FAILED: patch "[PATCH] mm/secretmem: properly account locked pages" failed to apply to 6.6-stable tree

The patch below does not apply to the 6.6-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y
git checkout FETCH_HEAD
git cherry-pick -x 97d34aa65c29cca85e3e9050f4c936389b38a054
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026090831-recent-irregular-5144@gregkh' --subject-prefix 'PATCH 6.6.y' 'HEAD^..'

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 97d34aa65c29cca85e3e9050f4c936389b38a054 Mon Sep 17 00:00:00 2001
From: "Lorenzo Stoakes (ARM)" <[email protected]>
Date: Wed, 26 Aug 2026 17:30:35 +0100
Subject: [PATCH] mm/secretmem: properly account locked pages

secretmem accounts folios by treating memory as if it were mlock()'d and thus limited by the RLIMIT_MEMLOCK limit.

However the folios are unevictable and remain so until the inode is evicted, eliminating usual mlock() semantics - mapping folios then unmapping them does not clear their unevictable state, since it depends on AS_UNEVICTABLE, not PG_mlocked.

A user can therefore easily work around the RLIMIT_MEMLOCK limit - simply map then unmap and VmLck no longer counts the secretmem range. Worse, folios are not accounted in the process's RSS, meaning the OOM killer won't know to kill the process.

Repeatedly mapping/unmapping (or forking) can then result in the consumption of all available system memory with unevictable folios and cause system instability.

A secretmem fd can be passed between processes and over fork so a per-process limit simply does not make sense, so follow the precedent set by io_uring, perf, skbuff, iommufd and xdp by tracking the number of locked pages in user_struct->locked_vm.

Since the scope tracked is actually inode lifetime, the RLIMIT_MEMLOCK applies per-user not per-process, so it doesn't make sense to bypass for users with CAP_IPC_LOCK, therefore remove this bypass.

There is simply no reason to carry on marking the mapping as mlock()'d since it's misleading and the lifecycle is now correctly handled, so remove this too.

Note that secretmem does not support any form of truncation (including hole punching) and the folios are unreclaimable, so the folios need only be accounted on fault and unaccounted on inode destruction.

__secretmem_account_pages() is more or less a duplicate of the code that io_uring etc. use, but since this is a bug fix that needs backporting, defer any de-duplication efforts to a follow-up.

test_mlock_limit() asserts mlock_future_ok() on mmap(), however this has been removed, so remove the test altogether for the fix. A new test will be sent separately for upstream.

index 4cc52698e214..8d7e5521f7cd 100644
@@ -25,7 +25,8 @@ struct user_struct {
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
 	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
-	defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD)
+	defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \
+	defined(CONFIG_SECRETMEM)
 	atomic_long_t locked_vm;
 #endif
 #ifdef CONFIG_WATCH_QUEUE

index aac4f795c327..c55d84c5e613 100644
@@ -57,33 +57,6 @@ static void test_file_apis(int fd)
 		pass("file IO is blocked as expected\n");
 }
 
-static void test_mlock_limit(int fd)
-{
-	size_t len;
-	char *mem;
-
-	len = mlock_limit_cur;
-	if (len % page_size != 0)
-		len = (len/page_size) * page_size;
-
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem == MAP_FAILED) {
-		fail("unable to mmap secret memory\n");
-		return;
-	}
-	munmap(mem, len);
-
-	len = mlock_limit_max * 2;
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem != MAP_FAILED) {
-		fail("unexpected mlock limit violation\n");
-		munmap(mem, len);
-		return;
-	}
-
-	pass("mlock limit is respected\n");
-}
-
 static void test_vmsplice(int fd, const char *desc)
 {
 	ssize_t transferred;

@@ -297,7 +270,7 @@ static void prepare(void)
 				   strerror(errno));
 }
 
-#define NUM_TESTS 6
+#define NUM_TESTS 5
 
 int main(int argc, char *argv[])
 {

@@ -319,7 +292,6 @@ int main(int argc, char *argv[])
 	if (ftruncate(fd, page_size))
 		ksft_exit_fail_msg("ftruncate failed: %s\n", strerror(errno));
 
-	test_mlock_limit(fd);
 	test_file_apis(fd);
 	/*
 	 * We have to run the first vmsplice test before any secretmem page was

From: "Lorenzo Stoakes (ARM)" <[email protected]>

[ Upstream commit 97d34aa65c29cca85e3e9050f4c936389b38a054 ]

secretmem accounts folios by treating memory as if it were mlock()'d and thus limited by the RLIMIT_MEMLOCK limit.

However the folios are unevictable and remain so until the inode is evicted, eliminating usual mlock() semantics - mapping folios then unmapping them does not clear their unevictable state, since it depends on AS_UNEVICTABLE, not PG_mlocked.

A user can therefore easily work around the RLIMIT_MEMLOCK limit - simply map then unmap and VmLck no longer counts the secretmem range. Worse, folios are not accounted in the process's RSS, meaning the OOM killer won't know to kill the process.

Repeatedly mapping/unmapping (or forking) can then result in the consumption of all available system memory with unevictable folios and cause system instability.

A secretmem fd can be passed between processes and over fork so a per-process limit simply does not make sense, so follow the precedent set by io_uring, perf, skbuff, iommufd and xdp by tracking the number of locked pages in user_struct->locked_vm.

Since the scope tracked is actually inode lifetime, the RLIMIT_MEMLOCK applies per-user not per-process, so it doesn't make sense to bypass for users with CAP_IPC_LOCK, therefore remove this bypass.

There is simply no reason to carry on marking the mapping as mlock()'d since it's misleading and the lifecycle is now correctly handled, so remove this too.

Note that secretmem does not support any form of truncation (including hole punching) and the folios are unreclaimable, so the folios need only be accounted on fault and unaccounted on inode destruction.

__secretmem_account_pages() is more or less a duplicate of the code that io_uring etc. use, but since this is a bug fix that needs backporting, defer any de-duplication efforts to a follow-up.

test_mlock_limit() asserts mlock_future_ok() on mmap(), however this has been removed, so remove the test altogether for the fix. A new test will be sent separately for upstream.

---
 include/linux/sched/user.h                |   3 +-
 mm/secretmem.c                            | 118 ++++++++++++++++++++--
 tools/testing/selftests/mm/memfd_secret.c |  30 +-----
 3 files changed, 111 insertions(+), 40 deletions(-)

index 4cc52698e214e..8d7e5521f7cdd 100644
@@ -25,7 +25,8 @@ struct user_struct {
 
 #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
 	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
-	defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD)
+	defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \
+	defined(CONFIG_SECRETMEM)
 	atomic_long_t locked_vm;
 #endif
 #ifdef CONFIG_WATCH_QUEUE

index 9b298f6a04b37..348cc976726bb 100644
@@ -56,33 +56,6 @@ static void test_file_apis(int fd)
 		pass("file IO is blocked as expected\n");
 }
 
-static void test_mlock_limit(int fd)
-{
-	size_t len;
-	char *mem;
-
-	len = mlock_limit_cur;
-	if (len % page_size != 0)
-		len = (len/page_size) * page_size;
-
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem == MAP_FAILED) {
-		fail("unable to mmap secret memory\n");
-		return;
-	}
-	munmap(mem, len);
-
-	len = mlock_limit_max * 2;
-	mem = mmap(NULL, len, prot, mode, fd, 0);
-	if (mem != MAP_FAILED) {
-		fail("unexpected mlock limit violation\n");
-		munmap(mem, len);
-		return;
-	}
-
-	pass("mlock limit is respected\n");
-}
-
 static void try_process_vm_read(int fd, int pipefd[2])
 {
 	struct iovec liov, riov;

@@ -258,7 +231,7 @@ static void prepare(void)
 				   strerror(errno));
 }
 
-#define NUM_TESTS 4
+#define NUM_TESTS 3
 
 int main(int argc, char *argv[])
 {

@@ -278,7 +251,6 @@ int main(int argc, char *argv[])
 					   strerror(errno));
 	}
 
-	test_mlock_limit(fd);
 	test_file_apis(fd);
 	test_process_vm_read(fd);
 	test_ptrace(fd);

2.53.0