cc linux-mm@xxxxxxxxx
yaozhenguo <yaozhenguo1@xxxxxxxxx> 于2021年9月2日周四 下午2:59写道：
>
> We can specify the number of hugepages to allocate at boot. But the
> hugepages is balanced in all nodes at present. In some scenarios,
> we only need hugepages in one node. For example: DPDK needs hugepages
> which is in the same node as NIC. if DPDK needs four hugepages of 1G
> size in node1 and system has 16 numa nodes. We must reserve 64 hugepages
> in kernel cmdline. But, only four hugepages are used. The others should
> be free after boot.If the system memory is low(for example: 64G), it will
> be an impossible task. So, extend hugepages kernel parameter to specify
> node number of hugepages to allocate at boot.
> For example add following parameter:
>
> hugepagesz=1G hugepages=0:1,1:3
>
> It will allocate 1 hugepages in node0 and 3 hugepages in node1.
>
> Signed-off-by: yaozhenguo <yaozhenguo1@xxxxxxxxx>
> ---
> v3: 1. Skip gigantic hugepages allocation if hugetlb_cma is enabled.
> 2. Fix wrong behavior for parameter: hugepagesz=2M hugepages=2 hugepages=5.
> 3. Update hugetlbpage.rst.
> 4. Fix side effects which v2 brings in.
> 5. add cond_resched in hugetlb_hstate_alloc_pages_onenode.
> ---
> .../admin-guide/kernel-parameters.txt | 8 +-
> Documentation/admin-guide/mm/hugetlbpage.rst | 12 +-
> include/linux/hugetlb.h | 1 +
> mm/hugetlb.c | 116 ++++++++++++++++--
> 4 files changed, 126 insertions(+), 11 deletions(-)
>
> diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
> index bdb22006f..64a128924 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1588,9 +1588,11 @@
> the number of pages of hugepagesz to be allocated.
> If this is the first HugeTLB parameter on the command
> line, it specifies the number of pages to allocate for
> - the default huge page size. See also
> - Documentation/admin-guide/mm/hugetlbpage.rst.
> - Format: <integer>
> + the default huge page size. If using node format, It
> + specifies numbers of hugepage in a specific node.
> + See also Documentation/admin-guide/mm/hugetlbpage.rst.
> + Format: <integer> or (node format)
> + <node>:<numbers>[,<node>:<numbers>]
>
> hugepagesz=
> [HW] The size of the HugeTLB pages. This is used in
> diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
> index 8abaeb144..bc5f674ff 100644
> --- a/Documentation/admin-guide/mm/hugetlbpage.rst
> +++ b/Documentation/admin-guide/mm/hugetlbpage.rst
> @@ -128,7 +128,9 @@ hugepages
> implicitly specifies the number of huge pages of default size to
> allocate. If the number of huge pages of default size is implicitly
> specified, it can not be overwritten by a hugepagesz,hugepages
> - parameter pair for the default size.
> + parameter pair for the default size. This parameter also has node
> + format. It specifies numbers of hugepage in a specific node when
> + using node format.
>
> For example, on an architecture with 2M default huge page size::
>
> @@ -138,6 +140,14 @@ hugepages
> indicating that the hugepages=512 parameter is ignored. If a hugepages
> parameter is preceded by an invalid hugepagesz parameter, it will
> be ignored.
> +
> + Node format example::
> +
> + hugepagesz=2M hugepages=0:1,1:2
> +
> + It will allocate 1 2M hugepages in node0 and 2 2M hugepages in node1.
> + If the node number exceeds the maximum node, the parameter will be
> + ignored.
> default_hugepagesz
> Specify the default huge page size. This parameter can
> only be specified once on the command line. default_hugepagesz can
> diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
> index f7ca1a387..5939ecd4f 100644
> --- a/include/linux/hugetlb.h
> +++ b/include/linux/hugetlb.h
> @@ -605,6 +605,7 @@ struct hstate {
> unsigned long nr_overcommit_huge_pages;
> struct list_head hugepage_activelist;
> struct list_head hugepage_freelists[MAX_NUMNODES];
> + unsigned int max_huge_pages_node[MAX_NUMNODES];
> unsigned int nr_huge_pages_node[MAX_NUMNODES];
> unsigned int free_huge_pages_node[MAX_NUMNODES];
> unsigned int surplus_huge_pages_node[MAX_NUMNODES];
> diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> index dfc940d52..317f8fa21 100644
> --- a/mm/hugetlb.c
> +++ b/mm/hugetlb.c
> @@ -66,6 +66,7 @@ static struct hstate * __initdata parsed_hstate;
> static unsigned long __initdata default_hstate_max_huge_pages;
> static bool __initdata parsed_valid_hugepagesz = true;
> static bool __initdata parsed_default_hugepagesz;
> +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata;
>
> /*
> * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
> @@ -2842,10 +2843,75 @@ static void __init gather_bootmem_prealloc(void)
> }
> }
>
> +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
> +{
> + unsigned long i;
> + char buf[32];
> +
> + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) {
> + if (hstate_is_gigantic(h)) {
> + struct huge_bootmem_page *m;
> + void *addr;
> +
> + addr = memblock_alloc_try_nid_raw(
> + huge_page_size(h), huge_page_size(h),
> + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
> + if (!addr)
> + break;
> + m = addr;
> + BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
> + /*
> + * Put them into a private list first because mem_map
> + * is not up yet
> + */
> + INIT_LIST_HEAD(&m->list);
> + list_add(&m->list, &huge_boot_pages);
> + m->hstate = h;
> + } else {
> + struct page *page;
> +
> + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
> +
> + page = alloc_fresh_huge_page(h, gfp_mask, nid,
> + &node_states[N_MEMORY], NULL);
> + if (!page)
> + break;
> + put_page(page); /* free it into the hugepage allocator */
> + }
> + cond_resched();
> + }
> + if (i == h->max_huge_pages_node[nid])
> + return;
> +
> + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
> + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n",
> + h->max_huge_pages_node[nid], buf, nid, i);
> + h->max_huge_pages_node[nid] = i;
> + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i);
> +}
> +
> static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
> {
> unsigned long i;
> nodemask_t *node_alloc_noretry;
> + bool hugetlb_node_set = false;
> +
> + /* skip gigantic hugepages allocation if hugetlb_cma enabled */
> + if (hstate_is_gigantic(h) && hugetlb_cma_size) {
> + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
> + return;
> + }
> +
> + /* do node alloc */
> + for (i = 0; i < nodes_weight(node_states[N_MEMORY]); i++) {
> + if (h->max_huge_pages_node[i] > 0) {
> + hugetlb_hstate_alloc_pages_onenode(h, i);
> + hugetlb_node_set = true;
> + }
> + }
> +
> + if (hugetlb_node_set)
> + return;
>
> if (!hstate_is_gigantic(h)) {
> /*
> @@ -2867,10 +2933,6 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
>
> for (i = 0; i < h->max_huge_pages; ++i) {
> if (hstate_is_gigantic(h)) {
> - if (hugetlb_cma_size) {
> - pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n");
> - goto free;
> - }
> if (!alloc_bootmem_huge_page(h))
> break;
> } else if (!alloc_pool_huge_page(h,
> @@ -2887,7 +2949,6 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
> h->max_huge_pages, buf, i);
> h->max_huge_pages = i;
> }
> -free:
> kfree(node_alloc_noretry);
> }
>
> @@ -3580,6 +3641,10 @@ static int __init hugetlb_init(void)
> default_hstate_max_huge_pages;
> }
> }
> + for (i = 0; i < nodes_weight(node_states[N_MEMORY]); i++)
> + if (default_hugepages_in_node[i] > 0)
> + default_hstate.max_huge_pages_node[i] =
> + default_hugepages_in_node[i];
>
> hugetlb_cma_check();
> hugetlb_init_hstates();
> @@ -3649,6 +3714,10 @@ static int __init hugepages_setup(char *s)
> {
> unsigned long *mhp;
> static unsigned long *last_mhp;
> + unsigned int node = NUMA_NO_NODE;
> + int count;
> + unsigned long tmp;
> + char *p = s;
>
> if (!parsed_valid_hugepagesz) {
> pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s);
> @@ -3672,8 +3741,37 @@ static int __init hugepages_setup(char *s)
> return 0;
> }
>
> - if (sscanf(s, "%lu", mhp) <= 0)
> - *mhp = 0;
> + while (*p) {
> + count = 0;
> + if (sscanf(p, "%lu%n", &tmp, &count) != 1)
> + goto invalid;
> + /* Parameter is node format */
> + if (p[count] == ':') {
> + node = tmp;
> + p += count + 1;
> + if (node < 0 ||
> + node >= nodes_weight(node_states[N_MEMORY]))
> + goto invalid;
> + /* Parse hugepages */
> + if (sscanf(p, "%lu%n", &tmp, &count) != 1)
> + goto invalid;
> + if (!hugetlb_max_hstate)
> + default_hugepages_in_node[node] = tmp;
> + else
> + parsed_hstate->max_huge_pages_node[node] = tmp;
> + *mhp += tmp;
> + /* Go to parse next node*/
> + if (p[count] == ',')
> + p += count + 1;
> + else
> + break;
> + } else {
> + if (p != s)
> + goto invalid;
> + *mhp = tmp;
> + break;
> + }
> + }
>
> /*
> * Global state is always initialized later in hugetlb_init.
> @@ -3686,6 +3784,10 @@ static int __init hugepages_setup(char *s)
> last_mhp = mhp;
>
> return 1;
> +
> +invalid:
> + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p);
> + return 0;
> }
> __setup("hugepages=", hugepages_setup);
>
> --
> 2.27.0
>
