please check. I keep the comments about we are safe to use PAGE_ALIGN() with the initrd_end. Thanks Yinghai Subject: [PATCH -v4] x86: Make sure free_init_pages() free pages in boundary When CONFIG_NO_BOOTMEM, it could use memory more effient, or more compact. Example is: Allocated new RAMDISK: 00ec2000 - 0248ce57 Move RAMDISK from 000000002ea04000 - 000000002ffcee56 to 00ec2000 - 0248ce56 The new RAMDISK's end is not page aligned. Last page could use shared with other user. When free_init_pages are called for initrd or .init, the page could be freed could have chance to corrupt other data. code segment in free_init_pages() | for (; addr < end; addr += PAGE_SIZE) { | ClearPageReserved(virt_to_page(addr)); | init_page_count(virt_to_page(addr)); | memset((void *)(addr & ~(PAGE_SIZE-1)), | POISON_FREE_INITMEM, PAGE_SIZE); | free_page(addr); | totalram_pages++; | } last half page could be used as one whole free page. Try to make the boundaries to be page aligned. -v2: make the original initramdisk to be aligned, according to Johannes. otherwise we have chance to lose one page. we still need to keep initrd_end not aligned, otherwise it could confuse decompresser. -v3: change to WARN_ON instead according to Johannes. -v4: use PAGE_ALIGN according to Johannes. We may fix that MARCO name later to PAGE_ALIGN_UP, and PAGE_ALIGN_DOWN Add comments about assuming ramdisk start is aligned in relocate_initrd(), change to re get ramdisk_image instead of save it to make diff smaller. Add WARN for wrong range according Johannes. Reported-by: Stanislaw Gruszka <sgruszka@xxxxxxxxxx> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Tested-by: Stanislaw Gruszka <sgruszka@xxxxxxxxxx> --- arch/x86/kernel/head32.c | 3 ++- arch/x86/kernel/head64.c | 3 ++- arch/x86/kernel/setup.c | 19 ++++++++++--------- arch/x86/mm/init.c | 32 ++++++++++++++++++++++++++------ 4 files changed, 40 insertions(+), 17 deletions(-) Index: linux-2.6/arch/x86/mm/init.c =================================================================== --- linux-2.6.orig/arch/x86/mm/init.c +++ linux-2.6/arch/x86/mm/init.c @@ -331,11 +331,23 @@ int devmem_is_allowed(unsigned long page void free_init_pages(char *what, unsigned long begin, unsigned long end) { - unsigned long addr = begin; + unsigned long addr; + unsigned long begin_aligned, end_aligned; - if (addr >= end) + /* Make sure boundaries are page aligned */ + begin_aligned = PAGE_ALIGN(begin); + end_aligned = end & PAGE_MASK; + + if (WARN(begin_aligned >= end_aligned, "wrong range: [%#lx, %#lx]\n", begin, end)) return; + if (WARN_ON(begin_aligned != begin || end_aligned != end)) { + begin = begin_aligned; + end = end_aligned; + } + + addr = begin; + /* * If debugging page accesses then do not free this memory but * mark them not present - any buggy init-section access will @@ -343,7 +355,7 @@ void free_init_pages(char *what, unsigne */ #ifdef CONFIG_DEBUG_PAGEALLOC printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n", - begin, PAGE_ALIGN(end)); + begin, end); set_memory_np(begin, (end - begin) >> PAGE_SHIFT); #else /* @@ -358,8 +370,7 @@ void free_init_pages(char *what, unsigne for (; addr < end; addr += PAGE_SIZE) { ClearPageReserved(virt_to_page(addr)); init_page_count(virt_to_page(addr)); - memset((void *)(addr & ~(PAGE_SIZE-1)), - POISON_FREE_INITMEM, PAGE_SIZE); + memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE); free_page(addr); totalram_pages++; } @@ -376,6 +387,15 @@ void free_initmem(void) #ifdef CONFIG_BLK_DEV_INITRD void free_initrd_mem(unsigned long start, unsigned long end) { - free_init_pages("initrd memory", start, end); + /* + * end could be not aligned, and We can not align that, + * decompresser could be confused by aligned initrd_end + * We already reserve the end partial page before in + * - i386_start_kernel() + * - x86_64_start_kernel() + * - relocate_initrd() + * So here We can do PAGE_ALIGN() safely to get partial page to be freed + */ + free_init_pages("initrd memory", start, PAGE_ALIGN(end)); } #endif Index: linux-2.6/arch/x86/kernel/head32.c =================================================================== --- linux-2.6.orig/arch/x86/kernel/head32.c +++ linux-2.6/arch/x86/kernel/head32.c @@ -44,9 +44,10 @@ void __init i386_start_kernel(void) #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + /* Assume only end is not page aligned */ u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; - u64 ramdisk_end = ramdisk_image + ramdisk_size; + u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif Index: linux-2.6/arch/x86/kernel/head64.c =================================================================== --- linux-2.6.orig/arch/x86/kernel/head64.c +++ linux-2.6/arch/x86/kernel/head64.c @@ -103,9 +103,10 @@ void __init x86_64_start_reservations(ch #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ if (boot_params.hdr.type_of_loader && boot_params.hdr.ramdisk_image) { + /* Assume only end is not page aligned */ unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; - unsigned long ramdisk_end = ramdisk_image + ramdisk_size; + unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif Index: linux-2.6/arch/x86/kernel/setup.c =================================================================== --- linux-2.6.orig/arch/x86/kernel/setup.c +++ linux-2.6/arch/x86/kernel/setup.c @@ -314,16 +314,17 @@ static void __init reserve_brk(void) #define MAX_MAP_CHUNK (NR_FIX_BTMAPS << PAGE_SHIFT) static void __init relocate_initrd(void) { - + /* Assume only end is not page aligned */ u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; + u64 area_size = PAGE_ALIGN(ramdisk_size); u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; u64 ramdisk_here; unsigned long slop, clen, mapaddr; char *p, *q; /* We need to move the initrd down into lowmem */ - ramdisk_here = find_e820_area(0, end_of_lowmem, ramdisk_size, + ramdisk_here = find_e820_area(0, end_of_lowmem, area_size, PAGE_SIZE); if (ramdisk_here == -1ULL) @@ -332,7 +333,7 @@ static void __init relocate_initrd(void) /* Note: this includes all the lowmem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - reserve_early(ramdisk_here, ramdisk_here + ramdisk_size, + reserve_early(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK"); initrd_start = ramdisk_here + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; @@ -348,13 +349,13 @@ static void __init relocate_initrd(void) memcpy(q, p, clen); q += clen; ramdisk_image += clen; - ramdisk_size -= clen; + area_size -= clen; } /* Copy the highmem portion of the initrd */ - while (ramdisk_size) { + while (area_size) { slop = ramdisk_image & ~PAGE_MASK; - clen = ramdisk_size; + clen = area_size; if (clen > MAX_MAP_CHUNK-slop) clen = MAX_MAP_CHUNK-slop; mapaddr = ramdisk_image & PAGE_MASK; @@ -363,11 +364,10 @@ static void __init relocate_initrd(void) early_iounmap(p, clen+slop); q += clen; ramdisk_image += clen; - ramdisk_size -= clen; + area_size -= clen; } /* high pages is not converted by early_res_to_bootmem */ ramdisk_image = boot_params.hdr.ramdisk_image; - ramdisk_size = boot_params.hdr.ramdisk_size; printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to" " %08llx - %08llx\n", ramdisk_image, ramdisk_image + ramdisk_size - 1, @@ -376,9 +376,10 @@ static void __init relocate_initrd(void) static void __init reserve_initrd(void) { + /* Assume only end is not page aligned */ u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; - u64 ramdisk_end = ramdisk_image + ramdisk_size; + u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); u64 end_of_lowmem = max_low_pfn_mapped << PAGE_SHIFT; if (!boot_params.hdr.type_of_loader || -- To unsubscribe from this list: send the line "unsubscribe linux-arch" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html