[PATCH v1] mm/hugetlb_cma: support percentage-based hugetlb_cma reservation

[Sourav Panda]

Currently, hugetlb_cma reservation only supports absolute sizes (e.g.,
hugetlb_cma=2G or hugetlb_cma=0:1G,1:1G). This can be restrictive in
heterogeneous environments or when deploying common kernel command lines
across machines with different memory capacities.

Add support for percentage-based hugetlb_cma reservation (e.g.,
hugetlb_cma=20% or hugetlb_cma=0:20%,1:10%).

The percentage is calculated against the total memory (for global
settings) or against the node-specific memory (for node-specific
settings) using memblock APIs during early boot.

Signed-off-by: Sourav Panda <souravpanda@xxxxxxxxxx>
---
 .../admin-guide/kernel-parameters.txt         |  7 +-
 mm/hugetlb_cma.c                              | 81 ++++++++++++++++++-
 2 files changed, 82 insertions(+), 6 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5a05b48d1684..846940ce2858 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2064,8 +2064,11 @@ Kernel parameters
 	hugetlb_cma=	[HW,CMA,EARLY] The size of a CMA area used for allocation
 			of gigantic hugepages. Or using node format, the size
 			of a CMA area per node can be specified.
-			Format: nn[KMGTPE] or (node format)
-				<node>:nn[KMGTPE][,<node>:nn[KMGTPE]]
+			The size can be an absolute value (e.g., 2G) or a
+			percentage of the total memory or node memory (e.g., 20%).
+			Format: nn[KMGTPE] or nn% or (node format)
+				<node>:nn[KMGTPE][,<node>:nn[KMGTPE]] or
+				<node>:nn%[,<node>:nn%]
 
 			Reserve a CMA area of given size and allocate gigantic
 			hugepages using the CMA allocator. If enabled, the
diff --git a/mm/hugetlb_cma.c b/mm/hugetlb_cma.c
index 7693ccefd0c6..b4f8bbe4c62d 100644
--- a/mm/hugetlb_cma.c
+++ b/mm/hugetlb_cma.c
@@ -9,6 +9,8 @@
 #include <asm/setup.h>
 
 #include <linux/hugetlb.h>
+#include <linux/memblock.h>
+#include <linux/math.h>
 #include "internal.h"
 #include "hugetlb_cma.h"
 
@@ -18,6 +20,28 @@ static unsigned long hugetlb_cma_size_in_node[MAX_NUMNODES] __initdata;
 static bool hugetlb_cma_only __ro_after_init;
 static unsigned long hugetlb_cma_size __ro_after_init;
 
+static unsigned int hugetlb_cma_percent __initdata;
+static unsigned int hugetlb_cma_percent_in_node[MAX_NUMNODES] __initdata;
+
+#ifdef CONFIG_NUMA
+static unsigned long __init memblock_node_memory_size(int nid)
+{
+	struct memblock_region *reg;
+	unsigned long size = 0;
+
+	for_each_mem_region(reg) {
+		if (reg->nid == nid)
+			size += reg->size;
+	}
+	return size;
+}
+#else
+static unsigned long __init memblock_node_memory_size(int nid)
+{
+	return memblock_phys_mem_size();
+}
+#endif
+
 void hugetlb_cma_free_frozen_folio(struct folio *folio)
 {
 	WARN_ON_ONCE(!cma_release_frozen(hugetlb_cma[folio_nid(folio)],
@@ -100,14 +124,27 @@ static int __init cmdline_parse_hugetlb_cma(char *p)
 			break;
 
 		if (s[count] == ':') {
+			char *next;
+
 			if (tmp >= MAX_NUMNODES)
 				break;
 			nid = array_index_nospec(tmp, MAX_NUMNODES);
 
 			s += count + 1;
-			tmp = memparse(s, &s);
-			hugetlb_cma_size_in_node[nid] = tmp;
-			hugetlb_cma_size += tmp;
+			tmp = memparse(s, &next);
+			if (*next == '%') {
+				if (tmp > 100) {
+					pr_warn("hugetlb_cma: invalid percentage %lu for node %d\n",
+						tmp, nid);
+					break;
+				}
+				hugetlb_cma_percent_in_node[nid] = tmp;
+				s = next + 1;
+			} else {
+				hugetlb_cma_size_in_node[nid] = tmp;
+				hugetlb_cma_size += tmp;
+				s = next;
+			}
 
 			/*
 			 * Skip the separator if have one, otherwise
@@ -118,7 +155,17 @@ static int __init cmdline_parse_hugetlb_cma(char *p)
 			else
 				break;
 		} else {
-			hugetlb_cma_size = memparse(p, &p);
+			char *next;
+
+			tmp = memparse(p, &next);
+			if (*next == '%') {
+				if (tmp > 100)
+					pr_warn("hugetlb_cma: invalid percentage %lu\n", tmp);
+				else
+					hugetlb_cma_percent = tmp;
+			} else {
+				hugetlb_cma_size = tmp;
+			}
 			break;
 		}
 	}
@@ -144,8 +191,34 @@ void __init hugetlb_cma_reserve(void)
 {
 	unsigned long size, reserved, per_node, order;
 	bool node_specific_cma_alloc = false;
+	bool has_node_specific_param = false;
 	int nid;
 
+	for (nid = 0; nid < MAX_NUMNODES; nid++) {
+		if (hugetlb_cma_size_in_node[nid] || hugetlb_cma_percent_in_node[nid]) {
+			has_node_specific_param = true;
+			break;
+		}
+	}
+
+	if (has_node_specific_param) {
+		for (nid = 0; nid < MAX_NUMNODES; nid++) {
+			if (hugetlb_cma_percent_in_node[nid]) {
+				unsigned long node_gfp_mem = memblock_node_memory_size(nid);
+				unsigned long s;
+
+				s = mult_frac(node_gfp_mem,
+					      hugetlb_cma_percent_in_node[nid],
+					      100);
+
+				hugetlb_cma_size_in_node[nid] = s;
+				hugetlb_cma_size += s;
+			}
+		}
+	} else if (hugetlb_cma_percent) {
+		hugetlb_cma_size = mult_frac(memblock_phys_mem_size(), hugetlb_cma_percent, 100);
+	}
+
 	if (!hugetlb_cma_size)
 		return;
 
-- 
2.55.0.rc0.799.gd6f94ed593-goog