From 492229d0176c1af2ab4ea4cf91bf211e940b5b12 Mon Sep 17 00:00:00 2001 From: Jamie Liu Date: Tue, 4 Feb 2020 11:28:36 -0800 Subject: VFS2 gofer client Updates #1198 Opening host pipes (by spinning in fdpipe) and host sockets is not yet complete, and will be done in a future CL. Major differences from VFS1 gofer client (sentry/fs/gofer), with varying levels of backportability: - "Cache policies" are replaced by InteropMode, which control the behavior of timestamps in addition to caching. Under InteropModeExclusive (analogous to cacheAll) and InteropModeWritethrough (analogous to cacheAllWritethrough), client timestamps are *not* written back to the server (it is not possible in 9P or Linux for clients to set ctime, so writing back client-authoritative timestamps results in incoherence between atime/mtime and ctime). Under InteropModeShared (analogous to cacheRemoteRevalidating), client timestamps are not used at all (remote filesystem clocks are authoritative). cacheNone is translated to InteropModeShared + new option filesystemOptions.specialRegularFiles. - Under InteropModeShared, "unstable attribute" reloading for permission checks, lookup, and revalidation are fused, which is feasible in VFS2 since gofer.filesystem controls path resolution. This results in a ~33% reduction in RPCs for filesystem operations compared to cacheRemoteRevalidating. For example, consider stat("/foo/bar/baz") where "/foo/bar/baz" fails revalidation, resulting in the instantiation of a new dentry: VFS1 RPCs: getattr("/") // fs.MountNamespace.FindLink() => fs.Inode.CheckPermission() => gofer.inodeOperations.check() => gofer.inodeOperations.UnstableAttr() walkgetattr("/", "foo") = fid1 // fs.Dirent.walk() => gofer.session.Revalidate() => gofer.cachePolicy.Revalidate() clunk(fid1) getattr("/foo") // CheckPermission walkgetattr("/foo", "bar") = fid2 // Revalidate clunk(fid2) getattr("/foo/bar") // CheckPermission walkgetattr("/foo/bar", "baz") = fid3 // Revalidate clunk(fid3) walkgetattr("/foo/bar", "baz") = fid4 // fs.Dirent.walk() => gofer.inodeOperations.Lookup getattr("/foo/bar/baz") // linux.stat() => gofer.inodeOperations.UnstableAttr() VFS2 RPCs: getattr("/") // gofer.filesystem.walkExistingLocked() walkgetattr("/", "foo") = fid1 // gofer.filesystem.stepExistingLocked() clunk(fid1) // No getattr: walkgetattr already updated metadata for permission check walkgetattr("/foo", "bar") = fid2 clunk(fid2) walkgetattr("/foo/bar", "baz") = fid3 // No clunk: fid3 used for new gofer.dentry // No getattr: walkgetattr already updated metadata for stat() - gofer.filesystem.unlinkAt() does not require instantiation of a dentry that represents the file to be deleted. Updates #898. - gofer.regularFileFD.OnClose() skips Tflushf for regular files under InteropModeExclusive, as it's nonsensical to request a remote file flush without flushing locally-buffered writes to that remote file first. - Symlink targets are cached when InteropModeShared is not in effect. - p9.QID.Path (which is already required to be unique for each file within a server, and is accordingly already synthesized from device/inode numbers in all known gofers) is used as-is for inode numbers, rather than being mapped along with attr.RDev in the client to yet another synthetic inode number. - Relevant parts of fsutil.CachingInodeOperations are inlined directly into gofer package code. This avoids having to duplicate part of its functionality in fsutil.HostMappable. PiperOrigin-RevId: 293190213 --- pkg/sentry/fs/fsutil/BUILD | 4 ++-- pkg/sentry/fs/fsutil/frame_ref_set.go | 13 +++++++------ pkg/sentry/fs/fsutil/inode_cached.go | 2 +- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'pkg/sentry/fs/fsutil') diff --git a/pkg/sentry/fs/fsutil/BUILD b/pkg/sentry/fs/fsutil/BUILD index 4ab2a384f..789369220 100644 --- a/pkg/sentry/fs/fsutil/BUILD +++ b/pkg/sentry/fs/fsutil/BUILD @@ -28,13 +28,13 @@ go_template_instance( "platform": "gvisor.dev/gvisor/pkg/sentry/platform", }, package = "fsutil", - prefix = "frameRef", + prefix = "FrameRef", template = "//pkg/segment:generic_set", types = { "Key": "uint64", "Range": "platform.FileRange", "Value": "uint64", - "Functions": "frameRefSetFunctions", + "Functions": "FrameRefSetFunctions", }, ) diff --git a/pkg/sentry/fs/fsutil/frame_ref_set.go b/pkg/sentry/fs/fsutil/frame_ref_set.go index dd63db32b..6564fd0c6 100644 --- a/pkg/sentry/fs/fsutil/frame_ref_set.go +++ b/pkg/sentry/fs/fsutil/frame_ref_set.go @@ -20,24 +20,25 @@ import ( "gvisor.dev/gvisor/pkg/sentry/platform" ) -type frameRefSetFunctions struct{} +// FrameRefSetFunctions implements segment.Functions for FrameRefSet. +type FrameRefSetFunctions struct{} // MinKey implements segment.Functions.MinKey. -func (frameRefSetFunctions) MinKey() uint64 { +func (FrameRefSetFunctions) MinKey() uint64 { return 0 } // MaxKey implements segment.Functions.MaxKey. -func (frameRefSetFunctions) MaxKey() uint64 { +func (FrameRefSetFunctions) MaxKey() uint64 { return math.MaxUint64 } // ClearValue implements segment.Functions.ClearValue. -func (frameRefSetFunctions) ClearValue(val *uint64) { +func (FrameRefSetFunctions) ClearValue(val *uint64) { } // Merge implements segment.Functions.Merge. -func (frameRefSetFunctions) Merge(_ platform.FileRange, val1 uint64, _ platform.FileRange, val2 uint64) (uint64, bool) { +func (FrameRefSetFunctions) Merge(_ platform.FileRange, val1 uint64, _ platform.FileRange, val2 uint64) (uint64, bool) { if val1 != val2 { return 0, false } @@ -45,6 +46,6 @@ func (frameRefSetFunctions) Merge(_ platform.FileRange, val1 uint64, _ platform. } // Split implements segment.Functions.Split. -func (frameRefSetFunctions) Split(_ platform.FileRange, val uint64, _ uint64) (uint64, uint64) { +func (FrameRefSetFunctions) Split(_ platform.FileRange, val uint64, _ uint64) (uint64, uint64) { return val, val } diff --git a/pkg/sentry/fs/fsutil/inode_cached.go b/pkg/sentry/fs/fsutil/inode_cached.go index 573b8586e..800c8b4e1 100644 --- a/pkg/sentry/fs/fsutil/inode_cached.go +++ b/pkg/sentry/fs/fsutil/inode_cached.go @@ -111,7 +111,7 @@ type CachingInodeOperations struct { // refs tracks active references to data in the cache. // // refs is protected by dataMu. - refs frameRefSet + refs FrameRefSet } // CachingInodeOperationsOptions configures a CachingInodeOperations. -- cgit v1.2.3