int curgeneration, n, pagerflags; + boolean_t clearobjflags, eio, res; VM_OBJECT_LOCK_ASSERT(object, MA_OWNED); KASSERT(object->type == OBJT_VNODE, ("Not a vnode object")); if ((object->flags & OBJ_MIGHTBEDIRTY) == 0 || object->resident_page_count == 0) - return; + return (TRUE); pagerflags = (flags & (OBJPC_SYNC | OBJPC_INVAL)) != 0 ? VM_PAGER_PUT_SYNC : VM_PAGER_CLUSTER_OK; @@ -835,7 +840,8 @@ vm_object_page_clean(vm_object_t object, * stay dirty so do not mess with the page and do not clear the * object flags. */ - clearobjflags = 1; + clearobjflags = TRUE; + res = TRUE; rescan: curgeneration = object->generation; @@ -858,7 +864,11 @@ rescan: continue; n = vm_object_page_collect_flush(object, p, pagerflags, - flags, &clearobjflags); + flags, &clearobjflags, &eio); + if (eio) { + res = FALSE; + clearobjflags = FALSE; + } if (object->generation != curgeneration) goto rescan; @@ -874,8 +884,10 @@ rescan: * behind, but there is not much we can do there if * filesystem refuses to write it. */ - if (n == 0) + if (n == 0) { n = 1; + clearobjflags = FALSE; + } np = vm_page_find_least(object, pi + n); } vm_page_unlock_queues(); @@ -886,11 +898,12 @@ rescan: vm_object_clear_flag(object, OBJ_CLEANING); if (clearobjflags && start == 0 && tend == object->size) vm_object_clear_flag(object, OBJ_MIGHTBEDIRTY); + return (res); } static int vm_object_page_collect_flush(vm_object_t object, vm_page_t p, int pagerflags, - int flags, int *clearobjflags) + int flags, boolean_t *clearobjflags, boolean_t *eio) { vm_page_t ma[vm_pageout_page_count], p_first, tp; int count, i, mreq, runlen; @@ -921,7 +934,7 @@ vm_object_page_collect_flush(vm_object_t for (tp = p_first, i = 0; i < count; tp = TAILQ_NEXT(tp, listq), i++) ma[i] = tp; - vm_pageout_flush(ma, count, pagerflags, mreq, &runlen); + vm_pageout_flush(ma, count, pagerflags, mreq, &runlen, eio); return (runlen); } @@ -935,17 +948,20 @@ vm_object_page_collect_flush(vm_object_t * Note: certain anonymous maps, such as MAP_NOSYNC maps, * may start out with a NULL object. */ -void +boolean_t vm_object_sync(vm_object_t object, vm_ooffset_t offset, vm_size_t size, boolean_t syncio, boolean_t invalidate) { vm_object_t backing_object; struct vnode *vp; struct mount *mp; - int flags, fsync_after; + int error, flags, fsync_after; + boolean_t res; if (object == NULL) - return; + return (TRUE); + res = TRUE; + error = 0; VM_OBJECT_LOCK(object); while ((backing_object = object->backing_object) != NULL) { VM_OBJECT_LOCK(backing_object); @@ -991,16 +1007,18 @@ vm_object_sync(vm_object_t object, vm_oo fsync_after = FALSE; } VM_OBJECT_LOCK(object); - vm_object_page_clean(object, + res = vm_object_page_clean(object, OFF_TO_IDX(offset), OFF_TO_IDX(offset + size + PAGE_MASK), flags); VM_OBJECT_UNLOCK(object); if (fsync_after) - (void) VOP_FSYNC(vp, MNT_WAIT, curthread); + error = VOP_FSYNC(vp, MNT_WAIT, curthread); VOP_UNLOCK(vp, 0); VFS_UNLOCK_GIANT(vfslocked); vn_finished_write(mp); + if (error != 0) + res = FALSE; VM_OBJECT_LOCK(object); } if ((object->type == OBJT_VNODE || @@ -1013,6 +1031,7 @@ vm_object_sync(vm_object_t object, vm_oo purge ? FALSE : TRUE); } VM_OBJECT_UNLOCK(object); + return (res); } /* Modified: stable/8/sys/vm/vm_object.h ============================================================================== --- stable/8/sys/vm/vm_object.h Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_object.h Tue Apr 10 10:44:41 2012 (r234094) @@ -220,7 +220,7 @@ void vm_object_set_writeable_dirty (vm_o void vm_object_init (void); void vm_object_page_cache(vm_object_t object, vm_pindex_t start, vm_pindex_t end); -void vm_object_page_clean (vm_object_t, vm_pindex_t, vm_pindex_t, boolean_t); +boolean_t vm_object_page_clean(vm_object_t, vm_pindex_t, vm_pindex_t, boolean_t); void vm_object_page_remove (vm_object_t, vm_pindex_t, vm_pindex_t, boolean_t); boolean_t vm_object_populate(vm_object_t, vm_pindex_t, vm_pindex_t); void vm_object_reference (vm_object_t); @@ -228,7 +228,7 @@ void vm_object_reference_locked(vm_objec int vm_object_set_memattr(vm_object_t object, vm_memattr_t memattr); void vm_object_shadow (vm_object_t *, vm_ooffset_t *, vm_size_t); void vm_object_split(vm_map_entry_t); -void vm_object_sync(vm_object_t, vm_ooffset_t, vm_size_t, boolean_t, +boolean_t vm_object_sync(vm_object_t, vm_ooffset_t, vm_size_t, boolean_t, boolean_t); void vm_object_madvise (vm_object_t, vm_pindex_t, int, int); #endif /* _KERNEL */ Modified: stable/8/sys/vm/vm_pageout.c ============================================================================== --- stable/8/sys/vm/vm_pageout.c Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_pageout.c Tue Apr 10 10:44:41 2012 (r234094) @@ -391,7 +391,8 @@ more: /* * we allow reads during pageouts... */ - return (vm_pageout_flush(&mc[page_base], pageout_count, 0, 0, NULL)); + return (vm_pageout_flush(&mc[page_base], pageout_count, 0, 0, NULL, + NULL)); } /* @@ -405,9 +406,12 @@ more: * * Returned runlen is the count of pages between mreq and first * page after mreq with status VM_PAGER_AGAIN. + * *eio is set to TRUE if pager returned VM_PAGER_ERROR or VM_PAGER_FAIL + * for any page in runlen set. */ int -vm_pageout_flush(vm_page_t *mc, int count, int flags, int mreq, int *prunlen) +vm_pageout_flush(vm_page_t *mc, int count, int flags, int mreq, int *prunlen, + boolean_t *eio) { vm_object_t object = mc[0]->object; int pageout_status[count]; @@ -439,6 +443,8 @@ vm_pageout_flush(vm_page_t *mc, int coun vm_pager_put_pages(object, mc, count, flags, pageout_status); runlen = count - mreq; + if (eio != NULL) + *eio = FALSE; vm_page_lock_queues(); for (i = 0; i < count; i++) { vm_page_t mt = mc[i]; @@ -467,6 +473,8 @@ vm_pageout_flush(vm_page_t *mc, int coun * will try paging out it again later). */ vm_page_activate(mt); + if (eio != NULL && i >= mreq && i - mreq < runlen) + *eio = TRUE; break; case VM_PAGER_AGAIN: if (i >= mreq && i - mreq < runlen) Modified: stable/8/sys/vm/vm_pageout.h ============================================================================== --- stable/8/sys/vm/vm_pageout.h Tue Apr 10 09:27:41 2012 (r234093) +++ stable/8/sys/vm/vm_pageout.h Tue Apr 10 10:44:41 2012 (r234094) @@ -102,7 +102,7 @@ extern void vm_waitpfault(void); #ifdef _KERNEL boolean_t vm_pageout_fallback_object_lock(vm_page_t, vm_page_t *); -int vm_pageout_flush(vm_page_t *, int, int, int, int *); +int vm_pageout_flush(vm_page_t *, int, int, int, int *, boolean_t *); void vm_pageout_oom(int shortage); void vm_contig_grow_cache(int, vm_paddr_t, vm_paddr_t); #endif
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201204101044.q3AAigCn020197>