2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								/*
							 | 
						
					
						
							
								
									
										
										
										
											2007-10-12 21:10:53 -04:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								 *  prepare to run common code
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 *
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 *  Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/init.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/linkage.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/types.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/kernel.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/string.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <linux/percpu.h>
							 | 
						
					
						
							
								
									
										
										
										
											2008-01-30 13:30:19 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <linux/start_kernel.h>
							 | 
						
					
						
							
								
									
										
										
										
											2008-03-28 10:49:44 +08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <linux/io.h>
							 | 
						
					
						
							
								
									
										
										
										
											2010-08-25 13:39:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <linux/memblock.h>
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <asm/processor.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <asm/proto.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <asm/smp.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <asm/setup.h>
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								#include <asm/desc.h>
							 | 
						
					
						
							
								
									
										
										
										
											2005-11-05 17:25:53 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/pgtable.h>
							 | 
						
					
						
							
								
									
										
										
										
											2007-05-02 19:27:07 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/tlbflush.h>
							 | 
						
					
						
							
								
									
										
										
										
											2005-11-05 17:25:53 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/sections.h>
							 | 
						
					
						
							
								
									
										
										
										
											2008-01-30 13:30:17 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/kdebug.h>
							 | 
						
					
						
							
								
									
										
										
										
											2008-01-30 13:33:17 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/e820.h>
							 | 
						
					
						
							
								
									
										
										
										
											2009-08-29 15:03:59 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/bios_ebda.h>
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-29 01:05:24 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/bootparam_utils.h>
							 | 
						
					
						
							
								
									
										
										
										
											2012-12-20 23:44:30 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								#include <asm/microcode.h>
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								/*
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 * Manage page tables very early on.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								 */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								extern pgd_t early_level4_pgt[PTRS_PER_PGD];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								static unsigned int __initdata next_early_pgt = 2;
							 | 
						
					
						
							
								
									
										
										
										
											2013-05-20 11:36:03 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								/* Wipe all early page tables except for the kernel symbol map */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								static void __init reset_early_page_tables(void)
							 | 
						
					
						
							
								
									
										
										
										
											2007-05-02 19:27:07 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									unsigned long i;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									for (i = 0; i < PTRS_PER_PGD-1; i++)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										early_level4_pgt[i].pgd = 0;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									next_early_pgt = 0;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									write_cr3(__pa(early_level4_pgt));
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								/* Create a new PMD entry */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								int __init early_make_pgtable(unsigned long address)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									unsigned long physaddr = address - __PAGE_OFFSET;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									unsigned long i;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									pgdval_t pgd, *pgd_p;
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pudval_t pud, *pud_p;
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pmdval_t pmd, *pmd_p;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									/* Invalid address or early pgt is done ?  */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									if (physaddr >= MAXMEM || read_cr3() != __pa(early_level4_pgt))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										return -1;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								again:
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									pgd_p = &early_level4_pgt[pgd_index(address)].pgd;
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pgd = *pgd_p;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									/*
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * The use of __START_KERNEL_map rather than __PAGE_OFFSET here is
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * critical -- __PAGE_OFFSET would point us back into the dynamic
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * range and we might end up looping forever...
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 */
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									if (pgd)
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
										pud_p = (pudval_t *)((pgd & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									else {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
											reset_early_page_tables();
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
											goto again;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										}
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										pud_p = (pudval_t *)early_dynamic_pgts[next_early_pgt++];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										for (i = 0; i < PTRS_PER_PUD; i++)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
											pud_p[i] = 0;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										*pgd_p = (pgdval_t)pud_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									}
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pud_p += pud_index(address);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									pud = *pud_p;
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									if (pud)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										pmd_p = (pmdval_t *)((pud & PTE_PFN_MASK) + __START_KERNEL_map - phys_base);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									else {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										if (next_early_pgt >= EARLY_DYNAMIC_PAGE_TABLES) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
											reset_early_page_tables();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
											goto again;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										pmd_p = (pmdval_t *)early_dynamic_pgts[next_early_pgt++];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										for (i = 0; i < PTRS_PER_PMD; i++)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
											pmd_p[i] = 0;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									}
							 | 
						
					
						
							
								
									
										
										
										
											2013-05-02 10:33:46 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pmd = (physaddr & PMD_MASK) + early_pmd_flags;
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:53 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									pmd_p[pmd_index(address)] = pmd;
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									return 0;
							 | 
						
					
						
							
								
									
										
										
										
											2007-05-02 19:27:07 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								/* Don't add a printk in there. printk relies on the PDA which is not initialized 
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								   yet. */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								static void __init clear_bss(void)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									memset(__bss_start, 0,
							 | 
						
					
						
							
								
									
										
										
										
											2005-11-05 17:25:53 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									       (unsigned long) __bss_stop - (unsigned long) __bss_start);
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:57 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								static unsigned long get_cmd_line_ptr(void)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									unsigned long cmd_line_ptr = boot_params.hdr.cmd_line_ptr;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-28 20:16:44 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									cmd_line_ptr |= (u64)boot_params.ext_cmd_line_ptr << 32;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:57 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									return cmd_line_ptr;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								static void __init copy_bootdata(char *real_mode_data)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									char * command_line;
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:57 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									unsigned long cmd_line_ptr;
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2007-10-15 17:13:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									memcpy(&boot_params, real_mode_data, sizeof boot_params);
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-29 01:05:24 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									sanitize_boot_params(&boot_params);
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:57 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									cmd_line_ptr = get_cmd_line_ptr();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									if (cmd_line_ptr) {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										command_line = __va(cmd_line_ptr);
							 | 
						
					
						
							
								
									
										
										
										
											2007-10-15 17:13:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
										memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
									}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-05-02 00:44:37 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									int i;
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2008-02-21 13:45:16 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									/*
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * Build-time sanity checks on the kernel image and module
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * area mappings. (these are purely build-time and produce no code)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 */
							 | 
						
					
						
							
								
									
										
										
										
											2013-03-04 21:16:17 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE);
							 | 
						
					
						
							
								
									
										
										
										
											2008-02-21 13:45:16 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE);
							 | 
						
					
						
							
								
									
										
										
										
											2013-03-04 21:16:17 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0);
							 | 
						
					
						
							
								
									
										
										
										
											2008-02-21 13:45:16 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
												(__START_KERNEL & PGDIR_MASK)));
							 | 
						
					
						
							
								
									
										
										
										
											2008-07-31 16:48:31 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
							 | 
						
					
						
							
								
									
										
										
										
											2008-02-21 13:45:16 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									/* Kill off the identity-map trampoline */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									reset_early_page_tables();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2006-12-07 02:14:12 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									/* clear bss before set_intr_gate with early_idt_handler */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									clear_bss();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-02-22 13:09:51 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
							 | 
						
					
						
							
								
									
										
										
										
											2013-10-30 16:37:00 -04:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
										set_intr_gate(i, early_idt_handlers[i]);
							 | 
						
					
						
							
								
									
										
										
										
											2007-10-19 20:35:03 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									load_idt((const struct desc_ptr *)&idt_descr);
							 | 
						
					
						
							
								
									
										
										
										
											2005-11-05 17:25:53 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:49 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									copy_bootdata(__va(real_mode_data));
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2012-12-20 23:44:30 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									/*
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 * Load microcode early on BSP.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									 */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									load_ucode_bsp();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-06-04 16:11:46 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG)
							 | 
						
					
						
							
								
									
										
										
										
											2008-09-28 18:49:46 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
										early_printk("Kernel alive\n");
							 | 
						
					
						
							
								
									
										
										
										
											2006-07-03 00:24:57 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
											 
										 
										
											
												x86, 64bit: Use a #PF handler to materialize early mappings on demand
Linear mode (CR0.PG = 0) is mutually exclusive with 64-bit mode; all
64-bit code has to use page tables.  This makes it awkward before we
have first set up properly all-covering page tables to access objects
that are outside the static kernel range.
So far we have dealt with that simply by mapping a fixed amount of
low memory, but that fails in at least two upcoming use cases:
1. We will support load and run kernel, struct boot_params, ramdisk,
   command line, etc. above the 4 GiB mark.
2. need to access ramdisk early to get microcode to update that as
   early possible.
We could use early_iomap to access them too, but it will make code to
messy and hard to be unified with 32 bit.
Hence, set up a #PF table and use a fixed number of buffers to set up
page tables on demand.  If the buffers fill up then we simply flush
them and start over.  These buffers are all in __initdata, so it does
not increase RAM usage at runtime.
Thus, with the help of the #PF handler, we can set the final kernel
mapping from blank, and switch to init_level4_pgt later.
During the switchover in head_64.S, before #PF handler is available,
we use three pages to handle kernel crossing 1G, 512G boundaries with
sharing page by playing games with page aliasing: the same page is
mapped twice in the higher-level tables with appropriate wraparound.
The kernel region itself will be properly mapped; other mappings may
be spurious.
early_make_pgtable is using kernel high mapping address to access pages
to set page table.
-v4: Add phys_base offset to make kexec happy, and add
	init_mapping_kernel()   - Yinghai
-v5: fix compiling with xen, and add back ident level3 and level2 for xen
     also move back init_level4_pgt from BSS to DATA again.
     because we have to clear it anyway.  - Yinghai
-v6: switch to init_level4_pgt in init_mem_mapping. - Yinghai
-v7: remove not needed clear_page for init_level4_page
     it is with fill 512,8,0 already in head_64.S  - Yinghai
-v8: we need to keep that handler alive until init_mem_mapping and don't
     let early_trap_init to trash that early #PF handler.
     So split early_trap_pf_init out and move it down. - Yinghai
-v9: switchover only cover kernel space instead of 1G so could avoid
     touch possible mem holes. - Yinghai
-v11: change far jmp back to far return to initial_code, that is needed
     to fix failure that is reported by Konrad on AMD systems.  - Yinghai
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-12-git-send-email-yinghai@kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
											
										 
										
											2013-01-24 12:19:52 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									clear_page(init_level4_pgt);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									/* set init_level4_pgt kernel high mapping*/
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									init_level4_pgt[511] = early_level4_pgt[511];
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2008-06-25 00:19:18 -04:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									x86_64_start_reservations(real_mode_data);
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								void __init x86_64_start_reservations(char *real_mode_data)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							
								
									
										
										
										
											2013-01-24 12:19:49 -08:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									/* version is always not zero if it is copied */
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
									if (!boot_params.hdr.version)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
										copy_bootdata(__va(real_mode_data));
							 | 
						
					
						
							
								
									
										
										
										
											2008-01-30 13:30:46 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2009-08-29 15:03:59 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
									reserve_ebda_region();
							 | 
						
					
						
							
								
									
										
										
										
											2008-01-30 13:33:17 +01:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2005-04-16 15:20:36 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
									start_kernel();
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 |