powerpc/powernv/npu: Add a debugfs setting to change ATSD threshold

The threshold at which it becomes more efficient to coalesce a range
of ATSDs into a single per-PID ATSD is currently not well understood
due to a lack of real-world work loads. This patch adds a debugfs
parameter allowing the threshold to be altered at runtime in order to
aid future development and refinement of the value.

Signed-off-by: Alistair Popple <alistair@popple.id.au>
Acked-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 8cdf91f..4583153 100644 (file)
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -17,7 +17,9 @@
 #include <linux/pci.h>
 #include <linux/memblock.h>
 #include <linux/iommu.h>
+#include <linux/debugfs.h>
 
+#include <asm/debugfs.h>
 #include <asm/tlb.h>
 #include <asm/powernv.h>
 #include <asm/reg.h>
@@ -44,7 +46,8 @@ static DEFINE_SPINLOCK(npu_context_lock);
  * entire TLB on the GPU for the given PID rather than each specific address in
  * the range.
  */
-#define ATSD_THRESHOLD (2*1024*1024)
+static uint64_t atsd_threshold = 2 * 1024 * 1024;
+static struct dentry *atsd_threshold_dentry;
 
 /*
  * Other types of TCE cache invalidation are not functional in the
@@ -683,7 +686,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
        struct npu_context *npu_context = mn_to_npu_context(mn);
        unsigned long address;
 
-       if (end - start > ATSD_THRESHOLD) {
+       if (end - start > atsd_threshold) {
                /*
                 * Just invalidate the entire PID if the address range is too
                 * large.
@@ -958,6 +961,11 @@ int pnv_npu2_init(struct pnv_phb *phb)
        static int npu_index;
        uint64_t rc = 0;
 
+       if (!atsd_threshold_dentry) {
+               atsd_threshold_dentry = debugfs_create_x64("atsd_threshold",
+                                  0600, powerpc_debugfs_root, &atsd_threshold);
+       }
+
        phb->npu.nmmu_flush =
                of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush");
        for_each_child_of_node(phb->hose->dn, dn) {