MFamd64: Add support for extended FPU states on i386. This includes

support for AVX on i386.
- Similar to amd64, move the FPU save area out of the PCB and instead
  store saved FPU state in a variable-sized buffer after the PCB on the
  stack.
- To support the variable PCB location, alter the locore code to only use
  the bottom-most page of proc0stack for init386().  init386() returns
  the correct stack pointer to locore which adjusts the stack for thread0
  before calling mi_startup().
- Don't bother setting cr3 in thread0's pcb in locore before calling
  init386().  It wasn't used (init386() overwrote it at the end) and
  it doesn't work with the variable-sized FPU save area.
- Remove the new-bus attachment from npx.  This was only ever useful for
  external co-processors using IRQ13, but those have not been supported
  for several years.  npxinit() is now called much earlier during boot
  (init386()) similar to amd64.
- Implement PT_{GET,SET}XSTATE and I386_GET_XFPUSTATE.
- npxsave() is now only called from context switch contexts so it can
  use XSAVEOPT.

Differential Revision:	https://reviews.freebsd.org/D1058
Reviewed by:	kib
Tested on:	FreeBSD/i386 VM under bhyve on Intel i5-2520

1 files changed, 14 insertions, 3 deletions

diff --git a/sys/i386/include/npx.h b/sys/i386/include/npx.h
index de55207..66f432a 100644
--- a/sys/i386/include/npx.h
+++ b/sys/i386/include/npx.h
@@ -45,17 +45,24 @@
 
 #ifdef _KERNEL
 
+struct fpu_kern_ctx;
+
 #define	PCB_USER_FPU(pcb) (((pcb)->pcb_flags & PCB_KERNNPX) == 0)
 
+#define	XSAVE_AREA_ALIGN	64
+
 int	npxdna(void);
 void	npxdrop(void);
 void	npxexit(struct thread *td);
 int	npxformat(void);
 int	npxgetregs(struct thread *td);
-void	npxinit(void);
+void	npxinit(bool bsp);
 void	npxresume(union savefpu *addr);
 void	npxsave(union savefpu *addr);
-void	npxsetregs(struct thread *td, union savefpu *addr);
+int	npxsetregs(struct thread *td, union savefpu *addr,
+	    char *xfpustate, size_t xfpustate_size);
+int	npxsetxstate(struct thread *td, char *xfpustate,
+	    size_t xfpustate_size);
 void	npxsuspend(union savefpu *addr);
 int	npxtrap_x87(void);
 int	npxtrap_sse(void);
@@ -68,8 +75,12 @@ int	fpu_kern_leave(struct thread *td, struct fpu_kern_ctx *ctx);
 int	fpu_kern_thread(u_int flags);
 int	is_fpu_kern_thread(u_int flags);
 
+union savefpu	*fpu_save_area_alloc(void);
+void	fpu_save_area_free(union savefpu *fsa);
+void	fpu_save_area_reset(union savefpu *fsa);
+
 /*
- * Flags for fpu_kern_enter() and fpu_kern_thread().
+ * Flags for fpu_kern_alloc_ctx(), fpu_kern_enter() and fpu_kern_thread().
  */
 #define	FPU_KERN_NORMAL	0x0000
 #define	FPU_KERN_NOWAIT	0x0001