linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Gang Li <gang.li@linux.dev>
To: David Hildenbrand <david@redhat.com>,
	David Rientjes <rientjes@google.com>,
	Mike Kravetz <mike.kravetz@oracle.com>,
	Muchun Song <muchun.song@linux.dev>,
	Andrew Morton <akpm@linux-foundation.org>,
	Tim Chen <tim.c.chen@linux.intel.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	ligang.bdlg@bytedance.com, Gang Li <gang.li@linux.dev>
Subject: [PATCH v4 2/7] hugetlb: split hugetlb_hstate_alloc_pages
Date: Thu, 18 Jan 2024 20:39:06 +0800	[thread overview]
Message-ID: <20240118123911.88833-3-gang.li@linux.dev> (raw)
In-Reply-To: <20240118123911.88833-1-gang.li@linux.dev>

1G and 2M huge pages have different allocation and initialization logic,
which leads to subtle differences in parallelization. Therefore, it is
appropriate to split hugetlb_hstate_alloc_pages into gigantic and
non-gigantic.

This patch has no functional changes.

Signed-off-by: Gang Li <gang.li@linux.dev>
Tested-by: David Rientjes <rientjes@google.com>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 mm/hugetlb.c | 87 ++++++++++++++++++++++++++--------------------------
 1 file changed, 43 insertions(+), 44 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b8e4a6adefd6..98ae108e1fac 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3509,6 +3509,43 @@ static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated,
 	}
 }
 
+static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h)
+{
+	unsigned long i;
+
+	for (i = 0; i < h->max_huge_pages; ++i) {
+		if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
+			break;
+		cond_resched();
+	}
+
+	return i;
+}
+
+static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
+{
+	unsigned long i;
+	struct folio *folio;
+	LIST_HEAD(folio_list);
+	nodemask_t node_alloc_noretry;
+
+	/* Bit mask controlling how hard we retry per-node allocations.*/
+	nodes_clear(node_alloc_noretry);
+
+	for (i = 0; i < h->max_huge_pages; ++i) {
+		folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
+						&node_alloc_noretry);
+		if (!folio)
+			break;
+		list_add(&folio->lru, &folio_list);
+		cond_resched();
+	}
+
+	prep_and_add_allocated_folios(h, &folio_list);
+
+	return i;
+}
+
 /*
  * NOTE: this routine is called in different contexts for gigantic and
  * non-gigantic pages.
@@ -3522,10 +3559,7 @@ static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated,
  */
 static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 {
-	unsigned long i;
-	struct folio *folio;
-	LIST_HEAD(folio_list);
-	nodemask_t *node_alloc_noretry;
+	unsigned long allocated;
 
 	/* skip gigantic hugepages allocation if hugetlb_cma enabled */
 	if (hstate_is_gigantic(h) && hugetlb_cma_size) {
@@ -3538,47 +3572,12 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		return;
 
 	/* below will do all node balanced alloc */
-	if (!hstate_is_gigantic(h)) {
-		/*
-		 * Bit mask controlling how hard we retry per-node allocations.
-		 * Ignore errors as lower level routines can deal with
-		 * node_alloc_noretry == NULL.  If this kmalloc fails at boot
-		 * time, we are likely in bigger trouble.
-		 */
-		node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry),
-						GFP_KERNEL);
-	} else {
-		/* allocations done at boot time */
-		node_alloc_noretry = NULL;
-	}
-
-	/* bit mask controlling how hard we retry per-node allocations */
-	if (node_alloc_noretry)
-		nodes_clear(*node_alloc_noretry);
-
-	for (i = 0; i < h->max_huge_pages; ++i) {
-		if (hstate_is_gigantic(h)) {
-			/*
-			 * gigantic pages not added to list as they are not
-			 * added to pools now.
-			 */
-			if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
-				break;
-		} else {
-			folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
-							node_alloc_noretry);
-			if (!folio)
-				break;
-			list_add(&folio->lru, &folio_list);
-		}
-		cond_resched();
-	}
-
-	/* list will be empty if hstate_is_gigantic */
-	prep_and_add_allocated_folios(h, &folio_list);
+	if (hstate_is_gigantic(h))
+		allocated = hugetlb_gigantic_pages_alloc_boot(h);
+	else
+		allocated = hugetlb_pages_alloc_boot(h);
 
-	hugetlb_hstate_alloc_pages_errcheck(i, h);
-	kfree(node_alloc_noretry);
+	hugetlb_hstate_alloc_pages_errcheck(allocated, h);
 }
 
 static void __init hugetlb_init_hstates(void)
-- 
2.20.1



  parent reply	other threads:[~2024-01-18 12:39 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-01-18 12:39 [RESEND PATCH v4 0/7] hugetlb: parallelize hugetlb page init on boot Gang Li
2024-01-18 12:39 ` [PATCH v4 1/7] hugetlb: code clean for hugetlb_hstate_alloc_pages Gang Li
2024-01-18 12:39 ` Gang Li [this message]
2024-01-22  3:43   ` [PATCH v4 2/7] hugetlb: split hugetlb_hstate_alloc_pages Muchun Song
2024-01-18 12:39 ` [PATCH v4 3/7] padata: dispatch works on different nodes Gang Li
2024-01-18 23:04   ` Tim Chen
2024-01-19 15:05     ` Gang Li
2024-01-19  2:59   ` Muchun Song
2024-01-19 15:04     ` Gang Li
2024-01-18 12:39 ` [PATCH v4 4/7] hugetlb: pass *next_nid_to_alloc directly to for_each_node_mask_to_alloc Gang Li
2024-01-18 23:01   ` Tim Chen
2024-01-19  2:54   ` Muchun Song
2024-01-22  6:16   ` Muchun Song
2024-01-22  9:14     ` Gang Li
2024-01-22  9:50       ` Muchun Song
2024-01-18 12:39 ` [PATCH v4 5/7] hugetlb: have CONFIG_HUGETLBFS select CONFIG_PADATA Gang Li
2024-01-18 12:39 ` [PATCH v4 6/7] hugetlb: parallelize 2M hugetlb allocation and initialization Gang Li
2024-01-22  7:10   ` Muchun Song
2024-01-22 10:12     ` Gang Li
2024-01-22 11:30       ` Muchun Song
2024-01-23  2:12         ` Gang Li
2024-01-23  3:32           ` Muchun Song
2024-01-18 12:39 ` [PATCH v4 7/7] hugetlb: parallelize 1G hugetlb initialization Gang Li
2024-01-18 14:22   ` Kefeng Wang
2024-01-19 14:45     ` Gang Li
2024-01-24  9:23   ` Muchun Song
2024-01-24 10:52     ` Gang Li
2024-01-25  2:48       ` Muchun Song
2024-01-25  3:47         ` Gang Li
2024-01-25  3:56         ` Gang Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240118123911.88833-3-gang.li@linux.dev \
    --to=gang.li@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=david@redhat.com \
    --cc=ligang.bdlg@bytedance.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mike.kravetz@oracle.com \
    --cc=muchun.song@linux.dev \
    --cc=rientjes@google.com \
    --cc=tim.c.chen@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).