Date: Tue, 07 Mar 2017 13:21:24 +0000 From: bugzilla-noreply@freebsd.org To: freebsd-arm@FreeBSD.org Subject: [Bug 217611] ARM VFP/NEON regs not preserved in signal delivery Message-ID: <bug-217611-7@https.bugs.freebsd.org/bugzilla/>
next in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D217611 Bug ID: 217611 Summary: ARM VFP/NEON regs not preserved in signal delivery Product: Base System Version: 11.0-STABLE Hardware: arm OS: Any Status: New Severity: Affects Many People Priority: --- Component: arm Assignee: freebsd-arm@FreeBSD.org Reporter: andrew@tao11.riddles.org.uk Created attachment 180600 --> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=3D180600&action= =3Dedit FP registers vs. signals Signal delivery to process is not saving/restoring the VFP/NEON registers. I found this on stable/11, but it also exists on CURRENT. I tested on an RP= I2 but the problem clearly exists on other ARM platforms. The bug is obvious by inspection, but I attach an example test program. (If= you try this on a much faster platform than cortex-a7 @900MHz, make sure you increase the loop count to ensure runtime exceeds 1 second.) cc fptst.c -o fptst ./fptst entering... h0: actual=3D10000000.000000 expected=3D10000000.000000 h1: actual=3D10000001.000000 expected=3D10000001.000000 h2: actual=3D10000002.000000 expected=3D10000002.000000 h3: actual=3D10000003.000000 expected=3D10000003.000000 h4: actual=3D10000004.000000 expected=3D10000004.000000 h5: actual=3D10000005.000000 expected=3D10000005.000000 h6: actual=3D10000006.000000 expected=3D10000006.000000 h7: actual=3D10000007.000000 expected=3D10000007.000000 ./fptst breakme entering... h0: actual=3D-18199474333245.414062 expected=3D10000000.000000 h1: actual=3D-18199474333245.414062 expected=3D10000001.000000 h2: actual=3D-18199476796269.414062 expected=3D10000002.000000 h3: actual=3D-18199476796271.312500 expected=3D10000003.000000 h4: actual=3D-18199479259296.312500 expected=3D10000004.000000 h5: actual=3D-18199479259295.312500 expected=3D10000005.000000 h6: actual=3D-18199481722320.312500 expected=3D10000006.000000 h7: actual=3D-18199481722319.312500 expected=3D10000007.000000 (actual results will vary) --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-217611-7>