diff options
author | Dan Williams <dan.j.williams@intel.com> | 2020-04-02 19:50:31 -0700 |
---|---|---|
committer | Dan Williams <dan.j.williams@intel.com> | 2020-04-02 19:50:31 -0700 |
commit | d3b88655c0a157c11370b8faf50e82ecb1c17d54 (patch) | |
tree | e3c868d5243a6073625287979bd52cf76f4eaaa8 /arch | |
parent | 91bf79bcb61df7a89690f894f06b78b0e66fb43c (diff) | |
parent | 7b27a8622f802761d5c6abd6c37b22312a35343c (diff) | |
download | linux-d3b88655c0a157c11370b8faf50e82ecb1c17d54.tar.bz2 |
Merge branch 'for-5.7/numa' into libnvdimm-for-next
- Promote numa_map_to_online_node() to a cross-kernel generic facility.
- Save x86 numa information to allow for node-id lookups for reserved
memory ranges, deploy that capability for the e820-pmem driver.
- Introduce phys_to_target_node() to facilitate drivers that want to
know resulting numa node if a given reserved address range was
onlined.
Diffstat (limited to 'arch')
-rw-r--r-- | arch/powerpc/platforms/pseries/papr_scm.c | 21 | ||||
-rw-r--r-- | arch/x86/Kconfig | 1 | ||||
-rw-r--r-- | arch/x86/mm/numa.c | 67 |
3 files changed, 54 insertions, 35 deletions
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 589858cb3203..5499fc06ed5a 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -285,25 +285,6 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, return 0; } -static inline int papr_scm_node(int node) -{ - int min_dist = INT_MAX, dist; - int nid, min_node; - - if ((node == NUMA_NO_NODE) || node_online(node)) - return node; - - min_node = first_online_node; - for_each_online_node(nid) { - dist = node_distance(node, nid); - if (dist < min_dist) { - min_dist = dist; - min_node = nid; - } - } - return min_node; -} - static int papr_scm_nvdimm_init(struct papr_scm_priv *p) { struct device *dev = &p->pdev->dev; @@ -349,7 +330,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) memset(&ndr_desc, 0, sizeof(ndr_desc)); target_nid = dev_to_node(&p->pdev->dev); - online_nid = papr_scm_node(target_nid); + online_nid = numa_map_to_online_node(target_nid); ndr_desc.numa_node = online_nid; ndr_desc.target_node = target_nid; ndr_desc.res = &p->res; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index beea77046f9b..d4e446daf457 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1664,6 +1664,7 @@ config X86_PMEM_LEGACY depends on PHYS_ADDR_T_64BIT depends on BLK_DEV select X86_PMEM_LEGACY_DEVICE + select NUMA_KEEP_MEMINFO if NUMA select LIBNVDIMM help Treat memory marked using the non-standard e820 type of 12 as used diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 99f7a68738f0..59ba008504dc 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -25,11 +25,8 @@ nodemask_t numa_nodes_parsed __initdata; struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); -static struct numa_meminfo numa_meminfo -#ifndef CONFIG_MEMORY_HOTPLUG -__initdata -#endif -; +static struct numa_meminfo numa_meminfo __initdata_or_meminfo; +static struct numa_meminfo numa_reserved_meminfo __initdata_or_meminfo; static int numa_distance_cnt; static u8 *numa_distance; @@ -169,6 +166,19 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) } /** + * numa_move_tail_memblk - Move a numa_memblk from one numa_meminfo to another + * @dst: numa_meminfo to append block to + * @idx: Index of memblk to remove + * @src: numa_meminfo to remove memblk from + */ +static void __init numa_move_tail_memblk(struct numa_meminfo *dst, int idx, + struct numa_meminfo *src) +{ + dst->blk[dst->nr_blks++] = src->blk[idx]; + numa_remove_memblk_from(idx, src); +} + +/** * numa_add_memblk - Add one numa_memblk to numa_meminfo * @nid: NUMA node ID of the new memblk * @start: Start address of the new memblk @@ -237,14 +247,19 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi) for (i = 0; i < mi->nr_blks; i++) { struct numa_memblk *bi = &mi->blk[i]; - /* make sure all blocks are inside the limits */ + /* move / save reserved memory ranges */ + if (!memblock_overlaps_region(&memblock.memory, + bi->start, bi->end - bi->start)) { + numa_move_tail_memblk(&numa_reserved_meminfo, i--, mi); + continue; + } + + /* make sure all non-reserved blocks are inside the limits */ bi->start = max(bi->start, low); bi->end = min(bi->end, high); - /* and there's no empty or non-exist block */ - if (bi->start >= bi->end || - !memblock_overlaps_region(&memblock.memory, - bi->start, bi->end - bi->start)) + /* and there's no empty block */ + if (bi->start >= bi->end) numa_remove_memblk_from(i--, mi); } @@ -881,16 +896,38 @@ EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ -#ifdef CONFIG_MEMORY_HOTPLUG -int memory_add_physaddr_to_nid(u64 start) +#ifdef CONFIG_NUMA_KEEP_MEMINFO +static int meminfo_to_nid(struct numa_meminfo *mi, u64 start) { - struct numa_meminfo *mi = &numa_meminfo; - int nid = mi->blk[0].nid; int i; for (i = 0; i < mi->nr_blks; i++) if (mi->blk[i].start <= start && mi->blk[i].end > start) - nid = mi->blk[i].nid; + return mi->blk[i].nid; + return NUMA_NO_NODE; +} + +int phys_to_target_node(phys_addr_t start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + /* + * Prefer online nodes, but if reserved memory might be + * hot-added continue the search with reserved ranges. + */ + if (nid != NUMA_NO_NODE) + return nid; + + return meminfo_to_nid(&numa_reserved_meminfo, start); +} +EXPORT_SYMBOL_GPL(phys_to_target_node); + +int memory_add_physaddr_to_nid(u64 start) +{ + int nid = meminfo_to_nid(&numa_meminfo, start); + + if (nid == NUMA_NO_NODE) + nid = numa_meminfo.blk[0].nid; return nid; } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); |