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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250915134041.151462-7-urezki@gmail.com>
Date: Mon, 15 Sep 2025 15:40:36 +0200
From: "Uladzislau Rezki (Sony)" <urezki@...il.com>
To: linux-mm@...ck.org,
	Andrew Morton <akpm@...ux-foundation.org>
Cc: Michal Hocko <mhocko@...nel.org>,
	Baoquan He <bhe@...hat.com>,
	LKML <linux-kernel@...r.kernel.org>,
	Uladzislau Rezki <urezki@...il.com>,
	Michal Hocko <mhocko@...e.com>
Subject: [PATCH v2 06/10] mm/vmalloc: Handle non-blocking GFP in __vmalloc_area_node()

Make __vmalloc_area_node() respect non-blocking GFP masks such
as GFP_ATOMIC and GFP_NOWAIT.

- Add memalloc_apply_gfp_scope()/memalloc_restore_scope()
  helpers to apply a proper scope.
- Apply memalloc_apply_gfp_scope()/memalloc_restore_scope()
  around vmap_pages_range() for page table setup.
- Set "nofail" to false if a non-blocking mask is used, as
  they are mutually exclusive.

This is particularly important for page table allocations that
internally use GFP_PGTABLE_KERNEL, which may sleep unless such
scope restrictions are applied. For example:

<snip>
__pte_alloc_kernel()
  pte_alloc_one_kernel(&init_mm);
    pagetable_alloc_noprof(GFP_PGTABLE_KERNEL & ~__GFP_HIGHMEM, 0);
<snip>

Note: in most cases, PTE entries are established only up to the
level required by current vmap space usage, meaning the page tables
are typically fully populated during the mapping process.

Acked-by: Michal Hocko <mhocko@...e.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@...il.com>
---
 include/linux/vmalloc.h |  2 ++
 mm/vmalloc.c            | 52 +++++++++++++++++++++++++++++++++--------
 2 files changed, 44 insertions(+), 10 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 97252078a3dc..dcbcbfa842ae 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -326,4 +326,6 @@ bool vmalloc_dump_obj(void *object);
 static inline bool vmalloc_dump_obj(void *object) { return false; }
 #endif
 
+unsigned int memalloc_apply_gfp_scope(gfp_t gfp_mask);
+void memalloc_restore_scope(unsigned int flags);
 #endif /* _LINUX_VMALLOC_H */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e61e62872372..5e01c6ac4aca 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3715,6 +3715,42 @@ static void defer_vm_area_cleanup(struct vm_struct *area)
 		schedule_work(&cleanup_vm_area);
 }
 
+/*
+ * Page tables allocations ignore external GFP. Enforces it by
+ * the memalloc scope API. It is used by vmalloc internals and
+ * KASAN shadow population only.
+ *
+ * GFP to scope mapping:
+ *
+ * non-blocking (no __GFP_DIRECT_RECLAIM) - memalloc_noreclaim_save()
+ * GFP_NOFS - memalloc_nofs_save()
+ * GFP_NOIO - memalloc_noio_save()
+ *
+ * Returns a flag cookie to pair with restore.
+ */
+unsigned int
+memalloc_apply_gfp_scope(gfp_t gfp_mask)
+{
+	unsigned int flags = 0;
+
+	if (!gfpflags_allow_blocking(gfp_mask))
+		flags = memalloc_noreclaim_save();
+	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
+		flags = memalloc_nofs_save();
+	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
+		flags = memalloc_noio_save();
+
+	/* 0 - no scope applied. */
+	return flags;
+}
+
+void
+memalloc_restore_scope(unsigned int flags)
+{
+	if (flags)
+		memalloc_flags_restore(flags);
+}
+
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, unsigned int page_shift,
 				 int node)
@@ -3731,6 +3767,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
 
+	/* __GFP_NOFAIL and "noblock" flags are mutually exclusive. */
+	if (!gfpflags_allow_blocking(gfp_mask))
+		nofail = false;
+
 	if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
 		gfp_mask |= __GFP_HIGHMEM;
 
@@ -3796,22 +3836,14 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	 * page tables allocations ignore external gfp mask, enforce it
 	 * by the scope API
 	 */
-	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
-		flags = memalloc_nofs_save();
-	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
-		flags = memalloc_noio_save();
-
+	flags = memalloc_apply_gfp_scope(gfp_mask);
 	do {
 		ret = vmap_pages_range(addr, addr + size, prot, area->pages,
 			page_shift);
 		if (nofail && (ret < 0))
 			schedule_timeout_uninterruptible(1);
 	} while (nofail && (ret < 0));
-
-	if ((gfp_mask & (__GFP_FS | __GFP_IO)) == __GFP_IO)
-		memalloc_nofs_restore(flags);
-	else if ((gfp_mask & (__GFP_FS | __GFP_IO)) == 0)
-		memalloc_noio_restore(flags);
+	memalloc_restore_scope(flags);
 
 	if (ret < 0) {
 		warn_alloc(gfp_mask, NULL,
-- 
2.47.3


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ