[Skiboot] [PATCH] npu2: Move NPU2_XTS_BDF_MAP_VALID assignment to context init

[Reza Arbab]

A bad GPU or other condition may leave us with a subset of links that
never get initialized. If an ATSD is sent to one of those bricks, it
will never complete, leaving us waiting forever for a response:

watchdog: BUG: soft lockup - CPU#23 stuck for 23s! [acos:2050]
...
Modules linked in: nvidia_uvm(O) nvidia(O)
CPU: 23 PID: 2050 Comm: acos Tainted: G        W  O    4.14.0 #2
task: c0000000285cfc00 task.stack: c000001fea860000
NIP:  c0000000000abdf0 LR: c0000000000acc48 CTR: c0000000000ace60
REGS: c000001fea863550 TRAP: 0901   Tainted: G        W  O     (4.14.0)
MSR:  9000000000009033 <SF,HV,EE,ME,IR,DR,RI,LE>  CR: 28004484  XER: 20040000
CFAR: c0000000000abdf4 SOFTE: 1
GPR00: c0000000000acc48 c000001fea8637d0 c0000000011f7c00 c000001fea863820
GPR04: 0000000002000000 0004100026000000 c0000000012778c8 c00000000127a560
GPR08: 0000000000000001 0000000000000080 c000201cc7cb7750 ffffffffffffffff
GPR12: 0000000000008000 c000000003167e80
NIP [c0000000000abdf0] mmio_invalidate_wait+0x90/0xc0
LR [c0000000000acc48] mmio_invalidate.isra.11+0x158/0x370

ATSDs are only sent to bricks which have a valid entry in the XTS_BDF
table. So to prevent the hang, don't set NPU2_XTS_BDF_MAP_VALID unless
we make it all the way to creating a context for the BDF.

Signed-off-by: Reza Arbab <arbab at linux.ibm.com>
---
 hw/npu2.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/hw/npu2.c b/hw/npu2.c
index 06e06d4..b243e8e 100644
--- a/hw/npu2.c
+++ b/hw/npu2.c
@@ -2118,6 +2118,11 @@ static int64_t opal_npu_init_context(uint64_t phb_id, int pasid __unused,
 	NPU2DBG(p, "XTS_PID_MAP[%03d] = 0x%08llx\n", id, xts_bdf_pid);
 	npu2_write(p, NPU2_XTS_PID_MAP + id*0x20, xts_bdf_pid);
 
+	if (!GETFIELD(NPU2_XTS_BDF_MAP_VALID, xts_bdf)) {
+		xts_bdf = SETFIELD(NPU2_XTS_BDF_MAP_VALID, xts_bdf, 1);
+		npu2_write(p, NPU2_XTS_BDF_MAP + id*8, xts_bdf);
+	}
+
 out:
 	unlock(&p->lock);
 	return id;
@@ -2182,12 +2187,9 @@ static int opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
 	lock(&p->lock);
 
 	/* Find any existing entries and update them */
-	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_VALID, 0UL, 1);
-	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_BDF, xts_bdf_lpar, bdf);
+	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_BDF, 0L, bdf);
 	id = npu_table_search(p, NPU2_XTS_BDF_MAP, 8, NPU2_XTS_BDF_MAP_SIZE,
-			      &xts_bdf_lpar,
-			      NPU2_XTS_BDF_MAP_VALID |
-			      NPU2_XTS_BDF_MAP_BDF);
+			      &xts_bdf_lpar, NPU2_XTS_BDF_MAP_BDF);
 	if (id < 0) {
 		/* No existing mapping found, find space for a new one */
 		xts_bdf_lpar = 0;
@@ -2202,8 +2204,7 @@ static int opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
 		goto out;
 	}
 
-	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_VALID, 0UL, 1);
-	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_UNFILT, xts_bdf_lpar, 1);
+	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_UNFILT, 0UL, 1);
 	xts_bdf_lpar = SETFIELD(NPU2_XTS_BDF_MAP_BDF, xts_bdf_lpar, bdf);
 
 	/* We only support radix for the moment */
-- 
1.8.3.1