Commit Graph

3 Commits

Author SHA1 Message Date
Tony Hutter
becdcec7b9 kernel_fpu fixes
This patch fixes a few issues when detecting which kernel_fpu functions
are available.

- Use kernel_fpu_begin() if it's exported on newer kernels.

- Use ZFS_LINUX_TRY_COMPILE_SYMBOL() to choose the right kernel_fpu
  function when using --enable-linux-builtin.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tony Hutter <hutter2@llnl.gov>
Closes #8259
Closes #8363
2019-03-06 16:03:03 -08:00
Tony Hutter
0c593296e9 Linux 5.0 compat: Disable vector instructions on 5.0+ kernels
The 5.0 kernel no longer exports the functions we need to do vector
(SSE/SSE2/SSE3/AVX...) instructions.  Disable vector-based checksum
algorithms when building against those kernels.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tony Hutter <hutter2@llnl.gov>
Closes #8259
2019-01-28 10:11:45 -08:00
Gvozden Neskovic
fc0c72b167 Support for vectorized algorithms on x86
This is initial support for x86 vectorized implementations of ZFS parity
and checksum algorithms.

For the compilation phase, configure step checks if toolchain supports relevant
instruction sets. Each implementation must ensure that the code is not passed
to compiler if relevant instruction set is not supported. For this purpose,
following new defines are provided if instruction set is supported:
	- HAVE_SSE,
	- HAVE_SSE2,
	- HAVE_SSE3,
	- HAVE_SSSE3,
	- HAVE_SSE4_1,
	- HAVE_SSE4_2,
	- HAVE_AVX,
	- HAVE_AVX2.

For detecting if an instruction set can be used in runtime, following functions
are provided in (include/linux/simd_x86.h):
	- zfs_sse_available()
	- zfs_sse2_available()
	- zfs_sse3_available()
	- zfs_ssse3_available()
	- zfs_sse4_1_available()
	- zfs_sse4_2_available()
	- zfs_avx_available()
	- zfs_avx2_available()
	- zfs_bmi1_available()
	- zfs_bmi2_available()

These function should be called once, on module load, or initialization.
They are safe to use from user and kernel space.
If an implementation is using more than single instruction set, both compiler
and runtime support for all relevant instruction sets should be checked.

Kernel fpu methods:
	- kfpu_begin()
	- kfpu_end()

Use __get_cpuid_max and __cpuid_count from <cpuid.h>
Both gcc and clang have support for these. They also handle ebx register
in case it is used for PIC code.

Signed-off-by: Gvozden Neskovic <neskovic@gmail.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chunwei Chen <tuxoko@gmail.com>
Closes #4381
2016-03-21 09:24:34 -07:00