mm: abstract initial stack setup to mm subsystem

There are peculiarities within the kernel where what is very clearly mm
code is performed elsewhere arbitrarily.

This violates separation of concerns and makes it harder to refactor code
to make changes to how fundamental initialisation and operation of mm
logic is performed.

One such case is the creation of the VMA containing the initial stack upon
execve()'ing a new process.  This is currently performed in
__bprm_mm_init() in fs/exec.c.

Abstract this operation to create_init_stack_vma().  This allows us to
limit use of vma allocation and free code to fork and mm only.

We previously did the same for the step at which we relocate the initial
stack VMA downwards via relocate_vma_down(), now we move the initial VMA
establishment too.

Take the opportunity to also move insert_vm_struct() to mm/vma.c as it's
no longer needed anywhere outside of mm.

Link: https://lkml.kernel.org/r/118c950ef7a8dd19ab20a23a68c3603751acd30e.1745853549.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 32 insertions, 0 deletions

diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 0df19ca0000a..32e990313158 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -56,6 +56,8 @@ extern unsigned long dac_mmap_min_addr;
 #define VM_PFNMAP	0x00000400
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000
+#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
+#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */
 #define VM_DONTEXPAND	0x00040000
 #define VM_LOCKONFAULT	0x00080000
 #define VM_ACCOUNT	0x00100000
@@ -70,6 +72,20 @@ extern unsigned long dac_mmap_min_addr;
 #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+#ifdef CONFIG_STACK_GROWSUP
+#define VM_STACK	VM_GROWSUP
+#define VM_STACK_EARLY	VM_GROWSDOWN
+#else
+#define VM_STACK	VM_GROWSDOWN
+#define VM_STACK_EARLY	0
+#endif
+
+#define DEFAULT_MAP_WINDOW	((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_LOW		DEFAULT_MAP_WINDOW
+#define TASK_SIZE_MAX		DEFAULT_MAP_WINDOW
+#define STACK_TOP		TASK_SIZE_LOW
+#define STACK_TOP_MAX		TASK_SIZE_MAX
+
 /* This mask represents all the VMA flag bits used by mlock */
 #define VM_LOCKED_MASK	(VM_LOCKED | VM_LOCKONFAULT)
 
@@ -82,6 +98,10 @@ extern unsigned long dac_mmap_min_addr;
 
 #define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
 
+#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
+#define VM_STACK_FLAGS	(VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
+
 #define RLIMIT_STACK		3	/* max stack size */
 #define RLIMIT_MEMLOCK		8	/* max locked-in-memory address space */
 
@@ -1280,4 +1300,16 @@ static inline void free_pgd_range(struct mmu_gather *tlb,
 	(void)ceiling;
 }
 
+static inline int ksm_execve(struct mm_struct *mm)
+{
+	(void)mm;
+
+	return 0;
+}
+
+static inline void ksm_exit(struct mm_struct *mm)
+{
+	(void)mm;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */