aboutsummaryrefslogtreecommitdiffstats
path: root/include/asm-sparc/sfp-machine.h
diff options
context:
space:
mode:
authorDavid S. Miller <davem@sunset.davemloft.net>2007-08-17 01:59:49 -0400
committerDavid S. Miller <davem@sunset.davemloft.net>2007-08-17 01:59:49 -0400
commit405849610fd96b4f34cd1875c4c033228fea6c0f (patch)
treea1438b7059f39f923d8b21337c0b242ef76f6059 /include/asm-sparc/sfp-machine.h
parent8b224b813aad0231af62dc75d056aae83c9d4d12 (diff)
[MATH-EMU]: Fix underflow exception reporting.
The underflow exception cases were wrong. This is one weird area of ieee1754 handling in that the underflow behavior changes based upon whether underflow is enabled in the trap enable mask of the FPU control register. As a specific case the Sparc V9 manual gives us the following description: -------------------- If UFM = 0: Underflow occurs if a nonzero result is tiny and a loss of accuracy occurs. Tininess may be detected before or after rounding. Loss of accuracy may be either a denormalization loss or an inexact result. If UFM = 1: Underflow occurs if a nonzero result is tiny. Tininess may be detected before or after rounding. -------------------- What this amounts to in the packing case is if we go subnormal, we set underflow if any of the following are true: 1) rounding sets inexact 2) we ended up rounding back up to normal (this is the case where we set the exponent to 1 and set the fraction to zero), this should set inexact too 3) underflow is set in FPU control register trap-enable mask The initially discovered example was "DBL_MIN / 16.0" which incorrectly generated an underflow. It should not, unless underflow is set in the trap-enable mask of the FPU csr. Another example, "0x0.0000000000001p-1022 / 16.0", should signal both inexact and underflow. The cpu implementations and ieee1754 literature is very clear about this. This is case #2 above. However, if underflow is set in the trap enable mask, only underflow should be set and reported as a trap. That is handled properly by the prioritization logic in arch/sparc{,64}/math-emu/math.c:record_exception(). Based upon a report and test case from Jakub Jelinek. Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/asm-sparc/sfp-machine.h')
-rw-r--r--include/asm-sparc/sfp-machine.h6
1 files changed, 6 insertions, 0 deletions
diff --git a/include/asm-sparc/sfp-machine.h b/include/asm-sparc/sfp-machine.h
index ecfc86a4a725..266a42b8f99f 100644
--- a/include/asm-sparc/sfp-machine.h
+++ b/include/asm-sparc/sfp-machine.h
@@ -203,4 +203,10 @@ extern struct task_struct *last_task_used_math;
203#define FP_INHIBIT_RESULTS ((last_task_used_math->thread.fsr >> 23) & _fex) 203#define FP_INHIBIT_RESULTS ((last_task_used_math->thread.fsr >> 23) & _fex)
204#endif 204#endif
205 205
206#ifdef CONFIG_SMP
207#define FP_TRAPPING_EXCEPTIONS ((current->thread.fsr >> 23) & 0x1f)
208#else
209#define FP_TRAPPING_EXCEPTIONS ((last_task_used_math->thread.fsr >> 23) & 0x1f)
210#endif
211
206#endif 212#endif