summaryrefslogtreecommitdiff
path: root/arch/x86/math-emu
diff options
context:
space:
mode:
authorIngo Molnar <mingo@kernel.org>2015-04-27 04:19:39 +0200
committerIngo Molnar <mingo@kernel.org>2015-05-19 15:47:49 +0200
commit7366ed771f6ed95e4c4525c335722888a83b4b6c (patch)
tree2afedca718ddad00b90102f6cdd427797459c1e5 /arch/x86/math-emu
parent1bc6b056d8f90f0a710ff1201964c1fffc9ddd3c (diff)
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/math-emu')
-rw-r--r--arch/x86/math-emu/fpu_aux.c2
-rw-r--r--arch/x86/math-emu/fpu_entry.c4
-rw-r--r--arch/x86/math-emu/fpu_system.h2
3 files changed, 4 insertions, 4 deletions
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index dc8adad10a2f..7562341ce299 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -52,7 +52,7 @@ void finit_soft_fpu(struct i387_soft_struct *soft)
void finit(void)
{
- finit_soft_fpu(&current->thread.fpu.state->soft);
+ finit_soft_fpu(&current->thread.fpu.state.soft);
}
/*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index cf843855e4f6..5e003704ebfa 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -683,7 +683,7 @@ int fpregs_soft_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct i387_soft_struct *s387 = &target->thread.fpu.state.soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
@@ -735,7 +735,7 @@ int fpregs_soft_get(struct task_struct *target,
unsigned int pos, unsigned int count,
void *kbuf, void __user *ubuf)
{
- struct i387_soft_struct *s387 = &target->thread.fpu.state->soft;
+ struct i387_soft_struct *s387 = &target->thread.fpu.state.soft;
const void *space = s387->st_space;
int ret;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 2c614410a5f3..9ccecb61a4fa 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -31,7 +31,7 @@
#define SEG_EXPAND_DOWN(s) (((s).b & ((1 << 11) | (1 << 10))) \
== (1 << 10))
-#define I387 (current->thread.fpu.state)
+#define I387 (&current->thread.fpu.state)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))