summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorAlistair Popple <alistair@popple.id.au>2018-04-17 19:11:28 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2018-04-24 09:46:57 +1000
commitd0cf9b561ca97d5245bb9e0c4774b7fadd897d67 (patch)
tree4b991ef6e71000ab4f70fe6cce1096f6e32a3b90 /arch
parenta1409adac748f0db655e096521bbe6904aadeb98 (diff)
downloadlinux-d0cf9b561ca97d5245bb9e0c4774b7fadd897d67.tar.gz
linux-d0cf9b561ca97d5245bb9e0c4774b7fadd897d67.tar.bz2
linux-d0cf9b561ca97d5245bb9e0c4774b7fadd897d67.zip
powerpc/powernv/npu: Do a PID GPU TLB flush when invalidating a large address range
The NPU has a limited number of address translation shootdown (ATSD) registers and the GPU has limited bandwidth to process ATSDs. This can result in contention of ATSD registers leading to soft lockups on some threads, particularly when invalidating a large address range in pnv_npu2_mn_invalidate_range(). At some threshold it becomes more efficient to flush the entire GPU TLB for the given MM context (PID) than individually flushing each address in the range. This patch will result in ranges greater than 2MB being converted from 32+ ATSDs into a single ATSD which will flush the TLB for the given PID on each GPU. Fixes: 1ab66d1fbada ("powerpc/powernv: Introduce address translation services for Nvlink2") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Alistair Popple <alistair@popple.id.au> Acked-by: Balbir Singh <bsingharora@gmail.com> Tested-by: Balbir Singh <bsingharora@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c23
1 files changed, 19 insertions, 4 deletions
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index ccd57d1b5bf8..525e966dce34 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -40,6 +40,13 @@
static DEFINE_SPINLOCK(npu_context_lock);
/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
+/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
*/
@@ -677,11 +684,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- for (address = start; address < end; address += PAGE_SIZE)
- mmio_invalidate(npu_context, 1, address, false);
+ if (end - start > ATSD_THRESHOLD) {
+ /*
+ * Just invalidate the entire PID if the address range is too
+ * large.
+ */
+ mmio_invalidate(npu_context, 0, 0, true);
+ } else {
+ for (address = start; address < end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address, false);
- /* Do the flush only on the final addess == end */
- mmio_invalidate(npu_context, 1, address, true);
+ /* Do the flush only on the final addess == end */
+ mmio_invalidate(npu_context, 1, address, true);
+ }
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {