The movntqda requires 16-byte alignment for the source pointer. Avoid
falling back to clflush if the source pointer is misaligned by doing the
doing a small uncached memcpy to fixup the alignments.
v2: Turn the unaligned copy into a genuine helper
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191211110437.4082687-5-chris@chris-wilson.co.uk
It used to be handy that we only had a couple of headers, but over time
i915_drv.h has become unwieldy. Extract declarations to a separate
header file corresponding to the implementation module, clarifying the
modularity of the driver.
Ensure the new header is self-contained, and do so with minimal further
includes, using forward declarations as needed. Include the new header
only where needed, and sort the modified include directives while at it
and as needed.
No functional changes.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/f2b887002150acdf218385ea846f7aa617aa5f15.1565271681.git.jani.nikula@intel.com
Our QA reported a problem caused by movntdqa instructions. Currently,
the KVM hypervisor doesn't support VEX-prefix instructions emulation.
If users passthrough a GPU to guest with vfio option 'x-no-mmap=on',
then all access to the BARs will be trapped and emulated. The KVM
hypervisor would raise an inertal error to qemu which cause the guest
killed. (Since 'movntdqa' ins is not supported.)
This patch try not to enable movntdqa optimization if the driver is
running in hypervisor guest.
Signed-off-by: Changbin Du <changbin.du@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1513924309-3113-1-git-send-email-changbin.du@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Silence sparse who warns that the global variable is not declared
static.
Fixes: 0b1de5d58e ("drm/i915: Use SSE4.1 movntdqa to ...")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Damien Lespiau <damien.lespiau@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471432146-5196-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
This patch provides the infrastructure for performing a 16-byte aligned
read from WC memory using non-temporal instructions introduced with sse4.1.
Using movntdqa we can bypass the CPU caches and read directly from memory
and ignoring the page attributes set on the CPU PTE i.e. negating the
impact of an otherwise UC access. Copying using movntdqa from WC is almost
as fast as reading from WB memory, modulo the possibility of both hitting
the CPU cache or leaving the data in the CPU cache for the next consumer.
(The CPU cache itself my be flushed for the region of the movntdqa and on
later access the movntdqa reads from a separate internal buffer for the
cacheline.) The write back to the memory is however cached.
This will be used in later patches to accelerate accessing WC memory.
v2: Report whether the accelerated copy is successful/possible.
v3: Function alignment override was only necessary when using the
function target("sse4.1") - which is not necessary for emitting movntdqa
from __asm__.
v4: Improve notes on CPU cache behaviour vs non-temporal stores.
v5: Fix byte offsets for unrolled moves.
v6: Find all remaining typos of "movntqda", use kernel_fpu_begin.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Damien Lespiau <damien.lespiau@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1471001999-17787-2-git-send-email-chris@chris-wilson.co.uk
