Add support for the extended FPU states on amd64, both for native

64bit and 32bit ABIs.  As a side-effect, it enables AVX on capable
CPUs.

In particular:

- Query the CPU support for XSAVE, list of the supported extensions
  and the required size of FPU save area. The hw.use_xsave tunable is
  provided for disabling XSAVE, and hw.xsave_mask may be used to
  select the enabled extensions.

- Remove the FPU save area from PCB and dynamically allocate the
  (run-time sized) user save area on the top of the kernel stack,
  right above the PCB. Reorganize the thread0 PCB initialization to
  postpone it after BSP is queried for save area size.

- The dumppcb, stoppcbs and susppcbs now do not carry the FPU state as
  well. FPU state is only useful for suspend, where it is saved in
  dynamically allocated suspfpusave area.

- Use XSAVE and XRSTOR to save/restore FPU state, if supported and
  enabled.

- Define new mcontext_t flag _MC_HASFPXSTATE, indicating that
  mcontext_t has a valid pointer to out-of-struct extended FPU
  state. Signal handlers are supplied with stack-allocated fpu
  state. The sigreturn(2) and setcontext(2) syscall honour the flag,
  allowing the signal handlers to inspect and manipilate extended
  state in the interrupted context.

- The getcontext(2) never returns extended state, since there is no
  place in the fixed-sized mcontext_t to place variable-sized save
  area. And, since mcontext_t is embedded into ucontext_t, makes it
  impossible to fix in a reasonable way.  Instead of extending
  getcontext(2) syscall, provide a sysarch(2) facility to query
  extended FPU state.

- Add ptrace(2) support for getting and setting extended state; while
  there, implement missed PT_I386_{GET,SET}XMMREGS for 32bit binaries.

- Change fpu_kern KPI to not expose struct fpu_kern_ctx layout to
  consumers, making it opaque. Internally, struct fpu_kern_ctx now
  contains a space for the extended state. Convert in-kernel consumers
  of fpu_kern KPI both on i386 and amd64.

First version of the support for AVX was submitted by Tim Bird
<tim.bird am sony com> on behalf of Sony. This version was written
from scratch.

Tested by:	pho (previous version), Yamagi Burmeister <lists yamagi org>
MFC after:	1 month

1 files changed, 45 insertions, 1 deletions

diff --git a/sys/i386/isa/npx.c b/sys/i386/isa/npx.c
index f314e44..0da580f 100644
--- a/sys/i386/isa/npx.c
+++ b/sys/i386/isa/npx.c
@@ -985,6 +985,50 @@ DRIVER_MODULE(npxisa, acpi, npxisa_driver, npxisa_devclass, 0, 0);
 #endif
 #endif /* DEV_ISA */
 
+static MALLOC_DEFINE(M_FPUKERN_CTX, "fpukern_ctx",
+    "Kernel contexts for FPU state");
+
+#define	XSAVE_AREA_ALIGN	64
+
+#define	FPU_KERN_CTX_NPXINITDONE 0x01
+
+struct fpu_kern_ctx {
+	union savefpu *prev;
+	uint32_t flags;
+	char hwstate1[];
+};
+
+struct fpu_kern_ctx *
+fpu_kern_alloc_ctx(u_int flags)
+{
+	struct fpu_kern_ctx *res;
+	size_t sz;
+
+	sz = sizeof(struct fpu_kern_ctx) + XSAVE_AREA_ALIGN +
+	    sizeof(union savefpu);
+	res = malloc(sz, M_FPUKERN_CTX, ((flags & FPU_KERN_NOWAIT) ?
+	    M_NOWAIT : M_WAITOK) | M_ZERO);
+	return (res);
+}
+
+void
+fpu_kern_free_ctx(struct fpu_kern_ctx *ctx)
+{
+
+	/* XXXKIB clear the memory ? */
+	free(ctx, M_FPUKERN_CTX);
+}
+
+static union savefpu *
+fpu_kern_ctx_savefpu(struct fpu_kern_ctx *ctx)
+{
+	vm_offset_t p;
+
+	p = (vm_offset_t)&ctx->hwstate1;
+	p = roundup2(p, XSAVE_AREA_ALIGN);
+	return ((union savefpu *)p);
+}
+
 int
 fpu_kern_enter(struct thread *td, struct fpu_kern_ctx *ctx, u_int flags)
 {
@@ -998,7 +1042,7 @@ fpu_kern_enter(struct thread *td, struct fpu_kern_ctx *ctx, u_int flags)
 		ctx->flags |= FPU_KERN_CTX_NPXINITDONE;
 	npxexit(td);
 	ctx->prev = pcb->pcb_save;
-	pcb->pcb_save = &ctx->hwstate;
+	pcb->pcb_save = fpu_kern_ctx_savefpu(ctx);
 	pcb->pcb_flags |= PCB_KERNNPX;
 	pcb->pcb_flags &= ~PCB_NPXINITDONE;
 	return (0);