Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752657AbbBVNYq (ORCPT ); Sun, 22 Feb 2015 08:24:46 -0500 Received: from mx1.redhat.com ([209.132.183.28]:60335 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752454AbbBVNYo (ORCPT ); Sun, 22 Feb 2015 08:24:44 -0500 Date: Sun, 22 Feb 2015 21:24:34 +0800 From: Baoquan He To: Yinghai Lu Cc: "H. Peter Anvin" , Linux Kernel Mailing List Subject: Re: [PATCH v2] x86, boot: Enable ident_mapping for kasl above 4G on 64bit Message-ID: <20150222132434.GB2073@dhcp-17-102.nay.redhat.com> References: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9900 Lines: 337 On 02/21/15 at 07:14pm, Yinghai Lu wrote: > On Sat, Feb 21, 2015 at 12:00 PM, Yinghai Lu wrote: > > > > Please use attached one to instead of the #PF handler in boot stage. > > It works when hard-code to move output above 4G. > > Please check v2 instead. Hi Yinghai, Many thanks. I just tested patch v2 and it works very well. Now I am working on the kaslr randomization separating job based on this patch, will post soon. Thanks again! Baoquan > > Thanks > > Yinghai > From: Yinghai Lu > Subject: [PATCH v2] x86, boot: Enable ident_mapping for kasl above 4G on 64bit > > split kernel_ident_mapping_init() and call that in boot::decompress_kernel > stage. it will cover new range that is above 4G. > > -v2: fix one typo, use round_up/round_down and use MACRO for size. > > Signed-off-by: Yinghai Lu > > --- > arch/x86/boot/compressed/misc.c | 10 ++++ > arch/x86/boot/compressed/misc_pgt.c | 61 +++++++++++++++++++++++++++++ > arch/x86/include/asm/page.h | 5 ++ > arch/x86/mm/ident_map.c | 74 ++++++++++++++++++++++++++++++++++++ > arch/x86/mm/init_64.c | 74 ------------------------------------ > 5 files changed, 151 insertions(+), 73 deletions(-) > > Index: linux-2.6/arch/x86/boot/compressed/misc.c > =================================================================== > --- linux-2.6.orig/arch/x86/boot/compressed/misc.c > +++ linux-2.6/arch/x86/boot/compressed/misc.c > @@ -9,6 +9,11 @@ > * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996 > */ > > +#ifdef CONFIG_X86_64 > +#define __pa(x) ((unsigned long)(x)) > +#define __va(x) ((void *)((unsigned long)(x))) > +#endif > + > #include "misc.h" > #include "../string.h" > > @@ -366,6 +371,8 @@ static void parse_elf(void *output) > free(phdrs); > } > > +#include "misc_pgt.c" > + > asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap, > unsigned char *input_data, > unsigned long input_len, > @@ -421,6 +428,9 @@ asmlinkage __visible void *decompress_ke > error("Wrong destination address"); > #endif > > + if (output != output_orig) > + fill_linux64_pagetable((unsigned long)output, output_len); > + > debug_putstr("\nDecompressing Linux... "); > decompress(input_data, input_len, NULL, NULL, output, NULL, error); > parse_elf(output); > Index: linux-2.6/arch/x86/include/asm/page.h > =================================================================== > --- linux-2.6.orig/arch/x86/include/asm/page.h > +++ linux-2.6/arch/x86/include/asm/page.h > @@ -37,7 +37,10 @@ static inline void copy_user_page(void * > alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr) > #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE > > +#ifndef __pa > #define __pa(x) __phys_addr((unsigned long)(x)) > +#endif > + > #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) > /* __pa_symbol should be used for C visible symbols. > This seems to be the official gcc blessed way to do such arithmetic. */ > @@ -51,7 +54,9 @@ static inline void copy_user_page(void * > #define __pa_symbol(x) \ > __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) > > +#ifndef __va > #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) > +#endif > > #define __boot_va(x) __va(x) > #define __boot_pa(x) __pa(x) > Index: linux-2.6/arch/x86/boot/compressed/misc_pgt.c > =================================================================== > --- /dev/null > +++ linux-2.6/arch/x86/boot/compressed/misc_pgt.c > @@ -0,0 +1,61 @@ > + > +#ifdef CONFIG_X86_64 > +#include > +#include > + > +#include "../../mm/ident_map.c" > + > +struct alloc_pgt_data { > + unsigned char *pgt_buf; > + unsigned long pgt_buf_size; > + unsigned long pgt_buf_offset; > +}; > + > +static void *alloc_pgt_page(void *context) > +{ > + struct alloc_pgt_data *d = (struct alloc_pgt_data *)context; > + unsigned char *p = (unsigned char *)d->pgt_buf; > + > + if (d->pgt_buf_offset >= d->pgt_buf_size) { > + debug_putstr("out of pgt_buf in misc.c\n"); > + return NULL; > + } > + > + p += d->pgt_buf_offset; > + d->pgt_buf_offset += PAGE_SIZE; > + > + return p; > +} > + > +/* 4 pages to cover cross 512G boundary */ > +#define PGT_BUF_SIZE (PAGE_SIZE*4) > + > +unsigned long __force_order; > +static unsigned char pgt_buf[PGT_BUF_SIZE] __aligned(PAGE_SIZE); > + > +static void fill_linux64_pagetable(unsigned long start, unsigned long size) > +{ > + struct alloc_pgt_data data = { > + .pgt_buf = (unsigned char *) pgt_buf, > + .pgt_buf_size = sizeof(pgt_buf), > + .pgt_buf_offset = 0, > + }; > + struct x86_mapping_info mapping_info = { > + .alloc_pgt_page = alloc_pgt_page, > + .context = &data, > + .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, > + }; > + unsigned long end = start + size; > + pgd_t *level4p = (pgd_t *)read_cr3(); > + > + /* align boundary to 2M */ > + start = round_down(start, PMD_SIZE); > + end = round_up(end, PMD_SIZE); > + if (start >= (1UL<<32)) > + kernel_ident_mapping_init(&mapping_info, level4p, start, end); > +} > +#else > +static void fill_linux64_pagetable(unsigned long start, unsigned long size) > +{ > +} > +#endif > Index: linux-2.6/arch/x86/mm/ident_map.c > =================================================================== > --- /dev/null > +++ linux-2.6/arch/x86/mm/ident_map.c > @@ -0,0 +1,74 @@ > + > +static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, > + unsigned long addr, unsigned long end) > +{ > + addr &= PMD_MASK; > + for (; addr < end; addr += PMD_SIZE) { > + pmd_t *pmd = pmd_page + pmd_index(addr); > + > + if (!pmd_present(*pmd)) > + set_pmd(pmd, __pmd(addr | pmd_flag)); > + } > +} > +static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, > + unsigned long addr, unsigned long end) > +{ > + unsigned long next; > + > + for (; addr < end; addr = next) { > + pud_t *pud = pud_page + pud_index(addr); > + pmd_t *pmd; > + > + next = (addr & PUD_MASK) + PUD_SIZE; > + if (next > end) > + next = end; > + > + if (pud_present(*pud)) { > + pmd = pmd_offset(pud, 0); > + ident_pmd_init(info->pmd_flag, pmd, addr, next); > + continue; > + } > + pmd = (pmd_t *)info->alloc_pgt_page(info->context); > + if (!pmd) > + return -ENOMEM; > + ident_pmd_init(info->pmd_flag, pmd, addr, next); > + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); > + } > + > + return 0; > +} > + > +int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, > + unsigned long addr, unsigned long end) > +{ > + unsigned long next; > + int result; > + int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; > + > + for (; addr < end; addr = next) { > + pgd_t *pgd = pgd_page + pgd_index(addr) + off; > + pud_t *pud; > + > + next = (addr & PGDIR_MASK) + PGDIR_SIZE; > + if (next > end) > + next = end; > + > + if (pgd_present(*pgd)) { > + pud = pud_offset(pgd, 0); > + result = ident_pud_init(info, pud, addr, next); > + if (result) > + return result; > + continue; > + } > + > + pud = (pud_t *)info->alloc_pgt_page(info->context); > + if (!pud) > + return -ENOMEM; > + result = ident_pud_init(info, pud, addr, next); > + if (result) > + return result; > + set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); > + } > + > + return 0; > +} > Index: linux-2.6/arch/x86/mm/init_64.c > =================================================================== > --- linux-2.6.orig/arch/x86/mm/init_64.c > +++ linux-2.6/arch/x86/mm/init_64.c > @@ -56,79 +56,7 @@ > > #include "mm_internal.h" > > -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, > - unsigned long addr, unsigned long end) > -{ > - addr &= PMD_MASK; > - for (; addr < end; addr += PMD_SIZE) { > - pmd_t *pmd = pmd_page + pmd_index(addr); > - > - if (!pmd_present(*pmd)) > - set_pmd(pmd, __pmd(addr | pmd_flag)); > - } > -} > -static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, > - unsigned long addr, unsigned long end) > -{ > - unsigned long next; > - > - for (; addr < end; addr = next) { > - pud_t *pud = pud_page + pud_index(addr); > - pmd_t *pmd; > - > - next = (addr & PUD_MASK) + PUD_SIZE; > - if (next > end) > - next = end; > - > - if (pud_present(*pud)) { > - pmd = pmd_offset(pud, 0); > - ident_pmd_init(info->pmd_flag, pmd, addr, next); > - continue; > - } > - pmd = (pmd_t *)info->alloc_pgt_page(info->context); > - if (!pmd) > - return -ENOMEM; > - ident_pmd_init(info->pmd_flag, pmd, addr, next); > - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); > - } > - > - return 0; > -} > - > -int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, > - unsigned long addr, unsigned long end) > -{ > - unsigned long next; > - int result; > - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; > - > - for (; addr < end; addr = next) { > - pgd_t *pgd = pgd_page + pgd_index(addr) + off; > - pud_t *pud; > - > - next = (addr & PGDIR_MASK) + PGDIR_SIZE; > - if (next > end) > - next = end; > - > - if (pgd_present(*pgd)) { > - pud = pud_offset(pgd, 0); > - result = ident_pud_init(info, pud, addr, next); > - if (result) > - return result; > - continue; > - } > - > - pud = (pud_t *)info->alloc_pgt_page(info->context); > - if (!pud) > - return -ENOMEM; > - result = ident_pud_init(info, pud, addr, next); > - if (result) > - return result; > - set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE)); > - } > - > - return 0; > -} > +#include "ident_map.c" > > static int __init parse_direct_gbpages_off(char *arg) > { -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/