merge-upstream/v5.4.98 from branch/tag: upstream/v5.4.98 into branch: cos-5.4

Changelog:
-------------------------------------------------------------

Baolin Wang (1):
      blk-cgroup: Use cond_resched() when destroy blkgs

Cong Wang (1):
      af_key: relax availability checks for skb size calculation

Daniel Borkmann (1):
      bpf: Fix 32 bit src register truncation on div/mod

Dave Wysochanski (2):
      SUNRPC: Move simple_get_bytes and simple_get_netobj into private header
      SUNRPC: Handle 0 length opaque XDR object data properly

David Collins (1):
      regulator: core: avoid regulator_resolve_supply() race condition

Eliot Blennerhassett (1):
      ASoC: ak4458: correct reset polarity

Emmanuel Grumbach (1):
      iwlwifi: pcie: add a NULL check in iwl_pcie_txq_unmap

Greg Kroah-Hartman (1):
      Linux 5.4.98

Gregory Greenman (1):
      iwlwifi: mvm: invalidate IDs of internal stations at mvm start

Johannes Berg (3):
      iwlwifi: mvm: take mutex for calling iwl_mvm_get_sync_time()
      iwlwifi: pcie: fix context info memory leak
      iwlwifi: mvm: guard against device removal in reprobe

Mark Brown (1):
      regulator: Fix lockdep warning resolving supplies

Masami Hiramatsu (1):
      tracing/kprobe: Fix to support kretprobe events on unloaded modules

Pan Bian (1):
      chtls: Fix potential resource leak

Peter Gonda (1):
      Fix unsynchronized access to sev members through svm_register_enc_region

Phillip Lougher (3):
      squashfs: add more sanity checks in id lookup
      squashfs: add more sanity checks in inode lookup
      squashfs: add more sanity checks in xattr id lookup

Qii Wang (1):
      i2c: mediatek: Move suspend and resume handling to NOIRQ phase

Ricardo Ribalda (1):
      ASoC: Intel: Skylake: Zero snd_ctl_elem_value

Sara Sharon (1):
      iwlwifi: mvm: skip power command when unbinding vif during CSA

Shay Bar (1):
      mac80211: 160MHz with extended NSS BW in CSA

Trond Myklebust (1):
      pNFS/NFSv4: Try to return invalid layout in pnfs_layout_process()

BUG=b/180208634
TEST=tryjob, validation and K8s e2e
RELEASE_NOTE=Updated the Linux kernel to upstream/v5.4.98.

Signed-off-by: COS Kernel Merge Bot <cloud-image-merge-automation@prod.google.com>
Change-Id: I508e1e7f8bd49a61d697f70e17f3670b59007568
diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst
index 6a8513a..d63bf2d 100644
--- a/Documentation/block/queue-sysfs.rst
+++ b/Documentation/block/queue-sysfs.rst
@@ -251,4 +251,13 @@
 do not support zone commands, they will be treated as regular block devices
 and zoned will report "none".
 
+split_alignment (RW)
+----------------------
+This is the alignment in bytes sectors at which the requeust queue is
+allowed to split IO requests. Once this value is set, the requeust
+queue splits IOs such that the individual IOs are aligned to
+split_alignment. The value of 0 indicates that an IO request can be
+split anywhere. This value must be a power of 2 and greater than or
+equal to 512.
+
 Jens Axboe <jens.axboe@oracle.com>, February 2009
diff --git a/Documentation/filesystems/ext4/journal.rst b/Documentation/filesystems/ext4/journal.rst
index ea613ee..cdbfec4 100644
--- a/Documentation/filesystems/ext4/journal.rst
+++ b/Documentation/filesystems/ext4/journal.rst
@@ -28,6 +28,17 @@
 safest. If ``data=writeback``, dirty data blocks are not flushed to the
 disk before the metadata are written to disk through the journal.
 
+In case of ``data=ordered`` mode, Ext4 also supports fast commits which
+help reduce commit latency significantly. The default ``data=ordered``
+mode works by logging metadata blocks to the journal. In fast commit
+mode, Ext4 only stores the minimal delta needed to recreate the
+affected metadata in fast commit space that is shared with JBD2.
+Once the fast commit area fills in or if fast commit is not possible
+or if JBD2 commit timer goes off, Ext4 performs a traditional full commit.
+A full commit invalidates all the fast commits that happened before
+it and thus it makes the fast commit area empty for further fast
+commits. This feature needs to be enabled at mkfs time.
+
 The journal inode is typically inode 8. The first 68 bytes of the
 journal inode are replicated in the ext4 superblock. The journal itself
 is normal (but hidden) file within the filesystem. The file usually
@@ -245,6 +256,10 @@
      - s\_padding2
      -
    * - 0x54
+     - \_\_be32
+     - s\_num\_fc\_blocks
+     - Number of fast commit blocks in the journal.
+   * - 0x58
      - \_\_u32
      - s\_padding[42]
      -
@@ -299,6 +314,8 @@
      - This journal uses v3 of the checksum on-disk format. This is the same as
        v2, but the journal block tag size is fixed regardless of the size of
        block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+   * - 0x20
+     - Journal has fast commit blocks. (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT)
 
 .. _jbd2_checksum_type:
 
@@ -609,3 +626,108 @@
      - h\_commit\_nsec
      - Nanoseconds component of the above timestamp.
 
+Fast commits
+~~~~~~~~~~~~
+
+Fast commit area is organized as a log of tag length values. Each TLV has
+a ``struct ext4_fc_tl`` in the beginning which stores the tag and the length
+of the entire field. It is followed by variable length tag specific value.
+Here is the list of supported tags and their meanings:
+
+.. list-table::
+   :widths: 8 20 20 32
+   :header-rows: 1
+
+   * - Tag
+     - Meaning
+     - Value struct
+     - Description
+   * - EXT4_FC_TAG_HEAD
+     - Fast commit area header
+     - ``struct ext4_fc_head``
+     - Stores the TID of the transaction after which these fast commits should
+       be applied.
+   * - EXT4_FC_TAG_ADD_RANGE
+     - Add extent to inode
+     - ``struct ext4_fc_add_range``
+     - Stores the inode number and extent to be added in this inode
+   * - EXT4_FC_TAG_DEL_RANGE
+     - Remove logical offsets to inode
+     - ``struct ext4_fc_del_range``
+     - Stores the inode number and the logical offset range that needs to be
+       removed
+   * - EXT4_FC_TAG_CREAT
+     - Create directory entry for a newly created file
+     - ``struct ext4_fc_dentry_info``
+     - Stores the parent inode number, inode number and directory entry of the
+       newly created file
+   * - EXT4_FC_TAG_LINK
+     - Link a directory entry to an inode
+     - ``struct ext4_fc_dentry_info``
+     - Stores the parent inode number, inode number and directory entry
+   * - EXT4_FC_TAG_UNLINK
+     - Unlink a directory entry of an inode
+     - ``struct ext4_fc_dentry_info``
+     - Stores the parent inode number, inode number and directory entry
+
+   * - EXT4_FC_TAG_PAD
+     - Padding (unused area)
+     - None
+     - Unused bytes in the fast commit area.
+
+   * - EXT4_FC_TAG_TAIL
+     - Mark the end of a fast commit
+     - ``struct ext4_fc_tail``
+     - Stores the TID of the commit, CRC of the fast commit of which this tag
+       represents the end of
+
+Fast Commit Replay Idempotence
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Fast commits tags are idempotent in nature provided the recovery code follows
+certain rules. The guiding principle that the commit path follows while
+committing is that it stores the result of a particular operation instead of
+storing the procedure.
+
+Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+was associated with inode 10. During fast commit, instead of storing this
+operation as a procedure "rename a to b", we store the resulting file system
+state as a "series" of outcomes:
+
+- Link dirent b to inode 10
+- Unlink dirent a
+- Inode 10 with valid refcount
+
+Now when recovery code runs, it needs "enforce" this state on the file
+system. This is what guarantees idempotence of fast commit replay.
+
+Let's take an example of a procedure that is not idempotent and see how fast
+commits make it idempotent. Consider following sequence of operations:
+
+1) rm A
+2) mv B A
+3) read A
+
+If we store this sequence of operations as is then the replay is not idempotent.
+Let's say while in replay, we crash after (2). During the second replay,
+file A (which was actually created as a result of "mv B A" operation) would get
+deleted. Thus, file named A would be absent when we try to read A. So, this
+sequence of operations is not idempotent. However, as mentioned above, instead
+of storing the procedure fast commits store the outcome of each procedure. Thus
+the fast commit log for above procedure would be as follows:
+
+(Let's assume dirent A was linked to inode 10 and dirent B was linked to
+inode 11 before the replay)
+
+1) Unlink A
+2) Link A to inode 11
+3) Unlink B
+4) Inode 11
+
+If we crash after (3) we will have file A linked to inode 11. During the second
+replay, we will remove file A (inode 11). But we will create it back and make
+it point to inode 11. We won't find B, so we'll just skip that step. At this
+point, the refcount for inode 11 is not reliable, but that gets fixed by the
+replay of last inode 11 tag. Thus, by converting a non-idempotent procedure
+into a series of idempotent outcomes, fast commits ensured idempotence during
+the replay.
diff --git a/Documentation/filesystems/ext4/super.rst b/Documentation/filesystems/ext4/super.rst
index 93e55d7..2eb1ab2 100644
--- a/Documentation/filesystems/ext4/super.rst
+++ b/Documentation/filesystems/ext4/super.rst
@@ -596,6 +596,13 @@
      - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
        points to the two block groups that contain backup superblocks
        (COMPAT\_SPARSE\_SUPER2).
+   * - 0x400
+     - Fast commits supported. Although fast commits blocks are
+       backward incompatible, fast commit blocks are not always
+       present in the journal. If fast commit blocks are present in
+       the journal, JBD2 incompat feature
+       (JBD2\_FEATURE\_INCOMPAT\_FAST\_COMMIT) gets
+       set (COMPAT\_FAST\_COMMIT).
 
 .. _super_incompat:
 
diff --git a/Documentation/filesystems/journalling.rst b/Documentation/filesystems/journalling.rst
index 58ce6b3..f88cbbe 100644
--- a/Documentation/filesystems/journalling.rst
+++ b/Documentation/filesystems/journalling.rst
@@ -132,6 +132,37 @@
 if you allow unprivileged userspace to trigger codepaths containing
 these calls.
 
+Fast commits
+~~~~~~~~~~~~
+
+JBD2 to also allows you to perform file-system specific delta commits known as
+fast commits. In order to use fast commits, you will need to set following
+callbacks that perform correspodning work:
+
+`journal->j_fc_cleanup_cb`: Cleanup function called after every full commit and
+fast commit.
+
+`journal->j_fc_replay_cb`: Replay function called for replay of fast commit
+blocks.
+
+File system is free to perform fast commits as and when it wants as long as it
+gets permission from JBD2 to do so by calling the function
+:c:func:`jbd2_fc_begin_commit()`. Once a fast commit is done, the client
+file  system should tell JBD2 about it by calling
+:c:func:`jbd2_fc_end_commit()`. If file system wants JBD2 to perform a full
+commit immediately after stopping the fast commit it can do so by calling
+:c:func:`jbd2_fc_end_commit_fallback()`. This is useful if fast commit operation
+fails for some reason and the only way to guarantee consistency is for JBD2 to
+perform the full traditional commit.
+
+JBD2 helper functions to manage fast commit buffers. File system can use
+:c:func:`jbd2_fc_get_buf()` and :c:func:`jbd2_fc_wait_bufs()` to allocate
+and wait on IO completion of fast commit buffers.
+
+Currently, only Ext4 implements fast commits. For details of its implementation
+of fast commits, please refer to the top level comments in
+fs/ext4/fast_commit.c.
+
 Summary
 ~~~~~~~
 
diff --git a/Makefile b/Makefile
index 4f6bfcf..6223e2e 100644
--- a/Makefile
+++ b/Makefile
@@ -789,11 +789,20 @@
 endif
 endif
 
-# Initialize all stack variables with a pattern, if desired.
-ifdef CONFIG_INIT_STACK_ALL
+# Initialize all stack variables with a 0xAA pattern.
+ifdef CONFIG_INIT_STACK_ALL_PATTERN
 KBUILD_CFLAGS	+= -ftrivial-auto-var-init=pattern
 endif
 
+# Initialize all stack variables with a zero value.
+ifdef CONFIG_INIT_STACK_ALL_ZERO
+# Future support for zero initialization is still being debated, see
+# https://bugs.llvm.org/show_bug.cgi?id=45497. These flags are subject to being
+# renamed or dropped.
+KBUILD_CFLAGS	+= -ftrivial-auto-var-init=zero
+KBUILD_CFLAGS	+= -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang
+endif
+
 DEBUG_CFLAGS	:= $(call cc-option, -fno-var-tracking-assignments)
 
 ifdef CONFIG_DEBUG_INFO
diff --git a/PRESUBMIT.cfg b/PRESUBMIT.cfg
new file mode 100644
index 0000000..0d7269b
--- /dev/null
+++ b/PRESUBMIT.cfg
@@ -0,0 +1,11 @@
+[Hook Overrides]
+aosp_license_check: false
+cros_license_check: false
+long_line_check: false
+stray_whitespace_check: false
+tab_check: false
+tabbed_indent_required_check: false
+signoff_check: true
+
+# Make sure RELEASE_NOTE field is present.
+release_note_field_check: true
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 02fc75d..f20b730 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -96,7 +96,7 @@
 {
 	return 0;
 }
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp) { }
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp) { }
 static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 {
 	return 0;
@@ -127,7 +127,7 @@
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
 static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
-static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
+static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
 
@@ -182,7 +182,7 @@
  * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the
  * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER.
  */
-static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
+static inline void perf_get_data_addr(struct perf_event *event, struct pt_regs *regs, u64 *addrp)
 {
 	unsigned long mmcra = regs->dsisr;
 	bool sdar_valid;
@@ -207,8 +207,7 @@
 	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 
-	if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-		is_kernel_addr(mfspr(SPRN_SDAR)))
+	if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
 		*addrp = 0;
 }
 
@@ -447,7 +446,7 @@
 }
 
 /* Processing BHRB entries */
-static void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw)
+static void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw)
 {
 	u64 val;
 	u64 addr;
@@ -475,8 +474,7 @@
 			 * exporting it to userspace (avoid exposure of regions
 			 * where we could have speculative execution)
 			 */
-			if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN) &&
-				is_kernel_addr(addr))
+			if (is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
 				continue;
 
 			/* Branches are read most recent first (ie. mfbhrb 0 is
@@ -2109,12 +2107,12 @@
 
 		if (event->attr.sample_type &
 		    (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
-			perf_get_data_addr(regs, &data.addr);
+			perf_get_data_addr(event, regs, &data.addr);
 
 		if (event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK) {
 			struct cpu_hw_events *cpuhw;
 			cpuhw = this_cpu_ptr(&cpu_hw_events);
-			power_pmu_bhrb_read(cpuhw);
+			power_pmu_bhrb_read(event, cpuhw);
 			data.br_stack = &cpuhw->bhrb_stack;
 		}
 
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 741540d..6a3b599 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -555,9 +555,11 @@
 	 * Note that the default paranoia setting permits unprivileged
 	 * users to profile the kernel.
 	 */
-	if (event->attr.exclude_kernel && perf_paranoid_kernel() &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if (event->attr.exclude_kernel) {
+		ret = perf_allow_kernel(&event->attr);
+		if (ret)
+			return ret;
+	}
 
 	if (x86_add_exclusive(x86_lbr_exclusive_bts))
 		return -EBUSY;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b24c380..40c1320 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3316,8 +3316,9 @@
 	if (x86_pmu.version < 3)
 		return -EINVAL;
 
-	if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	ret = perf_allow_cpu(&event->attr);
+	if (ret)
+		return ret;
 
 	event->hw.config |= ARCH_PERFMON_EVENTSEL_ANY;
 
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index dee579e..a4cc660 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -776,8 +776,9 @@
 	 * the user needs special permissions to be able to use it
 	 */
 	if (p4_ht_active() && p4_event_bind_map[v].shared) {
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		v = perf_allow_cpu(&event->attr);
+		if (v)
+			return v;
 	}
 
 	/* ESCR EventMask bits may be invalid */
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 86c4c1e..73c3504 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -105,15 +105,18 @@
 static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
 		struct bio *bio, struct bio_set *bs, unsigned *nsegs)
 {
+	sector_t split;
+
 	*nsegs = 0;
 
-	if (!q->limits.max_write_zeroes_sectors)
+	split = q->limits.max_write_zeroes_sectors;
+	if (split && q->split_alignment)
+		split = round_down(split, q->split_alignment);
+
+	if (!split || bio_sectors(bio) <= split)
 		return NULL;
 
-	if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
-		return NULL;
-
-	return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+	return bio_split(bio, split, GFP_NOIO, bs);
 }
 
 static struct bio *blk_bio_write_same_split(struct request_queue *q,
@@ -121,15 +124,18 @@
 					    struct bio_set *bs,
 					    unsigned *nsegs)
 {
+	sector_t split;
+
 	*nsegs = 1;
 
-	if (!q->limits.max_write_same_sectors)
+	split = q->limits.max_write_same_sectors;
+	if (split && q->split_alignment)
+		split = round_down(split, q->split_alignment);
+
+	if (!split || bio_sectors(bio) <= split)
 		return NULL;
 
-	if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
-		return NULL;
-
-	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+	return bio_split(bio, split, GFP_NOIO, bs);
 }
 
 /*
@@ -248,7 +254,9 @@
 {
 	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
-	unsigned nsegs = 0, sectors = 0;
+	unsigned int nsegs = 0, nsegs_aligned = 0;
+	unsigned int sectors = 0, sectors_aligned = 0, before = 0, after = 0;
+	unsigned int sector_alignment = q->split_alignment;
 	const unsigned max_sectors = get_max_io_size(q, bio);
 	const unsigned max_segs = queue_max_segments(q);
 
@@ -264,12 +272,31 @@
 		    sectors + (bv.bv_len >> 9) <= max_sectors &&
 		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
 			nsegs++;
-			sectors += bv.bv_len >> 9;
-		} else if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
-					 max_sectors)) {
-			goto split;
+			before = round_down(sectors, sector_alignment);
+			sectors += (bv.bv_len >> 9);
+			after = round_down(sectors, sector_alignment);
+			if (sector_alignment && before != after) {
+				/* This is a valid split point */
+				nsegs_aligned = nsegs;
+				sectors_aligned = after;
+			}
+			goto next;
 		}
-
+		if (sector_alignment) {
+			before = round_down(sectors, sector_alignment);
+			after = round_down(sectors + (bv.bv_len >> 9),
+					  sector_alignment);
+			if ((nsegs < max_segs) && before != after &&
+			    ((after - before) << 9) + bv.bv_offset <=  PAGE_SIZE
+			    && after <= max_sectors) {
+				sectors_aligned = after;
+				nsegs_aligned = nsegs + 1;
+			}
+		}
+		if (bvec_split_segs(q, &bv, &nsegs, &sectors, max_segs,
+				    max_sectors))
+			goto split;
+next:
 		bvprv = bv;
 		bvprvp = &bvprv;
 	}
@@ -278,7 +305,13 @@
 	return NULL;
 split:
 	*segs = nsegs;
-	return bio_split(bio, sectors, GFP_NOIO, bs);
+	if (sector_alignment && sectors_aligned == 0)
+		return NULL;
+
+	*segs = sector_alignment ? nsegs_aligned : nsegs;
+
+	return bio_split(bio, sector_alignment ? sectors_aligned : sectors,
+			 GFP_NOIO, bs);
 }
 
 /**
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index bf33570..6bc2cfb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -529,6 +529,33 @@
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
+static ssize_t queue_split_alignment_show(struct request_queue *q, char *page)
+{
+	return queue_var_show((q->split_alignment << 9), page);
+}
+
+static ssize_t queue_split_alignment_store(struct request_queue *q, const char *page,
+						size_t count)
+{
+	unsigned long split_alignment;
+	int ret;
+
+	ret = queue_var_store(&split_alignment, page, count);
+	if (ret < 0)
+		return ret;
+
+	/* split_alignment can only be a power of 2 */
+	if (split_alignment & (split_alignment - 1))
+		return -EINVAL;
+
+	/* ..and it should be greater than 512 */
+	if (!(split_alignment >> 9))
+		return -EINVAL;
+
+	q->split_alignment = split_alignment >> 9;
+	return count;
+}
+
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = 0644 },
 	.show = queue_requests_show,
@@ -727,6 +754,12 @@
 };
 #endif
 
+static struct queue_sysfs_entry queue_split_alignment = {
+	.attr = {.name = "split_alignment", .mode = 0644 },
+	.show = queue_split_alignment_show,
+	.store = queue_split_alignment_store,
+};
+
 static struct attribute *queue_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -766,6 +799,7 @@
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	&throtl_sample_time_entry.attr,
 #endif
+	&queue_split_alignment.attr,
 	NULL,
 };
 
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 28b92e3..796d660 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -59,6 +59,15 @@
 	  rescue mode with init=/bin/sh, even when the /dev directory
 	  on the rootfs is completely empty.
 
+config DEVTMPFS_SAFE
+	bool "Automount devtmpfs with nosuid/noexec"
+	depends on DEVTMPFS_MOUNT
+	default y
+	help
+	  This instructs the kernel to automount devtmpfs with the
+	  MS_NOEXEC and MS_NOSUID mount flags, which can prevent
+	  certain kinds of code-execution attack on embedded platforms.
+
 config STANDALONE
 	bool "Select only drivers that don't need compile-time external firmware"
 	default y
diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c
index 30d0523..354877e 100644
--- a/drivers/base/devtmpfs.c
+++ b/drivers/base/devtmpfs.c
@@ -362,6 +362,7 @@
 int devtmpfs_mount(const char *mntdir)
 {
 	int err;
+	int mflags = MS_SILENT;
 
 	if (!mount_dev)
 		return 0;
@@ -369,7 +370,10 @@
 	if (!thread)
 		return 0;
 
-	err = ksys_mount("devtmpfs", mntdir, "devtmpfs", MS_SILENT, NULL);
+#ifdef CONFIG_DEVTMPFS_SAFE
+	mflags |= MS_NOEXEC | MS_NOSUID;
+#endif
+	err = ksys_mount("devtmpfs", mntdir, "devtmpfs", mflags, NULL);
 	if (err)
 		printk(KERN_INFO "devtmpfs: error mounting %i\n", err);
 	else
diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c
index b869316..7ef3cec 100644
--- a/drivers/md/dm-init.c
+++ b/drivers/md/dm-init.c
@@ -301,3 +301,254 @@
 
 module_param(create, charp, 0);
 MODULE_PARM_DESC(create, "Create a mapped device in early boot");
+
+/* ---------------------------------------------------------------
+ * ChromeOS shim - convert dm= format to dm-mod.create= format
+ * ---------------------------------------------------------------
+ */
+
+struct dm_chrome_target {
+	char *field[4];
+};
+
+struct dm_chrome_dev {
+	char *name, *uuid, *mode;
+	unsigned int num_targets;
+	struct dm_chrome_target targets[DM_MAX_TARGETS];
+};
+
+static char __init *dm_chrome_parse_target(char *str, struct dm_chrome_target *tgt)
+{
+	unsigned int i;
+
+	tgt->field[0] = str;
+	/* Delimit first 3 fields that are separated by space */
+	for (i = 0; i < ARRAY_SIZE(tgt->field) - 1; i++) {
+		tgt->field[i + 1] = str_field_delimit(&tgt->field[i], ' ');
+		if (!tgt->field[i + 1])
+			return NULL;
+	}
+	/* Delimit last field that can be terminated by comma */
+	return str_field_delimit(&tgt->field[i], ',');
+}
+
+static char __init *dm_chrome_parse_dev(char *str, struct dm_chrome_dev *dev)
+{
+	char *target, *num;
+	unsigned int i;
+
+	if (!str)
+		return ERR_PTR(-EINVAL);
+
+	target = str_field_delimit(&str, ',');
+	if (!target)
+		return ERR_PTR(-EINVAL);
+
+	/* Delimit first 3 fields that are separated by space */
+	dev->name = str;
+	dev->uuid = str_field_delimit(&dev->name, ' ');
+	if (!dev->uuid)
+		return ERR_PTR(-EINVAL);
+
+	dev->mode = str_field_delimit(&dev->uuid, ' ');
+	if (!dev->mode)
+		return ERR_PTR(-EINVAL);
+
+	/* num is optional */
+	num = str_field_delimit(&dev->mode, ' ');
+	if (!num)
+		dev->num_targets = 1;
+	else {
+		/* Delimit num and check if it the last field */
+		if(str_field_delimit(&num, ' '))
+			return ERR_PTR(-EINVAL);
+		if (kstrtouint(num, 0, &dev->num_targets))
+			return ERR_PTR(-EINVAL);
+	}
+
+	if (dev->num_targets > DM_MAX_TARGETS) {
+		DMERR("too many targets %u > %d",
+		      dev->num_targets, DM_MAX_TARGETS);
+		return ERR_PTR(-EINVAL);
+	}
+
+	for (i = 0; i < dev->num_targets - 1; i++) {
+		target = dm_chrome_parse_target(target, &dev->targets[i]);
+		if (!target)
+			return ERR_PTR(-EINVAL);
+	}
+	/* The last one can return NULL if it reaches the end of str */
+	return dm_chrome_parse_target(target, &dev->targets[i]);
+}
+
+static char __init *dm_chrome_convert(struct dm_chrome_dev *devs, unsigned int num_devs)
+{
+	char *str = kmalloc(DM_MAX_STR_SIZE, GFP_KERNEL);
+	char *p = str;
+	unsigned int i, j;
+	int ret;
+
+	if (!str)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < num_devs; i++) {
+		if (!strcmp(devs[i].uuid, "none"))
+			devs[i].uuid = "";
+		ret = snprintf(p, DM_MAX_STR_SIZE - (p - str),
+			       "%s,%s,,%s",
+			       devs[i].name,
+			       devs[i].uuid,
+			       devs[i].mode);
+		if (ret < 0)
+			goto out;
+		p += ret;
+
+		for (j = 0; j < devs[i].num_targets; j++) {
+			ret = snprintf(p, DM_MAX_STR_SIZE - (p - str),
+				       ",%s %s %s %s",
+				       devs[i].targets[j].field[0],
+				       devs[i].targets[j].field[1],
+				       devs[i].targets[j].field[2],
+				       devs[i].targets[j].field[3]);
+			if (ret < 0)
+				goto out;
+			p += ret;
+		}
+		if (i < num_devs - 1) {
+			ret = snprintf(p, DM_MAX_STR_SIZE - (p - str), ";");
+			if (ret < 0)
+				goto out;
+			p += ret;
+		}
+	}
+
+	return str;
+
+out:
+	kfree(str);
+	return ERR_PTR(ret);
+}
+
+/**
+ * dm_chrome_shim - convert old dm= format used in chromeos to the new
+ * upstream format.
+ *
+ * ChromeOS old format
+ * -------------------
+ * <device>        ::= [<num>] <device-mapper>+
+ * <device-mapper> ::= <head> "," <target>+
+ * <head>          ::= <name> <uuid> <mode> [<num>]
+ * <target>        ::= <start> <length> <type> <options> ","
+ * <mode>          ::= "ro" | "rw"
+ * <uuid>          ::= xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx | "none"
+ * <type>          ::= "verity" | "bootcache" | ...
+ *
+ * Example:
+ * 2 vboot none ro 1,
+ *     0 1768000 bootcache
+ *       device=aa55b119-2a47-8c45-946a-5ac57765011f+1
+ *       signature=76e9be054b15884a9fa85973e9cb274c93afadb6
+ *       cache_start=1768000 max_blocks=100000 size_limit=23 max_trace=20000,
+ *   vroot none ro 1,
+ *     0 1740800 verity payload=254:0 hashtree=254:0 hashstart=1740800 alg=sha1
+ *       root_hexdigest=76e9be054b15884a9fa85973e9cb274c93afadb6
+ *       salt=5b3549d54d6c7a3837b9b81ed72e49463a64c03680c47835bef94d768e5646fe
+ *
+ * Notes:
+ *  1. uuid is a label for the device and we set it to "none".
+ *  2. The <num> field will be optional initially and assumed to be 1.
+ *     Once all the scripts that set these fields have been set, it will
+ *     be made mandatory.
+ */
+
+static char *chrome_create;
+
+static int __init dm_chrome_shim(char *arg) {
+	if (!arg || create)
+		return -EINVAL;
+	chrome_create = arg;
+	return 0;
+}
+
+static int __init dm_chrome_parse_devices(void)
+{
+	struct dm_chrome_dev *devs;
+	unsigned int num_devs, i;
+	char *next, *base_str;
+	int ret = 0;
+
+	/* Verify if dm-mod.create was not used */
+	if (!chrome_create || create)
+		return -EINVAL;
+
+	if (strlen(chrome_create) >= DM_MAX_STR_SIZE) {
+		DMERR("Argument is too big. Limit is %d\n", DM_MAX_STR_SIZE);
+		return -EINVAL;
+	}
+
+	base_str = kstrdup(chrome_create, GFP_KERNEL);
+	if (!base_str)
+		return -ENOMEM;
+
+	next = str_field_delimit(&base_str, ' ');
+	if (!next) {
+		ret = -EINVAL;
+		goto out_str;
+	}
+
+	/* if first field is not the optional <num> field */
+	if (kstrtouint(base_str, 0, &num_devs)) {
+		num_devs = 1;
+		/* rewind next pointer */
+		next = base_str;
+	}
+
+	if (num_devs > DM_MAX_DEVICES) {
+		DMERR("too many devices %u > %d", num_devs, DM_MAX_DEVICES);
+		ret = -EINVAL;
+		goto out_str;
+	}
+
+	devs = kcalloc(num_devs, sizeof(*devs), GFP_KERNEL);
+	if (!devs)
+		return -ENOMEM;
+
+	/* restore string */
+	strcpy(base_str, chrome_create);
+
+	/* parse devices */
+	for (i = 0; i < num_devs; i++) {
+		next = dm_chrome_parse_dev(next, &devs[i]);
+		if (IS_ERR(next)) {
+			DMERR("couldn't parse device");
+			ret = PTR_ERR(next);
+			goto out_devs;
+		}
+	}
+
+	create = dm_chrome_convert(devs, num_devs);
+	if (IS_ERR(create)) {
+		ret = PTR_ERR(create);
+		goto out_devs;
+	}
+
+	DMDEBUG("Converting:\n\tdm=\"%s\"\n\tdm-mod.create=\"%s\"\n",
+		chrome_create, create);
+
+	/* Call upstream code */
+	dm_init_init();
+
+	kfree(create);
+
+out_devs:
+	create = NULL;
+	kfree(devs);
+out_str:
+	kfree(base_str);
+
+	return ret;
+}
+
+late_initcall(dm_chrome_parse_devices);
+
+__setup("dm=", dm_chrome_shim);
diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
index 2aeb922..4f1c21f 100644
--- a/drivers/md/dm-verity-target.c
+++ b/drivers/md/dm-verity-target.c
@@ -16,8 +16,10 @@
 #include "dm-verity.h"
 #include "dm-verity-fec.h"
 #include "dm-verity-verify-sig.h"
+#include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/reboot.h>
+#include <crypto/hash.h>
 
 #define DM_MSG_PREFIX			"verity"
 
@@ -32,8 +34,9 @@
 #define DM_VERITY_OPT_RESTART		"restart_on_corruption"
 #define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"
 #define DM_VERITY_OPT_AT_MOST_ONCE	"check_at_most_once"
+#define DM_VERITY_OPT_ERROR_BEHAVIOR	"error_behavior"
 
-#define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC + \
+#define DM_VERITY_OPTS_MAX		(4 + DM_VERITY_OPTS_FEC + \
 					 DM_VERITY_ROOT_HASH_VERIFICATION_OPTS)
 
 static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
@@ -47,6 +50,120 @@
 	unsigned n_blocks;
 };
 
+/* Provide a lightweight means of specifying the global default for
+ * error behavior: eio, reboot, or none
+ * Legacy support for 0 = eio, 1 = reboot/panic, 2 = none, 3 = notify.
+ * This is matched to the enum in dm-verity.h.
+ */
+static char *error_behavior_istring[] = { "0", "1", "2", "3" };
+static const char *allowed_error_behaviors[] = { "eio", "panic", "none",
+						 "notify", NULL };
+static char *error_behavior = "eio";
+module_param(error_behavior, charp, 0644);
+MODULE_PARM_DESC(error_behavior, "Behavior on error "
+				 "(eio, panic, none, notify)");
+
+/* Controls whether verity_get_device will wait forever for a device. */
+static int dev_wait;
+module_param(dev_wait, int, 0444);
+MODULE_PARM_DESC(dev_wait, "Wait forever for a backing device");
+
+static BLOCKING_NOTIFIER_HEAD(verity_error_notifier);
+
+int dm_verity_register_error_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&verity_error_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(dm_verity_register_error_notifier);
+
+int dm_verity_unregister_error_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&verity_error_notifier, nb);
+}
+EXPORT_SYMBOL_GPL(dm_verity_unregister_error_notifier);
+
+/* If the request is not successful, this handler takes action.
+ * TODO make this call a registered handler.
+ */
+static void verity_error(struct dm_verity *v, struct dm_verity_io *io,
+			 blk_status_t status)
+{
+	const char *message = v->hash_failed ? "integrity" : "block";
+	int error_behavior = DM_VERITY_ERROR_BEHAVIOR_PANIC;
+	dev_t devt = 0;
+	u64 block = ~0;
+	struct dm_verity_error_state error_state;
+	/* If the hash did not fail, then this is likely transient. */
+	int transient = !v->hash_failed;
+
+	devt = v->data_dev->bdev->bd_dev;
+	error_behavior = v->error_behavior;
+
+	DMERR_LIMIT("verification failure occurred: %s failure", message);
+
+	if (error_behavior == DM_VERITY_ERROR_BEHAVIOR_NOTIFY) {
+		error_state.code = status;
+		error_state.transient = transient;
+		error_state.block = block;
+		error_state.message = message;
+		error_state.dev_start = v->data_start;
+		error_state.dev_len = v->data_blocks;
+		error_state.dev = v->data_dev->bdev;
+		error_state.hash_dev_start = v->hash_start;
+		error_state.hash_dev_len = v->hash_blocks;
+		error_state.hash_dev = v->hash_dev->bdev;
+
+		/* Set default fallthrough behavior. */
+		error_state.behavior = DM_VERITY_ERROR_BEHAVIOR_PANIC;
+		error_behavior = DM_VERITY_ERROR_BEHAVIOR_PANIC;
+
+		if (!blocking_notifier_call_chain(
+		    &verity_error_notifier, transient, &error_state)) {
+			error_behavior = error_state.behavior;
+		}
+	}
+
+	switch (error_behavior) {
+	case DM_VERITY_ERROR_BEHAVIOR_EIO:
+		break;
+	case DM_VERITY_ERROR_BEHAVIOR_NONE:
+		break;
+	default:
+		if (!transient)
+			goto do_panic;
+	}
+	return;
+
+do_panic:
+	panic("dm-verity failure: "
+	      "device:%u:%u status:%d block:%llu message:%s",
+	      MAJOR(devt), MINOR(devt), status, (u64)block, message);
+}
+
+/**
+ * verity_parse_error_behavior - parse a behavior charp to the enum
+ * @behavior:	NUL-terminated char array
+ *
+ * Checks if the behavior is valid either as text or as an index digit
+ * and returns the proper enum value in string form or ERR_PTR(-EINVAL)
+ * on error.
+ */
+static char *verity_parse_error_behavior(const char *behavior)
+{
+	const char **allowed = allowed_error_behaviors;
+	int index;
+
+	for (index = 0; *allowed; allowed++, index++)
+		if (!strcmp(*allowed, behavior) || behavior[0] == index + '0')
+			break;
+
+	if (!*allowed)
+		return ERR_PTR(-EINVAL);
+
+	/* Convert to the integer index matching the enum. */
+	return error_behavior_istring[index];
+}
+
 /*
  * Auxiliary structure appended to each dm-bufio buffer. If the value
  * hash_verified is nonzero, hash of the block has been verified.
@@ -550,6 +667,8 @@
 	struct dm_verity *v = io->v;
 	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
 
+	if (status && !verity_fec_is_enabled(io->v))
+		verity_error(v, io, status);
 	bio->bi_end_io = io->orig_bi_end_io;
 	bio->bi_status = status;
 
@@ -917,6 +1036,22 @@
 				return r;
 			continue;
 
+		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_ERROR_BEHAVIOR)) {
+			int behavior;
+
+			if (!argc) {
+				ti->error = "Missing error behavior parameter";
+				return -EINVAL;
+			}
+			if (kstrtoint(dm_shift_arg(as), 0, &behavior) ||
+			    behavior < 0) {
+				ti->error = "Bad error behavior parameter";
+				return -EINVAL;
+			}
+			v->error_behavior = behavior;
+			argc--;
+			continue;
+
 		} else if (verity_is_fec_opt_arg(arg_name)) {
 			r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
 			if (r)
@@ -939,6 +1074,132 @@
 	return r;
 }
 
+static int verity_get_device(struct dm_target *ti, const char *devname,
+			     struct dm_dev **dm_dev)
+{
+	do {
+		/* Try the normal path first since if everything is ready, it
+		 * will be the fastest.
+		 */
+		if (!dm_get_device(ti, devname,
+				   dm_table_get_mode(ti->table), dm_dev))
+			return 0;
+
+		if (!dev_wait)
+			break;
+
+		/* No need to be too aggressive since this is a slow path. */
+		msleep(500);
+	} while (dev_wait && (driver_probe_done() != 0 || *dm_dev == NULL));
+	return -1;
+}
+
+static void splitarg(char *arg, char **key, char **val)
+{
+	*key = strsep(&arg, "=");
+	*val = strsep(&arg, "");
+}
+
+/* Convert Chrome OS arguments into standard arguments */
+
+static char *chromeos_args(unsigned *pargc, char ***pargv)
+{
+	char *hashstart = NULL;
+	char **argv = *pargv;
+	int argc = *pargc;
+	char *key, *val;
+	int nargc = 10;
+	char **nargv;
+	char *errstr;
+	int i;
+
+	nargv = kcalloc(14, sizeof(char *), GFP_KERNEL);
+	if (!nargv)
+		return "Failed to allocate memory";
+
+	nargv[0] = "0";		/* version */
+	nargv[3] = "4096";	/* hash block size */
+	nargv[4] = "4096";	/* data block size */
+	nargv[9] = "-";		/* salt (optional) */
+
+	for (i = 0; i < argc; ++i) {
+		DMDEBUG("Argument %d: '%s'", i, argv[i]);
+		splitarg(argv[i], &key, &val);
+		if (!key) {
+			DMWARN("Bad argument %d: missing key?", i);
+			errstr = "Bad argument: missing key";
+			goto err;
+		}
+		if (!val) {
+			DMWARN("Bad argument %d='%s': missing value", i, key);
+			errstr = "Bad argument: missing value";
+			goto err;
+		}
+		if (!strcmp(key, "alg")) {
+			nargv[7] = val;
+		} else if (!strcmp(key, "payload")) {
+			nargv[1] = val;
+		} else if (!strcmp(key, "hashtree")) {
+			nargv[2] = val;
+		} else if (!strcmp(key, "root_hexdigest")) {
+			nargv[8] = val;
+		} else if (!strcmp(key, "hashstart")) {
+			unsigned long num;
+
+			if (kstrtoul(val, 10, &num)) {
+				errstr = "Invalid hashstart";
+				goto err;
+			}
+			num >>= (12 - SECTOR_SHIFT);
+			hashstart = kmalloc(24, GFP_KERNEL);
+			if (!hashstart) {
+				errstr = "Failed to allocate memory";
+				goto err;
+			}
+			scnprintf(hashstart, sizeof(hashstart), "%lu", num);
+			nargv[5] = hashstart;
+			nargv[6] = hashstart;
+		} else if (!strcmp(key, "salt")) {
+			nargv[9] = val;
+		} else if (!strcmp(key, DM_VERITY_OPT_ERROR_BEHAVIOR)) {
+			char *behavior = verity_parse_error_behavior(val);
+
+			if (IS_ERR(behavior)) {
+				errstr = "Invalid error behavior";
+				goto err;
+			}
+			nargv[10] = "2";
+			nargv[11] = key;
+			nargv[12] = behavior;
+			nargc = 13;
+		}
+	}
+
+	if (!nargv[1] || !nargv[2] || !nargv[5] || !nargv[7] || !nargv[8]) {
+		errstr = "Missing argument";
+		goto err;
+	}
+
+	*pargc = nargc;
+	*pargv = nargv;
+	return NULL;
+
+err:
+	kfree(nargv);
+	kfree(hashstart);
+	return errstr;
+}
+
+/* Release memory allocated for Chrome OS parameter conversion */
+
+static void free_chromeos_argv(char **argv)
+{
+	if (argv) {
+		kfree(argv[5]);
+		kfree(argv);
+	}
+}
+
 /*
  * Target parameters:
  *	<version>	The current format is version 1.
@@ -965,10 +1226,19 @@
 	sector_t hash_position;
 	char dummy;
 	char *root_hash_digest_to_validate;
+	char **chromeos_argv = NULL;
+
+	if (argc < 10) {
+		ti->error = chromeos_args(&argc, &argv);
+		if (ti->error)
+			return -EINVAL;
+		chromeos_argv = argv;
+	}
 
 	v = kzalloc(sizeof(struct dm_verity), GFP_KERNEL);
 	if (!v) {
 		ti->error = "Cannot allocate verity structure";
+		free_chromeos_argv(chromeos_argv);
 		return -ENOMEM;
 	}
 	ti->private = v;
@@ -998,13 +1268,13 @@
 	}
 	v->version = num;
 
-	r = dm_get_device(ti, argv[1], FMODE_READ, &v->data_dev);
+	r = verity_get_device(ti, argv[1], &v->data_dev);
 	if (r) {
 		ti->error = "Data device lookup failed";
 		goto bad;
 	}
 
-	r = dm_get_device(ti, argv[2], FMODE_READ, &v->hash_dev);
+	r = verity_get_device(ti, argv[2], &v->hash_dev);
 	if (r) {
 		ti->error = "Hash device lookup failed";
 		goto bad;
@@ -1204,14 +1474,14 @@
 				       __alignof__(struct dm_verity_io));
 
 	verity_verify_sig_opts_cleanup(&verify_args);
-
+	free_chromeos_argv(chromeos_argv);
 	return 0;
 
 bad:
 
 	verity_verify_sig_opts_cleanup(&verify_args);
 	verity_dtr(ti);
-
+	free_chromeos_argv(chromeos_argv);
 	return r;
 }
 
diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h
index 641b9e3..f453caf 100644
--- a/drivers/md/dm-verity.h
+++ b/drivers/md/dm-verity.h
@@ -14,6 +14,7 @@
 #include <linux/dm-bufio.h>
 #include <linux/device-mapper.h>
 #include <crypto/hash.h>
+#include <linux/notifier.h>
 
 #define DM_VERITY_MAX_LEVELS		63
 
@@ -55,6 +56,7 @@
 	int hash_failed;	/* set to 1 if hash of any block failed */
 	enum verity_mode mode;	/* mode for handling verification errors */
 	unsigned corrupted_errs;/* Number of errors for corrupted blocks */
+	int error_behavior;	/* selects error behavior on io errors */
 
 	struct workqueue_struct *verify_wq;
 
@@ -92,6 +94,40 @@
 	 */
 };
 
+struct verity_result {
+	struct completion completion;
+	int err;
+};
+
+struct dm_verity_error_state {
+	int code;
+	int transient;  /* Likely to not happen after a reboot */
+	u64 block;
+	const char *message;
+
+	sector_t dev_start;
+	sector_t dev_len;
+	struct block_device *dev;
+
+	sector_t hash_dev_start;
+	sector_t hash_dev_len;
+	struct block_device *hash_dev;
+
+	/* Final behavior after all notifications are completed. */
+	int behavior;
+};
+
+/* This enum must be matched to allowed_error_behaviors in dm-verity.c */
+enum dm_verity_error_behavior {
+	DM_VERITY_ERROR_BEHAVIOR_EIO = 0,
+	DM_VERITY_ERROR_BEHAVIOR_PANIC,
+	DM_VERITY_ERROR_BEHAVIOR_NONE,
+	DM_VERITY_ERROR_BEHAVIOR_NOTIFY
+};
+
+int dm_verity_register_error_notifier(struct notifier_block *nb);
+int dm_verity_unregister_error_notifier(struct notifier_block *nb);
+
 static inline struct ahash_request *verity_io_hash_req(struct dm_verity *v,
 						     struct dm_verity_io *io)
 {
diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index ebc37e2..133c698 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -27,6 +27,17 @@
 /* 1 for management, 1 for rx, 1 for tx */
 #define GVE_MIN_MSIX 3
 
+/* Numbers of gve tx/rx stats in stats report. */
+#define GVE_TX_STATS_REPORT_NUM	5
+#define GVE_RX_STATS_REPORT_NUM	2
+
+/* Numbers of NIC tx/rx stats in stats report. */
+#define NIC_TX_STATS_REPORT_NUM	0
+#define NIC_RX_STATS_REPORT_NUM	4
+
+/* Interval to schedule a service task, 20000ms. */
+#define GVE_SERVICE_TIMER_PERIOD	20000
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -39,6 +50,8 @@
 	struct page *page;
 	void *page_address;
 	u32 page_offset; /* offset to write to in page */
+	int pagecnt_bias; /* expected pagecnt if only the driver has a ref */
+	bool can_flip; /* page can be flipped and reused */
 };
 
 /* A list of pages registered with the device during setup and used by a queue
@@ -57,6 +70,7 @@
 	dma_addr_t data_bus; /* dma mapping of the slots */
 	struct gve_rx_slot_page_info *page_info; /* page info of the buffers */
 	struct gve_queue_page_list *qpl; /* qpl assigned to this queue */
+	bool raw_addressing; /* use raw_addressing? */
 };
 
 struct gve_priv;
@@ -71,6 +85,13 @@
 	u32 cnt; /* free-running total number of completed packets */
 	u32 fill_cnt; /* free-running total number of descs and buffs posted */
 	u32 mask; /* masks the cnt and fill_cnt to the size of the ring */
+	u32 db_threshold; /* threshold for posting new buffs and descs */
+	u64 rx_copybreak_pkt; /* free-running count of copybreak packets */
+	u64 rx_copied_pkt; /* free-running total number of copied packets */
+	u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */
+	u64 rx_buf_alloc_fail; /* free-running count of buffer alloc fails */
+	u64 rx_desc_err_dropped_pkt; /* free-running count of packets dropped by descriptor error */
+	u64 rx_no_refill_dropped_pkt; /* free-running count of packets dropped because of lack of buffer refill */
 	u32 q_num; /* queue index */
 	u32 ntfy_id; /* notification block index */
 	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
@@ -91,12 +112,20 @@
 	u32 iov_padding; /* padding associated with this segment */
 };
 
+struct gve_tx_dma_buf {
+	DEFINE_DMA_UNMAP_ADDR(dma);
+	DEFINE_DMA_UNMAP_LEN(len);
+};
+
 /* Tracks the memory in the fifo occupied by the skb. Mapped 1:1 to a desc
  * ring entry but only used for a pkt_desc not a seg_desc
  */
 struct gve_tx_buffer_state {
 	struct sk_buff *skb; /* skb for this pkt */
-	struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */
+	union {
+		struct gve_tx_iovec iov[GVE_TX_MAX_IOVEC]; /* segments of this pkt */
+		struct gve_tx_dma_buf buf;
+	};
 };
 
 /* A TX buffer - each queue has one */
@@ -119,13 +148,16 @@
 	__be32 last_nic_done ____cacheline_aligned; /* NIC tail pointer */
 	u64 pkt_done; /* free-running - total packets completed */
 	u64 bytes_done; /* free-running - total bytes completed */
+	u32 dropped_pkt; /* free-running - total packets dropped */
 
 	/* Cacheline 2 -- Read-mostly fields */
 	union gve_tx_desc *desc ____cacheline_aligned;
 	struct gve_tx_buffer_state *info; /* Maps 1:1 to a desc */
 	struct netdev_queue *netdev_txq;
 	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
+	struct device *dev;
 	u32 mask; /* masks req and done down to queue size */
+	bool raw_addressing; /* use raw_addressing? */
 
 	/* Slow-path fields */
 	u32 q_num ____cacheline_aligned; /* queue idx */
@@ -141,13 +173,13 @@
  * associated with that irq.
  */
 struct gve_notify_block {
-	__be32 irq_db_index; /* idx into Bar2 - set by device, must be 1st */
+	__be32 *irq_db_index; /* pointer to idx into Bar2 */
 	char name[IFNAMSIZ + 16]; /* name registered with the kernel */
 	struct napi_struct napi; /* kernel napi struct for this block */
 	struct gve_priv *priv;
 	struct gve_tx_ring *tx; /* tx rings on this block */
 	struct gve_rx_ring *rx; /* rx rings on this block */
-} ____cacheline_aligned;
+};
 
 /* Tracks allowed and current queue settings */
 struct gve_queue_config {
@@ -161,13 +193,18 @@
 	unsigned long *qpl_id_map; /* bitmap of used qpl ids */
 };
 
+struct gve_irq_db {
+	__be32 index;
+} ____cacheline_aligned;
+
 struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
 	struct gve_rx_ring *rx; /* array of rx_cfg.num_queues */
 	struct gve_queue_page_list *qpls; /* array of num qpls */
 	struct gve_notify_block *ntfy_blocks; /* array of num_ntfy_blks */
-	dma_addr_t ntfy_block_bus;
+	struct gve_irq_db *irq_db_indices; /* array of num_ntfy_blks */
+	dma_addr_t irq_db_indices_bus;
 	struct msix_entry *msix_vectors; /* array of num_ntfy_blks + 1 */
 	char mgmt_msix_name[IFNAMSIZ + 16];
 	u32 mgmt_msix_idx;
@@ -178,11 +215,12 @@
 	u16 tx_desc_cnt; /* num desc per ring */
 	u16 rx_desc_cnt; /* num desc per ring */
 	u16 tx_pages_per_qpl; /* tx buffer length */
-	u16 rx_pages_per_qpl; /* rx buffer length */
+	u16 rx_data_slot_cnt; /* rx buffer length */
 	u64 max_registered_pages;
 	u64 num_registered_pages; /* num pages registered with NIC */
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
+	bool raw_addressing; /* true if this dev supports raw addressing */
 
 	struct gve_queue_config tx_cfg;
 	struct gve_queue_config rx_cfg;
@@ -202,24 +240,63 @@
 	dma_addr_t adminq_bus_addr;
 	u32 adminq_mask; /* masks prod_cnt to adminq size */
 	u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */
+	u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */
+	u32 adminq_timeouts; /* free-running count of AQ cmds timeouts */
+	/* free-running count of per AQ cmd executed */
+	u32 adminq_describe_device_cnt;
+	u32 adminq_cfg_device_resources_cnt;
+	u32 adminq_register_page_list_cnt;
+	u32 adminq_unregister_page_list_cnt;
+	u32 adminq_create_tx_queue_cnt;
+	u32 adminq_create_rx_queue_cnt;
+	u32 adminq_destroy_tx_queue_cnt;
+	u32 adminq_destroy_rx_queue_cnt;
+	u32 adminq_dcfg_device_resources_cnt;
+	u32 adminq_set_driver_parameter_cnt;
+	u32 adminq_report_stats_cnt;
 
+	/* Global stats */
+	u32 interface_up_cnt; /* count of times interface turned up */
+	u32 interface_down_cnt; /* count of times interface turned down */
+	u32 reset_cnt; /* count of reset */
+	u32 page_alloc_fail; /* count of page alloc fails */
+	u32 dma_mapping_error; /* count of dma mapping errors */
 	struct workqueue_struct *gve_wq;
 	struct work_struct service_task;
 	unsigned long service_task_flags;
 	unsigned long state_flags;
+
+	struct gve_stats_report *stats_report;
+	u64 stats_report_len;
+	dma_addr_t stats_report_bus; /* dma address for the stats report */
+	unsigned long ethtool_flags;
+
+	unsigned long service_timer_period;
+	struct timer_list service_timer;
+
+	/* Gvnic device link speed from hypervisor. */
+	u64 link_speed;
+
+	/* Gvnic device's dma mask, set during probe. */
+	u8 dma_mask;
 };
 
-enum gve_service_task_flags {
-	GVE_PRIV_FLAGS_DO_RESET			= BIT(1),
-	GVE_PRIV_FLAGS_RESET_IN_PROGRESS	= BIT(2),
-	GVE_PRIV_FLAGS_PROBE_IN_PROGRESS	= BIT(3),
+enum gve_service_task_flags_bit {
+	GVE_PRIV_FLAGS_DO_RESET			= 1,
+	GVE_PRIV_FLAGS_RESET_IN_PROGRESS	= 2,
+	GVE_PRIV_FLAGS_PROBE_IN_PROGRESS	= 3,
+	GVE_PRIV_FLAGS_DO_REPORT_STATS = 4,
 };
 
-enum gve_state_flags {
-	GVE_PRIV_FLAGS_ADMIN_QUEUE_OK		= BIT(1),
-	GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK	= BIT(2),
-	GVE_PRIV_FLAGS_DEVICE_RINGS_OK		= BIT(3),
-	GVE_PRIV_FLAGS_NAPI_ENABLED		= BIT(4),
+enum gve_state_flags_bit {
+	GVE_PRIV_FLAGS_ADMIN_QUEUE_OK		= 1,
+	GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK	= 2,
+	GVE_PRIV_FLAGS_DEVICE_RINGS_OK		= 3,
+	GVE_PRIV_FLAGS_NAPI_ENABLED		= 4,
+};
+
+enum gve_ethtool_flags_bit {
+	GVE_PRIV_FLAGS_REPORT_STATS		= 0,
 };
 
 static inline bool gve_get_do_reset(struct gve_priv *priv)
@@ -269,6 +346,22 @@
 	clear_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS, &priv->service_task_flags);
 }
 
+static inline bool gve_get_do_report_stats(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS,
+			&priv->service_task_flags);
+}
+
+static inline void gve_set_do_report_stats(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags);
+}
+
+static inline void gve_clear_do_report_stats(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags);
+}
+
 static inline bool gve_get_admin_queue_ok(struct gve_priv *priv)
 {
 	return test_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags);
@@ -329,12 +422,27 @@
 	clear_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags);
 }
 
+static inline bool gve_get_report_stats(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags);
+}
+
+static inline void gve_set_report_stats(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags);
+}
+
+static inline void gve_clear_report_stats(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags);
+}
+
 /* Returns the address of the ntfy_blocks irq doorbell
  */
 static inline __be32 __iomem *gve_irq_doorbell(struct gve_priv *priv,
 					       struct gve_notify_block *block)
 {
-	return &priv->db_bar2[be32_to_cpu(block->irq_db_index)];
+	return &priv->db_bar2[be32_to_cpu(*block->irq_db_index)];
 }
 
 /* Returns the index into ntfy_blocks of the given tx ring's block
@@ -355,14 +463,22 @@
  */
 static inline u32 gve_num_tx_qpls(struct gve_priv *priv)
 {
-	return priv->tx_cfg.num_queues;
+	if (priv->raw_addressing) {
+		return 0;
+	} else {
+		return priv->tx_cfg.num_queues;
+	}
 }
 
 /* Returns the number of rx queue page lists
  */
 static inline u32 gve_num_rx_qpls(struct gve_priv *priv)
 {
-	return priv->rx_cfg.num_queues;
+	if (priv->raw_addressing) {
+		return 0;
+	} else {
+		return priv->rx_cfg.num_queues;
+	}
 }
 
 /* Returns a pointer to the next available tx qpl in the list of qpls
@@ -416,18 +532,10 @@
 		return DMA_FROM_DEVICE;
 }
 
-/* Returns true if the max mtu allows page recycling */
-static inline bool gve_can_recycle_pages(struct net_device *dev)
-{
-	/* We can't recycle the pages if we can't fit a packet into half a
-	 * page.
-	 */
-	return dev->max_mtu <= PAGE_SIZE / 2;
-}
-
 /* buffers */
-int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma,
-		   enum dma_data_direction);
+int gve_alloc_page(struct gve_priv* priv, struct device *dev,
+								struct page **page, dma_addr_t *dma,
+								enum dma_data_direction, gfp_t gfp_flags);
 void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
 		   enum dma_data_direction);
 /* tx handling */
@@ -450,6 +558,8 @@
 int gve_adjust_queues(struct gve_priv *priv,
 		      struct gve_queue_config new_rx_config,
 		      struct gve_queue_config new_tx_config);
+/* report stats handling */
+void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
 extern const struct ethtool_ops gve_ethtool_ops;
 /* needed by ethtool */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index c3ba7ba..b02336b 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -23,6 +23,19 @@
 
 	priv->adminq_mask = (PAGE_SIZE / sizeof(union gve_adminq_command)) - 1;
 	priv->adminq_prod_cnt = 0;
+	priv->adminq_cmd_fail = 0;
+	priv->adminq_timeouts = 0;
+	priv->adminq_describe_device_cnt = 0;
+	priv->adminq_cfg_device_resources_cnt = 0;
+	priv->adminq_register_page_list_cnt = 0;
+	priv->adminq_unregister_page_list_cnt = 0;
+	priv->adminq_create_tx_queue_cnt = 0;
+	priv->adminq_create_rx_queue_cnt = 0;
+	priv->adminq_destroy_tx_queue_cnt = 0;
+	priv->adminq_destroy_rx_queue_cnt = 0;
+	priv->adminq_dcfg_device_resources_cnt = 0;
+	priv->adminq_set_driver_parameter_cnt = 0;
+	priv->adminq_report_stats_cnt = 0;
 
 	/* Setup Admin queue with the device */
 	iowrite32be(priv->adminq_bus_addr / PAGE_SIZE,
@@ -81,17 +94,18 @@
 	return false;
 }
 
-static int gve_adminq_parse_err(struct device *dev, u32 status)
+static int gve_adminq_parse_err(struct gve_priv *priv, u32 status)
 {
 	if (status != GVE_ADMINQ_COMMAND_PASSED &&
-	    status != GVE_ADMINQ_COMMAND_UNSET)
-		dev_err(dev, "AQ command failed with status %d\n", status);
-
+	    status != GVE_ADMINQ_COMMAND_UNSET) {
+		dev_err(&priv->pdev->dev, "AQ command failed with status %d\n", status);
+		priv->adminq_cmd_fail++;
+	}
 	switch (status) {
 	case GVE_ADMINQ_COMMAND_PASSED:
 		return 0;
 	case GVE_ADMINQ_COMMAND_UNSET:
-		dev_err(dev, "parse_aq_err: err and status both unset, this should not be possible.\n");
+		dev_err(&priv->pdev->dev, "parse_aq_err: err and status both unset, this should not be possible.\n");
 		return -EINVAL;
 	case GVE_ADMINQ_COMMAND_ERROR_ABORTED:
 	case GVE_ADMINQ_COMMAND_ERROR_CANCELLED:
@@ -116,36 +130,143 @@
 	case GVE_ADMINQ_COMMAND_ERROR_UNIMPLEMENTED:
 		return -ENOTSUPP;
 	default:
-		dev_err(dev, "parse_aq_err: unknown status code %d\n", status);
+		dev_err(&priv->pdev->dev, "parse_aq_err: unknown status code %d\n", status);
 		return -EINVAL;
 	}
 }
 
+/* Flushes all AQ commands currently queued and waits for them to complete.
+ * If there are failures, it will return the first error.
+ */
+static int gve_adminq_kick_and_wait(struct gve_priv *priv)
+{
+	u32 tail, head;
+	int i;
+
+	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
+	head = priv->adminq_prod_cnt;
+
+	gve_adminq_kick_cmd(priv, head);
+	if (!gve_adminq_wait_for_cmd(priv, head)) {
+		dev_err(&priv->pdev->dev, "AQ commands timed out, need to reset AQ\n");
+		priv->adminq_timeouts++;
+		return -ENOTRECOVERABLE;
+	}
+
+	for (i = tail; i < head; i++) {
+		union gve_adminq_command *cmd;
+		u32 status, err;
+
+		cmd = &priv->adminq[i & priv->adminq_mask];
+		status = be32_to_cpu(READ_ONCE(cmd->status));
+		err = gve_adminq_parse_err(priv, status);
+		if (err)
+			// Return the first error if we failed.
+			return err;
+	}
+
+	return 0;
+}
+
 /* This function is not threadsafe - the caller is responsible for any
  * necessary locks.
  */
-int gve_adminq_execute_cmd(struct gve_priv *priv,
-			   union gve_adminq_command *cmd_orig)
+static int gve_adminq_issue_cmd(struct gve_priv *priv,
+				union gve_adminq_command *cmd_orig)
 {
 	union gve_adminq_command *cmd;
-	u32 status = 0;
-	u32 prod_cnt;
+	u32 tail;
+	u32 opcode;
+
+	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
+
+	// Check if next command will overflow the buffer.
+	if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) {
+		int err;
+
+		// Flush existing commands to make room.
+		err = gve_adminq_kick_and_wait(priv);
+		if (err)
+			return err;
+
+		// Retry.
+		tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
+		if (((priv->adminq_prod_cnt + 1) & priv->adminq_mask) == tail) {
+			// This should never happen. We just flushed the
+			// command queue so there should be enough space.
+			return -ENOMEM;
+		}
+	}
 
 	cmd = &priv->adminq[priv->adminq_prod_cnt & priv->adminq_mask];
 	priv->adminq_prod_cnt++;
-	prod_cnt = priv->adminq_prod_cnt;
 
 	memcpy(cmd, cmd_orig, sizeof(*cmd_orig));
+	opcode = be32_to_cpu(READ_ONCE(cmd->opcode));
 
-	gve_adminq_kick_cmd(priv, prod_cnt);
-	if (!gve_adminq_wait_for_cmd(priv, prod_cnt)) {
-		dev_err(&priv->pdev->dev, "AQ command timed out, need to reset AQ\n");
-		return -ENOTRECOVERABLE;
+	switch(opcode) {
+	case GVE_ADMINQ_DESCRIBE_DEVICE:
+		priv->adminq_describe_device_cnt++;
+		break;
+	case GVE_ADMINQ_CONFIGURE_DEVICE_RESOURCES:
+		priv->adminq_cfg_device_resources_cnt++;
+		break;
+	case GVE_ADMINQ_REGISTER_PAGE_LIST:
+		priv->adminq_register_page_list_cnt++;
+		break;
+	case GVE_ADMINQ_UNREGISTER_PAGE_LIST:
+		priv->adminq_unregister_page_list_cnt++;
+		break;
+	case GVE_ADMINQ_CREATE_TX_QUEUE:
+		priv->adminq_create_tx_queue_cnt++;
+		break;
+	case GVE_ADMINQ_CREATE_RX_QUEUE:
+		priv->adminq_create_rx_queue_cnt++;
+		break;
+	case GVE_ADMINQ_DESTROY_TX_QUEUE:
+		priv->adminq_destroy_tx_queue_cnt++;
+		break;
+	case GVE_ADMINQ_DESTROY_RX_QUEUE:
+		priv->adminq_destroy_rx_queue_cnt++;
+		break;
+	case GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES:
+		priv->adminq_dcfg_device_resources_cnt++;
+		break;
+	case GVE_ADMINQ_SET_DRIVER_PARAMETER:
+		priv->adminq_set_driver_parameter_cnt++;
+		break;
+	case GVE_ADMINQ_REPORT_STATS:
+		priv->adminq_report_stats_cnt++;
+		break;
+	default:
+		dev_err(&priv->pdev->dev, "unknown AQ command opcode %d\n", opcode);
 	}
 
-	memcpy(cmd_orig, cmd, sizeof(*cmd));
-	status = be32_to_cpu(READ_ONCE(cmd->status));
-	return gve_adminq_parse_err(&priv->pdev->dev, status);
+	return 0;
+}
+
+/* This function is not threadsafe - the caller is responsible for any
+ * necessary locks.
+ * The caller is also responsible for making sure there are no commands
+ * waiting to be executed.
+ */
+static int gve_adminq_execute_cmd(struct gve_priv *priv,
+			   union gve_adminq_command *cmd_orig)
+{
+	u32 tail, head;
+	int err;
+
+	tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
+	head = priv->adminq_prod_cnt;
+	if (tail != head)
+		// This is not a valid path
+		return -EINVAL;
+
+	err = gve_adminq_issue_cmd(priv, cmd_orig);
+	if (err)
+		return err;
+
+	return gve_adminq_kick_and_wait(priv);
 }
 
 /* The device specifies that the management vector can either be the first irq
@@ -172,7 +293,7 @@
 		.num_counters = cpu_to_be32(num_counters),
 		.irq_db_addr = cpu_to_be64(db_array_bus_addr),
 		.num_irq_dbs = cpu_to_be32(num_ntfy_blks),
-		.irq_db_stride = cpu_to_be32(sizeof(priv->ntfy_blocks[0])),
+		.irq_db_stride = cpu_to_be32(sizeof(*priv->irq_db_indices)),
 		.ntfy_blk_msix_base_idx =
 					cpu_to_be32(GVE_NTFY_BLK_BASE_MSIX_IDX),
 	};
@@ -190,80 +311,120 @@
 	return gve_adminq_execute_cmd(priv, &cmd);
 }
 
-int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_index)
+int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues)
 {
-	struct gve_tx_ring *tx = &priv->tx[queue_index];
 	union gve_adminq_command cmd;
+	struct gve_tx_ring *tx;
+	u32 qpl_id;
+	int err;
+	int i;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE);
-	cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) {
-		.queue_id = cpu_to_be32(queue_index),
-		.reserved = 0,
-		.queue_resources_addr = cpu_to_be64(tx->q_resources_bus),
-		.tx_ring_addr = cpu_to_be64(tx->bus),
-		.queue_page_list_id = cpu_to_be32(tx->tx_fifo.qpl->id),
-		.ntfy_id = cpu_to_be32(tx->ntfy_id),
-	};
+	for (i = 0; i < num_queues; i++) {
+		tx = &priv->tx[i];
+		qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID :
+			 tx->tx_fifo.qpl->id;
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_TX_QUEUE);
+		cmd.create_tx_queue = (struct gve_adminq_create_tx_queue) {
+			.queue_id = cpu_to_be32(i),
+			.reserved = 0,
+			.queue_resources_addr =
+				cpu_to_be64(tx->q_resources_bus),
+			.tx_ring_addr = cpu_to_be64(tx->bus),
+			.queue_page_list_id = cpu_to_be32(qpl_id),
+			.ntfy_id = cpu_to_be32(tx->ntfy_id),
+		};
+		err = gve_adminq_issue_cmd(priv, &cmd);
+		if (err)
+			return err;
+	}
 
-	return gve_adminq_execute_cmd(priv, &cmd);
+	return gve_adminq_kick_and_wait(priv);
 }
 
-int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_index)
+int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues)
 {
-	struct gve_rx_ring *rx = &priv->rx[queue_index];
 	union gve_adminq_command cmd;
+	struct gve_rx_ring *rx;
+	u32 qpl_id;
+	int err;
+	int i;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
-	cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) {
-		.queue_id = cpu_to_be32(queue_index),
-		.index = cpu_to_be32(queue_index),
-		.reserved = 0,
-		.ntfy_id = cpu_to_be32(rx->ntfy_id),
-		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
-		.rx_desc_ring_addr = cpu_to_be64(rx->desc.bus),
-		.rx_data_ring_addr = cpu_to_be64(rx->data.data_bus),
-		.queue_page_list_id = cpu_to_be32(rx->data.qpl->id),
-	};
+	for (i = 0; i < num_queues; i++) {
+		rx = &priv->rx[i];
+		qpl_id = priv->raw_addressing ? GVE_RAW_ADDRESSING_QPL_ID :
+			 rx->data.qpl->id;
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.opcode = cpu_to_be32(GVE_ADMINQ_CREATE_RX_QUEUE);
+		cmd.create_rx_queue = (struct gve_adminq_create_rx_queue) {
+			.queue_id = cpu_to_be32(i),
+			.index = cpu_to_be32(i),
+			.reserved = 0,
+			.ntfy_id = cpu_to_be32(rx->ntfy_id),
+			.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
+			.rx_desc_ring_addr = cpu_to_be64(rx->desc.bus),
+			.rx_data_ring_addr = cpu_to_be64(rx->data.data_bus),
+			.queue_page_list_id = cpu_to_be32(qpl_id),
+		};
+		err = gve_adminq_issue_cmd(priv, &cmd);
+		if (err)
+			return err;
+	}
 
-	return gve_adminq_execute_cmd(priv, &cmd);
+	return gve_adminq_kick_and_wait(priv);
 }
 
-int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_index)
+int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 num_queues)
 {
 	union gve_adminq_command cmd;
+	int err;
+	int i;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_TX_QUEUE);
-	cmd.destroy_tx_queue = (struct gve_adminq_destroy_tx_queue) {
-		.queue_id = cpu_to_be32(queue_index),
-	};
+	for (i = 0; i < num_queues; i++) {
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_TX_QUEUE);
+		cmd.destroy_tx_queue = (struct gve_adminq_destroy_tx_queue) {
+			.queue_id = cpu_to_be32(i),
+		};
+		err = gve_adminq_issue_cmd(priv, &cmd);
+		if (err)
+			return err;
+	}
 
-	return gve_adminq_execute_cmd(priv, &cmd);
+	return gve_adminq_kick_and_wait(priv);
 }
 
-int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_index)
+int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 num_queues)
 {
 	union gve_adminq_command cmd;
+	int err;
+	int i;
 
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
-	cmd.destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
-		.queue_id = cpu_to_be32(queue_index),
-	};
+	for (i = 0; i < num_queues; i++) {
+		memset(&cmd, 0, sizeof(cmd));
+		cmd.opcode = cpu_to_be32(GVE_ADMINQ_DESTROY_RX_QUEUE);
+		cmd.destroy_rx_queue = (struct gve_adminq_destroy_rx_queue) {
+			.queue_id = cpu_to_be32(i),
+		};
+		err = gve_adminq_issue_cmd(priv, &cmd);
+		if (err)
+			return err;
+	}
 
-	return gve_adminq_execute_cmd(priv, &cmd);
+	return gve_adminq_kick_and_wait(priv);
 }
 
 int gve_adminq_describe_device(struct gve_priv *priv)
 {
 	struct gve_device_descriptor *descriptor;
+	struct gve_device_option *dev_opt;
 	union gve_adminq_command cmd;
 	dma_addr_t descriptor_bus;
+	u16 num_options;
 	int err = 0;
 	u8 *mac;
 	u16 mtu;
+	int i;
 
 	memset(&cmd, 0, sizeof(cmd));
 	descriptor = dma_alloc_coherent(&priv->pdev->dev, PAGE_SIZE,
@@ -283,8 +444,8 @@
 
 	priv->tx_desc_cnt = be16_to_cpu(descriptor->tx_queue_entries);
 	if (priv->tx_desc_cnt * sizeof(priv->tx->desc[0]) < PAGE_SIZE) {
-		netif_err(priv, drv, priv->dev, "Tx desc count %d too low\n",
-			  priv->tx_desc_cnt);
+		dev_err(&priv->pdev->dev, "Tx desc count %d too low\n",
+						priv->tx_desc_cnt);
 		err = -EINVAL;
 		goto free_device_descriptor;
 	}
@@ -293,7 +454,7 @@
 	    < PAGE_SIZE ||
 	    priv->rx_desc_cnt * sizeof(priv->rx->data.data_ring[0])
 	    < PAGE_SIZE) {
-		netif_err(priv, drv, priv->dev, "Rx desc count %d too low\n",
+		dev_err(&priv->pdev->dev, "Rx desc count %d too low\n",
 			  priv->rx_desc_cnt);
 		err = -EINVAL;
 		goto free_device_descriptor;
@@ -302,7 +463,7 @@
 				be64_to_cpu(descriptor->max_registered_pages);
 	mtu = be16_to_cpu(descriptor->mtu);
 	if (mtu < ETH_MIN_MTU) {
-		netif_err(priv, drv, priv->dev, "MTU %d below minimum MTU\n",
+		dev_err(&priv->pdev->dev, "MTU %d below minimum MTU\n",
 			  mtu);
 		err = -EINVAL;
 		goto free_device_descriptor;
@@ -311,18 +472,64 @@
 	priv->num_event_counters = be16_to_cpu(descriptor->counters);
 	ether_addr_copy(priv->dev->dev_addr, descriptor->mac);
 	mac = descriptor->mac;
-	netif_info(priv, drv, priv->dev, "MAC addr: %pM\n", mac);
+	dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac);
 	priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl);
-	priv->rx_pages_per_qpl = be16_to_cpu(descriptor->rx_pages_per_qpl);
-	if (priv->rx_pages_per_qpl < priv->rx_desc_cnt) {
-		netif_err(priv, drv, priv->dev, "rx_pages_per_qpl cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n",
-			  priv->rx_pages_per_qpl);
-		priv->rx_desc_cnt = priv->rx_pages_per_qpl;
+	priv->rx_data_slot_cnt = be16_to_cpu(descriptor->rx_pages_per_qpl);
+	if (priv->rx_data_slot_cnt < priv->rx_desc_cnt) {
+		dev_err(&priv->pdev->dev, "rx_data_slot_cnt cannot be smaller than rx_desc_cnt, setting rx_desc_cnt down to %d.\n",
+			  priv->rx_data_slot_cnt);
+		priv->rx_desc_cnt = priv->rx_data_slot_cnt;
 	}
 	priv->default_num_queues = be16_to_cpu(descriptor->default_num_queues);
+	dev_opt = (struct gve_device_option *)((void *)descriptor +
+							sizeof(*descriptor));
+
+	num_options = be16_to_cpu(descriptor->num_device_options);
+	for (i = 0; i < num_options; i++) {
+		u16 option_id;
+		u16 option_length;
+
+		if ((void *)dev_opt + sizeof(*dev_opt)  > (void *)descriptor +
+				      be16_to_cpu(descriptor->total_length)) {
+			dev_err(&priv->dev->dev,
+				  "num_options in device_descriptor does not match total length.\n");
+			err = -EINVAL;
+			goto free_device_descriptor;
+		}
+
+		option_id = be16_to_cpu(dev_opt->option_id);
+		option_length = be16_to_cpu(dev_opt->option_length);
+		switch(option_id) {
+		case GVE_DEV_OPT_ID_RAW_ADDRESSING:
+			/* If the length or feature mask doesn't match,
+			 * continue without enabling the feature.
+			 */
+			if (option_length != GVE_DEV_OPT_LEN_RAW_ADDRESSING ||
+			    be32_to_cpu(dev_opt->feat_mask) !=
+			    GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING) {
+				dev_info(&priv->pdev->dev,
+					   "Raw addressing device option not enabled, length or features mask did not match expected.\n");
+				priv->raw_addressing = false;
+			} else {
+				dev_info(&priv->pdev->dev,
+					   "Raw addressing device option enabled.\n");
+				priv->raw_addressing = true;
+			}
+			break;
+		default:
+			/* If we don't recognize the option just continue
+			 * without doing anything.
+			 */
+			dev_info(&priv->pdev->dev,
+				   "Unrecognized device option 0x%hx not enabled.\n",
+				   option_id);
+			break;
+		}
+		dev_opt = (void *)dev_opt + sizeof(*dev_opt) + option_length;
+	}
 
 free_device_descriptor:
-	dma_free_coherent(&priv->pdev->dev, sizeof(*descriptor), descriptor,
+	dma_free_coherent(&priv->pdev->dev, PAGE_SIZE, descriptor,
 			  descriptor_bus);
 	return err;
 }
@@ -385,3 +592,45 @@
 
 	return gve_adminq_execute_cmd(priv, &cmd);
 }
+
+int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
+			    dma_addr_t stats_report_addr, u64 interval)
+{
+	union gve_adminq_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_STATS);
+	cmd.report_stats = (struct gve_adminq_report_stats) {
+		.stats_report_len = cpu_to_be64(stats_report_len),
+		.stats_report_addr = cpu_to_be64(stats_report_addr),
+		.interval = cpu_to_be64(interval),
+	};
+
+	return gve_adminq_execute_cmd(priv, &cmd);
+}
+
+int gve_adminq_report_link_speed(struct gve_priv *priv)
+{
+	union gve_adminq_command gvnic_cmd;
+	dma_addr_t link_speed_region_bus;
+	u64* link_speed_region;
+	int err;
+
+	link_speed_region = dma_alloc_coherent(&priv->pdev->dev,
+		sizeof(*link_speed_region), &link_speed_region_bus, GFP_KERNEL);
+
+	if (!link_speed_region)
+		return -ENOMEM;
+
+	memset(&gvnic_cmd, 0, sizeof(gvnic_cmd));
+	gvnic_cmd.opcode = cpu_to_be32(GVE_ADMINQ_REPORT_LINK_SPEED);
+	gvnic_cmd.report_link_speed.link_speed_address =
+		cpu_to_be64(link_speed_region_bus);
+
+	err = gve_adminq_execute_cmd(priv, &gvnic_cmd);
+
+	priv->link_speed = be64_to_cpu(*link_speed_region);
+	dma_free_coherent(&priv->pdev->dev, sizeof(*link_speed_region),
+					  link_speed_region, link_speed_region_bus);
+	return err;
+}
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.h b/drivers/net/ethernet/google/gve/gve_adminq.h
index 4dfa06e..c2fc677 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.h
+++ b/drivers/net/ethernet/google/gve/gve_adminq.h
@@ -21,6 +21,8 @@
 	GVE_ADMINQ_DESTROY_RX_QUEUE		= 0x8,
 	GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES	= 0x9,
 	GVE_ADMINQ_SET_DRIVER_PARAMETER		= 0xB,
+	GVE_ADMINQ_REPORT_STATS			= 0xC,
+	GVE_ADMINQ_REPORT_LINK_SPEED	= 0xD
 };
 
 /* Admin queue status codes */
@@ -77,12 +79,17 @@
 
 static_assert(sizeof(struct gve_device_descriptor) == 40);
 
-struct device_option {
-	__be32 option_id;
-	__be32 option_length;
+struct gve_device_option {
+	__be16 option_id;
+	__be16 option_length;
+	__be32 feat_mask;
 };
 
-static_assert(sizeof(struct device_option) == 8);
+static_assert(sizeof(struct gve_device_option) == 8);
+
+#define GVE_DEV_OPT_ID_RAW_ADDRESSING 0x1
+#define GVE_DEV_OPT_LEN_RAW_ADDRESSING 0x0
+#define GVE_DEV_OPT_FEAT_MASK_RAW_ADDRESSING 0x0
 
 struct gve_adminq_configure_device_resources {
 	__be64 counter_array;
@@ -109,6 +116,8 @@
 
 static_assert(sizeof(struct gve_adminq_unregister_page_list) == 4);
 
+#define GVE_RAW_ADDRESSING_QPL_ID 0xFFFFFFFF
+
 struct gve_adminq_create_tx_queue {
 	__be32 queue_id;
 	__be32 reserved;
@@ -172,6 +181,51 @@
 
 static_assert(sizeof(struct gve_adminq_set_driver_parameter) == 16);
 
+struct gve_adminq_report_stats {
+	__be64 stats_report_len;
+	__be64 stats_report_addr;
+	__be64 interval;
+};
+
+static_assert(sizeof(struct gve_adminq_report_stats) == 24);
+
+struct gve_adminq_report_link_speed {
+  __be64 link_speed_address;
+};
+
+static_assert(sizeof(struct gve_adminq_report_link_speed) == 8);
+
+struct stats {
+	__be32 stat_name;
+	__be32 queue_id;
+	__be64 value;
+};
+
+static_assert(sizeof(struct stats) == 16);
+
+struct gve_stats_report {
+	__be64 written_count;
+	struct stats stats[0];
+};
+
+static_assert(sizeof(struct gve_stats_report) == 8);
+
+enum gve_stat_names {
+	// stats from gve
+	TX_WAKE_CNT			= 1,
+	TX_STOP_CNT			= 2,
+	TX_FRAMES_SENT			= 3,
+	TX_BYTES_SENT			= 4,
+	TX_LAST_COMPLETION_PROCESSED	= 5,
+	RX_NEXT_EXPECTED_SEQUENCE	= 6,
+	RX_BUFFERS_POSTED		= 7,
+	// stats from NIC
+	RX_QUEUE_DROP_CNT		= 65,
+	RX_NO_BUFFERS_POSTED		= 66,
+	RX_DROPS_PACKET_OVER_MRU	= 67,
+	RX_DROPS_INVALID_CHECKSUM	= 68,
+};
+
 union gve_adminq_command {
 	struct {
 		__be32 opcode;
@@ -187,6 +241,8 @@
 			struct gve_adminq_register_page_list reg_page_list;
 			struct gve_adminq_unregister_page_list unreg_page_list;
 			struct gve_adminq_set_driver_parameter set_driver_param;
+			struct gve_adminq_report_stats report_stats;
+			struct gve_adminq_report_link_speed report_link_speed;
 		};
 	};
 	u8 reserved[64];
@@ -197,8 +253,6 @@
 int gve_adminq_alloc(struct device *dev, struct gve_priv *priv);
 void gve_adminq_free(struct device *dev, struct gve_priv *priv);
 void gve_adminq_release(struct gve_priv *priv);
-int gve_adminq_execute_cmd(struct gve_priv *priv,
-			   union gve_adminq_command *cmd_orig);
 int gve_adminq_describe_device(struct gve_priv *priv);
 int gve_adminq_configure_device_resources(struct gve_priv *priv,
 					  dma_addr_t counter_array_bus_addr,
@@ -206,12 +260,15 @@
 					  dma_addr_t db_array_bus_addr,
 					  u32 num_ntfy_blks);
 int gve_adminq_deconfigure_device_resources(struct gve_priv *priv);
-int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues);
+int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues);
+int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id);
 int gve_adminq_register_page_list(struct gve_priv *priv,
 				  struct gve_queue_page_list *qpl);
 int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id);
 int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu);
+int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
+			    dma_addr_t stats_report_addr, u64 interval);
+int gve_adminq_report_link_speed(struct gve_priv *priv);
 #endif /* _GVE_ADMINQ_H */
diff --git a/drivers/net/ethernet/google/gve/gve_desc.h b/drivers/net/ethernet/google/gve/gve_desc.h
index 54779871..a7da364 100644
--- a/drivers/net/ethernet/google/gve/gve_desc.h
+++ b/drivers/net/ethernet/google/gve/gve_desc.h
@@ -16,9 +16,11 @@
  * Base addresses encoded in seg_addr are not assumed to be physical
  * addresses. The ring format assumes these come from some linear address
  * space. This could be physical memory, kernel virtual memory, user virtual
- * memory. gVNIC uses lists of registered pages. Each queue is assumed
- * to be associated with a single such linear address space to ensure a
- * consistent meaning for seg_addrs posted to its rings.
+ * memory.
+ * If raw dma addressing is not supported then gVNIC uses lists of registered
+ * pages. Each queue is assumed to be associated with a single such linear
+ * address space to ensure a consistent meaning for seg_addrs posted to its
+ * rings.
  */
 
 struct gve_tx_pkt_desc {
@@ -72,12 +74,14 @@
 } __packed;
 static_assert(sizeof(struct gve_rx_desc) == 64);
 
-/* As with the Tx ring format, the qpl_offset entries below are offsets into an
- * ordered list of registered pages.
+/* If the device supports raw dma addressing then the addr in data slot is
+ * the dma address of the buffer.
+ * If the device only supports registered segments than the addr is a byte
+ * offset into the registered segment (an ordered list of pages) where the
+ * buffer is.
  */
 struct gve_rx_data_slot {
-	/* byte offset into the rx registered segment of this slot */
-	__be64 qpl_offset;
+	__be64 addr;
 };
 
 /* GVE Recive Packet Descriptor Seq No */
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index d8fa816..ae76683 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -6,6 +6,7 @@
 
 #include <linux/rtnetlink.h>
 #include "gve.h"
+#include "gve_adminq.h"
 
 static void gve_get_drvinfo(struct net_device *netdev,
 			    struct ethtool_drvinfo *info)
@@ -32,43 +33,86 @@
 }
 
 static const char gve_gstrings_main_stats[][ETH_GSTRING_LEN] = {
-	"rx_packets", "tx_packets", "rx_bytes", "tx_bytes",
-	"rx_dropped", "tx_dropped", "tx_timeouts",
+	"rx_packets", "rx_total_bytes", "rx_total_dropped_pkt",
+	"rx_skb_alloc_fail", "rx_buf_alloc_fail", "rx_desc_err_dropped_pkt",
+	"tx_packets", "tx_total_bytes", "tx_total_dropped_pkt", "tx_timeouts",
+	"interface_up_cnt", "interface_down_cnt", "reset_cnt",
+	"page_alloc_fail", "dma_mapping_error",
+};
+
+static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
+	"rx_posted_desc[%u]", "rx_completed_desc[%u]", "rx_bytes[%u]",
+	"rx_dropped_pkt[%u]", "rx_copybreak_pkt[%u]", "rx_copied_pkt[%u]",
+	"rx_queue_drop_cnt[%u]", "rx_no_buffers_posted[%u]",
+	"rx_drops_packet_over_mru[%u]", "rx_drops_invalid_checksum[%u]",
+};
+
+static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
+	"tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_bytes[%u]",
+	"tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]",
+};
+
+static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
+	"adminq_prod_cnt", "adminq_cmd_fail", "adminq_timeouts",
+	"adminq_describe_device_cnt", "adminq_cfg_device_resources_cnt",
+	"adminq_register_page_list_cnt", "adminq_unregister_page_list_cnt",
+	"adminq_create_tx_queue_cnt", "adminq_create_rx_queue_cnt",
+	"adminq_destroy_tx_queue_cnt", "adminq_destroy_rx_queue_cnt",
+	"adminq_dcfg_device_resources_cnt", "adminq_set_driver_parameter_cnt",
+	"adminq_report_stats_cnt",
+};
+
+static const char gve_gstrings_priv_flags[][ETH_GSTRING_LEN] = {
+	"report-stats",
 };
 
 #define GVE_MAIN_STATS_LEN  ARRAY_SIZE(gve_gstrings_main_stats)
-#define NUM_GVE_TX_CNTS	5
-#define NUM_GVE_RX_CNTS	2
+#define GVE_ADMINQ_STATS_LEN  ARRAY_SIZE(gve_gstrings_adminq_stats)
+#define NUM_GVE_TX_CNTS	ARRAY_SIZE(gve_gstrings_tx_stats)
+#define NUM_GVE_RX_CNTS	ARRAY_SIZE(gve_gstrings_rx_stats)
+#define GVE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(gve_gstrings_priv_flags)
 
 static void gve_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
 	char *s = (char *)data;
-	int i;
+	int i, j;
 
-	if (stringset != ETH_SS_STATS)
-		return;
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(s, *gve_gstrings_main_stats,
+		       sizeof(gve_gstrings_main_stats));
+		s += sizeof(gve_gstrings_main_stats);
 
-	memcpy(s, *gve_gstrings_main_stats,
-	       sizeof(gve_gstrings_main_stats));
-	s += sizeof(gve_gstrings_main_stats);
-	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
-		snprintf(s, ETH_GSTRING_LEN, "rx_desc_cnt[%u]", i);
-		s += ETH_GSTRING_LEN;
-		snprintf(s, ETH_GSTRING_LEN, "rx_desc_fill_cnt[%u]", i);
-		s += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
-		snprintf(s, ETH_GSTRING_LEN, "tx_req[%u]", i);
-		s += ETH_GSTRING_LEN;
-		snprintf(s, ETH_GSTRING_LEN, "tx_done[%u]", i);
-		s += ETH_GSTRING_LEN;
-		snprintf(s, ETH_GSTRING_LEN, "tx_wake[%u]", i);
-		s += ETH_GSTRING_LEN;
-		snprintf(s, ETH_GSTRING_LEN, "tx_stop[%u]", i);
-		s += ETH_GSTRING_LEN;
-		snprintf(s, ETH_GSTRING_LEN, "tx_event_counter[%u]", i);
-		s += ETH_GSTRING_LEN;
+		for (i = 0; i < priv->rx_cfg.num_queues; i++) {
+			for (j = 0; j < NUM_GVE_RX_CNTS; j++) {
+				snprintf(s, ETH_GSTRING_LEN,
+					 gve_gstrings_rx_stats[j], i);
+				s += ETH_GSTRING_LEN;
+			}
+		}
+
+		for (i = 0; i < priv->tx_cfg.num_queues; i++) {
+			for (j = 0; j < NUM_GVE_TX_CNTS; j++) {
+				snprintf(s, ETH_GSTRING_LEN,
+					 gve_gstrings_tx_stats[j], i);
+				s += ETH_GSTRING_LEN;
+			}
+		}
+
+		memcpy(s, *gve_gstrings_adminq_stats,
+		       sizeof(gve_gstrings_adminq_stats));
+		s += sizeof(gve_gstrings_adminq_stats);
+		break;
+
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(s, *gve_gstrings_priv_flags,
+		       sizeof(gve_gstrings_priv_flags));
+		s += sizeof(gve_gstrings_priv_flags);
+		break;
+
+	default:
+		break;
 	}
 }
 
@@ -78,9 +122,11 @@
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		return GVE_MAIN_STATS_LEN +
+		return GVE_MAIN_STATS_LEN + GVE_ADMINQ_STATS_LEN +
 		       (priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS) +
 		       (priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS);
+	case ETH_SS_PRIV_FLAGS:
+		return GVE_PRIV_FLAGS_STR_LEN;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -90,24 +136,57 @@
 gve_get_ethtool_stats(struct net_device *netdev,
 		      struct ethtool_stats *stats, u64 *data)
 {
+	u64 tmp_rx_pkts, tmp_rx_bytes, tmp_rx_skb_alloc_fail,
+		tmp_rx_buf_alloc_fail, tmp_rx_desc_err_dropped_pkt,
+		tmp_tx_pkts, tmp_tx_bytes;
+	u64 rx_pkts, rx_bytes, rx_skb_alloc_fail, rx_buf_alloc_fail,
+			rx_desc_err_dropped_pkt, tx_pkts,
+			tx_bytes;
 	struct gve_priv *priv = netdev_priv(netdev);
-	u64 rx_pkts, rx_bytes, tx_pkts, tx_bytes;
+	int *rx_qid_to_stats_idx;
+	int *tx_qid_to_stats_idx;
+	struct stats *report_stats = priv->stats_report->stats;
+	int stats_idx, base_stats_idx, max_stats_idx;
+	bool skip_nic_stats;
 	unsigned int start;
 	int ring;
-	int i;
+	int i, j;
 
 	ASSERT_RTNL();
 
-	for (rx_pkts = 0, rx_bytes = 0, ring = 0;
+	rx_qid_to_stats_idx = kmalloc_array(priv->rx_cfg.num_queues,
+					    sizeof(int), GFP_KERNEL);
+	if (!rx_qid_to_stats_idx) {
+		return;
+	}
+	tx_qid_to_stats_idx = kmalloc_array(priv->tx_cfg.num_queues,
+					    sizeof(int), GFP_KERNEL);
+	if (!tx_qid_to_stats_idx) {
+		kfree(rx_qid_to_stats_idx);
+		return;
+	}
+
+	for (rx_pkts = 0, rx_bytes = 0, rx_skb_alloc_fail = 0,
+	     rx_buf_alloc_fail = 0, rx_desc_err_dropped_pkt = 0, ring = 0;
 	     ring < priv->rx_cfg.num_queues; ring++) {
 		if (priv->rx) {
 			do {
+				struct gve_rx_ring *rx = &priv->rx[ring];
 				start =
 				  u64_stats_fetch_begin(&priv->rx[ring].statss);
-				rx_pkts += priv->rx[ring].rpackets;
-				rx_bytes += priv->rx[ring].rbytes;
+				tmp_rx_pkts = rx->rpackets;
+				tmp_rx_bytes = rx->rbytes;
+				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
+				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
+				tmp_rx_desc_err_dropped_pkt =
+					rx->rx_desc_err_dropped_pkt;
 			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
 						       start));
+			rx_pkts += tmp_rx_pkts;
+			rx_bytes += tmp_rx_bytes;
+			rx_skb_alloc_fail += tmp_rx_skb_alloc_fail;
+			rx_buf_alloc_fail += tmp_rx_buf_alloc_fail;
+			rx_desc_err_dropped_pkt += tmp_rx_desc_err_dropped_pkt;
 		}
 	}
 	for (tx_pkts = 0, tx_bytes = 0, ring = 0;
@@ -116,34 +195,111 @@
 			do {
 				start =
 				  u64_stats_fetch_begin(&priv->tx[ring].statss);
-				tx_pkts += priv->tx[ring].pkt_done;
-				tx_bytes += priv->tx[ring].bytes_done;
+				tmp_tx_pkts = priv->tx[ring].pkt_done;
+				tmp_tx_bytes = priv->tx[ring].bytes_done;
 			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
 						       start));
+			tx_pkts += tmp_tx_pkts;
+			tx_bytes += tmp_tx_bytes;
 		}
 	}
 
 	i = 0;
 	data[i++] = rx_pkts;
-	data[i++] = tx_pkts;
 	data[i++] = rx_bytes;
+	/* total rx dropped packets */
+	data[i++] = rx_skb_alloc_fail + rx_buf_alloc_fail +
+		    rx_desc_err_dropped_pkt;
+	data[i++] = rx_skb_alloc_fail;
+	data[i++] = rx_buf_alloc_fail;
+	data[i++] = rx_desc_err_dropped_pkt;
+	data[i++] = tx_pkts;
 	data[i++] = tx_bytes;
-	/* Skip rx_dropped and tx_dropped */
-	i += 2;
+	/* Skip tx_dropped */
+	i++;
 	data[i++] = priv->tx_timeo_cnt;
+	data[i++] = priv->interface_up_cnt;
+	data[i++] = priv->interface_down_cnt;
+	data[i++] = priv->reset_cnt;
+	data[i++] = priv->page_alloc_fail;
+	data[i++] = priv->dma_mapping_error;
 	i = GVE_MAIN_STATS_LEN;
 
+	/* For rx cross-reporting stats, start from nic rx stats in report */
+	base_stats_idx = GVE_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues +
+		GVE_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues;
+	max_stats_idx = NIC_RX_STATS_REPORT_NUM * priv->rx_cfg.num_queues +
+		base_stats_idx;
+	/* Preprocess the stats report for rx, map queue id to start index */
+	skip_nic_stats = false;
+	for (stats_idx = base_stats_idx; stats_idx < max_stats_idx;
+		stats_idx += NIC_RX_STATS_REPORT_NUM) {
+		u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name);
+		u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id);
+		if (stat_name == 0) {
+			/* no stats written by NIC yet */
+			skip_nic_stats = true;
+			break;
+		}
+		rx_qid_to_stats_idx[queue_id] = stats_idx;
+	}
 	/* walk RX rings */
 	if (priv->rx) {
 		for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) {
 			struct gve_rx_ring *rx = &priv->rx[ring];
 
-			data[i++] = rx->cnt;
 			data[i++] = rx->fill_cnt;
+			data[i++] = rx->cnt;
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->rx[ring].statss);
+				tmp_rx_bytes = rx->rbytes;
+				tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail;
+				tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail;
+				tmp_rx_desc_err_dropped_pkt =
+					rx->rx_desc_err_dropped_pkt;
+			} while (u64_stats_fetch_retry(&priv->rx[ring].statss,
+						       start));
+			data[i++] = tmp_rx_bytes;
+			/* rx dropped packets */
+			data[i++] = tmp_rx_skb_alloc_fail +
+				tmp_rx_buf_alloc_fail +
+				tmp_rx_desc_err_dropped_pkt;
+			data[i++] = rx->rx_copybreak_pkt;
+			data[i++] = rx->rx_copied_pkt;
+			/* stats from NIC */
+			if (skip_nic_stats) {
+				/* skip NIC rx stats */
+				i += NIC_RX_STATS_REPORT_NUM;
+				continue;
+			}
+			for (j = 0; j < NIC_RX_STATS_REPORT_NUM; j++) {
+				u64 value = be64_to_cpu(report_stats[
+					rx_qid_to_stats_idx[ring] + j].value);
+				data[i++] = value;
+			}
 		}
-	} else {
+	}
+ else {
 		i += priv->rx_cfg.num_queues * NUM_GVE_RX_CNTS;
 	}
+	/* For tx cross-reporting stats, start from nic tx stats in report */
+	base_stats_idx = max_stats_idx;
+	max_stats_idx = NIC_TX_STATS_REPORT_NUM * priv->tx_cfg.num_queues +
+		max_stats_idx;
+	/* Preprocess the stats report for tx, map queue id to start index */
+	skip_nic_stats = false;
+	for (stats_idx = base_stats_idx; stats_idx < max_stats_idx;
+		stats_idx += NIC_TX_STATS_REPORT_NUM) {
+		u32 stat_name = be32_to_cpu(report_stats[stats_idx].stat_name);
+		u32 queue_id = be32_to_cpu(report_stats[stats_idx].queue_id);
+		if (stat_name == 0) {
+			/* no stats written by NIC yet */
+			skip_nic_stats = true;
+			break;
+		}
+		tx_qid_to_stats_idx[queue_id] = stats_idx;
+	}
 	/* walk TX rings */
 	if (priv->tx) {
 		for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) {
@@ -151,14 +307,51 @@
 
 			data[i++] = tx->req;
 			data[i++] = tx->done;
+			do {
+				start =
+				  u64_stats_fetch_begin(&priv->tx[ring].statss);
+				tmp_tx_bytes = tx->bytes_done;
+			} while (u64_stats_fetch_retry(&priv->tx[ring].statss,
+						       start));
+			data[i++] = tmp_tx_bytes;
 			data[i++] = tx->wake_queue;
 			data[i++] = tx->stop_queue;
 			data[i++] = be32_to_cpu(gve_tx_load_event_counter(priv,
 									  tx));
+			/* stats from NIC */
+			if (skip_nic_stats) {
+				/* skip NIC tx stats */
+				i += NIC_TX_STATS_REPORT_NUM;
+				continue;
+			}
+			for (j = 0; j < NIC_TX_STATS_REPORT_NUM; j++) {
+				u64 value = be64_to_cpu(report_stats[
+					tx_qid_to_stats_idx[ring] + j].value);
+				data[i++] = value;
+			}
 		}
 	} else {
 		i += priv->tx_cfg.num_queues * NUM_GVE_TX_CNTS;
 	}
+
+	kfree(rx_qid_to_stats_idx);
+	kfree(tx_qid_to_stats_idx);
+
+	/* AQ Stats */
+	data[i++] = priv->adminq_prod_cnt;
+	data[i++] = priv->adminq_cmd_fail;
+	data[i++] = priv->adminq_timeouts;
+	data[i++] = priv->adminq_describe_device_cnt;
+	data[i++] = priv->adminq_cfg_device_resources_cnt;
+	data[i++] = priv->adminq_register_page_list_cnt;
+	data[i++] = priv->adminq_unregister_page_list_cnt;
+	data[i++] = priv->adminq_create_tx_queue_cnt;
+	data[i++] = priv->adminq_create_rx_queue_cnt;
+	data[i++] = priv->adminq_destroy_tx_queue_cnt;
+	data[i++] = priv->adminq_destroy_rx_queue_cnt;
+	data[i++] = priv->adminq_dcfg_device_resources_cnt;
+	data[i++] = priv->adminq_set_driver_parameter_cnt;
+	data[i++] = priv->adminq_report_stats_cnt;
 }
 
 static void gve_get_channels(struct net_device *netdev,
@@ -230,6 +423,99 @@
 	return -EOPNOTSUPP;
 }
 
+static int gve_get_tunable(struct net_device *netdev,
+			   const struct ethtool_tunable *etuna, void *value)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+
+	switch (etuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)value = priv->rx_copybreak;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int gve_set_tunable(struct net_device *netdev,
+			   const struct ethtool_tunable *etuna,
+			   const void *value)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	u32 len;
+
+	switch(etuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		len = *(u32 *)value;
+		if (len > priv->dev->mtu) {
+			return -EINVAL;
+		}
+		priv->rx_copybreak = len;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static u32 gve_get_priv_flags(struct net_device *netdev)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	u32 i, ret_flags = 0;
+
+	for (i = 0; i < GVE_PRIV_FLAGS_STR_LEN; i++) {
+		if (priv->ethtool_flags & BIT(i)) {
+			ret_flags |= BIT(i);
+		}
+	}
+	return ret_flags;
+}
+
+static int gve_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	u64 ori_flags, new_flags;
+	u32 i;
+
+	ori_flags = READ_ONCE(priv->ethtool_flags);
+	new_flags = ori_flags;
+
+	for (i = 0; i < GVE_PRIV_FLAGS_STR_LEN; i++) {
+		if (flags & BIT(i))
+			new_flags |= BIT(i);
+		else
+			new_flags &= ~(BIT(i));
+		priv->ethtool_flags = new_flags;
+		/* set report-stats */
+		if (strcmp(gve_gstrings_priv_flags[i], "report-stats") == 0) {
+			/* update the stats when user turns report-stats on */
+			if (flags & BIT(i))
+				gve_handle_report_stats(priv);
+			/* zero off gve stats when report-stats turned off */
+			if (!(flags & BIT(i)) && (ori_flags & BIT(i))) {
+				int tx_stats_num = GVE_TX_STATS_REPORT_NUM *
+					priv->tx_cfg.num_queues;
+				int rx_stats_num = GVE_RX_STATS_REPORT_NUM *
+					priv->rx_cfg.num_queues;
+				memset(priv->stats_report->stats, 0,
+				       (tx_stats_num + rx_stats_num) *
+				       sizeof(struct stats));
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int gve_get_link_ksettings(struct net_device *netdev,
+				       struct ethtool_link_ksettings *cmd)
+{
+	struct gve_priv *priv = netdev_priv(netdev);
+	int err = gve_adminq_report_link_speed(priv);
+
+	cmd->base.speed = priv->link_speed;
+	return err;
+}
+
 const struct ethtool_ops gve_ethtool_ops = {
 	.get_drvinfo = gve_get_drvinfo,
 	.get_strings = gve_get_strings,
@@ -242,4 +528,9 @@
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = gve_get_ringparam,
 	.reset = gve_user_reset,
+	.get_tunable = gve_get_tunable,
+	.set_tunable = gve_set_tunable,
+	.get_priv_flags = gve_get_priv_flags,
+	.set_priv_flags = gve_set_priv_flags,
+	.get_link_ksettings = gve_get_link_ksettings
 };
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 9b7a8db..5b4a50b 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -20,7 +20,7 @@
 #define GVE_DEFAULT_RX_COPYBREAK	(256)
 
 #define DEFAULT_MSG_LEVEL	(NETIF_MSG_DRV | NETIF_MSG_LINK)
-#define GVE_VERSION		"1.0.0"
+#define GVE_VERSION		"1.1.0"
 #define GVE_VERSION_PREFIX	"GVE-"
 
 const char gve_version_str[] = GVE_VERSION;
@@ -78,6 +78,60 @@
 	priv->counter_array = NULL;
 }
 
+void gve_service_task_schedule(struct gve_priv *priv)
+{
+	if (!gve_get_probe_in_progress(priv) &&
+	    !gve_get_reset_in_progress(priv)) {
+		gve_set_do_report_stats(priv);
+		queue_work(priv->gve_wq, &priv->service_task);
+	}
+}
+
+static void gve_service_timer(struct timer_list *t)
+{
+	struct gve_priv *priv = from_timer(priv, t, service_timer);
+
+	mod_timer(&priv->service_timer,
+		  round_jiffies(jiffies +
+		  msecs_to_jiffies(priv->service_timer_period)));
+	gve_service_task_schedule(priv);
+}
+
+static int gve_alloc_stats_report(struct gve_priv *priv)
+{
+	int tx_stats_num, rx_stats_num;
+
+	tx_stats_num = (GVE_TX_STATS_REPORT_NUM + NIC_TX_STATS_REPORT_NUM) *
+		       priv->tx_cfg.num_queues;
+	rx_stats_num = (GVE_RX_STATS_REPORT_NUM + NIC_RX_STATS_REPORT_NUM) *
+		       priv->rx_cfg.num_queues;
+	priv->stats_report_len = sizeof(struct gve_stats_report) +
+				 (tx_stats_num + rx_stats_num) *
+				 sizeof(struct stats);
+	priv->stats_report =
+		dma_alloc_coherent(&priv->pdev->dev, priv->stats_report_len,
+				   &priv->stats_report_bus, GFP_KERNEL);
+	if (!priv->stats_report)
+		return -ENOMEM;
+	/* Set up timer for periodic task */
+	timer_setup(&priv->service_timer, gve_service_timer, 0);
+	priv->service_timer_period = GVE_SERVICE_TIMER_PERIOD;
+	/* Start the service task timer */
+	mod_timer(&priv->service_timer,
+		  round_jiffies(jiffies +
+		  msecs_to_jiffies(priv->service_timer_period)));
+	return 0;
+}
+
+static void gve_free_stats_report(struct gve_priv *priv)
+{
+
+	del_timer_sync(&priv->service_timer);
+	dma_free_coherent(&priv->pdev->dev, priv->stats_report_len,
+			  priv->stats_report, priv->stats_report_bus);
+	priv->stats_report = NULL;
+}
+
 static irqreturn_t gve_mgmnt_intr(int irq, void *arg)
 {
 	struct gve_priv *priv = arg;
@@ -186,15 +240,24 @@
 		dev_err(&priv->pdev->dev, "Did not receive management vector.\n");
 		goto abort_with_msix_enabled;
 	}
-	priv->ntfy_blocks =
+
+	priv->irq_db_indices =
 		dma_alloc_coherent(&priv->pdev->dev,
 				   priv->num_ntfy_blks *
-				   sizeof(*priv->ntfy_blocks),
-				   &priv->ntfy_block_bus, GFP_KERNEL);
-	if (!priv->ntfy_blocks) {
+				   sizeof(*priv->irq_db_indices),
+				   &priv->irq_db_indices_bus, GFP_KERNEL);
+	if (!priv->irq_db_indices) {
 		err = -ENOMEM;
 		goto abort_with_mgmt_vector;
 	}
+
+	priv->ntfy_blocks = kvzalloc(priv->num_ntfy_blks *
+				     sizeof(*priv->ntfy_blocks), GFP_KERNEL);
+	if (!priv->ntfy_blocks) {
+		err = -ENOMEM;
+		goto abort_with_irq_db_indices;
+	}
+
 	/* Setup the other blocks - the first n-1 vectors */
 	for (i = 0; i < priv->num_ntfy_blks; i++) {
 		struct gve_notify_block *block = &priv->ntfy_blocks[i];
@@ -212,6 +275,7 @@
 		}
 		irq_set_affinity_hint(priv->msix_vectors[msix_idx].vector,
 				      get_cpu_mask(i % active_cpus));
+		block->irq_db_index = &priv->irq_db_indices[i].index;
 	}
 	return 0;
 abort_with_some_ntfy_blocks:
@@ -223,10 +287,13 @@
 				      NULL);
 		free_irq(priv->msix_vectors[msix_idx].vector, block);
 	}
-	dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks *
-			  sizeof(*priv->ntfy_blocks),
-			  priv->ntfy_blocks, priv->ntfy_block_bus);
+	kvfree(priv->ntfy_blocks);
 	priv->ntfy_blocks = NULL;
+abort_with_irq_db_indices:
+	dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks *
+			  sizeof(*priv->irq_db_indices),
+			  priv->irq_db_indices, priv->irq_db_indices_bus);
+	priv->irq_db_indices = NULL;
 abort_with_mgmt_vector:
 	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
 abort_with_msix_enabled:
@@ -250,10 +317,12 @@
 				      NULL);
 		free_irq(priv->msix_vectors[msix_idx].vector, block);
 	}
-	dma_free_coherent(&priv->pdev->dev,
-			  priv->num_ntfy_blks * sizeof(*priv->ntfy_blocks),
-			  priv->ntfy_blocks, priv->ntfy_block_bus);
+	kvfree(priv->ntfy_blocks);
 	priv->ntfy_blocks = NULL;
+	dma_free_coherent(&priv->pdev->dev, priv->num_ntfy_blks *
+			  sizeof(*priv->irq_db_indices),
+			  priv->irq_db_indices, priv->irq_db_indices_bus);
+	priv->irq_db_indices = NULL;
 	free_irq(priv->msix_vectors[priv->mgmt_msix_idx].vector, priv);
 	pci_disable_msix(priv->pdev);
 	kvfree(priv->msix_vectors);
@@ -270,19 +339,30 @@
 	err = gve_alloc_notify_blocks(priv);
 	if (err)
 		goto abort_with_counter;
+	err = gve_alloc_stats_report(priv);
+	if (err)
+		goto abort_with_ntfy_blocks;
 	err = gve_adminq_configure_device_resources(priv,
 						    priv->counter_array_bus,
 						    priv->num_event_counters,
-						    priv->ntfy_block_bus,
+						    priv->irq_db_indices_bus,
 						    priv->num_ntfy_blks);
 	if (unlikely(err)) {
 		dev_err(&priv->pdev->dev,
 			"could not setup device_resources: err=%d\n", err);
 		err = -ENXIO;
-		goto abort_with_ntfy_blocks;
+		goto abort_with_stats_report;
 	}
+	err = gve_adminq_report_stats(priv, priv->stats_report_len,
+				      priv->stats_report_bus,
+				      GVE_SERVICE_TIMER_PERIOD);
+	if (err)
+		dev_err(&priv->pdev->dev,
+			"Failed to report stats: err=%d\n", err);
 	gve_set_device_resources_ok(priv);
 	return 0;
+abort_with_stats_report:
+	gve_free_stats_report(priv);
 abort_with_ntfy_blocks:
 	gve_free_notify_blocks(priv);
 abort_with_counter:
@@ -298,6 +378,14 @@
 
 	/* Tell device its resources are being freed */
 	if (gve_get_device_resources_ok(priv)) {
+		/* detach the stats report */
+		err = gve_adminq_report_stats(priv, 0, 0x0,
+			GVE_SERVICE_TIMER_PERIOD);
+		if (err) {
+			dev_err(&priv->pdev->dev,
+				"Failed to detach stats report: err=%d\n", err);
+			gve_trigger_reset(priv);
+		}
 		err = gve_adminq_deconfigure_device_resources(priv);
 		if (err) {
 			dev_err(&priv->pdev->dev,
@@ -308,6 +396,7 @@
 	}
 	gve_free_counter_array(priv);
 	gve_free_notify_blocks(priv);
+	gve_free_stats_report(priv);
 	gve_clear_device_resources_ok(priv);
 }
 
@@ -371,35 +460,37 @@
 	int err;
 	int i;
 
-	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
-		err = gve_adminq_create_tx_queue(priv, i);
-		if (err) {
-			netif_err(priv, drv, priv->dev, "failed to create tx queue %d\n",
-				  i);
-			/* This failure will trigger a reset - no need to clean
-			 * up
-			 */
-			return err;
-		}
-		netif_dbg(priv, drv, priv->dev, "created tx queue %d\n", i);
-	}
-	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
-		err = gve_adminq_create_rx_queue(priv, i);
-		if (err) {
-			netif_err(priv, drv, priv->dev, "failed to create rx queue %d\n",
-				  i);
-			/* This failure will trigger a reset - no need to clean
-			 * up
-			 */
-			return err;
-		}
-		/* Rx data ring has been prefilled with packet buffers at
-		 * queue allocation time.
-		 * Write the doorbell to provide descriptor slots and packet
-		 * buffers to the NIC.
+	err = gve_adminq_create_tx_queues(priv, priv->tx_cfg.num_queues);
+	if (err) {
+		netif_err(priv, drv, priv->dev, "failed to create %d tx queues\n",
+			  priv->tx_cfg.num_queues);
+		/* This failure will trigger a reset - no need to clean
+		 * up
 		 */
+		return err;
+	}
+	netif_dbg(priv, drv, priv->dev, "created %d tx queues \n",
+		  priv->tx_cfg.num_queues);
+
+	err = gve_adminq_create_rx_queues(priv, priv->rx_cfg.num_queues);
+	if (err) {
+		netif_err(priv, drv, priv->dev, "failed to create %d rx queues\n",
+			  priv->rx_cfg.num_queues);
+		/* This failure will trigger a reset - no need to clean
+		 * up
+		 */
+		return err;
+	}
+	netif_dbg(priv, drv, priv->dev, "created %d rx queues \n",
+		  priv->rx_cfg.num_queues);
+
+	/* Rx data ring has been prefilled with packet buffers at queue
+	 * allocation time.
+	 * Write the doorbell to provide descriptor slots and packet buffers
+	 * to the NIC.
+	*/
+	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
 		gve_rx_write_doorbell(priv, &priv->rx[i]);
-		netif_dbg(priv, drv, priv->dev, "created rx queue %d\n", i);
 	}
 
 	return 0;
@@ -458,34 +549,23 @@
 static int gve_destroy_rings(struct gve_priv *priv)
 {
 	int err;
-	int i;
 
-	for (i = 0; i < priv->tx_cfg.num_queues; i++) {
-		err = gve_adminq_destroy_tx_queue(priv, i);
-		if (err) {
-			netif_err(priv, drv, priv->dev,
-				  "failed to destroy tx queue %d\n",
-				  i);
-			/* This failure will trigger a reset - no need to clean
-			 * up
-			 */
-			return err;
-		}
-		netif_dbg(priv, drv, priv->dev, "destroyed tx queue %d\n", i);
+	err = gve_adminq_destroy_tx_queues(priv, priv->tx_cfg.num_queues);
+	if (err) {
+		netif_err(priv, drv, priv->dev,
+			  "failed to destroy tx queues\n");
+		/* This failure will trigger a reset - no need to clean up */
+		return err;
 	}
-	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
-		err = gve_adminq_destroy_rx_queue(priv, i);
-		if (err) {
-			netif_err(priv, drv, priv->dev,
-				  "failed to destroy rx queue %d\n",
-				  i);
-			/* This failure will trigger a reset - no need to clean
-			 * up
-			 */
-			return err;
-		}
-		netif_dbg(priv, drv, priv->dev, "destroyed rx queue %d\n", i);
+	netif_dbg(priv, drv, priv->dev, "destroyed tx queues\n");
+	err = gve_adminq_destroy_rx_queues(priv, priv->rx_cfg.num_queues);
+	if (err) {
+		netif_err(priv, drv, priv->dev,
+			  "failed to destroy rx queues\n");
+		/* This failure will trigger a reset - no need to clean up */
+		return err;
 	}
+	netif_dbg(priv, drv, priv->dev, "destroyed rx queues\n");
 	return 0;
 }
 
@@ -514,15 +594,25 @@
 	}
 }
 
-int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma,
-		   enum dma_data_direction dir)
+int gve_alloc_page(struct gve_priv *priv, struct device *dev,
+		   struct page **page, dma_addr_t *dma,
+		   enum dma_data_direction dir, gfp_t gfp_flags)
 {
-	*page = alloc_page(GFP_KERNEL);
-	if (!*page)
+	if (priv->dma_mask == 24)
+		gfp_flags |= GFP_DMA;
+	else if (priv->dma_mask == 32)
+		gfp_flags |= GFP_DMA32;
+
+  *page = alloc_page(gfp_flags);
+	if (!*page) {
+		priv->page_alloc_fail++;
 		return -ENOMEM;
+	}
 	*dma = dma_map_page(dev, *page, 0, PAGE_SIZE, dir);
 	if (dma_mapping_error(dev, *dma)) {
+		priv->dma_mapping_error++;
 		put_page(*page);
+		*page = NULL;
 		return -ENOMEM;
 	}
 	return 0;
@@ -556,9 +646,9 @@
 		return -ENOMEM;
 
 	for (i = 0; i < pages; i++) {
-		err = gve_alloc_page(&priv->pdev->dev, &qpl->pages[i],
+		err = gve_alloc_page(priv, &priv->pdev->dev, &qpl->pages[i],
 				     &qpl->page_buses[i],
-				     gve_qpl_dma_dir(priv, id));
+				     gve_qpl_dma_dir(priv, id), GFP_KERNEL);
 		/* caller handles clean up */
 		if (err)
 			return -ENOMEM;
@@ -605,6 +695,10 @@
 	int i, j;
 	int err;
 
+	/* Raw addressing means no QPLs */
+	if (priv->raw_addressing)
+		return 0;
+
 	priv->qpls = kvzalloc(num_qpls * sizeof(*priv->qpls), GFP_KERNEL);
 	if (!priv->qpls)
 		return -ENOMEM;
@@ -617,7 +711,7 @@
 	}
 	for (; i < num_qpls; i++) {
 		err = gve_alloc_queue_page_list(priv, i,
-						priv->rx_pages_per_qpl);
+						priv->rx_data_slot_cnt);
 		if (err)
 			goto free_qpls;
 	}
@@ -645,6 +739,10 @@
 	int num_qpls = gve_num_tx_qpls(priv) + gve_num_rx_qpls(priv);
 	int i;
 
+	/* Raw addressing means no QPLs */
+	if (priv->raw_addressing)
+		return;
+
 	kvfree(priv->qpl_cfg.qpl_id_map);
 
 	for (i = 0; i < num_qpls; i++)
@@ -696,7 +794,8 @@
 	gve_set_device_rings_ok(priv);
 
 	gve_turnup(priv);
-	netif_carrier_on(dev);
+	queue_work(priv->gve_wq, &priv->service_task);
+	priv->interface_up_cnt++;
 	return 0;
 
 free_rings:
@@ -738,6 +837,7 @@
 
 	gve_free_rings(priv);
 	gve_free_qpls(priv);
+	priv->interface_down_cnt++;
 	return 0;
 
 err:
@@ -817,6 +917,7 @@
 	netif_tx_disable(priv->dev);
 
 	gve_clear_napi_enabled(priv);
+	gve_clear_report_stats(priv);
 }
 
 static void gve_turnup(struct gve_priv *priv)
@@ -867,6 +968,10 @@
 		dev_info(&priv->pdev->dev, "Device requested reset.\n");
 		gve_set_do_reset(priv);
 	}
+	if (GVE_DEVICE_STATUS_REPORT_STATS_MASK & status) {
+		dev_info(&priv->pdev->dev, "Device report stats on.\n");
+		gve_set_do_report_stats(priv);
+	}
 }
 
 static void gve_handle_reset(struct gve_priv *priv)
@@ -885,16 +990,100 @@
 	}
 }
 
-/* Handle NIC status register changes and reset requests */
+void gve_handle_report_stats(struct gve_priv *priv)
+{
+	int idx, stats_idx = 0, tx_bytes;
+	unsigned int start = 0;
+	struct stats *stats = priv->stats_report->stats;
+
+	if (!gve_get_report_stats(priv))
+		return;
+
+	be64_add_cpu(&priv->stats_report->written_count, 1);
+	/* tx stats */
+	if (priv->tx) {
+		for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) {
+			do {
+				start = u64_stats_fetch_begin(&priv->tx[idx].statss);
+				tx_bytes = priv->tx[idx].bytes_done;
+			} while (u64_stats_fetch_retry(&priv->tx[idx].statss, start));
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(TX_WAKE_CNT),
+				.value = cpu_to_be64(priv->tx[idx].wake_queue),
+				.queue_id = cpu_to_be32(idx),
+			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(TX_STOP_CNT),
+				.value = cpu_to_be64(priv->tx[idx].stop_queue),
+				.queue_id = cpu_to_be32(idx),
+			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(TX_FRAMES_SENT),
+				.value = cpu_to_be64(priv->tx[idx].req),
+				.queue_id = cpu_to_be32(idx),
+			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(TX_BYTES_SENT),
+				.value = cpu_to_be64(tx_bytes),
+				.queue_id = cpu_to_be32(idx),
+			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(
+					TX_LAST_COMPLETION_PROCESSED),
+				.value = cpu_to_be64(priv->tx[idx].done),
+				.queue_id = cpu_to_be32(idx),
+			};
+		}
+	}
+	/* rx stats */
+	if (priv->rx) {
+		for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(
+					RX_NEXT_EXPECTED_SEQUENCE),
+				.value = cpu_to_be64(priv->rx[idx].desc.seqno),
+				.queue_id = cpu_to_be32(idx),
+			};
+			stats[stats_idx++] = (struct stats) {
+				.stat_name = cpu_to_be32(RX_BUFFERS_POSTED),
+				.value = cpu_to_be64(priv->rx[0].fill_cnt),
+				.queue_id = cpu_to_be32(idx),
+			};
+		}
+	}
+}
+
+void gve_handle_link_status(struct gve_priv *priv, bool link_status)
+{
+	if (!gve_get_napi_enabled(priv))
+		return;
+
+	if (link_status == netif_carrier_ok(priv->dev))
+		return;
+
+	if (link_status) {
+		netif_carrier_on(priv->dev);
+	} else {
+		dev_info(&priv->pdev->dev, "Device link is down.\n");
+		netif_carrier_off(priv->dev);
+	}
+}
+
+/* Handle NIC status register changes, reset requests and report stats */
 static void gve_service_task(struct work_struct *work)
 {
 	struct gve_priv *priv = container_of(work, struct gve_priv,
 					     service_task);
+	u32 status = ioread32be(&priv->reg_bar0->device_status);
 
-	gve_handle_status(priv,
-			  ioread32be(&priv->reg_bar0->device_status));
+	gve_handle_status(priv, status);
 
 	gve_handle_reset(priv);
+	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
+	if (gve_get_do_report_stats(priv)) {
+		gve_handle_report_stats(priv);
+		gve_clear_do_report_stats(priv);
+	}
 }
 
 static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
@@ -913,6 +1102,7 @@
 	if (skip_describe_device)
 		goto setup_device;
 
+	priv->raw_addressing = false;
 	/* Get the initial information we need from the device */
 	err = gve_adminq_describe_device(priv);
 	if (err) {
@@ -924,7 +1114,7 @@
 		priv->dev->max_mtu = PAGE_SIZE;
 		err = gve_adminq_set_mtu(priv, priv->dev->mtu);
 		if (err) {
-			netif_err(priv, drv, priv->dev, "Could not set mtu");
+		        dev_err(&priv->pdev->dev, "Could not set mtu");
 			goto err;
 		}
 	}
@@ -964,10 +1154,10 @@
 						priv->rx_cfg.num_queues);
 	}
 
-	netif_info(priv, drv, priv->dev, "TX queues %d, RX queues %d\n",
-		   priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
-	netif_info(priv, drv, priv->dev, "Max TX queues %d, Max RX queues %d\n",
-		   priv->tx_cfg.max_queues, priv->rx_cfg.max_queues);
+	dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n",
+		 priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
+	dev_info(&priv->pdev->dev, "Max TX queues %d, Max RX queues %d\n",
+		 priv->tx_cfg.max_queues, priv->rx_cfg.max_queues);
 
 setup_device:
 	err = gve_setup_device_resources(priv);
@@ -1047,6 +1237,9 @@
 	/* Set it all back up */
 	err = gve_reset_recovery(priv, was_up);
 	gve_clear_reset_in_progress(priv);
+	priv->reset_cnt++;
+	priv->interface_up_cnt = 0;
+	priv->interface_down_cnt = 0;
 	return err;
 }
 
@@ -1074,6 +1267,7 @@
 	__be32 __iomem *db_bar;
 	struct gve_registers __iomem *reg_bar;
 	struct gve_priv *priv;
+	u8 dma_mask;
 	int err;
 
 	err = pci_enable_device(pdev);
@@ -1086,19 +1280,6 @@
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err);
-		goto abort_with_pci_region;
-	}
-
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err) {
-		dev_err(&pdev->dev,
-			"Failed to set consistent dma mask: err=%d\n", err);
-		goto abort_with_pci_region;
-	}
-
 	reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0);
 	if (!reg_bar) {
 		dev_err(&pdev->dev, "Failed to map pci bar!\n");
@@ -1113,10 +1294,28 @@
 		goto abort_with_reg_bar;
 	}
 
+	dma_mask = readb(&reg_bar->dma_mask);
+	// Default to 64 if the register isn't set
+	if (!dma_mask)
+		dma_mask = 64;
 	gve_write_version(&reg_bar->driver_version);
 	/* Get max queues to alloc etherdev */
-	max_rx_queues = ioread32be(&reg_bar->max_tx_queues);
-	max_tx_queues = ioread32be(&reg_bar->max_rx_queues);
+	max_tx_queues = ioread32be(&reg_bar->max_tx_queues);
+	max_rx_queues = ioread32be(&reg_bar->max_rx_queues);
+
+	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_mask));
+	if (err) {
+		dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err);
+		goto abort_with_reg_bar;
+	}
+
+	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_mask));
+	if (err) {
+		dev_err(&pdev->dev,
+			"Failed to set consistent dma mask: err=%d\n", err);
+		goto abort_with_reg_bar;
+	}
+
 	/* Alloc and setup the netdev and priv */
 	dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues);
 	if (!dev) {
@@ -1124,7 +1323,9 @@
 		goto abort_with_db_bar;
 	}
 	SET_NETDEV_DEV(dev, &pdev->dev);
+
 	pci_set_drvdata(pdev, dev);
+
 	dev->ethtool_ops = &gve_ethtool_ops;
 	dev->netdev_ops = &gve_netdev_ops;
 	/* advertise features */
@@ -1149,8 +1350,11 @@
 	priv->db_bar2 = db_bar;
 	priv->service_task_flags = 0x0;
 	priv->state_flags = 0x0;
+	priv->ethtool_flags = 0x0;
+	priv->dma_mask = dma_mask;
 
 	gve_set_probe_in_progress(priv);
+
 	priv->gve_wq = alloc_ordered_workqueue("gve", 0);
 	if (!priv->gve_wq) {
 		dev_err(&pdev->dev, "Could not allocate workqueue");
@@ -1172,6 +1376,7 @@
 	dev_info(&pdev->dev, "GVE version %s\n", gve_version_str);
 	gve_clear_probe_in_progress(priv);
 	queue_work(priv->gve_wq, &priv->service_task);
+
 	return 0;
 
 abort_with_wq:
diff --git a/drivers/net/ethernet/google/gve/gve_register.h b/drivers/net/ethernet/google/gve/gve_register.h
index 84ab889..776c291 100644
--- a/drivers/net/ethernet/google/gve/gve_register.h
+++ b/drivers/net/ethernet/google/gve/gve_register.h
@@ -16,12 +16,14 @@
 	__be32	adminq_pfn;
 	__be32	adminq_doorbell;
 	__be32	adminq_event_counter;
-	u8	reserved[3];
+	u8	reserved[2];
+	u8	dma_mask;
 	u8	driver_version;
 };
 
 enum gve_device_status_flags {
 	GVE_DEVICE_STATUS_RESET_MASK		= BIT(1),
 	GVE_DEVICE_STATUS_LINK_STATUS_MASK	= BIT(2),
+	GVE_DEVICE_STATUS_REPORT_STATS_MASK	= BIT(3),
 };
 #endif /* _GVE_REGISTER_H_ */
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 9f52e72..4aac734 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -16,12 +16,22 @@
 	block->rx = NULL;
 }
 
+static void gve_rx_free_buffer(struct device *dev,
+			       struct gve_rx_slot_page_info *page_info,
+			       struct gve_rx_data_slot *data_slot) {
+	dma_addr_t dma = (dma_addr_t)(be64_to_cpu(data_slot->addr) -
+				      page_info->page_offset);
+
+	page_ref_sub(page_info->page, page_info->pagecnt_bias - 1);
+	gve_free_page(dev, page_info->page, dma, DMA_FROM_DEVICE);
+}
+
 static void gve_rx_free_ring(struct gve_priv *priv, int idx)
 {
 	struct gve_rx_ring *rx = &priv->rx[idx];
 	struct device *dev = &priv->pdev->dev;
 	size_t bytes;
-	u32 slots;
+	u32 slots = rx->mask + 1;
 
 	gve_rx_remove_from_block(priv, idx);
 
@@ -33,11 +43,18 @@
 			  rx->q_resources, rx->q_resources_bus);
 	rx->q_resources = NULL;
 
-	gve_unassign_qpl(priv, rx->data.qpl->id);
-	rx->data.qpl = NULL;
+	if (rx->data.raw_addressing) {
+		int i;
+
+		for (i = 0; i < slots; i++)
+			gve_rx_free_buffer(dev, &rx->data.page_info[i],
+					   &rx->data.data_ring[i]);
+	} else {
+		gve_unassign_qpl(priv, rx->data.qpl->id);
+		rx->data.qpl = NULL;
+	}
 	kvfree(rx->data.page_info);
 
-	slots = rx->mask + 1;
 	bytes = sizeof(*rx->data.data_ring) * slots;
 	dma_free_coherent(dev, bytes, rx->data.data_ring,
 			  rx->data.data_bus);
@@ -52,13 +69,17 @@
 	page_info->page = page;
 	page_info->page_offset = 0;
 	page_info->page_address = page_address(page);
-	slot->qpl_offset = cpu_to_be64(addr);
+	slot->addr = cpu_to_be64(addr);
+	/* The page already has 1 ref */
+	page_ref_add(page, INT_MAX - 1);
+	page_info->pagecnt_bias = INT_MAX;
 }
 
 static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
 {
 	struct gve_priv *priv = rx->gve;
 	u32 slots;
+	int err;
 	int i;
 
 	/* Allocate one page per Rx queue slot. Each page is split into two
@@ -71,12 +92,31 @@
 	if (!rx->data.page_info)
 		return -ENOMEM;
 
-	rx->data.qpl = gve_assign_rx_qpl(priv);
-
+	if (!rx->data.raw_addressing)
+		rx->data.qpl = gve_assign_rx_qpl(priv);
 	for (i = 0; i < slots; i++) {
-		struct page *page = rx->data.qpl->pages[i];
-		dma_addr_t addr = i * PAGE_SIZE;
+		struct page *page;
+		dma_addr_t addr;
 
+		if (rx->data.raw_addressing) {
+			err = gve_alloc_page(priv, &priv->pdev->dev, &page,
+					     &addr, DMA_FROM_DEVICE,
+							 GFP_KERNEL);
+			if (err) {
+				int j;
+
+				u64_stats_update_begin(&rx->statss);
+				rx->rx_buf_alloc_fail++;
+				u64_stats_update_end(&rx->statss);
+				for (j = 0; j < i; j++)
+					gve_free_page(&priv->pdev->dev, page,
+						      addr, DMA_FROM_DEVICE);
+				return err;
+			}
+		} else {
+			page = rx->data.qpl->pages[i];
+			addr = i * PAGE_SIZE;
+		}
 		gve_setup_rx_buffer(&rx->data.page_info[i],
 				    &rx->data.data_ring[i], addr, page);
 	}
@@ -110,8 +150,9 @@
 	rx->gve = priv;
 	rx->q_num = idx;
 
-	slots = priv->rx_pages_per_qpl;
+	slots = priv->rx_data_slot_cnt;
 	rx->mask = slots - 1;
+	rx->data.raw_addressing = priv->raw_addressing;
 
 	/* alloc rx data ring */
 	bytes = sizeof(*rx->data.data_ring) * slots;
@@ -156,8 +197,8 @@
 		err = -ENOMEM;
 		goto abort_with_q_resources;
 	}
-	rx->mask = slots - 1;
 	rx->cnt = 0;
+	rx->db_threshold = priv->rx_desc_cnt / 2;
 	rx->desc.seqno = 1;
 	gve_rx_add_to_block(priv, idx);
 
@@ -242,11 +283,11 @@
 	skb_copy_to_linear_data(skb, va, len);
 
 	skb->protocol = eth_type_trans(skb, dev);
+
 	return skb;
 }
 
-static struct sk_buff *gve_rx_add_frags(struct net_device *dev,
-					struct napi_struct *napi,
+static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 					struct gve_rx_slot_page_info *page_info,
 					u16 len)
 {
@@ -262,14 +303,135 @@
 	return skb;
 }
 
-static void gve_rx_flip_buff(struct gve_rx_slot_page_info *page_info,
-			     struct gve_rx_data_slot *data_ring)
+static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev,
+			       struct gve_rx_slot_page_info *page_info,
+			       struct gve_rx_data_slot *data_slot,
+			       struct gve_rx_ring *rx)
 {
-	u64 addr = be64_to_cpu(data_ring->qpl_offset);
+	struct page *page;
+	dma_addr_t dma;
+	int err;
 
+	err = gve_alloc_page(priv, dev, &page, &dma, DMA_FROM_DEVICE,
+									GFP_ATOMIC);
+	if (err) {
+		u64_stats_update_begin(&rx->statss);
+		rx->rx_buf_alloc_fail++;
+		u64_stats_update_end(&rx->statss);
+		return err;
+	}
+
+	gve_setup_rx_buffer(page_info, data_slot, dma, page);
+	return 0;
+}
+
+static void gve_rx_flip_buffer(struct gve_rx_slot_page_info *page_info,
+			       struct gve_rx_data_slot *data_slot)
+{
+	u64 addr = be64_to_cpu(data_slot->addr);
+
+	/* "flip" to other packet buffer on this page */
 	page_info->page_offset ^= PAGE_SIZE / 2;
 	addr ^= PAGE_SIZE / 2;
-	data_ring->qpl_offset = cpu_to_be64(addr);
+	data_slot->addr = cpu_to_be64(addr);
+}
+
+static bool gve_rx_can_flip_buffers(struct net_device *netdev) {
+#if PAGE_SIZE == 4096
+	/* We can't flip a buffer if we can't fit a packet
+	 * into half a page.
+	 */
+	if (netdev->max_mtu + GVE_RX_PAD + ETH_HLEN  > PAGE_SIZE / 2)
+		return false;
+	return true;
+#else
+	/* PAGE_SIZE != 4096 - don't try to reuse */
+	return false;
+#endif
+}
+
+static int gve_rx_can_recycle_buffer(struct gve_rx_slot_page_info *page_info)
+{
+	int pagecount = page_count(page_info->page);
+
+	/* This page is not being used by any SKBs - reuse */
+	if (pagecount == page_info->pagecnt_bias) {
+		return 1;
+	/* This page is still being used by an SKB - we can't reuse */
+	} else if (pagecount > page_info->pagecnt_bias) {
+		return 0;
+	} else {
+		WARN(pagecount < page_info->pagecnt_bias,
+		     "Pagecount should never be less than the bias.");
+		return -1;
+	}
+}
+
+static void gve_rx_update_pagecnt_bias(struct gve_rx_slot_page_info *page_info)
+{
+	page_info->pagecnt_bias--;
+	if (page_info->pagecnt_bias == 0) {
+		int pagecount = page_count(page_info->page);
+
+		/* If we have run out of bias - set it back up to INT_MAX
+		 * minus the existing refs.
+		 */
+		page_info->pagecnt_bias = INT_MAX - (pagecount);
+		/* Set pagecount back up to max */
+		page_ref_add(page_info->page, INT_MAX - pagecount);
+	}
+}
+
+static struct sk_buff *
+gve_rx_raw_addressing(struct device *dev, struct net_device *netdev,
+		      struct gve_rx_slot_page_info *page_info, u16 len,
+		      struct napi_struct *napi,
+		      struct gve_rx_data_slot *data_slot, bool can_flip)
+{
+	struct sk_buff *skb = gve_rx_add_frags(napi, page_info, len);
+
+	if (!skb)
+		return NULL;
+
+	/* Optimistically stop the kernel from freeing the page.
+	 * We will check again in refill to determine if we need to alloc a
+	 * new page.
+	 */
+	gve_rx_update_pagecnt_bias(page_info);
+	page_info->can_flip = can_flip;
+
+	return skb;
+}
+
+static struct sk_buff *
+gve_rx_qpl(struct device *dev, struct net_device *netdev,
+	   struct gve_rx_ring *rx, struct gve_rx_slot_page_info *page_info,
+	   u16 len, struct napi_struct *napi,
+	   struct gve_rx_data_slot *data_slot, bool recycle)
+{
+	struct sk_buff *skb;
+	/* if raw_addressing mode is not enabled gvnic can only receive into
+	 * registered segments. If the buffer can't be recycled, our only
+	 * choice is to copy the data out of it so that we can return it to the
+	 * device.
+	 */
+	if (recycle) {
+		skb = gve_rx_add_frags(napi, page_info, len);
+		/* No point in recycling if we didn't get the skb */
+		if (skb) {
+			/* Make sure the networking stack can't free the page */
+			gve_rx_update_pagecnt_bias(page_info);
+			gve_rx_flip_buffer(page_info, data_slot);
+		}
+	} else {
+		skb = gve_rx_copy(netdev, napi, page_info, len);
+		if (skb) {
+			u64_stats_update_begin(&rx->statss);
+			rx->rx_copied_pkt++;
+			u64_stats_update_end(&rx->statss);
+		}
+	}
+	return skb;
 }
 
 static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
@@ -278,67 +440,68 @@
 	struct gve_rx_slot_page_info *page_info;
 	struct gve_priv *priv = rx->gve;
 	struct napi_struct *napi = &priv->ntfy_blocks[rx->ntfy_id].napi;
-	struct net_device *dev = priv->dev;
-	struct sk_buff *skb;
-	int pagecount;
+	struct net_device *netdev = priv->dev;
+	struct gve_rx_data_slot *data_slot;
+	struct sk_buff *skb = NULL;
+	dma_addr_t page_bus;
 	u16 len;
 
 	/* drop this packet */
-	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR))
-		return true;
+	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) {
+		u64_stats_update_begin(&rx->statss);
+		rx->rx_desc_err_dropped_pkt++;
+		u64_stats_update_end(&rx->statss);
+		return false;
+	}
 
 	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
 	page_info = &rx->data.page_info[idx];
-	dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx],
+
+	data_slot = &rx->data.data_ring[idx];
+	page_bus = (rx->data.raw_addressing) ?
+					be64_to_cpu(data_slot->addr) - page_info->page_offset:
+					rx->data.qpl->page_buses[idx];									
+	dma_sync_single_for_cpu(&priv->pdev->dev, page_bus,
 				PAGE_SIZE, DMA_FROM_DEVICE);
 
-	/* gvnic can only receive into registered segments. If the buffer
-	 * can't be recycled, our only choice is to copy the data out of
-	 * it so that we can return it to the device.
-	 */
-
-	if (PAGE_SIZE == 4096) {
-		if (len <= priv->rx_copybreak) {
-			/* Just copy small packets */
-			skb = gve_rx_copy(dev, napi, page_info, len);
-			goto have_skb;
-		}
-		if (unlikely(!gve_can_recycle_pages(dev))) {
-			skb = gve_rx_copy(dev, napi, page_info, len);
-			goto have_skb;
-		}
-		pagecount = page_count(page_info->page);
-		if (pagecount == 1) {
-			/* No part of this page is used by any SKBs; we attach
-			 * the page fragment to a new SKB and pass it up the
-			 * stack.
-			 */
-			skb = gve_rx_add_frags(dev, napi, page_info, len);
-			if (!skb)
-				return true;
-			/* Make sure the kernel stack can't release the page */
-			get_page(page_info->page);
-			/* "flip" to other packet buffer on this page */
-			gve_rx_flip_buff(page_info, &rx->data.data_ring[idx]);
-		} else if (pagecount >= 2) {
-			/* We have previously passed the other half of this
-			 * page up the stack, but it has not yet been freed.
-			 */
-			skb = gve_rx_copy(dev, napi, page_info, len);
-		} else {
-			WARN(pagecount < 1, "Pagecount should never be < 1");
-			return false;
-		}
+	if (len <= priv->rx_copybreak) {
+		/* Just copy small packets */
+		skb = gve_rx_copy(netdev, napi, page_info, len);
+		if (skb) {
+				u64_stats_update_begin(&rx->statss);
+				rx->rx_copied_pkt++;
+				rx->rx_copybreak_pkt++;
+				u64_stats_update_end(&rx->statss);
+			}
 	} else {
-		skb = gve_rx_copy(dev, napi, page_info, len);
+		bool can_flip = gve_rx_can_flip_buffers(netdev);
+		int recycle = 0;
+
+		if (can_flip) {
+			recycle = gve_rx_can_recycle_buffer(page_info);
+			if (recycle < 0) {
+				gve_schedule_reset(priv);
+				return false;
+			}
+		}
+		if (rx->data.raw_addressing) {
+			skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev,
+						    page_info, len, napi,
+						    data_slot,
+						    can_flip && recycle);
+		} else {
+			skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx,
+					 page_info, len, napi, data_slot,
+					 can_flip && recycle);
+		}
 	}
 
-have_skb:
-	/* We didn't manage to allocate an skb but we haven't had any
-	 * reset worthy failures.
-	 */
-	if (!skb)
-		return true;
+	if (!skb) {
+		u64_stats_update_begin(&rx->statss);
+		rx->rx_skb_alloc_fail++;
+		u64_stats_update_end(&rx->statss);
+ 		return false;
+	}
 
 	if (likely(feat & NETIF_F_RXCSUM)) {
 		/* NIC passes up the partial sum */
@@ -359,6 +522,7 @@
 		napi_gro_frags(napi);
 	else
 		napi_gro_receive(napi, skb);
+
 	return true;
 }
 
@@ -371,26 +535,80 @@
 	next_idx = rx->cnt & rx->mask;
 	desc = rx->desc.desc_ring + next_idx;
 
+	/* make sure we have synchronized the seq no with the device */
+	smp_mb();
 	flags_seq = desc->flags_seq;
-	/* Make sure we have synchronized the seq no with the device */
-	smp_rmb();
+
 
 	return (GVE_SEQNO(flags_seq) == rx->desc.seqno);
 }
 
+static bool gve_rx_refill_buffers(struct gve_priv *priv, struct gve_rx_ring *rx)
+{
+	u32 fill_cnt = rx->fill_cnt;
+
+	while ((fill_cnt & rx->mask) != (rx->cnt & rx->mask)) {
+		u32 idx = fill_cnt & rx->mask;
+		struct gve_rx_slot_page_info *page_info =
+						&rx->data.page_info[idx];
+
+		if (page_info->can_flip) {
+			/* The other half of the page is free because it was
+			 * free when we processed the descriptor. Flip to it.
+			 */
+			struct gve_rx_data_slot *data_slot =
+						&rx->data.data_ring[idx];
+
+			gve_rx_flip_buffer(page_info, data_slot);
+			page_info->can_flip = false;
+		} else {
+			/* It is possible that the networking stack has already
+			 * finished processing all outstanding packets in the buffer
+			 * and it can be reused.
+			 * Flipping is unceccessary here - if the networking stack still
+			 * owns half the page it is impossible to tell which half. Either
+			 * the whole page is free or it needs to be replaced.
+			 */
+			int recycle = gve_rx_can_recycle_buffer(page_info);
+
+			if (recycle < 0) {
+				gve_schedule_reset(priv);
+				return false;
+			}
+			if (!recycle) {
+				/* We can't reuse the buffer - alloc a new one*/
+				struct gve_rx_data_slot *data_slot =
+						&rx->data.data_ring[idx];
+				struct device *dev = &priv->pdev->dev;
+
+				gve_rx_free_buffer(dev, page_info, data_slot);
+				page_info->page = NULL;
+				if (gve_rx_alloc_buffer(priv, dev, page_info,
+							data_slot, rx)) {
+					break;
+				}
+			}
+		}
+		fill_cnt++;
+	}
+	rx->fill_cnt = fill_cnt;
+	return true;
+}
+
 bool gve_clean_rx_done(struct gve_rx_ring *rx, int budget,
 		       netdev_features_t feat)
 {
 	struct gve_priv *priv = rx->gve;
+	u32 work_done = 0, packets = 0;
 	struct gve_rx_desc *desc;
 	u32 cnt = rx->cnt;
 	u32 idx = cnt & rx->mask;
-	u32 work_done = 0;
 	u64 bytes = 0;
 
 	desc = rx->desc.desc_ring + idx;
 	while ((GVE_SEQNO(desc->flags_seq) == rx->desc.seqno) &&
 	       work_done < budget) {
+		bool dropped;
 		netif_info(priv, rx_status, priv->dev,
 			   "[%d] idx=%d desc=%p desc->flags_seq=0x%x\n",
 			   rx->q_num, idx, desc, desc->flags_seq);
@@ -398,9 +616,11 @@
 			   "[%d] seqno=%d rx->desc.seqno=%d\n",
 			   rx->q_num, GVE_SEQNO(desc->flags_seq),
 			   rx->desc.seqno);
-		bytes += be16_to_cpu(desc->len) - GVE_RX_PAD;
-		if (!gve_rx(rx, desc, feat, idx))
-			gve_schedule_reset(priv);
+		dropped = !gve_rx(rx, desc, feat, idx);
+		if (!dropped) {
+			bytes += be16_to_cpu(desc->len) - GVE_RX_PAD;
+			packets++;
+		}
 		cnt++;
 		idx = cnt & rx->mask;
 		desc = rx->desc.desc_ring + idx;
@@ -412,13 +632,27 @@
 		return false;
 
 	u64_stats_update_begin(&rx->statss);
-	rx->rpackets += work_done;
+	rx->rpackets += packets;
 	rx->rbytes += bytes;
 	u64_stats_update_end(&rx->statss);
 	rx->cnt = cnt;
-	rx->fill_cnt += work_done;
+	/* restock ring slots */
+	if (!rx->data.raw_addressing) {
+		/* In QPL mode buffs are refilled as the desc are processed */
+		rx->fill_cnt += work_done;
+		dma_wmb();/* Ensure descs are visible before ringing doorbell */
+		gve_rx_write_doorbell(priv, rx);
+	} else if (rx->fill_cnt - cnt <= rx->db_threshold) {
+		/* In raw addressing mode buffs are only refilled if the avail
+		 * falls below a threshold.
+		 */
+		if(!gve_rx_refill_buffers(priv, rx))
+			return false;
+		/* restock desc ring slots */
+		dma_wmb();/* Ensure descs are visible before ringing doorbell */
+		gve_rx_write_doorbell(priv, rx);
+	}
 
-	gve_rx_write_doorbell(priv, rx);
 	return gve_rx_work_pending(rx);
 }
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index d0244fe..b85b7a1 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -158,9 +158,11 @@
 			  tx->q_resources, tx->q_resources_bus);
 	tx->q_resources = NULL;
 
-	gve_tx_fifo_release(priv, &tx->tx_fifo);
-	gve_unassign_qpl(priv, tx->tx_fifo.qpl->id);
-	tx->tx_fifo.qpl = NULL;
+	if (!tx->raw_addressing) {
+		gve_tx_fifo_release(priv, &tx->tx_fifo);
+		gve_unassign_qpl(priv, tx->tx_fifo.qpl->id);
+		tx->tx_fifo.qpl = NULL;
+	}
 
 	bytes = sizeof(*tx->desc) * slots;
 	dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
@@ -174,12 +176,16 @@
 
 static void gve_tx_add_to_block(struct gve_priv *priv, int queue_idx)
 {
+	unsigned int active_cpus = min_t(int, priv->num_ntfy_blks / 2,
+					 num_online_cpus());
 	int ntfy_idx = gve_tx_idx_to_ntfy(priv, queue_idx);
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 	struct gve_tx_ring *tx = &priv->tx[queue_idx];
 
 	block->tx = tx;
 	tx->ntfy_id = ntfy_idx;
+	netif_set_xps_queue(priv->dev, get_cpu_mask(ntfy_idx % active_cpus),
+			    queue_idx);
 }
 
 static int gve_tx_alloc_ring(struct gve_priv *priv, int idx)
@@ -206,11 +212,15 @@
 	if (!tx->desc)
 		goto abort_with_info;
 
-	tx->tx_fifo.qpl = gve_assign_tx_qpl(priv);
+	tx->raw_addressing = priv->raw_addressing;
+	tx->dev = &priv->pdev->dev;
+	if (!tx->raw_addressing) {
+		tx->tx_fifo.qpl = gve_assign_tx_qpl(priv);
 
-	/* map Tx FIFO */
-	if (gve_tx_fifo_init(priv, &tx->tx_fifo))
-		goto abort_with_desc;
+		/* map Tx FIFO */
+		if (gve_tx_fifo_init(priv, &tx->tx_fifo))
+			goto abort_with_desc;
+	}
 
 	tx->q_resources =
 		dma_alloc_coherent(hdev,
@@ -228,7 +238,8 @@
 	return 0;
 
 abort_with_fifo:
-	gve_tx_fifo_release(priv, &tx->tx_fifo);
+	if (!tx->raw_addressing)
+		gve_tx_fifo_release(priv, &tx->tx_fifo);
 abort_with_desc:
 	dma_free_coherent(hdev, bytes, tx->desc, tx->bus);
 	tx->desc = NULL;
@@ -306,22 +317,44 @@
  * payload wraps to the beginning of the FIFO.
  */
 #define MAX_TX_DESC_NEEDED	3
+static void gve_tx_unmap_buf(struct device *dev,
+			     struct gve_tx_dma_buf *buf)
+{
+	const int buf_len = (int)dma_unmap_len(buf, len);
+	if (buf_len > 0) {
+		dma_unmap_single(dev, dma_unmap_addr(buf, dma),
+				 dma_unmap_len(buf, len),
+				 DMA_TO_DEVICE);
+		dma_unmap_len_set(buf, len, 0);
+	} else if (buf_len < 0) {
+		dma_unmap_page(dev, dma_unmap_addr(buf, dma),
+			       -dma_unmap_len(buf, len),
+			       DMA_TO_DEVICE);
+		dma_unmap_len_set(buf, len, 0);
+	}
+}
 
 /* Check if sufficient resources (descriptor ring space, FIFO space) are
  * available to transmit the given number of bytes.
  */
 static inline bool gve_can_tx(struct gve_tx_ring *tx, int bytes_required)
 {
-	return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED &&
-		gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required));
+	bool can_alloc = true;
+
+	if (!tx->raw_addressing)
+		can_alloc = gve_tx_fifo_can_alloc(&tx->tx_fifo, bytes_required);
+
+	return (gve_tx_avail(tx) >= MAX_TX_DESC_NEEDED && can_alloc);
 }
 
 /* Stops the queue if the skb cannot be transmitted. */
 static int gve_maybe_stop_tx(struct gve_tx_ring *tx, struct sk_buff *skb)
 {
-	int bytes_required;
+	int bytes_required = 0;
 
-	bytes_required = gve_skb_fifo_bytes_required(tx, skb);
+	if (!tx->raw_addressing)
+		bytes_required = gve_skb_fifo_bytes_required(tx, skb);
+
 	if (likely(gve_can_tx(tx, bytes_required)))
 		return 0;
 
@@ -390,22 +423,23 @@
 	seg_desc->seg.seg_addr = cpu_to_be64(addr);
 }
 
-static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses,
-				    u64 iov_offset, u64 iov_len)
+static void gve_dma_sync_for_device(struct gve_priv *priv,
+								dma_addr_t *page_buses,
+								u64 iov_offset, u64 iov_len)
 {
 	u64 last_page = (iov_offset + iov_len - 1) / PAGE_SIZE;
 	u64 first_page = iov_offset / PAGE_SIZE;
-	dma_addr_t dma;
 	u64 page;
 
 	for (page = first_page; page <= last_page; page++) {
-		dma = page_buses[page];
-		dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE);
+		dma_addr_t dma = page_buses[page];
+		dma_sync_single_for_device(&priv->pdev->dev, dma, PAGE_SIZE,
+					   DMA_TO_DEVICE);
 	}
 }
 
-static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb,
-			  struct device *dev)
+static int gve_tx_add_skb_copy(struct gve_priv* priv, struct gve_tx_ring *tx,
+								struct sk_buff *skb)
 {
 	int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset;
 	union gve_tx_desc *pkt_desc, *seg_desc;
@@ -447,7 +481,7 @@
 	skb_copy_bits(skb, 0,
 		      tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset,
 		      hlen);
-	gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+	gve_dma_sync_for_device(priv, tx->tx_fifo.qpl->page_buses,
 				info->iov[hdr_nfrags - 1].iov_offset,
 				info->iov[hdr_nfrags - 1].iov_len);
 	copy_offset = hlen;
@@ -463,7 +497,7 @@
 		skb_copy_bits(skb, copy_offset,
 			      tx->tx_fifo.base + info->iov[i].iov_offset,
 			      info->iov[i].iov_len);
-		gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+		gve_dma_sync_for_device(priv, tx->tx_fifo.qpl->page_buses,
 					info->iov[i].iov_offset,
 					info->iov[i].iov_len);
 		copy_offset += info->iov[i].iov_len;
@@ -472,6 +506,96 @@
 	return 1 + payload_nfrags;
 }
 
+static int gve_tx_add_skb_no_copy(struct gve_priv *priv, struct gve_tx_ring *tx,
+				  struct sk_buff *skb)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	int hlen, payload_nfrags, l4_hdr_offset, seg_idx_bias;
+	union gve_tx_desc *pkt_desc, *seg_desc;
+	struct gve_tx_buffer_state *info;
+	bool is_gso = skb_is_gso(skb);
+	u32 idx = tx->req & tx->mask;
+	struct gve_tx_dma_buf *buf;
+	int last_mapped = 0;
+	u64 addr;
+	u32 len;
+	int i;
+
+	info = &tx->info[idx];
+	pkt_desc = &tx->desc[idx];
+
+	l4_hdr_offset = skb_checksum_start_offset(skb);
+	/* If the skb is gso, then we want the tcp header in the first segment
+	 * otherwise we want the linear portion of the skb (which will contain
+	 * the checksum because skb->csum_start and skb->csum_offset are given
+	 * relative to skb->head) in the first segment.
+	 */
+	hlen = is_gso ? l4_hdr_offset + tcp_hdrlen(skb) :
+			skb_headlen(skb);
+	len = skb_headlen(skb);
+
+	info->skb =  skb;
+
+	addr = dma_map_single(tx->dev, skb->data, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(tx->dev, addr))) {
+		priv->dma_mapping_error++;
+		goto drop;
+	}
+	buf = &info->buf;
+	dma_unmap_len_set(buf, len, len);
+	dma_unmap_addr_set(buf, dma, addr);
+
+	payload_nfrags = shinfo->nr_frags;
+	if (hlen < len) {
+		/* For gso the rest of the linear portion of the skb needs to
+		 * be in its own descriptor.
+		 */
+		payload_nfrags++;
+		gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset,
+				     1 + payload_nfrags, hlen, addr);
+
+		len -= hlen;
+		addr += hlen;
+		seg_desc = &tx->desc[(tx->req + 1) & tx->mask];
+		seg_idx_bias = 2;
+		gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr);
+	} else {
+		seg_idx_bias = 1;
+		gve_tx_fill_pkt_desc(pkt_desc, skb, is_gso, l4_hdr_offset,
+				     1 + payload_nfrags, hlen, addr);
+	}
+
+	for (i = 0; i < payload_nfrags - (seg_idx_bias - 1); i++) {
+		const skb_frag_t* frag = &shinfo->frags[i];
+
+		idx = (tx->req + i + seg_idx_bias) & tx->mask;
+		seg_desc = &tx->desc[idx];
+		len = skb_frag_size(frag);
+		addr = skb_frag_dma_map(tx->dev, frag, 0, len, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(tx->dev, addr))) {
+			priv->dma_mapping_error++;
+			goto unmap_drop;
+		}
+		buf = &tx->info[idx].buf;
+		dma_unmap_len_set(buf, len, -len);
+		dma_unmap_addr_set(buf, dma, addr);
+
+		gve_tx_fill_seg_desc(seg_desc, skb, is_gso, len, addr);
+	}
+
+	return 1 + payload_nfrags;
+
+unmap_drop:
+	i--;
+	for (last_mapped = i + seg_idx_bias; last_mapped >= 0; last_mapped--) {
+		idx = (tx->req + last_mapped) & tx->mask;
+		gve_tx_unmap_buf(tx->dev, &tx->info[idx].buf);
+	}
+drop:
+	tx->dropped_pkt++;
+	return 0;
+}
+
 netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
 {
 	struct gve_priv *priv = netdev_priv(dev);
@@ -487,20 +611,34 @@
 		 * may have added descriptors without ringing the doorbell.
 		 */
 
+		/* Ensure tx descs from a prior gve_tx are visible before
+		 * ringing doorbell.
+		 */
+		dma_wmb();
 		gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
 		return NETDEV_TX_BUSY;
 	}
-	nsegs = gve_tx_add_skb(tx, skb, &priv->pdev->dev);
+	if (tx->raw_addressing)
+		nsegs = gve_tx_add_skb_no_copy(priv, tx, skb);
+	else
+		nsegs = gve_tx_add_skb_copy(priv, tx, skb);
 
-	netdev_tx_sent_queue(tx->netdev_txq, skb->len);
-	skb_tx_timestamp(skb);
+	/* If the packet is getting sent, we need to update the skb */
+	if (nsegs) {
+		netdev_tx_sent_queue(tx->netdev_txq, skb->len);
+		skb_tx_timestamp(skb);
+	}
 
-	/* give packets to NIC */
+	/* Give packets to NIC. Even if this packet failed to send the doorbell
+	 * might need to be rung because of xmit_more.
+	 */
 	tx->req += nsegs;
 
 	if (!netif_xmit_stopped(tx->netdev_txq) && netdev_xmit_more())
 		return NETDEV_TX_OK;
 
+	/* Ensure tx descs are visible before ringing doorbell */
+	dma_wmb();
 	gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
 	return NETDEV_TX_OK;
 }
@@ -525,24 +663,31 @@
 		info = &tx->info[idx];
 		skb = info->skb;
 
+		/* Unmap the buffer */
+		if (tx->raw_addressing)
+			gve_tx_unmap_buf(tx->dev, &tx->info[idx].buf);
 		/* Mark as free */
 		if (skb) {
 			info->skb = NULL;
 			bytes += skb->len;
 			pkts++;
 			dev_consume_skb_any(skb);
-			/* FIFO free */
-			for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
-				space_freed += info->iov[i].iov_len +
-					       info->iov[i].iov_padding;
-				info->iov[i].iov_len = 0;
-				info->iov[i].iov_padding = 0;
+			if (!tx->raw_addressing) {
+				/* FIFO free */
+				for (i = 0; i < ARRAY_SIZE(info->iov); i++) {
+					space_freed += info->iov[i].iov_len +
+						       info->iov[i].iov_padding;
+					info->iov[i].iov_len = 0;
+					info->iov[i].iov_padding = 0;
+				}
 			}
 		}
 		tx->done++;
 	}
 
-	gve_tx_free_fifo(&tx->tx_fifo, space_freed);
+	if (!tx->raw_addressing) {
+		gve_tx_free_fifo(&tx->tx_fifo, space_freed);
+	}
 	u64_stats_update_begin(&tx->statss);
 	tx->bytes_done += bytes;
 	tx->pkt_done += pkts;
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index b17ddc2..f4212d9 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -9,7 +9,8 @@
 		extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
 		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
 		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
-		super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
+		super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o \
+		fast_commit.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 8c7bbf3..e87ac95 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -243,6 +243,7 @@
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
+	ext4_fc_start_update(inode);
 
 	if ((type == ACL_TYPE_ACCESS) && acl) {
 		error = posix_acl_update_mode(inode, &mode, &acl);
@@ -260,6 +261,7 @@
 	}
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_update(inode);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
 	return error;
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 5aba67a..9bc007a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -368,7 +368,12 @@
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -412,7 +417,8 @@
  * Return buffer_head on success or NULL in case of failure.
  */
 struct buffer_head *
-ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
+ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
+			      bool ignore_locked)
 {
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
@@ -440,6 +446,12 @@
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (ignore_locked && buffer_locked(bh)) {
+		/* buffer under IO already, return if called for prefetching */
+		put_bh(bh);
+		return NULL;
+	}
+
 	if (bitmap_uptodate(bh))
 		goto verify;
 
@@ -486,10 +498,11 @@
 	 * submit the buffer_head for reading
 	 */
 	set_buffer_new(bh);
-	trace_ext4_read_block_bitmap_load(sb, block_group);
+	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
 	bh->b_end_io = ext4_end_bitmap_read;
 	get_bh(bh);
-	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+	submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO |
+		  (ignore_locked ? REQ_RAHEAD : 0), bh);
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -532,7 +545,7 @@
 	struct buffer_head *bh;
 	int err;
 
-	bh = ext4_read_block_bitmap_nowait(sb, block_group);
+	bh = ext4_read_block_bitmap_nowait(sb, block_group, false);
 	if (IS_ERR(bh))
 		return bh;
 	err = ext4_wait_block_bitmap(sb, block_group, bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1c558b5..18ef3bb 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -198,6 +198,12 @@
  */
 #define	EXT4_IO_END_UNWRITTEN	0x0001
 
+struct ext4_io_end_vec {
+	struct list_head list;		/* list of io_end_vec */
+	loff_t offset;			/* offset in the file */
+	ssize_t size;			/* size of the extent */
+};
+
 /*
  * For converting unwritten extents on a work queue. 'handle' is used for
  * buffered writeback.
@@ -211,8 +217,7 @@
 						 * bios covering the extent */
 	unsigned int		flag;		/* unwritten or not */
 	atomic_t		count;		/* reference counter */
-	loff_t			offset;		/* offset in the file */
-	ssize_t			size;		/* size of the extent */
+	struct list_head	list_vec;	/* list of ext4_io_end_vec */
 } ext4_io_end_t;
 
 struct ext4_io_submit {
@@ -922,6 +927,7 @@
 #endif /* defined(__KERNEL__) || defined(__linux__) */
 
 #include "extents_status.h"
+#include "fast_commit.h"
 
 /*
  * Lock subclasses for i_data_sem in the ext4_inode_info structure.
@@ -979,6 +985,28 @@
 
 	struct list_head i_orphan;	/* unlinked but open inodes */
 
+	/* Fast commit related info */
+
+	struct list_head i_fc_list;	/*
+					 * inodes that need fast commit
+					 * protected by sbi->s_fc_lock.
+					 */
+
+	/* Start of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_start;
+
+	/* End of lblk range that needs to be committed in this fast commit */
+	ext4_lblk_t i_fc_lblk_len;
+
+	/* Number of ongoing updates on this inode */
+	atomic_t  i_fc_updates;
+
+	/* Fast commit wait queue for this inode */
+	wait_queue_head_t i_fc_wait;
+
+	/* Protect concurrent accesses on i_fc_lblk_start, i_fc_lblk_len */
+	struct mutex i_fc_lock;
+
 	/*
 	 * i_disksize keeps track of what the inode size is ON DISK, not
 	 * in memory.  During truncate, i_size is set to the new size by
@@ -1100,6 +1128,7 @@
 #define	EXT4_VALID_FS			0x0001	/* Unmounted cleanly */
 #define	EXT4_ERROR_FS			0x0002	/* Errors detected */
 #define	EXT4_ORPHAN_FS			0x0004	/* Orphans being recovered */
+#define EXT4_FC_REPLAY			0x0020	/* Fast commit replay ongoing */
 
 /*
  * Misc. filesystem flags
@@ -1148,6 +1177,7 @@
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
+#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
@@ -1170,6 +1200,8 @@
 #define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM	0x00000008 /* User explicitly
 						specified journal checksum */
 
+#define EXT4_MOUNT2_JOURNAL_FAST_COMMIT	0x00000010 /* Journal fast commit */
+
 #define clear_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt &= \
 						~EXT4_MOUNT_##opt
 #define set_opt(sb, opt)		EXT4_SB(sb)->s_mount_opt |= \
@@ -1349,20 +1381,6 @@
 
 #ifdef __KERNEL__
 
-/*
- * run-time mount flags
- */
-#define EXT4_MF_MNTDIR_SAMPLED		0x0001
-#define EXT4_MF_FS_ABORTED		0x0002	/* Fatal error detected */
-#define EXT4_MF_TEST_DUMMY_ENCRYPTION	0x0004
-
-#ifdef CONFIG_FS_ENCRYPTION
-#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely((sbi)->s_mount_flags & \
-						EXT4_MF_TEST_DUMMY_ENCRYPTION))
-#else
-#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
-#endif
-
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
@@ -1399,7 +1417,7 @@
 	struct buffer_head * __rcu *s_group_desc;
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
-	unsigned int s_mount_flags;
+	unsigned long s_mount_flags;
 	unsigned int s_def_mount_opt;
 	ext4_fsblk_t s_sb_block;
 	atomic64_t s_resv_clusters;
@@ -1480,6 +1498,8 @@
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
+	unsigned int s_mb_prefetch;
+	unsigned int s_mb_prefetch_limit;
 
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
@@ -1554,6 +1574,34 @@
 	 */
 	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
+
+	/* Ext4 fast commit stuff */
+	atomic_t s_fc_subtid;
+	atomic_t s_fc_ineligible_updates;
+	/*
+	 * After commit starts, the main queue gets locked, and the further
+	 * updates get added in the staging queue.
+	 */
+#define FC_Q_MAIN	0
+#define FC_Q_STAGING	1
+	struct list_head s_fc_q[2];	/* Inodes staged for fast commit
+					 * that have data changes in them.
+					 */
+	struct list_head s_fc_dentry_q[2];	/* directory entry updates */
+	unsigned int s_fc_bytes;
+	/*
+	 * Main fast commit lock. This lock protects accesses to the
+	 * following fields:
+	 * ei->i_fc_list, s_fc_dentry_q, s_fc_q, s_fc_bytes, s_fc_bh.
+	 */
+	spinlock_t s_fc_lock;
+	struct buffer_head *s_fc_bh;
+	struct ext4_fc_stats s_fc_stats;
+	u64 s_fc_avg_commit_time;
+#ifdef CONFIG_EXT4_DEBUG
+	int s_fc_debug_max_replay;
+#endif
+	struct ext4_fc_replay_state s_fc_replay_state;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1590,6 +1638,41 @@
 })
 
 /*
+ * run-time mount flags
+ */
+enum {
+	EXT4_MF_MNTDIR_SAMPLED,
+	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
+	EXT4_MF_TEST_DUMMY_ENCRYPTION,
+	EXT4_MF_FC_INELIGIBLE,	/* Fast commit ineligible */
+	EXT4_MF_FC_COMMITTING	/* File system underoing a fast
+				 * commit.
+				 */
+};
+
+static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
+{
+	set_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline void ext4_clear_mount_flag(struct super_block *sb, int bit)
+{
+	clear_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+static inline int ext4_test_mount_flag(struct super_block *sb, int bit)
+{
+	return test_bit(bit, &EXT4_SB(sb)->s_mount_flags);
+}
+
+#ifdef CONFIG_FS_ENCRYPTION
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (unlikely(ext4_test_mount_flag(sbi->s_sb, \
+					     EXT4_MF_TEST_DUMMY_ENCRYPTION)))
+#else
+#define DUMMY_ENCRYPTION_ENABLED(sbi) (0)
+#endif
+
+/*
  * Inode dynamic state flags
  */
 enum {
@@ -1605,6 +1688,7 @@
 	EXT4_STATE_EXT_PRECACHED,	/* extents have been precached */
 	EXT4_STATE_LUSTRE_EA_INODE,	/* Lustre-style ea_inode */
 	EXT4_STATE_VERITY_IN_PROGRESS,	/* building fs-verity Merkle tree */
+	EXT4_STATE_FC_COMMITTING,	/* Fast commit ongoing */
 };
 
 #define EXT4_INODE_BIT_FNS(name, field, offset)				\
@@ -1698,6 +1782,14 @@
 #define EXT4_FEATURE_COMPAT_RESIZE_INODE	0x0010
 #define EXT4_FEATURE_COMPAT_DIR_INDEX		0x0020
 #define EXT4_FEATURE_COMPAT_SPARSE_SUPER2	0x0200
+/*
+ * The reason why "FAST_COMMIT" is a compat feature is that, FS becomes
+ * incompatible only if fast commit blocks are present in the FS. Since we
+ * clear the journal (and thus the fast commit blocks), we don't mark FS as
+ * incompatible. We also have a JBD2 incompat feature, which gets set when
+ * there are fast commit blocks present in the journal.
+ */
+#define EXT4_FEATURE_COMPAT_FAST_COMMIT		0x0400
 
 #define EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER	0x0001
 #define EXT4_FEATURE_RO_COMPAT_LARGE_FILE	0x0002
@@ -1799,6 +1891,7 @@
 EXT4_FEATURE_COMPAT_FUNCS(resize_inode,		RESIZE_INODE)
 EXT4_FEATURE_COMPAT_FUNCS(dir_index,		DIR_INDEX)
 EXT4_FEATURE_COMPAT_FUNCS(sparse_super2,	SPARSE_SUPER2)
+EXT4_FEATURE_COMPAT_FUNCS(fast_commit,		FAST_COMMIT)
 
 EXT4_FEATURE_RO_COMPAT_FUNCS(sparse_super,	SPARSE_SUPER)
 EXT4_FEATURE_RO_COMPAT_FUNCS(large_file,	LARGE_FILE)
@@ -2220,9 +2313,15 @@
 	struct mutex		li_list_mtx;
 };
 
+enum ext4_li_mode {
+	EXT4_LI_MODE_PREFETCH_BBITMAP,
+	EXT4_LI_MODE_ITABLE,
+};
+
 struct ext4_li_request {
 	struct super_block	*lr_super;
-	struct ext4_sb_info	*lr_sbi;
+	enum ext4_li_mode	lr_mode;
+	ext4_group_t		lr_first_not_zeroed;
 	ext4_group_t		lr_next_group;
 	struct list_head	lr_request;
 	unsigned long		lr_next_sched;
@@ -2353,7 +2452,8 @@
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
-						ext4_group_t block_group);
+						ext4_group_t block_group,
+						bool ignore_locked);
 extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  ext4_group_t block_group,
 				  struct buffer_head *bh);
@@ -2525,6 +2625,7 @@
 			  struct dx_hash_info *hinfo);
 
 /* ialloc.c */
+extern int ext4_mark_inode_used(struct super_block *sb, int ino);
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
 				      const struct qstr *qstr, __u32 goal,
 				      uid_t *owner, __u32 i_flags,
@@ -2550,6 +2651,31 @@
 				 ext4_group_t group, int barrier);
 extern void ext4_end_bitmap_read(struct buffer_head *bh, int uptodate);
 
+/* fast_commit.c */
+int ext4_fc_info_show(struct seq_file *seq, void *v);
+void ext4_fc_init(struct super_block *sb, journal_t *journal);
+void ext4_fc_init_inode(struct inode *inode);
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end);
+void __ext4_fc_track_unlink(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void __ext4_fc_track_link(handle_t *handle, struct inode *inode,
+	struct dentry *dentry);
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
+void ext4_fc_start_ineligible(struct super_block *sb, int reason);
+void ext4_fc_stop_ineligible(struct super_block *sb);
+void ext4_fc_start_update(struct inode *inode);
+void ext4_fc_stop_update(struct inode *inode);
+void ext4_fc_del(struct inode *inode);
+bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
+void ext4_fc_replay_cleanup(struct super_block *sb);
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid);
+int __init ext4_fc_init_dentry_cache(void);
+
 /* mballoc.c */
 extern const struct seq_operations ext4_mb_seq_groups_ops;
 extern long ext4_mb_stats;
@@ -2562,6 +2688,12 @@
 extern void ext4_discard_preallocations(struct inode *);
 extern int __init ext4_init_mballoc(void);
 extern void ext4_exit_mballoc(void);
+extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
+				     ext4_group_t group,
+				     unsigned int nr, int *cnt);
+extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+				  unsigned int nr);
+
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			     struct buffer_head *bh, ext4_fsblk_t block,
 			     unsigned long count, int flags);
@@ -2573,8 +2705,12 @@
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
 extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
+extern void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+		       int len, int state);
 
 /* inode.c */
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei);
 int ext4_inode_is_fast_symlink(struct inode *inode);
 struct buffer_head *ext4_getblk(handle_t *, struct inode *, ext4_lblk_t, int);
 struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
@@ -2623,6 +2759,8 @@
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
@@ -2658,12 +2796,15 @@
 /* ioctl.c */
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
+extern void ext4_reset_inode_seed(struct inode *inode);
 
 /* migrate.c */
 extern int ext4_ext_migrate(struct inode *);
 extern int ext4_ind_migrate(struct inode *inode);
 
 /* namei.c */
+extern int ext4_init_new_dir(handle_t *handle, struct inode *dir,
+			     struct inode *inode);
 extern int ext4_dirblock_csum_verify(struct inode *inode,
 				     struct buffer_head *bh);
 extern int ext4_orphan_add(handle_t *, struct inode *);
@@ -2698,6 +2839,11 @@
 /* super.c */
 extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 					 sector_t block, int op_flags);
+extern void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+				bh_end_io_t *end_io);
+extern int ext4_read_bh(struct buffer_head *bh, int op_flags,
+			bh_end_io_t *end_io);
+extern int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait);
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);
 extern int ext4_calculate_overhead(struct super_block *sb);
 extern void ext4_superblock_csum_set(struct super_block *sb);
@@ -3040,6 +3186,7 @@
 	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
 	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
@@ -3054,6 +3201,8 @@
 	(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
 #define EXT4_MB_GRP_CLEAR_TRIMMED(grp)	\
 	(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
+	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
 
 #define EXT4_MAX_CONTENTION		8
 #define EXT4_CONTENTION_THRESHOLD	2
@@ -3217,6 +3366,10 @@
 extern int ext4_ci_compare(const struct inode *parent,
 			   const struct qstr *fname,
 			   const struct qstr *entry, bool quick);
+extern int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
+			 struct inode *inode);
+extern int __ext4_link(struct inode *dir, struct inode *inode,
+		       struct dentry *dentry);
 
 #define S_SHIFT 12
 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
@@ -3289,6 +3442,8 @@
 			  loff_t len);
 extern int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode,
 					  loff_t offset, ssize_t len);
+extern int ext4_convert_unwritten_io_end_vec(handle_t *handle,
+					     ext4_io_end_t *io_end);
 extern int ext4_map_blocks(handle_t *handle, struct inode *inode,
 			   struct ext4_map_blocks *map, int flags);
 extern int ext4_ext_calc_metadata_amount(struct inode *inode,
@@ -3321,6 +3476,11 @@
 			     ext4_lblk_t lblk2,  ext4_lblk_t count,
 			     int mark_unwritten,int *err);
 extern int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu);
+extern void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end);
+extern int ext4_ext_replay_set_iblocks(struct inode *inode);
+extern int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+		int len, int unwritten, ext4_fsblk_t pblk);
+extern int ext4_ext_clear_bb(struct inode *inode);
 
 /* move_extent.c */
 extern void ext4_double_down_write_data_sem(struct inode *first,
@@ -3347,6 +3507,8 @@
 			       int len,
 			       struct writeback_control *wbc,
 			       bool keep_towrite);
+extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
+extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
 
 /* mmp.c */
 extern int ext4_multi_mount_protect(struct super_block *, ext4_fsblk_t);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 7c70b08..d32d351 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -76,7 +76,7 @@
 		return ERR_PTR(err);
 
 	journal = EXT4_SB(sb)->s_journal;
-	if (!journal)
+	if (!journal || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
 		return ext4_get_nojournal();
 	return jbd2__journal_start(journal, blocks, rsv_blocks, GFP_NOFS,
 				   type, line);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3193f0b4..33c7b44 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4839,6 +4839,8 @@
 			ext4_set_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
 	}
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_fc_track_range(handle, inode, offset >> inode->i_sb->s_blocksize_bits,
+			(offset + len - 1) >> inode->i_sb->s_blocksize_bits);
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
@@ -4892,22 +4894,31 @@
 		     FALLOC_FL_INSERT_RANGE))
 		return -EOPNOTSUPP;
 
-	if (mode & FALLOC_FL_PUNCH_HOLE)
-		return ext4_punch_hole(inode, offset, len);
+	ext4_fc_start_update(inode);
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		ret = ext4_punch_hole(inode, offset, len);
+		goto exit;
+	}
 
 	ret = ext4_convert_inline_data(inode);
 	if (ret)
-		return ret;
+		goto exit;
 
-	if (mode & FALLOC_FL_COLLAPSE_RANGE)
-		return ext4_collapse_range(inode, offset, len);
+	if (mode & FALLOC_FL_COLLAPSE_RANGE) {
+		ret = ext4_collapse_range(inode, offset, len);
+		goto exit;
+	}
 
-	if (mode & FALLOC_FL_INSERT_RANGE)
-		return ext4_insert_range(inode, offset, len);
+	if (mode & FALLOC_FL_INSERT_RANGE) {
+		ret = ext4_insert_range(inode, offset, len);
+		goto exit;
+	}
 
-	if (mode & FALLOC_FL_ZERO_RANGE)
-		return ext4_zero_range(file, offset, len, mode);
-
+	if (mode & FALLOC_FL_ZERO_RANGE) {
+		ret = ext4_zero_range(file, offset, len, mode);
+		goto exit;
+	}
 	trace_ext4_fallocate_enter(inode, offset, len, mode);
 	lblk = offset >> blkbits;
 
@@ -4943,12 +4954,14 @@
 		goto out;
 
 	if (file->f_flags & O_SYNC && EXT4_SB(inode->i_sb)->s_journal) {
-		ret = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
-						EXT4_I(inode)->i_sync_tid);
+		ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
+					EXT4_I(inode)->i_sync_tid);
 	}
 out:
 	inode_unlock(inode);
 	trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
+exit:
+	ext4_fc_stop_update(inode);
 	return ret;
 }
 
@@ -4969,23 +4982,13 @@
 	int ret = 0;
 	int ret2 = 0;
 	struct ext4_map_blocks map;
-	unsigned int credits, blkbits = inode->i_blkbits;
+	unsigned int blkbits = inode->i_blkbits;
+	unsigned int credits = 0;
 
 	map.m_lblk = offset >> blkbits;
 	max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits);
 
-	/*
-	 * This is somewhat ugly but the idea is clear: When transaction is
-	 * reserved, everything goes into it. Otherwise we rather start several
-	 * smaller transactions for conversion of each extent separately.
-	 */
-	if (handle) {
-		handle = ext4_journal_start_reserved(handle,
-						     EXT4_HT_EXT_CONVERT);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
-		credits = 0;
-	} else {
+	if (!handle) {
 		/*
 		 * credits to insert 1 extent into extent tree
 		 */
@@ -5016,11 +5019,40 @@
 		if (ret <= 0 || ret2)
 			break;
 	}
-	if (!credits)
-		ret2 = ext4_journal_stop(handle);
 	return ret > 0 ? ret2 : ret;
 }
 
+int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end)
+{
+	int ret, err = 0;
+	struct ext4_io_end_vec *io_end_vec;
+
+	/*
+	 * This is somewhat ugly but the idea is clear: When transaction is
+	 * reserved, everything goes into it. Otherwise we rather start several
+	 * smaller transactions for conversion of each extent separately.
+	 */
+	if (handle) {
+		handle = ext4_journal_start_reserved(handle,
+						     EXT4_HT_EXT_CONVERT);
+		if (IS_ERR(handle))
+			return PTR_ERR(handle);
+	}
+
+	list_for_each_entry(io_end_vec, &io_end->list_vec, list) {
+		ret = ext4_convert_unwritten_extents(handle, io_end->inode,
+						     io_end_vec->offset,
+						     io_end_vec->size);
+		if (ret)
+			break;
+	}
+
+	if (handle)
+		err = ext4_journal_stop(handle);
+
+	return ret < 0 ? ret : err;
+}
+
 /*
  * If newes is not existing extent (newes->ec_pblk equals zero) find
  * delayed extent at start of newes and update newes accordingly and
@@ -5537,6 +5569,7 @@
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_discard_preallocations(inode);
@@ -5575,6 +5608,7 @@
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex:
@@ -5679,6 +5713,7 @@
 		ret = PTR_ERR(handle);
 		goto out_mmap;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE);
 
 	/* Expand file to avoid data loss if there is error while shifting */
 	inode->i_size += len;
@@ -5753,6 +5788,7 @@
 
 out_stop:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 out_mmap:
 	up_write(&EXT4_I(inode)->i_mmap_sem);
 out_mutex:
@@ -6034,3 +6070,263 @@
 
 	return err ? err : mapped;
 }
+
+/*
+ * Updates physical block address and unwritten status of extent
+ * starting at lblk start and of len. If such an extent doesn't exist,
+ * this function splits the extent tree appropriately to create an
+ * extent like this.  This function is called in the fast commit
+ * replay path.  Returns 0 on success and error on failure.
+ */
+int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
+			      int len, int unwritten, ext4_fsblk_t pblk)
+{
+	struct ext4_ext_path *path = NULL, *ppath;
+	struct ext4_extent *ex;
+	int ret;
+
+	path = ext4_find_extent(inode, start, NULL, 0);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ret = -EFSCORRUPTED;
+		goto out;
+	}
+
+	if (le32_to_cpu(ex->ee_block) != start ||
+		ext4_ext_get_actual_len(ex) != len) {
+		/* We need to split this extent to match our extent first */
+		ppath = path;
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ret = ext4_force_split_extent_at(NULL, inode, &ppath, start, 1);
+		up_write(&EXT4_I(inode)->i_data_sem);
+		if (ret)
+			goto out;
+		kfree(path);
+		path = ext4_find_extent(inode, start, NULL, 0);
+		if (IS_ERR(path))
+			return -1;
+		ppath = path;
+		ex = path[path->p_depth].p_ext;
+		WARN_ON(le32_to_cpu(ex->ee_block) != start);
+		if (ext4_ext_get_actual_len(ex) != len) {
+			down_write(&EXT4_I(inode)->i_data_sem);
+			ret = ext4_force_split_extent_at(NULL, inode, &ppath,
+							 start + len, 1);
+			up_write(&EXT4_I(inode)->i_data_sem);
+			if (ret)
+				goto out;
+			kfree(path);
+			path = ext4_find_extent(inode, start, NULL, 0);
+			if (IS_ERR(path))
+				return -EINVAL;
+			ex = path[path->p_depth].p_ext;
+		}
+	}
+	if (unwritten)
+		ext4_ext_mark_unwritten(ex);
+	else
+		ext4_ext_mark_initialized(ex);
+	ext4_ext_store_pblock(ex, pblk);
+	down_write(&EXT4_I(inode)->i_data_sem);
+	ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+	up_write(&EXT4_I(inode)->i_data_sem);
+out:
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	ext4_mark_inode_dirty(NULL, inode);
+	return ret;
+}
+
+/* Try to shrink the extent tree */
+void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t old_cur, cur = 0;
+
+	while (cur < end) {
+		path = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path))
+			return;
+		ex = path[path->p_depth].p_ext;
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			ext4_mark_inode_dirty(NULL, inode);
+			return;
+		}
+		old_cur = cur;
+		cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+		if (cur <= old_cur)
+			cur = old_cur + 1;
+		ext4_ext_try_to_merge(NULL, inode, path, ex);
+		down_write(&EXT4_I(inode)->i_data_sem);
+		ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
+		up_write(&EXT4_I(inode)->i_data_sem);
+		ext4_mark_inode_dirty(NULL, inode);
+		ext4_ext_drop_refs(path);
+		kfree(path);
+	}
+}
+
+/* Check if *cur is a hole and if it is, skip it */
+static void skip_hole(struct inode *inode, ext4_lblk_t *cur)
+{
+	int ret;
+	struct ext4_map_blocks map;
+
+	map.m_lblk = *cur;
+	map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur;
+
+	ret = ext4_map_blocks(NULL, inode, &map, 0);
+	if (ret != 0)
+		return;
+	*cur = *cur + map.m_len;
+}
+
+/* Count number of blocks used by this inode and update i_blocks */
+int ext4_ext_replay_set_iblocks(struct inode *inode)
+{
+	struct ext4_ext_path *path = NULL, *path2 = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t cur = 0, end;
+	int numblks = 0, i, ret = 0;
+	ext4_fsblk_t cmp1, cmp2;
+	struct ext4_map_blocks map;
+
+	/* Determin the size of the file first */
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+					EXT4_EX_NOCACHE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		goto out;
+	}
+	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	/* Count the number of data blocks */
+	cur = 0;
+	while (cur < end) {
+		map.m_lblk = cur;
+		map.m_len = end - cur;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			break;
+		if (ret > 0)
+			numblks += ret;
+		cur = cur + map.m_len;
+	}
+
+	/*
+	 * Count the number of extent tree blocks. We do it by looking up
+	 * two successive extents and determining the difference between
+	 * their paths. When path is different for 2 successive extents
+	 * we compare the blocks in the path at each level and increment
+	 * iblocks by total number of differences found.
+	 */
+	cur = 0;
+	skip_hole(inode, &cur);
+	path = ext4_find_extent(inode, cur, NULL, 0);
+	if (IS_ERR(path))
+		goto out;
+	numblks += path->p_depth;
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	while (cur < end) {
+		path = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path))
+			break;
+		ex = path[path->p_depth].p_ext;
+		if (!ex) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			return 0;
+		}
+		cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
+					ext4_ext_get_actual_len(ex));
+		skip_hole(inode, &cur);
+
+		path2 = ext4_find_extent(inode, cur, NULL, 0);
+		if (IS_ERR(path2)) {
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			break;
+		}
+		for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
+			cmp1 = cmp2 = 0;
+			if (i <= path->p_depth)
+				cmp1 = path[i].p_bh ?
+					path[i].p_bh->b_blocknr : 0;
+			if (i <= path2->p_depth)
+				cmp2 = path2[i].p_bh ?
+					path2[i].p_bh->b_blocknr : 0;
+			if (cmp1 != cmp2 && cmp2 != 0)
+				numblks++;
+		}
+		ext4_ext_drop_refs(path);
+		ext4_ext_drop_refs(path2);
+		kfree(path);
+		kfree(path2);
+	}
+
+out:
+	inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9);
+	ext4_mark_inode_dirty(NULL, inode);
+	return 0;
+}
+
+int ext4_ext_clear_bb(struct inode *inode)
+{
+	struct ext4_ext_path *path = NULL;
+	struct ext4_extent *ex;
+	ext4_lblk_t cur = 0, end;
+	int j, ret = 0;
+	struct ext4_map_blocks map;
+
+	/* Determin the size of the file first */
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+					EXT4_EX_NOCACHE);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+	ex = path[path->p_depth].p_ext;
+	if (!ex) {
+		ext4_ext_drop_refs(path);
+		kfree(path);
+		return 0;
+	}
+	end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+
+	cur = 0;
+	while (cur < end) {
+		map.m_lblk = cur;
+		map.m_len = end - cur;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			break;
+		if (ret > 0) {
+			path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+			if (!IS_ERR_OR_NULL(path)) {
+				for (j = 0; j < path->p_depth; j++) {
+
+					ext4_mb_mark_bb(inode->i_sb,
+							path[j].p_block, 1, 0);
+				}
+				ext4_ext_drop_refs(path);
+				kfree(path);
+			}
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+		}
+		cur = cur + map.m_len;
+	}
+
+	return 0;
+}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index d996b44..69c16ac 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -311,6 +311,9 @@
 			       ext4_lblk_t lblk, ext4_lblk_t end,
 			       struct extent_status *es)
 {
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	trace_ext4_es_find_extent_range_enter(inode, lblk);
 
 	read_lock(&EXT4_I(inode)->i_es_lock);
@@ -361,6 +364,9 @@
 {
 	bool ret;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return false;
+
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	ret = __es_scan_range(inode, matching_fn, lblk, end);
 	read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -404,6 +410,9 @@
 {
 	bool ret;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return false;
+
 	read_lock(&EXT4_I(inode)->i_es_lock);
 	ret = __es_scan_clu(inode, matching_fn, lblk);
 	read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -812,6 +821,9 @@
 	int err = 0;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
 		 lblk, len, pblk, status, inode->i_ino);
 
@@ -873,6 +885,9 @@
 	struct extent_status newes;
 	ext4_lblk_t end = lblk + len - 1;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	newes.es_lblk = lblk;
 	newes.es_len = len;
 	ext4_es_store_pblock_status(&newes, pblk, status);
@@ -908,6 +923,9 @@
 	struct rb_node *node;
 	int found = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	trace_ext4_es_lookup_extent_enter(inode, lblk);
 	es_debug("lookup extent in block %u\n", lblk);
 
@@ -1419,6 +1437,9 @@
 	int err = 0;
 	int reserved = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	trace_ext4_es_remove_extent(inode, lblk, len);
 	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
 		 lblk, len, inode->i_ino);
@@ -1969,6 +1990,9 @@
 	struct extent_status newes;
 	int err = 0;
 
+	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
 	es_debug("add [%u/1) delayed to extent status tree of inode %lu\n",
 		 lblk, inode->i_ino);
 
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
new file mode 100644
index 0000000..fd74faa
--- /dev/null
+++ b/fs/ext4/fast_commit.c
@@ -0,0 +1,2180 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * fs/ext4/fast_commit.c
+ *
+ * Written by Harshad Shirwadkar <harshadshirwadkar@gmail.com>
+ *
+ * Ext4 fast commits routines.
+ */
+#include "ext4.h"
+#include "ext4_jbd2.h"
+#include "ext4_extents.h"
+#include "mballoc.h"
+
+/*
+ * Ext4 Fast Commits
+ * -----------------
+ *
+ * Ext4 fast commits implement fine grained journalling for Ext4.
+ *
+ * Fast commits are organized as a log of tag-length-value (TLV) structs. (See
+ * struct ext4_fc_tl). Each TLV contains some delta that is replayed TLV by
+ * TLV during the recovery phase. For the scenarios for which we currently
+ * don't have replay code, fast commit falls back to full commits.
+ * Fast commits record delta in one of the following three categories.
+ *
+ * (A) Directory entry updates:
+ *
+ * - EXT4_FC_TAG_UNLINK		- records directory entry unlink
+ * - EXT4_FC_TAG_LINK		- records directory entry link
+ * - EXT4_FC_TAG_CREAT		- records inode and directory entry creation
+ *
+ * (B) File specific data range updates:
+ *
+ * - EXT4_FC_TAG_ADD_RANGE	- records addition of new blocks to an inode
+ * - EXT4_FC_TAG_DEL_RANGE	- records deletion of blocks from an inode
+ *
+ * (C) Inode metadata (mtime / ctime etc):
+ *
+ * - EXT4_FC_TAG_INODE		- record the inode that should be replayed
+ *				  during recovery. Note that iblocks field is
+ *				  not replayed and instead derived during
+ *				  replay.
+ * Commit Operation
+ * ----------------
+ * With fast commits, we maintain all the directory entry operations in the
+ * order in which they are issued in an in-memory queue. This queue is flushed
+ * to disk during the commit operation. We also maintain a list of inodes
+ * that need to be committed during a fast commit in another in memory queue of
+ * inodes. During the commit operation, we commit in the following order:
+ *
+ * [1] Lock inodes for any further data updates by setting COMMITTING state
+ * [2] Submit data buffers of all the inodes
+ * [3] Wait for [2] to complete
+ * [4] Commit all the directory entry updates in the fast commit space
+ * [5] Commit all the changed inode structures
+ * [6] Write tail tag (this tag ensures the atomicity, please read the following
+ *     section for more details).
+ * [7] Wait for [4], [5] and [6] to complete.
+ *
+ * All the inode updates must call ext4_fc_start_update() before starting an
+ * update. If such an ongoing update is present, fast commit waits for it to
+ * complete. The completion of such an update is marked by
+ * ext4_fc_stop_update().
+ *
+ * Fast Commit Ineligibility
+ * -------------------------
+ * Not all operations are supported by fast commits today (e.g extended
+ * attributes). Fast commit ineligiblity is marked by calling one of the
+ * two following functions:
+ *
+ * - ext4_fc_mark_ineligible(): This makes next fast commit operation to fall
+ *   back to full commit. This is useful in case of transient errors.
+ *
+ * - ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() - This makes all
+ *   the fast commits happening between ext4_fc_start_ineligible() and
+ *   ext4_fc_stop_ineligible() and one fast commit after the call to
+ *   ext4_fc_stop_ineligible() to fall back to full commits. It is important to
+ *   make one more fast commit to fall back to full commit after stop call so
+ *   that it guaranteed that the fast commit ineligible operation contained
+ *   within ext4_fc_start_ineligible() and ext4_fc_stop_ineligible() is
+ *   followed by at least 1 full commit.
+ *
+ * Atomicity of commits
+ * --------------------
+ * In order to guarantee atomicity during the commit operation, fast commit
+ * uses "EXT4_FC_TAG_TAIL" tag that marks a fast commit as complete. Tail
+ * tag contains CRC of the contents and TID of the transaction after which
+ * this fast commit should be applied. Recovery code replays fast commit
+ * logs only if there's at least 1 valid tail present. For every fast commit
+ * operation, there is 1 tail. This means, we may end up with multiple tails
+ * in the fast commit space. Here's an example:
+ *
+ * - Create a new file A and remove existing file B
+ * - fsync()
+ * - Append contents to file A
+ * - Truncate file A
+ * - fsync()
+ *
+ * The fast commit space at the end of above operations would look like this:
+ *      [HEAD] [CREAT A] [UNLINK B] [TAIL] [ADD_RANGE A] [DEL_RANGE A] [TAIL]
+ *             |<---  Fast Commit 1   --->|<---      Fast Commit 2     ---->|
+ *
+ * Replay code should thus check for all the valid tails in the FC area.
+ *
+ * Fast Commit Replay Idempotence
+ * ------------------------------
+ *
+ * Fast commits tags are idempotent in nature provided the recovery code follows
+ * certain rules. The guiding principle that the commit path follows while
+ * committing is that it stores the result of a particular operation instead of
+ * storing the procedure.
+ *
+ * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+ * was associated with inode 10. During fast commit, instead of storing this
+ * operation as a procedure "rename a to b", we store the resulting file system
+ * state as a "series" of outcomes:
+ *
+ * - Link dirent b to inode 10
+ * - Unlink dirent a
+ * - Inode <10> with valid refcount
+ *
+ * Now when recovery code runs, it needs "enforce" this state on the file
+ * system. This is what guarantees idempotence of fast commit replay.
+ *
+ * Let's take an example of a procedure that is not idempotent and see how fast
+ * commits make it idempotent. Consider following sequence of operations:
+ *
+ *     rm A;    mv B A;    read A
+ *  (x)     (y)        (z)
+ *
+ * (x), (y) and (z) are the points at which we can crash. If we store this
+ * sequence of operations as is then the replay is not idempotent. Let's say
+ * while in replay, we crash at (z). During the second replay, file A (which was
+ * actually created as a result of "mv B A" operation) would get deleted. Thus,
+ * file named A would be absent when we try to read A. So, this sequence of
+ * operations is not idempotent. However, as mentioned above, instead of storing
+ * the procedure fast commits store the outcome of each procedure. Thus the fast
+ * commit log for above procedure would be as follows:
+ *
+ * (Let's assume dirent A was linked to inode 10 and dirent B was linked to
+ * inode 11 before the replay)
+ *
+ *    [Unlink A]   [Link A to inode 11]   [Unlink B]   [Inode 11]
+ * (w)          (x)                    (y)          (z)
+ *
+ * If we crash at (z), we will have file A linked to inode 11. During the second
+ * replay, we will remove file A (inode 11). But we will create it back and make
+ * it point to inode 11. We won't find B, so we'll just skip that step. At this
+ * point, the refcount for inode 11 is not reliable, but that gets fixed by the
+ * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled
+ * similarly. Thus, by converting a non-idempotent procedure into a series of
+ * idempotent outcomes, fast commits ensured idempotence during the replay.
+ *
+ * TODOs
+ * -----
+ *
+ * 0) Fast commit replay path hardening: Fast commit replay code should use
+ *    journal handles to make sure all the updates it does during the replay
+ *    path are atomic. With that if we crash during fast commit replay, after
+ *    trying to do recovery again, we will find a file system where fast commit
+ *    area is invalid (because new full commit would be found). In order to deal
+ *    with that, fast commit replay code should ensure that the "FC_REPLAY"
+ *    superblock state is persisted before starting the replay, so that after
+ *    the crash, fast commit recovery code can look at that flag and perform
+ *    fast commit recovery even if that area is invalidated by later full
+ *    commits.
+ *
+ * 1) Make fast commit atomic updates more fine grained. Today, a fast commit
+ *    eligible update must be protected within ext4_fc_start_update() and
+ *    ext4_fc_stop_update(). These routines are called at much higher
+ *    routines. This can be made more fine grained by combining with
+ *    ext4_journal_start().
+ *
+ * 2) Same above for ext4_fc_start_ineligible() and ext4_fc_stop_ineligible()
+ *
+ * 3) Handle more ineligible cases.
+ */
+
+#include <trace/events/ext4.h>
+static struct kmem_cache *ext4_fc_dentry_cachep;
+
+static void ext4_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
+{
+	BUFFER_TRACE(bh, "");
+	if (uptodate) {
+		ext4_debug("%s: Block %lld up-to-date",
+			   __func__, bh->b_blocknr);
+		set_buffer_uptodate(bh);
+	} else {
+		ext4_debug("%s: Block %lld not up-to-date",
+			   __func__, bh->b_blocknr);
+		clear_buffer_uptodate(bh);
+	}
+
+	unlock_buffer(bh);
+}
+
+static inline void ext4_fc_reset_inode(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	ei->i_fc_lblk_start = 0;
+	ei->i_fc_lblk_len = 0;
+}
+
+void ext4_fc_init_inode(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	ext4_fc_reset_inode(inode);
+	ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
+	INIT_LIST_HEAD(&ei->i_fc_list);
+	init_waitqueue_head(&ei->i_fc_wait);
+	atomic_set(&ei->i_fc_updates, 0);
+}
+
+/* This function must be called with sbi->s_fc_lock held. */
+static void ext4_fc_wait_committing_inode(struct inode *inode)
+__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
+{
+	wait_queue_head_t *wq;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+#if (BITS_PER_LONG < 64)
+	DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_state_flags,
+				EXT4_STATE_FC_COMMITTING);
+#else
+	DEFINE_WAIT_BIT(wait, &ei->i_flags,
+			EXT4_STATE_FC_COMMITTING);
+	wq = bit_waitqueue(&ei->i_flags,
+				EXT4_STATE_FC_COMMITTING);
+#endif
+	lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	schedule();
+	finish_wait(wq, &wait.wq_entry);
+}
+
+/*
+ * Inform Ext4's fast about start of an inode update
+ *
+ * This function is called by the high level call VFS callbacks before
+ * performing any inode update. This function blocks if there's an ongoing
+ * fast commit on the inode in question.
+ */
+void ext4_fc_start_update(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+restart:
+	spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	if (list_empty(&ei->i_fc_list))
+		goto out;
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
+		ext4_fc_wait_committing_inode(inode);
+		goto restart;
+	}
+out:
+	atomic_inc(&ei->i_fc_updates);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+}
+
+/*
+ * Stop inode update and wake up waiting fast commits if any.
+ */
+void ext4_fc_stop_update(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+	if (atomic_dec_and_test(&ei->i_fc_updates))
+		wake_up_all(&ei->i_fc_wait);
+}
+
+/*
+ * Remove inode from fast commit list. If the inode is being committed
+ * we wait until inode commit is done.
+ */
+void ext4_fc_del(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+restart:
+	spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	if (list_empty(&ei->i_fc_list)) {
+		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+		return;
+	}
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
+		ext4_fc_wait_committing_inode(inode);
+		goto restart;
+	}
+	list_del_init(&ei->i_fc_list);
+	spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+}
+
+/*
+ * Mark file system as fast commit ineligible. This means that next commit
+ * operation would result in a full jbd2 commit.
+ */
+void ext4_fc_mark_ineligible(struct super_block *sb, int reason)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	WARN_ON(reason >= EXT4_FC_REASON_MAX);
+	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
+}
+
+/*
+ * Start a fast commit ineligible update. Any commits that happen while
+ * such an operation is in progress fall back to full commits.
+ */
+void ext4_fc_start_ineligible(struct super_block *sb, int reason)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+	WARN_ON(reason >= EXT4_FC_REASON_MAX);
+	sbi->s_fc_stats.fc_ineligible_reason_count[reason]++;
+	atomic_inc(&sbi->s_fc_ineligible_updates);
+}
+
+/*
+ * Stop a fast commit ineligible update. We set EXT4_MF_FC_INELIGIBLE flag here
+ * to ensure that after stopping the ineligible update, at least one full
+ * commit takes place.
+ */
+void ext4_fc_stop_ineligible(struct super_block *sb)
+{
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+	    (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+		return;
+
+	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	atomic_dec(&EXT4_SB(sb)->s_fc_ineligible_updates);
+}
+
+static inline int ext4_fc_is_ineligible(struct super_block *sb)
+{
+	return (ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE) ||
+		atomic_read(&EXT4_SB(sb)->s_fc_ineligible_updates));
+}
+
+/*
+ * Generic fast commit tracking function. If this is the first time this we are
+ * called after a full commit, we initialize fast commit fields and then call
+ * __fc_track_fn() with update = 0. If we have already been called after a full
+ * commit, we pass update = 1. Based on that, the track function can determine
+ * if it needs to track a field for the first time or if it needs to just
+ * update the previously tracked value.
+ *
+ * If enqueue is set, this function enqueues the inode in fast commit list.
+ */
+static int ext4_fc_track_template(
+	handle_t *handle, struct inode *inode,
+	int (*__fc_track_fn)(struct inode *, void *, bool),
+	void *args, int enqueue)
+{
+	bool update = false;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	tid_t tid = 0;
+	int ret;
+
+	if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+	    (sbi->s_mount_state & EXT4_FC_REPLAY))
+		return -EOPNOTSUPP;
+
+	if (ext4_fc_is_ineligible(inode->i_sb))
+		return -EINVAL;
+
+	tid = handle->h_transaction->t_tid;
+	mutex_lock(&ei->i_fc_lock);
+	if (tid == ei->i_sync_tid) {
+		update = true;
+	} else {
+		ext4_fc_reset_inode(inode);
+		ei->i_sync_tid = tid;
+	}
+	ret = __fc_track_fn(inode, args, update);
+	mutex_unlock(&ei->i_fc_lock);
+
+	if (!enqueue)
+		return ret;
+
+	spin_lock(&sbi->s_fc_lock);
+	if (list_empty(&EXT4_I(inode)->i_fc_list))
+		list_add_tail(&EXT4_I(inode)->i_fc_list,
+				(ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
+				&sbi->s_fc_q[FC_Q_STAGING] :
+				&sbi->s_fc_q[FC_Q_MAIN]);
+	spin_unlock(&sbi->s_fc_lock);
+
+	return ret;
+}
+
+struct __track_dentry_update_args {
+	struct dentry *dentry;
+	int op;
+};
+
+/* __track_fn for directory entry updates. Called with ei->i_fc_lock. */
+static int __track_dentry_update(struct inode *inode, void *arg, bool update)
+{
+	struct ext4_fc_dentry_update *node;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct __track_dentry_update_args *dentry_update =
+		(struct __track_dentry_update_args *)arg;
+	struct dentry *dentry = dentry_update->dentry;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+	mutex_unlock(&ei->i_fc_lock);
+	node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS);
+	if (!node) {
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
+		mutex_lock(&ei->i_fc_lock);
+		return -ENOMEM;
+	}
+
+	node->fcd_op = dentry_update->op;
+	node->fcd_parent = dentry->d_parent->d_inode->i_ino;
+	node->fcd_ino = inode->i_ino;
+	if (dentry->d_name.len > DNAME_INLINE_LEN) {
+		node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS);
+		if (!node->fcd_name.name) {
+			kmem_cache_free(ext4_fc_dentry_cachep, node);
+			ext4_fc_mark_ineligible(inode->i_sb,
+				EXT4_FC_REASON_NOMEM);
+			mutex_lock(&ei->i_fc_lock);
+			return -ENOMEM;
+		}
+		memcpy((u8 *)node->fcd_name.name, dentry->d_name.name,
+			dentry->d_name.len);
+	} else {
+		memcpy(node->fcd_iname, dentry->d_name.name,
+			dentry->d_name.len);
+		node->fcd_name.name = node->fcd_iname;
+	}
+	node->fcd_name.len = dentry->d_name.len;
+
+	spin_lock(&sbi->s_fc_lock);
+	if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
+		list_add_tail(&node->fcd_list,
+				&sbi->s_fc_dentry_q[FC_Q_STAGING]);
+	else
+		list_add_tail(&node->fcd_list, &sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	spin_unlock(&sbi->s_fc_lock);
+	mutex_lock(&ei->i_fc_lock);
+
+	return 0;
+}
+
+void __ext4_fc_track_unlink(handle_t *handle,
+		struct inode *inode, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_UNLINK;
+
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_unlink(inode, dentry, ret);
+}
+
+void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_unlink(handle, d_inode(dentry), dentry);
+}
+
+void __ext4_fc_track_link(handle_t *handle,
+	struct inode *inode, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_LINK;
+
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_link(inode, dentry, ret);
+}
+
+void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
+{
+	__ext4_fc_track_link(handle, d_inode(dentry), dentry);
+}
+
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+{
+	struct __track_dentry_update_args args;
+	struct inode *inode = d_inode(dentry);
+	int ret;
+
+	args.dentry = dentry;
+	args.op = EXT4_FC_TAG_CREAT;
+
+	ret = ext4_fc_track_template(handle, inode, __track_dentry_update,
+					(void *)&args, 0);
+	trace_ext4_fc_track_create(inode, dentry, ret);
+}
+
+/* __track_fn for inode tracking */
+static int __track_inode(struct inode *inode, void *arg, bool update)
+{
+	if (update)
+		return -EEXIST;
+
+	EXT4_I(inode)->i_fc_lblk_len = 0;
+
+	return 0;
+}
+
+void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
+{
+	int ret;
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	if (ext4_should_journal_data(inode)) {
+		ext4_fc_mark_ineligible(inode->i_sb,
+					EXT4_FC_REASON_INODE_JOURNAL_DATA);
+		return;
+	}
+
+	ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
+	trace_ext4_fc_track_inode(inode, ret);
+}
+
+struct __track_range_args {
+	ext4_lblk_t start, end;
+};
+
+/* __track_fn for tracking data updates */
+static int __track_range(struct inode *inode, void *arg, bool update)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	ext4_lblk_t oldstart;
+	struct __track_range_args *__arg =
+		(struct __track_range_args *)arg;
+
+	if (inode->i_ino < EXT4_FIRST_INO(inode->i_sb)) {
+		ext4_debug("Special inode %ld being modified\n", inode->i_ino);
+		return -ECANCELED;
+	}
+
+	oldstart = ei->i_fc_lblk_start;
+
+	if (update && ei->i_fc_lblk_len > 0) {
+		ei->i_fc_lblk_start = min(ei->i_fc_lblk_start, __arg->start);
+		ei->i_fc_lblk_len =
+			max(oldstart + ei->i_fc_lblk_len - 1, __arg->end) -
+				ei->i_fc_lblk_start + 1;
+	} else {
+		ei->i_fc_lblk_start = __arg->start;
+		ei->i_fc_lblk_len = __arg->end - __arg->start + 1;
+	}
+
+	return 0;
+}
+
+void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
+			 ext4_lblk_t end)
+{
+	struct __track_range_args args;
+	int ret;
+
+	if (S_ISDIR(inode->i_mode))
+		return;
+
+	args.start = start;
+	args.end = end;
+
+	ret = ext4_fc_track_template(handle, inode,  __track_range, &args, 1);
+
+	trace_ext4_fc_track_range(inode, start, end, ret);
+}
+
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
+{
+	int write_flags = REQ_SYNC;
+	struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
+
+	/* Add REQ_FUA | REQ_PREFLUSH only its tail */
+	if (test_opt(sb, BARRIER) && is_tail)
+		write_flags |= REQ_FUA | REQ_PREFLUSH;
+	lock_buffer(bh);
+	set_buffer_dirty(bh);
+	set_buffer_uptodate(bh);
+	bh->b_end_io = ext4_end_buffer_io_sync;
+	submit_bh(REQ_OP_WRITE, write_flags, bh);
+	EXT4_SB(sb)->s_fc_bh = NULL;
+}
+
+/* Ext4 commit path routines */
+
+/* memzero and update CRC */
+static void *ext4_fc_memzero(struct super_block *sb, void *dst, int len,
+				u32 *crc)
+{
+	void *ret;
+
+	ret = memset(dst, 0, len);
+	if (crc)
+		*crc = ext4_chksum(EXT4_SB(sb), *crc, dst, len);
+	return ret;
+}
+
+/*
+ * Allocate len bytes on a fast commit buffer.
+ *
+ * During the commit time this function is used to manage fast commit
+ * block space. We don't split a fast commit log onto different
+ * blocks. So this function makes sure that if there's not enough space
+ * on the current block, the remaining space in the current block is
+ * marked as unused by adding EXT4_FC_TAG_PAD tag. In that case,
+ * new block is from jbd2 and CRC is updated to reflect the padding
+ * we added.
+ */
+static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
+{
+	struct ext4_fc_tl *tl;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct buffer_head *bh;
+	int bsize = sbi->s_journal->j_blocksize;
+	int ret, off = sbi->s_fc_bytes % bsize;
+	int pad_len;
+
+	/*
+	 * After allocating len, we should have space at least for a 0 byte
+	 * padding.
+	 */
+	if (len + sizeof(struct ext4_fc_tl) > bsize)
+		return NULL;
+
+	if (bsize - off - 1 > len + sizeof(struct ext4_fc_tl)) {
+		/*
+		 * Only allocate from current buffer if we have enough space for
+		 * this request AND we have space to add a zero byte padding.
+		 */
+		if (!sbi->s_fc_bh) {
+			ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
+			if (ret)
+				return NULL;
+			sbi->s_fc_bh = bh;
+		}
+		sbi->s_fc_bytes += len;
+		return sbi->s_fc_bh->b_data + off;
+	}
+	/* Need to add PAD tag */
+	tl = (struct ext4_fc_tl *)(sbi->s_fc_bh->b_data + off);
+	tl->fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD);
+	pad_len = bsize - off - 1 - sizeof(struct ext4_fc_tl);
+	tl->fc_len = cpu_to_le16(pad_len);
+	if (crc)
+		*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
+	if (pad_len > 0)
+		ext4_fc_memzero(sb, tl + 1, pad_len, crc);
+	ext4_fc_submit_bh(sb, false);
+
+	ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
+	if (ret)
+		return NULL;
+	sbi->s_fc_bh = bh;
+	sbi->s_fc_bytes = (sbi->s_fc_bytes / bsize + 1) * bsize + len;
+	return sbi->s_fc_bh->b_data;
+}
+
+/* memcpy to fc reserved space and update CRC */
+static void *ext4_fc_memcpy(struct super_block *sb, void *dst, const void *src,
+				int len, u32 *crc)
+{
+	if (crc)
+		*crc = ext4_chksum(EXT4_SB(sb), *crc, src, len);
+	return memcpy(dst, src, len);
+}
+
+/*
+ * Complete a fast commit by writing tail tag.
+ *
+ * Writing tail tag marks the end of a fast commit. In order to guarantee
+ * atomicity, after writing tail tag, even if there's space remaining
+ * in the block, next commit shouldn't use it. That's why tail tag
+ * has the length as that of the remaining space on the block.
+ */
+static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_tl tl;
+	struct ext4_fc_tail tail;
+	int off, bsize = sbi->s_journal->j_blocksize;
+	u8 *dst;
+
+	/*
+	 * ext4_fc_reserve_space takes care of allocating an extra block if
+	 * there's no enough space on this block for accommodating this tail.
+	 */
+	dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(tail), &crc);
+	if (!dst)
+		return -ENOSPC;
+
+	off = sbi->s_fc_bytes % bsize;
+
+	tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_TAIL);
+	tl.fc_len = cpu_to_le16(bsize - off - 1 + sizeof(struct ext4_fc_tail));
+	sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize);
+
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), &crc);
+	dst += sizeof(tl);
+	tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid);
+	ext4_fc_memcpy(sb, dst, &tail.fc_tid, sizeof(tail.fc_tid), &crc);
+	dst += sizeof(tail.fc_tid);
+	tail.fc_crc = cpu_to_le32(crc);
+	ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
+
+	ext4_fc_submit_bh(sb, true);
+
+	return 0;
+}
+
+/*
+ * Adds tag, length, value and updates CRC. Returns true if tlv was added.
+ * Returns false if there's not enough space.
+ */
+static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val,
+			   u32 *crc)
+{
+	struct ext4_fc_tl tl;
+	u8 *dst;
+
+	dst = ext4_fc_reserve_space(sb, sizeof(tl) + len, crc);
+	if (!dst)
+		return false;
+
+	tl.fc_tag = cpu_to_le16(tag);
+	tl.fc_len = cpu_to_le16(len);
+
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
+	ext4_fc_memcpy(sb, dst + sizeof(tl), val, len, crc);
+
+	return true;
+}
+
+/* Same as above, but adds dentry tlv. */
+static  bool ext4_fc_add_dentry_tlv(struct super_block *sb, u16 tag,
+					int parent_ino, int ino, int dlen,
+					const unsigned char *dname,
+					u32 *crc)
+{
+	struct ext4_fc_dentry_info fcd;
+	struct ext4_fc_tl tl;
+	u8 *dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(fcd) + dlen,
+					crc);
+
+	if (!dst)
+		return false;
+
+	fcd.fc_parent_ino = cpu_to_le32(parent_ino);
+	fcd.fc_ino = cpu_to_le32(ino);
+	tl.fc_tag = cpu_to_le16(tag);
+	tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen);
+	ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
+	dst += sizeof(tl);
+	ext4_fc_memcpy(sb, dst, &fcd, sizeof(fcd), crc);
+	dst += sizeof(fcd);
+	ext4_fc_memcpy(sb, dst, dname, dlen, crc);
+	dst += dlen;
+
+	return true;
+}
+
+/*
+ * Writes inode in the fast commit space under TLV with tag @tag.
+ * Returns 0 on success, error on failure.
+ */
+static int ext4_fc_write_inode(struct inode *inode, u32 *crc)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	int inode_len = EXT4_GOOD_OLD_INODE_SIZE;
+	int ret;
+	struct ext4_iloc iloc;
+	struct ext4_fc_inode fc_inode;
+	struct ext4_fc_tl tl;
+	u8 *dst;
+
+	ret = ext4_get_inode_loc(inode, &iloc);
+	if (ret)
+		return ret;
+
+	if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE)
+		inode_len += ei->i_extra_isize;
+
+	fc_inode.fc_ino = cpu_to_le32(inode->i_ino);
+	tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE);
+	tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino));
+
+	dst = ext4_fc_reserve_space(inode->i_sb,
+			sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc);
+	if (!dst)
+		return -ECANCELED;
+
+	if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc))
+		return -ECANCELED;
+	dst += sizeof(tl);
+	if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc))
+		return -ECANCELED;
+	dst += sizeof(fc_inode);
+	if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc),
+					inode_len, crc))
+		return -ECANCELED;
+
+	return 0;
+}
+
+/*
+ * Writes updated data ranges for the inode in question. Updates CRC.
+ * Returns 0 on success, error otherwise.
+ */
+static int ext4_fc_write_inode_data(struct inode *inode, u32 *crc)
+{
+	ext4_lblk_t old_blk_size, cur_lblk_off, new_blk_size;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_map_blocks map;
+	struct ext4_fc_add_range fc_ext;
+	struct ext4_fc_del_range lrange;
+	struct ext4_extent *ex;
+	int ret;
+
+	mutex_lock(&ei->i_fc_lock);
+	if (ei->i_fc_lblk_len == 0) {
+		mutex_unlock(&ei->i_fc_lock);
+		return 0;
+	}
+	old_blk_size = ei->i_fc_lblk_start;
+	new_blk_size = ei->i_fc_lblk_start + ei->i_fc_lblk_len - 1;
+	ei->i_fc_lblk_len = 0;
+	mutex_unlock(&ei->i_fc_lock);
+
+	cur_lblk_off = old_blk_size;
+	jbd_debug(1, "%s: will try writing %d to %d for inode %ld\n",
+		  __func__, cur_lblk_off, new_blk_size, inode->i_ino);
+
+	while (cur_lblk_off <= new_blk_size) {
+		map.m_lblk = cur_lblk_off;
+		map.m_len = new_blk_size - cur_lblk_off + 1;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0)
+			return -ECANCELED;
+
+		if (map.m_len == 0) {
+			cur_lblk_off++;
+			continue;
+		}
+
+		if (ret == 0) {
+			lrange.fc_ino = cpu_to_le32(inode->i_ino);
+			lrange.fc_lblk = cpu_to_le32(map.m_lblk);
+			lrange.fc_len = cpu_to_le32(map.m_len);
+			if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_DEL_RANGE,
+					    sizeof(lrange), (u8 *)&lrange, crc))
+				return -ENOSPC;
+		} else {
+			fc_ext.fc_ino = cpu_to_le32(inode->i_ino);
+			ex = (struct ext4_extent *)&fc_ext.fc_ex;
+			ex->ee_block = cpu_to_le32(map.m_lblk);
+			ex->ee_len = cpu_to_le16(map.m_len);
+			ext4_ext_store_pblock(ex, map.m_pblk);
+			if (map.m_flags & EXT4_MAP_UNWRITTEN)
+				ext4_ext_mark_unwritten(ex);
+			else
+				ext4_ext_mark_initialized(ex);
+			if (!ext4_fc_add_tlv(inode->i_sb, EXT4_FC_TAG_ADD_RANGE,
+					    sizeof(fc_ext), (u8 *)&fc_ext, crc))
+				return -ENOSPC;
+		}
+
+		cur_lblk_off += map.m_len;
+	}
+
+	return 0;
+}
+
+
+/* Submit data for all the fast commit inodes */
+static int ext4_fc_submit_inode_data_all(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *ei;
+	struct list_head *pos;
+	int ret = 0;
+
+	spin_lock(&sbi->s_fc_lock);
+	ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
+		ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
+		while (atomic_read(&ei->i_fc_updates)) {
+			DEFINE_WAIT(wait);
+
+			prepare_to_wait(&ei->i_fc_wait, &wait,
+						TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&ei->i_fc_updates)) {
+				spin_unlock(&sbi->s_fc_lock);
+				schedule();
+				spin_lock(&sbi->s_fc_lock);
+			}
+			finish_wait(&ei->i_fc_wait, &wait);
+		}
+		spin_unlock(&sbi->s_fc_lock);
+		ret = jbd2_submit_inode_data(ei->jinode);
+		if (ret)
+			return ret;
+		spin_lock(&sbi->s_fc_lock);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	return ret;
+}
+
+/* Wait for completion of data for all the fast commit inodes */
+static int ext4_fc_wait_inode_data_all(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *pos, *n;
+	int ret = 0;
+
+	spin_lock(&sbi->s_fc_lock);
+	list_for_each_entry_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
+		if (!ext4_test_inode_state(&pos->vfs_inode,
+					   EXT4_STATE_FC_COMMITTING))
+			continue;
+		spin_unlock(&sbi->s_fc_lock);
+
+		ret = jbd2_wait_inode_data(journal, pos->jinode);
+		if (ret)
+			return ret;
+		spin_lock(&sbi->s_fc_lock);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	return 0;
+}
+
+/* Commit all the directory entry updates */
+static int ext4_fc_commit_dentry_updates(journal_t *journal, u32 *crc)
+__acquires(&sbi->s_fc_lock)
+__releases(&sbi->s_fc_lock)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_dentry_update *fc_dentry;
+	struct inode *inode;
+	struct list_head *pos, *n, *fcd_pos, *fcd_n;
+	struct ext4_inode_info *ei;
+	int ret;
+
+	if (list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN]))
+		return 0;
+	list_for_each_safe(fcd_pos, fcd_n, &sbi->s_fc_dentry_q[FC_Q_MAIN]) {
+		fc_dentry = list_entry(fcd_pos, struct ext4_fc_dentry_update,
+					fcd_list);
+		if (fc_dentry->fcd_op != EXT4_FC_TAG_CREAT) {
+			spin_unlock(&sbi->s_fc_lock);
+			if (!ext4_fc_add_dentry_tlv(
+				sb, fc_dentry->fcd_op,
+				fc_dentry->fcd_parent, fc_dentry->fcd_ino,
+				fc_dentry->fcd_name.len,
+				fc_dentry->fcd_name.name, crc)) {
+				ret = -ENOSPC;
+				goto lock_and_exit;
+			}
+			spin_lock(&sbi->s_fc_lock);
+			continue;
+		}
+
+		inode = NULL;
+		list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) {
+			ei = list_entry(pos, struct ext4_inode_info, i_fc_list);
+			if (ei->vfs_inode.i_ino == fc_dentry->fcd_ino) {
+				inode = &ei->vfs_inode;
+				break;
+			}
+		}
+		/*
+		 * If we don't find inode in our list, then it was deleted,
+		 * in which case, we don't need to record it's create tag.
+		 */
+		if (!inode)
+			continue;
+		spin_unlock(&sbi->s_fc_lock);
+
+		/*
+		 * We first write the inode and then the create dirent. This
+		 * allows the recovery code to create an unnamed inode first
+		 * and then link it to a directory entry. This allows us
+		 * to use namei.c routines almost as is and simplifies
+		 * the recovery code.
+		 */
+		ret = ext4_fc_write_inode(inode, crc);
+		if (ret)
+			goto lock_and_exit;
+
+		ret = ext4_fc_write_inode_data(inode, crc);
+		if (ret)
+			goto lock_and_exit;
+
+		if (!ext4_fc_add_dentry_tlv(
+			sb, fc_dentry->fcd_op,
+			fc_dentry->fcd_parent, fc_dentry->fcd_ino,
+			fc_dentry->fcd_name.len,
+			fc_dentry->fcd_name.name, crc)) {
+			ret = -ENOSPC;
+			goto lock_and_exit;
+		}
+
+		spin_lock(&sbi->s_fc_lock);
+	}
+	return 0;
+lock_and_exit:
+	spin_lock(&sbi->s_fc_lock);
+	return ret;
+}
+
+static int ext4_fc_perform_commit(journal_t *journal)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *iter;
+	struct ext4_fc_head head;
+	struct list_head *pos;
+	struct inode *inode;
+	struct blk_plug plug;
+	int ret = 0;
+	u32 crc = 0;
+
+	ret = ext4_fc_submit_inode_data_all(journal);
+	if (ret)
+		return ret;
+
+	ret = ext4_fc_wait_inode_data_all(journal);
+	if (ret)
+		return ret;
+
+	/*
+	 * If file system device is different from journal device, issue a cache
+	 * flush before we start writing fast commit blocks.
+	 */
+	if (journal->j_fs_dev != journal->j_dev)
+		blkdev_issue_flush(journal->j_fs_dev, GFP_NOFS, NULL);
+
+	blk_start_plug(&plug);
+	if (sbi->s_fc_bytes == 0) {
+		/*
+		 * Add a head tag only if this is the first fast commit
+		 * in this TID.
+		 */
+		head.fc_features = cpu_to_le32(EXT4_FC_SUPPORTED_FEATURES);
+		head.fc_tid = cpu_to_le32(
+			sbi->s_journal->j_running_transaction->t_tid);
+		if (!ext4_fc_add_tlv(sb, EXT4_FC_TAG_HEAD, sizeof(head),
+			(u8 *)&head, &crc))
+			goto out;
+	}
+
+	spin_lock(&sbi->s_fc_lock);
+	ret = ext4_fc_commit_dentry_updates(journal, &crc);
+	if (ret) {
+		spin_unlock(&sbi->s_fc_lock);
+		goto out;
+	}
+
+	list_for_each(pos, &sbi->s_fc_q[FC_Q_MAIN]) {
+		iter = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		inode = &iter->vfs_inode;
+		if (!ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING))
+			continue;
+
+		spin_unlock(&sbi->s_fc_lock);
+		ret = ext4_fc_write_inode_data(inode, &crc);
+		if (ret)
+			goto out;
+		ret = ext4_fc_write_inode(inode, &crc);
+		if (ret)
+			goto out;
+		spin_lock(&sbi->s_fc_lock);
+	}
+	spin_unlock(&sbi->s_fc_lock);
+
+	ret = ext4_fc_write_tail(sb, crc);
+
+out:
+	blk_finish_plug(&plug);
+	return ret;
+}
+
+/*
+ * The main commit entry point. Performs a fast commit for transaction
+ * commit_tid if needed. If it's not possible to perform a fast commit
+ * due to various reasons, we fall back to full commit. Returns 0
+ * on success, error otherwise.
+ */
+int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
+{
+	struct super_block *sb = (struct super_block *)(journal->j_private);
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int nblks = 0, ret, bsize = journal->j_blocksize;
+	int subtid = atomic_read(&sbi->s_fc_subtid);
+	int reason = EXT4_FC_REASON_OK, fc_bufs_before = 0;
+	ktime_t start_time, commit_time;
+
+	trace_ext4_fc_commit_start(sb);
+
+	start_time = ktime_get();
+
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+		(ext4_fc_is_ineligible(sb))) {
+		reason = EXT4_FC_REASON_INELIGIBLE;
+		goto out;
+	}
+
+restart_fc:
+	ret = jbd2_fc_begin_commit(journal, commit_tid);
+	if (ret == -EALREADY) {
+		/* There was an ongoing commit, check if we need to restart */
+		if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
+			commit_tid > journal->j_commit_sequence)
+			goto restart_fc;
+		reason = EXT4_FC_REASON_ALREADY_COMMITTED;
+		goto out;
+	} else if (ret) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_START_FAILED;
+		goto out;
+	}
+
+	fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize;
+	ret = ext4_fc_perform_commit(journal);
+	if (ret < 0) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_FAILED;
+		goto out;
+	}
+	nblks = (sbi->s_fc_bytes + bsize - 1) / bsize - fc_bufs_before;
+	ret = jbd2_fc_wait_bufs(journal, nblks);
+	if (ret < 0) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_FC_FAILED;
+		goto out;
+	}
+	atomic_inc(&sbi->s_fc_subtid);
+	jbd2_fc_end_commit(journal);
+out:
+	/* Has any ineligible update happened since we started? */
+	if (reason == EXT4_FC_REASON_OK && ext4_fc_is_ineligible(sb)) {
+		sbi->s_fc_stats.fc_ineligible_reason_count[EXT4_FC_COMMIT_FAILED]++;
+		reason = EXT4_FC_REASON_INELIGIBLE;
+	}
+
+	spin_lock(&sbi->s_fc_lock);
+	if (reason != EXT4_FC_REASON_OK &&
+		reason != EXT4_FC_REASON_ALREADY_COMMITTED) {
+		sbi->s_fc_stats.fc_ineligible_commits++;
+	} else {
+		sbi->s_fc_stats.fc_num_commits++;
+		sbi->s_fc_stats.fc_numblks += nblks;
+	}
+	spin_unlock(&sbi->s_fc_lock);
+	nblks = (reason == EXT4_FC_REASON_OK) ? nblks : 0;
+	trace_ext4_fc_commit_stop(sb, nblks, reason);
+	commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+	/*
+	 * weight the commit time higher than the average time so we don't
+	 * react too strongly to vast changes in the commit time
+	 */
+	if (likely(sbi->s_fc_avg_commit_time))
+		sbi->s_fc_avg_commit_time = (commit_time +
+				sbi->s_fc_avg_commit_time * 3) / 4;
+	else
+		sbi->s_fc_avg_commit_time = commit_time;
+	jbd_debug(1,
+		"Fast commit ended with blks = %d, reason = %d, subtid - %d",
+		nblks, reason, subtid);
+	if (reason == EXT4_FC_REASON_FC_FAILED)
+		return jbd2_fc_end_commit_fallback(journal);
+	if (reason == EXT4_FC_REASON_FC_START_FAILED ||
+		reason == EXT4_FC_REASON_INELIGIBLE)
+		return jbd2_complete_transaction(journal, commit_tid);
+	return 0;
+}
+
+/*
+ * Fast commit cleanup routine. This is called after every fast commit and
+ * full commit. full is true if we are called after a full commit.
+ */
+static void ext4_fc_cleanup(journal_t *journal, int full)
+{
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_inode_info *iter;
+	struct ext4_fc_dentry_update *fc_dentry;
+	struct list_head *pos, *n;
+
+	if (full && sbi->s_fc_bh)
+		sbi->s_fc_bh = NULL;
+
+	jbd2_fc_release_bufs(journal);
+
+	spin_lock(&sbi->s_fc_lock);
+	list_for_each_safe(pos, n, &sbi->s_fc_q[FC_Q_MAIN]) {
+		iter = list_entry(pos, struct ext4_inode_info, i_fc_list);
+		list_del_init(&iter->i_fc_list);
+		ext4_clear_inode_state(&iter->vfs_inode,
+				       EXT4_STATE_FC_COMMITTING);
+		ext4_fc_reset_inode(&iter->vfs_inode);
+		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
+		smp_mb();
+#if (BITS_PER_LONG < 64)
+		wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_COMMITTING);
+#else
+		wake_up_bit(&iter->i_flags, EXT4_STATE_FC_COMMITTING);
+#endif
+	}
+
+	while (!list_empty(&sbi->s_fc_dentry_q[FC_Q_MAIN])) {
+		fc_dentry = list_first_entry(&sbi->s_fc_dentry_q[FC_Q_MAIN],
+					     struct ext4_fc_dentry_update,
+					     fcd_list);
+		list_del_init(&fc_dentry->fcd_list);
+		spin_unlock(&sbi->s_fc_lock);
+
+		if (fc_dentry->fcd_name.name &&
+			fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
+			kfree(fc_dentry->fcd_name.name);
+		kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
+		spin_lock(&sbi->s_fc_lock);
+	}
+
+	list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
+				&sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
+				&sbi->s_fc_q[FC_Q_MAIN]);
+
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+
+	if (full)
+		sbi->s_fc_bytes = 0;
+	spin_unlock(&sbi->s_fc_lock);
+	trace_ext4_fc_stats(sb);
+}
+
+/* Ext4 Replay Path Routines */
+
+/* Helper struct for dentry replay routines */
+struct dentry_info_args {
+	int parent_ino, dname_len, ino, inode_len;
+	char *dname;
+};
+
+static inline void tl_to_darg(struct dentry_info_args *darg,
+				struct  ext4_fc_tl *tl)
+{
+	struct ext4_fc_dentry_info *fcd;
+
+	fcd = (struct ext4_fc_dentry_info *)ext4_fc_tag_val(tl);
+
+	darg->parent_ino = le32_to_cpu(fcd->fc_parent_ino);
+	darg->ino = le32_to_cpu(fcd->fc_ino);
+	darg->dname = fcd->fc_dname;
+	darg->dname_len = ext4_fc_tag_len(tl) -
+			sizeof(struct ext4_fc_dentry_info);
+}
+
+/* Unlink replay function */
+static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode, *old_parent;
+	struct qstr entry;
+	struct dentry_info_args darg;
+	int ret = 0;
+
+	tl_to_darg(&darg, tl);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_UNLINK, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	entry.name = darg.dname;
+	entry.len = darg.dname_len;
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "Inode %d not found", darg.ino);
+		return 0;
+	}
+
+	old_parent = ext4_iget(sb, darg.parent_ino,
+				EXT4_IGET_NORMAL);
+	if (IS_ERR(old_parent)) {
+		jbd_debug(1, "Dir with inode  %d not found", darg.parent_ino);
+		iput(inode);
+		return 0;
+	}
+
+	ret = __ext4_unlink(NULL, old_parent, &entry, inode);
+	/* -ENOENT ok coz it might not exist anymore. */
+	if (ret == -ENOENT)
+		ret = 0;
+	iput(old_parent);
+	iput(inode);
+	return ret;
+}
+
+static int ext4_fc_replay_link_internal(struct super_block *sb,
+				struct dentry_info_args *darg,
+				struct inode *inode)
+{
+	struct inode *dir = NULL;
+	struct dentry *dentry_dir = NULL, *dentry_inode = NULL;
+	struct qstr qstr_dname = QSTR_INIT(darg->dname, darg->dname_len);
+	int ret = 0;
+
+	dir = ext4_iget(sb, darg->parent_ino, EXT4_IGET_NORMAL);
+	if (IS_ERR(dir)) {
+		jbd_debug(1, "Dir with inode %d not found.", darg->parent_ino);
+		dir = NULL;
+		goto out;
+	}
+
+	dentry_dir = d_obtain_alias(dir);
+	if (IS_ERR(dentry_dir)) {
+		jbd_debug(1, "Failed to obtain dentry");
+		dentry_dir = NULL;
+		goto out;
+	}
+
+	dentry_inode = d_alloc(dentry_dir, &qstr_dname);
+	if (!dentry_inode) {
+		jbd_debug(1, "Inode dentry not created.");
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = __ext4_link(dir, inode, dentry_inode);
+	/*
+	 * It's possible that link already existed since data blocks
+	 * for the dir in question got persisted before we crashed OR
+	 * we replayed this tag and crashed before the entire replay
+	 * could complete.
+	 */
+	if (ret && ret != -EEXIST) {
+		jbd_debug(1, "Failed to link\n");
+		goto out;
+	}
+
+	ret = 0;
+out:
+	if (dentry_dir) {
+		d_drop(dentry_dir);
+		dput(dentry_dir);
+	} else if (dir) {
+		iput(dir);
+	}
+	if (dentry_inode) {
+		d_drop(dentry_inode);
+		dput(dentry_inode);
+	}
+
+	return ret;
+}
+
+/* Link replay function */
+static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode;
+	struct dentry_info_args darg;
+	int ret = 0;
+
+	tl_to_darg(&darg, tl);
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_LINK, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return 0;
+	}
+
+	ret = ext4_fc_replay_link_internal(sb, &darg, inode);
+	iput(inode);
+	return ret;
+}
+
+/*
+ * Record all the modified inodes during replay. We use this later to setup
+ * block bitmaps correctly.
+ */
+static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
+{
+	struct ext4_fc_replay_state *state;
+	int i;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_modified_inodes_used; i++)
+		if (state->fc_modified_inodes[i] == ino)
+			return 0;
+	if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
+		state->fc_modified_inodes_size +=
+			EXT4_FC_REPLAY_REALLOC_INCREMENT;
+		state->fc_modified_inodes = krealloc(
+					state->fc_modified_inodes, sizeof(int) *
+					state->fc_modified_inodes_size,
+					GFP_KERNEL);
+		if (!state->fc_modified_inodes)
+			return -ENOMEM;
+	}
+	state->fc_modified_inodes[state->fc_modified_inodes_used++] = ino;
+	return 0;
+}
+
+/*
+ * Inode replay function
+ */
+static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct ext4_fc_inode *fc_inode;
+	struct ext4_inode *raw_inode;
+	struct ext4_inode *raw_fc_inode;
+	struct inode *inode = NULL;
+	struct ext4_iloc iloc;
+	int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag);
+	struct ext4_extent_header *eh;
+
+	fc_inode = (struct ext4_fc_inode *)ext4_fc_tag_val(tl);
+
+	ino = le32_to_cpu(fc_inode->fc_ino);
+	trace_ext4_fc_replay(sb, tag, ino, 0, 0);
+
+	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
+	if (!IS_ERR(inode)) {
+		ext4_ext_clear_bb(inode);
+		iput(inode);
+	}
+	inode = NULL;
+
+	ext4_fc_record_modified_inode(sb, ino);
+
+	raw_fc_inode = (struct ext4_inode *)fc_inode->fc_raw_inode;
+	ret = ext4_get_fc_inode_loc(sb, ino, &iloc);
+	if (ret)
+		goto out;
+
+	inode_len = ext4_fc_tag_len(tl) - sizeof(struct ext4_fc_inode);
+	raw_inode = ext4_raw_inode(&iloc);
+
+	memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
+	memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation,
+		inode_len - offsetof(struct ext4_inode, i_generation));
+	if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) {
+		eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]);
+		if (eh->eh_magic != EXT4_EXT_MAGIC) {
+			memset(eh, 0, sizeof(*eh));
+			eh->eh_magic = EXT4_EXT_MAGIC;
+			eh->eh_max = cpu_to_le16(
+				(sizeof(raw_inode->i_block) -
+				 sizeof(struct ext4_extent_header))
+				 / sizeof(struct ext4_extent));
+		}
+	} else if (le32_to_cpu(raw_inode->i_flags) & EXT4_INLINE_DATA_FL) {
+		memcpy(raw_inode->i_block, raw_fc_inode->i_block,
+			sizeof(raw_inode->i_block));
+	}
+
+	/* Immediately update the inode on disk. */
+	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
+	if (ret)
+		goto out;
+	ret = sync_dirty_buffer(iloc.bh);
+	if (ret)
+		goto out;
+	ret = ext4_mark_inode_used(sb, ino);
+	if (ret)
+		goto out;
+
+	/* Given that we just wrote the inode on disk, this SHOULD succeed. */
+	inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Our allocator could have made different decisions than before
+	 * crashing. This should be fixed but until then, we calculate
+	 * the number of blocks the inode.
+	 */
+	ext4_ext_replay_set_iblocks(inode);
+
+	inode->i_generation = le32_to_cpu(ext4_raw_inode(&iloc)->i_generation);
+	ext4_reset_inode_seed(inode);
+
+	ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode));
+	ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh);
+	sync_dirty_buffer(iloc.bh);
+	brelse(iloc.bh);
+out:
+	iput(inode);
+	if (!ret)
+		blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL);
+
+	return 0;
+}
+
+/*
+ * Dentry create replay function.
+ *
+ * EXT4_FC_TAG_CREAT is preceded by EXT4_FC_TAG_INODE_FULL. Which means, the
+ * inode for which we are trying to create a dentry here, should already have
+ * been replayed before we start here.
+ */
+static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	int ret = 0;
+	struct inode *inode = NULL;
+	struct inode *dir = NULL;
+	struct dentry_info_args darg;
+
+	tl_to_darg(&darg, tl);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_CREAT, darg.ino,
+			darg.parent_ino, darg.dname_len);
+
+	/* This takes care of update group descriptor and other metadata */
+	ret = ext4_mark_inode_used(sb, darg.ino);
+	if (ret)
+		goto out;
+
+	inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "inode %d not found.", darg.ino);
+		inode = NULL;
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (S_ISDIR(inode->i_mode)) {
+		/*
+		 * If we are creating a directory, we need to make sure that the
+		 * dot and dot dot dirents are setup properly.
+		 */
+		dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
+		if (IS_ERR(dir)) {
+			jbd_debug(1, "Dir %d not found.", darg.ino);
+			goto out;
+		}
+		ret = ext4_init_new_dir(NULL, dir, inode);
+		iput(dir);
+		if (ret) {
+			ret = 0;
+			goto out;
+		}
+	}
+	ret = ext4_fc_replay_link_internal(sb, &darg, inode);
+	if (ret)
+		goto out;
+	set_nlink(inode, 1);
+	ext4_mark_inode_dirty(NULL, inode);
+out:
+	if (inode)
+		iput(inode);
+	return ret;
+}
+
+/*
+ * Record physical disk regions which are in use as per fast commit area. Our
+ * simple replay phase allocator excludes these regions from allocation.
+ */
+static int ext4_fc_record_regions(struct super_block *sb, int ino,
+		ext4_lblk_t lblk, ext4_fsblk_t pblk, int len)
+{
+	struct ext4_fc_replay_state *state;
+	struct ext4_fc_alloc_region *region;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	if (state->fc_regions_used == state->fc_regions_size) {
+		state->fc_regions_size +=
+			EXT4_FC_REPLAY_REALLOC_INCREMENT;
+		state->fc_regions = krealloc(
+					state->fc_regions,
+					state->fc_regions_size *
+					sizeof(struct ext4_fc_alloc_region),
+					GFP_KERNEL);
+		if (!state->fc_regions)
+			return -ENOMEM;
+	}
+	region = &state->fc_regions[state->fc_regions_used++];
+	region->ino = ino;
+	region->lblk = lblk;
+	region->pblk = pblk;
+	region->len = len;
+
+	return 0;
+}
+
+/* Replay add range tag */
+static int ext4_fc_replay_add_range(struct super_block *sb,
+				struct ext4_fc_tl *tl)
+{
+	struct ext4_fc_add_range *fc_add_ex;
+	struct ext4_extent newex, *ex;
+	struct inode *inode;
+	ext4_lblk_t start, cur;
+	int remaining, len;
+	ext4_fsblk_t start_pblk;
+	struct ext4_map_blocks map;
+	struct ext4_ext_path *path = NULL;
+	int ret;
+
+	fc_add_ex = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
+	ex = (struct ext4_extent *)&fc_add_ex->fc_ex;
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_ADD_RANGE,
+		le32_to_cpu(fc_add_ex->fc_ino), le32_to_cpu(ex->ee_block),
+		ext4_ext_get_actual_len(ex));
+
+	inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
+				EXT4_IGET_NORMAL);
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "Inode not found.");
+		return 0;
+	}
+
+	ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+
+	start = le32_to_cpu(ex->ee_block);
+	start_pblk = ext4_ext_pblock(ex);
+	len = ext4_ext_get_actual_len(ex);
+
+	cur = start;
+	remaining = len;
+	jbd_debug(1, "ADD_RANGE, lblk %d, pblk %lld, len %d, unwritten %d, inode %ld\n",
+		  start, start_pblk, len, ext4_ext_is_unwritten(ex),
+		  inode->i_ino);
+
+	while (remaining > 0) {
+		map.m_lblk = cur;
+		map.m_len = remaining;
+		map.m_pblk = 0;
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+
+		if (ret < 0) {
+			iput(inode);
+			return 0;
+		}
+
+		if (ret == 0) {
+			/* Range is not mapped */
+			path = ext4_find_extent(inode, cur, NULL, 0);
+			if (IS_ERR(path)) {
+				iput(inode);
+				return 0;
+			}
+			memset(&newex, 0, sizeof(newex));
+			newex.ee_block = cpu_to_le32(cur);
+			ext4_ext_store_pblock(
+				&newex, start_pblk + cur - start);
+			newex.ee_len = cpu_to_le16(map.m_len);
+			if (ext4_ext_is_unwritten(ex))
+				ext4_ext_mark_unwritten(&newex);
+			down_write(&EXT4_I(inode)->i_data_sem);
+			ret = ext4_ext_insert_extent(
+				NULL, inode, &path, &newex, 0);
+			up_write((&EXT4_I(inode)->i_data_sem));
+			ext4_ext_drop_refs(path);
+			kfree(path);
+			if (ret) {
+				iput(inode);
+				return 0;
+			}
+			goto next;
+		}
+
+		if (start_pblk + cur - start != map.m_pblk) {
+			/*
+			 * Logical to physical mapping changed. This can happen
+			 * if this range was removed and then reallocated to
+			 * map to new physical blocks during a fast commit.
+			 */
+			ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
+					ext4_ext_is_unwritten(ex),
+					start_pblk + cur - start);
+			if (ret) {
+				iput(inode);
+				return 0;
+			}
+			/*
+			 * Mark the old blocks as free since they aren't used
+			 * anymore. We maintain an array of all the modified
+			 * inodes. In case these blocks are still used at either
+			 * a different logical range in the same inode or in
+			 * some different inode, we will mark them as allocated
+			 * at the end of the FC replay using our array of
+			 * modified inodes.
+			 */
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+			goto next;
+		}
+
+		/* Range is mapped and needs a state change */
+		jbd_debug(1, "Converting from %d to %d %lld",
+				map.m_flags & EXT4_MAP_UNWRITTEN,
+			ext4_ext_is_unwritten(ex), map.m_pblk);
+		ret = ext4_ext_replay_update_ex(inode, cur, map.m_len,
+					ext4_ext_is_unwritten(ex), map.m_pblk);
+		if (ret) {
+			iput(inode);
+			return 0;
+		}
+		/*
+		 * We may have split the extent tree while toggling the state.
+		 * Try to shrink the extent tree now.
+		 */
+		ext4_ext_replay_shrink_inode(inode, start + len);
+next:
+		cur += map.m_len;
+		remaining -= map.m_len;
+	}
+	ext4_ext_replay_shrink_inode(inode, i_size_read(inode) >>
+					sb->s_blocksize_bits);
+	iput(inode);
+	return 0;
+}
+
+/* Replay DEL_RANGE tag */
+static int
+ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
+{
+	struct inode *inode;
+	struct ext4_fc_del_range *lrange;
+	struct ext4_map_blocks map;
+	ext4_lblk_t cur, remaining;
+	int ret;
+
+	lrange = (struct ext4_fc_del_range *)ext4_fc_tag_val(tl);
+	cur = le32_to_cpu(lrange->fc_lblk);
+	remaining = le32_to_cpu(lrange->fc_len);
+
+	trace_ext4_fc_replay(sb, EXT4_FC_TAG_DEL_RANGE,
+		le32_to_cpu(lrange->fc_ino), cur, remaining);
+
+	inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
+	if (IS_ERR(inode)) {
+		jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
+		return 0;
+	}
+
+	ret = ext4_fc_record_modified_inode(sb, inode->i_ino);
+
+	jbd_debug(1, "DEL_RANGE, inode %ld, lblk %d, len %d\n",
+			inode->i_ino, le32_to_cpu(lrange->fc_lblk),
+			le32_to_cpu(lrange->fc_len));
+	while (remaining > 0) {
+		map.m_lblk = cur;
+		map.m_len = remaining;
+
+		ret = ext4_map_blocks(NULL, inode, &map, 0);
+		if (ret < 0) {
+			iput(inode);
+			return 0;
+		}
+		if (ret > 0) {
+			remaining -= ret;
+			cur += ret;
+			ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
+		} else {
+			remaining -= map.m_len;
+			cur += map.m_len;
+		}
+	}
+
+	ret = ext4_punch_hole(inode,
+		le32_to_cpu(lrange->fc_lblk) << sb->s_blocksize_bits,
+		le32_to_cpu(lrange->fc_len) <<  sb->s_blocksize_bits);
+	if (ret)
+		jbd_debug(1, "ext4_punch_hole returned %d", ret);
+	ext4_ext_replay_shrink_inode(inode,
+		i_size_read(inode) >> sb->s_blocksize_bits);
+	ext4_mark_inode_dirty(NULL, inode);
+	iput(inode);
+
+	return 0;
+}
+
+static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
+{
+	struct ext4_fc_replay_state *state;
+	struct inode *inode;
+	struct ext4_ext_path *path = NULL;
+	struct ext4_map_blocks map;
+	int i, ret, j;
+	ext4_lblk_t cur, end;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_modified_inodes_used; i++) {
+		inode = ext4_iget(sb, state->fc_modified_inodes[i],
+			EXT4_IGET_NORMAL);
+		if (IS_ERR(inode)) {
+			jbd_debug(1, "Inode %d not found.",
+				state->fc_modified_inodes[i]);
+			continue;
+		}
+		cur = 0;
+		end = EXT_MAX_BLOCKS;
+		while (cur < end) {
+			map.m_lblk = cur;
+			map.m_len = end - cur;
+
+			ret = ext4_map_blocks(NULL, inode, &map, 0);
+			if (ret < 0)
+				break;
+
+			if (ret > 0) {
+				path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
+				if (!IS_ERR(path)) {
+					for (j = 0; j < path->p_depth; j++)
+						ext4_mb_mark_bb(inode->i_sb,
+							path[j].p_block, 1, 1);
+					ext4_ext_drop_refs(path);
+					kfree(path);
+				}
+				cur += ret;
+				ext4_mb_mark_bb(inode->i_sb, map.m_pblk,
+							map.m_len, 1);
+			} else {
+				cur = cur + (map.m_len ? map.m_len : 1);
+			}
+		}
+		iput(inode);
+	}
+}
+
+/*
+ * Check if block is in excluded regions for block allocation. The simple
+ * allocator that runs during replay phase is calls this function to see
+ * if it is okay to use a block.
+ */
+bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t blk)
+{
+	int i;
+	struct ext4_fc_replay_state *state;
+
+	state = &EXT4_SB(sb)->s_fc_replay_state;
+	for (i = 0; i < state->fc_regions_valid; i++) {
+		if (state->fc_regions[i].ino == 0 ||
+			state->fc_regions[i].len == 0)
+			continue;
+		if (blk >= state->fc_regions[i].pblk &&
+		    blk < state->fc_regions[i].pblk + state->fc_regions[i].len)
+			return true;
+	}
+	return false;
+}
+
+/* Cleanup function called after replay */
+void ext4_fc_replay_cleanup(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+	sbi->s_mount_state &= ~EXT4_FC_REPLAY;
+	kfree(sbi->s_fc_replay_state.fc_regions);
+	kfree(sbi->s_fc_replay_state.fc_modified_inodes);
+}
+
+/*
+ * Recovery Scan phase handler
+ *
+ * This function is called during the scan phase and is responsible
+ * for doing following things:
+ * - Make sure the fast commit area has valid tags for replay
+ * - Count number of tags that need to be replayed by the replay handler
+ * - Verify CRC
+ * - Create a list of excluded blocks for allocation during replay phase
+ *
+ * This function returns JBD2_FC_REPLAY_CONTINUE to indicate that SCAN is
+ * incomplete and JBD2 should send more blocks. It returns JBD2_FC_REPLAY_STOP
+ * to indicate that scan has finished and JBD2 can now start replay phase.
+ * It returns a negative error to indicate that there was an error. At the end
+ * of a successful scan phase, sbi->s_fc_replay_state.fc_replay_num_tags is set
+ * to indicate the number of tags that need to replayed during the replay phase.
+ */
+static int ext4_fc_replay_scan(journal_t *journal,
+				struct buffer_head *bh, int off,
+				tid_t expected_tid)
+{
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_replay_state *state;
+	int ret = JBD2_FC_REPLAY_CONTINUE;
+	struct ext4_fc_add_range *ext;
+	struct ext4_fc_tl *tl;
+	struct ext4_fc_tail *tail;
+	__u8 *start, *end;
+	struct ext4_fc_head *head;
+	struct ext4_extent *ex;
+
+	state = &sbi->s_fc_replay_state;
+
+	start = (u8 *)bh->b_data;
+	end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
+
+	if (state->fc_replay_expected_off == 0) {
+		state->fc_cur_tag = 0;
+		state->fc_replay_num_tags = 0;
+		state->fc_crc = 0;
+		state->fc_regions = NULL;
+		state->fc_regions_valid = state->fc_regions_used =
+			state->fc_regions_size = 0;
+		/* Check if we can stop early */
+		if (le16_to_cpu(((struct ext4_fc_tl *)start)->fc_tag)
+			!= EXT4_FC_TAG_HEAD)
+			return 0;
+	}
+
+	if (off != state->fc_replay_expected_off) {
+		ret = -EFSCORRUPTED;
+		goto out_err;
+	}
+
+	state->fc_replay_expected_off++;
+	fc_for_each_tl(start, end, tl) {
+		jbd_debug(3, "Scan phase, tag:%s, blk %lld\n",
+			  tag2str(le16_to_cpu(tl->fc_tag)), bh->b_blocknr);
+		switch (le16_to_cpu(tl->fc_tag)) {
+		case EXT4_FC_TAG_ADD_RANGE:
+			ext = (struct ext4_fc_add_range *)ext4_fc_tag_val(tl);
+			ex = (struct ext4_extent *)&ext->fc_ex;
+			ret = ext4_fc_record_regions(sb,
+				le32_to_cpu(ext->fc_ino),
+				le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex),
+				ext4_ext_get_actual_len(ex));
+			if (ret < 0)
+				break;
+			ret = JBD2_FC_REPLAY_CONTINUE;
+			fallthrough;
+		case EXT4_FC_TAG_DEL_RANGE:
+		case EXT4_FC_TAG_LINK:
+		case EXT4_FC_TAG_UNLINK:
+		case EXT4_FC_TAG_CREAT:
+		case EXT4_FC_TAG_INODE:
+		case EXT4_FC_TAG_PAD:
+			state->fc_cur_tag++;
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+					sizeof(*tl) + ext4_fc_tag_len(tl));
+			break;
+		case EXT4_FC_TAG_TAIL:
+			state->fc_cur_tag++;
+			tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+						sizeof(*tl) +
+						offsetof(struct ext4_fc_tail,
+						fc_crc));
+			if (le32_to_cpu(tail->fc_tid) == expected_tid &&
+				le32_to_cpu(tail->fc_crc) == state->fc_crc) {
+				state->fc_replay_num_tags = state->fc_cur_tag;
+				state->fc_regions_valid =
+					state->fc_regions_used;
+			} else {
+				ret = state->fc_replay_num_tags ?
+					JBD2_FC_REPLAY_STOP : -EFSBADCRC;
+			}
+			state->fc_crc = 0;
+			break;
+		case EXT4_FC_TAG_HEAD:
+			head = (struct ext4_fc_head *)ext4_fc_tag_val(tl);
+			if (le32_to_cpu(head->fc_features) &
+				~EXT4_FC_SUPPORTED_FEATURES) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
+			if (le32_to_cpu(head->fc_tid) != expected_tid) {
+				ret = JBD2_FC_REPLAY_STOP;
+				break;
+			}
+			state->fc_cur_tag++;
+			state->fc_crc = ext4_chksum(sbi, state->fc_crc, tl,
+					sizeof(*tl) + ext4_fc_tag_len(tl));
+			break;
+		default:
+			ret = state->fc_replay_num_tags ?
+				JBD2_FC_REPLAY_STOP : -ECANCELED;
+		}
+		if (ret < 0 || ret == JBD2_FC_REPLAY_STOP)
+			break;
+	}
+
+out_err:
+	trace_ext4_fc_replay_scan(sb, ret, off);
+	return ret;
+}
+
+/*
+ * Main recovery path entry point.
+ * The meaning of return codes is similar as above.
+ */
+static int ext4_fc_replay(journal_t *journal, struct buffer_head *bh,
+				enum passtype pass, int off, tid_t expected_tid)
+{
+	struct super_block *sb = journal->j_private;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_fc_tl *tl;
+	__u8 *start, *end;
+	int ret = JBD2_FC_REPLAY_CONTINUE;
+	struct ext4_fc_replay_state *state = &sbi->s_fc_replay_state;
+	struct ext4_fc_tail *tail;
+
+	if (pass == PASS_SCAN) {
+		state->fc_current_pass = PASS_SCAN;
+		return ext4_fc_replay_scan(journal, bh, off, expected_tid);
+	}
+
+	if (state->fc_current_pass != pass) {
+		state->fc_current_pass = pass;
+		sbi->s_mount_state |= EXT4_FC_REPLAY;
+	}
+	if (!sbi->s_fc_replay_state.fc_replay_num_tags) {
+		jbd_debug(1, "Replay stops\n");
+		ext4_fc_set_bitmaps_and_counters(sb);
+		return 0;
+	}
+
+#ifdef CONFIG_EXT4_DEBUG
+	if (sbi->s_fc_debug_max_replay && off >= sbi->s_fc_debug_max_replay) {
+		pr_warn("Dropping fc block %d because max_replay set\n", off);
+		return JBD2_FC_REPLAY_STOP;
+	}
+#endif
+
+	start = (u8 *)bh->b_data;
+	end = (__u8 *)bh->b_data + journal->j_blocksize - 1;
+
+	fc_for_each_tl(start, end, tl) {
+		if (state->fc_replay_num_tags == 0) {
+			ret = JBD2_FC_REPLAY_STOP;
+			ext4_fc_set_bitmaps_and_counters(sb);
+			break;
+		}
+		jbd_debug(3, "Replay phase, tag:%s\n",
+				tag2str(le16_to_cpu(tl->fc_tag)));
+		state->fc_replay_num_tags--;
+		switch (le16_to_cpu(tl->fc_tag)) {
+		case EXT4_FC_TAG_LINK:
+			ret = ext4_fc_replay_link(sb, tl);
+			break;
+		case EXT4_FC_TAG_UNLINK:
+			ret = ext4_fc_replay_unlink(sb, tl);
+			break;
+		case EXT4_FC_TAG_ADD_RANGE:
+			ret = ext4_fc_replay_add_range(sb, tl);
+			break;
+		case EXT4_FC_TAG_CREAT:
+			ret = ext4_fc_replay_create(sb, tl);
+			break;
+		case EXT4_FC_TAG_DEL_RANGE:
+			ret = ext4_fc_replay_del_range(sb, tl);
+			break;
+		case EXT4_FC_TAG_INODE:
+			ret = ext4_fc_replay_inode(sb, tl);
+			break;
+		case EXT4_FC_TAG_PAD:
+			trace_ext4_fc_replay(sb, EXT4_FC_TAG_PAD, 0,
+				ext4_fc_tag_len(tl), 0);
+			break;
+		case EXT4_FC_TAG_TAIL:
+			trace_ext4_fc_replay(sb, EXT4_FC_TAG_TAIL, 0,
+				ext4_fc_tag_len(tl), 0);
+			tail = (struct ext4_fc_tail *)ext4_fc_tag_val(tl);
+			WARN_ON(le32_to_cpu(tail->fc_tid) != expected_tid);
+			break;
+		case EXT4_FC_TAG_HEAD:
+			break;
+		default:
+			trace_ext4_fc_replay(sb, le16_to_cpu(tl->fc_tag), 0,
+				ext4_fc_tag_len(tl), 0);
+			ret = -ECANCELED;
+			break;
+		}
+		if (ret < 0)
+			break;
+		ret = JBD2_FC_REPLAY_CONTINUE;
+	}
+	return ret;
+}
+
+void ext4_fc_init(struct super_block *sb, journal_t *journal)
+{
+	/*
+	 * We set replay callback even if fast commit disabled because we may
+	 * could still have fast commit blocks that need to be replayed even if
+	 * fast commit has now been turned off.
+	 */
+	journal->j_fc_replay_callback = ext4_fc_replay;
+	if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
+		return;
+	journal->j_fc_cleanup_callback = ext4_fc_cleanup;
+}
+
+static const char *fc_ineligible_reasons[] = {
+	"Extended attributes changed",
+	"Cross rename",
+	"Journal flag changed",
+	"Insufficient memory",
+	"Swap boot",
+	"Resize",
+	"Dir renamed",
+	"Falloc range op",
+	"Data journalling",
+	"FC Commit Failed"
+};
+
+int ext4_fc_info_show(struct seq_file *seq, void *v)
+{
+	struct ext4_sb_info *sbi = EXT4_SB((struct super_block *)seq->private);
+	struct ext4_fc_stats *stats = &sbi->s_fc_stats;
+	int i;
+
+	if (v != SEQ_START_TOKEN)
+		return 0;
+
+	seq_printf(seq,
+		"fc stats:\n%ld commits\n%ld ineligible\n%ld numblks\n%lluus avg_commit_time\n",
+		   stats->fc_num_commits, stats->fc_ineligible_commits,
+		   stats->fc_numblks,
+		   div_u64(sbi->s_fc_avg_commit_time, 1000));
+	seq_puts(seq, "Ineligible reasons:\n");
+	for (i = 0; i < EXT4_FC_REASON_MAX; i++)
+		seq_printf(seq, "\"%s\":\t%d\n", fc_ineligible_reasons[i],
+			stats->fc_ineligible_reason_count[i]);
+
+	return 0;
+}
+
+int __init ext4_fc_init_dentry_cache(void)
+{
+	ext4_fc_dentry_cachep = KMEM_CACHE(ext4_fc_dentry_update,
+					   SLAB_RECLAIM_ACCOUNT);
+
+	if (ext4_fc_dentry_cachep == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
new file mode 100644
index 0000000..b77f70f
--- /dev/null
+++ b/fs/ext4/fast_commit.h
@@ -0,0 +1,201 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __FAST_COMMIT_H__
+#define __FAST_COMMIT_H__
+
+/*
+ * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and
+ * linux/fs/ext4/fast_commit.h. These file should always be byte identical.
+ */
+
+/* Fast commit tags */
+#define EXT4_FC_TAG_ADD_RANGE		0x0001
+#define EXT4_FC_TAG_DEL_RANGE		0x0002
+#define EXT4_FC_TAG_CREAT		0x0003
+#define EXT4_FC_TAG_LINK		0x0004
+#define EXT4_FC_TAG_UNLINK		0x0005
+#define EXT4_FC_TAG_INODE		0x0006
+#define EXT4_FC_TAG_PAD			0x0007
+#define EXT4_FC_TAG_TAIL		0x0008
+#define EXT4_FC_TAG_HEAD		0x0009
+
+#define EXT4_FC_SUPPORTED_FEATURES	0x0
+
+/* On disk fast commit tlv value structures */
+
+/* Fast commit on disk tag length structure */
+struct ext4_fc_tl {
+	__le16 fc_tag;
+	__le16 fc_len;
+};
+
+/* Value structure for tag EXT4_FC_TAG_HEAD. */
+struct ext4_fc_head {
+	__le32 fc_features;
+	__le32 fc_tid;
+};
+
+/* Value structure for EXT4_FC_TAG_ADD_RANGE. */
+struct ext4_fc_add_range {
+	__le32 fc_ino;
+	__u8 fc_ex[12];
+};
+
+/* Value structure for tag EXT4_FC_TAG_DEL_RANGE. */
+struct ext4_fc_del_range {
+	__le32 fc_ino;
+	__le32 fc_lblk;
+	__le32 fc_len;
+};
+
+/*
+ * This is the value structure for tags EXT4_FC_TAG_CREAT, EXT4_FC_TAG_LINK
+ * and EXT4_FC_TAG_UNLINK.
+ */
+struct ext4_fc_dentry_info {
+	__le32 fc_parent_ino;
+	__le32 fc_ino;
+	__u8 fc_dname[0];
+};
+
+/* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */
+struct ext4_fc_inode {
+	__le32 fc_ino;
+	__u8 fc_raw_inode[0];
+};
+
+/* Value structure for tag EXT4_FC_TAG_TAIL. */
+struct ext4_fc_tail {
+	__le32 fc_tid;
+	__le32 fc_crc;
+};
+
+/*
+ * Fast commit reason codes
+ */
+enum {
+	/*
+	 * Commit status codes:
+	 */
+	EXT4_FC_REASON_OK = 0,
+	EXT4_FC_REASON_INELIGIBLE,
+	EXT4_FC_REASON_ALREADY_COMMITTED,
+	EXT4_FC_REASON_FC_START_FAILED,
+	EXT4_FC_REASON_FC_FAILED,
+
+	/*
+	 * Fast commit ineligiblity reasons:
+	 */
+	EXT4_FC_REASON_XATTR = 0,
+	EXT4_FC_REASON_CROSS_RENAME,
+	EXT4_FC_REASON_JOURNAL_FLAG_CHANGE,
+	EXT4_FC_REASON_NOMEM,
+	EXT4_FC_REASON_SWAP_BOOT,
+	EXT4_FC_REASON_RESIZE,
+	EXT4_FC_REASON_RENAME_DIR,
+	EXT4_FC_REASON_FALLOC_RANGE,
+	EXT4_FC_REASON_INODE_JOURNAL_DATA,
+	EXT4_FC_COMMIT_FAILED,
+	EXT4_FC_REASON_MAX
+};
+
+#ifdef __KERNEL__
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+	int fcd_op;		/* Type of update create / unlink / link */
+	int fcd_parent;		/* Parent inode number */
+	int fcd_ino;		/* Inode number */
+	struct qstr fcd_name;	/* Dirent name */
+	unsigned char fcd_iname[DNAME_INLINE_LEN];	/* Dirent name string */
+	struct list_head fcd_list;
+};
+
+struct ext4_fc_stats {
+	unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
+	unsigned long fc_num_commits;
+	unsigned long fc_ineligible_commits;
+	unsigned long fc_numblks;
+};
+
+#define EXT4_FC_REPLAY_REALLOC_INCREMENT	4
+
+/*
+ * Physical block regions added to different inodes due to fast commit
+ * recovery. These are set during the SCAN phase. During the replay phase,
+ * our allocator excludes these from its allocation. This ensures that
+ * we don't accidentally allocating a block that is going to be used by
+ * another inode.
+ */
+struct ext4_fc_alloc_region {
+	ext4_lblk_t lblk;
+	ext4_fsblk_t pblk;
+	int ino, len;
+};
+
+/*
+ * Fast commit replay state.
+ */
+struct ext4_fc_replay_state {
+	int fc_replay_num_tags;
+	int fc_replay_expected_off;
+	int fc_current_pass;
+	int fc_cur_tag;
+	int fc_crc;
+	struct ext4_fc_alloc_region *fc_regions;
+	int fc_regions_size, fc_regions_used, fc_regions_valid;
+	int *fc_modified_inodes;
+	int fc_modified_inodes_used, fc_modified_inodes_size;
+};
+
+#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
+#endif
+
+#define fc_for_each_tl(__start, __end, __tl)				\
+	for (tl = (struct ext4_fc_tl *)(__start);			\
+	     (__u8 *)tl < (__u8 *)(__end);				\
+		tl = (struct ext4_fc_tl *)((__u8 *)tl +			\
+					sizeof(struct ext4_fc_tl) +	\
+					+ le16_to_cpu(tl->fc_len)))
+
+static inline const char *tag2str(__u16 tag)
+{
+	switch (tag) {
+	case EXT4_FC_TAG_LINK:
+		return "ADD_ENTRY";
+	case EXT4_FC_TAG_UNLINK:
+		return "DEL_ENTRY";
+	case EXT4_FC_TAG_ADD_RANGE:
+		return "ADD_RANGE";
+	case EXT4_FC_TAG_CREAT:
+		return "CREAT_DENTRY";
+	case EXT4_FC_TAG_DEL_RANGE:
+		return "DEL_RANGE";
+	case EXT4_FC_TAG_INODE:
+		return "INODE";
+	case EXT4_FC_TAG_PAD:
+		return "PAD";
+	case EXT4_FC_TAG_TAIL:
+		return "TAIL";
+	case EXT4_FC_TAG_HEAD:
+		return "HEAD";
+	default:
+		return "ERROR";
+	}
+}
+
+/* Get length of a particular tlv */
+static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
+{
+	return le16_to_cpu(tl->fc_len);
+}
+
+/* Get a pointer to "value" of a tlv */
+static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
+{
+	return (__u8 *)tl + sizeof(*tl);
+}
+
+#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 1513e90..0875931 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -191,9 +191,12 @@
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
+	ext4_fc_start_update(inode);
 	if (iocb->ki_flags & IOCB_NOWAIT) {
-		if (!inode_trylock(inode))
+		if (!inode_trylock(inode)) {
+			ext4_fc_stop_update(inode);
 			return -EAGAIN;
+		}
 	} else {
 		inode_lock(inode);
 	}
@@ -210,6 +213,7 @@
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 out:
 	inode_unlock(inode);
+	ext4_fc_stop_update(inode);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	return ret;
@@ -403,13 +407,13 @@
 	handle_t *handle;
 	int err;
 
-	if (likely(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED))
+	if (likely(ext4_test_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED)))
 		return 0;
 
 	if (sb_rdonly(sb) || !sb_start_intwrite_trylock(sb))
 		return 0;
 
-	sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
+	ext4_set_mount_flag(sb, EXT4_MF_MNTDIR_SAMPLED);
 	/*
 	 * Sample where the filesystem has been mounted and
 	 * store it in the superblock for sysadmin convenience
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
index 37347ba..d840447 100644
--- a/fs/ext4/fsmap.c
+++ b/fs/ext4/fsmap.c
@@ -280,7 +280,7 @@
 
 	/* Fabricate an rmap entry for the external log device. */
 	irec.fmr_physical = journal->j_blk_offset;
-	irec.fmr_length = journal->j_maxlen;
+	irec.fmr_length = journal->j_total_len;
 	irec.fmr_owner = EXT4_FMR_OWN_LOG;
 	irec.fmr_flags = 0;
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 8a28d47..8694d347 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -109,7 +109,7 @@
 	if (sb_rdonly(inode->i_sb)) {
 		/* Make sure that we read updated s_mount_flags value */
 		smp_rmb();
-		if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+		if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))
 			ret = -EROFS;
 		goto out;
 	}
@@ -149,7 +149,7 @@
 	if (journal->j_flags & JBD2_BARRIER &&
 	    !jbd2_trans_will_send_data_barrier(journal, commit_tid))
 		needs_barrier = true;
-	ret = jbd2_complete_transaction(journal, commit_tid);
+	ret = ext4_fc_commit(journal, commit_tid);
 	if (needs_barrier) {
 	issue_flush:
 		err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 64b6549..f8078d0 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -82,7 +82,12 @@
 				      struct buffer_head *bh)
 {
 	ext4_fsblk_t	blk;
-	struct ext4_group_info *grp = ext4_get_group_info(sb, block_group);
+	struct ext4_group_info *grp;
+
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return 0;
+
+	grp = ext4_get_group_info(sb, block_group);
 
 	if (buffer_verified(bh))
 		return 0;
@@ -282,15 +287,17 @@
 	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
 	bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
 	/* Don't bother if the inode bitmap is corrupt. */
-	grp = ext4_get_group_info(sb, block_group);
 	if (IS_ERR(bitmap_bh)) {
 		fatal = PTR_ERR(bitmap_bh);
 		bitmap_bh = NULL;
 		goto error_return;
 	}
-	if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
-		fatal = -EFSCORRUPTED;
-		goto error_return;
+	if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+		grp = ext4_get_group_info(sb, block_group);
+		if (unlikely(EXT4_MB_GRP_IBITMAP_CORRUPT(grp))) {
+			fatal = -EFSCORRUPTED;
+			goto error_return;
+		}
 	}
 
 	BUFFER_TRACE(bitmap_bh, "get_write_access");
@@ -727,6 +734,122 @@
 	return 1;
 }
 
+int ext4_mark_inode_used(struct super_block *sb, int ino)
+{
+	unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
+	struct buffer_head *inode_bitmap_bh = NULL, *group_desc_bh = NULL;
+	struct ext4_group_desc *gdp;
+	ext4_group_t group;
+	int bit;
+	int err = -EFSCORRUPTED;
+
+	if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+		goto out;
+
+	group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+	inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+	if (IS_ERR(inode_bitmap_bh))
+		return PTR_ERR(inode_bitmap_bh);
+
+	if (ext4_test_bit(bit, inode_bitmap_bh->b_data)) {
+		err = 0;
+		goto out;
+	}
+
+	gdp = ext4_get_group_desc(sb, group, &group_desc_bh);
+	if (!gdp || !group_desc_bh) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	ext4_set_bit(bit, inode_bitmap_bh->b_data);
+
+	BUFFER_TRACE(inode_bitmap_bh, "call ext4_handle_dirty_metadata");
+	err = ext4_handle_dirty_metadata(NULL, NULL, inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+	err = sync_dirty_buffer(inode_bitmap_bh);
+	if (err) {
+		ext4_std_error(sb, err);
+		goto out;
+	}
+
+	/* We may have to initialize the block bitmap if it isn't already */
+	if (ext4_has_group_desc_csum(sb) &&
+	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		struct buffer_head *block_bitmap_bh;
+
+		block_bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(block_bitmap_bh)) {
+			err = PTR_ERR(block_bitmap_bh);
+			goto out;
+		}
+
+		BUFFER_TRACE(block_bitmap_bh, "dirty block bitmap");
+		err = ext4_handle_dirty_metadata(NULL, NULL, block_bitmap_bh);
+		sync_dirty_buffer(block_bitmap_bh);
+
+		/* recheck and clear flag under lock if we still need to */
+		ext4_lock_group(sb, group);
+		if (ext4_has_group_desc_csum(sb) &&
+		    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+			ext4_free_group_clusters_set(sb, gdp,
+				ext4_free_clusters_after_init(sb, group, gdp));
+			ext4_block_bitmap_csum_set(sb, group, gdp,
+						   block_bitmap_bh);
+			ext4_group_desc_csum_set(sb, group, gdp);
+		}
+		ext4_unlock_group(sb, group);
+		brelse(block_bitmap_bh);
+
+		if (err) {
+			ext4_std_error(sb, err);
+			goto out;
+		}
+	}
+
+	/* Update the relevant bg descriptor fields */
+	if (ext4_has_group_desc_csum(sb)) {
+		int free;
+
+		ext4_lock_group(sb, group); /* while we modify the bg desc */
+		free = EXT4_INODES_PER_GROUP(sb) -
+			ext4_itable_unused_count(sb, gdp);
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			free = 0;
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to update the bg_itable_unused count
+		 */
+		if (bit >= free)
+			ext4_itable_unused_set(sb, gdp,
+					(EXT4_INODES_PER_GROUP(sb) - bit - 1));
+	} else {
+		ext4_lock_group(sb, group);
+	}
+
+	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
+	if (ext4_has_group_desc_csum(sb)) {
+		ext4_inode_bitmap_csum_set(sb, group, gdp, inode_bitmap_bh,
+					   EXT4_INODES_PER_GROUP(sb) / 8);
+		ext4_group_desc_csum_set(sb, group, gdp);
+	}
+
+	ext4_unlock_group(sb, group);
+	err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
+	sync_dirty_buffer(group_desc_bh);
+out:
+	return err;
+}
+
 /*
  * There are two policies for allocating an inode.  If the new inode is
  * a directory, then a forward search is made for a block group with both
@@ -756,7 +879,7 @@
 	struct inode *ret;
 	ext4_group_t i;
 	ext4_group_t flex_group;
-	struct ext4_group_info *grp;
+	struct ext4_group_info *grp = NULL;
 	int encrypt = 0;
 
 	/* Cannot create files in a deleted directory */
@@ -894,15 +1017,21 @@
 		if (ext4_free_inodes_count(sb, gdp) == 0)
 			goto next_group;
 
-		grp = ext4_get_group_info(sb, group);
-		/* Skip groups with already-known suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
-			goto next_group;
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			/*
+			 * Skip groups with already-known suspicious inode
+			 * tables
+			 */
+			if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
+				goto next_group;
+		}
 
 		brelse(inode_bitmap_bh);
 		inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
 		/* Skip groups with suspicious inode tables */
-		if (EXT4_MB_GRP_IBITMAP_CORRUPT(grp) ||
+		if (((!(sbi->s_mount_state & EXT4_FC_REPLAY))
+		     && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) ||
 		    IS_ERR(inode_bitmap_bh)) {
 			inode_bitmap_bh = NULL;
 			goto next_group;
@@ -921,7 +1050,7 @@
 			goto next_group;
 		}
 
-		if (!handle) {
+		if ((!(sbi->s_mount_state & EXT4_FC_REPLAY)) && !handle) {
 			BUG_ON(nblocks <= 0);
 			handle = __ext4_journal_start_sb(dir->i_sb, line_no,
 							 handle_type, nblocks,
@@ -1025,9 +1154,15 @@
 	/* Update the relevant bg descriptor fields */
 	if (ext4_has_group_desc_csum(sb)) {
 		int free;
-		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+		struct ext4_group_info *grp = NULL;
 
-		down_read(&grp->alloc_sem); /* protect vs itable lazyinit */
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			grp = ext4_get_group_info(sb, group);
+			down_read(&grp->alloc_sem); /*
+						     * protect vs itable
+						     * lazyinit
+						     */
+		}
 		ext4_lock_group(sb, group); /* while we modify the bg desc */
 		free = EXT4_INODES_PER_GROUP(sb) -
 			ext4_itable_unused_count(sb, gdp);
@@ -1043,7 +1178,8 @@
 		if (ino > free)
 			ext4_itable_unused_set(sb, gdp,
 					(EXT4_INODES_PER_GROUP(sb) - ino));
-		up_read(&grp->alloc_sem);
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY))
+			up_read(&grp->alloc_sem);
 	} else {
 		ext4_lock_group(sb, group);
 	}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 539d95b..0c93da1 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -103,8 +103,8 @@
 	return provided == calculated;
 }
 
-static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
-				struct ext4_inode_info *ei)
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+			 struct ext4_inode_info *ei)
 {
 	__u32 csum;
 
@@ -354,6 +354,8 @@
 	ext4_xattr_inode_array_free(ea_inode_array);
 	return;
 no_delete:
+	if (!list_empty(&EXT4_I(inode)->i_fc_list))
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
 	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
 }
 
@@ -545,7 +547,8 @@
 		return -EFSCORRUPTED;
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+	if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
+	    ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
 		if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
 			map->m_pblk = ext4_es_pblock(&es) +
 					map->m_lblk - es.es_lblk;
@@ -762,6 +765,8 @@
 			if (ret)
 				return ret;
 		}
+		ext4_fc_track_range(handle, inode, map->m_lblk,
+			    map->m_lblk + map->m_len - 1);
 	}
 	return retval;
 }
@@ -985,7 +990,8 @@
 	int create = map_flags & EXT4_GET_BLOCKS_CREATE;
 	int err;
 
-	J_ASSERT(handle != NULL || create == 0);
+	J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+		 || handle != NULL || create == 0);
 
 	map.m_lblk = block;
 	map.m_len = 1;
@@ -1001,7 +1007,8 @@
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
 		J_ASSERT(create != 0);
-		J_ASSERT(handle != NULL);
+		J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			 || (handle != NULL));
 
 		/*
 		 * Now that we do not always journal data, we should
@@ -2359,6 +2366,79 @@
 }
 
 /*
+ * mpage_process_page - update page buffers corresponding to changed extent and
+ *		       may submit fully mapped page for IO
+ *
+ * @mpd		- description of extent to map, on return next extent to map
+ * @m_lblk	- logical block mapping.
+ * @m_pblk	- corresponding physical mapping.
+ * @map_bh	- determines on return whether this page requires any further
+ *		  mapping or not.
+ * Scan given page buffers corresponding to changed extent and update buffer
+ * state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits.
+ * If the given page is not fully mapped, we update @map to the next extent in
+ * the given page that needs mapping & return @map_bh as true.
+ */
+static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
+			      ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
+			      bool *map_bh)
+{
+	struct buffer_head *head, *bh;
+	ext4_io_end_t *io_end = mpd->io_submit.io_end;
+	ext4_lblk_t lblk = *m_lblk;
+	ext4_fsblk_t pblock = *m_pblk;
+	int err = 0;
+	int blkbits = mpd->inode->i_blkbits;
+	ssize_t io_end_size = 0;
+	struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
+
+	bh = head = page_buffers(page);
+	do {
+		if (lblk < mpd->map.m_lblk)
+			continue;
+		if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+			/*
+			 * Buffer after end of mapped extent.
+			 * Find next buffer in the page to map.
+			 */
+			mpd->map.m_len = 0;
+			mpd->map.m_flags = 0;
+			io_end_vec->size += io_end_size;
+			io_end_size = 0;
+
+			err = mpage_process_page_bufs(mpd, head, bh, lblk);
+			if (err > 0)
+				err = 0;
+			if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
+				io_end_vec = ext4_alloc_io_end_vec(io_end);
+				if (IS_ERR(io_end_vec)) {
+					err = PTR_ERR(io_end_vec);
+					goto out;
+				}
+				io_end_vec->offset = mpd->map.m_lblk << blkbits;
+			}
+			*map_bh = true;
+			goto out;
+		}
+		if (buffer_delay(bh)) {
+			clear_buffer_delay(bh);
+			bh->b_blocknr = pblock++;
+		}
+		clear_buffer_unwritten(bh);
+		io_end_size += (1 << blkbits);
+	} while (lblk++, (bh = bh->b_this_page) != head);
+
+	io_end_vec->size += io_end_size;
+	io_end_size = 0;
+	*map_bh = false;
+out:
+	*m_lblk = lblk;
+	*m_pblk = pblock;
+	return err;
+}
+
+/*
  * mpage_map_buffers - update buffers corresponding to changed extent and
  *		       submit fully mapped pages for IO
  *
@@ -2377,12 +2457,12 @@
 	struct pagevec pvec;
 	int nr_pages, i;
 	struct inode *inode = mpd->inode;
-	struct buffer_head *head, *bh;
 	int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
 	pgoff_t start, end;
 	ext4_lblk_t lblk;
-	sector_t pblock;
+	ext4_fsblk_t pblock;
 	int err;
+	bool map_bh = false;
 
 	start = mpd->map.m_lblk >> bpp_bits;
 	end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
@@ -2398,50 +2478,19 @@
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
-			bh = head = page_buffers(page);
-			do {
-				if (lblk < mpd->map.m_lblk)
-					continue;
-				if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
-					/*
-					 * Buffer after end of mapped extent.
-					 * Find next buffer in the page to map.
-					 */
-					mpd->map.m_len = 0;
-					mpd->map.m_flags = 0;
-					/*
-					 * FIXME: If dioread_nolock supports
-					 * blocksize < pagesize, we need to make
-					 * sure we add size mapped so far to
-					 * io_end->size as the following call
-					 * can submit the page for IO.
-					 */
-					err = mpage_process_page_bufs(mpd, head,
-								      bh, lblk);
-					pagevec_release(&pvec);
-					if (err > 0)
-						err = 0;
-					return err;
-				}
-				if (buffer_delay(bh)) {
-					clear_buffer_delay(bh);
-					bh->b_blocknr = pblock++;
-				}
-				clear_buffer_unwritten(bh);
-			} while (lblk++, (bh = bh->b_this_page) != head);
-
+			err = mpage_process_page(mpd, page, &lblk, &pblock,
+						 &map_bh);
 			/*
-			 * FIXME: This is going to break if dioread_nolock
-			 * supports blocksize < pagesize as we will try to
-			 * convert potentially unmapped parts of inode.
+			 * If map_bh is true, means page may require further bh
+			 * mapping, or maybe the page was submitted for IO.
+			 * So we return to call further extent mapping.
 			 */
-			mpd->io_submit.io_end->size += PAGE_SIZE;
+			if (err < 0 || map_bh == true)
+				goto out;
 			/* Page fully mapped - let IO run! */
 			err = mpage_submit_page(mpd, page);
-			if (err < 0) {
-				pagevec_release(&pvec);
-				return err;
-			}
+			if (err < 0)
+				goto out;
 		}
 		pagevec_release(&pvec);
 	}
@@ -2449,6 +2498,9 @@
 	mpd->map.m_len = 0;
 	mpd->map.m_flags = 0;
 	return 0;
+out:
+	pagevec_release(&pvec);
+	return err;
 }
 
 static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
@@ -2528,16 +2580,20 @@
 	int err;
 	loff_t disksize;
 	int progress = 0;
+	ext4_io_end_t *io_end = mpd->io_submit.io_end;
+	struct ext4_io_end_vec *io_end_vec;
 
-	mpd->io_submit.io_end->offset =
-				((loff_t)map->m_lblk) << inode->i_blkbits;
+	io_end_vec = ext4_alloc_io_end_vec(io_end);
+	if (IS_ERR(io_end_vec))
+		return PTR_ERR(io_end_vec);
+	io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
 	do {
 		err = mpage_map_one_extent(handle, mpd);
 		if (err < 0) {
 			struct super_block *sb = inode->i_sb;
 
 			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
-			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			    ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2770,7 +2826,7 @@
 	 * the stack trace.
 	 */
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
-		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+		     ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -3415,9 +3471,15 @@
 {
 	journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 
-	if (journal)
-		return !jbd2_transaction_committed(journal,
-					EXT4_I(inode)->i_datasync_tid);
+	if (journal) {
+		if (jbd2_transaction_committed(journal,
+			EXT4_I(inode)->i_datasync_tid))
+			return false;
+		if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+			return !list_empty(&EXT4_I(inode)->i_fc_list);
+		return true;
+	}
+
 	/* Any metadata buffers to write? */
 	if (!list_empty(&inode->i_mapping->private_list))
 		return true;
@@ -3637,6 +3699,7 @@
 			    ssize_t size, void *private)
 {
         ext4_io_end_t *io_end = private;
+	struct ext4_io_end_vec *io_end_vec;
 
 	/* if not async direct IO just return */
 	if (!io_end)
@@ -3654,8 +3717,9 @@
 		ext4_clear_io_unwritten_flag(io_end);
 		size = 0;
 	}
-	io_end->offset = offset;
-	io_end->size = size;
+	io_end_vec = ext4_alloc_io_end_vec(io_end);
+	io_end_vec->offset = offset;
+	io_end_vec->size = size;
 	ext4_put_io_end(io_end);
 
 	return 0;
@@ -4403,6 +4467,7 @@
 
 		up_write(&EXT4_I(inode)->i_data_sem);
 	}
+	ext4_fc_track_range(handle, inode, first_block, stop_block);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
 
@@ -4579,22 +4644,22 @@
  * data in memory that is needed to recreate the on-disk version of this
  * inode.
  */
-static int __ext4_get_inode_loc(struct inode *inode,
-				struct ext4_iloc *iloc, int in_mem)
+static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
+				struct ext4_iloc *iloc, int in_mem,
+				ext4_fsblk_t *ret_block)
 {
 	struct ext4_group_desc	*gdp;
 	struct buffer_head	*bh;
-	struct super_block	*sb = inode->i_sb;
 	ext4_fsblk_t		block;
 	struct blk_plug		plug;
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (inode->i_ino < EXT4_ROOT_INO ||
-	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+	if (ino < EXT4_ROOT_INO ||
+	    ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
-	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+	iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
 	gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
 	if (!gdp)
 		return -EIO;
@@ -4603,7 +4668,7 @@
 	 * Figure out the offset within the block group inode table
 	 */
 	inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
-	inode_offset = ((inode->i_ino - 1) %
+	inode_offset = ((ino - 1) %
 			EXT4_INODES_PER_GROUP(sb));
 	block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
 	iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
@@ -4702,15 +4767,15 @@
 		 * has in-inode xattrs, or we don't have this inode in memory.
 		 * Read the block from disk.
 		 */
-		trace_ext4_load_inode(inode);
+		trace_ext4_load_inode(sb, ino);
 		get_bh(bh);
 		bh->b_end_io = end_buffer_read_sync;
 		submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
 		blk_finish_plug(&plug);
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			EXT4_ERROR_INODE_BLOCK(inode, block,
-					       "unable to read itable block");
+			if (ret_block)
+				*ret_block = block;
 			brelse(bh);
 			return -EIO;
 		}
@@ -4720,11 +4785,43 @@
 	return 0;
 }
 
+static int __ext4_get_inode_loc_noinmem(struct inode *inode,
+					struct ext4_iloc *iloc)
+{
+	ext4_fsblk_t err_blk;
+	int ret;
+
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0,
+					&err_blk);
+
+	if (ret == -EIO)
+		EXT4_ERROR_INODE_BLOCK(inode, err_blk,
+					"unable to read itable block");
+
+	return ret;
+}
+
 int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
 {
+	ext4_fsblk_t err_blk;
+	int ret;
+
 	/* We have all inode data except xattrs in memory here. */
-	return __ext4_get_inode_loc(inode, iloc,
-		!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+	ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc,
+		!ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk);
+
+	if (ret == -EIO)
+		EXT4_ERROR_INODE_BLOCK(inode, err_blk,
+					"unable to read itable block");
+
+	return ret;
+}
+
+
+int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+			  struct ext4_iloc *iloc)
+{
+	return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL);
 }
 
 static bool ext4_should_use_dax(struct inode *inode)
@@ -4876,7 +4973,7 @@
 	ei = EXT4_I(inode);
 	iloc.bh = NULL;
 
-	ret = __ext4_get_inode_loc(inode, &iloc, 0);
+	ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
 	if (ret < 0)
 		goto bad_inode;
 	raw_inode = ext4_raw_inode(&iloc);
@@ -4922,7 +5019,8 @@
 					      sizeof(gen));
 	}
 
-	if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
+	if (!ext4_inode_csum_verify(inode, raw_inode, ei) &&
+	    (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
 		ext4_error_inode(inode, function, line, 0,
 				 "iget: checksum invalid");
 		ret = -EFSBADCRC;
@@ -5012,6 +5110,7 @@
 	for (block = 0; block < EXT4_N_BLOCKS; block++)
 		ei->i_data[block] = raw_inode->i_block[block];
 	INIT_LIST_HEAD(&ei->i_orphan);
+	ext4_fc_init_inode(&ei->vfs_inode);
 
 	/*
 	 * Set transaction id's of transactions that have to be committed
@@ -5077,9 +5176,10 @@
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
 		/* validate the block references in the inode */
-		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-		   (S_ISLNK(inode->i_mode) &&
-		    !ext4_inode_is_fast_symlink(inode))) {
+		if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+			(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+			(S_ISLNK(inode->i_mode) &&
+			!ext4_inode_is_fast_symlink(inode)))) {
 			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
 			else
@@ -5459,12 +5559,12 @@
 		if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
 			return 0;
 
-		err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+		err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
 						EXT4_I(inode)->i_sync_tid);
 	} else {
 		struct ext4_iloc iloc;
 
-		err = __ext4_get_inode_loc(inode, &iloc, 0);
+		err = __ext4_get_inode_loc_noinmem(inode, &iloc);
 		if (err)
 			return err;
 		/*
@@ -5588,6 +5688,7 @@
 		if (error)
 			return error;
 	}
+	ext4_fc_start_update(inode);
 	if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
 	    (ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
 		handle_t *handle;
@@ -5611,6 +5712,7 @@
 
 		if (error) {
 			ext4_journal_stop(handle);
+			ext4_fc_stop_update(inode);
 			return error;
 		}
 		/* Update corresponding info in inode so that everything is in
@@ -5631,11 +5733,15 @@
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
-			if (attr->ia_size > sbi->s_bitmap_maxbytes)
+			if (attr->ia_size > sbi->s_bitmap_maxbytes) {
+				ext4_fc_stop_update(inode);
 				return -EFBIG;
+			}
 		}
-		if (!S_ISREG(inode->i_mode))
+		if (!S_ISREG(inode->i_mode)) {
+			ext4_fc_stop_update(inode);
 			return -EINVAL;
+		}
 
 		if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
 			inode_inc_iversion(inode);
@@ -5659,7 +5765,7 @@
 		rc = ext4_break_layouts(inode);
 		if (rc) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
-			return rc;
+			goto err_out;
 		}
 
 		if (attr->ia_size != inode->i_size) {
@@ -5680,6 +5786,21 @@
 				inode->i_mtime = current_time(inode);
 				inode->i_ctime = inode->i_mtime;
 			}
+
+			if (shrink)
+				ext4_fc_track_range(handle, inode,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits,
+					(oldsize > 0 ? oldsize - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+			else
+				ext4_fc_track_range(
+					handle, inode,
+					(oldsize > 0 ? oldsize - 1 : oldsize) >>
+					inode->i_sb->s_blocksize_bits,
+					(attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+					inode->i_sb->s_blocksize_bits);
+
 			down_write(&EXT4_I(inode)->i_data_sem);
 			EXT4_I(inode)->i_disksize = attr->ia_size;
 			rc = ext4_mark_inode_dirty(handle, inode);
@@ -5738,9 +5859,11 @@
 		rc = posix_acl_chmod(inode, inode->i_mode);
 
 err_out:
-	ext4_std_error(inode->i_sb, error);
+	if  (error)
+		ext4_std_error(inode->i_sb, error);
 	if (!error)
 		error = rc;
+	ext4_fc_stop_update(inode);
 	return error;
 }
 
@@ -5918,6 +6041,8 @@
 		put_bh(iloc->bh);
 		return -EIO;
 	}
+	ext4_fc_track_inode(handle, inode);
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -6236,6 +6361,8 @@
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
+	ext4_fc_mark_ineligible(inode->i_sb,
+		EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
 	err = ext4_mark_inode_dirty(handle, inode);
 	ext4_handle_sync(handle);
 	ext4_journal_stop(handle);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index ba13fbb..d7d934c 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -86,7 +86,7 @@
 	i_size_write(inode2, isize);
 }
 
-static void reset_inode_seed(struct inode *inode)
+void ext4_reset_inode_seed(struct inode *inode)
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -165,6 +165,7 @@
 		err = -EINVAL;
 		goto err_out;
 	}
+	ext4_fc_start_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT);
 
 	/* Protect extent tree against block allocations via delalloc */
 	ext4_double_down_write_data_sem(inode, inode_bl);
@@ -199,8 +200,8 @@
 
 	inode->i_generation = prandom_u32();
 	inode_bl->i_generation = prandom_u32();
-	reset_inode_seed(inode);
-	reset_inode_seed(inode_bl);
+	ext4_reset_inode_seed(inode);
+	ext4_reset_inode_seed(inode_bl);
 
 	ext4_discard_preallocations(inode);
 
@@ -247,6 +248,7 @@
 
 err_out1:
 	ext4_journal_stop(handle);
+	ext4_fc_stop_ineligible(sb);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
 err_out:
@@ -813,7 +815,7 @@
 	return error;
 }
 
-long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	struct super_block *sb = inode->i_sb;
@@ -1080,6 +1082,7 @@
 
 		err = ext4_resize_fs(sb, n_blocks_count);
 		if (EXT4_SB(sb)->s_journal) {
+			ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE);
 			jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
 			err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
 			jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
@@ -1312,6 +1315,17 @@
 	}
 }
 
+long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
+{
+	long ret;
+
+	ext4_fc_start_update(file_inode(filp));
+	ret = __ext4_ioctl(filp, cmd, arg);
+	ext4_fc_stop_update(file_inode(filp));
+
+	return ret;
+}
+
 #ifdef CONFIG_COMPAT
 long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cd69510..033ed8c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -861,7 +861,7 @@
 			bh[i] = NULL;
 			continue;
 		}
-		bh[i] = ext4_read_block_bitmap_nowait(sb, group);
+		bh[i] = ext4_read_block_bitmap_nowait(sb, group, false);
 		if (IS_ERR(bh[i])) {
 			err = PTR_ERR(bh[i]);
 			bh[i] = NULL;
@@ -1449,14 +1449,16 @@
 
 		blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
 		blocknr += EXT4_C2B(sbi, block);
-		ext4_grp_locked_error(sb, e4b->bd_group,
-				      inode ? inode->i_ino : 0,
-				      blocknr,
-				      "freeing already freed block "
-				      "(bit %u); block bitmap corrupt.",
-				      block);
-		ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+		if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
+			ext4_grp_locked_error(sb, e4b->bd_group,
+					      inode ? inode->i_ino : 0,
+					      blocknr,
+					      "freeing already freed block (bit %u); block bitmap corrupt.",
+					      block);
+			ext4_mark_group_bitmap_corrupted(
+				sb, e4b->bd_group,
 				EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+		}
 		mb_regenerate_buddy(e4b);
 		goto done;
 	}
@@ -2044,6 +2046,7 @@
 				ext4_group_t group, int cr)
 {
 	unsigned free, fragments;
+	struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
 	int flex_size = ext4_flex_bg_size(EXT4_SB(ac->ac_sb));
 	struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group);
 
@@ -2060,7 +2063,26 @@
 
 	/* We only do this if the grp has never been initialized */
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) {
-		int ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
+		struct ext4_group_desc *gdp =
+			ext4_get_group_desc(ac->ac_sb, group, NULL);
+		int ret;
+
+		/* cr=0/1 is a very optimistic search to find large
+		 * good chunks almost for free.  If buddy data is not
+		 * ready, then this optimization makes no sense.  But
+		 * we never skip the first block group in a flex_bg,
+		 * since this gets used for metadata block allocation,
+		 * and we want to make sure we locate metadata blocks
+		 * in the first block group in the flex_bg if
+		 * possible.
+		 */
+		if (cr < 2 &&
+		    (!sbi->s_log_groups_per_flex ||
+		     ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) &&
+		    !(ext4_has_group_desc_csum(ac->ac_sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))))
+			return 0;
+		ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -2104,12 +2126,92 @@
 	return 0;
 }
 
+/*
+ * Start prefetching @nr block bitmaps starting at @group.
+ * Return the next group which needs to be prefetched.
+ */
+ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group,
+			      unsigned int nr, int *cnt)
+{
+	ext4_group_t ngroups = ext4_get_groups_count(sb);
+	struct buffer_head *bh;
+	struct blk_plug plug;
+
+	blk_start_plug(&plug);
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		/*
+		 * Prefetch block groups with free blocks; but don't
+		 * bother if it is marked uninitialized on disk, since
+		 * it won't require I/O to read.  Also only try to
+		 * prefetch once, so we avoid getblk() call, which can
+		 * be expensive.
+		 */
+		if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) &&
+		    EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			bh = ext4_read_block_bitmap_nowait(sb, group, true);
+			if (bh && !IS_ERR(bh)) {
+				if (!buffer_uptodate(bh) && cnt)
+					(*cnt)++;
+				brelse(bh);
+			}
+		}
+		if (++group >= ngroups)
+			group = 0;
+	}
+	blk_finish_plug(&plug);
+	return group;
+}
+
+/*
+ * Prefetching reads the block bitmap into the buffer cache; but we
+ * need to make sure that the buddy bitmap in the page cache has been
+ * initialized.  Note that ext4_mb_init_group() will block if the I/O
+ * is not yet completed, or indeed if it was not initiated by
+ * ext4_mb_prefetch did not start the I/O.
+ *
+ * TODO: We should actually kick off the buddy bitmap setup in a work
+ * queue when the buffer I/O is completed, so that we don't block
+ * waiting for the block allocation bitmap read to finish when
+ * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator().
+ */
+void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group,
+			   unsigned int nr)
+{
+	while (nr-- > 0) {
+		struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group,
+								  NULL);
+		struct ext4_group_info *grp = ext4_get_group_info(sb, group);
+
+		if (!group)
+			group = ext4_get_groups_count(sb);
+		group--;
+		grp = ext4_get_group_info(sb, group);
+
+		if (EXT4_MB_GRP_NEED_INIT(grp) &&
+		    ext4_free_group_clusters(sb, gdp) > 0 &&
+		    !(ext4_has_group_desc_csum(sb) &&
+		      (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) {
+			if (ext4_mb_init_group(sb, group, GFP_NOFS))
+				break;
+		}
+	}
+}
+
+
 static noinline_for_stack int
 ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 {
-	ext4_group_t ngroups, group, i;
+	ext4_group_t prefetch_grp = 0, ngroups, group, i;
 	int cr;
 	int err = 0, first_err = 0;
+	unsigned int nr = 0, prefetch_ios = 0;
 	struct ext4_sb_info *sbi;
 	struct super_block *sb;
 	struct ext4_buddy e4b;
@@ -2177,6 +2279,7 @@
 		 * from the goal value specified
 		 */
 		group = ac->ac_g_ex.fe_group;
+		prefetch_grp = group;
 
 		for (i = 0; i < ngroups; group++, i++) {
 			int ret = 0;
@@ -2188,6 +2291,29 @@
 			if (group >= ngroups)
 				group = 0;
 
+			/*
+			 * Batch reads of the block allocation bitmaps
+			 * to get multiple READs in flight; limit
+			 * prefetching at cr=0/1, otherwise mballoc can
+			 * spend a lot of time loading imperfect groups
+			 */
+			if ((prefetch_grp == group) &&
+			    (cr > 1 ||
+			     prefetch_ios < sbi->s_mb_prefetch_limit)) {
+				unsigned int curr_ios = prefetch_ios;
+
+				nr = sbi->s_mb_prefetch;
+				if (ext4_has_feature_flex_bg(sb)) {
+					nr = (group / sbi->s_mb_prefetch) *
+						sbi->s_mb_prefetch;
+					nr = nr + sbi->s_mb_prefetch - group;
+				}
+				prefetch_grp = ext4_mb_prefetch(sb, group,
+							nr, &prefetch_ios);
+				if (prefetch_ios == curr_ios)
+					nr = 0;
+			}
+
 			/* This now checks without needing the buddy page */
 			ret = ext4_mb_good_group(ac, group, cr);
 			if (ret <= 0) {
@@ -2260,6 +2386,10 @@
 out:
 	if (!err && ac->ac_status != AC_STATUS_FOUND && first_err)
 		err = first_err;
+
+	if (nr)
+		ext4_mb_prefetch_fini(sb, prefetch_grp, nr);
+
 	return err;
 }
 
@@ -2519,6 +2649,26 @@
 			goto err_freebuddy;
 	}
 
+	if (ext4_has_feature_flex_bg(sb)) {
+		/* a single flex group is supposed to be read by a single IO */
+		sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+		sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
+	} else {
+		sbi->s_mb_prefetch = 32;
+	}
+	if (sbi->s_mb_prefetch > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch = ext4_get_groups_count(sb);
+	/* now many real IOs to prefetch within a single allocation at cr=0
+	 * given cr=0 is an CPU-related optimization we shouldn't try to
+	 * load too many groups, at some point we should start to use what
+	 * we've got in memory.
+	 * with an average random access time 5ms, it'd take a second to get
+	 * 200 groups (* N with flex_bg), so let's make this limit 4
+	 */
+	sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4;
+	if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb))
+		sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb);
+
 	return 0;
 
 err_freebuddy:
@@ -3062,6 +3212,84 @@
 }
 
 /*
+ * Idempotent helper for Ext4 fast commit replay path to set the state of
+ * blocks in bitmaps and update counters.
+ */
+void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
+			int len, int state)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int i, clen, err;
+	int already;
+
+	clen = EXT4_B2C(sbi, len);
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		bitmap_bh = NULL;
+		goto out_err;
+	}
+
+	err = -EIO;
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		goto out_err;
+
+	ext4_lock_group(sb, group);
+	already = 0;
+	for (i = 0; i < clen; i++)
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
+			already++;
+
+	if (state)
+		ext4_set_bits(bitmap_bh->b_data, blkoff, clen);
+	else
+		mb_test_and_clear_bits(bitmap_bh->b_data, blkoff, clen);
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
+		ext4_free_group_clusters_set(sb, gdp,
+					     ext4_free_clusters_after_init(sb,
+						group, gdp));
+	}
+	if (state)
+		clen = ext4_free_group_clusters(sb, gdp) - clen + already;
+	else
+		clen = ext4_free_group_clusters(sb, gdp) + clen - already;
+
+	ext4_free_group_clusters_set(sb, gdp, clen);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+
+	ext4_unlock_group(sb, group);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, group);
+
+		atomic64_sub(len,
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
+	}
+
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		goto out_err;
+	sync_dirty_buffer(bitmap_bh);
+	err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(gdp_bh);
+
+out_err:
+	brelse(bitmap_bh);
+}
+
+/*
  * here we normalize request for locality group
  * Group request are normalized to s_mb_group_prealloc, which goes to
  * s_strip if we set the same via mount option.
@@ -4030,6 +4258,9 @@
 		return;
 	}
 
+	if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
+		return;
+
 	mb_debug(1, "discard preallocation for inode %lu\n", inode->i_ino);
 	trace_ext4_discard_preallocations(inode);
 
@@ -4125,7 +4356,7 @@
 	ext4_group_t ngroups, i;
 
 	if (!ext4_mballoc_debug ||
-	    (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED))
+	    (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)))
 		return;
 
 	ext4_msg(ac->ac_sb, KERN_ERR, "Can't allocate:"
@@ -4483,6 +4714,9 @@
 	return freed;
 }
 
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp);
+
 /*
  * Main entry point into mballoc to allocate blocks
  * it tries to use preallocation first, then falls back
@@ -4504,6 +4738,8 @@
 	sbi = EXT4_SB(sb);
 
 	trace_ext4_request_blocks(ar);
+	if (sbi->s_mount_state & EXT4_FC_REPLAY)
+		return ext4_mb_new_blocks_simple(handle, ar, errp);
 
 	/* Allow to use superuser reservation for quota file */
 	if (ext4_is_quota_file(ar->inode))
@@ -4721,6 +4957,102 @@
 	return 0;
 }
 
+/*
+ * Simple allocator for Ext4 fast commit replay path. It searches for blocks
+ * linearly starting at the goal block and also excludes the blocks which
+ * are going to be in use after fast commit replay.
+ */
+static ext4_fsblk_t ext4_mb_new_blocks_simple(handle_t *handle,
+				struct ext4_allocation_request *ar, int *errp)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = ar->inode->i_sb;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int  i;
+	ext4_fsblk_t goal, block;
+	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+	goal = ar->goal;
+	if (goal < le32_to_cpu(es->s_first_data_block) ||
+			goal >= ext4_blocks_count(es))
+		goal = le32_to_cpu(es->s_first_data_block);
+
+	ar->len = 0;
+	ext4_get_group_no_and_offset(sb, goal, &group, &blkoff);
+	for (; group < ext4_get_groups_count(sb); group++) {
+		bitmap_bh = ext4_read_block_bitmap(sb, group);
+		if (IS_ERR(bitmap_bh)) {
+			*errp = PTR_ERR(bitmap_bh);
+			pr_warn("Failed to read block bitmap\n");
+			return 0;
+		}
+
+		ext4_get_group_no_and_offset(sb,
+			max(ext4_group_first_block_no(sb, group), goal),
+			NULL, &blkoff);
+		i = mb_find_next_zero_bit(bitmap_bh->b_data, sb->s_blocksize,
+						blkoff);
+		brelse(bitmap_bh);
+		if (i >= sb->s_blocksize)
+			continue;
+		if (ext4_fc_replay_check_excluded(sb,
+			ext4_group_first_block_no(sb, group) + i))
+			continue;
+		break;
+	}
+
+	if (group >= ext4_get_groups_count(sb) && i >= sb->s_blocksize)
+		return 0;
+
+	block = ext4_group_first_block_no(sb, group) + i;
+	ext4_mb_mark_bb(sb, block, 1, 1);
+	ar->len = 1;
+
+	return block;
+}
+
+static void ext4_free_blocks_simple(struct inode *inode, ext4_fsblk_t block,
+					unsigned long count)
+{
+	struct buffer_head *bitmap_bh;
+	struct super_block *sb = inode->i_sb;
+	struct ext4_group_desc *gdp;
+	struct buffer_head *gdp_bh;
+	ext4_group_t group;
+	ext4_grpblk_t blkoff;
+	int already_freed = 0, err, i;
+
+	ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+	bitmap_bh = ext4_read_block_bitmap(sb, group);
+	if (IS_ERR(bitmap_bh)) {
+		err = PTR_ERR(bitmap_bh);
+		pr_warn("Failed to read block bitmap\n");
+		return;
+	}
+	gdp = ext4_get_group_desc(sb, group, &gdp_bh);
+	if (!gdp)
+		return;
+
+	for (i = 0; i < count; i++) {
+		if (!mb_test_bit(blkoff + i, bitmap_bh->b_data))
+			already_freed++;
+	}
+	mb_clear_bits(bitmap_bh->b_data, blkoff, count);
+	err = ext4_handle_dirty_metadata(NULL, NULL, bitmap_bh);
+	if (err)
+		return;
+	ext4_free_group_clusters_set(
+		sb, gdp, ext4_free_group_clusters(sb, gdp) +
+		count - already_freed);
+	ext4_block_bitmap_csum_set(sb, group, gdp, bitmap_bh);
+	ext4_group_desc_csum_set(sb, group, gdp);
+	ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
+	sync_dirty_buffer(bitmap_bh);
+	sync_dirty_buffer(gdp_bh);
+	brelse(bitmap_bh);
+}
+
 /**
  * ext4_free_blocks() -- Free given blocks and update quota
  * @handle:		handle for this transaction
@@ -4747,6 +5079,13 @@
 	int err = 0;
 	int ret;
 
+	sbi = EXT4_SB(sb);
+
+	if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+		ext4_free_blocks_simple(inode, block, count);
+		return;
+	}
+
 	might_sleep();
 	if (bh) {
 		if (block)
@@ -4755,7 +5094,6 @@
 			block = bh->b_blocknr;
 	}
 
-	sbi = EXT4_SB(sb);
 	if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) &&
 	    !ext4_data_block_valid(sbi, block, count)) {
 		ext4_error(sb, "Freeing blocks not in datazone - "
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index f05ec9b..3eb1858 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2616,6 +2616,8 @@
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))
 			ext4_handle_sync(handle);
+		if (!err)
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2648,6 +2650,8 @@
 		err = ext4_add_nondir(handle, dentry, inode);
 		if (!err && IS_DIRSYNC(dir))
 			ext4_handle_sync(handle);
+		if (!err)
+			ext4_fc_track_create(handle, dentry);
 	}
 	if (handle)
 		ext4_journal_stop(handle);
@@ -2724,7 +2728,7 @@
 	return ext4_next_entry(de, blocksize);
 }
 
-static int ext4_init_new_dir(handle_t *handle, struct inode *dir,
+int ext4_init_new_dir(handle_t *handle, struct inode *dir,
 			     struct inode *inode)
 {
 	struct buffer_head *dir_block = NULL;
@@ -2806,11 +2810,13 @@
 		goto out_stop;
 	}
 	ext4_inc_count(handle, dir);
+
 	ext4_update_dx_flag(dir);
 	err = ext4_mark_inode_dirty(handle, dir);
 	if (err)
 		goto out_clear_inode;
 	d_instantiate_new(dentry, inode);
+	ext4_fc_track_create(handle, dentry);
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
@@ -3142,6 +3148,7 @@
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_dec_count(handle, dir);
 	ext4_update_dx_flag(dir);
+	ext4_fc_track_unlink(handle, dentry);
 	ext4_mark_inode_dirty(handle, dir);
 
 #ifdef CONFIG_UNICODE
@@ -3162,60 +3169,52 @@
 	return retval;
 }
 
-static int ext4_unlink(struct inode *dir, struct dentry *dentry)
+int __ext4_unlink(handle_t *handle, struct inode *dir, const struct qstr *d_name,
+		  struct inode *inode)
 {
-	int retval;
-	struct inode *inode;
+	int retval = -ENOENT;
 	struct buffer_head *bh;
 	struct ext4_dir_entry_2 *de;
-	handle_t *handle = NULL;
+	int skip_remove_dentry = 0;
 
-	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
-		return -EIO;
-
-	trace_ext4_unlink_enter(dir, dentry);
-	/* Initialize quotas before so that eventual writes go
-	 * in separate transaction */
-	retval = dquot_initialize(dir);
-	if (retval)
-		return retval;
-	retval = dquot_initialize(d_inode(dentry));
-	if (retval)
-		return retval;
-
-	retval = -ENOENT;
-	bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL);
+	bh = ext4_find_entry(dir, d_name, &de, NULL);
 	if (IS_ERR(bh))
 		return PTR_ERR(bh);
-	if (!bh)
-		goto end_unlink;
 
-	inode = d_inode(dentry);
+	if (!bh)
+		return -ENOENT;
 
 	retval = -EFSCORRUPTED;
-	if (le32_to_cpu(de->inode) != inode->i_ino)
-		goto end_unlink;
-
-	handle = ext4_journal_start(dir, EXT4_HT_DIR,
-				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
-	if (IS_ERR(handle)) {
-		retval = PTR_ERR(handle);
-		handle = NULL;
-		goto end_unlink;
+	if (le32_to_cpu(de->inode) != inode->i_ino) {
+		/*
+		 * It's okay if we find dont find dentry which matches
+		 * the inode. That's because it might have gotten
+		 * renamed to a different inode number
+		 */
+		if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+			skip_remove_dentry = 1;
+		else
+			goto out;
 	}
 
 	if (IS_DIRSYNC(dir))
 		ext4_handle_sync(handle);
 
-	retval = ext4_delete_entry(handle, dir, de, bh);
-	if (retval)
-		goto end_unlink;
-	dir->i_ctime = dir->i_mtime = current_time(dir);
-	ext4_update_dx_flag(dir);
-	ext4_mark_inode_dirty(handle, dir);
+	if (!skip_remove_dentry) {
+		retval = ext4_delete_entry(handle, dir, de, bh);
+		if (retval)
+			goto out;
+		dir->i_ctime = dir->i_mtime = current_time(dir);
+		ext4_update_dx_flag(dir);
+		retval = ext4_mark_inode_dirty(handle, dir);
+		if (retval)
+			goto out;
+	} else {
+		retval = 0;
+	}
 	if (inode->i_nlink == 0)
 		ext4_warning_inode(inode, "Deleting file '%.*s' with no links",
-				   dentry->d_name.len, dentry->d_name.name);
+				   d_name->len, d_name->name);
 	else
 		drop_nlink(inode);
 	if (!inode->i_nlink)
@@ -3223,6 +3222,41 @@
 	inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 
+out:
+	brelse(bh);
+	return retval;
+}
+
+static int ext4_unlink(struct inode *dir, struct dentry *dentry)
+{
+	handle_t *handle;
+	int retval;
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
+	trace_ext4_unlink_enter(dir, dentry);
+	/*
+	 * Initialize quotas before so that eventual writes go
+	 * in separate transaction
+	 */
+	retval = dquot_initialize(dir);
+	if (retval)
+		goto out_trace;
+	retval = dquot_initialize(d_inode(dentry));
+	if (retval)
+		goto out_trace;
+
+	handle = ext4_journal_start(dir, EXT4_HT_DIR,
+				    EXT4_DATA_TRANS_BLOCKS(dir->i_sb));
+	if (IS_ERR(handle)) {
+		retval = PTR_ERR(handle);
+		goto out_trace;
+	}
+
+	retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry));
+	if (!retval)
+		ext4_fc_track_unlink(handle, dentry);
 #ifdef CONFIG_UNICODE
 	/* VFS negative dentries are incompatible with Encoding and
 	 * Case-insensitiveness. Eventually we'll want avoid
@@ -3233,11 +3267,10 @@
 	if (IS_CASEFOLDED(dir))
 		d_invalidate(dentry);
 #endif
-
-end_unlink:
-	brelse(bh);
 	if (handle)
 		ext4_journal_stop(handle);
+
+out_trace:
 	trace_ext4_unlink_exit(dentry, retval);
 	return retval;
 }
@@ -3317,7 +3350,8 @@
 		 */
 		drop_nlink(inode);
 		err = ext4_orphan_add(handle, inode);
-		ext4_journal_stop(handle);
+		if (handle)
+			ext4_journal_stop(handle);
 		handle = NULL;
 		if (err)
 			goto err_drop_inode;
@@ -3372,29 +3406,10 @@
 	return err;
 }
 
-static int ext4_link(struct dentry *old_dentry,
-		     struct inode *dir, struct dentry *dentry)
+int __ext4_link(struct inode *dir, struct inode *inode, struct dentry *dentry)
 {
 	handle_t *handle;
-	struct inode *inode = d_inode(old_dentry);
 	int err, retries = 0;
-
-	if (inode->i_nlink >= EXT4_LINK_MAX)
-		return -EMLINK;
-
-	err = fscrypt_prepare_link(old_dentry, dir, dentry);
-	if (err)
-		return err;
-
-	if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
-	    (!projid_eq(EXT4_I(dir)->i_projid,
-			EXT4_I(old_dentry->d_inode)->i_projid)))
-		return -EXDEV;
-
-	err = dquot_initialize(dir);
-	if (err)
-		return err;
-
 retry:
 	handle = ext4_journal_start(dir, EXT4_HT_DIR,
 		(EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
@@ -3418,6 +3433,7 @@
 		if (inode->i_nlink == 1)
 			ext4_orphan_del(handle, inode);
 		d_instantiate(dentry, inode);
+		ext4_fc_track_link(handle, dentry);
 	} else {
 		drop_nlink(inode);
 		iput(inode);
@@ -3428,6 +3444,29 @@
 	return err;
 }
 
+static int ext4_link(struct dentry *old_dentry,
+		     struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = d_inode(old_dentry);
+	int err;
+
+	if (inode->i_nlink >= EXT4_LINK_MAX)
+		return -EMLINK;
+
+	err = fscrypt_prepare_link(old_dentry, dir, dentry);
+	if (err)
+		return err;
+
+	if ((ext4_test_inode_flag(dir, EXT4_INODE_PROJINHERIT)) &&
+	    (!projid_eq(EXT4_I(dir)->i_projid,
+			EXT4_I(old_dentry->d_inode)->i_projid)))
+		return -EXDEV;
+
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+	return __ext4_link(dir, inode, dentry);
+}
 
 /*
  * Try to find buffer head where contains the parent block.
@@ -3834,6 +3873,21 @@
 		}
 	}
 	ext4_mark_inode_dirty(handle, old.dir);
+	if (S_ISDIR(old.inode->i_mode)) {
+		/*
+		 * We disable fast commits here that's because the
+		 * replay code is not yet capable of changing dot dot
+		 * dirents in directories.
+		 */
+		ext4_fc_mark_ineligible(old.inode->i_sb,
+			EXT4_FC_REASON_RENAME_DIR);
+	} else {
+		if (new.inode)
+			ext4_fc_track_unlink(handle, new.dentry);
+		__ext4_fc_track_link(handle, old.inode, new.dentry);
+		__ext4_fc_track_unlink(handle, old.inode, old.dentry);
+	}
+
 	if (new.inode) {
 		ext4_mark_inode_dirty(handle, new.inode);
 		if (!new.inode->i_nlink)
@@ -3975,6 +4029,8 @@
 	new.inode->i_ctime = ctime;
 	ext4_mark_inode_dirty(handle, old.inode);
 	ext4_mark_inode_dirty(handle, new.inode);
+	ext4_fc_mark_ineligible(new.inode->i_sb,
+				EXT4_FC_REASON_CROSS_RENAME);
 
 	if (old.dir_bh) {
 		retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 2cc9f21..47a57fc 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -31,18 +31,56 @@
 #include "acl.h"
 
 static struct kmem_cache *io_end_cachep;
+static struct kmem_cache *io_end_vec_cachep;
 
 int __init ext4_init_pageio(void)
 {
 	io_end_cachep = KMEM_CACHE(ext4_io_end, SLAB_RECLAIM_ACCOUNT);
 	if (io_end_cachep == NULL)
 		return -ENOMEM;
+
+	io_end_vec_cachep = KMEM_CACHE(ext4_io_end_vec, 0);
+	if (io_end_vec_cachep == NULL) {
+		kmem_cache_destroy(io_end_cachep);
+		return -ENOMEM;
+	}
 	return 0;
 }
 
 void ext4_exit_pageio(void)
 {
 	kmem_cache_destroy(io_end_cachep);
+	kmem_cache_destroy(io_end_vec_cachep);
+}
+
+struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end)
+{
+	struct ext4_io_end_vec *io_end_vec;
+
+	io_end_vec = kmem_cache_zalloc(io_end_vec_cachep, GFP_NOFS);
+	if (!io_end_vec)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&io_end_vec->list);
+	list_add_tail(&io_end_vec->list, &io_end->list_vec);
+	return io_end_vec;
+}
+
+static void ext4_free_io_end_vec(ext4_io_end_t *io_end)
+{
+	struct ext4_io_end_vec *io_end_vec, *tmp;
+
+	if (list_empty(&io_end->list_vec))
+		return;
+	list_for_each_entry_safe(io_end_vec, tmp, &io_end->list_vec, list) {
+		list_del(&io_end_vec->list);
+		kmem_cache_free(io_end_vec_cachep, io_end_vec);
+	}
+}
+
+struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end)
+{
+	BUG_ON(list_empty(&io_end->list_vec));
+	return list_last_entry(&io_end->list_vec, struct ext4_io_end_vec, list);
 }
 
 /*
@@ -125,6 +163,7 @@
 		ext4_finish_bio(bio);
 		bio_put(bio);
 	}
+	ext4_free_io_end_vec(io_end);
 	kmem_cache_free(io_end_cachep, io_end);
 }
 
@@ -136,29 +175,26 @@
  * cannot get to ext4_ext_truncate() before all IOs overlapping that range are
  * completed (happens from ext4_free_ioend()).
  */
-static int ext4_end_io(ext4_io_end_t *io)
+static int ext4_end_io_end(ext4_io_end_t *io_end)
 {
-	struct inode *inode = io->inode;
-	loff_t offset = io->offset;
-	ssize_t size = io->size;
-	handle_t *handle = io->handle;
+	struct inode *inode = io_end->inode;
+	handle_t *handle = io_end->handle;
 	int ret = 0;
 
-	ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
+	ext4_debug("ext4_end_io_nolock: io_end 0x%p from inode %lu,list->next 0x%p,"
 		   "list->prev 0x%p\n",
-		   io, inode->i_ino, io->list.next, io->list.prev);
+		   io_end, inode->i_ino, io_end->list.next, io_end->list.prev);
 
-	io->handle = NULL;	/* Following call will use up the handle */
-	ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
+	io_end->handle = NULL;	/* Following call will use up the handle */
+	ret = ext4_convert_unwritten_io_end_vec(handle, io_end);
 	if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
 		ext4_msg(inode->i_sb, KERN_EMERG,
 			 "failed to convert unwritten extents to written "
 			 "extents -- potential data loss!  "
-			 "(inode %lu, offset %llu, size %zd, error %d)",
-			 inode->i_ino, offset, size, ret);
+			 "(inode %lu, error %d)", inode->i_ino, ret);
 	}
-	ext4_clear_io_unwritten_flag(io);
-	ext4_release_io_end(io);
+	ext4_clear_io_unwritten_flag(io_end);
+	ext4_release_io_end(io_end);
 	return ret;
 }
 
@@ -166,21 +202,21 @@
 {
 #ifdef	EXT4FS_DEBUG
 	struct list_head *cur, *before, *after;
-	ext4_io_end_t *io, *io0, *io1;
+	ext4_io_end_t *io_end, *io_end0, *io_end1;
 
 	if (list_empty(head))
 		return;
 
 	ext4_debug("Dump inode %lu completed io list\n", inode->i_ino);
-	list_for_each_entry(io, head, list) {
-		cur = &io->list;
+	list_for_each_entry(io_end, head, list) {
+		cur = &io_end->list;
 		before = cur->prev;
-		io0 = container_of(before, ext4_io_end_t, list);
+		io_end0 = container_of(before, ext4_io_end_t, list);
 		after = cur->next;
-		io1 = container_of(after, ext4_io_end_t, list);
+		io_end1 = container_of(after, ext4_io_end_t, list);
 
 		ext4_debug("io 0x%p from inode %lu,prev 0x%p,next 0x%p\n",
-			    io, inode->i_ino, io0, io1);
+			    io_end, inode->i_ino, io_end0, io_end1);
 	}
 #endif
 }
@@ -207,7 +243,7 @@
 static int ext4_do_flush_completed_IO(struct inode *inode,
 				      struct list_head *head)
 {
-	ext4_io_end_t *io;
+	ext4_io_end_t *io_end;
 	struct list_head unwritten;
 	unsigned long flags;
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -219,11 +255,11 @@
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 
 	while (!list_empty(&unwritten)) {
-		io = list_entry(unwritten.next, ext4_io_end_t, list);
-		BUG_ON(!(io->flag & EXT4_IO_END_UNWRITTEN));
-		list_del_init(&io->list);
+		io_end = list_entry(unwritten.next, ext4_io_end_t, list);
+		BUG_ON(!(io_end->flag & EXT4_IO_END_UNWRITTEN));
+		list_del_init(&io_end->list);
 
-		err = ext4_end_io(io);
+		err = ext4_end_io_end(io_end);
 		if (unlikely(!ret && err))
 			ret = err;
 	}
@@ -242,19 +278,22 @@
 
 ext4_io_end_t *ext4_init_io_end(struct inode *inode, gfp_t flags)
 {
-	ext4_io_end_t *io = kmem_cache_zalloc(io_end_cachep, flags);
-	if (io) {
-		io->inode = inode;
-		INIT_LIST_HEAD(&io->list);
-		atomic_set(&io->count, 1);
+	ext4_io_end_t *io_end = kmem_cache_zalloc(io_end_cachep, flags);
+
+	if (io_end) {
+		io_end->inode = inode;
+		INIT_LIST_HEAD(&io_end->list);
+		INIT_LIST_HEAD(&io_end->list_vec);
+		atomic_set(&io_end->count, 1);
 	}
-	return io;
+	return io_end;
 }
 
 void ext4_put_io_end_defer(ext4_io_end_t *io_end)
 {
 	if (atomic_dec_and_test(&io_end->count)) {
-		if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) || !io_end->size) {
+		if (!(io_end->flag & EXT4_IO_END_UNWRITTEN) ||
+				list_empty(&io_end->list_vec)) {
 			ext4_release_io_end(io_end);
 			return;
 		}
@@ -268,9 +307,8 @@
 
 	if (atomic_dec_and_test(&io_end->count)) {
 		if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
-			err = ext4_convert_unwritten_extents(io_end->handle,
-						io_end->inode, io_end->offset,
-						io_end->size);
+			err = ext4_convert_unwritten_io_end_vec(io_end->handle,
+								io_end);
 			io_end->handle = NULL;
 			ext4_clear_io_unwritten_flag(io_end);
 		}
@@ -307,10 +345,8 @@
 		struct inode *inode = io_end->inode;
 
 		ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
-			     "(offset %llu size %ld starting block %llu)",
+			     "starting block %llu)",
 			     bio->bi_status, inode->i_ino,
-			     (unsigned long long) io_end->offset,
-			     (long) io_end->size,
 			     (unsigned long long)
 			     bi_sector >> (inode->i_blkbits - 9));
 		mapping_set_error(inode->i_mapping,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0656846..b8cdb85 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -141,6 +141,68 @@
 MODULE_ALIAS("ext3");
 #define IS_EXT3_SB(sb) ((sb)->s_bdev->bd_holder == &ext3_fs_type)
 
+
+static inline void __ext4_read_bh(struct buffer_head *bh, int op_flags,
+				  bh_end_io_t *end_io)
+{
+	/*
+	 * buffer's verified bit is no longer valid after reading from
+	 * disk again due to write out error, clear it to make sure we
+	 * recheck the buffer contents.
+	 */
+	clear_buffer_verified(bh);
+
+	bh->b_end_io = end_io ? end_io : end_buffer_read_sync;
+	get_bh(bh);
+	submit_bh(REQ_OP_READ, op_flags, bh);
+}
+
+void ext4_read_bh_nowait(struct buffer_head *bh, int op_flags,
+			 bh_end_io_t *end_io)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (ext4_buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return;
+	}
+	__ext4_read_bh(bh, op_flags, end_io);
+}
+
+int ext4_read_bh(struct buffer_head *bh, int op_flags, bh_end_io_t *end_io)
+{
+	BUG_ON(!buffer_locked(bh));
+
+	if (ext4_buffer_uptodate(bh)) {
+		unlock_buffer(bh);
+		return 0;
+	}
+
+	__ext4_read_bh(bh, op_flags, end_io);
+
+	wait_on_buffer(bh);
+	if (buffer_uptodate(bh))
+		return 0;
+	return -EIO;
+}
+
+int ext4_read_bh_lock(struct buffer_head *bh, int op_flags, bool wait)
+{
+	if (trylock_buffer(bh)) {
+		if (wait)
+			return ext4_read_bh(bh, op_flags, NULL);
+		ext4_read_bh_nowait(bh, op_flags, NULL);
+		return 0;
+	}
+	if (wait) {
+		wait_on_buffer(bh);
+		if (buffer_uptodate(bh))
+			return 0;
+		return -EIO;
+	}
+	return 0;
+}
+
 /*
  * This works like sb_bread() except it uses ERR_PTR for error
  * returns.  Currently with sb_bread it's impossible to distinguish
@@ -463,9 +525,10 @@
 	if (sb_rdonly(sb) || test_opt(sb, ERRORS_CONT))
 		return;
 
-	EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+	ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 	if (journal)
 		jbd2_journal_abort(journal, -EIO);
+
 	/*
 	 * We force ERRORS_RO behavior when system is rebooting. Otherwise we
 	 * could panic during 'reboot -f' as the underlying device got already
@@ -686,6 +749,7 @@
 	va_end(args);
 
 	if (sb_rdonly(sb) == 0) {
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
 		/*
@@ -1109,6 +1173,8 @@
 	ei->i_datasync_tid = 0;
 	atomic_set(&ei->i_unwritten, 0);
 	INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work);
+	ext4_fc_init_inode(&ei->vfs_inode);
+	mutex_init(&ei->i_fc_lock);
 	return &ei->vfs_inode;
 }
 
@@ -1126,6 +1192,10 @@
 static void ext4_free_in_core_inode(struct inode *inode)
 {
 	fscrypt_free_inode(inode);
+	if (!list_empty(&(EXT4_I(inode)->i_fc_list))) {
+		pr_warn("%s: inode %ld still in fc list",
+			__func__, inode->i_ino);
+	}
 	kmem_cache_free(ext4_inode_cachep, EXT4_I(inode));
 }
 
@@ -1151,6 +1221,7 @@
 	init_rwsem(&ei->i_data_sem);
 	init_rwsem(&ei->i_mmap_sem);
 	inode_init_once(&ei->vfs_inode);
+	ext4_fc_init_inode(&ei->vfs_inode);
 }
 
 static int __init init_inodecache(void)
@@ -1179,6 +1250,7 @@
 
 void ext4_clear_inode(struct inode *inode)
 {
+	ext4_fc_del(inode);
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
 	ext4_discard_preallocations(inode);
@@ -1468,6 +1540,10 @@
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
 	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
+	Opt_prefetch_block_bitmaps,
+#ifdef CONFIG_EXT4_DEBUG
+	Opt_fc_debug_max_replay, Opt_fc_debug_force
+#endif
 };
 
 static const match_table_t tokens = {
@@ -1550,10 +1626,15 @@
 	{Opt_init_itable, "init_itable=%u"},
 	{Opt_init_itable, "init_itable"},
 	{Opt_noinit_itable, "noinit_itable"},
+#ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_force, "fc_debug_force"},
+	{Opt_fc_debug_max_replay, "fc_debug_max_replay=%u"},
+#endif
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
 	{Opt_nombcache, "nombcache"},
 	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
+	{Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"},
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1672,6 +1753,7 @@
 #define MOPT_NO_EXT3	0x0200
 #define MOPT_EXT4_ONLY	(MOPT_NO_EXT2 | MOPT_NO_EXT3)
 #define MOPT_STRING	0x0400
+#define	MOPT_2		0x1000
 
 static const struct mount_opts {
 	int	token;
@@ -1764,6 +1846,13 @@
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_GTE0},
 	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
+	{Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS,
+	 MOPT_SET},
+#ifdef CONFIG_EXT4_DEBUG
+	{Opt_fc_debug_force, EXT4_MOUNT2_JOURNAL_FAST_COMMIT,
+	 MOPT_SET | MOPT_2 | MOPT_EXT4_ONLY},
+	{Opt_fc_debug_max_replay, 0, MOPT_GTE0},
+#endif
 	{Opt_err, 0, 0}
 };
 
@@ -1828,7 +1917,7 @@
 		ext4_msg(sb, KERN_WARNING, "Ignoring removed %s option", opt);
 		return 1;
 	case Opt_abort:
-		sbi->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
 		return 1;
 	case Opt_i_version:
 		sb->s_flags |= SB_I_VERSION;
@@ -1923,6 +2012,10 @@
 		sbi->s_li_wait_mult = arg;
 	} else if (token == Opt_max_dir_size_kb) {
 		sbi->s_max_dir_size_kb = arg;
+#ifdef CONFIG_EXT4_DEBUG
+	} else if (token == Opt_fc_debug_max_replay) {
+		sbi->s_fc_debug_max_replay = arg;
+#endif
 	} else if (token == Opt_stripe) {
 		sbi->s_stripe = arg;
 	} else if (token == Opt_resuid) {
@@ -2064,10 +2157,17 @@
 			WARN_ON(1);
 			return -1;
 		}
-		if (arg != 0)
-			sbi->s_mount_opt |= m->mount_opt;
-		else
-			sbi->s_mount_opt &= ~m->mount_opt;
+		if (m->flags & MOPT_2) {
+			if (arg != 0)
+				sbi->s_mount_opt2 |= m->mount_opt;
+			else
+				sbi->s_mount_opt2 &= ~m->mount_opt;
+		} else {
+			if (arg != 0)
+				sbi->s_mount_opt |= m->mount_opt;
+			else
+				sbi->s_mount_opt &= ~m->mount_opt;
+		}
 	}
 	return 1;
 }
@@ -2077,7 +2177,7 @@
 			 unsigned int *journal_ioprio,
 			 int is_remount)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_sb_info __maybe_unused *sbi = EXT4_SB(sb);
 	char *p, __maybe_unused *usr_qf_name, __maybe_unused *grp_qf_name;
 	substring_t args[MAX_OPT_ARGS];
 	int token;
@@ -2131,16 +2231,6 @@
 		}
 	}
 #endif
-	if (test_opt(sb, DIOREAD_NOLOCK)) {
-		int blocksize =
-			BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
-
-		if (blocksize < PAGE_SIZE) {
-			ext4_msg(sb, KERN_ERR, "can't mount with "
-				 "dioread_nolock if block size != PAGE_SIZE");
-			return 0;
-		}
-	}
 	return 1;
 }
 
@@ -3058,15 +3148,34 @@
 static int ext4_run_li_request(struct ext4_li_request *elr)
 {
 	struct ext4_group_desc *gdp = NULL;
-	ext4_group_t group, ngroups;
-	struct super_block *sb;
+	struct super_block *sb = elr->lr_super;
+	ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count;
+	ext4_group_t group = elr->lr_next_group;
 	unsigned long timeout = 0;
+	unsigned int prefetch_ios = 0;
 	int ret = 0;
 
-	sb = elr->lr_super;
-	ngroups = EXT4_SB(sb)->s_groups_count;
+	if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) {
+		elr->lr_next_group = ext4_mb_prefetch(sb, group,
+				EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios);
+		if (prefetch_ios)
+			ext4_mb_prefetch_fini(sb, elr->lr_next_group,
+					      prefetch_ios);
+		trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group,
+					    prefetch_ios);
+		if (group >= elr->lr_next_group) {
+			ret = 1;
+			if (elr->lr_first_not_zeroed != ngroups &&
+			    !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) {
+				elr->lr_next_group = elr->lr_first_not_zeroed;
+				elr->lr_mode = EXT4_LI_MODE_ITABLE;
+				ret = 0;
+			}
+		}
+		return ret;
+	}
 
-	for (group = elr->lr_next_group; group < ngroups; group++) {
+	for (; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp) {
 			ret = 1;
@@ -3084,9 +3193,10 @@
 		timeout = jiffies;
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
+		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
 			timeout = (jiffies - timeout) *
-				  elr->lr_sbi->s_li_wait_mult;
+				EXT4_SB(elr->lr_super)->s_li_wait_mult;
 			elr->lr_timeout = timeout;
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3101,15 +3211,11 @@
  */
 static void ext4_remove_li_request(struct ext4_li_request *elr)
 {
-	struct ext4_sb_info *sbi;
-
 	if (!elr)
 		return;
 
-	sbi = elr->lr_sbi;
-
 	list_del(&elr->lr_request);
-	sbi->s_li_request = NULL;
+	EXT4_SB(elr->lr_super)->s_li_request = NULL;
 	kfree(elr);
 }
 
@@ -3318,7 +3424,6 @@
 static struct ext4_li_request *ext4_li_request_new(struct super_block *sb,
 					    ext4_group_t start)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_li_request *elr;
 
 	elr = kzalloc(sizeof(*elr), GFP_KERNEL);
@@ -3326,8 +3431,13 @@
 		return NULL;
 
 	elr->lr_super = sb;
-	elr->lr_sbi = sbi;
-	elr->lr_next_group = start;
+	elr->lr_first_not_zeroed = start;
+	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS))
+		elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
+	else {
+		elr->lr_mode = EXT4_LI_MODE_ITABLE;
+		elr->lr_next_group = start;
+	}
 
 	/*
 	 * Randomize first schedule time of the request to
@@ -3345,6 +3455,7 @@
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_li_request *elr = NULL;
 	ext4_group_t ngroups = sbi->s_groups_count;
+	enum ext4_li_mode lr_mode = EXT4_LI_MODE_ITABLE;
 	int ret = 0;
 
 	mutex_lock(&ext4_li_mtx);
@@ -3357,8 +3468,10 @@
 		goto out;
 	}
 
-	if (first_not_zeroed == ngroups || sb_rdonly(sb) ||
-	    !test_opt(sb, INIT_INODE_TABLE))
+	if (test_opt(sb, PREFETCH_BLOCK_BITMAPS)) {
+		lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP;
+	} else if (first_not_zeroed == ngroups || sb_rdonly(sb) ||
+		   !test_opt(sb, INIT_INODE_TABLE))
 		goto out;
 
 	elr = ext4_li_request_new(sb, first_not_zeroed);
@@ -3570,7 +3683,7 @@
 	 * loaded or not
 	 */
 	if (sbi->s_journal && !sbi->journal_bdev)
-		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_maxlen);
+		overhead += EXT4_NUM_B2C(sbi, sbi->s_journal->j_total_len);
 	else if (ext4_has_feature_journal(sb) && !sbi->s_journal && j_inum) {
 		/* j_inum for internal journal is non-zero */
 		j_inode = ext4_get_journal_inode(sb, j_inum);
@@ -3751,6 +3864,8 @@
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	set_opt(sb, POSIX_ACL);
 #endif
+	if (ext4_has_feature_fast_commit(sb))
+		set_opt2(sb, JOURNAL_FAST_COMMIT);
 	/* don't forget to enable journal_csum when metadata_csum is enabled. */
 	if (ext4_has_metadata_csum(sb))
 		set_opt(sb, JOURNAL_CHECKSUM);
@@ -3927,7 +4042,8 @@
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
 		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
 			    "with data=journal disables delayed "
-			    "allocation and O_DIRECT support!\n");
+			    "allocation, O_DIRECT and fast_commit support!\n");
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		if (test_opt2(sb, EXPLICIT_DELALLOC)) {
 			ext4_msg(sb, KERN_ERR, "can't mount with "
 				 "both data=journal and delalloc");
@@ -4353,6 +4469,26 @@
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
 
+	/* Initialize fast commit stuff */
+	atomic_set(&sbi->s_fc_subtid, 0);
+	atomic_set(&sbi->s_fc_ineligible_updates, 0);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_q[FC_Q_STAGING]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_MAIN]);
+	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
+	sbi->s_fc_bytes = 0;
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
+	spin_lock_init(&sbi->s_fc_lock);
+	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
+	sbi->s_fc_replay_state.fc_regions = NULL;
+	sbi->s_fc_replay_state.fc_regions_size = 0;
+	sbi->s_fc_replay_state.fc_regions_used = 0;
+	sbi->s_fc_replay_state.fc_regions_valid = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes = NULL;
+	sbi->s_fc_replay_state.fc_modified_inodes_size = 0;
+	sbi->s_fc_replay_state.fc_modified_inodes_used = 0;
+
 	sb->s_root = NULL;
 
 	needs_recovery = (es->s_last_orphan != 0 ||
@@ -4402,6 +4538,7 @@
 		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
+		clear_opt2(sb, JOURNAL_FAST_COMMIT);
 		sbi->s_journal = NULL;
 		needs_recovery = 0;
 		goto no_journal;
@@ -4420,6 +4557,14 @@
 		goto failed_mount_wq;
 	}
 
+	if (test_opt2(sb, JOURNAL_FAST_COMMIT) &&
+		!jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
+					  JBD2_FEATURE_INCOMPAT_FAST_COMMIT)) {
+		ext4_msg(sb, KERN_ERR,
+			"Failed to set fast commit journal feature");
+		goto failed_mount_wq;
+	}
+
 	/* We have now updated the journal if required, so we can
 	 * validate the data journaling mode. */
 	switch (test_opt(sb, DATA_FLAGS)) {
@@ -4569,6 +4714,7 @@
 			goto failed_mount4a;
 		}
 	}
+	ext4_fc_replay_cleanup(sb);
 
 	ext4_ext_init(sb);
 	err = ext4_mb_init(sb);
@@ -4770,6 +4916,7 @@
 	journal->j_commit_interval = sbi->s_commit_interval;
 	journal->j_min_batch_time = sbi->s_min_batch_time;
 	journal->j_max_batch_time = sbi->s_max_batch_time;
+	ext4_fc_init(sb, journal);
 
 	write_lock(&journal->j_state_lock);
 	if (test_opt(sb, BARRIER))
@@ -5427,7 +5574,7 @@
 		goto restore_opts;
 	}
 
-	if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
+	if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
 		ext4_abort(sb, "Abort forced by user");
 
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
@@ -5441,7 +5588,7 @@
 	}
 
 	if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
-		if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) {
+		if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
 			err = -EROFS;
 			goto restore_opts;
 		}
@@ -6263,6 +6410,11 @@
 	err = init_inodecache();
 	if (err)
 		goto out1;
+
+	err = ext4_fc_init_dentry_cache();
+	if (err)
+		goto out05;
+
 	register_as_ext3();
 	register_as_ext2();
 	err = register_filesystem(&ext4_fs_type);
@@ -6273,6 +6425,7 @@
 out:
 	unregister_as_ext2();
 	unregister_as_ext3();
+out05:
 	destroy_inodecache();
 out1:
 	ext4_exit_mballoc();
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index eb1efad..992b3ec5 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -198,6 +198,8 @@
 EXT4_ATTR(first_error_time, 0444, first_error_time);
 EXT4_ATTR(last_error_time, 0444, last_error_time);
 EXT4_ATTR(journal_task, 0444, journal_task);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch);
+EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -228,6 +230,8 @@
 	ATTR_LIST(first_error_time),
 	ATTR_LIST(last_error_time),
 	ATTR_LIST(journal_task),
+	ATTR_LIST(mb_prefetch),
+	ATTR_LIST(mb_prefetch_limit),
 	NULL,
 };
 ATTRIBUTE_GROUPS(ext4);
@@ -246,6 +250,7 @@
 EXT4_ATTR_FEATURE(verity);
 #endif
 EXT4_ATTR_FEATURE(metadata_csum_seed);
+EXT4_ATTR_FEATURE(fast_commit);
 
 static struct attribute *ext4_feat_attrs[] = {
 	ATTR_LIST(lazy_itable_init),
@@ -261,6 +266,7 @@
 	ATTR_LIST(verity),
 #endif
 	ATTR_LIST(metadata_csum_seed),
+	ATTR_LIST(fast_commit),
 	NULL,
 };
 ATTRIBUTE_GROUPS(ext4_feat);
@@ -419,6 +425,8 @@
 		proc_create_single_data("es_shrinker_info", S_IRUGO,
 				sbi->s_proc, ext4_seq_es_shrinker_info_show,
 				sb);
+		proc_create_single_data("fc_info", 0444, sbi->s_proc,
+					ext4_fc_info_show, sb);
 		proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
 				&ext4_mb_seq_groups_ops, sb);
 	}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 894a610..cdf9fce 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -2436,6 +2436,7 @@
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 cleanup:
 	brelse(is.iloc.bh);
@@ -2513,6 +2514,7 @@
 		if (error == 0)
 			error = error2;
 	}
+	ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 
 	return error;
 }
@@ -2945,6 +2947,7 @@
 					 error);
 			goto cleanup;
 		}
+		ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR);
 	}
 	error = 0;
 cleanup:
diff --git a/fs/file_table.c b/fs/file_table.c
index 30d55c9..b448f13 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -278,6 +278,7 @@
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
+	security_file_pre_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8814600..2b4faf9 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -202,6 +202,32 @@
 	return ret;
 }
 
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return journal_submit_inode_data_buffers(jinode->i_vfs_inode->i_mapping,
+						 jinode->i_dirty_start,
+						 jinode->i_dirty_end);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
+}
+EXPORT_SYMBOL(jbd2_wait_inode_data);
+
 /*
  * Submit all the data buffers of inode associated with the transaction to
  * disk.
@@ -413,6 +439,29 @@
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (journal->j_flags & JBD2_FAST_COMMIT_ONGOING) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+		/*
+		 * TODO: by blocking fast commits here, we are increasing
+		 * fsync() latency slightly. Strictly speaking, we don't need
+		 * to block fast commits until the transaction enters T_FLUSH
+		 * state. So an optimization is possible where we block new fast
+		 * commits here and wait for existing ones to complete
+		 * just before we enter T_FLUSH. That way, the existing fast
+		 * commits and this full commit can proceed parallely.
+		 */
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -420,6 +469,7 @@
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -762,7 +812,7 @@
 		if (first_block < journal->j_tail)
 			freed += journal->j_last - journal->j_first;
 		/* Update tail only if we free significant amount of space */
-		if (freed < journal->j_maxlen / 4)
+		if (freed < jbd2_journal_get_max_txn_bufs(journal))
 			update_tail = 0;
 	}
 	J_ASSERT(commit_transaction->t_state == T_COMMIT);
@@ -1115,12 +1165,16 @@
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1132,6 +1186,7 @@
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index b7c5819..c748f0a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -157,7 +157,9 @@
  *
  * 1) COMMIT:  Every so often we need to commit the current state of the
  *    filesystem to disk.  The journal thread is responsible for writing
- *    all of the metadata buffers to disk.
+ *    all of the metadata buffers to disk. If a fast commit is ongoing
+ *    journal thread waits until it's done and then continues from
+ *    there on.
  *
  * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
  *    of the data in that part of the log has been rewritten elsewhere on
@@ -714,6 +716,85 @@
 	return err;
 }
 
+/*
+ * Start a fast commit. If there's an ongoing fast or full commit wait for
+ * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY
+ * if a fast commit is not needed, either because there's an already a commit
+ * going on or this tid has already been committed. Returns -EINVAL if no jbd2
+ * commit has yet been performed.
+ */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
+{
+	if (unlikely(is_journal_aborted(journal)))
+		return -EIO;
+	/*
+	 * Fast commits only allowed if at least one full commit has
+	 * been processed.
+	 */
+	if (!journal->j_stats.ts_tid)
+		return -EINVAL;
+
+	write_lock(&journal->j_state_lock);
+	if (tid <= journal->j_commit_sequence) {
+		write_unlock(&journal->j_state_lock);
+		return -EALREADY;
+	}
+
+	if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+	    (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) {
+		DEFINE_WAIT(wait);
+
+		prepare_to_wait(&journal->j_fc_wait, &wait,
+				TASK_UNINTERRUPTIBLE);
+		write_unlock(&journal->j_state_lock);
+		schedule();
+		finish_wait(&journal->j_fc_wait, &wait);
+		return -EALREADY;
+	}
+	journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_begin_commit);
+
+/*
+ * Stop a fast commit. If fallback is set, this function starts commit of
+ * TID tid before any other fast commit can start.
+ */
+static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
+{
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 0);
+	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
+	if (fallback)
+		journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	write_unlock(&journal->j_state_lock);
+	wake_up(&journal->j_fc_wait);
+	if (fallback)
+		return jbd2_complete_transaction(journal, tid);
+	return 0;
+}
+
+int jbd2_fc_end_commit(journal_t *journal)
+{
+	return __jbd2_fc_end_commit(journal, 0, false);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit);
+
+int jbd2_fc_end_commit_fallback(journal_t *journal)
+{
+	tid_t tid;
+
+	read_lock(&journal->j_state_lock);
+	tid = journal->j_running_transaction ?
+		journal->j_running_transaction->t_tid : 0;
+	read_unlock(&journal->j_state_lock);
+	return __jbd2_fc_end_commit(journal, tid, true);
+}
+EXPORT_SYMBOL(jbd2_fc_end_commit_fallback);
+
 /* Return 1 when transaction with given tid has already committed. */
 int jbd2_transaction_committed(journal_t *journal, tid_t tid)
 {
@@ -782,6 +863,100 @@
 	return jbd2_journal_bmap(journal, blocknr, retp);
 }
 
+/* Map one fast commit buffer for use by the file system */
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out)
+{
+	unsigned long long pblock;
+	unsigned long blocknr;
+	int ret = 0;
+	struct buffer_head *bh;
+	int fc_off;
+
+	*bh_out = NULL;
+
+	if (journal->j_fc_off + journal->j_fc_first < journal->j_fc_last) {
+		fc_off = journal->j_fc_off;
+		blocknr = journal->j_fc_first + fc_off;
+		journal->j_fc_off++;
+	} else {
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	ret = jbd2_journal_bmap(journal, blocknr, &pblock);
+	if (ret)
+		return ret;
+
+	bh = __getblk(journal->j_dev, pblock, journal->j_blocksize);
+	if (!bh)
+		return -ENOMEM;
+
+
+	journal->j_fc_wbuf[fc_off] = bh;
+
+	*bh_out = bh;
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_get_buf);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	j_fc_off = journal->j_fc_off;
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) {
+		bh = journal->j_fc_wbuf[i];
+		wait_on_buffer(bh);
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+		if (unlikely(!buffer_uptodate(bh)))
+			return -EIO;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_wait_bufs);
+
+/*
+ * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf
+ * for completion.
+ */
+int jbd2_fc_release_bufs(journal_t *journal)
+{
+	struct buffer_head *bh;
+	int i, j_fc_off;
+
+	j_fc_off = journal->j_fc_off;
+
+	/*
+	 * Wait in reverse order to minimize chances of us being woken up before
+	 * all IOs have completed
+	 */
+	for (i = j_fc_off - 1; i >= 0; i--) {
+		bh = journal->j_fc_wbuf[i];
+		if (!bh)
+			break;
+		put_bh(bh);
+		journal->j_fc_wbuf[i] = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(jbd2_fc_release_bufs);
+
 /*
  * Conversion of logical to physical block numbers for the journal
  *
@@ -1126,6 +1301,7 @@
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
 	init_waitqueue_head(&journal->j_wait_reserved);
+	init_waitqueue_head(&journal->j_fc_wait);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
 	spin_lock_init(&journal->j_revoke_lock);
@@ -1155,9 +1331,10 @@
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
 	journal->j_blk_offset = start;
-	journal->j_maxlen = len;
+	journal->j_total_len = len;
 	n = journal->j_blocksize / sizeof(journal_block_tag_t);
 	journal->j_wbufsize = n;
+	journal->j_fc_wbuf = NULL;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
 	if (!journal->j_wbuf)
@@ -1297,15 +1474,22 @@
 	journal->j_first = first;
 	journal->j_last = last;
 
-	journal->j_head = first;
-	journal->j_tail = first;
-	journal->j_free = last - first;
+	journal->j_head = journal->j_first;
+	journal->j_tail = journal->j_first;
+	journal->j_free = journal->j_last - journal->j_first;
 
 	journal->j_tail_sequence = journal->j_transaction_sequence;
 	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
 	journal->j_commit_request = journal->j_commit_sequence;
 
-	journal->j_max_transaction_buffers = journal->j_maxlen / 4;
+	journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+
+	/*
+	 * Now that journal recovery is done, turn fast commits off here. This
+	 * way, if fast commit was enabled before the crash but if now FS has
+	 * disabled it, we don't enable fast commits.
+	 */
+	jbd2_clear_feature_fast_commit(journal);
 
 	/*
 	 * As a special case, if the on-disk copy is already marked as needing
@@ -1444,6 +1628,7 @@
 static void jbd2_mark_journal_empty(journal_t *journal, int write_op)
 {
 	journal_superblock_t *sb = journal->j_superblock;
+	bool had_fast_commit = false;
 
 	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
 	lock_buffer(journal->j_sb_buffer);
@@ -1457,9 +1642,20 @@
 
 	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
 	sb->s_start    = cpu_to_be32(0);
+	if (jbd2_has_feature_fast_commit(journal)) {
+		/*
+		 * When journal is clean, no need to commit fast commit flag and
+		 * make file system incompatible with older kernels.
+		 */
+		jbd2_clear_feature_fast_commit(journal);
+		had_fast_commit = true;
+	}
 
 	jbd2_write_superblock(journal, write_op);
 
+	if (had_fast_commit)
+		jbd2_set_feature_fast_commit(journal);
+
 	/* Log is no longer empty */
 	write_lock(&journal->j_state_lock);
 	journal->j_flags |= JBD2_FLUSHED;
@@ -1538,15 +1734,15 @@
 		goto out;
 	}
 
-	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
-		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
-	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
+	if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len)
+		journal->j_total_len = be32_to_cpu(sb->s_maxlen);
+	else if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) {
 		printk(KERN_WARNING "JBD2: journal file too short\n");
 		goto out;
 	}
 
 	if (be32_to_cpu(sb->s_first) == 0 ||
-	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
+	    be32_to_cpu(sb->s_first) >= journal->j_total_len) {
 		printk(KERN_WARNING
 			"JBD2: Invalid start block of journal: %u\n",
 			be32_to_cpu(sb->s_first));
@@ -1616,6 +1812,7 @@
 {
 	int err;
 	journal_superblock_t *sb;
+	int num_fc_blocks;
 
 	err = journal_get_superblock(journal);
 	if (err)
@@ -1626,8 +1823,17 @@
 	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
 	journal->j_tail = be32_to_cpu(sb->s_start);
 	journal->j_first = be32_to_cpu(sb->s_first);
-	journal->j_last = be32_to_cpu(sb->s_maxlen);
 	journal->j_errno = be32_to_cpu(sb->s_errno);
+	journal->j_last = be32_to_cpu(sb->s_maxlen);
+
+	if (jbd2_has_feature_fast_commit(journal)) {
+		journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
+		num_fc_blocks = jbd2_journal_get_num_fc_blks(sb);
+		if (journal->j_last - num_fc_blocks >= JBD2_MIN_JOURNAL_BLOCKS)
+			journal->j_last = journal->j_fc_last - num_fc_blocks;
+		journal->j_fc_first = journal->j_last + 1;
+		journal->j_fc_off = 0;
+	}
 
 	return 0;
 }
@@ -1772,6 +1978,7 @@
 		jbd2_journal_destroy_revoke(journal);
 	if (journal->j_chksum_driver)
 		crypto_free_shash(journal->j_chksum_driver);
+	kfree(journal->j_fc_wbuf);
 	kfree(journal->j_wbuf);
 	kfree(journal);
 
@@ -1846,6 +2053,35 @@
 	return 0;
 }
 
+static int
+jbd2_journal_initialize_fast_commit(journal_t *journal)
+{
+	journal_superblock_t *sb = journal->j_superblock;
+	unsigned long long num_fc_blks;
+
+	num_fc_blks = jbd2_journal_get_num_fc_blks(sb);
+	if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS)
+		return -ENOSPC;
+
+	/* Are we called twice? */
+	WARN_ON(journal->j_fc_wbuf != NULL);
+	journal->j_fc_wbuf = kmalloc_array(num_fc_blks,
+				sizeof(struct buffer_head *), GFP_KERNEL);
+	if (!journal->j_fc_wbuf)
+		return -ENOMEM;
+
+	journal->j_fc_wbufsize = num_fc_blks;
+	journal->j_fc_last = journal->j_last;
+	journal->j_last = journal->j_fc_last - num_fc_blks;
+	journal->j_fc_first = journal->j_last + 1;
+	journal->j_fc_off = 0;
+	journal->j_free = journal->j_last - journal->j_first;
+	journal->j_max_transaction_buffers =
+		jbd2_journal_get_max_txn_bufs(journal);
+
+	return 0;
+}
+
 /**
  * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
  * @journal: Journal to act on.
@@ -1889,6 +2125,13 @@
 
 	sb = journal->j_superblock;
 
+	if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) {
+		if (jbd2_journal_initialize_fast_commit(journal)) {
+			pr_err("JBD2: Cannot enable fast commits.\n");
+			return 0;
+		}
+	}
+
 	/* Load the checksum driver if necessary */
 	if ((journal->j_chksum_driver == NULL) &&
 	    INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) {
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index a4967b2..a5b9149 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -35,7 +35,6 @@
 	int		nr_revoke_hits;
 };
 
-enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
 static int do_one_pass(journal_t *journal,
 				struct recovery_info *info, enum passtype pass);
 static int scan_revoke_records(journal_t *, struct buffer_head *,
@@ -75,8 +74,8 @@
 
 	/* Do up to 128K of readahead */
 	max = start + (128 * 1024 / journal->j_blocksize);
-	if (max > journal->j_maxlen)
-		max = journal->j_maxlen;
+	if (max > journal->j_total_len)
+		max = journal->j_total_len;
 
 	/* Do the readahead itself.  We'll submit MAXBUF buffer_heads at
 	 * a time to the block device IO layer. */
@@ -135,7 +134,7 @@
 
 	*bhp = NULL;
 
-	if (offset >= journal->j_maxlen) {
+	if (offset >= journal->j_total_len) {
 		printk(KERN_ERR "JBD2: corrupted journal superblock\n");
 		return -EFSCORRUPTED;
 	}
@@ -225,10 +224,51 @@
 /* Make sure we wrap around the log correctly! */
 #define wrap(journal, var)						\
 do {									\
-	if (var >= (journal)->j_last)					\
-		var -= ((journal)->j_last - (journal)->j_first);	\
+	unsigned long _wrap_last =					\
+		jbd2_has_feature_fast_commit(journal) ?			\
+			(journal)->j_fc_last : (journal)->j_last;	\
+									\
+	if (var >= _wrap_last)						\
+		var -= (_wrap_last - (journal)->j_first);		\
 } while (0)
 
+static int fc_do_one_pass(journal_t *journal,
+			  struct recovery_info *info, enum passtype pass)
+{
+	unsigned int expected_commit_id = info->end_transaction;
+	unsigned long next_fc_block;
+	struct buffer_head *bh;
+	int err = 0;
+
+	next_fc_block = journal->j_fc_first;
+	if (!journal->j_fc_replay_callback)
+		return 0;
+
+	while (next_fc_block <= journal->j_fc_last) {
+		jbd_debug(3, "Fast commit replay: next block %ld",
+			  next_fc_block);
+		err = jread(&bh, journal, next_fc_block);
+		if (err) {
+			jbd_debug(3, "Fast commit replay: read error");
+			break;
+		}
+
+		jbd_debug(3, "Processing fast commit blk with seq %d");
+		err = journal->j_fc_replay_callback(journal, bh, pass,
+					next_fc_block - journal->j_fc_first,
+					expected_commit_id);
+		next_fc_block++;
+		if (err < 0 || err == JBD2_FC_REPLAY_STOP)
+			break;
+		err = 0;
+	}
+
+	if (err)
+		jbd_debug(3, "Fast commit replay failed, err = %d\n", err);
+
+	return err;
+}
+
 /**
  * jbd2_journal_recover - recovers a on-disk journal
  * @journal: the journal to recover
@@ -470,7 +510,9 @@
 				break;
 
 		jbd_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
-			  next_commit_ID, next_log_block, journal->j_last);
+			  next_commit_ID, next_log_block,
+			  jbd2_has_feature_fast_commit(journal) ?
+			  journal->j_fc_last : journal->j_last);
 
 		/* Skip over each chunk of the transaction looking
 		 * either the next descriptor block or the final commit
@@ -799,6 +841,13 @@
 				success = -EIO;
 		}
 	}
+
+	if (jbd2_has_feature_fast_commit(journal) &&  pass != PASS_REVOKE) {
+		err = fc_do_one_pass(journal, info, pass);
+		if (err)
+			success = err;
+	}
+
 	if (block_error && success == 0)
 		success = -EIO;
 	return success;
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 900e4ef..899311d 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -877,7 +877,7 @@
 		goto done;
 	}
 
-	trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
+	trace_ocfs2_journal_init_maxlen(j_journal->j_total_len);
 
 	*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
 		  OCFS2_JOURNAL_DIRTY_FL);
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index cb5629bd..9f650c7 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -103,3 +103,11 @@
 config PROC_PID_ARCH_STATUS
 	def_bool n
 	depends on PROC_FS
+
+config PROC_SELF_MEM_READONLY
+	bool "Force /proc/<pid>/mem paths to be read-only"
+	default y
+	help
+	  When enabled, attempts to open /proc/self/mem for write access
+	  will always fail.  Write access to this file allows bypassing
+	  of memory map permissions (such as modifying read-only code).
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 653c2d8..6081d08 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -148,6 +148,12 @@
 		NULL, &proc_pid_attr_operations,	\
 		{ .lsm = LSM })
 
+#ifdef CONFIG_PROC_SELF_MEM_READONLY
+# define PROC_PID_MEM_MODE S_IRUSR
+#else
+# define PROC_PID_MEM_MODE S_IRUSR|S_IWUSR
+#endif
+
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
  * and .. links.
@@ -877,7 +883,11 @@
 static ssize_t mem_write(struct file *file, const char __user *buf,
 			 size_t count, loff_t *ppos)
 {
+#ifdef CONFIG_PROC_SELF_MEM_READONLY
+	return -EACCES;
+#else
 	return mem_rw(file, (char __user*)buf, count, ppos, 1);
+#endif
 }
 
 loff_t mem_lseek(struct file *file, loff_t offset, int orig)
@@ -3026,7 +3036,7 @@
 #ifdef CONFIG_NUMA
 	REG("numa_maps",  S_IRUGO, proc_pid_numa_maps_operations),
 #endif
-	REG("mem",        S_IRUSR|S_IWUSR, proc_mem_operations),
+	REG("mem",        PROC_PID_MEM_MODE, proc_mem_operations),
 	LNK("cwd",        proc_cwd_link),
 	LNK("root",       proc_root_link),
 	LNK("exe",        proc_exe_link),
@@ -3427,7 +3437,7 @@
 #ifdef CONFIG_NUMA
 	REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations),
 #endif
-	REG("mem",       S_IRUSR|S_IWUSR, proc_mem_operations),
+	REG("mem",       PROC_PID_MEM_MODE, proc_mem_operations),
 	LNK("cwd",       proc_cwd_link),
 	LNK("root",      proc_root_link),
 	LNK("exe",       proc_exe_link),
diff --git a/include/linux/audit.h b/include/linux/audit.h
index aee3dc9..d887925 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -94,6 +94,17 @@
 struct audit_ntp_data {};
 #endif
 
+struct audit_task_info {
+	kuid_t			loginuid;
+	unsigned int		sessionid;
+	u64			contid;
+#ifdef CONFIG_AUDITSYSCALL
+	struct audit_context	*ctx;
+#endif
+};
+
+extern struct audit_task_info init_struct_audit;
+
 extern int is_audit_feature_set(int which);
 
 extern int __init audit_register_class(int class, unsigned *list);
@@ -130,6 +141,9 @@
 #ifdef CONFIG_AUDIT
 /* These are defined in audit.c */
 				/* Public API */
+extern int  audit_alloc(struct task_struct *task);
+extern void audit_free(struct task_struct *task);
+extern void __init audit_task_init(void);
 extern __printf(4, 5)
 void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type,
 	       const char *fmt, ...);
@@ -172,12 +186,25 @@
 
 static inline kuid_t audit_get_loginuid(struct task_struct *tsk)
 {
-	return tsk->loginuid;
+	if (!tsk->audit)
+		return INVALID_UID;
+	return tsk->audit->loginuid;
 }
 
 static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
 {
-	return tsk->sessionid;
+	if (!tsk->audit)
+		return AUDIT_SID_UNSET;
+	return tsk->audit->sessionid;
+}
+
+extern int audit_set_contid(struct task_struct *tsk, u64 contid);
+
+static inline u64 audit_get_contid(struct task_struct *tsk)
+{
+	if (!tsk->audit)
+		return AUDIT_CID_UNSET;
+	return tsk->audit->contid;
 }
 
 extern u32 audit_enabled;
@@ -185,6 +212,14 @@
 extern int audit_signal_info(int sig, struct task_struct *t);
 
 #else /* CONFIG_AUDIT */
+static inline int audit_alloc(struct task_struct *task)
+{
+	return 0;
+}
+static inline void audit_free(struct task_struct *task)
+{ }
+static inline void __init audit_task_init(void)
+{ }
 static inline __printf(4, 5)
 void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type,
 	       const char *fmt, ...)
@@ -236,6 +271,11 @@
 	return AUDIT_SID_UNSET;
 }
 
+static inline u64 audit_get_contid(struct task_struct *tsk)
+{
+	return AUDIT_CID_UNSET;
+}
+
 #define audit_enabled AUDIT_OFF
 
 static inline int audit_signal_info(int sig, struct task_struct *t)
@@ -260,8 +300,6 @@
 
 /* These are defined in auditsc.c */
 				/* Public API */
-extern int  audit_alloc(struct task_struct *task);
-extern void __audit_free(struct task_struct *task);
 extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1,
 				  unsigned long a2, unsigned long a3);
 extern void __audit_syscall_exit(int ret_success, long ret_value);
@@ -281,12 +319,14 @@
 
 static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx)
 {
-	task->audit_context = ctx;
+	task->audit->ctx = ctx;
 }
 
 static inline struct audit_context *audit_context(void)
 {
-	return current->audit_context;
+	if (!current->audit)
+		return NULL;
+	return current->audit->ctx;
 }
 
 static inline bool audit_dummy_context(void)
@@ -294,11 +334,7 @@
 	void *p = audit_context();
 	return !p || *(int *)p;
 }
-static inline void audit_free(struct task_struct *task)
-{
-	if (unlikely(task->audit_context))
-		__audit_free(task);
-}
+
 static inline void audit_syscall_entry(int major, unsigned long a0,
 				       unsigned long a1, unsigned long a2,
 				       unsigned long a3)
@@ -516,12 +552,6 @@
 extern int audit_n_rules;
 extern int audit_signals;
 #else /* CONFIG_AUDITSYSCALL */
-static inline int audit_alloc(struct task_struct *task)
-{
-	return 0;
-}
-static inline void audit_free(struct task_struct *task)
-{ }
 static inline void audit_syscall_entry(int major, unsigned long a0,
 				       unsigned long a1, unsigned long a2,
 				       unsigned long a3)
@@ -654,6 +684,16 @@
 	return uid_valid(audit_get_loginuid(tsk));
 }
 
+static inline bool audit_contid_valid(u64 contid)
+{
+	return contid != AUDIT_CID_UNSET;
+}
+
+static inline bool audit_contid_set(struct task_struct *tsk)
+{
+	return audit_contid_valid(audit_get_contid(tsk));
+}
+
 static inline void audit_log_string(struct audit_buffer *ab, const char *buf)
 {
 	audit_log_n_string(ab, buf, strlen(buf));
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d5338b9..c5869b17 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -480,6 +480,7 @@
 	void			*dma_drain_buffer;
 	unsigned int		dma_pad_mask;
 	unsigned int		dma_alignment;
+	unsigned int		split_alignment;
 
 	unsigned int		rq_timeout;
 	int			poll_nsec;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 169fd25..359fdae 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -378,6 +378,7 @@
 }
 
 #define cgroup_bpf_enabled (0)
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) ({ 0; })
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7aa0d8b..b6766a9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -205,6 +205,7 @@
 	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */
 
 	ARG_PTR_TO_CTX,		/* pointer to context */
+	ARG_PTR_TO_CTX_OR_NULL,	/* pointer to context or NULL */
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
@@ -1064,6 +1065,7 @@
 extern const struct bpf_func_proto bpf_strtol_proto;
 extern const struct bpf_func_proto bpf_strtoul_proto;
 extern const struct bpf_func_proto bpf_tcp_sock_proto;
+extern const struct bpf_func_proto bpf_jiffies64_proto;
 
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index b0e97e5..178a037 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -67,6 +67,7 @@
 extern void jbd2_free(void *ptr, size_t size);
 
 #define JBD2_MIN_JOURNAL_BLOCKS 1024
+#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256
 
 #ifdef __KERNEL__
 
@@ -262,7 +263,10 @@
 /* 0x0050 */
 	__u8	s_checksum_type;	/* checksum type */
 	__u8	s_padding2[3];
-	__u32	s_padding[42];
+/* 0x0054 */
+	__be32	s_num_fc_blks;		/* Number of fast commit blocks */
+/* 0x0058 */
+	__u32	s_padding[41];
 	__be32	s_checksum;		/* crc32c(superblock) */
 
 /* 0x0100 */
@@ -288,6 +292,7 @@
 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
 #define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
 #define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
+#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT	0x00000020
 
 /* See "journal feature predicate functions" below */
 
@@ -298,7 +303,8 @@
 					JBD2_FEATURE_INCOMPAT_64BIT | \
 					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
 					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
-					JBD2_FEATURE_INCOMPAT_CSUM_V3)
+					JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
+					JBD2_FEATURE_INCOMPAT_FAST_COMMIT)
 
 #ifdef __KERNEL__
 
@@ -754,6 +760,11 @@
 
 #define JBD2_NR_BATCH	64
 
+enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};
+
+#define JBD2_FC_REPLAY_STOP	0
+#define JBD2_FC_REPLAY_CONTINUE	1
+
 /**
  * struct journal_s - The journal_s type is the concrete type associated with
  *     journal_t.
@@ -860,6 +871,13 @@
 	wait_queue_head_t	j_wait_reserved;
 
 	/**
+	 * @j_fc_wait:
+	 *
+	 * Wait queue to wait for completion of async fast commits.
+	 */
+	wait_queue_head_t	j_fc_wait;
+
+	/**
 	 * @j_checkpoint_mutex:
 	 *
 	 * Semaphore for locking against concurrent checkpoints.
@@ -917,6 +935,31 @@
 	unsigned long		j_last;
 
 	/**
+	 * @j_fc_first:
+	 *
+	 * The block number of the first fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_first;
+
+	/**
+	 * @j_fc_off:
+	 *
+	 * Number of fast commit blocks currently allocated. Accessed only
+	 * during fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
+	 */
+	unsigned long		j_fc_off;
+
+	/**
+	 * @j_fc_last:
+	 *
+	 * The block number one beyond the last fast commit block in the journal
+	 * [j_state_lock].
+	 */
+	unsigned long		j_fc_last;
+
+	/**
 	 * @j_dev: Device where we store the journal.
 	 */
 	struct block_device	*j_dev;
@@ -947,9 +990,9 @@
 	struct block_device	*j_fs_dev;
 
 	/**
-	 * @j_maxlen: Total maximum capacity of the journal region on disk.
+	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
-	unsigned int		j_maxlen;
+	unsigned int		j_total_len;
 
 	/**
 	 * @j_reserved_credits:
@@ -1060,6 +1103,13 @@
 	struct buffer_head	**j_wbuf;
 
 	/**
+	 * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
+	 * during a fast commit. Currently only process can do fast commit, so
+	 * this field is not protected by any lock.
+	 */
+	struct buffer_head	**j_fc_wbuf;
+
+	/**
 	 * @j_wbufsize:
 	 *
 	 * Size of @j_wbuf array.
@@ -1067,6 +1117,13 @@
 	int			j_wbufsize;
 
 	/**
+	 * @j_fc_wbufsize:
+	 *
+	 * Size of @j_fc_wbuf array.
+	 */
+	int			j_fc_wbufsize;
+
+	/**
 	 * @j_last_sync_writer:
 	 *
 	 * The pid of the last person to run a synchronous operation
@@ -1165,6 +1222,30 @@
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+
+	/**
+	 * @j_fc_cleanup_callback:
+	 *
+	 * Clean-up after fast commit or full commit. JBD2 calls this function
+	 * after every commit operation.
+	 */
+	void (*j_fc_cleanup_callback)(struct journal_s *journal, int);
+
+	/*
+	 * @j_fc_replay_callback:
+	 *
+	 * File-system specific function that performs replay of a fast
+	 * commit. JBD2 calls this function for each fast commit block found in
+	 * the journal. This function should return JBD2_FC_REPLAY_CONTINUE
+	 * to indicate that the block was processed correctly and more fast
+	 * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP
+	 * indicates the end of replay (no more blocks remaining). A negative
+	 * return value indicates error.
+	 */
+	int (*j_fc_replay_callback)(struct journal_s *journal,
+				    struct buffer_head *bh,
+				    enum passtype pass, int off,
+				    tid_t expected_commit_id);
 };
 
 #define jbd2_might_wait_for_commit(j) \
@@ -1235,6 +1316,7 @@
 JBD2_FEATURE_INCOMPAT_FUNCS(async_commit,	ASYNC_COMMIT)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
+JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
 /*
  * Journal flag definitions
@@ -1249,6 +1331,8 @@
 						 * data write error in ordered
 						 * mode */
 #define JBD2_REC_ERR	0x080	/* The errno in the sb has been recorded */
+#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
+#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 
 /*
  * Function declarations for the journaling transaction and buffer
@@ -1499,6 +1583,21 @@
 extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
 extern int jbd2_cleanup_journal_tail(journal_t *);
 
+/* Fast commit related APIs */
+int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
+int jbd2_fc_end_commit(journal_t *journal);
+int jbd2_fc_end_commit_fallback(journal_t *journal);
+int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
+int jbd2_submit_inode_data(struct jbd2_inode *jinode);
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+int jbd2_fc_release_bufs(journal_t *journal);
+
+static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+{
+	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+}
+
 /*
  * is_journal_abort
  *
@@ -1559,6 +1658,13 @@
 	return journal->j_chksum_driver != NULL;
 }
 
+static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb)
+{
+	int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks);
+
+	return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS;
+}
+
 /*
  * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
  * transaction control blocks.
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index a376324..1299786 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -489,6 +489,10 @@
  * @file_free_security:
  *	Deallocate and free any security structures stored in file->f_security.
  *	@file contains the file structure being modified.
+ * @file_pre_free_security:
+ *	Perform any logging or LSM state updates for a file being deleted
+ *	using fields of the file before they have been cleared.
+ *	@file contains the file structure being freed
  * @file_ioctl:
  *	@file contains the file structure.
  *	@cmd contains the operation to perform.
@@ -565,6 +569,10 @@
  *	@clone_flags contains the flags indicating what should be shared.
  *	Handle allocation of task-related resources.
  *	Returns a zero on success, negative values on failure.
+ * @task_post_alloc:
+ *	@task task being allocated.
+ *	Handle allocation of task-related resources after all task fields are
+ *	filled in.
  * @task_free:
  *	@task task about to be freed.
  *	Handle release of task-related resources. (Note that this can be called
@@ -713,6 +721,9 @@
  *	@cred contains the cred of the process where the signal originated, or
  *	NULL if the current task is the originator.
  *	Return 0 if permission is granted.
+ * @task_exit:
+ *      Called early when a task is exiting before all state is lost.
+ *      @p contains the task_struct for process.
  * @task_prctl:
  *	Check permission before performing a process control operation on the
  *	current process.
@@ -1600,6 +1611,7 @@
 	int (*file_permission)(struct file *file, int mask);
 	int (*file_alloc_security)(struct file *file);
 	void (*file_free_security)(struct file *file);
+	void (*file_pre_free_security)(struct file *file);
 	int (*file_ioctl)(struct file *file, unsigned int cmd,
 				unsigned long arg);
 	int (*mmap_addr)(unsigned long addr);
@@ -1617,6 +1629,7 @@
 	int (*file_open)(struct file *file);
 
 	int (*task_alloc)(struct task_struct *task, unsigned long clone_flags);
+	void (*task_post_alloc)(struct task_struct *task); // Do not upstream.
 	void (*task_free)(struct task_struct *task);
 	int (*cred_alloc_blank)(struct cred *cred, gfp_t gfp);
 	void (*cred_free)(struct cred *cred);
@@ -1649,6 +1662,7 @@
 	int (*task_movememory)(struct task_struct *p);
 	int (*task_kill)(struct task_struct *p, struct kernel_siginfo *info,
 				int sig, const struct cred *cred);
+	void (*task_exit)(struct task_struct *p);
 	int (*task_prctl)(int option, unsigned long arg2, unsigned long arg3,
 				unsigned long arg4, unsigned long arg5);
 	void (*task_to_inode)(struct task_struct *p, struct inode *inode);
@@ -1818,6 +1832,14 @@
 	void (*bpf_prog_free_security)(struct bpf_prog_aux *aux);
 #endif /* CONFIG_BPF_SYSCALL */
 	int (*locked_down)(enum lockdown_reason what);
+#ifdef CONFIG_PERF_EVENTS
+	int (*perf_event_open)(struct perf_event_attr *attr, int type);
+	int (*perf_event_alloc)(struct perf_event *event);
+	void (*perf_event_free)(struct perf_event *event);
+	int (*perf_event_read)(struct perf_event *event);
+	int (*perf_event_write)(struct perf_event *event);
+
+#endif
 };
 
 struct security_hook_heads {
@@ -1906,6 +1928,7 @@
 	struct hlist_head file_permission;
 	struct hlist_head file_alloc_security;
 	struct hlist_head file_free_security;
+	struct hlist_head file_pre_free_security;
 	struct hlist_head file_ioctl;
 	struct hlist_head mmap_addr;
 	struct hlist_head mmap_file;
@@ -1917,6 +1940,7 @@
 	struct hlist_head file_receive;
 	struct hlist_head file_open;
 	struct hlist_head task_alloc;
+	struct hlist_head task_post_alloc;
 	struct hlist_head task_free;
 	struct hlist_head cred_alloc_blank;
 	struct hlist_head cred_free;
@@ -1943,6 +1967,7 @@
 	struct hlist_head task_getscheduler;
 	struct hlist_head task_movememory;
 	struct hlist_head task_kill;
+	struct hlist_head task_exit;
 	struct hlist_head task_prctl;
 	struct hlist_head task_to_inode;
 	struct hlist_head ipc_permission;
@@ -2060,6 +2085,13 @@
 	struct hlist_head bpf_prog_free_security;
 #endif /* CONFIG_BPF_SYSCALL */
 	struct hlist_head locked_down;
+#ifdef CONFIG_PERF_EVENTS
+	struct hlist_head perf_event_open;
+	struct hlist_head perf_event_alloc;
+	struct hlist_head perf_event_free;
+	struct hlist_head perf_event_read;
+	struct hlist_head perf_event_write;
+#endif
 } __randomize_layout;
 
 /*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 68ccc5b..4f77b22 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -56,6 +56,7 @@
 #include <linux/perf_regs.h>
 #include <linux/cgroup.h>
 #include <linux/refcount.h>
+#include <linux/security.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -721,6 +722,9 @@
 	struct perf_cgroup		*cgrp; /* cgroup event is attach to */
 #endif
 
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 	struct list_head		sb_list;
 #endif /* CONFIG_PERF_EVENTS */
 };
@@ -1241,19 +1245,41 @@
 int perf_event_max_stack_handler(struct ctl_table *table, int write,
 				 void __user *buffer, size_t *lenp, loff_t *ppos);
 
-static inline bool perf_paranoid_tracepoint_raw(void)
+/* Access to perf_event_open(2) syscall. */
+#define PERF_SECURITY_OPEN		0
+
+/* Finer grained perf_event_open(2) access control. */
+#define PERF_SECURITY_CPU		1
+#define PERF_SECURITY_KERNEL		2
+#define PERF_SECURITY_TRACEPOINT	3
+
+static inline int perf_is_paranoid(void)
 {
 	return sysctl_perf_event_paranoid > -1;
 }
 
-static inline bool perf_paranoid_cpu(void)
+static inline int perf_allow_kernel(struct perf_event_attr *attr)
 {
-	return sysctl_perf_event_paranoid > 0;
+	if (sysctl_perf_event_paranoid > 1 && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return security_perf_event_open(attr, PERF_SECURITY_KERNEL);
 }
 
-static inline bool perf_paranoid_kernel(void)
+static inline int perf_allow_cpu(struct perf_event_attr *attr)
 {
-	return sysctl_perf_event_paranoid > 1;
+	if (sysctl_perf_event_paranoid > 0 && !capable(CAP_SYS_ADMIN))
+		return -EACCES;
+
+	return security_perf_event_open(attr, PERF_SECURITY_CPU);
+}
+
+static inline int perf_allow_tracepoint(struct perf_event_attr *attr)
+{
+	if (sysctl_perf_event_paranoid > -1 && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return security_perf_event_open(attr, PERF_SECURITY_TRACEPOINT);
 }
 
 extern void perf_event_init(void);
diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h
index 49538b1..dded498 100644
--- a/include/linux/pid_namespace.h
+++ b/include/linux/pid_namespace.h
@@ -45,6 +45,9 @@
 	int hide_pid;
 	int reboot;	/* group exit code if this pidns was rebooted */
 	struct ns_common ns;
+#ifdef CONFIG_SECURITY_CONTAINER_MONITOR
+	u64 cid;  /* Main container identifier, zero if not assigned. */
+#endif
 } __randomize_layout;
 
 extern struct pid_namespace init_pid_ns;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5710b80..de9f8ae 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -33,7 +33,6 @@
 #include <linux/rseq.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
-struct audit_context;
 struct backing_dev_info;
 struct bio_list;
 struct blk_plug;
@@ -925,11 +924,7 @@
 	struct callback_head		*task_works;
 
 #ifdef CONFIG_AUDIT
-#ifdef CONFIG_AUDITSYSCALL
-	struct audit_context		*audit_context;
-#endif
-	kuid_t				loginuid;
-	unsigned int			sessionid;
+	struct audit_task_info		*audit;
 #endif
 	struct seccomp			seccomp;
 
@@ -1674,6 +1669,12 @@
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 
+/*
+ * Wake up tsk and try to swap it into the current tasks place, which
+ * initially means just trying to migrate it to the current CPU.
+ */
+extern int wake_up_swap(struct task_struct *tsk);
+
 #ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
 #else
diff --git a/include/linux/security.h b/include/linux/security.h
index df90399..0576e82 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -359,6 +359,7 @@
 int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_free(struct file *file);
+void security_file_pre_free(struct file *file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
@@ -373,6 +374,7 @@
 int security_file_receive(struct file *file);
 int security_file_open(struct file *file);
 int security_task_alloc(struct task_struct *task, unsigned long clone_flags);
+void security_task_post_alloc(struct task_struct *task);
 void security_task_free(struct task_struct *task);
 int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
 void security_cred_free(struct cred *cred);
@@ -404,6 +406,7 @@
 int security_task_movememory(struct task_struct *p);
 int security_task_kill(struct task_struct *p, struct kernel_siginfo *info,
 			int sig, const struct cred *cred);
+void security_task_exit(struct task_struct *p);
 int security_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			unsigned long arg4, unsigned long arg5);
 void security_task_to_inode(struct task_struct *p, struct inode *inode);
@@ -899,6 +902,9 @@
 static inline void security_file_free(struct file *file)
 { }
 
+static inline void security_file_pre_free(struct file *file)
+{ }
+
 static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 				      unsigned long arg)
 {
@@ -962,6 +968,9 @@
 	return 0;
 }
 
+static inline void security_task_post_alloc(struct task_struct *task)
+{ }
+
 static inline void security_task_free(struct task_struct *task)
 { }
 
@@ -1097,6 +1106,9 @@
 	return 0;
 }
 
+static inline void security_task_exit(struct task_struct *p)
+{ }
+
 static inline int security_task_prctl(int option, unsigned long arg2,
 				      unsigned long arg3,
 				      unsigned long arg4,
@@ -1897,5 +1909,41 @@
 #endif /* CONFIG_SECURITY */
 #endif /* CONFIG_BPF_SYSCALL */
 
-#endif /* ! __LINUX_SECURITY_H */
+#ifdef CONFIG_PERF_EVENTS
+struct perf_event_attr;
 
+#ifdef CONFIG_SECURITY
+extern int security_perf_event_open(struct perf_event_attr *attr, int type);
+extern int security_perf_event_alloc(struct perf_event *event);
+extern void security_perf_event_free(struct perf_event *event);
+extern int security_perf_event_read(struct perf_event *event);
+extern int security_perf_event_write(struct perf_event *event);
+#else
+static inline int security_perf_event_open(struct perf_event_attr *attr,
+					   int type)
+{
+	return 0;
+}
+
+static inline int security_perf_event_alloc(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline void security_perf_event_free(struct perf_event *event)
+{
+}
+
+static inline int security_perf_event_read(struct perf_event *event)
+{
+	return 0;
+}
+
+static inline int security_perf_event_write(struct perf_event *event)
+{
+	return 0;
+}
+#endif /* CONFIG_SECURITY */
+#endif /* CONFIG_PERF_EVENTS */
+
+#endif /* ! __LINUX_SECURITY_H */
diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h
index 4295de3..7e78e7d 100644
--- a/include/net/cls_cgroup.h
+++ b/include/net/cls_cgroup.h
@@ -45,9 +45,14 @@
 	sock_cgroup_set_classid(skcd, classid);
 }
 
+static inline u32 __task_get_classid(struct task_struct *task)
+{
+	return task_cls_state(task)->classid;
+}
+
 static inline u32 task_get_classid(const struct sk_buff *skb)
 {
-	u32 classid = task_cls_state(current)->classid;
+	u32 classid = __task_get_classid(current);
 
 	/* Due to the nature of the classifier it is required to ignore all
 	 * packets originating from softirq context as accessing `current'
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fe96bf2..81b9659 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -85,9 +85,8 @@
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 59802eb..9256097 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -385,10 +385,9 @@
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct sock *sk = skb_steal_sock(skb);
+	struct sock *sk = skb_steal_sock(skb, refcounted);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	*refcounted = true;
 	if (sk)
 		return sk;
 
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 0fca98a..aa42db4a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -165,6 +165,9 @@
 #ifdef CONFIG_XFRM
 	struct netns_xfrm	xfrm;
 #endif
+
+	atomic64_t		net_cookie; /* written once */
+
 #if IS_ENABLED(CONFIG_IP_VS)
 	struct netns_ipvs	*ipvs;
 #endif
@@ -222,6 +225,8 @@
 struct net *get_net_ns_by_pid(pid_t pid);
 struct net *get_net_ns_by_fd(int fd);
 
+u64 net_gen_cookie(struct net *net);
+
 #ifdef CONFIG_SYSCTL
 void ipx_register_sysctl(void);
 void ipx_unregister_sysctl(void);
diff --git a/include/net/sock.h b/include/net/sock.h
index e6a48eb..91179f6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1621,6 +1621,7 @@
 void sock_efree(struct sk_buff *skb);
 #ifdef CONFIG_INET
 void sock_edemux(struct sk_buff *skb);
+void sock_pfree(struct sk_buff *skb);
 #else
 #define sock_edemux sock_efree
 #endif
@@ -2484,16 +2485,14 @@
 	write_pnet(&sk->sk_net, net);
 }
 
-static inline struct sock *skb_steal_sock(struct sk_buff *skb)
+static inline bool
+skb_sk_is_prefetched(struct sk_buff *skb)
 {
-	if (skb->sk) {
-		struct sock *sk = skb->sk;
-
-		skb->destructor = NULL;
-		skb->sk = NULL;
-		return sk;
-	}
-	return NULL;
+#ifdef CONFIG_INET
+	return skb->destructor == sock_pfree;
+#else
+	return false;
+#endif /* CONFIG_INET */
 }
 
 /* This helper checks if a socket is a full socket,
@@ -2504,6 +2503,35 @@
 	return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV);
 }
 
+static inline bool
+sk_is_refcounted(struct sock *sk)
+{
+	/* Only full sockets have sk->sk_flags. */
+	return !sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE);
+}
+
+/**
+ * skb_steal_sock
+ * @skb to steal the socket from
+ * @refcounted is set to true if the socket is reference-counted
+ */
+static inline struct sock *
+skb_steal_sock(struct sk_buff *skb, bool *refcounted)
+{
+	if (skb->sk) {
+		struct sock *sk = skb->sk;
+
+		*refcounted = true;
+		if (skb_sk_is_prefetched(skb))
+			*refcounted = sk_is_refcounted(sk);
+		skb->destructor = NULL;
+		skb->sk = NULL;
+		return sk;
+	}
+	*refcounted = false;
+	return NULL;
+}
+
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
  * Check decrypted mark in case skb_orphan() cleared socket.
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d68e9e5..e33cea9 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -75,6 +75,17 @@
 	{ FALLOC_FL_COLLAPSE_RANGE,	"COLLAPSE_RANGE"},	\
 	{ FALLOC_FL_ZERO_RANGE,		"ZERO_RANGE"})
 
+#define show_fc_reason(reason)						\
+	__print_symbolic(reason,					\
+		{ EXT4_FC_REASON_XATTR,		"XATTR"},		\
+		{ EXT4_FC_REASON_CROSS_RENAME,	"CROSS_RENAME"},	\
+		{ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, "JOURNAL_FLAG_CHANGE"}, \
+		{ EXT4_FC_REASON_NOMEM,	"NO_MEM"},			\
+		{ EXT4_FC_REASON_SWAP_BOOT,	"SWAP_BOOT"},		\
+		{ EXT4_FC_REASON_RESIZE,	"RESIZE"},		\
+		{ EXT4_FC_REASON_RENAME_DIR,	"RENAME_DIR"},		\
+		{ EXT4_FC_REASON_FALLOC_RANGE,	"FALLOC_RANGE"},	\
+		{ EXT4_FC_REASON_INODE_JOURNAL_DATA,	"INODE_JOURNAL_DATA"})
 
 TRACE_EVENT(ext4_other_inode_update_time,
 	TP_PROTO(struct inode *inode, ino_t orig_ino),
@@ -1292,18 +1303,34 @@
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load,
+DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
 
 	TP_PROTO(struct super_block *sb, unsigned long group),
 
 	TP_ARGS(sb, group)
 );
 
-DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap,
+TRACE_EVENT(ext4_read_block_bitmap_load,
+	TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch),
 
-	TP_PROTO(struct super_block *sb, unsigned long group),
+	TP_ARGS(sb, group, prefetch),
 
-	TP_ARGS(sb, group)
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	bool,	prefetch		)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->prefetch = prefetch;
+	),
+
+	TP_printk("dev %d,%d group %u prefetch %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->prefetch)
 );
 
 TRACE_EVENT(ext4_direct_IO_enter,
@@ -1725,9 +1752,9 @@
 );
 
 TRACE_EVENT(ext4_load_inode,
-	TP_PROTO(struct inode *inode),
+	TP_PROTO(struct super_block *sb, unsigned long ino),
 
-	TP_ARGS(inode),
+	TP_ARGS(sb, ino),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev		)
@@ -1735,8 +1762,8 @@
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
-		__entry->ino		= inode->i_ino;
+		__entry->dev		= sb->s_dev;
+		__entry->ino		= ino;
 	),
 
 	TP_printk("dev %d,%d ino %ld",
@@ -2703,6 +2730,261 @@
 		  __entry->function, __entry->line)
 );
 
+TRACE_EVENT(ext4_prefetch_bitmaps,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group,
+		     ext4_group_t next, unsigned int prefetch_ios),
+
+	TP_ARGS(sb, group, next, prefetch_ios),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+		__field(	__u32,	next			)
+		__field(	__u32,	ios			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+		__entry->next	= next;
+		__entry->ios	= prefetch_ios;
+	),
+
+	TP_printk("dev %d,%d group %u next %u ios %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->group, __entry->next, __entry->ios)
+);
+
+TRACE_EVENT(ext4_lazy_itable_init,
+	    TP_PROTO(struct super_block *sb, ext4_group_t group),
+
+	TP_ARGS(sb, group),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %d,%d group %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group)
+);
+
+TRACE_EVENT(ext4_fc_replay_scan,
+	TP_PROTO(struct super_block *sb, int error, int off),
+
+	TP_ARGS(sb, error, off),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, error)
+		__field(int, off)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->error = error;
+		__entry->off = off;
+	),
+
+	TP_printk("FC scan pass on dev %d,%d: error %d, off %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->error, __entry->off)
+);
+
+TRACE_EVENT(ext4_fc_replay,
+	TP_PROTO(struct super_block *sb, int tag, int ino, int priv1, int priv2),
+
+	TP_ARGS(sb, tag, ino, priv1, priv2),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, tag)
+		__field(int, ino)
+		__field(int, priv1)
+		__field(int, priv2)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->tag = tag;
+		__entry->ino = ino;
+		__entry->priv1 = priv1;
+		__entry->priv2 = priv2;
+	),
+
+	TP_printk("FC Replay %d,%d: tag %d, ino %d, data1 %d, data2 %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->tag, __entry->ino, __entry->priv1, __entry->priv2)
+);
+
+TRACE_EVENT(ext4_fc_commit_start,
+	TP_PROTO(struct super_block *sb),
+
+	TP_ARGS(sb),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+	),
+
+	TP_printk("fast_commit started on dev %d,%d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev))
+);
+
+TRACE_EVENT(ext4_fc_commit_stop,
+	    TP_PROTO(struct super_block *sb, int nblks, int reason),
+
+	TP_ARGS(sb, nblks, reason),
+
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(int, nblks)
+		__field(int, reason)
+		__field(int, num_fc)
+		__field(int, num_fc_ineligible)
+		__field(int, nblks_agg)
+	),
+
+	TP_fast_assign(
+		__entry->dev = sb->s_dev;
+		__entry->nblks = nblks;
+		__entry->reason = reason;
+		__entry->num_fc = EXT4_SB(sb)->s_fc_stats.fc_num_commits;
+		__entry->num_fc_ineligible =
+			EXT4_SB(sb)->s_fc_stats.fc_ineligible_commits;
+		__entry->nblks_agg = EXT4_SB(sb)->s_fc_stats.fc_numblks;
+	),
+
+	TP_printk("fc on [%d,%d] nblks %d, reason %d, fc = %d, ineligible = %d, agg_nblks %d",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->nblks, __entry->reason, __entry->num_fc,
+		  __entry->num_fc_ineligible, __entry->nblks_agg)
+);
+
+#define FC_REASON_NAME_STAT(reason)					\
+	show_fc_reason(reason),						\
+	__entry->sbi->s_fc_stats.fc_ineligible_reason_count[reason]
+
+TRACE_EVENT(ext4_fc_stats,
+	    TP_PROTO(struct super_block *sb),
+
+	    TP_ARGS(sb),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(struct ext4_sb_info *, sbi)
+		    __field(int, count)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = sb->s_dev;
+		    __entry->sbi = EXT4_SB(sb);
+		    ),
+
+	    TP_printk("dev %d:%d fc ineligible reasons:\n"
+		      "%s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d, %s:%d; "
+		      "num_commits:%ld, ineligible: %ld, numblks: %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_XATTR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_CROSS_RENAME),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_JOURNAL_FLAG_CHANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_NOMEM),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_SWAP_BOOT),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RESIZE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_RENAME_DIR),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_FALLOC_RANGE),
+		      FC_REASON_NAME_STAT(EXT4_FC_REASON_INODE_JOURNAL_DATA),
+		      __entry->sbi->s_fc_stats.fc_num_commits,
+		      __entry->sbi->s_fc_stats.fc_ineligible_commits,
+		      __entry->sbi->s_fc_stats.fc_numblks)
+
+);
+
+#define DEFINE_TRACE_DENTRY_EVENT(__type)				\
+	TRACE_EVENT(ext4_fc_track_##__type,				\
+	    TP_PROTO(struct inode *inode, struct dentry *dentry, int ret), \
+									\
+	    TP_ARGS(inode, dentry, ret),				\
+									\
+	    TP_STRUCT__entry(						\
+		    __field(dev_t, dev)					\
+		    __field(int, ino)					\
+		    __field(int, error)					\
+		    ),							\
+									\
+	    TP_fast_assign(						\
+		    __entry->dev = inode->i_sb->s_dev;			\
+		    __entry->ino = inode->i_ino;			\
+		    __entry->error = ret;				\
+		    ),							\
+									\
+	    TP_printk("dev %d:%d, inode %d, error %d, fc_%s",		\
+		      MAJOR(__entry->dev), MINOR(__entry->dev),		\
+		      __entry->ino, __entry->error,			\
+		      #__type)						\
+	)
+
+DEFINE_TRACE_DENTRY_EVENT(create);
+DEFINE_TRACE_DENTRY_EVENT(link);
+DEFINE_TRACE_DENTRY_EVENT(unlink);
+
+TRACE_EVENT(ext4_fc_track_inode,
+	    TP_PROTO(struct inode *inode, int ret),
+
+	    TP_ARGS(inode, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error)
+	);
+
+TRACE_EVENT(ext4_fc_track_range,
+	    TP_PROTO(struct inode *inode, long start, long end, int ret),
+
+	    TP_ARGS(inode, start, end, ret),
+
+	    TP_STRUCT__entry(
+		    __field(dev_t, dev)
+		    __field(int, ino)
+		    __field(long, start)
+		    __field(long, end)
+		    __field(int, error)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->dev = inode->i_sb->s_dev;
+		    __entry->ino = inode->i_ino;
+		    __entry->start = start;
+		    __entry->end = end;
+		    __entry->error = ret;
+		    ),
+
+	    TP_printk("dev %d:%d, inode %d, error %d, start %ld, end %ld",
+		      MAJOR(__entry->dev), MINOR(__entry->dev),
+		      __entry->ino, __entry->error, __entry->start,
+		      __entry->end)
+	);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index c89c649..5d0ea2a 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -71,6 +71,7 @@
 #define AUDIT_TTY_SET		1017	/* Set TTY auditing status */
 #define AUDIT_SET_FEATURE	1018	/* Turn an audit feature on or off */
 #define AUDIT_GET_FEATURE	1019	/* Get which features are enabled */
+#define AUDIT_CONTAINER_OP	1020	/* Define the container id and info */
 
 #define AUDIT_FIRST_USER_MSG	1100	/* Userspace messages mostly uninteresting to kernel */
 #define AUDIT_USER_AVC		1107	/* We filter this differently */
@@ -488,6 +489,7 @@
 
 #define AUDIT_UID_UNSET (unsigned int)-1
 #define AUDIT_SID_UNSET ((unsigned int)-1)
+#define AUDIT_CID_UNSET ((u64)-1)
 
 /* audit_rule_data supports filter rules with both integer and string
  * fields.  It corresponds with AUDIT_ADD_RULE, AUDIT_DEL_RULE and
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 8649422..005e8aa 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -199,6 +199,16 @@
 	BPF_CGROUP_UDP6_RECVMSG,
 	BPF_CGROUP_GETSOCKOPT,
 	BPF_CGROUP_SETSOCKOPT,
+	BPF_TRACE_RAW_TP,
+	BPF_TRACE_FENTRY,
+	BPF_TRACE_FEXIT,
+	BPF_MODIFY_RETURN,
+	BPF_LSM_MAC,
+	BPF_TRACE_ITER,
+	BPF_CGROUP_INET4_GETPEERNAME,
+	BPF_CGROUP_INET6_GETPEERNAME,
+	BPF_CGROUP_INET4_GETSOCKNAME,
+	BPF_CGROUP_INET6_GETSOCKNAME,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -2750,6 +2760,231 @@
  *		**-EOPNOTSUPP** kernel configuration does not enable SYN cookies
  *
  *		**-EPROTONOSUPPORT** IP packet version is not 4 or 6
+ *
+ * int bpf_skb_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * 	Description
+ * 		Write raw *data* blob into a special BPF perf event held by
+ * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ * 		event must have the following attributes: **PERF_SAMPLE_RAW**
+ * 		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ * 		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ * 		The *flags* are used to indicate the index in *map* for which
+ * 		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ * 		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ * 		to indicate that the index of the current CPU core should be
+ * 		used.
+ *
+ * 		The value to write, of *size*, is passed through eBPF stack and
+ * 		pointed by *data*.
+ *
+ * 		*ctx* is a pointer to in-kernel struct sk_buff.
+ *
+ * 		This helper is similar to **bpf_perf_event_output**\ () but
+ * 		restricted to raw_tracepoint bpf programs.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Safely attempt to read *size* bytes from user space address
+ * 		*unsafe_ptr* and store the data in *dst*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Safely attempt to read *size* bytes from kernel space address
+ * 		*unsafe_ptr* and store the data in *dst*.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_probe_read_user_str(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Copy a NUL terminated string from an unsafe user address
+ * 		*unsafe_ptr* to *dst*. The *size* should include the
+ * 		terminating NUL byte. In case the string length is smaller than
+ * 		*size*, the target is not padded with further NUL bytes. If the
+ * 		string length is larger than *size*, just *size*-1 bytes are
+ * 		copied and the last byte is set to NUL.
+ *
+ * 		On success, the length of the copied string is returned. This
+ * 		makes this helper useful in tracing programs for reading
+ * 		strings, and more importantly to get its length at runtime. See
+ * 		the following snippet:
+ *
+ * 		::
+ *
+ * 			SEC("kprobe/sys_open")
+ * 			void bpf_sys_open(struct pt_regs *ctx)
+ * 			{
+ * 			        char buf[PATHLEN]; // PATHLEN is defined to 256
+ * 			        int res = bpf_probe_read_user_str(buf, sizeof(buf),
+ * 				                                  ctx->di);
+ *
+ * 				// Consume buf, for example push it to
+ * 				// userspace via bpf_perf_event_output(); we
+ * 				// can use res (the string length) as event
+ * 				// size, after checking its boundaries.
+ * 			}
+ *
+ * 		In comparison, using **bpf_probe_read_user()** helper here
+ * 		instead to read the string would require to estimate the length
+ * 		at compile time, and would often result in copying more memory
+ * 		than necessary.
+ *
+ * 		Another useful use case is when parsing individual process
+ * 		arguments or individual environment variables navigating
+ * 		*current*\ **->mm->arg_start** and *current*\
+ * 		**->mm->env_start**: using this helper and the return value,
+ * 		one can quickly iterate at the right offset of the memory area.
+ * 	Return
+ * 		On success, the strictly positive length of the string,
+ * 		including the trailing NUL character. On error, a negative
+ * 		value.
+ *
+ * int bpf_probe_read_kernel_str(void *dst, u32 size, const void *unsafe_ptr)
+ * 	Description
+ * 		Copy a NUL terminated string from an unsafe kernel address *unsafe_ptr*
+ * 		to *dst*. Same semantics as with bpf_probe_read_user_str() apply.
+ * 	Return
+ * 		On success, the strictly positive length of the string,	including
+ * 		the trailing NUL character. On error, a negative value.
+ *
+ * int bpf_tcp_send_ack(void *tp, u32 rcv_nxt)
+ *	Description
+ *		Send out a tcp-ack. *tp* is the in-kernel struct tcp_sock.
+ *		*rcv_nxt* is the ack_seq to be sent out.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_send_signal_thread(u32 sig)
+ *	Description
+ *		Send signal *sig* to the thread corresponding to the current task.
+ *	Return
+ *		0 on success or successfully queued.
+ *
+ *		**-EBUSY** if work queue under nmi is full.
+ *
+ *		**-EINVAL** if *sig* is invalid.
+ *
+ *		**-EPERM** if no permission to send the *sig*.
+ *
+ *		**-EAGAIN** if bpf program can try again.
+ *
+ * u64 bpf_jiffies64(void)
+ *	Description
+ *		Obtain the 64bit jiffies
+ *	Return
+ *		The 64 bit jiffies
+ *
+ * int bpf_read_branch_records(struct bpf_perf_event_data *ctx, void *buf, u32 size, u64 flags)
+ *	Description
+ *		For an eBPF program attached to a perf event, retrieve the
+ *		branch records (struct perf_branch_entry) associated to *ctx*
+ *		and store it in	the buffer pointed by *buf* up to size
+ *		*size* bytes.
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		The *flags* can be set to **BPF_F_GET_BRANCH_RECORDS_SIZE** to
+ *		instead	return the number of bytes required to store all the
+ *		branch entries. If this flag is set, *buf* may be NULL.
+ *
+ *		**-EINVAL** if arguments invalid or **size** not a multiple
+ *		of sizeof(struct perf_branch_entry).
+ *
+ *		**-ENOENT** if architecture does not support branch records.
+ *
+ * int bpf_get_ns_current_pid_tgid(u64 dev, u64 ino, struct bpf_pidns_info *nsdata, u32 size)
+ *	Description
+ *		Returns 0 on success, values for *pid* and *tgid* as seen from the current
+ *		*namespace* will be returned in *nsdata*.
+ *
+ *		On failure, the returned value is one of the following:
+ *
+ *		**-EINVAL** if dev and inum supplied don't match dev_t and inode number
+ *              with nsfs of current task, or if dev conversion to dev_t lost high bits.
+ *
+ *		**-ENOENT** if pidns does not exists for the current task.
+ *
+ * int bpf_xdp_output(void *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ *	Description
+ *		Write raw *data* blob into a special BPF perf event held by
+ *		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
+ *		event must have the following attributes: **PERF_SAMPLE_RAW**
+ *		as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and
+ *		**PERF_COUNT_SW_BPF_OUTPUT** as **config**.
+ *
+ *		The *flags* are used to indicate the index in *map* for which
+ *		the value must be put, masked with **BPF_F_INDEX_MASK**.
+ *		Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU**
+ *		to indicate that the index of the current CPU core should be
+ *		used.
+ *
+ *		The value to write, of *size*, is passed through eBPF stack and
+ *		pointed by *data*.
+ *
+ *		*ctx* is a pointer to in-kernel struct xdp_buff.
+ *
+ *		This helper is similar to **bpf_perf_eventoutput**\ () but
+ *		restricted to raw_tracepoint bpf programs.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * u64 bpf_get_netns_cookie(void *ctx)
+ * 	Description
+ * 		Retrieve the cookie (generated by the kernel) of the network
+ * 		namespace the input *ctx* is associated with. The network
+ * 		namespace cookie remains stable for its lifetime and provides
+ * 		a global identifier that can be assumed unique. If *ctx* is
+ * 		NULL, then the helper returns the cookie for the initial
+ * 		network namespace. The cookie itself is very similar to that
+ * 		of bpf_get_socket_cookie() helper, but for network namespaces
+ * 		instead of sockets.
+ * 	Return
+ * 		A 8-byte long opaque number.
+ *
+ * u64 bpf_get_current_ancestor_cgroup_id(int ancestor_level)
+ * 	Description
+ * 		Return id of cgroup v2 that is ancestor of the cgroup associated
+ * 		with the current task at the *ancestor_level*. The root cgroup
+ * 		is at *ancestor_level* zero and each step down the hierarchy
+ * 		increments the level. If *ancestor_level* == level of cgroup
+ * 		associated with the current task, then return value will be the
+ * 		same as that of **bpf_get_current_cgroup_id**\ ().
+ *
+ * 		The helper is useful to implement policies based on cgroups
+ * 		that are upper in hierarchy than immediate cgroup associated
+ * 		with the current task.
+ *
+ * 		The format of returned id and helper limitations are same as in
+ * 		**bpf_get_current_cgroup_id**\ ().
+ * 	Return
+ * 		The id is returned or 0 in case the id could not be retrieved.
+ *
+ * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags)
+ *	Description
+ *		Assign the *sk* to the *skb*. When combined with appropriate
+ *		routing configuration to receive the packet towards the socket,
+ *		will cause *skb* to be delivered to the specified socket.
+ *		Subsequent redirection of *skb* via  **bpf_redirect**\ (),
+ *		**bpf_clone_redirect**\ () or other methods outside of BPF may
+ *		interfere with successful delivery to the socket.
+ *
+ *		This operation is only valid from TC ingress path.
+ *
+ *		The *flags* argument must be zero.
+ *	Return
+ *		0 on success, or a negative errno in case of failure.
+ *
+ *		* **-EINVAL**		Unsupported flags specified.
+ *		* **-ENOENT**		Socket is unavailable for assignment.
+ *		* **-ENETUNREACH**	Socket is unreachable (wrong netns).
+ *		* **-EOPNOTSUPP**	Unsupported operation, for example a
+ *					call from outside of TC ingress.
+ *		* **-ESOCKTNOSUPPORT**	Socket type not supported (reuseport).
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2862,7 +3097,21 @@
 	FN(sk_storage_get),		\
 	FN(sk_storage_delete),		\
 	FN(send_signal),		\
-	FN(tcp_gen_syncookie),
+	FN(tcp_gen_syncookie),		\
+	FN(skb_output),			\
+	FN(probe_read_user),		\
+	FN(probe_read_kernel),		\
+	FN(probe_read_user_str),	\
+	FN(probe_read_kernel_str),	\
+	FN(tcp_send_ack),		\
+	FN(send_signal_thread),		\
+	FN(jiffies64),			\
+	FN(read_branch_records),	\
+	FN(get_ns_current_pid_tgid),	\
+	FN(xdp_output),			\
+	FN(get_netns_cookie),		\
+	FN(get_current_ancestor_cgroup_id),	\
+	FN(sk_assign),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h
index a89eb0a..7e2b8a8 100644
--- a/include/uapi/linux/futex.h
+++ b/include/uapi/linux/futex.h
@@ -22,6 +22,8 @@
 #define FUTEX_WAIT_REQUEUE_PI	11
 #define FUTEX_CMP_REQUEUE_PI	12
 
+#define GFUTEX_SWAP		60
+
 #define FUTEX_PRIVATE_FLAG	128
 #define FUTEX_CLOCK_REALTIME	256
 #define FUTEX_CMD_MASK		~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
@@ -41,6 +43,8 @@
 #define FUTEX_CMP_REQUEUE_PI_PRIVATE	(FUTEX_CMP_REQUEUE_PI | \
 					 FUTEX_PRIVATE_FLAG)
 
+#define GFUTEX_SWAP_PRIVATE		(GFUTEX_SWAP | FUTEX_PRIVATE_FLAG)
+
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
  * thread exit time.
diff --git a/init/init_task.c b/init/init_task.c
index 5d8359c..e40f14b 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -123,8 +123,7 @@
 	.thread_group	= LIST_HEAD_INIT(init_task.thread_group),
 	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),
 #ifdef CONFIG_AUDIT
-	.loginuid	= INVALID_UID,
-	.sessionid	= AUDIT_SID_UNSET,
+	.audit		= &init_struct_audit,
 #endif
 #ifdef CONFIG_PERF_EVENTS
 	.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
diff --git a/init/main.c b/init/main.c
index fef9e61..2f7dc9e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -94,6 +94,7 @@
 #include <linux/rodata_test.h>
 #include <linux/jump_label.h>
 #include <linux/mem_encrypt.h>
+#include <linux/audit.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -526,14 +527,16 @@
 {
 	const char *stack;
 
-	if (IS_ENABLED(CONFIG_INIT_STACK_ALL))
-		stack = "all";
+	if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN))
+		stack = "all(pattern)";
+	else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO))
+		stack = "all(zero)";
 	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
-		stack = "byref_all";
+		stack = "byref_all(zero)";
 	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
-		stack = "byref";
+		stack = "byref(zero)";
 	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
-		stack = "__user";
+		stack = "__user(zero)";
 	else
 		stack = "off";
 
@@ -771,6 +774,7 @@
 	nsfs_init();
 	cpuset_init();
 	cgroup_init();
+	audit_task_init();
 	taskstats_init_early();
 	delayacct_init();
 
diff --git a/kernel/audit.c b/kernel/audit.c
index 05ae208..5dd7c2b 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -202,6 +202,75 @@
 	struct sk_buff *skb;
 };
 
+static struct kmem_cache *audit_task_cache;
+
+void __init audit_task_init(void)
+{
+	audit_task_cache = kmem_cache_create("audit_task",
+					     sizeof(struct audit_task_info),
+					     0, SLAB_PANIC, NULL);
+}
+
+/**
+ * audit_alloc - allocate an audit info block for a task
+ * @tsk: task
+ *
+ * Call audit_alloc_syscall to filter on the task information and
+ * allocate a per-task audit context if necessary.  This is called from
+ * copy_process, so no lock is needed.
+ */
+int audit_alloc(struct task_struct *tsk)
+{
+	int ret = 0;
+	struct audit_task_info *info;
+
+	info = kmem_cache_alloc(audit_task_cache, GFP_KERNEL);
+	if (!info) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	info->loginuid = audit_get_loginuid(current);
+	info->sessionid = audit_get_sessionid(current);
+	info->contid = audit_get_contid(current);
+	tsk->audit = info;
+
+	ret = audit_alloc_syscall(tsk);
+	if (ret) {
+		tsk->audit = NULL;
+		kmem_cache_free(audit_task_cache, info);
+	}
+out:
+	return ret;
+}
+
+struct audit_task_info init_struct_audit = {
+	.loginuid = INVALID_UID,
+	.sessionid = AUDIT_SID_UNSET,
+	.contid = AUDIT_CID_UNSET,
+#ifdef CONFIG_AUDITSYSCALL
+	.ctx = NULL,
+#endif
+};
+
+/**
+ * audit_free - free per-task audit info
+ * @tsk: task whose audit info block to free
+ *
+ * Called from copy_process and do_exit
+ */
+void audit_free(struct task_struct *tsk)
+{
+	struct audit_task_info *info = tsk->audit;
+
+	audit_free_syscall(tsk);
+	/* Freeing the audit_task_info struct must be performed after
+	 * audit_log_exit() due to need for loginuid and sessionid.
+	 */
+	info = tsk->audit;
+	tsk->audit = NULL;
+	kmem_cache_free(audit_task_cache, info);
+}
+
 /**
  * auditd_test_task - Check to see if a given task is an audit daemon
  * @task: the task to check
@@ -2266,8 +2335,8 @@
 			sessionid = (unsigned int)atomic_inc_return(&session_id);
 	}
 
-	current->sessionid = sessionid;
-	current->loginuid = loginuid;
+	current->audit->sessionid = sessionid;
+	current->audit->loginuid = loginuid;
 out:
 	audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
 	return rc;
@@ -2300,6 +2369,62 @@
 	return audit_signal_info_syscall(t);
 }
 
+/*
+ * audit_set_contid - set current task's audit contid
+ * @task: target task
+ * @contid: contid value
+ *
+ * Returns 0 on success, -EPERM on permission failure.
+ *
+ * Called (set) from fs/proc/base.c::proc_contid_write().
+ */
+int audit_set_contid(struct task_struct *task, u64 contid)
+{
+	u64 oldcontid;
+	int rc = 0;
+	struct audit_buffer *ab;
+
+	task_lock(task);
+	/* Can't set if audit disabled */
+	if (!task->audit) {
+		task_unlock(task);
+		return -ENOPROTOOPT;
+	}
+	oldcontid = audit_get_contid(task);
+	read_lock(&tasklist_lock);
+	/* Don't allow the audit containerid to be unset */
+	if (!audit_contid_valid(contid))
+		rc = -EINVAL;
+	/* if we don't have caps, reject */
+	else if (!capable(CAP_AUDIT_CONTROL))
+		rc = -EPERM;
+	/* if task has children or is not single-threaded, deny */
+	else if (!list_empty(&task->children))
+		rc = -EBUSY;
+	else if (!(thread_group_leader(task) && thread_group_empty(task)))
+		rc = -EALREADY;
+	/* if contid is already set, deny */
+	else if (audit_contid_set(task))
+		rc = -ECHILD;
+	read_unlock(&tasklist_lock);
+	if (!rc)
+		task->audit->contid = contid;
+	task_unlock(task);
+
+	if (!audit_enabled)
+		return rc;
+
+	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONTAINER_OP);
+	if (!ab)
+		return rc;
+
+	audit_log_format(ab,
+			 "op=set opid=%d contid=%llu old-contid=%llu",
+			 task_tgid_nr(task), contid, oldcontid);
+	audit_log_end(ab);
+	return rc;
+}
+
 /**
  * audit_log_end - end one audit record
  * @ab: the audit_buffer
diff --git a/kernel/audit.h b/kernel/audit.h
index ddc2287..2be1b95 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -135,6 +135,7 @@
 	kuid_t		    target_uid;
 	unsigned int	    target_sessionid;
 	u32		    target_sid;
+	u64		    target_cid;
 	char		    target_comm[TASK_COMM_LEN];
 
 	struct audit_tree_refs *trees, *first_trees;
@@ -251,6 +252,8 @@
 extern unsigned int audit_serial(void);
 extern int auditsc_get_stamp(struct audit_context *ctx,
 			      struct timespec64 *t, unsigned int *serial);
+extern int audit_alloc_syscall(struct task_struct *tsk);
+extern void audit_free_syscall(struct task_struct *tsk);
 
 extern void audit_put_watch(struct audit_watch *watch);
 extern void audit_get_watch(struct audit_watch *watch);
@@ -292,6 +295,9 @@
 extern struct list_head *audit_killed_trees(void);
 #else /* CONFIG_AUDITSYSCALL */
 #define auditsc_get_stamp(c, t, s) 0
+#define audit_alloc_syscall(t) 0
+#define audit_free_syscall(t) {}
+
 #define audit_put_watch(w) {}
 #define audit_get_watch(w) {}
 #define audit_to_watch(k, p, l, o) (-EINVAL)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 4effe01..0e2d505 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -113,6 +113,7 @@
 	kuid_t			target_uid[AUDIT_AUX_PIDS];
 	unsigned int		target_sessionid[AUDIT_AUX_PIDS];
 	u32			target_sid[AUDIT_AUX_PIDS];
+	u64			target_cid[AUDIT_AUX_PIDS];
 	char 			target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN];
 	int			pid_count;
 };
@@ -903,23 +904,25 @@
 	return context;
 }
 
-/**
- * audit_alloc - allocate an audit context block for a task
+/*
+ * audit_alloc_syscall - allocate an audit context block for a task
  * @tsk: task
  *
  * Filter on the task information and allocate a per-task audit context
  * if necessary.  Doing so turns on system call auditing for the
- * specified task.  This is called from copy_process, so no lock is
- * needed.
+ * specified task.  This is called from copy_process via audit_alloc, so
+ * no lock is needed.
  */
-int audit_alloc(struct task_struct *tsk)
+int audit_alloc_syscall(struct task_struct *tsk)
 {
 	struct audit_context *context;
 	enum audit_state     state;
 	char *key = NULL;
 
-	if (likely(!audit_ever_enabled))
+	if (likely(!audit_ever_enabled)) {
+		audit_set_context(tsk, NULL);
 		return 0; /* Return if not auditing. */
+	}
 
 	state = audit_filter_task(tsk, &key);
 	if (state == AUDIT_DISABLED) {
@@ -929,7 +932,7 @@
 
 	if (!(context = audit_alloc_context(state))) {
 		kfree(key);
-		audit_log_lost("out of memory in audit_alloc");
+		audit_log_lost("out of memory in audit_alloc_syscall");
 		return -ENOMEM;
 	}
 	context->filterkey = key;
@@ -1574,14 +1577,15 @@
 }
 
 /**
- * __audit_free - free a per-task audit context
+ * audit_free_syscall - free per-task audit context info
  * @tsk: task whose audit context block to free
  *
- * Called from copy_process and do_exit
+ * Called from audit_free
  */
-void __audit_free(struct task_struct *tsk)
+void audit_free_syscall(struct task_struct *tsk)
 {
-	struct audit_context *context = tsk->audit_context;
+	struct audit_task_info *info = tsk->audit;
+	struct audit_context *context = info->ctx;
 
 	if (!context)
 		return;
@@ -1604,7 +1608,6 @@
 		if (context->current_state == AUDIT_RECORD_CONTEXT)
 			audit_log_exit();
 	}
-
 	audit_set_context(tsk, NULL);
 	audit_free_context(context);
 }
@@ -2373,6 +2376,7 @@
 	context->target_uid = task_uid(t);
 	context->target_sessionid = audit_get_sessionid(t);
 	security_task_getsecid(t, &context->target_sid);
+	context->target_cid = audit_get_contid(t);
 	memcpy(context->target_comm, t->comm, TASK_COMM_LEN);
 }
 
@@ -2400,6 +2404,7 @@
 		ctx->target_uid = t_uid;
 		ctx->target_sessionid = audit_get_sessionid(t);
 		security_task_getsecid(t, &ctx->target_sid);
+		ctx->target_cid = audit_get_contid(t);
 		memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN);
 		return 0;
 	}
@@ -2421,6 +2426,7 @@
 	axp->target_uid[axp->pid_count] = t_uid;
 	axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t);
 	security_task_getsecid(t, &axp->target_sid[axp->pid_count]);
+	axp->target_cid[axp->pid_count] = audit_get_contid(t);
 	memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN);
 	axp->pid_count++;
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 56bc96f5a..d37d212 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2031,6 +2031,7 @@
 const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
 const struct bpf_func_proto bpf_spin_lock_proto __weak;
 const struct bpf_func_proto bpf_spin_unlock_proto __weak;
+const struct bpf_func_proto bpf_jiffies64_proto __weak;
 
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index a77d281..91fe4e0 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -11,6 +11,7 @@
 #include <linux/uidgid.h>
 #include <linux/filter.h>
 #include <linux/ctype.h>
+#include <linux/jiffies.h>
 
 #include "../../lib/kstrtox.h"
 
@@ -312,6 +313,17 @@
 	preempt_enable();
 }
 
+BPF_CALL_0(bpf_jiffies64)
+{
+	return get_jiffies_64();
+}
+
+const struct bpf_func_proto bpf_jiffies64_proto = {
+	.func		= bpf_jiffies64,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+
 #ifdef CONFIG_CGROUPS
 BPF_CALL_0(bpf_get_current_cgroup_id)
 {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index bf03d04..b6695e6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1598,6 +1598,10 @@
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
@@ -1925,6 +1929,10 @@
 	case BPF_CGROUP_INET6_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
@@ -2073,6 +2081,10 @@
 	case BPF_CGROUP_INET6_POST_BIND:
 	case BPF_CGROUP_INET4_CONNECT:
 	case BPF_CGROUP_INET6_CONNECT:
+	case BPF_CGROUP_INET4_GETPEERNAME:
+	case BPF_CGROUP_INET6_GETPEERNAME:
+	case BPF_CGROUP_INET4_GETSOCKNAME:
+	case BPF_CGROUP_INET6_GETSOCKNAME:
 	case BPF_CGROUP_UDP4_SENDMSG:
 	case BPF_CGROUP_UDP6_SENDMSG:
 	case BPF_CGROUP_UDP4_RECVMSG:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2c248c4..7401691c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3312,13 +3312,17 @@
 		expected_type = CONST_PTR_TO_MAP;
 		if (type != expected_type)
 			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_CTX) {
+	} else if (arg_type == ARG_PTR_TO_CTX ||
+		   arg_type == ARG_PTR_TO_CTX_OR_NULL) {
 		expected_type = PTR_TO_CTX;
-		if (type != expected_type)
-			goto err_type;
-		err = check_ctx_reg(env, reg, regno);
-		if (err < 0)
-			return err;
+		if (!(register_is_null(reg) &&
+		      arg_type == ARG_PTR_TO_CTX_OR_NULL)) {
+			if (type != expected_type)
+				goto err_type;
+			err = check_ctx_reg(env, reg, regno);
+			if (err < 0)
+				return err;
+		}
 	} else if (arg_type == ARG_PTR_TO_SOCK_COMMON) {
 		expected_type = PTR_TO_SOCK_COMMON;
 		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
@@ -6224,7 +6228,11 @@
 	switch (env->prog->type) {
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 		if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
-		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+		    env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
+		    env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
 			range = tnum_range(1, 1);
 		break;
 	case BPF_PROG_TYPE_CGROUP_SKB:
@@ -9250,6 +9258,30 @@
 			goto patch_call_imm;
 		}
 
+		if (prog->jit_requested && BITS_PER_LONG == 64 &&
+		    insn->imm == BPF_FUNC_jiffies64) {
+			struct bpf_insn ld_jiffies_addr[2] = {
+				BPF_LD_IMM64(BPF_REG_0,
+					     (unsigned long)&jiffies),
+			};
+
+			insn_buf[0] = ld_jiffies_addr[0];
+			insn_buf[1] = ld_jiffies_addr[1];
+			insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0,
+						  BPF_REG_0, 0);
+			cnt = 3;
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+						       cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 patch_call_imm:
 		fn = env->ops->get_func_proto(insn->imm, env->prog);
 		/* all functions that have prototype and verifier allowed
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2ef33e9..c6180f78 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4243,8 +4243,9 @@
 
 	if (!task) {
 		/* Must be root to operate on a CPU event: */
-		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
-			return ERR_PTR(-EACCES);
+		err = perf_allow_cpu(&event->attr);
+		if (err)
+			return ERR_PTR(err);
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
@@ -4553,6 +4554,8 @@
 
 	unaccount_event(event);
 
+	security_perf_event_free(event);
+
 	if (event->rb) {
 		/*
 		 * Can happen when we close an event with re-directed output.
@@ -5006,6 +5009,10 @@
 	struct perf_event_context *ctx;
 	int ret;
 
+	ret = security_perf_event_read(event);
+	if (ret)
+		return ret;
+
 	ctx = perf_event_ctx_lock(event);
 	ret = __perf_read(event, buf, count);
 	perf_event_ctx_unlock(event, ctx);
@@ -5270,6 +5277,11 @@
 	struct perf_event_context *ctx;
 	long ret;
 
+	/* Treat ioctl like writes as it is likely a mutating operation. */
+	ret = security_perf_event_write(event);
+	if (ret)
+		return ret;
+
 	ctx = perf_event_ctx_lock(event);
 	ret = _perf_ioctl(event, cmd, arg);
 	perf_event_ctx_unlock(event, ctx);
@@ -5734,6 +5746,10 @@
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
+	ret = security_perf_event_read(event);
+	if (ret)
+		return ret;
+
 	vma_size = vma->vm_end - vma->vm_start;
 
 	if (vma->vm_pgoff == 0) {
@@ -5867,7 +5883,7 @@
 	lock_limit >>= PAGE_SHIFT;
 	locked = atomic64_read(&vma->vm_mm->pinned_vm) + extra;
 
-	if ((locked > lock_limit) && perf_paranoid_tracepoint_raw() &&
+	if ((locked > lock_limit) && perf_is_paranoid() &&
 		!capable(CAP_IPC_LOCK)) {
 		ret = -EPERM;
 		goto unlock;
@@ -10618,11 +10634,20 @@
 		}
 	}
 
+	err = security_perf_event_alloc(event);
+	if (err)
+		goto err_callchain_buffer;
+
 	/* symmetric to unaccount_event() in _free_event() */
 	account_event(event);
 
 	return event;
 
+err_callchain_buffer:
+	if (!event->parent) {
+		if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+			put_callchain_buffers();
+	}
 err_addr_filters:
 	kfree(event->addr_filter_ranges);
 
@@ -10711,9 +10736,11 @@
 			attr->branch_sample_type = mask;
 		}
 		/* privileged levels capture (kernel, hv): check permissions */
-		if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
-		    && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		if (mask & PERF_SAMPLE_BRANCH_PERM_PLM) {
+			ret = perf_allow_kernel(attr);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (attr->sample_type & PERF_SAMPLE_REGS_USER) {
@@ -10926,13 +10953,19 @@
 	if (flags & ~PERF_FLAG_ALL)
 		return -EINVAL;
 
+	/* Do we allow access to perf_event_open(2) ? */
+	err = security_perf_event_open(&attr, PERF_SECURITY_OPEN);
+	if (err)
+		return err;
+
 	err = perf_copy_attr(attr_uptr, &attr);
 	if (err)
 		return err;
 
 	if (!attr.exclude_kernel) {
-		if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-			return -EACCES;
+		err = perf_allow_kernel(&attr);
+		if (err)
+			return err;
 	}
 
 	if (attr.namespaces) {
@@ -10949,9 +10982,11 @@
 	}
 
 	/* Only privileged users can get physical addresses */
-	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) &&
-	    perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
-		return -EACCES;
+	if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR)) {
+		err = perf_allow_kernel(&attr);
+		if (err)
+			return err;
+	}
 
 	err = security_locked_down(LOCKDOWN_PERF);
 	if (err && (attr.sample_type & PERF_SAMPLE_REGS_INTR))
diff --git a/kernel/exit.c b/kernel/exit.c
index ece6477..db8f9ee 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -63,6 +63,7 @@
 #include <linux/random.h>
 #include <linux/rcuwait.h>
 #include <linux/compat.h>
+#include <linux/security.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -786,6 +787,8 @@
 #endif
 		if (tsk->mm)
 			setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm);
+
+		security_task_exit(tsk);
 	}
 	acct_collect(code, group_dead);
 	if (group_dead)
diff --git a/kernel/fork.c b/kernel/fork.c
index 50f37d5..be1780a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1949,7 +1949,6 @@
 	posix_cputimers_init(&p->posix_cputimers);
 
 	p->io_context = NULL;
-	audit_set_context(p, NULL);
 	cgroup_fork(p);
 #ifdef CONFIG_NUMA
 	p->mempolicy = mpol_dup(p->mempolicy);
@@ -2242,6 +2241,7 @@
 	uprobe_copy_process(p, clone_flags);
 
 	copy_oom_score_adj(clone_flags, p);
+	security_task_post_alloc(p);
 
 	return p;
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 042c270..6e742a7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1676,16 +1676,16 @@
 }
 
 /*
- * Wake up waiters matching bitset queued on this futex (uaddr).
+ * Prepare wake queue matching bitset queued on this futex (uaddr).
  */
 static int
-futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
+prepare_wake_q(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset,
+		struct wake_q_head *wake_q)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
-	DEFINE_WAKE_Q(wake_q);
 
 	if (!bitset)
 		return -EINVAL;
@@ -1713,20 +1713,35 @@
 			if (!(this->bitset & bitset))
 				continue;
 
-			mark_wake_futex(&wake_q, this);
+			mark_wake_futex(wake_q, this);
 			if (++ret >= nr_wake)
 				break;
 		}
 	}
 
 	spin_unlock(&hb->lock);
-	wake_up_q(&wake_q);
+
 out_put_key:
 	put_futex_key(&key);
 out:
 	return ret;
 }
 
+/*
+ * Wake up waiters matching bitset queued on this futex (uaddr).
+ */
+static int
+futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
+{
+	int ret;
+	DEFINE_WAKE_Q(wake_q);
+
+	ret = prepare_wake_q(uaddr, flags, nr_wake, bitset, &wake_q);
+	if (ret > 0)
+		wake_up_q(&wake_q);
+	return ret;
+}
+
 static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 {
 	unsigned int op =	  (encoded_op & 0x70000000) >> 28;
@@ -2708,9 +2723,12 @@
  * @hb:		the futex hash bucket, must be locked by the caller
  * @q:		the futex_q to queue up on
  * @timeout:	the prepared hrtimer_sleeper, or null for no timeout
+ * @next:	if present, wake next and hint to the scheduler that we'd
+ *		prefer to execute it locally.
  */
 static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q,
-				struct hrtimer_sleeper *timeout)
+				struct hrtimer_sleeper *timeout,
+				struct task_struct *next)
 {
 	/*
 	 * The task state is guaranteed to be set before another task can
@@ -2735,10 +2753,25 @@
 		 * flagged for rescheduling. Only call schedule if there
 		 * is no timeout, or if it has yet to expire.
 		 */
-		if (!timeout || timeout->task)
+		if (!timeout || timeout->task) {
+			if (next) {
+#ifdef CONFIG_SMP
+				wake_up_swap(next);
+#else
+				wake_up_process(next);
+#endif
+				put_task_struct(next);
+				next = NULL;
+			}
 			freezable_schedule();
+		}
 	}
 	__set_current_state(TASK_RUNNING);
+
+	if (next) {
+		wake_up_process(next);
+		put_task_struct(next);
+	}
 }
 
 /**
@@ -2818,7 +2851,7 @@
 }
 
 static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
-		      ktime_t *abs_time, u32 bitset)
+		      ktime_t *abs_time, u32 bitset, struct task_struct *next)
 {
 	struct hrtimer_sleeper timeout, *to;
 	struct restart_block *restart;
@@ -2842,7 +2875,8 @@
 		goto out;
 
 	/* queue_me and wait for wakeup, timeout, or a signal. */
-	futex_wait_queue_me(hb, &q, to);
+	futex_wait_queue_me(hb, &q, to, next);
+	next = NULL;
 
 	/* If we were woken (and unqueued), we succeeded, whatever. */
 	ret = 0;
@@ -2875,6 +2909,10 @@
 	ret = -ERESTART_RESTARTBLOCK;
 
 out:
+	if (next) {
+		wake_up_process(next);
+		put_task_struct(next);
+	}
 	if (to) {
 		hrtimer_cancel(&to->timer);
 		destroy_hrtimer_on_stack(&to->timer);
@@ -2894,10 +2932,30 @@
 	}
 	restart->fn = do_no_restart_syscall;
 
-	return (long)futex_wait(uaddr, restart->futex.flags,
-				restart->futex.val, tp, restart->futex.bitset);
+	return (long)futex_wait(uaddr, restart->futex.flags, restart->futex.val,
+				tp, restart->futex.bitset, NULL);
 }
 
+static int futex_swap(u32 __user *uaddr, unsigned int flags, u32 val,
+		      ktime_t *abs_time, u32 __user *uaddr2)
+{
+	u32 bitset = FUTEX_BITSET_MATCH_ANY;
+	struct task_struct *next = NULL;
+	DEFINE_WAKE_Q(wake_q);
+	int ret;
+
+	ret = prepare_wake_q(uaddr2, flags, 1, bitset, &wake_q);
+	if (ret < 0)
+		return ret;
+	if (wake_q.first != WAKE_Q_TAIL) {
+		WARN_ON(ret != 1);
+		/* At most one wakee can be present. Pull it out. */
+		next = container_of(wake_q.first, struct task_struct, wake_q);
+		next->wake_q.next = NULL;
+	}
+
+	return futex_wait(uaddr, flags, val, abs_time, bitset, next);
+}
 
 /*
  * Userspace tried a 0 -> TID atomic transition of the futex value
@@ -3367,7 +3425,7 @@
 	}
 
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
-	futex_wait_queue_me(hb, &q, to);
+	futex_wait_queue_me(hb, &q, to, NULL);
 
 	spin_lock(&hb->lock);
 	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
@@ -3883,7 +3941,7 @@
 		val3 = FUTEX_BITSET_MATCH_ANY;
 		/* fall through */
 	case FUTEX_WAIT_BITSET:
-		return futex_wait(uaddr, flags, val, timeout, val3);
+		return futex_wait(uaddr, flags, val, timeout, val3, NULL);
 	case FUTEX_WAKE:
 		val3 = FUTEX_BITSET_MATCH_ANY;
 		/* fall through */
@@ -3907,6 +3965,8 @@
 					     uaddr2);
 	case FUTEX_CMP_REQUEUE_PI:
 		return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1);
+	case GFUTEX_SWAP:
+		return futex_swap(uaddr, flags, val, timeout, uaddr2);
 	}
 	return -ENOSYS;
 }
@@ -3923,7 +3983,7 @@
 
 	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
 		      cmd == FUTEX_WAIT_BITSET ||
-		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
+		      cmd == FUTEX_WAIT_REQUEUE_PI || cmd == GFUTEX_SWAP)) {
 		if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG))))
 			return -EFAULT;
 		if (get_timespec64(&ts, utime))
@@ -3932,7 +3992,7 @@
 			return -EINVAL;
 
 		t = timespec64_to_ktime(ts);
-		if (cmd == FUTEX_WAIT)
+		if (cmd == FUTEX_WAIT || cmd == GFUTEX_SWAP)
 			t = ktime_add_safe(ktime_get(), t);
 		tp = &t;
 	}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7841e73..bf88a5b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2752,6 +2752,11 @@
 }
 EXPORT_SYMBOL(wake_up_process);
 
+int wake_up_swap(struct task_struct *tsk)
+{
+	return try_to_wake_up(tsk, TASK_NORMAL, WF_CURRENT_CPU);
+}
+
 int wake_up_state(struct task_struct *p, unsigned int state)
 {
 	return try_to_wake_up(p, state, 0);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3dd7c10..5342ba1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6515,6 +6515,9 @@
 	int want_affine = 0;
 	int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
 
+	if ((wake_flags & WF_CURRENT_CPU) && cpumask_test_cpu(cpu, p->cpus_ptr))
+		return cpu;
+
 	if (sd_flag & SD_BALANCE_WAKE) {
 		record_wakee(p);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e10fb9b..4e13f91 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1653,6 +1653,7 @@
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
 #define WF_MIGRATED		0x4		/* Internal use, task got migrated */
+#define WF_CURRENT_CPU		0x200		/* Prefer to move wakee to the current CPU */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a9dfa04..643e0b1 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -8,6 +8,7 @@
 
 #include <linux/module.h>
 #include <linux/kprobes.h>
+#include <linux/security.h>
 #include "trace.h"
 #include "trace_probe.h"
 
@@ -26,8 +27,10 @@
 static int perf_trace_event_perm(struct trace_event_call *tp_event,
 				 struct perf_event *p_event)
 {
+	int ret;
+
 	if (tp_event->perf_perm) {
-		int ret = tp_event->perf_perm(tp_event, p_event);
+		ret = tp_event->perf_perm(tp_event, p_event);
 		if (ret)
 			return ret;
 	}
@@ -46,8 +49,9 @@
 
 	/* The ftrace function trace is allowed only for root. */
 	if (ftrace_event_is_function(tp_event)) {
-		if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-			return -EPERM;
+		ret = perf_allow_tracepoint(&p_event->attr);
+		if (ret)
+			return ret;
 
 		if (!is_sampling_event(p_event))
 			return 0;
@@ -82,8 +86,9 @@
 	 * ...otherwise raw tracepoint data can be a severe data leak,
 	 * only allow root to have these.
 	 */
-	if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-		return -EPERM;
+	ret = perf_allow_tracepoint(&p_event->attr);
+	if (ret)
+		return ret;
 
 	return 0;
 }
diff --git a/net/core/filter.c b/net/core/filter.c
index 2fa10fd..72c2767 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2644,6 +2644,19 @@
 	.arg4_type	= ARG_ANYTHING,
 };
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
+BPF_CALL_0(bpf_get_cgroup_classid_curr)
+{
+	return __task_get_classid(current);
+}
+
+static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
+	.func		= bpf_get_cgroup_classid_curr,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+};
+#endif
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -4186,6 +4199,18 @@
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx)
+{
+	return sock_gen_cookie(ctx);
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
+	.func		= bpf_get_socket_cookie_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
 	return sock_gen_cookie(ctx->sk);
@@ -4198,6 +4223,39 @@
 	.arg1_type	= ARG_PTR_TO_CTX,
 };
 
+static u64 __bpf_get_netns_cookie(struct sock *sk)
+{
+#ifdef CONFIG_NET_NS
+	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+#else
+	return 0;
+#endif
+}
+
+BPF_CALL_1(bpf_get_netns_cookie_sock, struct sock *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sock_proto = {
+	.func		= bpf_get_netns_cookie_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
+BPF_CALL_1(bpf_get_netns_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
+{
+	return __bpf_get_netns_cookie(ctx ? ctx->sk : NULL);
+}
+
+static const struct bpf_func_proto bpf_get_netns_cookie_sock_addr_proto = {
+	.func		= bpf_get_netns_cookie_sock_addr,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX_OR_NULL,
+};
+
 BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
 {
 	struct sock *sk = sk_to_full_sk(skb->sk);
@@ -4216,8 +4274,8 @@
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_5(bpf_sockopt_event_output, struct bpf_sock_ops_kern *, bpf_sock,
-	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
+BPF_CALL_5(bpf_event_output_data, void *, ctx, struct bpf_map *, map, u64, flags,
+	   void *, data, u64, size)
 {
 	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
 		return -EINVAL;
@@ -4225,8 +4283,8 @@
 	return bpf_event_output(map, flags, data, size, NULL, 0, NULL);
 }
 
-static const struct bpf_func_proto bpf_sockopt_event_output_proto =  {
-	.func		= bpf_sockopt_event_output,
+static const struct bpf_func_proto bpf_event_output_data_proto =  {
+	.func		= bpf_event_output_data,
 	.gpl_only       = true,
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
@@ -5414,8 +5472,7 @@
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	/* Only full sockets have sk->sk_flags. */
-	if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE))
+	if (sk_is_refcounted(sk))
 		sock_gen_put(sk);
 	return 0;
 }
@@ -5935,6 +5992,36 @@
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
+{
+	if (flags != 0)
+		return -EINVAL;
+	if (!skb_at_tc_ingress(skb))
+		return -EOPNOTSUPP;
+	if (unlikely(dev_net(skb->dev) != sock_net(sk)))
+		return -ENETUNREACH;
+	if (unlikely(sk_fullsock(sk) && sk->sk_reuseport))
+		return -ESOCKTNOSUPPORT;
+	if (sk_is_refcounted(sk) &&
+	    unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
+		return -ENOENT;
+
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = sock_pfree;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sk_assign_proto = {
+	.func		= bpf_sk_assign,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_SOCK_COMMON,
+	.arg3_type	= ARG_ANYTHING,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -6011,6 +6098,8 @@
 		return &bpf_spin_unlock_proto;
 	case BPF_FUNC_trace_printk:
 		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_jiffies64:
+		return &bpf_jiffies64_proto;
 	default:
 		return NULL;
 	}
@@ -6027,6 +6116,20 @@
 		return &bpf_get_current_uid_gid_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_sock_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sock_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6051,8 +6154,20 @@
 		}
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_addr_proto;
+	case BPF_FUNC_get_netns_cookie:
+		return &bpf_get_netns_cookie_sock_addr_proto;
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+	case BPF_FUNC_get_current_comm:
+		return &bpf_get_current_comm_proto;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
 		return &bpf_sock_addr_sk_lookup_tcp_proto;
@@ -6226,6 +6341,8 @@
 		return &bpf_skb_ecn_set_ce_proto;
 	case BPF_FUNC_tcp_gen_syncookie:
 		return &bpf_tcp_gen_syncookie_proto;
+	case BPF_FUNC_sk_assign:
+		return &bpf_sk_assign_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6295,7 +6412,7 @@
 	case BPF_FUNC_get_local_storage:
 		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_perf_event_output:
-		return &bpf_sockopt_event_output_proto;
+		return &bpf_event_output_data_proto;
 	case BPF_FUNC_sk_storage_get:
 		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
@@ -6330,6 +6447,16 @@
 		return &bpf_msg_push_data_proto;
 	case BPF_FUNC_msg_pop_data:
 		return &bpf_msg_pop_data_proto;
+	case BPF_FUNC_perf_event_output:
+		return &bpf_event_output_data_proto;
+	case BPF_FUNC_get_current_uid_gid:
+		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_current_pid_tgid:
+		return &bpf_get_current_pid_tgid_proto;
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_get_cgroup_classid:
+		return &bpf_get_cgroup_classid_curr_proto;
+#endif
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6936,6 +7063,8 @@
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET4_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
+		case BPF_CGROUP_INET4_GETPEERNAME:
+		case BPF_CGROUP_INET4_GETSOCKNAME:
 		case BPF_CGROUP_UDP4_SENDMSG:
 		case BPF_CGROUP_UDP4_RECVMSG:
 			break;
@@ -6947,6 +7076,8 @@
 		switch (prog->expected_attach_type) {
 		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET6_CONNECT:
+		case BPF_CGROUP_INET6_GETPEERNAME:
+		case BPF_CGROUP_INET6_GETSOCKNAME:
 		case BPF_CGROUP_UDP6_SENDMSG:
 		case BPF_CGROUP_UDP6_RECVMSG:
 			break;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 3940284..0495692 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -69,6 +69,20 @@
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
+static atomic64_t cookie_gen;
+
+u64 net_gen_cookie(struct net *net)
+{
+	while (1) {
+		u64 res = atomic64_read(&net->net_cookie);
+
+		if (res)
+			return res;
+		res = atomic64_inc_return(&cookie_gen);
+		atomic64_cmpxchg(&net->net_cookie, 0, res);
+	}
+}
+
 static struct net_generic *net_alloc_generic(void)
 {
 	struct net_generic *ng;
@@ -1104,6 +1118,7 @@
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
+	net_gen_cookie(&init_net);
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
diff --git a/net/core/sock.c b/net/core/sock.c
index 33543d5..9df7db3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2062,6 +2062,18 @@
 }
 EXPORT_SYMBOL(sock_efree);
 
+/* Buffer destructor for prefetch/receive path where reference count may
+ * not be held, e.g. for listen sockets.
+ */
+#ifdef CONFIG_INET
+void sock_pfree(struct sk_buff *skb)
+{
+	if (sk_is_refcounted(skb->sk))
+		sock_gen_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_pfree);
+#endif /* CONFIG_INET */
+
 kuid_t sock_i_uid(struct sock *sk)
 {
 	kuid_t uid;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 70f92aa..c530271 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -753,12 +753,11 @@
 }
 EXPORT_SYMBOL(inet_accept);
 
-
 /*
  *	This does both peername and sockname.
  */
 int inet_getname(struct socket *sock, struct sockaddr *uaddr,
-			int peer)
+		 int peer)
 {
 	struct sock *sk		= sock->sk;
 	struct inet_sock *inet	= inet_sk(sk);
@@ -779,6 +778,11 @@
 		sin->sin_port = inet->inet_sport;
 		sin->sin_addr.s_addr = addr;
 	}
+	if (cgroup_bpf_enabled)
+		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
+					    peer ? BPF_CGROUP_INET4_GETPEERNAME :
+						   BPF_CGROUP_INET4_GETSOCKNAME,
+					    NULL);
 	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 	return sizeof(*sin);
 }
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index c59a78a..72cbfc7 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -494,7 +494,8 @@
 	IPCB(skb)->iif = skb->skb_iif;
 
 	/* Must drop socket now because of tproxy. */
-	skb_orphan(skb);
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
 
 	return skb;
 
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 994a150..b3f7dd1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2289,6 +2289,7 @@
 	struct rtable *rt = skb_rtable(skb);
 	__be32 saddr, daddr;
 	struct net *net = dev_net(skb->dev);
+	bool refcounted;
 
 	/*
 	 *  Validate the packet.
@@ -2314,7 +2315,7 @@
 	if (udp4_csum_init(skb, uh, proto))
 		goto csum_error;
 
-	sk = skb_steal_sock(skb);
+	sk = skb_steal_sock(skb, &refcounted);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -2323,7 +2324,8 @@
 			udp_sk_rx_dst_set(sk, dst);
 
 		ret = udp_unicast_rcv_skb(sk, skb, uh);
-		sock_put(sk);
+		if (refcounted)
+			sock_put(sk);
 		return ret;
 	}
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 14ac1d9..224dddc 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -501,9 +501,8 @@
 /*
  *	This does both peername and sockname.
  */
-
 int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
-		 int peer)
+		  int peer)
 {
 	struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr;
 	struct sock *sk = sock->sk;
@@ -528,9 +527,13 @@
 			sin->sin6_addr = np->saddr;
 		else
 			sin->sin6_addr = sk->sk_v6_rcv_saddr;
-
 		sin->sin6_port = inet->inet_sport;
 	}
+	if (cgroup_bpf_enabled)
+		BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin,
+					    peer ? BPF_CGROUP_INET6_GETPEERNAME :
+						   BPF_CGROUP_INET6_GETSOCKNAME,
+					    NULL);
 	sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr,
 						 sk->sk_bound_dev_if);
 	return sizeof(*sin);
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 3d71c7d..f2336b5 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -263,7 +263,8 @@
 	rcu_read_unlock();
 
 	/* Must drop socket now because of tproxy. */
-	skb_orphan(skb);
+	if (!skb_sk_is_prefetched(skb))
+		skb_orphan(skb);
 
 	return skb;
 err:
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6762430..54a109d 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -847,6 +847,7 @@
 	struct net *net = dev_net(skb->dev);
 	struct udphdr *uh;
 	struct sock *sk;
+	bool refcounted;
 	u32 ulen = 0;
 
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
@@ -883,7 +884,7 @@
 		goto csum_error;
 
 	/* Check if the socket is already available, e.g. due to early demux */
-	sk = skb_steal_sock(skb);
+	sk = skb_steal_sock(skb, &refcounted);
 	if (sk) {
 		struct dst_entry *dst = skb_dst(skb);
 		int ret;
@@ -892,12 +893,14 @@
 			udp6_sk_rx_dst_set(sk, dst);
 
 		if (!uh->check && !udp_sk(sk)->no_check6_rx) {
-			sock_put(sk);
+			if (refcounted)
+				sock_put(sk);
 			goto report_csum_error;
 		}
 
 		ret = udp6_unicast_rcv_skb(sk, skb, uh);
-		sock_put(sk);
+		if (refcounted)
+			sock_put(sk);
 		return ret;
 	}
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index b7d83d0..0b015ce 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -12,6 +12,7 @@
 #include <linux/bpf.h>
 
 #include <net/netlink.h>
+#include <net/sock.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
 
@@ -53,6 +54,8 @@
 		bpf_compute_data_pointers(skb);
 		filter_res = BPF_PROG_RUN(filter, skb);
 	}
+	if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK)
+		skb_orphan(skb);
 	rcu_read_unlock();
 
 	/* A BPF program may overwrite the default action opcode.
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 7da10af..d1dd4a6 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -82,21 +82,20 @@
 			$(if $(shell command -v -- $(c)gcc 2>/dev/null), $(c))))
 
 # output directory for tests below
-TMPOUT = $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/).tmp_$$$$
+TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/)
 
 # try-run
 # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise)
 # Exit code chooses option. "$$TMP" serves as a temporary file and is
 # automatically cleaned up.
 try-run = $(shell set -e;		\
-	TMP=$(TMPOUT)/tmp;		\
-	TMPO=$(TMPOUT)/tmp.o;		\
-	mkdir -p $(TMPOUT);		\
-	trap "rm -rf $(TMPOUT)" EXIT;	\
+	TMP="$(TMPOUT).$$$$.tmp";	\
+	TMPO="$(TMPOUT).$$$$.o";	\
 	if ($(1)) >/dev/null 2>&1;	\
 	then echo "$(2)";		\
 	else echo "$(3)";		\
-	fi)
+	fi;				\
+	rm -f "$$TMP" "$$TMPO")
 
 # as-option
 # Usage: cflags-y += $(call as-option,-Wa$(comma)-isa=foo,)
diff --git a/security/Kconfig b/security/Kconfig
index 2a1a2d3..2a8bb1d 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -236,6 +236,7 @@
 source "security/apparmor/Kconfig"
 source "security/loadpin/Kconfig"
 source "security/yama/Kconfig"
+source "security/container/Kconfig"
 source "security/safesetid/Kconfig"
 source "security/lockdown/Kconfig"
 
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index af4c979..269967c 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -19,13 +19,16 @@
 
 menu "Memory initialization"
 
-config CC_HAS_AUTO_VAR_INIT
+config CC_HAS_AUTO_VAR_INIT_PATTERN
 	def_bool $(cc-option,-ftrivial-auto-var-init=pattern)
 
+config CC_HAS_AUTO_VAR_INIT_ZERO
+	def_bool $(cc-option,-ftrivial-auto-var-init=zero -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang)
+
 choice
 	prompt "Initialize kernel stack variables at function entry"
 	default GCC_PLUGIN_STRUCTLEAK_BYREF_ALL if COMPILE_TEST && GCC_PLUGINS
-	default INIT_STACK_ALL if COMPILE_TEST && CC_HAS_AUTO_VAR_INIT
+	default INIT_STACK_ALL_PATTERN if COMPILE_TEST && CC_HAS_AUTO_VAR_INIT_PATTERN
 	default INIT_STACK_NONE
 	help
 	  This option enables initialization of stack variables at
@@ -88,9 +91,9 @@
 		  of uninitialized stack variable exploits and information
 		  exposures.
 
-	config INIT_STACK_ALL
+	config INIT_STACK_ALL_PATTERN
 		bool "0xAA-init everything on the stack (strongest)"
-		depends on CC_HAS_AUTO_VAR_INIT
+		depends on CC_HAS_AUTO_VAR_INIT_PATTERN
 		help
 		  Initializes everything on the stack with a 0xAA
 		  pattern. This is intended to eliminate all classes
@@ -98,6 +101,24 @@
 		  exposures, even variables that were warned to have been
 		  left uninitialized.
 
+		  Pattern initialization is known to provoke many existing bugs
+		  related to uninitialized locals, e.g. pointers receive
+		  non-NULL values, buffer sizes and indices are very big.
+
+	config INIT_STACK_ALL_ZERO
+		bool "zero-init everything on the stack (strongest and safest)"
+		depends on CC_HAS_AUTO_VAR_INIT_ZERO
+		help
+		  Initializes everything on the stack with a zero
+		  value. This is intended to eliminate all classes
+		  of uninitialized stack variable exploits and information
+		  exposures, even variables that were warned to have been
+		  left uninitialized.
+
+		  Zero initialization provides safe defaults for strings,
+		  pointers, indices and sizes, and is therefore
+		  more suitable as a security mitigation measure.
+
 endchoice
 
 config GCC_PLUGIN_STRUCTLEAK_VERBOSE
diff --git a/security/Makefile b/security/Makefile
index be1dd9d..a5d987b 100644
--- a/security/Makefile
+++ b/security/Makefile
@@ -10,6 +10,7 @@
 subdir-$(CONFIG_SECURITY_APPARMOR)	+= apparmor
 subdir-$(CONFIG_SECURITY_YAMA)		+= yama
 subdir-$(CONFIG_SECURITY_LOADPIN)	+= loadpin
+subdir-$(CONFIG_SECURITY_CONTAINER_MONITOR) += container
 subdir-$(CONFIG_SECURITY_SAFESETID)    += safesetid
 subdir-$(CONFIG_SECURITY_LOCKDOWN_LSM)	+= lockdown
 
@@ -30,6 +31,7 @@
 obj-$(CONFIG_SECURITY_SAFESETID)       += safesetid/
 obj-$(CONFIG_SECURITY_LOCKDOWN_LSM)	+= lockdown/
 obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
+obj-$(CONFIG_SECURITY_CONTAINER_MONITOR) += container/
 
 # Object integrity file lists
 subdir-$(CONFIG_INTEGRITY)		+= integrity
diff --git a/security/container/Kconfig b/security/container/Kconfig
new file mode 100644
index 0000000..827fe0a
--- /dev/null
+++ b/security/container/Kconfig
@@ -0,0 +1,18 @@
+config SECURITY_CONTAINER_MONITOR
+	bool "Monitor containerized processes"
+	depends on SECURITY
+	depends on MMU
+	depends on VSOCKETS=y
+	depends on X86_64
+	select SECURITYFS
+	help
+	  Instrument the Linux kernel to collect more information about containers
+	  and identify security threats.
+
+config SECURITY_CONTAINER_MONITOR_DEBUG
+    bool "Enable debug pr_devel logs"
+	depends on SECURITY_CONTAINER_MONITOR
+	help
+	  Define DEBUG for CSM files to compile verbose debugging messages.
+
+	  Only for debugging/testing do not enable for production.
diff --git a/security/container/Makefile b/security/container/Makefile
new file mode 100644
index 0000000..678d0f7
--- /dev/null
+++ b/security/container/Makefile
@@ -0,0 +1,16 @@
+PB_CCFLAGS := -DPB_SYSTEM_HEADER="<pbsystem.h>" \
+	-DPB_NO_ERRMSG \
+	-DPB_FIELD_16BIT \
+	-DPB_BUFFER_ONLY
+export PB_CCFLAGS
+
+subdir-$(CONFIG_SECURITY_CONTAINER_MONITOR) += protos
+
+obj-$(CONFIG_SECURITY_CONTAINER_MONITOR) += protos/
+obj-$(CONFIG_SECURITY_CONTAINER_MONITOR) += monitor.o pb.o process.o vsock.o
+
+ccflags-y := -I$(srctree)/security/container/protos \
+	-I$(srctree)/security/container/protos/nanopb \
+	-I$(srctree)/fs \
+	$(PB_CCFLAGS)
+ccflags-$(CONFIG_SECURITY_CONTAINER_MONITOR_DEBUG) += -DDEBUG
diff --git a/security/container/monitor.c b/security/container/monitor.c
new file mode 100644
index 0000000..fa03398
--- /dev/null
+++ b/security/container/monitor.c
@@ -0,0 +1,782 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Container Security Monitor module
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#include "monitor.h"
+#include "process.h"
+
+#include <linux/audit.h>
+#include <linux/lsm_hooks.h>
+#include <linux/module.h>
+#include <linux/pipe_fs_i.h>
+#include <linux/rwsem.h>
+#include <linux/string.h>
+#include <linux/sysctl.h>
+#include <linux/socket.h>
+#include <net/sock.h>
+#include <linux/vm_sockets.h>
+#include <linux/file.h>
+
+/* protects csm_*_enabled and configurations. */
+DECLARE_RWSEM(csm_rwsem_config);
+
+/* protects csm_host_port and csm_vsocket. */
+DECLARE_RWSEM(csm_rwsem_vsocket);
+
+/* queue used for poll wait on config changes. */
+static DECLARE_WAIT_QUEUE_HEAD(config_wait);
+
+/* increase each time a new configuration is applied. */
+static unsigned long config_version;
+
+/* Stats gathered from the LSM. */
+struct container_stats csm_stats;
+
+struct container_stats_mapping {
+	const char *key;
+	size_t *value;
+};
+
+/* Key value pair mapping for the sysfs entry. */
+struct container_stats_mapping csm_stats_mapping[] = {
+	{ "ProtoEncodingFailed", &csm_stats.proto_encoding_failed },
+	{ "WorkQueueFailed", &csm_stats.workqueue_failed },
+	{ "EventWritingFailed", &csm_stats.event_writing_failed },
+	{ "SizePickingFailed", &csm_stats.size_picking_failed },
+	{ "PipeAlreadyOpened", &csm_stats.pipe_already_opened },
+};
+
+/*
+ * Is monitoring enabled? Defaults to disabled.
+ * These variables might be used without locking csm_rwsem_config to check if an
+ * LSM hook can bail quickly. The semaphore is taken later to ensure CSM is
+ * still enabled.
+ *
+ * csm_enabled is true if any collector is enabled.
+ */
+bool csm_enabled;
+static bool csm_container_enabled;
+bool csm_execute_enabled;
+bool csm_memexec_enabled;
+
+/* securityfs control files */
+static struct dentry *csm_dir;
+static struct dentry *csm_enabled_file;
+static struct dentry *csm_container_file;
+static struct dentry *csm_config_file;
+static struct dentry *csm_config_vers_file;
+static struct dentry *csm_pipe_file;
+static struct dentry *csm_stats_file;
+
+/* Pipes to forward data to user-mode. */
+DECLARE_RWSEM(csm_rwsem_pipe);
+static struct file *csm_user_read_pipe;
+struct file *csm_user_write_pipe;
+
+/* Option to disable the CSM features at boot. */
+static bool cmdline_boot_disabled;
+bool cmdline_boot_vsock_enabled;
+
+/* Options disabled by default. */
+static bool cmdline_boot_pipe_enabled;
+static bool cmdline_boot_config_enabled;
+
+/* Option to fully enabled the LSM at boot for automated testing. */
+static bool cmdline_default_enabled;
+
+static int csm_boot_disabled_setup(char *str)
+{
+	return kstrtobool(str, &cmdline_boot_disabled);
+}
+early_param("csm.disabled", csm_boot_disabled_setup);
+
+static int csm_default_enabled_setup(char *str)
+{
+	return kstrtobool(str, &cmdline_default_enabled);
+}
+early_param("csm.default.enabled", csm_default_enabled_setup);
+
+static int csm_boot_vsock_enabled_setup(char *str)
+{
+	return kstrtobool(str, &cmdline_boot_vsock_enabled);
+}
+early_param("csm.vsock.enabled", csm_boot_vsock_enabled_setup);
+
+static int csm_boot_pipe_enabled_setup(char *str)
+{
+	return kstrtobool(str, &cmdline_boot_pipe_enabled);
+}
+early_param("csm.pipe.enabled", csm_boot_pipe_enabled_setup);
+
+static int csm_boot_config_enabled_setup(char *str)
+{
+	return kstrtobool(str, &cmdline_boot_config_enabled);
+}
+early_param("csm.config.enabled", csm_boot_config_enabled_setup);
+
+static bool pipe_in_use(void)
+{
+	struct pipe_inode_info *pipe;
+
+	lockdep_assert_held_write(&csm_rwsem_config);
+	if (csm_user_read_pipe) {
+		pipe = get_pipe_info(csm_user_read_pipe);
+		if (pipe)
+			return READ_ONCE(pipe->readers) > 1;
+	}
+	return false;
+}
+
+/* Close pipe, force has to be true to close pipe if it is still being used. */
+int close_pipe_files(bool force)
+{
+	if (csm_user_read_pipe) {
+		/* Pipe is still used. */
+		if (pipe_in_use()) {
+			if (!force)
+				return -EBUSY;
+			pr_warn("pipe is closed while it is still being used.\n");
+		}
+
+		fput(csm_user_read_pipe);
+		fput(csm_user_write_pipe);
+		csm_user_read_pipe = NULL;
+		csm_user_write_pipe = NULL;
+	}
+	return 0;
+}
+
+static void csm_update_config(schema_ConfigurationRequest *req)
+{
+	schema_ExecuteCollectorConfig *econf;
+	size_t i;
+	bool enumerate_processes = false;
+
+	/* Expect the lock to be held for write before this call. */
+	lockdep_assert_held_write(&csm_rwsem_config);
+
+	/* This covers the scenario where a client is connected and the config
+	 * transitions the execute collector from disabled to enabled. In that
+	 * case there may have been execute events not sent. So they are
+	 * enumerated.
+	 */
+	if (!csm_execute_enabled && req->execute_config.enabled &&
+	    pipe_in_use())
+		enumerate_processes = true;
+
+	csm_container_enabled = req->container_config.enabled;
+	csm_execute_enabled = req->execute_config.enabled;
+	csm_memexec_enabled = req->memexec_config.enabled;
+
+	/* csm_enabled is true if any collector is enabled. */
+	csm_enabled = csm_container_enabled || csm_execute_enabled ||
+		csm_memexec_enabled;
+
+	/* Clean-up existing configurations. */
+	kfree(csm_execute_config.envp_allowlist);
+	memset(&csm_execute_config, 0, sizeof(csm_execute_config));
+
+	if (csm_execute_enabled) {
+		econf = &req->execute_config;
+		csm_execute_config.argv_limit = econf->argv_limit;
+		csm_execute_config.envp_limit = econf->envp_limit;
+
+		/* Swap the allowlist so it is not freed on return. */
+		csm_execute_config.envp_allowlist = econf->envp_allowlist.arg;
+		econf->envp_allowlist.arg = NULL;
+	}
+
+	/* Reset all stats and close pipe if disabled. */
+	if (!csm_enabled) {
+		for (i = 0; i < ARRAY_SIZE(csm_stats_mapping); i++)
+			*csm_stats_mapping[i].value = 0;
+
+		close_pipe_files(true);
+	}
+
+	config_version++;
+	if (enumerate_processes)
+		csm_enumerate_processes();
+	wake_up(&config_wait);
+}
+
+int csm_update_config_from_buffer(void *data, size_t size)
+{
+	schema_ConfigurationRequest c = {};
+	pb_istream_t istream;
+
+	c.execute_config.envp_allowlist.funcs.decode = pb_decode_string_array;
+
+	istream = pb_istream_from_buffer(data, size);
+	if (!pb_decode(&istream, schema_ConfigurationRequest_fields, &c)) {
+		kfree(c.execute_config.envp_allowlist.arg);
+		return -EINVAL;
+	}
+
+	down_write(&csm_rwsem_config);
+	csm_update_config(&c);
+	up_write(&csm_rwsem_config);
+
+	return 0;
+}
+
+static ssize_t csm_config_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	ssize_t err = 0;
+	void *mem;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	/* Duplicate user memory to safely parse protobuf. */
+	mem = memdup_user(buf, count);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
+	err = csm_update_config_from_buffer(mem, count);
+	if (!err)
+		err = count;
+
+	kfree(mem);
+	return err;
+}
+
+static const struct file_operations csm_config_fops = {
+	.write = csm_config_write,
+};
+
+static void csm_enable(void)
+{
+	schema_ConfigurationRequest req = {};
+
+	/* Expect the lock to be held for write before this call. */
+	lockdep_assert_held_write(&csm_rwsem_config);
+
+	/* Default configuration */
+	req.container_config.enabled = true;
+	req.execute_config.enabled = true;
+	req.execute_config.argv_limit = UINT_MAX;
+	req.execute_config.envp_limit = UINT_MAX;
+	req.memexec_config.enabled = true;
+	csm_update_config(&req);
+}
+
+static void csm_disable(void)
+{
+	schema_ConfigurationRequest req = {};
+
+	/* Expect the lock to be held for write before this call. */
+	lockdep_assert_held_write(&csm_rwsem_config);
+
+	/* Zero configuration disable all collectors. */
+	csm_update_config(&req);
+	pr_info("disabled\n");
+}
+
+static ssize_t csm_enabled_read(struct file *file, char __user *buf,
+				size_t count, loff_t *ppos)
+{
+	const char *str = csm_enabled ? "1\n" : "0\n";
+
+	return simple_read_from_buffer(buf, count, ppos, str, 2);
+}
+
+static ssize_t csm_enabled_write(struct file *file, const char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	bool enabled;
+	int err;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (count <= 0 || count > PAGE_SIZE || *ppos)
+		return -EINVAL;
+
+	err = kstrtobool_from_user(buf, count, &enabled);
+	if (err)
+		return err;
+
+	down_write(&csm_rwsem_config);
+
+	if (enabled)
+		csm_enable();
+	else
+		csm_disable();
+
+	up_write(&csm_rwsem_config);
+
+	return count;
+}
+
+static const struct file_operations csm_enabled_fops = {
+	.read = csm_enabled_read,
+	.write = csm_enabled_write,
+};
+
+static int csm_config_version_open(struct inode *inode, struct file *file)
+{
+	/* private_data is used to keep the latest config version read. */
+	file->private_data = (void*)-1;
+	return 0;
+}
+
+static ssize_t csm_config_version_read(struct file *file, char __user *buf,
+				       size_t count, loff_t *ppos)
+{
+	unsigned long version = config_version;
+	file->private_data = (void*)version;
+	return simple_read_from_buffer(buf, count, ppos, &version,
+				       sizeof(version));
+}
+
+static __poll_t csm_config_version_poll(struct file *file,
+					struct poll_table_struct *poll_tab)
+{
+	if ((unsigned long)file->private_data != config_version)
+		return EPOLLIN;
+	poll_wait(file, &config_wait, poll_tab);
+	if ((unsigned long)file->private_data != config_version)
+		return EPOLLIN;
+	return 0;
+}
+
+static const struct file_operations csm_config_version_fops = {
+	.open = csm_config_version_open,
+	.read = csm_config_version_read,
+	.poll = csm_config_version_poll,
+};
+
+static int csm_pipe_open(struct inode *inode, struct file *file)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	if (!csm_enabled)
+		return -EAGAIN;
+	return 0;
+}
+
+/* Similar to file_clone_open that is available only in 4.19 and up. */
+static inline struct file *pipe_clone_open(struct file *file)
+{
+	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
+}
+
+/* Check if the pipe is still used, else recreate and dup it. */
+static struct file *csm_dup_pipe(void)
+{
+	long pipe_size = 1024 * PAGE_SIZE;
+	long actual_size;
+	struct file *pipes[2] = {NULL, NULL};
+	struct file *ret;
+	int err;
+
+	down_write(&csm_rwsem_pipe);
+
+	err = close_pipe_files(false);
+	if (err) {
+		ret = ERR_PTR(err);
+		csm_stats.pipe_already_opened++;
+		goto out;
+	}
+
+	err = create_pipe_files(pipes, O_NONBLOCK);
+	if (err) {
+		ret = ERR_PTR(err);
+		goto out;
+	}
+
+	/*
+	 * Try to increase the pipe size to 1024 pages, if there is not
+	 * enough memory, pipes will stay unchanged.
+	 */
+	actual_size = pipe_fcntl(pipes[0], F_SETPIPE_SZ, pipe_size);
+	if (actual_size != pipe_size)
+		pr_err("failed to resize pipe to 1024 pages, error: %ld, fallback to the default value\n",
+		       actual_size);
+
+	csm_user_read_pipe = pipes[0];
+	csm_user_write_pipe = pipes[1];
+
+	/* Clone the file so we can track if the reader is still used. */
+	ret = pipe_clone_open(csm_user_read_pipe);
+
+out:
+	up_write(&csm_rwsem_pipe);
+	return ret;
+}
+
+static ssize_t csm_pipe_read(struct file *file, char __user *buf,
+				       size_t count, loff_t *ppos)
+{
+	int fd;
+	ssize_t err;
+	struct file *local_pipe;
+
+	/* No partial reads. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	fd = get_unused_fd_flags(0);
+	if (fd < 0)
+		return fd;
+
+	local_pipe = csm_dup_pipe();
+	if (IS_ERR(local_pipe)) {
+		err = PTR_ERR(local_pipe);
+		local_pipe = NULL;
+		goto error;
+	}
+
+	err = simple_read_from_buffer(buf, count, ppos, &fd, sizeof(fd));
+	if (err < 0)
+		goto error;
+
+	if (err < sizeof(fd)) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	/* Install the file descriptor when we know everything succeeded. */
+	fd_install(fd, local_pipe);
+
+	csm_enumerate_processes();
+
+	return err;
+
+error:
+	if (local_pipe)
+		fput(local_pipe);
+	put_unused_fd(fd);
+	return err;
+}
+
+
+static const struct file_operations csm_pipe_fops = {
+	.open = csm_pipe_open,
+	.read = csm_pipe_read,
+};
+
+static void set_container_decode_callbacks(schema_Container *container)
+{
+	container->pod_namespace.funcs.decode = pb_decode_string_field;
+	container->pod_name.funcs.decode = pb_decode_string_field;
+	container->container_name.funcs.decode = pb_decode_string_field;
+	container->container_image_uri.funcs.decode = pb_decode_string_field;
+	container->labels.funcs.decode = pb_decode_string_array;
+}
+
+static void set_container_encode_callbacks(schema_Container *container)
+{
+	container->pod_namespace.funcs.encode = pb_encode_string_field;
+	container->pod_name.funcs.encode = pb_encode_string_field;
+	container->container_name.funcs.encode = pb_encode_string_field;
+	container->container_image_uri.funcs.encode = pb_encode_string_field;
+	container->labels.funcs.encode = pb_encode_string_array;
+}
+
+static void free_container_callbacks_args(schema_Container *container)
+{
+	kfree(container->pod_namespace.arg);
+	kfree(container->pod_name.arg);
+	kfree(container->container_name.arg);
+	kfree(container->container_image_uri.arg);
+	kfree(container->labels.arg);
+}
+
+static ssize_t csm_container_write(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	ssize_t err = 0;
+	void *mem;
+	u64 cid;
+	pb_istream_t istream;
+	struct task_struct *task;
+	schema_ContainerReport report = {};
+	schema_Event event = {};
+	schema_Container *container;
+	char *uuid = NULL;
+
+	/* Notify that this collector is not yet enabled. */
+	if (!csm_container_enabled)
+		return -EAGAIN;
+
+	/* No partial writes. */
+	if (*ppos != 0)
+		return -EINVAL;
+
+	/* Duplicate user memory to safely parse protobuf. */
+	mem = memdup_user(buf, count);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
+	/* Callback to decode string in protobuf. */
+	set_container_decode_callbacks(&report.container);
+
+	istream = pb_istream_from_buffer(mem, count);
+	if (!pb_decode(&istream, schema_ContainerReport_fields, &report)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Check protobuf is as expected */
+	if (report.pid == 0 ||
+	    report.container.container_id != 0) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	/* Find if the process id is linked to an existing container-id. */
+	rcu_read_lock();
+	task = find_task_by_pid_ns(report.pid, &init_pid_ns);
+	if (task) {
+		cid = audit_get_contid(task);
+		if (cid == AUDIT_CID_UNSET)
+			err = -ENOENT;
+	} else {
+		err = -ENOENT;
+	}
+	rcu_read_unlock();
+
+	if (err)
+		goto out;
+
+	uuid = kzalloc(PROCESS_UUID_SIZE, GFP_KERNEL);
+	if (!uuid)
+		goto out;
+
+	/* Provide the uuid for the top process of the container. */
+	err = get_process_uuid_by_pid(report.pid, uuid, PROCESS_UUID_SIZE);
+	if (err)
+		goto out;
+
+	/* Correct the container-id and feed the event to vsock */
+	report.container.container_id = cid;
+	report.container.init_uuid.funcs.encode = pb_encode_uuid_field;
+	report.container.init_uuid.arg = uuid;
+	container = &event.event.container.container;
+	*container = report.container;
+
+	/* Use encode callback to generate the final proto. */
+	set_container_encode_callbacks(container);
+
+	event.which_event = schema_Event_container_tag;
+
+	err = csm_sendeventproto(schema_Event_fields, &event);
+	if (!err)
+		err = count;
+
+out:
+	/* Free any allocated nanopb callback arguments. */
+	free_container_callbacks_args(&report.container);
+	kfree(uuid);
+	kfree(mem);
+	return err;
+}
+
+static const struct file_operations csm_container_fops = {
+	.write = csm_container_write,
+};
+
+static int csm_show_stats(struct seq_file *p, void *v)
+{
+	size_t i;
+
+	for (i = 0; i < ARRAY_SIZE(csm_stats_mapping); i++) {
+		seq_printf(p, "%s:\t%zu\n",
+			   csm_stats_mapping[i].key,
+			   *csm_stats_mapping[i].value);
+	}
+
+	return 0;
+}
+
+static int csm_stats_open(struct inode *inode, struct file *file)
+{
+	size_t i, size = 1; /* Start at one for the null byte. */
+
+	for (i = 0; i < ARRAY_SIZE(csm_stats_mapping); i++) {
+		/*
+		 * Calculate the maximum length:
+		 * - Length of the key
+		 * - 3 additional chars :\t\n
+		 * - longest unsigned 64-bit integer.
+		 */
+		size += strlen(csm_stats_mapping[i].key)
+			+ 3 + sizeof("18446744073709551615");
+	}
+
+	return single_open_size(file, csm_show_stats, NULL, size);
+}
+
+static const struct file_operations csm_stats_fops = {
+	.open		= csm_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/* Prevent user-mode from using vsock on our port. */
+static int csm_socket_connect(struct socket *sock, struct sockaddr *address,
+			      int addrlen)
+{
+	struct sockaddr_vm *vaddr = (struct sockaddr_vm *)address;
+
+	/* Filter only vsock sockets */
+	if (!sock->sk || sock->sk->sk_family != AF_VSOCK)
+		return 0;
+
+	/* Allow kernel sockets. */
+	if (sock->sk->sk_kern_sock)
+		return 0;
+
+	if (addrlen < sizeof(*vaddr))
+		return -EINVAL;
+
+	/* Forbid access to the CSM VMM backend port. */
+	if (vaddr->svm_port == CSM_HOST_PORT)
+		return -EPERM;
+
+	return 0;
+}
+
+static int csm_setxattr(struct dentry *dentry, const char *name,
+			const void *value, size_t size, int flags)
+{
+	if (csm_enabled && !strcmp(name, XATTR_SECURITY_CSM))
+		return -EPERM;
+	return 0;
+}
+
+static struct security_hook_list csm_hooks[] __lsm_ro_after_init = {
+	/* Track process execution. */
+	LSM_HOOK_INIT(bprm_check_security, csm_bprm_check_security),
+	LSM_HOOK_INIT(task_post_alloc, csm_task_post_alloc),
+	LSM_HOOK_INIT(task_exit, csm_task_exit),
+
+	/* Block vsock access when relevant. */
+	LSM_HOOK_INIT(socket_connect, csm_socket_connect),
+
+	/* Track memory execution */
+	LSM_HOOK_INIT(file_mprotect, csm_mprotect),
+	LSM_HOOK_INIT(mmap_file, csm_mmap_file),
+
+	/* Track file modification provenance. */
+	LSM_HOOK_INIT(file_pre_free_security, csm_file_pre_free),
+
+	/* Block modyfing csm xattr. */
+	LSM_HOOK_INIT(inode_setxattr, csm_setxattr),
+};
+
+static int __init csm_init(void)
+{
+	int err;
+
+	if (cmdline_boot_disabled)
+		return 0;
+
+	/*
+	 * If cmdline_boot_vsock_enabled is false, only the event pool will be
+	 * allocated. The destroy function will clean-up only what was reserved.
+	 */
+	err = vsock_initialize();
+	if (err)
+		return err;
+
+	csm_dir = securityfs_create_dir("container_monitor", NULL);
+	if (IS_ERR(csm_dir)) {
+		err = PTR_ERR(csm_dir);
+		goto error;
+	}
+
+	csm_enabled_file = securityfs_create_file("enabled", 0644, csm_dir,
+						  NULL, &csm_enabled_fops);
+	if (IS_ERR(csm_enabled_file)) {
+		err = PTR_ERR(csm_enabled_file);
+		goto error_rmdir;
+	}
+
+	csm_container_file = securityfs_create_file("container", 0200, csm_dir,
+						  NULL, &csm_container_fops);
+	if (IS_ERR(csm_container_file)) {
+		err = PTR_ERR(csm_container_file);
+		goto error_rm_enabled;
+	}
+
+	csm_config_vers_file = securityfs_create_file("config_version", 0400,
+						      csm_dir, NULL,
+						      &csm_config_version_fops);
+	if (IS_ERR(csm_config_vers_file)) {
+		err = PTR_ERR(csm_config_vers_file);
+		goto error_rm_container;
+	}
+
+	if (cmdline_boot_config_enabled) {
+		csm_config_file = securityfs_create_file("config", 0200,
+							 csm_dir, NULL,
+							 &csm_config_fops);
+		if (IS_ERR(csm_config_file)) {
+			err = PTR_ERR(csm_config_file);
+			goto error_rm_config_vers;
+		}
+	}
+
+	if (cmdline_boot_pipe_enabled) {
+		csm_pipe_file = securityfs_create_file("pipe", 0400, csm_dir,
+						       NULL, &csm_pipe_fops);
+		if (IS_ERR(csm_pipe_file)) {
+			err = PTR_ERR(csm_pipe_file);
+			goto error_rm_config;
+		}
+	}
+
+	csm_stats_file = securityfs_create_file("stats", 0400, csm_dir,
+						 NULL, &csm_stats_fops);
+	if (IS_ERR(csm_stats_file)) {
+		err = PTR_ERR(csm_stats_file);
+		goto error_rm_pipe;
+	}
+
+	pr_debug("created securityfs control files\n");
+
+	security_add_hooks(csm_hooks, ARRAY_SIZE(csm_hooks), "csm");
+	pr_debug("registered hooks\n");
+
+	/* Off-by-default, only used for testing images. */
+	if (cmdline_default_enabled) {
+		down_write(&csm_rwsem_config);
+		csm_enable();
+		up_write(&csm_rwsem_config);
+	}
+
+	return 0;
+
+error_rm_pipe:
+	if (cmdline_boot_pipe_enabled)
+		securityfs_remove(csm_pipe_file);
+error_rm_config:
+	if (cmdline_boot_config_enabled)
+		securityfs_remove(csm_config_file);
+error_rm_config_vers:
+	securityfs_remove(csm_config_vers_file);
+error_rm_container:
+	securityfs_remove(csm_container_file);
+error_rm_enabled:
+	securityfs_remove(csm_enabled_file);
+error_rmdir:
+	securityfs_remove(csm_dir);
+error:
+	vsock_destroy();
+	pr_warn("fs initialization error: %d", err);
+	return err;
+}
+
+late_initcall(csm_init);
diff --git a/security/container/monitor.h b/security/container/monitor.h
new file mode 100644
index 0000000..cab3d5b
--- /dev/null
+++ b/security/container/monitor.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Container Security Monitor module
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#define pr_fmt(fmt)	"container-security-monitor: " fmt
+
+#include <linux/kernel.h>
+#include <linux/security.h>
+#include <linux/fs.h>
+#include <linux/rwsem.h>
+#include <linux/binfmts.h>
+#include <linux/xattr.h>
+#include <config.pb.h>
+#include <event.pb.h>
+#include <pb_encode.h>
+#include <pb_decode.h>
+
+#include "monitoring_protocol.h"
+
+/* Part of the CSM configuration response. */
+#define CSM_VERSION 1
+
+/* protects csm_*_enabled and configurations. */
+extern struct rw_semaphore csm_rwsem_config;
+
+/* protects csm_host_port and csm_vsocket. */
+extern struct rw_semaphore csm_rwsem_vsocket;
+
+/* Port to connect to the host on, over virtio-vsock */
+#define CSM_HOST_PORT 4444
+
+/*
+ * Is monitoring enabled? Defaults to disabled.
+ * These variables might be used as gates without locking (as processor ensures
+ * valid proper access for native scalar values) so it can bail quickly.
+ */
+extern bool csm_enabled;
+extern bool csm_execute_enabled;
+extern bool csm_memexec_enabled;
+
+/* Configuration options for execute collector. */
+struct execute_config {
+	size_t argv_limit;
+	size_t envp_limit;
+	char *envp_allowlist;
+};
+
+extern struct execute_config csm_execute_config;
+
+/* pipe to forward vsock packets to user-mode. */
+extern struct rw_semaphore csm_rwsem_pipe;
+extern struct file *csm_user_write_pipe;
+
+/* Was vsock enabled at boot time? */
+extern bool cmdline_boot_vsock_enabled;
+
+/* Stats on LSM events. */
+struct container_stats {
+	size_t proto_encoding_failed;
+	size_t event_writing_failed;
+	size_t workqueue_failed;
+	size_t size_picking_failed;
+	size_t pipe_already_opened;
+};
+
+extern struct container_stats csm_stats;
+
+/* Streams file numbers are unknown from the kernel */
+#define STDIN_FILENO	0
+#define STDOUT_FILENO	1
+#define STDERR_FILENO	2
+
+/* security attribute for file provenance. */
+#define XATTR_SECURITY_CSM XATTR_SECURITY_PREFIX "csm"
+
+/* monitor functions */
+int csm_update_config_from_buffer(void *data, size_t size);
+
+/* vsock functions */
+int vsock_initialize(void);
+void vsock_destroy(void);
+int vsock_late_initialize(void);
+int csm_sendeventproto(const pb_field_t fields[], schema_Event *event);
+int csm_sendconfigrespproto(const pb_field_t fields[],
+			    schema_ConfigurationResponse *resp);
+
+/* process events functions */
+int csm_bprm_check_security(struct linux_binprm *bprm);
+void csm_task_exit(struct task_struct *task);
+void csm_task_post_alloc(struct task_struct *task);
+int get_process_uuid_by_pid(pid_t pid_nr, char *buffer, size_t size);
+
+/* memory execution events functions */
+int csm_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
+					  unsigned long prot);
+int csm_mmap_file(struct file *file, unsigned long reqprot,
+				  unsigned long prot, unsigned long flags);
+
+/* Tracking of file modification provenance. */
+void csm_file_pre_free(struct file *file);
+
+/* nano functions */
+bool pb_encode_string_field(pb_ostream_t *stream, const pb_field_t *field,
+			    void * const *arg);
+bool pb_decode_string_field(pb_istream_t *stream, const pb_field_t *field,
+		      void **arg);
+ssize_t pb_encode_string_field_limit(pb_ostream_t *stream,
+				     const pb_field_t *field,
+				     void * const *arg, size_t limit);
+bool pb_encode_string_array(pb_ostream_t *stream, const pb_field_t *field,
+			    void * const *arg);
+bool pb_decode_string_array(pb_istream_t *stream, const pb_field_t *field,
+			    void **arg);
+bool pb_encode_uuid_field(pb_ostream_t *stream, const pb_field_t *field,
+			  void * const *arg);
+bool pb_encode_ip4(pb_ostream_t *stream, const pb_field_t *field,
+		   void * const *arg);
+bool pb_encode_ip6(pb_ostream_t *stream, const pb_field_t *field,
+		   void * const *arg);
+
diff --git a/security/container/monitoring_protocol.h b/security/container/monitoring_protocol.h
new file mode 100644
index 0000000..dbdfc9c
--- /dev/null
+++ b/security/container/monitoring_protocol.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+/* Container security monitoring protocol definitions */
+
+#include <linux/types.h>
+
+enum csm_msgtype {
+	CSM_MSG_TYPE_HEARTBEAT = 1,
+	CSM_MSG_EVENT_PROTO = 2,
+	CSM_MSG_CONFIG_REQUEST_PROTO = 3,
+	CSM_MSG_CONFIG_RESPONSE_PROTO = 4,
+};
+
+struct csm_msg_hdr {
+	__le32 msg_type;
+	__le32 msg_length;
+};
+
+/* The process uuid is a 128-bits identifier */
+#define PROCESS_UUID_SIZE 16
+
+/* The entire structure forms the collision domain. */
+union process_uuid {
+	struct {
+		__u32 machineid;
+		__u64 start_time;
+		__u32 tgid;
+	} __attribute__((packed));
+	__u8 data[PROCESS_UUID_SIZE];
+};
diff --git a/security/container/pb.c b/security/container/pb.c
new file mode 100644
index 0000000..f24e58f
--- /dev/null
+++ b/security/container/pb.c
@@ -0,0 +1,175 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Container Security Monitor module
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#include "monitor.h"
+
+#include <linux/string.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <net/ipv6.h>
+
+bool pb_encode_string_field(pb_ostream_t *stream, const pb_field_t *field,
+			    void * const *arg)
+{
+	const uint8_t *str = (const uint8_t *)*arg;
+
+	/* If the string is not set, skip this string. */
+	if (!str)
+		return true;
+
+	if (!pb_encode_tag_for_field(stream, field))
+		return false;
+
+	return pb_encode_string(stream, str, strlen(str));
+}
+
+bool pb_decode_string_field(pb_istream_t *stream, const pb_field_t *field,
+			    void **arg)
+{
+	size_t size;
+	void *data;
+
+	*arg = NULL;
+
+	size = stream->bytes_left;
+
+	/* Ensure a null-byte at the end */
+	if (size + 1 < size)
+		return false;
+
+	data = kzalloc(size + 1, GFP_KERNEL);
+	if (!data)
+		return false;
+
+	if (!pb_read(stream, data, size)) {
+		kfree(data);
+		return false;
+	}
+
+	*arg = data;
+
+	return true;
+}
+
+bool pb_encode_string_array(pb_ostream_t *stream, const pb_field_t *field,
+			    void * const *arg)
+{
+	char *strs = (char *)*arg;
+
+	/* If the string array is not set, skip this string array. */
+	if (!strs)
+		return true;
+
+	do {
+		if (!pb_encode_string_field(stream, field,
+					    (void * const *) &strs))
+			return false;
+
+		strs += strlen(strs) + 1;
+	} while (*strs != 0);
+
+	return true;
+}
+
+/* Limit the encoded string size and return how many characters were added. */
+ssize_t pb_encode_string_field_limit(pb_ostream_t *stream,
+				     const pb_field_t *field,
+				     void * const *arg, size_t limit)
+{
+	char *str = (char *)*arg;
+	size_t length;
+
+	/* If the string is not set, skip this string. */
+	if (!str)
+		return 0;
+
+	if (!pb_encode_tag_for_field(stream, field))
+		return -EINVAL;
+
+	length = strlen(str);
+	if (length > limit)
+		length = limit;
+
+	if (!pb_encode_string(stream, (uint8_t *)str, length))
+		return -EINVAL;
+
+	return length;
+}
+
+bool pb_decode_string_array(pb_istream_t *stream, const pb_field_t *field,
+			    void **arg)
+{
+	size_t needed, used = 0;
+	char *data, *strs;
+
+	/* String length, and two null-bytes for the end of the list. */
+	needed = stream->bytes_left + 2;
+	if (needed < stream->bytes_left)
+		return false;
+
+	if (*arg) {
+		/* Calculate used space from the current list. */
+		strs = (char *)*arg;
+		do {
+			used += strlen(strs + used) + 1;
+		} while (strs[used] != 0);
+
+		if (used + needed < needed)
+			return false;
+	}
+
+	data = krealloc(*arg, used + needed, GFP_KERNEL);
+	if (!data)
+		return false;
+
+	/* Will always be freed by the caller */
+	*arg = data;
+
+	/* Reset the new part of the buffer. */
+	memset(data + used, 0, needed);
+
+	/* Read what's in the stream buffer only. */
+	if (!pb_read(stream, data + used, stream->bytes_left))
+		return false;
+
+	return true;
+}
+
+bool pb_encode_fixed_string(pb_ostream_t *stream, const pb_field_t *field,
+			    const uint8_t *data, size_t length)
+{
+	/* If the data is not set, skip this string. */
+	if (!data)
+		return true;
+
+	if (!pb_encode_tag_for_field(stream, field))
+		return false;
+
+	return pb_encode_string(stream, data, length);
+}
+
+
+bool pb_encode_uuid_field(pb_ostream_t *stream, const pb_field_t *field,
+			  void * const *arg)
+{
+	return pb_encode_fixed_string(stream, field, (const uint8_t *)*arg,
+				      PROCESS_UUID_SIZE);
+}
+
+bool pb_encode_ip4(pb_ostream_t *stream, const pb_field_t *field,
+		   void * const *arg)
+{
+	return pb_encode_fixed_string(stream, field, (const uint8_t *)*arg,
+				      sizeof(struct in_addr));
+}
+
+bool pb_encode_ip6(pb_ostream_t *stream, const pb_field_t *field,
+		   void * const *arg)
+{
+	return pb_encode_fixed_string(stream, field, (const uint8_t *)*arg,
+				      sizeof(struct in6_addr));
+}
diff --git a/security/container/process.c b/security/container/process.c
new file mode 100644
index 0000000..a66fd2b
--- /dev/null
+++ b/security/container/process.c
@@ -0,0 +1,1149 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Container Security Monitor module
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#include "monitor.h"
+
+#include <linux/atomic.h>
+#include <linux/audit.h>
+#include <linux/file.h>
+#include <linux/highmem.h>
+#include <linux/mempool.h>
+#include <linux/mm.h>
+#include <linux/mount.h>
+#include <linux/notifier.h>
+#include <linux/net.h>
+#include <linux/path.h>
+#include <linux/pid.h>
+#include <linux/pid_namespace.h>
+#include <linux/random.h>
+#include <linux/rcupdate.h>
+#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/timekeeping.h>
+#include <linux/vmalloc.h>
+#include <linux/workqueue.h>
+#include <linux/xattr.h>
+#include <net/ipv6.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <overlayfs/overlayfs.h>
+#include <uapi/linux/magic.h>
+#include <uapi/asm/mman.h>
+
+/* Configuration options for execute collector. */
+struct execute_config csm_execute_config;
+
+/* unique atomic value for the machine boot instance */
+static atomic_t machine_rand = ATOMIC_INIT(0);
+
+/* sequential container identifier */
+static atomic_t contid = ATOMIC_INIT(0);
+
+/* Generation id for each enumeration invocation. */
+static atomic_t enumeration_count = ATOMIC_INIT(0);
+
+struct file_provenance {
+	/* pid of the process doing the first write. */
+	pid_t tgid;
+	/* start_time of the process to uniquely identify it. */
+	u64 start_time;
+};
+
+struct csm_enumerate_processes_work_data {
+	struct work_struct work;
+	int enumeration_count;
+};
+
+static void *kmap_argument_stack(struct linux_binprm *bprm, void **ctx)
+{
+	char *argv;
+	int err;
+	unsigned long i, pos, count;
+	void *map;
+	struct page *page;
+
+	/* vma_pages() returns the number of pages reserved for the stack */
+	count = vma_pages(bprm->vma);
+
+	if (likely(count == 1)) {
+		err = get_user_pages_remote(current, bprm->mm, bprm->p, 1,
+					    FOLL_FORCE, &page, NULL, NULL);
+		if (err != 1)
+			return NULL;
+
+		argv = kmap(page);
+		*ctx = page;
+	} else {
+		/*
+		 * If more than one pages is needed, copy all of them to a set
+		 * of pages. Parsing the argument across kmap pages in different
+		 * addresses would make it impractical.
+		 */
+		argv = vmalloc(count * PAGE_SIZE);
+		if (!argv)
+			return NULL;
+
+		for (i = 0; i < count; i++) {
+			pos = ALIGN_DOWN(bprm->p, PAGE_SIZE) + i * PAGE_SIZE;
+			err = get_user_pages_remote(current, bprm->mm, pos, 1,
+						    FOLL_FORCE, &page, NULL,
+						    NULL);
+			if (err <= 0) {
+				vfree(argv);
+				return NULL;
+			}
+
+			map = kmap(page);
+			memcpy(argv + i * PAGE_SIZE, map, PAGE_SIZE);
+			kunmap(page);
+			put_page(page);
+		}
+		*ctx = bprm;
+	}
+
+	return argv;
+}
+
+static void kunmap_argument_stack(struct linux_binprm *bprm, void *addr,
+				  void *ctx)
+{
+	struct page *page;
+
+	if (!addr)
+		return;
+
+	if (likely(vma_pages(bprm->vma) == 1)) {
+		page = (struct page *)ctx;
+		kunmap(page);
+		put_page(ctx);
+	} else {
+		vfree(addr);
+	}
+}
+
+static char *find_array_next_entry(char *array, unsigned long *offset,
+				   unsigned long end)
+{
+	char *entry;
+	unsigned long off = *offset;
+
+	if (off >= end)
+		return NULL;
+
+	/* Check the entry is null terminated and in bound */
+	entry = array + off;
+	while (array[off]) {
+		if (++off >= end)
+			return NULL;
+	}
+
+	/* Pass the null byte for the next iteration */
+	*offset = off + 1;
+
+	return entry;
+}
+
+struct string_arr_ctx {
+	struct linux_binprm *bprm;
+	void *stack;
+};
+
+static size_t get_config_limit(size_t *config_ptr)
+{
+	lockdep_assert_held_read(&csm_rwsem_config);
+
+	/*
+	 * If execute is not enabled, do not capture arguments.
+	 * The vsock packet won't be sent anyway.
+	 */
+	if (!csm_execute_enabled)
+		return 0;
+
+	return *config_ptr;
+}
+
+static bool encode_current_argv(pb_ostream_t *stream, const pb_field_t *field,
+				void * const *arg)
+{
+	struct string_arr_ctx *ctx = (struct string_arr_ctx *)*arg;
+	int i;
+	struct linux_binprm *bprm = ctx->bprm;
+	unsigned long offset = bprm->p % PAGE_SIZE;
+	unsigned long end = vma_pages(bprm->vma) * PAGE_SIZE;
+	char *argv = ctx->stack;
+	char *entry;
+	size_t limit, used = 0;
+	ssize_t ret;
+
+	limit = get_config_limit(&csm_execute_config.argv_limit);
+	if (!limit)
+		return true;
+
+	for (i = 0; i < bprm->argc; i++) {
+		entry = find_array_next_entry(argv, &offset, end);
+		if (!entry)
+			return false;
+
+		ret = pb_encode_string_field_limit(stream, field,
+						   (void * const *)&entry,
+						   limit - used);
+		if (ret < 0)
+			return false;
+
+		used += ret;
+
+		if (used >= limit)
+			break;
+	}
+
+	return true;
+}
+
+static bool check_envp_allowlist(char *envp)
+{
+	bool ret = false;
+	char *strs, *equal;
+	size_t str_size, equal_pos;
+
+	/* If execute is not enabled, skip all. */
+	if (!csm_execute_enabled)
+		goto out;
+
+	/* No filter, allow all. */
+	strs = csm_execute_config.envp_allowlist;
+	if (!strs) {
+		ret = true;
+		goto out;
+	}
+
+	/*
+	 * Identify the key=value separation.
+	 * If none exists use the whole string as a key.
+	 */
+	equal = strchr(envp, '=');
+	equal_pos = equal ? (equal - envp) : strlen(envp);
+
+	/* Default to skip if no match found. */
+	ret = false;
+
+	do {
+		str_size = strlen(strs);
+
+		/*
+		 * If the filter length align with the key value equal sign,
+		 * it might be a match, check the key value.
+		 */
+		if (str_size == equal_pos &&
+		    !strncmp(strs, envp, str_size)) {
+			ret = true;
+			goto out;
+		}
+
+		strs += str_size + 1;
+	} while (*strs != 0);
+
+out:
+	return ret;
+}
+
+static bool encode_current_envp(pb_ostream_t *stream, const pb_field_t *field,
+				void * const *arg)
+{
+	struct string_arr_ctx *ctx = (struct string_arr_ctx *)*arg;
+	int i;
+	struct linux_binprm *bprm = ctx->bprm;
+	unsigned long offset = bprm->p % PAGE_SIZE;
+	unsigned long end = vma_pages(bprm->vma) * PAGE_SIZE;
+	char *argv = ctx->stack;
+	char *entry;
+	size_t limit, used = 0;
+	ssize_t ret;
+
+	limit = get_config_limit(&csm_execute_config.envp_limit);
+	if (!limit)
+		return true;
+
+	/* Skip arguments */
+	for (i = 0; i < bprm->argc; i++) {
+		if (!find_array_next_entry(argv, &offset, end))
+			return false;
+	}
+
+	for (i = 0; i < bprm->envc; i++) {
+		entry = find_array_next_entry(argv, &offset, end);
+		if (!entry)
+			return false;
+
+		if (!check_envp_allowlist(entry))
+			continue;
+
+		ret = pb_encode_string_field_limit(stream, field,
+						   (void * const *)&entry,
+						   limit - used);
+		if (ret < 0)
+			return false;
+
+		used += ret;
+
+		if (used >= limit)
+			break;
+	}
+
+	return true;
+}
+
+static bool is_overlayfs_mounted(struct file *file)
+{
+	struct vfsmount *mnt;
+	struct super_block *mnt_sb;
+
+	mnt = file->f_path.mnt;
+	if (mnt == NULL)
+		return false;
+
+	mnt_sb = mnt->mnt_sb;
+	if (mnt_sb == NULL || mnt_sb->s_magic != OVERLAYFS_SUPER_MAGIC)
+		return false;
+
+	return true;
+}
+
+/*
+ * Before the process starts, identify a possible container by checking if the
+ * task is on a pid namespace and the target file is using an overlayfs mounting
+ * point. This check is valid for COS and GKE but not all existing containers.
+ */
+static bool is_possible_container(struct task_struct *task,
+				  struct file *file)
+{
+	if (task_active_pid_ns(task) == &init_pid_ns)
+		return false;
+
+	return is_overlayfs_mounted(file);
+}
+
+/*
+ * Generates a random identifier for this boot instance.
+ * This identifier is generated only when needed to increase the entropy
+ * available compared to doing it at early boot.
+ */
+static u32 get_machine_id(void)
+{
+	int machineid, old;
+
+	machineid = atomic_read(&machine_rand);
+
+	if (unlikely(machineid == 0)) {
+		machineid = (int)get_random_int();
+		if (machineid == 0)
+			machineid = 1;
+		old = atomic_cmpxchg(&machine_rand, 0, machineid);
+
+		/* If someone beat us, use their value. */
+		if (old != 0)
+			machineid = old;
+	}
+
+	return (u32)machineid;
+}
+
+/*
+ * Generate a 128-bit unique identifier for the process by appending:
+ *  - A machine identifier unique per boot.
+ *  - The start time of the process in nanoseconds.
+ *  - The tgid for the set of threads in a process.
+ */
+static int get_process_uuid(struct task_struct *task, char *buffer, size_t size)
+{
+	union process_uuid *id = (union process_uuid *)buffer;
+
+	memset(buffer, 0, size);
+
+	if (WARN_ON(size < PROCESS_UUID_SIZE))
+		return -EINVAL;
+
+	id->machineid = get_machine_id();
+	id->start_time = ktime_mono_to_real(task->group_leader->start_time);
+	id->tgid = task_tgid_nr(task);
+
+	return 0;
+}
+
+int get_process_uuid_by_pid(pid_t pid_nr, char *buffer, size_t size)
+{
+	int err;
+	struct task_struct *task = NULL;
+
+	rcu_read_lock();
+	task = find_task_by_pid_ns(pid_nr, &init_pid_ns);
+	if (!task) {
+		err = -ENOENT;
+		goto out;
+	}
+	err = get_process_uuid(task, buffer, size);
+out:
+	rcu_read_unlock();
+	return err;
+}
+
+static int get_process_uuid_from_xattr(struct file *file, char *buffer,
+				       size_t size)
+{
+	struct dentry *dentry;
+	int err;
+	struct file_provenance prov;
+	union process_uuid *id = (union process_uuid *)buffer;
+
+	memset(buffer, 0, size);
+
+	if (WARN_ON(size < PROCESS_UUID_SIZE))
+		return -EINVAL;
+
+	/* The file is part of overlayfs on the upper layer. */
+	if (!is_overlayfs_mounted(file))
+		return -ENODATA;
+
+	dentry = ovl_dentry_upper(file->f_path.dentry);
+	if (!dentry)
+		return -ENODATA;
+
+	err = __vfs_getxattr(dentry, dentry->d_inode,
+			     XATTR_SECURITY_CSM, &prov, sizeof(prov));
+	/* returns -ENODATA if the xattr does not exist. */
+	if (err < 0)
+		return err;
+	if (err != sizeof(prov)) {
+		pr_err("unexpected size for xattr: %zu -> %d\n",
+		       size, err);
+		return -ENODATA;
+	}
+
+	id->machineid = get_machine_id();
+	id->start_time = prov.start_time;
+	id->tgid = prov.tgid;
+	return 0;
+}
+
+u64 csm_set_contid(struct task_struct *task)
+{
+	u64 cid;
+	struct pid_namespace *ns;
+
+	ns = task_active_pid_ns(task);
+	if (WARN_ON(!task->audit) || WARN_ON(!ns))
+		return AUDIT_CID_UNSET;
+
+	cid = atomic_inc_return(&contid);
+	task->audit->contid = cid;
+
+	/*
+	 * If the namespace container-id is not set, use the one assigned
+	 * to the first process created.
+	 */
+	cmpxchg(&ns->cid, 0, cid);
+	return cid;
+}
+
+u64 csm_get_ns_contid(struct pid_namespace *ns)
+{
+	if (!ns || !ns->cid)
+		return AUDIT_CID_UNSET;
+
+	return ns->cid;
+}
+
+union ip_data {
+	struct in_addr ip4;
+	struct in6_addr ip6;
+};
+
+struct file_data {
+	void *allocated;
+	union ip_data local;
+	union ip_data remote;
+	char modified_uuid[PROCESS_UUID_SIZE];
+};
+
+static void free_file_data(struct file_data *fdata)
+{
+	free_page((unsigned long)fdata->allocated);
+	fdata->allocated = NULL;
+}
+
+static void fill_socket_description(struct sockaddr_storage *saddr,
+				   union ip_data *idata,
+				   schema_SocketIp *schema_socketip)
+{
+	struct sockaddr_in *sin4 = (struct sockaddr_in *)saddr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)saddr;
+
+	schema_socketip->family = saddr->ss_family;
+
+	switch (saddr->ss_family) {
+	case AF_INET:
+		schema_socketip->port = ntohs(sin4->sin_port);
+		idata->ip4 = sin4->sin_addr;
+		schema_socketip->ip.funcs.encode = pb_encode_ip4;
+		schema_socketip->ip.arg = &idata->ip4;
+		break;
+	case AF_INET6:
+		schema_socketip->port = ntohs(sin6->sin6_port);
+		idata->ip6 = sin6->sin6_addr;
+		schema_socketip->ip.funcs.encode = pb_encode_ip6;
+		schema_socketip->ip.arg = &idata->ip6;
+		break;
+	}
+}
+
+static int fill_file_overlayfs(struct file *file, schema_File *schema_file,
+			       struct file_data *fdata)
+{
+	struct dentry *dentry;
+	int err;
+	schema_Overlay *overlayfs;
+
+	/* If not an overlayfs superblock, done. */
+	if (!is_overlayfs_mounted(file))
+		return 0;
+
+	dentry = file->f_path.dentry;
+	schema_file->which_filesystem = schema_File_overlayfs_tag;
+	overlayfs = &schema_file->filesystem.overlayfs;
+	overlayfs->lower_layer = ovl_dentry_lower(dentry);
+	overlayfs->upper_layer = ovl_dentry_upper(dentry);
+
+	err = get_process_uuid_from_xattr(file, fdata->modified_uuid,
+					  sizeof(fdata->modified_uuid));
+	/* If there is no xattr, just skip the modified_uuid field. */
+	if (err == -ENODATA)
+		return 0;
+	if (err < 0)
+		return err;
+
+	overlayfs->modified_uuid.funcs.encode = pb_encode_uuid_field;
+	overlayfs->modified_uuid.arg = fdata->modified_uuid;
+	return 0;
+}
+
+static int fill_file_description(struct file *file, schema_File *schema_file,
+				 struct file_data *fdata)
+{
+	char *buf;
+	int err;
+	u32 mode;
+	char *path;
+	struct socket *socket;
+	schema_Socket *socketfs;
+	struct sockaddr_storage saddr;
+
+	memset(fdata, 0, sizeof(*fdata));
+
+	if (file == NULL)
+		return 0;
+
+	schema_file->ino = file_inode(file)->i_ino;
+	mode = file_inode(file)->i_mode;
+
+	/* For pipes, no need to resolve the path. */
+	if (S_ISFIFO(mode))
+		return 0;
+
+	if (S_ISSOCK(mode)) {
+		socket = (struct socket *)file->private_data;
+		socketfs = &schema_file->filesystem.socket;
+
+		/* Local socket */
+		err = kernel_getsockname(socket, (struct sockaddr *)&saddr);
+		if (err >= 0) {
+			fill_socket_description(&saddr, &fdata->local,
+						&socketfs->local);
+		}
+
+		/* Remote socket, might not be connected. */
+		err = kernel_getpeername(socket, (struct sockaddr *)&saddr);
+		if (err >= 0) {
+			fill_socket_description(&saddr, &fdata->remote,
+						&socketfs->remote);
+		}
+
+		schema_file->which_filesystem = schema_File_socket_tag;
+		return 0;
+	}
+
+	/*
+	 * From this point, we care about all the other types of files as their
+	 * path provides interesting insight.
+	 */
+	buf = (char *)__get_free_page(GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	fdata->allocated = buf;
+
+	path = d_path(&file->f_path, buf, PAGE_SIZE);
+	if (IS_ERR(path)) {
+		free_file_data(fdata);
+		return PTR_ERR(path);
+	}
+
+	schema_file->fullpath.funcs.encode = pb_encode_string_field;
+	schema_file->fullpath.arg = path; /* buf is freed in free_file_data. */
+
+	err = fill_file_overlayfs(file, schema_file, fdata);
+	if (err) {
+		free_file_data(fdata);
+		return err;
+	}
+
+	return 0;
+}
+
+static int fill_stream_description(schema_Descriptor *desc, int fd,
+				   struct file_data *fdata)
+{
+	struct fd sfd;
+	struct file *file;
+	int err = 0;
+
+	sfd = fdget(fd);
+	file = sfd.file;
+
+	if (file == NULL) {
+		memset(fdata, 0, sizeof(*fdata));
+		goto end;
+	}
+
+	desc->mode = file_inode(file)->i_mode;
+	err = fill_file_description(file, &desc->file, fdata);
+
+end:
+	fdput(sfd);
+	return err;
+}
+
+static int populate_proc_uuid_common(schema_Process *proc, char *uuid,
+				     size_t uuid_size, char *parent_uuid,
+				     size_t parent_uuid_size,
+				     struct task_struct *task)
+{
+	int err;
+	struct task_struct *parent;
+	/* Generate unique identifier for the process and its parent */
+	err = get_process_uuid(task, uuid, uuid_size);
+	if (err)
+		return err;
+
+	proc->uuid.funcs.encode = pb_encode_uuid_field;
+	proc->uuid.arg = uuid;
+
+	rcu_read_lock();
+
+	if (!pid_alive(task))
+		goto out;
+	/*
+	 * I don't think this needs to be task_rcu_dereference because
+	 * real_parent is only supposed to be accessed using RCU.
+	 */
+	parent = rcu_dereference(task->real_parent);
+
+	if (parent) {
+		err = get_process_uuid(parent, parent_uuid, parent_uuid_size);
+		if (!err) {
+			proc->parent_uuid.funcs.encode = pb_encode_uuid_field;
+			proc->parent_uuid.arg = parent_uuid;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+
+	return err;
+}
+
+/* Populate the fields that we always want to set in Process messages. */
+static int populate_proc_common(schema_Process *proc, char *uuid,
+				size_t uuid_size, char *parent_uuid,
+				size_t parent_uuid_size,
+				struct task_struct *task)
+{
+	u64 cid;
+	struct pid_namespace *ns = task_active_pid_ns(task);
+
+	/* Container identifier for the current namespace. */
+	proc->container_id = csm_get_ns_contid(ns);
+
+	/*
+	 * If the process container-id is different, the process tree is part of
+	 * a different session within the namespace (kubectl/docker exec,
+	 * liveness probe or others).
+	 */
+	cid = audit_get_contid(task);
+	if (proc->container_id != cid)
+		proc->exec_session_id = cid;
+
+	/* Add information about pid in different namespaces */
+	proc->pid = task_pid_nr(task);
+	proc->parent_pid = task_ppid_nr(task);
+	proc->container_pid = task_pid_nr_ns(task, ns);
+	proc->container_parent_pid = task_ppid_nr_ns(task, ns);
+
+	return populate_proc_uuid_common(proc, uuid, uuid_size, parent_uuid,
+					 parent_uuid_size, task);
+}
+
+int csm_bprm_check_security(struct linux_binprm *bprm)
+{
+	char uuid[PROCESS_UUID_SIZE];
+	char parent_uuid[PROCESS_UUID_SIZE];
+	int err;
+	schema_Event event = {};
+	schema_Process *proc;
+	struct string_arr_ctx argv_ctx;
+	void *stack = NULL, *ctx = NULL;
+	u64 cid;
+	struct file_data path_data = {};
+	struct file_data stdin_data = {};
+	struct file_data stdout_data = {};
+	struct file_data stderr_data = {};
+
+	/*
+	 * Always create a container-id for containerized processes.
+	 * If the LSM is enabled later, we can track existing containers.
+	 */
+	cid = audit_get_contid(current);
+
+	if (cid == AUDIT_CID_UNSET) {
+		if (!is_possible_container(current, bprm->file))
+			return 0;
+
+		cid = csm_set_contid(current);
+
+		if (cid == AUDIT_CID_UNSET)
+			return 0;
+	}
+
+	if (!csm_execute_enabled)
+		return 0;
+
+	/* The interpreter will call us again with more context. */
+	if (bprm->buf[0] == '#' && bprm->buf[1] == '!')
+		return 0;
+
+	proc = &event.event.execute.proc;
+	err = populate_proc_common(proc, uuid, sizeof(uuid), parent_uuid,
+				   sizeof(parent_uuid), cu