It was on my TODO list for long time. Lets handle amd64 first, both for native and compat32.
I think the following should be somewhat better variant. I do leave
the fnclex there for x87.
diff --git a/sys/amd64/amd64/fpu.c b/sys/amd64/amd64/fpu.c
index a7812b7..34cf8d4 100644
--- a/sys/amd64/amd64/fpu.c
+++ b/sys/amd64/amd64/fpu.c
@@ -73,6 +73,7 @@ __FBSDID("$FreeBSD$");
#define fxrstor(addr) __asm __volatile("fxrstor %0" : : "m"
(*(addr)))
#define fxsave(addr) __asm __volatile("fxsave %0" : "=m"
(*(addr)))
#define ldmxcsr(csr) __asm __volatile("ldmxcsr %0" : : "m"
(csr))
+#define stmxcsr(addr) __asm __volatile("stmxcsr %0" : : "m"
(*(addr)))
static __inline void
xrstor(char *addr, uint64_t mask)
@@ -105,6 +106,7 @@ void fnstsw(caddr_t addr);
void fxsave(caddr_t addr);
void fxrstor(caddr_t addr);
void ldmxcsr(u_int csr);
+void stmxcsr(u_int csr);
void xrstor(char *addr, uint64_t mask);
void xsave(char *addr, uint64_t mask);
@@ -113,9 +115,6 @@ void xsave(char *addr, uint64_t mask);
#define start_emulating() load_cr0(rcr0() | CR0_TS)
#define stop_emulating() clts()
-#define GET_FPU_CW(thread) ((thread)->td_pcb->pcb_save->sv_env.en_cw)
-#define GET_FPU_SW(thread) ((thread)->td_pcb->pcb_save->sv_env.en_sw)
-
CTASSERT(sizeof(struct savefpu) == 512);
CTASSERT(sizeof(struct xstate_hdr) == 64);
CTASSERT(sizeof(struct savefpu_ymm) == 832);
@@ -514,11 +513,15 @@ static char fpetable[128] = {
};
/*
- * Preserve the FP status word, clear FP exceptions, then generate a SIGFPE.
+ * Preserve the FP status word, clear FP exceptions for x87, then
+ * generate a SIGFPE.
+ *
+ * Clearing exceptions was necessary mainly to avoid IRQ13 bugs and is
+ * engraved in our i386 ABI. We now depend on longjmp() restoring a
+ * usable state. Restoring the state or examining it might fail if we
+ * didn't clear exceptions.
*
- * Clearing exceptions is necessary mainly to avoid IRQ13 bugs. We now
- * depend on longjmp() restoring a usable state. Restoring the state
- * or examining it might fail if we didn't clear exceptions.
+ * For SSE exceptions, the exceptions are not cleared.
*
* The error code chosen will be one of the FPE_... macros. It will be
* sent as the second argument to old BSD-style signal handlers and as
@@ -531,8 +534,9 @@ static char fpetable[128] = {
* solution for signals other than SIGFPE.
*/
int
-fputrap()
+fputrap_x87(void)
{
+ struct savefpu *pcb_save;
u_short control, status;
critical_enter();
@@ -543,19 +547,43 @@ fputrap()
* wherever they are.
*/
if (PCPU_GET(fpcurthread) != curthread) {
- control = GET_FPU_CW(curthread);
- status = GET_FPU_SW(curthread);
+ pcb_save = curthread->td_pcb->pcb_save;
+ control = pcb_save->sv_env.en_cw;
+ status = pcb_save->sv_env.en_sw;
} else {
fnstcw(&control);
fnstsw(&status);
+ fnclex();
}
- if (PCPU_GET(fpcurthread) == curthread)
- fnclex();
critical_exit();
return (fpetable[status & ((~control & 0x3f) | 0x40)]);
}
+int
+fputrap_sse(void)
+{
+ u_int mxcsr;
+ u_short control, status;
+
+ critical_enter();
+
+ /*
+ * Coomparing with the x87 #MF handler, we do not clear
+ * exceptions from the mxcsr.
+ */
+ if (PCPU_GET(fpcurthread) != curthread)
+ mxcsr = curthread->td_pcb->pcb_save->sv_env.en_mxcsr;
+ else
+ stmxcsr(&mxcsr);
+
+ critical_exit();
+
+ status = mxcsr & 0x3f;
+ control = (mxcsr >> 16) & 0x3f;
+ return (fpetable[status & (~control | 0x40)]);
+}
+
/*
* Implement device not available (DNA) exception
*
diff --git a/sys/amd64/amd64/trap.c b/sys/amd64/amd64/trap.c
index 75e15e0..57d1cc2 100644
--- a/sys/amd64/amd64/trap.c
+++ b/sys/amd64/amd64/trap.c
@@ -328,7 +328,7 @@ trap(struct trapframe *frame)
break;
case T_ARITHTRAP: /* arithmetic trap */
- ucode = fputrap();
+ ucode = fputrap_x87();
if (ucode == -1)
goto userout;
i = SIGFPE;
@@ -442,7 +442,9 @@ trap(struct trapframe *frame)
break;
case T_XMMFLT: /* SIMD floating-point exception */
- ucode = 0; /* XXX */
+ ucode = fputrap_sse();
+ if (ucode == -1)
+ goto userout;
i = SIGFPE;
break;
}
diff --git a/sys/amd64/include/fpu.h b/sys/amd64/include/fpu.h
index 98a016b..7d0f0ea 100644
--- a/sys/amd64/include/fpu.h
+++ b/sys/amd64/include/fpu.h
@@ -62,7 +62,8 @@ int fpusetregs(struct thread *td, struct savefpu *addr,
char *xfpustate, size_t xfpustate_size);
int fpusetxstate(struct thread *td, char *xfpustate,
size_t xfpustate_size);
-int fputrap(void);
+int fputrap_sse(void);
+int fputrap_x87(void);
void fpuuserinited(struct thread *td);
struct fpu_kern_ctx *fpu_kern_alloc_ctx(u_int flags);
void fpu_kern_free_ctx(struct fpu_kern_ctx *ctx);
pgpAAZJB5HD5X.pgp
Description: PGP signature
