Re: [PATCH v5 4/6] powerpc/pseries: Consolidate different NUMA distance update code paths
From: Aneesh Kumar K.V <hidden>
Date: 2021-07-27 03:33:27
David Gibson [off-list ref] writes:
On Thu, Jul 22, 2021 at 12:37:46PM +0530, Aneesh Kumar K.V wrote:quoted
David Gibson [off-list ref] writes:quoted
On Mon, Jun 28, 2021 at 08:41:15PM +0530, Aneesh Kumar K.V wrote:
....
quoted
quoted
quoted
+ nid = of_read_number(&aa.arrays[index], 1); + + if (nid == 0xffff || nid >= nr_node_ids) + nid = default_nid; + if (nid > 0 && affinity_form == FORM1_AFFINITY) { + int i; + const __be32 *associativity; + + index = lmb->aa_index * aa.array_sz; + associativity = &aa.arrays[index]; + /* + * lookup array associativity entries have different format + * There is no length of the array as the first element.The difference it very small, and this is not a hot path. Couldn't you reduce a chunk of code by prepending aa.array_sz, then re-using __initialize_form1_numa_distance. Or even making __initialize_form1_numa_distance() take the length as a parameter.The changes are small but confusing w.r.t how we look at the associativity-lookup-arrays. The way we interpret associativity array and associativity lookup array using primary_domain_index is different. Hence the '-1' in the node lookup here.They're really not, though. It's exactly the same interpretation of the associativity array itself - it's just that one of them has the array prepended with a (redundant) length. So you can make __initialize_form1_numa_distance() work on the "bare" associativity array, with a given length. Here you call it with aa.array_sz as the length, and in the other place you call it with prop[0] as the length.quoted
index = lmb->aa_index * aa.array_sz + primary_domain_index - 1; nid = of_read_number(&aa.arrays[index], 1);quoted
quoted
+ */ + for (i = 0; i < max_associativity_domain_index; i++) { + const __be32 *entry; + + entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1];Does anywhere verify that distance_ref_points[i] <= aa.array_size for every i?We do check for if (primary_domain_index <= aa.array_sz &&Right, but that doesn't check the other distance_ref_points entries. Not that there's any reason to have extra entries with Form2, but we still don't want stray array accesses.
This is how the change looks. I am not convinced this makes it simpler. I will add that as the last patch and we can drop that if we find that not helpful? modified arch/powerpc/mm/numa.c
@@ -171,20 +171,31 @@ static void unmap_cpu_from_node(unsigned long cpu) } #endif /* CONFIG_HOTPLUG_CPU || CONFIG_PPC_SPLPAR */ -/* - * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA - * info is found. - */ -static int associativity_to_nid(const __be32 *associativity) +static int __associativity_to_nid(const __be32 *associativity, + bool lookup_array_assoc, + int max_array_index) { int nid = NUMA_NO_NODE; + int index; if (!numa_enabled) goto out; + /* + * ibm,associativity-lookup-array doesn't have element + * count at the start of the associativity. Hence + * decrement the primary_domain_index when used with + * lookup-array associativity. + */ + if (lookup_array_assoc) + index = primary_domain_index - 1; + else { + index = primary_domain_index; + max_array_index = of_read_number(associativity, 1); + } + if (index > max_array_index) + goto out; - if (of_read_number(associativity, 1) >= primary_domain_index) - nid = of_read_number(&associativity[primary_domain_index], 1); - + nid = of_read_number(&associativity[index], 1); /* POWER4 LPAR uses 0xffff as invalid node */ if (nid == 0xffff || nid >= nr_node_ids) nid = NUMA_NO_NODE;
@@ -192,6 +203,15 @@ static int associativity_to_nid(const __be32 *associativity) return nid; } +/* + * Returns nid in the range [0..nr_node_ids], or -1 if no useful NUMA + * info is found. + */ +static inline int associativity_to_nid(const __be32 *associativity) +{ + return __associativity_to_nid(associativity, false, 0); +} + static int __cpu_form2_relative_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) { int dist;
@@ -295,19 +315,38 @@ int of_node_to_nid(struct device_node *device) } EXPORT_SYMBOL(of_node_to_nid); -static void __initialize_form1_numa_distance(const __be32 *associativity) +static void __initialize_form1_numa_distance(const __be32 *associativity, + bool lookup_array_assoc, + int max_array_index) { int i, nid; + int index_offset = 0; if (affinity_form != FORM1_AFFINITY) return; + /* + * ibm,associativity-lookup-array doesn't have element + * count at the start of the associativity. Hence + * decrement the distance_ref_points index when used with + * lookup-array associativity. + */ + if (lookup_array_assoc) + index_offset = 1; + else + max_array_index = of_read_number(associativity, 1); - nid = associativity_to_nid(associativity); + nid = __associativity_to_nid(associativity, lookup_array_assoc, max_array_index); if (nid != NUMA_NO_NODE) { for (i = 0; i < distance_ref_points_depth; i++) { const __be32 *entry; + int index = be32_to_cpu(distance_ref_points[i]) - index_offset; - entry = &associativity[be32_to_cpu(distance_ref_points[i])]; + /* + * broken hierarchy, return with broken distance table + */ + if (index > max_array_index) + return; + entry = &associativity[index]; distance_lookup_table[nid][i] = of_read_number(entry, 1); } }
@@ -321,7 +360,7 @@ static void initialize_form1_numa_distance(struct device_node *node) if (!associativity) return; - __initialize_form1_numa_distance(associativity); + __initialize_form1_numa_distance(associativity, false, 0); } /*
@@ -586,27 +625,14 @@ static int get_nid_and_numa_distance(struct drmem_lmb *lmb) if (primary_domain_index <= aa.array_sz && !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { - index = lmb->aa_index * aa.array_sz + primary_domain_index - 1; - nid = of_read_number(&aa.arrays[index], 1); + const __be32 *associativity; - if (nid == 0xffff || nid >= nr_node_ids) - nid = default_nid; + index = lmb->aa_index * aa.array_sz; + associativity = &aa.arrays[index]; + nid = __associativity_to_nid(associativity, true, aa.array_sz - 1); if (nid > 0 && affinity_form == FORM1_AFFINITY) { - int i; - const __be32 *associativity; - - index = lmb->aa_index * aa.array_sz; - associativity = &aa.arrays[index]; - /* - * lookup array associativity entries have different format - * There is no length of the array as the first element. - */ - for (i = 0; i < distance_ref_points_depth; i++) { - const __be32 *entry; - - entry = &associativity[be32_to_cpu(distance_ref_points[i]) - 1]; - distance_lookup_table[nid][i] = of_read_number(entry, 1); - } + __initialize_form1_numa_distance(associativity, + true, aa.array_sz - 1); } } return nid;
@@ -632,9 +658,11 @@ int of_drconf_to_nid_single(struct drmem_lmb *lmb) if (primary_domain_index <= aa.array_sz && !(lmb->flags & DRCONF_MEM_AI_INVALID) && lmb->aa_index < aa.n_arrays) { - index = lmb->aa_index * aa.array_sz + primary_domain_index - 1; - nid = of_read_number(&aa.arrays[index], 1); + const __be32 *associativity; + index = lmb->aa_index * aa.array_sz; + associativity = &aa.arrays[index]; + nid = __associativity_to_nid(associativity, true, aa.array_sz - 1); if (nid == 0xffff || nid >= nr_node_ids) nid = default_nid; }
@@ -939,7 +967,7 @@ static int __init parse_numa_properties(void) if (__vphn_get_associativity(i, vphn_assoc) == 0) { nid = associativity_to_nid(vphn_assoc); - __initialize_form1_numa_distance(vphn_assoc); + __initialize_form1_numa_distance(vphn_assoc, false, 0); } else { /*
@@ -953,7 +981,7 @@ static int __init parse_numa_properties(void) associativity = of_get_associativity(cpu); if (associativity) { nid = associativity_to_nid(associativity); - __initialize_form1_numa_distance(associativity); + __initialize_form1_numa_distance(associativity, false, 0); } of_node_put(cpu); }
@@ -993,7 +1021,7 @@ static int __init parse_numa_properties(void) associativity = of_get_associativity(memory); if (associativity) { nid = associativity_to_nid(associativity); - __initialize_form1_numa_distance(associativity); + __initialize_form1_numa_distance(associativity, false, 0); } else nid = default_nid;