From 5c9fb1899400096c6818181c525897a31d57e488 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Wed, 15 Oct 2014 12:42:58 +0200 Subject: powerpc/vphn: NUMA node code expects big-endian The associativity domain numbers are obtained from the hypervisor through registers and written into memory by the guest: the packed array passed to vphn_unpack_associativity() is then native-endian, unlike what was assumed in the following commit: commit b08a2a12e44eaec5024b2b969f4fcb98169d1ca3 Author: Alistair Popple Date: Wed Aug 7 02:01:44 2013 +1000 powerpc: Make NUMA device node code endian safe This issue fills the topology with bogus data and makes it unusable. It may lead to severe performance breakdowns. We should ideally patch the vphn_unpack_associativity() function to do the 64-bit loads, but this requires some more brain storming. In the meantime, let's go for a suboptimal and temporary bug fix: this patch converts each 64-bit value of the packed array to big endian, as expected by the current parsing code in vphn_unpack_associativity(). Signed-off-by: Greg Kurz Signed-off-by: Michael Ellerman --- arch/powerpc/mm/numa.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 177659050fa..e5236c24dc0 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1460,8 +1460,11 @@ static long hcall_vphn(unsigned long cpu, __be32 *associativity) long retbuf[PLPAR_HCALL9_BUFSIZE] = {0}; u64 flags = 1; int hwcpu = get_hard_smp_processor_id(cpu); + int i; rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu); + for (i = 0; i < 6; i++) + retbuf[i] = cpu_to_be64(retbuf[i]); vphn_unpack_associativity(retbuf, associativity); return rc; -- cgit v1.2.3-70-g09d2