David S. Miller
405849610f
[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>
2007-08-16 22:59:49 -07:00
arch: personality independent stack top
2007-07-19 10:04:45 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC]: Emulate cmpxchg like parisc
2007-05-29 02:51:13 -07:00
[PATCH] auxiliary vector cleanups
2005-09-07 16:57:21 -07:00
[SPARC]: Make bitops use same spinlocks as atomics.
2006-12-17 16:18:47 -08:00
[PATCH] fix the breakage in sparc headers
2005-10-05 07:33:42 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[PATCH] Kill L1_CACHE_SHIFT_MAX
2006-01-08 20:13:39 -08:00
[PATCH] Optimize D-cache alias handling on fork
2006-12-13 09:27:08 -08:00
[SPARC32]: Fix over-optimization by GCC near ip_fast_csum.
2007-02-01 20:24:35 -08:00
[SPARC]: Try to start getting SMP back into shape.
2006-03-23 22:36:19 -08:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling.
2007-07-30 00:27:34 -07:00
[PATCH] sparc: have dma-mapping.h include generic/dma-mapping-broken in non-PCI case
2007-03-14 15:27:49 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC]: Port of_device layer and make ebus use it.
2006-06-23 23:15:47 -07:00
[SPARC]: Clean up asm-sparc/elf.h pollution in userspace.
2006-10-20 00:29:33 -07:00
[SPARC]: Implement fb_is_primary_device().
2007-07-20 17:15:09 -07:00
[SPARC32]: Fix build.
2007-08-04 21:17:18 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC32]: Fix modular build of floppy driver.
2007-08-03 14:08:42 -07:00
[PATCH] consolidate asm/futex.h
2006-01-08 20:13:39 -08:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC]: Clean up idprom header files.
2006-03-20 01:12:08 -08:00
[PATCH] add missing io...._rep() on sparc32
2007-02-11 11:18:07 -08:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[SPARC32]: Fix modular build of floppy driver.
2007-08-03 14:08:42 -07:00
[PATCH] sparc32 pt_regs fixes
2006-10-08 12:32:35 -07:00
Fix exported headers for SPARC, SPARC64
2006-09-21 08:48:27 +01:00
[SPARC32]: Fix sparc32 kdebug changes.
2007-05-14 03:22:08 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[PATCH] sun4c_memerr_reg __iomem annotations
2005-12-15 10:01:29 -08:00
[PATCH] IA64,sparc: local DoS with corrupted ELFs
2006-09-08 08:40:46 -07:00
[PATCH] x86: PARAVIRT: add hooks to intercept mm creation and destruction
2007-05-02 19:27:14 +02:00
[SPARC]: sparc64 gcc-4.2.0 20070317 -Werror failure
2007-03-27 01:13:55 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[PATCH] mutex subsystem, add default include/asm-*/mutex.h files
2006-01-09 15:59:19 -08:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
Create linux/of_platorm.h
2007-07-20 14:25:22 +10:00
Create linux/of_platorm.h
2007-07-20 14:25:22 +10:00
[SPARC]: Fix serial console device detection.
2007-07-20 16:59:26 -07:00
Fix exported headers for SPARC, SPARC64
2006-09-21 08:48:27 +01:00
[SPARC]: Port sparc64 in-kernel device tree code to sparc32.
2006-06-23 23:15:45 -07:00
PCI: remove pci_dac_dma_... APIs
2007-07-11 16:02:11 -07:00
[PATCH] fix iomem annotations in sparc32 pcic code
2005-12-15 10:01:28 -08:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC32]: Make PAGE_SHARED a read-mostly variable.
2007-07-21 19:20:34 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
Consolidate asm/poll.h
2007-05-11 08:29:34 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[SPARC]: Centralize find_in_proplist() instead of duplicating N times.
2007-08-07 18:46:36 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[PATCH] consolidate sys_ptrace()
2005-11-07 07:53:42 -08:00
fix file specification in comments
2006-10-03 23:01:26 +02:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[SPARC32]: Remove iommu from struct sbus_bus and use archdata like sparc64.
2007-08-10 15:52:06 -07:00
[PATCH] semaphore: Remove __MUTEX_INITIALIZER()
2005-10-30 17:37:27 -08:00
[MATH-EMU]: Fix underflow exception reporting.
2007-08-16 22:59:49 -07:00
[SPARC]: Fix SA_STATIC_ALLOC value.
2006-07-24 22:34:00 -07:00
Remove hardcoding of hard_smp_processor_id on UP systems
2007-05-09 12:30:48 -07:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[NET]: Adding SO_TIMESTAMPNS / SCM_TIMESTAMPNS support
2007-04-25 22:24:21 -07:00
[NET]: Introduce SIOCGSTAMPNS ioctl to get timestamps with nanosec resolution
2007-04-25 22:24:04 -07:00
[PATCH] sparc32 rwlock fix
2006-10-08 12:32:35 -07:00
[PATCH] spinlock consolidation
2005-09-10 10:06:21 -07:00
[PATCH] sched: sched_cacheflush is now unused
2007-07-19 21:28:35 +02:00
[PATCH] tty: preparatory structures for termios revamp
2006-12-08 08:28:56 -08:00
[PATCH] consolidate line discipline number definitions
2007-02-11 10:51:26 -08:00
[SPARC]: Add support for *at(), ppoll, and pselect syscalls.
2006-01-19 02:42:49 -08:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[SPARC]: "extern inline" doesn't make much sense.
2005-10-03 17:37:02 -07:00
[PATCH] sab: consolidate kmem_bufctl_t
2005-09-05 00:05:48 -07:00
[SPARC]: Kill off these __put_user_ret things.
2006-03-20 01:13:15 -08:00
[SPARC]: Add sys_fallocate() entries.
2007-07-19 21:26:47 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
[PATCH] sparc32 vga support
2006-04-11 06:18:54 -07:00
Don't include linux/config.h from anywhere else in include/
2006-04-26 12:56:16 +01:00
405849610f