summaryrefslogtreecommitdiffstats
path: root/arch
diff options
context:
space:
mode:
authorAlexey Kardashevskiy <aik@ozlabs.ru>2016-04-29 18:55:22 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2016-05-11 21:54:30 +1000
commitb575c731fe58c1ecb1247c6a334ba6c7b4c0b480 (patch)
treefac95487154fecab05a0ea80f7e67030c6079298 /arch
parent7d623e42560ea69eb248d48a1b1b105f28807e6e (diff)
downloadop-kernel-dev-b575c731fe58c1ecb1247c6a334ba6c7b4c0b480.zip
op-kernel-dev-b575c731fe58c1ecb1247c6a334ba6c7b4c0b480.tar.gz
powerpc/powernv/npu: Add set/unset window helpers
The upcoming NVLink passthrough support will require NPU code to cope with two DMA windows. This adds a pnv_npu_set_window() helper which programs 32bit window to the hardware. This also adds multilevel TCE support. This adds a pnv_npu_unset_window() helper which removes the DMA window from the hardware. This does not make difference now as the caller - pnv_npu_dma_set_bypass() - enables bypass in the hardware but the next patch will use it to manage TCE table lists for TCE Kill handling. Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-By: Alistair Popple <alistair@popple.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch')
-rw-r--r--arch/powerpc/platforms/powernv/npu-dma.c65
1 files changed, 55 insertions, 10 deletions
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index bec9267..800d70f 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -159,6 +159,56 @@ static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe,
return pe;
}
+static long pnv_npu_set_window(struct pnv_ioda_pe *npe,
+ struct iommu_table *tbl)
+{
+ struct pnv_phb *phb = npe->phb;
+ int64_t rc;
+ const unsigned long size = tbl->it_indirect_levels ?
+ tbl->it_level_size : tbl->it_size;
+ const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
+ const __u64 win_size = tbl->it_size << tbl->it_page_shift;
+
+ pe_info(npe, "Setting up window %llx..%llx pg=%lx\n",
+ start_addr, start_addr + win_size - 1,
+ IOMMU_PAGE_SIZE(tbl));
+
+ rc = opal_pci_map_pe_dma_window(phb->opal_id,
+ npe->pe_number,
+ npe->pe_number,
+ tbl->it_indirect_levels + 1,
+ __pa(tbl->it_base),
+ size << 3,
+ IOMMU_PAGE_SIZE(tbl));
+ if (rc) {
+ pe_err(npe, "Failed to configure TCE table, err %lld\n", rc);
+ return rc;
+ }
+ pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+
+ return 0;
+}
+
+static long pnv_npu_unset_window(struct pnv_ioda_pe *npe)
+{
+ struct pnv_phb *phb = npe->phb;
+ int64_t rc;
+
+ pe_info(npe, "Removing DMA window\n");
+
+ rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number,
+ npe->pe_number,
+ 0/* levels */, 0/* table address */,
+ 0/* table size */, 0/* page size */);
+ if (rc) {
+ pe_err(npe, "Unmapping failed, ret = %lld\n", rc);
+ return rc;
+ }
+ pnv_pci_ioda2_tce_invalidate_entire(phb, false);
+
+ return 0;
+}
+
void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe)
{
struct pnv_ioda_pe *gpe;
@@ -200,10 +250,8 @@ void pnv_npu_init_dma_pe(struct pnv_ioda_pe *npe)
*/
static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
{
- struct pnv_phb *phb = npe->phb;
struct pci_dev *gpdev;
struct pnv_ioda_pe *gpe;
- struct iommu_table *tbl;
int64_t rc;
/*
@@ -217,14 +265,7 @@ static void pnv_npu_dma_set_32(struct pnv_ioda_pe *npe)
if (!gpe)
return;
- tbl = gpe->table_group.tables[0];
- rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number,
- npe->pe_number, 1, __pa(tbl->it_base),
- tbl->it_size << 3,
- IOMMU_PAGE_SIZE(tbl));
- if (rc != OPAL_SUCCESS)
- pr_warn("%s: Error %lld setting DMA window on PHB#%d-PE#%d\n",
- __func__, rc, phb->hose->global_number, npe->pe_number);
+ rc = pnv_npu_set_window(npe, gpe->table_group.tables[0]);
/*
* We don't initialise npu_pe->tce32_table as we always use
@@ -248,6 +289,10 @@ static int pnv_npu_dma_set_bypass(struct pnv_ioda_pe *npe)
if (phb->type != PNV_PHB_NPU || !npe->pdev)
return -EINVAL;
+ rc = pnv_npu_unset_window(npe);
+ if (rc != OPAL_SUCCESS)
+ return rc;
+
/* Enable the bypass window */
top = roundup_pow_of_two(top);
OpenPOWER on IntegriCloud