arch/x86: teach arch_get_unmapped_area_vmflags to handle hugetlb mappings

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.

Link: https://lkml.kernel.org/r/20241007075037.267650-4-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Donet Tom <donettom@linux.ibm.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Peter Xu <peterx@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 87f8c9a71c496430a552e0e0bdc9495cbbe99614..776ae6fa7f2d675a0ec795a2815fd87ba5d62e26 100644 (file)
--- 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 @@ get_unmapped_area:
                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 @@ get_unmapped_area:
        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);