linux-kernel - [RFC 08/14] fork: separate vmap stack alloction and free calls

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]

Date: Mon, 11 Mar 2024 16:46:32 +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 08/14] fork: separate vmap stack alloction and free calls

In preparation for the dynamic stacks, separate out the
__vmalloc_node_range and vfree calls from the vmap based stack
allocations. The dynamic stacks will use their own variants of these
functions.

Signed-off-by: Pasha Tatashin <pasha.tatashin@...een.com>
---
 kernel/fork.c | 53 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/kernel/fork.c b/kernel/fork.c
index 3004e6ce6c65..bbae5f705773 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -204,6 +204,29 @@ static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area)
 	return false;
 }
 
+static inline struct vm_struct *alloc_vmap_stack(int node)
+{
+	void *stack;
+
+	/*
+	 * Allocated stacks are cached and later reused by new threads,
+	 * so memcg accounting is performed manually on assigning/releasing
+	 * stacks to tasks. Drop __GFP_ACCOUNT.
+	 */
+	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
+				     VMALLOC_START, VMALLOC_END,
+				     THREADINFO_GFP & ~__GFP_ACCOUNT,
+				     PAGE_KERNEL,
+				     0, node, __builtin_return_address(0));
+
+	return (stack) ? find_vm_area(stack) : NULL;
+}
+
+static inline void free_vmap_stack(struct vm_struct *vm_area)
+{
+	vfree(vm_area->addr);
+}
+
 static void thread_stack_free_rcu(struct rcu_head *rh)
 {
 	struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu);
@@ -212,7 +235,7 @@ static void thread_stack_free_rcu(struct rcu_head *rh)
 	if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area))
 		return;
 
-	vfree(vm_area->addr);
+	free_vmap_stack(vm_area);
 }
 
 static void thread_stack_delayed_free(struct task_struct *tsk)
@@ -235,7 +258,7 @@ static int free_vm_stack_cache(unsigned int cpu)
 		if (!vm_area)
 			continue;
 
-		vfree(vm_area->addr);
+		free_vmap_stack(vm_area);
 		cached_vm_stacks[i] = NULL;
 	}
 
@@ -265,7 +288,6 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 {
 	struct vm_struct *vm_area;
 	int i, j, nr_pages;
-	void *stack;
 
 	for (i = 0; i < NR_CACHED_STACKS; i++) {
 		vm_area = this_cpu_xchg(cached_stacks[i], NULL);
@@ -273,14 +295,13 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 			continue;
 
 		if (memcg_charge_kernel_stack(vm_area)) {
-			vfree(vm_area->addr);
+			free_vmap_stack(vm_area);
 			return -ENOMEM;
 		}
 
 		/* Reset stack metadata. */
 		kasan_unpoison_range(vm_area->addr, THREAD_SIZE);
-
-		stack = kasan_reset_tag(vm_area->addr);
+		tsk->stack = kasan_reset_tag(vm_area->addr);
 
 		/* Clear stale pointers from reused stack. */
 		nr_pages = vm_area->nr_pages;
@@ -288,26 +309,15 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 			clear_page(page_address(vm_area->pages[j]));
 
 		tsk->stack_vm_area = vm_area;
-		tsk->stack = stack;
 		return 0;
 	}
 
-	/*
-	 * Allocated stacks are cached and later reused by new threads,
-	 * so memcg accounting is performed manually on assigning/releasing
-	 * stacks to tasks. Drop __GFP_ACCOUNT.
-	 */
-	stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
-				     VMALLOC_START, VMALLOC_END,
-				     THREADINFO_GFP & ~__GFP_ACCOUNT,
-				     PAGE_KERNEL,
-				     0, node, __builtin_return_address(0));
-	if (!stack)
+	vm_area = alloc_vmap_stack(node);
+	if (!vm_area)
 		return -ENOMEM;
 
-	vm_area = find_vm_area(stack);
 	if (memcg_charge_kernel_stack(vm_area)) {
-		vfree(stack);
+		free_vmap_stack(vm_area);
 		return -ENOMEM;
 	}
 	/*
@@ -316,8 +326,7 @@ static int alloc_thread_stack_node(struct task_struct *tsk, int node)
 	 * so cache the vm_struct.
 	 */
 	tsk->stack_vm_area = vm_area;
-	stack = kasan_reset_tag(stack);
-	tsk->stack = stack;
+	tsk->stack = kasan_reset_tag(vm_area->addr);
 	return 0;
 }
 
-- 
2.44.0.278.ge034bb2e1d-goog