diff --git a/.gitignore b/.gitignore
index edb1dcf..81e12c0 100644
--- a/.gitignore
+++ b/.gitignore
@@ -181,6 +181,7 @@
 /test-date
 /test-delta
 /test-dump-cache-tree
+/test-dump-split-index
 /test-scrap-cache-tree
 /test-genrandom
 /test-hashmap
diff --git a/.mailmap b/.mailmap
index 11057cb..8aefb5a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -85,6 +85,7 @@
 Jeff Muizelaar <jmuizelaar@mozilla.com> <jeff@infidigm.net>
 Jens Axboe <axboe@kernel.dk> <axboe@suse.de>
 Jens Axboe <axboe@kernel.dk> <jens.axboe@oracle.com>
+Jens Lindström <jl@opera.com> Jens Lindstrom <jl@opera.com>
 Jim Meyering <jim@meyering.net> <meyering@redhat.com>
 Joachim Berdal Haga <cjhaga@fys.uio.no>
 Johannes Schindelin <Johannes.Schindelin@gmx.de> <johannes.schindelin@gmx.de>
@@ -113,6 +114,7 @@
 Karsten Blees <blees@dcon.de> <karsten.blees@gmail.com>
 Kay Sievers <kay.sievers@vrfy.org> <kay.sievers@suse.de>
 Kay Sievers <kay.sievers@vrfy.org> <kay@mam.(none)>
+Kazuki Saitoh <ksaitoh560@gmail.com> kazuki saitoh <ksaitoh560@gmail.com>
 Keith Cascio <keith@CS.UCLA.EDU> <keith@cs.ucla.edu>
 Kent Engstrom <kent@lysator.liu.se>
 Kevin Leung <kevinlsk@gmail.com>
@@ -202,6 +204,7 @@
 Shawn O. Pearce <spearce@spearce.org>
 Simon Hausmann <hausmann@kde.org> <simon@lst.de>
 Simon Hausmann <hausmann@kde.org> <shausman@trolltech.com>
+Stefan Beller <stefanbeller@gmail.com> <stefanbeller@googlemail.com>
 Stefan Naewe <stefan.naewe@gmail.com> <stefan.naewe@atlas-elektronik.com>
 Stefan Naewe <stefan.naewe@gmail.com> <stefan.naewe@googlemail.com>
 Stefan Sperling <stsp@elego.de> <stsp@stsp.name>
@@ -229,6 +232,7 @@
 Tommy Thorn <tommy-git@thorn.ws> <tt1729@yahoo.com>
 Tony Luck <tony.luck@intel.com>
 Tor Arne Vestbø <torarnv@gmail.com> <tavestbo@trolltech.com>
+Trần Ngọc Quân <vnwildman@gmail.com> Tran Ngoc Quan <vnwildman@gmail.com>
 Trent Piepho <tpiepho@gmail.com> <tpiepho@freescale.com>
 Trent Piepho <tpiepho@gmail.com> <xyzzy@speakeasy.org>
 Uwe Kleine-König <u.kleine-koenig@pengutronix.de> <Uwe.Kleine-Koenig@digi.com>
diff --git a/Documentation/CodingGuidelines b/Documentation/CodingGuidelines
index 4d90c77..894546d 100644
--- a/Documentation/CodingGuidelines
+++ b/Documentation/CodingGuidelines
@@ -404,6 +404,15 @@
    documentation for version 2.6 does not mention this prefix, it has
    been supported since version 2.6.0.
 
+Error Messages
+
+ - Do not end error messages with a full stop.
+
+ - Do not capitalize ("unable to open %s", not "Unable to open %s")
+
+ - Say what the error is first ("cannot open %s", not "%s: cannot open")
+
+
 Writing Documentation:
 
  Most (if not all) of the documentation pages are written in the
diff --git a/Documentation/RelNotes/2.0.2.txt b/Documentation/RelNotes/2.0.2.txt
index c48c0aa..8e8321b 100644
--- a/Documentation/RelNotes/2.0.2.txt
+++ b/Documentation/RelNotes/2.0.2.txt
@@ -11,3 +11,22 @@
  * Recent updates to "git repack" started to duplicate objects that
    are in packfiles marked with .keep flag into the new packfile by
    mistake.
+
+ * "git clone -b brefs/tags/bar" would have mistakenly thought we were
+   following a single tag, even though it was a name of the branch,
+   because it incorrectly used strstr().
+
+ * "%G" (nothing after G) is an invalid pretty format specifier, but
+   the parser did not notice it as garbage.
+
+ * Code to avoid adding the same alternate object store twice was
+   subtly broken for a long time, but nobody seems to have noticed.
+
+ * A handful of code paths had to read the commit object more than
+   once when showing header fields that are usually not parsed.  The
+   internal data structure to keep track of the contents of the commit
+   object has been updated to reduce the need for this double-reading,
+   and to allow the caller find the length of the object.
+
+ * During "git rebase --merge", a conflicted patch could not be
+   skipped with "--skip" if the next one also conflicted.
diff --git a/Documentation/RelNotes/2.0.3.txt b/Documentation/RelNotes/2.0.3.txt
new file mode 100644
index 0000000..4047b46
--- /dev/null
+++ b/Documentation/RelNotes/2.0.3.txt
@@ -0,0 +1,17 @@
+Git v2.0.3 Release Notes
+========================
+
+ * An ancient rewrite passed a wrong pointer to a curl library
+   function in a rarely used code path.
+
+ * "filter-branch" left an empty single-parent commit that results when
+   all parents of a merge commit gets mapped to the same commit, even
+   under "--prune-empty".
+
+ * "log --show-signature" incorrectly decided the color to paint a
+   mergetag that was and was not correctly validated.
+
+ * "log --show-signature" did not pay attention to "--graph" option.
+
+Also a lot of fixes to the tests and some updates to the docs are
+included.
diff --git a/Documentation/RelNotes/2.1.0.txt b/Documentation/RelNotes/2.1.0.txt
index 3b65461..13c7ec5 100644
--- a/Documentation/RelNotes/2.1.0.txt
+++ b/Documentation/RelNotes/2.1.0.txt
@@ -93,7 +93,8 @@
    users need to explicitly set the variable to 'true' if they want
    to resurrect the now-ignored use case.
 
- * "git replace" learned the "--edit" subcommand.
+ * "git replace" learned the "--edit" subcommand to create a
+   replacement by editing an existing object.
 
  * "git send-email" learned "--to-cover" and "--cc-cover" options, to
    tell it to copy To: and Cc: headers found in the first input file
@@ -115,6 +116,14 @@
 
  * Build procedure for 'subtree' (in contrib/) has been cleaned up.
 
+ * The support for the profile-feedback build, which has been left
+   bit-rotten for quite a while, has been updated.
+
+ * An experimental format to use two files (the base file and
+   incremental changes relative to it) to represent the index has been
+   introduced; this may reduce I/O cost of rewriting a large index
+   when only small part of the working tree changes.
+
  * Effort to shrink the size of patches Windows folks maintain on top
    by upstreaming them continues.
 
@@ -141,6 +150,9 @@
    example, "update-ref --stdin [-z]" has been updated to use this
    API.
 
+ * skip_prefix() and strip_suffix() API functions are used a lot more
+   widely throughout the codebase now.
+
  * Parts of the test scripts can be skipped by using a range notation,
    e.g. "sh t1234-test.sh --run='1-4 6 8-'" to omit test piece 5 and 7
    and run everything else.
@@ -185,6 +197,7 @@
  * Code to avoid adding the same alternate object store twice was
    subtly broken for a long time, but nobody seems to have noticed.
    (merge 80b4785 rs/fix-alt-odb-path-comparison later to maint).
+   (merge 539e750 ek/alt-odb-entry-fix later to maint).
 
  * The "%<(10,trunc)%s" pretty format specifier in the log family of
    commands is used to truncate the string to a given length (e.g. 10
@@ -213,6 +226,10 @@
    couple of options unique to "git merge".
    (merge 8fee872 jk/complete-merge-pull later to maint).
 
+ * An ancient rewrite passed a wrong pointer to a curl library
+   function in a rarely used code path.
+   (merge 479eaa8 ah/fix-http-push later to maint).
+
  * "--ignore-space-change" option of "git apply" ignored the spaces
    at the beginning of line too aggressively, which is inconsistent
    with the option of the same name "diff" and "git diff" have.
@@ -242,6 +259,11 @@
    bit.
    (merge 5304810 jk/diff-files-assume-unchanged later to maint).
 
+ * "filter-branch" left an empty single-parent commit that results when
+   all parents of a merge commit gets mapped to the same commit, even
+   under "--prune-empty".
+   (merge 79bc4ef cb/filter-branch-prune-empty-degenerate-merges later to maint).
+
  * "git format-patch" did not enforce the rule that the "--follow"
    option from the log/diff family of commands must be used with
    exactly one pathspec.
@@ -267,6 +289,13 @@
    distinguish missing objects from type errors.
    (merge 77583e7 jk/index-pack-report-missing later to maint).
 
+ * "log --show-signature" incorrectly decided the color to paint a
+   mergetag that was and was not correctly validated.
+   (merge 42c55ce mg/fix-log-mergetag-color later to maint).
+
+ * "log --show-signature" did not pay attention to "--graph" option.
+   (merge cf3983d zk/log-graph-showsig later to maint).
+
  * "git mailinfo" used to read beyond the end of header string while
    parsing an incoming e-mail message to extract the patch.
    (merge b1a013d rs/mailinfo-header-cmp later to maint).
@@ -276,6 +305,11 @@
    except for case differences.
    (merge baa37bf dt/merge-recursive-case-insensitive later to maint).
 
+ * Merging changes into a file that ends in an incomplete line made the
+   last line into a complete one, even when the other branch did not
+   change anything around the end of file.
+   (merge ba31180 mk/merge-incomplete-files later to maint).
+
  * "git pack-objects" unnecessarily copied the previous contents when
    extending the hashtable, even though it will populate the table
    from scratch anyway.
diff --git a/Documentation/config.txt b/Documentation/config.txt
index 1d718bd..c55c22a 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -2354,6 +2354,11 @@
 	"--ignore-submodules" option. The 'git submodule' commands are not
 	affected by this setting.
 
+tag.sort::
+	This variable controls the sort ordering of tags when displayed by
+	linkgit:git-tag[1]. Without the "--sort=<value>" option provided, the
+	value of this variable will be used as the default.
+
 tar.umask::
 	This variable can be used to restrict the permission bits of
 	tar archive entries.  The default is 0002, which turns off the
diff --git a/Documentation/git-replace.txt b/Documentation/git-replace.txt
index 61461b9..8fff598 100644
--- a/Documentation/git-replace.txt
+++ b/Documentation/git-replace.txt
@@ -10,6 +10,7 @@
 [verse]
 'git replace' [-f] <object> <replacement>
 'git replace' [-f] --edit <object>
+'git replace' [-f] --graft <commit> [<parent>...]
 'git replace' -d <object>...
 'git replace' [--format=<format>] [-l [<pattern>]]
 
@@ -73,6 +74,23 @@
 	newly created object. See linkgit:git-var[1] for details about
 	how the editor will be chosen.
 
+--raw::
+	When editing, provide the raw object contents rather than
+	pretty-printed ones. Currently this only affects trees, which
+	will be shown in their binary form. This is harder to work with,
+	but can help when repairing a tree that is so corrupted it
+	cannot be pretty-printed. Note that you may need to configure
+	your editor to cleanly read and write binary data.
+
+--graft <commit> [<parent>...]::
+	Create a graft commit. A new commit is created with the same
+	content as <commit> except that its parents will be
+	[<parent>...] instead of <commit>'s parents. A replacement ref
+	is then created to replace <commit> with the newly created
+	commit. See contrib/convert-grafts-to-replace-refs.sh for an
+	example script based on this option that can convert grafts to
+	replace refs.
+
 -l <pattern>::
 --list <pattern>::
 	List replace refs for objects that match the given pattern (or
diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt
index 987395d..0b84769 100644
--- a/Documentation/git-rev-parse.txt
+++ b/Documentation/git-rev-parse.txt
@@ -102,7 +102,7 @@
 +
 If you want to make sure that the output actually names an object in
 your object database and/or can be used as a specific type of object
-you require, you can add "^{type}" peeling operator to the parameter.
+you require, you can add "\^{type}" peeling operator to the parameter.
 For example, `git rev-parse "$VAR^{commit}"` will make sure `$VAR`
 names an existing object that is a commit-ish (i.e. a commit, or an
 annotated tag that points at a commit).  To make sure that `$VAR`
@@ -245,6 +245,10 @@
 --show-toplevel::
 	Show the absolute path of the top-level directory.
 
+--shared-index-path::
+	Show the path to the shared index file in split index mode, or
+	empty if not in split-index mode.
+
 Other Options
 ~~~~~~~~~~~~~
 
diff --git a/Documentation/git-tag.txt b/Documentation/git-tag.txt
index b424a1b..3209083 100644
--- a/Documentation/git-tag.txt
+++ b/Documentation/git-tag.txt
@@ -99,7 +99,9 @@
 	Sort in a specific order. Supported type is "refname"
 	(lexicographic order), "version:refname" or "v:refname" (tag
 	names are treated as versions). Prepend "-" to reverse sort
-	order.
+	order. When this option is not given, the sort order defaults to the
+	value configured for the 'tag.sort' variable if it exists, or
+	lexicographic order otherwise. See linkgit:git-config[1].
 
 --column[=<options>]::
 --no-column::
@@ -317,6 +319,7 @@
 SEE ALSO
 --------
 linkgit:git-check-ref-format[1].
+linkgit:git-config[1].
 
 GIT
 ---
diff --git a/Documentation/git-update-index.txt b/Documentation/git-update-index.txt
index d6de4a0..dfc09d9 100644
--- a/Documentation/git-update-index.txt
+++ b/Documentation/git-update-index.txt
@@ -161,6 +161,17 @@
 	Only meaningful with `--stdin` or `--index-info`; paths are
 	separated with NUL character instead of LF.
 
+--split-index::
+--no-split-index::
+	Enable or disable split index mode. If enabled, the index is
+	split into two files, $GIT_DIR/index and $GIT_DIR/sharedindex.<SHA-1>.
+	Changes are accumulated in $GIT_DIR/index while the shared
+	index file contains all index entries stays unchanged. If
+	split-index mode is already enabled and `--split-index` is
+	given again, all changes in $GIT_DIR/index are pushed back to
+	the shared index file. This mode is designed for very large
+	indexes that take a signficant amount of time to read or write.
+
 \--::
 	Do not interpret any more arguments as options.
 
diff --git a/Documentation/git.txt b/Documentation/git.txt
index 7924209..a0f1ede 100644
--- a/Documentation/git.txt
+++ b/Documentation/git.txt
@@ -43,9 +43,11 @@
 branch of the `git.git` repository.
 Documentation for older releases are available here:
 
-* link:v2.0.1/git.html[documentation for release 2.0.1]
+* link:v2.0.3/git.html[documentation for release 2.0.3]
 
 * release notes for
+  link:RelNotes/2.0.3.txt[2.0.3],
+  link:RelNotes/2.0.2.txt[2.0.2],
   link:RelNotes/2.0.1.txt[2.0.1],
   link:RelNotes/2.0.0.txt[2.0.0].
 
@@ -905,31 +907,54 @@
 	based on whether stdout appears to be redirected to a file or not.
 
 'GIT_TRACE'::
-	If this variable is set to "1", "2" or "true" (comparison
-	is case insensitive), Git will print `trace:` messages on
-	stderr telling about alias expansion, built-in command
-	execution and external command execution.
-	If this variable is set to an integer value greater than 1
-	and lower than 10 (strictly) then Git will interpret this
-	value as an open file descriptor and will try to write the
-	trace messages into this file descriptor.
-	Alternatively, if this variable is set to an absolute path
-	(starting with a '/' character), Git will interpret this
-	as a file path and will try to write the trace messages
-	into it.
+	Enables general trace messages, e.g. alias expansion, built-in
+	command execution and external command execution.
++
+If this variable is set to "1", "2" or "true" (comparison
+is case insensitive), trace messages will be printed to
+stderr.
++
+If the variable is set to an integer value greater than 2
+and lower than 10 (strictly) then Git will interpret this
+value as an open file descriptor and will try to write the
+trace messages into this file descriptor.
++
+Alternatively, if the variable is set to an absolute path
+(starting with a '/' character), Git will interpret this
+as a file path and will try to write the trace messages
+into it.
++
+Unsetting the variable, or setting it to empty, "0" or
+"false" (case insensitive) disables trace messages.
 
 'GIT_TRACE_PACK_ACCESS'::
-	If this variable is set to a path, a file will be created at
-	the given path logging all accesses to any packs. For each
+	Enables trace messages for all accesses to any packs. For each
 	access, the pack file name and an offset in the pack is
 	recorded. This may be helpful for troubleshooting some
 	pack-related performance problems.
+	See 'GIT_TRACE' for available trace output options.
 
 'GIT_TRACE_PACKET'::
-	If this variable is set, it shows a trace of all packets
-	coming in or out of a given program. This can help with
-	debugging object negotiation or other protocol issues. Tracing
-	is turned off at a packet starting with "PACK".
+	Enables trace messages for all packets coming in or out of a
+	given program. This can help with debugging object negotiation
+	or other protocol issues. Tracing is turned off at a packet
+	starting with "PACK".
+	See 'GIT_TRACE' for available trace output options.
+
+'GIT_TRACE_PERFORMANCE'::
+	Enables performance related trace messages, e.g. total execution
+	time of each Git command.
+	See 'GIT_TRACE' for available trace output options.
+
+'GIT_TRACE_SETUP'::
+	Enables trace messages printing the .git, working tree and current
+	working directory after Git has completed its setup phase.
+	See 'GIT_TRACE' for available trace output options.
+
+'GIT_TRACE_SHALLOW'::
+	Enables trace messages that can help debugging fetching /
+	cloning of shallow repositories.
+	See 'GIT_TRACE' for available trace output options.
 
 GIT_LITERAL_PATHSPECS::
 	Setting this variable to `1` will cause Git to treat all
@@ -1043,7 +1068,7 @@
 -------
 Git was started by Linus Torvalds, and is currently maintained by Junio
 C Hamano. Numerous contributions have come from the Git mailing list
-<git@vger.kernel.org>.  http://www.ohloh.net/p/git/contributors/summary
+<git@vger.kernel.org>.  http://www.openhub.net/p/git/contributors/summary
 gives you a more complete list of contributors.
 
 If you have a clone of git.git itself, the
diff --git a/Documentation/gitrepository-layout.txt b/Documentation/gitrepository-layout.txt
index 17d2ea6..79653f3 100644
--- a/Documentation/gitrepository-layout.txt
+++ b/Documentation/gitrepository-layout.txt
@@ -155,6 +155,10 @@
 	The current index file for the repository.  It is
 	usually not found in a bare repository.
 
+sharedindex.<SHA-1>::
+	The shared index part, to be referenced by $GIT_DIR/index and
+	other temporary index files. Only valid in split index mode.
+
 info::
 	Additional information about the repository is recorded
 	in this directory.
diff --git a/Documentation/technical/api-hashmap.txt b/Documentation/technical/api-hashmap.txt
index b977ae8..ad7a5bd 100644
--- a/Documentation/technical/api-hashmap.txt
+++ b/Documentation/technical/api-hashmap.txt
@@ -8,11 +8,19 @@
 
 `struct hashmap`::
 
-	The hash table structure.
+	The hash table structure. Members can be used as follows, but should
+	not be modified directly:
 +
-The `size` member keeps track of the total number of entries. The `cmpfn`
-member is a function used to compare two entries for equality. The `table` and
-`tablesize` members store the hash table and its size, respectively.
+The `size` member keeps track of the total number of entries (0 means the
+hashmap is empty).
++
+`tablesize` is the allocated size of the hash table. A non-0 value indicates
+that the hashmap is initialized. It may also be useful for statistical purposes
+(i.e. `size / tablesize` is the current load factor).
++
+`cmpfn` stores the comparison function specified in `hashmap_init()`. In
+advanced scenarios, it may be useful to change this, e.g. to switch between
+case-sensitive and case-insensitive lookup.
 
 `struct hashmap_entry`::
 
@@ -58,6 +66,15 @@
 +
 `strihash` and `memihash` are case insensitive versions.
 
+`unsigned int sha1hash(const unsigned char *sha1)`::
+
+	Converts a cryptographic hash (e.g. SHA-1) into an int-sized hash code
+	for use in hash tables. Cryptographic hashes are supposed to have
+	uniform distribution, so in contrast to `memhash()`, this just copies
+	the first `sizeof(int)` bytes without shuffling any bits. Note that
+	the results will be different on big-endian and little-endian
+	platforms, so they should not be stored or transferred over the net.
+
 `void hashmap_init(struct hashmap *map, hashmap_cmp_fn equals_function, size_t initial_size)`::
 
 	Initializes a hashmap structure.
@@ -101,6 +118,20 @@
 If an entry with matching hash code is found, `key` and `keydata` are passed
 to `hashmap_cmp_fn` to decide whether the entry matches the key.
 
+`void *hashmap_get_from_hash(const struct hashmap *map, unsigned int hash, const void *keydata)`::
+
+	Returns the hashmap entry for the specified hash code and key data,
+	or NULL if not found.
++
+`map` is the hashmap structure.
++
+`hash` is the hash code of the entry to look up.
++
+If an entry with matching hash code is found, `keydata` is passed to
+`hashmap_cmp_fn` to decide whether the entry matches the key. The
+`entry_or_key` parameter points to a bogus hashmap_entry structure that
+should not be used in the comparison.
+
 `void *hashmap_get_next(const struct hashmap *map, const void *entry)`::
 
 	Returns the next equal hashmap entry, or NULL if not found. This can be
@@ -162,6 +193,21 @@
 `hashmap_iter_first` is a combination of both (i.e. initializes the iterator
 and returns the first entry, if any).
 
+`const char *strintern(const char *string)`::
+`const void *memintern(const void *data, size_t len)`::
+
+	Returns the unique, interned version of the specified string or data,
+	similar to the `String.intern` API in Java and .NET, respectively.
+	Interned strings remain valid for the entire lifetime of the process.
++
+Can be used as `[x]strdup()` or `xmemdupz` replacement, except that interned
+strings / data must not be modified or freed.
++
+Interned strings are best used for short strings with high probability of
+duplicates.
++
+Uses a hashmap to store the pool of interned strings.
+
 Usage example
 -------------
 
diff --git a/Documentation/technical/api-string-list.txt b/Documentation/technical/api-string-list.txt
index f1add51..d51a657 100644
--- a/Documentation/technical/api-string-list.txt
+++ b/Documentation/technical/api-string-list.txt
@@ -68,6 +68,11 @@
 
 * General ones (works with sorted and unsorted lists as well)
 
+`string_list_init`::
+
+	Initialize the members of the string_list, set `strdup_strings`
+	member according to the value of the second parameter.
+
 `filter_string_list`::
 
 	Apply a function to each item in a list, retaining only the
diff --git a/Documentation/technical/api-trace.txt b/Documentation/technical/api-trace.txt
new file mode 100644
index 0000000..097a651
--- /dev/null
+++ b/Documentation/technical/api-trace.txt
@@ -0,0 +1,97 @@
+trace API
+=========
+
+The trace API can be used to print debug messages to stderr or a file. Trace
+code is inactive unless explicitly enabled by setting `GIT_TRACE*` environment
+variables.
+
+The trace implementation automatically adds `timestamp file:line ... \n` to
+all trace messages. E.g.:
+
+------------
+23:59:59.123456 git.c:312               trace: built-in: git 'foo'
+00:00:00.000001 builtin/foo.c:99        foo: some message
+------------
+
+Data Structures
+---------------
+
+`struct trace_key`::
+
+	Defines a trace key (or category). The default (for API functions that
+	don't take a key) is `GIT_TRACE`.
++
+E.g. to define a trace key controlled by environment variable `GIT_TRACE_FOO`:
++
+------------
+static struct trace_key trace_foo = TRACE_KEY_INIT(FOO);
+
+static void trace_print_foo(const char *message)
+{
+	trace_print_key(&trace_foo, message);
+}
+------------
++
+Note: don't use `const` as the trace implementation stores internal state in
+the `trace_key` structure.
+
+Functions
+---------
+
+`int trace_want(struct trace_key *key)`::
+
+	Checks whether the trace key is enabled. Used to prevent expensive
+	string formatting before calling one of the printing APIs.
+
+`void trace_disable(struct trace_key *key)`::
+
+	Disables tracing for the specified key, even if the environment
+	variable was set.
+
+`void trace_printf(const char *format, ...)`::
+`void trace_printf_key(struct trace_key *key, const char *format, ...)`::
+
+	Prints a formatted message, similar to printf.
+
+`void trace_argv_printf(const char **argv, const char *format, ...)``::
+
+	Prints a formatted message, followed by a quoted list of arguments.
+
+`void trace_strbuf(struct trace_key *key, const struct strbuf *data)`::
+
+	Prints the strbuf, without additional formatting (i.e. doesn't
+	choke on `%` or even `\0`).
+
+`uint64_t getnanotime(void)`::
+
+	Returns nanoseconds since the epoch (01/01/1970), typically used
+	for performance measurements.
++
+Currently there are high precision timer implementations for Linux (using
+`clock_gettime(CLOCK_MONOTONIC)`) and Windows (`QueryPerformanceCounter`).
+Other platforms use `gettimeofday` as time source.
+
+`void trace_performance(uint64_t nanos, const char *format, ...)`::
+`void trace_performance_since(uint64_t start, const char *format, ...)`::
+
+	Prints the elapsed time (in nanoseconds), or elapsed time since
+	`start`, followed by a formatted message. Enabled via environment
+	variable `GIT_TRACE_PERFORMANCE`. Used for manual profiling, e.g.:
++
+------------
+uint64_t start = getnanotime();
+/* code section to measure */
+trace_performance_since(start, "foobar");
+------------
++
+------------
+uint64_t t = 0;
+for (;;) {
+	/* ignore */
+	t -= getnanotime();
+	/* code section to measure */
+	t += getnanotime();
+	/* ignore */
+}
+trace_performance(t, "frotz");
+------------
diff --git a/Documentation/technical/index-format.txt b/Documentation/technical/index-format.txt
index f352a9b..fe6f316 100644
--- a/Documentation/technical/index-format.txt
+++ b/Documentation/technical/index-format.txt
@@ -129,6 +129,9 @@
   (Version 4) In version 4, the padding after the pathname does not
   exist.
 
+  Interpretation of index entries in split index mode is completely
+  different. See below for details.
+
 == Extensions
 
 === Cached tree
@@ -198,3 +201,35 @@
   - At most three 160-bit object names of the entry in stages from 1 to 3
     (nothing is written for a missing stage).
 
+=== Split index
+
+  In split index mode, the majority of index entries could be stored
+  in a separate file. This extension records the changes to be made on
+  top of that to produce the final index.
+
+  The signature for this extension is { 'l', 'i, 'n', 'k' }.
+
+  The extension consists of:
+
+  - 160-bit SHA-1 of the shared index file. The shared index file path
+    is $GIT_DIR/sharedindex.<SHA-1>. If all 160 bits are zero, the
+    index does not require a shared index file.
+
+  - An ewah-encoded delete bitmap, each bit represents an entry in the
+    shared index. If a bit is set, its corresponding entry in the
+    shared index will be removed from the final index.  Note, because
+    a delete operation changes index entry positions, but we do need
+    original positions in replace phase, it's best to just mark
+    entries for removal, then do a mass deletion after replacement.
+
+  - An ewah-encoded replace bitmap, each bit represents an entry in
+    the shared index. If a bit is set, its corresponding entry in the
+    shared index will be replaced with an entry in this index
+    file. All replaced entries are stored in sorted order in this
+    index. The first "1" bit in the replace bitmap corresponds to the
+    first index entry, the second "1" bit to the second entry and so
+    on. Replaced entries may have empty path names to save space.
+
+  The remaining index entries after replaced ones will be added to the
+  final index. These added entries are also sorted by entry namme then
+  stage.
diff --git a/INSTALL b/INSTALL
index ba01e74..6ec7a24 100644
--- a/INSTALL
+++ b/INSTALL
@@ -28,7 +28,7 @@
 If you're willing to trade off (much) longer build time for a later
 faster git you can also do a profile feedback build with
 
-	$ make prefix=/usr PROFILE=BUILD all
+	$ make prefix=/usr profile
 	# make prefix=/usr PROFILE=BUILD install
 
 This will run the complete test suite as training workload and then
@@ -36,10 +36,20 @@
 which is a few percent faster on CPU intensive workloads.  This
 may be a good tradeoff for distribution packagers.
 
+Alternatively you can run profile feedback only with the git benchmark
+suite. This runs significantly faster than the full test suite, but
+has less coverage:
+
+	$ make prefix=/usr profile-fast
+	# make prefix=/usr PROFILE=BUILD install
+
 Or if you just want to install a profile-optimized version of git into
 your home directory, you could run:
 
-	$ make PROFILE=BUILD install
+	$ make profile-install
+
+or
+	$ make profile-fast-install
 
 As a caveat: a profile-optimized build takes a *lot* longer since the
 git tree must be built twice, and in order for the profiling
diff --git a/Makefile b/Makefile
index b92418d..2320de5 100644
--- a/Makefile
+++ b/Makefile
@@ -340,6 +340,8 @@
 #
 # Define GMTIME_UNRELIABLE_ERRORS if your gmtime() function does not
 # return NULL when it receives a bogus time_t.
+#
+# Define HAVE_CLOCK_GETTIME if your platform has clock_gettime in librt.
 
 GIT-VERSION-FILE: FORCE
 	@$(SHELL_PATH) ./GIT-VERSION-GEN
@@ -552,6 +554,7 @@
 TEST_PROGRAMS_NEED_X += test-date
 TEST_PROGRAMS_NEED_X += test-delta
 TEST_PROGRAMS_NEED_X += test-dump-cache-tree
+TEST_PROGRAMS_NEED_X += test-dump-split-index
 TEST_PROGRAMS_NEED_X += test-genrandom
 TEST_PROGRAMS_NEED_X += test-hashmap
 TEST_PROGRAMS_NEED_X += test-index-version
@@ -875,6 +878,7 @@
 LIB_OBJS += shallow.o
 LIB_OBJS += sideband.o
 LIB_OBJS += sigchain.o
+LIB_OBJS += split-index.o
 LIB_OBJS += strbuf.o
 LIB_OBJS += streaming.o
 LIB_OBJS += string-list.o
@@ -1498,6 +1502,11 @@
 	BASIC_CFLAGS += -DGMTIME_UNRELIABLE_ERRORS
 endif
 
+ifdef HAVE_CLOCK_GETTIME
+	BASIC_CFLAGS += -DHAVE_CLOCK_GETTIME
+	EXTLIBS += -lrt
+endif
+
 ifeq ($(TCLTK_PATH),)
 NO_TCLTK = NoThanks
 endif
@@ -1553,13 +1562,13 @@
 PROFILE_DIR := $(CURDIR)
 
 ifeq ("$(PROFILE)","GEN")
-	CFLAGS += -fprofile-generate=$(PROFILE_DIR) -DNO_NORETURN=1
+	BASIC_CFLAGS += -fprofile-generate=$(PROFILE_DIR) -DNO_NORETURN=1
 	EXTLIBS += -lgcov
 	export CCACHE_DISABLE = t
 	V = 1
 else
 ifneq ("$(PROFILE)","")
-	CFLAGS += -fprofile-use=$(PROFILE_DIR) -fprofile-correction -DNO_NORETURN=1
+	BASIC_CFLAGS += -fprofile-use=$(PROFILE_DIR) -fprofile-correction -DNO_NORETURN=1
 	export CCACHE_DISABLE = t
 	V = 1
 endif
@@ -1644,12 +1653,20 @@
 all:: shell_compatibility_test
 
 ifeq "$(PROFILE)" "BUILD"
-ifeq ($(filter all,$(MAKECMDGOALS)),all)
-all:: profile-clean
+all:: profile
+endif
+
+profile:: profile-clean
 	$(MAKE) PROFILE=GEN all
 	$(MAKE) PROFILE=GEN -j1 test
-endif
-endif
+	$(MAKE) PROFILE=GEN -j1 perf
+	$(MAKE) PROFILE=USE all
+
+profile-fast: profile-clean
+	$(MAKE) PROFILE=GEN all
+	$(MAKE) PROFILE=GEN -j1 perf
+	$(MAKE) PROFILE=USE all
+
 
 all:: $(ALL_PROGRAMS) $(SCRIPT_LIB) $(BUILT_INS) $(OTHER_PROGRAMS) GIT-BUILD-OPTIONS
 ifneq (,$X)
@@ -2336,6 +2353,12 @@
 
 install_bindir_programs := $(patsubst %,%$X,$(BINDIR_PROGRAMS_NEED_X)) $(BINDIR_PROGRAMS_NO_X)
 
+profile-install: profile
+	$(MAKE) install
+
+profile-fast-install: profile-fast
+	$(MAKE) install
+
 install: all
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
 	$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(gitexec_instdir_SQ)'
diff --git a/alloc.c b/alloc.c
index eb22a45..12afadf 100644
--- a/alloc.c
+++ b/alloc.c
@@ -18,25 +18,6 @@
 
 #define BLOCKING 1024
 
-#define DEFINE_ALLOCATOR(name, type)				\
-static unsigned int name##_allocs;				\
-void *alloc_##name##_node(void)					\
-{								\
-	static int nr;						\
-	static type *block;					\
-	void *ret;						\
-								\
-	if (!nr) {						\
-		nr = BLOCKING;					\
-		block = xmalloc(BLOCKING * sizeof(type));	\
-	}							\
-	nr--;							\
-	name##_allocs++;					\
-	ret = block++;						\
-	memset(ret, 0, sizeof(type));				\
-	return ret;						\
-}
-
 union any_object {
 	struct object object;
 	struct blob blob;
@@ -45,17 +26,73 @@
 	struct tag tag;
 };
 
-DEFINE_ALLOCATOR(blob, struct blob)
-DEFINE_ALLOCATOR(tree, struct tree)
-DEFINE_ALLOCATOR(raw_commit, struct commit)
-DEFINE_ALLOCATOR(tag, struct tag)
-DEFINE_ALLOCATOR(object, union any_object)
+struct alloc_state {
+	int count; /* total number of nodes allocated */
+	int nr;    /* number of nodes left in current allocation */
+	void *p;   /* first free node in current allocation */
+};
+
+static inline void *alloc_node(struct alloc_state *s, size_t node_size)
+{
+	void *ret;
+
+	if (!s->nr) {
+		s->nr = BLOCKING;
+		s->p = xmalloc(BLOCKING * node_size);
+	}
+	s->nr--;
+	s->count++;
+	ret = s->p;
+	s->p = (char *)s->p + node_size;
+	memset(ret, 0, node_size);
+	return ret;
+}
+
+static struct alloc_state blob_state;
+void *alloc_blob_node(void)
+{
+	struct blob *b = alloc_node(&blob_state, sizeof(struct blob));
+	b->object.type = OBJ_BLOB;
+	return b;
+}
+
+static struct alloc_state tree_state;
+void *alloc_tree_node(void)
+{
+	struct tree *t = alloc_node(&tree_state, sizeof(struct tree));
+	t->object.type = OBJ_TREE;
+	return t;
+}
+
+static struct alloc_state tag_state;
+void *alloc_tag_node(void)
+{
+	struct tag *t = alloc_node(&tag_state, sizeof(struct tag));
+	t->object.type = OBJ_TAG;
+	return t;
+}
+
+static struct alloc_state object_state;
+void *alloc_object_node(void)
+{
+	struct object *obj = alloc_node(&object_state, sizeof(union any_object));
+	obj->type = OBJ_NONE;
+	return obj;
+}
+
+static struct alloc_state commit_state;
+
+unsigned int alloc_commit_index(void)
+{
+	static unsigned int count;
+	return count++;
+}
 
 void *alloc_commit_node(void)
 {
-	static int commit_count;
-	struct commit *c = alloc_raw_commit_node();
-	c->index = commit_count++;
+	struct commit *c = alloc_node(&commit_state, sizeof(struct commit));
+	c->object.type = OBJ_COMMIT;
+	c->index = alloc_commit_index();
 	return c;
 }
 
@@ -66,13 +103,13 @@
 }
 
 #define REPORT(name, type)	\
-    report(#name, name##_allocs, name##_allocs * sizeof(type) >> 10)
+    report(#name, name##_state.count, name##_state.count * sizeof(type) >> 10)
 
 void alloc_report(void)
 {
 	REPORT(blob, struct blob);
 	REPORT(tree, struct tree);
-	REPORT(raw_commit, struct commit);
+	REPORT(commit, struct commit);
 	REPORT(tag, struct tag);
 	REPORT(object, union any_object);
 }
diff --git a/blob.c b/blob.c
index ae320bd..1fcb8e4 100644
--- a/blob.c
+++ b/blob.c
@@ -7,15 +7,8 @@
 {
 	struct object *obj = lookup_object(sha1);
 	if (!obj)
-		return create_object(sha1, OBJ_BLOB, alloc_blob_node());
-	if (!obj->type)
-		obj->type = OBJ_BLOB;
-	if (obj->type != OBJ_BLOB) {
-		error("Object %s is a %s, not a blob",
-		      sha1_to_hex(sha1), typename(obj->type));
-		return NULL;
-	}
-	return (struct blob *) obj;
+		return create_object(sha1, alloc_blob_node());
+	return object_as_type(obj, OBJ_BLOB, 0);
 }
 
 int parse_blob_buffer(struct blob *item, void *buffer, unsigned long size)
diff --git a/builtin/add.c b/builtin/add.c
index 459208a..4baf3a5 100644
--- a/builtin/add.c
+++ b/builtin/add.c
@@ -299,7 +299,6 @@
 int cmd_add(int argc, const char **argv, const char *prefix)
 {
 	int exit_status = 0;
-	int newfd;
 	struct pathspec pathspec;
 	struct dir_struct dir;
 	int flags;
@@ -345,7 +344,7 @@
 	add_new_files = !take_worktree_changes && !refresh_only;
 	require_pathspec = !take_worktree_changes;
 
-	newfd = hold_locked_index(&lock_file, 1);
+	hold_locked_index(&lock_file, 1);
 
 	flags = ((verbose ? ADD_CACHE_VERBOSE : 0) |
 		 (show_only ? ADD_CACHE_PRETEND : 0) |
@@ -443,8 +442,7 @@
 
 finish:
 	if (active_cache_changed) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 
diff --git a/builtin/annotate.c b/builtin/annotate.c
index fc43eed..da413ae 100644
--- a/builtin/annotate.c
+++ b/builtin/annotate.c
@@ -5,20 +5,18 @@
  */
 #include "git-compat-util.h"
 #include "builtin.h"
+#include "argv-array.h"
 
 int cmd_annotate(int argc, const char **argv, const char *prefix)
 {
-	const char **nargv;
+	struct argv_array args = ARGV_ARRAY_INIT;
 	int i;
-	nargv = xmalloc(sizeof(char *) * (argc + 2));
 
-	nargv[0] = "annotate";
-	nargv[1] = "-c";
+	argv_array_pushl(&args, "annotate", "-c", NULL);
 
 	for (i = 1; i < argc; i++) {
-		nargv[i+1] = argv[i];
+		argv_array_push(&args, argv[i]);
 	}
-	nargv[argc + 1] = NULL;
 
-	return cmd_blame(argc + 1, nargv, prefix);
+	return cmd_blame(args.argc, args.argv, prefix);
 }
diff --git a/builtin/apply.c b/builtin/apply.c
index 16cc935..9f8f5ba 100644
--- a/builtin/apply.c
+++ b/builtin/apply.c
@@ -2867,9 +2867,7 @@
 	case BINARY_LITERAL_DEFLATED:
 		clear_image(img);
 		img->len = fragment->size;
-		img->buf = xmalloc(img->len+1);
-		memcpy(img->buf, fragment->patch, img->len);
-		img->buf[img->len] = '\0';
+		img->buf = xmemdupz(fragment->patch, img->len);
 		return 0;
 	}
 	return -1;
@@ -3084,13 +3082,15 @@
 	}
 }
 
-static int checkout_target(struct cache_entry *ce, struct stat *st)
+static int checkout_target(struct index_state *istate,
+			   struct cache_entry *ce, struct stat *st)
 {
 	struct checkout costate;
 
 	memset(&costate, 0, sizeof(costate));
 	costate.base_dir = "";
 	costate.refresh_cache = 1;
+	costate.istate = istate;
 	if (checkout_entry(ce, &costate, NULL) || lstat(ce->name, st))
 		return error(_("cannot checkout %s"), ce->name);
 	return 0;
@@ -3257,7 +3257,7 @@
 	if (lstat(name, &st)) {
 		if (errno != ENOENT)
 			return error(_("%s: %s"), name, strerror(errno));
-		if (checkout_target(ce, &st))
+		if (checkout_target(&the_index, ce, &st))
 			return -1;
 	}
 	if (verify_index_match(ce, &st))
@@ -3411,7 +3411,7 @@
 		}
 		*ce = active_cache[pos];
 		if (stat_ret < 0) {
-			if (checkout_target(*ce, st))
+			if (checkout_target(&the_index, *ce, st))
 				return -1;
 		}
 		if (!cached && verify_index_match(*ce, st))
@@ -3644,7 +3644,7 @@
 {
 	struct patch *patch;
 	struct index_state result = { NULL };
-	int fd;
+	static struct lock_file lock;
 
 	/* Once we start supporting the reverse patch, it may be
 	 * worth showing the new sha1 prefix, but until then...
@@ -3682,8 +3682,8 @@
 			die ("Could not add %s to temporary index", name);
 	}
 
-	fd = open(filename, O_WRONLY | O_CREAT, 0666);
-	if (fd < 0 || write_index(&result, fd) || close(fd))
+	hold_lock_file_for_update(&lock, filename, LOCK_DIE_ON_ERROR);
+	if (write_locked_index(&result, &lock, COMMIT_LOCK))
 		die ("Could not write temporary index to %s", filename);
 
 	discard_index(&result);
@@ -4502,8 +4502,7 @@
 	}
 
 	if (update_index) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 
diff --git a/builtin/blame.c b/builtin/blame.c
index d3b256e..17d30d0 100644
--- a/builtin/blame.c
+++ b/builtin/blame.c
@@ -1371,11 +1371,8 @@
 
 static int num_scapegoats(struct rev_info *revs, struct commit *commit)
 {
-	int cnt;
 	struct commit_list *l = first_scapegoat(revs, commit);
-	for (cnt = 0; l; l = l->next)
-		cnt++;
-	return cnt;
+	return commit_list_count(l);
 }
 
 /* Distribute collected unsorted blames to the respected sorted lists
@@ -2287,7 +2284,6 @@
 	commit = alloc_commit_node();
 	commit->object.parsed = 1;
 	commit->date = now;
-	commit->object.type = OBJ_COMMIT;
 	parent_tail = &commit->parents;
 
 	if (!resolve_ref_unsafe("HEAD", head_sha1, 1, NULL))
@@ -2389,7 +2385,7 @@
 	 * right now, but someday we might optimize diff-index --cached
 	 * with cache-tree information.
 	 */
-	cache_tree_invalidate_path(active_cache_tree, path);
+	cache_tree_invalidate_path(&the_index, path);
 
 	return commit;
 }
@@ -2707,11 +2703,8 @@
 		die("revision walk setup failed");
 
 	if (is_null_sha1(sb.final->object.sha1)) {
-		char *buf;
 		o = sb.final->util;
-		buf = xmalloc(o->file.size + 1);
-		memcpy(buf, o->file.ptr, o->file.size + 1);
-		sb.final_buf = buf;
+		sb.final_buf = xmemdupz(o->file.ptr, o->file.size);
 		sb.final_buf_size = o->file.size;
 	}
 	else {
diff --git a/builtin/checkout-index.c b/builtin/checkout-index.c
index 61e75eb..05edd9e 100644
--- a/builtin/checkout-index.c
+++ b/builtin/checkout-index.c
@@ -135,6 +135,7 @@
 	int *newfd = opt->value;
 
 	state.refresh_cache = 1;
+	state.istate = &the_index;
 	if (*newfd < 0)
 		*newfd = hold_locked_index(&lock_file, 1);
 	return 0;
@@ -279,8 +280,7 @@
 		checkout_all(prefix, prefix_length);
 
 	if (0 <= newfd &&
-	    (write_cache(newfd, active_cache, active_nr) ||
-	     commit_locked_index(&lock_file)))
+	    write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("Unable to write new index file");
 	return 0;
 }
diff --git a/builtin/checkout.c b/builtin/checkout.c
index 463cfee..f71e745 100644
--- a/builtin/checkout.c
+++ b/builtin/checkout.c
@@ -225,7 +225,6 @@
 	int flag;
 	struct commit *head;
 	int errs = 0;
-	int newfd;
 	struct lock_file *lock_file;
 
 	if (opts->track != BRANCH_TRACK_UNSPECIFIED)
@@ -256,7 +255,7 @@
 
 	lock_file = xcalloc(1, sizeof(struct lock_file));
 
-	newfd = hold_locked_index(lock_file, 1);
+	hold_locked_index(lock_file, 1);
 	if (read_cache_preload(&opts->pathspec) < 0)
 		return error(_("corrupt index file"));
 
@@ -337,6 +336,7 @@
 	memset(&state, 0, sizeof(state));
 	state.force = 1;
 	state.refresh_cache = 1;
+	state.istate = &the_index;
 	for (pos = 0; pos < active_nr; pos++) {
 		struct cache_entry *ce = active_cache[pos];
 		if (ce->ce_flags & CE_MATCHED) {
@@ -352,8 +352,7 @@
 		}
 	}
 
-	if (write_cache(newfd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	read_ref_full("HEAD", rev, 0, &flag);
@@ -444,8 +443,8 @@
 {
 	int ret;
 	struct lock_file *lock_file = xcalloc(1, sizeof(struct lock_file));
-	int newfd = hold_locked_index(lock_file, 1);
 
+	hold_locked_index(lock_file, 1);
 	if (read_cache_preload(NULL) < 0)
 		return error(_("corrupt index file"));
 
@@ -553,8 +552,7 @@
 		}
 	}
 
-	if (write_cache(newfd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	if (!opts->force && !opts->quiet)
diff --git a/builtin/clean.c b/builtin/clean.c
index 27701d2..1032563 100644
--- a/builtin/clean.c
+++ b/builtin/clean.c
@@ -621,8 +621,7 @@
 				nr += chosen[i];
 		}
 
-		result = xmalloc(sizeof(int) * (nr + 1));
-		memset(result, 0, sizeof(int) * (nr + 1));
+		result = xcalloc(nr + 1, sizeof(int));
 		for (i = 0; i < stuff->nr && j < nr; i++) {
 			if (chosen[i])
 				result[j++] = i;
diff --git a/builtin/clone.c b/builtin/clone.c
index e15ca33..bbd169c 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -617,7 +617,7 @@
 	struct unpack_trees_options opts;
 	struct tree *tree;
 	struct tree_desc t;
-	int err = 0, fd;
+	int err = 0;
 
 	if (option_no_checkout)
 		return 0;
@@ -641,7 +641,7 @@
 	setup_work_tree();
 
 	lock_file = xcalloc(1, sizeof(struct lock_file));
-	fd = hold_locked_index(lock_file, 1);
+	hold_locked_index(lock_file, 1);
 
 	memset(&opts, 0, sizeof opts);
 	opts.update = 1;
@@ -657,8 +657,7 @@
 	if (unpack_trees(1, &t, &opts) < 0)
 		die(_("unable to checkout working tree"));
 
-	if (write_cache(fd, active_cache, active_nr) ||
-	    commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 
 	err |= run_hook_le(NULL, "post-checkout", sha1_to_hex(null_sha1),
@@ -800,18 +799,6 @@
 		die(_("repository '%s' does not exist"), repo_name);
 	else
 		repo = repo_name;
-	is_local = option_local != 0 && path && !is_bundle;
-	if (is_local) {
-		if (option_depth)
-			warning(_("--depth is ignored in local clones; use file:// instead."));
-		if (!access(mkpath("%s/shallow", path), F_OK)) {
-			if (option_local > 0)
-				warning(_("source repository is shallow, ignoring --local"));
-			is_local = 0;
-		}
-	}
-	if (option_local > 0 && !is_local)
-		warning(_("--local is ignored"));
 
 	/* no need to be strict, transport_set_option() will validate it again */
 	if (option_depth && atoi(option_depth) < 1)
@@ -904,6 +891,19 @@
 
 	remote = remote_get(option_origin);
 	transport = transport_get(remote, remote->url[0]);
+	path = get_repo_path(remote->url[0], &is_bundle);
+	is_local = option_local != 0 && path && !is_bundle;
+	if (is_local) {
+		if (option_depth)
+			warning(_("--depth is ignored in local clones; use file:// instead."));
+		if (!access(mkpath("%s/shallow", path), F_OK)) {
+			if (option_local > 0)
+				warning(_("source repository is shallow, ignoring --local"));
+			is_local = 0;
+		}
+	}
+	if (option_local > 0 && !is_local)
+		warning(_("--local is ignored"));
 	transport->cloning = 1;
 
 	if (!transport->get_refs_list || (!is_local && !transport->fetch))
diff --git a/builtin/commit.c b/builtin/commit.c
index 461c3b1..5ed6036 100644
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -305,7 +305,6 @@
 static char *prepare_index(int argc, const char **argv, const char *prefix,
 			   const struct commit *current_head, int is_status)
 {
-	int fd;
 	struct string_list partial;
 	struct pathspec pathspec;
 	int refresh_flags = REFRESH_QUIET;
@@ -321,12 +320,11 @@
 
 	if (interactive) {
 		char *old_index_env = NULL;
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 
 		refresh_cache_or_die(refresh_flags);
 
-		if (write_cache(fd, active_cache, active_nr) ||
-		    close_lock_file(&index_lock))
+		if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 			die(_("unable to create temporary index"));
 
 		old_index_env = getenv(INDEX_ENVIRONMENT);
@@ -360,12 +358,11 @@
 	 * (B) on failure, rollback the real index.
 	 */
 	if (all || (also && pathspec.nr)) {
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 		add_files_to_cache(also ? prefix : NULL, &pathspec, 0);
 		refresh_cache_or_die(refresh_flags);
 		update_main_cache_tree(WRITE_TREE_SILENT);
-		if (write_cache(fd, active_cache, active_nr) ||
-		    close_lock_file(&index_lock))
+		if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 			die(_("unable to write new_index file"));
 		commit_style = COMMIT_NORMAL;
 		return index_lock.filename;
@@ -381,12 +378,12 @@
 	 * We still need to refresh the index here.
 	 */
 	if (!only && !pathspec.nr) {
-		fd = hold_locked_index(&index_lock, 1);
+		hold_locked_index(&index_lock, 1);
 		refresh_cache_or_die(refresh_flags);
 		if (active_cache_changed) {
 			update_main_cache_tree(WRITE_TREE_SILENT);
-			if (write_cache(fd, active_cache, active_nr) ||
-			    commit_locked_index(&index_lock))
+			if (write_locked_index(&the_index, &index_lock,
+					       COMMIT_LOCK))
 				die(_("unable to write new_index file"));
 		} else {
 			rollback_lock_file(&index_lock);
@@ -423,8 +420,7 @@
 			die(_("cannot do a partial commit during a cherry-pick."));
 	}
 
-	memset(&partial, 0, sizeof(partial));
-	partial.strdup_strings = 1;
+	string_list_init(&partial, 1);
 	if (list_paths(&partial, !current_head ? NULL : "HEAD", prefix, &pathspec))
 		exit(1);
 
@@ -432,24 +428,22 @@
 	if (read_cache() < 0)
 		die(_("cannot read the index"));
 
-	fd = hold_locked_index(&index_lock, 1);
+	hold_locked_index(&index_lock, 1);
 	add_remove_files(&partial);
 	refresh_cache(REFRESH_QUIET);
-	if (write_cache(fd, active_cache, active_nr) ||
-	    close_lock_file(&index_lock))
+	if (write_locked_index(&the_index, &index_lock, CLOSE_LOCK))
 		die(_("unable to write new_index file"));
 
-	fd = hold_lock_file_for_update(&false_lock,
-				       git_path("next-index-%"PRIuMAX,
-						(uintmax_t) getpid()),
-				       LOCK_DIE_ON_ERROR);
+	hold_lock_file_for_update(&false_lock,
+				  git_path("next-index-%"PRIuMAX,
+					   (uintmax_t) getpid()),
+				  LOCK_DIE_ON_ERROR);
 
 	create_base_index(current_head);
 	add_remove_files(&partial);
 	refresh_cache(REFRESH_QUIET);
 
-	if (write_cache(fd, active_cache, active_nr) ||
-	    close_lock_file(&false_lock))
+	if (write_locked_index(&the_index, &false_lock, CLOSE_LOCK))
 		die(_("unable to write temporary index file"));
 
 	discard_cache();
@@ -707,7 +701,7 @@
 		char *buffer;
 		buffer = strstr(use_message_buffer, "\n\n");
 		if (buffer)
-			strbuf_add(&sb, buffer + 2, strlen(buffer + 2));
+			strbuf_addstr(&sb, buffer + 2);
 		hook_arg1 = "commit";
 		hook_arg2 = use_message;
 	} else if (fixup_message) {
diff --git a/builtin/describe.c b/builtin/describe.c
index 24d740c..ee6a3b9 100644
--- a/builtin/describe.c
+++ b/builtin/describe.c
@@ -56,18 +56,9 @@
 	return hashcmp(cn1->peeled, peeled ? peeled : cn2->peeled);
 }
 
-static inline unsigned int hash_sha1(const unsigned char *sha1)
-{
-	unsigned int hash;
-	memcpy(&hash, sha1, sizeof(hash));
-	return hash;
-}
-
 static inline struct commit_name *find_commit_name(const unsigned char *peeled)
 {
-	struct commit_name key;
-	hashmap_entry_init(&key, hash_sha1(peeled));
-	return hashmap_get(&names, &key, peeled);
+	return hashmap_get_from_hash(&names, sha1hash(peeled), peeled);
 }
 
 static int replace_name(struct commit_name *e,
@@ -114,7 +105,7 @@
 		if (!e) {
 			e = xmalloc(sizeof(struct commit_name));
 			hashcpy(e->peeled, peeled);
-			hashmap_entry_init(e, hash_sha1(peeled));
+			hashmap_entry_init(e, sha1hash(peeled));
 			hashmap_add(&names, e);
 			e->path = NULL;
 		}
diff --git a/builtin/diff-tree.c b/builtin/diff-tree.c
index ce0e019..1c4ad62 100644
--- a/builtin/diff-tree.c
+++ b/builtin/diff-tree.c
@@ -68,9 +68,7 @@
 	line[len-1] = 0;
 	if (get_sha1_hex(line, sha1))
 		return -1;
-	obj = lookup_unknown_object(sha1);
-	if (!obj || !obj->parsed)
-		obj = parse_object(sha1);
+	obj = parse_object(sha1);
 	if (!obj)
 		return -1;
 	if (obj->type == OBJ_COMMIT)
diff --git a/builtin/for-each-ref.c b/builtin/for-each-ref.c
index 4135980..47bd624 100644
--- a/builtin/for-each-ref.c
+++ b/builtin/for-each-ref.c
@@ -283,18 +283,6 @@
 	}
 }
 
-static int num_parents(struct commit *commit)
-{
-	struct commit_list *parents;
-	int i;
-
-	for (i = 0, parents = commit->parents;
-	     parents;
-	     parents = parents->next)
-		i++;
-	return i;
-}
-
 /* See grab_values */
 static void grab_commit_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
 {
@@ -315,12 +303,12 @@
 		}
 		if (!strcmp(name, "numparent")) {
 			char *s = xmalloc(40);
-			v->ul = num_parents(commit);
+			v->ul = commit_list_count(commit->parents);
 			sprintf(s, "%lu", v->ul);
 			v->s = s;
 		}
 		else if (!strcmp(name, "parent")) {
-			int num = num_parents(commit);
+			int num = commit_list_count(commit->parents);
 			int i;
 			struct commit_list *parents;
 			char *s = xmalloc(41 * num + 1);
diff --git a/builtin/fsck.c b/builtin/fsck.c
index 8aadca1..d42a27d 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -481,11 +481,6 @@
 	return 0;
 }
 
-static int is_branch(const char *refname)
-{
-	return !strcmp(refname, "HEAD") || starts_with(refname, "refs/heads/");
-}
-
 static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
 {
 	struct object *obj;
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 8b3bd29..5568a5b 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -362,8 +362,7 @@
 
 static struct base_data *alloc_base_data(void)
 {
-	struct base_data *base = xmalloc(sizeof(struct base_data));
-	memset(base, 0, sizeof(*base));
+	struct base_data *base = xcalloc(1, sizeof(struct base_data));
 	base->ref_last = -1;
 	base->ofs_last = -1;
 	return base;
@@ -1506,7 +1505,8 @@
 	const char *curr_index;
 	const char *index_name = NULL, *pack_name = NULL;
 	const char *keep_name = NULL, *keep_msg = NULL;
-	char *index_name_buf = NULL, *keep_name_buf = NULL;
+	struct strbuf index_name_buf = STRBUF_INIT,
+		      keep_name_buf = STRBUF_INIT;
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;
 	unsigned char pack_sha1[20];
@@ -1603,24 +1603,22 @@
 	if (fix_thin_pack && !from_stdin)
 		die(_("--fix-thin cannot be used without --stdin"));
 	if (!index_name && pack_name) {
-		int len = strlen(pack_name);
-		if (!has_extension(pack_name, ".pack"))
+		size_t len;
+		if (!strip_suffix(pack_name, ".pack", &len))
 			die(_("packfile name '%s' does not end with '.pack'"),
 			    pack_name);
-		index_name_buf = xmalloc(len);
-		memcpy(index_name_buf, pack_name, len - 5);
-		strcpy(index_name_buf + len - 5, ".idx");
-		index_name = index_name_buf;
+		strbuf_add(&index_name_buf, pack_name, len);
+		strbuf_addstr(&index_name_buf, ".idx");
+		index_name = index_name_buf.buf;
 	}
 	if (keep_msg && !keep_name && pack_name) {
-		int len = strlen(pack_name);
-		if (!has_extension(pack_name, ".pack"))
+		size_t len;
+		if (!strip_suffix(pack_name, ".pack", &len))
 			die(_("packfile name '%s' does not end with '.pack'"),
 			    pack_name);
-		keep_name_buf = xmalloc(len);
-		memcpy(keep_name_buf, pack_name, len - 5);
-		strcpy(keep_name_buf + len - 5, ".keep");
-		keep_name = keep_name_buf;
+		strbuf_add(&keep_name_buf, pack_name, len);
+		strbuf_addstr(&keep_name_buf, ".idx");
+		keep_name = keep_name_buf.buf;
 	}
 	if (verify) {
 		if (!index_name)
@@ -1668,8 +1666,8 @@
 	else
 		close(input_fd);
 	free(objects);
-	free(index_name_buf);
-	free(keep_name_buf);
+	strbuf_release(&index_name_buf);
+	strbuf_release(&keep_name_buf);
 	if (pack_name == NULL)
 		free((void *) curr_pack);
 	if (index_name == NULL)
diff --git a/builtin/log.c b/builtin/log.c
index 27c1b65..4389722 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -861,7 +861,7 @@
 	read_branch_desc(&desc, branch_name);
 	if (desc.len) {
 		strbuf_addch(buf, '\n');
-		strbuf_add(buf, desc.buf, desc.len);
+		strbuf_addbuf(buf, &desc);
 		strbuf_addch(buf, '\n');
 	}
 }
diff --git a/builtin/merge.c b/builtin/merge.c
index 86e9c61..ce82eb2 100644
--- a/builtin/merge.c
+++ b/builtin/merge.c
@@ -657,14 +657,12 @@
 			      struct commit_list *remoteheads,
 			      struct commit *head, const char *head_arg)
 {
-	int index_fd;
 	struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
 
-	index_fd = hold_locked_index(lock, 1);
+	hold_locked_index(lock, 1);
 	refresh_cache(REFRESH_QUIET);
 	if (active_cache_changed &&
-			(write_cache(index_fd, active_cache, active_nr) ||
-			 commit_locked_index(lock)))
+	    write_locked_index(&the_index, lock, COMMIT_LOCK))
 		return error(_("Unable to write index."));
 	rollback_lock_file(lock);
 
@@ -672,7 +670,6 @@
 		int clean, x;
 		struct commit *result;
 		struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
-		int index_fd;
 		struct commit_list *reversed = NULL;
 		struct merge_options o;
 		struct commit_list *j;
@@ -700,12 +697,11 @@
 		for (j = common; j; j = j->next)
 			commit_list_insert(j->item, &reversed);
 
-		index_fd = hold_locked_index(lock, 1);
+		hold_locked_index(lock, 1);
 		clean = merge_recursive(&o, head,
 				remoteheads->item, reversed, &result);
 		if (active_cache_changed &&
-				(write_cache(index_fd, active_cache, active_nr) ||
-				 commit_locked_index(lock)))
+		    write_locked_index(&the_index, lock, COMMIT_LOCK))
 			die (_("unable to write %s"), get_index_file());
 		rollback_lock_file(lock);
 		return clean ? 0 : 1;
@@ -843,16 +839,14 @@
 static int merge_trivial(struct commit *head, struct commit_list *remoteheads)
 {
 	unsigned char result_tree[20], result_commit[20];
-	struct commit_list *parent = xmalloc(sizeof(*parent));
+	struct commit_list *parents, **pptr = &parents;
 
 	write_tree_trivial(result_tree);
 	printf(_("Wonderful.\n"));
-	parent->item = head;
-	parent->next = xmalloc(sizeof(*parent->next));
-	parent->next->item = remoteheads->item;
-	parent->next->next = NULL;
+	pptr = commit_list_append(head, pptr);
+	pptr = commit_list_append(remoteheads->item, pptr);
 	prepare_to_commit(remoteheads);
-	if (commit_tree(merge_msg.buf, merge_msg.len, result_tree, parent,
+	if (commit_tree(merge_msg.buf, merge_msg.len, result_tree, parents,
 			result_commit, NULL, sign_commit))
 		die(_("failed to write commit object"));
 	finish(head, remoteheads, result_commit, "In-index merge");
diff --git a/builtin/mv.c b/builtin/mv.c
index 180ef99..6ffe540 100644
--- a/builtin/mv.c
+++ b/builtin/mv.c
@@ -63,7 +63,7 @@
 
 int cmd_mv(int argc, const char **argv, const char *prefix)
 {
-	int i, newfd, gitmodules_modified = 0;
+	int i, gitmodules_modified = 0;
 	int verbose = 0, show_only = 0, force = 0, ignore_errors = 0;
 	struct option builtin_mv_options[] = {
 		OPT__VERBOSE(&verbose, N_("be verbose")),
@@ -85,7 +85,7 @@
 	if (--argc < 1)
 		usage_with_options(builtin_mv_usage, builtin_mv_options);
 
-	newfd = hold_locked_index(&lock_file, 1);
+	hold_locked_index(&lock_file, 1);
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
 
@@ -276,8 +276,7 @@
 		stage_updated_gitmodules();
 
 	if (active_cache_changed) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 
diff --git a/builtin/read-tree.c b/builtin/read-tree.c
index 0d7ef84..e7e1c33 100644
--- a/builtin/read-tree.c
+++ b/builtin/read-tree.c
@@ -99,7 +99,7 @@
 
 int cmd_read_tree(int argc, const char **argv, const char *unused_prefix)
 {
-	int i, newfd, stage = 0;
+	int i, stage = 0;
 	unsigned char sha1[20];
 	struct tree_desc t[MAX_UNPACK_TREES];
 	struct unpack_trees_options opts;
@@ -149,12 +149,21 @@
 	argc = parse_options(argc, argv, unused_prefix, read_tree_options,
 			     read_tree_usage, 0);
 
-	newfd = hold_locked_index(&lock_file, 1);
+	hold_locked_index(&lock_file, 1);
 
 	prefix_set = opts.prefix ? 1 : 0;
 	if (1 < opts.merge + opts.reset + prefix_set)
 		die("Which one? -m, --reset, or --prefix?");
 
+	/*
+	 * NEEDSWORK
+	 *
+	 * The old index should be read anyway even if we're going to
+	 * destroy all index entries because we still need to preserve
+	 * certain information such as index version or split-index
+	 * mode.
+	 */
+
 	if (opts.reset || opts.merge || opts.prefix) {
 		if (read_cache_unmerged() && (opts.prefix || opts.merge))
 			die("You need to resolve your current index first");
@@ -231,10 +240,9 @@
 	 * what came from the tree.
 	 */
 	if (nr_trees == 1 && !opts.prefix)
-		prime_cache_tree(&active_cache_tree, trees[0]);
+		prime_cache_tree(&the_index, trees[0]);
 
-	if (write_cache(newfd, active_cache, active_nr) ||
-	    commit_locked_index(&lock_file))
+	if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 		die("unable to write new index file");
 	return 0;
 }
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index 18458e8..92561bf 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -438,7 +438,7 @@
 	uint32_t mask = 1 << (cmd->index % 32);
 	int i;
 
-	trace_printf_key("GIT_TRACE_SHALLOW",
+	trace_printf_key(&trace_shallow,
 			 "shallow: update_shallow_ref %s\n", cmd->ref_name);
 	for (i = 0; i < si->shallow->nr; i++)
 		if (si->used_shallow[i] &&
diff --git a/builtin/remote.c b/builtin/remote.c
index a8efe3d..9a4640d 100644
--- a/builtin/remote.c
+++ b/builtin/remote.c
@@ -263,16 +263,17 @@
 		struct string_list_item *item;
 		struct branch_info *info;
 		enum { REMOTE, MERGE, REBASE } type;
+		size_t key_len;
 
 		key += 7;
-		if (ends_with(key, ".remote")) {
-			name = xstrndup(key, strlen(key) - 7);
+		if (strip_suffix(key, ".remote", &key_len)) {
+			name = xmemdupz(key, key_len);
 			type = REMOTE;
-		} else if (ends_with(key, ".merge")) {
-			name = xstrndup(key, strlen(key) - 6);
+		} else if (strip_suffix(key, ".merge", &key_len)) {
+			name = xmemdupz(key, key_len);
 			type = MERGE;
-		} else if (ends_with(key, ".rebase")) {
-			name = xstrndup(key, strlen(key) - 7);
+		} else if (strip_suffix(key, ".rebase", &key_len)) {
+			name = xmemdupz(key, key_len);
 			type = REBASE;
 		} else
 			return 0;
@@ -753,7 +754,7 @@
 	branch_names = xmalloc(branches->nr * sizeof(*branch_names));
 	for (i = 0; i < branches->nr; i++)
 		branch_names[i] = branches->items[i].string;
-	result |= repack_without_refs(branch_names, branches->nr);
+	result |= repack_without_refs(branch_names, branches->nr, NULL);
 	free(branch_names);
 
 	for (i = 0; i < branches->nr; i++) {
@@ -1331,7 +1332,8 @@
 		for (i = 0; i < states.stale.nr; i++)
 			delete_refs[i] = states.stale.items[i].util;
 		if (!dry_run)
-			result |= repack_without_refs(delete_refs, states.stale.nr);
+			result |= repack_without_refs(delete_refs,
+						      states.stale.nr, NULL);
 		free(delete_refs);
 	}
 
diff --git a/builtin/repack.c b/builtin/repack.c
index ff2216a..a77e743 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -83,16 +83,15 @@
 	DIR *dir;
 	struct dirent *e;
 	char *fname;
-	size_t len;
 
 	if (!(dir = opendir(packdir)))
 		return;
 
 	while ((e = readdir(dir)) != NULL) {
-		if (!ends_with(e->d_name, ".pack"))
+		size_t len;
+		if (!strip_suffix(e->d_name, ".pack", &len))
 			continue;
 
-		len = strlen(e->d_name) - strlen(".pack");
 		fname = xmemdupz(e->d_name, len);
 
 		if (!file_exists(mkpath("%s/%s.keep", packdir, fname)))
diff --git a/builtin/replace.c b/builtin/replace.c
index 1bb491d..294b61b 100644
--- a/builtin/replace.c
+++ b/builtin/replace.c
@@ -13,19 +13,21 @@
 #include "refs.h"
 #include "parse-options.h"
 #include "run-command.h"
+#include "tag.h"
 
 static const char * const git_replace_usage[] = {
 	N_("git replace [-f] <object> <replacement>"),
 	N_("git replace [-f] --edit <object>"),
+	N_("git replace [-f] --graft <commit> [<parent>...]"),
 	N_("git replace -d <object>..."),
 	N_("git replace [--format=<format>] [-l [<pattern>]]"),
 	NULL
 };
 
 enum replace_format {
-      REPLACE_FORMAT_SHORT,
-      REPLACE_FORMAT_MEDIUM,
-      REPLACE_FORMAT_LONG
+	REPLACE_FORMAT_SHORT,
+	REPLACE_FORMAT_MEDIUM,
+	REPLACE_FORMAT_LONG
 };
 
 struct show_data {
@@ -188,27 +190,32 @@
 }
 
 /*
- * Write the contents of the object named by "sha1" to the file "filename",
- * pretty-printed for human editing based on its type.
+ * Write the contents of the object named by "sha1" to the file "filename".
+ * If "raw" is true, then the object's raw contents are printed according to
+ * "type". Otherwise, we pretty-print the contents for human editing.
  */
-static void export_object(const unsigned char *sha1, const char *filename)
+static void export_object(const unsigned char *sha1, enum object_type type,
+			  int raw, const char *filename)
 {
-	const char *argv[] = { "--no-replace-objects", "cat-file", "-p", NULL, NULL };
-	struct child_process cmd = { argv };
+	struct child_process cmd = { NULL };
 	int fd;
 
 	fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC, 0666);
 	if (fd < 0)
 		die_errno("unable to open %s for writing", filename);
 
-	argv[3] = sha1_to_hex(sha1);
+	argv_array_push(&cmd.args, "--no-replace-objects");
+	argv_array_push(&cmd.args, "cat-file");
+	if (raw)
+		argv_array_push(&cmd.args, typename(type));
+	else
+		argv_array_push(&cmd.args, "-p");
+	argv_array_push(&cmd.args, sha1_to_hex(sha1));
 	cmd.git_cmd = 1;
 	cmd.out = fd;
 
 	if (run_command(&cmd))
 		die("cat-file reported failure");
-
-	close(fd);
 }
 
 /*
@@ -217,7 +224,7 @@
  * The sha1 of the written object is returned via sha1.
  */
 static void import_object(unsigned char *sha1, enum object_type type,
-			  const char *filename)
+			  int raw, const char *filename)
 {
 	int fd;
 
@@ -225,7 +232,7 @@
 	if (fd < 0)
 		die_errno("unable to open %s for reading", filename);
 
-	if (type == OBJ_TREE) {
+	if (!raw && type == OBJ_TREE) {
 		const char *argv[] = { "mktree", NULL };
 		struct child_process cmd = { argv };
 		struct strbuf result = STRBUF_INIT;
@@ -265,7 +272,7 @@
 	 */
 }
 
-static int edit_and_replace(const char *object_ref, int force)
+static int edit_and_replace(const char *object_ref, int force, int raw)
 {
 	char *tmpfile = git_pathdup("REPLACE_EDITOBJ");
 	enum object_type type;
@@ -281,10 +288,10 @@
 
 	check_ref_valid(old, prev, ref, sizeof(ref), force);
 
-	export_object(old, tmpfile);
+	export_object(old, type, raw, tmpfile);
 	if (launch_editor(tmpfile, NULL, NULL) < 0)
 		die("editing object file failed");
-	import_object(new, type, tmpfile);
+	import_object(new, type, raw, tmpfile);
 
 	free(tmpfile);
 
@@ -294,22 +301,137 @@
 	return replace_object_sha1(object_ref, old, "replacement", new, force);
 }
 
+static void replace_parents(struct strbuf *buf, int argc, const char **argv)
+{
+	struct strbuf new_parents = STRBUF_INIT;
+	const char *parent_start, *parent_end;
+	int i;
+
+	/* find existing parents */
+	parent_start = buf->buf;
+	parent_start += 46; /* "tree " + "hex sha1" + "\n" */
+	parent_end = parent_start;
+
+	while (starts_with(parent_end, "parent "))
+		parent_end += 48; /* "parent " + "hex sha1" + "\n" */
+
+	/* prepare new parents */
+	for (i = 0; i < argc; i++) {
+		unsigned char sha1[20];
+		if (get_sha1(argv[i], sha1) < 0)
+			die(_("Not a valid object name: '%s'"), argv[i]);
+		lookup_commit_or_die(sha1, argv[i]);
+		strbuf_addf(&new_parents, "parent %s\n", sha1_to_hex(sha1));
+	}
+
+	/* replace existing parents with new ones */
+	strbuf_splice(buf, parent_start - buf->buf, parent_end - parent_start,
+		      new_parents.buf, new_parents.len);
+
+	strbuf_release(&new_parents);
+}
+
+struct check_mergetag_data {
+	int argc;
+	const char **argv;
+};
+
+static void check_one_mergetag(struct commit *commit,
+			       struct commit_extra_header *extra,
+			       void *data)
+{
+	struct check_mergetag_data *mergetag_data = (struct check_mergetag_data *)data;
+	const char *ref = mergetag_data->argv[0];
+	unsigned char tag_sha1[20];
+	struct tag *tag;
+	int i;
+
+	hash_sha1_file(extra->value, extra->len, typename(OBJ_TAG), tag_sha1);
+	tag = lookup_tag(tag_sha1);
+	if (!tag)
+		die(_("bad mergetag in commit '%s'"), ref);
+	if (parse_tag_buffer(tag, extra->value, extra->len))
+		die(_("malformed mergetag in commit '%s'"), ref);
+
+	/* iterate over new parents */
+	for (i = 1; i < mergetag_data->argc; i++) {
+		unsigned char sha1[20];
+		if (get_sha1(mergetag_data->argv[i], sha1) < 0)
+			die(_("Not a valid object name: '%s'"), mergetag_data->argv[i]);
+		if (!hashcmp(tag->tagged->sha1, sha1))
+			return; /* found */
+	}
+
+	die(_("original commit '%s' contains mergetag '%s' that is discarded; "
+	      "use --edit instead of --graft"), ref, sha1_to_hex(tag_sha1));
+}
+
+static void check_mergetags(struct commit *commit, int argc, const char **argv)
+{
+	struct check_mergetag_data mergetag_data;
+
+	mergetag_data.argc = argc;
+	mergetag_data.argv = argv;
+	for_each_mergetag(check_one_mergetag, commit, &mergetag_data);
+}
+
+static int create_graft(int argc, const char **argv, int force)
+{
+	unsigned char old[20], new[20];
+	const char *old_ref = argv[0];
+	struct commit *commit;
+	struct strbuf buf = STRBUF_INIT;
+	const char *buffer;
+	unsigned long size;
+
+	if (get_sha1(old_ref, old) < 0)
+		die(_("Not a valid object name: '%s'"), old_ref);
+	commit = lookup_commit_or_die(old, old_ref);
+
+	buffer = get_commit_buffer(commit, &size);
+	strbuf_add(&buf, buffer, size);
+	unuse_commit_buffer(commit, buffer);
+
+	replace_parents(&buf, argc - 1, &argv[1]);
+
+	if (remove_signature(&buf)) {
+		warning(_("the original commit '%s' has a gpg signature."), old_ref);
+		warning(_("the signature will be removed in the replacement commit!"));
+	}
+
+	check_mergetags(commit, argc, argv);
+
+	if (write_sha1_file(buf.buf, buf.len, commit_type, new))
+		die(_("could not write replacement commit for: '%s'"), old_ref);
+
+	strbuf_release(&buf);
+
+	if (!hashcmp(old, new))
+		return error("new commit is the same as the old one: '%s'", sha1_to_hex(old));
+
+	return replace_object_sha1(old_ref, old, "replacement", new, force);
+}
+
 int cmd_replace(int argc, const char **argv, const char *prefix)
 {
 	int force = 0;
+	int raw = 0;
 	const char *format = NULL;
 	enum {
 		MODE_UNSPECIFIED = 0,
 		MODE_LIST,
 		MODE_DELETE,
 		MODE_EDIT,
+		MODE_GRAFT,
 		MODE_REPLACE
 	} cmdmode = MODE_UNSPECIFIED;
 	struct option options[] = {
 		OPT_CMDMODE('l', "list", &cmdmode, N_("list replace refs"), MODE_LIST),
 		OPT_CMDMODE('d', "delete", &cmdmode, N_("delete replace refs"), MODE_DELETE),
 		OPT_CMDMODE('e', "edit", &cmdmode, N_("edit existing object"), MODE_EDIT),
+		OPT_CMDMODE('g', "graft", &cmdmode, N_("change a commit's parents"), MODE_GRAFT),
 		OPT_BOOL('f', "force", &force, N_("replace the ref if it exists")),
+		OPT_BOOL(0, "raw", &raw, N_("do not pretty-print contents for --edit")),
 		OPT_STRING(0, "format", &format, N_("format"), N_("use this format")),
 		OPT_END()
 	};
@@ -325,10 +447,17 @@
 		usage_msg_opt("--format cannot be used when not listing",
 			      git_replace_usage, options);
 
-	if (force && cmdmode != MODE_REPLACE && cmdmode != MODE_EDIT)
+	if (force &&
+	    cmdmode != MODE_REPLACE &&
+	    cmdmode != MODE_EDIT &&
+	    cmdmode != MODE_GRAFT)
 		usage_msg_opt("-f only makes sense when writing a replacement",
 			      git_replace_usage, options);
 
+	if (raw && cmdmode != MODE_EDIT)
+		usage_msg_opt("--raw only makes sense with --edit",
+			      git_replace_usage, options);
+
 	switch (cmdmode) {
 	case MODE_DELETE:
 		if (argc < 1)
@@ -346,7 +475,13 @@
 		if (argc != 1)
 			usage_msg_opt("-e needs exactly one argument",
 				      git_replace_usage, options);
-		return edit_and_replace(argv[0], force);
+		return edit_and_replace(argv[0], force, raw);
+
+	case MODE_GRAFT:
+		if (argc < 1)
+			usage_msg_opt("-g needs at least one argument",
+				      git_replace_usage, options);
+		return create_graft(argc, argv, force);
 
 	case MODE_LIST:
 		if (argc > 1)
diff --git a/builtin/reset.c b/builtin/reset.c
index 850d532..855d478 100644
--- a/builtin/reset.c
+++ b/builtin/reset.c
@@ -84,7 +84,7 @@
 
 	if (reset_type == MIXED || reset_type == HARD) {
 		tree = parse_tree_indirect(sha1);
-		prime_cache_tree(&active_cache_tree, tree);
+		prime_cache_tree(&the_index, tree);
 	}
 
 	return 0;
@@ -353,7 +353,7 @@
 
 	if (reset_type != SOFT) {
 		struct lock_file *lock = xcalloc(1, sizeof(*lock));
-		int newfd = hold_locked_index(lock, 1);
+		hold_locked_index(lock, 1);
 		if (reset_type == MIXED) {
 			int flags = quiet ? REFRESH_QUIET : REFRESH_IN_PORCELAIN;
 			if (read_from_tree(&pathspec, sha1, intent_to_add))
@@ -369,8 +369,7 @@
 				die(_("Could not reset index file to revision '%s'."), rev);
 		}
 
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(lock))
+		if (write_locked_index(&the_index, lock, COMMIT_LOCK))
 			die(_("Could not write new index file."));
 	}
 
diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c
index 1a6122d..8102aaa 100644
--- a/builtin/rev-parse.c
+++ b/builtin/rev-parse.c
@@ -11,6 +11,7 @@
 #include "parse-options.h"
 #include "diff.h"
 #include "revision.h"
+#include "split-index.h"
 
 #define DO_REVS		1
 #define DO_NOREV	2
@@ -775,6 +776,15 @@
 						: "false");
 				continue;
 			}
+			if (!strcmp(arg, "--shared-index-path")) {
+				if (read_cache() < 0)
+					die(_("Could not read the index"));
+				if (the_index.split_index) {
+					const unsigned char *sha1 = the_index.split_index->base_sha1;
+					puts(git_path("sharedindex.%s", sha1_to_hex(sha1)));
+				}
+				continue;
+			}
 			if (starts_with(arg, "--since=")) {
 				show_datestring("--max-age=", arg+8);
 				continue;
diff --git a/builtin/rm.c b/builtin/rm.c
index 960634d..bc6490b 100644
--- a/builtin/rm.c
+++ b/builtin/rm.c
@@ -278,7 +278,7 @@
 
 int cmd_rm(int argc, const char **argv, const char *prefix)
 {
-	int i, newfd;
+	int i;
 	struct pathspec pathspec;
 	char *seen;
 
@@ -293,7 +293,7 @@
 	if (!index_only)
 		setup_work_tree();
 
-	newfd = hold_locked_index(&lock_file, 1);
+	hold_locked_index(&lock_file, 1);
 
 	if (read_cache() < 0)
 		die(_("index file corrupt"));
@@ -427,8 +427,7 @@
 	}
 
 	if (active_cache_changed) {
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(&lock_file))
+		if (write_locked_index(&the_index, &lock_file, COMMIT_LOCK))
 			die(_("Unable to write new index file"));
 	}
 
diff --git a/builtin/tag.c b/builtin/tag.c
index ef76556..19eb747 100644
--- a/builtin/tag.c
+++ b/builtin/tag.c
@@ -32,6 +32,8 @@
 #define SORT_MASK       0x7fff
 #define REVERSE_SORT    0x8000
 
+static int tag_sort;
+
 struct tag_filter {
 	const char **patterns;
 	int lines;
@@ -346,9 +348,51 @@
 	"Lines starting with '%c' will be kept; you may remove them"
 	" yourself if you want to.\n");
 
+/*
+ * Parse a sort string, and return 0 if parsed successfully. Will return
+ * non-zero when the sort string does not parse into a known type. If var is
+ * given, the error message becomes a warning and includes information about
+ * the configuration value.
+ */
+static int parse_sort_string(const char *var, const char *arg, int *sort)
+{
+	int type = 0, flags = 0;
+
+	if (skip_prefix(arg, "-", &arg))
+		flags |= REVERSE_SORT;
+
+	if (skip_prefix(arg, "version:", &arg) || skip_prefix(arg, "v:", &arg))
+		type = VERCMP_SORT;
+	else
+		type = STRCMP_SORT;
+
+	if (strcmp(arg, "refname")) {
+		if (!var)
+			return error(_("unsupported sort specification '%s'"), arg);
+		else {
+			warning(_("unsupported sort specification '%s' in variable '%s'"),
+				var, arg);
+			return -1;
+		}
+	}
+
+	*sort = (type | flags);
+
+	return 0;
+}
+
 static int git_tag_config(const char *var, const char *value, void *cb)
 {
-	int status = git_gpg_config(var, value, cb);
+	int status;
+
+	if (!strcmp(var, "tag.sort")) {
+		if (!value)
+			return config_error_nonbool(var);
+		parse_sort_string(var, value, &tag_sort);
+		return 0;
+	}
+
+	status = git_gpg_config(var, value, cb);
 	if (status)
 		return status;
 	if (starts_with(var, "column."))
@@ -522,24 +566,8 @@
 static int parse_opt_sort(const struct option *opt, const char *arg, int unset)
 {
 	int *sort = opt->value;
-	int flags = 0;
 
-	if (*arg == '-') {
-		flags |= REVERSE_SORT;
-		arg++;
-	}
-	if (starts_with(arg, "version:")) {
-		*sort = VERCMP_SORT;
-		arg += 8;
-	} else if (starts_with(arg, "v:")) {
-		*sort = VERCMP_SORT;
-		arg += 2;
-	} else
-		*sort = STRCMP_SORT;
-	if (strcmp(arg, "refname"))
-		die(_("unsupported sort specification %s"), arg);
-	*sort |= flags;
-	return 0;
+	return parse_sort_string(NULL, arg, sort);
 }
 
 int cmd_tag(int argc, const char **argv, const char *prefix)
@@ -552,7 +580,7 @@
 	struct create_tag_options opt;
 	char *cleanup_arg = NULL;
 	int annotate = 0, force = 0, lines = -1;
-	int cmdmode = 0, sort = 0;
+	int cmdmode = 0;
 	const char *msgfile = NULL, *keyid = NULL;
 	struct msg_arg msg = { 0, STRBUF_INIT };
 	struct commit_list *with_commit = NULL;
@@ -578,7 +606,7 @@
 		OPT__FORCE(&force, N_("replace the tag if exists")),
 		OPT_COLUMN(0, "column", &colopts, N_("show tag list in columns")),
 		{
-			OPTION_CALLBACK, 0, "sort", &sort, N_("type"), N_("sort tags"),
+			OPTION_CALLBACK, 0, "sort", &tag_sort, N_("type"), N_("sort tags"),
 			PARSE_OPT_NONEG, parse_opt_sort
 		},
 
@@ -634,9 +662,9 @@
 			copts.padding = 2;
 			run_column_filter(colopts, &copts);
 		}
-		if (lines != -1 && sort)
+		if (lines != -1 && tag_sort)
 			die(_("--sort and -n are incompatible"));
-		ret = list_tags(argv, lines == -1 ? 0 : lines, with_commit, sort);
+		ret = list_tags(argv, lines == -1 ? 0 : lines, with_commit, tag_sort);
 		if (column_active(colopts))
 			stop_column_filter();
 		return ret;
diff --git a/builtin/update-index.c b/builtin/update-index.c
index ebea285..e8c7fd4 100644
--- a/builtin/update-index.c
+++ b/builtin/update-index.c
@@ -13,6 +13,7 @@
 #include "parse-options.h"
 #include "pathspec.h"
 #include "dir.h"
+#include "split-index.h"
 
 /*
  * Default to not allowing changes to the list of files. The
@@ -55,8 +56,9 @@
 			active_cache[pos]->ce_flags |= flag;
 		else
 			active_cache[pos]->ce_flags &= ~flag;
-		cache_tree_invalidate_path(active_cache_tree, path);
-		active_cache_changed = 1;
+		active_cache[pos]->ce_flags |= CE_UPDATE_IN_BASE;
+		cache_tree_invalidate_path(&the_index, path);
+		active_cache_changed |= CE_ENTRY_CHANGED;
 		return 0;
 	}
 	return -1;
@@ -267,8 +269,9 @@
 	default:
 		goto fail;
 	}
-	cache_tree_invalidate_path(active_cache_tree, path);
-	active_cache_changed = 1;
+	cache_tree_invalidate_path(&the_index, path);
+	ce->ce_flags |= CE_UPDATE_IN_BASE;
+	active_cache_changed |= CE_ENTRY_CHANGED;
 	report("chmod %cx '%s'", flip, path);
 	return;
  fail:
@@ -743,6 +746,7 @@
 	char set_executable_bit = 0;
 	struct refresh_params refresh_args = {0, &has_errors};
 	int lock_error = 0;
+	int split_index = -1;
 	struct lock_file *lock_file;
 	struct parse_opt_ctx_t ctx;
 	int parseopt_state = PARSE_OPT_UNKNOWN;
@@ -825,6 +829,8 @@
 			resolve_undo_clear_callback},
 		OPT_INTEGER(0, "index-version", &preferred_index_format,
 			N_("write index in this format")),
+		OPT_BOOL(0, "split-index", &split_index,
+			N_("enable or disable split index")),
 		OPT_END()
 	};
 
@@ -892,7 +898,7 @@
 			    INDEX_FORMAT_LB, INDEX_FORMAT_UB);
 
 		if (the_index.version != preferred_index_format)
-			active_cache_changed = 1;
+			active_cache_changed |= SOMETHING_CHANGED;
 		the_index.version = preferred_index_format;
 	}
 
@@ -918,14 +924,27 @@
 		strbuf_release(&buf);
 	}
 
+	if (split_index > 0) {
+		init_split_index(&the_index);
+		the_index.cache_changed |= SPLIT_INDEX_ORDERED;
+	} else if (!split_index && the_index.split_index) {
+		/*
+		 * can't discard_split_index(&the_index); because that
+		 * will destroy split_index->base->cache[], which may
+		 * be shared with the_index.cache[]. So yeah we're
+		 * leaking a bit here.
+		 */
+		the_index.split_index = NULL;
+		the_index.cache_changed |= SOMETHING_CHANGED;
+	}
+
 	if (active_cache_changed) {
 		if (newfd < 0) {
 			if (refresh_args.flags & REFRESH_QUIET)
 				exit(128);
 			unable_to_lock_index_die(get_index_file(), lock_error);
 		}
-		if (write_cache(newfd, active_cache, active_nr) ||
-		    commit_locked_index(lock_file))
+		if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 			die("Unable to write new index file");
 	}
 
diff --git a/builtin/update-ref.c b/builtin/update-ref.c
index 405267f..3067b11 100644
--- a/builtin/update-ref.c
+++ b/builtin/update-ref.c
@@ -16,6 +16,7 @@
 
 static char line_termination = '\n';
 static int update_flags;
+static struct strbuf err = STRBUF_INIT;
 
 /*
  * Parse one whitespace- or NUL-terminated, possibly C-quoted argument
@@ -197,8 +198,9 @@
 	if (*next != line_termination)
 		die("update %s: extra input: %s", refname, next);
 
-	ref_transaction_update(transaction, refname, new_sha1, old_sha1,
-			       update_flags, have_old);
+	if (ref_transaction_update(transaction, refname, new_sha1, old_sha1,
+				   update_flags, have_old, &err))
+		die("%s", err.buf);
 
 	update_flags = 0;
 	free(refname);
@@ -286,8 +288,9 @@
 	if (*next != line_termination)
 		die("verify %s: extra input: %s", refname, next);
 
-	ref_transaction_update(transaction, refname, new_sha1, old_sha1,
-			       update_flags, have_old);
+	if (ref_transaction_update(transaction, refname, new_sha1, old_sha1,
+				   update_flags, have_old, &err))
+		die("%s", err.buf);
 
 	update_flags = 0;
 	free(refname);
@@ -359,17 +362,16 @@
 		die("Refusing to perform update with empty message.");
 
 	if (read_stdin) {
-		int ret;
 		transaction = ref_transaction_begin();
-
 		if (delete || no_deref || argc > 0)
 			usage_with_options(git_update_ref_usage, options);
 		if (end_null)
 			line_termination = '\0';
 		update_refs_stdin();
-		ret = ref_transaction_commit(transaction, msg,
-					     UPDATE_REFS_DIE_ON_ERR);
-		return ret;
+		if (ref_transaction_commit(transaction, msg, &err))
+			die("%s", err.buf);
+		ref_transaction_free(transaction);
+		return 0;
 	}
 
 	if (end_null)
diff --git a/builtin/verify-pack.c b/builtin/verify-pack.c
index 66cd2df..972579f 100644
--- a/builtin/verify-pack.c
+++ b/builtin/verify-pack.c
@@ -27,10 +27,9 @@
 	 * normalize these forms to "foo.pack" for "index-pack --verify".
 	 */
 	strbuf_addstr(&arg, path);
-	if (has_extension(arg.buf, ".idx"))
-		strbuf_splice(&arg, arg.len - 3, 3, "pack", 4);
-	else if (!has_extension(arg.buf, ".pack"))
-		strbuf_add(&arg, ".pack", 5);
+	if (strbuf_strip_suffix(&arg, ".idx") ||
+	    !ends_with(arg.buf, ".pack"))
+		strbuf_addstr(&arg, ".pack");
 	argv[2] = arg.buf;
 
 	memset(&index_pack, 0, sizeof(index_pack));
diff --git a/bundle.c b/bundle.c
index 1222952..71a21a6 100644
--- a/bundle.c
+++ b/bundle.c
@@ -237,8 +237,6 @@
 	static struct lock_file lock;
 	int bundle_fd = -1;
 	int bundle_to_stdout;
-	struct argv_array argv_boundary = ARGV_ARRAY_INIT;
-	struct argv_array argv_pack = ARGV_ARRAY_INIT;
 	int i, ref_count = 0;
 	struct strbuf buf = STRBUF_INIT;
 	struct rev_info revs;
@@ -260,14 +258,12 @@
 	init_revisions(&revs, NULL);
 
 	/* write prerequisites */
-	argv_array_pushl(&argv_boundary,
+	memset(&rls, 0, sizeof(rls));
+	argv_array_pushl(&rls.args,
 			 "rev-list", "--boundary", "--pretty=oneline",
 			 NULL);
 	for (i = 1; i < argc; i++)
-		argv_array_push(&argv_boundary, argv[i]);
-
-	memset(&rls, 0, sizeof(rls));
-	rls.argv = argv_boundary.argv;
+		argv_array_push(&rls.args, argv[i]);
 	rls.out = -1;
 	rls.git_cmd = 1;
 	if (start_command(&rls))
@@ -382,12 +378,11 @@
 	write_or_die(bundle_fd, "\n", 1);
 
 	/* write pack */
-	argv_array_pushl(&argv_pack,
+	memset(&rls, 0, sizeof(rls));
+	argv_array_pushl(&rls.args,
 			 "pack-objects", "--all-progress-implied",
 			 "--stdout", "--thin", "--delta-base-offset",
 			 NULL);
-	memset(&rls, 0, sizeof(rls));
-	rls.argv = argv_pack.argv;
 	rls.in = -1;
 	rls.out = bundle_fd;
 	rls.git_cmd = 1;
diff --git a/cache-tree.c b/cache-tree.c
index 7fa524a..c53f7de 100644
--- a/cache-tree.c
+++ b/cache-tree.c
@@ -98,7 +98,7 @@
 	return find_subtree(it, path, pathlen, 1);
 }
 
-void cache_tree_invalidate_path(struct cache_tree *it, const char *path)
+static int do_invalidate_path(struct cache_tree *it, const char *path)
 {
 	/* a/b/c
 	 * ==> invalidate self
@@ -116,7 +116,7 @@
 #endif
 
 	if (!it)
-		return;
+		return 0;
 	slash = strchrnul(path, '/');
 	namelen = slash - path;
 	it->entry_count = -1;
@@ -137,14 +137,21 @@
 				(it->subtree_nr - pos - 1));
 			it->subtree_nr--;
 		}
-		return;
+		return 1;
 	}
 	down = find_subtree(it, path, namelen, 0);
 	if (down)
-		cache_tree_invalidate_path(down->cache_tree, slash + 1);
+		do_invalidate_path(down->cache_tree, slash + 1);
+	return 1;
 }
 
-static int verify_cache(const struct cache_entry * const *cache,
+void cache_tree_invalidate_path(struct index_state *istate, const char *path)
+{
+	if (do_invalidate_path(istate->cache_tree, path))
+		istate->cache_changed |= CACHE_TREE_CHANGED;
+}
+
+static int verify_cache(struct cache_entry **cache,
 			int entries, int flags)
 {
 	int i, funny;
@@ -229,7 +236,7 @@
 }
 
 static int update_one(struct cache_tree *it,
-		      const struct cache_entry * const *cache,
+		      struct cache_entry **cache,
 		      int entries,
 		      const char *base,
 		      int baselen,
@@ -391,18 +398,19 @@
 	return i;
 }
 
-int cache_tree_update(struct cache_tree *it,
-		      const struct cache_entry * const *cache,
-		      int entries,
-		      int flags)
+int cache_tree_update(struct index_state *istate, int flags)
 {
-	int i, skip;
-	i = verify_cache(cache, entries, flags);
+	struct cache_tree *it = istate->cache_tree;
+	struct cache_entry **cache = istate->cache;
+	int entries = istate->cache_nr;
+	int skip, i = verify_cache(cache, entries, flags);
+
 	if (i)
 		return i;
 	i = update_one(it, cache, entries, "", 0, &skip, flags);
 	if (i < 0)
 		return i;
+	istate->cache_changed |= CACHE_TREE_CHANGED;
 	return 0;
 }
 
@@ -590,13 +598,10 @@
 
 	was_valid = cache_tree_fully_valid(active_cache_tree);
 	if (!was_valid) {
-		if (cache_tree_update(active_cache_tree,
-				      (const struct cache_entry * const *)active_cache,
-				      active_nr, flags) < 0)
+		if (cache_tree_update(&the_index, flags) < 0)
 			return WRITE_TREE_UNMERGED_INDEX;
 		if (0 <= newfd) {
-			if (!write_cache(newfd, active_cache, active_nr) &&
-			    !commit_lock_file(lock_file))
+			if (!write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 				newfd = -1;
 		}
 		/* Not being able to write is fine -- we are only interested
@@ -649,11 +654,12 @@
 	it->entry_count = cnt;
 }
 
-void prime_cache_tree(struct cache_tree **it, struct tree *tree)
+void prime_cache_tree(struct index_state *istate, struct tree *tree)
 {
-	cache_tree_free(it);
-	*it = cache_tree();
-	prime_cache_tree_rec(*it, tree);
+	cache_tree_free(&istate->cache_tree);
+	istate->cache_tree = cache_tree();
+	prime_cache_tree_rec(istate->cache_tree, tree);
+	istate->cache_changed |= CACHE_TREE_CHANGED;
 }
 
 /*
@@ -692,7 +698,5 @@
 {
 	if (!the_index.cache_tree)
 		the_index.cache_tree = cache_tree();
-	return cache_tree_update(the_index.cache_tree,
-				 (const struct cache_entry * const *)the_index.cache,
-				 the_index.cache_nr, flags);
+	return cache_tree_update(&the_index, flags);
 }
diff --git a/cache-tree.h b/cache-tree.h
index f1923ad..b47ccec 100644
--- a/cache-tree.h
+++ b/cache-tree.h
@@ -23,14 +23,14 @@
 
 struct cache_tree *cache_tree(void);
 void cache_tree_free(struct cache_tree **);
-void cache_tree_invalidate_path(struct cache_tree *, const char *);
+void cache_tree_invalidate_path(struct index_state *, const char *);
 struct cache_tree_sub *cache_tree_sub(struct cache_tree *, const char *);
 
 void cache_tree_write(struct strbuf *, struct cache_tree *root);
 struct cache_tree *cache_tree_read(const char *buffer, unsigned long size);
 
 int cache_tree_fully_valid(struct cache_tree *);
-int cache_tree_update(struct cache_tree *, const struct cache_entry * const *, int, int);
+int cache_tree_update(struct index_state *, int);
 
 int update_main_cache_tree(int);
 
@@ -46,7 +46,7 @@
 #define WRITE_TREE_PREFIX_ERROR (-3)
 
 int write_cache_as_tree(unsigned char *sha1, int flags, const char *prefix);
-void prime_cache_tree(struct cache_tree **, struct tree *);
+void prime_cache_tree(struct index_state *, struct tree *);
 
 extern int cache_tree_matches_traversal(struct cache_tree *, struct name_entry *ent, struct traverse_info *info);
 
diff --git a/cache.h b/cache.h
index 44aa439..fcb511d 100644
--- a/cache.h
+++ b/cache.h
@@ -7,6 +7,7 @@
 #include "advice.h"
 #include "gettext.h"
 #include "convert.h"
+#include "trace.h"
 
 #include SHA1_HEADER
 #ifndef git_SHA_CTX
@@ -150,6 +151,7 @@
 	unsigned int ce_mode;
 	unsigned int ce_flags;
 	unsigned int ce_namelen;
+	unsigned int index;	/* for link extension */
 	unsigned char sha1[20];
 	char name[FLEX_ARRAY]; /* more */
 };
@@ -160,7 +162,7 @@
 #define CE_STAGESHIFT 12
 
 /*
- * Range 0xFFFF0000 in ce_flags is divided into
+ * Range 0xFFFF0FFF in ce_flags is divided into
  * two parts: in-memory flags and on-disk ones.
  * Flags in CE_EXTENDED_FLAGS will get saved on-disk
  * if you want to save a new flag, add it in
@@ -183,6 +185,9 @@
 /* used to temporarily mark paths matched by pathspecs */
 #define CE_MATCHED           (1 << 26)
 
+#define CE_UPDATE_IN_BASE    (1 << 27)
+#define CE_STRIP_NAME        (1 << 28)
+
 /*
  * Extended on-disk flags
  */
@@ -283,12 +288,22 @@
 
 #define cache_entry_size(len) (offsetof(struct cache_entry,name) + (len) + 1)
 
+#define SOMETHING_CHANGED	(1 << 0) /* unclassified changes go here */
+#define CE_ENTRY_CHANGED	(1 << 1)
+#define CE_ENTRY_REMOVED	(1 << 2)
+#define CE_ENTRY_ADDED		(1 << 3)
+#define RESOLVE_UNDO_CHANGED	(1 << 4)
+#define CACHE_TREE_CHANGED	(1 << 5)
+#define SPLIT_INDEX_ORDERED	(1 << 6)
+
+struct split_index;
 struct index_state {
 	struct cache_entry **cache;
 	unsigned int version;
 	unsigned int cache_nr, cache_alloc, cache_changed;
 	struct string_list *resolve_undo;
 	struct cache_tree *cache_tree;
+	struct split_index *split_index;
 	struct cache_time timestamp;
 	unsigned name_hash_initialized : 1,
 		 initialized : 1;
@@ -317,7 +332,6 @@
 #define read_cache_preload(pathspec) read_index_preload(&the_index, (pathspec))
 #define is_cache_unborn() is_index_unborn(&the_index)
 #define read_cache_unmerged() read_index_unmerged(&the_index)
-#define write_cache(newfd, cache, entries) write_index(&the_index, (newfd))
 #define discard_cache() discard_index(&the_index)
 #define unmerged_cache() unmerged_index(&the_index)
 #define cache_name_pos(name, namelen) index_name_pos(&the_index,(name),(namelen))
@@ -472,12 +486,17 @@
 	} while (0)
 
 /* Initialize and use the cache information */
+struct lock_file;
 extern int read_index(struct index_state *);
 extern int read_index_preload(struct index_state *, const struct pathspec *pathspec);
+extern int do_read_index(struct index_state *istate, const char *path,
+			 int must_exist); /* for testting only! */
 extern int read_index_from(struct index_state *, const char *path);
 extern int is_index_unborn(struct index_state *);
 extern int read_index_unmerged(struct index_state *);
-extern int write_index(struct index_state *, int newfd);
+#define COMMIT_LOCK		(1 << 0)
+#define CLOSE_LOCK		(1 << 1)
+extern int write_locked_index(struct index_state *, struct lock_file *lock, unsigned flags);
 extern int discard_index(struct index_state *);
 extern int unmerged_index(const struct index_state *);
 extern int verify_path(const char *path);
@@ -489,6 +508,7 @@
 #define ADD_CACHE_SKIP_DFCHECK 4	/* Ok to skip DF conflict checks */
 #define ADD_CACHE_JUST_APPEND 8		/* Append only; tree.c::read_tree() */
 #define ADD_CACHE_NEW_ONLY 16		/* Do not replace existing ones */
+#define ADD_CACHE_KEEP_CACHE_TREE 32	/* Do not invalidate cache-tree */
 extern int add_index_entry(struct index_state *, struct cache_entry *ce, int option);
 extern void rename_index_entry_at(struct index_state *, int pos, const char *new_name);
 extern int remove_index_entry_at(struct index_state *, int pos);
@@ -559,6 +579,8 @@
 #define LOCK_DIE_ON_ERROR 1
 #define LOCK_NODEREF 2
 extern int unable_to_lock_error(const char *path, int err);
+extern void unable_to_lock_message(const char *path, int err,
+				   struct strbuf *buf);
 extern NORETURN void unable_to_lock_index_die(const char *path, int err);
 extern int hold_lock_file_for_update(struct lock_file *, const char *path, int);
 extern int hold_lock_file_for_append(struct lock_file *, const char *path, int);
@@ -566,7 +588,6 @@
 extern void update_index_if_able(struct index_state *, struct lock_file *);
 
 extern int hold_locked_index(struct lock_file *, int);
-extern int commit_locked_index(struct lock_file *);
 extern void set_alternate_index_output(const char *);
 extern int close_lock_file(struct lock_file *);
 extern void rollback_lock_file(struct lock_file *);
@@ -977,7 +998,7 @@
  * NULL.  If more than MAXDEPTH recursive symbolic lookups are needed,
  * give up and return NULL.
  *
- * errno is sometimes set on errors, but not always.
+ * errno is set to something meaningful on error.
  */
 extern const char *resolve_ref_unsafe(const char *ref, unsigned char *sha1, int reading, int *flag);
 extern char *resolve_refdup(const char *ref, unsigned char *sha1, int reading, int *flag);
@@ -1078,6 +1099,7 @@
 extern int ident_cmp(const struct ident_split *, const struct ident_split *);
 
 struct checkout {
+	struct index_state *istate;
 	const char *base_dir;
 	int base_dir_len;
 	unsigned force:1,
@@ -1096,7 +1118,7 @@
 	int prefix_len_stat_func;
 };
 #define CACHE_DEF_INIT { STRBUF_INIT, 0, 0, 0 }
-static inline void cache_def_free(struct cache_def *cache)
+static inline void cache_def_clear(struct cache_def *cache)
 {
 	strbuf_release(&cache->path);
 }
@@ -1380,18 +1402,9 @@
 extern void *alloc_tag_node(void);
 extern void *alloc_object_node(void);
 extern void alloc_report(void);
+extern unsigned int alloc_commit_index(void);
 
-/* trace.c */
-__attribute__((format (printf, 1, 2)))
-extern void trace_printf(const char *format, ...);
-__attribute__((format (printf, 2, 3)))
-extern void trace_argv_printf(const char **argv, const char *format, ...);
-extern void trace_repo_setup(const char *prefix);
-extern int trace_want(const char *key);
-__attribute__((format (printf, 2, 3)))
-extern void trace_printf_key(const char *key, const char *fmt, ...);
-extern void trace_strbuf(const char *key, const struct strbuf *buf);
-
+/* pkt-line.c */
 void packet_trace_identity(const char *prog);
 
 /* add */
diff --git a/commit.c b/commit.c
index acb74b5..ae7f2b1 100644
--- a/commit.c
+++ b/commit.c
@@ -18,19 +18,6 @@
 
 const char *commit_type = "commit";
 
-static struct commit *check_commit(struct object *obj,
-				   const unsigned char *sha1,
-				   int quiet)
-{
-	if (obj->type != OBJ_COMMIT) {
-		if (!quiet)
-			error("Object %s is a %s, not a commit",
-			      sha1_to_hex(sha1), typename(obj->type));
-		return NULL;
-	}
-	return (struct commit *) obj;
-}
-
 struct commit *lookup_commit_reference_gently(const unsigned char *sha1,
 					      int quiet)
 {
@@ -38,7 +25,7 @@
 
 	if (!obj)
 		return NULL;
-	return check_commit(obj, sha1, quiet);
+	return object_as_type(obj, OBJ_COMMIT, quiet);
 }
 
 struct commit *lookup_commit_reference(const unsigned char *sha1)
@@ -61,13 +48,9 @@
 struct commit *lookup_commit(const unsigned char *sha1)
 {
 	struct object *obj = lookup_object(sha1);
-	if (!obj) {
-		struct commit *c = alloc_commit_node();
-		return create_object(sha1, OBJ_COMMIT, c);
-	}
-	if (!obj->type)
-		obj->type = OBJ_COMMIT;
-	return check_commit(obj, sha1, 0);
+	if (!obj)
+		return create_object(sha1, alloc_commit_node());
+	return object_as_type(obj, OBJ_COMMIT, 0);
 }
 
 struct commit *lookup_commit_reference_by_name(const char *name)
@@ -447,12 +430,7 @@
 	struct commit_list *head = NULL;
 	struct commit_list **pp = &head;
 	while (list) {
-		struct commit_list *new;
-		new = xmalloc(sizeof(struct commit_list));
-		new->item = list->item;
-		new->next = NULL;
-		*pp = new;
-		pp = &new->next;
+		pp = commit_list_append(list->item, pp);
 		list = list->next;
 	}
 	return head;
@@ -786,45 +764,41 @@
 
 static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
 
-static struct commit *interesting(struct commit_list *list)
+static int queue_has_nonstale(struct prio_queue *queue)
 {
-	while (list) {
-		struct commit *commit = list->item;
-		list = list->next;
-		if (commit->object.flags & STALE)
-			continue;
-		return commit;
+	int i;
+	for (i = 0; i < queue->nr; i++) {
+		struct commit *commit = queue->array[i].data;
+		if (!(commit->object.flags & STALE))
+			return 1;
 	}
-	return NULL;
+	return 0;
 }
 
 /* all input commits in one and twos[] must have been parsed! */
 static struct commit_list *paint_down_to_common(struct commit *one, int n, struct commit **twos)
 {
-	struct commit_list *list = NULL;
+	struct prio_queue queue = { compare_commits_by_commit_date };
 	struct commit_list *result = NULL;
 	int i;
 
 	one->object.flags |= PARENT1;
-	commit_list_insert_by_date(one, &list);
-	if (!n)
-		return list;
+	if (!n) {
+		commit_list_append(one, &result);
+		return result;
+	}
+	prio_queue_put(&queue, one);
+
 	for (i = 0; i < n; i++) {
 		twos[i]->object.flags |= PARENT2;
-		commit_list_insert_by_date(twos[i], &list);
+		prio_queue_put(&queue, twos[i]);
 	}
 
-	while (interesting(list)) {
-		struct commit *commit;
+	while (queue_has_nonstale(&queue)) {
+		struct commit *commit = prio_queue_get(&queue);
 		struct commit_list *parents;
-		struct commit_list *next;
 		int flags;
 
-		commit = list->item;
-		next = list->next;
-		free(list);
-		list = next;
-
 		flags = commit->object.flags & (PARENT1 | PARENT2 | STALE);
 		if (flags == (PARENT1 | PARENT2)) {
 			if (!(commit->object.flags & RESULT)) {
@@ -843,11 +817,11 @@
 			if (parse_commit(p))
 				return NULL;
 			p->object.flags |= flags;
-			commit_list_insert_by_date(p, &list);
+			prio_queue_put(&queue, p);
 		}
 	}
 
-	free_commit_list(list);
+	clear_prio_queue(&queue);
 	return result;
 }
 
@@ -992,12 +966,7 @@
 	}
 
 	/* There are more than one */
-	cnt = 0;
-	list = result;
-	while (list) {
-		list = list->next;
-		cnt++;
-	}
+	cnt = commit_list_count(result);
 	rslt = xcalloc(cnt, sizeof(*rslt));
 	for (list = result, i = 0; list; list = list->next)
 		rslt[i++] = list->item;
@@ -1177,6 +1146,40 @@
 	return saw_signature;
 }
 
+int remove_signature(struct strbuf *buf)
+{
+	const char *line = buf->buf;
+	const char *tail = buf->buf + buf->len;
+	int in_signature = 0;
+	const char *sig_start = NULL;
+	const char *sig_end = NULL;
+
+	while (line < tail) {
+		const char *next = memchr(line, '\n', tail - line);
+		next = next ? next + 1 : tail;
+
+		if (in_signature && line[0] == ' ')
+			sig_end = next;
+		else if (starts_with(line, gpg_sig_header) &&
+			 line[gpg_sig_header_len] == ' ') {
+			sig_start = line;
+			sig_end = next;
+			in_signature = 1;
+		} else {
+			if (*line == '\n')
+				/* dump the whole remainder of the buffer */
+				next = tail;
+			in_signature = 0;
+		}
+		line = next;
+	}
+
+	if (sig_start)
+		strbuf_remove(buf, sig_start - buf->buf, sig_end - sig_start);
+
+	return sig_start != NULL;
+}
+
 static void handle_signed_tag(struct commit *parent, struct commit_extra_header ***tail)
 {
 	struct merge_remote_desc *desc;
@@ -1315,6 +1318,19 @@
 	return extra;
 }
 
+void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data)
+{
+	struct commit_extra_header *extra, *to_free;
+
+	to_free = read_commit_extra_headers(commit, NULL);
+	for (extra = to_free; extra; extra = extra->next) {
+		if (strcmp(extra->key, "mergetag"))
+			continue; /* not a merge tag */
+		fn(commit, extra, data);
+	}
+	free_commit_extra_headers(to_free);
+}
+
 static inline int standard_header_field(const char *field, size_t len)
 {
 	return ((len == 4 && !memcmp(field, "tree ", 5)) ||
diff --git a/commit.h b/commit.h
index 2e1492a..a8cbf52 100644
--- a/commit.h
+++ b/commit.h
@@ -271,6 +271,7 @@
 					   int *ref_status);
 extern int delayed_reachability_test(struct shallow_info *si, int c);
 extern void prune_shallow(int show_only);
+extern struct trace_key trace_shallow;
 
 int is_descendant_of(struct commit *, struct commit_list *);
 int in_merge_bases(struct commit *, struct commit *);
@@ -312,6 +313,11 @@
 
 extern void free_commit_extra_headers(struct commit_extra_header *extra);
 
+typedef void (*each_mergetag_fn)(struct commit *commit, struct commit_extra_header *extra,
+				 void *cb_data);
+
+extern void for_each_mergetag(each_mergetag_fn fn, struct commit *commit, void *data);
+
 struct merge_remote_desc {
 	struct object *obj; /* the named object, could be a tag */
 	const char *name;
@@ -327,6 +333,8 @@
 
 extern int parse_signed_commit(const struct commit *commit,
 			       struct strbuf *message, struct strbuf *signature);
+extern int remove_signature(struct strbuf *buf);
+
 extern void print_commit_list(struct commit_list *list,
 			      const char *format_cur,
 			      const char *format_last);
diff --git a/compat/mingw.c b/compat/mingw.c
index 3baaa4d..9d435e2 100644
--- a/compat/mingw.c
+++ b/compat/mingw.c
@@ -1,6 +1,7 @@
 #include "../git-compat-util.h"
 #include "win32.h"
 #include <conio.h>
+#include <wchar.h>
 #include "../strbuf.h"
 #include "../run-command.h"
 
@@ -198,14 +199,16 @@
 	}
 }
 
-#undef unlink
 int mingw_unlink(const char *pathname)
 {
 	int ret, tries = 0;
+	wchar_t wpathname[MAX_PATH];
+	if (xutftowcs_path(wpathname, pathname) < 0)
+		return -1;
 
 	/* read-only files cannot be removed */
-	chmod(pathname, 0666);
-	while ((ret = unlink(pathname)) == -1 && tries < ARRAY_SIZE(delay)) {
+	_wchmod(wpathname, 0666);
+	while ((ret = _wunlink(wpathname)) == -1 && tries < ARRAY_SIZE(delay)) {
 		if (!is_file_in_use_error(GetLastError()))
 			break;
 		/*
@@ -221,45 +224,45 @@
 	while (ret == -1 && is_file_in_use_error(GetLastError()) &&
 	       ask_yes_no_if_possible("Unlink of file '%s' failed. "
 			"Should I try again?", pathname))
-	       ret = unlink(pathname);
+	       ret = _wunlink(wpathname);
 	return ret;
 }
 
-static int is_dir_empty(const char *path)
+static int is_dir_empty(const wchar_t *wpath)
 {
-	struct strbuf buf = STRBUF_INIT;
-	WIN32_FIND_DATAA findbuf;
+	WIN32_FIND_DATAW findbuf;
 	HANDLE handle;
-
-	strbuf_addf(&buf, "%s\\*", path);
-	handle = FindFirstFileA(buf.buf, &findbuf);
-	if (handle == INVALID_HANDLE_VALUE) {
-		strbuf_release(&buf);
+	wchar_t wbuf[MAX_PATH + 2];
+	wcscpy(wbuf, wpath);
+	wcscat(wbuf, L"\\*");
+	handle = FindFirstFileW(wbuf, &findbuf);
+	if (handle == INVALID_HANDLE_VALUE)
 		return GetLastError() == ERROR_NO_MORE_FILES;
-	}
 
-	while (!strcmp(findbuf.cFileName, ".") ||
-			!strcmp(findbuf.cFileName, ".."))
-		if (!FindNextFile(handle, &findbuf)) {
-			strbuf_release(&buf);
-			return GetLastError() == ERROR_NO_MORE_FILES;
+	while (!wcscmp(findbuf.cFileName, L".") ||
+			!wcscmp(findbuf.cFileName, L".."))
+		if (!FindNextFileW(handle, &findbuf)) {
+			DWORD err = GetLastError();
+			FindClose(handle);
+			return err == ERROR_NO_MORE_FILES;
 		}
 	FindClose(handle);
-	strbuf_release(&buf);
 	return 0;
 }
 
-#undef rmdir
 int mingw_rmdir(const char *pathname)
 {
 	int ret, tries = 0;
+	wchar_t wpathname[MAX_PATH];
+	if (xutftowcs_path(wpathname, pathname) < 0)
+		return -1;
 
-	while ((ret = rmdir(pathname)) == -1 && tries < ARRAY_SIZE(delay)) {
+	while ((ret = _wrmdir(wpathname)) == -1 && tries < ARRAY_SIZE(delay)) {
 		if (!is_file_in_use_error(GetLastError()))
 			errno = err_win_to_posix(GetLastError());
 		if (errno != EACCES)
 			break;
-		if (!is_dir_empty(pathname)) {
+		if (!is_dir_empty(wpathname)) {
 			errno = ENOTEMPTY;
 			break;
 		}
@@ -276,16 +279,26 @@
 	while (ret == -1 && errno == EACCES && is_file_in_use_error(GetLastError()) &&
 	       ask_yes_no_if_possible("Deletion of directory '%s' failed. "
 			"Should I try again?", pathname))
-	       ret = rmdir(pathname);
+	       ret = _wrmdir(wpathname);
 	return ret;
 }
 
-#undef open
+int mingw_mkdir(const char *path, int mode)
+{
+	int ret;
+	wchar_t wpath[MAX_PATH];
+	if (xutftowcs_path(wpath, path) < 0)
+		return -1;
+	ret = _wmkdir(wpath);
+	return ret;
+}
+
 int mingw_open (const char *filename, int oflags, ...)
 {
 	va_list args;
 	unsigned mode;
 	int fd;
+	wchar_t wfilename[MAX_PATH];
 
 	va_start(args, oflags);
 	mode = va_arg(args, int);
@@ -294,10 +307,12 @@
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
 
-	fd = open(filename, oflags, mode);
+	if (xutftowcs_path(wfilename, filename) < 0)
+		return -1;
+	fd = _wopen(wfilename, oflags, mode);
 
 	if (fd < 0 && (oflags & O_CREAT) && errno == EACCES) {
-		DWORD attrs = GetFileAttributes(filename);
+		DWORD attrs = GetFileAttributesW(wfilename);
 		if (attrs != INVALID_FILE_ATTRIBUTES && (attrs & FILE_ATTRIBUTE_DIRECTORY))
 			errno = EISDIR;
 	}
@@ -332,17 +347,28 @@
 #undef fopen
 FILE *mingw_fopen (const char *filename, const char *otype)
 {
+	FILE *file;
+	wchar_t wfilename[MAX_PATH], wotype[4];
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
-	return fopen(filename, otype);
+	if (xutftowcs_path(wfilename, filename) < 0 ||
+		xutftowcs(wotype, otype, ARRAY_SIZE(wotype)) < 0)
+		return NULL;
+	file = _wfopen(wfilename, wotype);
+	return file;
 }
 
-#undef freopen
 FILE *mingw_freopen (const char *filename, const char *otype, FILE *stream)
 {
+	FILE *file;
+	wchar_t wfilename[MAX_PATH], wotype[4];
 	if (filename && !strcmp(filename, "/dev/null"))
 		filename = "nul";
-	return freopen(filename, otype, stream);
+	if (xutftowcs_path(wfilename, filename) < 0 ||
+		xutftowcs(wotype, otype, ARRAY_SIZE(wotype)) < 0)
+		return NULL;
+	file = _wfreopen(wfilename, wotype, stream);
+	return file;
 }
 
 #undef fflush
@@ -367,6 +393,31 @@
 	return ret;
 }
 
+int mingw_access(const char *filename, int mode)
+{
+	wchar_t wfilename[MAX_PATH];
+	if (xutftowcs_path(wfilename, filename) < 0)
+		return -1;
+	/* X_OK is not supported by the MSVCRT version */
+	return _waccess(wfilename, mode & ~X_OK);
+}
+
+int mingw_chdir(const char *dirname)
+{
+	wchar_t wdirname[MAX_PATH];
+	if (xutftowcs_path(wdirname, dirname) < 0)
+		return -1;
+	return _wchdir(wdirname);
+}
+
+int mingw_chmod(const char *filename, int mode)
+{
+	wchar_t wfilename[MAX_PATH];
+	if (xutftowcs_path(wfilename, filename) < 0)
+		return -1;
+	return _wchmod(wfilename, mode);
+}
+
 /*
  * The unit of FILETIME is 100-nanoseconds since January 1, 1601, UTC.
  * Returns the 100-nanoseconds ("hekto nanoseconds") since the epoch.
@@ -392,10 +443,12 @@
  */
 static int do_lstat(int follow, const char *file_name, struct stat *buf)
 {
-	int err;
 	WIN32_FILE_ATTRIBUTE_DATA fdata;
+	wchar_t wfilename[MAX_PATH];
+	if (xutftowcs_path(wfilename, file_name) < 0)
+		return -1;
 
-	if (!(err = get_file_attr(file_name, &fdata))) {
+	if (GetFileAttributesExW(wfilename, GetFileExInfoStandard, &fdata)) {
 		buf->st_ino = 0;
 		buf->st_gid = 0;
 		buf->st_uid = 0;
@@ -408,8 +461,8 @@
 		buf->st_mtime = filetime_to_time_t(&(fdata.ftLastWriteTime));
 		buf->st_ctime = filetime_to_time_t(&(fdata.ftCreationTime));
 		if (fdata.dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT) {
-			WIN32_FIND_DATAA findbuf;
-			HANDLE handle = FindFirstFileA(file_name, &findbuf);
+			WIN32_FIND_DATAW findbuf;
+			HANDLE handle = FindFirstFileW(wfilename, &findbuf);
 			if (handle != INVALID_HANDLE_VALUE) {
 				if ((findbuf.dwFileAttributes & FILE_ATTRIBUTE_REPARSE_POINT) &&
 						(findbuf.dwReserved0 == IO_REPARSE_TAG_SYMLINK)) {
@@ -428,7 +481,23 @@
 		}
 		return 0;
 	}
-	errno = err;
+	switch (GetLastError()) {
+	case ERROR_ACCESS_DENIED:
+	case ERROR_SHARING_VIOLATION:
+	case ERROR_LOCK_VIOLATION:
+	case ERROR_SHARING_BUFFER_EXCEEDED:
+		errno = EACCES;
+		break;
+	case ERROR_BUFFER_OVERFLOW:
+		errno = ENAMETOOLONG;
+		break;
+	case ERROR_NOT_ENOUGH_MEMORY:
+		errno = ENOMEM;
+		break;
+	default:
+		errno = ENOENT;
+		break;
+	}
 	return -1;
 }
 
@@ -516,16 +585,20 @@
 {
 	FILETIME mft, aft;
 	int fh, rc;
+	DWORD attrs;
+	wchar_t wfilename[MAX_PATH];
+	if (xutftowcs_path(wfilename, file_name) < 0)
+		return -1;
 
 	/* must have write permission */
-	DWORD attrs = GetFileAttributes(file_name);
+	attrs = GetFileAttributesW(wfilename);
 	if (attrs != INVALID_FILE_ATTRIBUTES &&
 	    (attrs & FILE_ATTRIBUTE_READONLY)) {
 		/* ignore errors here; open() will report them */
-		SetFileAttributes(file_name, attrs & ~FILE_ATTRIBUTE_READONLY);
+		SetFileAttributesW(wfilename, attrs & ~FILE_ATTRIBUTE_READONLY);
 	}
 
-	if ((fh = open(file_name, O_RDWR | O_BINARY)) < 0) {
+	if ((fh = _wopen(wfilename, O_RDWR | O_BINARY)) < 0) {
 		rc = -1;
 		goto revert_attrs;
 	}
@@ -548,7 +621,7 @@
 	if (attrs != INVALID_FILE_ATTRIBUTES &&
 	    (attrs & FILE_ATTRIBUTE_READONLY)) {
 		/* ignore errors again */
-		SetFileAttributes(file_name, attrs);
+		SetFileAttributesW(wfilename, attrs);
 	}
 	return rc;
 }
@@ -559,6 +632,18 @@
 	return 0;
 }
 
+char *mingw_mktemp(char *template)
+{
+	wchar_t wtemplate[MAX_PATH];
+	if (xutftowcs_path(wtemplate, template) < 0)
+		return NULL;
+	if (!_wmktemp(wtemplate))
+		return NULL;
+	if (xwcstoutf(template, wtemplate, strlen(template) + 1) < 0)
+		return NULL;
+	return template;
+}
+
 int mkstemp(char *template)
 {
 	char *filename = mktemp(template);
@@ -617,17 +702,18 @@
 	return result;
 }
 
-#undef getcwd
 char *mingw_getcwd(char *pointer, int len)
 {
 	int i;
-	char *ret = getcwd(pointer, len);
-	if (!ret)
-		return ret;
+	wchar_t wpointer[MAX_PATH];
+	if (!_wgetcwd(wpointer, ARRAY_SIZE(wpointer)))
+		return NULL;
+	if (xwcstoutf(pointer, wpointer, len) < 0)
+		return NULL;
 	for (i = 0; pointer[i]; i++)
 		if (pointer[i] == '\\')
 			pointer[i] = '/';
-	return ret;
+	return pointer;
 }
 
 /*
@@ -1230,8 +1316,7 @@
 	else
 		ai->ai_canonname = NULL;
 
-	sin = xmalloc(ai->ai_addrlen);
-	memset(sin, 0, ai->ai_addrlen);
+	sin = xcalloc(1, ai->ai_addrlen);
 	sin->sin_family = AF_INET;
 	/* Note: getaddrinfo is supposed to allow service to be a string,
 	 * which should be looked up using getservbyname. This is
@@ -1485,33 +1570,36 @@
 {
 	DWORD attrs, gle;
 	int tries = 0;
+	wchar_t wpold[MAX_PATH], wpnew[MAX_PATH];
+	if (xutftowcs_path(wpold, pold) < 0 || xutftowcs_path(wpnew, pnew) < 0)
+		return -1;
 
 	/*
 	 * Try native rename() first to get errno right.
 	 * It is based on MoveFile(), which cannot overwrite existing files.
 	 */
-	if (!rename(pold, pnew))
+	if (!_wrename(wpold, wpnew))
 		return 0;
 	if (errno != EEXIST)
 		return -1;
 repeat:
-	if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING))
+	if (MoveFileExW(wpold, wpnew, MOVEFILE_REPLACE_EXISTING))
 		return 0;
 	/* TODO: translate more errors */
 	gle = GetLastError();
 	if (gle == ERROR_ACCESS_DENIED &&
-	    (attrs = GetFileAttributes(pnew)) != INVALID_FILE_ATTRIBUTES) {
+	    (attrs = GetFileAttributesW(wpnew)) != INVALID_FILE_ATTRIBUTES) {
 		if (attrs & FILE_ATTRIBUTE_DIRECTORY) {
 			errno = EISDIR;
 			return -1;
 		}
 		if ((attrs & FILE_ATTRIBUTE_READONLY) &&
-		    SetFileAttributes(pnew, attrs & ~FILE_ATTRIBUTE_READONLY)) {
-			if (MoveFileEx(pold, pnew, MOVEFILE_REPLACE_EXISTING))
+		    SetFileAttributesW(wpnew, attrs & ~FILE_ATTRIBUTE_READONLY)) {
+			if (MoveFileExW(wpold, wpnew, MOVEFILE_REPLACE_EXISTING))
 				return 0;
 			gle = GetLastError();
 			/* revert file attributes on failure */
-			SetFileAttributes(pnew, attrs);
+			SetFileAttributesW(wpnew, attrs);
 		}
 	}
 	if (tries < ARRAY_SIZE(delay) && gle == ERROR_ACCESS_DENIED) {
@@ -1757,11 +1845,16 @@
 
 int link(const char *oldpath, const char *newpath)
 {
-	typedef BOOL (WINAPI *T)(const char*, const char*, LPSECURITY_ATTRIBUTES);
+	typedef BOOL (WINAPI *T)(LPCWSTR, LPCWSTR, LPSECURITY_ATTRIBUTES);
 	static T create_hard_link = NULL;
+	wchar_t woldpath[MAX_PATH], wnewpath[MAX_PATH];
+	if (xutftowcs_path(woldpath, oldpath) < 0 ||
+		xutftowcs_path(wnewpath, newpath) < 0)
+		return -1;
+
 	if (!create_hard_link) {
 		create_hard_link = (T) GetProcAddress(
-			GetModuleHandle("kernel32.dll"), "CreateHardLinkA");
+			GetModuleHandle("kernel32.dll"), "CreateHardLinkW");
 		if (!create_hard_link)
 			create_hard_link = (T)-1;
 	}
@@ -1769,7 +1862,7 @@
 		errno = ENOSYS;
 		return -1;
 	}
-	if (!create_hard_link(newpath, oldpath, NULL)) {
+	if (!create_hard_link(wnewpath, woldpath, NULL)) {
 		errno = err_win_to_posix(GetLastError());
 		return -1;
 	}
diff --git a/compat/mingw.h b/compat/mingw.h
index 8dac6f9..510530c 100644
--- a/compat/mingw.h
+++ b/compat/mingw.h
@@ -35,6 +35,9 @@
 #ifndef EWOULDBLOCK
 #define EWOULDBLOCK EAGAIN
 #endif
+#ifndef ELOOP
+#define ELOOP EMLINK
+#endif
 #define SHUT_WR SD_SEND
 
 #define SIGHUP 1
@@ -118,10 +121,7 @@
  * simple adaptors
  */
 
-static inline int mingw_mkdir(const char *path, int mode)
-{
-	return mkdir(path);
-}
+int mingw_mkdir(const char *path, int mode);
 #define mkdir mingw_mkdir
 
 #define WNOHANG 1
@@ -192,6 +192,19 @@
 int mingw_fflush(FILE *stream);
 #define fflush mingw_fflush
 
+int mingw_access(const char *filename, int mode);
+#undef access
+#define access mingw_access
+
+int mingw_chdir(const char *dirname);
+#define chdir mingw_chdir
+
+int mingw_chmod(const char *filename, int mode);
+#define chmod mingw_chmod
+
+char *mingw_mktemp(char *template);
+#define mktemp mingw_mktemp
+
 char *mingw_getcwd(char *pointer, int len);
 #define getcwd mingw_getcwd
 
diff --git a/compat/win32/dirent.c b/compat/win32/dirent.c
index 82a515c..52420ec 100644
--- a/compat/win32/dirent.c
+++ b/compat/win32/dirent.c
@@ -6,10 +6,10 @@
 	int dd_stat;          /* 0-based index */
 };
 
-static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAA *fdata)
+static inline void finddata2dirent(struct dirent *ent, WIN32_FIND_DATAW *fdata)
 {
-	/* copy file name from WIN32_FIND_DATA to dirent */
-	memcpy(ent->d_name, fdata->cFileName, sizeof(ent->d_name));
+	/* convert UTF-16 name to UTF-8 */
+	xwcstoutf(ent->d_name, fdata->cFileName, sizeof(ent->d_name));
 
 	/* Set file type, based on WIN32_FIND_DATA */
 	if (fdata->dwFileAttributes & FILE_ATTRIBUTE_DIRECTORY)
@@ -20,25 +20,15 @@
 
 DIR *opendir(const char *name)
 {
-	char pattern[MAX_PATH];
-	WIN32_FIND_DATAA fdata;
+	wchar_t pattern[MAX_PATH + 2]; /* + 2 for '/' '*' */
+	WIN32_FIND_DATAW fdata;
 	HANDLE h;
 	int len;
 	DIR *dir;
 
-	/* check that name is not NULL */
-	if (!name) {
-		errno = EINVAL;
+	/* convert name to UTF-16 and check length < MAX_PATH */
+	if ((len = xutftowcs_path(pattern, name)) < 0)
 		return NULL;
-	}
-	/* check that the pattern won't be too long for FindFirstFileA */
-	len = strlen(name);
-	if (len + 2 >= MAX_PATH) {
-		errno = ENAMETOOLONG;
-		return NULL;
-	}
-	/* copy name to temp buffer */
-	memcpy(pattern, name, len + 1);
 
 	/* append optional '/' and wildcard '*' */
 	if (len && !is_dir_sep(pattern[len - 1]))
@@ -47,7 +37,7 @@
 	pattern[len] = 0;
 
 	/* open find handle */
-	h = FindFirstFileA(pattern, &fdata);
+	h = FindFirstFileW(pattern, &fdata);
 	if (h == INVALID_HANDLE_VALUE) {
 		DWORD err = GetLastError();
 		errno = (err == ERROR_DIRECTORY) ? ENOTDIR : err_win_to_posix(err);
@@ -72,8 +62,8 @@
 	/* if first entry, dirent has already been set up by opendir */
 	if (dir->dd_stat) {
 		/* get next entry and convert from WIN32_FIND_DATA to dirent */
-		WIN32_FIND_DATAA fdata;
-		if (FindNextFileA(dir->dd_handle, &fdata)) {
+		WIN32_FIND_DATAW fdata;
+		if (FindNextFileW(dir->dd_handle, &fdata)) {
 			finddata2dirent(&dir->dd_dir, &fdata);
 		} else {
 			DWORD lasterr = GetLastError();
diff --git a/compat/win32/dirent.h b/compat/win32/dirent.h
index 8838cd6..058207e 100644
--- a/compat/win32/dirent.h
+++ b/compat/win32/dirent.h
@@ -10,7 +10,7 @@
 
 struct dirent {
 	unsigned char d_type;      /* file type to prevent lstat after readdir */
-	char d_name[MAX_PATH];     /* file name */
+	char d_name[MAX_PATH * 3]; /* file name (* 3 for UTF-8 conversion) */
 };
 
 DIR *opendir(const char *dirname);
diff --git a/config.c b/config.c
index ba882a1..9767c4b 100644
--- a/config.c
+++ b/config.c
@@ -1636,8 +1636,8 @@
 			MAP_PRIVATE, in_fd, 0);
 		close(in_fd);
 
-		if (fchmod(fd, st.st_mode & 07777) < 0) {
-			error("fchmod on %s failed: %s",
+		if (chmod(lock->filename, st.st_mode & 07777) < 0) {
+			error("chmod on %s failed: %s",
 				lock->filename, strerror(errno));
 			ret = CONFIG_NO_WRITE;
 			goto out_free;
@@ -1815,8 +1815,8 @@
 
 	fstat(fileno(config_file), &st);
 
-	if (fchmod(out_fd, st.st_mode & 07777) < 0) {
-		ret = error("fchmod on %s failed: %s",
+	if (chmod(lock->filename, st.st_mode & 07777) < 0) {
+		ret = error("chmod on %s failed: %s",
 				lock->filename, strerror(errno));
 		goto out;
 	}
diff --git a/config.mak.uname b/config.mak.uname
index 8131c81..00cf4c6 100644
--- a/config.mak.uname
+++ b/config.mak.uname
@@ -34,6 +34,7 @@
 	HAVE_PATHS_H = YesPlease
 	LIBC_CONTAINS_LIBINTL = YesPlease
 	HAVE_DEV_TTY = YesPlease
+	HAVE_CLOCK_GETTIME = YesPlease
 endif
 ifeq ($(uname_S),GNU/kFreeBSD)
 	HAVE_ALLOCA_H = YesPlease
diff --git a/connect.c b/connect.c
index 37ff018..5047402 100644
--- a/connect.c
+++ b/connect.c
@@ -64,9 +64,7 @@
 	if (!len)
 		return; /* just "symref" */
 	/* e.g. "symref=HEAD:refs/heads/master" */
-	sym = xmalloc(len + 1);
-	memcpy(sym, val, len);
-	sym[len] = '\0';
+	sym = xmemdupz(val, len);
 	target = strchr(sym, ':');
 	if (!target)
 		/* just "symref=something" */
diff --git a/connected.c b/connected.c
index be0253e..dae9c99 100644
--- a/connected.c
+++ b/connected.c
@@ -31,6 +31,7 @@
 	unsigned char sha1[20];
 	int err = 0, ac = 0;
 	struct packed_git *new_pack = NULL;
+	size_t base_len;
 
 	if (fn(cb_data, sha1))
 		return err;
@@ -38,10 +39,9 @@
 	if (transport && transport->smart_options &&
 	    transport->smart_options->self_contained_and_connected &&
 	    transport->pack_lockfile &&
-	    ends_with(transport->pack_lockfile, ".keep")) {
+	    strip_suffix(transport->pack_lockfile, ".keep", &base_len)) {
 		struct strbuf idx_file = STRBUF_INIT;
-		strbuf_addstr(&idx_file, transport->pack_lockfile);
-		strbuf_setlen(&idx_file, idx_file.len - 5); /* ".keep" */
+		strbuf_add(&idx_file, transport->pack_lockfile, base_len);
 		strbuf_addstr(&idx_file, ".idx");
 		new_pack = add_packed_git(idx_file.buf, idx_file.len, 1);
 		strbuf_release(&idx_file);
diff --git a/contrib/convert-grafts-to-replace-refs.sh b/contrib/convert-grafts-to-replace-refs.sh
new file mode 100755
index 0000000..0cbc917
--- /dev/null
+++ b/contrib/convert-grafts-to-replace-refs.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+
+# You should execute this script in the repository where you
+# want to convert grafts to replace refs.
+
+GRAFTS_FILE="${GIT_DIR:-.git}/info/grafts"
+
+. $(git --exec-path)/git-sh-setup
+
+test -f "$GRAFTS_FILE" || die "Could not find graft file: '$GRAFTS_FILE'"
+
+grep '^[^# ]' "$GRAFTS_FILE" |
+while read definition
+do
+	if test -n "$definition"
+	then
+		echo "Converting: $definition"
+		git replace --graft $definition ||
+			die "Conversion failed for: $definition"
+	fi
+done
+
+mv "$GRAFTS_FILE" "$GRAFTS_FILE.bak" ||
+	die "Could not rename '$GRAFTS_FILE' to '$GRAFTS_FILE.bak'"
+
+echo "Success!"
+echo "All the grafts in '$GRAFTS_FILE' have been converted to replace refs!"
+echo "The grafts file '$GRAFTS_FILE' has been renamed: '$GRAFTS_FILE.bak'"
diff --git a/contrib/subtree/Makefile b/contrib/subtree/Makefile
index d888d45..d9a0ce2 100644
--- a/contrib/subtree/Makefile
+++ b/contrib/subtree/Makefile
@@ -18,6 +18,11 @@
 ASCIIDOC = asciidoc
 XMLTO    = xmlto
 
+ifndef SHELL_PATH
+	SHELL_PATH = /bin/sh
+endif
+SHELL_PATH_SQ = $(subst ','\'',$(SHELL_PATH))
+
 ASCIIDOC_CONF = ../../Documentation/asciidoc.conf
 MANPAGE_XSL   = ../../Documentation/manpage-normal.xsl
 
@@ -32,7 +37,8 @@
 all: $(GIT_SUBTREE)
 
 $(GIT_SUBTREE): $(GIT_SUBTREE_SH)
-	cp $< $@ && chmod +x $@
+	sed -e '1s|#!.*/sh|#!$(SHELL_PATH_SQ)|' $< >$@
+	chmod +x $@
 
 doc: $(GIT_SUBTREE_DOC) $(GIT_SUBTREE_HTML)
 
diff --git a/daemon.c b/daemon.c
index 1eb6631..e6b51ed 100644
--- a/daemon.c
+++ b/daemon.c
@@ -778,7 +778,6 @@
 		logerror("unable to fork");
 	else
 		add_child(&cld, addr, addrlen);
-	close(incoming);
 }
 
 static void child_handler(int signo)
diff --git a/decorate.c b/decorate.c
index 7cb5d29..b2aac90 100644
--- a/decorate.c
+++ b/decorate.c
@@ -8,10 +8,7 @@
 
 static unsigned int hash_obj(const struct object *obj, unsigned int n)
 {
-	unsigned int hash;
-
-	memcpy(&hash, obj->sha1, sizeof(unsigned int));
-	return hash % n;
+	return sha1hash(obj->sha1) % n;
 }
 
 static void *insert_decoration(struct decoration *n, const struct object *base, void *decoration)
diff --git a/diff.c b/diff.c
index 06bdfb8..867f034 100644
--- a/diff.c
+++ b/diff.c
@@ -525,9 +525,9 @@
 	ep += 2; /* skip over @@ */
 
 	/* The hunk header in fraginfo color */
-	strbuf_add(&msgbuf, frag, strlen(frag));
+	strbuf_addstr(&msgbuf, frag);
 	strbuf_add(&msgbuf, line, ep - line);
-	strbuf_add(&msgbuf, reset, strlen(reset));
+	strbuf_addstr(&msgbuf, reset);
 
 	/*
 	 * trailing "\r\n"
@@ -541,15 +541,15 @@
 		if (*ep != ' ' && *ep != '\t')
 			break;
 	if (ep != cp) {
-		strbuf_add(&msgbuf, plain, strlen(plain));
+		strbuf_addstr(&msgbuf, plain);
 		strbuf_add(&msgbuf, cp, ep - cp);
-		strbuf_add(&msgbuf, reset, strlen(reset));
+		strbuf_addstr(&msgbuf, reset);
 	}
 
 	if (ep < line + len) {
-		strbuf_add(&msgbuf, func, strlen(func));
+		strbuf_addstr(&msgbuf, func);
 		strbuf_add(&msgbuf, ep, line + len - ep);
-		strbuf_add(&msgbuf, reset, strlen(reset));
+		strbuf_addstr(&msgbuf, reset);
 	}
 
 	strbuf_add(&msgbuf, line + len, org_len - len);
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 749a35d..2e44a37 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -242,14 +242,12 @@
 
 static unsigned int hash_filespec(struct diff_filespec *filespec)
 {
-	unsigned int hash;
 	if (!filespec->sha1_valid) {
 		if (diff_populate_filespec(filespec, 0))
 			return 0;
 		hash_sha1_file(filespec->data, filespec->size, "blob", filespec->sha1);
 	}
-	memcpy(&hash, filespec->sha1, sizeof(hash));
-	return hash;
+	return sha1hash(filespec->sha1);
 }
 
 static int find_identical_files(struct hashmap *srcs,
@@ -259,15 +257,14 @@
 	int renames = 0;
 
 	struct diff_filespec *target = rename_dst[dst_index].two;
-	struct file_similarity *p, *best, dst;
+	struct file_similarity *p, *best = NULL;
 	int i = 100, best_score = -1;
 
 	/*
 	 * Find the best source match for specified destination.
 	 */
-	best = NULL;
-	hashmap_entry_init(&dst, hash_filespec(target));
-	for (p = hashmap_get(srcs, &dst, NULL); p; p = hashmap_get_next(srcs, p)) {
+	p = hashmap_get_from_hash(srcs, hash_filespec(target), NULL);
+	for (; p; p = hashmap_get_next(srcs, p)) {
 		int score;
 		struct diff_filespec *source = p->filespec;
 
diff --git a/dir.c b/dir.c
index e65888d..fcb6872 100644
--- a/dir.c
+++ b/dir.c
@@ -557,8 +557,7 @@
 			buf = xrealloc(buf, size+1);
 			buf[size++] = '\n';
 		}
-	}
-	else {
+	} else {
 		size = xsize_t(st.st_size);
 		if (size == 0) {
 			close(fd);
@@ -793,17 +792,19 @@
 
 	group = &dir->exclude_list_group[EXC_DIRS];
 
-	/* Pop the exclude lists from the EXCL_DIRS exclude_list_group
+	/*
+	 * Pop the exclude lists from the EXCL_DIRS exclude_list_group
 	 * which originate from directories not in the prefix of the
-	 * path being checked. */
+	 * path being checked.
+	 */
 	while ((stk = dir->exclude_stack) != NULL) {
 		if (stk->baselen <= baselen &&
-		    !strncmp(dir->basebuf, base, stk->baselen))
+		    !strncmp(dir->basebuf.buf, base, stk->baselen))
 			break;
 		el = &group->el[dir->exclude_stack->exclude_ix];
 		dir->exclude_stack = stk->prev;
 		dir->exclude = NULL;
-		free((char *)el->src); /* see strdup() below */
+		free((char *)el->src); /* see strbuf_detach() below */
 		clear_exclude_list(el);
 		free(stk);
 		group->nr--;
@@ -813,8 +814,17 @@
 	if (dir->exclude)
 		return;
 
+	/*
+	 * Lazy initialization. All call sites currently just
+	 * memset(dir, 0, sizeof(*dir)) before use. Changing all of
+	 * them seems lots of work for little benefit.
+	 */
+	if (!dir->basebuf.buf)
+		strbuf_init(&dir->basebuf, PATH_MAX);
+
 	/* Read from the parent directories and push them down. */
 	current = stk ? stk->baselen : -1;
+	strbuf_setlen(&dir->basebuf, current < 0 ? 0 : current);
 	while (current < baselen) {
 		struct exclude_stack *stk = xcalloc(1, sizeof(*stk));
 		const char *cp;
@@ -822,8 +832,7 @@
 		if (current < 0) {
 			cp = base;
 			current = 0;
-		}
-		else {
+		} else {
 			cp = strchr(base + current + 1, '/');
 			if (!cp)
 				die("oops in prep_exclude");
@@ -833,48 +842,47 @@
 		stk->baselen = cp - base;
 		stk->exclude_ix = group->nr;
 		el = add_exclude_list(dir, EXC_DIRS, NULL);
-		memcpy(dir->basebuf + current, base + current,
-		       stk->baselen - current);
+		strbuf_add(&dir->basebuf, base + current, stk->baselen - current);
+		assert(stk->baselen == dir->basebuf.len);
 
 		/* Abort if the directory is excluded */
 		if (stk->baselen) {
 			int dt = DT_DIR;
-			dir->basebuf[stk->baselen - 1] = 0;
+			dir->basebuf.buf[stk->baselen - 1] = 0;
 			dir->exclude = last_exclude_matching_from_lists(dir,
-				dir->basebuf, stk->baselen - 1,
-				dir->basebuf + current, &dt);
-			dir->basebuf[stk->baselen - 1] = '/';
+				dir->basebuf.buf, stk->baselen - 1,
+				dir->basebuf.buf + current, &dt);
+			dir->basebuf.buf[stk->baselen - 1] = '/';
 			if (dir->exclude &&
 			    dir->exclude->flags & EXC_FLAG_NEGATIVE)
 				dir->exclude = NULL;
 			if (dir->exclude) {
-				dir->basebuf[stk->baselen] = 0;
 				dir->exclude_stack = stk;
 				return;
 			}
 		}
 
-		/* Try to read per-directory file unless path is too long */
-		if (dir->exclude_per_dir &&
-		    stk->baselen + strlen(dir->exclude_per_dir) < PATH_MAX) {
-			strcpy(dir->basebuf + stk->baselen,
-					dir->exclude_per_dir);
+		/* Try to read per-directory file */
+		if (dir->exclude_per_dir) {
 			/*
 			 * dir->basebuf gets reused by the traversal, but we
 			 * need fname to remain unchanged to ensure the src
 			 * member of each struct exclude correctly
 			 * back-references its source file.  Other invocations
 			 * of add_exclude_list provide stable strings, so we
-			 * strdup() and free() here in the caller.
+			 * strbuf_detach() and free() here in the caller.
 			 */
-			el->src = strdup(dir->basebuf);
-			add_excludes_from_file_to_list(dir->basebuf,
-					dir->basebuf, stk->baselen, el, 1);
+			struct strbuf sb = STRBUF_INIT;
+			strbuf_addbuf(&sb, &dir->basebuf);
+			strbuf_addstr(&sb, dir->exclude_per_dir);
+			el->src = strbuf_detach(&sb, NULL);
+			add_excludes_from_file_to_list(el->src, el->src,
+						       stk->baselen, el, 1);
 		}
 		dir->exclude_stack = stk;
 		current = stk->baselen;
 	}
-	dir->basebuf[baselen] = '\0';
+	strbuf_setlen(&dir->basebuf, baselen);
 }
 
 /*
@@ -1671,4 +1679,5 @@
 		free(stk);
 		stk = prev;
 	}
+	strbuf_release(&dir->basebuf);
 }
diff --git a/dir.h b/dir.h
index 55e5345..6c45e9d 100644
--- a/dir.h
+++ b/dir.h
@@ -15,6 +15,27 @@
 #define EXC_FLAG_MUSTBEDIR 8
 #define EXC_FLAG_NEGATIVE 16
 
+struct exclude {
+	/*
+	 * This allows callers of last_exclude_matching() etc.
+	 * to determine the origin of the matching pattern.
+	 */
+	struct exclude_list *el;
+
+	const char *pattern;
+	int patternlen;
+	int nowildcardlen;
+	const char *base;
+	int baselen;
+	int flags;
+
+	/*
+	 * Counting starts from 1 for line numbers in ignore files,
+	 * and from -1 decrementing for patterns from CLI args.
+	 */
+	int srcpos;
+};
+
 /*
  * Each excludes file will be parsed into a fresh exclude_list which
  * is appended to the relevant exclude_list_group (either EXC_DIRS or
@@ -32,26 +53,7 @@
 	/* origin of list, e.g. path to filename, or descriptive string */
 	const char *src;
 
-	struct exclude {
-		/*
-		 * This allows callers of last_exclude_matching() etc.
-		 * to determine the origin of the matching pattern.
-		 */
-		struct exclude_list *el;
-
-		const char *pattern;
-		int patternlen;
-		int nowildcardlen;
-		const char *base;
-		int baselen;
-		int flags;
-
-		/*
-		 * Counting starts from 1 for line numbers in ignore files,
-		 * and from -1 decrementing for patterns from CLI args.
-		 */
-		int srcpos;
-	} **excludes;
+	struct exclude **excludes;
 };
 
 /*
@@ -117,7 +119,7 @@
 	 */
 	struct exclude_stack *exclude_stack;
 	struct exclude *exclude;
-	char basebuf[PATH_MAX];
+	struct strbuf basebuf;
 };
 
 /*
diff --git a/entry.c b/entry.c
index 77c6882..1eda8e9 100644
--- a/entry.c
+++ b/entry.c
@@ -210,9 +210,12 @@
 
 finish:
 	if (state->refresh_cache) {
+		assert(state->istate);
 		if (!fstat_done)
 			lstat(ce->name, &st);
 		fill_stat_cache_info(ce, &st);
+		ce->ce_flags |= CE_UPDATE_IN_BASE;
+		state->istate->cache_changed |= CE_ENTRY_CHANGED;
 	}
 	return 0;
 }
diff --git a/ewah/ewah_io.c b/ewah/ewah_io.c
index f7f700e..1c2d7af 100644
--- a/ewah/ewah_io.c
+++ b/ewah/ewah_io.c
@@ -110,9 +110,9 @@
 	return ewah_serialize_to(self, write_helper, (void *)(intptr_t)fd);
 }
 
-int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len)
+int ewah_read_mmap(struct ewah_bitmap *self, const void *map, size_t len)
 {
-	uint8_t *ptr = map;
+	const uint8_t *ptr = map;
 	size_t i;
 
 	self->bit_size = get_be32(ptr);
diff --git a/ewah/ewok.h b/ewah/ewok.h
index 43adeb5..f6ad190 100644
--- a/ewah/ewok.h
+++ b/ewah/ewok.h
@@ -99,8 +99,7 @@
 int ewah_serialize_native(struct ewah_bitmap *self, int fd);
 
 int ewah_deserialize(struct ewah_bitmap *self, int fd);
-int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len);
-int ewah_read_mmap_native(struct ewah_bitmap *self, void *map, size_t len);
+int ewah_read_mmap(struct ewah_bitmap *self, const void *map, size_t len);
 
 uint32_t ewah_checksum(struct ewah_bitmap *self);
 
diff --git a/fast-import.c b/fast-import.c
index fa635f7..d73f58c 100644
--- a/fast-import.c
+++ b/fast-import.c
@@ -2324,7 +2324,7 @@
 	}
 
 	/* Git does not track empty, non-toplevel directories. */
-	if (S_ISDIR(mode) && !memcmp(sha1, EMPTY_TREE_SHA1_BIN, 20) && *p) {
+	if (S_ISDIR(mode) && !hashcmp(sha1, EMPTY_TREE_SHA1_BIN) && *p) {
 		tree_content_remove(&b->branch_tree, p, NULL, 0);
 		return;
 	}
diff --git a/fsck.c b/fsck.c
index a4e8593..56156ff 100644
--- a/fsck.c
+++ b/fsck.c
@@ -281,7 +281,7 @@
 {
 	unsigned char tree_sha1[20], sha1[20];
 	struct commit_graft *graft;
-	int parents = 0;
+	unsigned parent_count, parent_line_count = 0;
 	int err;
 
 	if (!skip_prefix(buffer, "tree ", &buffer))
@@ -293,27 +293,17 @@
 		if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n')
 			return error_func(&commit->object, FSCK_ERROR, "invalid 'parent' line format - bad sha1");
 		buffer += 41;
-		parents++;
+		parent_line_count++;
 	}
 	graft = lookup_commit_graft(commit->object.sha1);
+	parent_count = commit_list_count(commit->parents);
 	if (graft) {
-		struct commit_list *p = commit->parents;
-		parents = 0;
-		while (p) {
-			p = p->next;
-			parents++;
-		}
-		if (graft->nr_parent == -1 && !parents)
+		if (graft->nr_parent == -1 && !parent_count)
 			; /* shallow commit */
-		else if (graft->nr_parent != parents)
+		else if (graft->nr_parent != parent_count)
 			return error_func(&commit->object, FSCK_ERROR, "graft objects missing");
 	} else {
-		struct commit_list *p = commit->parents;
-		while (p && parents) {
-			p = p->next;
-			parents--;
-		}
-		if (p || parents)
+		if (parent_count != parent_line_count)
 			return error_func(&commit->object, FSCK_ERROR, "parent objects missing");
 	}
 	if (!skip_prefix(buffer, "author ", &buffer))
diff --git a/git-compat-util.h b/git-compat-util.h
index 9de3180..26e92f1 100644
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -291,10 +291,12 @@
 #else
 #define NORETURN
 #define NORETURN_PTR
+#ifndef __GNUC__
 #ifndef __attribute__
 #define __attribute__(x)
 #endif
 #endif
+#endif
 
 /* The sentinel attribute is valid from gcc version 4.0 */
 #if defined(__GNUC__) && (__GNUC__ >= 4)
@@ -347,7 +349,6 @@
 extern void set_die_is_recursing_routine(int (*routine)(void));
 
 extern int starts_with(const char *str, const char *prefix);
-extern int ends_with(const char *str, const char *suffix);
 
 /*
  * If the string "str" begins with the string found in "prefix", return 1.
@@ -377,6 +378,39 @@
 	return 0;
 }
 
+/*
+ * If buf ends with suffix, return 1 and subtract the length of the suffix
+ * from *len. Otherwise, return 0 and leave *len untouched.
+ */
+static inline int strip_suffix_mem(const char *buf, size_t *len,
+				   const char *suffix)
+{
+	size_t suflen = strlen(suffix);
+	if (*len < suflen || memcmp(buf + (*len - suflen), suffix, suflen))
+		return 0;
+	*len -= suflen;
+	return 1;
+}
+
+/*
+ * If str ends with suffix, return 1 and set *len to the size of the string
+ * without the suffix. Otherwise, return 0 and set *len to the size of the
+ * string.
+ *
+ * Note that we do _not_ NUL-terminate str to the new length.
+ */
+static inline int strip_suffix(const char *str, const char *suffix, size_t *len)
+{
+	*len = strlen(str);
+	return strip_suffix_mem(str, len, suffix);
+}
+
+static inline int ends_with(const char *str, const char *suffix)
+{
+	size_t len;
+	return strip_suffix(str, suffix, &len);
+}
+
 #if defined(NO_MMAP) || defined(USE_WIN32_MMAP)
 
 #ifndef PROT_READ
@@ -581,13 +615,6 @@
 	return (size_t)len;
 }
 
-static inline int has_extension(const char *filename, const char *ext)
-{
-	size_t len = strlen(filename);
-	size_t extlen = strlen(ext);
-	return len > extlen && !memcmp(filename + len - extlen, ext, extlen);
-}
-
 /* in ctype.c, for kwset users */
 extern const char tolower_trans_tbl[256];
 
@@ -734,6 +761,10 @@
 #endif
 #endif
 
+#if defined(__GNUC__) || (_MSC_VER >= 1400)
+#define HAVE_VARIADIC_MACROS 1
+#endif
+
 /*
  * Preserves errno, prints a message, but gives no warning for ENOENT.
  * Always returns the return value of unlink(2).
diff --git a/git-filter-branch.sh b/git-filter-branch.sh
index 86d6994..e6e99f5 100755
--- a/git-filter-branch.sh
+++ b/git-filter-branch.sh
@@ -332,7 +332,13 @@
 	parentstr=
 	for parent in $parents; do
 		for reparent in $(map "$parent"); do
-			parentstr="$parentstr -p $reparent"
+			case "$parentstr " in
+			*" -p $reparent "*)
+				;;
+			*)
+				parentstr="$parentstr -p $reparent"
+				;;
+			esac
 		done
 	done
 	if [ "$filter_parent" ]; then
diff --git a/git.c b/git.c
index 5b6c761..9c49519 100644
--- a/git.c
+++ b/git.c
@@ -613,6 +613,8 @@
 
 	git_setup_gettext();
 
+	trace_command_performance(argv);
+
 	/*
 	 * "git-xxxx" is the same as "git xxxx", but we obviously:
 	 *
diff --git a/hashmap.c b/hashmap.c
index d1b8056..f693839 100644
--- a/hashmap.c
+++ b/hashmap.c
@@ -226,3 +226,41 @@
 		current = iter->map->table[iter->tablepos++];
 	}
 }
+
+struct pool_entry {
+	struct hashmap_entry ent;
+	size_t len;
+	unsigned char data[FLEX_ARRAY];
+};
+
+static int pool_entry_cmp(const struct pool_entry *e1,
+			  const struct pool_entry *e2,
+			  const unsigned char *keydata)
+{
+	return e1->data != keydata &&
+	       (e1->len != e2->len || memcmp(e1->data, keydata, e1->len));
+}
+
+const void *memintern(const void *data, size_t len)
+{
+	static struct hashmap map;
+	struct pool_entry key, *e;
+
+	/* initialize string pool hashmap */
+	if (!map.tablesize)
+		hashmap_init(&map, (hashmap_cmp_fn) pool_entry_cmp, 0);
+
+	/* lookup interned string in pool */
+	hashmap_entry_init(&key, memhash(data, len));
+	key.len = len;
+	e = hashmap_get(&map, &key, data);
+	if (!e) {
+		/* not found: create it */
+		e = xmallocz(sizeof(struct pool_entry) + len);
+		hashmap_entry_init(e, key.ent.hash);
+		e->len = len;
+		memcpy(e->data, data, len);
+		hashmap_add(&map, e);
+	}
+	return e->data;
+}
diff --git a/hashmap.h b/hashmap.h
index a816ad4..ab7958a 100644
--- a/hashmap.h
+++ b/hashmap.h
@@ -13,6 +13,17 @@
 extern unsigned int memhash(const void *buf, size_t len);
 extern unsigned int memihash(const void *buf, size_t len);
 
+static inline unsigned int sha1hash(const unsigned char *sha1)
+{
+	/*
+	 * Equivalent to 'return *(unsigned int *)sha1;', but safe on
+	 * platforms that don't support unaligned reads.
+	 */
+	unsigned int hash;
+	memcpy(&hash, sha1, sizeof(hash));
+	return hash;
+}
+
 /* data structures */
 
 struct hashmap_entry {
@@ -57,6 +68,14 @@
 extern void *hashmap_remove(struct hashmap *map, const void *key,
 		const void *keydata);
 
+static inline void *hashmap_get_from_hash(const struct hashmap *map,
+		unsigned int hash, const void *keydata)
+{
+	struct hashmap_entry key;
+	hashmap_entry_init(&key, hash);
+	return hashmap_get(map, &key, keydata);
+}
+
 /* hashmap_iter functions */
 
 extern void hashmap_iter_init(struct hashmap *map, struct hashmap_iter *iter);
@@ -68,4 +87,12 @@
 	return hashmap_iter_next(iter);
 }
 
+/* string interning */
+
+extern const void *memintern(const void *data, size_t len);
+static inline const char *strintern(const char *string)
+{
+	return memintern(string, strlen(string));
+}
+
 #endif
diff --git a/help.c b/help.c
index f31f29a..7af65e2 100644
--- a/help.c
+++ b/help.c
@@ -144,7 +144,7 @@
 
 	while ((de = readdir(dir)) != NULL) {
 		const char *ent;
-		int entlen;
+		size_t entlen;
 
 		if (!skip_prefix(de->d_name, prefix, &ent))
 			continue;
@@ -155,8 +155,7 @@
 			continue;
 
 		entlen = strlen(ent);
-		if (has_extension(ent, ".exe"))
-			entlen -= 4;
+		strip_suffix(ent, ".exe", &entlen);
 
 		add_cmdname(cmds, ent, entlen);
 	}
diff --git a/http-backend.c b/http-backend.c
index 57290d9..80790bb 100644
--- a/http-backend.c
+++ b/http-backend.c
@@ -610,9 +610,7 @@
 
 			cmd = c;
 			n = out[0].rm_eo - out[0].rm_so;
-			cmd_arg = xmalloc(n);
-			memcpy(cmd_arg, dir + out[0].rm_so + 1, n-1);
-			cmd_arg[n-1] = '\0';
+			cmd_arg = xmemdupz(dir + out[0].rm_so + 1, n - 1);
 			dir[out[0].rm_so] = 0;
 			break;
 		}
diff --git a/http-push.c b/http-push.c
index 6c3cc17..952f8ed 100644
--- a/http-push.c
+++ b/http-push.c
@@ -199,7 +199,7 @@
 	curl_easy_setopt(curl, CURLOPT_READFUNCTION, fread_buffer);
 #ifndef NO_CURL_IOCTL
 	curl_easy_setopt(curl, CURLOPT_IOCTLFUNCTION, ioctl_buffer);
-	curl_easy_setopt(curl, CURLOPT_IOCTLDATA, &buffer);
+	curl_easy_setopt(curl, CURLOPT_IOCTLDATA, buffer);
 #endif
 	curl_easy_setopt(curl, CURLOPT_WRITEFUNCTION, write_fn);
 	curl_easy_setopt(curl, CURLOPT_NOBODY, 0);
diff --git a/khash.h b/khash.h
index 57ff603..06c7906 100644
--- a/khash.h
+++ b/khash.h
@@ -320,19 +320,12 @@
 		code;												\
 	} }
 
-static inline khint_t __kh_oid_hash(const unsigned char *oid)
-{
-	khint_t hash;
-	memcpy(&hash, oid, sizeof(hash));
-	return hash;
-}
-
 #define __kh_oid_cmp(a, b) (hashcmp(a, b) == 0)
 
-KHASH_INIT(sha1, const unsigned char *, void *, 1, __kh_oid_hash, __kh_oid_cmp)
+KHASH_INIT(sha1, const unsigned char *, void *, 1, sha1hash, __kh_oid_cmp)
 typedef kh_sha1_t khash_sha1;
 
-KHASH_INIT(sha1_pos, const unsigned char *, int, 1, __kh_oid_hash, __kh_oid_cmp)
+KHASH_INIT(sha1_pos, const unsigned char *, int, 1, sha1hash, __kh_oid_cmp)
 typedef kh_sha1_pos_t khash_sha1_pos;
 
 #endif /* __AC_KHASH_H */
diff --git a/line-log.c b/line-log.c
index afcc98d..1008e72 100644
--- a/line-log.c
+++ b/line-log.c
@@ -766,17 +766,6 @@
 	}
 }
 
-static int count_parents(struct commit *commit)
-{
-	struct commit_list *parents = commit->parents;
-	int count = 0;
-	while (parents) {
-		count++;
-		parents = parents->next;
-	}
-	return count;
-}
-
 static void move_diff_queue(struct diff_queue_struct *dst,
 			    struct diff_queue_struct *src)
 {
@@ -1150,7 +1139,7 @@
 	struct commit **parents;
 	struct commit_list *p;
 	int i;
-	int nparents = count_parents(commit);
+	int nparents = commit_list_count(commit->parents);
 
 	diffqueues = xmalloc(nparents * sizeof(*diffqueues));
 	cand = xmalloc(nparents * sizeof(*cand));
diff --git a/lockfile.c b/lockfile.c
index 8fbcb6a..2564a7f 100644
--- a/lockfile.c
+++ b/lockfile.c
@@ -5,7 +5,6 @@
 #include "sigchain.h"
 
 static struct lock_file *lock_file_list;
-static const char *alternate_index_output;
 
 static void remove_lock_file(void)
 {
@@ -121,7 +120,7 @@
 	return p;
 }
 
-
+/* Make sure errno contains a meaningful value on error */
 static int lock_file(struct lock_file *lk, const char *path, int flags)
 {
 	/*
@@ -130,8 +129,10 @@
 	 */
 	static const size_t max_path_len = sizeof(lk->filename) - 5;
 
-	if (strlen(path) >= max_path_len)
+	if (strlen(path) >= max_path_len) {
+		errno = ENAMETOOLONG;
 		return -1;
+	}
 	strcpy(lk->filename, path);
 	if (!(flags & LOCK_NODEREF))
 		resolve_symlink(lk->filename, max_path_len);
@@ -148,44 +149,51 @@
 			lock_file_list = lk;
 			lk->on_list = 1;
 		}
-		if (adjust_shared_perm(lk->filename))
-			return error("cannot fix permission bits on %s",
-				     lk->filename);
+		if (adjust_shared_perm(lk->filename)) {
+			int save_errno = errno;
+			error("cannot fix permission bits on %s",
+			      lk->filename);
+			errno = save_errno;
+			return -1;
+		}
 	}
 	else
 		lk->filename[0] = 0;
 	return lk->fd;
 }
 
-static char *unable_to_lock_message(const char *path, int err)
+void unable_to_lock_message(const char *path, int err, struct strbuf *buf)
 {
-	struct strbuf buf = STRBUF_INIT;
-
 	if (err == EEXIST) {
-		strbuf_addf(&buf, "Unable to create '%s.lock': %s.\n\n"
+		strbuf_addf(buf, "Unable to create '%s.lock': %s.\n\n"
 		    "If no other git process is currently running, this probably means a\n"
 		    "git process crashed in this repository earlier. Make sure no other git\n"
 		    "process is running and remove the file manually to continue.",
 			    absolute_path(path), strerror(err));
 	} else
-		strbuf_addf(&buf, "Unable to create '%s.lock': %s",
+		strbuf_addf(buf, "Unable to create '%s.lock': %s",
 			    absolute_path(path), strerror(err));
-	return strbuf_detach(&buf, NULL);
 }
 
 int unable_to_lock_error(const char *path, int err)
 {
-	char *msg = unable_to_lock_message(path, err);
-	error("%s", msg);
-	free(msg);
+	struct strbuf buf = STRBUF_INIT;
+
+	unable_to_lock_message(path, err, &buf);
+	error("%s", buf.buf);
+	strbuf_release(&buf);
 	return -1;
 }
 
 NORETURN void unable_to_lock_index_die(const char *path, int err)
 {
-	die("%s", unable_to_lock_message(path, err));
+	struct strbuf buf = STRBUF_INIT;
+
+	unable_to_lock_message(path, err, &buf);
+	die("%s", buf.buf);
 }
 
+/* This should return a meaningful errno on failure */
 int hold_lock_file_for_update(struct lock_file *lk, const char *path, int flags)
 {
 	int fd = lock_file(lk, path, flags);
@@ -252,25 +260,6 @@
 					 : 0);
 }
 
-void set_alternate_index_output(const char *name)
-{
-	alternate_index_output = name;
-}
-
-int commit_locked_index(struct lock_file *lk)
-{
-	if (alternate_index_output) {
-		if (lk->fd >= 0 && close_lock_file(lk))
-			return -1;
-		if (rename(lk->filename, alternate_index_output))
-			return -1;
-		lk->filename[0] = 0;
-		return 0;
-	}
-	else
-		return commit_lock_file(lk);
-}
-
 void rollback_lock_file(struct lock_file *lk)
 {
 	if (lk->filename[0]) {
diff --git a/log-tree.c b/log-tree.c
index 10e6844..0c53dc1 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -365,6 +365,7 @@
 		eol = strchrnul(bol, '\n');
 		printf("%s%.*s%s%s", color, (int)(eol - bol), bol, reset,
 		       *eol ? "\n" : "");
+		graph_show_oneline(opt->graph);
 		bol = (*eol) ? (eol + 1) : eol;
 	}
 }
@@ -413,10 +414,11 @@
 		&& !commit->parents->next->next);
 }
 
-static void show_one_mergetag(struct rev_info *opt,
+static void show_one_mergetag(struct commit *commit,
 			      struct commit_extra_header *extra,
-			      struct commit *commit)
+			      void *data)
 {
+	struct rev_info *opt = (struct rev_info *)data;
 	unsigned char sha1[20];
 	struct tag *tag;
 	struct strbuf verify_message;
@@ -446,16 +448,17 @@
 
 	payload_size = parse_signature(extra->value, extra->len);
 	status = -1;
-	if (extra->len > payload_size)
-		if (verify_signed_buffer(extra->value, payload_size,
-					 extra->value + payload_size,
-					 extra->len - payload_size,
-					 &verify_message, NULL)) {
-			if (verify_message.len <= gpg_message_offset)
-				strbuf_addstr(&verify_message, "No signature\n");
-			else
-				status = 0;
-		}
+	if (extra->len > payload_size) {
+		/* could have a good signature */
+		if (!verify_signed_buffer(extra->value, payload_size,
+					  extra->value + payload_size,
+					  extra->len - payload_size,
+					  &verify_message, NULL))
+			status = 0; /* good */
+		else if (verify_message.len <= gpg_message_offset)
+			strbuf_addstr(&verify_message, "No signature\n");
+		/* otherwise we couldn't verify, which is shown as bad */
+	}
 
 	show_sig_lines(opt, status, verify_message.buf);
 	strbuf_release(&verify_message);
@@ -463,15 +466,7 @@
 
 static void show_mergetag(struct rev_info *opt, struct commit *commit)
 {
-	struct commit_extra_header *extra, *to_free;
-
-	to_free = read_commit_extra_headers(commit, NULL);
-	for (extra = to_free; extra; extra = extra->next) {
-		if (strcmp(extra->key, "mergetag"))
-			continue; /* not a merge tag */
-		show_one_mergetag(opt, extra, commit);
-	}
-	free_commit_extra_headers(to_free);
+	for_each_mergetag(show_one_mergetag, commit, opt);
 }
 
 void show_log(struct rev_info *opt)
diff --git a/merge-recursive.c b/merge-recursive.c
index b5c3c53..1d332b8 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -171,7 +171,7 @@
 	strbuf_vaddf(&o->obuf, fmt, ap);
 	va_end(ap);
 
-	strbuf_add(&o->obuf, "\n", 1);
+	strbuf_addch(&o->obuf, '\n');
 	if (!o->buffer_output)
 		flush_output(o);
 }
@@ -267,9 +267,7 @@
 		active_cache_tree = cache_tree();
 
 	if (!cache_tree_fully_valid(active_cache_tree) &&
-	    cache_tree_update(active_cache_tree,
-			      (const struct cache_entry * const *)active_cache,
-			      active_nr, 0) < 0)
+	    cache_tree_update(&the_index, 0) < 0)
 		die(_("error building trees"));
 
 	result = lookup_tree(active_cache_tree->sha1);
@@ -2001,7 +1999,7 @@
 			    const unsigned char **base_list,
 			    struct commit **result)
 {
-	int clean, index_fd;
+	int clean;
 	struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
 	struct commit *head_commit = get_ref(head, o->branch1);
 	struct commit *next_commit = get_ref(merge, o->branch2);
@@ -2018,12 +2016,11 @@
 		}
 	}
 
-	index_fd = hold_locked_index(lock, 1);
+	hold_locked_index(lock, 1);
 	clean = merge_recursive(o, head_commit, next_commit, ca,
 			result);
 	if (active_cache_changed &&
-			(write_cache(index_fd, active_cache, active_nr) ||
-			 commit_locked_index(lock)))
+	    write_locked_index(&the_index, lock, COMMIT_LOCK))
 		return error(_("Unable to write index."));
 
 	return clean ? 0 : 1;
@@ -2062,12 +2059,9 @@
 	if (o->verbosity >= 5)
 		o->buffer_output = 0;
 	strbuf_init(&o->obuf, 0);
-	memset(&o->current_file_set, 0, sizeof(struct string_list));
-	o->current_file_set.strdup_strings = 1;
-	memset(&o->current_directory_set, 0, sizeof(struct string_list));
-	o->current_directory_set.strdup_strings = 1;
-	memset(&o->df_conflict_file_set, 0, sizeof(struct string_list));
-	o->df_conflict_file_set.strdup_strings = 1;
+	string_list_init(&o->current_file_set, 1);
+	string_list_init(&o->current_directory_set, 1);
+	string_list_init(&o->df_conflict_file_set, 1);
 }
 
 int parse_merge_opt(struct merge_options *o, const char *s)
diff --git a/merge.c b/merge.c
index 1fa6e52..74ced7f 100644
--- a/merge.c
+++ b/merge.c
@@ -50,13 +50,13 @@
 	struct tree *trees[MAX_UNPACK_TREES];
 	struct unpack_trees_options opts;
 	struct tree_desc t[MAX_UNPACK_TREES];
-	int i, fd, nr_trees = 0;
+	int i, nr_trees = 0;
 	struct dir_struct dir;
 	struct lock_file *lock_file = xcalloc(1, sizeof(struct lock_file));
 
 	refresh_cache(REFRESH_QUIET);
 
-	fd = hold_locked_index(lock_file, 1);
+	hold_locked_index(lock_file, 1);
 
 	memset(&trees, 0, sizeof(trees));
 	memset(&opts, 0, sizeof(opts));
@@ -89,8 +89,7 @@
 	}
 	if (unpack_trees(nr_trees, t, &opts))
 		return -1;
-	if (write_cache(fd, active_cache, active_nr) ||
-		commit_locked_index(lock_file))
+	if (write_locked_index(&the_index, lock_file, COMMIT_LOCK))
 		die(_("unable to write new index file"));
 	return 0;
 }
diff --git a/name-hash.c b/name-hash.c
index 49fd508..702cd05 100644
--- a/name-hash.c
+++ b/name-hash.c
@@ -213,12 +213,11 @@
 struct cache_entry *index_file_exists(struct index_state *istate, const char *name, int namelen, int icase)
 {
 	struct cache_entry *ce;
-	struct hashmap_entry key;
 
 	lazy_init_name_hash(istate);
 
-	hashmap_entry_init(&key, memihash(name, namelen));
-	ce = hashmap_get(&istate->name_hash, &key, NULL);
+	ce = hashmap_get_from_hash(&istate->name_hash,
+				   memihash(name, namelen), NULL);
 	while (ce) {
 		if (same_name(ce, name, namelen, icase))
 			return ce;
diff --git a/object.c b/object.c
index 9c31e9a..a16b9f9 100644
--- a/object.c
+++ b/object.c
@@ -50,18 +50,7 @@
  */
 static unsigned int hash_obj(const unsigned char *sha1, unsigned int n)
 {
-	unsigned int hash;
-
-	/*
-	 * Since the sha1 is essentially random, we just take the
-	 * required number of bits directly from the first
-	 * sizeof(unsigned int) bytes of sha1.  First we have to copy
-	 * the bytes into a properly aligned integer.  If we cared
-	 * about getting consistent results across architectures, we
-	 * would have to call ntohl() here, too.
-	 */
-	memcpy(&hash, sha1, sizeof(unsigned int));
-	return hash & (n - 1);
+	return sha1hash(sha1) & (n - 1);
 }
 
 /*
@@ -141,13 +130,12 @@
 	obj_hash_size = new_hash_size;
 }
 
-void *create_object(const unsigned char *sha1, int type, void *o)
+void *create_object(const unsigned char *sha1, void *o)
 {
 	struct object *obj = o;
 
 	obj->parsed = 0;
 	obj->used = 0;
-	obj->type = type;
 	obj->flags = 0;
 	hashcpy(obj->sha1, sha1);
 
@@ -159,11 +147,30 @@
 	return obj;
 }
 
+void *object_as_type(struct object *obj, enum object_type type, int quiet)
+{
+	if (obj->type == type)
+		return obj;
+	else if (obj->type == OBJ_NONE) {
+		if (type == OBJ_COMMIT)
+			((struct commit *)obj)->index = alloc_commit_index();
+		obj->type = type;
+		return obj;
+	}
+	else {
+		if (!quiet)
+			error("object %s is a %s, not a %s",
+			      sha1_to_hex(obj->sha1),
+			      typename(obj->type), typename(type));
+		return NULL;
+	}
+}
+
 struct object *lookup_unknown_object(const unsigned char *sha1)
 {
 	struct object *obj = lookup_object(sha1);
 	if (!obj)
-		obj = create_object(sha1, OBJ_NONE, alloc_object_node());
+		obj = create_object(sha1, alloc_object_node());
 	return obj;
 }
 
@@ -214,8 +221,6 @@
 		warning("object %s has unknown type id %d", sha1_to_hex(sha1), type);
 		obj = NULL;
 	}
-	if (obj && obj->type == OBJ_NONE)
-		obj->type = type;
 	return obj;
 }
 
diff --git a/object.h b/object.h
index 6e12f2c..5e8d8ee 100644
--- a/object.h
+++ b/object.h
@@ -79,7 +79,9 @@
  */
 struct object *lookup_object(const unsigned char *sha1);
 
-extern void *create_object(const unsigned char *sha1, int type, void *obj);
+extern void *create_object(const unsigned char *sha1, void *obj);
+
+void *object_as_type(struct object *obj, enum object_type type, int quiet);
 
 /*
  * Returns the object, having parsed it to find out what it is.
diff --git a/pack-objects.c b/pack-objects.c
index 4f36c32..9992f3e 100644
--- a/pack-objects.c
+++ b/pack-objects.c
@@ -7,10 +7,9 @@
 					 const unsigned char *sha1,
 					 int *found)
 {
-	uint32_t i, hash, mask = (pdata->index_size - 1);
+	uint32_t i, mask = (pdata->index_size - 1);
 
-	memcpy(&hash, sha1, sizeof(uint32_t));
-	i = hash & mask;
+	i = sha1hash(sha1) & mask;
 
 	while (pdata->index[i] > 0) {
 		uint32_t pos = pdata->index[i] - 1;
diff --git a/path.c b/path.c
index bc804a3..3afcdb4 100644
--- a/path.c
+++ b/path.c
@@ -249,9 +249,7 @@
 static struct passwd *getpw_str(const char *username, size_t len)
 {
 	struct passwd *pw;
-	char *username_z = xmalloc(len + 1);
-	memcpy(username_z, username, len);
-	username_z[len] = '\0';
+	char *username_z = xmemdupz(username, len);
 	pw = getpwnam(username_z);
 	free(username_z);
 	return pw;
@@ -277,16 +275,16 @@
 			const char *home = getenv("HOME");
 			if (!home)
 				goto return_null;
-			strbuf_add(&user_path, home, strlen(home));
+			strbuf_addstr(&user_path, home);
 		} else {
 			struct passwd *pw = getpw_str(username, username_len);
 			if (!pw)
 				goto return_null;
-			strbuf_add(&user_path, pw->pw_dir, strlen(pw->pw_dir));
+			strbuf_addstr(&user_path, pw->pw_dir);
 		}
 		to_copy = first_slash;
 	}
-	strbuf_add(&user_path, to_copy, strlen(to_copy));
+	strbuf_addstr(&user_path, to_copy);
 	return strbuf_detach(&user_path, NULL);
 return_null:
 	strbuf_release(&user_path);
diff --git a/pathspec.c b/pathspec.c
index 8043099..9304ee3 100644
--- a/pathspec.c
+++ b/pathspec.c
@@ -338,7 +338,7 @@
 		if (!(magic & m->bit))
 			continue;
 		if (sb.len)
-			strbuf_addstr(&sb, " ");
+			strbuf_addch(&sb, ' ');
 		if (short_magic & m->bit)
 			strbuf_addf(&sb, "'%c'", m->mnemonic);
 		else
@@ -389,8 +389,7 @@
 		if (!(flags & PATHSPEC_PREFER_CWD))
 			die("BUG: PATHSPEC_PREFER_CWD requires arguments");
 
-		pathspec->items = item = xmalloc(sizeof(*item));
-		memset(item, 0, sizeof(*item));
+		pathspec->items = item = xcalloc(1, sizeof(*item));
 		item->match = prefix;
 		item->original = prefix;
 		item->nowildcard_len = item->len = strlen(prefix);
diff --git a/pkt-line.c b/pkt-line.c
index bc63b3b..8bc89b1 100644
--- a/pkt-line.c
+++ b/pkt-line.c
@@ -3,7 +3,7 @@
 
 char packet_buffer[LARGE_PACKET_MAX];
 static const char *packet_trace_prefix = "git";
-static const char trace_key[] = "GIT_TRACE_PACKET";
+static struct trace_key trace_packet = TRACE_KEY_INIT(PACKET);
 
 void packet_trace_identity(const char *prog)
 {
@@ -15,7 +15,7 @@
 	int i;
 	struct strbuf out;
 
-	if (!trace_want(trace_key))
+	if (!trace_want(&trace_packet))
 		return;
 
 	/* +32 is just a guess for header + quoting */
@@ -27,7 +27,7 @@
 	if ((len >= 4 && starts_with(buf, "PACK")) ||
 	    (len >= 5 && starts_with(buf+1, "PACK"))) {
 		strbuf_addstr(&out, "PACK ...");
-		unsetenv(trace_key);
+		trace_disable(&trace_packet);
 	}
 	else {
 		/* XXX we should really handle printable utf8 */
@@ -43,7 +43,7 @@
 	}
 
 	strbuf_addch(&out, '\n');
-	trace_strbuf(trace_key, &out);
+	trace_strbuf(&trace_packet, &out);
 	strbuf_release(&out);
 }
 
diff --git a/preload-index.c b/preload-index.c
index 79ce8a9..c1fe3a3 100644
--- a/preload-index.c
+++ b/preload-index.c
@@ -63,7 +63,7 @@
 			continue;
 		ce_mark_uptodate(ce);
 	} while (--nr > 0);
-	cache_def_free(&cache);
+	cache_def_clear(&cache);
 	return NULL;
 }
 
diff --git a/pretty.c b/pretty.c
index 14357e2..3a1da6f 100644
--- a/pretty.c
+++ b/pretty.c
@@ -1376,7 +1376,7 @@
 		case trunc_none:
 			break;
 		}
-		strbuf_addstr(sb, local_sb.buf);
+		strbuf_addbuf(sb, &local_sb);
 	} else {
 		int sb_len = sb->len, offset = 0;
 		if (c->flush_type == flush_left)
@@ -1554,12 +1554,7 @@
 		}
 
 		if (!parents_shown) {
-			struct commit_list *parent;
-			int num;
-			for (parent = commit->parents, num = 0;
-			     parent;
-			     parent = parent->next, num++)
-				;
+			unsigned num = commit_list_count(commit->parents);
 			/* with enough slop */
 			strbuf_grow(sb, num * 50 + 20);
 			add_merge_info(pp, sb, commit);
diff --git a/prio-queue.c b/prio-queue.c
index c9f8c6d..e4365b0 100644
--- a/prio-queue.c
+++ b/prio-queue.c
@@ -1,18 +1,30 @@
 #include "cache.h"
-#include "commit.h"
 #include "prio-queue.h"
 
+static inline int compare(struct prio_queue *queue, int i, int j)
+{
+	int cmp = queue->compare(queue->array[i].data, queue->array[j].data,
+				 queue->cb_data);
+	if (!cmp)
+		cmp = queue->array[i].ctr - queue->array[j].ctr;
+	return cmp;
+}
+
+static inline void swap(struct prio_queue *queue, int i, int j)
+{
+	struct prio_queue_entry tmp = queue->array[i];
+	queue->array[i] = queue->array[j];
+	queue->array[j] = tmp;
+}
+
 void prio_queue_reverse(struct prio_queue *queue)
 {
 	int i, j;
 
 	if (queue->compare != NULL)
 		die("BUG: prio_queue_reverse() on non-LIFO queue");
-	for (i = 0; i <= (j = (queue->nr - 1) - i); i++) {
-		struct commit *swap = queue->array[i];
-		queue->array[i] = queue->array[j];
-		queue->array[j] = swap;
-	}
+	for (i = 0; i <= (j = (queue->nr - 1) - i); i++)
+		swap(queue, i, j);
 }
 
 void clear_prio_queue(struct prio_queue *queue)
@@ -21,44 +33,42 @@
 	queue->nr = 0;
 	queue->alloc = 0;
 	queue->array = NULL;
+	queue->insertion_ctr = 0;
 }
 
 void prio_queue_put(struct prio_queue *queue, void *thing)
 {
-	prio_queue_compare_fn compare = queue->compare;
 	int ix, parent;
 
 	/* Append at the end */
 	ALLOC_GROW(queue->array, queue->nr + 1, queue->alloc);
-	queue->array[queue->nr++] = thing;
-	if (!compare)
+	queue->array[queue->nr].ctr = queue->insertion_ctr++;
+	queue->array[queue->nr].data = thing;
+	queue->nr++;
+	if (!queue->compare)
 		return; /* LIFO */
 
 	/* Bubble up the new one */
 	for (ix = queue->nr - 1; ix; ix = parent) {
 		parent = (ix - 1) / 2;
-		if (compare(queue->array[parent], queue->array[ix],
-			    queue->cb_data) <= 0)
+		if (compare(queue, parent, ix) <= 0)
 			break;
 
-		thing = queue->array[parent];
-		queue->array[parent] = queue->array[ix];
-		queue->array[ix] = thing;
+		swap(queue, parent, ix);
 	}
 }
 
 void *prio_queue_get(struct prio_queue *queue)
 {
-	void *result, *swap;
+	void *result;
 	int ix, child;
-	prio_queue_compare_fn compare = queue->compare;
 
 	if (!queue->nr)
 		return NULL;
-	if (!compare)
-		return queue->array[--queue->nr]; /* LIFO */
+	if (!queue->compare)
+		return queue->array[--queue->nr].data; /* LIFO */
 
-	result = queue->array[0];
+	result = queue->array[0].data;
 	if (!--queue->nr)
 		return result;
 
@@ -67,18 +77,14 @@
 	/* Push down the one at the root */
 	for (ix = 0; ix * 2 + 1 < queue->nr; ix = child) {
 		child = ix * 2 + 1; /* left */
-		if ((child + 1 < queue->nr) &&
-		    (compare(queue->array[child], queue->array[child + 1],
-			     queue->cb_data) >= 0))
+		if (child + 1 < queue->nr &&
+		    compare(queue, child, child + 1) >= 0)
 			child++; /* use right child */
 
-		if (compare(queue->array[ix], queue->array[child],
-			    queue->cb_data) <= 0)
+		if (compare(queue, ix, child) <= 0)
 			break;
 
-		swap = queue->array[child];
-		queue->array[child] = queue->array[ix];
-		queue->array[ix] = swap;
+		swap(queue, child, ix);
 	}
 	return result;
 }
diff --git a/prio-queue.h b/prio-queue.h
index 9c3cd1f..d030ec9 100644
--- a/prio-queue.h
+++ b/prio-queue.h
@@ -21,11 +21,17 @@
  */
 typedef int (*prio_queue_compare_fn)(const void *one, const void *two, void *cb_data);
 
+struct prio_queue_entry {
+	unsigned ctr;
+	void *data;
+};
+
 struct prio_queue {
 	prio_queue_compare_fn compare;
+	unsigned insertion_ctr;
 	void *cb_data;
 	int alloc, nr;
-	void **array;
+	struct prio_queue_entry *array;
 };
 
 /*
diff --git a/progress.c b/progress.c
index 261314e..412e6b1 100644
--- a/progress.c
+++ b/progress.c
@@ -12,13 +12,14 @@
 #include "gettext.h"
 #include "progress.h"
 #include "strbuf.h"
+#include "trace.h"
 
 #define TP_IDX_MAX      8
 
 struct throughput {
 	off_t curr_total;
 	off_t prev_total;
-	struct timeval prev_tv;
+	uint64_t prev_ns;
 	unsigned int avg_bytes;
 	unsigned int avg_misecs;
 	unsigned int last_bytes[TP_IDX_MAX];
@@ -127,65 +128,65 @@
 void display_throughput(struct progress *progress, off_t total)
 {
 	struct throughput *tp;
-	struct timeval tv;
-	unsigned int misecs;
+	uint64_t now_ns;
+	unsigned int misecs, count, rate;
+	struct strbuf buf = STRBUF_INIT;
 
 	if (!progress)
 		return;
 	tp = progress->throughput;
 
-	gettimeofday(&tv, NULL);
+	now_ns = getnanotime();
 
 	if (!tp) {
 		progress->throughput = tp = calloc(1, sizeof(*tp));
 		if (tp) {
 			tp->prev_total = tp->curr_total = total;
-			tp->prev_tv = tv;
+			tp->prev_ns = now_ns;
 		}
 		return;
 	}
 	tp->curr_total = total;
 
+	/* only update throughput every 0.5 s */
+	if (now_ns - tp->prev_ns <= 500000000)
+		return;
+
 	/*
-	 * We have x = bytes and y = microsecs.  We want z = KiB/s:
+	 * We have x = bytes and y = nanosecs.  We want z = KiB/s:
 	 *
-	 *	z = (x / 1024) / (y / 1000000)
-	 *	z = x / y * 1000000 / 1024
-	 *	z = x / (y * 1024 / 1000000)
+	 *	z = (x / 1024) / (y / 1000000000)
+	 *	z = x / y * 1000000000 / 1024
+	 *	z = x / (y * 1024 / 1000000000)
 	 *	z = x / y'
 	 *
 	 * To simplify things we'll keep track of misecs, or 1024th of a sec
 	 * obtained with:
 	 *
-	 *	y' = y * 1024 / 1000000
-	 *	y' = y / (1000000 / 1024)
-	 *	y' = y / 977
+	 *	y' = y * 1024 / 1000000000
+	 *	y' = y * (2^10 / 2^42) * (2^42 / 1000000000)
+	 *	y' = y / 2^32 * 4398
+	 *	y' = (y * 4398) >> 32
 	 */
-	misecs = (tv.tv_sec - tp->prev_tv.tv_sec) * 1024;
-	misecs += (int)(tv.tv_usec - tp->prev_tv.tv_usec) / 977;
+	misecs = ((now_ns - tp->prev_ns) * 4398) >> 32;
 
-	if (misecs > 512) {
-		struct strbuf buf = STRBUF_INIT;
-		unsigned int count, rate;
+	count = total - tp->prev_total;
+	tp->prev_total = total;
+	tp->prev_ns = now_ns;
+	tp->avg_bytes += count;
+	tp->avg_misecs += misecs;
+	rate = tp->avg_bytes / tp->avg_misecs;
+	tp->avg_bytes -= tp->last_bytes[tp->idx];
+	tp->avg_misecs -= tp->last_misecs[tp->idx];
+	tp->last_bytes[tp->idx] = count;
+	tp->last_misecs[tp->idx] = misecs;
+	tp->idx = (tp->idx + 1) % TP_IDX_MAX;
 
-		count = total - tp->prev_total;
-		tp->prev_total = total;
-		tp->prev_tv = tv;
-		tp->avg_bytes += count;
-		tp->avg_misecs += misecs;
-		rate = tp->avg_bytes / tp->avg_misecs;
-		tp->avg_bytes -= tp->last_bytes[tp->idx];
-		tp->avg_misecs -= tp->last_misecs[tp->idx];
-		tp->last_bytes[tp->idx] = count;
-		tp->last_misecs[tp->idx] = misecs;
-		tp->idx = (tp->idx + 1) % TP_IDX_MAX;
-
-		throughput_string(&buf, total, rate);
-		strncpy(tp->display, buf.buf, sizeof(tp->display));
-		strbuf_release(&buf);
-		if (progress->last_value != -1 && progress_update)
-			display(progress, progress->last_value, NULL);
-	}
+	throughput_string(&buf, total, rate);
+	strncpy(tp->display, buf.buf, sizeof(tp->display));
+	strbuf_release(&buf);
+	if (progress->last_value != -1 && progress_update)
+		display(progress, progress->last_value, NULL);
 }
 
 int display_progress(struct progress *progress, unsigned n)
diff --git a/read-cache.c b/read-cache.c
index 6a45966..5d3c8bd 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -14,6 +14,8 @@
 #include "resolve-undo.h"
 #include "strbuf.h"
 #include "varint.h"
+#include "split-index.h"
+#include "sigchain.h"
 
 static struct cache_entry *refresh_cache_entry(struct cache_entry *ce,
 					       unsigned int options);
@@ -34,8 +36,15 @@
 #define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
 #define CACHE_EXT_TREE 0x54524545	/* "TREE" */
 #define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */
+#define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */
+
+/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
+#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
+		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
+		 SPLIT_INDEX_ORDERED)
 
 struct index_state the_index;
+static const char *alternate_index_output;
 
 static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
 {
@@ -47,10 +56,12 @@
 {
 	struct cache_entry *old = istate->cache[nr];
 
+	replace_index_entry_in_base(istate, old, ce);
 	remove_name_hash(istate, old);
 	free(old);
 	set_index_entry(istate, nr, ce);
-	istate->cache_changed = 1;
+	ce->ce_flags |= CE_UPDATE_IN_BASE;
+	istate->cache_changed |= CE_ENTRY_CHANGED;
 }
 
 void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
@@ -62,9 +73,10 @@
 	copy_cache_entry(new, old);
 	new->ce_flags &= ~CE_HASHED;
 	new->ce_namelen = namelen;
+	new->index = 0;
 	memcpy(new->name, new_name, namelen + 1);
 
-	cache_tree_invalidate_path(istate->cache_tree, old->name);
+	cache_tree_invalidate_path(istate, old->name);
 	remove_index_entry_at(istate, nr);
 	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
 }
@@ -483,8 +495,8 @@
 
 	record_resolve_undo(istate, ce);
 	remove_name_hash(istate, ce);
-	free(ce);
-	istate->cache_changed = 1;
+	save_or_free_index_entry(istate, ce);
+	istate->cache_changed |= CE_ENTRY_REMOVED;
 	istate->cache_nr--;
 	if (pos >= istate->cache_nr)
 		return 0;
@@ -507,12 +519,14 @@
 	for (i = j = 0; i < istate->cache_nr; i++) {
 		if (ce_array[i]->ce_flags & CE_REMOVE) {
 			remove_name_hash(istate, ce_array[i]);
-			free(ce_array[i]);
+			save_or_free_index_entry(istate, ce_array[i]);
 		}
 		else
 			ce_array[j++] = ce_array[i];
 	}
-	istate->cache_changed = 1;
+	if (j == istate->cache_nr)
+		return;
+	istate->cache_changed |= CE_ENTRY_REMOVED;
 	istate->cache_nr = j;
 }
 
@@ -521,7 +535,7 @@
 	int pos = index_name_pos(istate, path, strlen(path));
 	if (pos < 0)
 		pos = -pos-1;
-	cache_tree_invalidate_path(istate->cache_tree, path);
+	cache_tree_invalidate_path(istate, path);
 	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
 		remove_index_entry_at(istate, pos);
 	return 0;
@@ -570,7 +584,9 @@
  * So we use the CE_ADDED flag to verify that the alias was an old
  * one before we accept it as
  */
-static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_entry *alias)
+static struct cache_entry *create_alias_ce(struct index_state *istate,
+					   struct cache_entry *ce,
+					   struct cache_entry *alias)
 {
 	int len;
 	struct cache_entry *new;
@@ -583,7 +599,7 @@
 	new = xcalloc(1, cache_entry_size(len));
 	memcpy(new->name, alias->name, len);
 	copy_cache_entry(new, ce);
-	free(ce);
+	save_or_free_index_entry(istate, ce);
 	return new;
 }
 
@@ -676,7 +692,7 @@
 		set_object_name_for_intent_to_add_entry(ce);
 
 	if (ignore_case && alias && different_name(ce, alias))
-		ce = create_alias_ce(ce, alias);
+		ce = create_alias_ce(istate, ce, alias);
 	ce->ce_flags |= CE_ADDED;
 
 	/* It was suspected to be racily clean, but it turns out to be Ok */
@@ -939,7 +955,8 @@
 	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
 	int new_only = option & ADD_CACHE_NEW_ONLY;
 
-	cache_tree_invalidate_path(istate->cache_tree, ce->name);
+	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
+		cache_tree_invalidate_path(istate, ce->name);
 	pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
 
 	/* existing match? Just replace it. */
@@ -1002,7 +1019,7 @@
 			istate->cache + pos,
 			(istate->cache_nr - pos - 1) * sizeof(ce));
 	set_index_entry(istate, pos, ce);
-	istate->cache_changed = 1;
+	istate->cache_changed |= CE_ENTRY_ADDED;
 	return 0;
 }
 
@@ -1101,6 +1118,7 @@
 	    !(ce->ce_flags & CE_VALID))
 		updated->ce_flags &= ~CE_VALID;
 
+	/* istate->cache_changed is updated in the caller */
 	return updated;
 }
 
@@ -1182,7 +1200,8 @@
 				 * means the index is not valid anymore.
 				 */
 				ce->ce_flags &= ~CE_VALID;
-				istate->cache_changed = 1;
+				ce->ce_flags |= CE_UPDATE_IN_BASE;
+				istate->cache_changed |= CE_ENTRY_CHANGED;
 			}
 			if (quiet)
 				continue;
@@ -1334,6 +1353,10 @@
 	case CACHE_EXT_RESOLVE_UNDO:
 		istate->resolve_undo = resolve_undo_read(data, sz);
 		break;
+	case CACHE_EXT_LINK:
+		if (read_link_extension(istate, data, sz))
+			return -1;
+		break;
 	default:
 		if (*ext < 'A' || 'Z' < *ext)
 			return error("index uses %.4s extension, which we do not understand",
@@ -1368,6 +1391,7 @@
 	ce->ce_stat_data.sd_size  = get_be32(&ondisk->size);
 	ce->ce_flags = flags & ~CE_NAMEMASK;
 	ce->ce_namelen = len;
+	ce->index = 0;
 	hashcpy(ce->sha1, ondisk->sha1);
 	memcpy(ce->name, name, len);
 	ce->name[len] = '\0';
@@ -1442,7 +1466,7 @@
 }
 
 /* remember to discard_cache() before reading a different cache! */
-int read_index_from(struct index_state *istate, const char *path)
+int do_read_index(struct index_state *istate, const char *path, int must_exist)
 {
 	int fd, i;
 	struct stat st;
@@ -1459,9 +1483,9 @@
 	istate->timestamp.nsec = 0;
 	fd = open(path, O_RDONLY);
 	if (fd < 0) {
-		if (errno == ENOENT)
+		if (!must_exist && errno == ENOENT)
 			return 0;
-		die_errno("index file open failed");
+		die_errno("%s: index file open failed", path);
 	}
 
 	if (fstat(fd, &st))
@@ -1480,7 +1504,7 @@
 	if (verify_hdr(hdr, mmap_size) < 0)
 		goto unmap;
 
-	hashcpy(istate->sha1, (unsigned char *)hdr + mmap_size - 20);
+	hashcpy(istate->sha1, (const unsigned char *)hdr + mmap_size - 20);
 	istate->version = ntohl(hdr->hdr_version);
 	istate->cache_nr = ntohl(hdr->hdr_entries);
 	istate->cache_alloc = alloc_nr(istate->cache_nr);
@@ -1534,6 +1558,40 @@
 	die("index file corrupt");
 }
 
+int read_index_from(struct index_state *istate, const char *path)
+{
+	struct split_index *split_index;
+	int ret;
+
+	/* istate->initialized covers both .git/index and .git/sharedindex.xxx */
+	if (istate->initialized)
+		return istate->cache_nr;
+
+	ret = do_read_index(istate, path, 0);
+	split_index = istate->split_index;
+	if (!split_index)
+		return ret;
+
+	if (is_null_sha1(split_index->base_sha1))
+		return ret;
+
+	if (split_index->base)
+		discard_index(split_index->base);
+	else
+		split_index->base = xcalloc(1, sizeof(*split_index->base));
+	ret = do_read_index(split_index->base,
+			    git_path("sharedindex.%s",
+				     sha1_to_hex(split_index->base_sha1)), 1);
+	if (hashcmp(split_index->base_sha1, split_index->base->sha1))
+		die("broken index, expect %s in %s, got %s",
+		    sha1_to_hex(split_index->base_sha1),
+		    git_path("sharedindex.%s",
+				     sha1_to_hex(split_index->base_sha1)),
+		    sha1_to_hex(split_index->base->sha1));
+	merge_base_index(istate);
+	return ret;
+}
+
 int is_index_unborn(struct index_state *istate)
 {
 	return (!istate->cache_nr && !istate->timestamp.sec);
@@ -1543,8 +1601,15 @@
 {
 	int i;
 
-	for (i = 0; i < istate->cache_nr; i++)
+	for (i = 0; i < istate->cache_nr; i++) {
+		if (istate->cache[i]->index &&
+		    istate->split_index &&
+		    istate->split_index->base &&
+		    istate->cache[i]->index <= istate->split_index->base->cache_nr &&
+		    istate->cache[i] == istate->split_index->base->cache[istate->cache[i]->index - 1])
+			continue;
 		free(istate->cache[i]);
+	}
 	resolve_undo_clear_index(istate);
 	istate->cache_nr = 0;
 	istate->cache_changed = 0;
@@ -1556,6 +1621,7 @@
 	free(istate->cache);
 	istate->cache = NULL;
 	istate->cache_alloc = 0;
+	discard_split_index(istate);
 	return 0;
 }
 
@@ -1616,7 +1682,7 @@
 		(ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0;
 }
 
-static int ce_flush(git_SHA_CTX *context, int fd)
+static int ce_flush(git_SHA_CTX *context, int fd, unsigned char *sha1)
 {
 	unsigned int left = write_buffer_len;
 
@@ -1634,6 +1700,7 @@
 
 	/* Append the SHA1 signature at the end */
 	git_SHA1_Final(write_buffer + left, context);
+	hashcpy(sha1, write_buffer + left);
 	left += 20;
 	return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0;
 }
@@ -1705,7 +1772,7 @@
 	ondisk->size = htonl(ce->ce_stat_data.sd_size);
 	hashcpy(ondisk->sha1, ce->sha1);
 
-	flags = ce->ce_flags;
+	flags = ce->ce_flags & ~CE_NAMEMASK;
 	flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce));
 	ondisk->flags = htons(flags);
 	if (ce->ce_flags & CE_EXTENDED) {
@@ -1724,9 +1791,15 @@
 {
 	int size;
 	struct ondisk_cache_entry *ondisk;
+	int saved_namelen = saved_namelen; /* compiler workaround */
 	char *name;
 	int result;
 
+	if (ce->ce_flags & CE_STRIP_NAME) {
+		saved_namelen = ce_namelen(ce);
+		ce->ce_namelen = 0;
+	}
+
 	if (!previous_name) {
 		size = ondisk_ce_size(ce);
 		ondisk = xcalloc(1, size);
@@ -1758,6 +1831,10 @@
 		strbuf_splice(previous_name, common, to_remove,
 			      ce->name + common, ce_namelen(ce) - common);
 	}
+	if (ce->ce_flags & CE_STRIP_NAME) {
+		ce->ce_namelen = saved_namelen;
+		ce->ce_flags &= ~CE_STRIP_NAME;
+	}
 
 	result = ce_write(c, fd, ondisk, size);
 	free(ondisk);
@@ -1827,13 +1904,13 @@
 void update_index_if_able(struct index_state *istate, struct lock_file *lockfile)
 {
 	if ((istate->cache_changed || has_racy_timestamp(istate)) &&
-	    verify_index(istate) && !write_index(istate, lockfile->fd))
-		commit_locked_index(lockfile);
-	else
+	    verify_index(istate) &&
+	    write_locked_index(istate, lockfile, COMMIT_LOCK))
 		rollback_lock_file(lockfile);
 }
 
-int write_index(struct index_state *istate, int newfd)
+static int do_write_index(struct index_state *istate, int newfd,
+			  int strip_extensions)
 {
 	git_SHA_CTX c;
 	struct cache_header hdr;
@@ -1855,8 +1932,11 @@
 		}
 	}
 
-	if (!istate->version)
+	if (!istate->version) {
 		istate->version = get_index_format_default();
+		if (getenv("GIT_TEST_SPLIT_INDEX"))
+			init_split_index(istate);
+	}
 
 	/* demote version 3 to version 2 when the latter suffices */
 	if (istate->version == 3 || istate->version == 2)
@@ -1896,7 +1976,18 @@
 	strbuf_release(&previous_name_buf);
 
 	/* Write extension data here */
-	if (istate->cache_tree) {
+	if (!strip_extensions && istate->split_index) {
+		struct strbuf sb = STRBUF_INIT;
+
+		err = write_link_extension(&sb, istate) < 0 ||
+			write_index_ext_header(&c, newfd, CACHE_EXT_LINK,
+					       sb.len) < 0 ||
+			ce_write(&c, newfd, sb.buf, sb.len) < 0;
+		strbuf_release(&sb);
+		if (err)
+			return -1;
+	}
+	if (!strip_extensions && istate->cache_tree) {
 		struct strbuf sb = STRBUF_INIT;
 
 		cache_tree_write(&sb, istate->cache_tree);
@@ -1906,7 +1997,7 @@
 		if (err)
 			return -1;
 	}
-	if (istate->resolve_undo) {
+	if (!strip_extensions && istate->resolve_undo) {
 		struct strbuf sb = STRBUF_INIT;
 
 		resolve_undo_write(&sb, istate->resolve_undo);
@@ -1918,13 +2009,138 @@
 			return -1;
 	}
 
-	if (ce_flush(&c, newfd) || fstat(newfd, &st))
+	if (ce_flush(&c, newfd, istate->sha1) || fstat(newfd, &st))
 		return -1;
 	istate->timestamp.sec = (unsigned int)st.st_mtime;
 	istate->timestamp.nsec = ST_MTIME_NSEC(st);
 	return 0;
 }
 
+void set_alternate_index_output(const char *name)
+{
+	alternate_index_output = name;
+}
+
+static int commit_locked_index(struct lock_file *lk)
+{
+	if (alternate_index_output) {
+		if (lk->fd >= 0 && close_lock_file(lk))
+			return -1;
+		if (rename(lk->filename, alternate_index_output))
+			return -1;
+		lk->filename[0] = 0;
+		return 0;
+	} else {
+		return commit_lock_file(lk);
+	}
+}
+
+static int do_write_locked_index(struct index_state *istate, struct lock_file *lock,
+				 unsigned flags)
+{
+	int ret = do_write_index(istate, lock->fd, 0);
+	if (ret)
+		return ret;
+	assert((flags & (COMMIT_LOCK | CLOSE_LOCK)) !=
+	       (COMMIT_LOCK | CLOSE_LOCK));
+	if (flags & COMMIT_LOCK)
+		return commit_locked_index(lock);
+	else if (flags & CLOSE_LOCK)
+		return close_lock_file(lock);
+	else
+		return ret;
+}
+
+static int write_split_index(struct index_state *istate,
+			     struct lock_file *lock,
+			     unsigned flags)
+{
+	int ret;
+	prepare_to_write_split_index(istate);
+	ret = do_write_locked_index(istate, lock, flags);
+	finish_writing_split_index(istate);
+	return ret;
+}
+
+static char *temporary_sharedindex;
+
+static void remove_temporary_sharedindex(void)
+{
+	if (temporary_sharedindex) {
+		unlink_or_warn(temporary_sharedindex);
+		free(temporary_sharedindex);
+		temporary_sharedindex = NULL;
+	}
+}
+
+static void remove_temporary_sharedindex_on_signal(int signo)
+{
+	remove_temporary_sharedindex();
+	sigchain_pop(signo);
+	raise(signo);
+}
+
+static int write_shared_index(struct index_state *istate,
+			      struct lock_file *lock, unsigned flags)
+{
+	struct split_index *si = istate->split_index;
+	static int installed_handler;
+	int fd, ret;
+
+	temporary_sharedindex = git_pathdup("sharedindex_XXXXXX");
+	fd = mkstemp(temporary_sharedindex);
+	if (fd < 0) {
+		free(temporary_sharedindex);
+		temporary_sharedindex = NULL;
+		hashclr(si->base_sha1);
+		return do_write_locked_index(istate, lock, flags);
+	}
+	if (!installed_handler) {
+		atexit(remove_temporary_sharedindex);
+		sigchain_push_common(remove_temporary_sharedindex_on_signal);
+	}
+	move_cache_to_base_index(istate);
+	ret = do_write_index(si->base, fd, 1);
+	close(fd);
+	if (ret) {
+		remove_temporary_sharedindex();
+		return ret;
+	}
+	ret = rename(temporary_sharedindex,
+		     git_path("sharedindex.%s", sha1_to_hex(si->base->sha1)));
+	free(temporary_sharedindex);
+	temporary_sharedindex = NULL;
+	if (!ret)
+		hashcpy(si->base_sha1, si->base->sha1);
+	return ret;
+}
+
+int write_locked_index(struct index_state *istate, struct lock_file *lock,
+		       unsigned flags)
+{
+	struct split_index *si = istate->split_index;
+
+	if (!si || alternate_index_output ||
+	    (istate->cache_changed & ~EXTMASK)) {
+		if (si)
+			hashclr(si->base_sha1);
+		return do_write_locked_index(istate, lock, flags);
+	}
+
+	if (getenv("GIT_TEST_SPLIT_INDEX")) {
+		int v = si->base_sha1[0];
+		if ((v & 15) < 6)
+			istate->cache_changed |= SPLIT_INDEX_ORDERED;
+	}
+	if (istate->cache_changed & SPLIT_INDEX_ORDERED) {
+		int ret = write_shared_index(istate, lock, flags);
+		if (ret)
+			return ret;
+	}
+
+	return write_split_index(istate, lock, flags);
+}
+
 /*
  * Read the index file that is potentially unmerged into given
  * index_state, dropping any unmerged entries.  Returns true if
diff --git a/refs.c b/refs.c
index 82e4842..84b9070 100644
--- a/refs.c
+++ b/refs.c
@@ -1361,7 +1361,7 @@
 
 		if (de->d_name[0] == '.')
 			continue;
-		if (has_extension(de->d_name, ".lock"))
+		if (ends_with(de->d_name, ".lock"))
 			continue;
 		strbuf_addstr(&refname, de->d_name);
 		refdir = *refs->name
@@ -1533,6 +1533,7 @@
 	}
 }
 
+/* This function needs to return a meaningful errno on failure */
 const char *resolve_ref_unsafe(const char *refname, unsigned char *sha1, int reading, int *flag)
 {
 	int depth = MAXDEPTH;
@@ -1543,8 +1544,10 @@
 	if (flag)
 		*flag = 0;
 
-	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL))
+	if (check_refname_format(refname, REFNAME_ALLOW_ONELEVEL)) {
+		errno = EINVAL;
 		return NULL;
+	}
 
 	for (;;) {
 		char path[PATH_MAX];
@@ -1552,8 +1555,10 @@
 		char *buf;
 		int fd;
 
-		if (--depth < 0)
+		if (--depth < 0) {
+			errno = ELOOP;
 			return NULL;
+		}
 
 		git_snpath(path, sizeof(path), "%s", refname);
 
@@ -1615,9 +1620,13 @@
 				return NULL;
 		}
 		len = read_in_full(fd, buffer, sizeof(buffer)-1);
-		close(fd);
-		if (len < 0)
+		if (len < 0) {
+			int save_errno = errno;
+			close(fd);
+			errno = save_errno;
 			return NULL;
+		}
+		close(fd);
 		while (len && isspace(buffer[len-1]))
 			len--;
 		buffer[len] = '\0';
@@ -1634,6 +1643,7 @@
 			    (buffer[40] != '\0' && !isspace(buffer[40]))) {
 				if (flag)
 					*flag |= REF_ISBROKEN;
+				errno = EINVAL;
 				return NULL;
 			}
 			return refname;
@@ -1646,6 +1656,7 @@
 		if (check_refname_format(buf, REFNAME_ALLOW_ONELEVEL)) {
 			if (flag)
 				*flag |= REF_ISBROKEN;
+			errno = EINVAL;
 			return NULL;
 		}
 		refname = strcpy(refname_buffer, buf);
@@ -1730,9 +1741,8 @@
 
 	if (o->type == OBJ_NONE) {
 		int type = sha1_object_info(name, NULL);
-		if (type < 0)
+		if (type < 0 || !object_as_type(o, type, 0))
 			return PEEL_INVALID;
-		o->type = type;
 	}
 
 	if (o->type != OBJ_TAG)
@@ -2131,18 +2141,22 @@
 	return 0;
 }
 
+/* This function should make sure errno is meaningful on error */
 static struct ref_lock *verify_lock(struct ref_lock *lock,
 	const unsigned char *old_sha1, int mustexist)
 {
 	if (read_ref_full(lock->ref_name, lock->old_sha1, mustexist, NULL)) {
+		int save_errno = errno;
 		error("Can't verify ref %s", lock->ref_name);
 		unlock_ref(lock);
+		errno = save_errno;
 		return NULL;
 	}
 	if (hashcmp(lock->old_sha1, old_sha1)) {
 		error("Ref %s is at %s but expected %s", lock->ref_name,
 			sha1_to_hex(lock->old_sha1), sha1_to_hex(old_sha1));
 		unlock_ref(lock);
+		errno = EBUSY;
 		return NULL;
 	}
 	return lock;
@@ -2155,14 +2169,16 @@
 	 * only empty directories), remove them.
 	 */
 	struct strbuf path;
-	int result;
+	int result, save_errno;
 
 	strbuf_init(&path, 20);
 	strbuf_addstr(&path, file);
 
 	result = remove_dir_recursively(&path, REMOVE_DIR_EMPTY_ONLY);
+	save_errno = errno;
 
 	strbuf_release(&path);
+	errno = save_errno;
 
 	return result;
 }
@@ -2251,6 +2267,7 @@
 	return logs_found;
 }
 
+/* This function should make sure errno is meaningful on error */
 static struct ref_lock *lock_ref_sha1_basic(const char *refname,
 					    const unsigned char *old_sha1,
 					    int flags, int *type_p)
@@ -2411,6 +2428,7 @@
 	return 0;
 }
 
+/* This should return a meaningful errno on failure */
 int lock_packed_refs(int flags)
 {
 	struct packed_ref_cache *packed_ref_cache;
@@ -2430,11 +2448,16 @@
 	return 0;
 }
 
+/*
+ * Commit the packed refs changes.
+ * On error we must make sure that errno contains a meaningful value.
+ */
 int commit_packed_refs(void)
 {
 	struct packed_ref_cache *packed_ref_cache =
 		get_packed_ref_cache(&ref_cache);
 	int error = 0;
+	int save_errno = 0;
 
 	if (!packed_ref_cache->lock)
 		die("internal error: packed-refs not locked");
@@ -2444,10 +2467,13 @@
 	do_for_each_entry_in_dir(get_packed_ref_dir(packed_ref_cache),
 				 0, write_packed_entry_fn,
 				 &packed_ref_cache->lock->fd);
-	if (commit_lock_file(packed_ref_cache->lock))
+	if (commit_lock_file(packed_ref_cache->lock)) {
+		save_errno = errno;
 		error = -1;
+	}
 	packed_ref_cache->lock = NULL;
 	release_packed_ref_cache(packed_ref_cache);
+	errno = save_errno;
 	return error;
 }
 
@@ -2654,12 +2680,12 @@
 	return 0;
 }
 
-int repack_without_refs(const char **refnames, int n)
+int repack_without_refs(const char **refnames, int n, struct strbuf *err)
 {
 	struct ref_dir *packed;
 	struct string_list refs_to_delete = STRING_LIST_INIT_DUP;
 	struct string_list_item *ref_to_delete;
-	int i, removed = 0;
+	int i, ret, removed = 0;
 
 	/* Look for a packed ref */
 	for (i = 0; i < n; i++)
@@ -2671,6 +2697,11 @@
 		return 0; /* no refname exists in packed refs */
 
 	if (lock_packed_refs(0)) {
+		if (err) {
+			unable_to_lock_message(git_path("packed-refs"), errno,
+					       err);
+			return -1;
+		}
 		unable_to_lock_error(git_path("packed-refs"), errno);
 		return error("cannot delete '%s' from packed refs", refnames[i]);
 	}
@@ -2697,12 +2728,16 @@
 	}
 
 	/* Write what remains */
-	return commit_packed_refs();
+	ret = commit_packed_refs();
+	if (ret && err)
+		strbuf_addf(err, "unable to overwrite old ref-pack file: %s",
+			    strerror(errno));
+	return ret;
 }
 
 static int repack_without_ref(const char *refname)
 {
-	return repack_without_refs(&refname, 1);
+	return repack_without_refs(&refname, 1, NULL);
 }
 
 static int delete_ref_loose(struct ref_lock *lock, int flag)
@@ -2940,6 +2975,7 @@
 	return cp - buf;
 }
 
+/* This function must set a meaningful errno on failure */
 int log_ref_setup(const char *refname, char *logfile, int bufsize)
 {
 	int logfd, oflags = O_APPEND | O_WRONLY;
@@ -2950,9 +2986,12 @@
 	     starts_with(refname, "refs/remotes/") ||
 	     starts_with(refname, "refs/notes/") ||
 	     !strcmp(refname, "HEAD"))) {
-		if (safe_create_leading_directories(logfile) < 0)
-			return error("unable to create directory for %s",
-				     logfile);
+		if (safe_create_leading_directories(logfile) < 0) {
+			int save_errno = errno;
+			error("unable to create directory for %s", logfile);
+			errno = save_errno;
+			return -1;
+		}
 		oflags |= O_CREAT;
 	}
 
@@ -2963,15 +3002,22 @@
 
 		if ((oflags & O_CREAT) && errno == EISDIR) {
 			if (remove_empty_directories(logfile)) {
-				return error("There are still logs under '%s'",
-					     logfile);
+				int save_errno = errno;
+				error("There are still logs under '%s'",
+				      logfile);
+				errno = save_errno;
+				return -1;
 			}
 			logfd = open(logfile, oflags, 0666);
 		}
 
-		if (logfd < 0)
-			return error("Unable to append to %s: %s",
-				     logfile, strerror(errno));
+		if (logfd < 0) {
+			int save_errno = errno;
+			error("Unable to append to %s: %s", logfile,
+			      strerror(errno));
+			errno = save_errno;
+			return -1;
+		}
 	}
 
 	adjust_shared_perm(logfile);
@@ -3011,24 +3057,38 @@
 		len += copy_msg(logrec + len - 1, msg) - 1;
 	written = len <= maxlen ? write_in_full(logfd, logrec, len) : -1;
 	free(logrec);
-	if (close(logfd) != 0 || written != len)
-		return error("Unable to append to %s", log_file);
+	if (written != len) {
+		int save_errno = errno;
+		close(logfd);
+		error("Unable to append to %s", log_file);
+		errno = save_errno;
+		return -1;
+	}
+	if (close(logfd)) {
+		int save_errno = errno;
+		error("Unable to append to %s", log_file);
+		errno = save_errno;
+		return -1;
+	}
 	return 0;
 }
 
-static int is_branch(const char *refname)
+int is_branch(const char *refname)
 {
 	return !strcmp(refname, "HEAD") || starts_with(refname, "refs/heads/");
 }
 
+/* This function must return a meaningful errno */
 int write_ref_sha1(struct ref_lock *lock,
 	const unsigned char *sha1, const char *logmsg)
 {
 	static char term = '\n';
 	struct object *o;
 
-	if (!lock)
+	if (!lock) {
+		errno = EINVAL;
 		return -1;
+	}
 	if (!lock->force_write && !hashcmp(lock->old_sha1, sha1)) {
 		unlock_ref(lock);
 		return 0;
@@ -3038,19 +3098,23 @@
 		error("Trying to write ref %s with nonexistent object %s",
 			lock->ref_name, sha1_to_hex(sha1));
 		unlock_ref(lock);
+		errno = EINVAL;
 		return -1;
 	}
 	if (o->type != OBJ_COMMIT && is_branch(lock->ref_name)) {
 		error("Trying to write non-commit object %s to branch %s",
 			sha1_to_hex(sha1), lock->ref_name);
 		unlock_ref(lock);
+		errno = EINVAL;
 		return -1;
 	}
 	if (write_in_full(lock->lock_fd, sha1_to_hex(sha1), 40) != 40 ||
-	    write_in_full(lock->lock_fd, &term, 1) != 1
-		|| close_ref(lock) < 0) {
+	    write_in_full(lock->lock_fd, &term, 1) != 1 ||
+	    close_ref(lock) < 0) {
+		int save_errno = errno;
 		error("Couldn't write %s", lock->lk->filename);
 		unlock_ref(lock);
+		errno = save_errno;
 		return -1;
 	}
 	clear_loose_ref_cache(&ref_cache);
@@ -3432,7 +3496,7 @@
 
 		if (de->d_name[0] == '.')
 			continue;
-		if (has_extension(de->d_name, ".lock"))
+		if (ends_with(de->d_name, ".lock"))
 			continue;
 		strbuf_addstr(name, de->d_name);
 		if (stat(git_path("logs/%s", name->buf), &st) < 0) {
@@ -3487,10 +3551,13 @@
 
 static int update_ref_write(const char *action, const char *refname,
 			    const unsigned char *sha1, struct ref_lock *lock,
-			    enum action_on_err onerr)
+			    struct strbuf *err, enum action_on_err onerr)
 {
 	if (write_ref_sha1(lock, sha1, action) < 0) {
 		const char *str = "Cannot update the ref '%s'.";
+		if (err)
+			strbuf_addf(err, str, refname);
+
 		switch (onerr) {
 		case UPDATE_REFS_MSG_ON_ERR: error(str, refname); break;
 		case UPDATE_REFS_DIE_ON_ERR: die(str, refname); break;
@@ -3533,10 +3600,13 @@
 	return xcalloc(1, sizeof(struct ref_transaction));
 }
 
-static void ref_transaction_free(struct ref_transaction *transaction)
+void ref_transaction_free(struct ref_transaction *transaction)
 {
 	int i;
 
+	if (!transaction)
+		return;
+
 	for (i = 0; i < transaction->nr; i++)
 		free(transaction->updates[i]);
 
@@ -3544,11 +3614,6 @@
 	free(transaction);
 }
 
-void ref_transaction_rollback(struct ref_transaction *transaction)
-{
-	ref_transaction_free(transaction);
-}
-
 static struct ref_update *add_update(struct ref_transaction *transaction,
 				     const char *refname)
 {
@@ -3561,23 +3626,30 @@
 	return update;
 }
 
-void ref_transaction_update(struct ref_transaction *transaction,
-			    const char *refname,
-			    unsigned char *new_sha1, unsigned char *old_sha1,
-			    int flags, int have_old)
+int ref_transaction_update(struct ref_transaction *transaction,
+			   const char *refname,
+			   const unsigned char *new_sha1,
+			   const unsigned char *old_sha1,
+			   int flags, int have_old,
+			   struct strbuf *err)
 {
-	struct ref_update *update = add_update(transaction, refname);
+	struct ref_update *update;
 
+	if (have_old && !old_sha1)
+		die("BUG: have_old is true but old_sha1 is NULL");
+
+	update = add_update(transaction, refname);
 	hashcpy(update->new_sha1, new_sha1);
 	update->flags = flags;
 	update->have_old = have_old;
 	if (have_old)
 		hashcpy(update->old_sha1, old_sha1);
+	return 0;
 }
 
 void ref_transaction_create(struct ref_transaction *transaction,
 			    const char *refname,
-			    unsigned char *new_sha1,
+			    const unsigned char *new_sha1,
 			    int flags)
 {
 	struct ref_update *update = add_update(transaction, refname);
@@ -3591,7 +3663,7 @@
 
 void ref_transaction_delete(struct ref_transaction *transaction,
 			    const char *refname,
-			    unsigned char *old_sha1,
+			    const unsigned char *old_sha1,
 			    int flags, int have_old)
 {
 	struct ref_update *update = add_update(transaction, refname);
@@ -3612,7 +3684,7 @@
 	lock = update_ref_lock(refname, oldval, flags, NULL, onerr);
 	if (!lock)
 		return 1;
-	return update_ref_write(action, refname, sha1, lock, onerr);
+	return update_ref_write(action, refname, sha1, lock, NULL, onerr);
 }
 
 static int ref_update_compare(const void *r1, const void *r2)
@@ -3623,28 +3695,23 @@
 }
 
 static int ref_update_reject_duplicates(struct ref_update **updates, int n,
-					enum action_on_err onerr)
+					struct strbuf *err)
 {
 	int i;
 	for (i = 1; i < n; i++)
 		if (!strcmp(updates[i - 1]->refname, updates[i]->refname)) {
 			const char *str =
 				"Multiple updates for ref '%s' not allowed.";
-			switch (onerr) {
-			case UPDATE_REFS_MSG_ON_ERR:
-				error(str, updates[i]->refname); break;
-			case UPDATE_REFS_DIE_ON_ERR:
-				die(str, updates[i]->refname); break;
-			case UPDATE_REFS_QUIET_ON_ERR:
-				break;
-			}
+			if (err)
+				strbuf_addf(err, str, updates[i]->refname);
+
 			return 1;
 		}
 	return 0;
 }
 
 int ref_transaction_commit(struct ref_transaction *transaction,
-			   const char *msg, enum action_on_err onerr)
+			   const char *msg, struct strbuf *err)
 {
 	int ret = 0, delnum = 0, i;
 	const char **delnames;
@@ -3659,7 +3726,7 @@
 
 	/* Copy, sort, and reject duplicate refs */
 	qsort(updates, n, sizeof(*updates), ref_update_compare);
-	ret = ref_update_reject_duplicates(updates, n, onerr);
+	ret = ref_update_reject_duplicates(updates, n, err);
 	if (ret)
 		goto cleanup;
 
@@ -3671,8 +3738,12 @@
 					       (update->have_old ?
 						update->old_sha1 : NULL),
 					       update->flags,
-					       &update->type, onerr);
+					       &update->type,
+					       UPDATE_REFS_QUIET_ON_ERR);
 		if (!update->lock) {
+			if (err)
+				strbuf_addf(err, "Cannot lock the ref '%s'.",
+					    update->refname);
 			ret = 1;
 			goto cleanup;
 		}
@@ -3686,7 +3757,8 @@
 			ret = update_ref_write(msg,
 					       update->refname,
 					       update->new_sha1,
-					       update->lock, onerr);
+					       update->lock, err,
+					       UPDATE_REFS_QUIET_ON_ERR);
 			update->lock = NULL; /* freed by update_ref_write */
 			if (ret)
 				goto cleanup;
@@ -3703,7 +3775,7 @@
 		}
 	}
 
-	ret |= repack_without_refs(delnames, delnum);
+	ret |= repack_without_refs(delnames, delnum, err);
 	for (i = 0; i < delnum; i++)
 		unlink_or_warn(git_path("logs/%s", delnames[i]));
 	clear_loose_ref_cache(&ref_cache);
@@ -3713,7 +3785,6 @@
 		if (updates[i]->lock)
 			unlock_ref(updates[i]->lock);
 	free(delnames);
-	ref_transaction_free(transaction);
 	return ret;
 }
 
diff --git a/refs.h b/refs.h
index 4e3050d..ec46acd 100644
--- a/refs.h
+++ b/refs.h
@@ -82,6 +82,7 @@
 /*
  * Lock the packed-refs file for writing.  Flags is passed to
  * hold_lock_file_for_update().  Return 0 on success.
+ * Errno is set to something meaningful on error.
  */
 extern int lock_packed_refs(int flags);
 
@@ -97,6 +98,7 @@
  * Write the current version of the packed refs cache from memory to
  * disk.  The packed-refs file must already be locked for writing (see
  * lock_packed_refs()).  Return zero on success.
+ * Sets errno to something meaningful on error.
  */
 extern int commit_packed_refs(void);
 
@@ -121,10 +123,13 @@
  */
 int pack_refs(unsigned int flags);
 
-extern int repack_without_refs(const char **refnames, int n);
+extern int repack_without_refs(const char **refnames, int n,
+			       struct strbuf *err);
 
 extern int ref_exists(const char *);
 
+extern int is_branch(const char *refname);
+
 /*
  * If refname is a non-symbolic reference that refers to a tag object,
  * and the tag can be (recursively) dereferenced to a non-tag object,
@@ -135,11 +140,15 @@
  */
 extern int peel_ref(const char *refname, unsigned char *sha1);
 
-/** Locks a "refs/" ref returning the lock on success and NULL on failure. **/
+/*
+ * Locks a "refs/" ref returning the lock on success and NULL on failure.
+ * On failure errno is set to something meaningful.
+ */
 extern struct ref_lock *lock_ref_sha1(const char *refname, const unsigned char *old_sha1);
 
 /** Locks any ref (for 'HEAD' type refs). */
 #define REF_NODEREF	0x01
+/* errno is set to something meaningful on failure */
 extern struct ref_lock *lock_any_ref_for_update(const char *refname,
 						const unsigned char *old_sha1,
 						int flags, int *type_p);
@@ -156,7 +165,9 @@
 /** Writes sha1 into the ref specified by the lock. **/
 extern int write_ref_sha1(struct ref_lock *lock, const unsigned char *sha1, const char *msg);
 
-/** Setup reflog before using. **/
+/*
+ * Setup reflog before using. Set errno to something meaningful on failure.
+ */
 int log_ref_setup(const char *refname, char *logfile, int bufsize);
 
 /** Reads log for the value of ref during at_time. **/
@@ -219,18 +230,11 @@
 
 /*
  * Begin a reference transaction.  The reference transaction must
- * eventually be commited using ref_transaction_commit() or rolled
- * back using ref_transaction_rollback().
+ * be freed by calling ref_transaction_free().
  */
 struct ref_transaction *ref_transaction_begin(void);
 
 /*
- * Roll back a ref_transaction and free all associated data.
- */
-void ref_transaction_rollback(struct ref_transaction *transaction);
-
-
-/*
  * The following functions add a reference check or update to a
  * ref_transaction.  In all of them, refname is the name of the
  * reference to be affected.  The functions make internal copies of
@@ -238,18 +242,22 @@
  * can be REF_NODEREF; it is passed to update_ref_lock().
  */
 
-
 /*
  * Add a reference update to transaction.  new_sha1 is the value that
  * the reference should have after the update, or zeros if it should
  * be deleted.  If have_old is true, then old_sha1 holds the value
  * that the reference should have had before the update, or zeros if
  * it must not have existed beforehand.
+ * Function returns 0 on success and non-zero on failure. A failure to update
+ * means that the transaction as a whole has failed and will need to be
+ * rolled back. On failure the err buffer will be updated.
  */
-void ref_transaction_update(struct ref_transaction *transaction,
-			    const char *refname,
-			    unsigned char *new_sha1, unsigned char *old_sha1,
-			    int flags, int have_old);
+int ref_transaction_update(struct ref_transaction *transaction,
+			   const char *refname,
+			   const unsigned char *new_sha1,
+			   const unsigned char *old_sha1,
+			   int flags, int have_old,
+			   struct strbuf *err);
 
 /*
  * Add a reference creation to transaction.  new_sha1 is the value
@@ -259,7 +267,7 @@
  */
 void ref_transaction_create(struct ref_transaction *transaction,
 			    const char *refname,
-			    unsigned char *new_sha1,
+			    const unsigned char *new_sha1,
 			    int flags);
 
 /*
@@ -269,16 +277,23 @@
  */
 void ref_transaction_delete(struct ref_transaction *transaction,
 			    const char *refname,
-			    unsigned char *old_sha1,
+			    const unsigned char *old_sha1,
 			    int flags, int have_old);
 
 /*
  * Commit all of the changes that have been queued in transaction, as
  * atomically as possible.  Return a nonzero value if there is a
- * problem.  The ref_transaction is freed by this function.
+ * problem.
+ * If err is non-NULL we will add an error string to it to explain why
+ * the transaction failed. The string does not end in newline.
  */
 int ref_transaction_commit(struct ref_transaction *transaction,
-			   const char *msg, enum action_on_err onerr);
+			   const char *msg, struct strbuf *err);
+
+/*
+ * Free an existing transaction and all associated data.
+ */
+void ref_transaction_free(struct ref_transaction *transaction);
 
 /** Lock a ref and then write its file */
 int update_ref(const char *action, const char *refname,
diff --git a/remote-curl.c b/remote-curl.c
index cdcca29..0fcf2ce 100644
--- a/remote-curl.c
+++ b/remote-curl.c
@@ -399,7 +399,7 @@
 			rpc->pos = 0;
 			return CURLIOE_OK;
 		}
-		fprintf(stderr, "Unable to rewind rpc post data - try increasing http.postBuffer\n");
+		error("unable to rewind rpc post data - try increasing http.postBuffer");
 		return CURLIOE_FAILRESTART;
 
 	default:
@@ -709,7 +709,7 @@
 		free(targets[i]);
 	free(targets);
 
-	return ret ? error("Fetch failed.") : 0;
+	return ret ? error("fetch failed.") : 0;
 }
 
 static int fetch_git(struct discovery *heads,
@@ -949,7 +949,7 @@
 	git_extract_argv0_path(argv[0]);
 	setup_git_directory_gently(&nongit);
 	if (argc < 2) {
-		fprintf(stderr, "Remote needed\n");
+		error("remote-curl: usage: git remote-curl <remote> [<url>]");
 		return 1;
 	}
 
@@ -972,16 +972,14 @@
 
 		if (strbuf_getline(&buf, stdin, '\n') == EOF) {
 			if (ferror(stdin))
-				fprintf(stderr, "Error reading command stream\n");
-			else
-				fprintf(stderr, "Unexpected end of command stream\n");
+				error("remote-curl: error reading command stream from git");
 			return 1;
 		}
 		if (buf.len == 0)
 			break;
 		if (starts_with(buf.buf, "fetch ")) {
 			if (nongit)
-				die("Fetch attempted without a local repo");
+				die("remote-curl: fetch attempted without a local repo");
 			parse_fetch(&buf);
 
 		} else if (!strcmp(buf.buf, "list") || starts_with(buf.buf, "list ")) {
@@ -1017,7 +1015,7 @@
 			printf("\n");
 			fflush(stdout);
 		} else {
-			fprintf(stderr, "Unknown command '%s'\n", buf.buf);
+			error("remote-curl: unknown command '%s' from git", buf.buf);
 			return 1;
 		}
 		strbuf_reset(&buf);
diff --git a/remote-testsvn.c b/remote-testsvn.c
index 6be55cb..686e07d 100644
--- a/remote-testsvn.c
+++ b/remote-testsvn.c
@@ -175,8 +175,8 @@
 	char *note_msg;
 	unsigned char head_sha1[20];
 	unsigned int startrev;
-	struct argv_array svndump_argv = ARGV_ARRAY_INIT;
 	struct child_process svndump_proc;
+	const char *command = "svnrdump";
 
 	if (read_ref(private_ref, head_sha1))
 		startrev = 0;
@@ -202,15 +202,14 @@
 	} else {
 		memset(&svndump_proc, 0, sizeof(struct child_process));
 		svndump_proc.out = -1;
-		argv_array_push(&svndump_argv, "svnrdump");
-		argv_array_push(&svndump_argv, "dump");
-		argv_array_push(&svndump_argv, url);
-		argv_array_pushf(&svndump_argv, "-r%u:HEAD", startrev);
-		svndump_proc.argv = svndump_argv.argv;
+		argv_array_push(&svndump_proc.args, command);
+		argv_array_push(&svndump_proc.args, "dump");
+		argv_array_push(&svndump_proc.args, url);
+		argv_array_pushf(&svndump_proc.args, "-r%u:HEAD", startrev);
 
 		code = start_command(&svndump_proc);
 		if (code)
-			die("Unable to start %s, code %d", svndump_proc.argv[0], code);
+			die("Unable to start %s, code %d", command, code);
 		dumpin_fd = svndump_proc.out;
 	}
 	/* setup marks file import/export */
@@ -226,8 +225,7 @@
 	if (!dump_from_file) {
 		code = finish_command(&svndump_proc);
 		if (code)
-			warning("%s, returned %d", svndump_proc.argv[0], code);
-		argv_array_clear(&svndump_argv);
+			warning("%s, returned %d", command, code);
 	}
 
 	return 0;
diff --git a/rerere.c b/rerere.c
index d55aa8a..d84b495 100644
--- a/rerere.c
+++ b/rerere.c
@@ -207,11 +207,11 @@
 			strbuf_reset(&one);
 			strbuf_reset(&two);
 		} else if (hunk == RR_SIDE_1)
-			strbuf_addstr(&one, buf.buf);
+			strbuf_addbuf(&one, &buf);
 		else if (hunk == RR_ORIGINAL)
 			; /* discard */
 		else if (hunk == RR_SIDE_2)
-			strbuf_addstr(&two, buf.buf);
+			strbuf_addbuf(&two, &buf);
 		else
 			rerere_io_putstr(buf.buf, io);
 		continue;
@@ -492,8 +492,7 @@
 	}
 
 	if (!status && active_cache_changed) {
-		if (write_cache(fd, active_cache, active_nr) ||
-		    commit_locked_index(&index_lock))
+		if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
 			die("Unable to write new index file");
 	} else if (fd >= 0)
 		rollback_lock_file(&index_lock);
diff --git a/resolve-undo.c b/resolve-undo.c
index 44c697c..468a2eb 100644
--- a/resolve-undo.c
+++ b/resolve-undo.c
@@ -110,7 +110,7 @@
 	string_list_clear(resolve_undo, 1);
 	free(resolve_undo);
 	istate->resolve_undo = NULL;
-	istate->cache_changed = 1;
+	istate->cache_changed |= RESOLVE_UNDO_CHANGED;
 }
 
 int unmerge_index_entry_at(struct index_state *istate, int pos)
diff --git a/run-command.c b/run-command.c
index be07d4a..576dfea 100644
--- a/run-command.c
+++ b/run-command.c
@@ -770,28 +770,21 @@
 int run_hook_ve(const char *const *env, const char *name, va_list args)
 {
 	struct child_process hook;
-	struct argv_array argv = ARGV_ARRAY_INIT;
 	const char *p;
-	int ret;
 
 	p = find_hook(name);
 	if (!p)
 		return 0;
 
-	argv_array_push(&argv, p);
-
-	while ((p = va_arg(args, const char *)))
-		argv_array_push(&argv, p);
-
 	memset(&hook, 0, sizeof(hook));
-	hook.argv = argv.argv;
+	argv_array_push(&hook.args, p);
+	while ((p = va_arg(args, const char *)))
+		argv_array_push(&hook.args, p);
 	hook.env = env;
 	hook.no_stdin = 1;
 	hook.stdout_to_stderr = 1;
 
-	ret = run_command(&hook);
-	argv_array_clear(&argv);
-	return ret;
+	return run_command(&hook);
 }
 
 int run_hook_le(const char *const *env, const char *name, ...)
diff --git a/sequencer.c b/sequencer.c
index cdd30c0..3c060e0 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -263,11 +263,11 @@
 {
 	struct merge_options o;
 	struct tree *result, *next_tree, *base_tree, *head_tree;
-	int clean, index_fd;
+	int clean;
 	const char **xopt;
 	static struct lock_file index_lock;
 
-	index_fd = hold_locked_index(&index_lock, 1);
+	hold_locked_index(&index_lock, 1);
 
 	read_cache();
 
@@ -288,8 +288,7 @@
 			    next_tree, base_tree, &result);
 
 	if (active_cache_changed &&
-	    (write_cache(index_fd, active_cache, active_nr) ||
-	     commit_locked_index(&index_lock)))
+	    write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
 		/* TRANSLATORS: %s will be "revert" or "cherry-pick" */
 		die(_("%s: Unable to write new index file"), action_name(opts));
 	rollback_lock_file(&index_lock);
@@ -341,9 +340,7 @@
 		active_cache_tree = cache_tree();
 
 	if (!cache_tree_fully_valid(active_cache_tree))
-		if (cache_tree_update(active_cache_tree,
-				      (const struct cache_entry * const *)active_cache,
-				      active_nr, 0))
+		if (cache_tree_update(&the_index, 0))
 			return error(_("Unable to update cache tree\n"));
 
 	return !hashcmp(active_cache_tree->sha1, head_commit->tree->object.sha1);
@@ -643,9 +640,8 @@
 	if (read_index_preload(&the_index, NULL) < 0)
 		die(_("git %s: failed to read the index"), action_name(opts));
 	refresh_index(&the_index, REFRESH_QUIET|REFRESH_UNMERGED, NULL, NULL, NULL);
-	if (the_index.cache_changed) {
-		if (write_index(&the_index, index_fd) ||
-		    commit_locked_index(&index_lock))
+	if (the_index.cache_changed && index_fd >= 0) {
+		if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
 			die(_("git %s: failed to refresh the index"), action_name(opts));
 	}
 	rollback_lock_file(&index_lock);
diff --git a/sh-i18n--envsubst.c b/sh-i18n--envsubst.c
index 855d28c..6dd03a9 100644
--- a/sh-i18n--envsubst.c
+++ b/sh-i18n--envsubst.c
@@ -278,9 +278,7 @@
 static void
 note_variable (const char *var_ptr, size_t var_len)
 {
-  char *string = xmalloc (var_len + 1);
-  memcpy (string, var_ptr, var_len);
-  string[var_len] = '\0';
+  char *string = xmemdupz (var_ptr, var_len);
 
   string_list_append (&variables_set, string);
 }
diff --git a/sha1_file.c b/sha1_file.c
index a38854c..3f70b1d 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -36,9 +36,6 @@
 
 const unsigned char null_sha1[20];
 
-static const char *no_log_pack_access = "no_log_pack_access";
-static const char *log_pack_access;
-
 /*
  * This is meant to hold a *small* number of objects that you would
  * want read_sha1_file() to be able to return, but yet you do not want
@@ -268,9 +265,9 @@
  * SHA1, an extra slash for the first level indirection, and the
  * terminating NUL.
  */
-static int link_alt_odb_entry(const char *entry, const char *relative_base, int depth)
+static int link_alt_odb_entry(const char *entry, const char *relative_base,
+	int depth, const char *normalized_objdir)
 {
-	const char *objdir = get_object_directory();
 	struct alternate_object_database *ent;
 	struct alternate_object_database *alt;
 	int pfxlen, entlen;
@@ -321,7 +318,7 @@
 			return -1;
 		}
 	}
-	if (!strcmp(ent->base, objdir)) {
+	if (!strcmp_icase(ent->base, normalized_objdir)) {
 		free(ent);
 		return -1;
 	}
@@ -345,6 +342,7 @@
 	struct string_list entries = STRING_LIST_INIT_NODUP;
 	char *alt_copy;
 	int i;
+	struct strbuf objdirbuf = STRBUF_INIT;
 
 	if (depth > 5) {
 		error("%s: ignoring alternate object stores, nesting too deep.",
@@ -352,6 +350,9 @@
 		return;
 	}
 
+	strbuf_addstr(&objdirbuf, absolute_path(get_object_directory()));
+	normalize_path_copy(objdirbuf.buf, objdirbuf.buf);
+
 	alt_copy = xmemdupz(alt, len);
 	string_list_split_in_place(&entries, alt_copy, sep, -1);
 	for (i = 0; i < entries.nr; i++) {
@@ -362,11 +363,12 @@
 			error("%s: ignoring relative alternate object store %s",
 					relative_base, entry);
 		} else {
-			link_alt_odb_entry(entry, relative_base, depth);
+			link_alt_odb_entry(entry, relative_base, depth, objdirbuf.buf);
 		}
 	}
 	string_list_clear(&entries, 0);
 	free(alt_copy);
+	strbuf_release(&objdirbuf);
 }
 
 void read_info_alternates(const char * relative_base, int depth)
@@ -1178,48 +1180,42 @@
 
 static void prepare_packed_git_one(char *objdir, int local)
 {
-	/* Ensure that this buffer is large enough so that we can
-	   append "/pack/" without clobbering the stack even if
-	   strlen(objdir) were PATH_MAX.  */
-	char path[PATH_MAX + 1 + 4 + 1 + 1];
-	int len;
+	struct strbuf path = STRBUF_INIT;
+	size_t dirnamelen;
 	DIR *dir;
 	struct dirent *de;
 	struct string_list garbage = STRING_LIST_INIT_DUP;
 
-	sprintf(path, "%s/pack", objdir);
-	len = strlen(path);
-	dir = opendir(path);
+	strbuf_addstr(&path, objdir);
+	strbuf_addstr(&path, "/pack");
+	dir = opendir(path.buf);
 	if (!dir) {
 		if (errno != ENOENT)
 			error("unable to open object pack directory: %s: %s",
-			      path, strerror(errno));
+			      path.buf, strerror(errno));
+		strbuf_release(&path);
 		return;
 	}
-	path[len++] = '/';
+	strbuf_addch(&path, '/');
+	dirnamelen = path.len;
 	while ((de = readdir(dir)) != NULL) {
-		int namelen = strlen(de->d_name);
 		struct packed_git *p;
-
-		if (len + namelen + 1 > sizeof(path)) {
-			if (report_garbage) {
-				struct strbuf sb = STRBUF_INIT;
-				strbuf_addf(&sb, "%.*s/%s", len - 1, path, de->d_name);
-				report_garbage("path too long", sb.buf);
-				strbuf_release(&sb);
-			}
-			continue;
-		}
+		size_t base_len;
 
 		if (is_dot_or_dotdot(de->d_name))
 			continue;
 
-		strcpy(path + len, de->d_name);
+		strbuf_setlen(&path, dirnamelen);
+		strbuf_addstr(&path, de->d_name);
 
-		if (has_extension(de->d_name, ".idx")) {
+		base_len = path.len;
+		if (strip_suffix_mem(path.buf, &base_len, ".idx")) {
 			/* Don't reopen a pack we already have. */
 			for (p = packed_git; p; p = p->next) {
-				if (!memcmp(path, p->pack_name, len + namelen - 4))
+				size_t len;
+				if (strip_suffix(p->pack_name, ".pack", &len) &&
+				    len == base_len &&
+				    !memcmp(p->pack_name, path.buf, len))
 					break;
 			}
 			if (p == NULL &&
@@ -1227,24 +1223,25 @@
 			     * See if it really is a valid .idx file with
 			     * corresponding .pack file that we can map.
 			     */
-			    (p = add_packed_git(path, len + namelen, local)) != NULL)
+			    (p = add_packed_git(path.buf, path.len, local)) != NULL)
 				install_packed_git(p);
 		}
 
 		if (!report_garbage)
 			continue;
 
-		if (has_extension(de->d_name, ".idx") ||
-		    has_extension(de->d_name, ".pack") ||
-		    has_extension(de->d_name, ".bitmap") ||
-		    has_extension(de->d_name, ".keep"))
-			string_list_append(&garbage, path);
+		if (ends_with(de->d_name, ".idx") ||
+		    ends_with(de->d_name, ".pack") ||
+		    ends_with(de->d_name, ".bitmap") ||
+		    ends_with(de->d_name, ".keep"))
+			string_list_append(&garbage, path.buf);
 		else
-			report_garbage("garbage found", path);
+			report_garbage("garbage found", path.buf);
 	}
 	closedir(dir);
 	report_pack_garbage(&garbage);
 	string_list_clear(&garbage, 0);
+	strbuf_release(&path);
 }
 
 static int sort_pack(const void *a_, const void *b_)
@@ -2086,27 +2083,9 @@
 
 static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
 {
-	static FILE *log_file;
-
-	if (!log_pack_access)
-		log_pack_access = getenv("GIT_TRACE_PACK_ACCESS");
-	if (!log_pack_access)
-		log_pack_access = no_log_pack_access;
-	if (log_pack_access == no_log_pack_access)
-		return;
-
-	if (!log_file) {
-		log_file = fopen(log_pack_access, "w");
-		if (!log_file) {
-			error("cannot open pack access log '%s' for writing: %s",
-			      log_pack_access, strerror(errno));
-			log_pack_access = no_log_pack_access;
-			return;
-		}
-	}
-	fprintf(log_file, "%s %"PRIuMAX"\n",
-		p->pack_name, (uintmax_t)obj_offset);
-	fflush(log_file);
+	static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS);
+	trace_printf_key(&pack_access, "%s %"PRIuMAX"\n",
+			 p->pack_name, (uintmax_t)obj_offset);
 }
 
 int do_check_packed_object_crc;
@@ -2131,8 +2110,7 @@
 	int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC;
 	int base_from_cache = 0;
 
-	if (log_pack_access != no_log_pack_access)
-		write_pack_access_log(p, obj_offset);
+	write_pack_access_log(p, obj_offset);
 
 	/* PHASE 1: drill down to the innermost base object */
 	for (;;) {
diff --git a/sha1_name.c b/sha1_name.c
index 5bfa841..6ccd3a5 100644
--- a/sha1_name.c
+++ b/sha1_name.c
@@ -946,7 +946,7 @@
 	retval = 0;
 	if (0 < for_each_reflog_ent_reverse("HEAD", grab_nth_branch_switch, &cb)) {
 		strbuf_reset(buf);
-		strbuf_add(buf, cb.buf.buf, cb.buf.len);
+		strbuf_addbuf(buf, &cb.buf);
 		retval = brace - name + 1;
 	}
 
diff --git a/shallow.c b/shallow.c
index 0b267b6..de07709 100644
--- a/shallow.c
+++ b/shallow.c
@@ -325,7 +325,7 @@
 	strbuf_release(&sb);
 }
 
-#define TRACE_KEY "GIT_TRACE_SHALLOW"
+struct trace_key trace_shallow = TRACE_KEY_INIT(SHALLOW);
 
 /*
  * Step 1, split sender shallow commits into "ours" and "theirs"
@@ -334,7 +334,7 @@
 void prepare_shallow_info(struct shallow_info *info, struct sha1_array *sa)
 {
 	int i;
-	trace_printf_key(TRACE_KEY, "shallow: prepare_shallow_info\n");
+	trace_printf_key(&trace_shallow, "shallow: prepare_shallow_info\n");
 	memset(info, 0, sizeof(*info));
 	info->shallow = sa;
 	if (!sa)
@@ -365,7 +365,7 @@
 {
 	unsigned char (*sha1)[20] = info->shallow->sha1;
 	int i, dst;
-	trace_printf_key(TRACE_KEY, "shallow: remove_nonexistent_theirs_shallow\n");
+	trace_printf_key(&trace_shallow, "shallow: remove_nonexistent_theirs_shallow\n");
 	for (i = dst = 0; i < info->nr_theirs; i++) {
 		if (i != dst)
 			info->theirs[dst] = info->theirs[i];
@@ -516,7 +516,7 @@
 	int *shallow, nr_shallow = 0;
 	struct paint_info pi;
 
-	trace_printf_key(TRACE_KEY, "shallow: assign_shallow_commits_to_refs\n");
+	trace_printf_key(&trace_shallow, "shallow: assign_shallow_commits_to_refs\n");
 	shallow = xmalloc(sizeof(*shallow) * (info->nr_ours + info->nr_theirs));
 	for (i = 0; i < info->nr_ours; i++)
 		shallow[nr_shallow++] = info->ours[i];
@@ -622,7 +622,7 @@
 	int bitmap_nr = (info->ref->nr + 31) / 32;
 	struct commit_array ca;
 
-	trace_printf_key(TRACE_KEY, "shallow: post_assign_shallow\n");
+	trace_printf_key(&trace_shallow, "shallow: post_assign_shallow\n");
 	if (ref_status)
 		memset(ref_status, 0, sizeof(*ref_status) * info->ref->nr);
 
diff --git a/split-index.c b/split-index.c
new file mode 100644
index 0000000..21485e2
--- /dev/null
+++ b/split-index.c
@@ -0,0 +1,328 @@
+#include "cache.h"
+#include "split-index.h"
+#include "ewah/ewok.h"
+
+struct split_index *init_split_index(struct index_state *istate)
+{
+	if (!istate->split_index) {
+		istate->split_index = xcalloc(1, sizeof(*istate->split_index));
+		istate->split_index->refcount = 1;
+	}
+	return istate->split_index;
+}
+
+int read_link_extension(struct index_state *istate,
+			 const void *data_, unsigned long sz)
+{
+	const unsigned char *data = data_;
+	struct split_index *si;
+	int ret;
+
+	if (sz < 20)
+		return error("corrupt link extension (too short)");
+	si = init_split_index(istate);
+	hashcpy(si->base_sha1, data);
+	data += 20;
+	sz -= 20;
+	if (!sz)
+		return 0;
+	si->delete_bitmap = ewah_new();
+	ret = ewah_read_mmap(si->delete_bitmap, data, sz);
+	if (ret < 0)
+		return error("corrupt delete bitmap in link extension");
+	data += ret;
+	sz -= ret;
+	si->replace_bitmap = ewah_new();
+	ret = ewah_read_mmap(si->replace_bitmap, data, sz);
+	if (ret < 0)
+		return error("corrupt replace bitmap in link extension");
+	if (ret != sz)
+		return error("garbage at the end of link extension");
+	return 0;
+}
+
+static int write_strbuf(void *user_data, const void *data, size_t len)
+{
+	struct strbuf *sb = user_data;
+	strbuf_add(sb, data, len);
+	return len;
+}
+
+int write_link_extension(struct strbuf *sb,
+			 struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	strbuf_add(sb, si->base_sha1, 20);
+	if (!si->delete_bitmap && !si->replace_bitmap)
+		return 0;
+	ewah_serialize_to(si->delete_bitmap, write_strbuf, sb);
+	ewah_serialize_to(si->replace_bitmap, write_strbuf, sb);
+	return 0;
+}
+
+static void mark_base_index_entries(struct index_state *base)
+{
+	int i;
+	/*
+	 * To keep track of the shared entries between
+	 * istate->base->cache[] and istate->cache[], base entry
+	 * position is stored in each base entry. All positions start
+	 * from 1 instead of 0, which is resrved to say "this is a new
+	 * entry".
+	 */
+	for (i = 0; i < base->cache_nr; i++)
+		base->cache[i]->index = i + 1;
+}
+
+void move_cache_to_base_index(struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	int i;
+
+	/*
+	 * do not delete old si->base, its index entries may be shared
+	 * with istate->cache[]. Accept a bit of leaking here because
+	 * this code is only used by short-lived update-index.
+	 */
+	si->base = xcalloc(1, sizeof(*si->base));
+	si->base->version = istate->version;
+	/* zero timestamp disables racy test in ce_write_index() */
+	si->base->timestamp = istate->timestamp;
+	ALLOC_GROW(si->base->cache, istate->cache_nr, si->base->cache_alloc);
+	si->base->cache_nr = istate->cache_nr;
+	memcpy(si->base->cache, istate->cache,
+	       sizeof(*istate->cache) * istate->cache_nr);
+	mark_base_index_entries(si->base);
+	for (i = 0; i < si->base->cache_nr; i++)
+		si->base->cache[i]->ce_flags &= ~CE_UPDATE_IN_BASE;
+}
+
+static void mark_entry_for_delete(size_t pos, void *data)
+{
+	struct index_state *istate = data;
+	if (pos >= istate->cache_nr)
+		die("position for delete %d exceeds base index size %d",
+		    (int)pos, istate->cache_nr);
+	istate->cache[pos]->ce_flags |= CE_REMOVE;
+	istate->split_index->nr_deletions = 1;
+}
+
+static void replace_entry(size_t pos, void *data)
+{
+	struct index_state *istate = data;
+	struct split_index *si = istate->split_index;
+	struct cache_entry *dst, *src;
+
+	if (pos >= istate->cache_nr)
+		die("position for replacement %d exceeds base index size %d",
+		    (int)pos, istate->cache_nr);
+	if (si->nr_replacements >= si->saved_cache_nr)
+		die("too many replacements (%d vs %d)",
+		    si->nr_replacements, si->saved_cache_nr);
+	dst = istate->cache[pos];
+	if (dst->ce_flags & CE_REMOVE)
+		die("entry %d is marked as both replaced and deleted",
+		    (int)pos);
+	src = si->saved_cache[si->nr_replacements];
+	if (ce_namelen(src))
+		die("corrupt link extension, entry %d should have "
+		    "zero length name", (int)pos);
+	src->index = pos + 1;
+	src->ce_flags |= CE_UPDATE_IN_BASE;
+	src->ce_namelen = dst->ce_namelen;
+	copy_cache_entry(dst, src);
+	free(src);
+	si->nr_replacements++;
+}
+
+void merge_base_index(struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	unsigned int i;
+
+	mark_base_index_entries(si->base);
+
+	si->saved_cache	    = istate->cache;
+	si->saved_cache_nr  = istate->cache_nr;
+	istate->cache_nr    = si->base->cache_nr;
+	istate->cache	    = NULL;
+	istate->cache_alloc = 0;
+	ALLOC_GROW(istate->cache, istate->cache_nr, istate->cache_alloc);
+	memcpy(istate->cache, si->base->cache,
+	       sizeof(*istate->cache) * istate->cache_nr);
+
+	si->nr_deletions = 0;
+	si->nr_replacements = 0;
+	ewah_each_bit(si->replace_bitmap, replace_entry, istate);
+	ewah_each_bit(si->delete_bitmap, mark_entry_for_delete, istate);
+	if (si->nr_deletions)
+		remove_marked_cache_entries(istate);
+
+	for (i = si->nr_replacements; i < si->saved_cache_nr; i++) {
+		if (!ce_namelen(si->saved_cache[i]))
+			die("corrupt link extension, entry %d should "
+			    "have non-zero length name", i);
+		add_index_entry(istate, si->saved_cache[i],
+				ADD_CACHE_OK_TO_ADD |
+				ADD_CACHE_KEEP_CACHE_TREE |
+				/*
+				 * we may have to replay what
+				 * merge-recursive.c:update_stages()
+				 * does, which has this flag on
+				 */
+				ADD_CACHE_SKIP_DFCHECK);
+		si->saved_cache[i] = NULL;
+	}
+
+	ewah_free(si->delete_bitmap);
+	ewah_free(si->replace_bitmap);
+	free(si->saved_cache);
+	si->delete_bitmap  = NULL;
+	si->replace_bitmap = NULL;
+	si->saved_cache	   = NULL;
+	si->saved_cache_nr = 0;
+}
+
+void prepare_to_write_split_index(struct index_state *istate)
+{
+	struct split_index *si = init_split_index(istate);
+	struct cache_entry **entries = NULL, *ce;
+	int i, nr_entries = 0, nr_alloc = 0;
+
+	si->delete_bitmap = ewah_new();
+	si->replace_bitmap = ewah_new();
+
+	if (si->base) {
+		/* Go through istate->cache[] and mark CE_MATCHED to
+		 * entry with positive index. We'll go through
+		 * base->cache[] later to delete all entries in base
+		 * that are not marked eith either CE_MATCHED or
+		 * CE_UPDATE_IN_BASE. If istate->cache[i] is a
+		 * duplicate, deduplicate it.
+		 */
+		for (i = 0; i < istate->cache_nr; i++) {
+			struct cache_entry *base;
+			/* namelen is checked separately */
+			const unsigned int ondisk_flags =
+				CE_STAGEMASK | CE_VALID | CE_EXTENDED_FLAGS;
+			unsigned int ce_flags, base_flags, ret;
+			ce = istate->cache[i];
+			if (!ce->index)
+				continue;
+			if (ce->index > si->base->cache_nr) {
+				ce->index = 0;
+				continue;
+			}
+			ce->ce_flags |= CE_MATCHED; /* or "shared" */
+			base = si->base->cache[ce->index - 1];
+			if (ce == base)
+				continue;
+			if (ce->ce_namelen != base->ce_namelen ||
+			    strcmp(ce->name, base->name)) {
+				ce->index = 0;
+				continue;
+			}
+			ce_flags = ce->ce_flags;
+			base_flags = base->ce_flags;
+			/* only on-disk flags matter */
+			ce->ce_flags   &= ondisk_flags;
+			base->ce_flags &= ondisk_flags;
+			ret = memcmp(&ce->ce_stat_data, &base->ce_stat_data,
+				     offsetof(struct cache_entry, name) -
+				     offsetof(struct cache_entry, ce_stat_data));
+			ce->ce_flags = ce_flags;
+			base->ce_flags = base_flags;
+			if (ret)
+				ce->ce_flags |= CE_UPDATE_IN_BASE;
+			free(base);
+			si->base->cache[ce->index - 1] = ce;
+		}
+		for (i = 0; i < si->base->cache_nr; i++) {
+			ce = si->base->cache[i];
+			if ((ce->ce_flags & CE_REMOVE) ||
+			    !(ce->ce_flags & CE_MATCHED))
+				ewah_set(si->delete_bitmap, i);
+			else if (ce->ce_flags & CE_UPDATE_IN_BASE) {
+				ewah_set(si->replace_bitmap, i);
+				ce->ce_flags |= CE_STRIP_NAME;
+				ALLOC_GROW(entries, nr_entries+1, nr_alloc);
+				entries[nr_entries++] = ce;
+			}
+		}
+	}
+
+	for (i = 0; i < istate->cache_nr; i++) {
+		ce = istate->cache[i];
+		if ((!si->base || !ce->index) && !(ce->ce_flags & CE_REMOVE)) {
+			assert(!(ce->ce_flags & CE_STRIP_NAME));
+			ALLOC_GROW(entries, nr_entries+1, nr_alloc);
+			entries[nr_entries++] = ce;
+		}
+		ce->ce_flags &= ~CE_MATCHED;
+	}
+
+	/*
+	 * take cache[] out temporarily, put entries[] in its place
+	 * for writing
+	 */
+	si->saved_cache = istate->cache;
+	si->saved_cache_nr = istate->cache_nr;
+	istate->cache = entries;
+	istate->cache_nr = nr_entries;
+}
+
+void finish_writing_split_index(struct index_state *istate)
+{
+	struct split_index *si = init_split_index(istate);
+
+	ewah_free(si->delete_bitmap);
+	ewah_free(si->replace_bitmap);
+	si->delete_bitmap = NULL;
+	si->replace_bitmap = NULL;
+	free(istate->cache);
+	istate->cache = si->saved_cache;
+	istate->cache_nr = si->saved_cache_nr;
+}
+
+void discard_split_index(struct index_state *istate)
+{
+	struct split_index *si = istate->split_index;
+	if (!si)
+		return;
+	istate->split_index = NULL;
+	si->refcount--;
+	if (si->refcount)
+		return;
+	if (si->base) {
+		discard_index(si->base);
+		free(si->base);
+	}
+	free(si);
+}
+
+void save_or_free_index_entry(struct index_state *istate, struct cache_entry *ce)
+{
+	if (ce->index &&
+	    istate->split_index &&
+	    istate->split_index->base &&
+	    ce->index <= istate->split_index->base->cache_nr &&
+	    ce == istate->split_index->base->cache[ce->index - 1])
+		ce->ce_flags |= CE_REMOVE;
+	else
+		free(ce);
+}
+
+void replace_index_entry_in_base(struct index_state *istate,
+				 struct cache_entry *old,
+				 struct cache_entry *new)
+{
+	if (old->index &&
+	    istate->split_index &&
+	    istate->split_index->base &&
+	    old->index <= istate->split_index->base->cache_nr) {
+		new->index = old->index;
+		if (old != istate->split_index->base->cache[new->index - 1])
+			free(istate->split_index->base->cache[new->index - 1]);
+		istate->split_index->base->cache[new->index - 1] = new;
+	}
+}
diff --git a/split-index.h b/split-index.h
new file mode 100644
index 0000000..c1324f5
--- /dev/null
+++ b/split-index.h
@@ -0,0 +1,35 @@
+#ifndef SPLIT_INDEX_H
+#define SPLIT_INDEX_H
+
+struct index_state;
+struct strbuf;
+struct ewah_bitmap;
+
+struct split_index {
+	unsigned char base_sha1[20];
+	struct index_state *base;
+	struct ewah_bitmap *delete_bitmap;
+	struct ewah_bitmap *replace_bitmap;
+	struct cache_entry **saved_cache;
+	unsigned int saved_cache_nr;
+	unsigned int nr_deletions;
+	unsigned int nr_replacements;
+	int refcount;
+};
+
+struct split_index *init_split_index(struct index_state *istate);
+void save_or_free_index_entry(struct index_state *istate, struct cache_entry *ce);
+void replace_index_entry_in_base(struct index_state *istate,
+				 struct cache_entry *old,
+				 struct cache_entry *new);
+int read_link_extension(struct index_state *istate,
+			const void *data, unsigned long sz);
+int write_link_extension(struct strbuf *sb,
+			 struct index_state *istate);
+void move_cache_to_base_index(struct index_state *istate);
+void merge_base_index(struct index_state *istate);
+void prepare_to_write_split_index(struct index_state *istate);
+void finish_writing_split_index(struct index_state *istate);
+void discard_split_index(struct index_state *istate);
+
+#endif
diff --git a/strbuf.c b/strbuf.c
index 12c7865..33018d8 100644
--- a/strbuf.c
+++ b/strbuf.c
@@ -11,15 +11,6 @@
 			return 0;
 }
 
-int ends_with(const char *str, const char *suffix)
-{
-	int len = strlen(str), suflen = strlen(suffix);
-	if (len < suflen)
-		return 0;
-	else
-		return !strcmp(str + len - suflen, suffix);
-}
-
 /*
  * Used as the default ->buf value, so that people can always assume
  * buf is non NULL and ->buf is NUL terminated even for a freshly
diff --git a/strbuf.h b/strbuf.h
index a594c24..a7c0192 100644
--- a/strbuf.h
+++ b/strbuf.h
@@ -49,6 +49,15 @@
 extern void strbuf_tolower(struct strbuf *sb);
 extern int strbuf_cmp(const struct strbuf *, const struct strbuf *);
 
+static inline int strbuf_strip_suffix(struct strbuf *sb, const char *suffix)
+{
+	if (strip_suffix_mem(sb->buf, &sb->len, suffix)) {
+		strbuf_setlen(sb, sb->len);
+		return 1;
+	} else
+		return 0;
+}
+
 /*
  * Split str (of length slen) at the specified terminator character.
  * Return a null-terminated array of pointers to strbuf objects
diff --git a/string-list.c b/string-list.c
index aabb25e..db38b62 100644
--- a/string-list.c
+++ b/string-list.c
@@ -1,6 +1,12 @@
 #include "cache.h"
 #include "string-list.h"
 
+void string_list_init(struct string_list *list, int strdup_strings)
+{
+	memset(list, 0, sizeof(*list));
+	list->strdup_strings = strdup_strings;
+}
+
 /* if there is no exact match, point to the index where the entry could be
  * inserted */
 static int get_entry_index(const struct string_list *list, const char *string,
diff --git a/string-list.h b/string-list.h
index dd5e294..494eb5d 100644
--- a/string-list.h
+++ b/string-list.h
@@ -18,6 +18,8 @@
 #define STRING_LIST_INIT_NODUP { NULL, 0, 0, 0, NULL }
 #define STRING_LIST_INIT_DUP   { NULL, 0, 0, 1, NULL }
 
+void string_list_init(struct string_list *list, int strdup_strings);
+
 void print_string_list(const struct string_list *p, const char *text);
 void string_list_clear(struct string_list *list, int free_util);
 
diff --git a/submodule.c b/submodule.c
index b80ecac..c3a61e7 100644
--- a/submodule.c
+++ b/submodule.c
@@ -544,10 +544,7 @@
 int push_unpushed_submodules(unsigned char new_sha1[20], const char *remotes_name)
 {
 	int i, ret = 1;
-	struct string_list needs_pushing;
-
-	memset(&needs_pushing, 0, sizeof(struct string_list));
-	needs_pushing.strdup_strings = 1;
+	struct string_list needs_pushing = STRING_LIST_INIT_DUP;
 
 	if (!find_unpushed_submodules(new_sha1, remotes_name, &needs_pushing))
 		return 1;
@@ -965,7 +962,7 @@
 			sha1_to_hex(a->object.sha1));
 	init_revisions(&revs, NULL);
 	rev_opts.submodule = path;
-	setup_revisions(sizeof(rev_args)/sizeof(char *)-1, rev_args, &revs, &rev_opts);
+	setup_revisions(ARRAY_SIZE(rev_args)-1, rev_args, &revs, &rev_opts);
 
 	/* save all revisions from the above list that contain b */
 	if (prepare_revision_walk(&revs))
diff --git a/t/Makefile b/t/Makefile
index 8fd1a72..43b15e3 100644
--- a/t/Makefile
+++ b/t/Makefile
@@ -13,7 +13,7 @@
 RM ?= rm -f
 PROVE ?= prove
 DEFAULT_TEST_TARGET ?= test
-TEST_LINT ?= test-lint-duplicates test-lint-executable
+TEST_LINT ?= test-lint
 
 ifdef TEST_OUTPUT_DIRECTORY
 TEST_RESULTS_DIRECTORY = $(TEST_OUTPUT_DIRECTORY)/test-results
@@ -29,6 +29,7 @@
 T = $(sort $(wildcard t[0-9][0-9][0-9][0-9]-*.sh))
 TSVN = $(sort $(wildcard t91[0-9][0-9]-*.sh))
 TGITWEB = $(sort $(wildcard t95[0-9][0-9]-*.sh))
+THELPERS = $(sort $(filter-out $(T),$(wildcard *.sh)))
 
 all: $(DEFAULT_TEST_TARGET)
 
@@ -65,7 +66,7 @@
 		echo >&2 "non-executable tests:" $$bad; exit 1; }
 
 test-lint-shell-syntax:
-	@'$(PERL_PATH_SQ)' check-non-portable-shell.pl $(T)
+	@'$(PERL_PATH_SQ)' check-non-portable-shell.pl $(T) $(THELPERS)
 
 aggregate-results-and-cleanup: $(T)
 	$(MAKE) aggregate-results
diff --git a/t/lib-submodule-update.sh b/t/lib-submodule-update.sh
new file mode 100755
index 0000000..79cdd34
--- /dev/null
+++ b/t/lib-submodule-update.sh
@@ -0,0 +1,680 @@
+# Create a submodule layout used for all tests below.
+#
+# The following use cases are covered:
+# - New submodule (no_submodule => add_sub1)
+# - Removed submodule (add_sub1 => remove_sub1)
+# - Updated submodule (add_sub1 => modify_sub1)
+# - Submodule updated to invalid commit (add_sub1 => invalid_sub1)
+# - Submodule updated from invalid commit (invalid_sub1 => valid_sub1)
+# - Submodule replaced by tracked files in directory (add_sub1 =>
+#   replace_sub1_with_directory)
+# - Directory containing tracked files replaced by submodule
+#   (replace_sub1_with_directory => replace_directory_with_sub1)
+# - Submodule replaced by tracked file with the same name (add_sub1 =>
+#   replace_sub1_with_file)
+# - Tracked file replaced by submodule (replace_sub1_with_file =>
+#   replace_file_with_sub1)
+#
+#                   --O-----O
+#                  /  ^     replace_directory_with_sub1
+#                 /   replace_sub1_with_directory
+#                /----O
+#               /     ^
+#              /      modify_sub1
+#      O------O-------O
+#      ^      ^\      ^
+#      |      | \     remove_sub1
+#      |      |  -----O-----O
+#      |      |   \   ^     replace_file_with_sub1
+#      |      |    \  replace_sub1_with_file
+#      |   add_sub1 --O-----O
+# no_submodule        ^     valid_sub1
+#                     invalid_sub1
+#
+create_lib_submodule_repo () {
+	git init submodule_update_repo &&
+	(
+		cd submodule_update_repo &&
+		echo "expect" >>.gitignore &&
+		echo "actual" >>.gitignore &&
+		echo "x" >file1 &&
+		echo "y" >file2 &&
+		git add .gitignore file1 file2 &&
+		git commit -m "Base" &&
+		git branch "no_submodule" &&
+
+		git checkout -b "add_sub1" &&
+		git submodule add ./. sub1 &&
+		git config -f .gitmodules submodule.sub1.ignore all &&
+		git config submodule.sub1.ignore all &&
+		git add .gitmodules &&
+		git commit -m "Add sub1" &&
+		git checkout -b remove_sub1 &&
+		git revert HEAD &&
+
+		git checkout -b "modify_sub1" "add_sub1" &&
+		git submodule update &&
+		(
+			cd sub1 &&
+			git fetch &&
+			git checkout -b "modifications" &&
+			echo "z" >file2 &&
+			echo "x" >file3 &&
+			git add file2 file3 &&
+			git commit -m "modified file2 and added file3" &&
+			git push origin modifications
+		) &&
+		git add sub1 &&
+		git commit -m "Modify sub1" &&
+
+		git checkout -b "replace_sub1_with_directory" "add_sub1" &&
+		git submodule update &&
+		(
+			cd sub1 &&
+			git checkout modifications
+		) &&
+		git rm --cached sub1 &&
+		rm sub1/.git* &&
+		git config -f .gitmodules --remove-section "submodule.sub1" &&
+		git add .gitmodules sub1/* &&
+		git commit -m "Replace sub1 with directory" &&
+		git checkout -b replace_directory_with_sub1 &&
+		git revert HEAD &&
+
+		git checkout -b "replace_sub1_with_file" "add_sub1" &&
+		git rm sub1 &&
+		echo "content" >sub1 &&
+		git add sub1 &&
+		git commit -m "Replace sub1 with file" &&
+		git checkout -b replace_file_with_sub1 &&
+		git revert HEAD &&
+
+		git checkout -b "invalid_sub1" "add_sub1" &&
+		git update-index --cacheinfo 160000 0123456789012345678901234567890123456789 sub1 &&
+		git commit -m "Invalid sub1 commit" &&
+		git checkout -b valid_sub1 &&
+		git revert HEAD &&
+		git checkout master
+	)
+}
+
+# Helper function to replace gitfile with .git directory
+replace_gitfile_with_git_dir () {
+	(
+		cd "$1" &&
+		git_dir="$(git rev-parse --git-dir)" &&
+		rm -f .git &&
+		cp -R "$git_dir" .git &&
+		GIT_WORK_TREE=. git config --unset core.worktree
+	)
+}
+
+# Test that the .git directory in the submodule is unchanged (except for the
+# core.worktree setting, which appears only in $GIT_DIR/modules/$1/config).
+# Call this function before test_submodule_content as the latter might
+# write the index file leading to false positive index differences.
+#
+# Note that this only supports submodules at the root level of the
+# superproject, with the default name, i.e. same as its path.
+test_git_directory_is_unchanged () {
+	(
+		cd ".git/modules/$1" &&
+		# does core.worktree point at the right place?
+		test "$(git config core.worktree)" = "../../../$1" &&
+		# remove it temporarily before comparing, as
+		# "$1/.git/config" lacks it...
+		git config --unset core.worktree
+	) &&
+	diff -r ".git/modules/$1" "$1/.git" &&
+	(
+		# ... and then restore.
+		cd ".git/modules/$1" &&
+		git config core.worktree "../../../$1"
+	)
+}
+
+# Helper function to be executed at the start of every test below, it sets up
+# the submodule repo if it doesn't exist and configures the most problematic
+# settings for diff.ignoreSubmodules.
+prolog () {
+	(test -d submodule_update_repo || create_lib_submodule_repo) &&
+	test_config_global diff.ignoreSubmodules all &&
+	test_config diff.ignoreSubmodules all
+}
+
+# Helper function to bring work tree back into the state given by the
+# commit. This includes trying to populate sub1 accordingly if it exists and
+# should be updated to an existing commit.
+reset_work_tree_to () {
+	rm -rf submodule_update &&
+	git clone submodule_update_repo submodule_update &&
+	(
+		cd submodule_update &&
+		rm -rf sub1 &&
+		git checkout -f "$1" &&
+		git status -u -s >actual &&
+		test_must_be_empty actual &&
+		sha1=$(git rev-parse --revs-only HEAD:sub1) &&
+		if test -n "$sha1" &&
+		   test $(cd "sub1" && git rev-parse --verify "$sha1^{commit}")
+		then
+			git submodule update --init --recursive "sub1"
+		fi
+	)
+}
+
+# Test that the superproject contains the content according to commit "$1"
+# (the work tree must match the index for everything but submodules but the
+# index must exactly match the given commit including any submodule SHA-1s).
+test_superproject_content () {
+	git diff-index --cached "$1" >actual &&
+	test_must_be_empty actual &&
+	git diff-files --ignore-submodules >actual &&
+	test_must_be_empty actual
+}
+
+# Test that the given submodule at path "$1" contains the content according
+# to the submodule commit recorded in the superproject's commit "$2"
+test_submodule_content () {
+	if test $# != 2
+	then
+		echo "test_submodule_content needs two arguments"
+		return 1
+	fi &&
+	submodule="$1" &&
+	commit="$2" &&
+	test -d "$submodule"/ &&
+	if ! test -f "$submodule"/.git && ! test -d "$submodule"/.git
+	then
+		echo "Submodule $submodule is not populated"
+		return 1
+	fi &&
+	sha1=$(git rev-parse --verify "$commit:$submodule") &&
+	if test -z "$sha1"
+	then
+		echo "Couldn't retrieve SHA-1 of $submodule for $commit"
+		return 1
+	fi &&
+	(
+		cd "$submodule" &&
+		git status -u -s >actual &&
+		test_must_be_empty actual &&
+		git diff "$sha1" >actual &&
+		test_must_be_empty actual
+	)
+}
+
+# Test that the following transitions are correctly handled:
+# - Updated submodule
+# - New submodule
+# - Removed submodule
+# - Directory containing tracked files replaced by submodule
+# - Submodule replaced by tracked files in directory
+# - Submodule replaced by tracked file with the same name
+# - tracked file replaced by submodule
+#
+# The default is that submodule contents aren't changed until "git submodule
+# update" is run. And even then that command doesn't delete the work tree of
+# a removed submodule.
+#
+# Removing a submodule containing a .git directory must fail even when forced
+# to protect the history!
+#
+
+# Test that submodule contents are currently not updated when switching
+# between commits that change a submodule.
+test_submodule_switch () {
+	command="$1"
+	######################### Appearing submodule #########################
+	# Switching to a commit letting a submodule appear creates empty dir ...
+	if test "$KNOWN_FAILURE_STASH_DOES_IGNORE_SUBMODULE_CHANGES" = 1
+	then
+		# Restoring stash fails to restore submodule index entry
+		RESULT="failure"
+	else
+		RESULT="success"
+	fi
+	test_expect_$RESULT "$command: added submodule creates empty directory" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			$command add_sub1 &&
+			test_superproject_content origin/add_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... and doesn't care if it already exists ...
+	test_expect_$RESULT "$command: added submodule leaves existing empty directory alone" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			mkdir sub1 &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			$command add_sub1 &&
+			test_superproject_content origin/add_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... unless there is an untracked file in its place.
+	test_expect_success "$command: added submodule doesn't remove untracked unignored file with same name" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			>sub1 &&
+			test_must_fail $command add_sub1 &&
+			test_superproject_content origin/no_submodule &&
+			test_must_be_empty sub1
+		)
+	'
+	# Replacing a tracked file with a submodule produces an empty
+	# directory ...
+	test_expect_$RESULT "$command: replace tracked file with submodule creates empty directory" '
+		prolog &&
+		reset_work_tree_to replace_sub1_with_file &&
+		(
+			cd submodule_update &&
+			git branch -t replace_file_with_sub1 origin/replace_file_with_sub1 &&
+			$command replace_file_with_sub1 &&
+			test_superproject_content origin/replace_file_with_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/replace_file_with_sub1
+		)
+	'
+	# ... as does removing a directory with tracked files with a
+	# submodule.
+	if test "$KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR" = 1
+	then
+		# Non fast-forward merges fail with "Directory sub1 doesn't
+		# exist. sub1" because the empty submodule directory is not
+		# created
+		RESULT="failure"
+	else
+		RESULT="success"
+	fi
+	test_expect_$RESULT "$command: replace directory with submodule" '
+		prolog &&
+		reset_work_tree_to replace_sub1_with_directory &&
+		(
+			cd submodule_update &&
+			git branch -t replace_directory_with_sub1 origin/replace_directory_with_sub1 &&
+			$command replace_directory_with_sub1 &&
+			test_superproject_content origin/replace_directory_with_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/replace_directory_with_sub1
+		)
+	'
+
+	######################## Disappearing submodule #######################
+	# Removing a submodule doesn't remove its work tree ...
+	if test "$KNOWN_FAILURE_STASH_DOES_IGNORE_SUBMODULE_CHANGES" = 1
+	then
+		RESULT="failure"
+	else
+		RESULT="success"
+	fi
+	test_expect_$RESULT "$command: removed submodule leaves submodule directory and its contents in place" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t remove_sub1 origin/remove_sub1 &&
+			$command remove_sub1 &&
+			test_superproject_content origin/remove_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... especially when it contains a .git directory.
+	test_expect_$RESULT "$command: removed submodule leaves submodule containing a .git directory alone" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t remove_sub1 origin/remove_sub1 &&
+			replace_gitfile_with_git_dir sub1 &&
+			$command remove_sub1 &&
+			test_superproject_content origin/remove_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Replacing a submodule with files in a directory must fail as the
+	# submodule work tree isn't removed ...
+	if test "$KNOWN_FAILURE_NOFF_MERGE_ATTEMPTS_TO_MERGE_REMOVED_SUBMODULE_FILES" = 1
+	then
+		# Non fast-forward merges attempt to merge the former
+		# submodule files with the newly checked out ones in the
+		# directory of the same name while it shouldn't.
+		RESULT="failure"
+	else
+		RESULT="success"
+	fi
+	test_expect_$RESULT "$command: replace submodule with a directory must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_directory origin/replace_sub1_with_directory &&
+			test_must_fail $command replace_sub1_with_directory &&
+			test_superproject_content origin/add_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... especially when it contains a .git directory.
+	test_expect_$RESULT "$command: replace submodule containing a .git directory with a directory must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_directory origin/replace_sub1_with_directory &&
+			replace_gitfile_with_git_dir sub1 &&
+			test_must_fail $command replace_sub1_with_directory &&
+			test_superproject_content origin/add_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Replacing it with a file must fail as it could throw away any local
+	# work tree changes ...
+	test_expect_failure "$command: replace submodule with a file must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_file origin/replace_sub1_with_file &&
+			test_must_fail $command replace_sub1_with_file &&
+			test_superproject_content origin/add_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... or even destroy unpushed parts of submodule history if that
+	# still uses a .git directory.
+	test_expect_failure "$command: replace submodule containing a .git directory with a file must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_file origin/replace_sub1_with_file &&
+			replace_gitfile_with_git_dir sub1 &&
+			test_must_fail $command replace_sub1_with_file &&
+			test_superproject_content origin/add_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+
+	########################## Modified submodule #########################
+	# Updating a submodule sha1 doesn't update the submodule's work tree
+	if test "$KNOWN_FAILURE_CHERRY_PICK_SEES_EMPTY_COMMIT" = 1
+	then
+		# When cherry picking a SHA-1 update for an ignored submodule
+		# the commit incorrectly fails with "The previous cherry-pick
+		# is now empty, possibly due to conflict resolution."
+		RESULT="failure"
+	else
+		RESULT="success"
+	fi
+	test_expect_$RESULT "$command: modified submodule does not update submodule work tree" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t modify_sub1 origin/modify_sub1 &&
+			$command modify_sub1 &&
+			test_superproject_content origin/modify_sub1 &&
+			test_submodule_content sub1 origin/add_sub1 &&
+			git submodule update &&
+			test_submodule_content sub1 origin/modify_sub1
+		)
+	'
+
+	# Updating a submodule to an invalid sha1 doesn't update the
+	# submodule's work tree, subsequent update will fail
+	test_expect_$RESULT "$command: modified submodule does not update submodule work tree to invalid commit" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t invalid_sub1 origin/invalid_sub1 &&
+			$command invalid_sub1 &&
+			test_superproject_content origin/invalid_sub1 &&
+			test_submodule_content sub1 origin/add_sub1 &&
+			test_must_fail git submodule update &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Updating a submodule from an invalid sha1 doesn't update the
+	# submodule's work tree, subsequent update will succeed
+	test_expect_$RESULT "$command: modified submodule does not update submodule work tree from invalid commit" '
+		prolog &&
+		reset_work_tree_to invalid_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t valid_sub1 origin/valid_sub1 &&
+			$command valid_sub1 &&
+			test_superproject_content origin/valid_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/valid_sub1
+		)
+	'
+}
+
+# Test that submodule contents are currently not updated when switching
+# between commits that change a submodule, but throwing away local changes in
+# the superproject is allowed.
+test_submodule_forced_switch () {
+	command="$1"
+	######################### Appearing submodule #########################
+	# Switching to a commit letting a submodule appear creates empty dir ...
+	test_expect_success "$command: added submodule creates empty directory" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			$command add_sub1 &&
+			test_superproject_content origin/add_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... and doesn't care if it already exists ...
+	test_expect_success "$command: added submodule leaves existing empty directory alone" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			mkdir sub1 &&
+			$command add_sub1 &&
+			test_superproject_content origin/add_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... unless there is an untracked file in its place.
+	test_expect_success "$command: added submodule does remove untracked unignored file with same name when forced" '
+		prolog &&
+		reset_work_tree_to no_submodule &&
+		(
+			cd submodule_update &&
+			git branch -t add_sub1 origin/add_sub1 &&
+			>sub1 &&
+			$command add_sub1 &&
+			test_superproject_content origin/add_sub1 &&
+			test_dir_is_empty sub1
+		)
+	'
+	# Replacing a tracked file with a submodule produces an empty
+	# directory ...
+	test_expect_success "$command: replace tracked file with submodule creates empty directory" '
+		prolog &&
+		reset_work_tree_to replace_sub1_with_file &&
+		(
+			cd submodule_update &&
+			git branch -t replace_file_with_sub1 origin/replace_file_with_sub1 &&
+			$command replace_file_with_sub1 &&
+			test_superproject_content origin/replace_file_with_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/replace_file_with_sub1
+		)
+	'
+	# ... as does removing a directory with tracked files with a
+	# submodule.
+	test_expect_success "$command: replace directory with submodule" '
+		prolog &&
+		reset_work_tree_to replace_sub1_with_directory &&
+		(
+			cd submodule_update &&
+			git branch -t replace_directory_with_sub1 origin/replace_directory_with_sub1 &&
+			$command replace_directory_with_sub1 &&
+			test_superproject_content origin/replace_directory_with_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/replace_directory_with_sub1
+		)
+	'
+
+	######################## Disappearing submodule #######################
+	# Removing a submodule doesn't remove its work tree ...
+	test_expect_success "$command: removed submodule leaves submodule directory and its contents in place" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t remove_sub1 origin/remove_sub1 &&
+			$command remove_sub1 &&
+			test_superproject_content origin/remove_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... especially when it contains a .git directory.
+	test_expect_success "$command: removed submodule leaves submodule containing a .git directory alone" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t remove_sub1 origin/remove_sub1 &&
+			replace_gitfile_with_git_dir sub1 &&
+			$command remove_sub1 &&
+			test_superproject_content origin/remove_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Replacing a submodule with files in a directory must fail as the
+	# submodule work tree isn't removed ...
+	test_expect_failure "$command: replace submodule with a directory must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_directory origin/replace_sub1_with_directory &&
+			test_must_fail $command replace_sub1_with_directory &&
+			test_superproject_content origin/add_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... especially when it contains a .git directory.
+	test_expect_failure "$command: replace submodule containing a .git directory with a directory must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_directory origin/replace_sub1_with_directory &&
+			replace_gitfile_with_git_dir sub1 &&
+			test_must_fail $command replace_sub1_with_directory &&
+			test_superproject_content origin/add_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Replacing it with a file must fail as it could throw away any local
+	# work tree changes ...
+	test_expect_failure "$command: replace submodule with a file must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_file origin/replace_sub1_with_file &&
+			test_must_fail $command replace_sub1_with_file &&
+			test_superproject_content origin/add_sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# ... or even destroy unpushed parts of submodule history if that
+	# still uses a .git directory.
+	test_expect_failure "$command: replace submodule containing a .git directory with a file must fail" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t replace_sub1_with_file origin/replace_sub1_with_file &&
+			replace_gitfile_with_git_dir sub1 &&
+			test_must_fail $command replace_sub1_with_file &&
+			test_superproject_content origin/add_sub1 &&
+			test_git_directory_is_unchanged sub1 &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+
+	########################## Modified submodule #########################
+	# Updating a submodule sha1 doesn't update the submodule's work tree
+	test_expect_success "$command: modified submodule does not update submodule work tree" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t modify_sub1 origin/modify_sub1 &&
+			$command modify_sub1 &&
+			test_superproject_content origin/modify_sub1 &&
+			test_submodule_content sub1 origin/add_sub1 &&
+			git submodule update &&
+			test_submodule_content sub1 origin/modify_sub1
+		)
+	'
+	# Updating a submodule to an invalid sha1 doesn't update the
+	# submodule's work tree, subsequent update will fail
+	test_expect_success "$command: modified submodule does not update submodule work tree to invalid commit" '
+		prolog &&
+		reset_work_tree_to add_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t invalid_sub1 origin/invalid_sub1 &&
+			$command invalid_sub1 &&
+			test_superproject_content origin/invalid_sub1 &&
+			test_submodule_content sub1 origin/add_sub1 &&
+			test_must_fail git submodule update &&
+			test_submodule_content sub1 origin/add_sub1
+		)
+	'
+	# Updating a submodule from an invalid sha1 doesn't update the
+	# submodule's work tree, subsequent update will succeed
+	test_expect_success "$command: modified submodule does not update submodule work tree from invalid commit" '
+		prolog &&
+		reset_work_tree_to invalid_sub1 &&
+		(
+			cd submodule_update &&
+			git branch -t valid_sub1 origin/valid_sub1 &&
+			$command valid_sub1 &&
+			test_superproject_content origin/valid_sub1 &&
+			test_dir_is_empty sub1 &&
+			git submodule update --init --recursive &&
+			test_submodule_content sub1 origin/valid_sub1
+		)
+	'
+}
diff --git a/t/t0011-hashmap.sh b/t/t0011-hashmap.sh
index 391e2b6..f97c805 100755
--- a/t/t0011-hashmap.sh
+++ b/t/t0011-hashmap.sh
@@ -237,4 +237,17 @@
 
 '
 
+test_expect_success 'string interning' '
+
+test_hashmap "intern value1
+intern Value1
+intern value2
+intern value2
+" "value1
+Value1
+value2
+value2"
+
+'
+
 test_done
diff --git a/t/t0025-crlf-auto.sh b/t/t0025-crlf-auto.sh
index 28102de..c164b46 100755
--- a/t/t0025-crlf-auto.sh
+++ b/t/t0025-crlf-auto.sh
@@ -12,144 +12,144 @@
 
 	git config core.autocrlf false &&
 
-	for w in Hello world how are you; do echo $w; done >one &&
-	for w in I am very very fine thank you; do echo ${w}Q; done | q_to_cr >two &&
-	for w in Oh here is a QNUL byte how alarming; do echo ${w}; done | q_to_nul >three &&
+	for w in Hello world how are you; do echo $w; done >LFonly &&
+	for w in I am very very fine thank you; do echo ${w}Q; done | q_to_cr >CRLFonly &&
+	for w in Oh here is a QNUL byte how alarming; do echo ${w}; done | q_to_nul >LFwithNUL &&
 	git add . &&
 
 	git commit -m initial &&
 
-	one=$(git rev-parse HEAD:one) &&
-	two=$(git rev-parse HEAD:two) &&
-	three=$(git rev-parse HEAD:three) &&
+	LFonly=$(git rev-parse HEAD:LFonly) &&
+	CRLFonly=$(git rev-parse HEAD:CRLFonly) &&
+	LFwithNUL=$(git rev-parse HEAD:LFwithNUL) &&
 
 	echo happy.
 '
 
 test_expect_success 'default settings cause no changes' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git read-tree --reset -u HEAD &&
 
-	! has_cr one &&
-	has_cr two &&
-	onediff=$(git diff one) &&
-	twodiff=$(git diff two) &&
-	threediff=$(git diff three) &&
-	test -z "$onediff" && test -z "$twodiff" && test -z "$threediff"
+	! has_cr LFonly &&
+	has_cr CRLFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	CRLFonlydiff=$(git diff CRLFonly) &&
+	LFwithNULdiff=$(git diff LFwithNUL) &&
+	test -z "$LFonlydiff" -a -z "$CRLFonlydiff" -a -z "$LFwithNULdiff"
 '
 
 test_expect_success 'crlf=true causes a CRLF file to be normalized' '
 
 	# Backwards compatibility check
-	rm -f .gitattributes tmp one two three &&
-	echo "two crlf" > .gitattributes &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
+	echo "CRLFonly crlf" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
 	# Note, "normalized" means that git will normalize it if added
-	has_cr two &&
-	twodiff=$(git diff two) &&
-	test -n "$twodiff"
+	has_cr CRLFonly &&
+	CRLFonlydiff=$(git diff CRLFonly) &&
+	test -n "$CRLFonlydiff"
 '
 
 test_expect_success 'text=true causes a CRLF file to be normalized' '
 
-	rm -f .gitattributes tmp one two three &&
-	echo "two text" > .gitattributes &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
+	echo "CRLFonly text" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
 	# Note, "normalized" means that git will normalize it if added
-	has_cr two &&
-	twodiff=$(git diff two) &&
-	test -n "$twodiff"
+	has_cr CRLFonly &&
+	CRLFonlydiff=$(git diff CRLFonly) &&
+	test -n "$CRLFonlydiff"
 '
 
 test_expect_success 'eol=crlf gives a normalized file CRLFs with autocrlf=false' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf false &&
-	echo "one eol=crlf" > .gitattributes &&
+	echo "LFonly eol=crlf" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	has_cr one &&
-	onediff=$(git diff one) &&
-	test -z "$onediff"
+	has_cr LFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	test -z "$LFonlydiff"
 '
 
 test_expect_success 'eol=crlf gives a normalized file CRLFs with autocrlf=input' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf input &&
-	echo "one eol=crlf" > .gitattributes &&
+	echo "LFonly eol=crlf" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	has_cr one &&
-	onediff=$(git diff one) &&
-	test -z "$onediff"
+	has_cr LFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	test -z "$LFonlydiff"
 '
 
 test_expect_success 'eol=lf gives a normalized file LFs with autocrlf=true' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf true &&
-	echo "one eol=lf" > .gitattributes &&
+	echo "LFonly eol=lf" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	! has_cr one &&
-	onediff=$(git diff one) &&
-	test -z "$onediff"
+	! has_cr LFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	test -z "$LFonlydiff"
 '
 
 test_expect_success 'autocrlf=true does not normalize CRLF files' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf true &&
 	git read-tree --reset -u HEAD &&
 
-	has_cr one &&
-	has_cr two &&
-	onediff=$(git diff one) &&
-	twodiff=$(git diff two) &&
-	threediff=$(git diff three) &&
-	test -z "$onediff" && test -z "$twodiff" && test -z "$threediff"
+	has_cr LFonly &&
+	has_cr CRLFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	CRLFonlydiff=$(git diff CRLFonly) &&
+	LFwithNULdiff=$(git diff LFwithNUL) &&
+	test -z "$LFonlydiff" -a -z "$CRLFonlydiff" -a -z "$LFwithNULdiff"
 '
 
 test_expect_success 'text=auto, autocrlf=true _does_ normalize CRLF files' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf true &&
 	echo "* text=auto" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	has_cr one &&
-	has_cr two &&
-	onediff=$(git diff one) &&
-	twodiff=$(git diff two) &&
-	threediff=$(git diff three) &&
-	test -z "$onediff" && test -n "$twodiff" && test -z "$threediff"
+	has_cr LFonly &&
+	has_cr CRLFonly &&
+	LFonlydiff=$(git diff LFonly) &&
+	CRLFonlydiff=$(git diff CRLFonly) &&
+	LFwithNULdiff=$(git diff LFwithNUL) &&
+	test -z "$LFonlydiff" -a -n "$CRLFonlydiff" -a -z "$LFwithNULdiff"
 '
 
 test_expect_success 'text=auto, autocrlf=true does not normalize binary files' '
 
-	rm -f .gitattributes tmp one two three &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
 	git config core.autocrlf true &&
 	echo "* text=auto" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	! has_cr three &&
-	threediff=$(git diff three) &&
-	test -z "$threediff"
+	! has_cr LFwithNUL &&
+	LFwithNULdiff=$(git diff LFwithNUL) &&
+	test -z "$LFwithNULdiff"
 '
 
 test_expect_success 'eol=crlf _does_ normalize binary files' '
 
-	rm -f .gitattributes tmp one two three &&
-	echo "three eol=crlf" > .gitattributes &&
+	rm -f .gitattributes tmp LFonly CRLFonly LFwithNUL &&
+	echo "LFwithNUL eol=crlf" > .gitattributes &&
 	git read-tree --reset -u HEAD &&
 
-	has_cr three &&
-	threediff=$(git diff three) &&
-	test -z "$threediff"
+	has_cr LFwithNUL &&
+	LFwithNULdiff=$(git diff LFwithNUL) &&
+	test -z "$LFwithNULdiff"
 '
 
 test_done
diff --git a/t/t0027-auto-crlf.sh b/t/t0027-auto-crlf.sh
new file mode 100755
index 0000000..72dd3e8
--- /dev/null
+++ b/t/t0027-auto-crlf.sh
@@ -0,0 +1,265 @@
+#!/bin/sh
+
+test_description='CRLF conversion all combinations'
+
+. ./test-lib.sh
+
+if ! test_have_prereq EXPENSIVE
+then
+	skip_all="EXPENSIVE not set"
+	test_done
+fi
+
+
+compare_files()
+{
+	od -c <"$1" >"$1".expect &&
+	od -c <"$2" >"$2".actual &&
+	test_cmp "$1".expect "$2".actual &&
+	rm "$1".expect "$2".actual
+}
+
+compare_ws_file()
+{
+	pfx=$1
+	exp=$2.expect
+	act=$pfx.actual.$3
+	od -c <"$2" >"$exp" &&
+	od -c <"$3" >"$act" &&
+	test_cmp $exp $act &&
+	rm $exp $act
+}
+
+create_gitattributes()
+{
+	txtbin=$1
+	case "$txtbin" in
+		auto)
+		echo "*.txt text=auto" >.gitattributes
+		;;
+		text)
+		echo "*.txt text" >.gitattributes
+		;;
+		-text)
+		echo "*.txt -text" >.gitattributes
+		;;
+		*)
+		echo >.gitattributes
+		;;
+	esac
+}
+
+create_file_in_repo()
+{
+	crlf=$1
+	txtbin=$2
+	create_gitattributes "$txtbin" &&
+	for f in LF CRLF LF_mix_CR CRLF_mix_LF CRLF_nul
+	do
+		pfx=crlf_${crlf}_attr_${txtbin}_$f.txt &&
+		cp $f $pfx && git -c core.autocrlf=$crlf add $pfx
+	done &&
+	git commit -m "core.autocrlf $crlf"
+}
+
+check_files_in_repo()
+{
+	crlf=$1
+	txtbin=$2
+	lfname=$3
+	crlfname=$4
+	lfmixcrlf=$5
+	lfmixcr=$6
+	crlfnul=$7
+	pfx=crlf_${crlf}_attr_${txtbin}_ &&
+	compare_files $lfname ${pfx}LF.txt &&
+	compare_files $crlfname ${pfx}CRLF.txt &&
+	compare_files $lfmixcrlf ${pfx}CRLF_mix_LF.txt &&
+	compare_files $lfmixcr ${pfx}LF_mix_CR.txt &&
+	compare_files $crlfnul ${pfx}CRLF_nul.txt
+}
+
+
+check_files_in_ws()
+{
+	eol=$1
+	crlf=$2
+	txtbin=$3
+	lfname=$4
+	crlfname=$5
+	lfmixcrlf=$6
+	lfmixcr=$7
+	crlfnul=$8
+	create_gitattributes $txtbin &&
+	git config core.autocrlf $crlf &&
+	pfx=eol_${eol}_crlf_${crlf}_attr_${txtbin}_ &&
+	src=crlf_false_attr__ &&
+	for f in LF CRLF LF_mix_CR CRLF_mix_LF CRLF_nul
+	do
+		rm $src$f.txt &&
+		if test -z "$eol"; then
+			git checkout $src$f.txt
+		else
+			git -c core.eol=$eol checkout $src$f.txt
+		fi
+	done
+
+
+	test_expect_success "checkout core.eol=$eol core.autocrlf=$crlf gitattributes=$txtbin file=LF" "
+		compare_ws_file $pfx $lfname    ${src}LF.txt
+	"
+	test_expect_success "checkout core.eol=$eol core.autocrlf=$crlf gitattributes=$txtbin file=CRLF" "
+		compare_ws_file $pfx $crlfname  ${src}CRLF.txt
+	"
+	test_expect_success "checkout core.eol=$eol core.autocrlf=$crlf gitattributes=$txtbin file=CRLF_mix_LF" "
+		compare_ws_file $pfx $lfmixcrlf ${src}CRLF_mix_LF.txt
+	"
+	test_expect_success "checkout core.eol=$eol core.autocrlf=$crlf gitattributes=$txtbin file=LF_mix_CR" "
+		compare_ws_file $pfx $lfmixcr   ${src}LF_mix_CR.txt
+	"
+	test_expect_success "checkout core.eol=$eol core.autocrlf=$crlf gitattributes=$txtbin file=CRLF_nul" "
+		compare_ws_file $pfx $crlfnul   ${src}CRLF_nul.txt
+	"
+}
+
+#######
+(
+	type od >/dev/null &&
+	printf "line1Q\r\nline2\r\nline3" | q_to_nul >CRLF_nul &&
+	cat >expect <<-EOF &&
+	0000000 l i n e 1 \0 \r \n l i n e 2 \r \n l
+	0000020 i n e 3
+	0000024
+EOF
+	od -c CRLF_nul | sed -e "s/[ 	][	 ]*/ /g" -e "s/ *$//" >actual
+	test_cmp expect actual &&
+	rm expect actual
+) || {
+		skip_all="od not found or od -c not usable"
+		exit 0
+		test_done
+}
+
+test_expect_success 'setup master' '
+	echo >.gitattributes &&
+	git checkout -b master &&
+	git add .gitattributes &&
+	git commit -m "add .gitattributes" "" &&
+	printf "line1\nline2\nline3"     >LF &&
+	printf "line1\r\nline2\r\nline3" >CRLF &&
+	printf "line1\r\nline2\nline3"   >CRLF_mix_LF &&
+	printf "line1\nline2\rline3"     >LF_mix_CR &&
+	printf "line1\r\nline2\rline3"   >CRLF_mix_CR &&
+	printf "line1Q\nline2\nline3" | q_to_nul >LF_nul
+'
+#  CRLF_nul had been created above
+
+test_expect_success 'create files' '
+	create_file_in_repo false "" &&
+	create_file_in_repo true  "" &&
+	create_file_in_repo input "" &&
+
+	create_file_in_repo false "auto" &&
+	create_file_in_repo true  "auto" &&
+	create_file_in_repo input "auto" &&
+
+	create_file_in_repo false "text" &&
+	create_file_in_repo true  "text" &&
+	create_file_in_repo input "text" &&
+
+	create_file_in_repo false "-text" &&
+	create_file_in_repo true  "-text" &&
+	create_file_in_repo input "-text" &&
+	rm -f *.txt &&
+	git reset --hard
+'
+
+test_expect_success 'commit empty gitattribues' '
+	check_files_in_repo false ""      LF CRLF CRLF_mix_LF LF_mix_CR CRLF_nul &&
+	check_files_in_repo true  ""      LF LF   LF          LF_mix_CR CRLF_nul &&
+	check_files_in_repo input ""      LF LF   LF          LF_mix_CR CRLF_nul
+'
+
+test_expect_success 'commit text=auto' '
+	check_files_in_repo false "auto"  LF LF   LF          LF_mix_CR CRLF_nul &&
+	check_files_in_repo true  "auto"  LF LF   LF          LF_mix_CR CRLF_nul &&
+	check_files_in_repo input "auto"  LF LF   LF          LF_mix_CR CRLF_nul
+'
+
+test_expect_success 'commit text' '
+	check_files_in_repo false "text"  LF LF   LF          LF_mix_CR LF_nul &&
+	check_files_in_repo true  "text"  LF LF   LF          LF_mix_CR LF_nul &&
+	check_files_in_repo input "text"  LF LF   LF          LF_mix_CR LF_nul
+'
+
+test_expect_success 'commit -text' '
+	check_files_in_repo false "-text" LF CRLF CRLF_mix_LF LF_mix_CR CRLF_nul &&
+	check_files_in_repo true  "-text" LF CRLF CRLF_mix_LF LF_mix_CR CRLF_nul &&
+	check_files_in_repo input "-text" LF CRLF CRLF_mix_LF LF_mix_CR CRLF_nul
+'
+
+################################################################################
+# Check how files in the repo are changed when they are checked out
+# How to read the table below:
+# - check_files_in_ws will check multiple files, see below
+# - parameter $1 : core.eol               lf | crlf
+# - parameter $2 : core.autocrlf          false | true | input
+# - parameter $3 : text in .gitattributs  "" (empty) | auto | text | -text
+# - parameter $4 : reference for a file with only LF in the repo
+# - parameter $5 : reference for a file with only CRLF in the repo
+# - parameter $6 : reference for a file with mixed LF and CRLF in the repo
+# - parameter $7 : reference for a file with LF and CR in the repo (does somebody uses this ?)
+# - parameter $8 : reference for a file with CRLF and a NUL (should be handled as binary when auto)
+
+check_files_in_ws lf      false  ""       LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      true   ""       CRLF  CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      input  ""       LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+check_files_in_ws lf      false "auto"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      true  "auto"    CRLF  CRLF  CRLF         LF_mix_CR    CRLF_nul
+check_files_in_ws lf      input "auto"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+check_files_in_ws lf      false "text"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      true  "text"    CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
+check_files_in_ws lf      input "text"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+check_files_in_ws lf      false "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      true  "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws lf      input "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+###########
+#core.autocrlf=input is forbidden with core.eol=crlf
+check_files_in_ws crlf    false ""        LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws crlf    true  ""        CRLF  CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+check_files_in_ws crlf    false "auto"    CRLF  CRLF  CRLF         LF_mix_CR    CRLF_nul
+check_files_in_ws crlf    true  "auto"    CRLF  CRLF  CRLF         LF_mix_CR    CRLF_nul
+
+check_files_in_ws crlf    false "text"    CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
+check_files_in_ws crlf    true  "text"    CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
+
+check_files_in_ws crlf    false "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws crlf    true  "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+if test_have_prereq MINGW
+then
+check_files_in_ws ""      false ""        LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws ""      true  ""        CRLF  CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws ""      false "auto"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws ""      true  "auto"    CRLF  CRLF  CRLF         LF_mix_CR    CRLF_nul
+check_files_in_ws ""      false "text"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws ""      true  "text"    CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
+check_files_in_ws ""      false "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws ""      true  "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+
+check_files_in_ws native  false ""        LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws native  true  ""        CRLF  CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws native  false "auto"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws native  true  "auto"    CRLF  CRLF  CRLF         LF_mix_CR    CRLF_nul
+check_files_in_ws native  false "text"    LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws native  true  "text"    CRLF  CRLF  CRLF         CRLF_mix_CR  CRLF_nul
+check_files_in_ws native  false "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+check_files_in_ws native  true  "-text"   LF    CRLF  CRLF_mix_LF  LF_mix_CR    CRLF_nul
+fi
+
+test_done
diff --git a/t/t1013-read-tree-submodule.sh b/t/t1013-read-tree-submodule.sh
new file mode 100755
index 0000000..20526ae
--- /dev/null
+++ b/t/t1013-read-tree-submodule.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+
+test_description='read-tree can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+test_submodule_switch "git read-tree -u -m"
+
+test_submodule_forced_switch "git read-tree -u --reset"
+
+test_done
diff --git a/t/t1700-split-index.sh b/t/t1700-split-index.sh
new file mode 100755
index 0000000..94fb473
--- /dev/null
+++ b/t/t1700-split-index.sh
@@ -0,0 +1,194 @@
+#!/bin/sh
+
+test_description='split index mode tests'
+
+. ./test-lib.sh
+
+# We need total control of index splitting here
+sane_unset GIT_TEST_SPLIT_INDEX
+
+test_expect_success 'enable split index' '
+	git update-index --split-index &&
+	test-dump-split-index .git/index >actual &&
+	cat >expect <<EOF &&
+own 8299b0bcd1ac364e5f1d7768efb62fa2da79a339
+base 39d890139ee5356c7ef572216cebcd27aa41f9df
+replacements:
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'add one file' '
+	: >one &&
+	git update-index --add one &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+base 39d890139ee5356c7ef572216cebcd27aa41f9df
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+replacements:
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'disable split index' '
+	git update-index --no-split-index &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	BASE=`test-dump-split-index .git/index | grep "^own" | sed "s/own/base/"` &&
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+not a split index
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'enable split index again, "one" now belongs to base index"' '
+	git update-index --split-index &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+$BASE
+replacements:
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'modify original file, base index untouched' '
+	echo modified >one &&
+	git update-index one &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	q_to_tab >expect <<EOF &&
+$BASE
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0Q
+replacements: 0
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'add another file, which stays index' '
+	: >two &&
+	git update-index --add two &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0	one
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	two
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	q_to_tab >expect <<EOF &&
+$BASE
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0Q
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	two
+replacements: 0
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'remove file not in base index' '
+	git update-index --force-remove two &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	q_to_tab >expect <<EOF &&
+$BASE
+100644 2e0996000b7e9019eabcad29391bf0f5c7702f0b 0Q
+replacements: 0
+deletions:
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'remove file in base index' '
+	git update-index --force-remove one &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+$BASE
+replacements:
+deletions: 0
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'add original file back' '
+	: >one &&
+	git update-index --add one &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+EOF
+	test_cmp ls-files.expect ls-files.actual &&
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+$BASE
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+replacements:
+deletions: 0
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'add new file' '
+	: >two &&
+	git update-index --add two &&
+	git ls-files --stage >actual &&
+	cat >expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	two
+EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'unify index, two files remain' '
+	git update-index --no-split-index &&
+	git ls-files --stage >ls-files.actual &&
+	cat >ls-files.expect <<EOF &&
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	one
+100644 e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 0	two
+EOF
+	test_cmp ls-files.expect ls-files.actual
+
+	test-dump-split-index .git/index | sed "/^own/d" >actual &&
+	cat >expect <<EOF &&
+not a split index
+EOF
+	test_cmp expect actual
+'
+
+test_done
diff --git a/t/t2013-checkout-submodule.sh b/t/t2013-checkout-submodule.sh
index 06b18f8..6847f75 100755
--- a/t/t2013-checkout-submodule.sh
+++ b/t/t2013-checkout-submodule.sh
@@ -3,6 +3,7 @@
 test_description='checkout can handle submodules'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
 
 test_expect_success 'setup' '
 	mkdir submodule &&
@@ -62,4 +63,8 @@
 	! test -s actual
 '
 
+test_submodule_switch "git checkout"
+
+test_submodule_forced_switch "git checkout -f"
+
 test_done
diff --git a/t/t2104-update-index-skip-worktree.sh b/t/t2104-update-index-skip-worktree.sh
index 29c1fb1..cc830da 100755
--- a/t/t2104-update-index-skip-worktree.sh
+++ b/t/t2104-update-index-skip-worktree.sh
@@ -7,6 +7,8 @@
 
 . ./test-lib.sh
 
+sane_unset GIT_TEST_SPLIT_INDEX
+
 test_set_index_version 3
 
 cat >expect.full <<EOF
diff --git a/t/t3426-rebase-submodule.sh b/t/t3426-rebase-submodule.sh
new file mode 100755
index 0000000..d5b896d
--- /dev/null
+++ b/t/t3426-rebase-submodule.sh
@@ -0,0 +1,46 @@
+#!/bin/sh
+
+test_description='rebase can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+. "$TEST_DIRECTORY"/lib-rebase.sh
+
+git_rebase () {
+	git status -su >expect &&
+	ls -1pR * >>expect &&
+	git checkout -b ours HEAD &&
+	echo x >>file1 &&
+	git add file1 &&
+	git commit -m add_x &&
+	git revert HEAD &&
+	git status -su >actual &&
+	ls -1pR * >>actual &&
+	test_cmp expect actual &&
+	git rebase "$1"
+}
+
+test_submodule_switch "git_rebase"
+
+git_rebase_interactive () {
+	git status -su >expect &&
+	ls -1pR * >>expect &&
+	git checkout -b ours HEAD &&
+	echo x >>file1 &&
+	git add file1 &&
+	git commit -m add_x &&
+	git revert HEAD &&
+	git status -su >actual &&
+	ls -1pR * >>actual &&
+	test_cmp expect actual &&
+	set_fake_editor &&
+	echo "fake-editor.sh" >.git/info/exclude &&
+	git rebase -i "$1"
+}
+
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+# The real reason "replace directory with submodule" fails is because a
+# directory "sub1" exists, but we reuse the suppression added for merge here
+test_submodule_switch "git_rebase_interactive"
+
+test_done
diff --git a/t/t3512-cherry-pick-submodule.sh b/t/t3512-cherry-pick-submodule.sh
new file mode 100755
index 0000000..6863b7b
--- /dev/null
+++ b/t/t3512-cherry-pick-submodule.sh
@@ -0,0 +1,13 @@
+#!/bin/sh
+
+test_description='cherry-pick can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+KNOWN_FAILURE_CHERRY_PICK_SEES_EMPTY_COMMIT=1
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+KNOWN_FAILURE_NOFF_MERGE_ATTEMPTS_TO_MERGE_REMOVED_SUBMODULE_FILES=1
+test_submodule_switch "git cherry-pick"
+
+test_done
diff --git a/t/t3513-revert-submodule.sh b/t/t3513-revert-submodule.sh
new file mode 100755
index 0000000..a1c4e02
--- /dev/null
+++ b/t/t3513-revert-submodule.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+
+test_description='revert can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+# Create a revert that moves from HEAD (including any test modifications to
+# the work tree) to $1 by first checking out $1 and reverting it. Reverting
+# the revert is the transition we test for. We tar the current work tree
+# first so we can restore the work tree test setup after doing the checkout
+# and revert.  We test here that the restored work tree content is identical
+# to that at the beginning. The last revert is then tested by the framework.
+git_revert () {
+	git status -su >expect &&
+	ls -1pR * >>expect &&
+	tar czf "$TRASH_DIRECTORY/tmp.tgz" * &&
+	git checkout "$1" &&
+	git revert HEAD &&
+	rm -rf * &&
+	tar xzf "$TRASH_DIRECTORY/tmp.tgz" &&
+	git status -su >actual &&
+	ls -1pR * >>actual &&
+	test_cmp expect actual &&
+	git revert HEAD
+}
+
+KNOWN_FAILURE_CHERRY_PICK_SEES_EMPTY_COMMIT=1
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+test_submodule_switch "git_revert"
+
+test_done
diff --git a/t/t3906-stash-submodule.sh b/t/t3906-stash-submodule.sh
new file mode 100755
index 0000000..d7219d6
--- /dev/null
+++ b/t/t3906-stash-submodule.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+
+test_description='stash apply can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+git_stash () {
+	git status -su >expect &&
+	ls -1pR * >>expect &&
+	git read-tree -u -m "$1" &&
+	git stash &&
+	git status -su >actual &&
+	ls -1pR * >>actual &&
+	test_cmp expect actual &&
+	git stash apply
+}
+
+KNOWN_FAILURE_STASH_DOES_IGNORE_SUBMODULE_CHANGES=1
+KNOWN_FAILURE_CHERRY_PICK_SEES_EMPTY_COMMIT=1
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+test_submodule_switch "git_stash"
+
+test_done
diff --git a/t/t4137-apply-submodule.sh b/t/t4137-apply-submodule.sh
new file mode 100755
index 0000000..a9bd40a
--- /dev/null
+++ b/t/t4137-apply-submodule.sh
@@ -0,0 +1,20 @@
+#!/bin/sh
+
+test_description='git apply handling submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+apply_index () {
+	git diff --ignore-submodules=dirty "..$1" | git apply --index -
+}
+
+test_submodule_switch "apply_index"
+
+apply_3way () {
+	git diff --ignore-submodules=dirty "..$1" | git apply --3way -
+}
+
+test_submodule_switch "apply_3way"
+
+test_done
diff --git a/t/t4202-log.sh b/t/t4202-log.sh
index cb03d28..99ab7ca 100755
--- a/t/t4202-log.sh
+++ b/t/t4202-log.sh
@@ -3,6 +3,7 @@
 test_description='git log'
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-gpg.sh"
 
 test_expect_success setup '
 
@@ -841,4 +842,34 @@
 	test_cmp expect actual
 '
 
+test_expect_success GPG 'log --graph --show-signature' '
+	test_when_finished "git reset --hard && git checkout master" &&
+	git checkout -b signed master &&
+	echo foo >foo &&
+	git add foo &&
+	git commit -S -m signed_commit &&
+	git log --graph --show-signature -n1 signed >actual &&
+	grep "^| gpg: Signature made" actual &&
+	grep "^| gpg: Good signature" actual
+'
+
+test_expect_success GPG 'log --graph --show-signature for merged tag' '
+	test_when_finished "git reset --hard && git checkout master" &&
+	git checkout -b plain master &&
+	echo aaa >bar &&
+	git add bar &&
+	git commit -m bar_commit &&
+	git checkout -b tagged master &&
+	echo bbb >baz &&
+	git add baz &&
+	git commit -m baz_commit &&
+	git tag -s -m signed_tag_msg signed_tag &&
+	git checkout plain &&
+	git merge --no-ff -m msg signed_tag &&
+	git log --graph --show-signature -n1 plain >actual &&
+	grep "^|\\\  merged tag" actual &&
+	grep "^| | gpg: Signature made" actual &&
+	grep "^| | gpg: Good signature" actual
+'
+
 test_done
diff --git a/t/t4255-am-submodule.sh b/t/t4255-am-submodule.sh
new file mode 100755
index 0000000..8bde7db
--- /dev/null
+++ b/t/t4255-am-submodule.sh
@@ -0,0 +1,21 @@
+#!/bin/sh
+
+test_description='git am handling submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+am () {
+	git format-patch --stdout --ignore-submodules=dirty "..$1" | git am -
+}
+
+test_submodule_switch "am"
+
+am_3way () {
+	git format-patch --stdout --ignore-submodules=dirty "..$1" | git am --3way -
+}
+
+KNOWN_FAILURE_NOFF_MERGE_ATTEMPTS_TO_MERGE_REMOVED_SUBMODULE_FILES=1
+test_submodule_switch "am_3way"
+
+test_done
diff --git a/t/t5539-fetch-http-shallow.sh b/t/t5539-fetch-http-shallow.sh
index 94553e1..b461188 100755
--- a/t/t5539-fetch-http-shallow.sh
+++ b/t/t5539-fetch-http-shallow.sh
@@ -54,6 +54,7 @@
 test_expect_success 'no shallow lines after receiving ACK ready' '
 	(
 		cd shallow &&
+		test_tick &&
 		for i in $(test_seq 15)
 		do
 			git checkout --orphan unrelated$i &&
diff --git a/t/t5572-pull-submodule.sh b/t/t5572-pull-submodule.sh
new file mode 100755
index 0000000..accfa5c
--- /dev/null
+++ b/t/t5572-pull-submodule.sh
@@ -0,0 +1,45 @@
+#!/bin/sh
+
+test_description='pull can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+reset_branch_to_HEAD () {
+	git branch -D "$1" &&
+	git checkout -b "$1" HEAD &&
+	git branch --set-upstream-to="origin/$1" "$1"
+}
+
+git_pull () {
+	reset_branch_to_HEAD "$1" &&
+	git pull
+}
+
+# pulls without conflicts
+test_submodule_switch "git_pull"
+
+git_pull_ff () {
+	reset_branch_to_HEAD "$1" &&
+	git pull --ff
+}
+
+test_submodule_switch "git_pull_ff"
+
+git_pull_ff_only () {
+	reset_branch_to_HEAD "$1" &&
+	git pull --ff-only
+}
+
+test_submodule_switch "git_pull_ff_only"
+
+git_pull_noff () {
+	reset_branch_to_HEAD "$1" &&
+	git pull --no-ff
+}
+
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+KNOWN_FAILURE_NOFF_MERGE_ATTEMPTS_TO_MERGE_REMOVED_SUBMODULE_FILES=1
+test_submodule_switch "git_pull_noff"
+
+test_done
diff --git a/t/t6023-merge-file.sh b/t/t6023-merge-file.sh
index 432f086..3758961 100755
--- a/t/t6023-merge-file.sh
+++ b/t/t6023-merge-file.sh
@@ -77,12 +77,29 @@
 	"git merge-file --quiet test.txt orig.txt new2.txt"
 
 cp new1.txt test2.txt
-test_expect_success "merge without conflict (missing LF at EOF)" \
-	"git merge-file test2.txt orig.txt new2.txt"
+test_expect_failure "merge without conflict (missing LF at EOF)" \
+	"git merge-file test2.txt orig.txt new4.txt"
 
-test_expect_success "merge result added missing LF" \
+test_expect_failure "merge result added missing LF" \
 	"test_cmp test.txt test2.txt"
 
+cp new4.txt test3.txt
+test_expect_success "merge without conflict (missing LF at EOF, away from change in the other file)" \
+	"git merge-file --quiet test3.txt new2.txt new3.txt"
+
+cat > expect.txt << EOF
+DOMINUS regit me,
+et nihil mihi deerit.
+In loco pascuae ibi me collocavit,
+super aquam refectionis educavit me;
+animam meam convertit,
+deduxit me super semitas jusitiae,
+EOF
+printf "propter nomen suum." >> expect.txt
+
+test_expect_success "merge does not add LF away of change" \
+	"test_cmp test3.txt expect.txt"
+
 cp test.txt backup.txt
 test_expect_success "merge with conflicts" \
 	"test_must_fail git merge-file test.txt orig.txt new3.txt"
@@ -107,6 +124,55 @@
 test_expect_success "expected conflict markers" "test_cmp test.txt expect.txt"
 
 cp backup.txt test.txt
+
+cat > expect.txt << EOF
+Dominus regit me, et nihil mihi deerit.
+In loco pascuae ibi me collocavit,
+super aquam refectionis educavit me;
+animam meam convertit,
+deduxit me super semitas jusitiae,
+propter nomen suum.
+Nam et si ambulavero in medio umbrae mortis,
+non timebo mala, quoniam tu mecum es:
+virga tua et baculus tuus ipsa me consolata sunt.
+EOF
+test_expect_success "merge conflicting with --ours" \
+	"git merge-file --ours test.txt orig.txt new3.txt && test_cmp test.txt expect.txt"
+cp backup.txt test.txt
+
+cat > expect.txt << EOF
+DOMINUS regit me,
+et nihil mihi deerit.
+In loco pascuae ibi me collocavit,
+super aquam refectionis educavit me;
+animam meam convertit,
+deduxit me super semitas jusitiae,
+propter nomen suum.
+Nam et si ambulavero in medio umbrae mortis,
+non timebo mala, quoniam tu mecum es:
+virga tua et baculus tuus ipsa me consolata sunt.
+EOF
+test_expect_success "merge conflicting with --theirs" \
+	"git merge-file --theirs test.txt orig.txt new3.txt && test_cmp test.txt expect.txt"
+cp backup.txt test.txt
+
+cat > expect.txt << EOF
+Dominus regit me, et nihil mihi deerit.
+DOMINUS regit me,
+et nihil mihi deerit.
+In loco pascuae ibi me collocavit,
+super aquam refectionis educavit me;
+animam meam convertit,
+deduxit me super semitas jusitiae,
+propter nomen suum.
+Nam et si ambulavero in medio umbrae mortis,
+non timebo mala, quoniam tu mecum es:
+virga tua et baculus tuus ipsa me consolata sunt.
+EOF
+test_expect_success "merge conflicting with --union" \
+	"git merge-file --union test.txt orig.txt new3.txt && test_cmp test.txt expect.txt"
+cp backup.txt test.txt
+
 test_expect_success "merge with conflicts, using -L" \
 	"test_must_fail git merge-file -L 1 -L 2 test.txt orig.txt new3.txt"
 
@@ -260,4 +326,23 @@
 	test_cmp expect actual
 '
 
+printf "line1\nline2\nline3" >nolf-orig.txt
+printf "line1\nline2\nline3x" >nolf-diff1.txt
+printf "line1\nline2\nline3y" >nolf-diff2.txt
+
+test_expect_success 'conflict at EOF without LF resolved by --ours' \
+	'git merge-file -p --ours nolf-diff1.txt nolf-orig.txt nolf-diff2.txt >output.txt &&
+	 printf "line1\nline2\nline3x" >expect.txt &&
+	 test_cmp expect.txt output.txt'
+
+test_expect_success 'conflict at EOF without LF resolved by --theirs' \
+	'git merge-file -p --theirs nolf-diff1.txt nolf-orig.txt nolf-diff2.txt >output.txt &&
+	 printf "line1\nline2\nline3y" >expect.txt &&
+	 test_cmp expect.txt output.txt'
+
+test_expect_success 'conflict at EOF without LF resolved by --union' \
+	'git merge-file -p --union nolf-diff1.txt nolf-orig.txt nolf-diff2.txt >output.txt &&
+	 printf "line1\nline2\nline3x\nline3y" >expect.txt &&
+	 test_cmp expect.txt output.txt'
+
 test_done
diff --git a/t/t6041-bisect-submodule.sh b/t/t6041-bisect-submodule.sh
new file mode 100755
index 0000000..c6b7aa6
--- /dev/null
+++ b/t/t6041-bisect-submodule.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+
+test_description='bisect can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+git_bisect () {
+	git status -su >expect &&
+	ls -1pR * >>expect &&
+	tar czf "$TRASH_DIRECTORY/tmp.tgz" * &&
+	GOOD=$(git rev-parse --verify HEAD) &&
+	git checkout "$1" &&
+	echo "foo" >bar &&
+	git add bar &&
+	git commit -m "bisect bad" &&
+	BAD=$(git rev-parse --verify HEAD) &&
+	git reset --hard HEAD^^ &&
+	git submodule update &&
+	git bisect start &&
+	git bisect good $GOOD &&
+	rm -rf * &&
+	tar xzf "$TRASH_DIRECTORY/tmp.tgz" &&
+	git status -su >actual &&
+	ls -1pR * >>actual &&
+	test_cmp expect actual &&
+	git bisect bad $BAD
+}
+
+test_submodule_switch "git_bisect"
+
+test_done
diff --git a/t/t6050-replace.sh b/t/t6050-replace.sh
index 68b3cb2..4d5a25e 100755
--- a/t/t6050-replace.sh
+++ b/t/t6050-replace.sh
@@ -7,8 +7,9 @@
 exec </dev/null
 
 . ./test-lib.sh
+. "$TEST_DIRECTORY/lib-gpg.sh"
 
-add_and_commit_file()
+add_and_commit_file ()
 {
     _file="$1"
     _msg="$2"
@@ -18,6 +19,38 @@
     git commit --quiet -m "$_file: $_msg"
 }
 
+commit_buffer_contains_parents ()
+{
+    git cat-file commit "$1" >payload &&
+    sed -n -e '/^$/q' -e '/^parent /p' <payload >actual &&
+    shift &&
+    for _parent
+    do
+	echo "parent $_parent"
+    done >expected &&
+    test_cmp expected actual
+}
+
+commit_peeling_shows_parents ()
+{
+    _parent_number=1
+    _commit="$1"
+    shift &&
+    for _parent
+    do
+	_found=$(git rev-parse --verify $_commit^$_parent_number) || return 1
+	test "$_found" = "$_parent" || return 1
+	_parent_number=$(( $_parent_number + 1 ))
+    done &&
+    test_must_fail git rev-parse --verify $_commit^$_parent_number
+}
+
+commit_has_parents ()
+{
+    commit_buffer_contains_parents "$@" &&
+    commit_peeling_shows_parents "$@"
+}
+
 HASH1=
 HASH2=
 HASH3=
@@ -27,36 +60,36 @@
 HASH7=
 
 test_expect_success 'set up buggy branch' '
-     echo "line 1" >> hello &&
-     echo "line 2" >> hello &&
-     echo "line 3" >> hello &&
-     echo "line 4" >> hello &&
+     echo "line 1" >>hello &&
+     echo "line 2" >>hello &&
+     echo "line 3" >>hello &&
+     echo "line 4" >>hello &&
      add_and_commit_file hello "4 lines" &&
      HASH1=$(git rev-parse --verify HEAD) &&
-     echo "line BUG" >> hello &&
-     echo "line 6" >> hello &&
-     echo "line 7" >> hello &&
-     echo "line 8" >> hello &&
+     echo "line BUG" >>hello &&
+     echo "line 6" >>hello &&
+     echo "line 7" >>hello &&
+     echo "line 8" >>hello &&
      add_and_commit_file hello "4 more lines with a BUG" &&
      HASH2=$(git rev-parse --verify HEAD) &&
-     echo "line 9" >> hello &&
-     echo "line 10" >> hello &&
+     echo "line 9" >>hello &&
+     echo "line 10" >>hello &&
      add_and_commit_file hello "2 more lines" &&
      HASH3=$(git rev-parse --verify HEAD) &&
-     echo "line 11" >> hello &&
+     echo "line 11" >>hello &&
      add_and_commit_file hello "1 more line" &&
      HASH4=$(git rev-parse --verify HEAD) &&
-     sed -e "s/BUG/5/" hello > hello.new &&
+     sed -e "s/BUG/5/" hello >hello.new &&
      mv hello.new hello &&
      add_and_commit_file hello "BUG fixed" &&
      HASH5=$(git rev-parse --verify HEAD) &&
-     echo "line 12" >> hello &&
-     echo "line 13" >> hello &&
+     echo "line 12" >>hello &&
+     echo "line 13" >>hello &&
      add_and_commit_file hello "2 more lines" &&
      HASH6=$(git rev-parse --verify HEAD) &&
-     echo "line 14" >> hello &&
-     echo "line 15" >> hello &&
-     echo "line 16" >> hello &&
+     echo "line 14" >>hello &&
+     echo "line 15" >>hello &&
+     echo "line 16" >>hello &&
      add_and_commit_file hello "again 3 more lines" &&
      HASH7=$(git rev-parse --verify HEAD)
 '
@@ -95,7 +128,7 @@
 '
 
 test_expect_success '"git fsck" works' '
-     git fsck master > fsck_master.out &&
+     git fsck master >fsck_master.out &&
      grep "dangling commit $R" fsck_master.out &&
      grep "dangling tag $(cat .git/refs/tags/mytag)" fsck_master.out &&
      test -z "$(git fsck)"
@@ -217,14 +250,14 @@
      (
 	  cd clone_dir &&
 	  git fetch origin refs/heads/tofetch:refs/heads/parallel3 &&
-	  git log --pretty=oneline parallel3 > output.txt &&
+	  git log --pretty=oneline parallel3 >output.txt &&
 	  ! grep $PARA3 output.txt &&
-	  git show $PARA3 > para3.txt &&
+	  git show $PARA3 >para3.txt &&
 	  grep "A U Thor" para3.txt &&
 	  git fetch origin "refs/replace/*:refs/replace/*" &&
-	  git log --pretty=oneline parallel3 > output.txt &&
+	  git log --pretty=oneline parallel3 >output.txt &&
 	  grep $PARA3 output.txt &&
-	  git show $PARA3 > para3.txt &&
+	  git show $PARA3 >para3.txt &&
 	  grep "O Thor" para3.txt
      )
 '
@@ -302,7 +335,7 @@
 		echo "$PARA3 -> $S" &&
 		echo "$MYTAG -> $HASH1"
 	} | sort >expected &&
-	git replace -l --format medium | sort > actual &&
+	git replace -l --format medium | sort >actual &&
 	test_cmp expected actual
 '
 
@@ -314,7 +347,7 @@
 		echo "$PARA3 (commit) -> $S (commit)" &&
 		echo "$MYTAG (tag) -> $HASH1 (commit)"
 	} | sort >expected &&
-	git replace --format=long | sort > actual &&
+	git replace --format=long | sort >actual &&
 	test_cmp expected actual
 '
 
@@ -351,4 +384,60 @@
 	test -z "$(git replace)"
 '
 
+test_expect_success '--graft with and without already replaced object' '
+	test $(git log --oneline | wc -l) = 7 &&
+	git replace --graft $HASH5 &&
+	test $(git log --oneline | wc -l) = 3 &&
+	commit_has_parents $HASH5 &&
+	test_must_fail git replace --graft $HASH5 $HASH4 $HASH3 &&
+	git replace --force -g $HASH5 $HASH4 $HASH3 &&
+	commit_has_parents $HASH5 $HASH4 $HASH3 &&
+	git replace -d $HASH5
+'
+
+test_expect_success GPG 'set up a signed commit' '
+	echo "line 17" >>hello &&
+	echo "line 18" >>hello &&
+	git add hello &&
+	test_tick &&
+	git commit --quiet -S -m "hello: 2 more lines in a signed commit" &&
+	HASH8=$(git rev-parse --verify HEAD) &&
+	git verify-commit $HASH8
+'
+
+test_expect_success GPG '--graft with a signed commit' '
+	git cat-file commit $HASH8 >orig &&
+	git replace --graft $HASH8 &&
+	git cat-file commit $HASH8 >repl &&
+	commit_has_parents $HASH8 &&
+	test_must_fail git verify-commit $HASH8 &&
+	sed -n -e "/^tree /p" -e "/^author /p" -e "/^committer /p" orig >expected &&
+	echo >>expected &&
+	sed -e "/^$/q" repl >actual &&
+	test_cmp expected actual &&
+	git replace -d $HASH8
+'
+
+test_expect_success GPG 'set up a merge commit with a mergetag' '
+	git reset --hard HEAD &&
+	git checkout -b test_branch HEAD~2 &&
+	echo "line 1 from test branch" >>hello &&
+	echo "line 2 from test branch" >>hello &&
+	git add hello &&
+	test_tick &&
+	git commit -m "hello: 2 more lines from a test branch" &&
+	HASH9=$(git rev-parse --verify HEAD) &&
+	git tag -s -m "tag for testing with a mergetag" test_tag HEAD &&
+	git checkout master &&
+	git merge -s ours test_tag &&
+	HASH10=$(git rev-parse --verify HEAD) &&
+	git cat-file commit $HASH10 | grep "^mergetag object"
+'
+
+test_expect_success GPG '--graft on a commit with a mergetag' '
+	test_must_fail git replace --graft $HASH10 $HASH8^1 &&
+	git replace --graft $HASH10 $HASH8^1 $HASH9 &&
+	git replace -d $HASH10
+'
+
 test_done
diff --git a/t/t7003-filter-branch.sh b/t/t7003-filter-branch.sh
index 9496736..66643e4 100755
--- a/t/t7003-filter-branch.sh
+++ b/t/t7003-filter-branch.sh
@@ -308,6 +308,17 @@
 	test_cmp expect actual
 '
 
+test_expect_success 'prune empty collapsed merges' '
+	test_config merge.ff false &&
+	git rev-list HEAD >expect &&
+	test_commit to_remove_2 &&
+	git reset --hard HEAD^ &&
+	test_merge non-ff to_remove_2 &&
+	git filter-branch -f --index-filter "git update-index --remove to_remove_2.t" --prune-empty HEAD &&
+	git rev-list HEAD >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success '--remap-to-ancestor with filename filters' '
 	git checkout master &&
 	git reset --hard A &&
diff --git a/t/t7004-tag.sh b/t/t7004-tag.sh
index e4ab0f5..0366653 100755
--- a/t/t7004-tag.sh
+++ b/t/t7004-tag.sh
@@ -1385,41 +1385,77 @@
 	git tag foo1.6 &&
 	git tag foo1.10 &&
 	git tag -l --sort=refname "foo*" >actual &&
-	cat >expect <<EOF &&
-foo1.10
-foo1.3
-foo1.6
-EOF
+	cat >expect <<-\EOF &&
+	foo1.10
+	foo1.3
+	foo1.6
+	EOF
 	test_cmp expect actual
 '
 
 test_expect_success 'version sort' '
 	git tag -l --sort=version:refname "foo*" >actual &&
-	cat >expect <<EOF &&
-foo1.3
-foo1.6
-foo1.10
-EOF
+	cat >expect <<-\EOF &&
+	foo1.3
+	foo1.6
+	foo1.10
+	EOF
 	test_cmp expect actual
 '
 
 test_expect_success 'reverse version sort' '
 	git tag -l --sort=-version:refname "foo*" >actual &&
-	cat >expect <<EOF &&
-foo1.10
-foo1.6
-foo1.3
-EOF
+	cat >expect <<-\EOF &&
+	foo1.10
+	foo1.6
+	foo1.3
+	EOF
 	test_cmp expect actual
 '
 
 test_expect_success 'reverse lexical sort' '
 	git tag -l --sort=-refname "foo*" >actual &&
-	cat >expect <<EOF &&
-foo1.6
-foo1.3
-foo1.10
-EOF
+	cat >expect <<-\EOF &&
+	foo1.6
+	foo1.3
+	foo1.10
+	EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'configured lexical sort' '
+	git config tag.sort "v:refname" &&
+	git tag -l "foo*" >actual &&
+	cat >expect <<-\EOF &&
+	foo1.3
+	foo1.6
+	foo1.10
+	EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'option override configured sort' '
+	git tag -l --sort=-refname "foo*" >actual &&
+	cat >expect <<-\EOF &&
+	foo1.6
+	foo1.3
+	foo1.10
+	EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'invalid sort parameter on command line' '
+	test_must_fail git tag -l --sort=notvalid "foo*" >actual
+'
+
+test_expect_success 'invalid sort parameter in configuratoin' '
+	git config tag.sort "v:notvalid" &&
+	git tag -l "foo*" >actual &&
+	cat >expect <<-\EOF &&
+	foo1.10
+	foo1.3
+	foo1.6
+	EOF
 	test_cmp expect actual
 '
 
diff --git a/t/t7112-reset-submodule.sh b/t/t7112-reset-submodule.sh
new file mode 100755
index 0000000..2eda6ad
--- /dev/null
+++ b/t/t7112-reset-submodule.sh
@@ -0,0 +1,14 @@
+#!/bin/sh
+
+test_description='reset can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+test_submodule_switch "git reset --keep"
+
+test_submodule_switch "git reset --merge"
+
+test_submodule_forced_switch "git reset --hard"
+
+test_done
diff --git a/t/t7613-merge-submodule.sh b/t/t7613-merge-submodule.sh
new file mode 100755
index 0000000..d1e9fcc
--- /dev/null
+++ b/t/t7613-merge-submodule.sh
@@ -0,0 +1,19 @@
+#!/bin/sh
+
+test_description='merge can handle submodules'
+
+. ./test-lib.sh
+. "$TEST_DIRECTORY"/lib-submodule-update.sh
+
+# merges without conflicts
+test_submodule_switch "git merge"
+
+test_submodule_switch "git merge --ff"
+
+test_submodule_switch "git merge --ff-only"
+
+KNOWN_FAILURE_NOFF_MERGE_DOESNT_CREATE_EMPTY_SUBMODULE_DIR=1
+KNOWN_FAILURE_NOFF_MERGE_ATTEMPTS_TO_MERGE_REMOVED_SUBMODULE_FILES=1
+test_submodule_switch "git merge --no-ff"
+
+test_done
diff --git a/t/t7702-repack-cyclic-alternate.sh b/t/t7702-repack-cyclic-alternate.sh
new file mode 100755
index 0000000..93b7486
--- /dev/null
+++ b/t/t7702-repack-cyclic-alternate.sh
@@ -0,0 +1,24 @@
+#!/bin/sh
+#
+# Copyright (c) 2014 Ephrim Khong
+#
+
+test_description='repack involving cyclic alternate'
+. ./test-lib.sh
+
+test_expect_success setup '
+	GIT_OBJECT_DIRECTORY=.git//../.git/objects &&
+	export GIT_OBJECT_DIRECTORY &&
+	touch a &&
+	git add a &&
+	git commit -m 1 &&
+	git repack -adl &&
+	echo "$(pwd)"/.git/objects/../objects >.git/objects/info/alternates
+'
+
+test_expect_success 're-packing repository with itsself as alternate' '
+	git repack -adl &&
+	git fsck
+'
+
+test_done
diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh
index 0377d3e..dafd6ad 100644
--- a/t/test-lib-functions.sh
+++ b/t/test-lib-functions.sh
@@ -489,6 +489,17 @@
 	fi
 }
 
+# Check if the directory exists and is empty as expected, barf otherwise.
+test_dir_is_empty () {
+	test_path_is_dir "$1" &&
+	if test -n "$(ls -a1 "$1" | egrep -v '^\.\.?$')"
+	then
+		echo "Directory '$1' is not empty, it contains:"
+		ls -la "$1"
+		return 1
+	fi
+}
+
 test_path_is_missing () {
 	if [ -e "$1" ]
 	then
diff --git a/t/test-lib.sh b/t/test-lib.sh
index a479537..b1bc65b 100644
--- a/t/test-lib.sh
+++ b/t/test-lib.sh
@@ -109,6 +109,10 @@
 export GIT_COMMITTER_EMAIL GIT_COMMITTER_NAME
 export EDITOR
 
+# Tests using GIT_TRACE typically don't want <timestamp> <file>:<line> output
+GIT_TRACE_BARE=1
+export GIT_TRACE_BARE
+
 if test -n "${TEST_GIT_INDEX_VERSION:+isset}"
 then
 	GIT_INDEX_VERSION="$TEST_GIT_INDEX_VERSION"
diff --git a/tag.c b/tag.c
index 7b07921..82d841b 100644
--- a/tag.c
+++ b/tag.c
@@ -40,15 +40,8 @@
 {
 	struct object *obj = lookup_object(sha1);
 	if (!obj)
-		return create_object(sha1, OBJ_TAG, alloc_tag_node());
-	if (!obj->type)
-		obj->type = OBJ_TAG;
-	if (obj->type != OBJ_TAG) {
-		error("Object %s is a %s, not a tag",
-		      sha1_to_hex(sha1), typename(obj->type));
-		return NULL;
-	}
-	return (struct tag *) obj;
+		return create_object(sha1, alloc_tag_node());
+	return object_as_type(obj, OBJ_TAG, 0);
 }
 
 static unsigned long parse_tag_date(const char *buf, const char *tail)
diff --git a/test-dump-cache-tree.c b/test-dump-cache-tree.c
index 47eab97..330ba4f 100644
--- a/test-dump-cache-tree.c
+++ b/test-dump-cache-tree.c
@@ -56,11 +56,12 @@
 
 int main(int ac, char **av)
 {
+	struct index_state istate;
 	struct cache_tree *another = cache_tree();
 	if (read_cache() < 0)
 		die("unable to read index file");
-	cache_tree_update(another,
-			  (const struct cache_entry * const *)active_cache,
-			  active_nr, WRITE_TREE_DRY_RUN);
+	istate = the_index;
+	istate.cache_tree = another;
+	cache_tree_update(&istate, WRITE_TREE_DRY_RUN);
 	return dump_cache_tree(active_cache_tree, another, "");
 }
diff --git a/test-dump-split-index.c b/test-dump-split-index.c
new file mode 100644
index 0000000..9cf3112
--- /dev/null
+++ b/test-dump-split-index.c
@@ -0,0 +1,34 @@
+#include "cache.h"
+#include "split-index.h"
+#include "ewah/ewok.h"
+
+static void show_bit(size_t pos, void *data)
+{
+	printf(" %d", (int)pos);
+}
+
+int main(int ac, char **av)
+{
+	struct split_index *si;
+	int i;
+
+	do_read_index(&the_index, av[1], 1);
+	printf("own %s\n", sha1_to_hex(the_index.sha1));
+	si = the_index.split_index;
+	if (!si) {
+		printf("not a split index\n");
+		return 0;
+	}
+	printf("base %s\n", sha1_to_hex(si->base_sha1));
+	for (i = 0; i < the_index.cache_nr; i++) {
+		struct cache_entry *ce = the_index.cache[i];
+		printf("%06o %s %d\t%s\n", ce->ce_mode,
+		       sha1_to_hex(ce->sha1), ce_stage(ce), ce->name);
+	}
+	printf("replacements:");
+	ewah_each_bit(si->replace_bitmap, show_bit, NULL);
+	printf("\ndeletions:");
+	ewah_each_bit(si->delete_bitmap, show_bit, NULL);
+	printf("\n");
+	return 0;
+}
diff --git a/test-hashmap.c b/test-hashmap.c
index f5183fb..07aa7ec 100644
--- a/test-hashmap.c
+++ b/test-hashmap.c
@@ -115,9 +115,8 @@
 
 		for (j = 0; j < rounds; j++) {
 			for (i = 0; i < TEST_SIZE; i++) {
-				struct hashmap_entry key;
-				hashmap_entry_init(&key, hashes[i]);
-				hashmap_get(&map, &key, entries[i]->key);
+				hashmap_get_from_hash(&map, hashes[i],
+						      entries[i]->key);
 			}
 		}
 
@@ -199,12 +198,8 @@
 
 		} else if (!strcmp("get", cmd) && l1) {
 
-			/* setup static key */
-			struct hashmap_entry key;
-			hashmap_entry_init(&key, hash);
-
 			/* lookup entry in hashmap */
-			entry = hashmap_get(&map, &key, p1);
+			entry = hashmap_get_from_hash(&map, hash, p1);
 
 			/* print result */
 			if (!entry)
@@ -239,6 +234,20 @@
 			/* print table sizes */
 			printf("%u %u\n", map.tablesize, map.size);
 
+		} else if (!strcmp("intern", cmd) && l1) {
+
+			/* test that strintern works */
+			const char *i1 = strintern(p1);
+			const char *i2 = strintern(p1);
+			if (strcmp(i1, p1))
+				printf("strintern(%s) returns %s\n", p1, i1);
+			else if (i1 == p1)
+				printf("strintern(%s) returns input pointer\n", p1);
+			else if (i1 != i2)
+				printf("strintern(%s) != strintern(%s)", i1, i2);
+			else
+				printf("%s\n", i1);
+
 		} else if (!strcmp("perfhashmap", cmd) && l1 && l2) {
 
 			perf_hashmap(atoi(p1), atoi(p2));
diff --git a/test-scrap-cache-tree.c b/test-scrap-cache-tree.c
index 4728013..9ebcbca 100644
--- a/test-scrap-cache-tree.c
+++ b/test-scrap-cache-tree.c
@@ -6,12 +6,11 @@
 
 int main(int ac, char **av)
 {
-	int fd = hold_locked_index(&index_lock, 1);
+	hold_locked_index(&index_lock, 1);
 	if (read_cache() < 0)
 		die("unable to read index file");
 	active_cache_tree = NULL;
-	if (write_cache(fd, active_cache, active_nr)
-	    || commit_lock_file(&index_lock))
+	if (write_locked_index(&the_index, &index_lock, COMMIT_LOCK))
 		die("unable to write index file");
 	return 0;
 }
diff --git a/trace.c b/trace.c
index 08180a9..e583dc6 100644
--- a/trace.c
+++ b/trace.c
@@ -26,110 +26,250 @@
 #include "quote.h"
 
 /* Get a trace file descriptor from "key" env variable. */
-static int get_trace_fd(const char *key, int *need_close)
+static int get_trace_fd(struct trace_key *key)
 {
-	char *trace = getenv(key);
+	static struct trace_key trace_default = { "GIT_TRACE" };
+	const char *trace;
+
+	/* use default "GIT_TRACE" if NULL */
+	if (!key)
+		key = &trace_default;
+
+	/* don't open twice */
+	if (key->initialized)
+		return key->fd;
+
+	trace = getenv(key->key);
 
 	if (!trace || !strcmp(trace, "") ||
 	    !strcmp(trace, "0") || !strcasecmp(trace, "false"))
-		return 0;
-	if (!strcmp(trace, "1") || !strcasecmp(trace, "true"))
-		return STDERR_FILENO;
-	if (strlen(trace) == 1 && isdigit(*trace))
-		return atoi(trace);
-	if (is_absolute_path(trace)) {
+		key->fd = 0;
+	else if (!strcmp(trace, "1") || !strcasecmp(trace, "true"))
+		key->fd = STDERR_FILENO;
+	else if (strlen(trace) == 1 && isdigit(*trace))
+		key->fd = atoi(trace);
+	else if (is_absolute_path(trace)) {
 		int fd = open(trace, O_WRONLY | O_APPEND | O_CREAT, 0666);
 		if (fd == -1) {
 			fprintf(stderr,
 				"Could not open '%s' for tracing: %s\n"
 				"Defaulting to tracing on stderr...\n",
 				trace, strerror(errno));
-			return STDERR_FILENO;
+			key->fd = STDERR_FILENO;
+		} else {
+			key->fd = fd;
+			key->need_close = 1;
 		}
-		*need_close = 1;
-		return fd;
+	} else {
+		fprintf(stderr, "What does '%s' for %s mean?\n"
+			"If you want to trace into a file, then please set "
+			"%s to an absolute pathname (starting with /).\n"
+			"Defaulting to tracing on stderr...\n",
+			trace, key->key, key->key);
+		key->fd = STDERR_FILENO;
 	}
 
-	fprintf(stderr, "What does '%s' for %s mean?\n", trace, key);
-	fprintf(stderr, "If you want to trace into a file, "
-		"then please set %s to an absolute pathname "
-		"(starting with /).\n", key);
-	fprintf(stderr, "Defaulting to tracing on stderr...\n");
+	key->initialized = 1;
+	return key->fd;
+}
 
-	return STDERR_FILENO;
+void trace_disable(struct trace_key *key)
+{
+	if (key->need_close)
+		close(key->fd);
+	key->fd = 0;
+	key->initialized = 1;
+	key->need_close = 0;
 }
 
 static const char err_msg[] = "Could not trace into fd given by "
 	"GIT_TRACE environment variable";
 
-static void trace_vprintf(const char *key, const char *fmt, va_list ap)
+static int prepare_trace_line(const char *file, int line,
+			      struct trace_key *key, struct strbuf *buf)
 {
-	struct strbuf buf = STRBUF_INIT;
+	static struct trace_key trace_bare = TRACE_KEY_INIT(BARE);
+	struct timeval tv;
+	struct tm tm;
+	time_t secs;
 
 	if (!trace_want(key))
-		return;
+		return 0;
 
 	set_try_to_free_routine(NULL);	/* is never reset */
-	strbuf_vaddf(&buf, fmt, ap);
-	trace_strbuf(key, &buf);
-	strbuf_release(&buf);
+
+	/* unit tests may want to disable additional trace output */
+	if (trace_want(&trace_bare))
+		return 1;
+
+	/* print current timestamp */
+	gettimeofday(&tv, NULL);
+	secs = tv.tv_sec;
+	localtime_r(&secs, &tm);
+	strbuf_addf(buf, "%02d:%02d:%02d.%06ld ", tm.tm_hour, tm.tm_min,
+		    tm.tm_sec, (long) tv.tv_usec);
+
+#ifdef HAVE_VARIADIC_MACROS
+	/* print file:line */
+	strbuf_addf(buf, "%s:%d ", file, line);
+	/* align trace output (column 40 catches most files names in git) */
+	while (buf->len < 40)
+		strbuf_addch(buf, ' ');
+#endif
+
+	return 1;
 }
 
-__attribute__((format (printf, 2, 3)))
-void trace_printf_key(const char *key, const char *fmt, ...)
+static void print_trace_line(struct trace_key *key, struct strbuf *buf)
 {
-	va_list ap;
-	va_start(ap, fmt);
-	trace_vprintf(key, fmt, ap);
-	va_end(ap);
+	/* append newline if missing */
+	if (buf->len && buf->buf[buf->len - 1] != '\n')
+		strbuf_addch(buf, '\n');
+
+	write_or_whine_pipe(get_trace_fd(key), buf->buf, buf->len, err_msg);
+	strbuf_release(buf);
 }
 
-void trace_printf(const char *fmt, ...)
-{
-	va_list ap;
-	va_start(ap, fmt);
-	trace_vprintf("GIT_TRACE", fmt, ap);
-	va_end(ap);
-}
-
-void trace_strbuf(const char *key, const struct strbuf *buf)
-{
-	int fd, need_close = 0;
-
-	fd = get_trace_fd(key, &need_close);
-	if (!fd)
-		return;
-
-	write_or_whine_pipe(fd, buf->buf, buf->len, err_msg);
-
-	if (need_close)
-		close(fd);
-}
-
-void trace_argv_printf(const char **argv, const char *fmt, ...)
+static void trace_vprintf_fl(const char *file, int line, struct trace_key *key,
+			     const char *format, va_list ap)
 {
 	struct strbuf buf = STRBUF_INIT;
-	va_list ap;
-	int fd, need_close = 0;
 
-	fd = get_trace_fd("GIT_TRACE", &need_close);
-	if (!fd)
+	if (!prepare_trace_line(file, line, key, &buf))
 		return;
 
-	set_try_to_free_routine(NULL);	/* is never reset */
-	va_start(ap, fmt);
-	strbuf_vaddf(&buf, fmt, ap);
-	va_end(ap);
+	strbuf_vaddf(&buf, format, ap);
+	print_trace_line(key, &buf);
+}
+
+static void trace_argv_vprintf_fl(const char *file, int line,
+				  const char **argv, const char *format,
+				  va_list ap)
+{
+	struct strbuf buf = STRBUF_INIT;
+
+	if (!prepare_trace_line(file, line, NULL, &buf))
+		return;
+
+	strbuf_vaddf(&buf, format, ap);
 
 	sq_quote_argv(&buf, argv, 0);
-	strbuf_addch(&buf, '\n');
-	write_or_whine_pipe(fd, buf.buf, buf.len, err_msg);
-	strbuf_release(&buf);
-
-	if (need_close)
-		close(fd);
+	print_trace_line(NULL, &buf);
 }
 
+void trace_strbuf_fl(const char *file, int line, struct trace_key *key,
+		     const struct strbuf *data)
+{
+	struct strbuf buf = STRBUF_INIT;
+
+	if (!prepare_trace_line(file, line, key, &buf))
+		return;
+
+	strbuf_addbuf(&buf, data);
+	print_trace_line(key, &buf);
+}
+
+static struct trace_key trace_perf_key = TRACE_KEY_INIT(PERFORMANCE);
+
+static void trace_performance_vprintf_fl(const char *file, int line,
+					 uint64_t nanos, const char *format,
+					 va_list ap)
+{
+	struct strbuf buf = STRBUF_INIT;
+
+	if (!prepare_trace_line(file, line, &trace_perf_key, &buf))
+		return;
+
+	strbuf_addf(&buf, "performance: %.9f s", (double) nanos / 1000000000);
+
+	if (format && *format) {
+		strbuf_addstr(&buf, ": ");
+		strbuf_vaddf(&buf, format, ap);
+	}
+
+	print_trace_line(&trace_perf_key, &buf);
+}
+
+#ifndef HAVE_VARIADIC_MACROS
+
+void trace_printf(const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_vprintf_fl(NULL, 0, NULL, format, ap);
+	va_end(ap);
+}
+
+void trace_printf_key(struct trace_key *key, const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_vprintf_fl(NULL, 0, key, format, ap);
+	va_end(ap);
+}
+
+void trace_argv_printf(const char **argv, const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_argv_vprintf_fl(NULL, 0, argv, format, ap);
+	va_end(ap);
+}
+
+void trace_strbuf(const char *key, const struct strbuf *data)
+{
+	trace_strbuf_fl(NULL, 0, key, data);
+}
+
+void trace_performance(uint64_t nanos, const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_performance_vprintf_fl(NULL, 0, nanos, format, ap);
+	va_end(ap);
+}
+
+void trace_performance_since(uint64_t start, const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_performance_vprintf_fl(NULL, 0, getnanotime() - start,
+				     format, ap);
+	va_end(ap);
+}
+
+#else
+
+void trace_printf_key_fl(const char *file, int line, struct trace_key *key,
+			 const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_vprintf_fl(file, line, key, format, ap);
+	va_end(ap);
+}
+
+void trace_argv_printf_fl(const char *file, int line, const char **argv,
+			  const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_argv_vprintf_fl(file, line, argv, format, ap);
+	va_end(ap);
+}
+
+void trace_performance_fl(const char *file, int line, uint64_t nanos,
+			      const char *format, ...)
+{
+	va_list ap;
+	va_start(ap, format);
+	trace_performance_vprintf_fl(file, line, nanos, format, ap);
+	va_end(ap);
+}
+
+#endif /* HAVE_VARIADIC_MACROS */
+
+
 static const char *quote_crnl(const char *path)
 {
 	static char new_path[PATH_MAX];
@@ -156,11 +296,11 @@
 /* FIXME: move prefix to startup_info struct and get rid of this arg */
 void trace_repo_setup(const char *prefix)
 {
-	static const char *key = "GIT_TRACE_SETUP";
+	static struct trace_key key = TRACE_KEY_INIT(SETUP);
 	const char *git_work_tree;
 	char cwd[PATH_MAX];
 
-	if (!trace_want(key))
+	if (!trace_want(&key))
 		return;
 
 	if (!getcwd(cwd, PATH_MAX))
@@ -172,18 +312,117 @@
 	if (!prefix)
 		prefix = "(null)";
 
-	trace_printf_key(key, "setup: git_dir: %s\n", quote_crnl(get_git_dir()));
-	trace_printf_key(key, "setup: worktree: %s\n", quote_crnl(git_work_tree));
-	trace_printf_key(key, "setup: cwd: %s\n", quote_crnl(cwd));
-	trace_printf_key(key, "setup: prefix: %s\n", quote_crnl(prefix));
+	trace_printf_key(&key, "setup: git_dir: %s\n", quote_crnl(get_git_dir()));
+	trace_printf_key(&key, "setup: worktree: %s\n", quote_crnl(git_work_tree));
+	trace_printf_key(&key, "setup: cwd: %s\n", quote_crnl(cwd));
+	trace_printf_key(&key, "setup: prefix: %s\n", quote_crnl(prefix));
 }
 
-int trace_want(const char *key)
+int trace_want(struct trace_key *key)
 {
-	const char *trace = getenv(key);
+	return !!get_trace_fd(key);
+}
 
-	if (!trace || !strcmp(trace, "") ||
-	    !strcmp(trace, "0") || !strcasecmp(trace, "false"))
+#ifdef HAVE_CLOCK_GETTIME
+
+static inline uint64_t highres_nanos(void)
+{
+	struct timespec ts;
+	if (clock_gettime(CLOCK_MONOTONIC, &ts))
 		return 0;
-	return 1;
+	return (uint64_t) ts.tv_sec * 1000000000 + ts.tv_nsec;
+}
+
+#elif defined (GIT_WINDOWS_NATIVE)
+
+static inline uint64_t highres_nanos(void)
+{
+	static uint64_t high_ns, scaled_low_ns;
+	static int scale;
+	LARGE_INTEGER cnt;
+
+	if (!scale) {
+		if (!QueryPerformanceFrequency(&cnt))
+			return 0;
+
+		/* high_ns = number of ns per cnt.HighPart */
+		high_ns = (1000000000LL << 32) / (uint64_t) cnt.QuadPart;
+
+		/*
+		 * Number of ns per cnt.LowPart is 10^9 / frequency (or
+		 * high_ns >> 32). For maximum precision, we scale this factor
+		 * so that it just fits within 32 bit (i.e. won't overflow if
+		 * multiplied with cnt.LowPart).
+		 */
+		scaled_low_ns = high_ns;
+		scale = 32;
+		while (scaled_low_ns >= 0x100000000LL) {
+			scaled_low_ns >>= 1;
+			scale--;
+		}
+	}
+
+	/* if QPF worked on initialization, we expect QPC to work as well */
+	QueryPerformanceCounter(&cnt);
+
+	return (high_ns * cnt.HighPart) +
+	       ((scaled_low_ns * cnt.LowPart) >> scale);
+}
+
+#else
+# define highres_nanos() 0
+#endif
+
+static inline uint64_t gettimeofday_nanos(void)
+{
+	struct timeval tv;
+	gettimeofday(&tv, NULL);
+	return (uint64_t) tv.tv_sec * 1000000000 + tv.tv_usec * 1000;
+}
+
+/*
+ * Returns nanoseconds since the epoch (01/01/1970), for performance tracing
+ * (i.e. favoring high precision over wall clock time accuracy).
+ */
+inline uint64_t getnanotime(void)
+{
+	static uint64_t offset;
+	if (offset > 1) {
+		/* initialization succeeded, return offset + high res time */
+		return offset + highres_nanos();
+	} else if (offset == 1) {
+		/* initialization failed, fall back to gettimeofday */
+		return gettimeofday_nanos();
+	} else {
+		/* initialize offset if high resolution timer works */
+		uint64_t now = gettimeofday_nanos();
+		uint64_t highres = highres_nanos();
+		if (highres)
+			offset = now - highres;
+		else
+			offset = 1;
+		return now;
+	}
+}
+
+static uint64_t command_start_time;
+static struct strbuf command_line = STRBUF_INIT;
+
+static void print_command_performance_atexit(void)
+{
+	trace_performance_since(command_start_time, "git command:%s",
+				command_line.buf);
+}
+
+void trace_command_performance(const char **argv)
+{
+	if (!trace_want(&trace_perf_key))
+		return;
+
+	if (!command_start_time)
+		atexit(print_command_performance_atexit);
+
+	strbuf_reset(&command_line);
+	sq_quote_argv(&command_line, argv, 0);
+	command_start_time = getnanotime();
 }
diff --git a/trace.h b/trace.h
new file mode 100644
index 0000000..ae6a332
--- /dev/null
+++ b/trace.h
@@ -0,0 +1,113 @@
+#ifndef TRACE_H
+#define TRACE_H
+
+#include "git-compat-util.h"
+#include "strbuf.h"
+
+struct trace_key {
+	const char * const key;
+	int fd;
+	unsigned int initialized : 1;
+	unsigned int  need_close : 1;
+};
+
+#define TRACE_KEY_INIT(name) { "GIT_TRACE_" #name, 0, 0, 0 }
+
+extern void trace_repo_setup(const char *prefix);
+extern int trace_want(struct trace_key *key);
+extern void trace_disable(struct trace_key *key);
+extern uint64_t getnanotime(void);
+extern void trace_command_performance(const char **argv);
+
+#ifndef HAVE_VARIADIC_MACROS
+
+__attribute__((format (printf, 1, 2)))
+extern void trace_printf(const char *format, ...);
+
+__attribute__((format (printf, 2, 3)))
+extern void trace_printf_key(struct trace_key *key, const char *format, ...);
+
+__attribute__((format (printf, 2, 3)))
+extern void trace_argv_printf(const char **argv, const char *format, ...);
+
+extern void trace_strbuf(struct trace_key *key, const struct strbuf *data);
+
+/* Prints elapsed time (in nanoseconds) if GIT_TRACE_PERFORMANCE is enabled. */
+__attribute__((format (printf, 2, 3)))
+extern void trace_performance(uint64_t nanos, const char *format, ...);
+
+/* Prints elapsed time since 'start' if GIT_TRACE_PERFORMANCE is enabled. */
+__attribute__((format (printf, 2, 3)))
+extern void trace_performance_since(uint64_t start, const char *format, ...);
+
+#else
+
+/*
+ * Macros to add file:line - see above for C-style declarations of how these
+ * should be used.
+ */
+
+/*
+ * TRACE_CONTEXT may be set to __FUNCTION__ if the compiler supports it. The
+ * default is __FILE__, as it is consistent with assert(), and static function
+ * names are not necessarily unique.
+ *
+ * __FILE__ ":" __FUNCTION__ doesn't work with GNUC, as __FILE__ is supplied
+ * by the preprocessor as a string literal, and __FUNCTION__ is filled in by
+ * the compiler as a string constant.
+ */
+#ifndef TRACE_CONTEXT
+# define TRACE_CONTEXT __FILE__
+#endif
+
+/*
+ * Note: with C99 variadic macros, __VA_ARGS__ must include the last fixed
+ * parameter ('format' in this case). Otherwise, a call without variable
+ * arguments will have a surplus ','. E.g.:
+ *
+ *  #define foo(format, ...) bar(format, __VA_ARGS__)
+ *  foo("test");
+ *
+ * will expand to
+ *
+ *  bar("test",);
+ *
+ * which is invalid (note the ',)'). With GNUC, '##__VA_ARGS__' drops the
+ * comma, but this is non-standard.
+ */
+
+#define trace_printf(...) \
+	trace_printf_key_fl(TRACE_CONTEXT, __LINE__, NULL, __VA_ARGS__)
+
+#define trace_printf_key(key, ...) \
+	trace_printf_key_fl(TRACE_CONTEXT, __LINE__, key, __VA_ARGS__)
+
+#define trace_argv_printf(argv, ...) \
+	trace_argv_printf_fl(TRACE_CONTEXT, __LINE__, argv, __VA_ARGS__)
+
+#define trace_strbuf(key, data) \
+	trace_strbuf_fl(TRACE_CONTEXT, __LINE__, key, data)
+
+#define trace_performance(nanos, ...) \
+	trace_performance_fl(TRACE_CONTEXT, __LINE__, nanos, __VA_ARGS__)
+
+#define trace_performance_since(start, ...) \
+	trace_performance_fl(TRACE_CONTEXT, __LINE__, getnanotime() - (start), \
+			     __VA_ARGS__)
+
+/* backend functions, use non-*fl macros instead */
+__attribute__((format (printf, 4, 5)))
+extern void trace_printf_key_fl(const char *file, int line, struct trace_key *key,
+				const char *format, ...);
+__attribute__((format (printf, 4, 5)))
+extern void trace_argv_printf_fl(const char *file, int line, const char **argv,
+				 const char *format, ...);
+extern void trace_strbuf_fl(const char *file, int line, struct trace_key *key,
+			    const struct strbuf *data);
+__attribute__((format (printf, 4, 5)))
+extern void trace_performance_fl(const char *file, int line,
+				 uint64_t nanos, const char *fmt, ...);
+
+#endif /* HAVE_VARIADIC_MACROS */
+
+#endif /* TRACE_H */
diff --git a/transport.c b/transport.c
index 59c9727..80ed126 100644
--- a/transport.c
+++ b/transport.c
@@ -263,32 +263,20 @@
 static int fetch_objs_via_rsync(struct transport *transport,
 				int nr_objs, struct ref **to_fetch)
 {
-	struct strbuf buf = STRBUF_INIT;
 	struct child_process rsync;
-	const char *args[8];
-	int result;
-
-	strbuf_addstr(&buf, rsync_url(transport->url));
-	strbuf_addstr(&buf, "/objects/");
 
 	memset(&rsync, 0, sizeof(rsync));
-	rsync.argv = args;
 	rsync.stdout_to_stderr = 1;
-	args[0] = "rsync";
-	args[1] = (transport->verbose > 1) ? "-rv" : "-r";
-	args[2] = "--ignore-existing";
-	args[3] = "--exclude";
-	args[4] = "info";
-	args[5] = buf.buf;
-	args[6] = get_object_directory();
-	args[7] = NULL;
+	argv_array_push(&rsync.args, "rsync");
+	argv_array_push(&rsync.args, (transport->verbose > 1) ? "-rv" : "-r");
+	argv_array_push(&rsync.args, "--ignore-existing");
+	argv_array_push(&rsync.args, "--exclude");
+	argv_array_push(&rsync.args, "info");
+	argv_array_pushf(&rsync.args, "%s/objects/", rsync_url(transport->url));
+	argv_array_push(&rsync.args, get_object_directory());
 
 	/* NEEDSWORK: handle one level of alternates */
-	result = run_command(&rsync);
-
-	strbuf_release(&buf);
-
-	return result;
+	return run_command(&rsync);
 }
 
 static int write_one_ref(const char *name, const unsigned char *sha1,
@@ -1188,10 +1176,8 @@
 		if ((flags & (TRANSPORT_RECURSE_SUBMODULES_ON_DEMAND |
 			      TRANSPORT_RECURSE_SUBMODULES_CHECK)) && !is_bare_repository()) {
 			struct ref *ref = remote_refs;
-			struct string_list needs_pushing;
+			struct string_list needs_pushing = STRING_LIST_INIT_DUP;
 
-			memset(&needs_pushing, 0, sizeof(struct string_list));
-			needs_pushing.strdup_strings = 1;
 			for (; ref; ref = ref->next)
 				if (!is_null_sha1(ref->new_sha1) &&
 				    find_unpushed_submodules(ref->new_sha1,
diff --git a/tree.c b/tree.c
index c8c49d7..bb02c1c 100644
--- a/tree.c
+++ b/tree.c
@@ -183,15 +183,8 @@
 {
 	struct object *obj = lookup_object(sha1);
 	if (!obj)
-		return create_object(sha1, OBJ_TREE, alloc_tree_node());
-	if (!obj->type)
-		obj->type = OBJ_TREE;
-	if (obj->type != OBJ_TREE) {
-		error("Object %s is a %s, not a tree",
-		      sha1_to_hex(sha1), typename(obj->type));
-		return NULL;
-	}
-	return (struct tree *) obj;
+		return create_object(sha1, alloc_tree_node());
+	return object_as_type(obj, OBJ_TREE, 0);
 }
 
 int parse_tree_buffer(struct tree *item, void *buffer, unsigned long size)
diff --git a/unix-socket.c b/unix-socket.c
index 01f119f..91bd6b8 100644
--- a/unix-socket.c
+++ b/unix-socket.c
@@ -99,11 +99,12 @@
 	struct sockaddr_un sa;
 	struct unix_sockaddr_context ctx;
 
+	unlink(path);
+
 	if (unix_sockaddr_init(&sa, path, &ctx) < 0)
 		return -1;
 	fd = unix_stream_socket();
 
-	unlink(path);
 	if (bind(fd, (struct sockaddr *)&sa, sizeof(sa)) < 0)
 		goto fail;
 
diff --git a/unpack-trees.c b/unpack-trees.c
index 0ac39e9..c6aa8fb 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -8,6 +8,7 @@
 #include "progress.h"
 #include "refs.h"
 #include "attr.h"
+#include "split-index.h"
 
 /*
  * Error messages expected by scripts out of plumbing commands such as
@@ -241,7 +242,9 @@
 				enum unpack_trees_error_types,
 				struct unpack_trees_options *o);
 
-static int apply_sparse_checkout(struct cache_entry *ce, struct unpack_trees_options *o)
+static int apply_sparse_checkout(struct index_state *istate,
+				 struct cache_entry *ce,
+				 struct unpack_trees_options *o)
 {
 	int was_skip_worktree = ce_skip_worktree(ce);
 
@@ -249,6 +252,10 @@
 		ce->ce_flags |= CE_SKIP_WORKTREE;
 	else
 		ce->ce_flags &= ~CE_SKIP_WORKTREE;
+	if (was_skip_worktree != ce_skip_worktree(ce)) {
+		ce->ce_flags |= CE_UPDATE_IN_BASE;
+		istate->cache_changed |= CE_ENTRY_CHANGED;
+	}
 
 	/*
 	 * if (!was_skip_worktree && !ce_skip_worktree()) {
@@ -1009,6 +1016,7 @@
 	state.force = 1;
 	state.quiet = 1;
 	state.refresh_cache = 1;
+	state.istate = &o->result;
 
 	memset(&el, 0, sizeof(el));
 	if (!core_apply_sparse_checkout || !o->update)
@@ -1025,6 +1033,10 @@
 	o->result.timestamp.sec = o->src_index->timestamp.sec;
 	o->result.timestamp.nsec = o->src_index->timestamp.nsec;
 	o->result.version = o->src_index->version;
+	o->result.split_index = o->src_index->split_index;
+	if (o->result.split_index)
+		o->result.split_index->refcount++;
+	hashcpy(o->result.sha1, o->src_index->sha1);
 	o->merge_size = len;
 	mark_all_ce_unused(o->src_index);
 
@@ -1115,7 +1127,7 @@
 				ret = -1;
 			}
 
-			if (apply_sparse_checkout(ce, o)) {
+			if (apply_sparse_checkout(&o->result, ce, o)) {
 				if (!o->show_all_errors)
 					goto return_failed;
 				ret = -1;
@@ -1243,7 +1255,7 @@
 			       struct unpack_trees_options *o)
 {
 	if (ce)
-		cache_tree_invalidate_path(o->src_index->cache_tree, ce->name);
+		cache_tree_invalidate_path(o->src_index, ce->name);
 }
 
 /*
diff --git a/url.c b/url.c
index 335d97d..7ca2a69 100644
--- a/url.c
+++ b/url.c
@@ -121,7 +121,7 @@
 {
 	strbuf_addstr(buf, url);
 	if (buf->len && buf->buf[buf->len - 1] != '/')
-		strbuf_addstr(buf, "/");
+		strbuf_addch(buf, '/');
 }
 
 void str_end_url_with_slash(const char *url, char **dest) {
diff --git a/wt-status.c b/wt-status.c
index 882cfe9..27da529 100644
--- a/wt-status.c
+++ b/wt-status.c
@@ -574,14 +574,11 @@
 {
 	int i;
 	struct dir_struct dir;
-	struct timeval t_begin;
+	uint64_t t_begin = getnanotime();
 
 	if (!s->show_untracked_files)
 		return;
 
-	if (advice_status_u_option)
-		gettimeofday(&t_begin, NULL);
-
 	memset(&dir, 0, sizeof(dir));
 	if (s->show_untracked_files != SHOW_ALL_UNTRACKED_FILES)
 		dir.flags |=
@@ -612,13 +609,8 @@
 	free(dir.ignored);
 	clear_directory(&dir);
 
-	if (advice_status_u_option) {
-		struct timeval t_end;
-		gettimeofday(&t_end, NULL);
-		s->untracked_in_ms =
-			(uint64_t)t_end.tv_sec * 1000 + t_end.tv_usec / 1000 -
-			((uint64_t)t_begin.tv_sec * 1000 + t_begin.tv_usec / 1000);
-	}
+	if (advice_status_u_option)
+		s->untracked_in_ms = (getnanotime() - t_begin) / 1000000;
 }
 
 void wt_status_collect(struct wt_status *s)
diff --git a/xdiff/xmerge.c b/xdiff/xmerge.c
index 9e13b25..625198e 100644
--- a/xdiff/xmerge.c
+++ b/xdiff/xmerge.c
@@ -245,11 +245,11 @@
 					      dest ? dest + size : NULL);
 			/* Postimage from side #1 */
 			if (m->mode & 1)
-				size += xdl_recs_copy(xe1, m->i1, m->chg1, 1,
+				size += xdl_recs_copy(xe1, m->i1, m->chg1, (m->mode & 2),
 						      dest ? dest + size : NULL);
 			/* Postimage from side #2 */
 			if (m->mode & 2)
-				size += xdl_recs_copy(xe2, m->i2, m->chg2, 1,
+				size += xdl_recs_copy(xe2, m->i2, m->chg2, 0,
 						      dest ? dest + size : NULL);
 		} else
 			continue;