alistair23-linux/arch/x86/math-emu/fpu_system.h

102 lines
3.8 KiB
C
Raw Normal View History

/*---------------------------------------------------------------------------+
| fpu_system.h |
| |
| Copyright (C) 1992,1994,1997 |
| W. Metzenthen, 22 Parker St, Ormond, Vic 3163, |
| Australia. E-mail billm@suburbia.net |
| |
+---------------------------------------------------------------------------*/
#ifndef _FPU_SYSTEM_H
#define _FPU_SYSTEM_H
/* system dependent definitions */
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
{
static struct desc_struct zero_desc;
struct desc_struct ret = zero_desc;
#ifdef CONFIG_MODIFY_LDT_SYSCALL
seg >>= 3;
mutex_lock(&current->mm->context.lock);
if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
ret = current->mm->context.ldt->entries[seg];
mutex_unlock(&current->mm->context.lock);
#endif
return ret;
}
#define SEG_D_SIZE(x) ((x).b & (3 << 21))
#define SEG_G_BIT(x) ((x).b & (1 << 23))
#define SEG_GRANULARITY(x) (((x).b & (1 << 23)) ? 4096 : 1)
#define SEG_286_MODE(x) ((x).b & ( 0xff000000 | 0xf0000 | (1 << 23)))
#define SEG_BASE_ADDR(s) (((s).b & 0xff000000) \
| (((s).b & 0xff) << 16) | ((s).a >> 16))
#define SEG_LIMIT(s) (((s).b & 0xff0000) | ((s).a & 0xffff))
#define SEG_EXECUTE_ONLY(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 11))
#define SEG_WRITE_PERM(s) (((s).b & ((1 << 11) | (1 << 9))) == (1 << 9))
#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \
== (1 << 10))
x86/fpu: Simplify FPU handling by embedding the fpstate in task_struct (again) So 6 years ago we made the FPU fpstate dynamically allocated: aa283f49276e ("x86, fpu: lazy allocation of FPU area - v5") 61c4628b5386 ("x86, fpu: split FPU state from task struct - v5") In hindsight this was a mistake: - it complicated context allocation failure handling, such as: /* kthread execs. TODO: cleanup this horror. */ if (WARN_ON(fpstate_alloc_init(fpu))) force_sig(SIGKILL, tsk); - it caused us to enable irqs in fpu__restore(): local_irq_enable(); /* * does a slab alloc which can sleep */ if (fpstate_alloc_init(fpu)) { /* * ran out of memory! */ do_group_exit(SIGKILL); return; } local_irq_disable(); - it (slightly) slowed down task creation/destruction by adding slab allocation/free pattens. - it made access to context contents (slightly) slower by adding one more pointer dereference. The motivation for the dynamic allocation was two-fold: - reduce memory consumption by non-FPU tasks - allocate and handle only the necessary amount of context for various XSAVE processors that have varying hardware frame sizes. These days, with glibc using SSE memcpy by default and GCC optimizing for SSE/AVX by default, the scope of FPU using apps on an x86 system is much larger than it was 6 years ago. For example on a freshly installed Fedora 21 desktop system, with a recent kernel, all non-kthread tasks have used the FPU shortly after bootup. Also, even modern embedded x86 CPUs try to support the latest vector instruction set - so they'll too often use the larger xstate frame sizes. So remove the dynamic allocation complication by embedding the FPU fpstate in task_struct again. This should make the FPU a lot more accessible to all sorts of atomic contexts. We could still optimize for the xstate frame size in the future, by moving the state structure to the last element of task_struct, and allocating only a part of that. This change is kept minimal by still keeping the ctx_alloc()/free() routines (that now do nothing substantial) - we'll remove them in the following patches. Reviewed-by: Borislav Petkov <bp@alien8.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-04-26 20:19:39 -06:00
#define I387 (&current->thread.fpu.state)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
#define FPU_SS (*(unsigned short *) &(FPU_info->regs->ss))
#define FPU_DS (*(unsigned short *) &(FPU_info->regs->ds))
#define FPU_EAX (FPU_info->regs->ax)
#define FPU_EFLAGS (FPU_info->regs->flags)
#define FPU_EIP (FPU_info->regs->ip)
#define FPU_ORIG_EIP (FPU_info->___orig_eip)
#define FPU_lookahead (I387->soft.lookahead)
/* nz if ip_offset and cs_selector are not to be set for the current
instruction. */
#define no_ip_update (*(u_char *)&(I387->soft.no_update))
#define FPU_rm (*(u_char *)&(I387->soft.rm))
/* Number of bytes of data which can be legally accessed by the current
instruction. This only needs to hold a number <= 108, so a byte will do. */
#define access_limit (*(u_char *)&(I387->soft.alimit))
#define partial_status (I387->soft.swd)
#define control_word (I387->soft.cwd)
#define fpu_tag_word (I387->soft.twd)
#define registers (I387->soft.st_space)
#define top (I387->soft.ftop)
#define instruction_address (*(struct address *)&I387->soft.fip)
#define operand_address (*(struct address *)&I387->soft.foo)
#define FPU_access_ok(x,y,z) if ( !access_ok(x,y,z) ) \
math_abort(FPU_info,SIGSEGV)
#define FPU_abort math_abort(FPU_info, SIGSEGV)
#undef FPU_IGNORE_CODE_SEGV
#ifdef FPU_IGNORE_CODE_SEGV
/* access_ok() is very expensive, and causes the emulator to run
about 20% slower if applied to the code. Anyway, errors due to bad
code addresses should be much rarer than errors due to bad data
addresses. */
#define FPU_code_access_ok(z)
#else
/* A simpler test than access_ok() can probably be done for
FPU_code_access_ok() because the only possible error is to step
past the upper boundary of a legal code area. */
#define FPU_code_access_ok(z) FPU_access_ok(VERIFY_READ,(void __user *)FPU_EIP,z)
#endif
#define FPU_get_user(x,y) get_user((x),(y))
#define FPU_put_user(x,y) put_user((x),(y))
#endif