[PATCH v3 0/9] Unify hugetlb into arch_get_unmapped_area functions

[PATCH v3 0/9] Unify hugetlb into arch_get_unmapped_area functions

[Oscar Salvador]

rfc -> v1: Fix s390 compilation errors
           Tested on s390
v1  -> v2: Rebased on top of mm-unstable
           Fix sparc64 compilation errors
v2  -> v3: Rebased on top of mm-unstable
           Fix bug reported by Lorenzo Stoakes


This is an attempt to get rid of a fair amount of duplicated code
wrt. hugetlb and *get_unmapped_area* functions.

HugeTLB registers a .get_unmapped_area function which gets called from
__get_unmapped_area().
hugetlb_get_unmapped_area() is defined by a bunch of architectures and
it also has a generic definition for those that do not define it.
Short-long story is that there is a ton of duplicated code between
specific hugetlb *_get_unmapped_area_* functions and mm-core functions,
so we can do better by teaching arch_get_unmapped_area* functions how
to deal with hugetlb mappings.

Note that not a lot of things need to be taught though.
hugetlb_get_unmapped_area, that gets called for hugetlb mappings,
runs some sanity checks prior to calling mm_get_unmapped_area_vmflags(),
so we do not need to that down the road in the respective
{generic,arch}_get_unmapped_area* functions.

More information can be found in the respective patches.

LTP mmapstress hugetlb selftests were ran succesfully on:

- arm64
- powerpc64
- s390
- x86_64

Oscar Salvador (9):
  mm/mmap: Teach generic_get_unmapped_area{_topdown} to handle hugetlb
    mappings
  arch/s390: Teach arch_get_unmapped_area{_topdown} to handle hugetlb
    mappings
  arch/x86: Teach arch_get_unmapped_area_vmflags to handle hugetlb
    mappings
  arch/sparc: Teach arch_get_unmapped_area{_topdown} to handle hugetlb
    mappings
  arch/powerpc: Teach book3s64 arch_get_unmapped_area{_topdown} to
    handle hugetlb mappings
  mm: Make hugetlb mappings go through mm_get_unmapped_area_vmflags
  mm: Drop hugetlb_get_unmapped_area{_*} functions
  arch/s390: Clean up hugetlb definitions
  mm: Consolidate common checks in hugetlb_get_unmapped_area

 arch/loongarch/include/asm/hugetlb.h |   4 -
 arch/mips/include/asm/hugetlb.h      |   4 -
 arch/parisc/include/asm/hugetlb.h    |  15 ----
 arch/parisc/mm/hugetlbpage.c         |  21 ------
 arch/powerpc/mm/book3s64/slice.c     |  50 ++++++++-----
 arch/s390/include/asm/hugetlb.h      |  73 ++++--------------
 arch/s390/mm/hugetlbpage.c           |  85 ---------------------
 arch/s390/mm/mmap.c                  |   9 ++-
 arch/sh/include/asm/hugetlb.h        |  15 ----
 arch/sparc/kernel/sys_sparc_32.c     |  17 ++++-
 arch/sparc/kernel/sys_sparc_64.c     |  37 +++++++--
 arch/sparc/mm/hugetlbpage.c          | 108 ---------------------------
 arch/x86/kernel/sys_x86_64.c         |  24 ++++--
 arch/x86/mm/hugetlbpage.c            | 101 -------------------------
 fs/hugetlbfs/inode.c                 |  94 +++--------------------
 include/asm-generic/hugetlb.h        |  15 ++--
 include/linux/hugetlb.h              |  22 +++---
 mm/mmap.c                            |   4 +
 18 files changed, 145 insertions(+), 553 deletions(-)

-- 
2.46.0

[PATCH v3 1/9] mm/mmap: Teach generic_get_unmapped_area{_topdown} to handle hugetlb mappings

[Oscar Salvador]

We want to stop special casing hugetlb mappings and make them go
through generic channels, so teach generic_get_unmapped_area{_topdown}
to handle those.
The main difference is that we set info.align_mask for huge mappings.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 include/linux/hugetlb.h | 10 ++++++++++
 mm/mmap.c               |  4 ++++
 2 files changed, 14 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index e4697539b665..368d552e4860 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1035,9 +1035,19 @@ void hugetlb_unregister_node(struct node *node);
  */
 bool is_raw_hwpoison_page_in_hugepage(struct page *page);
 
+static inline unsigned long huge_page_mask_align(struct file *file)
+{
+	return PAGE_MASK & ~huge_page_mask(hstate_file(file));
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline unsigned long huge_page_mask_align(struct file *file)
+{
+	return 0;
+}
+
 static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
 {
 	return NULL;
diff --git a/mm/mmap.c b/mm/mmap.c
index 270bd8d504b8..5f05df7d58f5 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -776,6 +776,8 @@ generic_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.low_limit = mm->mmap_base;
 	info.high_limit = mmap_end;
 	info.start_gap = stack_guard_placement(vm_flags);
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
 	return vm_unmapped_area(&info);
 }
 
@@ -826,6 +828,8 @@ generic_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = arch_get_mmap_base(addr, mm->mmap_base);
 	info.start_gap = stack_guard_placement(vm_flags);
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
 	addr = vm_unmapped_area(&info);
 
 	/*
-- 
2.46.0

[PATCH v3 2/9] arch/s390: Teach arch_get_unmapped_area{_topdown} to handle hugetlb mappings

[Oscar Salvador]

We want to stop special casing hugetlb mappings and make them go
through generic channels, so teach arch_get_unmapped_area{_topdown}
to handle those.
s390 specific hugetlb function does not set info.align_offset, so do
the same here for compatibility.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/s390/mm/mmap.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 96efa061ce01..33f3504be90b 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -17,6 +17,7 @@
 #include <linux/random.h>
 #include <linux/compat.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 #include <asm/elf.h>
 
 static unsigned long stack_maxrandom_size(void)
@@ -73,6 +74,8 @@ static inline unsigned long mmap_base(unsigned long rnd,
 
 static int get_align_mask(struct file *filp, unsigned long flags)
 {
+	if (filp && is_file_hugepages(filp))
+		return huge_page_mask_align(filp);
 	if (!(current->flags & PF_RANDOMIZE))
 		return 0;
 	if (filp || (flags & MAP_SHARED))
@@ -106,7 +109,8 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.low_limit = mm->mmap_base;
 	info.high_limit = TASK_SIZE;
 	info.align_mask = get_align_mask(filp, flags);
-	info.align_offset = pgoff << PAGE_SHIFT;
+	if (!(filp && is_file_hugepages(filp)))
+		info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 	if (offset_in_page(addr))
 		return addr;
@@ -144,7 +148,8 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long ad
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
 	info.align_mask = get_align_mask(filp, flags);
-	info.align_offset = pgoff << PAGE_SHIFT;
+	if (!(filp && is_file_hugepages(filp)))
+		info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 
 	/*
-- 
2.46.0

[PATCH v3 3/9] arch/x86: Teach arch_get_unmapped_area_vmflags to handle hugetlb mappings

[Oscar Salvador]

We want to stop special casing hugetlb mappings and make them go
through generic channels, so teach arch_get_unmapped_area_{topdown_}vmflags
to handle those.
x86 specific hugetlb function does not set either info.start_gap or
info.align_offset so the same here for compatibility.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/kernel/sys_x86_64.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 87f8c9a71c49..776ae6fa7f2d 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -18,6 +18,7 @@
 #include <linux/random.h>
 #include <linux/uaccess.h>
 #include <linux/elf.h>
+#include <linux/hugetlb.h>
 
 #include <asm/elf.h>
 #include <asm/ia32.h>
@@ -25,8 +26,10 @@
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
  */
-static unsigned long get_align_mask(void)
+static unsigned long get_align_mask(struct file *filp)
 {
+	if (filp && is_file_hugepages(filp))
+		return huge_page_mask_align(filp);
 	/* handle 32- and 64-bit case with a single conditional */
 	if (va_align.flags < 0 || !(va_align.flags & (2 - mmap_is_ia32())))
 		return 0;
@@ -49,7 +52,7 @@ static unsigned long get_align_mask(void)
  */
 static unsigned long get_align_bits(void)
 {
-	return va_align.bits & get_align_mask();
+	return va_align.bits & get_align_mask(NULL);
 }
 
 static int __init control_va_addr_alignment(char *str)
@@ -148,12 +151,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len,
 	info.length = len;
 	info.low_limit = begin;
 	info.high_limit = end;
-	info.align_offset = pgoff << PAGE_SHIFT;
-	info.start_gap = stack_guard_placement(vm_flags);
+	if (!(filp && is_file_hugepages(filp))) {
+		info.align_offset = pgoff << PAGE_SHIFT;
+		info.start_gap = stack_guard_placement(vm_flags);
+	}
 	if (filp) {
-		info.align_mask = get_align_mask();
+		info.align_mask = get_align_mask(filp);
 		info.align_offset += get_align_bits();
 	}
+
 	return vm_unmapped_area(&info);
 }
 
@@ -199,7 +205,10 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0,
 		info.low_limit = PAGE_SIZE;
 
 	info.high_limit = get_mmap_base(0);
-	info.start_gap = stack_guard_placement(vm_flags);
+	if (!(filp && is_file_hugepages(filp))) {
+		info.start_gap = stack_guard_placement(vm_flags);
+		info.align_offset = pgoff << PAGE_SHIFT;
+	}
 
 	/*
 	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
@@ -211,9 +220,8 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr0,
 	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
 		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
 
-	info.align_offset = pgoff << PAGE_SHIFT;
 	if (filp) {
-		info.align_mask = get_align_mask();
+		info.align_mask = get_align_mask(filp);
 		info.align_offset += get_align_bits();
 	}
 	addr = vm_unmapped_area(&info);
-- 
2.46.0

[PATCH v3 4/9] arch/sparc: Teach arch_get_unmapped_area{_topdown} to handle hugetlb mappings

[Oscar Salvador]

We want to stop special casing hugetlb mappings and make them go
through generic channels, so teach arch_get_unmapped_area{_topdown}
to handle those.
sparc specific hugetlb function does not set info.align_offset, and
does not care about adjusting the align_mask for MAP_SHARED cases,
so the same here for compatibility.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/sparc/kernel/sys_sparc_32.c | 17 +++++++++++----
 arch/sparc/kernel/sys_sparc_64.c | 37 +++++++++++++++++++++++++-------
 2 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/arch/sparc/kernel/sys_sparc_32.c b/arch/sparc/kernel/sys_sparc_32.c
index 80822f922e76..959f3c2ca201 100644
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@@ -23,6 +23,7 @@
 #include <linux/utsname.h>
 #include <linux/smp.h>
 #include <linux/ipc.h>
+#include <linux/hugetlb.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
@@ -42,12 +43,16 @@ SYSCALL_DEFINE0(getpagesize)
 unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
 {
 	struct vm_unmapped_area_info info = {};
+	bool file_hugepage = false;
+
+	if (filp && is_file_hugepages(filp))
+		file_hugepage = true;
 
 	if (flags & MAP_FIXED) {
 		/* We do not accept a shared mapping if it would violate
 		 * cache aliasing constraints.
 		 */
-		if ((flags & MAP_SHARED) &&
+		if (!file_huge_pages && (flags & MAP_SHARED) &&
 		    ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)))
 			return -EINVAL;
 		return addr;
@@ -62,9 +67,13 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 	info.length = len;
 	info.low_limit = addr;
 	info.high_limit = TASK_SIZE;
-	info.align_mask = (flags & MAP_SHARED) ?
-		(PAGE_MASK & (SHMLBA - 1)) : 0;
-	info.align_offset = pgoff << PAGE_SHIFT;
+	if (!file_hugepage) {
+		info.align_mask = (flags & MAP_SHARED) ?
+			(PAGE_MASK & (SHMLBA - 1)) : 0;
+		info.align_offset = pgoff << PAGE_SHIFT;
+	} else {
+		info.align_mask = huge_page_mask_align(filp);
+	}
 	return vm_unmapped_area(&info);
 }
 
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index acade309dc2f..c5a284df7b41 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -30,6 +30,7 @@
 #include <linux/context_tracking.h>
 #include <linux/timex.h>
 #include <linux/uaccess.h>
+#include <linux/hugetlb.h>
 
 #include <asm/utrap.h>
 #include <asm/unistd.h>
@@ -87,6 +88,16 @@ static inline unsigned long COLOR_ALIGN(unsigned long addr,
 	return base + off;
 }
 
+static unsigned long get_align_mask(struct file *filp, unsigned long flags)
+{
+	if (filp && is_file_hugepages(filp))
+		return huge_page_mask_align(filp);
+	if (filp || (flags & MAP_SHARED))
+		return PAGE_MASK & (SHMLBA - 1);
+
+	return 0;
+}
+
 unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
 {
 	struct mm_struct *mm = current->mm;
@@ -94,12 +105,16 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 	unsigned long task_size = TASK_SIZE;
 	int do_color_align;
 	struct vm_unmapped_area_info info = {};
+	bool file_hugepage = false;
+
+	if (filp && is_file_hugepages(filp))
+		file_hugepage = true;
 
 	if (flags & MAP_FIXED) {
 		/* We do not accept a shared mapping if it would violate
 		 * cache aliasing constraints.
 		 */
-		if ((flags & MAP_SHARED) &&
+		if (!file_hugepage && (flags & MAP_SHARED) &&
 		    ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)))
 			return -EINVAL;
 		return addr;
@@ -111,7 +126,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 		return -ENOMEM;
 
 	do_color_align = 0;
-	if (filp || (flags & MAP_SHARED))
+	if ((filp || (flags & MAP_SHARED)) && !file_hugepage)
 		do_color_align = 1;
 
 	if (addr) {
@@ -129,8 +144,9 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsi
 	info.length = len;
 	info.low_limit = TASK_UNMAPPED_BASE;
 	info.high_limit = min(task_size, VA_EXCLUDE_START);
-	info.align_mask = do_color_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
-	info.align_offset = pgoff << PAGE_SHIFT;
+	info.align_mask = get_align_mask(filp, flags);
+	if (!file_hugepage)
+		info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 
 	if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) {
@@ -154,15 +170,19 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	unsigned long addr = addr0;
 	int do_color_align;
 	struct vm_unmapped_area_info info = {};
+	bool file_hugepage = false;
 
 	/* This should only ever run for 32-bit processes.  */
 	BUG_ON(!test_thread_flag(TIF_32BIT));
 
+	if (filp && is_file_hugepages(filp))
+		file_hugepage = true;
+
 	if (flags & MAP_FIXED) {
 		/* We do not accept a shared mapping if it would violate
 		 * cache aliasing constraints.
 		 */
-		if ((flags & MAP_SHARED) &&
+		if (!file_hugepage && (flags & MAP_SHARED) &&
 		    ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)))
 			return -EINVAL;
 		return addr;
@@ -172,7 +192,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 		return -ENOMEM;
 
 	do_color_align = 0;
-	if (filp || (flags & MAP_SHARED))
+	if ((filp || (flags & MAP_SHARED)) && !file_hugepage)
 		do_color_align = 1;
 
 	/* requesting a specific address */
@@ -192,8 +212,9 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	info.length = len;
 	info.low_limit = PAGE_SIZE;
 	info.high_limit = mm->mmap_base;
-	info.align_mask = do_color_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
-	info.align_offset = pgoff << PAGE_SHIFT;
+	info.align_mask = get_align_mask(filp, flags);
+	if (!file_hugepage)
+		info.align_offset = pgoff << PAGE_SHIFT;
 	addr = vm_unmapped_area(&info);
 
 	/*
-- 
2.46.0

[PATCH v3 5/9] arch/powerpc: Teach book3s64 arch_get_unmapped_area{_topdown} to handle hugetlb mappings

[Oscar Salvador]

We want to stop special casing hugetlb mappings and make them go
through generic channels, so teach arch_get_unmapped_area{_topdown}
to handle those.
Reshuffle file_to_psize() definition so arch_get_unmapped_area{_topdown}
can make use of it.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/powerpc/mm/book3s64/slice.c | 40 ++++++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 10 deletions(-)

diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index 87307d0fc3b8..3a858f6b7270 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -633,6 +633,20 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
 }
 EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
 
+#ifdef CONFIG_HUGETLB_PAGE
+static int file_to_psize(struct file *file)
+{
+	struct hstate *hstate = hstate_file(file);
+
+	return shift_to_mmu_psize(huge_page_shift(hstate));
+}
+#else
+static int file_to_psize(struct file *file)
+{
+	return 0;
+}
+#endif
+
 unsigned long arch_get_unmapped_area(struct file *filp,
 				     unsigned long addr,
 				     unsigned long len,
@@ -640,11 +654,17 @@ unsigned long arch_get_unmapped_area(struct file *filp,
 				     unsigned long flags,
 				     vm_flags_t vm_flags)
 {
+	unsigned int psize;
+
 	if (radix_enabled())
 		return generic_get_unmapped_area(filp, addr, len, pgoff, flags, vm_flags);
 
-	return slice_get_unmapped_area(addr, len, flags,
-				       mm_ctx_user_psize(&current->mm->context), 0);
+	if (filp && is_file_hugepages(filp))
+		psize = file_to_psize(filp);
+	else
+		psize = mm_ctx_user_psize(&current->mm->context);
+
+	return slice_get_unmapped_area(addr, len, flags, psize, 0);
 }
 
 unsigned long arch_get_unmapped_area_topdown(struct file *filp,
@@ -654,11 +674,17 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
 					     const unsigned long flags,
 					     vm_flags_t vm_flags)
 {
+	unsigned int psize;
+
 	if (radix_enabled())
 		return generic_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags, vm_flags);
 
-	return slice_get_unmapped_area(addr0, len, flags,
-				       mm_ctx_user_psize(&current->mm->context), 1);
+	if (filp && is_file_hugepages(filp))
+		psize = file_to_psize(filp);
+	else
+		psize = mm_ctx_user_psize(&current->mm->context);
+
+	return slice_get_unmapped_area(addr0, len, flags, psize, 1);
 }
 
 unsigned int notrace get_slice_psize(struct mm_struct *mm, unsigned long addr)
@@ -789,12 +815,6 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 	return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
 }
 
-static int file_to_psize(struct file *file)
-{
-	struct hstate *hstate = hstate_file(file);
-	return shift_to_mmu_psize(huge_page_shift(hstate));
-}
-
 unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 					unsigned long len, unsigned long pgoff,
 					unsigned long flags)
-- 
2.46.0

[PATCH v3 6/9] mm: Make hugetlb mappings go through mm_get_unmapped_area_vmflags

[Oscar Salvador]

Hugetlb mappings will no longer be special cased but rather go through
the generic mm_get_unmapped_area_vmflags function.
For that to happen, let us remove the .get_unmapped_area from
hugetlbfs_file_operations struct, and hint __get_unmapped_area
that it should not send hugetlb mappings through thp_get_unmapped_area_vmflags
but through mm_get_unmapped_area_vmflags.

Create also a function called hugetlb_mmap_check_and_align() where a
couple of safety checks are being done and the addr is aligned to
the huge page size.
Otherwise we will have to do this in every single function, which
duplicates quite a lot of code.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 fs/hugetlbfs/inode.c    | 24 ++++++++++++++++--------
 include/linux/hugetlb.h |  9 ++++-----
 2 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 9f6cff356796..978f5d62c5cf 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -258,15 +258,23 @@ generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 			pgoff, flags);
 }
 
-#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-static unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-			  unsigned long len, unsigned long pgoff,
-			  unsigned long flags)
+unsigned long
+__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+			    unsigned long len, unsigned long flags)
 {
-	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
+	unsigned long addr0 = 0;
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if ((flags & MAP_FIXED) && prepare_hugepage_range(file, addr, len))
+		return -EINVAL;
+	if (addr)
+		addr0 = ALIGN(addr, huge_page_size(h));
+
+	return mm_get_unmapped_area_vmflags(current->mm, file, addr, len, pgoff,
+					    flags, 0);
 }
-#endif
 
 /*
  * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
@@ -1300,7 +1308,7 @@ static const struct file_operations hugetlbfs_file_operations = {
 	.read_iter		= hugetlbfs_read_iter,
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
-	.get_unmapped_area	= hugetlb_get_unmapped_area,
+	.get_unmapped_area	= __hugetlb_get_unmapped_area,
 	.llseek			= default_llseek,
 	.fallocate		= hugetlbfs_fallocate,
 	.fop_flags		= FOP_HUGE_PAGES,
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 368d552e4860..3a81b6126f62 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -546,11 +546,10 @@ static inline struct hstate *hstate_inode(struct inode *i)
 }
 #endif /* !CONFIG_HUGETLBFS */
 
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-					unsigned long len, unsigned long pgoff,
-					unsigned long flags);
-#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
+unsigned long
+__generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				    unsigned long len, unsigned long pgoff,
+				    unsigned long flags);
 
 unsigned long
 generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-- 
2.46.0

[PATCH v3 7/9] mm: Drop hugetlb_get_unmapped_area{_*} functions

[Oscar Salvador]

Hugetlb mappings are now handled through normal channels just like any
other mapping, so we no longer need hugetlb_get_unmapped_area* specific
functions.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/parisc/mm/hugetlbpage.c     |  21 ------
 arch/powerpc/mm/book3s64/slice.c |  10 ---
 arch/s390/mm/hugetlbpage.c       |  85 ------------------------
 arch/sparc/mm/hugetlbpage.c      | 108 -------------------------------
 arch/x86/mm/hugetlbpage.c        | 101 -----------------------------
 fs/hugetlbfs/inode.c             |  96 ++-------------------------
 include/linux/hugetlb.h          |   7 +-
 7 files changed, 6 insertions(+), 422 deletions(-)

diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index aa664f7ddb63..e9d18cf25b79 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -21,27 +21,6 @@
 #include <asm/mmu_context.h>
 
 
-unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (len > TASK_SIZE)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED)
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-
-	if (addr)
-		addr = ALIGN(addr, huge_page_size(h));
-
-	/* we need to make sure the colouring is OK */
-	return arch_get_unmapped_area(file, addr, len, pgoff, flags, 0);
-}
 
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index 3a858f6b7270..bc9a39821d1c 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -814,14 +814,4 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 
 	return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
 }
-
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-					unsigned long len, unsigned long pgoff,
-					unsigned long flags)
-{
-	if (radix_enabled())
-		return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
-
-	return slice_get_unmapped_area(addr, len, flags, file_to_psize(file), 1);
-}
 #endif
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index ded0eff58a19..7c79cf1bc7d7 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -242,88 +242,3 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 	else
 		return false;
 }
-
-static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
-		unsigned long addr, unsigned long len,
-		unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-
-	info.length = len;
-	info.low_limit = current->mm->mmap_base;
-	info.high_limit = TASK_SIZE;
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	return vm_unmapped_area(&info);
-}
-
-static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
-		unsigned long addr0, unsigned long len,
-		unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-	unsigned long addr;
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = current->mm->mmap_base;
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (addr & ~PAGE_MASK) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = TASK_SIZE;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (len > TASK_SIZE - mmap_min_addr)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		goto check_asce_limit;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
-			goto check_asce_limit;
-	}
-
-	if (!test_bit(MMF_TOPDOWN, &mm->flags))
-		addr = hugetlb_get_unmapped_area_bottomup(file, addr, len,
-				pgoff, flags);
-	else
-		addr = hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-	if (offset_in_page(addr))
-		return addr;
-
-check_asce_limit:
-	return check_asce_limit(mm, addr, len);
-}
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index cc91ca7a1e18..eee601a0d2cf 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -19,114 +19,6 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 
-/* Slightly simplified from the non-hugepage variant because by
- * definition we don't have to worry about any page coloring stuff
- */
-
-static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
-							unsigned long addr,
-							unsigned long len,
-							unsigned long pgoff,
-							unsigned long flags)
-{
-	struct hstate *h = hstate_file(filp);
-	unsigned long task_size = TASK_SIZE;
-	struct vm_unmapped_area_info info = {};
-
-	if (test_thread_flag(TIF_32BIT))
-		task_size = STACK_TOP32;
-
-	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
-	info.high_limit = min(task_size, VA_EXCLUDE_START);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	addr = vm_unmapped_area(&info);
-
-	if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.low_limit = VA_EXCLUDE_END;
-		info.high_limit = task_size;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-static unsigned long
-hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
-				  const unsigned long len,
-				  const unsigned long pgoff,
-				  const unsigned long flags)
-{
-	struct hstate *h = hstate_file(filp);
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0;
-	struct vm_unmapped_area_info info = {};
-
-	/* This should only ever run for 32-bit processes.  */
-	BUG_ON(!test_thread_flag(TIF_32BIT));
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = mm->mmap_base;
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (addr & ~PAGE_MASK) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = STACK_TOP32;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long task_size = TASK_SIZE;
-
-	if (test_thread_flag(TIF_32BIT))
-		task_size = STACK_TOP32;
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (len > task_size)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma(mm, addr);
-		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
-			return addr;
-	}
-	if (!test_bit(MMF_TOPDOWN, &mm->flags))
-		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
-				pgoff, flags);
-	else
-		return hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-}
 
 static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 {
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 807a5859a3c4..58f7f2bd535d 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -19,107 +19,6 @@
 #include <asm/tlbflush.h>
 #include <asm/elf.h>
 
-#ifdef CONFIG_HUGETLB_PAGE
-static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
-		unsigned long addr, unsigned long len,
-		unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-
-	info.length = len;
-	info.low_limit = get_mmap_base(1);
-
-	/*
-	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
-	 * in the full address space.
-	 */
-	info.high_limit = in_32bit_syscall() ?
-		task_size_32bit() : task_size_64bit(addr > DEFAULT_MAP_WINDOW);
-
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	return vm_unmapped_area(&info);
-}
-
-static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
-		unsigned long addr, unsigned long len,
-		unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = get_mmap_base(0);
-
-	/*
-	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
-	 * in the full address space.
-	 */
-	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
-		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
-
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (addr & ~PAGE_MASK) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = TASK_SIZE_LOW;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-
-	if (len > TASK_SIZE)
-		return -ENOMEM;
-
-	/* No address checking. See comment at mmap_address_hint_valid() */
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr &= huge_page_mask(h);
-		if (!mmap_address_hint_valid(addr, len))
-			goto get_unmapped_area;
-
-		vma = find_vma(mm, addr);
-		if (!vma || addr + len <= vm_start_gap(vma))
-			return addr;
-	}
-
-get_unmapped_area:
-	if (!test_bit(MMF_TOPDOWN, &mm->flags))
-		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
-				pgoff, flags);
-	else
-		return hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-}
-#endif /* CONFIG_HUGETLB_PAGE */
 
 #ifdef CONFIG_X86_64
 bool __init arch_hugetlb_valid_size(unsigned long size)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 978f5d62c5cf..b6a619f5a85a 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -171,96 +171,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
  * Called under mmap_write_lock(mm).
  */
 
-static unsigned long
-hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-
-	info.length = len;
-	info.low_limit = current->mm->mmap_base;
-	info.high_limit = arch_get_mmap_end(addr, len, flags);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	return vm_unmapped_area(&info);
-}
-
-static unsigned long
-hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct vm_unmapped_area_info info = {};
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (unlikely(offset_in_page(addr))) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = current->mm->mmap_base;
-		info.high_limit = arch_get_mmap_end(addr, len, flags);
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-unsigned long
-generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-				  unsigned long len, unsigned long pgoff,
-				  unsigned long flags)
-{
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma, *prev;
-	struct hstate *h = hstate_file(file);
-	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (len > mmap_end - mmap_min_addr)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma_prev(mm, addr, &prev);
-		if (mmap_end - len >= addr && addr >= mmap_min_addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)) &&
-		    (!prev || addr >= vm_end_gap(prev)))
-			return addr;
-	}
-
-	/*
-	 * 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 (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,
-			pgoff, flags);
-}
-
 unsigned long
-__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-			    unsigned long len, unsigned long flags)
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+			    unsigned long len, unsigned long pgoff,
+			    unsigned long flags)
 {
 	unsigned long addr0 = 0;
 	struct hstate *h = hstate_file(file);
@@ -272,7 +186,7 @@ __hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (addr)
 		addr0 = ALIGN(addr, huge_page_size(h));
 
-	return mm_get_unmapped_area_vmflags(current->mm, file, addr, len, pgoff,
+	return mm_get_unmapped_area_vmflags(current->mm, file, addr0, len, pgoff,
 					    flags, 0);
 }
 
@@ -1308,7 +1222,7 @@ static const struct file_operations hugetlbfs_file_operations = {
 	.read_iter		= hugetlbfs_read_iter,
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
-	.get_unmapped_area	= __hugetlb_get_unmapped_area,
+	.get_unmapped_area	= hugetlb_get_unmapped_area,
 	.llseek			= default_llseek,
 	.fallocate		= hugetlbfs_fallocate,
 	.fop_flags		= FOP_HUGE_PAGES,
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3a81b6126f62..ae4fe8615bb6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -547,15 +547,10 @@ static inline struct hstate *hstate_inode(struct inode *i)
 #endif /* !CONFIG_HUGETLBFS */
 
 unsigned long
-__generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				    unsigned long len, unsigned long pgoff,
 				    unsigned long flags);
 
-unsigned long
-generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-				  unsigned long len, unsigned long pgoff,
-				  unsigned long flags);
-
 /*
  * huegtlb page specific state flags.  These flags are located in page.private
  * of the hugetlb head page.  Functions created via the below macros should be
-- 
2.46.0

[PATCH v3 8/9] arch/s390: Clean up hugetlb definitions

[Oscar Salvador]

s390 redefines functions that are already defined (and the same)
in include/asm-generic/hugetlb.h.
Do as the other architectures: 1) include include/asm-generic/hugetlb.h
2) drop the already defined functions in the generic hugetlb.h and
3) use the __HAVE_ARCH_HUGE_* macros to define our own.

This gets rid of quite some code.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/s390/include/asm/hugetlb.h | 58 +++++++++------------------------
 include/asm-generic/hugetlb.h   |  8 +++++
 2 files changed, 24 insertions(+), 42 deletions(-)

diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index cf1b5d6fb1a6..37e80a32623a 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -12,21 +12,24 @@
 #include <linux/pgtable.h>
 #include <asm/page.h>
 
-#define hugetlb_free_pgd_range			free_pgd_range
 #define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte, unsigned long sz);
 void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
-pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+#define __HAVE_ARCH_HUGE_PTEP_GET
+extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep);
 
 /*
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
@@ -45,6 +48,7 @@ static inline void arch_clear_hugetlb_flags(struct folio *folio)
 }
 #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
 
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
 {
@@ -54,12 +58,14 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		set_pte(ptep, __pte(_SEGMENT_ENTRY_EMPTY));
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
 	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
+#define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
@@ -72,6 +78,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
@@ -79,69 +86,36 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
 
-static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
-{
-	return mk_pte(page, pgprot);
-}
-
+#define __HAVE_ARCH_HUGE_PTE_NONE
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
 }
 
+#define __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY
 static inline int huge_pte_none_mostly(pte_t pte)
 {
 	return huge_pte_none(pte);
 }
 
-static inline int huge_pte_write(pte_t pte)
-{
-	return pte_write(pte);
-}
-
-static inline int huge_pte_dirty(pte_t pte)
-{
-	return pte_dirty(pte);
-}
-
-static inline pte_t huge_pte_mkwrite(pte_t pte)
-{
-	return pte_mkwrite_novma(pte);
-}
-
-static inline pte_t huge_pte_mkdirty(pte_t pte)
-{
-	return pte_mkdirty(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
-{
-	return pte_modify(pte, newprot);
-}
-
+#define __HAVE_ARCH_HUGE_PTE_MKUFFD_WP
 static inline pte_t huge_pte_mkuffd_wp(pte_t pte)
 {
 	return pte;
 }
 
+#define __HAVE_ARCH_HUGE_PTE_CLEAR_UFFD_WP
 static inline pte_t huge_pte_clear_uffd_wp(pte_t pte)
 {
 	return pte;
 }
 
+#define __HAVE_ARCH_HUGE_PTE_UFFD_WP
 static inline int huge_pte_uffd_wp(pte_t pte)
 {
 	return 0;
 }
 
-static inline bool gigantic_page_runtime_supported(void)
-{
-	return true;
-}
+#include <asm-generic/hugetlb.h>
 
 #endif /* _ASM_S390_HUGETLB_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 594d5905f615..67bbdafcfc22 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -42,20 +42,26 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
+#ifndef __HAVE_ARCH_HUGE_PTE_MKUFFD_WP
 static inline pte_t huge_pte_mkuffd_wp(pte_t pte)
 {
 	return huge_pte_wrprotect(pte_mkuffd_wp(pte));
 }
+#endif
 
+#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR_UFFD_WP
 static inline pte_t huge_pte_clear_uffd_wp(pte_t pte)
 {
 	return pte_clear_uffd_wp(pte);
 }
+#endif
 
+#ifndef __HAVE_ARCH_HUGE_PTE_UFFD_WP
 static inline int huge_pte_uffd_wp(pte_t pte)
 {
 	return pte_uffd_wp(pte);
 }
+#endif
 
 #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
@@ -106,10 +112,12 @@ static inline int huge_pte_none(pte_t pte)
 #endif
 
 /* Please refer to comments above pte_none_mostly() for the usage */
+#ifndef __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY
 static inline int huge_pte_none_mostly(pte_t pte)
 {
 	return huge_pte_none(pte) || is_pte_marker(pte);
 }
+#endif
 
 #ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
-- 
2.46.0

[PATCH v3 9/9] mm: Consolidate common checks in hugetlb_get_unmapped_area

[Oscar Salvador]

prepare_hugepage_range() performs almost the same checks for all
architectures that define it, with the exception of mips and loongarch
that also check for overflows.
The rest checks for the addr and len to be properly aligned, so we can
move that to hugetlb_get_unmapped_area() and get rid of a fair amount of
duplicated code.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
---
 arch/loongarch/include/asm/hugetlb.h |  4 ----
 arch/mips/include/asm/hugetlb.h      |  4 ----
 arch/parisc/include/asm/hugetlb.h    | 15 ---------------
 arch/s390/include/asm/hugetlb.h      | 17 -----------------
 arch/sh/include/asm/hugetlb.h        | 15 ---------------
 fs/hugetlbfs/inode.c                 |  8 ++++++--
 include/asm-generic/hugetlb.h        |  7 -------
 7 files changed, 6 insertions(+), 64 deletions(-)

diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index 5da32c00d483..bf41b024b6a4 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -18,10 +18,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	unsigned long task_size = STACK_TOP;
 	struct hstate *h = hstate_file(file);
 
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
 	if (len > task_size)
 		return -ENOMEM;
 	if (task_size - len < addr)
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index fd69c8808554..6a63d82a8ab3 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -19,10 +19,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	unsigned long task_size = STACK_TOP;
 	struct hstate *h = hstate_file(file);
 
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
 	if (len > task_size)
 		return -ENOMEM;
 	if (task_size - len < addr)
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 72daacc472a0..5b3a5429f71b 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -12,21 +12,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	if (len & ~HPAGE_MASK)
-		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 37e80a32623a..6f815d4ba0ca 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,23 +25,6 @@ extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep
 extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep);
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
 	clear_bit(PG_arch_1, &folio->flags);
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 75028bd568ba..4a92e6e4d627 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -5,21 +5,6 @@
 #include <asm/cacheflush.h>
 #include <asm/page.h>
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	if (len & ~HPAGE_MASK)
-		return -EINVAL;
-	if (addr & ~HPAGE_MASK)
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index b6a619f5a85a..cd49d21e7284 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -181,8 +181,12 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if ((flags & MAP_FIXED) && prepare_hugepage_range(file, addr, len))
-		return -EINVAL;
+	if (flags & MAP_FIXED) {
+		if (addr & ~huge_page_mask(h))
+			return -EINVAL;
+		if (prepare_hugepage_range(file, addr, len))
+			return -EINVAL;
+	}
 	if (addr)
 		addr0 = ALIGN(addr, huge_page_size(h));
 
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 67bbdafcfc22..f42133dae68e 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -123,13 +123,6 @@ static inline int huge_pte_none_mostly(pte_t pte)
 static inline int prepare_hugepage_range(struct file *file,
 		unsigned long addr, unsigned long len)
 {
-	struct hstate *h = hstate_file(file);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-
 	return 0;
 }
 #endif
-- 
2.46.0

Re: [PATCH v3 9/9] mm: Consolidate common checks in hugetlb_get_unmapped_area

[kernel test robot]

Hi Oscar,

kernel test robot noticed the following build warnings:

[auto build test WARNING on akpm-mm/mm-everything]
[also build test WARNING on next-20240912]
[cannot apply to s390/features powerpc/next powerpc/fixes deller-parisc/for-next arnd-asm-generic/master linus/master v6.11-rc7]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Oscar-Salvador/mm-mmap-Teach-generic_get_unmapped_area-_topdown-to-handle-hugetlb-mappings/20240910-160312
base:   https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link:    https://lore.kernel.org/r/20240910080030.1272373-10-osalvador%40suse.de
patch subject: [PATCH v3 9/9] mm: Consolidate common checks in hugetlb_get_unmapped_area
config: loongarch-randconfig-002-20240913 (https://download.01.org/0day-ci/archive/20240913/202409131650.lUO7EoXP-lkp@intel.com/config)
compiler: loongarch64-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240913/202409131650.lUO7EoXP-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409131650.lUO7EoXP-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from include/linux/hugetlb.h:792,
                    from include/linux/migrate.h:8,
                    from fs/aio.c:40:
   arch/loongarch/include/asm/hugetlb.h: In function 'prepare_hugepage_range':
>> arch/loongarch/include/asm/hugetlb.h:19:24: warning: unused variable 'h' [-Wunused-variable]
      19 |         struct hstate *h = hstate_file(file);
         |                        ^


vim +/h +19 arch/loongarch/include/asm/hugetlb.h

09cfefb7fa70c3 Huacai Chen 2022-05-31  12  
09cfefb7fa70c3 Huacai Chen 2022-05-31  13  #define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
09cfefb7fa70c3 Huacai Chen 2022-05-31  14  static inline int prepare_hugepage_range(struct file *file,
09cfefb7fa70c3 Huacai Chen 2022-05-31  15  					 unsigned long addr,
09cfefb7fa70c3 Huacai Chen 2022-05-31  16  					 unsigned long len)
09cfefb7fa70c3 Huacai Chen 2022-05-31  17  {
09cfefb7fa70c3 Huacai Chen 2022-05-31  18  	unsigned long task_size = STACK_TOP;
09cfefb7fa70c3 Huacai Chen 2022-05-31 @19  	struct hstate *h = hstate_file(file);
09cfefb7fa70c3 Huacai Chen 2022-05-31  20  
09cfefb7fa70c3 Huacai Chen 2022-05-31  21  	if (len > task_size)
09cfefb7fa70c3 Huacai Chen 2022-05-31  22  		return -ENOMEM;
09cfefb7fa70c3 Huacai Chen 2022-05-31  23  	if (task_size - len < addr)
09cfefb7fa70c3 Huacai Chen 2022-05-31  24  		return -EINVAL;
09cfefb7fa70c3 Huacai Chen 2022-05-31  25  	return 0;
09cfefb7fa70c3 Huacai Chen 2022-05-31  26  }
09cfefb7fa70c3 Huacai Chen 2022-05-31  27  

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

Re: [PATCH v3 4/9] arch/sparc: Teach arch_get_unmapped_area{_topdown} to handle hugetlb mappings

[kernel test robot]

Hi Oscar,

kernel test robot noticed the following build errors:

[auto build test ERROR on akpm-mm/mm-everything]
[also build test ERROR on next-20240913]
[cannot apply to s390/features powerpc/next powerpc/fixes deller-parisc/for-next arnd-asm-generic/master linus/master v6.11-rc7]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Oscar-Salvador/mm-mmap-Teach-generic_get_unmapped_area-_topdown-to-handle-hugetlb-mappings/20240910-160312
base:   https://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm.git mm-everything
patch link:    https://lore.kernel.org/r/20240910080030.1272373-5-osalvador%40suse.de
patch subject: [PATCH v3 4/9] arch/sparc: Teach arch_get_unmapped_area{_topdown} to handle hugetlb mappings
config: sparc-randconfig-002-20240913 (https://download.01.org/0day-ci/archive/20240913/202409131805.4Dlb536A-lkp@intel.com/config)
compiler: sparc-linux-gcc (GCC) 14.1.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240913/202409131805.4Dlb536A-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202409131805.4Dlb536A-lkp@intel.com/

All errors (new ones prefixed by >>):

   arch/sparc/kernel/sys_sparc_32.c: In function 'arch_get_unmapped_area':
>> arch/sparc/kernel/sys_sparc_32.c:55:22: error: 'file_huge_pages' undeclared (first use in this function); did you mean 'file_hugepage'?
      55 |                 if (!file_huge_pages && (flags & MAP_SHARED) &&
         |                      ^~~~~~~~~~~~~~~
         |                      file_hugepage
   arch/sparc/kernel/sys_sparc_32.c:55:22: note: each undeclared identifier is reported only once for each function it appears in


vim +55 arch/sparc/kernel/sys_sparc_32.c

    42	
    43	unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags)
    44	{
    45		struct vm_unmapped_area_info info = {};
    46		bool file_hugepage = false;
    47	
    48		if (filp && is_file_hugepages(filp))
    49			file_hugepage = true;
    50	
    51		if (flags & MAP_FIXED) {
    52			/* We do not accept a shared mapping if it would violate
    53			 * cache aliasing constraints.
    54			 */
  > 55			if (!file_huge_pages && (flags & MAP_SHARED) &&
    56			    ((addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1)))
    57				return -EINVAL;
    58			return addr;
    59		}
    60	
    61		/* See asm-sparc/uaccess.h */
    62		if (len > TASK_SIZE - PAGE_SIZE)
    63			return -ENOMEM;
    64		if (!addr)
    65			addr = TASK_UNMAPPED_BASE;
    66	
    67		info.length = len;
    68		info.low_limit = addr;
    69		info.high_limit = TASK_SIZE;
    70		if (!file_hugepage) {
    71			info.align_mask = (flags & MAP_SHARED) ?
    72				(PAGE_MASK & (SHMLBA - 1)) : 0;
    73			info.align_offset = pgoff << PAGE_SHIFT;
    74		} else {
    75			info.align_mask = huge_page_mask_align(filp);
    76		}
    77		return vm_unmapped_area(&info);
    78	}
    79	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki