Merge tag 'x86-boot-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Ingo Molnar:
 "The main change in this cycle was to add support for ZSTD-compressed
  kernel and initrd images.

  ZSTD has a very fast decompressor, yet it compresses better than gzip"

* tag 'x86-boot-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Documentation: dontdiff: Add zstd compressed files
  .gitignore: Add ZSTD-compressed files
  x86: Add support for ZSTD compressed kernel
  x86: Bump ZO_z_extra_bytes margin for zstd
  usr: Add support for zstd compressed initramfs
  init: Add support for zstd compressed kernel
  lib: Add zstd support to decompress
  lib: Prepare zstd for preboot environment, improve performance

21 files changed, 469 insertions, 26 deletions

diff --git a/.gitignore b/.gitignore
index d5f4804ed07c..162bd2b67bdf 100644
--- a/.gitignore
+++ b/.gitignore
@@ -44,6 +44,7 @@
 *.tab.[ch]
 *.tar
 *.xz
+*.zst
 Module.symvers
 modules.builtin
 modules.order
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index ef9519c32c55..e361fc95ca29 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -55,6 +55,7 @@
 *.ver
 *.xml
 *.xz
+*.zst
 *_MODULES
 *_vga16.c
 *~
diff --git a/Documentation/x86/boot.rst b/Documentation/x86/boot.rst
index 5325c71ca877..7fafc7ac00d7 100644
--- a/Documentation/x86/boot.rst
+++ b/Documentation/x86/boot.rst
@@ -782,9 +782,9 @@ Protocol:	2.08+
   uncompressed data should be determined using the standard magic
   numbers.  The currently supported compression formats are gzip
   (magic numbers 1F 8B or 1F 9E), bzip2 (magic number 42 5A), LZMA
-  (magic number 5D 00), XZ (magic number FD 37), and LZ4 (magic number
-  02 21).  The uncompressed payload is currently always ELF (magic
-  number 7F 45 4C 46).
+  (magic number 5D 00), XZ (magic number FD 37), LZ4 (magic number
+  02 21) and ZSTD (magic number 28 B5). The uncompressed payload is
+  currently always ELF (magic number 7F 45 4C 46).
 
 ============	==============
 Field name:	payload_length
diff --git a/Makefile b/Makefile
index 24a4c1b97bb0..aef9ca61caf0 100644
--- a/Makefile
+++ b/Makefile
@@ -464,6 +464,7 @@ KLZOP		= lzop
 LZMA		= lzma
 LZ4		= lz4c
 XZ		= xz
+ZSTD		= zstd
 
 CHECKFLAGS     := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \
 		  -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF)
@@ -512,7 +513,7 @@ CLANG_FLAGS :=
 export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC
 export CPP AR NM STRIP OBJCOPY OBJDUMP OBJSIZE READELF PAHOLE LEX YACC AWK INSTALLKERNEL
 export PERL PYTHON PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX
-export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ
+export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD
 export KBUILD_HOSTCXXFLAGS KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS LDFLAGS_MODULE
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 883da0abf779..4a64395bc35d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -188,6 +188,7 @@ config X86
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_XZ
+	select HAVE_KERNEL_ZSTD
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_FUNCTION_ERROR_INJECTION
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 5a828fde7a42..c08714ae76ec 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -26,7 +26,7 @@ OBJECT_FILES_NON_STANDARD	:= y
 KCOV_INSTRUMENT		:= n
 
 targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
-	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
+	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4 vmlinux.bin.zst
 
 KBUILD_CFLAGS := -m$(BITS) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
@@ -42,6 +42,7 @@ KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
 KBUILD_CFLAGS += -Wno-pointer-sign
 KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=)
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
 GCOV_PROFILE := n
@@ -145,6 +146,8 @@ $(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzo)
 $(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lz4)
+$(obj)/vmlinux.bin.zst: $(vmlinux.bin.all-y) FORCE
+	$(call if_changed,zstd22)
 
 suffix-$(CONFIG_KERNEL_GZIP)	:= gz
 suffix-$(CONFIG_KERNEL_BZIP2)	:= bz2
@@ -152,6 +155,7 @@ suffix-$(CONFIG_KERNEL_LZMA)	:= lzma
 suffix-$(CONFIG_KERNEL_XZ)	:= xz
 suffix-$(CONFIG_KERNEL_LZO) 	:= lzo
 suffix-$(CONFIG_KERNEL_LZ4) 	:= lz4
+suffix-$(CONFIG_KERNEL_ZSTD)	:= zst
 
 quiet_cmd_mkpiggy = MKPIGGY $@
       cmd_mkpiggy = $(obj)/mkpiggy $< > $@
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index d7408af55738..0048269180d5 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -19,13 +19,6 @@
  */
 #define BOOT_CTYPE_H
 
-/*
- * _ctype[] in lib/ctype.c is needed by isspace() of linux/ctype.h.
- * While both lib/ctype.c and lib/cmdline.c will bring EXPORT_SYMBOL
- * which is meaningless and will cause compiling error in some cases.
- */
-#define __DISABLE_EXPORTS
-
 #include "misc.h"
 #include "error.h"
 #include "../string.h"
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 9652d5c2afda..39e592d0e0b4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -77,6 +77,10 @@ static int lines, cols;
 #ifdef CONFIG_KERNEL_LZ4
 #include "../../../../lib/decompress_unlz4.c"
 #endif
+
+#ifdef CONFIG_KERNEL_ZSTD
+#include "../../../../lib/decompress_unzstd.c"
+#endif
 /*
  * NOTE: When adding a new decompressor, please update the analysis in
  * ../header.S.
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 735ad7f21ab0..6dbd7e9f74c9 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -539,8 +539,14 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 # the size-dependent part now grows so fast.
 #
 # extra_bytes = (uncompressed_size >> 8) + 65536
+#
+# ZSTD compressed data grows by at most 3 bytes per 128K, and only has a 22
+# byte fixed overhead but has a maximum block size of 128K, so it needs a
+# larger margin.
+#
+# extra_bytes = (uncompressed_size >> 8) + 131072
 
-#define ZO_z_extra_bytes	((ZO_z_output_len >> 8) + 65536)
+#define ZO_z_extra_bytes	((ZO_z_output_len >> 8) + 131072)
 #if ZO_z_output_len > ZO_z_input_len
 # define ZO_z_extract_offset	(ZO_z_output_len + ZO_z_extra_bytes - \
 				 ZO_z_input_len)
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 680c320363db..9191280d9ea3 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -24,9 +24,16 @@
 # error "Invalid value for CONFIG_PHYSICAL_ALIGN"
 #endif
 
-#ifdef CONFIG_KERNEL_BZIP2
+#if defined(CONFIG_KERNEL_BZIP2)
 # define BOOT_HEAP_SIZE		0x400000
-#else /* !CONFIG_KERNEL_BZIP2 */
+#elif defined(CONFIG_KERNEL_ZSTD)
+/*
+ * Zstd needs to allocate the ZSTD_DCtx in order to decompress the kernel.
+ * The ZSTD_DCtx is ~160KB, so set the heap size to 192KB because it is a
+ * round number and to allow some slack.
+ */
+# define BOOT_HEAP_SIZE		 0x30000
+#else
 # define BOOT_HEAP_SIZE		 0x10000
 #endif
 
diff --git a/include/linux/decompress/unzstd.h b/include/linux/decompress/unzstd.h
new file mode 100644
index 000000000000..56d539ae880f
--- /dev/null
+++ b/include/linux/decompress/unzstd.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_DECOMPRESS_UNZSTD_H
+#define LINUX_DECOMPRESS_UNZSTD_H
+
+int unzstd(unsigned char *inbuf, long len,
+	   long (*fill)(void*, unsigned long),
+	   long (*flush)(void*, unsigned long),
+	   unsigned char *output,
+	   long *pos,
+	   void (*error_fn)(char *x));
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index 9f7f249dab43..f4bffefdbed5 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -191,13 +191,16 @@ config HAVE_KERNEL_LZO
 config HAVE_KERNEL_LZ4
 	bool
 
+config HAVE_KERNEL_ZSTD
+	bool
+
 config HAVE_KERNEL_UNCOMPRESSED
 	bool
 
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_ZSTD || HAVE_KERNEL_UNCOMPRESSED
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -276,6 +279,16 @@ config KERNEL_LZ4
 	  is about 8% bigger than LZO. But the decompression speed is
 	  faster than LZO.
 
+config KERNEL_ZSTD
+	bool "ZSTD"
+	depends on HAVE_KERNEL_ZSTD
+	help
+	  ZSTD is a compression algorithm targeting intermediate compression
+	  with fast decompression speed. It will compress better than GZIP and
+	  decompress around the same speed as LZO, but slower than LZ4. You
+	  will need at least 192 KB RAM or more for booting. The zstd command
+	  line tool is required for compression.
+
 config KERNEL_UNCOMPRESSED
 	bool "None"
 	depends on HAVE_KERNEL_UNCOMPRESSED
diff --git a/lib/Kconfig b/lib/Kconfig
index df3f3da95990..a5d6f23c4cab 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -342,6 +342,10 @@ config DECOMPRESS_LZ4
 	select LZ4_DECOMPRESS
 	tristate
 
+config DECOMPRESS_ZSTD
+	select ZSTD_DECOMPRESS
+	tristate
+
 #
 # Generic allocator support is selected if needed
 #
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..2ba9642a3a87 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -170,6 +170,7 @@ lib-$(CONFIG_DECOMPRESS_LZMA) += decompress_unlzma.o
 lib-$(CONFIG_DECOMPRESS_XZ) += decompress_unxz.o
 lib-$(CONFIG_DECOMPRESS_LZO) += decompress_unlzo.o
 lib-$(CONFIG_DECOMPRESS_LZ4) += decompress_unlz4.o
+lib-$(CONFIG_DECOMPRESS_ZSTD) += decompress_unzstd.o
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o
 obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
diff --git a/lib/decompress.c b/lib/decompress.c
index 857ab1af1ef3..ab3fc90ffc64 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -13,6 +13,7 @@
 #include <linux/decompress/inflate.h>
 #include <linux/decompress/unlzo.h>
 #include <linux/decompress/unlz4.h>
+#include <linux/decompress/unzstd.h>
 
 #include <linux/types.h>
 #include <linux/string.h>
@@ -37,6 +38,9 @@
 #ifndef CONFIG_DECOMPRESS_LZ4
 # define unlz4 NULL
 #endif
+#ifndef CONFIG_DECOMPRESS_ZSTD
+# define unzstd NULL
+#endif
 
 struct compress_format {
 	unsigned char magic[2];
@@ -52,6 +56,7 @@ static const struct compress_format compressed_formats[] __initconst = {
 	{ {0xfd, 0x37}, "xz", unxz },
 	{ {0x89, 0x4c}, "lzo", unlzo },
 	{ {0x02, 0x21}, "lz4", unlz4 },
+	{ {0x28, 0xb5}, "zstd", unzstd },
 	{ {0, 0}, NULL, NULL }
 };
 
diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c
new file mode 100644
index 000000000000..0ad2c15479ed
--- /dev/null
+++ b/lib/decompress_unzstd.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Important notes about in-place decompression
+ *
+ * At least on x86, the kernel is decompressed in place: the compressed data
+ * is placed to the end of the output buffer, and the decompressor overwrites
+ * most of the compressed data. There must be enough safety margin to
+ * guarantee that the write position is always behind the read position.
+ *
+ * The safety margin for ZSTD with a 128 KB block size is calculated below.
+ * Note that the margin with ZSTD is bigger than with GZIP or XZ!
+ *
+ * The worst case for in-place decompression is that the beginning of
+ * the file is compressed extremely well, and the rest of the file is
+ * uncompressible. Thus, we must look for worst-case expansion when the
+ * compressor is encoding uncompressible data.
+ *
+ * The structure of the .zst file in case of a compresed kernel is as follows.
+ * Maximum sizes (as bytes) of the fields are in parenthesis.
+ *
+ *    Frame Header: (18)
+ *    Blocks: (N)
+ *    Checksum: (4)
+ *
+ * The frame header and checksum overhead is at most 22 bytes.
+ *
+ * ZSTD stores the data in blocks. Each block has a header whose size is
+ * a 3 bytes. After the block header, there is up to 128 KB of payload.
+ * The maximum uncompressed size of the payload is 128 KB. The minimum
+ * uncompressed size of the payload is never less than the payload size
+ * (excluding the block header).
+ *
+ * The assumption, that the uncompressed size of the payload is never
+ * smaller than the payload itself, is valid only when talking about
+ * the payload as a whole. It is possible that the payload has parts where
+ * the decompressor consumes more input than it produces output. Calculating
+ * the worst case for this would be tricky. Instead of trying to do that,
+ * let's simply make sure that the decompressor never overwrites any bytes
+ * of the payload which it is currently reading.
+ *
+ * Now we have enough information to calculate the safety margin. We need
+ *   - 22 bytes for the .zst file format headers;
+ *   - 3 bytes per every 128 KiB of uncompressed size (one block header per
+ *     block); and
+ *   - 128 KiB (biggest possible zstd block size) to make sure that the
+ *     decompressor never overwrites anything from the block it is currently
+ *     reading.
+ *
+ * We get the following formula:
+ *
+ *    safety_margin = 22 + uncompressed_size * 3 / 131072 + 131072
+ *                 <= 22 + (uncompressed_size >> 15) + 131072
+ */
+
+/*
+ * Preboot environments #include "path/to/decompress_unzstd.c".
+ * All of the source files we depend on must be #included.
+ * zstd's only source dependeny is xxhash, which has no source
+ * dependencies.
+ *
+ * When UNZSTD_PREBOOT is defined we declare __decompress(), which is
+ * used for kernel decompression, instead of unzstd().
+ *
+ * Define __DISABLE_EXPORTS in preboot environments to prevent symbols
+ * from xxhash and zstd from being exported by the EXPORT_SYMBOL macro.
+ */
+#ifdef STATIC
+# define UNZSTD_PREBOOT
+# include "xxhash.c"
+# include "zstd/entropy_common.c"
+# include "zstd/fse_decompress.c"
+# include "zstd/huf_decompress.c"
+# include "zstd/zstd_common.c"
+# include "zstd/decompress.c"
+#endif
+
+#include <linux/decompress/mm.h>
+#include <linux/kernel.h>
+#include <linux/zstd.h>
+
+/* 128MB is the maximum window size supported by zstd. */
+#define ZSTD_WINDOWSIZE_MAX	(1 << ZSTD_WINDOWLOG_MAX)
+/*
+ * Size of the input and output buffers in multi-call mode.
+ * Pick a larger size because it isn't used during kernel decompression,
+ * since that is single pass, and we have to allocate a large buffer for
+ * zstd's window anyway. The larger size speeds up initramfs decompression.
+ */
+#define ZSTD_IOBUF_SIZE		(1 << 17)
+
+static int INIT handle_zstd_error(size_t ret, void (*error)(char *x))
+{
+	const int err = ZSTD_getErrorCode(ret);
+
+	if (!ZSTD_isError(ret))
+		return 0;
+
+	switch (err) {
+	case ZSTD_error_memory_allocation:
+		error("ZSTD decompressor ran out of memory");
+		break;
+	case ZSTD_error_prefix_unknown:
+		error("Input is not in the ZSTD format (wrong magic bytes)");
+		break;
+	case ZSTD_error_dstSize_tooSmall:
+	case ZSTD_error_corruption_detected:
+	case ZSTD_error_checksum_wrong:
+		error("ZSTD-compressed data is corrupt");
+		break;
+	default:
+		error("ZSTD-compressed data is probably corrupt");
+		break;
+	}
+	return -1;
+}
+
+/*
+ * Handle the case where we have the entire input and output in one segment.
+ * We can allocate less memory (no circular buffer for the sliding window),
+ * and avoid some memcpy() calls.
+ */
+static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf,
+				  long out_len, long *in_pos,
+				  void (*error)(char *x))
+{
+	const size_t wksp_size = ZSTD_DCtxWorkspaceBound();
+	void *wksp = large_malloc(wksp_size);
+	ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size);
+	int err;
+	size_t ret;
+
+	if (dctx == NULL) {
+		error("Out of memory while allocating ZSTD_DCtx");
+		err = -1;
+		goto out;
+	}
+	/*
+	 * Find out how large the frame actually is, there may be junk at
+	 * the end of the frame that ZSTD_decompressDCtx() can't handle.
+	 */
+	ret = ZSTD_findFrameCompressedSize(in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	in_len = (long)ret;
+
+	ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+
+	if (in_pos != NULL)
+		*in_pos = in_len;
+
+	err = 0;
+out:
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+static int INIT __unzstd(unsigned char *in_buf, long in_len,
+			 long (*fill)(void*, unsigned long),
+			 long (*flush)(void*, unsigned long),
+			 unsigned char *out_buf, long out_len,
+			 long *in_pos,
+			 void (*error)(char *x))
+{
+	ZSTD_inBuffer in;
+	ZSTD_outBuffer out;
+	ZSTD_frameParams params;
+	void *in_allocated = NULL;
+	void *out_allocated = NULL;
+	void *wksp = NULL;
+	size_t wksp_size;
+	ZSTD_DStream *dstream;
+	int err;
+	size_t ret;
+
+	if (out_len == 0)
+		out_len = LONG_MAX; /* no limit */
+
+	if (fill == NULL && flush == NULL)
+		/*
+		 * We can decompress faster and with less memory when we have a
+		 * single chunk.
+		 */
+		return decompress_single(in_buf, in_len, out_buf, out_len,
+					 in_pos, error);
+
+	/*
+	 * If in_buf is not provided, we must be using fill(), so allocate
+	 * a large enough buffer. If it is provided, it must be at least
+	 * ZSTD_IOBUF_SIZE large.
+	 */
+	if (in_buf == NULL) {
+		in_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (in_allocated == NULL) {
+			error("Out of memory while allocating input buffer");
+			err = -1;
+			goto out;
+		}
+		in_buf = in_allocated;
+		in_len = 0;
+	}
+	/* Read the first chunk, since we need to decode the frame header. */
+	if (fill != NULL)
+		in_len = fill(in_buf, ZSTD_IOBUF_SIZE);
+	if (in_len < 0) {
+		error("ZSTD-compressed data is truncated");
+		err = -1;
+		goto out;
+	}
+	/* Set the first non-empty input buffer. */
+	in.src = in_buf;
+	in.pos = 0;
+	in.size = in_len;
+	/* Allocate the output buffer if we are using flush(). */
+	if (flush != NULL) {
+		out_allocated = large_malloc(ZSTD_IOBUF_SIZE);
+		if (out_allocated == NULL) {
+			error("Out of memory while allocating output buffer");
+			err = -1;
+			goto out;
+		}
+		out_buf = out_allocated;
+		out_len = ZSTD_IOBUF_SIZE;
+	}
+	/* Set the output buffer. */
+	out.dst = out_buf;
+	out.pos = 0;
+	out.size = out_len;
+
+	/*
+	 * We need to know the window size to allocate the ZSTD_DStream.
+	 * Since we are streaming, we need to allocate a buffer for the sliding
+	 * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX
+	 * (8 MB), so it is important to use the actual value so as not to
+	 * waste memory when it is smaller.
+	 */
+	ret = ZSTD_getFrameParams(&params, in.src, in.size);
+	err = handle_zstd_error(ret, error);
+	if (err)
+		goto out;
+	if (ret != 0) {
+		error("ZSTD-compressed data has an incomplete frame header");
+		err = -1;
+		goto out;
+	}
+	if (params.windowSize > ZSTD_WINDOWSIZE_MAX) {
+		error("ZSTD-compressed data has too large a window size");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Allocate the ZSTD_DStream now that we know how much memory is
+	 * required.
+	 */
+	wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize);
+	wksp = large_malloc(wksp_size);
+	dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size);
+	if (dstream == NULL) {
+		error("Out of memory while allocating ZSTD_DStream");
+		err = -1;
+		goto out;
+	}
+
+	/*
+	 * Decompression loop:
+	 * Read more data if necessary (error if no more data can be read).
+	 * Call the decompression function, which returns 0 when finished.
+	 * Flush any data produced if using flush().
+	 */
+	if (in_pos != NULL)
+		*in_pos = 0;
+	do {
+		/*
+		 * If we need to reload data, either we have fill() and can
+		 * try to get more data, or we don't and the input is truncated.
+		 */
+		if (in.pos == in.size) {
+			if (in_pos != NULL)
+				*in_pos += in.pos;
+			in_len = fill ? fill(in_buf, ZSTD_IOBUF_SIZE) : -1;
+			if (in_len < 0) {
+				error("ZSTD-compressed data is truncated");
+				err = -1;
+				goto out;
+			}
+			in.pos = 0;
+			in.size = in_len;
+		}
+		/* Returns zero when the frame is complete. */
+		ret = ZSTD_decompressStream(dstream, &out, &in);
+		err = handle_zstd_error(ret, error);
+		if (err)
+			goto out;
+		/* Flush all of the data produced if using flush(). */
+		if (flush != NULL && out.pos > 0) {
+			if (out.pos != flush(out.dst, out.pos)) {
+				error("Failed to flush()");
+				err = -1;
+				goto out;
+			}
+			out.pos = 0;
+		}
+	} while (ret != 0);
+
+	if (in_pos != NULL)
+		*in_pos += in.pos;
+
+	err = 0;
+out:
+	if (in_allocated != NULL)
+		large_free(in_allocated);
+	if (out_allocated != NULL)
+		large_free(out_allocated);
+	if (wksp != NULL)
+		large_free(wksp);
+	return err;
+}
+
+#ifndef UNZSTD_PREBOOT
+STATIC int INIT unzstd(unsigned char *buf, long len,
+		       long (*fill)(void*, unsigned long),
+		       long (*flush)(void*, unsigned long),
+		       unsigned char *out_buf,
+		       long *pos,
+		       void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, 0, pos, error);
+}
+#else
+STATIC int INIT __decompress(unsigned char *buf, long len,
+			     long (*fill)(void*, unsigned long),
+			     long (*flush)(void*, unsigned long),
+			     unsigned char *out_buf, long out_len,
+			     long *pos,
+			     void (*error)(char *x))
+{
+	return __unzstd(buf, len, fill, flush, out_buf, out_len, pos, error);
+}
+#endif
diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c
index a84300e5a013..0b353530fb3f 100644
--- a/lib/zstd/fse_decompress.c
+++ b/lib/zstd/fse_decompress.c
@@ -47,6 +47,7 @@
 ****************************************************************/
 #include "bitstream.h"
 #include "fse.h"
+#include "zstd_internal.h"
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/string.h> /* memcpy, memset */
@@ -60,14 +61,6 @@
 		enum { FSE_static_assert = 1 / (int)(!!(c)) }; \
 	} /* use only *after* variable declarations */
 
-/* check and forward error code */
-#define CHECK_F(f)                  \
-	{                           \
-		size_t const e = f; \
-		if (FSE_isError(e)) \
-			return e;   \
-	}
-
 /* **************************************************************
 *  Templates
 ****************************************************************/
diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h
index 1a79fab9e13a..dac753397f86 100644
--- a/lib/zstd/zstd_internal.h
+++ b/lib/zstd/zstd_internal.h
@@ -127,7 +127,14 @@ static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG;
 *  Shared functions to include for inlining
 *********************************************/
 ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) {
-	memcpy(dst, src, 8);
+	/*
+	 * zstd relies heavily on gcc being able to analyze and inline this
+	 * memcpy() call, since it is called in a tight loop. Preboot mode
+	 * is compiled in freestanding mode, which stops gcc from analyzing
+	 * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a
+	 * regular memcpy().
+	 */
+	__builtin_memcpy(dst, src, 8);
 }
 /*! ZSTD_wildcopy() :
 *   custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */
@@ -137,13 +144,16 @@ ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length)
 	const BYTE* ip = (const BYTE*)src;
 	BYTE* op = (BYTE*)dst;
 	BYTE* const oend = op + length;
-	/* Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
+#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200
+	/*
+	 * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388.
 	 * Avoid the bad case where the loop only runs once by handling the
 	 * special case separately. This doesn't trigger the bug because it
 	 * doesn't involve pointer/integer overflow.
 	 */
 	if (length <= 8)
 		return ZSTD_copy8(dst, src);
+#endif
 	do {
 		ZSTD_copy8(op, ip);
 		op += 8;
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 916b2f7f7098..54f7b7eb580b 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -413,6 +413,28 @@ quiet_cmd_xzkern = XZKERN  $@
 quiet_cmd_xzmisc = XZMISC  $@
       cmd_xzmisc = cat $(real-prereqs) | $(XZ) --check=crc32 --lzma2=dict=1MiB > $@
 
+# ZSTD
+# ---------------------------------------------------------------------------
+# Appends the uncompressed size of the data using size_append. The .zst
+# format has the size information available at the beginning of the file too,
+# but it's in a more complex format and it's good to avoid changing the part
+# of the boot code that reads the uncompressed size.
+#
+# Note that the bytes added by size_append will make the zstd tool think that
+# the file is corrupt. This is expected.
+#
+# zstd uses a maximum window size of 8 MB. zstd22 uses a maximum window size of
+# 128 MB. zstd22 is used for kernel compression because it is decompressed in a
+# single pass, so zstd doesn't need to allocate a window buffer. When streaming
+# decompression is used, like initramfs decompression, zstd22 should likely not
+# be used because it would require zstd to allocate a 128 MB buffer.
+
+quiet_cmd_zstd = ZSTD    $@
+      cmd_zstd = { cat $(real-prereqs) | $(ZSTD) -19; $(size_append); } > $@
+
+quiet_cmd_zstd22 = ZSTD22  $@
+      cmd_zstd22 = { cat $(real-prereqs) | $(ZSTD) -22 --ultra; $(size_append); } > $@
+
 # ASM offsets
 # ---------------------------------------------------------------------------
 
diff --git a/usr/Kconfig b/usr/Kconfig
index 96afb03b65f9..2599bc21c1b2 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -100,6 +100,15 @@ config RD_LZ4
 	  Support loading of a LZ4 encoded initial ramdisk or cpio buffer
 	  If unsure, say N.
 
+config RD_ZSTD
+	bool "Support initial ramdisk/ramfs compressed using ZSTD"
+	default y
+	depends on BLK_DEV_INITRD
+	select DECOMPRESS_ZSTD
+	help
+	  Support loading of a ZSTD encoded initial ramdisk or cpio buffer.
+	  If unsure, say N.
+
 choice
 	prompt "Built-in initramfs compression mode"
 	depends on INITRAMFS_SOURCE != ""
@@ -196,6 +205,17 @@ config INITRAMFS_COMPRESSION_LZ4
 	  If you choose this, keep in mind that most distros don't provide lz4
 	  by default which could cause a build failure.
 
+config INITRAMFS_COMPRESSION_ZSTD
+	bool "ZSTD"
+	depends on RD_ZSTD
+	help
+	  ZSTD is a compression algorithm targeting intermediate compression
+	  with fast decompression speed. It will compress better than GZIP and
+	  decompress around the same speed as LZO, but slower than LZ4.
+
+	  If you choose this, keep in mind that you may need to install the zstd
+	  tool to be able to compress the initram.
+
 config INITRAMFS_COMPRESSION_NONE
 	bool "None"
 	help
diff --git a/usr/Makefile b/usr/Makefile
index c12e6b15ce72..b1a81a40eab1 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -15,6 +15,7 @@ compress-$(CONFIG_INITRAMFS_COMPRESSION_LZMA)	:= lzma
 compress-$(CONFIG_INITRAMFS_COMPRESSION_XZ)	:= xzmisc
 compress-$(CONFIG_INITRAMFS_COMPRESSION_LZO)	:= lzo
 compress-$(CONFIG_INITRAMFS_COMPRESSION_LZ4)	:= lz4
+compress-$(CONFIG_INITRAMFS_COMPRESSION_ZSTD)	:= zstd
 
 obj-$(CONFIG_BLK_DEV_INITRD) := initramfs_data.o