linux/arch/x86/boot/compressed/misc.c

414 lines
10 KiB
C
Raw Normal View History

/*
* misc.c
*
* This is a collection of several routines from gzip-1.0.3
* adapted for Linux.
*
* malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
* puts by Nick Holloway 1993, better puts by Martin Mares 1995
* High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
*/
/*
* we have to be careful, because no indirections are allowed here, and
* paravirt_ops is a kind of one. As it will only run in baremetal anyway,
* we just keep it from happening
*/
#undef CONFIG_PARAVIRT
#ifdef CONFIG_X86_64
#define _LINUX_STRING_H_ 1
#define __LINUX_BITMAP_H 1
#endif
#include <linux/linkage.h>
#include <linux/screen_info.h>
#include <asm/io.h>
#include <asm/page.h>
#include <asm/boot.h>
/* WARNING!!
* This code is compiled with -fPIC and it is relocated dynamically
* at run time, but no relocation processing is performed.
* This means that it is not safe to place pointers in static structures.
*/
/*
* Getting to provable safe in place decompression is hard.
* Worst case behaviours need to be analyzed.
* Background information:
*
* The file layout is:
* magic[2]
* method[1]
* flags[1]
* timestamp[4]
* extraflags[1]
* os[1]
* compressed data blocks[N]
* crc[4] orig_len[4]
*
* resulting in 18 bytes of non compressed data overhead.
*
* Files divided into blocks
* 1 bit (last block flag)
* 2 bits (block type)
*
* 1 block occurs every 32K -1 bytes or when there 50% compression has been achieved.
* The smallest block type encoding is always used.
*
* stored:
* 32 bits length in bytes.
*
* fixed:
* magic fixed tree.
* symbols.
*
* dynamic:
* dynamic tree encoding.
* symbols.
*
*
* The buffer for decompression in place is the length of the
* uncompressed data, plus a small amount extra to keep the algorithm safe.
* The compressed data is placed at the end of the buffer. The output
* pointer is placed at the start of the buffer and the input pointer
* is placed where the compressed data starts. Problems will occur
* when the output pointer overruns the input pointer.
*
* The output pointer can only overrun the input pointer if the input
* pointer is moving faster than the output pointer. A condition only
* triggered by data whose compressed form is larger than the uncompressed
* form.
*
* The worst case at the block level is a growth of the compressed data
* of 5 bytes per 32767 bytes.
*
* The worst case internal to a compressed block is very hard to figure.
* The worst case can at least be boundined by having one bit that represents
* 32764 bytes and then all of the rest of the bytes representing the very
* very last byte.
*
* All of which is enough to compute an amount of extra data that is required
* to be safe. To avoid problems at the block level allocating 5 extra bytes
* per 32767 bytes of data is sufficient. To avoind problems internal to a block
* adding an extra 32767 bytes (the worst case uncompressed block size) is
* sufficient, to ensure that in the worst case the decompressed data for
* block will stop the byte before the compressed data for a block begins.
* To avoid problems with the compressed data's meta information an extra 18
* bytes are needed. Leading to the formula:
*
* extra_bytes = (uncompressed_size >> 12) + 32768 + 18 + decompressor_size.
*
* Adding 8 bytes per 32K is a bit excessive but much easier to calculate.
* Adding 32768 instead of 32767 just makes for round numbers.
* Adding the decompressor_size is necessary as it musht live after all
* of the data as well. Last I measured the decompressor is about 14K.
* 10K of actual data and 4K of bss.
*
*/
/*
* gzip declarations
*/
#define OF(args) args
#define STATIC static
#undef memset
#undef memcpy
#define memzero(s, n) memset ((s), 0, (n))
typedef unsigned char uch;
typedef unsigned short ush;
typedef unsigned long ulg;
#define WSIZE 0x80000000 /* Window size must be at least 32k,
* and a power of two
* We don't actually have a window just
* a huge output buffer so I report
* a 2G windows size, as that should
* always be larger than our output buffer.
*/
static uch *inbuf; /* input buffer */
static uch *window; /* Sliding window buffer, (and final output buffer) */
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 */
/* gzip flag byte */
#define ASCII_FLAG 0x01 /* bit 0 set: file probably ASCII text */
#define CONTINUATION 0x02 /* bit 1 set: continuation of multi-part gzip file */
#define EXTRA_FIELD 0x04 /* bit 2 set: extra field present */
#define ORIG_NAME 0x08 /* bit 3 set: original file name present */
#define COMMENT 0x10 /* bit 4 set: file comment present */
#define ENCRYPTED 0x20 /* bit 5 set: file is encrypted */
#define RESERVED 0xC0 /* bit 6,7: reserved */
#define get_byte() (inptr < insize ? inbuf[inptr++] : fill_inbuf())
/* Diagnostic functions */
#ifdef DEBUG
# define Assert(cond,msg) {if(!(cond)) error(msg);}
# define Trace(x) fprintf x
# define Tracev(x) {if (verbose) fprintf x ;}
# define Tracevv(x) {if (verbose>1) fprintf x ;}
# define Tracec(c,x) {if (verbose && (c)) fprintf x ;}
# define Tracecv(c,x) {if (verbose>1 && (c)) fprintf x ;}
#else
# define Assert(cond,msg)
# define Trace(x)
# define Tracev(x)
# define Tracevv(x)
# define Tracec(c,x)
# define Tracecv(c,x)
#endif
static int fill_inbuf(void);
static void flush_window(void);
static void error(char *m);
static void gzip_mark(void **);
static void gzip_release(void **);
/*
* This is set up by the setup-routine at boot-time
*/
static unsigned char *real_mode; /* Pointer to real-mode data */
#define RM_EXT_MEM_K (*(unsigned short *)(real_mode + 0x2))
#ifndef STANDARD_MEMORY_BIOS_CALL
#define RM_ALT_MEM_K (*(unsigned long *)(real_mode + 0x1e0))
#endif
#define RM_SCREEN_INFO (*(struct screen_info *)(real_mode+0))
extern unsigned char input_data[];
extern int input_len;
static long bytes_out = 0;
static void *malloc(int size);
static void free(void *where);
static void *memset(void *s, int c, unsigned n);
static void *memcpy(void *dest, const void *src, unsigned n);
static void putstr(const char *);
#ifdef CONFIG_X86_64
#define memptr long
#else
#define memptr unsigned
#endif
static memptr free_mem_ptr;
static memptr free_mem_end_ptr;
#ifdef CONFIG_X86_64
#define HEAP_SIZE 0x7000
#else
[PATCH] x86: deflate stack usage in lib/inflate.c inflate_fixed and huft_build together use around 2.7k of stack. When using 4k stacks, I saw stack overflows from interrupts arriving while unpacking the root initrd: do_IRQ: stack overflow: 384 [<c0106b64>] show_trace_log_lvl+0x1a/0x30 [<c01075e6>] show_trace+0x12/0x14 [<c010763f>] dump_stack+0x16/0x18 [<c0107ca4>] do_IRQ+0x6d/0xd9 [<c010202b>] xen_evtchn_do_upcall+0x6e/0xa2 [<c0106781>] xen_hypervisor_callback+0x25/0x2c [<c010116c>] xen_restore_fl+0x27/0x29 [<c0330f63>] _spin_unlock_irqrestore+0x4a/0x50 [<c0117aab>] change_page_attr+0x577/0x584 [<c0117b45>] kernel_map_pages+0x8d/0xb4 [<c016a314>] cache_alloc_refill+0x53f/0x632 [<c016a6c2>] __kmalloc+0xc1/0x10d [<c0463d34>] malloc+0x10/0x12 [<c04641c1>] huft_build+0x2a7/0x5fa [<c04645a5>] inflate_fixed+0x91/0x136 [<c04657e2>] unpack_to_rootfs+0x5f2/0x8c1 [<c0465acf>] populate_rootfs+0x1e/0xe4 (This was under Xen, but there's no reason it couldn't happen on bare hardware.) This patch mallocs the local variables, thereby reducing the stack usage to sane levels. Also, up the heap size for the kernel decompressor to deal with the extra allocation. Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Cc: Tim Yamin <plasmaroo@gentoo.org> Cc: Andi Kleen <ak@suse.de> Cc: Matt Mackall <mpm@selenic.com> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Richard Henderson <rth@twiddle.net> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com>
2007-05-02 17:27:15 +00:00
#define HEAP_SIZE 0x4000
#endif
static char *vidmem = (char *)0xb8000;
static int vidport;
static int lines, cols;
#ifdef CONFIG_X86_NUMAQ
void *xquad_portio;
#endif
#include "../../../../lib/inflate.c"
static void *malloc(int size)
{
void *p;
if (size <0) error("Malloc error");
if (free_mem_ptr <= 0) error("Memory error");
free_mem_ptr = (free_mem_ptr + 3) & ~3; /* Align */
p = (void *)free_mem_ptr;
free_mem_ptr += size;
if (free_mem_ptr >= free_mem_end_ptr)
error("Out of memory");
return p;
}
static void free(void *where)
{ /* Don't care */
}
static void gzip_mark(void **ptr)
{
*ptr = (void *) free_mem_ptr;
}
static void gzip_release(void **ptr)
{
free_mem_ptr = (memptr) *ptr;
}
static void scroll(void)
{
int i;
memcpy ( vidmem, vidmem + cols * 2, ( lines - 1 ) * cols * 2 );
for ( i = ( lines - 1 ) * cols * 2; i < lines * cols * 2; i += 2 )
vidmem[i] = ' ';
}
static void putstr(const char *s)
{
int x,y,pos;
char c;
#ifdef CONFIG_X86_32
if (RM_SCREEN_INFO.orig_video_mode == 0 && lines == 0 && cols == 0)
return;
#endif
x = RM_SCREEN_INFO.orig_x;
y = RM_SCREEN_INFO.orig_y;
while ( ( c = *s++ ) != '\0' ) {
if ( c == '\n' ) {
x = 0;
if ( ++y >= lines ) {
scroll();
y--;
}
} else {
vidmem [(x + cols * y) * 2] = c;
if ( ++x >= cols ) {
x = 0;
if ( ++y >= lines ) {
scroll();
y--;
}
}
}
}
RM_SCREEN_INFO.orig_x = x;
RM_SCREEN_INFO.orig_y = y;
pos = (x + cols * y) * 2; /* Update cursor position */
x86: provide a DMI based port 0x80 I/O delay override. x86: provide a DMI based port 0x80 I/O delay override. Certain (HP) laptops experience trouble from our port 0x80 I/O delay writes. This patch provides for a DMI based switch to the "alternate diagnostic port" 0xed (as used by some BIOSes as well) for these. David P. Reed confirmed that port 0xed works for him and provides a proper delay. The symptoms of _not_ working are a hanging machine, with "hwclock" use being a direct trigger. Earlier versions of this attempted to simply use udelay(2), with the 2 being a value tested to be a nicely conservative upper-bound with help from many on the linux-kernel mailinglist but that approach has two problems. First, pre-loops_per_jiffy calibration (which is post PIT init while some implementations of the PIT are actually one of the historically problematic devices that need the delay) udelay() isn't particularly well-defined. We could initialise loops_per_jiffy conservatively (and based on CPU family so as to not unduly delay old machines) which would sort of work, but... Second, delaying isn't the only effect that a write to port 0x80 has. It's also a PCI posting barrier which some devices may be explicitly or implicitly relying on. Alan Cox did a survey and found evidence that additionally some drivers may be racy on SMP without the bus locking outb. Switching to an inb() makes the timing too unpredictable and as such, this DMI based switch should be the safest approach for now. Any more invasive changes should get more rigid testing first. It's moreover only very few machines with the problem and a DMI based hack seems to fit that situation. This also introduces a command-line parameter "io_delay" to override the DMI based choice again: io_delay=<standard|alternate> where "standard" means using the standard port 0x80 and "alternate" port 0xed. This retains the udelay method as a config (CONFIG_UDELAY_IO_DELAY) and command-line ("io_delay=udelay") choice for testing purposes as well. This does not change the io_delay() in the boot code which is using the same port 0x80 I/O delay but those do not appear to be a problem as David P. Reed reported the problem was already gone after using the udelay version. He moreover reported that booting with "acpi=off" also fixed things and seeing as how ACPI isn't touched until after this DMI based I/O port switch I believe it's safe to leave the ones in the boot code be. The DMI strings from David's HP Pavilion dv9000z are in there already and we need to get/verify the DMI info from other machines with the problem, notably the HP Pavilion dv6000z. This patch is partly based on earlier patches from Pavel Machek and David P. Reed. Signed-off-by: Rene Herman <rene.herman@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-01-30 12:30:05 +00:00
outb(14, vidport);
outb(0xff & (pos >> 9), vidport+1);
outb(15, vidport);
outb(0xff & (pos >> 1), vidport+1);
}
static void* memset(void* s, int c, unsigned n)
{
int i;
char *ss = s;
for (i=0;i<n;i++) ss[i] = c;
return s;
}
static void* memcpy(void* dest, const void* src, unsigned n)
{
int i;
const char *s = src;
char *d = dest;
for (i=0;i<n;i++) d[i] = s[i];
return dest;
}
/* ===========================================================================
* Fill the input buffer. This is called only when the buffer is empty
* and at least one byte is really needed.
*/
static int fill_inbuf(void)
{
error("ran out of input data");
return 0;
}
/* ===========================================================================
* Write the output window window[0..outcnt-1] and update crc and bytes_out.
* (Used for the decompressed data only.)
*/
static void flush_window(void)
{
/* With my window equal to my output buffer
* I only need to compute the crc here.
*/
ulg c = crc; /* temporary variable */
unsigned n;
uch *in, ch;
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;
}
static void error(char *x)
{
putstr("\n\n");
putstr(x);
putstr("\n\n -- System halted");
while (1)
asm("hlt");
}
asmlinkage void decompress_kernel(void *rmode, memptr heap,
uch *input_data, unsigned long input_len,
uch *output)
{
real_mode = rmode;
if (RM_SCREEN_INFO.orig_video_mode == 7) {
vidmem = (char *) 0xb0000;
vidport = 0x3b4;
} else {
vidmem = (char *) 0xb8000;
vidport = 0x3d4;
}
lines = RM_SCREEN_INFO.orig_video_lines;
cols = RM_SCREEN_INFO.orig_video_cols;
window = output; /* Output buffer (Normally at 1M) */
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + HEAP_SIZE;
inbuf = input_data; /* Input buffer */
insize = input_len;
inptr = 0;
#ifdef CONFIG_X86_64
if ((ulg)output & (__KERNEL_ALIGN - 1))
error("Destination address not 2M aligned");
if ((ulg)output >= 0xffffffffffUL)
error("Destination address too large");
#else
if ((u32)output & (CONFIG_PHYSICAL_ALIGN -1))
error("Destination address not CONFIG_PHYSICAL_ALIGN aligned");
if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
error("Destination address too large");
#ifndef CONFIG_RELOCATABLE
if ((u32)output != LOAD_PHYSICAL_ADDR)
error("Wrong destination address");
#endif
#endif
makecrc();
putstr("\nDecompressing Linux... ");
gunzip();
putstr("done.\nBooting the kernel.\n");
return;
}