From 4bcfa56ca9f6970974255dd5621b08e5aa9e5af5 Mon Sep 17 00:00:00 2001 From: Michael Roth Date: Tue, 18 Oct 2016 15:50:23 -0500 Subject: [PATCH] spapr_pci: advertise explicit numa IDs even when there's 1 node With the addition of "numa_node" properties for PHBs we began advertising NUMA affinity in cases where nb_numa_nodes > 1. Since the default on the guest side is to make no assumptions about PHB NUMA affinity (defaulting to -1), there is still a valid use-case for explicitly defining a PHB's NUMA affinity even when there's just one node. In particular, some workloads make faulty assumptions about /sys/bus/pci//numa_node being >= 0, warranting the use of this property as a workaround even if there's just 1 PHB or NUMA node. Enable this use-case by always advertising the PHB's NUMA affinity if "numa_node" has been explicitly set. We could achieve this by relaxing the check to simply be nb_numa_nodes > 0, but even safer would be to check numa_info[nodeid].present explicitly, and to fail at start time for cases where it does not exist. This has an additional affect of no longer advertising PHB NUMA affinity unconditionally if nb_numa_nodes > 1 and "numa_node" property is unset/-1, but since the default value on the guest side for each PHB is also -1, the behavior should be the same for that situation. We could still retain the old behavior if desired, but the decision seems arbitrary, so we take the simpler route. Cc: Alexey Kardashevskiy Cc: Shivaprasad G. Bhat Signed-off-by: Michael Roth Signed-off-by: David Gibson --- hw/ppc/spapr_pci.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 2a1ccf59ea..7cde30ee09 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1392,6 +1392,12 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) return; } + if (sphb->numa_node != -1 && + (sphb->numa_node >= MAX_NODES || !numa_info[sphb->numa_node].present)) { + error_setg(errp, "Invalid NUMA node ID for PCI host bridge"); + return; + } + sphb->dtbusname = g_strdup_printf("pci@%" PRIx64, sphb->buid); namebuf = alloca(strlen(sphb->dtbusname) + 32); @@ -1880,7 +1886,7 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, } /* Advertise NUMA via ibm,associativity */ - if (nb_numa_nodes > 1) { + if (phb->numa_node != -1) { _FDT(fdt_setprop(fdt, bus_off, "ibm,associativity", associativity, sizeof(associativity))); } -- 2.11.4.GIT