diff options
author | Ingo Molnar <mingo@kernel.org> | 2015-04-27 04:19:39 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@kernel.org> | 2015-05-19 15:47:49 +0200 |
commit | 7366ed771f6ed95e4c4525c335722888a83b4b6c (patch) | |
tree | 2afedca718ddad00b90102f6cdd427797459c1e5 /arch/x86/kernel/fpu/core.c | |
parent | 1bc6b056d8f90f0a710ff1201964c1fffc9ddd3c (diff) | |
download | linux-stable-7366ed771f6ed95e4c4525c335722888a83b4b6c.tar.gz linux-stable-7366ed771f6ed95e4c4525c335722888a83b4b6c.tar.bz2 linux-stable-7366ed771f6ed95e4c4525c335722888a83b4b6c.zip |
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>
Diffstat (limited to 'arch/x86/kernel/fpu/core.c')
-rw-r--r-- | arch/x86/kernel/fpu/core.c | 52 |
1 files changed, 20 insertions, 32 deletions
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index ca88608a62a5..1697a9a34ff0 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -174,9 +174,9 @@ static void __save_fpu(struct fpu *fpu) { if (use_xsave()) { if (unlikely(system_state == SYSTEM_BOOTING)) - xsave_state_booting(&fpu->state->xsave); + xsave_state_booting(&fpu->state.xsave); else - xsave_state(&fpu->state->xsave); + xsave_state(&fpu->state.xsave); } else { fpu_fxsave(fpu); } @@ -207,16 +207,16 @@ EXPORT_SYMBOL_GPL(fpu__save); void fpstate_init(struct fpu *fpu) { if (!cpu_has_fpu) { - finit_soft_fpu(&fpu->state->soft); + finit_soft_fpu(&fpu->state.soft); return; } - memset(fpu->state, 0, xstate_size); + memset(&fpu->state, 0, xstate_size); if (cpu_has_fxsr) { - fx_finit(&fpu->state->fxsave); + fx_finit(&fpu->state.fxsave); } else { - struct i387_fsave_struct *fp = &fpu->state->fsave; + struct i387_fsave_struct *fp = &fpu->state.fsave; fp->cwd = 0xffff037fu; fp->swd = 0xffff0000u; fp->twd = 0xffffffffu; @@ -241,15 +241,8 @@ void fpstate_cache_init(void) int fpstate_alloc(struct fpu *fpu) { - if (fpu->state) - return 0; - - fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL); - if (!fpu->state) - return -ENOMEM; - /* The CPU requires the FPU state to be aligned to 16 byte boundaries: */ - WARN_ON((unsigned long)fpu->state & 15); + WARN_ON((unsigned long)&fpu->state & 15); return 0; } @@ -257,10 +250,6 @@ EXPORT_SYMBOL_GPL(fpstate_alloc); void fpstate_free(struct fpu *fpu) { - if (fpu->state) { - kmem_cache_free(task_xstate_cachep, fpu->state); - fpu->state = NULL; - } } EXPORT_SYMBOL_GPL(fpstate_free); @@ -277,11 +266,11 @@ static void fpu_copy(struct fpu *dst_fpu, struct fpu *src_fpu) WARN_ON(src_fpu != ¤t->thread.fpu); if (use_eager_fpu()) { - memset(&dst_fpu->state->xsave, 0, xstate_size); + memset(&dst_fpu->state.xsave, 0, xstate_size); __save_fpu(dst_fpu); } else { fpu__save(src_fpu); - memcpy(dst_fpu->state, src_fpu->state, xstate_size); + memcpy(&dst_fpu->state, &src_fpu->state, xstate_size); } } @@ -289,7 +278,6 @@ int fpu__copy(struct fpu *dst_fpu, struct fpu *src_fpu) { dst_fpu->counter = 0; dst_fpu->fpregs_active = 0; - dst_fpu->state = NULL; dst_fpu->last_cpu = -1; if (src_fpu->fpstate_active) { @@ -483,7 +471,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset, sanitize_i387_state(target); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &fpu->state->fxsave, 0, -1); + &fpu->state.fxsave, 0, -1); } int xfpregs_set(struct task_struct *target, const struct user_regset *regset, @@ -503,19 +491,19 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, sanitize_i387_state(target); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpu->state->fxsave, 0, -1); + &fpu->state.fxsave, 0, -1); /* * mxcsr reserved bits must be masked to zero for security reasons. */ - fpu->state->fxsave.mxcsr &= mxcsr_feature_mask; + fpu->state.fxsave.mxcsr &= mxcsr_feature_mask; /* * update the header bits in the xsave header, indicating the * presence of FP and SSE state. */ if (cpu_has_xsave) - fpu->state->xsave.header.xfeatures |= XSTATE_FPSSE; + fpu->state.xsave.header.xfeatures |= XSTATE_FPSSE; return ret; } @@ -535,7 +523,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - xsave = &fpu->state->xsave; + xsave = &fpu->state.xsave; /* * Copy the 48bytes defined by the software first into the xstate @@ -566,7 +554,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - xsave = &fpu->state->xsave; + xsave = &fpu->state.xsave; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, xsave, 0, -1); /* @@ -657,7 +645,7 @@ static inline u32 twd_fxsr_to_i387(struct i387_fxsave_struct *fxsave) void convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk) { - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state.fxsave; struct _fpreg *to = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *from = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -695,7 +683,7 @@ void convert_to_fxsr(struct task_struct *tsk, const struct user_i387_ia32_struct *env) { - struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state->fxsave; + struct i387_fxsave_struct *fxsave = &tsk->thread.fpu.state.fxsave; struct _fpreg *from = (struct _fpreg *) &env->st_space[0]; struct _fpxreg *to = (struct _fpxreg *) &fxsave->st_space[0]; int i; @@ -736,7 +724,7 @@ int fpregs_get(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &fpu->state->fsave, 0, + &fpu->state.fsave, 0, -1); sanitize_i387_state(target); @@ -770,7 +758,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (!cpu_has_fxsr) return user_regset_copyin(&pos, &count, &kbuf, &ubuf, - &fpu->state->fsave, 0, + &fpu->state.fsave, 0, -1); if (pos > 0 || count < sizeof(env)) @@ -785,7 +773,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, * presence of FP. */ if (cpu_has_xsave) - fpu->state->xsave.header.xfeatures |= XSTATE_FP; + fpu->state.xsave.header.xfeatures |= XSTATE_FP; return ret; } |