[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <083829f3f633d6d24d64d4639f92d163355b24fd.1726009989.git.ackerleytng@google.com>
Date: Tue, 10 Sep 2024 23:43:41 +0000
From: Ackerley Tng <ackerleytng@...gle.com>
To: tabba@...gle.com, quic_eberman@...cinc.com, roypat@...zon.co.uk,
jgg@...dia.com, peterx@...hat.com, david@...hat.com, rientjes@...gle.com,
fvdl@...gle.com, jthoughton@...gle.com, seanjc@...gle.com,
pbonzini@...hat.com, zhiquan1.li@...el.com, fan.du@...el.com,
jun.miao@...el.com, isaku.yamahata@...el.com, muchun.song@...ux.dev,
mike.kravetz@...cle.com
Cc: erdemaktas@...gle.com, vannapurve@...gle.com, ackerleytng@...gle.com,
qperret@...gle.com, jhubbard@...dia.com, willy@...radead.org,
shuah@...nel.org, brauner@...nel.org, bfoster@...hat.com,
kent.overstreet@...ux.dev, pvorel@...e.cz, rppt@...nel.org,
richard.weiyang@...il.com, anup@...infault.org, haibo1.xu@...el.com,
ajones@...tanamicro.com, vkuznets@...hat.com, maciej.wieczor-retman@...el.com,
pgonda@...gle.com, oliver.upton@...ux.dev, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, kvm@...r.kernel.org, linux-kselftest@...r.kernel.org,
linux-fsdevel@...ck.org
Subject: [RFC PATCH 10/39] mm: hugetlb: Add option to create new subpool
without using surplus
__hugetlb_acct_memory() today does more than just memory
accounting. when there's insufficient HugeTLB pages,
__hugetlb_acct_memory() will attempt to get surplus pages.
This change adds a flag to disable getting surplus pages if there are
insufficient HugeTLB pages.
Signed-off-by: Ackerley Tng <ackerleytng@...gle.com>
---
fs/hugetlbfs/inode.c | 2 +-
include/linux/hugetlb.h | 2 +-
mm/hugetlb.c | 43 ++++++++++++++++++++++++++++++-----------
3 files changed, 34 insertions(+), 13 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 9f6cff356796..300a6ef300c1 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1488,7 +1488,7 @@ hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
if (ctx->max_hpages != -1 || ctx->min_hpages != -1) {
sbinfo->spool = hugepage_new_subpool(ctx->hstate,
ctx->max_hpages,
- ctx->min_hpages);
+ ctx->min_hpages, true);
if (!sbinfo->spool)
goto out_free;
}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 907cfbbd9e24..9ef1adbd3207 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -116,7 +116,7 @@ extern int hugetlb_max_hstate __read_mostly;
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
- long min_hpages);
+ long min_hpages, bool use_surplus);
void hugepage_put_subpool(struct hugepage_subpool *spool);
long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 808915108126..efdb5772b367 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -92,6 +92,7 @@ static int num_fault_mutexes;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
/* Forward declaration */
+static int __hugetlb_acct_memory(struct hstate *h, long delta, bool use_surplus);
static int hugetlb_acct_memory(struct hstate *h, long delta);
static void hugetlb_vma_lock_free(struct vm_area_struct *vma);
static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
@@ -129,7 +130,7 @@ static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
}
struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
- long min_hpages)
+ long min_hpages, bool use_surplus)
{
struct hugepage_subpool *spool;
@@ -143,7 +144,8 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
spool->hstate = h;
spool->min_hpages = min_hpages;
- if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
+ if (min_hpages != -1 &&
+ __hugetlb_acct_memory(h, min_hpages, use_surplus)) {
kfree(spool);
return NULL;
}
@@ -2592,6 +2594,21 @@ static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
return NULL;
}
+static int hugetlb_hstate_reserve_pages(struct hstate *h,
+ long num_pages_to_reserve)
+ __must_hold(&hugetlb_lock)
+{
+ long needed;
+
+ needed = (h->resv_huge_pages + num_pages_to_reserve) - h->free_huge_pages;
+ if (needed <= 0) {
+ h->resv_huge_pages += num_pages_to_reserve;
+ return 0;
+ }
+
+ return needed;
+}
+
/*
* Increase the hugetlb pool such that it can accommodate a reservation
* of size 'delta'.
@@ -2608,13 +2625,7 @@ static int gather_surplus_pages(struct hstate *h, long delta)
int node;
nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
- lockdep_assert_held(&hugetlb_lock);
- needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
- if (needed <= 0) {
- h->resv_huge_pages += delta;
- return 0;
- }
-
+ needed = delta;
allocated = 0;
ret = -ENOMEM;
@@ -5104,7 +5115,7 @@ unsigned long hugetlb_total_pages(void)
return nr_total_pages;
}
-static int hugetlb_acct_memory(struct hstate *h, long delta)
+static int __hugetlb_acct_memory(struct hstate *h, long delta, bool use_surplus)
{
int ret = -ENOMEM;
@@ -5136,7 +5147,12 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
* above.
*/
if (delta > 0) {
- if (gather_surplus_pages(h, delta) < 0)
+ long required_surplus = hugetlb_hstate_reserve_pages(h, delta);
+
+ if (!use_surplus && required_surplus > 0)
+ goto out;
+
+ if (gather_surplus_pages(h, required_surplus) < 0)
goto out;
if (delta > allowed_mems_nr(h)) {
@@ -5154,6 +5170,11 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
return ret;
}
+static int hugetlb_acct_memory(struct hstate *h, long delta)
+{
+ return __hugetlb_acct_memory(h, delta, true);
+}
+
static void hugetlb_vm_op_open(struct vm_area_struct *vma)
{
struct resv_map *resv = vma_resv_map(vma);
--
2.46.0.598.g6f2099f65c-goog
Powered by blists - more mailing lists