i387: re-introduce FPU state preloading at context switch time

After all the FPU state cleanups and finally finding the problem that
caused all our FPU save/restore problems, this re-introduces the
preloading of FPU state that was removed in commit b3b0870ef3ff ("i387:
do not preload FPU state at task switch time").

However, instead of simply reverting the removal, this reimplements
preloading with several fixes, most notably

 - properly abstracted as a true FPU state switch, rather than as
   open-coded save and restore with various hacks.

   In particular, implementing it as a proper FPU state switch allows us
   to optimize the CR0.TS flag accesses: there is no reason to set the
   TS bit only to then almost immediately clear it again.  CR0 accesses
   are quite slow and expensive, don't flip the bit back and forth for
   no good reason.

 - Make sure that the same model works for both x86-32 and x86-64, so
   that there are no gratuitous differences between the two due to the
   way they save and restore segment state differently due to
   architectural differences that really don't matter to the FPU state.

 - Avoid exposing the "preload" state to the context switch routines,
   and in particular allow the concept of lazy state restore: if nothing
   else has used the FPU in the meantime, and the process is still on
   the same CPU, we can avoid restoring state from memory entirely, just
   re-expose the state that is still in the FPU unit.

   That optimized lazy restore isn't actually implemented here, but the
   infrastructure is set up for it.  Of course, older CPU's that use
   'fnsave' to save the state cannot take advantage of this, since the
   state saving also trashes the state.

In other words, there is now an actual _design_ to the FPU state saving,
rather than just random historical baggage.  Hopefully it's easier to
follow as a result.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 133 insertions, 42 deletions

diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index f5376676f89c..a850b4d8d14d 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -29,6 +29,7 @@ extern unsigned int sig_xstate_size;
 extern void fpu_init(void);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
+extern void __math_state_restore(struct task_struct *);
 extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
@@ -212,9 +213,10 @@ static inline void fpu_fxsave(struct fpu *fpu)
 #endif  /* CONFIG_X86_64 */
 
 /*
- * These must be called with preempt disabled
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
  */
-static inline void fpu_save_init(struct fpu *fpu)
+static inline int fpu_save_init(struct fpu *fpu)
 {
         if (use_xsave()) {
                 fpu_xsave(fpu);
@@ -223,22 +225,33 @@ static inline void fpu_save_init(struct fpu *fpu)
                  * xsave header may indicate the init state of the FP.
                  */
                 if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-                        return;
+                        return 1;
         } else if (use_fxsr()) {
                 fpu_fxsave(fpu);
         } else {
                 asm volatile("fnsave %[fx]; fwait"
                              : [fx] "=m" (fpu->state->fsave));
-                return;
+                return 0;
         }
 
-        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES))
+        /*
+         * If exceptions are pending, we need to clear them so
+         * that we don't randomly get exceptions later.
+         *
+         * FIXME! Is this perhaps only true for the old-style
+         * irq13 case? Maybe we could leave the x87 state
+         * intact otherwise?
+         */
+        if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
                 asm volatile("fnclex");
+                return 0;
+        }
+        return 1;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline int __save_init_fpu(struct task_struct *tsk)
 {
-        fpu_save_init(&tsk->thread.fpu);
+        return fpu_save_init(&tsk->thread.fpu);
 }
 
 static inline int fpu_fxrstor_checking(struct fpu *fpu)
@@ -301,20 +314,79 @@ static inline void __thread_fpu_begin(struct task_struct *tsk)
 }
 
 /*
- * Signal frame handlers...
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
  */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+#define fpu_lazy_restore(tsk) (0)
+#define fpu_lazy_state_intact(tsk) do { } while (0)
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new)
+{
+        fpu_switch_t fpu;
+
+        fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+        if (__thread_has_fpu(old)) {
+                if (__save_init_fpu(old))
+                        fpu_lazy_state_intact(old);
+                __thread_clear_has_fpu(old);
+                old->fpu_counter++;
+
+                /* Don't change CR0.TS if we just switch! */
+                if (fpu.preload) {
+                        __thread_set_has_fpu(new);
+                        prefetch(new->thread.fpu.state);
+                } else
+                        stts();
+        } else {
+                old->fpu_counter = 0;
+                if (fpu.preload) {
+                        if (fpu_lazy_restore(new))
+                                fpu.preload = 0;
+                        else
+                                prefetch(new->thread.fpu.state);
+                        __thread_fpu_begin(new);
+                }
+        }
+        return fpu;
+}
 
-static inline void __unlazy_fpu(struct task_struct *tsk)
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
 {
-        if (__thread_has_fpu(tsk)) {
-                __save_init_fpu(tsk);
-                __thread_fpu_end(tsk);
-        } else
-                tsk->fpu_counter = 0;
+        if (fpu.preload)
+                __math_state_restore(new);
 }
 
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
 static inline void __clear_fpu(struct task_struct *tsk)
 {
         if (__thread_has_fpu(tsk)) {
@@ -474,7 +546,11 @@ static inline void save_init_fpu(struct task_struct *tsk)
 static inline void unlazy_fpu(struct task_struct *tsk)
 {
         preempt_disable();
-        __unlazy_fpu(tsk);
+        if (__thread_has_fpu(tsk)) {
+                __save_init_fpu(tsk);
+                __thread_fpu_end(tsk);
+        } else
+                tsk->fpu_counter = 0;
         preempt_enable();
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 324cd722b447..80bfe1ab0031 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -299,10 +299,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                                  *next = &next_p->thread;
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
+        fpu_switch_t fpu;
 
         /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-        __unlazy_fpu(prev_p);
+        fpu = switch_fpu_prepare(prev_p, next_p);
 
         /*
          * Reload esp0.
@@ -357,6 +358,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         if (prev->gs | next->gs)
                 lazy_load_gs(next->gs);
 
+        switch_fpu_finish(next_p, fpu);
+
         percpu_write(current_task, next_p);
 
         return prev_p;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 753e803f7197..1fd94bc4279d 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -386,8 +386,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
         int cpu = smp_processor_id();
         struct tss_struct *tss = &per_cpu(init_tss, cpu);
         unsigned fsindex, gsindex;
+        fpu_switch_t fpu;
 
-        __unlazy_fpu(prev_p);
+        fpu = switch_fpu_prepare(prev_p, next_p);
 
         /*
          * Reload esp0, LDT and the page table pointer:
@@ -457,6 +458,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
                 wrmsrl(MSR_KERNEL_GS_BASE, next->gs);
         prev->gsindex = gsindex;
 
+        switch_fpu_finish(next_p, fpu);
+
         /*
          * Switch the PDA and FPU contexts.
          */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index ad25e51f40c4..77da5b475ad2 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -571,6 +571,37 @@ asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
 }
 
 /*
+ * This gets called with the process already owning the
+ * FPU state, and with CR0.TS cleared. It just needs to
+ * restore the FPU register state.
+ */
+void __math_state_restore(struct task_struct *tsk)
+{
+        /* We need a safe address that is cheap to find and that is already
+           in L1. We've just brought in "tsk->thread.has_fpu", so use that */
+#define safe_address (tsk->thread.has_fpu)
+
+        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+           is pending.  Clear the x87 state here by setting it to fixed
+           values. safe_address is a random variable that should be in L1 */
+        alternative_input(
+                ASM_NOP8 ASM_NOP2,
+                "emms\n\t"              /* clear stack tags */
+                "fildl %P[addr]",       /* set F?P to defined value */
+                X86_FEATURE_FXSAVE_LEAK,
+                [addr] "m" (safe_address));
+
+        /*
+         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
+         */
+        if (unlikely(restore_fpu_checking(tsk))) {
+                __thread_fpu_end(tsk);
+                force_sig(SIGSEGV, tsk);
+                return;
+        }
+}
+
+/*
  * 'math_state_restore()' saves the current math information in the
  * old math state array, and gets the new ones from the current task
  *
@@ -584,10 +615,6 @@ void math_state_restore(void)
 {
         struct task_struct *tsk = current;
 
-        /* We need a safe address that is cheap to find and that is already
-           in L1. We're just bringing in "tsk->thread.has_fpu", so use that */
-#define safe_address (tsk->thread.has_fpu)
-
         if (!tsk_used_math(tsk)) {
                 local_irq_enable();
                 /*
@@ -604,25 +631,7 @@ void math_state_restore(void)
         }
 
         __thread_fpu_begin(tsk);
-
-        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-           is pending.  Clear the x87 state here by setting it to fixed
-           values. safe_address is a random variable that should be in L1 */
-        alternative_input(
-                ASM_NOP8 ASM_NOP2,
-                "emms\n\t"              /* clear stack tags */
-                "fildl %P[addr]",       /* set F?P to defined value */
-                X86_FEATURE_FXSAVE_LEAK,
-                [addr] "m" (safe_address));
-
-        /*
-         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
-         */
-        if (unlikely(restore_fpu_checking(tsk))) {
-                __thread_fpu_end(tsk);
-                force_sig(SIGSEGV, tsk);
-                return;
-        }
+        __math_state_restore(tsk);
 
         tsk->fpu_counter++;
 }