| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <3f2ac9240cd39295e7341d408548719818d5ea91.1747264138.git.ackerleytng@google.com>
Date: Wed, 14 May 2025 16:42:03 -0700
From: Ackerley Tng <ackerleytng@...gle.com>
To: kvm@...r.kernel.org, linux-mm@...ck.org, linux-kernel@...r.kernel.org,
x86@...nel.org, linux-fsdevel@...r.kernel.org
Cc: ackerleytng@...gle.com, aik@....com, ajones@...tanamicro.com,
akpm@...ux-foundation.org, amoorthy@...gle.com, anthony.yznaga@...cle.com,
anup@...infault.org, aou@...s.berkeley.edu, bfoster@...hat.com,
binbin.wu@...ux.intel.com, brauner@...nel.org, catalin.marinas@....com,
chao.p.peng@...el.com, chenhuacai@...nel.org, dave.hansen@...el.com,
david@...hat.com, dmatlack@...gle.com, dwmw@...zon.co.uk,
erdemaktas@...gle.com, fan.du@...el.com, fvdl@...gle.com, graf@...zon.com,
haibo1.xu@...el.com, hch@...radead.org, hughd@...gle.com, ira.weiny@...el.com,
isaku.yamahata@...el.com, jack@...e.cz, james.morse@....com,
jarkko@...nel.org, jgg@...pe.ca, jgowans@...zon.com, jhubbard@...dia.com,
jroedel@...e.de, jthoughton@...gle.com, jun.miao@...el.com,
kai.huang@...el.com, keirf@...gle.com, kent.overstreet@...ux.dev,
kirill.shutemov@...el.com, liam.merwick@...cle.com,
maciej.wieczor-retman@...el.com, mail@...iej.szmigiero.name, maz@...nel.org,
mic@...ikod.net, michael.roth@....com, mpe@...erman.id.au,
muchun.song@...ux.dev, nikunj@....com, nsaenz@...zon.es,
oliver.upton@...ux.dev, palmer@...belt.com, pankaj.gupta@....com,
paul.walmsley@...ive.com, pbonzini@...hat.com, pdurrant@...zon.co.uk,
peterx@...hat.com, pgonda@...gle.com, pvorel@...e.cz, qperret@...gle.com,
quic_cvanscha@...cinc.com, quic_eberman@...cinc.com,
quic_mnalajal@...cinc.com, quic_pderrin@...cinc.com, quic_pheragu@...cinc.com,
quic_svaddagi@...cinc.com, quic_tsoni@...cinc.com, richard.weiyang@...il.com,
rick.p.edgecombe@...el.com, rientjes@...gle.com, roypat@...zon.co.uk,
rppt@...nel.org, seanjc@...gle.com, shuah@...nel.org, steven.price@....com,
steven.sistare@...cle.com, suzuki.poulose@....com, tabba@...gle.com,
thomas.lendacky@....com, usama.arif@...edance.com, vannapurve@...gle.com,
vbabka@...e.cz, viro@...iv.linux.org.uk, vkuznets@...hat.com,
wei.w.wang@...el.com, will@...nel.org, willy@...radead.org,
xiaoyao.li@...el.com, yan.y.zhao@...el.com, yilun.xu@...el.com,
yuzenghui@...wei.com, zhiquan1.li@...el.com
Subject: [RFC PATCH v2 24/51] 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>
Change-Id: Id79fdeaa236b4fed38fc3c20482b03fff729198f
---
fs/hugetlbfs/inode.c | 2 +-
include/linux/hugetlb.h | 2 +-
mm/hugetlb.c | 77 +++++++++++++++++++++++++++++++----------
3 files changed, 61 insertions(+), 20 deletions(-)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e4de5425838d..609a88950354 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1424,7 +1424,7 @@ 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 8ba941d88956..c59264391c33 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);
void hugetlb_dup_vma_private(struct vm_area_struct *vma);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5b088fe002a2..d22c5a8fd441 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -115,6 +115,7 @@ static int num_fault_mutexes __ro_after_init;
struct mutex *hugetlb_fault_mutex_table __ro_after_init;
/* 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);
@@ -162,7 +163,7 @@ 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;
@@ -176,7 +177,8 @@ 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;
}
@@ -2382,35 +2384,64 @@ static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
return NULL;
}
-/*
- * Increase the hugetlb pool such that it can accommodate a reservation
- * of size 'delta'.
+/**
+ * hugetlb_hstate_reserve_pages() - Reserve @requested number of hugetlb pages
+ * from hstate @h.
+ *
+ * @h: the hstate to reserve from.
+ * @requested: number of hugetlb pages to reserve.
+ *
+ * If there are insufficient available hugetlb pages, no reservations are made.
+ *
+ * Return: the number of surplus pages required to meet the @requested number of
+ * hugetlb pages.
*/
-static int gather_surplus_pages(struct hstate *h, long delta)
+static int hugetlb_hstate_reserve_pages(struct hstate *h, long requested)
+ __must_hold(&hugetlb_lock)
+{
+ long needed;
+
+ needed = (h->resv_huge_pages + requested) - h->free_huge_pages;
+ if (needed <= 0) {
+ h->resv_huge_pages += requested;
+ return 0;
+ }
+
+ return needed;
+}
+
+/**
+ * gather_surplus_pages() - Increase the hugetlb pool such that it can
+ * accommodate a reservation of size @requested.
+ *
+ * @h: the hstate in concern.
+ * @requested: The requested number of hugetlb pages.
+ * @needed: The number of hugetlb pages the pool needs to be increased by, based
+ * on current number of reservations and free hugetlb pages.
+ *
+ * Return: 0 if successful or negative error otherwise.
+ */
+static int gather_surplus_pages(struct hstate *h, long requested, long needed)
__must_hold(&hugetlb_lock)
{
LIST_HEAD(surplus_list);
struct folio *folio, *tmp;
int ret;
long i;
- long needed, allocated;
+ long allocated;
bool alloc_ok = true;
int node;
nodemask_t *mbind_nodemask, alloc_nodemask;
+ if (needed == 0)
+ return 0;
+
mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
if (mbind_nodemask)
nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed);
else
alloc_nodemask = cpuset_current_mems_allowed;
- 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;
- }
-
allocated = 0;
ret = -ENOMEM;
@@ -2448,7 +2479,7 @@ static int gather_surplus_pages(struct hstate *h, long delta)
* because either resv_huge_pages or free_huge_pages may have changed.
*/
spin_lock_irq(&hugetlb_lock);
- needed = (h->resv_huge_pages + delta) -
+ needed = (h->resv_huge_pages + requested) -
(h->free_huge_pages + allocated);
if (needed > 0) {
if (alloc_ok)
@@ -2469,7 +2500,7 @@ static int gather_surplus_pages(struct hstate *h, long delta)
* before they are reserved.
*/
needed += allocated;
- h->resv_huge_pages += delta;
+ h->resv_huge_pages += requested;
ret = 0;
/* Free the needed pages to the hugetlb pool */
@@ -5284,7 +5315,7 @@ 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;
@@ -5316,7 +5347,12 @@ static int hugetlb_acct_memory(struct hstate *h, long delta)
* above.
*/
if (delta > 0) {
- if (gather_surplus_pages(h, delta) < 0)
+ long needed = hugetlb_hstate_reserve_pages(h, delta);
+
+ if (!use_surplus && needed > 0)
+ goto out;
+
+ if (gather_surplus_pages(h, delta, needed) < 0)
goto out;
if (delta > allowed_mems_nr(h)) {
@@ -5334,6 +5370,11 @@ 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);
--
2.49.0.1045.g170613ef41-goog
Powered by blists - more mailing lists