linux_dsm_epyc7002/arch/x86/include/asm/setup.h
H. Peter Anvin 3891a04aaf x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack
The IRET instruction, when returning to a 16-bit segment, only
restores the bottom 16 bits of the user space stack pointer.  This
causes some 16-bit software to break, but it also leaks kernel state
to user space.  We have a software workaround for that ("espfix") for
the 32-bit kernel, but it relies on a nonzero stack segment base which
is not available in 64-bit mode.

In checkin:

    b3b42ac2cb x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels

we "solved" this by forbidding 16-bit segments on 64-bit kernels, with
the logic that 16-bit support is crippled on 64-bit kernels anyway (no
V86 support), but it turns out that people are doing stuff like
running old Win16 binaries under Wine and expect it to work.

This works around this by creating percpu "ministacks", each of which
is mapped 2^16 times 64K apart.  When we detect that the return SS is
on the LDT, we copy the IRET frame to the ministack and use the
relevant alias to return to userspace.  The ministacks are mapped
readonly, so if IRET faults we promote #GP to #DF which is an IST
vector and thus has its own stack; we then do the fixup in the #DF
handler.

(Making #GP an IST exception would make the msr_safe functions unsafe
in NMI/MC context, and quite possibly have other effects.)

Special thanks to:

- Andy Lutomirski, for the suggestion of using very small stack slots
  and copy (as opposed to map) the IRET frame there, and for the
  suggestion to mark them readonly and let the fault promote to #DF.
- Konrad Wilk for paravirt fixup and testing.
- Borislav Petkov for testing help and useful comments.

Reported-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Lutomriski <amluto@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dirk Hohndel <dirk@hohndel.org>
Cc: Arjan van de Ven <arjan.van.de.ven@intel.com>
Cc: comex <comexk@gmail.com>
Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: <stable@vger.kernel.org> # consider after upstream merge
2014-04-30 14:14:28 -07:00

128 lines
3.2 KiB
C

#ifndef _ASM_X86_SETUP_H
#define _ASM_X86_SETUP_H
#include <uapi/asm/setup.h>
#define COMMAND_LINE_SIZE 2048
#include <linux/linkage.h>
#ifdef __i386__
#include <linux/pfn.h>
/*
* Reserved space for vmalloc and iomap - defined in asm/page.h
*/
#define MAXMEM_PFN PFN_DOWN(MAXMEM)
#define MAX_NONPAE_PFN (1 << 20)
#endif /* __i386__ */
#define PARAM_SIZE 4096 /* sizeof(struct boot_params) */
#define OLD_CL_MAGIC 0xA33F
#define OLD_CL_ADDRESS 0x020 /* Relative to real mode data */
#define NEW_CL_POINTER 0x228 /* Relative to real mode data */
#ifndef __ASSEMBLY__
#include <asm/bootparam.h>
#include <asm/x86_init.h>
extern u64 relocated_ramdisk;
/* Interrupt control for vSMPowered x86_64 systems */
#ifdef CONFIG_X86_64
void vsmp_init(void);
#else
static inline void vsmp_init(void) { }
#endif
void setup_bios_corruption_check(void);
extern unsigned long saved_video_mode;
extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
extern void setup_default_timer_irq(void);
#ifdef CONFIG_X86_INTEL_MID
extern void x86_intel_mid_early_setup(void);
#else
static inline void x86_intel_mid_early_setup(void) { }
#endif
#ifdef CONFIG_X86_INTEL_CE
extern void x86_ce4100_early_setup(void);
#else
static inline void x86_ce4100_early_setup(void) { }
#endif
extern void init_espfix_bsp(void);
extern void init_espfix_ap(void);
#ifndef _SETUP
/*
* This is set up by the setup-routine at boot-time
*/
extern struct boot_params boot_params;
/*
* Do NOT EVER look at the BIOS memory size location.
* It does not work on many machines.
*/
#define LOWMEMSIZE() (0x9f000)
/* exceedingly early brk-like allocator */
extern unsigned long _brk_end;
void *extend_brk(size_t size, size_t align);
/*
* Reserve space in the brk section. The name must be unique within
* the file, and somewhat descriptive. The size is in bytes. Must be
* used at file scope.
*
* (This uses a temp function to wrap the asm so we can pass it the
* size parameter; otherwise we wouldn't be able to. We can't use a
* "section" attribute on a normal variable because it always ends up
* being @progbits, which ends up allocating space in the vmlinux
* executable.)
*/
#define RESERVE_BRK(name,sz) \
static void __section(.discard.text) __used notrace \
__brk_reservation_fn_##name##__(void) { \
asm volatile ( \
".pushsection .brk_reservation,\"aw\",@nobits;" \
".brk." #name ":" \
" 1:.skip %c0;" \
" .size .brk." #name ", . - 1b;" \
" .popsection" \
: : "i" (sz)); \
}
/* Helper for reserving space for arrays of things */
#define RESERVE_BRK_ARRAY(type, name, entries) \
type *name; \
RESERVE_BRK(name, sizeof(type) * entries)
extern void probe_roms(void);
#ifdef __i386__
asmlinkage void __init i386_start_kernel(void);
#else
asmlinkage void __init x86_64_start_kernel(char *real_mode);
asmlinkage void __init x86_64_start_reservations(char *real_mode_data);
#endif /* __i386__ */
#endif /* _SETUP */
#else
#define RESERVE_BRK(name,sz) \
.pushsection .brk_reservation,"aw",@nobits; \
.brk.name: \
1: .skip sz; \
.size .brk.name,.-1b; \
.popsection
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_SETUP_H */