From: David Hildenbrand <david@xxxxxxxxxx> We want to reuse the functionality when remapping or resizing RAM. Signed-off-by: David Hildenbrand <david@xxxxxxxxxx> Signed-off-by: William Roche <william.roche@xxxxxxxxxx> --- backends/hostmem.c | 155 ++++++++++++++++++++++++--------------------- 1 file changed, 82 insertions(+), 73 deletions(-) diff --git a/backends/hostmem.c b/backends/hostmem.c index 181446626a..bf85d716e5 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -36,6 +36,87 @@ QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND); QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE); #endif +static void host_memory_backend_apply_settings(HostMemoryBackend *backend, + void *ptr, uint64_t size, + Error **errp) +{ + bool async = !phase_check(PHASE_LATE_BACKENDS_CREATED); + + if (backend->merge) { + qemu_madvise(ptr, size, QEMU_MADV_MERGEABLE); + } + if (!backend->dump) { + qemu_madvise(ptr, size, QEMU_MADV_DONTDUMP); + } +#ifdef CONFIG_NUMA + unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES); + /* lastbit == MAX_NODES means maxnode = 0 */ + unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1); + /* + * Ensure policy won't be ignored in case memory is preallocated + * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so + * this doesn't catch hugepage case. + */ + unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE; + int mode = backend->policy; + + /* + * Check for invalid host-nodes and policies and give more verbose + * error messages than mbind(). + */ + if (maxnode && backend->policy == MPOL_DEFAULT) { + error_setg(errp, "host-nodes must be empty for policy default," + " or you should explicitly specify a policy other" + " than default"); + return; + } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) { + error_setg(errp, "host-nodes must be set for policy %s", + HostMemPolicy_str(backend->policy)); + return; + } + + /* + * We can have up to MAX_NODES nodes, but we need to pass maxnode+1 + * as argument to mbind() due to an old Linux bug (feature?) which + * cuts off the last specified node. This means backend->host_nodes + * must have MAX_NODES+1 bits available. + */ + assert(sizeof(backend->host_nodes) >= + BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long)); + assert(maxnode <= MAX_NODES); + +#ifdef HAVE_NUMA_HAS_PREFERRED_MANY + if (mode == MPOL_PREFERRED && numa_has_preferred_many() > 0) { + /* + * Replace with MPOL_PREFERRED_MANY otherwise the mbind() below + * silently picks the first node. + */ + mode = MPOL_PREFERRED_MANY; + } +#endif + + if (maxnode && + mbind(ptr, size, mode, backend->host_nodes, maxnode + 1, flags)) { + if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) { + error_setg_errno(errp, errno, + "cannot bind memory to host NUMA nodes"); + return; + } + } +#endif + /* + * Preallocate memory after the NUMA policy has been instantiated. + * This is necessary to guarantee memory is allocated with + * specified NUMA policy in place. + */ + if (backend->prealloc && + !qemu_prealloc_mem(memory_region_get_fd(&backend->mr), + ptr, size, backend->prealloc_threads, + backend->prealloc_context, async, errp)) { + return; + } +} + char * host_memory_backend_get_name(HostMemoryBackend *backend) { @@ -337,7 +418,6 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp) void *ptr; uint64_t sz; size_t pagesize; - bool async = !phase_check(PHASE_LATE_BACKENDS_CREATED); if (!bc->alloc) { return; @@ -357,78 +437,7 @@ host_memory_backend_memory_complete(UserCreatable *uc, Error **errp) return; } - if (backend->merge) { - qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE); - } - if (!backend->dump) { - qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP); - } -#ifdef CONFIG_NUMA - unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES); - /* lastbit == MAX_NODES means maxnode = 0 */ - unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1); - /* - * Ensure policy won't be ignored in case memory is preallocated - * before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so - * this doesn't catch hugepage case. - */ - unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE; - int mode = backend->policy; - - /* check for invalid host-nodes and policies and give more verbose - * error messages than mbind(). */ - if (maxnode && backend->policy == MPOL_DEFAULT) { - error_setg(errp, "host-nodes must be empty for policy default," - " or you should explicitly specify a policy other" - " than default"); - return; - } else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) { - error_setg(errp, "host-nodes must be set for policy %s", - HostMemPolicy_str(backend->policy)); - return; - } - - /* - * We can have up to MAX_NODES nodes, but we need to pass maxnode+1 - * as argument to mbind() due to an old Linux bug (feature?) which - * cuts off the last specified node. This means backend->host_nodes - * must have MAX_NODES+1 bits available. - */ - assert(sizeof(backend->host_nodes) >= - BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long)); - assert(maxnode <= MAX_NODES); - -#ifdef HAVE_NUMA_HAS_PREFERRED_MANY - if (mode == MPOL_PREFERRED && numa_has_preferred_many() > 0) { - /* - * Replace with MPOL_PREFERRED_MANY otherwise the mbind() below - * silently picks the first node. - */ - mode = MPOL_PREFERRED_MANY; - } -#endif - - if (maxnode && - mbind(ptr, sz, mode, backend->host_nodes, maxnode + 1, flags)) { - if (backend->policy != MPOL_DEFAULT || errno != ENOSYS) { - error_setg_errno(errp, errno, - "cannot bind memory to host NUMA nodes"); - return; - } - } -#endif - /* - * Preallocate memory after the NUMA policy has been instantiated. - * This is necessary to guarantee memory is allocated with - * specified NUMA policy in place. - */ - if (backend->prealloc && !qemu_prealloc_mem(memory_region_get_fd(&backend->mr), - ptr, sz, - backend->prealloc_threads, - backend->prealloc_context, - async, errp)) { - return; - } + host_memory_backend_apply_settings(backend, ptr, sz, errp); } static bool -- 2.43.5