MFC 270850,271053,271192,271717:

Save and restore FPU state across suspend and resume on i386.
- Create a separate structure for per-CPU state saved across suspend and
  resume that is a superset of a pcb.
- Store the FPU state for suspend and resume in the new structure
  (for amd64, this moves it out of the PCB)
- On both i386 and amd64, all of the FPU suspend/resume handling is now
  done in C.

Approved by:	re (hrs)

5 files changed, 48 insertions, 45 deletions

diff --git a/sys/i386/i386/mp_machdep.c b/sys/i386/i386/mp_machdep.c
index 222e8e2..acc4989 100644
--- a/sys/i386/i386/mp_machdep.c
+++ b/sys/i386/i386/mp_machdep.c
@@ -147,7 +147,7 @@ void *bootstacks[MAXCPU];
 static void *dpcpu;
 
 struct pcb stoppcbs[MAXCPU];
-struct pcb **susppcbs = NULL;
+struct susppcb **susppcbs;
 
 /* Variables needed for SMP tlb shootdown. */
 vm_offset_t smp_tlb_addr1;
@@ -1523,10 +1523,12 @@ cpususpend_handler(void)
 	mtx_assert(&smp_ipi_mtx, MA_NOTOWNED);
 
 	cpu = PCPU_GET(cpuid);
-	if (savectx(susppcbs[cpu])) {
+	if (savectx(&susppcbs[cpu]->sp_pcb)) {
+		npxsuspend(&susppcbs[cpu]->sp_fpususpend);
 		wbinvd();
 		CPU_SET_ATOMIC(cpu, &suspended_cpus);
 	} else {
+		npxresume(&susppcbs[cpu]->sp_fpususpend);
 		pmap_init_pat();
 		PCPU_SET(switchtime, 0);
 		PCPU_SET(switchticks, ticks);
diff --git a/sys/i386/i386/swtch.s b/sys/i386/i386/swtch.s
index 80aa6c4..e810434 100644
--- a/sys/i386/i386/swtch.s
+++ b/sys/i386/i386/swtch.s
@@ -416,45 +416,6 @@ ENTRY(savectx)
 	sldt	PCB_LDT(%ecx)
 	str	PCB_TR(%ecx)
 
-#ifdef DEV_NPX
-	/*
-	 * If fpcurthread == NULL, then the npx h/w state is irrelevant and the
-	 * state had better already be in the pcb.  This is true for forks
-	 * but not for dumps (the old book-keeping with FP flags in the pcb
-	 * always lost for dumps because the dump pcb has 0 flags).
-	 *
-	 * If fpcurthread != NULL, then we have to save the npx h/w state to
-	 * fpcurthread's pcb and copy it to the requested pcb, or save to the
-	 * requested pcb and reload.  Copying is easier because we would
-	 * have to handle h/w bugs for reloading.  We used to lose the
-	 * parent's npx state for forks by forgetting to reload.
-	 */
-	pushfl
-	CLI
-	movl	PCPU(FPCURTHREAD),%eax
-	testl	%eax,%eax
-	je	1f
-
-	pushl	%ecx
-	movl	TD_PCB(%eax),%eax
-	movl	PCB_SAVEFPU(%eax),%eax
-	pushl	%eax
-	pushl	%eax
-	call	npxsave
-	addl	$4,%esp
-	popl	%eax
-	popl	%ecx
-
-	pushl	$PCB_SAVEFPU_SIZE
-	leal	PCB_USERFPU(%ecx),%ecx
-	pushl	%ecx
-	pushl	%eax
-	call	bcopy
-	addl	$12,%esp
-1:
-	popfl
-#endif	/* DEV_NPX */
-
 	movl	$1,%eax
 	ret
 END(savectx)
@@ -519,10 +480,6 @@ ENTRY(resumectx)
 	movl	PCB_DR7(%ecx),%eax
 	movl	%eax,%dr7
 
-#ifdef DEV_NPX
-	/* XXX FIX ME */
-#endif
-
 	/* Restore other registers */
 	movl	PCB_EDI(%ecx),%edi
 	movl	PCB_ESI(%ecx),%esi
diff --git a/sys/i386/include/npx.h b/sys/i386/include/npx.h
index 19e9b31..de55207 100644
--- a/sys/i386/include/npx.h
+++ b/sys/i386/include/npx.h
@@ -53,8 +53,10 @@ void	npxexit(struct thread *td);
 int	npxformat(void);
 int	npxgetregs(struct thread *td);
 void	npxinit(void);
+void	npxresume(union savefpu *addr);
 void	npxsave(union savefpu *addr);
 void	npxsetregs(struct thread *td, union savefpu *addr);
+void	npxsuspend(union savefpu *addr);
 int	npxtrap_x87(void);
 int	npxtrap_sse(void);
 void	npxuserinited(struct thread *);
diff --git a/sys/i386/include/pcb.h b/sys/i386/include/pcb.h
index 9cefed1..01ace72 100644
--- a/sys/i386/include/pcb.h
+++ b/sys/i386/include/pcb.h
@@ -92,6 +92,11 @@ struct pcb {
 	uint16_t	pcb_tr;
 };
 
+struct susppcb {
+	struct pcb	sp_pcb;
+	union savefpu	sp_fpususpend;
+};
+
 #ifdef _KERNEL
 struct trapframe;
 
diff --git a/sys/i386/isa/npx.c b/sys/i386/isa/npx.c
index dec7366..dd8403a 100644
--- a/sys/i386/isa/npx.c
+++ b/sys/i386/isa/npx.c
@@ -761,6 +761,43 @@ npxsave(addr)
 	PCPU_SET(fpcurthread, NULL);
 }
 
+/*
+ * Unconditionally save the current co-processor state across suspend and
+ * resume.
+ */
+void
+npxsuspend(union savefpu *addr)
+{
+	register_t cr0;
+
+	if (!hw_float)
+		return;
+	if (PCPU_GET(fpcurthread) == NULL) {
+		*addr = npx_initialstate;
+		return;
+	}
+	cr0 = rcr0();
+	clts();
+	fpusave(addr);
+	load_cr0(cr0);
+}
+
+void
+npxresume(union savefpu *addr)
+{
+	register_t cr0;
+
+	if (!hw_float)
+		return;
+
+	cr0 = rcr0();
+	clts();
+	npxinit();
+	stop_emulating();
+	fpurstor(addr);
+	load_cr0(cr0);
+}
+
 void
 npxdrop()
 {