Re: [PATCH v3] mm/hugetlb_cma: support percentage-based hugetlb_cma reservation

[Sourav Panda]

On Thu, Jul 30, 2026 at 5:49 AM Usama Arif <usama.arif@xxxxxxxxx> wrote:
>
> On Wed, 29 Jul 2026 16:31:48 +0000 Sourav Panda <souravpanda@xxxxxxxxxx> wrote:
>
> > 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>
> > ---
> > Link: https://lore.kernel.org/linux-mm/20260628190155.3655895-1-souravpanda@xxxxxxxxxx/ [v2]
> > Link: https://lore.kernel.org/linux-mm/20260625215900.2151690-1-souravpanda@xxxxxxxxxx/ [v1]
> >
> > v3:
> > - Enhance pr_info logs to explicitly show percentage-derived sizes per Andrew Morton's suggestions.
> > - Explicitly align percentage-derived sizes down to the gigantic page size to prevent allocation failures (Usama Arif).
> >
> >   .../admin-guide/kernel-parameters.txt         |   7 +-
> >  mm/hugetlb_cma.c                              | 126 ++++++++++++++++--
> >  2 files changed, 123 insertions(+), 10 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..99d05eb82abc 100644
> > --- a/mm/hugetlb_cma.c
> > +++ b/mm/hugetlb_cma.c
> > @@ -9,6 +9,9 @@
> >  #include <asm/setup.h>
> >
> >  #include <linux/hugetlb.h>
> > +#include <linux/memblock.h>
> > +#include <linux/math.h>
> > +#include <linux/math64.h>
> >  #include "internal.h"
> >  #include "hugetlb_cma.h"
> >
> > @@ -18,6 +21,28 @@ 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 phys_addr_t __init memblock_node_memory_size(int nid)
> > +{
> > +     struct memblock_region *reg;
> > +     phys_addr_t size = 0;
> > +
> > +     for_each_mem_region(reg) {
> > +             if (reg->nid == nid)
> > +                     size += reg->size;
> > +     }
> > +     return size;
> > +}
> > +#else
> > +static phys_addr_t __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 +125,28 @@ 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;
> > +                             hugetlb_cma_size_in_node[nid] = 0;
> > +                             s = next + 1;
> > +                     } else {
> > +                             hugetlb_cma_size_in_node[nid] = tmp;
> > +                             hugetlb_cma_percent_in_node[nid] = 0;
> > +                             s = next;
> > +                     }
> >
> >                       /*
> >                        * Skip the separator if have one, otherwise
> > @@ -118,7 +157,28 @@ 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;
> > +                                     hugetlb_cma_size = 0;
> > +                                     for (nid = 0; nid < MAX_NUMNODES; nid++) {
> > +                                             hugetlb_cma_size_in_node[nid] = 0;
> > +                                             hugetlb_cma_percent_in_node[nid] = 0;
> > +                                     }
> > +                             }
> > +                     } else {
> > +                             hugetlb_cma_size = tmp;
> > +                             hugetlb_cma_percent = 0;
> > +                             for (nid = 0; nid < MAX_NUMNODES; nid++) {
> > +                                     hugetlb_cma_size_in_node[nid] = 0;
> > +                                     hugetlb_cma_percent_in_node[nid] = 0;
> > +                             }
> > +                     }
> >                       break;
> >               }
> >       }
> > @@ -144,8 +204,36 @@ 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) {
> > +             hugetlb_cma_size = 0;
> > +             for (nid = 0; nid < MAX_NUMNODES; nid++) {
> > +                     if (hugetlb_cma_percent_in_node[nid]) {
> > +                             phys_addr_t node_gfp_mem = memblock_node_memory_size(nid);
> > +                             u64 s;
> > +
> > +                             s = mul_u64_u32_div((u64)node_gfp_mem,
> > +                                                 hugetlb_cma_percent_in_node[nid],
> > +                                                 100);
> > +
> > +                             hugetlb_cma_size_in_node[nid] = s;
> > +                     }
> > +                     hugetlb_cma_size += hugetlb_cma_size_in_node[nid];
> > +             }
> > +     } else if (hugetlb_cma_percent) {
> > +             hugetlb_cma_size = mul_u64_u32_div((u64)memblock_phys_mem_size(),
> > +                                                hugetlb_cma_percent, 100);
> > +     }
> > +
> >       if (!hugetlb_cma_size)
> >               return;
> >
> > @@ -163,6 +251,20 @@ void __init hugetlb_cma_reserve(void)
> >        */
> >       VM_WARN_ON(order <= MAX_PAGE_ORDER);
> >
> > +     if (hugetlb_cma_percent) {
> > +             hugetlb_cma_size = ALIGN_DOWN(hugetlb_cma_size, PAGE_SIZE << order);
> > +     } else if (has_node_specific_param) {
>
> Hello,
>
> What will be done here if you have the following in kernel commandline?
>
> hugetlb_cma=20% hugetlb_cma=0:20%,1:20%
>
>
> It looks like the later node form doesn't clear hugetlb_cma_percent,
> so node specific sizes will be ignored, which I think is not the right
> behaviour.

Thanks for the review, Usama!

Agreed. This was because the node-specific parser in
cmdline_parse_hugetlb_cma() does not clear hugetlb_cma_percent.

Will fix this in v4 by clearing both hugetlb_cma_percent = 0 and
hugetlb_cma_size = 0 whenever node-specific parameters are parsed.

>
> > +             hugetlb_cma_size = 0;
> > +             for (nid = 0; nid < MAX_NUMNODES; nid++) {
> > +                     if (hugetlb_cma_percent_in_node[nid]) {
> > +                             hugetlb_cma_size_in_node[nid] =
> > +                                     ALIGN_DOWN(hugetlb_cma_size_in_node[nid],
> > +                                                PAGE_SIZE << order);
>
> Maybe print a warning here if you round down to 0?
>
> For example, 5% of a 16G machine will round down to 0.

Sounds good! Will add a pr_warn() whenever ALIGN_DOWN() reduces
reservation size to 0 (for both global and node-specific reservations)
in v4

>
> > +                     }
> > +                     hugetlb_cma_size += hugetlb_cma_size_in_node[nid];
> > +             }
> > +     }
> > +
> >       hugetlb_bootmem_set_nodes();
> >
> >       for (nid = 0; nid < MAX_NUMNODES; nid++) {
> > @@ -205,8 +307,12 @@ void __init hugetlb_cma_reserve(void)
> >               per_node = DIV_ROUND_UP(hugetlb_cma_size,
> >                                       nodes_weight(hugetlb_bootmem_nodes));
> >               per_node = round_up(per_node, PAGE_SIZE << order);
> > -             pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n",
> > -                     hugetlb_cma_size / SZ_1M, per_node / SZ_1M);
> > +             if (hugetlb_cma_percent)
> > +                     pr_info("hugetlb_cma: reserve %lu MiB (%u%%), up to %lu MiB per node\n",
> > +                             hugetlb_cma_size / SZ_1M, hugetlb_cma_percent, per_node / SZ_1M);
> > +             else
> > +                     pr_info("hugetlb_cma: reserve %lu MiB, up to %lu MiB per node\n",
> > +                             hugetlb_cma_size / SZ_1M, per_node / SZ_1M);
> >       }
> >
> >       reserved = 0;
> > @@ -241,8 +347,12 @@ void __init hugetlb_cma_reserve(void)
> >               }
> >
> >               reserved += size;
> > -             pr_info("hugetlb_cma: reserved %lu MiB on node %d\n",
> > -                     size / SZ_1M, nid);
> > +             if (hugetlb_cma_percent_in_node[nid])
> > +                     pr_info("hugetlb_cma: reserved %lu MiB (%u%%) on node %d\n",
> > +                             size / SZ_1M, hugetlb_cma_percent_in_node[nid], nid);
> > +             else
> > +                     pr_info("hugetlb_cma: reserved %lu MiB on node %d\n",
> > +                             size / SZ_1M, nid);
> >
> >               if (reserved >= hugetlb_cma_size)
> >                       break;
> > --
> > 2.55.0.rc0.799.gd6f94ed593-goog
> >
> >