diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 73856ba..47876a4 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -81,44 +81,21 @@
     if: needs.ci-config.outputs.enabled == 'yes'
     runs-on: windows-latest
     steps:
-    - uses: actions/checkout@v1
-    - name: download git-sdk-64-minimal
-      shell: bash
-      run: |
-        ## Get artifact
-        urlbase=https://dev.azure.com/git-for-windows/git/_apis/build/builds
-        id=$(curl "$urlbase?definitions=22&statusFilter=completed&resultFilter=succeeded&\$top=1" |
-          jq -r ".value[] | .id")
-        download_url="$(curl "$urlbase/$id/artifacts" |
-          jq -r '.value[] | select(.name == "git-sdk-64-minimal").resource.downloadUrl')"
-        curl --connect-timeout 10 --retry 5 --retry-delay 0 --retry-max-time 240 \
-          -o artifacts.zip "$download_url"
-
-        ## Unzip and remove the artifact
-        unzip artifacts.zip
-        rm artifacts.zip
+    - uses: actions/checkout@v2
+    - uses: git-for-windows/setup-git-for-windows-sdk@v1
     - name: build
-      shell: powershell
+      shell: bash
       env:
         HOME: ${{runner.workspace}}
-        MSYSTEM: MINGW64
         NO_PERL: 1
-      run: |
-        & .\git-sdk-64-minimal\usr\bin\bash.exe -lc @"
-        printf '%s\n' /git-sdk-64-minimal/ >>.git/info/exclude
-
-          ci/make-test-artifacts.sh artifacts
-        "@
-    - name: upload build artifacts
-      uses: actions/upload-artifact@v1
+      run: ci/make-test-artifacts.sh artifacts
+    - name: zip up tracked files
+      run: git archive -o artifacts/tracked.tar.gz HEAD
+    - name: upload tracked files and build artifacts
+      uses: actions/upload-artifact@v2
       with:
         name: windows-artifacts
         path: artifacts
-    - name: upload git-sdk-64-minimal
-      uses: actions/upload-artifact@v1
-      with:
-        name: git-sdk-64-minimal
-        path: git-sdk-64-minimal
   windows-test:
     runs-on: windows-latest
     needs: [windows-build]
@@ -127,37 +104,25 @@
       matrix:
         nr: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
     steps:
-    - uses: actions/checkout@v1
-    - name: download build artifacts
-      uses: actions/download-artifact@v1
+    - name: download tracked files and build artifacts
+      uses: actions/download-artifact@v2
       with:
         name: windows-artifacts
         path: ${{github.workspace}}
-    - name: extract build artifacts
+    - name: extract tracked files and build artifacts
       shell: bash
-      run: tar xf artifacts.tar.gz
-    - name: download git-sdk-64-minimal
-      uses: actions/download-artifact@v1
-      with:
-        name: git-sdk-64-minimal
-        path: ${{github.workspace}}/git-sdk-64-minimal/
+      run: tar xf artifacts.tar.gz && tar xf tracked.tar.gz
+    - uses: git-for-windows/setup-git-for-windows-sdk@v1
     - name: test
-      shell: powershell
-      run: |
-        & .\git-sdk-64-minimal\usr\bin\bash.exe -lc @"
-          # Let Git ignore the SDK
-          printf '%s\n' /git-sdk-64-minimal/ >>.git/info/exclude
-
-          ci/run-test-slice.sh ${{matrix.nr}} 10
-        "@
+      shell: bash
+      run: ci/run-test-slice.sh ${{matrix.nr}} 10
     - name: ci/print-test-failures.sh
       if: failure()
-      shell: powershell
-      run: |
-        & .\git-sdk-64-minimal\usr\bin\bash.exe -lc ci/print-test-failures.sh
+      shell: bash
+      run: ci/print-test-failures.sh
     - name: Upload failed tests' directories
       if: failure() && env.FAILED_TEST_ARTIFACTS != ''
-      uses: actions/upload-artifact@v1
+      uses: actions/upload-artifact@v2
       with:
         name: failed-tests-windows
         path: ${{env.FAILED_TEST_ARTIFACTS}}
@@ -165,27 +130,12 @@
     needs: ci-config
     if: needs.ci-config.outputs.enabled == 'yes'
     env:
-      MSYSTEM: MINGW64
       NO_PERL: 1
       GIT_CONFIG_PARAMETERS: "'user.name=CI' 'user.email=ci@git'"
     runs-on: windows-latest
     steps:
-    - uses: actions/checkout@v1
-    - name: download git-sdk-64-minimal
-      shell: bash
-      run: |
-        ## Get artifact
-        urlbase=https://dev.azure.com/git-for-windows/git/_apis/build/builds
-        id=$(curl "$urlbase?definitions=22&statusFilter=completed&resultFilter=succeeded&\$top=1" |
-          jq -r ".value[] | .id")
-        download_url="$(curl "$urlbase/$id/artifacts" |
-          jq -r '.value[] | select(.name == "git-sdk-64-minimal").resource.downloadUrl')"
-        curl --connect-timeout 10 --retry 5 --retry-delay 0 --retry-max-time 240 \
-          -o artifacts.zip "$download_url"
-
-        ## Unzip and remove the artifact
-        unzip artifacts.zip
-        rm artifacts.zip
+    - uses: actions/checkout@v2
+    - uses: git-for-windows/setup-git-for-windows-sdk@v1
     - name: initialize vcpkg
       uses: actions/checkout@v2
       with:
@@ -203,75 +153,60 @@
     - name: add msbuild to PATH
       uses: microsoft/setup-msbuild@v1
     - name: copy dlls to root
-      shell: powershell
-      run: |
-        & compat\vcbuild\vcpkg_copy_dlls.bat release
-        if (!$?) { exit(1) }
+      shell: cmd
+      run: compat\vcbuild\vcpkg_copy_dlls.bat release
     - name: generate Visual Studio solution
       shell: bash
       run: |
         cmake `pwd`/contrib/buildsystems/ -DCMAKE_PREFIX_PATH=`pwd`/compat/vcbuild/vcpkg/installed/x64-windows \
-        -DMSGFMT_EXE=`pwd`/git-sdk-64-minimal/mingw64/bin/msgfmt.exe -DPERL_TESTS=OFF -DPYTHON_TESTS=OFF -DCURL_NO_CURL_CMAKE=ON
+        -DNO_GETTEXT=YesPlease -DPERL_TESTS=OFF -DPYTHON_TESTS=OFF -DCURL_NO_CURL_CMAKE=ON
     - name: MSBuild
       run: msbuild git.sln -property:Configuration=Release -property:Platform=x64 -maxCpuCount:4 -property:PlatformToolset=v142
     - name: bundle artifact tar
-      shell: powershell
+      shell: bash
       env:
         MSVC: 1
         VCPKG_ROOT: ${{github.workspace}}\compat\vcbuild\vcpkg
       run: |
-        & git-sdk-64-minimal\usr\bin\bash.exe -lc @"
-          mkdir -p artifacts &&
-          eval \"`$(make -n artifacts-tar INCLUDE_DLLS_IN_ARTIFACTS=YesPlease ARTIFACTS_DIRECTORY=artifacts 2>&1 | grep ^tar)\"
-        "@
-    - name: upload build artifacts
-      uses: actions/upload-artifact@v1
+        mkdir -p artifacts &&
+        eval "$(make -n artifacts-tar INCLUDE_DLLS_IN_ARTIFACTS=YesPlease ARTIFACTS_DIRECTORY=artifacts NO_GETTEXT=YesPlease 2>&1 | grep ^tar)"
+    - name: zip up tracked files
+      run: git archive -o artifacts/tracked.tar.gz HEAD
+    - name: upload tracked files and build artifacts
+      uses: actions/upload-artifact@v2
       with:
         name: vs-artifacts
         path: artifacts
   vs-test:
     runs-on: windows-latest
-    needs: [vs-build, windows-build]
+    needs: vs-build
     strategy:
       fail-fast: false
       matrix:
         nr: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
     steps:
-    - uses: actions/checkout@v1
-    - name: download git-sdk-64-minimal
-      uses: actions/download-artifact@v1
-      with:
-        name: git-sdk-64-minimal
-        path: ${{github.workspace}}/git-sdk-64-minimal/
-    - name: download build artifacts
-      uses: actions/download-artifact@v1
+    - uses: git-for-windows/setup-git-for-windows-sdk@v1
+    - name: download tracked files and build artifacts
+      uses: actions/download-artifact@v2
       with:
         name: vs-artifacts
         path: ${{github.workspace}}
-    - name: extract build artifacts
+    - name: extract tracked files and build artifacts
       shell: bash
-      run: tar xf artifacts.tar.gz
+      run: tar xf artifacts.tar.gz && tar xf tracked.tar.gz
     - name: test
-      shell: powershell
+      shell: bash
       env:
-        MSYSTEM: MINGW64
         NO_SVN_TESTS: 1
         GIT_TEST_SKIP_REBASE_P: 1
-      run: |
-        & .\git-sdk-64-minimal\usr\bin\bash.exe -lc @"
-          # Let Git ignore the SDK and the test-cache
-          printf '%s\n' /git-sdk-64-minimal/ /test-cache/ >>.git/info/exclude
-
-          ci/run-test-slice.sh ${{matrix.nr}} 10
-        "@
+      run: ci/run-test-slice.sh ${{matrix.nr}} 10
     - name: ci/print-test-failures.sh
       if: failure()
-      shell: powershell
-      run: |
-        & .\git-sdk-64-minimal\usr\bin\bash.exe -lc ci/print-test-failures.sh
+      shell: bash
+      run: ci/print-test-failures.sh
     - name: Upload failed tests' directories
       if: failure() && env.FAILED_TEST_ARTIFACTS != ''
-      uses: actions/upload-artifact@v1
+      uses: actions/upload-artifact@v2
       with:
         name: failed-tests-windows
         path: ${{env.FAILED_TEST_ARTIFACTS}}
@@ -302,14 +237,14 @@
       jobname: ${{matrix.vector.jobname}}
     runs-on: ${{matrix.vector.pool}}
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v2
     - run: ci/install-dependencies.sh
     - run: ci/run-build-and-tests.sh
     - run: ci/print-test-failures.sh
       if: failure()
     - name: Upload failed tests' directories
       if: failure() && env.FAILED_TEST_ARTIFACTS != ''
-      uses: actions/upload-artifact@v1
+      uses: actions/upload-artifact@v2
       with:
         name: failed-tests-${{matrix.vector.jobname}}
         path: ${{env.FAILED_TEST_ARTIFACTS}}
@@ -336,7 +271,7 @@
       if: failure()
     - name: Upload failed tests' directories
       if: failure() && env.FAILED_TEST_ARTIFACTS != ''
-      uses: actions/upload-artifact@v1
+      uses: actions/upload-artifact@v2
       with:
         name: failed-tests-${{matrix.vector.jobname}}
         path: ${{env.FAILED_TEST_ARTIFACTS}}
@@ -347,9 +282,29 @@
       jobname: StaticAnalysis
     runs-on: ubuntu-18.04
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v2
     - run: ci/install-dependencies.sh
     - run: ci/run-static-analysis.sh
+  sparse:
+    needs: ci-config
+    if: needs.ci-config.outputs.enabled == 'yes'
+    env:
+      jobname: sparse
+    runs-on: ubuntu-20.04
+    steps:
+    - name: Download a current `sparse` package
+      # Ubuntu's `sparse` version is too old for us
+      uses: git-for-windows/get-azure-pipelines-artifact@v0
+      with:
+        repository: git/git
+        definitionId: 10
+        artifact: sparse-20.04
+    - name: Install the current `sparse` package
+      run: sudo dpkg -i sparse-20.04/sparse_*.deb
+    - uses: actions/checkout@v2
+    - name: Install other dependencies
+      run: ci/install-dependencies.sh
+    - run: make sparse
   documentation:
     needs: ci-config
     if: needs.ci-config.outputs.enabled == 'yes'
@@ -357,6 +312,6 @@
       jobname: Documentation
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v1
+    - uses: actions/checkout@v2
     - run: ci/install-dependencies.sh
     - run: ci/test-documentation.sh
diff --git a/Documentation/CodingGuidelines b/Documentation/CodingGuidelines
index e3af089..711cb91 100644
--- a/Documentation/CodingGuidelines
+++ b/Documentation/CodingGuidelines
@@ -551,6 +551,51 @@
  documentation, please see the documentation-related advice in the
  Documentation/SubmittingPatches file).
 
+ In order to ensure the documentation is inclusive, avoid assuming
+ that an unspecified example person is male or female, and think
+ twice before using "he", "him", "she", or "her".  Here are some
+ tips to avoid use of gendered pronouns:
+
+  - Prefer succinctness and matter-of-factly describing functionality
+    in the abstract.  E.g.
+
+     --short:: Emit output in the short-format.
+
+    and avoid something like these overly verbose alternatives:
+
+     --short:: Use this to emit output in the short-format.
+     --short:: You can use this to get output in the short-format.
+     --short:: A user who prefers shorter output could....
+     --short:: Should a person and/or program want shorter output, he
+               she/they/it can...
+
+    This practice often eliminates the need to involve human actors in
+    your description, but it is a good practice regardless of the
+    avoidance of gendered pronouns.
+
+  - When it becomes awkward to stick to this style, prefer "you" when
+    addressing the the hypothetical user, and possibly "we" when
+    discussing how the program might react to the user.  E.g.
+
+      You can use this option instead of --xyz, but we might remove
+      support for it in future versions.
+
+    while keeping in mind that you can probably be less verbose, e.g.
+
+      Use this instead of --xyz. This option might be removed in future
+      versions.
+
+  - If you still need to refer to an example person that is
+    third-person singular, you may resort to "singular they" to avoid
+    "he/she/him/her", e.g.
+
+      A contributor asks their upstream to pull from them.
+
+    Note that this sounds ungrammatical and unnatural to those who
+    learned that "they" is only used for third-person plural, e.g.
+    those who learn English as a second language in some parts of the
+    world.
+
  Every user-visible change should be reflected in the documentation.
  The same general rule as for code applies -- imitate the existing
  conventions.
diff --git a/Documentation/RelNotes/2.33.0.txt b/Documentation/RelNotes/2.33.0.txt
index d4c56de..a69531c 100644
--- a/Documentation/RelNotes/2.33.0.txt
+++ b/Documentation/RelNotes/2.33.0.txt
@@ -30,6 +30,9 @@
 
  * The userdiff pattern for C# learned the token "record".
 
+ * "git rev-list" learns to omit the "commit <object-name>" header
+   lines from the output with the `--no-commit-header` option.
+
 
 Performance, Internal Implementation, Development Support etc.
 
@@ -54,6 +57,11 @@
 
  * Code cleanup around struct_type_init() functions.
 
+ * "git send-email" optimization.
+
+ * GitHub Actions / CI update.
+   (merge 0dc787a9f2 js/ci-windows-update later to maint).
+
 
 Fixes since v2.32
 -----------------
@@ -208,3 +216,5 @@
    (merge 617480d75b hn/refs-iterator-peel-returns-boolean later to maint).
    (merge 6a24cc71ed ar/submodule-helper-include-cleanup later to maint).
    (merge 5632e838f8 rs/khash-alloc-cleanup later to maint).
+   (merge b1d87fbaf1 jk/typofix later to maint).
+   (merge e04170697a ab/gitignore-discovery-doc later to maint).
diff --git a/Documentation/config/diff.txt b/Documentation/config/diff.txt
index 2d3331f..32f8483 100644
--- a/Documentation/config/diff.txt
+++ b/Documentation/config/diff.txt
@@ -118,9 +118,10 @@
 	relative to the top of the working tree.
 
 diff.renameLimit::
-	The number of files to consider when performing the copy/rename
-	detection; equivalent to the 'git diff' option `-l`. This setting
-	has no effect if rename detection is turned off.
+	The number of files to consider in the exhaustive portion of
+	copy/rename detection; equivalent to the 'git diff' option
+	`-l`.  If not set, the default value is currently 1000.  This
+	setting has no effect if rename detection is turned off.
 
 diff.renames::
 	Whether and how Git detects renames.  If set to "false",
diff --git a/Documentation/config/merge.txt b/Documentation/config/merge.txt
index 6b66c83..e27cc63 100644
--- a/Documentation/config/merge.txt
+++ b/Documentation/config/merge.txt
@@ -33,10 +33,12 @@
 include::fmt-merge-msg.txt[]
 
 merge.renameLimit::
-	The number of files to consider when performing rename detection
-	during a merge; if not specified, defaults to the value of
-	diff.renameLimit. This setting has no effect if rename detection
-	is turned off.
+	The number of files to consider in the exhaustive portion of
+	rename detection during a merge.  If not specified, defaults
+	to the value of diff.renameLimit.  If neither
+	merge.renameLimit nor diff.renameLimit are specified,
+	currently defaults to 7000.  This setting has no effect if
+	rename detection is turned off.
 
 merge.renames::
 	Whether Git detects renames.  If set to "false", rename detection
diff --git a/Documentation/config/sendemail.txt b/Documentation/config/sendemail.txt
index cbc5af4..50baa5d 100644
--- a/Documentation/config/sendemail.txt
+++ b/Documentation/config/sendemail.txt
@@ -8,9 +8,6 @@
 	See linkgit:git-send-email[1] for description.  Note that this
 	setting is not subject to the 'identity' mechanism.
 
-sendemail.smtpssl (deprecated)::
-	Deprecated alias for 'sendemail.smtpEncryption = ssl'.
-
 sendemail.smtpsslcertpath::
 	Path to ca-certificates (either a directory or a single file).
 	Set it to an empty string to disable certificate verification.
diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index 32e6dee..0aebe83 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -588,11 +588,17 @@
 of a delete/create pair.
 
 -l<num>::
-	The `-M` and `-C` options require O(n^2) processing time where n
-	is the number of potential rename/copy targets.  This
-	option prevents rename/copy detection from running if
-	the number of rename/copy targets exceeds the specified
-	number.
+	The `-M` and `-C` options involve some preliminary steps that
+	can detect subsets of renames/copies cheaply, followed by an
+	exhaustive fallback portion that compares all remaining
+	unpaired destinations to all relevant sources.  (For renames,
+	only remaining unpaired sources are relevant; for copies, all
+	original sources are relevant.)  For N sources and
+	destinations, this exhaustive check is O(N^2).  This option
+	prevents the exhaustive portion of rename/copy detection from
+	running if the number of source/destination files involved
+	exceeds the specified number.  Defaults to diff.renameLimit.
+	Note that a value of 0 is treated as unlimited.
 
 ifndef::git-format-patch[]
 --diff-filter=[(A|C|D|M|R|T|U|X|B)...[*]]::
diff --git a/Documentation/git-diff.txt b/Documentation/git-diff.txt
index 7f4c8a8..6236c75 100644
--- a/Documentation/git-diff.txt
+++ b/Documentation/git-diff.txt
@@ -51,16 +51,20 @@
 	--staged is a synonym of --cached.
 +
 If --merge-base is given, instead of using <commit>, use the merge base
-of <commit> and HEAD.  `git diff --merge-base A` is equivalent to
-`git diff $(git merge-base A HEAD)`.
+of <commit> and HEAD.  `git diff --cached --merge-base A` is equivalent to
+`git diff --cached $(git merge-base A HEAD)`.
 
-'git diff' [<options>] <commit> [--] [<path>...]::
+'git diff' [<options>] [--merge-base] <commit> [--] [<path>...]::
 
 	This form is to view the changes you have in your
 	working tree relative to the named <commit>.  You can
 	use HEAD to compare it with the latest commit, or a
 	branch name to compare with the tip of a different
 	branch.
++
+If --merge-base is given, instead of using <commit>, use the merge base
+of <commit> and HEAD.  `git diff --merge-base A` is equivalent to
+`git diff $(git merge-base A HEAD)`.
 
 'git diff' [<options>] [--merge-base] <commit> <commit> [--] [<path>...]::
 
diff --git a/Documentation/git-worktree.txt b/Documentation/git-worktree.txt
index 66e67e6..8a7cbdd 100644
--- a/Documentation/git-worktree.txt
+++ b/Documentation/git-worktree.txt
@@ -9,7 +9,7 @@
 SYNOPSIS
 --------
 [verse]
-'git worktree add' [-f] [--detach] [--checkout] [--lock] [-b <new-branch>] <path> [<commit-ish>]
+'git worktree add' [-f] [--detach] [--checkout] [--lock [--reason <string>]] [-b <new-branch>] <path> [<commit-ish>]
 'git worktree list' [--porcelain]
 'git worktree lock' [--reason <string>] <worktree>
 'git worktree move' <worktree> <new-path>
@@ -242,7 +242,7 @@
 older than `<time>`.
 
 --reason <string>::
-	With `lock`, an explanation why the working tree is locked.
+	With `lock` or with `add --lock`, an explanation why the working tree is locked.
 
 <worktree>::
 	Working trees can be identified by path, either relative or
diff --git a/Documentation/gitignore.txt b/Documentation/gitignore.txt
index 53e7d5c..f8a1fc2 100644
--- a/Documentation/gitignore.txt
+++ b/Documentation/gitignore.txt
@@ -27,12 +27,11 @@
    them.
 
  * Patterns read from a `.gitignore` file in the same directory
-   as the path, or in any parent directory, with patterns in the
-   higher level files (up to the toplevel of the work tree) being overridden
-   by those in lower level files down to the directory containing the file.
-   These patterns match relative to the location of the
-   `.gitignore` file.  A project normally includes such
-   `.gitignore` files in its repository, containing patterns for
+   as the path, or in any parent directory (up to the top-level of the working
+   tree), with patterns in the higher level files being overridden by those in
+   lower level files down to the directory containing the file. These patterns
+   match relative to the location of the `.gitignore` file.  A project normally
+   includes such `.gitignore` files in its repository, containing patterns for
    files generated as part of the project build.
 
  * Patterns read from `$GIT_DIR/info/exclude`.
diff --git a/Documentation/rev-list-options.txt b/Documentation/rev-list-options.txt
index 5bf2a85..24569b0 100644
--- a/Documentation/rev-list-options.txt
+++ b/Documentation/rev-list-options.txt
@@ -897,7 +897,7 @@
 +
 The form '--filter=sparse:oid=<blob-ish>' uses a sparse-checkout
 specification contained in the blob (or blob-expression) '<blob-ish>'
-to omit blobs that would not be not required for a sparse checkout on
+to omit blobs that would not be required for a sparse checkout on
 the requested refs.
 +
 The form '--filter=tree:<depth>' omits all blobs and trees whose depth
@@ -1064,6 +1064,14 @@
 --header::
 	Print the contents of the commit in raw-format; each record is
 	separated with a NUL character.
+
+--no-commit-header::
+	Suppress the header line containing "commit" and the object ID printed before
+	the specified format.  This has no effect on the built-in formats; only custom
+	formats are affected.
+
+--commit-header::
+	Overrides a previous `--no-commit-header`.
 endif::git-rev-list[]
 
 --parents::
diff --git a/Makefile b/Makefile
index c7c46c0..c6f6246 100644
--- a/Makefile
+++ b/Makefile
@@ -726,6 +726,7 @@
 TEST_BUILTINS_OBJS += test-mktemp.o
 TEST_BUILTINS_OBJS += test-oid-array.o
 TEST_BUILTINS_OBJS += test-oidmap.o
+TEST_BUILTINS_OBJS += test-oidtree.o
 TEST_BUILTINS_OBJS += test-online-cpus.o
 TEST_BUILTINS_OBJS += test-parse-options.o
 TEST_BUILTINS_OBJS += test-parse-pathspec-file.o
@@ -850,6 +851,7 @@
 LIB_OBJS += bulk-checkin.o
 LIB_OBJS += bundle.o
 LIB_OBJS += cache-tree.o
+LIB_OBJS += cbtree.o
 LIB_OBJS += chdir-notify.o
 LIB_OBJS += checkout.o
 LIB_OBJS += chunk-format.o
@@ -945,6 +947,7 @@
 LIB_OBJS += oid-array.o
 LIB_OBJS += oidmap.o
 LIB_OBJS += oidset.o
+LIB_OBJS += oidtree.o
 LIB_OBJS += pack-bitmap-write.o
 LIB_OBJS += pack-bitmap.o
 LIB_OBJS += pack-check.o
@@ -2687,10 +2690,13 @@
 .PHONY: pot
 pot: po/git.pot
 
+ifdef NO_GETTEXT
+POFILES :=
+MOFILES :=
+else
 POFILES := $(wildcard po/*.po)
 MOFILES := $(patsubst po/%.po,po/build/locale/%/LC_MESSAGES/git.mo,$(POFILES))
 
-ifndef NO_GETTEXT
 all:: $(MOFILES)
 endif
 
diff --git a/add-patch.c b/add-patch.c
index 2fad92c..8c41cdf 100644
--- a/add-patch.c
+++ b/add-patch.c
@@ -280,6 +280,7 @@
 	clear_add_i_state(&s->s);
 }
 
+__attribute__((format (printf, 2, 3)))
 static void err(struct add_p_state *s, const char *fmt, ...)
 {
 	va_list args;
diff --git a/advice.h b/advice.h
index bd26c38..9f8ffc7 100644
--- a/advice.h
+++ b/advice.h
@@ -90,6 +90,7 @@
 /**
  * Checks the visibility of the advice before printing.
  */
+__attribute__((format (printf, 2, 3)))
 void advise_if_enabled(enum advice_type type, const char *advice, ...);
 
 int error_resolve_conflict(const char *me);
diff --git a/builtin/am.c b/builtin/am.c
index 0b2d886..0c2ad96 100644
--- a/builtin/am.c
+++ b/builtin/am.c
@@ -210,6 +210,7 @@
  * If state->quiet is false, calls fprintf(fp, fmt, ...), and appends a newline
  * at the end.
  */
+__attribute__((format (printf, 3, 4)))
 static void say(const struct am_state *state, FILE *fp, const char *fmt, ...)
 {
 	va_list ap;
diff --git a/builtin/bisect--helper.c b/builtin/bisect--helper.c
index 9d9540a..f184eae 100644
--- a/builtin/bisect--helper.c
+++ b/builtin/bisect--helper.c
@@ -117,6 +117,7 @@
 	return fclose(fp);
 }
 
+__attribute__((format (printf, 2, 3)))
 static int write_to_file(const char *path, const char *format, ...)
 {
 	int res;
@@ -129,6 +130,7 @@
 	return res;
 }
 
+__attribute__((format (printf, 2, 3)))
 static int append_to_file(const char *path, const char *format, ...)
 {
 	int res;
diff --git a/builtin/commit.c b/builtin/commit.c
index 190d215..7436262 100644
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -889,7 +889,22 @@
 		int ident_shown = 0;
 		int saved_color_setting;
 		struct ident_split ci, ai;
-
+		const char *hint_cleanup_all = allow_empty_message ?
+			_("Please enter the commit message for your changes."
+			  " Lines starting\nwith '%c' will be ignored.\n") :
+			_("Please enter the commit message for your changes."
+			  " Lines starting\nwith '%c' will be ignored, and an empty"
+			  " message aborts the commit.\n");
+		const char *hint_cleanup_space = allow_empty_message ?
+			_("Please enter the commit message for your changes."
+			  " Lines starting\n"
+			  "with '%c' will be kept; you may remove them"
+			  " yourself if you want to.\n") :
+			_("Please enter the commit message for your changes."
+			  " Lines starting\n"
+			  "with '%c' will be kept; you may remove them"
+			  " yourself if you want to.\n"
+			  "An empty message aborts the commit.\n");
 		if (whence != FROM_COMMIT) {
 			if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS &&
 				!merge_contains_scissors)
@@ -911,20 +926,12 @@
 
 		fprintf(s->fp, "\n");
 		if (cleanup_mode == COMMIT_MSG_CLEANUP_ALL)
-			status_printf(s, GIT_COLOR_NORMAL,
-				_("Please enter the commit message for your changes."
-				  " Lines starting\nwith '%c' will be ignored, and an empty"
-				  " message aborts the commit.\n"), comment_line_char);
+			status_printf(s, GIT_COLOR_NORMAL, hint_cleanup_all, comment_line_char);
 		else if (cleanup_mode == COMMIT_MSG_CLEANUP_SCISSORS) {
 			if (whence == FROM_COMMIT && !merge_contains_scissors)
 				wt_status_add_cut_line(s->fp);
 		} else /* COMMIT_MSG_CLEANUP_SPACE, that is. */
-			status_printf(s, GIT_COLOR_NORMAL,
-				_("Please enter the commit message for your changes."
-				  " Lines starting\n"
-				  "with '%c' will be kept; you may remove them"
-				  " yourself if you want to.\n"
-				  "An empty message aborts the commit.\n"), comment_line_char);
+			status_printf(s, GIT_COLOR_NORMAL, hint_cleanup_space, comment_line_char);
 
 		/*
 		 * These should never fail because they come from our own
@@ -1510,6 +1517,9 @@
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage_with_options(builtin_status_usage, builtin_status_options);
 
+	prepare_repo_settings(the_repository);
+	the_repository->settings.command_requires_full_index = 0;
+
 	status_init_config(&s, git_status_config);
 	argc = parse_options(argc, argv, prefix,
 			     builtin_status_options,
diff --git a/builtin/diff.c b/builtin/diff.c
index 2d87c37..dd8ce68 100644
--- a/builtin/diff.c
+++ b/builtin/diff.c
@@ -26,8 +26,8 @@
 
 static const char builtin_diff_usage[] =
 "git diff [<options>] [<commit>] [--] [<path>...]\n"
-"   or: git diff [<options>] --cached [<commit>] [--] [<path>...]\n"
-"   or: git diff [<options>] <commit> [--merge-base] [<commit>...] <commit> [--] [<path>...]\n"
+"   or: git diff [<options>] --cached [--merge-base] [<commit>] [--] [<path>...]\n"
+"   or: git diff [<options>] [--merge-base] <commit> [<commit>...] <commit> [--] [<path>...]\n"
 "   or: git diff [<options>] <commit>...<commit>] [--] [<path>...]\n"
 "   or: git diff [<options>] <blob> <blob>]\n"
 "   or: git diff [<options>] --no-index [--] <path> <path>]\n"
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 3fbc5d7..8336466 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -369,9 +369,7 @@
 	use(sizeof(struct pack_header));
 }
 
-static NORETURN void bad_object(off_t offset, const char *format,
-		       ...) __attribute__((format (printf, 2, 3)));
-
+__attribute__((format (printf, 2, 3)))
 static NORETURN void bad_object(off_t offset, const char *format, ...)
 {
 	va_list params;
diff --git a/builtin/log.c b/builtin/log.c
index 516a114..3d7717b 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -245,6 +245,9 @@
 			rev->abbrev_commit = 0;
 	}
 
+	if (rev->commit_format == CMIT_FMT_USERFORMAT && !w.decorate)
+		decoration_style = 0;
+
 	if (decoration_style) {
 		const struct string_list *config_exclude =
 			repo_config_get_value_multi(the_repository,
diff --git a/builtin/multi-pack-index.c b/builtin/multi-pack-index.c
index 5d3ea44..8ff0dee 100644
--- a/builtin/multi-pack-index.c
+++ b/builtin/multi-pack-index.c
@@ -176,8 +176,8 @@
 	else if (!strcmp(argv[0], "expire"))
 		return cmd_multi_pack_index_expire(argc, argv);
 	else {
-usage:
 		error(_("unrecognized subcommand: %s"), argv[0]);
+usage:
 		usage_with_options(builtin_multi_pack_index_usage,
 				   builtin_multi_pack_index_options);
 	}
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index a347425..2d1f97e 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -425,9 +425,6 @@
 	return 0;
 }
 
-static void rp_error(const char *err, ...) __attribute__((format (printf, 1, 2)));
-static void rp_warning(const char *err, ...) __attribute__((format (printf, 1, 2)));
-
 static void report_message(const char *prefix, const char *err, va_list params)
 {
 	int sz;
@@ -445,6 +442,7 @@
 		xwrite(2, msg, sz);
 }
 
+__attribute__((format (printf, 1, 2)))
 static void rp_warning(const char *err, ...)
 {
 	va_list params;
@@ -453,6 +451,7 @@
 	va_end(params);
 }
 
+__attribute__((format (printf, 1, 2)))
 static void rp_error(const char *err, ...)
 {
 	va_list params;
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index 7677b1a..36cb909 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -127,13 +127,15 @@
 	if (info->header_prefix)
 		fputs(info->header_prefix, stdout);
 
-	if (!revs->graph)
-		fputs(get_revision_mark(revs, commit), stdout);
-	if (revs->abbrev_commit && revs->abbrev)
-		fputs(find_unique_abbrev(&commit->object.oid, revs->abbrev),
-		      stdout);
-	else
-		fputs(oid_to_hex(&commit->object.oid), stdout);
+	if (revs->include_header) {
+		if (!revs->graph)
+			fputs(get_revision_mark(revs, commit), stdout);
+		if (revs->abbrev_commit && revs->abbrev)
+			fputs(find_unique_abbrev(&commit->object.oid, revs->abbrev),
+			      stdout);
+		else
+			fputs(oid_to_hex(&commit->object.oid), stdout);
+	}
 	if (revs->print_parents) {
 		struct commit_list *parents = commit->parents;
 		while (parents) {
@@ -153,7 +155,7 @@
 	show_decorations(revs, commit);
 	if (revs->commit_format == CMIT_FMT_ONELINE)
 		putchar(' ');
-	else
+	else if (revs->include_header)
 		putchar('\n');
 
 	if (revs->verbose_header) {
@@ -512,6 +514,7 @@
 	repo_init_revisions(the_repository, &revs, prefix);
 	revs.abbrev = DEFAULT_ABBREV;
 	revs.commit_format = CMIT_FMT_UNSPECIFIED;
+	revs.include_header = 1;
 
 	/*
 	 * Scan the argument list before invoking setup_revisions(), so that we
@@ -627,6 +630,16 @@
 			continue;
 		}
 
+		if (!strcmp(arg, ("--commit-header"))) {
+			revs.include_header = 1;
+			continue;
+		}
+
+		if (!strcmp(arg, ("--no-commit-header"))) {
+			revs.include_header = 0;
+			continue;
+		}
+
 		if (!strcmp(arg, "--disk-usage")) {
 			show_disk_usage = 1;
 			info.flags |= REV_LIST_QUIET;
@@ -636,10 +649,12 @@
 		usage(rev_list_usage);
 
 	}
+	if (revs.commit_format != CMIT_FMT_USERFORMAT)
+		revs.include_header = 1;
 	if (revs.commit_format != CMIT_FMT_UNSPECIFIED) {
 		/* The command line has a --pretty  */
 		info.hdr_termination = '\n';
-		if (revs.commit_format == CMIT_FMT_ONELINE)
+		if (revs.commit_format == CMIT_FMT_ONELINE || !revs.include_header)
 			info.header_prefix = "";
 		else
 			info.header_prefix = "commit ";
diff --git a/builtin/worktree.c b/builtin/worktree.c
index 976bf8e..0d0a80d 100644
--- a/builtin/worktree.c
+++ b/builtin/worktree.c
@@ -30,7 +30,7 @@
 	int detach;
 	int quiet;
 	int checkout;
-	int keep_locked;
+	const char *keep_locked;
 };
 
 static int show_only;
@@ -302,10 +302,10 @@
 	 * after the preparation is over.
 	 */
 	strbuf_addf(&sb, "%s/locked", sb_repo.buf);
-	if (!opts->keep_locked)
-		write_file(sb.buf, "initializing");
+	if (opts->keep_locked)
+		write_file(sb.buf, "%s", opts->keep_locked);
 	else
-		write_file(sb.buf, "added with --lock");
+		write_file(sb.buf, _("initializing"));
 
 	strbuf_addf(&sb_git, "%s/.git", path);
 	if (safe_create_leading_directories_const(sb_git.buf))
@@ -475,6 +475,8 @@
 	const char *branch;
 	const char *new_branch = NULL;
 	const char *opt_track = NULL;
+	const char *lock_reason = NULL;
+	int keep_locked = 0;
 	struct option options[] = {
 		OPT__FORCE(&opts.force,
 			   N_("checkout <branch> even if already checked out in other worktree"),
@@ -485,7 +487,9 @@
 			   N_("create or reset a branch")),
 		OPT_BOOL('d', "detach", &opts.detach, N_("detach HEAD at named commit")),
 		OPT_BOOL(0, "checkout", &opts.checkout, N_("populate the new working tree")),
-		OPT_BOOL(0, "lock", &opts.keep_locked, N_("keep the new working tree locked")),
+		OPT_BOOL(0, "lock", &keep_locked, N_("keep the new working tree locked")),
+		OPT_STRING(0, "reason", &lock_reason, N_("string"),
+			   N_("reason for locking")),
 		OPT__QUIET(&opts.quiet, N_("suppress progress reporting")),
 		OPT_PASSTHRU(0, "track", &opt_track, NULL,
 			     N_("set up tracking mode (see git-branch(1))"),
@@ -500,6 +504,13 @@
 	ac = parse_options(ac, av, prefix, options, worktree_usage, 0);
 	if (!!opts.detach + !!new_branch + !!new_branch_force > 1)
 		die(_("-b, -B, and --detach are mutually exclusive"));
+	if (lock_reason && !keep_locked)
+		die(_("--reason requires --lock"));
+	if (lock_reason)
+		opts.keep_locked = lock_reason;
+	else if (keep_locked)
+		opts.keep_locked = _("added with --lock");
+
 	if (ac < 1 || ac > 2)
 		usage_with_options(worktree_usage, options);
 
diff --git a/cache.h b/cache.h
index ba04ff8..f9aed2d 100644
--- a/cache.h
+++ b/cache.h
@@ -1385,6 +1385,7 @@
 };
 
 int repo_get_oid(struct repository *r, const char *str, struct object_id *oid);
+__attribute__((format (printf, 2, 3)))
 int get_oidf(struct object_id *oid, const char *fmt, ...);
 int repo_get_oid_commit(struct repository *r, const char *str, struct object_id *oid);
 int repo_get_oid_committish(struct repository *r, const char *str, struct object_id *oid);
diff --git a/cbtree.c b/cbtree.c
new file mode 100644
index 0000000..b0c65d8
--- /dev/null
+++ b/cbtree.c
@@ -0,0 +1,167 @@
+/*
+ * crit-bit tree implementation, does no allocations internally
+ * For more information on crit-bit trees: https://cr.yp.to/critbit.html
+ * Based on Adam Langley's adaptation of Dan Bernstein's public domain code
+ * git clone https://github.com/agl/critbit.git
+ */
+#include "cbtree.h"
+
+static struct cb_node *cb_node_of(const void *p)
+{
+	return (struct cb_node *)((uintptr_t)p - 1);
+}
+
+/* locate the best match, does not do a final comparision */
+static struct cb_node *cb_internal_best_match(struct cb_node *p,
+					const uint8_t *k, size_t klen)
+{
+	while (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		uint8_t c = q->byte < klen ? k[q->byte] : 0;
+		size_t direction = (1 + (q->otherbits | c)) >> 8;
+
+		p = q->child[direction];
+	}
+	return p;
+}
+
+/* returns NULL if successful, existing cb_node if duplicate */
+struct cb_node *cb_insert(struct cb_tree *t, struct cb_node *node, size_t klen)
+{
+	size_t newbyte, newotherbits;
+	uint8_t c;
+	int newdirection;
+	struct cb_node **wherep, *p;
+
+	assert(!((uintptr_t)node & 1)); /* allocations must be aligned */
+
+	if (!t->root) {		/* insert into empty tree */
+		t->root = node;
+		return NULL;	/* success */
+	}
+
+	/* see if a node already exists */
+	p = cb_internal_best_match(t->root, node->k, klen);
+
+	/* find first differing byte */
+	for (newbyte = 0; newbyte < klen; newbyte++) {
+		if (p->k[newbyte] != node->k[newbyte])
+			goto different_byte_found;
+	}
+	return p;	/* element exists, let user deal with it */
+
+different_byte_found:
+	newotherbits = p->k[newbyte] ^ node->k[newbyte];
+	newotherbits |= newotherbits >> 1;
+	newotherbits |= newotherbits >> 2;
+	newotherbits |= newotherbits >> 4;
+	newotherbits = (newotherbits & ~(newotherbits >> 1)) ^ 255;
+	c = p->k[newbyte];
+	newdirection = (1 + (newotherbits | c)) >> 8;
+
+	node->byte = newbyte;
+	node->otherbits = newotherbits;
+	node->child[1 - newdirection] = node;
+
+	/* find a place to insert it */
+	wherep = &t->root;
+	for (;;) {
+		struct cb_node *q;
+		size_t direction;
+
+		p = *wherep;
+		if (!(1 & (uintptr_t)p))
+			break;
+		q = cb_node_of(p);
+		if (q->byte > newbyte)
+			break;
+		if (q->byte == newbyte && q->otherbits > newotherbits)
+			break;
+		c = q->byte < klen ? node->k[q->byte] : 0;
+		direction = (1 + (q->otherbits | c)) >> 8;
+		wherep = q->child + direction;
+	}
+
+	node->child[newdirection] = *wherep;
+	*wherep = (struct cb_node *)(1 + (uintptr_t)node);
+
+	return NULL; /* success */
+}
+
+struct cb_node *cb_lookup(struct cb_tree *t, const uint8_t *k, size_t klen)
+{
+	struct cb_node *p = cb_internal_best_match(t->root, k, klen);
+
+	return p && !memcmp(p->k, k, klen) ? p : NULL;
+}
+
+struct cb_node *cb_unlink(struct cb_tree *t, const uint8_t *k, size_t klen)
+{
+	struct cb_node **wherep = &t->root;
+	struct cb_node **whereq = NULL;
+	struct cb_node *q = NULL;
+	size_t direction = 0;
+	uint8_t c;
+	struct cb_node *p = t->root;
+
+	if (!p) return NULL;	/* empty tree, nothing to delete */
+
+	/* traverse to find best match, keeping link to parent */
+	while (1 & (uintptr_t)p) {
+		whereq = wherep;
+		q = cb_node_of(p);
+		c = q->byte < klen ? k[q->byte] : 0;
+		direction = (1 + (q->otherbits | c)) >> 8;
+		wherep = q->child + direction;
+		p = *wherep;
+	}
+
+	if (memcmp(p->k, k, klen))
+		return NULL;		/* no match, nothing unlinked */
+
+	/* found an exact match */
+	if (whereq)	/* update parent */
+		*whereq = q->child[1 - direction];
+	else
+		t->root = NULL;
+	return p;
+}
+
+static enum cb_next cb_descend(struct cb_node *p, cb_iter fn, void *arg)
+{
+	if (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		enum cb_next n = cb_descend(q->child[0], fn, arg);
+
+		return n == CB_BREAK ? n : cb_descend(q->child[1], fn, arg);
+	} else {
+		return fn(p, arg);
+	}
+}
+
+void cb_each(struct cb_tree *t, const uint8_t *kpfx, size_t klen,
+			cb_iter fn, void *arg)
+{
+	struct cb_node *p = t->root;
+	struct cb_node *top = p;
+	size_t i = 0;
+
+	if (!p) return; /* empty tree */
+
+	/* Walk tree, maintaining top pointer */
+	while (1 & (uintptr_t)p) {
+		struct cb_node *q = cb_node_of(p);
+		uint8_t c = q->byte < klen ? kpfx[q->byte] : 0;
+		size_t direction = (1 + (q->otherbits | c)) >> 8;
+
+		p = q->child[direction];
+		if (q->byte < klen)
+			top = p;
+	}
+
+	for (i = 0; i < klen; i++) {
+		if (p->k[i] != kpfx[i])
+			return; /* "best" match failed */
+	}
+	cb_descend(top, fn, arg);
+}
diff --git a/cbtree.h b/cbtree.h
new file mode 100644
index 0000000..fe45870
--- /dev/null
+++ b/cbtree.h
@@ -0,0 +1,56 @@
+/*
+ * crit-bit tree implementation, does no allocations internally
+ * For more information on crit-bit trees: https://cr.yp.to/critbit.html
+ * Based on Adam Langley's adaptation of Dan Bernstein's public domain code
+ * git clone https://github.com/agl/critbit.git
+ *
+ * This is adapted to store arbitrary data (not just NUL-terminated C strings
+ * and allocates no memory internally.  The user needs to allocate
+ * "struct cb_node" and fill cb_node.k[] with arbitrary match data
+ * for memcmp.
+ * If "klen" is variable, then it should be embedded into "c_node.k[]"
+ * Recursion is bound by the maximum value of "klen" used.
+ */
+#ifndef CBTREE_H
+#define CBTREE_H
+
+#include "git-compat-util.h"
+
+struct cb_node;
+struct cb_node {
+	struct cb_node *child[2];
+	/*
+	 * n.b. uint32_t for `byte' is excessive for OIDs,
+	 * we may consider shorter variants if nothing else gets stored.
+	 */
+	uint32_t byte;
+	uint8_t otherbits;
+	uint8_t k[FLEX_ARRAY]; /* arbitrary data */
+};
+
+struct cb_tree {
+	struct cb_node *root;
+};
+
+enum cb_next {
+	CB_CONTINUE = 0,
+	CB_BREAK = 1
+};
+
+#define CBTREE_INIT { .root = NULL }
+
+static inline void cb_init(struct cb_tree *t)
+{
+	t->root = NULL;
+}
+
+struct cb_node *cb_lookup(struct cb_tree *, const uint8_t *k, size_t klen);
+struct cb_node *cb_insert(struct cb_tree *, struct cb_node *, size_t klen);
+struct cb_node *cb_unlink(struct cb_tree *t, const uint8_t *k, size_t klen);
+
+typedef enum cb_next (*cb_iter)(struct cb_node *, void *arg);
+
+void cb_each(struct cb_tree *, const uint8_t *kpfx, size_t klen,
+		cb_iter, void *arg);
+
+#endif /* CBTREE_H */
diff --git a/ci/install-dependencies.sh b/ci/install-dependencies.sh
index 67852d0..5772081 100755
--- a/ci/install-dependencies.sh
+++ b/ci/install-dependencies.sh
@@ -65,6 +65,11 @@
 	sudo apt-get -q -y install coccinelle libcurl4-openssl-dev libssl-dev \
 		libexpat-dev gettext make
 	;;
+sparse)
+	sudo apt-get -q update -q
+	sudo apt-get -q -y install libssl-dev libcurl4-openssl-dev \
+		libexpat-dev gettext zlib1g-dev
+	;;
 Documentation)
 	sudo apt-get -q update
 	sudo apt-get -q -y install asciidoc xmlto docbook-xsl-ns make
diff --git a/commit-graph.c b/commit-graph.c
index 1a2602d..3860a0d 100644
--- a/commit-graph.c
+++ b/commit-graph.c
@@ -2408,6 +2408,7 @@
 #define VERIFY_COMMIT_GRAPH_ERROR_HASH 2
 static int verify_commit_graph_error;
 
+__attribute__((format (printf, 1, 2)))
 static void graph_report(const char *fmt, ...)
 {
 	va_list ap;
diff --git a/contrib/credential/osxkeychain/git-credential-osxkeychain.c b/contrib/credential/osxkeychain/git-credential-osxkeychain.c
index bcd3f57..0b44a9b 100644
--- a/contrib/credential/osxkeychain/git-credential-osxkeychain.c
+++ b/contrib/credential/osxkeychain/git-credential-osxkeychain.c
@@ -10,6 +10,7 @@
 static char *password;
 static UInt16 port;
 
+__attribute__((format (printf, 1, 2)))
 static void die(const char *err, ...)
 {
 	char msg[4096];
diff --git a/contrib/credential/wincred/git-credential-wincred.c b/contrib/credential/wincred/git-credential-wincred.c
index 5bdad41..5091048 100644
--- a/contrib/credential/wincred/git-credential-wincred.c
+++ b/contrib/credential/wincred/git-credential-wincred.c
@@ -11,6 +11,7 @@
 
 #define ARRAY_SIZE(x) (sizeof(x)/sizeof(x[0]))
 
+__attribute__((format (printf, 1, 2)))
 static void die(const char *err, ...)
 {
 	char msg[4096];
diff --git a/diff-lib.c b/diff-lib.c
index c2ac925..f9eadc4 100644
--- a/diff-lib.c
+++ b/diff-lib.c
@@ -325,6 +325,11 @@
 	unsigned dirty_submodule = 0;
 	struct index_state *istate = revs->diffopt.repo->index;
 
+	if (new_file && S_ISSPARSEDIR(new_file->ce_mode)) {
+		diff_tree_oid(NULL, &new_file->oid, new_file->name, &revs->diffopt);
+		return;
+	}
+
 	/*
 	 * New file in the index: it might actually be different in
 	 * the working tree.
@@ -347,6 +352,20 @@
 	unsigned dirty_submodule = 0;
 	struct index_state *istate = revs->diffopt.repo->index;
 
+	assert(S_ISSPARSEDIR(old_entry->ce_mode) ==
+	       S_ISSPARSEDIR(new_entry->ce_mode));
+
+	/*
+	 * If both are sparse directory entries, then expand the
+	 * modifications to the file level. If only one was a sparse
+	 * directory, then they appear as an add and delete instead of
+	 * a modification.
+	 */
+	if (S_ISSPARSEDIR(new_entry->ce_mode)) {
+		diff_tree_oid(&old_entry->oid, &new_entry->oid, new_entry->name, &revs->diffopt);
+		return 0;
+	}
+
 	if (get_stat_data(istate, new_entry, &oid, &mode, cached, match_missing,
 			  &dirty_submodule, &revs->diffopt) < 0) {
 		if (report_missing)
diff --git a/diff.c b/diff.c
index 260dc37..82f88de 100644
--- a/diff.c
+++ b/diff.c
@@ -35,7 +35,7 @@
 
 static int diff_detect_rename_default;
 static int diff_indent_heuristic = 1;
-static int diff_rename_limit_default = 400;
+static int diff_rename_limit_default = 1000;
 static int diff_suppress_blank_empty;
 static int diff_use_color_default = -1;
 static int diff_color_moved_default;
@@ -6295,7 +6295,7 @@
 }
 
 static const char rename_limit_warning[] =
-N_("inexact rename detection was skipped due to too many files.");
+N_("exhaustive rename detection was skipped due to too many files.");
 
 static const char degrade_cc_to_c_warning[] =
 N_("only found copies from modified paths due to too many files.");
diff --git a/diffcore-rename.c b/diffcore-rename.c
index 4ef0459..2618bb0 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -1091,7 +1091,7 @@
 	 * memory for the matrix anyway.
 	 */
 	if (rename_limit <= 0)
-		rename_limit = 32767;
+		return 0; /* treat as unlimited */
 	if (st_mult(num_destinations, num_sources)
 	    <= st_mult(rename_limit, rename_limit))
 		return 0;
diff --git a/dir.c b/dir.c
index 313e932..23b4417 100644
--- a/dir.c
+++ b/dir.c
@@ -78,11 +78,21 @@
 	return ignore_case ? strcasecmp(a, b) : strcmp(a, b);
 }
 
+int fspatheq(const char *a, const char *b)
+{
+	return !fspathcmp(a, b);
+}
+
 int fspathncmp(const char *a, const char *b, size_t count)
 {
 	return ignore_case ? strncasecmp(a, b, count) : strncmp(a, b, count);
 }
 
+unsigned int fspathhash(const char *str)
+{
+	return ignore_case ? strihash(str) : strhash(str);
+}
+
 int git_fnmatch(const struct pathspec_item *item,
 		const char *pattern, const char *string,
 		int prefix)
@@ -1370,7 +1380,7 @@
 	struct path_pattern *pattern;
 	struct strbuf parent_pathname = STRBUF_INIT;
 	int result = NOT_MATCHED;
-	const char *slash_pos;
+	size_t slash_pos;
 
 	if (!pl->use_cone_patterns) {
 		pattern = last_matching_pattern_from_list(pathname, pathlen, basename,
@@ -1391,21 +1401,35 @@
 	strbuf_addch(&parent_pathname, '/');
 	strbuf_add(&parent_pathname, pathname, pathlen);
 
+	/*
+	 * Directory entries are matched if and only if a file
+	 * contained immediately within them is matched. For the
+	 * case of a directory entry, modify the path to create
+	 * a fake filename within this directory, allowing us to
+	 * use the file-base matching logic in an equivalent way.
+	 */
+	if (parent_pathname.len > 0 &&
+	    parent_pathname.buf[parent_pathname.len - 1] == '/') {
+		slash_pos = parent_pathname.len - 1;
+		strbuf_add(&parent_pathname, "-", 1);
+	} else {
+		const char *slash_ptr = strrchr(parent_pathname.buf, '/');
+		slash_pos = slash_ptr ? slash_ptr - parent_pathname.buf : 0;
+	}
+
 	if (hashmap_contains_path(&pl->recursive_hashmap,
 				  &parent_pathname)) {
 		result = MATCHED_RECURSIVE;
 		goto done;
 	}
 
-	slash_pos = strrchr(parent_pathname.buf, '/');
-
-	if (slash_pos == parent_pathname.buf) {
+	if (!slash_pos) {
 		/* include every file in root */
 		result = MATCHED;
 		goto done;
 	}
 
-	strbuf_setlen(&parent_pathname, slash_pos - parent_pathname.buf);
+	strbuf_setlen(&parent_pathname, slash_pos);
 
 	if (hashmap_contains_path(&pl->parent_hashmap, &parent_pathname)) {
 		result = MATCHED;
diff --git a/dir.h b/dir.h
index 8d0ddd8..b3e1a54a 100644
--- a/dir.h
+++ b/dir.h
@@ -489,7 +489,9 @@
 int remove_path(const char *path);
 
 int fspathcmp(const char *a, const char *b);
+int fspatheq(const char *a, const char *b);
 int fspathncmp(const char *a, const char *b, size_t count);
+unsigned int fspathhash(const char *str);
 
 /*
  * The prefix part of pattern must not contains wildcards.
diff --git a/gettext.c b/gettext.c
index af2413b..bb5ba1f 100644
--- a/gettext.c
+++ b/gettext.c
@@ -66,6 +66,7 @@
 }
 
 #ifndef NO_GETTEXT
+__attribute__((format (printf, 1, 2)))
 static int test_vsnprintf(const char *fmt, ...)
 {
 	char buf[26];
diff --git a/git-send-email.perl b/git-send-email.perl
index 7ba0b34..e65d969 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -18,21 +18,11 @@
 
 use 5.008;
 use strict;
-use warnings;
-use POSIX qw/strftime/;
-use Term::ReadLine;
+use warnings $ENV{GIT_PERL_FATAL_WARNINGS} ? qw(FATAL all) : ();
 use Getopt::Long;
-use Text::ParseWords;
-use Term::ANSIColor;
-use File::Temp qw/ tempdir tempfile /;
-use File::Spec::Functions qw(catdir catfile);
 use Git::LoadCPAN::Error qw(:try);
-use Cwd qw(abs_path cwd);
 use Git;
 use Git::I18N;
-use Net::Domain ();
-use Net::SMTP ();
-use Git::LoadCPAN::Mail::Address;
 
 Getopt::Long::Configure qw/ pass_through /;
 
@@ -167,7 +157,6 @@
 		       );
 }
 
-my $have_email_valid = eval { require Email::Valid; 1 };
 my $smtp;
 my $auth;
 my $num_sent = 0;
@@ -193,14 +182,6 @@
 
 my $repo = eval { Git->repository() };
 my @repo = $repo ? ($repo) : ();
-my $term = eval {
-	$ENV{"GIT_SEND_EMAIL_NOTTY"}
-		? new Term::ReadLine 'git-send-email', \*STDIN, \*STDOUT
-		: new Term::ReadLine 'git-send-email';
-};
-if ($@) {
-	$term = new FakeTerm "$@: going non-interactive";
-}
 
 # Behavior modification variables
 my ($quiet, $dry_run) = (0, 0);
@@ -289,6 +270,7 @@
 );
 
 my %config_settings = (
+    "smtpencryption" => \$smtp_encryption,
     "smtpserver" => \$smtp_server,
     "smtpserverport" => \$smtp_server_port,
     "smtpserveroption" => \@smtp_server_options,
@@ -321,9 +303,9 @@
 
 # Handle Uncouth Termination
 sub signal_handler {
-
 	# Make text normal
-	print color("reset"), "\n";
+	require Term::ANSIColor;
+	print Term::ANSIColor::color("reset"), "\n";
 
 	# SMTP password masked
 	system "stty echo";
@@ -349,11 +331,17 @@
 
 # Read our sendemail.* config
 sub read_config {
-	my ($configured, $prefix) = @_;
+	my ($known_keys, $configured, $prefix) = @_;
 
 	foreach my $setting (keys %config_bool_settings) {
 		my $target = $config_bool_settings{$setting};
-		my $v = Git::config_bool(@repo, "$prefix.$setting");
+		my $key = "$prefix.$setting";
+		next unless exists $known_keys->{$key};
+		my $v = (@{$known_keys->{$key}} == 1 &&
+			 (defined $known_keys->{$key}->[0] &&
+			  $known_keys->{$key}->[0] =~ /^(?:true|false)$/s))
+			? $known_keys->{$key}->[0] eq 'true'
+			: Git::config_bool(@repo, $key);
 		next unless defined $v;
 		next if $configured->{$setting}++;
 		$$target = $v;
@@ -361,8 +349,10 @@
 
 	foreach my $setting (keys %config_path_settings) {
 		my $target = $config_path_settings{$setting};
+		my $key = "$prefix.$setting";
+		next unless exists $known_keys->{$key};
 		if (ref($target) eq "ARRAY") {
-			my @values = Git::config_path(@repo, "$prefix.$setting");
+			my @values = Git::config_path(@repo, $key);
 			next unless @values;
 			next if $configured->{$setting}++;
 			@$target = @values;
@@ -377,36 +367,64 @@
 
 	foreach my $setting (keys %config_settings) {
 		my $target = $config_settings{$setting};
+		my $key = "$prefix.$setting";
+		next unless exists $known_keys->{$key};
 		if (ref($target) eq "ARRAY") {
-			my @values = Git::config(@repo, "$prefix.$setting");
-			next unless @values;
+			my @values = @{$known_keys->{$key}};
+			@values = grep { defined } @values;
 			next if $configured->{$setting}++;
 			@$target = @values;
 		}
 		else {
-			my $v = Git::config(@repo, "$prefix.$setting");
+			my $v = $known_keys->{$key}->[0];
 			next unless defined $v;
 			next if $configured->{$setting}++;
 			$$target = $v;
 		}
 	}
+}
 
-	if (!defined $smtp_encryption) {
-		my $setting = "$prefix.smtpencryption";
-		my $enc = Git::config(@repo, $setting);
-		return unless defined $enc;
-		return if $configured->{$setting}++;
-		if (defined $enc) {
-			$smtp_encryption = $enc;
-		} elsif (Git::config_bool(@repo, "$prefix.smtpssl")) {
-			$smtp_encryption = 'ssl';
-		}
+sub config_regexp {
+	my ($regex) = @_;
+	my @ret;
+	eval {
+		my $ret = Git::command(
+			'config',
+			'--null',
+			'--get-regexp',
+			$regex,
+		);
+		@ret = map {
+			# We must always return ($k, $v) here, since
+			# empty config values will be just "key\0",
+			# not "key\nvalue\0".
+			my ($k, $v) = split /\n/, $_, 2;
+			($k, $v);
+		} split /\0/, $ret;
+		1;
+	} or do {
+		# If we have no keys we're OK, otherwise re-throw
+		die $@ if $@->value != 1;
+	};
+	return @ret;
+}
+
+# Save ourselves a lot of work of shelling out to 'git config' (it
+# parses 'bool' etc.) by only doing so for config keys that exist.
+my %known_config_keys;
+{
+	my @kv = config_regexp("^sende?mail[.]");
+	while (my ($k, $v) = splice @kv, 0, 2) {
+		push @{$known_config_keys{$k}} => $v;
 	}
 }
 
 # sendemail.identity yields to --identity. We must parse this
 # special-case first before the rest of the config is read.
-$identity = Git::config(@repo, "sendemail.identity");
+{
+	my $key = "sendemail.identity";
+	$identity = Git::config(@repo, $key) if exists $known_config_keys{$key};
+}
 my $rc = GetOptions(
 	"identity=s" => \$identity,
 	"no-identity" => \$no_identity,
@@ -417,8 +435,8 @@
 # Now we know enough to read the config
 {
     my %configured;
-    read_config(\%configured, "sendemail.$identity") if defined $identity;
-    read_config(\%configured, "sendemail");
+    read_config(\%known_config_keys, \%configured, "sendemail.$identity") if defined $identity;
+    read_config(\%known_config_keys, \%configured, "sendemail");
 }
 
 # Begin by accumulating all the variables (defined above), that we will end up
@@ -503,7 +521,7 @@
     usage();
 }
 
-if ($forbid_sendmail_variables && (scalar Git::config_regexp("^sendmail[.]")) != 0) {
+if ($forbid_sendmail_variables && grep { /^sendmail/s } keys %known_config_keys) {
 	die __("fatal: found configuration options for 'sendmail'\n" .
 		"git-send-email is configured with the sendemail.* options - note the 'e'.\n" .
 		"Set sendemail.forbidSendmailVariables to false to disable this check.\n");
@@ -568,15 +586,27 @@
 }
 
 my ($repoauthor, $repocommitter);
-($repoauthor) = Git::ident_person(@repo, 'author');
-($repocommitter) = Git::ident_person(@repo, 'committer');
+{
+	my %cache;
+	my ($author, $committer);
+	my $common = sub {
+		my ($what) = @_;
+		return $cache{$what} if exists $cache{$what};
+		($cache{$what}) = Git::ident_person(@repo, $what);
+		return $cache{$what};
+	};
+	$repoauthor = sub { $common->('author') };
+	$repocommitter = sub { $common->('committer') };
+}
 
 sub parse_address_line {
+	require Git::LoadCPAN::Mail::Address;
 	return map { $_->format } Mail::Address->parse($_[0]);
 }
 
 sub split_addrs {
-	return quotewords('\s*,\s*', 1, @_);
+	require Text::ParseWords;
+	return Text::ParseWords::quotewords('\s*,\s*', 1, @_);
 }
 
 my %aliases;
@@ -625,10 +655,11 @@
 			s/\\"/"/g foreach @addr;
 			$aliases{$alias} = \@addr
 		}}},
-	mailrc => sub { my $fh = shift; while (<$fh>) {
+	mailrc => sub {	my $fh = shift; while (<$fh>) {
 		if (/^alias\s+(\S+)\s+(.*?)\s*$/) {
+			require Text::ParseWords;
 			# spaces delimit multiple addresses
-			$aliases{$1} = [ quotewords('\s+', 0, $2) ];
+			$aliases{$1} = [ Text::ParseWords::quotewords('\s+', 0, $2) ];
 		}}},
 	pine => sub { my $fh = shift; my $f='\t[^\t]*';
 	        for (my $x = ''; defined($x); $x = $_) {
@@ -676,7 +707,7 @@
 		if (defined($format_patch)) {
 			return $format_patch;
 		}
-		die sprintf(__ <<EOF, $f, $f);
+		die sprintf(__(<<EOF), $f, $f);
 File '%s' exists but it could also be the range of commits
 to produce patches for.  Please disambiguate by...
 
@@ -700,7 +731,8 @@
 		opendir my $dh, $f
 			or die sprintf(__("Failed to opendir %s: %s"), $f, $!);
 
-		push @files, grep { -f $_ } map { catfile($f, $_) }
+		require File::Spec;
+		push @files, grep { -f $_ } map { File::Spec->catfile($f, $_) }
 				sort readdir $dh;
 		closedir $dh;
 	} elsif ((-f $f or -p $f) and !is_format_patch_arg($f)) {
@@ -713,7 +745,8 @@
 if (@rev_list_opts) {
 	die __("Cannot run git format-patch from outside a repository\n")
 		unless $repo;
-	push @files, $repo->command('format-patch', '-o', tempdir(CLEANUP => 1), @rev_list_opts);
+	require File::Temp;
+	push @files, $repo->command('format-patch', '-o', File::Temp::tempdir(CLEANUP => 1), @rev_list_opts);
 }
 
 @files = handle_backup_files(@files);
@@ -750,19 +783,20 @@
 if ($compose) {
 	# Note that this does not need to be secure, but we will make a small
 	# effort to have it be unique
+	require File::Temp;
 	$compose_filename = ($repo ?
-		tempfile(".gitsendemail.msg.XXXXXX", DIR => $repo->repo_path()) :
-		tempfile(".gitsendemail.msg.XXXXXX", DIR => "."))[1];
+		File::Temp::tempfile(".gitsendemail.msg.XXXXXX", DIR => $repo->repo_path()) :
+		File::Temp::tempfile(".gitsendemail.msg.XXXXXX", DIR => "."))[1];
 	open my $c, ">", $compose_filename
 		or die sprintf(__("Failed to open for writing %s: %s"), $compose_filename, $!);
 
 
-	my $tpl_sender = $sender || $repoauthor || $repocommitter || '';
+	my $tpl_sender = $sender || $repoauthor->() || $repocommitter->() || '';
 	my $tpl_subject = $initial_subject || '';
 	my $tpl_in_reply_to = $initial_in_reply_to || '';
 	my $tpl_reply_to = $reply_to || '';
 
-	print $c <<EOT1, Git::prefix_lines("GIT: ", __ <<EOT2), <<EOT3;
+	print $c <<EOT1, Git::prefix_lines("GIT: ", __(<<EOT2)), <<EOT3;
 From $tpl_sender # This line is ignored.
 EOT1
 Lines beginning in "GIT:" will be removed.
@@ -859,6 +893,19 @@
 	do_edit(@files);
 }
 
+sub term {
+	my $term = eval {
+		require Term::ReadLine;
+		$ENV{"GIT_SEND_EMAIL_NOTTY"}
+			? Term::ReadLine->new('git-send-email', \*STDIN, \*STDOUT)
+			: Term::ReadLine->new('git-send-email');
+	};
+	if ($@) {
+		$term = FakeTerm->new("$@: going non-interactive");
+	}
+	return $term;
+}
+
 sub ask {
 	my ($prompt, %arg) = @_;
 	my $valid_re = $arg{valid_re};
@@ -866,6 +913,7 @@
 	my $confirm_only = $arg{confirm_only};
 	my $resp;
 	my $i = 0;
+	my $term = term();
 	return defined $default ? $default : undef
 		unless defined $term->IN and defined fileno($term->IN) and
 		       defined $term->OUT and defined fileno($term->OUT);
@@ -963,7 +1011,7 @@
 	$sender =~ s/^\s+|\s+$//g;
 	($sender) = expand_aliases($sender);
 } else {
-	$sender = $repoauthor || $repocommitter || '';
+	$sender = $repoauthor->() || $repocommitter->() || '';
 }
 
 # $sender could be an already sanitized address
@@ -1049,6 +1097,7 @@
 	return $address if ($address =~ /^($local_part_regexp)$/);
 
 	$address =~ s/^\s*<(.*)>\s*$/$1/;
+	my $have_email_valid = eval { require Email::Valid; 1 };
 	if ($have_email_valid) {
 		return scalar Email::Valid->address($address);
 	}
@@ -1108,14 +1157,15 @@
 sub make_message_id {
 	my $uniq;
 	if (!defined $message_id_stamp) {
-		$message_id_stamp = strftime("%Y%m%d%H%M%S.$$", gmtime(time));
+		require POSIX;
+		$message_id_stamp = POSIX::strftime("%Y%m%d%H%M%S.$$", gmtime(time));
 		$message_id_serial = 0;
 	}
 	$message_id_serial++;
 	$uniq = "$message_id_stamp-$message_id_serial";
 
 	my $du_part;
-	for ($sender, $repocommitter, $repoauthor) {
+	for ($sender, $repocommitter->(), $repoauthor->()) {
 		$du_part = extract_valid_address(sanitize_address($_));
 		last if (defined $du_part and $du_part ne '');
 	}
@@ -1278,6 +1328,7 @@
 sub maildomain_net {
 	my $maildomain;
 
+	require Net::Domain;
 	my $domain = Net::Domain::domainname();
 	$maildomain = $domain if valid_fqdn($domain);
 
@@ -1288,6 +1339,7 @@
 	my $maildomain;
 
 	for my $host (qw(mailhost localhost)) {
+		require Net::SMTP;
 		my $smtp = Net::SMTP->new($host);
 		if (defined $smtp) {
 			my $domain = $smtp->domain;
@@ -1980,13 +2032,15 @@
 
 	if ($repo) {
 		my $hooks_path = $repo->command_oneline('rev-parse', '--git-path', 'hooks');
-		my $validate_hook = catfile($hooks_path,
+		require File::Spec;
+		my $validate_hook = File::Spec->catfile($hooks_path,
 					    'sendemail-validate');
 		my $hook_error;
 		if (-x $validate_hook) {
-			my $target = abs_path($fn);
+			require Cwd;
+			my $target = Cwd::abs_path($fn);
 			# The hook needs a correct cwd and GIT_DIR.
-			my $cwd_save = cwd();
+			my $cwd_save = Cwd::getcwd();
 			chdir($repo->wc_path() or $repo->repo_path())
 				or die("chdir: $!");
 			local $ENV{"GIT_DIR"} = $repo->repo_path();
diff --git a/hash.h b/hash.h
index 9c6df4d..27a1802 100644
--- a/hash.h
+++ b/hash.h
@@ -265,7 +265,7 @@
 
 /* Like oidcpy() but zero-pads the unused bytes in dst's hash array. */
 static inline void oidcpy_with_padding(struct object_id *dst,
-				       struct object_id *src)
+				       const struct object_id *src)
 {
 	size_t hashsz;
 
diff --git a/imap-send.c b/imap-send.c
index bb085d6..a0540ba 100644
--- a/imap-send.c
+++ b/imap-send.c
@@ -451,6 +451,7 @@
 	/* not reached */
 }
 
+__attribute__((format (printf, 1, 2)))
 static void imap_info(const char *msg, ...)
 {
 	va_list va;
@@ -463,6 +464,7 @@
 	}
 }
 
+__attribute__((format (printf, 1, 2)))
 static void imap_warn(const char *msg, ...)
 {
 	va_list va;
@@ -504,6 +506,7 @@
 	return ret;
 }
 
+__attribute__((format (printf, 3, 4)))
 static int nfsnprintf(char *buf, int blen, const char *fmt, ...)
 {
 	int ret;
@@ -1266,18 +1269,6 @@
 	*msg = buf;
 }
 
-#define CHUNKSIZE 0x1000
-
-static int read_message(FILE *f, struct strbuf *all_msgs)
-{
-	do {
-		if (strbuf_fread(all_msgs, CHUNKSIZE, f) <= 0)
-			break;
-	} while (!feof(f));
-
-	return ferror(f) ? -1 : 0;
-}
-
 static int count_messages(struct strbuf *all_msgs)
 {
 	int count = 0;
@@ -1582,8 +1573,8 @@
 	}
 
 	/* read the messages */
-	if (read_message(stdin, &all_msgs)) {
-		fprintf(stderr, "error reading input\n");
+	if (strbuf_read(&all_msgs, 0, 0) < 0) {
+		error_errno(_("could not read from stdin"));
 		return 1;
 	}
 
diff --git a/log-tree.c b/log-tree.c
index 7b82378..6dc4412 100644
--- a/log-tree.c
+++ b/log-tree.c
@@ -134,7 +134,8 @@
 			      int flags, void *cb_data)
 {
 	struct object *obj;
-	enum decoration_type type = DECORATION_NONE;
+	enum object_type objtype;
+	enum decoration_type deco_type = DECORATION_NONE;
 	struct decoration_filter *filter = (struct decoration_filter *)cb_data;
 
 	if (filter && !ref_filter_match(refname, filter))
@@ -155,28 +156,29 @@
 		return 0;
 	}
 
-	obj = parse_object(the_repository, oid);
-	if (!obj)
+	objtype = oid_object_info(the_repository, oid, NULL);
+	if (objtype < 0)
 		return 0;
+	obj = lookup_object_by_type(the_repository, oid, objtype);
 
 	if (starts_with(refname, "refs/heads/"))
-		type = DECORATION_REF_LOCAL;
+		deco_type = DECORATION_REF_LOCAL;
 	else if (starts_with(refname, "refs/remotes/"))
-		type = DECORATION_REF_REMOTE;
+		deco_type = DECORATION_REF_REMOTE;
 	else if (starts_with(refname, "refs/tags/"))
-		type = DECORATION_REF_TAG;
+		deco_type = DECORATION_REF_TAG;
 	else if (!strcmp(refname, "refs/stash"))
-		type = DECORATION_REF_STASH;
+		deco_type = DECORATION_REF_STASH;
 	else if (!strcmp(refname, "HEAD"))
-		type = DECORATION_REF_HEAD;
+		deco_type = DECORATION_REF_HEAD;
 
-	add_name_decoration(type, refname, obj);
+	add_name_decoration(deco_type, refname, obj);
 	while (obj->type == OBJ_TAG) {
+		if (!obj->parsed)
+			parse_object(the_repository, &obj->oid);
 		obj = ((struct tag *)obj)->tagged;
 		if (!obj)
 			break;
-		if (!obj->parsed)
-			parse_object(the_repository, &obj->oid);
 		add_name_decoration(DECORATION_REF_TAG, refname, obj);
 	}
 	return 0;
diff --git a/mailmap.c b/mailmap.c
index d1f7c0d..462b395 100644
--- a/mailmap.c
+++ b/mailmap.c
@@ -8,6 +8,7 @@
 #define debug_mm(...) fprintf(stderr, __VA_ARGS__)
 #define debug_str(X) ((X) ? (X) : "(none)")
 #else
+__attribute__((format (printf, 1, 2)))
 static inline void debug_mm(const char *format, ...) {}
 static inline const char *debug_str(const char *s) { return s; }
 #endif
diff --git a/merge-ort.c b/merge-ort.c
index 8cfa0cc..ec0c590 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -530,6 +530,7 @@
 	renames->callback_data_nr = renames->callback_data_alloc = 0;
 }
 
+__attribute__((format (printf, 2, 3)))
 static int err(struct merge_options *opt, const char *err, ...)
 {
 	va_list params;
@@ -2562,7 +2563,7 @@
 	diff_opts.detect_rename = DIFF_DETECT_RENAME;
 	diff_opts.rename_limit = opt->rename_limit;
 	if (opt->rename_limit <= 0)
-		diff_opts.rename_limit = 1000;
+		diff_opts.rename_limit = 7000;
 	diff_opts.rename_score = opt->rename_score;
 	diff_opts.show_rename_progress = opt->show_rename_progress;
 	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
diff --git a/merge-recursive.c b/merge-recursive.c
index a67bf2a..7008a90 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -167,6 +167,7 @@
 	}
 }
 
+__attribute__((format (printf, 2, 3)))
 static int err(struct merge_options *opt, const char *err, ...)
 {
 	va_list params;
@@ -1879,7 +1880,7 @@
 	 */
 	if (opts.detect_rename > DIFF_DETECT_RENAME)
 		opts.detect_rename = DIFF_DETECT_RENAME;
-	opts.rename_limit = (opt->rename_limit >= 0) ? opt->rename_limit : 1000;
+	opts.rename_limit = (opt->rename_limit >= 0) ? opt->rename_limit : 7000;
 	opts.rename_score = opt->rename_score;
 	opts.show_rename_progress = opt->show_rename_progress;
 	opts.output_format = DIFF_FORMAT_NO_OUTPUT;
diff --git a/midx.c b/midx.c
index 9a35b02..321c6fd 100644
--- a/midx.c
+++ b/midx.c
@@ -1172,6 +1172,7 @@
 
 static int verify_midx_error;
 
+__attribute__((format (printf, 1, 2)))
 static void midx_report(const char *fmt, ...)
 {
 	va_list ap;
diff --git a/object-file.c b/object-file.c
index ecca5a8..3d27dc8 100644
--- a/object-file.c
+++ b/object-file.c
@@ -517,9 +517,9 @@
  */
 static int alt_odb_usable(struct raw_object_store *o,
 			  struct strbuf *path,
-			  const char *normalized_objdir)
+			  const char *normalized_objdir, khiter_t *pos)
 {
-	struct object_directory *odb;
+	int r;
 
 	/* Detect cases where alternate disappeared */
 	if (!is_directory(path->buf)) {
@@ -533,14 +533,20 @@
 	 * Prevent the common mistake of listing the same
 	 * thing twice, or object directory itself.
 	 */
-	for (odb = o->odb; odb; odb = odb->next) {
-		if (!fspathcmp(path->buf, odb->path))
-			return 0;
-	}
-	if (!fspathcmp(path->buf, normalized_objdir))
-		return 0;
+	if (!o->odb_by_path) {
+		khiter_t p;
 
-	return 1;
+		o->odb_by_path = kh_init_odb_path_map();
+		assert(!o->odb->next);
+		p = kh_put_odb_path_map(o->odb_by_path, o->odb->path, &r);
+		assert(r == 1); /* never used */
+		kh_value(o->odb_by_path, p) = o->odb;
+	}
+	if (fspatheq(path->buf, normalized_objdir))
+		return 0;
+	*pos = kh_put_odb_path_map(o->odb_by_path, path->buf, &r);
+	/* r: 0 = exists, 1 = never used, 2 = deleted */
+	return r == 0 ? 0 : 1;
 }
 
 /*
@@ -561,17 +567,18 @@
 static void read_info_alternates(struct repository *r,
 				 const char *relative_base,
 				 int depth);
-static int link_alt_odb_entry(struct repository *r, const char *entry,
+static int link_alt_odb_entry(struct repository *r, const struct strbuf *entry,
 	const char *relative_base, int depth, const char *normalized_objdir)
 {
 	struct object_directory *ent;
 	struct strbuf pathbuf = STRBUF_INIT;
+	khiter_t pos;
 
-	if (!is_absolute_path(entry) && relative_base) {
+	if (!is_absolute_path(entry->buf) && relative_base) {
 		strbuf_realpath(&pathbuf, relative_base, 1);
 		strbuf_addch(&pathbuf, '/');
 	}
-	strbuf_addstr(&pathbuf, entry);
+	strbuf_addbuf(&pathbuf, entry);
 
 	if (strbuf_normalize_path(&pathbuf) < 0 && relative_base) {
 		error(_("unable to normalize alternate object path: %s"),
@@ -587,23 +594,25 @@
 	while (pathbuf.len && pathbuf.buf[pathbuf.len - 1] == '/')
 		strbuf_setlen(&pathbuf, pathbuf.len - 1);
 
-	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir)) {
+	if (!alt_odb_usable(r->objects, &pathbuf, normalized_objdir, &pos)) {
 		strbuf_release(&pathbuf);
 		return -1;
 	}
 
 	CALLOC_ARRAY(ent, 1);
-	ent->path = xstrdup(pathbuf.buf);
+	/* pathbuf.buf is already in r->objects->odb_by_path */
+	ent->path = strbuf_detach(&pathbuf, NULL);
 
 	/* add the alternate entry */
 	*r->objects->odb_tail = ent;
 	r->objects->odb_tail = &(ent->next);
 	ent->next = NULL;
+	assert(r->objects->odb_by_path);
+	kh_value(r->objects->odb_by_path, pos) = ent;
 
 	/* recursively add alternates */
-	read_info_alternates(r, pathbuf.buf, depth + 1);
+	read_info_alternates(r, ent->path, depth + 1);
 
-	strbuf_release(&pathbuf);
 	return 0;
 }
 
@@ -660,7 +669,7 @@
 		alt = parse_alt_odb_entry(alt, sep, &entry);
 		if (!entry.len)
 			continue;
-		link_alt_odb_entry(r, entry.buf,
+		link_alt_odb_entry(r, &entry,
 				   relative_base, depth, objdirbuf.buf);
 	}
 	strbuf_release(&entry);
@@ -1178,7 +1187,7 @@
 
 	prepare_alt_odb(r);
 	for (odb = r->objects->odb; odb; odb = odb->next) {
-		if (oid_array_lookup(odb_loose_cache(odb, oid), oid) >= 0)
+		if (oidtree_contains(odb_loose_cache(odb, oid), oid))
 			return 1;
 	}
 	return 0;
@@ -2454,39 +2463,45 @@
 static int append_loose_object(const struct object_id *oid, const char *path,
 			       void *data)
 {
-	oid_array_append(data, oid);
+	oidtree_insert(data, oid);
 	return 0;
 }
 
-struct oid_array *odb_loose_cache(struct object_directory *odb,
+struct oidtree *odb_loose_cache(struct object_directory *odb,
 				  const struct object_id *oid)
 {
 	int subdir_nr = oid->hash[0];
 	struct strbuf buf = STRBUF_INIT;
+	size_t word_bits = bitsizeof(odb->loose_objects_subdir_seen[0]);
+	size_t word_index = subdir_nr / word_bits;
+	size_t mask = 1 << (subdir_nr % word_bits);
+	uint32_t *bitmap;
 
 	if (subdir_nr < 0 ||
-	    subdir_nr >= ARRAY_SIZE(odb->loose_objects_subdir_seen))
+	    subdir_nr >= bitsizeof(odb->loose_objects_subdir_seen))
 		BUG("subdir_nr out of range");
 
-	if (odb->loose_objects_subdir_seen[subdir_nr])
-		return &odb->loose_objects_cache[subdir_nr];
-
+	bitmap = &odb->loose_objects_subdir_seen[word_index];
+	if (*bitmap & mask)
+		return odb->loose_objects_cache;
+	if (!odb->loose_objects_cache) {
+		ALLOC_ARRAY(odb->loose_objects_cache, 1);
+		oidtree_init(odb->loose_objects_cache);
+	}
 	strbuf_addstr(&buf, odb->path);
 	for_each_file_in_obj_subdir(subdir_nr, &buf,
 				    append_loose_object,
 				    NULL, NULL,
-				    &odb->loose_objects_cache[subdir_nr]);
-	odb->loose_objects_subdir_seen[subdir_nr] = 1;
+				    odb->loose_objects_cache);
+	*bitmap |= mask;
 	strbuf_release(&buf);
-	return &odb->loose_objects_cache[subdir_nr];
+	return odb->loose_objects_cache;
 }
 
 void odb_clear_loose_cache(struct object_directory *odb)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(odb->loose_objects_cache); i++)
-		oid_array_clear(&odb->loose_objects_cache[i]);
+	oidtree_clear(odb->loose_objects_cache);
+	FREE_AND_NULL(odb->loose_objects_cache);
 	memset(&odb->loose_objects_subdir_seen, 0,
 	       sizeof(odb->loose_objects_subdir_seen));
 }
diff --git a/object-name.c b/object-name.c
index 64202de..3263c19 100644
--- a/object-name.c
+++ b/object-name.c
@@ -87,27 +87,21 @@
 
 static int match_hash(unsigned, const unsigned char *, const unsigned char *);
 
+static enum cb_next match_prefix(const struct object_id *oid, void *arg)
+{
+	struct disambiguate_state *ds = arg;
+	/* no need to call match_hash, oidtree_each did prefix match */
+	update_candidates(ds, oid);
+	return ds->ambiguous ? CB_BREAK : CB_CONTINUE;
+}
+
 static void find_short_object_filename(struct disambiguate_state *ds)
 {
 	struct object_directory *odb;
 
-	for (odb = ds->repo->objects->odb; odb && !ds->ambiguous; odb = odb->next) {
-		int pos;
-		struct oid_array *loose_objects;
-
-		loose_objects = odb_loose_cache(odb, &ds->bin_pfx);
-		pos = oid_array_lookup(loose_objects, &ds->bin_pfx);
-		if (pos < 0)
-			pos = -1 - pos;
-		while (!ds->ambiguous && pos < loose_objects->nr) {
-			const struct object_id *oid;
-			oid = loose_objects->oid + pos;
-			if (!match_hash(ds->len, ds->bin_pfx.hash, oid->hash))
-				break;
-			update_candidates(ds, oid);
-			pos++;
-		}
-	}
+	for (odb = ds->repo->objects->odb; odb && !ds->ambiguous; odb = odb->next)
+		oidtree_each(odb_loose_cache(odb, &ds->bin_pfx),
+				&ds->bin_pfx, ds->len, match_prefix, ds);
 }
 
 static int match_hash(unsigned len, const unsigned char *a, const unsigned char *b)
diff --git a/object-store.h b/object-store.h
index ec32c23..e679acc 100644
--- a/object-store.h
+++ b/object-store.h
@@ -7,6 +7,9 @@
 #include "oid-array.h"
 #include "strbuf.h"
 #include "thread-utils.h"
+#include "khash.h"
+#include "dir.h"
+#include "oidtree.h"
 
 struct object_directory {
 	struct object_directory *next;
@@ -20,8 +23,8 @@
 	 *
 	 * Be sure to call odb_load_loose_cache() before using.
 	 */
-	char loose_objects_subdir_seen[256];
-	struct oid_array loose_objects_cache[256];
+	uint32_t loose_objects_subdir_seen[8]; /* 256 bits */
+	struct oidtree *loose_objects_cache;
 
 	/*
 	 * Path to the alternative object store. If this is a relative path,
@@ -30,6 +33,9 @@
 	char *path;
 };
 
+KHASH_INIT(odb_path_map, const char * /* key: odb_path */,
+	struct object_directory *, 1, fspathhash, fspatheq);
+
 void prepare_alt_odb(struct repository *r);
 char *compute_alternate_path(const char *path, struct strbuf *err);
 typedef int alt_odb_fn(struct object_directory *, void *);
@@ -54,7 +60,7 @@
  * Populate and return the loose object cache array corresponding to the
  * given object ID.
  */
-struct oid_array *odb_loose_cache(struct object_directory *odb,
+struct oidtree *odb_loose_cache(struct object_directory *odb,
 				  const struct object_id *oid);
 
 /* Empty the loose object cache for the specified object directory. */
@@ -116,6 +122,8 @@
 	 */
 	struct object_directory *odb;
 	struct object_directory **odb_tail;
+	kh_odb_path_map_t *odb_by_path;
+
 	int loaded_alternates;
 
 	/*
diff --git a/object.c b/object.c
index 1418845..4e85955 100644
--- a/object.c
+++ b/object.c
@@ -185,6 +185,24 @@
 	return obj;
 }
 
+struct object *lookup_object_by_type(struct repository *r,
+			    const struct object_id *oid,
+			    enum object_type type)
+{
+	switch (type) {
+	case OBJ_COMMIT:
+		return (struct object *)lookup_commit(r, oid);
+	case OBJ_TREE:
+		return (struct object *)lookup_tree(r, oid);
+	case OBJ_TAG:
+		return (struct object *)lookup_tag(r, oid);
+	case OBJ_BLOB:
+		return (struct object *)lookup_blob(r, oid);
+	default:
+		die("BUG: unknown object type %d", type);
+	}
+}
+
 struct object *parse_object_buffer(struct repository *r, const struct object_id *oid, enum object_type type, unsigned long size, void *buffer, int *eaten_p)
 {
 	struct object *obj;
@@ -511,6 +529,8 @@
 		free_object_directory(o->odb);
 		o->odb = next;
 	}
+	kh_destroy_odb_path_map(o->odb_by_path);
+	o->odb_by_path = NULL;
 }
 
 void raw_object_store_clear(struct raw_object_store *o)
diff --git a/object.h b/object.h
index 8bca310..3b38c9c 100644
--- a/object.h
+++ b/object.h
@@ -144,9 +144,27 @@
  */
 struct object *parse_object_buffer(struct repository *r, const struct object_id *oid, enum object_type type, unsigned long size, void *buffer, int *eaten_p);
 
-/** Returns the object, with potentially excess memory allocated. **/
+/*
+ * Allocate and return an object struct, even if you do not know the type of
+ * the object. The returned object may have its "type" field set to a real type
+ * (if somebody previously called lookup_blob(), etc), or it may be set to
+ * OBJ_NONE. In the latter case, subsequent calls to lookup_blob(), etc, will
+ * set the type field as appropriate.
+ *
+ * Use this when you do not know the expected type of an object and want to
+ * avoid parsing it for efficiency reasons. Try to avoid it otherwise; it
+ * may allocate excess memory, since the returned object must be as large as
+ * the maximum struct of any type.
+ */
 struct object *lookup_unknown_object(struct repository *r, const struct object_id *oid);
 
+/*
+ * Dispatch to the appropriate lookup_blob(), lookup_commit(), etc, based on
+ * "type".
+ */
+struct object *lookup_object_by_type(struct repository *r, const struct object_id *oid,
+				     enum object_type type);
+
 struct object_list *object_list_insert(struct object *item,
 				       struct object_list **list_p);
 
diff --git a/oidtree.c b/oidtree.c
new file mode 100644
index 0000000..7eb0e9b
--- /dev/null
+++ b/oidtree.c
@@ -0,0 +1,104 @@
+/*
+ * A wrapper around cbtree which stores oids
+ * May be used to replace oid-array for prefix (abbreviation) matches
+ */
+#include "oidtree.h"
+#include "alloc.h"
+#include "hash.h"
+
+struct oidtree_node {
+	/* n.k[] is used to store "struct object_id" */
+	struct cb_node n;
+};
+
+struct oidtree_iter_data {
+	oidtree_iter fn;
+	void *arg;
+	size_t *last_nibble_at;
+	int algo;
+	uint8_t last_byte;
+};
+
+void oidtree_init(struct oidtree *ot)
+{
+	cb_init(&ot->tree);
+	mem_pool_init(&ot->mem_pool, 0);
+}
+
+void oidtree_clear(struct oidtree *ot)
+{
+	if (ot) {
+		mem_pool_discard(&ot->mem_pool, 0);
+		oidtree_init(ot);
+	}
+}
+
+void oidtree_insert(struct oidtree *ot, const struct object_id *oid)
+{
+	struct oidtree_node *on;
+
+	if (!oid->algo)
+		BUG("oidtree_insert requires oid->algo");
+
+	on = mem_pool_alloc(&ot->mem_pool, sizeof(*on) + sizeof(*oid));
+	oidcpy_with_padding((struct object_id *)on->n.k, oid);
+
+	/*
+	 * n.b. Current callers won't get us duplicates, here.  If a
+	 * future caller causes duplicates, there'll be a a small leak
+	 * that won't be freed until oidtree_clear.  Currently it's not
+	 * worth maintaining a free list
+	 */
+	cb_insert(&ot->tree, &on->n, sizeof(*oid));
+}
+
+
+int oidtree_contains(struct oidtree *ot, const struct object_id *oid)
+{
+	struct object_id k;
+	size_t klen = sizeof(k);
+
+	oidcpy_with_padding(&k, oid);
+
+	if (oid->algo == GIT_HASH_UNKNOWN)
+		klen -= sizeof(oid->algo);
+
+	/* cb_lookup relies on memcmp on the struct, so order matters: */
+	klen += BUILD_ASSERT_OR_ZERO(offsetof(struct object_id, hash) <
+				offsetof(struct object_id, algo));
+
+	return cb_lookup(&ot->tree, (const uint8_t *)&k, klen) ? 1 : 0;
+}
+
+static enum cb_next iter(struct cb_node *n, void *arg)
+{
+	struct oidtree_iter_data *x = arg;
+	const struct object_id *oid = (const struct object_id *)n->k;
+
+	if (x->algo != GIT_HASH_UNKNOWN && x->algo != oid->algo)
+		return CB_CONTINUE;
+
+	if (x->last_nibble_at) {
+		if ((oid->hash[*x->last_nibble_at] ^ x->last_byte) & 0xf0)
+			return CB_CONTINUE;
+	}
+
+	return x->fn(oid, x->arg);
+}
+
+void oidtree_each(struct oidtree *ot, const struct object_id *oid,
+			size_t oidhexsz, oidtree_iter fn, void *arg)
+{
+	size_t klen = oidhexsz / 2;
+	struct oidtree_iter_data x = { 0 };
+	assert(oidhexsz <= GIT_MAX_HEXSZ);
+
+	x.fn = fn;
+	x.arg = arg;
+	x.algo = oid->algo;
+	if (oidhexsz & 1) {
+		x.last_byte = oid->hash[klen];
+		x.last_nibble_at = &klen;
+	}
+	cb_each(&ot->tree, (const uint8_t *)oid, klen, iter, &x);
+}
diff --git a/oidtree.h b/oidtree.h
new file mode 100644
index 0000000..77898f5
--- /dev/null
+++ b/oidtree.h
@@ -0,0 +1,22 @@
+#ifndef OIDTREE_H
+#define OIDTREE_H
+
+#include "cbtree.h"
+#include "hash.h"
+#include "mem-pool.h"
+
+struct oidtree {
+	struct cb_tree tree;
+	struct mem_pool mem_pool;
+};
+
+void oidtree_init(struct oidtree *);
+void oidtree_clear(struct oidtree *);
+void oidtree_insert(struct oidtree *, const struct object_id *);
+int oidtree_contains(struct oidtree *, const struct object_id *);
+
+typedef enum cb_next (*oidtree_iter)(const struct object_id *, void *data);
+void oidtree_each(struct oidtree *, const struct object_id *,
+			size_t oidhexsz, oidtree_iter, void *data);
+
+#endif /* OIDTREE_H */
diff --git a/parse-options.c b/parse-options.c
index e6f5676..2abff13 100644
--- a/parse-options.c
+++ b/parse-options.c
@@ -585,7 +585,7 @@
 		if (!opts->long_name)
 			continue;
 		if (!show_all &&
-			(opts->flags & (PARSE_OPT_HIDDEN | PARSE_OPT_NOCOMPLETE)))
+			(opts->flags & (PARSE_OPT_HIDDEN | PARSE_OPT_NOCOMPLETE | PARSE_OPT_FROM_ALIAS)))
 			continue;
 
 		switch (opts->type) {
diff --git a/perl/Git.pm b/perl/Git.pm
index 02eacef..090a7df 100644
--- a/perl/Git.pm
+++ b/perl/Git.pm
@@ -11,9 +11,6 @@
 use strict;
 use warnings $ENV{GIT_PERL_FATAL_WARNINGS} ? qw(FATAL all) : ();
 
-use File::Temp ();
-use File::Spec ();
-
 BEGIN {
 
 our ($VERSION, @ISA, @EXPORT, @EXPORT_OK);
@@ -103,12 +100,9 @@
 =cut
 
 
-use Carp qw(carp croak); # but croak is bad - throw instead
+sub carp { require Carp; goto &Carp::carp }
+sub croak { require Carp; goto &Carp::croak }
 use Git::LoadCPAN::Error qw(:try);
-use Cwd qw(abs_path cwd);
-use IPC::Open2 qw(open2);
-use Fcntl qw(SEEK_SET SEEK_CUR);
-use Time::Local qw(timegm);
 }
 
 
@@ -191,13 +185,15 @@
 			$dir = undef;
 		};
 
+		require Cwd;
 		if ($dir) {
+			require File::Spec;
 			File::Spec->file_name_is_absolute($dir) or $dir = $opts{Directory} . '/' . $dir;
-			$opts{Repository} = abs_path($dir);
+			$opts{Repository} = Cwd::abs_path($dir);
 
 			# If --git-dir went ok, this shouldn't die either.
 			my $prefix = $search->command_oneline('rev-parse', '--show-prefix');
-			$dir = abs_path($opts{Directory}) . '/';
+			$dir = Cwd::abs_path($opts{Directory}) . '/';
 			if ($prefix) {
 				if (substr($dir, -length($prefix)) ne $prefix) {
 					throw Error::Simple("rev-parse confused me - $dir does not have trailing $prefix");
@@ -223,7 +219,7 @@
 				throw Error::Simple("fatal: Not a git repository: $dir");
 			}
 
-			$opts{Repository} = abs_path($dir);
+			$opts{Repository} = Cwd::abs_path($dir);
 		}
 
 		delete $opts{Directory};
@@ -408,10 +404,12 @@
 	my $cwd_save = undef;
 	if ($self) {
 		shift;
-		$cwd_save = cwd();
+		require Cwd;
+		$cwd_save = Cwd::getcwd();
 		_setup_git_cmd_env($self);
 	}
-	$pid = open2($in, $out, 'git', @_);
+	require IPC::Open2;
+	$pid = IPC::Open2::open2($in, $out, 'git', @_);
 	chdir($cwd_save) if $cwd_save;
 	return ($pid, $in, $out, join(' ', @_));
 }
@@ -538,7 +536,8 @@
 	my $t = shift || time;
 	my @t = localtime($t);
 	$t[5] += 1900;
-	my $gm = timegm(@t);
+	require Time::Local;
+	my $gm = Time::Local::timegm(@t);
 	my $sign = qw( + + - )[ $gm <=> $t ];
 	return sprintf("%s%02d%02d", $sign, (gmtime(abs($t - $gm)))[2,1]);
 }
@@ -1340,6 +1339,7 @@
 		my $n = $name;
 		$n =~ s/\W/_/g; # no strange chars
 
+		require File::Temp;
 		($$temp_fd, $fname) = File::Temp::tempfile(
 			"Git_${n}_XXXXXX", UNLINK => 1, DIR => $tmpdir,
 			) or throw Error::Simple("couldn't open new temp file");
@@ -1362,9 +1362,9 @@
 
 	truncate $temp_fd, 0
 		or throw Error::Simple("couldn't truncate file");
-	sysseek($temp_fd, 0, SEEK_SET) and seek($temp_fd, 0, SEEK_SET)
+	sysseek($temp_fd, 0, Fcntl::SEEK_SET()) and seek($temp_fd, 0, Fcntl::SEEK_SET())
 		or throw Error::Simple("couldn't seek to beginning of file");
-	sysseek($temp_fd, 0, SEEK_CUR) == 0 and tell($temp_fd) == 0
+	sysseek($temp_fd, 0, Fcntl::SEEK_CUR()) == 0 and tell($temp_fd) == 0
 		or throw Error::Simple("expected file position to be reset");
 }
 
diff --git a/pkt-line.c b/pkt-line.c
index 98304ce..9f63eae 100644
--- a/pkt-line.c
+++ b/pkt-line.c
@@ -103,7 +103,7 @@
 {
 	packet_trace("0002", 4, 1);
 	if (write_in_full(fd, "0002", 4) < 0)
-		die_errno(_("unable to write stateless separator packet"));
+		die_errno(_("unable to write response end packet"));
 }
 
 int packet_flush_gently(int fd)
diff --git a/pretty.c b/pretty.c
index b1ecd03..9631529 100644
--- a/pretty.c
+++ b/pretty.c
@@ -1735,6 +1735,10 @@
 	case 'S':
 		w->source = 1;
 		break;
+	case 'd':
+	case 'D':
+		w->decorate = 1;
+		break;
 	}
 	return 0;
 }
diff --git a/pretty.h b/pretty.h
index f034609..2f16acd 100644
--- a/pretty.h
+++ b/pretty.h
@@ -65,12 +65,16 @@
 	return (fmt == CMIT_FMT_EMAIL || fmt == CMIT_FMT_MBOXRD);
 }
 
+/*
+ * Examine the user-specified format given by "fmt" (or if NULL, the global one
+ * previously saved by get_commit_format()), and set flags based on which items
+ * the format will need when it is expanded.
+ */
 struct userformat_want {
 	unsigned notes:1;
 	unsigned source:1;
+	unsigned decorate:1;
 };
-
-/* Set the flag "w->notes" if there is placeholder %N in "fmt". */
 void userformat_find_requirements(const char *fmt, struct userformat_want *w);
 
 /*
diff --git a/quote.h b/quote.h
index 768cc63..049d8dd 100644
--- a/quote.h
+++ b/quote.h
@@ -31,6 +31,7 @@
 
 void sq_quote_buf(struct strbuf *, const char *src);
 void sq_quote_argv(struct strbuf *, const char **argv);
+__attribute__((format (printf, 2, 3)))
 void sq_quotef(struct strbuf *, const char *fmt, ...);
 
 /*
diff --git a/reachable.c b/reachable.c
index c598472..84e3d0d 100644
--- a/reachable.c
+++ b/reachable.c
@@ -159,24 +159,6 @@
 				      FOR_EACH_OBJECT_LOCAL_ONLY);
 }
 
-static void *lookup_object_by_type(struct repository *r,
-				   const struct object_id *oid,
-				   enum object_type type)
-{
-	switch (type) {
-	case OBJ_COMMIT:
-		return lookup_commit(r, oid);
-	case OBJ_TREE:
-		return lookup_tree(r, oid);
-	case OBJ_TAG:
-		return lookup_tag(r, oid);
-	case OBJ_BLOB:
-		return lookup_blob(r, oid);
-	default:
-		die("BUG: unknown object type %d", type);
-	}
-}
-
 static int mark_object_seen(const struct object_id *oid,
 			     enum object_type type,
 			     int exclude,
diff --git a/read-cache.c b/read-cache.c
index ba2b012..46ccd66 100644
--- a/read-cache.c
+++ b/read-cache.c
@@ -1585,8 +1585,7 @@
 	 */
 	preload_index(istate, pathspec, 0);
 	trace2_region_enter("index", "refresh", NULL);
-	/* TODO: audit for interaction with sparse-index. */
-	ensure_full_index(istate);
+
 	for (i = 0; i < istate->cache_nr; i++) {
 		struct cache_entry *ce, *new_entry;
 		int cache_errno = 0;
@@ -1601,6 +1600,13 @@
 		if (ignore_skip_worktree && ce_skip_worktree(ce))
 			continue;
 
+		/*
+		 * If this entry is a sparse directory, then there isn't
+		 * any stat() information to update. Ignore the entry.
+		 */
+		if (S_ISSPARSEDIR(ce->ce_mode))
+			continue;
+
 		if (pathspec && !ce_path_match(istate, ce, pathspec, seen))
 			filtered = 1;
 
diff --git a/ref-filter.c b/ref-filter.c
index 4db0e40..f45d3a1 100644
--- a/ref-filter.c
+++ b/ref-filter.c
@@ -213,6 +213,7 @@
  * Expand string, append it to strbuf *sb, then return error code ret.
  * Allow to save few lines of code.
  */
+__attribute__((format (printf, 3, 4)))
 static int strbuf_addf_ret(struct strbuf *sb, int ret, const char *fmt, ...)
 {
 	va_list ap;
diff --git a/refs/debug.c b/refs/debug.c
index 7db4abc..1a7a9e1 100644
--- a/refs/debug.c
+++ b/refs/debug.c
@@ -232,7 +232,8 @@
 	struct debug_ref_iterator *diter = xcalloc(1, sizeof(*diter));
 	base_ref_iterator_init(&diter->base, &debug_ref_iterator_vtable, 1);
 	diter->iter = res;
-	trace_printf_key(&trace_refs, "ref_iterator_begin: %s (0x%x)\n", prefix, flags);
+	trace_printf_key(&trace_refs, "ref_iterator_begin: \"%s\" (0x%x)\n",
+			 prefix, flags);
 	return &diter->base;
 }
 
diff --git a/remote-curl.c b/remote-curl.c
index 9d432c2..6c320d5 100644
--- a/remote-curl.c
+++ b/remote-curl.c
@@ -653,7 +653,7 @@
 			memcpy(buf - 4, "0000", 4);
 			break;
 		case PACKET_READ_RESPONSE_END:
-			die(_("remote server sent stateless separator"));
+			die(_("remote server sent unexpected response end packet"));
 		}
 	}
 
diff --git a/revision.h b/revision.h
index 5c5510d..fbb068d 100644
--- a/revision.h
+++ b/revision.h
@@ -215,7 +215,8 @@
 			missing_newline:1,
 			date_mode_explicit:1,
 			preserve_subject:1,
-			encode_email_headers:1;
+			encode_email_headers:1,
+			include_header:1;
 	unsigned int	disable_stdin:1;
 	/* --show-linear-break */
 	unsigned int	track_linear:1,
diff --git a/sequencer.c b/sequencer.c
index 0bec01c..7f07cd0 100644
--- a/sequencer.c
+++ b/sequencer.c
@@ -3521,6 +3521,7 @@
 	return status;
 }
 
+__attribute__((format (printf, 2, 3)))
 static int safe_append(const char *filename, const char *fmt, ...)
 {
 	va_list ap;
@@ -3598,8 +3599,27 @@
 	return ret;
 }
 
+__attribute__((format (printf, 3, 4)))
 static const char *reflog_message(struct replay_opts *opts,
-	const char *sub_action, const char *fmt, ...);
+	const char *sub_action, const char *fmt, ...)
+{
+	va_list ap;
+	static struct strbuf buf = STRBUF_INIT;
+	char *reflog_action = getenv(GIT_REFLOG_ACTION);
+
+	va_start(ap, fmt);
+	strbuf_reset(&buf);
+	strbuf_addstr(&buf, reflog_action ? reflog_action : action_name(opts));
+	if (sub_action)
+		strbuf_addf(&buf, " (%s)", sub_action);
+	if (fmt) {
+		strbuf_addstr(&buf, ": ");
+		strbuf_vaddf(&buf, fmt, ap);
+	}
+	va_end(ap);
+
+	return buf.buf;
+}
 
 static int do_reset(struct repository *r,
 		    const char *name, int len,
@@ -4178,27 +4198,6 @@
 	return apply_save_autostash_oid(stash_oid, 1);
 }
 
-static const char *reflog_message(struct replay_opts *opts,
-	const char *sub_action, const char *fmt, ...)
-{
-	va_list ap;
-	static struct strbuf buf = STRBUF_INIT;
-	char *reflog_action = getenv(GIT_REFLOG_ACTION);
-
-	va_start(ap, fmt);
-	strbuf_reset(&buf);
-	strbuf_addstr(&buf, reflog_action ? reflog_action : action_name(opts));
-	if (sub_action)
-		strbuf_addf(&buf, " (%s)", sub_action);
-	if (fmt) {
-		strbuf_addstr(&buf, ": ");
-		strbuf_vaddf(&buf, fmt, ap);
-	}
-	va_end(ap);
-
-	return buf.buf;
-}
-
 static int run_git_checkout(struct repository *r, struct replay_opts *opts,
 			    const char *commit, const char *action)
 {
diff --git a/serve.c b/serve.c
index aa8209f..f11c0e0 100644
--- a/serve.c
+++ b/serve.c
@@ -258,7 +258,7 @@
 			state = PROCESS_REQUEST_DONE;
 			break;
 		case PACKET_READ_RESPONSE_END:
-			BUG("unexpected stateless separator packet");
+			BUG("unexpected response end packet");
 		}
 	}
 
diff --git a/server-info.c b/server-info.c
index de0aa44..7701d7c 100644
--- a/server-info.c
+++ b/server-info.c
@@ -27,6 +27,7 @@
 	return uic->old_fp == NULL;
 }
 
+__attribute__((format (printf, 2, 3)))
 static int uic_printf(struct update_info_ctx *uic, const char *fmt, ...)
 {
 	va_list ap;
diff --git a/sparse-index.c b/sparse-index.c
index affc404..53c8f71 100644
--- a/sparse-index.c
+++ b/sparse-index.c
@@ -116,6 +116,17 @@
 	return res;
 }
 
+static int index_has_unmerged_entries(struct index_state *istate)
+{
+	int i;
+	for (i = 0; i < istate->cache_nr; i++) {
+		if (ce_stage(istate->cache[i]))
+			return 1;
+	}
+
+	return 0;
+}
+
 int convert_to_sparse(struct index_state *istate)
 {
 	int test_env;
@@ -152,6 +163,13 @@
 		return -1;
 	}
 
+	/*
+	 * NEEDSWORK: If we have unmerged entries, then stay full.
+	 * Unmerged entries prevent the cache-tree extension from working.
+	 */
+	if (index_has_unmerged_entries(istate))
+		return 0;
+
 	if (cache_tree_update(istate, 0)) {
 		warning(_("unable to update cache-tree, staying full"));
 		return -1;
@@ -168,6 +186,10 @@
 	cache_tree_free(&istate->cache_tree);
 	cache_tree_update(istate, 0);
 
+	istate->fsmonitor_has_run_once = 0;
+	FREE_AND_NULL(istate->fsmonitor_dirty);
+	FREE_AND_NULL(istate->fsmonitor_last_update);
+
 	istate->sparse_index = 1;
 	trace2_region_leave("index", "convert_to_sparse", istate->repo);
 	return 0;
@@ -195,7 +217,7 @@
 	strbuf_addstr(base, path);
 
 	ce = make_cache_entry(istate, mode, oid, base->buf, 0, 0);
-	ce->ce_flags |= CE_SKIP_WORKTREE;
+	ce->ce_flags |= CE_SKIP_WORKTREE | CE_EXTENDED;
 	set_index_entry(istate, istate->cache_nr++, ce);
 
 	strbuf_setlen(base, len);
@@ -264,6 +286,9 @@
 	istate->cache = full->cache;
 	istate->cache_nr = full->cache_nr;
 	istate->cache_alloc = full->cache_alloc;
+	istate->fsmonitor_has_run_once = 0;
+	FREE_AND_NULL(istate->fsmonitor_dirty);
+	FREE_AND_NULL(istate->fsmonitor_last_update);
 
 	strbuf_release(&base);
 	free(full);
diff --git a/strbuf.h b/strbuf.h
index a86dcaa..5b1113a 100644
--- a/strbuf.h
+++ b/strbuf.h
@@ -263,6 +263,7 @@
 void strbuf_vinsertf(struct strbuf *sb, size_t pos, const char *fmt,
 		     va_list ap);
 
+__attribute__((format (printf, 3, 4)))
 void strbuf_insertf(struct strbuf *sb, size_t pos, const char *fmt, ...);
 
 /**
diff --git a/t/helper/test-advise.c b/t/helper/test-advise.c
index a7043df..cb88113 100644
--- a/t/helper/test-advise.c
+++ b/t/helper/test-advise.c
@@ -16,7 +16,7 @@
 	 * selected here and in t0018 where this command is being
 	 * executed.
 	 */
-	advise_if_enabled(ADVICE_NESTED_TAG, argv[1]);
+	advise_if_enabled(ADVICE_NESTED_TAG, "%s", argv[1]);
 
 	return 0;
 }
diff --git a/t/helper/test-oidtree.c b/t/helper/test-oidtree.c
new file mode 100644
index 0000000..180ee28
--- /dev/null
+++ b/t/helper/test-oidtree.c
@@ -0,0 +1,49 @@
+#include "test-tool.h"
+#include "cache.h"
+#include "oidtree.h"
+
+static enum cb_next print_oid(const struct object_id *oid, void *data)
+{
+	puts(oid_to_hex(oid));
+	return CB_CONTINUE;
+}
+
+int cmd__oidtree(int argc, const char **argv)
+{
+	struct oidtree ot;
+	struct strbuf line = STRBUF_INIT;
+	int nongit_ok;
+	int algo = GIT_HASH_UNKNOWN;
+
+	oidtree_init(&ot);
+	setup_git_directory_gently(&nongit_ok);
+
+	while (strbuf_getline(&line, stdin) != EOF) {
+		const char *arg;
+		struct object_id oid;
+
+		if (skip_prefix(line.buf, "insert ", &arg)) {
+			if (get_oid_hex_any(arg, &oid) == GIT_HASH_UNKNOWN)
+				die("insert not a hexadecimal oid: %s", arg);
+			algo = oid.algo;
+			oidtree_insert(&ot, &oid);
+		} else if (skip_prefix(line.buf, "contains ", &arg)) {
+			if (get_oid_hex(arg, &oid))
+				die("contains not a hexadecimal oid: %s", arg);
+			printf("%d\n", oidtree_contains(&ot, &oid));
+		} else if (skip_prefix(line.buf, "each ", &arg)) {
+			char buf[GIT_MAX_HEXSZ + 1] = { '0' };
+			memset(&oid, 0, sizeof(oid));
+			memcpy(buf, arg, strlen(arg));
+			buf[hash_algos[algo].hexsz] = '\0';
+			get_oid_hex_any(buf, &oid);
+			oid.algo = algo;
+			oidtree_each(&ot, &oid, strlen(arg), print_oid, NULL);
+		} else if (!strcmp(line.buf, "clear")) {
+			oidtree_clear(&ot);
+		} else {
+			die("unknown command: %s", line.buf);
+		}
+	}
+	return 0;
+}
diff --git a/t/helper/test-pkt-line.c b/t/helper/test-pkt-line.c
index 5e638f0..c5e052e 100644
--- a/t/helper/test-pkt-line.c
+++ b/t/helper/test-pkt-line.c
@@ -26,6 +26,16 @@
 	}
 }
 
+static void pack_raw_stdin(void)
+{
+	struct strbuf sb = STRBUF_INIT;
+
+	if (strbuf_read(&sb, 0, 0) < 0)
+		die_errno("failed to read from stdin");
+	packet_write(1, sb.buf, sb.len);
+	strbuf_release(&sb);
+}
+
 static void unpack(void)
 {
 	struct packet_reader reader;
@@ -110,6 +120,8 @@
 
 	if (!strcmp(argv[1], "pack"))
 		pack(argc - 2, argv + 2);
+	else if (!strcmp(argv[1], "pack-raw-stdin"))
+		pack_raw_stdin();
 	else if (!strcmp(argv[1], "unpack"))
 		unpack();
 	else if (!strcmp(argv[1], "unpack-sideband"))
diff --git a/t/helper/test-tool.c b/t/helper/test-tool.c
index b21e8f1..490ac02 100644
--- a/t/helper/test-tool.c
+++ b/t/helper/test-tool.c
@@ -43,6 +43,7 @@
 	{ "mktemp", cmd__mktemp },
 	{ "oid-array", cmd__oid_array },
 	{ "oidmap", cmd__oidmap },
+	{ "oidtree", cmd__oidtree },
 	{ "online-cpus", cmd__online_cpus },
 	{ "parse-options", cmd__parse_options },
 	{ "parse-pathspec-file", cmd__parse_pathspec_file },
diff --git a/t/helper/test-tool.h b/t/helper/test-tool.h
index f845ced..f8dc266 100644
--- a/t/helper/test-tool.h
+++ b/t/helper/test-tool.h
@@ -32,6 +32,7 @@
 int cmd__mergesort(int argc, const char **argv);
 int cmd__mktemp(int argc, const char **argv);
 int cmd__oidmap(int argc, const char **argv);
+int cmd__oidtree(int argc, const char **argv);
 int cmd__online_cpus(int argc, const char **argv);
 int cmd__parse_options(int argc, const char **argv);
 int cmd__parse_pathspec_file(int argc, const char** argv);
diff --git a/t/t0069-oidtree.sh b/t/t0069-oidtree.sh
new file mode 100755
index 0000000..bfb1397
--- /dev/null
+++ b/t/t0069-oidtree.sh
@@ -0,0 +1,49 @@
+#!/bin/sh
+
+test_description='basic tests for the oidtree implementation'
+. ./test-lib.sh
+
+maxhexsz=$(test_oid hexsz)
+echoid () {
+	prefix="${1:+$1 }"
+	shift
+	while test $# -gt 0
+	do
+		shortoid="$1"
+		shift
+		difference=$(($maxhexsz - ${#shortoid}))
+		printf "%s%s%0${difference}d\\n" "$prefix" "$shortoid" "0"
+	done
+}
+
+test_expect_success 'oidtree insert and contains' '
+	cat >expect <<-\EOF &&
+		0
+		0
+		0
+		1
+		1
+		0
+	EOF
+	{
+		echoid insert 444 1 2 3 4 5 a b c d e &&
+		echoid contains 44 441 440 444 4440 4444
+		echo clear
+	} | test-tool oidtree >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'oidtree each' '
+	echoid "" 123 321 321 >expect &&
+	{
+		echoid insert f 9 8 123 321 a b c d e
+		echo each 12300
+		echo each 3211
+		echo each 3210
+		echo each 32100
+		echo clear
+	} | test-tool oidtree >actual &&
+	test_cmp expect actual
+'
+
+test_done
diff --git a/t/t1092-sparse-checkout-compatibility.sh b/t/t1092-sparse-checkout-compatibility.sh
index d028b73..cabbd42 100755
--- a/t/t1092-sparse-checkout-compatibility.sh
+++ b/t/t1092-sparse-checkout-compatibility.sh
@@ -17,7 +17,7 @@
 		echo "after folder1" >g &&
 		echo "after x" >z &&
 		mkdir folder1 folder2 deep x &&
-		mkdir deep/deeper1 deep/deeper2 &&
+		mkdir deep/deeper1 deep/deeper2 deep/before deep/later &&
 		mkdir deep/deeper1/deepest &&
 		echo "after deeper1" >deep/e &&
 		echo "after deepest" >deep/deeper1/e &&
@@ -25,10 +25,23 @@
 		cp a folder2 &&
 		cp a x &&
 		cp a deep &&
+		cp a deep/before &&
 		cp a deep/deeper1 &&
 		cp a deep/deeper2 &&
+		cp a deep/later &&
 		cp a deep/deeper1/deepest &&
 		cp -r deep/deeper1/deepest deep/deeper2 &&
+		mkdir deep/deeper1/0 &&
+		mkdir deep/deeper1/0/0 &&
+		touch deep/deeper1/0/1 &&
+		touch deep/deeper1/0/0/0 &&
+		>folder1- &&
+		>folder1.x &&
+		>folder10 &&
+		cp -r deep/deeper1/0 folder1 &&
+		cp -r deep/deeper1/0 folder2 &&
+		echo >>folder1/0/0/0 &&
+		echo >>folder2/0/1 &&
 		git add . &&
 		git commit -m "initial commit" &&
 		git checkout -b base &&
@@ -40,7 +53,7 @@
 		done &&
 
 		git checkout -b rename-base base &&
-		echo >folder1/larger-content <<-\EOF &&
+		cat >folder1/larger-content <<-\EOF &&
 		matching
 		lines
 		help
@@ -56,11 +69,17 @@
 		mv folder1/a folder2/b &&
 		mv folder1/larger-content folder2/edited-content &&
 		echo >>folder2/edited-content &&
+		echo >>folder2/0/1 &&
+		echo stuff >>deep/deeper1/a &&
 		git add . &&
 		git commit -m "rename folder1/... to folder2/..." &&
 
 		git checkout -b rename-out-to-in rename-base &&
 		mv folder1/a deep/deeper1/b &&
+		echo more stuff >>deep/deeper1/a &&
+		rm folder2/0/1 &&
+		mkdir folder2/0/1 &&
+		echo >>folder2/0/1/1 &&
 		mv folder1/larger-content deep/deeper1/edited-content &&
 		echo >>deep/deeper1/edited-content &&
 		git add . &&
@@ -68,6 +87,9 @@
 
 		git checkout -b rename-in-to-out rename-base &&
 		mv deep/deeper1/a folder1/b &&
+		echo >>folder2/0/1 &&
+		rm -rf folder1/0/0 &&
+		echo >>folder1/0/0 &&
 		mv deep/deeper1/larger-content folder1/edited-content &&
 		echo >>folder1/edited-content &&
 		git add . &&
@@ -196,6 +218,14 @@
 	test_all_match git status --porcelain=v2 -uno
 '
 
+test_expect_success 'status reports sparse-checkout' '
+	init_repos &&
+	git -C sparse-checkout status >full &&
+	git -C sparse-index status >sparse &&
+	test_i18ngrep "You are in a sparse checkout with " full &&
+	test_i18ngrep "You are in a sparse checkout." sparse
+'
+
 test_expect_success 'add, commit, checkout' '
 	init_repos &&
 
@@ -232,6 +262,44 @@
 	test_all_match git checkout -
 '
 
+test_expect_success 'status/add: outside sparse cone' '
+	init_repos &&
+
+	# adding a "missing" file outside the cone should fail
+	test_sparse_match test_must_fail git add folder1/a &&
+
+	# folder1 is at HEAD, but outside the sparse cone
+	run_on_sparse mkdir folder1 &&
+	cp initial-repo/folder1/a sparse-checkout/folder1/a &&
+	cp initial-repo/folder1/a sparse-index/folder1/a &&
+
+	test_sparse_match git status &&
+
+	write_script edit-contents <<-\EOF &&
+	echo text >>$1
+	EOF
+	run_on_sparse ../edit-contents folder1/a &&
+	run_on_all ../edit-contents folder1/new &&
+
+	test_sparse_match git status --porcelain=v2 &&
+
+	# This "git add folder1/a" fails with a warning
+	# in the sparse repos, differing from the full
+	# repo. This is intentional.
+	test_sparse_match test_must_fail git add folder1/a &&
+	test_sparse_match test_must_fail git add --refresh folder1/a &&
+	test_all_match git status --porcelain=v2 &&
+
+	test_all_match git add . &&
+	test_all_match git status --porcelain=v2 &&
+	test_all_match git commit -m folder1/new &&
+
+	run_on_all ../edit-contents folder1/newer &&
+	test_all_match git add folder1/ &&
+	test_all_match git status --porcelain=v2 &&
+	test_all_match git commit -m folder1/newer
+'
+
 test_expect_success 'checkout and reset --hard' '
 	init_repos &&
 
@@ -262,13 +330,29 @@
 	test_all_match git diff --staged
 '
 
-test_expect_success 'diff with renames' '
+test_expect_success 'diff with renames and conflicts' '
 	init_repos &&
 
 	for branch in rename-out-to-out rename-out-to-in rename-in-to-out
 	do
 		test_all_match git checkout rename-base &&
 		test_all_match git checkout $branch -- . &&
+		test_all_match git status --porcelain=v2 &&
+		test_all_match git diff --staged --no-renames &&
+		test_all_match git diff --staged --find-renames || return 1
+	done
+'
+
+test_expect_success 'diff with directory/file conflicts' '
+	init_repos &&
+
+	for branch in rename-out-to-out rename-out-to-in rename-in-to-out
+	do
+		git -C full-checkout reset --hard &&
+		test_sparse_match git reset --hard &&
+		test_all_match git checkout $branch &&
+		test_all_match git checkout rename-base -- . &&
+		test_all_match git status --porcelain=v2 &&
 		test_all_match git diff --staged --no-renames &&
 		test_all_match git diff --staged --find-renames || return 1
 	done
@@ -308,8 +392,8 @@
 	test_all_match git blame deep/deeper2/deepest/a
 '
 
-# TODO: reset currently does not behave as expected when in a
-# sparse-checkout.
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
+# in this scenario, but it shouldn't.
 test_expect_failure 'checkout and reset (mixed)' '
 	init_repos &&
 
@@ -319,8 +403,8 @@
 	test_all_match git reset update-folder2
 '
 
-# Ensure that sparse-index behaves identically to
-# sparse-checkout with a full index.
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
+# in this scenario, but it shouldn't.
 test_expect_success 'checkout and reset (mixed) [sparse]' '
 	init_repos &&
 
@@ -352,6 +436,28 @@
 	done
 '
 
+# Sparse-index fails to convert the index in the
+# final 'git cherry-pick' command.
+test_expect_success 'cherry-pick with conflicts' '
+	init_repos &&
+
+	write_script edit-conflict <<-\EOF &&
+	echo $1 >conflict
+	EOF
+
+	test_all_match git checkout -b to-cherry-pick &&
+	run_on_all ../edit-conflict ABC &&
+	test_all_match git add conflict &&
+	test_all_match git commit -m "conflict to pick" &&
+
+	test_all_match git checkout -B base HEAD~1 &&
+	run_on_all ../edit-conflict DEF &&
+	test_all_match git add conflict &&
+	test_all_match git commit -m "conflict in base" &&
+
+	test_all_match test_must_fail git cherry-pick to-cherry-pick
+'
+
 test_expect_success 'clean' '
 	init_repos &&
 
@@ -405,12 +511,52 @@
 	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
 		git -C sparse-index -c core.fsmonitor="" reset --hard &&
 	test_region index convert_to_sparse trace2.txt &&
-	test_region index ensure_full_index trace2.txt &&
-
-	rm trace2.txt &&
-	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
-		git -C sparse-index -c core.fsmonitor="" status -uno &&
 	test_region index ensure_full_index trace2.txt
 '
 
+test_expect_success 'sparse-index is not expanded' '
+	init_repos &&
+
+	rm -f trace2.txt &&
+	echo >>sparse-index/untracked.txt &&
+	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
+		git -C sparse-index status &&
+	test_region ! index ensure_full_index trace2.txt
+'
+
+# NEEDSWORK: a sparse-checkout behaves differently from a full checkout
+# in this scenario, but it shouldn't.
+test_expect_success 'reset mixed and checkout orphan' '
+	init_repos &&
+
+	test_all_match git checkout rename-out-to-in &&
+
+	# Sparse checkouts do not agree with full checkouts about
+	# how to report a directory/file conflict during a reset.
+	# This command would fail with test_all_match because the
+	# full checkout reports "T folder1/0/1" while a sparse
+	# checkout reports "D folder1/0/1". This matches because
+	# the sparse checkouts skip "adding" the other side of
+	# the conflict.
+	test_sparse_match git reset --mixed HEAD~1 &&
+	test_sparse_match test-tool read-cache --table --expand &&
+	test_sparse_match git status --porcelain=v2 &&
+
+	# At this point, sparse-checkouts behave differently
+	# from the full-checkout.
+	test_sparse_match git checkout --orphan new-branch &&
+	test_sparse_match test-tool read-cache --table --expand &&
+	test_sparse_match git status --porcelain=v2
+'
+
+test_expect_success 'add everything with deep new file' '
+	init_repos &&
+
+	run_on_sparse git sparse-checkout set deep/deeper1/deepest &&
+
+	run_on_all touch deep/deeper1/x &&
+	test_all_match git add . &&
+	test_all_match git status --porcelain=v2
+'
+
 test_done
diff --git a/t/t2400-worktree-add.sh b/t/t2400-worktree-add.sh
index 96dfca1..37ad794 100755
--- a/t/t2400-worktree-add.sh
+++ b/t/t2400-worktree-add.sh
@@ -67,11 +67,25 @@
 '
 
 test_expect_success '"add" worktree with lock' '
-	git rev-parse HEAD >expect &&
 	git worktree add --detach --lock here-with-lock main &&
+	test_when_finished "git worktree unlock here-with-lock || :" &&
 	test -f .git/worktrees/here-with-lock/locked
 '
 
+test_expect_success '"add" worktree with lock and reason' '
+	lock_reason="why not" &&
+	git worktree add --detach --lock --reason "$lock_reason" here-with-lock-reason main &&
+	test_when_finished "git worktree unlock here-with-lock-reason || :" &&
+	test -f .git/worktrees/here-with-lock-reason/locked &&
+	echo "$lock_reason" >expect &&
+	test_cmp expect .git/worktrees/here-with-lock-reason/locked
+'
+
+test_expect_success '"add" worktree with reason but no lock' '
+	test_must_fail git worktree add --detach --reason "why not" here-with-reason-only main &&
+	test_path_is_missing .git/worktrees/here-with-reason-only/locked
+'
+
 test_expect_success '"add" worktree from a subdir' '
 	(
 		mkdir sub &&
diff --git a/t/t4202-log.sh b/t/t4202-log.sh
index 39e746f..9dfead9 100755
--- a/t/t4202-log.sh
+++ b/t/t4202-log.sh
@@ -1915,6 +1915,20 @@
 	test_must_fail git log --exclude-promisor-objects source-a
 '
 
+test_expect_success 'log --decorate includes all levels of tag annotated tags' '
+	git checkout -b branch &&
+	git commit --allow-empty -m "new commit" &&
+	git tag lightweight HEAD &&
+	git tag -m annotated annotated HEAD &&
+	git tag -m double-0 double-0 HEAD &&
+	git tag -m double-1 double-1 double-0 &&
+	cat >expect <<-\EOF &&
+	HEAD -> branch, tag: lightweight, tag: double-1, tag: double-0, tag: annotated
+	EOF
+	git log -1 --format="%D" >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'log --end-of-options' '
        git update-ref refs/heads/--source HEAD &&
        git log --end-of-options --source >actual &&
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index 7609f1e..3d4d9f1 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -837,4 +837,9 @@
 	)
 '
 
+test_expect_success 'usage shown without sub-command' '
+	test_expect_code 129 git multi-pack-index 2>err &&
+	! test_i18ngrep "unrecognized subcommand" err
+'
+
 test_done
diff --git a/t/t5411/once-0010-report-status-v1.sh b/t/t5411/once-0010-report-status-v1.sh
index 1233a46..297b109 100644
--- a/t/t5411/once-0010-report-status-v1.sh
+++ b/t/t5411/once-0010-report-status-v1.sh
@@ -28,10 +28,10 @@
 		if test -z "$GIT_DEFAULT_HASH" || test "$GIT_DEFAULT_HASH" = "sha1"
 		then
 			printf "%s %s refs/heads/main\0report-status\n" \
-				$A $B | packetize
+				$A $B | packetize_raw
 		else
 			printf "%s %s refs/heads/main\0report-status object-format=$GIT_DEFAULT_HASH\n" \
-				$A $B | packetize
+				$A $B | packetize_raw
 		fi &&
 		printf "%s %s refs/for/main/topic1\n" \
 			$ZERO_OID $A | packetize &&
diff --git a/t/t5562-http-backend-content-length.sh b/t/t5562-http-backend-content-length.sh
index e5d3d15..05a5806 100755
--- a/t/t5562-http-backend-content-length.sh
+++ b/t/t5562-http-backend-content-length.sh
@@ -63,7 +63,7 @@
 	hash_next=$(git commit-tree -p HEAD -m next HEAD^{tree}) &&
 	{
 		printf "%s %s refs/heads/newbranch\\0report-status object-format=%s\\n" \
-			"$ZERO_OID" "$hash_next" "$(test_oid algo)" | packetize &&
+			"$ZERO_OID" "$hash_next" "$(test_oid algo)" | packetize_raw
 		printf 0000 &&
 		echo "$hash_next" | git pack-objects --stdout
 	} >push_body &&
diff --git a/t/t5570-git-daemon.sh b/t/t5570-git-daemon.sh
index 82c31ab..b87ca06 100755
--- a/t/t5570-git-daemon.sh
+++ b/t/t5570-git-daemon.sh
@@ -194,7 +194,7 @@
 
 test_expect_success FAKENC 'hostname interpolation works after LF-stripping' '
 	{
-		printf "git-upload-pack /interp.git\n\0host=localhost" | packetize
+		printf "git-upload-pack /interp.git\n\0host=localhost" | packetize_raw
 		printf "0000"
 	} >input &&
 	fake_nc "$GIT_DAEMON_HOST_PORT" <input >output &&
diff --git a/t/t6006-rev-list-format.sh b/t/t6006-rev-list-format.sh
index 35a2f62..41d0ca0 100755
--- a/t/t6006-rev-list-format.sh
+++ b/t/t6006-rev-list-format.sh
@@ -41,22 +41,59 @@
 	echo "$added_iso88591" | git commit -F - &&
 	head1=$(git rev-parse --verify HEAD) &&
 	head1_short=$(git rev-parse --verify --short $head1) &&
+	head1_short4=$(git rev-parse --verify --short=4 $head1) &&
 	tree1=$(git rev-parse --verify HEAD:) &&
 	tree1_short=$(git rev-parse --verify --short $tree1) &&
 	echo "$changed" > foo &&
 	echo "$changed_iso88591" | git commit -a -F - &&
 	head2=$(git rev-parse --verify HEAD) &&
 	head2_short=$(git rev-parse --verify --short $head2) &&
+	head2_short4=$(git rev-parse --verify --short=4 $head2) &&
 	tree2=$(git rev-parse --verify HEAD:) &&
 	tree2_short=$(git rev-parse --verify --short $tree2) &&
 	git config --unset i18n.commitEncoding
 '
 
-# usage: test_format name format_string [failure] <expected_output
+# usage: test_format [argument...] name format_string [failure] <expected_output
 test_format () {
+	local args=
+	while true
+	do
+		case "$1" in
+		--*)
+			args="$args $1"
+			shift;;
+		*)
+			break;;
+		esac
+	done
 	cat >expect.$1
 	test_expect_${3:-success} "format $1" "
-		git rev-list --pretty=format:'$2' main >output.$1 &&
+		git rev-list $args --pretty=format:'$2' main >output.$1 &&
+		test_cmp expect.$1 output.$1
+	"
+}
+
+# usage: test_pretty [argument...] name format_name [failure] <expected_output
+test_pretty () {
+	local args=
+	while true
+	do
+		case "$1" in
+		--*)
+			args="$args $1"
+			shift;;
+		*)
+			break;;
+		esac
+	done
+	cat >expect.$1
+	test_expect_${3:-success} "pretty $1 (without --no-commit-header)" "
+		git rev-list $args --pretty='$2' main >output.$1 &&
+		test_cmp expect.$1 output.$1
+	"
+	test_expect_${3:-success} "pretty $1 (with --no-commit-header)" "
+		git rev-list $args --no-commit-header --pretty='$2' main >output.$1 &&
 		test_cmp expect.$1 output.$1
 	"
 }
@@ -93,6 +130,20 @@
 $head1_short
 EOF
 
+test_format --no-commit-header hash-no-header %H%n%h <<EOF
+$head2
+$head2_short
+$head1
+$head1_short
+EOF
+
+test_format --abbrev-commit --abbrev=0 --no-commit-header hash-no-header-abbrev %H%n%h <<EOF
+$head2
+$head2_short4
+$head1
+$head1_short4
+EOF
+
 test_format tree %T%n%t <<EOF
 commit $head2
 $tree2
@@ -181,6 +232,31 @@
 
 EOF
 
+test_format --no-commit-header raw-body-no-header %B <<EOF
+$changed
+
+$added
+
+EOF
+
+test_pretty oneline oneline <<EOF
+$head2 $changed
+$head1 $added
+EOF
+
+test_pretty short short <<EOF
+commit $head2
+Author: $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL>
+
+    $changed
+
+commit $head1
+Author: $GIT_AUTHOR_NAME <$GIT_AUTHOR_EMAIL>
+
+    $added
+
+EOF
+
 test_expect_success 'basic colors' '
 	cat >expect <<-EOF &&
 	commit $head2
diff --git a/t/t7500-commit-template-squash-signoff.sh b/t/t7500-commit-template-squash-signoff.sh
index 7d02f79..54c2082 100755
--- a/t/t7500-commit-template-squash-signoff.sh
+++ b/t/t7500-commit-template-squash-signoff.sh
@@ -498,7 +498,7 @@
 cat >expected-template <<EOF
 
 # Please enter the commit message for your changes. Lines starting
-# with '#' will be ignored, and an empty message aborts the commit.
+# with '#' will be ignored.
 #
 # Author:    A U Thor <author@example.com>
 #
diff --git a/t/t7519-status-fsmonitor.sh b/t/t7519-status-fsmonitor.sh
index 637391c..deea88d 100755
--- a/t/t7519-status-fsmonitor.sh
+++ b/t/t7519-status-fsmonitor.sh
@@ -73,6 +73,7 @@
 	expect*
 	actual*
 	marker*
+	trace2*
 	EOF
 '
 
@@ -383,4 +384,52 @@
 	)
 '
 
+# Usage:
+# check_sparse_index_behavior [!]
+# If "!" is supplied, then we verify that we do not call ensure_full_index
+# during a call to 'git status'. Otherwise, we verify that we _do_ call it.
+check_sparse_index_behavior () {
+	git status --porcelain=v2 >expect &&
+	git sparse-checkout init --cone --sparse-index &&
+	git sparse-checkout set dir1 dir2 &&
+	GIT_TRACE2_EVENT="$(pwd)/trace2.txt" GIT_TRACE2_EVENT_NESTING=10 \
+		git status --porcelain=v2 >actual &&
+	test_region $1 index ensure_full_index trace2.txt &&
+	test_region fsm_hook query trace2.txt &&
+	test_cmp expect actual &&
+	rm trace2.txt &&
+	git sparse-checkout disable
+}
+
+test_expect_success 'status succeeds with sparse index' '
+	git reset --hard &&
+
+	test_config core.fsmonitor "$TEST_DIRECTORY/t7519/fsmonitor-all" &&
+	check_sparse_index_behavior ! &&
+
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+	EOF
+	git config core.fsmonitor .git/hooks/fsmonitor-test &&
+	check_sparse_index_behavior ! &&
+
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+		printf "dir1/modified\0"
+	EOF
+	check_sparse_index_behavior ! &&
+
+	cp -r dir1 dir1a &&
+	git add dir1a &&
+	git commit -m "add dir1a" &&
+
+	# This one modifies outside the sparse-checkout definition
+	# and hence we expect to expand the sparse-index.
+	write_script .git/hooks/fsmonitor-test<<-\EOF &&
+		printf "last_update_token\0"
+		printf "dir1a/modified\0"
+	EOF
+	check_sparse_index_behavior
+'
+
 test_done
diff --git a/t/t9001-send-email.sh b/t/t9001-send-email.sh
index e9dc58f..57fc10e 100755
--- a/t/t9001-send-email.sh
+++ b/t/t9001-send-email.sh
@@ -1368,6 +1368,16 @@
 	! grep "X-Mailer" stdout
 '
 
+test_expect_success $PREREQ 'sendemail.identity: bool variable without a value' '
+	git -c sendemail.xmailer \
+		send-email \
+		--dry-run \
+		--from="nobody@example.com" \
+		$patches >stdout &&
+	grep "To: default@example.com" stdout &&
+	grep "X-Mailer" stdout
+'
+
 test_expect_success $PREREQ '--no-to overrides sendemail.to' '
 	git send-email \
 		--dry-run \
@@ -2092,6 +2102,18 @@
 	do_xmailer_test 1 "--xmailer"
 '
 
+test_expect_success $PREREQ '--[no-]xmailer with sendemail.xmailer' '
+	test_when_finished "test_unconfig sendemail.xmailer" &&
+	cat >>.git/config <<-\EOF &&
+	[sendemail]
+		xmailer
+	EOF
+	test_config sendemail.xmailer true &&
+	do_xmailer_test 1 "" &&
+	do_xmailer_test 0 "--no-xmailer" &&
+	do_xmailer_test 1 "--xmailer"
+'
+
 test_expect_success $PREREQ '--[no-]xmailer with sendemail.xmailer=false' '
 	test_config sendemail.xmailer false &&
 	do_xmailer_test 0 "" &&
@@ -2099,6 +2121,13 @@
 	do_xmailer_test 1 "--xmailer"
 '
 
+test_expect_success $PREREQ '--[no-]xmailer with sendemail.xmailer=' '
+	test_config sendemail.xmailer "" &&
+	do_xmailer_test 0 "" &&
+	do_xmailer_test 0 "--no-xmailer" &&
+	do_xmailer_test 1 "--xmailer"
+'
+
 test_expect_success $PREREQ 'setup expected-list' '
 	git send-email \
 	--dry-run \
diff --git a/t/t9902-completion.sh b/t/t9902-completion.sh
index cb057ef..1157393 100755
--- a/t/t9902-completion.sh
+++ b/t/t9902-completion.sh
@@ -2404,6 +2404,19 @@
 	verbose test -z "$__gitcomp_builtin_notes_edit"
 '
 
+test_expect_success 'option aliases are not shown by default' '
+	test_completion "git clone --recurs" "--recurse-submodules "
+'
+
+test_expect_success 'option aliases are shown with GIT_COMPLETION_SHOW_ALL' '
+	. "$GIT_BUILD_DIR/contrib/completion/git-completion.bash" &&
+	GIT_COMPLETION_SHOW_ALL=1 && export GIT_COMPLETION_SHOW_ALL &&
+	test_completion "git clone --recurs" <<-\EOF
+	--recurse-submodules Z
+	--recursive Z
+	EOF
+'
+
 test_expect_success '__git_complete' '
 	unset -f __git_wrap__git_main &&
 
diff --git a/t/test-lib-functions.sh b/t/test-lib-functions.sh
index ce41596..e28411b 100644
--- a/t/test-lib-functions.sh
+++ b/t/test-lib-functions.sh
@@ -1479,46 +1479,24 @@
 	)
 } 7>&2 2>&4
 
-# convert function arguments or stdin (if not arguments given) to pktline
-# representation. If multiple arguments are given, they are separated by
-# whitespace and put in a single packet. Note that data containing NULs must be
-# given on stdin, and that empty input becomes an empty packet, not a flush
-# packet (for that you can just print 0000 yourself).
+# These functions are historical wrappers around "test-tool pkt-line"
+# for older tests. Use "test-tool pkt-line" itself in new tests.
 packetize () {
 	if test $# -gt 0
 	then
 		packet="$*"
 		printf '%04x%s' "$((4 + ${#packet}))" "$packet"
 	else
-		perl -e '
-			my $packet = do { local $/; <STDIN> };
-			printf "%04x%s", 4 + length($packet), $packet;
-		'
+		test-tool pkt-line pack
 	fi
 }
 
-# Parse the input as a series of pktlines, writing the result to stdout.
-# Sideband markers are removed automatically, and the output is routed to
-# stderr if appropriate.
-#
-# NUL bytes are converted to "\\0" for ease of parsing with text tools.
+packetize_raw () {
+	test-tool pkt-line pack-raw-stdin
+}
+
 depacketize () {
-	perl -e '
-		while (read(STDIN, $len, 4) == 4) {
-			if ($len eq "0000") {
-				print "FLUSH\n";
-			} else {
-				read(STDIN, $buf, hex($len) - 4);
-				$buf =~ s/\0/\\0/g;
-				if ($buf =~ s/^[\x2\x3]//) {
-					print STDERR $buf;
-				} else {
-					$buf =~ s/^\x1//;
-					print $buf;
-				}
-			}
-		}
-	'
+	test-tool pkt-line unpack
 }
 
 # Converts base-16 data into base-8. The output is given as a sequence of
diff --git a/unpack-trees.c b/unpack-trees.c
index f88a69f..0a5135a 100644
--- a/unpack-trees.c
+++ b/unpack-trees.c
@@ -600,6 +600,13 @@
 {
 	ce->ce_flags |= CE_UNPACKED;
 
+	/*
+	 * If this is a sparse directory, don't advance cache_bottom.
+	 * That will be advanced later using the cache-tree data.
+	 */
+	if (S_ISSPARSEDIR(ce->ce_mode))
+		return;
+
 	if (o->cache_bottom < o->src_index->cache_nr &&
 	    o->src_index->cache[o->cache_bottom] == ce) {
 		int bottom = o->cache_bottom;
@@ -797,7 +804,7 @@
 		BUG("We need cache-tree to do this optimization");
 
 	/*
-	 * Do what unpack_callback() and unpack_nondirectories() normally
+	 * Do what unpack_callback() and unpack_single_entry() normally
 	 * do. But we walk all paths in an iterative loop instead.
 	 *
 	 * D/F conflicts and higher stage entries are not a concern
@@ -976,6 +983,7 @@
 	int pathlen, ce_len;
 	const char *ce_name;
 	int cmp;
+	unsigned ce_mode;
 
 	/*
 	 * If we have not precomputed the traverse path, it is quicker
@@ -998,7 +1006,8 @@
 	ce_len -= pathlen;
 	ce_name = ce->name + pathlen;
 
-	return df_name_compare(ce_name, ce_len, S_IFREG, name, namelen, mode);
+	ce_mode = S_ISSPARSEDIR(ce->ce_mode) ? S_IFDIR : S_IFREG;
+	return df_name_compare(ce_name, ce_len, ce_mode, name, namelen, mode);
 }
 
 static int compare_entry(const struct cache_entry *ce, const struct traverse_info *info, const struct name_entry *n)
@@ -1008,6 +1017,16 @@
 		return cmp;
 
 	/*
+	 * At this point, we know that we have a prefix match. If ce
+	 * is a sparse directory, then allow an exact match. This only
+	 * works when the input name is a directory, since ce->name
+	 * ends in a directory separator.
+	 */
+	if (S_ISSPARSEDIR(ce->ce_mode) &&
+	    ce->ce_namelen == traverse_path_len(info, tree_entry_len(n)) + 1)
+		return 0;
+
+	/*
 	 * Even if the beginning compared identically, the ce should
 	 * compare as bigger than a directory leading up to it!
 	 */
@@ -1033,13 +1052,15 @@
 	const struct name_entry *n,
 	int stage,
 	struct index_state *istate,
-	int is_transient)
+	int is_transient,
+	int is_sparse_directory)
 {
 	size_t len = traverse_path_len(info, tree_entry_len(n));
+	size_t alloc_len = is_sparse_directory ? len + 1 : len;
 	struct cache_entry *ce =
 		is_transient ?
-		make_empty_transient_cache_entry(len, NULL) :
-		make_empty_cache_entry(istate, len);
+		make_empty_transient_cache_entry(alloc_len, NULL) :
+		make_empty_cache_entry(istate, alloc_len);
 
 	ce->ce_mode = create_ce_mode(n->mode);
 	ce->ce_flags = create_ce_flags(stage);
@@ -1048,6 +1069,13 @@
 	/* len+1 because the cache_entry allocates space for NUL */
 	make_traverse_path(ce->name, len + 1, info, n->path, n->pathlen);
 
+	if (is_sparse_directory) {
+		ce->name[len] = '/';
+		ce->name[len + 1] = '\0';
+		ce->ce_namelen++;
+		ce->ce_flags |= CE_SKIP_WORKTREE;
+	}
+
 	return ce;
 }
 
@@ -1056,21 +1084,28 @@
  * without actually calling it. If you change the logic here you may need to
  * check and change there as well.
  */
-static int unpack_nondirectories(int n, unsigned long mask,
-				 unsigned long dirmask,
-				 struct cache_entry **src,
-				 const struct name_entry *names,
-				 const struct traverse_info *info)
+static int unpack_single_entry(int n, unsigned long mask,
+			       unsigned long dirmask,
+			       struct cache_entry **src,
+			       const struct name_entry *names,
+			       const struct traverse_info *info)
 {
 	int i;
 	struct unpack_trees_options *o = info->data;
 	unsigned long conflicts = info->df_conflicts | dirmask;
 
-	/* Do we have *only* directories? Nothing to do */
 	if (mask == dirmask && !src[0])
 		return 0;
 
 	/*
+	 * When we have a sparse directory entry for src[0],
+	 * then this isn't necessarily a directory-file conflict.
+	 */
+	if (mask == dirmask && src[0] &&
+	    S_ISSPARSEDIR(src[0]->ce_mode))
+		conflicts = 0;
+
+	/*
 	 * Ok, we've filled in up to any potential index entry in src[0],
 	 * now do the rest.
 	 */
@@ -1099,7 +1134,9 @@
 		 * not stored in the index.  otherwise construct the
 		 * cache entry from the index aware logic.
 		 */
-		src[i + o->merge] = create_ce_entry(info, names + i, stage, &o->result, o->merge);
+		src[i + o->merge] = create_ce_entry(info, names + i, stage,
+						    &o->result, o->merge,
+						    bit & dirmask);
 	}
 
 	if (o->merge) {
@@ -1203,16 +1240,71 @@
 	return -1;
 }
 
+/*
+ * Given a sparse directory entry 'ce', compare ce->name to
+ * info->name + '/' + p->path + '/' if info->name is non-empty.
+ * Compare ce->name to p->path + '/' otherwise. Note that
+ * ce->name must end in a trailing '/' because it is a sparse
+ * directory entry.
+ */
+static int sparse_dir_matches_path(const struct cache_entry *ce,
+				   struct traverse_info *info,
+				   const struct name_entry *p)
+{
+	assert(S_ISSPARSEDIR(ce->ce_mode));
+	assert(ce->name[ce->ce_namelen - 1] == '/');
+
+	if (info->namelen)
+		return ce->ce_namelen == info->namelen + p->pathlen + 2 &&
+		       ce->name[info->namelen] == '/' &&
+		       !strncmp(ce->name, info->name, info->namelen) &&
+		       !strncmp(ce->name + info->namelen + 1, p->path, p->pathlen);
+	return ce->ce_namelen == p->pathlen + 1 &&
+	       !strncmp(ce->name, p->path, p->pathlen);
+}
+
 static struct cache_entry *find_cache_entry(struct traverse_info *info,
 					    const struct name_entry *p)
 {
+	struct cache_entry *ce;
 	int pos = find_cache_pos(info, p->path, p->pathlen);
 	struct unpack_trees_options *o = info->data;
 
 	if (0 <= pos)
 		return o->src_index->cache[pos];
-	else
+
+	/*
+	 * Check for a sparse-directory entry named "path/".
+	 * Due to the input p->path not having a trailing
+	 * slash, the negative 'pos' value overshoots the
+	 * expected position, hence "-2" instead of "-1".
+	 */
+	pos = -pos - 2;
+
+	if (pos < 0 || pos >= o->src_index->cache_nr)
 		return NULL;
+
+	/*
+	 * Due to lexicographic sorting and sparse directory
+	 * entries ending with a trailing slash, our path as a
+	 * sparse directory (e.g "subdir/") and	our path as a
+	 * file (e.g. "subdir") might be separated by other
+	 * paths (e.g. "subdir-").
+	 */
+	while (pos >= 0) {
+		ce = o->src_index->cache[pos];
+
+		if (strncmp(ce->name, p->path, p->pathlen))
+			return NULL;
+
+		if (S_ISSPARSEDIR(ce->ce_mode) &&
+		    sparse_dir_matches_path(ce, info, p))
+			return ce;
+
+		pos--;
+	}
+
+	return NULL;
 }
 
 static void debug_path(struct traverse_info *info)
@@ -1248,6 +1340,21 @@
 }
 
 /*
+ * Returns true if and only if the given cache_entry is a
+ * sparse-directory entry that matches the given name_entry
+ * from the tree walk at the given traverse_info.
+ */
+static int is_sparse_directory_entry(struct cache_entry *ce,
+				     struct name_entry *name,
+				     struct traverse_info *info)
+{
+	if (!ce || !name || !S_ISSPARSEDIR(ce->ce_mode))
+		return 0;
+
+	return sparse_dir_matches_path(ce, info, name);
+}
+
+/*
  * Note that traverse_by_cache_tree() duplicates some logic in this function
  * without actually calling it. If you change the logic here you may need to
  * check and change there as well.
@@ -1303,7 +1410,7 @@
 		}
 	}
 
-	if (unpack_nondirectories(n, mask, dirmask, src, names, info) < 0)
+	if (unpack_single_entry(n, mask, dirmask, src, names, info) < 0)
 		return -1;
 
 	if (o->merge && src[0]) {
@@ -1333,9 +1440,12 @@
 			}
 		}
 
-		if (traverse_trees_recursive(n, dirmask, mask & ~dirmask,
-					     names, info) < 0)
+		if (!is_sparse_directory_entry(src[0], names, info) &&
+		    traverse_trees_recursive(n, dirmask, mask & ~dirmask,
+						    names, info) < 0) {
 			return -1;
+		}
+
 		return mask;
 	}
 
diff --git a/worktree.c b/worktree.c
index 237517b..092a4f9 100644
--- a/worktree.c
+++ b/worktree.c
@@ -265,6 +265,7 @@
 }
 
 /* convenient wrapper to deal with NULL strbuf */
+__attribute__((format (printf, 2, 3)))
 static void strbuf_addf_gently(struct strbuf *buf, const char *fmt, ...)
 {
 	va_list params;
diff --git a/wt-status.c b/wt-status.c
index c0dbf96..eaed30e 100644
--- a/wt-status.c
+++ b/wt-status.c
@@ -657,6 +657,36 @@
 	clear_pathspec(&rev.prune_data);
 }
 
+static int add_file_to_list(const struct object_id *oid,
+			    struct strbuf *base, const char *path,
+			    unsigned int mode, void *context)
+{
+	struct string_list_item *it;
+	struct wt_status_change_data *d;
+	struct wt_status *s = context;
+	struct strbuf full_name = STRBUF_INIT;
+
+	if (S_ISDIR(mode))
+		return READ_TREE_RECURSIVE;
+
+	strbuf_add(&full_name, base->buf, base->len);
+	strbuf_addstr(&full_name, path);
+	it = string_list_insert(&s->change, full_name.buf);
+	d = it->util;
+	if (!d) {
+		CALLOC_ARRAY(d, 1);
+		it->util = d;
+	}
+
+	d->index_status = DIFF_STATUS_ADDED;
+	/* Leave {mode,oid}_head zero for adds. */
+	d->mode_index = mode;
+	oidcpy(&d->oid_index, oid);
+	s->committable = 1;
+	strbuf_release(&full_name);
+	return 0;
+}
+
 static void wt_status_collect_changes_initial(struct wt_status *s)
 {
 	struct index_state *istate = s->repo->index;
@@ -671,6 +701,27 @@
 			continue;
 		if (ce_intent_to_add(ce))
 			continue;
+		if (S_ISSPARSEDIR(ce->ce_mode)) {
+			/*
+			 * This is a sparse directory entry, so we want to collect all
+			 * of the added files within the tree. This requires recursively
+			 * expanding the trees to find the elements that are new in this
+			 * tree and marking them with DIFF_STATUS_ADDED.
+			 */
+			struct strbuf base = STRBUF_INIT;
+			struct pathspec ps = { 0 };
+			struct tree *tree = lookup_tree(istate->repo, &ce->oid);
+
+			ps.recursive = 1;
+			ps.has_wildcard = 1;
+			ps.max_depth = -1;
+
+			strbuf_add(&base, ce->name, ce->ce_namelen);
+			read_tree_at(istate->repo, tree, &base, &ps,
+				     add_file_to_list, s);
+			continue;
+		}
+
 		it = string_list_insert(&s->change, ce->name);
 		d = it->util;
 		if (!d) {
@@ -1492,9 +1543,12 @@
 	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_DISABLED)
 		return;
 
-	status_printf_ln(s, color,
-			 _("You are in a sparse checkout with %d%% of tracked files present."),
-			 s->state.sparse_checkout_percentage);
+	if (s->state.sparse_checkout_percentage == SPARSE_CHECKOUT_SPARSE_INDEX)
+		status_printf_ln(s, color, _("You are in a sparse checkout."));
+	else
+		status_printf_ln(s, color,
+				_("You are in a sparse checkout with %d%% of tracked files present."),
+				s->state.sparse_checkout_percentage);
 	wt_longstatus_print_trailer(s);
 }
 
@@ -1652,6 +1706,11 @@
 		return;
 	}
 
+	if (r->index->sparse_index) {
+		state->sparse_checkout_percentage = SPARSE_CHECKOUT_SPARSE_INDEX;
+		return;
+	}
+
 	for (i = 0; i < r->index->cache_nr; i++) {
 		struct cache_entry *ce = r->index->cache[i];
 		if (ce_skip_worktree(ce))
diff --git a/wt-status.h b/wt-status.h
index 0d32799b..ab9cc9d 100644
--- a/wt-status.h
+++ b/wt-status.h
@@ -78,6 +78,7 @@
 };
 
 #define SPARSE_CHECKOUT_DISABLED -1
+#define SPARSE_CHECKOUT_SPARSE_INDEX -2
 
 struct wt_status_state {
 	int merge_in_progress;