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>

arch/s390/mm/hugetlbpage.c

@@ -318,7 +318,7 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 			goto check_asce_limit;
 	}
 
-	if (mm->get_unmapped_area == arch_get_unmapped_area)
+	if (!test_bit(MMF_TOPDOWN, &mm->flags))
 		addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
 				pgoff, flags);
 	else

arch/s390/mm/mmap.c

@@ -185,10 +185,10 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 	 */
 	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = mmap_base_legacy(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);
 	}
 }
 

arch/sparc/kernel/sys_sparc_64.c

@@ -218,14 +218,10 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, unsigned long len, unsigned long pgoff, unsigned long flags)
 {
 	unsigned long align_goal, addr = -ENOMEM;
-	unsigned long (*get_area)(struct file *, unsigned long,
-				  unsigned long, unsigned long, unsigned long);
-
-	get_area = current->mm->get_unmapped_area;
 
 	if (flags & MAP_FIXED) {
 		/* Ok, don't mess with it. */
-		return get_area(NULL, orig_addr, len, pgoff, flags);
+		return mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags);
 	}
 	flags &= ~MAP_SHARED;
 
@@ -238,7 +234,8 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u
 		align_goal = (64UL * 1024);
 
 	do {
-		addr = get_area(NULL, orig_addr, len + (align_goal - PAGE_SIZE), pgoff, flags);
+		addr = mm_get_unmapped_area(current->mm, NULL, orig_addr,
+					    len + (align_goal - PAGE_SIZE), pgoff, flags);
 		if (!(addr & ~PAGE_MASK)) {
 			addr = (addr + (align_goal - 1UL)) & ~(align_goal - 1UL);
 			break;
@@ -256,7 +253,7 @@ unsigned long get_fb_unmapped_area(struct file *filp, unsigned long orig_addr, u
 	 * be obtained.
 	 */
 	if (addr & ~PAGE_MASK)
-		addr = get_area(NULL, orig_addr, len, pgoff, flags);
+		addr = mm_get_unmapped_area(current->mm, NULL, orig_addr, len, pgoff, flags);
 
 	return addr;
 }
@@ -292,7 +289,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 	    gap == RLIM_INFINITY ||
 	    sysctl_legacy_va_layout) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
+		clear_bit(MMF_TOPDOWN, &mm->flags);
 	} else {
 		/* We know it's 32-bit */
 		unsigned long task_size = STACK_TOP32;
@@ -303,7 +300,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 			gap = (task_size / 6 * 5);
 
 		mm->mmap_base = PAGE_ALIGN(task_size - gap - random_factor);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		set_bit(MMF_TOPDOWN, &mm->flags);
 	}
 }
 

arch/sparc/mm/hugetlbpage.c

@@ -123,7 +123,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
-	if (mm->get_unmapped_area == arch_get_unmapped_area)
+	if (!test_bit(MMF_TOPDOWN, &mm->flags))
 		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 				pgoff, flags);
 	else

arch/x86/kernel/cpu/sgx/driver.c

@@ -113,7 +113,7 @@ static unsigned long sgx_get_unmapped_area(struct file *file,
 	if (flags & MAP_FIXED)
 		return addr;
 
-	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
 }
 
 #ifdef CONFIG_COMPAT

arch/x86/mm/hugetlbpage.c

@@ -115,7 +115,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	}
 
 get_unmapped_area:
-	if (mm->get_unmapped_area == arch_get_unmapped_area)
+	if (!test_bit(MMF_TOPDOWN, &mm->flags))
 		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 				pgoff, flags);
 	else

arch/x86/mm/mmap.c

@@ -129,9 +129,9 @@ static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
 void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	if (mmap_is_legacy())
-		mm->get_unmapped_area = arch_get_unmapped_area;
+		clear_bit(MMF_TOPDOWN, &mm->flags);
 	else
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+		set_bit(MMF_TOPDOWN, &mm->flags);
 
 	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
 			arch_rnd(mmap64_rnd_bits), task_size_64bit(0),

drivers/char/mem.c

@@ -544,7 +544,7 @@ static unsigned long get_unmapped_area_zero(struct file *file,
 	}
 
 	/* Otherwise flags & MAP_PRIVATE: with no shmem object beneath it */
-	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, file, addr, len, pgoff, flags);
 #else
 	return -ENOSYS;
 #endif

drivers/dax/device.c

@@ -329,14 +329,14 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 	if ((off + len_align) < off)
 		goto out;
 
-	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
+	addr_align = mm_get_unmapped_area(current->mm, filp, addr, len_align,
-			pgoff, flags);
+					  pgoff, flags);
 	if (!IS_ERR_VALUE(addr_align)) {
 		addr_align += (off - addr_align) & (align - 1);
 		return addr_align;
 	}
  out:
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags);
 }
 
 static const struct address_space_operations dev_dax_aops = {

fs/hugetlbfs/inode.c

@@ -249,11 +249,11 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	}
 
 	/*
-	 * Use mm->get_unmapped_area value as a hint to use topdown routine.
+	 * Use MMF_TOPDOWN flag as a hint to use topdown routine.
 	 * If architectures have special needs, they should define their own
 	 * version of hugetlb_get_unmapped_area.
 	 */
-	if (mm->get_unmapped_area == arch_get_unmapped_area_topdown)
+	if (test_bit(MMF_TOPDOWN, &mm->flags))
 		return hugetlb_get_unmapped_area_topdown(file, addr, len,
 				pgoff, flags);
 	return hugetlb_get_unmapped_area_bottomup(file, addr, len,

fs/proc/inode.c

@@ -455,8 +455,9 @@ pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned lo
 		return pde->proc_ops->proc_get_unmapped_area(file, orig_addr, len, pgoff, flags);
 
 #ifdef CONFIG_MMU
-	return current->mm->get_unmapped_area(file, orig_addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, file, orig_addr, len, pgoff, flags);
 #endif
+
 	return orig_addr;
 }
 

fs/ramfs/file-mmu.c

@@ -35,7 +35,7 @@ static unsigned long ramfs_mmu_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);
 }
 
 const struct file_operations ramfs_file_operations = {

include/linux/mm_types.h

@@ -777,11 +777,7 @@ struct mm_struct {
 		} ____cacheline_aligned_in_smp;
 
 		struct maple_tree mm_mt;
-#ifdef CONFIG_MMU
+
-		unsigned long (*get_unmapped_area) (struct file *filp,
-				unsigned long addr, unsigned long len,
-				unsigned long pgoff, unsigned long flags);
-#endif
 		unsigned long mmap_base;	/* base of mmap area */
 		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES

include/linux/sched/coredump.h

@@ -92,9 +92,12 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_VM_MERGE_ANY	30
 #define MMF_VM_MERGE_ANY_MASK	(1 << MMF_VM_MERGE_ANY)
 
+#define MMF_TOPDOWN		31	/* mm searches top down by default */
+#define MMF_TOPDOWN_MASK	(1 << MMF_TOPDOWN)
+
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
 				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
-				 MMF_VM_MERGE_ANY_MASK)
+				 MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK)
 
 static inline unsigned long mmf_init_flags(unsigned long flags)
 {

include/linux/sched/mm.h

@@ -8,6 +8,7 @@
 #include <linux/mm_types.h>
 #include <linux/gfp.h>
 #include <linux/sync_core.h>
+#include <linux/sched/coredump.h>
 
 /*
  * Routines for handling mm_structs
@@ -186,6 +187,10 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
 
+unsigned long mm_get_unmapped_area(struct mm_struct *mm, struct file *filp,
+				   unsigned long addr, unsigned long len,
+				   unsigned long pgoff, unsigned long flags);
+
 unsigned long
 generic_get_unmapped_area(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,

io_uring/io_uring.c

@@ -3525,7 +3525,7 @@ static unsigned long io_uring_mmu_get_unmapped_area(struct file *filp,
 #else
 	addr = 0UL;
 #endif
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags);
 }
 
 #else /* !CONFIG_MMU */

kernel/bpf/arena.c

@@ -314,7 +314,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 			return -EINVAL;
 	}
 
-	ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags);
+	ret = mm_get_unmapped_area(current->mm, filp, addr, len * 2, 0, flags);
 	if (IS_ERR_VALUE(ret))
 		return ret;
 	if ((ret >> 32) == ((ret + len - 1) >> 32))

kernel/bpf/syscall.c

@@ -980,7 +980,7 @@ static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr
 	if (map->ops->map_get_unmapped_area)
 		return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags);
 #ifdef CONFIG_MMU
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+	return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags);
 #else
 	return addr;
 #endif

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),

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,
+	ret = mm_get_unmapped_area(current->mm, filp, addr, len_pad,
-					      off >> PAGE_SHIFT, flags);
+				   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 &&
+	if (test_bit(MMF_TOPDOWN, &current->mm->flags) && !off_sub)
-	    !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);
 

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.

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 = mm_get_unmapped_area(current->mm, file, uaddr, len, pgoff,
-	addr = get_area(file, uaddr, len, pgoff, flags);
+				    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
 

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