mm: switch mm->get_unmapped_area() to a flag

The mm_struct contains a function pointer *get_unmapped_area(), which is
set to either arch_get_unmapped_area() or arch_get_unmapped_area_topdown()
during the initialization of the mm.

Since the function pointer only ever points to two functions that are
named the same across all arch's, a function pointer is not really
required.  In addition future changes will want to add versions of the
functions that take additional arguments.  So to save a pointers worth of
bytes in mm_struct, and prevent adding additional function pointers to
mm_struct in future changes, remove it and keep the information about
which get_unmapped_area() to use in a flag.

Add the new flag to MMF_INIT_MASK so it doesn't get clobbered on fork by
mmf_init_flags().  Most MM flags get clobbered on fork.  In the
pre-existing behavior mm->get_unmapped_area() would get copied to the new
mm in dup_mm(), so not clobbering the flag preserves the existing behavior
around inheriting the topdown-ness.

Introduce a helper, mm_get_unmapped_area(), to easily convert code that
refers to the old function pointer to instead select and call either
arch_get_unmapped_area() or arch_get_unmapped_area_topdown() based on the
flag.  Then drop the mm->get_unmapped_area() function pointer.  Leave the
get_unmapped_area() pointer in struct file_operations alone.  The main
purpose of this change is to reorganize in preparation for future changes,
but it also converts the calls of mm->get_unmapped_area() from indirect
branches into a direct ones.

The stress-ng bigheap benchmark calls realloc a lot, which calls through
get_unmapped_area() in the kernel.  On x86, the change yielded a ~1%
improvement there on a retpoline config.

In testing a few x86 configs, removing the pointer unfortunately didn't
result in any actual size reductions in the compiled layout of mm_struct. 
But depending on compiler or arch alignment requirements, the change could
shrink the size of mm_struct.

Link: https://lkml.kernel.org/r/20240326021656.202649-3-rick.p.edgecombe@intel.com
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@kernel.org>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: Helge Deller <deller@gmx.de>
Cc: H. Peter Anvin (Intel) <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Naveen N. Rao <naveen.n.rao@linux.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 30 insertions, 23 deletions

diff --git a/mm/debug.c b/mm/debug.c
index e8a96b8b7197..b71186f1fb0b 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -177,9 +177,6 @@ EXPORT_SYMBOL(dump_vma);
 void dump_mm(const struct mm_struct *mm)
 {
 	pr_emerg("mm %px task_size %lu\n"
-#ifdef CONFIG_MMU
-		"get_unmapped_area %px\n"
-#endif
 		"mmap_base %lu mmap_legacy_base %lu\n"
 		"pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n"
 		"hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n"
@@ -205,9 +202,6 @@ void dump_mm(const struct mm_struct *mm)
 		"def_flags: %#lx(%pGv)\n",
 
 		mm, mm->task_size,
-#ifdef CONFIG_MMU
-		mm->get_unmapped_area,
-#endif
 		mm->mmap_base, mm->mmap_legacy_base,
 		mm->pgd, atomic_read(&mm->mm_users),
 		atomic_read(&mm->mm_count),
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 157cee64850c..7fdb2275a1e0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -816,8 +816,8 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	if (len_pad < len || (off + len_pad) < off)
 		return 0;
 
-	ret = current->mm->get_unmapped_area(filp, addr, len_pad,
-					      off >> PAGE_SHIFT, flags);
+	ret = mm_get_unmapped_area(current->mm, filp, addr, len_pad,
+				   off >> PAGE_SHIFT, flags);
 
 	/*
 	 * The failure might be due to length padding. The caller will retry
@@ -835,8 +835,7 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 
 	off_sub = (off - ret) & (size - 1);
 
-	if (current->mm->get_unmapped_area == arch_get_unmapped_area_topdown &&
-	    !off_sub)
+	if (test_bit(MMF_TOPDOWN, &current->mm->flags) && !off_sub)
 		return ret + size;
 
 	ret += off_sub;
@@ -853,7 +852,7 @@ unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (ret)
 		return ret;
 
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags);
 }
 EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 77a625e13ec1..dfb8a518e8c9 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1812,7 +1812,8 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
 	unsigned long (*get_area)(struct file *, unsigned long,
-				  unsigned long, unsigned long, unsigned long);
+				  unsigned long, unsigned long, unsigned long)
+				  = NULL;
 
 	unsigned long error = arch_mmap_check(addr, len, flags);
 	if (error)
@@ -1822,7 +1823,6 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
-	get_area = current->mm->get_unmapped_area;
 	if (file) {
 		if (file->f_op->get_unmapped_area)
 			get_area = file->f_op->get_unmapped_area;
@@ -1841,7 +1841,11 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	if (!file)
 		pgoff = 0;
 
-	addr = get_area(file, addr, len, pgoff, flags);
+	if (get_area)
+		addr = get_area(file, addr, len, pgoff, flags);
+	else
+		addr = mm_get_unmapped_area(current->mm, file, addr, len,
+					    pgoff, flags);
 	if (IS_ERR_VALUE(addr))
 		return addr;
 
@@ -1856,6 +1860,17 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 
 EXPORT_SYMBOL(get_unmapped_area);
 
+unsigned long
+mm_get_unmapped_area(struct mm_struct *mm, struct file *file,
+		     unsigned long addr, unsigned long len,
+		     unsigned long pgoff, unsigned long flags)
+{
+	if (test_bit(MMF_TOPDOWN, &mm->flags))
+		return arch_get_unmapped_area_topdown(file, addr, len, pgoff, flags);
+	return arch_get_unmapped_area(file, addr, len, pgoff, flags);
+}
+EXPORT_SYMBOL(mm_get_unmapped_area);
+
 /**
  * find_vma_intersection() - Look up the first VMA which intersects the interval
  * @mm: The process address space.
diff --git a/mm/shmem.c b/mm/shmem.c
index 98985179f495..fa2a0ed97507 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2267,8 +2267,6 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 				      unsigned long uaddr, unsigned long len,
 				      unsigned long pgoff, unsigned long flags)
 {
-	unsigned long (*get_area)(struct file *,
-		unsigned long, unsigned long, unsigned long, unsigned long);
 	unsigned long addr;
 	unsigned long offset;
 	unsigned long inflated_len;
@@ -2278,8 +2276,8 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
-	get_area = current->mm->get_unmapped_area;
-	addr = get_area(file, uaddr, len, pgoff, flags);
+	addr = mm_get_unmapped_area(current->mm, file, uaddr, len, pgoff,
+				    flags);
 
 	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
 		return addr;
@@ -2336,7 +2334,8 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 	if (inflated_len < len)
 		return addr;
 
-	inflated_addr = get_area(NULL, uaddr, inflated_len, 0, flags);
+	inflated_addr = mm_get_unmapped_area(current->mm, NULL, uaddr,
+					     inflated_len, 0, flags);
 	if (IS_ERR_VALUE(inflated_addr))
 		return addr;
 	if (inflated_addr & ~PAGE_MASK)
@@ -4801,7 +4800,7 @@ unsigned long shmem_get_unmapped_area(struct file *file,
 				      unsigned long addr, unsigned long len,
 				      unsigned long pgoff, unsigned long flags)
 {
-	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
 }
 #endif
 
diff --git a/mm/util.c b/mm/util.c
index a9e911b22b99..c9e519e6811f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -469,17 +469,17 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 
 	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
+		clear_bit(MMF_TOPDOWN, &mm->flags);
 	} else {
 		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		set_bit(MMF_TOPDOWN, &mm->flags);
 	}
 }
 #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	mm->mmap_base = TASK_UNMAPPED_BASE;
-	mm->get_unmapped_area = arch_get_unmapped_area;
+	clear_bit(MMF_TOPDOWN, &mm->flags);
 }
 #endif