linux/arch/x86/boot/boot.h
Kirill A. Shutemov 70f1528747 x86/mm: Fix regression with huge pages on PAE
Recent PAT patchset has caused issue on 32-bit PAE machines:

  page:eea45000 count:0 mapcount:-128 mapping:  (null) index:0x0 flags: 0x40000000()
  page dumped because: VM_BUG_ON_PAGE(page_mapcount(page) < 0)
  ------------[ cut here ]------------
  kernel BUG at /home/build/linux-boris/mm/huge_memory.c:1485!
  invalid opcode: 0000 [#1] SMP
  [...]
  Call Trace:
   unmap_single_vma
   ? __wake_up
   unmap_vmas
   unmap_region
   do_munmap
   vm_munmap
   SyS_munmap
   do_fast_syscall_32
   ? __do_page_fault
   sysenter_past_esp
  Code: ...
  EIP: [<c11bde80>] zap_huge_pmd+0x240/0x260 SS:ESP 0068:f6459d98

The problem is in pmd_pfn_mask() and pmd_flags_mask(). These
helpers use PMD_PAGE_MASK to calculate resulting mask.
PMD_PAGE_MASK is 'unsigned long', not 'unsigned long long' as
phys_addr_t is on 32-bit PAE (ARCH_PHYS_ADDR_T_64BIT). As a
result, the upper bits of resulting mask get truncated.

pud_pfn_mask() and pud_flags_mask() aren't problematic since we
don't have PUD page table level on 32-bit systems, but it's
reasonable to keep them consistent with PMD counterpart.

Introduce PHYSICAL_PMD_PAGE_MASK and PHYSICAL_PUD_PAGE_MASK in
addition to existing PHYSICAL_PAGE_MASK and reworks helpers to
use them.

Reported-and-Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
[ Fix -Woverflow warnings from the realmode code. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Toshi Kani <toshi.kani@hpe.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jürgen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: elliott@hpe.com
Cc: konrad.wilk@oracle.com
Cc: linux-mm <linux-mm@kvack.org>
Fixes: f70abb0fc3 ("x86/asm: Fix pud/pmd interfaces to handle large PAT bit")
Link: http://lkml.kernel.org/r/1448878233-11390-2-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-12-04 09:14:27 +01:00

356 lines
7.8 KiB
C

/* -*- linux-c -*- ------------------------------------------------------- *
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright 2007 rPath, Inc. - All Rights Reserved
* Copyright 2009 Intel Corporation; author H. Peter Anvin
*
* This file is part of the Linux kernel, and is made available under
* the terms of the GNU General Public License version 2.
*
* ----------------------------------------------------------------------- */
/*
* Header file for the real-mode kernel code
*/
#ifndef BOOT_BOOT_H
#define BOOT_BOOT_H
#define STACK_SIZE 512 /* Minimum number of bytes for stack */
#ifndef __ASSEMBLY__
#include <stdarg.h>
#include <linux/types.h>
#include <linux/edd.h>
#include <asm/setup.h>
#include "bitops.h"
#include "ctype.h"
#include "cpuflags.h"
/* Useful macros */
#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x)))
extern struct setup_header hdr;
extern struct boot_params boot_params;
#define cpu_relax() asm volatile("rep; nop")
/* Basic port I/O */
static inline void outb(u8 v, u16 port)
{
asm volatile("outb %0,%1" : : "a" (v), "dN" (port));
}
static inline u8 inb(u16 port)
{
u8 v;
asm volatile("inb %1,%0" : "=a" (v) : "dN" (port));
return v;
}
static inline void outw(u16 v, u16 port)
{
asm volatile("outw %0,%1" : : "a" (v), "dN" (port));
}
static inline u16 inw(u16 port)
{
u16 v;
asm volatile("inw %1,%0" : "=a" (v) : "dN" (port));
return v;
}
static inline void outl(u32 v, u16 port)
{
asm volatile("outl %0,%1" : : "a" (v), "dN" (port));
}
static inline u32 inl(u16 port)
{
u32 v;
asm volatile("inl %1,%0" : "=a" (v) : "dN" (port));
return v;
}
static inline void io_delay(void)
{
const u16 DELAY_PORT = 0x80;
asm volatile("outb %%al,%0" : : "dN" (DELAY_PORT));
}
/* These functions are used to reference data in other segments. */
static inline u16 ds(void)
{
u16 seg;
asm("movw %%ds,%0" : "=rm" (seg));
return seg;
}
static inline void set_fs(u16 seg)
{
asm volatile("movw %0,%%fs" : : "rm" (seg));
}
static inline u16 fs(void)
{
u16 seg;
asm volatile("movw %%fs,%0" : "=rm" (seg));
return seg;
}
static inline void set_gs(u16 seg)
{
asm volatile("movw %0,%%gs" : : "rm" (seg));
}
static inline u16 gs(void)
{
u16 seg;
asm volatile("movw %%gs,%0" : "=rm" (seg));
return seg;
}
typedef unsigned int addr_t;
static inline u8 rdfs8(addr_t addr)
{
u8 v;
asm volatile("movb %%fs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
return v;
}
static inline u16 rdfs16(addr_t addr)
{
u16 v;
asm volatile("movw %%fs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
return v;
}
static inline u32 rdfs32(addr_t addr)
{
u32 v;
asm volatile("movl %%fs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
return v;
}
static inline void wrfs8(u8 v, addr_t addr)
{
asm volatile("movb %1,%%fs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
}
static inline void wrfs16(u16 v, addr_t addr)
{
asm volatile("movw %1,%%fs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
}
static inline void wrfs32(u32 v, addr_t addr)
{
asm volatile("movl %1,%%fs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
}
static inline u8 rdgs8(addr_t addr)
{
u8 v;
asm volatile("movb %%gs:%1,%0" : "=q" (v) : "m" (*(u8 *)addr));
return v;
}
static inline u16 rdgs16(addr_t addr)
{
u16 v;
asm volatile("movw %%gs:%1,%0" : "=r" (v) : "m" (*(u16 *)addr));
return v;
}
static inline u32 rdgs32(addr_t addr)
{
u32 v;
asm volatile("movl %%gs:%1,%0" : "=r" (v) : "m" (*(u32 *)addr));
return v;
}
static inline void wrgs8(u8 v, addr_t addr)
{
asm volatile("movb %1,%%gs:%0" : "+m" (*(u8 *)addr) : "qi" (v));
}
static inline void wrgs16(u16 v, addr_t addr)
{
asm volatile("movw %1,%%gs:%0" : "+m" (*(u16 *)addr) : "ri" (v));
}
static inline void wrgs32(u32 v, addr_t addr)
{
asm volatile("movl %1,%%gs:%0" : "+m" (*(u32 *)addr) : "ri" (v));
}
/* Note: these only return true/false, not a signed return value! */
static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
{
u8 diff;
asm volatile("fs; repe; cmpsb; setnz %0"
: "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
{
u8 diff;
asm volatile("gs; repe; cmpsb; setnz %0"
: "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
/* Heap -- available for dynamic lists. */
extern char _end[];
extern char *HEAP;
extern char *heap_end;
#define RESET_HEAP() ((void *)( HEAP = _end ))
static inline char *__get_heap(size_t s, size_t a, size_t n)
{
char *tmp;
HEAP = (char *)(((size_t)HEAP+(a-1)) & ~(a-1));
tmp = HEAP;
HEAP += s*n;
return tmp;
}
#define GET_HEAP(type, n) \
((type *)__get_heap(sizeof(type),__alignof__(type),(n)))
static inline bool heap_free(size_t n)
{
return (int)(heap_end-HEAP) >= (int)n;
}
/* copy.S */
void copy_to_fs(addr_t dst, void *src, size_t len);
void *copy_from_fs(void *dst, addr_t src, size_t len);
void copy_to_gs(addr_t dst, void *src, size_t len);
void *copy_from_gs(void *dst, addr_t src, size_t len);
/* a20.c */
int enable_a20(void);
/* apm.c */
int query_apm_bios(void);
/* bioscall.c */
struct biosregs {
union {
struct {
u32 edi;
u32 esi;
u32 ebp;
u32 _esp;
u32 ebx;
u32 edx;
u32 ecx;
u32 eax;
u32 _fsgs;
u32 _dses;
u32 eflags;
};
struct {
u16 di, hdi;
u16 si, hsi;
u16 bp, hbp;
u16 _sp, _hsp;
u16 bx, hbx;
u16 dx, hdx;
u16 cx, hcx;
u16 ax, hax;
u16 gs, fs;
u16 es, ds;
u16 flags, hflags;
};
struct {
u8 dil, dih, edi2, edi3;
u8 sil, sih, esi2, esi3;
u8 bpl, bph, ebp2, ebp3;
u8 _spl, _sph, _esp2, _esp3;
u8 bl, bh, ebx2, ebx3;
u8 dl, dh, edx2, edx3;
u8 cl, ch, ecx2, ecx3;
u8 al, ah, eax2, eax3;
};
};
};
void intcall(u8 int_no, const struct biosregs *ireg, struct biosregs *oreg);
/* cmdline.c */
int __cmdline_find_option(unsigned long cmdline_ptr, const char *option, char *buffer, int bufsize);
int __cmdline_find_option_bool(unsigned long cmdline_ptr, const char *option);
static inline int cmdline_find_option(const char *option, char *buffer, int bufsize)
{
unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
if (cmd_line_ptr >= 0x100000)
return -1; /* inaccessible */
return __cmdline_find_option(cmd_line_ptr, option, buffer, bufsize);
}
static inline int cmdline_find_option_bool(const char *option)
{
unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
if (cmd_line_ptr >= 0x100000)
return -1; /* inaccessible */
return __cmdline_find_option_bool(cmd_line_ptr, option);
}
/* cpu.c, cpucheck.c */
int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
int validate_cpu(void);
/* early_serial_console.c */
extern int early_serial_base;
void console_init(void);
/* edd.c */
void query_edd(void);
/* header.S */
void __attribute__((noreturn)) die(void);
/* memory.c */
int detect_memory(void);
/* pm.c */
void __attribute__((noreturn)) go_to_protected_mode(void);
/* pmjump.S */
void __attribute__((noreturn))
protected_mode_jump(u32 entrypoint, u32 bootparams);
/* printf.c */
int sprintf(char *buf, const char *fmt, ...);
int vsprintf(char *buf, const char *fmt, va_list args);
int printf(const char *fmt, ...);
/* regs.c */
void initregs(struct biosregs *regs);
/* string.c */
int strcmp(const char *str1, const char *str2);
int strncmp(const char *cs, const char *ct, size_t count);
size_t strnlen(const char *s, size_t maxlen);
unsigned int atou(const char *s);
unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
size_t strlen(const char *s);
/* tty.c */
void puts(const char *);
void putchar(int);
int getchar(void);
void kbd_flush(void);
int getchar_timeout(void);
/* video.c */
void set_video(void);
/* video-mode.c */
int set_mode(u16 mode);
int mode_defined(u16 mode);
void probe_cards(int unsafe);
/* video-vesa.c */
void vesa_store_edid(void);
#endif /* __ASSEMBLY__ */
#endif /* BOOT_BOOT_H */