linux-kernel - [RFC 09/14] mm/vmalloc: Add a get_vm_area_node() and vmap_pages_range

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 for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 11 Mar 2024 16:46:33 +0000
From: Pasha Tatashin <pasha.tatashin@...een.com>
To: linux-kernel@...r.kernel.org,
	linux-mm@...ck.org,
	akpm@...ux-foundation.org,
	x86@...nel.org,
	bp@...en8.de,
	brauner@...nel.org,
	bristot@...hat.com,
	bsegall@...gle.com,
	dave.hansen@...ux.intel.com,
	dianders@...omium.org,
	dietmar.eggemann@....com,
	eric.devolder@...cle.com,
	hca@...ux.ibm.com,
	hch@...radead.org,
	hpa@...or.com,
	jacob.jun.pan@...ux.intel.com,
	jgg@...pe.ca,
	jpoimboe@...nel.org,
	jroedel@...e.de,
	juri.lelli@...hat.com,
	kent.overstreet@...ux.dev,
	kinseyho@...gle.com,
	kirill.shutemov@...ux.intel.com,
	lstoakes@...il.com,
	luto@...nel.org,
	mgorman@...e.de,
	mic@...ikod.net,
	michael.christie@...cle.com,
	mingo@...hat.com,
	mjguzik@...il.com,
	mst@...hat.com,
	npiggin@...il.com,
	peterz@...radead.org,
	pmladek@...e.com,
	rick.p.edgecombe@...el.com,
	rostedt@...dmis.org,
	surenb@...gle.com,
	tglx@...utronix.de,
	urezki@...il.com,
	vincent.guittot@...aro.org,
	vschneid@...hat.com,
	pasha.tatashin@...een.com
Subject: [RFC 09/14] mm/vmalloc: Add a get_vm_area_node() and vmap_pages_range_noflush() public functions

get_vm_area_node()
Unlike the other public get_vm_area_* variants, this one accepts node
from which to allocate data structure, and also the align, which allows
to create vm area with a specific alignment.

This call is going to be used by dynamic stacks in order to ensure that
the stack VM area of a specific alignment, and that even if there is
only one page mapped, no page table allocations are going to be needed
to map the other stack pages.

vmap_pages_range_noflush()
Is already a global function, but was exported through mm/internal.h,
since we will need it from kernel/fork.c in order to map the initial
stack pages, move the forward declaration of this function to the
linux/vmalloc.h header.

Signed-off-by: Pasha Tatashin <pasha.tatashin@...een.com>
---
 include/linux/vmalloc.h | 15 +++++++++++++++
 mm/internal.h           |  9 ---------
 mm/vmalloc.c            | 24 ++++++++++++++++++++++++
 3 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index c720be70c8dd..e18b6ab1584b 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -210,6 +210,9 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long flags,
 					unsigned long start, unsigned long end,
 					const void *caller);
+struct vm_struct *get_vm_area_node(unsigned long size, unsigned long align,
+				   unsigned long flags, int node, gfp_t gfp,
+				   const void *caller);
 void free_vm_area(struct vm_struct *area);
 extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
@@ -241,10 +244,22 @@ static inline void set_vm_flush_reset_perms(void *addr)
 		vm->flags |= VM_FLUSH_RESET_PERMS;
 }
 
+int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+					  pgprot_t prot, struct page **pages,
+					  unsigned int page_shift);
+
 #else
 static inline void set_vm_flush_reset_perms(void *addr)
 {
 }
+
+static inline
+int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+					  pgprot_t prot, struct page **pages,
+					  unsigned int page_shift)
+{
+	return -EINVAL;
+}
 #endif
 
 /* for /proc/kcore */
diff --git a/mm/internal.h b/mm/internal.h
index f309a010d50f..ba1e2ce68157 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -969,19 +969,10 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
  */
 #ifdef CONFIG_MMU
 void __init vmalloc_init(void);
-int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
-                pgprot_t prot, struct page **pages, unsigned int page_shift);
 #else
 static inline void vmalloc_init(void)
 {
 }
-
-static inline
-int __must_check vmap_pages_range_noflush(unsigned long addr, unsigned long end,
-                pgprot_t prot, struct page **pages, unsigned int page_shift)
-{
-	return -EINVAL;
-}
 #endif
 
 int __must_check __vmap_pages_range_noflush(unsigned long addr,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d12a17fc0c17..7dcba463ff99 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2650,6 +2650,30 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 				  NUMA_NO_NODE, GFP_KERNEL, caller);
 }
 
+/**
+ * get_vm_area_node - reserve a contiguous and aligned kernel virtual area
+ * @size:	 size of the area
+ * @align:	 alignment of the start address of the area
+ * @flags:	 %VM_IOREMAP for I/O mappings
+ * @node:	 NUMA node from which to allocate the area data structure
+ * @gfp:	 Flags to pass to the allocator
+ * @caller:	 Caller to be stored in the vm area data structure
+ *
+ * Search an area of @size/align in the kernel virtual mapping area,
+ * and reserved it for out purposes.  Returns the area descriptor
+ * on success or %NULL on failure.
+ *
+ * Return: the area descriptor on success or %NULL on failure.
+ */
+struct vm_struct *get_vm_area_node(unsigned long size, unsigned long align,
+				   unsigned long flags, int node, gfp_t gfp,
+				   const void *caller)
+{
+	return __get_vm_area_node(size, align, PAGE_SHIFT, flags,
+				  VMALLOC_START, VMALLOC_END,
+				  node, gfp, caller);
+}
+
 /**
  * find_vm_area - find a continuous kernel virtual area
  * @addr:	  base address
-- 
2.44.0.278.ge034bb2e1d-goog