From b9ce08c01020eb28bfbfa6faf1c740281c5f418e Mon Sep 17 00:00:00 2001 From: Eduard - Gabriel Munteanu Date: Sun, 10 Aug 2008 20:14:03 +0300 Subject: kmemtrace: Core implementation. kmemtrace provides tracing for slab allocator functions, such as kmalloc, kfree, kmem_cache_alloc, kmem_cache_free etc.. Collected data is then fed to the userspace application in order to analyse allocation hotspots, internal fragmentation and so on, making it possible to see how well an allocator performs, as well as debug and profile kernel code. Signed-off-by: Eduard - Gabriel Munteanu Signed-off-by: Pekka Enberg --- init/main.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index 7e117a231af1..be1fe2242a55 100644 --- a/init/main.c +++ b/init/main.c @@ -69,6 +69,7 @@ #include #include #include +#include #ifdef CONFIG_X86_LOCAL_APIC #include @@ -653,6 +654,7 @@ asmlinkage void __init start_kernel(void) enable_debug_pagealloc(); cpu_hotplug_init(); kmem_cache_init(); + kmemtrace_init(); debug_objects_mem_init(); idr_init_cache(); setup_per_cpu_pageset(); -- cgit v1.2.2 From 36994e58a48fb8f9651c7dc845a6de298aba5bfc Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Mon, 29 Dec 2008 13:42:23 -0800 Subject: tracing/kmemtrace: normalize the raw tracer event to the unified tracing API Impact: new tracer plugin This patch adapts kmemtrace raw events tracing to the unified tracing API. To enable and use this tracer, just do the following: echo kmemtrace > /debugfs/tracing/current_tracer cat /debugfs/tracing/trace You will have the following output: # tracer: kmemtrace # # # ALLOC TYPE REQ GIVEN FLAGS POINTER NODE CALLER # FREE | | | | | | | | # | type_id 1 call_site 18446744071565527833 ptr 18446612134395152256 type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1 type_id 1 call_site 18446744071565585534 ptr 18446612134405955584 type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1 type_id 0 call_site 18446744071565636711 ptr 18446612134345164672 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1 type_id 1 call_site 18446744071565585534 ptr 18446612134405955584 type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1 type_id 0 call_site 18446744071565636711 ptr 18446612134345164912 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1 type_id 1 call_site 18446744071565585534 ptr 18446612134405955584 type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1 type_id 0 call_site 18446744071565636711 ptr 18446612134345165152 bytes_req 240 bytes_alloc 240 gfp_flags 208 node -1 type_id 0 call_site 18446744071566144042 ptr 18446612134346191680 bytes_req 1304 bytes_alloc 1312 gfp_flags 208 node -1 type_id 1 call_site 18446744071565585534 ptr 18446612134405955584 type_id 0 call_site 18446744071565585597 ptr 18446612134405955584 bytes_req 4096 bytes_alloc 4096 gfp_flags 208 node -1 type_id 1 call_site 18446744071565585534 ptr 18446612134405955584 That was to stay backward compatible with the format output produced in inux/tracepoint.h. This is the default ouput, but note that I tried something else. If you change an option: echo kmem_minimalistic > /debugfs/trace_options and then cat /debugfs/trace, you will have the following output: # tracer: kmemtrace # # # ALLOC TYPE REQ GIVEN FLAGS POINTER NODE CALLER # FREE | | | | | | | | # | - C 0xffff88007c088780 file_free_rcu + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname - C 0xffff88007cad6000 putname + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname + K 240 240 000000d0 0xffff8800790dc780 -1 d_alloc - C 0xffff88007cad6000 putname + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname + K 240 240 000000d0 0xffff8800790dc870 -1 d_alloc - C 0xffff88007cad6000 putname + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname + K 240 240 000000d0 0xffff8800790dc960 -1 d_alloc + K 1304 1312 000000d0 0xffff8800791d7340 -1 reiserfs_alloc_inode - C 0xffff88007cad6000 putname + K 4096 4096 000000d0 0xffff88007cad6000 -1 getname - C 0xffff88007cad6000 putname + K 992 1000 000000d0 0xffff880079045b58 -1 alloc_inode + K 768 1024 000080d0 0xffff88007c096400 -1 alloc_pipe_info + K 240 240 000000d0 0xffff8800790dca50 -1 d_alloc + K 272 320 000080d0 0xffff88007c088780 -1 get_empty_filp + K 272 320 000080d0 0xffff88007c088000 -1 get_empty_filp Yeah I shall confess kmem_minimalistic should be: kmem_alternative. Whatever, I find it more readable but this a personal opinion of course. We can drop it if you want. On the ALLOC/FREE column, + means an allocation and - a free. On the type column, you have K = kmalloc, C = cache, P = page I would like the flags to be GFP_* strings but that would not be easy to not break the column with strings.... About the node...it seems to always be -1. I don't know why but that shouldn't be difficult to find. I moved linux/tracepoint.h to trace/tracepoint.h as well. I think that would be more easy to find the tracer headers if they are all in their common directory. Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 9711586aa7c9..beca7aaddb22 100644 --- a/init/main.c +++ b/init/main.c @@ -70,7 +70,7 @@ #include #include #include -#include +#include #ifdef CONFIG_X86_LOCAL_APIC #include -- cgit v1.2.2 From 30d65dbfe3add7f010a075991dc0bfeaebb7d9e1 Mon Sep 17 00:00:00 2001 From: Alain Knaff Date: Sun, 4 Jan 2009 22:46:17 +0100 Subject: bzip2/lzma: config and initramfs support for bzip2/lzma decompression Impact: New code for initramfs decompression, new features This is the second part of the bzip2/lzma patch The bzip patch is based on an idea by Christian Ludwig, includes support for compressing the kernel with bzip2 or lzma rather than gzip. Both compressors give smaller sizes than gzip. Lzma's decompresses faster than bzip2. It also supports ramdisks and initramfs' compressed using these two compressors. The functionality has been successfully used for a couple of years by the udpcast project This version applies to "tip" kernel 2.6.28 This part contains: - support for new compressions (bzip2 and lzma) in initramfs and old-style ramdisk - config dialog for kernel compression (but new kernel compressions not yet supported) Signed-off-by: Alain Knaff Signed-off-by: H. Peter Anvin --- init/Kconfig | 50 +++++++++++++++ init/do_mounts_rd.c | 182 +++++++++++++++++++--------------------------------- init/initramfs.c | 123 ++++++++++++----------------------- 3 files changed, 157 insertions(+), 198 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f6281711166d..df84625b1373 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -101,6 +101,56 @@ config LOCALVERSION_AUTO which is done within the script "scripts/setlocalversion".) +choice + prompt "Kernel compression mode" + default KERNEL_GZIP + help + The linux kernel is a kind of self-extracting executable. + Several compression algorithms are available, which differ + in efficiency, compression and decompression speed. + Compression speed is only relevant when building a kernel. + Decompression speed is relevant at each boot. + + If you have any problems with bzip2 or lzma compressed + kernels, mail me (Alain Knaff) . (An older + version of this functionality (bzip2 only), for 2.4, was + supplied by Christian Ludwig) + + High compression options are mostly useful for users, who + are low on disk space (embedded systems), but for whom ram + size matters less. + + If in doubt, select 'gzip' + +config KERNEL_GZIP + bool "Gzip" + help + The old and tried gzip compression. Its compression ratio is + the poorest among the 3 choices; however its speed (both + compression and decompression) is the fastest. + +config KERNEL_BZIP2 + bool "Bzip2" + help + Its compression ratio and speed is intermediate. + Decompression speed is slowest among the 3. + The kernel size is about 10 per cent smaller with bzip2, + in comparison to gzip. + Bzip2 uses a large amount of memory. For modern kernels + you will need at least 8MB RAM or more for booting. + +config KERNEL_LZMA + bool "LZMA" + help + The most recent compression algorithm. + Its ratio is best, decompression speed is between the other + 2. Compression is slowest. + The kernel size is about 33 per cent smaller with lzma, + in comparison to gzip. + +endchoice + + config SWAP bool "Support for paging of anonymous memory (swap)" depends on MMU && BLOCK diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index a7c748fa977a..dcaeb1f90b32 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -10,6 +10,12 @@ #include "do_mounts.h" +#include + +#include +#include +#include + int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */ static int __init prompt_ramdisk(char *str) @@ -28,7 +34,7 @@ static int __init ramdisk_start_setup(char *str) } __setup("ramdisk_start=", ramdisk_start_setup); -static int __init crd_load(int in_fd, int out_fd); +static int __init crd_load(int in_fd, int out_fd, decompress_fn deco); /* * This routine tries to find a RAM disk image to load, and returns the @@ -44,7 +50,7 @@ static int __init crd_load(int in_fd, int out_fd); * gzip */ static int __init -identify_ramdisk_image(int fd, int start_block) +identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) { const int size = 512; struct minix_super_block *minixsb; @@ -70,6 +76,7 @@ identify_ramdisk_image(int fd, int start_block) sys_lseek(fd, start_block * BLOCK_SIZE, 0); sys_read(fd, buf, size); +#ifdef CONFIG_RD_GZIP /* * If it matches the gzip magic numbers, return 0 */ @@ -77,9 +84,39 @@ identify_ramdisk_image(int fd, int start_block) printk(KERN_NOTICE "RAMDISK: Compressed image found at block %d\n", start_block); + *decompressor = gunzip; + nblocks = 0; + goto done; + } +#endif + +#ifdef CONFIG_RD_BZIP2 + /* + * If it matches the bzip2 magic numbers, return -1 + */ + if (buf[0] == 0x42 && (buf[1] == 0x5a)) { + printk(KERN_NOTICE + "RAMDISK: Bzipped image found at block %d\n", + start_block); + *decompressor = bunzip2; + nblocks = 0; + goto done; + } +#endif + +#ifdef CONFIG_RD_LZMA + /* + * If it matches the lzma magic numbers, return -1 + */ + if (buf[0] == 0x5d && (buf[1] == 0x00)) { + printk(KERN_NOTICE + "RAMDISK: Lzma image found at block %d\n", + start_block); + *decompressor = unlzma; nblocks = 0; goto done; } +#endif /* romfs is at block zero too */ if (romfsb->word0 == ROMSB_WORD0 && @@ -143,6 +180,7 @@ int __init rd_load_image(char *from) int nblocks, i, disk; char *buf = NULL; unsigned short rotate = 0; + decompress_fn decompressor = NULL; #if !defined(CONFIG_S390) && !defined(CONFIG_PPC_ISERIES) char rotator[4] = { '|' , '/' , '-' , '\\' }; #endif @@ -155,12 +193,12 @@ int __init rd_load_image(char *from) if (in_fd < 0) goto noclose_input; - nblocks = identify_ramdisk_image(in_fd, rd_image_start); + nblocks = identify_ramdisk_image(in_fd, rd_image_start, &decompressor); if (nblocks < 0) goto done; if (nblocks == 0) { - if (crd_load(in_fd, out_fd) == 0) + if (crd_load(in_fd, out_fd, decompressor) == 0) goto successful_load; goto done; } @@ -259,138 +297,48 @@ int __init rd_load_disk(int n) return rd_load_image("/dev/root"); } -/* - * gzip declarations - */ - -#define OF(args) args - -#ifndef memzero -#define memzero(s, n) memset ((s), 0, (n)) -#endif - -typedef unsigned char uch; -typedef unsigned short ush; -typedef unsigned long ulg; - -#define INBUFSIZ 4096 -#define WSIZE 0x8000 /* window size--must be a power of two, and */ - /* at least 32K for zip's deflate method */ - -static uch *inbuf; -static uch *window; - -static unsigned insize; /* valid bytes in inbuf */ -static unsigned inptr; /* index of next byte to be processed in inbuf */ -static unsigned outcnt; /* bytes in output buffer */ static int exit_code; -static int unzip_error; -static long bytes_out; +static int decompress_error; static int crd_infd, crd_outfd; -#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf()) - -/* Diagnostic functions (stubbed out) */ -#define Assert(cond,msg) -#define Trace(x) -#define Tracev(x) -#define Tracevv(x) -#define Tracec(c,x) -#define Tracecv(c,x) - -#define STATIC static -#define INIT __init - -static int __init fill_inbuf(void); -static void __init flush_window(void); -static void __init error(char *m); - -#define NO_INFLATE_MALLOC - -#include "../lib/inflate.c" - -/* =========================================================================== - * Fill the input buffer. This is called only when the buffer is empty - * and at least one byte is really needed. - * Returning -1 does not guarantee that gunzip() will ever return. - */ -static int __init fill_inbuf(void) +static int __init compr_fill(void *buf, unsigned int len) { - if (exit_code) return -1; - - insize = sys_read(crd_infd, inbuf, INBUFSIZ); - if (insize == 0) { - error("RAMDISK: ran out of compressed data"); - return -1; - } - - inptr = 1; - - return inbuf[0]; + int r = sys_read(crd_infd, buf, len); + if (r < 0) + printk(KERN_ERR "RAMDISK: error while reading compressed data"); + else if (r == 0) + printk(KERN_ERR "RAMDISK: EOF while reading compressed data"); + return r; } -/* =========================================================================== - * Write the output window window[0..outcnt-1] and update crc and bytes_out. - * (Used for the decompressed data only.) - */ -static void __init flush_window(void) +static int __init compr_flush(void *window, unsigned int outcnt) { - ulg c = crc; /* temporary variable */ - unsigned n, written; - uch *in, ch; - - written = sys_write(crd_outfd, window, outcnt); - if (written != outcnt && unzip_error == 0) { - printk(KERN_ERR "RAMDISK: incomplete write (%d != %d) %ld\n", - written, outcnt, bytes_out); - unzip_error = 1; - } - in = window; - for (n = 0; n < outcnt; n++) { - ch = *in++; - c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); - } - crc = c; - bytes_out += (ulg)outcnt; - outcnt = 0; + int written = sys_write(crd_outfd, window, outcnt); + if (written != outcnt) { + if (decompress_error == 0) + printk(KERN_ERR + "RAMDISK: incomplete write (%d != %d)\n", + written, outcnt); + decompress_error = 1; + return -1; + } + return outcnt; } static void __init error(char *x) { printk(KERN_ERR "%s\n", x); exit_code = 1; - unzip_error = 1; + decompress_error = 1; } -static int __init crd_load(int in_fd, int out_fd) +static int __init crd_load(int in_fd, int out_fd, decompress_fn deco) { int result; - - insize = 0; /* valid bytes in inbuf */ - inptr = 0; /* index of next byte to be processed in inbuf */ - outcnt = 0; /* bytes in output buffer */ - exit_code = 0; - bytes_out = 0; - crc = (ulg)0xffffffffL; /* shift register contents */ - crd_infd = in_fd; crd_outfd = out_fd; - inbuf = kmalloc(INBUFSIZ, GFP_KERNEL); - if (!inbuf) { - printk(KERN_ERR "RAMDISK: Couldn't allocate gzip buffer\n"); - return -1; - } - window = kmalloc(WSIZE, GFP_KERNEL); - if (!window) { - printk(KERN_ERR "RAMDISK: Couldn't allocate gzip window\n"); - kfree(inbuf); - return -1; - } - makecrc(); - result = gunzip(); - if (unzip_error) + result = deco(NULL, 0, compr_fill, compr_flush, NULL, NULL, error); + if (decompress_error) result = 1; - kfree(inbuf); - kfree(window); return result; } diff --git a/init/initramfs.c b/init/initramfs.c index 4f5ba75aaa7c..40bd4fb95788 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -389,11 +389,14 @@ static int __init write_buffer(char *buf, unsigned len) return len - count; } -static void __init flush_buffer(char *buf, unsigned len) + +static int __init flush_buffer(void *bufv, unsigned len) { + char *buf = (char *) bufv; int written; + int origLen = len; if (message) - return; + return -1; while ((written = write_buffer(buf, len)) < len && !message) { char c = buf[written]; if (c == '0') { @@ -407,73 +410,14 @@ static void __init flush_buffer(char *buf, unsigned len) } else error("junk in compressed archive"); } + return origLen; } -/* - * gzip declarations - */ - -#define OF(args) args - -#ifndef memzero -#define memzero(s, n) memset ((s), 0, (n)) -#endif - -typedef unsigned char uch; -typedef unsigned short ush; -typedef unsigned long ulg; - -#define WSIZE 0x8000 /* window size--must be a power of two, and */ - /* at least 32K for zip's deflate method */ - -static uch *inbuf; -static uch *window; - -static unsigned insize; /* valid bytes in inbuf */ -static unsigned inptr; /* index of next byte to be processed in inbuf */ -static unsigned outcnt; /* bytes in output buffer */ -static long bytes_out; - -#define get_byte() (inptr < insize ? inbuf[inptr++] : -1) - -/* Diagnostic functions (stubbed out) */ -#define Assert(cond,msg) -#define Trace(x) -#define Tracev(x) -#define Tracevv(x) -#define Tracec(c,x) -#define Tracecv(c,x) - -#define STATIC static -#define INIT __init - -static void __init flush_window(void); -static void __init error(char *m); - -#define NO_INFLATE_MALLOC +static unsigned my_inptr; /* index of next byte to be processed in inbuf */ -#include "../lib/inflate.c" - -/* =========================================================================== - * Write the output window window[0..outcnt-1] and update crc and bytes_out. - * (Used for the decompressed data only.) - */ -static void __init flush_window(void) -{ - ulg c = crc; /* temporary variable */ - unsigned n; - uch *in, ch; - - flush_buffer(window, outcnt); - in = window; - for (n = 0; n < outcnt; n++) { - ch = *in++; - c = crc_32_tab[((int)c ^ ch) & 0xff] ^ (c >> 8); - } - crc = c; - bytes_out += (ulg)outcnt; - outcnt = 0; -} +#include +#include +#include static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) { @@ -482,9 +426,10 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) header_buf = kmalloc(110, GFP_KERNEL); symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL); name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL); - window = kmalloc(WSIZE, GFP_KERNEL); - if (!window || !header_buf || !symlink_buf || !name_buf) + + if (!header_buf || !symlink_buf || !name_buf) panic("can't allocate buffers"); + state = Start; this_header = 0; message = NULL; @@ -504,22 +449,38 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) continue; } this_header = 0; - insize = len; - inbuf = buf; - inptr = 0; - outcnt = 0; /* bytes in output buffer */ - bytes_out = 0; - crc = (ulg)0xffffffffL; /* shift register contents */ - makecrc(); - gunzip(); + if (!gunzip(buf, len, NULL, flush_buffer, NULL, + &my_inptr, error) && + message == NULL) + goto ok; + +#ifdef CONFIG_RD_BZIP2 + message = NULL; /* Zero out message, or else cpio will + think an error has already occured */ + if (!bunzip2(buf, len, NULL, flush_buffer, NULL, + &my_inptr, error) && + message == NULL) { + goto ok; + } +#endif + +#ifdef CONFIG_RD_LZMA + message = NULL; /* Zero out message, or else cpio will + think an error has already occured */ + if (!unlzma(buf, len, NULL, flush_buffer, NULL, + &my_inptr, error) && + message == NULL) { + goto ok; + } +#endif +ok: if (state != Reset) - error("junk in gzipped archive"); - this_header = saved_offset + inptr; - buf += inptr; - len -= inptr; + error("junk in compressed archive"); + this_header = saved_offset + my_inptr; + buf += my_inptr; + len -= my_inptr; } dir_utime(); - kfree(window); kfree(name_buf); kfree(symlink_buf); kfree(header_buf); -- cgit v1.2.2 From b172fd882d201cf8aa67cddd9c1a023421fd4956 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 4 Jan 2009 14:42:52 -0800 Subject: bzip2/lzma: use a table to search for initramfs compression formats Impact: Code simplification Instead of open-coding testing for initramfs compression formats, use a table. Signed-off-by: H. Peter Anvin --- init/do_mounts_rd.c | 82 +++++++++++++++++++++++------------------------------ 1 file changed, 35 insertions(+), 47 deletions(-) (limited to 'init') diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index dcaeb1f90b32..9c9d7dbcf9ca 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -43,13 +43,31 @@ static int __init crd_load(int in_fd, int out_fd, decompress_fn deco); * numbers could not be found. * * We currently check for the following magic numbers: - * minix - * ext2 + * minix + * ext2 * romfs * cramfs - * gzip + * gzip */ -static int __init +static const struct compress_format { + unsigned char magic[2]; + const char *name; + decompress_fn decompressor; +} compressed_formats[] = { +#ifdef CONFIG_RD_GZIP + { {037, 0213}, "gzip", gunzip }, + { {037, 0236}, "gzip", gunzip }, +#endif +#ifdef CONFIG_RD_BZIP2 + { {0x42, 0x5a}, "bzip2", bunzip2 }, +#endif +#ifdef CONFIG_RD_LZMA + { {0x5d, 0x00}, "lzma", unlzma }, +#endif + { {0, 0}, NULL, NULL } +}; + +static int __init identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) { const int size = 512; @@ -59,6 +77,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) struct cramfs_super *cramfsb; int nblocks = -1; unsigned char *buf; + const struct compress_format *cf; buf = kmalloc(size, GFP_KERNEL); if (!buf) @@ -71,52 +90,21 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) memset(buf, 0xe5, size); /* - * Read block 0 to test for gzipped kernel + * Read block 0 to test for compressed kernel */ sys_lseek(fd, start_block * BLOCK_SIZE, 0); sys_read(fd, buf, size); -#ifdef CONFIG_RD_GZIP - /* - * If it matches the gzip magic numbers, return 0 - */ - if (buf[0] == 037 && ((buf[1] == 0213) || (buf[1] == 0236))) { - printk(KERN_NOTICE - "RAMDISK: Compressed image found at block %d\n", - start_block); - *decompressor = gunzip; - nblocks = 0; - goto done; - } -#endif - -#ifdef CONFIG_RD_BZIP2 - /* - * If it matches the bzip2 magic numbers, return -1 - */ - if (buf[0] == 0x42 && (buf[1] == 0x5a)) { - printk(KERN_NOTICE - "RAMDISK: Bzipped image found at block %d\n", - start_block); - *decompressor = bunzip2; - nblocks = 0; - goto done; - } -#endif - -#ifdef CONFIG_RD_LZMA - /* - * If it matches the lzma magic numbers, return -1 - */ - if (buf[0] == 0x5d && (buf[1] == 0x00)) { - printk(KERN_NOTICE - "RAMDISK: Lzma image found at block %d\n", - start_block); - *decompressor = unlzma; - nblocks = 0; - goto done; + for (cf = compressed_formats; cf->decompressor; cf++) { + if (buf[0] == cf->magic[0] && buf[1] == cf->magic[1]) { + printk(KERN_NOTICE + "RAMDISK: %s image found at block %d\n", + cf->name, start_block); + *decompressor = cf->decompressor; + nblocks = 0; + goto done; + } } -#endif /* romfs is at block zero too */ if (romfsb->word0 == ROMSB_WORD0 && @@ -165,7 +153,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) printk(KERN_NOTICE "RAMDISK: Couldn't find valid RAM disk image starting at %d.\n", start_block); - + done: sys_lseek(fd, start_block * BLOCK_SIZE, 0); kfree(buf); @@ -224,7 +212,7 @@ int __init rd_load_image(char *from) nblocks, rd_blocks); goto done; } - + /* * OK, time to copy in the data */ -- cgit v1.2.2 From 2e9f3bddcbc711bb14d86c6f068a779bf3710247 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Sun, 4 Jan 2009 15:41:25 -0800 Subject: bzip2/lzma: make config machinery an arch configurable Impact: Bug fix (we should not show this menu on irrelevant architectures) Make the config machinery to drive the gzip/bzip2/lzma selection dependent on the architecture advertising HAVE_KERNEL_* so that we don't display this for architectures where it doesn't matter. Signed-off-by: H. Peter Anvin --- init/Kconfig | 52 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 31 insertions(+), 21 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index df84625b1373..f9633c03cb12 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -101,10 +101,20 @@ config LOCALVERSION_AUTO which is done within the script "scripts/setlocalversion".) +config HAVE_KERNEL_GZIP + bool + +config HAVE_KERNEL_BZIP2 + bool + +config HAVE_KERNEL_LZMA + bool + choice - prompt "Kernel compression mode" - default KERNEL_GZIP - help + prompt "Kernel compression mode" + default KERNEL_GZIP + depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA + help The linux kernel is a kind of self-extracting executable. Several compression algorithms are available, which differ in efficiency, compression and decompression speed. @@ -123,34 +133,34 @@ choice If in doubt, select 'gzip' config KERNEL_GZIP - bool "Gzip" - help - The old and tried gzip compression. Its compression ratio is - the poorest among the 3 choices; however its speed (both - compression and decompression) is the fastest. + bool "Gzip" + depends on HAVE_KERNEL_GZIP + help + The old and tried gzip compression. Its compression ratio is + the poorest among the 3 choices; however its speed (both + compression and decompression) is the fastest. config KERNEL_BZIP2 bool "Bzip2" + depends on HAVE_KERNEL_BZIP2 help Its compression ratio and speed is intermediate. - Decompression speed is slowest among the 3. - The kernel size is about 10 per cent smaller with bzip2, - in comparison to gzip. - Bzip2 uses a large amount of memory. For modern kernels - you will need at least 8MB RAM or more for booting. + Decompression speed is slowest among the three. The kernel + size is about 10% smaller with bzip2, in comparison to gzip. + Bzip2 uses a large amount of memory. For modern kernels you + will need at least 8MB RAM or more for booting. config KERNEL_LZMA - bool "LZMA" - help - The most recent compression algorithm. - Its ratio is best, decompression speed is between the other - 2. Compression is slowest. - The kernel size is about 33 per cent smaller with lzma, - in comparison to gzip. + bool "LZMA" + depends on HAVE_KERNEL_LZMA + help + The most recent compression algorithm. + Its ratio is best, decompression speed is between the other + two. Compression is slowest. The kernel size is about 33% + smaller with LZMA in comparison to gzip. endchoice - config SWAP bool "Support for paging of anonymous memory (swap)" depends on MMU && BLOCK -- cgit v1.2.2 From a26ee60f90daffe1de6be0d093af86e7279b3dfd Mon Sep 17 00:00:00 2001 From: Alain Knaff Date: Wed, 7 Jan 2009 00:10:27 -0800 Subject: bzip2/lzma: fix built-in initramfs vs CONFIG_RD_GZIP Impact: Resolves build failures in some configurations Makes it possible to disable CONFIG_RD_GZIP . In that case, the built-in initramfs will be compressed by whatever compressor is available (bzip2 or lzma) or left uncompressed if none is available. It also removes a couple of warnings which occur when no ramdisk compression at all is chosen. It also restores the select ZLIB_INFLATE in drivers/block/Kconfig which somehow came missing. This is needed to activate compilation of the stuff in zlib_deflate. Signed-off-by: Alain Knaff Signed-off-by: H. Peter Anvin --- init/initramfs.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index 40bd4fb95788..a3ba91cdab89 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -389,7 +389,7 @@ static int __init write_buffer(char *buf, unsigned len) return len - count; } - +#if defined CONFIG_RD_GZIP || defined CONFIG_RD_BZIP2 || defined CONFIG_RD_LZMA static int __init flush_buffer(void *bufv, unsigned len) { char *buf = (char *) bufv; @@ -412,6 +412,7 @@ static int __init flush_buffer(void *bufv, unsigned len) } return origLen; } +#endif static unsigned my_inptr; /* index of next byte to be processed in inbuf */ @@ -449,10 +450,12 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) continue; } this_header = 0; +#ifdef CONFIG_RD_GZIP if (!gunzip(buf, len, NULL, flush_buffer, NULL, &my_inptr, error) && message == NULL) goto ok; +#endif #ifdef CONFIG_RD_BZIP2 message = NULL; /* Zero out message, or else cpio will @@ -473,7 +476,9 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) goto ok; } #endif +#if defined CONFIG_RD_GZIP || defined CONFIG_RD_BZIP2 || defined CONFIG_RD_LZMA ok: +#endif if (state != Reset) error("junk in compressed archive"); this_header = saved_offset + my_inptr; -- cgit v1.2.2 From 889c92d21db40be0b7d22a59395060237895bb85 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Thu, 8 Jan 2009 15:14:17 -0800 Subject: bzip2/lzma: centralize format detection Centralize the compression format detection to a common routine in the lib directory, and use it for both initramfs and initrd. Signed-off-by: H. Peter Anvin --- init/do_mounts_rd.c | 38 +++++++------------------------------- init/initramfs.c | 39 +++++++-------------------------------- 2 files changed, 14 insertions(+), 63 deletions(-) (limited to 'init') diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 9c9d7dbcf9ca..a06ed4f92e0e 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -12,9 +12,6 @@ #include -#include -#include -#include int __initdata rd_prompt = 1;/* 1 = prompt for RAM disk, 0 = don't prompt */ @@ -49,24 +46,6 @@ static int __init crd_load(int in_fd, int out_fd, decompress_fn deco); * cramfs * gzip */ -static const struct compress_format { - unsigned char magic[2]; - const char *name; - decompress_fn decompressor; -} compressed_formats[] = { -#ifdef CONFIG_RD_GZIP - { {037, 0213}, "gzip", gunzip }, - { {037, 0236}, "gzip", gunzip }, -#endif -#ifdef CONFIG_RD_BZIP2 - { {0x42, 0x5a}, "bzip2", bunzip2 }, -#endif -#ifdef CONFIG_RD_LZMA - { {0x5d, 0x00}, "lzma", unlzma }, -#endif - { {0, 0}, NULL, NULL } -}; - static int __init identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) { @@ -77,7 +56,7 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) struct cramfs_super *cramfsb; int nblocks = -1; unsigned char *buf; - const struct compress_format *cf; + const char *compress_name; buf = kmalloc(size, GFP_KERNEL); if (!buf) @@ -95,15 +74,12 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) sys_lseek(fd, start_block * BLOCK_SIZE, 0); sys_read(fd, buf, size); - for (cf = compressed_formats; cf->decompressor; cf++) { - if (buf[0] == cf->magic[0] && buf[1] == cf->magic[1]) { - printk(KERN_NOTICE - "RAMDISK: %s image found at block %d\n", - cf->name, start_block); - *decompressor = cf->decompressor; - nblocks = 0; - goto done; - } + *decompressor = decompress_method(buf, size, &compress_name); + if (*decompressor) { + printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n", + compress_name, start_block); + nblocks = 0; + goto done; } /* romfs is at block zero too */ diff --git a/init/initramfs.c b/init/initramfs.c index a3ba91cdab89..2f42984e5582 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -416,13 +416,13 @@ static int __init flush_buffer(void *bufv, unsigned len) static unsigned my_inptr; /* index of next byte to be processed in inbuf */ -#include -#include -#include +#include static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) { int written; + decompress_fn decompress; + dry_run = check_only; header_buf = kmalloc(110, GFP_KERNEL); symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL); @@ -450,35 +450,10 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) continue; } this_header = 0; -#ifdef CONFIG_RD_GZIP - if (!gunzip(buf, len, NULL, flush_buffer, NULL, - &my_inptr, error) && - message == NULL) - goto ok; -#endif - -#ifdef CONFIG_RD_BZIP2 - message = NULL; /* Zero out message, or else cpio will - think an error has already occured */ - if (!bunzip2(buf, len, NULL, flush_buffer, NULL, - &my_inptr, error) && - message == NULL) { - goto ok; - } -#endif - -#ifdef CONFIG_RD_LZMA - message = NULL; /* Zero out message, or else cpio will - think an error has already occured */ - if (!unlzma(buf, len, NULL, flush_buffer, NULL, - &my_inptr, error) && - message == NULL) { - goto ok; - } -#endif -#if defined CONFIG_RD_GZIP || defined CONFIG_RD_BZIP2 || defined CONFIG_RD_LZMA -ok: -#endif + decompress = decompress_method(buf, len, NULL); + if (decompress) + decompress(buf, len, NULL, flush_buffer, NULL, + &my_inptr, error); if (state != Reset) error("junk in compressed archive"); this_header = saved_offset + my_inptr; -- cgit v1.2.2 From 736f93236ce786d1bcf09ad4dcb38a360d35ea1b Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 10 Jan 2009 12:06:19 +0100 Subject: bzip2/lzma: make flush_buffer() unconditional Impact: build fix flush_buffer() is used unconditionally: init/initramfs.c:456: error: 'flush_buffer' undeclared (first use in this function) init/initramfs.c:456: error: (Each undeclared identifier is reported only once init/initramfs.c:456: error: for each function it appears in.) So remove the decompressor #ifdefs from around it. Signed-off-by: Ingo Molnar --- init/initramfs.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index f8241e832aa3..76f4a0125338 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -390,7 +390,6 @@ static int __init write_buffer(char *buf, unsigned len) return len - count; } -#if defined CONFIG_RD_GZIP || defined CONFIG_RD_BZIP2 || defined CONFIG_RD_LZMA static int __init flush_buffer(void *bufv, unsigned len) { char *buf = (char *) bufv; @@ -413,7 +412,6 @@ static int __init flush_buffer(void *bufv, unsigned len) } return origLen; } -#endif static unsigned my_inptr; /* index of next byte to be processed in inbuf */ -- cgit v1.2.2 From 23a22d57a8962479ca630c9542e62d6f86fdf927 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Mon, 12 Jan 2009 14:24:04 -0800 Subject: bzip2/lzma: comprehensible error messages for missing decompressor Instead of failing to identify a compressed image with a decompressor that we don't have compiled in, identify it and fail with a comprehensible panic message. Signed-off-by: H. Peter Anvin --- init/do_mounts_rd.c | 5 ++++- init/initramfs.c | 12 +++++++++++- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'init') diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index a015e267fd17..91d0cfca5071 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -79,9 +79,12 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) sys_read(fd, buf, size); *decompressor = decompress_method(buf, size, &compress_name); - if (*decompressor) { + if (compress_name) { printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n", compress_name, start_block); + if (!*decompressor) + printk(KERN_CRIT "RAMDISK: %s decompressor not configured!\n", + compress_name); nblocks = 0; goto done; } diff --git a/init/initramfs.c b/init/initramfs.c index 76f4a0125338..9a7290ec8187 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -421,6 +421,8 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) { int written; decompress_fn decompress; + const char *compress_name; + static __initdata char msg_buf[64]; dry_run = check_only; header_buf = kmalloc(110, GFP_KERNEL); @@ -449,10 +451,18 @@ static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) continue; } this_header = 0; - decompress = decompress_method(buf, len, NULL); + decompress = decompress_method(buf, len, &compress_name); if (decompress) decompress(buf, len, NULL, flush_buffer, NULL, &my_inptr, error); + else if (compress_name) { + if (!message) { + snprintf(msg_buf, sizeof msg_buf, + "compression method %s not configured", + compress_name); + message = msg_buf; + } + } if (state != Reset) error("junk in compressed archive"); this_header = saved_offset + my_inptr; -- cgit v1.2.2 From 73310a169aebe257efdd35a763cce1c7658f40c9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Wed, 14 Jan 2009 11:28:35 -0800 Subject: init: make initrd/initramfs decompression failure a KERN_EMERG event Impact: More consistent behaviour, avoid policy in the kernel Upgrade/downgrade initrd/initramfs decompression failure from inconsistently a panic or a KERN_ALERT message to a KERN_EMERG event. It is, however, possible do design a system which can recover from this (using the kernel builtin code and/or the internal initramfs), which means this is policy, not a technical necessity. A good way to handle this would be to have a panic-level=X option, to force a panic on a printk above a certain level. That is a separate patch, however. Signed-off-by: H. Peter Anvin --- init/do_mounts_rd.c | 3 ++- init/initramfs.c | 11 +++++++---- 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'init') diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c index 91d0cfca5071..027a402708de 100644 --- a/init/do_mounts_rd.c +++ b/init/do_mounts_rd.c @@ -83,7 +83,8 @@ identify_ramdisk_image(int fd, int start_block, decompress_fn *decompressor) printk(KERN_NOTICE "RAMDISK: %s image found at block %d\n", compress_name, start_block); if (!*decompressor) - printk(KERN_CRIT "RAMDISK: %s decompressor not configured!\n", + printk(KERN_EMERG + "RAMDISK: %s decompressor not configured!\n", compress_name); nblocks = 0; goto done; diff --git a/init/initramfs.c b/init/initramfs.c index 9a7290ec8187..7dcde7ea6603 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -528,7 +528,7 @@ static int __init populate_rootfs(void) char *err = unpack_to_rootfs(__initramfs_start, __initramfs_end - __initramfs_start, 0); if (err) - panic(err); + panic(err); /* Failed to decompress INTERNAL initramfs */ if (initrd_start) { #ifdef CONFIG_BLK_DEV_RAM int fd; @@ -554,9 +554,12 @@ static int __init populate_rootfs(void) printk(KERN_INFO "Unpacking initramfs..."); err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start, 0); - if (err) - panic(err); - printk(" done\n"); + if (err) { + printk(" failed!\n"); + printk(KERN_EMERG "%s\n", err); + } else { + printk(" done\n"); + } free_initrd(); #endif } -- cgit v1.2.2 From ceacc2c1c85ac498ca4cf297bdfe5b4aaa9fd0e0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 16 Jan 2009 14:46:40 +0100 Subject: sched: make plist a library facility Ingo Molnar wrote: > here's a new build failure with tip/sched/rt: > > LD .tmp_vmlinux1 > kernel/built-in.o: In function `set_curr_task_rt': > sched.c:(.text+0x3675): undefined reference to `plist_del' > kernel/built-in.o: In function `pick_next_task_rt': > sched.c:(.text+0x37ce): undefined reference to `plist_del' > kernel/built-in.o: In function `enqueue_pushable_task': > sched.c:(.text+0x381c): undefined reference to `plist_del' Eliminate the plist library kconfig and make it available unconditionally. Signed-off-by: Peter Zijlstra Signed-off-by: Ingo Molnar --- init/Kconfig | 1 - 1 file changed, 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index a724a149bf3f..19b78aa010e3 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -874,7 +874,6 @@ config SLABINFO config RT_MUTEXES boolean - select PLIST config BASE_SMALL int -- cgit v1.2.2 From 91f73f90d97fa67effbb49e0a79c50cf26dfe324 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 20 Feb 2009 17:34:06 +0100 Subject: tracing/markers: make markers select tracepoints Sometimes it happens that KConfig dependencies are not handled like in the following scenario: - config A bool - config B bool depends on A - config C bool select B If one selects C, then it will select B without checking its dependency to A, if A hasn't been selected elsewhere, it will result in a build failure. This is what happens on the following build error: kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52f64): undefined reference to `tracepoint_probe_register_noupdate' kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52f74): undefined reference to `tracepoint_probe_unregister_noupdate' kernel/built-in.o: In function `marker_update_probe_range': (.text+0x52fb9): undefined reference to `tracepoint_probe_unregister_noupdate' kernel/built-in.o: In function `marker_update_probes': marker.c:(.text+0x530ba): undefined reference to `tracepoint_probe_update_all' CONFIG_KVM_TRACE will select CONFIG_MARKER, but the latter depends on CONFIG_TRACEPOINTS which will not be selected. Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Signed-off-by: Ingo Molnar --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f068071fcc5d..26b5bab6f6e8 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -945,7 +945,7 @@ config TRACEPOINTS config MARKERS bool "Activate markers" - depends on TRACEPOINTS + select TRACEPOINTS help Place an empty function call at each marker site. Can be dynamically changed for a probe function. -- cgit v1.2.2 From b943c460ff8556a193b28e2145b513f8b978e869 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Tue, 10 Mar 2009 12:55:46 -0700 Subject: menu: fix embedded menu snafu The COMPAT_BRK kconfig symbol does not depend on EMBEDDED, but it is in the midst of the EMBEDDED menu symbols, so it mucks up the EMBEDDED menu. Fix by moving it to just after all of the EMBEDDED menu symbols. Also, ANON_INODES has a similar problem, so move it to just above the EMBEDDED menu items since it is used in the EMBEDDED menu. Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index f068071fcc5d..6a5c5fed66c9 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -675,6 +675,9 @@ config CC_OPTIMIZE_FOR_SIZE config SYSCTL bool +config ANON_INODES + bool + menuconfig EMBEDDED bool "Configure standard kernel features (for small systems)" help @@ -780,18 +783,6 @@ config PCSPKR_PLATFORM This option allows to disable the internal PC-Speaker support, saving some memory. -config COMPAT_BRK - bool "Disable heap randomization" - default y - help - Randomizing heap placement makes heap exploits harder, but it - also breaks ancient binaries (including anything libc5 based). - This option changes the bootup default to heap randomization - disabled, and can be overriden runtime by setting - /proc/sys/kernel/randomize_va_space to 2. - - On non-ancient distros (post-2000 ones) N is usually a safe choice. - config BASE_FULL default y bool "Enable full-sized data structures for core" if EMBEDDED @@ -809,9 +800,6 @@ config FUTEX support for "fast userspace mutexes". The resulting kernel may not run glibc-based applications correctly. -config ANON_INODES - bool - config EPOLL bool "Enable eventpoll support" if EMBEDDED default y @@ -897,6 +885,18 @@ config SLUB_DEBUG SLUB sysfs support. /sys/slab will not exist and there will be no support for cache validation etc. +config COMPAT_BRK + bool "Disable heap randomization" + default y + help + Randomizing heap placement makes heap exploits harder, but it + also breaks ancient binaries (including anything libc5 based). + This option changes the bootup default to heap randomization + disabled, and can be overriden runtime by setting + /proc/sys/kernel/randomize_va_space to 2. + + On non-ancient distros (post-2000 ones) N is usually a safe choice. + choice prompt "Choose SLAB allocator" default SLUB -- cgit v1.2.2 From 759ee0915dd713361e72facb78b66600b5712d65 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Wed, 25 Mar 2009 17:06:30 +0800 Subject: init,cpuset: fix initialize order Impact: cpuset_wq should be initialized after init_workqueues() When I read /debugfs/tracing/trace_stat/workqueues, I got this: # CPU INSERTED EXECUTED NAME # | | | | 0 0 0 cpuset 0 285 285 events/0 0 2 2 work_on_cpu/0 0 1115 1115 khelper 0 325 325 kblockd/0 0 0 0 kacpid 0 0 0 kacpi_notify 0 0 0 ata/0 0 0 0 ata_aux 0 0 0 ksuspend_usbd 0 0 0 aio/0 0 0 0 nfsiod 0 0 0 kpsmoused 0 0 0 kstriped 0 0 0 kondemand/0 0 1 1 hid_compat 0 0 0 rpciod/0 1 64 64 events/1 1 2 2 work_on_cpu/1 1 5 5 kblockd/1 1 0 0 ata/1 1 0 0 aio/1 1 0 0 kondemand/1 1 0 0 rpciod/1 I found "cpuset" is at the earliest. I found a create_singlethread_workqueue() is earlier than init_workqueues(): kernel_init() ->cpuset_init_smp() ->create_singlethread_workqueue() ->do_basic_setup() ->init_workqueues() I think it's better that create_singlethread_workqueue() is called after workqueue subsystem has been initialized. Signed-off-by: Lai Jiangshan Acked-by: Steven Rostedt Acked-by: Frederic Weisbecker Cc: Paul Menage Cc: miaoxie Cc: Li Zefan Cc: Andrew Morton LKML-Reference: <49C9F416.1050707@cn.fujitsu.com> Signed-off-by: Ingo Molnar --- init/main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 20d784ab5ef8..b0097d2b63ae 100644 --- a/init/main.c +++ b/init/main.c @@ -772,6 +772,7 @@ static void __init do_basic_setup(void) { rcu_init_sched(); /* needed by module_init stage. */ init_workqueues(); + cpuset_init_smp(); usermodehelper_init(); driver_init(); init_irq_proc(); @@ -865,8 +866,6 @@ static int __init kernel_init(void * unused) smp_init(); sched_init_smp(); - cpuset_init_smp(); - do_basic_setup(); /* -- cgit v1.2.2 From df52092f3c97788592ef72501a43fb7ac6a3cfe0 Mon Sep 17 00:00:00 2001 From: "Li, Shaohua" Date: Wed, 13 Aug 2008 17:26:01 +0800 Subject: fastboot: remove duplicate unpack_to_rootfs() we check if initrd is initramfs first and then do the real unpack. The check isn't required, we can directly do unpack. If the initrd isn't an initramfs, we can remove the garbage. In my laptop, this saves 0.1s boot time. This patch penalizes non-initramfs initrd case, but nowadays, initramfs is the most widely used method for initrds. Signed-off-by: Shaohua Li Acked-by: Arjan van de Ven Signed-off-by: Ingo Molnar --- init/initramfs.c | 71 ++++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 56 insertions(+), 15 deletions(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index d9c941c0c3ca..d3c56fcb30b8 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include @@ -166,8 +167,6 @@ static __initdata char *victim; static __initdata unsigned count; static __initdata loff_t this_header, next_header; -static __initdata int dry_run; - static inline void __init eat(unsigned n) { victim += n; @@ -229,10 +228,6 @@ static int __init do_header(void) parse_header(collected); next_header = this_header + N_ALIGN(name_len) + body_len; next_header = (next_header + 3) & ~3; - if (dry_run) { - read_into(name_buf, N_ALIGN(name_len), GotName); - return 0; - } state = SkipIt; if (name_len <= 0 || name_len > PATH_MAX) return 0; @@ -303,8 +298,6 @@ static int __init do_name(void) free_hash(); return 0; } - if (dry_run) - return 0; clean_path(collected, mode); if (S_ISREG(mode)) { int ml = maybe_link(); @@ -476,10 +469,9 @@ static void __init flush_window(void) outcnt = 0; } -static char * __init unpack_to_rootfs(char *buf, unsigned len, int check_only) +static char * __init unpack_to_rootfs(char *buf, unsigned len) { int written; - dry_run = check_only; header_buf = kmalloc(110, GFP_KERNEL); symlink_buf = kmalloc(PATH_MAX + N_ALIGN(PATH_MAX) + 1, GFP_KERNEL); name_buf = kmalloc(N_ALIGN(PATH_MAX), GFP_KERNEL); @@ -574,10 +566,57 @@ skip: initrd_end = 0; } +#define BUF_SIZE 1024 +static void __init clean_rootfs(void) +{ + int fd; + void *buf; + struct linux_dirent64 *dirp; + int count; + + fd = sys_open("/", O_RDONLY, 0); + WARN_ON(fd < 0); + if (fd < 0) + return; + buf = kzalloc(BUF_SIZE, GFP_KERNEL); + WARN_ON(!buf); + if (!buf) { + sys_close(fd); + return; + } + + dirp = buf; + count = sys_getdents64(fd, dirp, BUF_SIZE); + while (count > 0) { + while (count > 0) { + struct stat st; + int ret; + + ret = sys_newlstat(dirp->d_name, &st); + WARN_ON_ONCE(ret); + if (!ret) { + if (S_ISDIR(st.st_mode)) + sys_rmdir(dirp->d_name); + else + sys_unlink(dirp->d_name); + } + + count -= dirp->d_reclen; + dirp = (void *)dirp + dirp->d_reclen; + } + dirp = buf; + memset(buf, 0, BUF_SIZE); + count = sys_getdents64(fd, dirp, BUF_SIZE); + } + + sys_close(fd); + kfree(buf); +} + static int __init populate_rootfs(void) { char *err = unpack_to_rootfs(__initramfs_start, - __initramfs_end - __initramfs_start, 0); + __initramfs_end - __initramfs_start); if (err) panic(err); if (initrd_start) { @@ -585,13 +624,15 @@ static int __init populate_rootfs(void) int fd; printk(KERN_INFO "checking if image is initramfs..."); err = unpack_to_rootfs((char *)initrd_start, - initrd_end - initrd_start, 1); + initrd_end - initrd_start); if (!err) { printk(" it is\n"); - unpack_to_rootfs((char *)initrd_start, - initrd_end - initrd_start, 0); free_initrd(); return 0; + } else { + clean_rootfs(); + unpack_to_rootfs(__initramfs_start, + __initramfs_end - __initramfs_start); } printk("it isn't (%s); looks like an initrd\n", err); fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700); @@ -604,7 +645,7 @@ static int __init populate_rootfs(void) #else printk(KERN_INFO "Unpacking initramfs..."); err = unpack_to_rootfs((char *)initrd_start, - initrd_end - initrd_start, 0); + initrd_end - initrd_start); if (err) panic(err); printk(" done\n"); -- cgit v1.2.2 From 1a2142afa5646ad5af44bbe1febaa5e0b7e71156 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 Mar 2009 22:05:10 -0600 Subject: cpumask: remove dangerous CPU_MASK_ALL_PTR, &CPU_MASK_ALL Impact: cleanup (Thanks to Al Viro for reminding me of this, via Ingo) CPU_MASK_ALL is the (deprecated) "all bits set" cpumask, defined as so: #define CPU_MASK_ALL (cpumask_t) { { ... } } Taking the address of such a temporary is questionable at best, unfortunately 321a8e9d (cpumask: add CPU_MASK_ALL_PTR macro) added CPU_MASK_ALL_PTR: #define CPU_MASK_ALL_PTR (&CPU_MASK_ALL) Which formalizes this practice. One day gcc could bite us over this usage (though we seem to have gotten away with it so far). So replace everywhere which used &CPU_MASK_ALL or CPU_MASK_ALL_PTR with the modern "cpu_all_mask" (a real const struct cpumask *). Signed-off-by: Rusty Russell Acked-by: Ingo Molnar Reported-by: Al Viro Cc: Mike Travis --- init/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 6bf83afd654d..1ac7ec78e601 100644 --- a/init/main.c +++ b/init/main.c @@ -842,7 +842,7 @@ static int __init kernel_init(void * unused) /* * init can run on any cpu. */ - set_cpus_allowed_ptr(current, CPU_MASK_ALL_PTR); + set_cpus_allowed_ptr(current, cpu_all_mask); /* * Tell the world that we're going to be the grim * reaper of innocent orphaned children. -- cgit v1.2.2 From 2b17fa506c418e9fb02bbbc7f426d2bbb5b247a6 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Mon, 30 Mar 2009 22:05:12 -0600 Subject: cpumask: use set_cpu_active in init/main.c cpu_active_map is deprecated in favor of cpu_active_mask, which is const for safety: we use accessors now (set_cpu_active) is we really want to make a change. Signed-off-by: Rusty Russell --- init/main.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'init') diff --git a/init/main.c b/init/main.c index 1ac7ec78e601..d6b388fbffa6 100644 --- a/init/main.c +++ b/init/main.c @@ -407,8 +407,7 @@ static void __init smp_init(void) * Set up the current CPU as possible to migrate to. * The other ones will be done by cpu_up/cpu_down() */ - cpu = smp_processor_id(); - cpu_set(cpu, cpu_active_map); + set_cpu_active(smp_processor_id(), true); /* FIXME: This should be done in userspace --RR */ for_each_present_cpu(cpu) { -- cgit v1.2.2 From 692105b8ac5bcd75dc65f6a8f10bdbd0f0f34dcf Mon Sep 17 00:00:00 2001 From: Matt LaPlante Date: Mon, 26 Jan 2009 11:12:25 +0100 Subject: trivial: fix typos/grammar errors in Kconfig texts Signed-off-by: Matt LaPlante Acked-by: Randy Dunlap Signed-off-by: Jiri Kosina --- init/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 14c483d2b7c9..bcffc0e47647 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -687,7 +687,7 @@ config PID_NS depends on NAMESPACES && EXPERIMENTAL help Support process id namespaces. This allows having multiple - process with the same pid as long as they are in different + processes with the same pid as long as they are in different pid namespaces. This is a building block of containers. Unless you want to work with an experimental feature @@ -952,7 +952,7 @@ config COMPAT_BRK Randomizing heap placement makes heap exploits harder, but it also breaks ancient binaries (including anything libc5 based). This option changes the bootup default to heap randomization - disabled, and can be overriden runtime by setting + disabled, and can be overridden at runtime by setting /proc/sys/kernel/randomize_va_space to 2. On non-ancient distros (post-2000 ones) N is usually a safe choice. @@ -1110,7 +1110,7 @@ config INIT_ALL_POSSIBLE cpu_possible_map, some of them chose to initialize cpu_possible_map with all 1s, and others with all 0s. When they were centralised, it was better to provide this option than to break all the archs - and have several arch maintainers persuing me down dark alleys. + and have several arch maintainers pursuing me down dark alleys. config STOP_MACHINE bool -- cgit v1.2.2 From 21acb9caa2e30b100e9a1943d995bb99d40f4035 Mon Sep 17 00:00:00 2001 From: Thadeu Lima de Souza Cascardo Date: Wed, 4 Feb 2009 10:12:08 +0100 Subject: trivial: fix where cgroup documentation is not correctly referred to cgroup documentation was moved to Documentation/cgroups/. There are some places that still refer to Documentation/controllers/, Documentation/cgroups.txt and Documentation/cpusets.txt. Fix those. Signed-off-by: Thadeu Lima de Souza Cascardo Reviewed-by: Li Zefan Acked-by: Paul Menage Signed-off-by: Jiri Kosina --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index bcffc0e47647..99eb4196bd0a 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -565,7 +565,7 @@ config CGROUP_MEM_RES_CTLR select MM_OWNER help Provides a memory resource controller that manages both anonymous - memory and page cache. (See Documentation/controllers/memory.txt) + memory and page cache. (See Documentation/cgroups/memory.txt) Note that setting this option increases fixed memory overhead associated with each page of memory in the system. By this, -- cgit v1.2.2 From 8b2b5c217c20b5460218ab8731295f2e46c7dd29 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:27:03 +1100 Subject: md: move LEVEL_* definition from md_k.h to md_u.h .. as they are part of the user-space interface. Also move MdpMinorShift into there so we can remove duplication. Lastly move mdp_major in. It is less obviously part of the user-space interface, but do_mounts_md.c uses it, and it is acting a bit like user-space. Signed-off-by: NeilBrown --- init/do_mounts_md.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'init') diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 9bdddbcb3d6a..23a15fb57e15 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -112,8 +112,6 @@ static int __init md_setup(char *str) return 1; } -#define MdpMinorShift 6 - static void __init md_setup_drive(void) { int minor, i, ent, partitioned; -- cgit v1.2.2 From bff61975b3d6c18ee31457cc5b4d73042f44915f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 31 Mar 2009 14:33:13 +1100 Subject: md: move lots of #include lines out of .h files and into .c This makes the includes more explicit, and is preparation for moving md_k.h to drivers/md/md.h Remove include/raid/md.h as its only remaining use was to #include other files. Signed-off-by: NeilBrown --- init/do_mounts.h | 1 + init/do_mounts_md.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'init') diff --git a/init/do_mounts.h b/init/do_mounts.h index 9aa968d54329..f5b978a9bb92 100644 --- a/init/do_mounts.h +++ b/init/do_mounts.h @@ -1,4 +1,5 @@ #include +#include #include #include #include diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c index 23a15fb57e15..69aebbf8fd2d 100644 --- a/init/do_mounts_md.c +++ b/init/do_mounts_md.c @@ -1,5 +1,6 @@ #include -#include +#include +#include #include "do_mounts.h" -- cgit v1.2.2 From 5ad4e53bd5406ee214ddc5a41f03f779b8b2d526 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 29 Mar 2009 19:50:06 -0400 Subject: Get rid of indirect include of fs_struct.h Don't pull it in sched.h; very few files actually need it and those can include directly. sched.h itself only needs forward declaration of struct fs_struct; Signed-off-by: Al Viro --- init/do_mounts.c | 1 + 1 file changed, 1 insertion(+) (limited to 'init') diff --git a/init/do_mounts.c b/init/do_mounts.c index 8d4ff5afc1d8..dd7ee5f203f3 100644 --- a/init/do_mounts.c +++ b/init/do_mounts.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include -- cgit v1.2.2 From acdd052a285a7b4cc7da4fa7d34ef9fd0a67b2f8 Mon Sep 17 00:00:00 2001 From: Hannes Eder Date: Tue, 31 Mar 2009 15:23:50 -0700 Subject: init/main.c: fix sparse warnings: context imbalance Impact: Attribute function 'init_post' with __releases(...). Fix these sparse warnings: init/main.c:805:21: warning: context imbalance in 'init_post' - unexpected unlock init/main.c:899:9: warning: context imbalance in 'kernel_init' - wrong count at exit Signed-off-by: Hannes Eder Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 1 + 1 file changed, 1 insertion(+) (limited to 'init') diff --git a/init/main.c b/init/main.c index d6b388fbffa6..07c8658ffca5 100644 --- a/init/main.c +++ b/init/main.c @@ -793,6 +793,7 @@ static void run_init_process(char *init_filename) * makes it inline to init() and it becomes part of init.text section */ static noinline int init_post(void) + __releases(kernel_lock) { /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); -- cgit v1.2.2 From c1c490e017b66b31f6559db9cbb51a3ce00cf639 Mon Sep 17 00:00:00 2001 From: Simon Kitching Date: Thu, 2 Apr 2009 16:57:00 -0700 Subject: initramfs: prevent initramfs printk message being split by messages from other code. initramfs uses printk without a linefeed, then does some work, then uses printk to finish the message off. However if some other code does a printk in between, then the messages get mixed together. Better for each message to be an independent line... Example of problem that this fixes: checking if image is initramfs...<7>Switched to high resolution mode on CPU 1 Switched to high resolution mode on CPU 0 it is Signed-off-by: Simon Kitching Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/initramfs.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'init') diff --git a/init/initramfs.c b/init/initramfs.c index 619c1baf7701..80cd713f6cc5 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -571,11 +571,11 @@ static int __init populate_rootfs(void) if (initrd_start) { #ifdef CONFIG_BLK_DEV_RAM int fd; - printk(KERN_INFO "checking if image is initramfs..."); + printk(KERN_INFO "checking if image is initramfs...\n"); err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start); if (!err) { - printk(" it is\n"); + printk(KERN_INFO "rootfs image is initramfs; unpacking...\n"); free_initrd(); return 0; } else { @@ -583,7 +583,8 @@ static int __init populate_rootfs(void) unpack_to_rootfs(__initramfs_start, __initramfs_end - __initramfs_start); } - printk("it isn't (%s); looks like an initrd\n", err); + printk(KERN_INFO "rootfs image is not initramfs (%s)" + "; looks like an initrd\n", err); fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700); if (fd >= 0) { sys_write(fd, (char *)initrd_start, -- cgit v1.2.2 From 627991a20b3f4d504d20466ab405fe035cb1a20a Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 2 Apr 2009 16:57:47 -0700 Subject: memcg: remove redundant message at swapon It's pointed out that swap_cgroup's message at swapon() is nonsense. Because * It can be calculated very easily if all necessary information is written in Kconfig. * It's not necessary to annoying people at every swapon(). In other view, now, memory usage per swp_entry is reduced to 2bytes from 8bytes(64bit) and I think it's reasonably small. Reported-by: Hugh Dickins Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 ++ 1 file changed, 2 insertions(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 14c483d2b7c9..92d410603932 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -597,6 +597,8 @@ config CGROUP_MEM_RES_CTLR_SWAP is disabled by boot option, this will be automatically disabled and there will be no overhead from this. Even when you set this config=y, if boot option "noswapaccount" is set, swap will not be accounted. + Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page + size is 4096bytes, 512k per 1Gbytes of swap. endif # CGROUPS -- cgit v1.2.2 From db7f47cf4805e30decb0841764b21b7c4000f7dc Mon Sep 17 00:00:00 2001 From: Paul Menage Date: Thu, 2 Apr 2009 16:57:55 -0700 Subject: cpusets: allow cpusets to be configured/built on non-SMP systems Allow cpusets to be configured/built on non-SMP systems Currently it's impossible to build cpusets under UML on x86-64, since cpusets depends on SMP and x86-64 UML doesn't support SMP. There's code in cpusets that doesn't depend on SMP. This patch surrounds the minimum amount of cpusets code with #ifdef CONFIG_SMP in order to allow cpusets to build/run on UP systems (for testing purposes under UML). Reviewed-by: Li Zefan Signed-off-by: Paul Menage Cc: Ingo Molnar Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 92d410603932..1398a14b0191 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -531,7 +531,7 @@ config CGROUP_DEVICE config CPUSETS bool "Cpuset support" - depends on SMP && CGROUPS + depends on CGROUPS help This option will let you create and manage CPUSETs which allow dynamically partitioning a system into sets of CPUs and -- cgit v1.2.2 From 07fe7cb7c7c179f473fd9c823348fd3eb5dad369 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Create a dynamically sized pool of threads for doing very slow work items Create a dynamically sized pool of threads for doing very slow work items, such as invoking mkdir() or rmdir() - things that may take a long time and may sleep, holding mutexes/semaphores and hogging a thread, and are thus unsuitable for workqueues. The number of threads is always at least a settable minimum, but more are started when there's more work to do, up to a limit. Because of the nature of the load, it's not suitable for a 1-thread-per-CPU type pool. A system with one CPU may well want several threads. This is used by FS-Cache to do slow caching operations in the background, such as looking up, creating or deleting cache objects. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- init/Kconfig | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'init') diff --git a/init/Kconfig b/init/Kconfig index 1398a14b0191..236a79377b8e 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1014,6 +1014,18 @@ config MARKERS source "arch/Kconfig" +config SLOW_WORK + default n + bool "Enable slow work thread pool" + help + The slow work thread pool provides a number of dynamically allocated + threads that can be used by the kernel to perform operations that + take a relatively long time. + + An example of this would be CacheFiles doing a path lookup followed + by a series of mkdirs and a create call, all of which have to touch + disk. + endmenu # General setup config HAVE_GENERIC_DMA_COHERENT -- cgit v1.2.2