linux/arch/x86/mm/init_32.c

1247 lines
32 KiB
C
Raw Normal View History

/*
*
* Copyright (C) 1995 Linus Torvalds
*
* Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
*/
#include <linux/module.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/bootmem.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/bugs.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
#include <asm/smp.h>
unsigned int __VMALLOC_RESERVE = 128 << 20;
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
unsigned long highstart_pfn, highend_pfn;
static noinline int do_test_wp_bit(void);
static unsigned long __initdata table_start;
static unsigned long __meminitdata table_end;
static unsigned long __meminitdata table_top;
static int __initdata after_init_bootmem;
static __init void *alloc_low_page(void)
{
unsigned long pfn = table_end++;
void *adr;
if (pfn >= table_top)
panic("alloc_low_page: ran out of memory");
adr = __va(pfn * PAGE_SIZE);
memset(adr, 0, PAGE_SIZE);
return adr;
}
/*
* Creates a middle page table and puts a pointer to it in the
* given global directory entry. This only returns the gd entry
* in non-PAE compilation mode, since the middle layer is folded.
*/
static pmd_t * __init one_md_table_init(pgd_t *pgd)
{
pud_t *pud;
pmd_t *pmd_table;
#ifdef CONFIG_X86_PAE
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
if (after_init_bootmem)
pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
else
pmd_table = (pmd_t *)alloc_low_page();
paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
pud = pud_offset(pgd, 0);
BUG_ON(pmd_table != pmd_offset(pud, 0));
return pmd_table;
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
}
#endif
pud = pud_offset(pgd, 0);
pmd_table = pmd_offset(pud, 0);
return pmd_table;
}
/*
* Create a page table and place a pointer to it in a middle page
* directory entry:
*/
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
x86: fix CONFIG_PAGEALLOC related boot hangs/OOMs if CONFIG_PAGEALLOC is enabled then X86_FEATURE_PSE is disabled and all the kernel physical RAM pagetables are set up as 4K pages. This is needed so that CONFIG_PAGEALLOC can do finegrained mapping and unmapping of pages. as a side-effect though, the total size of memory allocated as kernel pagetables increases significantly. All these pagetables are allocated via alloc_bootmem_low_pages(), straight out of the lowmem DMA pool. If the system has enough RAM and a large kernel image then almost all of the 16 MB lowmem DMA pool is allocated to the image and to pagetables - leaving no space for __GFP_DMA allocations. this results in drivers failing and the bootup hanging: swapper invoked oom-killer: gfp_mask=0x80d1, order=0, oomkilladj=0 [<4015059f>] out_of_memory+0x17f/0x1c0 [<40151f3c>] __alloc_pages+0x37c/0x3a0 [<40168cd7>] slob_new_page+0x37/0x50 [<40168dff>] slob_alloc+0x10f/0x190 [<40169010>] __kmalloc_node+0x80/0x90 [<405a17e3>] scsi_host_alloc+0x33/0x2c0 [<405a1a82>] scsi_register+0x12/0x60 [<40d5889e>] aha1542_detect+0x9e/0x940 [<405c5ba5>] ultrastor_detect+0x265/0x5f0 [<401352f5>] getnstimeofday+0x35/0xf0 [<40d58751>] init_this_scsi_driver+0x41/0xf0 [<40d0b856>] kernel_init+0x136/0x310 [<40d58710>] init_this_scsi_driver+0x0/0xf0 [<40d0b720>] kernel_init+0x0/0x310 [<40105547>] kernel_thread_helper+0x7/0x10 ======================= the fix is to first allocate from above the DMA pool, and if that fails (for example due to it being a machine with less than 16 MB of RAM), allocate from the DMA pool as a fallback. With this fix applied i was able to boot a PAGEALLOC=y kernel that would hang before. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-10-17 16:04:34 +00:00
pte_t *page_table = NULL;
if (after_init_bootmem) {
x86: fix CONFIG_PAGEALLOC related boot hangs/OOMs if CONFIG_PAGEALLOC is enabled then X86_FEATURE_PSE is disabled and all the kernel physical RAM pagetables are set up as 4K pages. This is needed so that CONFIG_PAGEALLOC can do finegrained mapping and unmapping of pages. as a side-effect though, the total size of memory allocated as kernel pagetables increases significantly. All these pagetables are allocated via alloc_bootmem_low_pages(), straight out of the lowmem DMA pool. If the system has enough RAM and a large kernel image then almost all of the 16 MB lowmem DMA pool is allocated to the image and to pagetables - leaving no space for __GFP_DMA allocations. this results in drivers failing and the bootup hanging: swapper invoked oom-killer: gfp_mask=0x80d1, order=0, oomkilladj=0 [<4015059f>] out_of_memory+0x17f/0x1c0 [<40151f3c>] __alloc_pages+0x37c/0x3a0 [<40168cd7>] slob_new_page+0x37/0x50 [<40168dff>] slob_alloc+0x10f/0x190 [<40169010>] __kmalloc_node+0x80/0x90 [<405a17e3>] scsi_host_alloc+0x33/0x2c0 [<405a1a82>] scsi_register+0x12/0x60 [<40d5889e>] aha1542_detect+0x9e/0x940 [<405c5ba5>] ultrastor_detect+0x265/0x5f0 [<401352f5>] getnstimeofday+0x35/0xf0 [<40d58751>] init_this_scsi_driver+0x41/0xf0 [<40d0b856>] kernel_init+0x136/0x310 [<40d58710>] init_this_scsi_driver+0x0/0xf0 [<40d0b720>] kernel_init+0x0/0x310 [<40105547>] kernel_thread_helper+0x7/0x10 ======================= the fix is to first allocate from above the DMA pool, and if that fails (for example due to it being a machine with less than 16 MB of RAM), allocate from the DMA pool as a fallback. With this fix applied i was able to boot a PAGEALLOC=y kernel that would hang before. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-10-17 16:04:34 +00:00
#ifdef CONFIG_DEBUG_PAGEALLOC
page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
x86: fix CONFIG_PAGEALLOC related boot hangs/OOMs if CONFIG_PAGEALLOC is enabled then X86_FEATURE_PSE is disabled and all the kernel physical RAM pagetables are set up as 4K pages. This is needed so that CONFIG_PAGEALLOC can do finegrained mapping and unmapping of pages. as a side-effect though, the total size of memory allocated as kernel pagetables increases significantly. All these pagetables are allocated via alloc_bootmem_low_pages(), straight out of the lowmem DMA pool. If the system has enough RAM and a large kernel image then almost all of the 16 MB lowmem DMA pool is allocated to the image and to pagetables - leaving no space for __GFP_DMA allocations. this results in drivers failing and the bootup hanging: swapper invoked oom-killer: gfp_mask=0x80d1, order=0, oomkilladj=0 [<4015059f>] out_of_memory+0x17f/0x1c0 [<40151f3c>] __alloc_pages+0x37c/0x3a0 [<40168cd7>] slob_new_page+0x37/0x50 [<40168dff>] slob_alloc+0x10f/0x190 [<40169010>] __kmalloc_node+0x80/0x90 [<405a17e3>] scsi_host_alloc+0x33/0x2c0 [<405a1a82>] scsi_register+0x12/0x60 [<40d5889e>] aha1542_detect+0x9e/0x940 [<405c5ba5>] ultrastor_detect+0x265/0x5f0 [<401352f5>] getnstimeofday+0x35/0xf0 [<40d58751>] init_this_scsi_driver+0x41/0xf0 [<40d0b856>] kernel_init+0x136/0x310 [<40d58710>] init_this_scsi_driver+0x0/0xf0 [<40d0b720>] kernel_init+0x0/0x310 [<40105547>] kernel_thread_helper+0x7/0x10 ======================= the fix is to first allocate from above the DMA pool, and if that fails (for example due to it being a machine with less than 16 MB of RAM), allocate from the DMA pool as a fallback. With this fix applied i was able to boot a PAGEALLOC=y kernel that would hang before. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-10-17 16:04:34 +00:00
#endif
if (!page_table)
page_table =
x86: fix CONFIG_PAGEALLOC related boot hangs/OOMs if CONFIG_PAGEALLOC is enabled then X86_FEATURE_PSE is disabled and all the kernel physical RAM pagetables are set up as 4K pages. This is needed so that CONFIG_PAGEALLOC can do finegrained mapping and unmapping of pages. as a side-effect though, the total size of memory allocated as kernel pagetables increases significantly. All these pagetables are allocated via alloc_bootmem_low_pages(), straight out of the lowmem DMA pool. If the system has enough RAM and a large kernel image then almost all of the 16 MB lowmem DMA pool is allocated to the image and to pagetables - leaving no space for __GFP_DMA allocations. this results in drivers failing and the bootup hanging: swapper invoked oom-killer: gfp_mask=0x80d1, order=0, oomkilladj=0 [<4015059f>] out_of_memory+0x17f/0x1c0 [<40151f3c>] __alloc_pages+0x37c/0x3a0 [<40168cd7>] slob_new_page+0x37/0x50 [<40168dff>] slob_alloc+0x10f/0x190 [<40169010>] __kmalloc_node+0x80/0x90 [<405a17e3>] scsi_host_alloc+0x33/0x2c0 [<405a1a82>] scsi_register+0x12/0x60 [<40d5889e>] aha1542_detect+0x9e/0x940 [<405c5ba5>] ultrastor_detect+0x265/0x5f0 [<401352f5>] getnstimeofday+0x35/0xf0 [<40d58751>] init_this_scsi_driver+0x41/0xf0 [<40d0b856>] kernel_init+0x136/0x310 [<40d58710>] init_this_scsi_driver+0x0/0xf0 [<40d0b720>] kernel_init+0x0/0x310 [<40105547>] kernel_thread_helper+0x7/0x10 ======================= the fix is to first allocate from above the DMA pool, and if that fails (for example due to it being a machine with less than 16 MB of RAM), allocate from the DMA pool as a fallback. With this fix applied i was able to boot a PAGEALLOC=y kernel that would hang before. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-10-17 16:04:34 +00:00
(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
} else
page_table = (pte_t *)alloc_low_page();
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
BUG_ON(page_table != pte_offset_kernel(pmd, 0));
}
x86: fix CONFIG_PAGEALLOC related boot hangs/OOMs if CONFIG_PAGEALLOC is enabled then X86_FEATURE_PSE is disabled and all the kernel physical RAM pagetables are set up as 4K pages. This is needed so that CONFIG_PAGEALLOC can do finegrained mapping and unmapping of pages. as a side-effect though, the total size of memory allocated as kernel pagetables increases significantly. All these pagetables are allocated via alloc_bootmem_low_pages(), straight out of the lowmem DMA pool. If the system has enough RAM and a large kernel image then almost all of the 16 MB lowmem DMA pool is allocated to the image and to pagetables - leaving no space for __GFP_DMA allocations. this results in drivers failing and the bootup hanging: swapper invoked oom-killer: gfp_mask=0x80d1, order=0, oomkilladj=0 [<4015059f>] out_of_memory+0x17f/0x1c0 [<40151f3c>] __alloc_pages+0x37c/0x3a0 [<40168cd7>] slob_new_page+0x37/0x50 [<40168dff>] slob_alloc+0x10f/0x190 [<40169010>] __kmalloc_node+0x80/0x90 [<405a17e3>] scsi_host_alloc+0x33/0x2c0 [<405a1a82>] scsi_register+0x12/0x60 [<40d5889e>] aha1542_detect+0x9e/0x940 [<405c5ba5>] ultrastor_detect+0x265/0x5f0 [<401352f5>] getnstimeofday+0x35/0xf0 [<40d58751>] init_this_scsi_driver+0x41/0xf0 [<40d0b856>] kernel_init+0x136/0x310 [<40d58710>] init_this_scsi_driver+0x0/0xf0 [<40d0b720>] kernel_init+0x0/0x310 [<40105547>] kernel_thread_helper+0x7/0x10 ======================= the fix is to first allocate from above the DMA pool, and if that fails (for example due to it being a machine with less than 16 MB of RAM), allocate from the DMA pool as a fallback. With this fix applied i was able to boot a PAGEALLOC=y kernel that would hang before. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2007-10-17 16:04:34 +00:00
return pte_offset_kernel(pmd, 0);
}
x86: fix assumed to be contiguous leaf page tables for kmap_atomic region (take 2) Debugging and original patch from Nick Piggin <npiggin@suse.de> The early fixmap pmd entry inserted at the very top of the KVA is causing the subsequent fixmap mapping code to not provide physically linear pte pages over the kmap atomic portion of the fixmap (which relies on said property to calculate pte addresses). This has caused weird boot failures in kmap_atomic much later in the boot process (initial userspace faults) on a 32-bit PAE system with a larger number of CPUs (smaller CPU counts tend not to run over into the next page so don't show up the problem). Solve this by attempting to clear out the page table, and copy any of its entries to the new one. Also, add a bug if a nonlinear condition is encountered and can't be resolved, which might save some hours of debugging if this fragile scheme ever breaks again... Once we have such logic, we can also use it to eliminate the early ioremap trickery around the page table setup for the fixmap area. This also fixes potential issues with FIX_* entries sharing the leaf page table with the early ioremap ones getting discarded by early_ioremap_clear() and not restored by early_ioremap_reset(). It at once eliminates the temporary (and configuration, namely NR_CPUS, dependent) unavailability of early fixed mappings during the time the fixmap area page tables get constructed. Finally, also replace the hard coded calculation of the initial table space needed for the fixmap area with a proper one, allowing kernels configured for large CPU counts to actually boot. Based-on: Nick Piggin <npiggin@suse.de> Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-16 11:59:33 +00:00
static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
unsigned long vaddr, pte_t *lastpte)
{
#ifdef CONFIG_HIGHMEM
/*
* Something (early fixmap) may already have put a pte
* page here, which causes the page table allocation
* to become nonlinear. Attempt to fix it, and if it
* is still nonlinear then we have to bug.
*/
int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
if (pmd_idx_kmap_begin != pmd_idx_kmap_end
&& (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
&& (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
&& ((__pa(pte) >> PAGE_SHIFT) < table_start
|| (__pa(pte) >> PAGE_SHIFT) >= table_end)) {
pte_t *newpte;
int i;
BUG_ON(after_init_bootmem);
newpte = alloc_low_page();
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(newpte + i, pte[i]);
paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
BUG_ON(newpte != pte_offset_kernel(pmd, 0));
__flush_tlb_all();
paravirt_release_pte(__pa(pte) >> PAGE_SHIFT);
pte = newpte;
}
BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
&& vaddr > fix_to_virt(FIX_KMAP_END)
&& lastpte && lastpte + PTRS_PER_PTE != pte);
#endif
return pte;
}
/*
* This function initializes a certain range of kernel virtual memory
* with new bootmem page tables, everywhere page tables are missing in
* the given range.
*
* NOTE: The pagetables are allocated contiguous on the physical space
* so we can cache the place of the first one and move around without
* checking the pgd every time.
*/
static void __init
page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
{
int pgd_idx, pmd_idx;
unsigned long vaddr;
pgd_t *pgd;
pmd_t *pmd;
x86: fix assumed to be contiguous leaf page tables for kmap_atomic region (take 2) Debugging and original patch from Nick Piggin <npiggin@suse.de> The early fixmap pmd entry inserted at the very top of the KVA is causing the subsequent fixmap mapping code to not provide physically linear pte pages over the kmap atomic portion of the fixmap (which relies on said property to calculate pte addresses). This has caused weird boot failures in kmap_atomic much later in the boot process (initial userspace faults) on a 32-bit PAE system with a larger number of CPUs (smaller CPU counts tend not to run over into the next page so don't show up the problem). Solve this by attempting to clear out the page table, and copy any of its entries to the new one. Also, add a bug if a nonlinear condition is encountered and can't be resolved, which might save some hours of debugging if this fragile scheme ever breaks again... Once we have such logic, we can also use it to eliminate the early ioremap trickery around the page table setup for the fixmap area. This also fixes potential issues with FIX_* entries sharing the leaf page table with the early ioremap ones getting discarded by early_ioremap_clear() and not restored by early_ioremap_reset(). It at once eliminates the temporary (and configuration, namely NR_CPUS, dependent) unavailability of early fixed mappings during the time the fixmap area page tables get constructed. Finally, also replace the hard coded calculation of the initial table space needed for the fixmap area with a proper one, allowing kernels configured for large CPU counts to actually boot. Based-on: Nick Piggin <npiggin@suse.de> Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-16 11:59:33 +00:00
pte_t *pte = NULL;
vaddr = start;
pgd_idx = pgd_index(vaddr);
pmd_idx = pmd_index(vaddr);
pgd = pgd_base + pgd_idx;
for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
pmd = one_md_table_init(pgd);
pmd = pmd + pmd_index(vaddr);
for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
pmd++, pmd_idx++) {
x86: fix assumed to be contiguous leaf page tables for kmap_atomic region (take 2) Debugging and original patch from Nick Piggin <npiggin@suse.de> The early fixmap pmd entry inserted at the very top of the KVA is causing the subsequent fixmap mapping code to not provide physically linear pte pages over the kmap atomic portion of the fixmap (which relies on said property to calculate pte addresses). This has caused weird boot failures in kmap_atomic much later in the boot process (initial userspace faults) on a 32-bit PAE system with a larger number of CPUs (smaller CPU counts tend not to run over into the next page so don't show up the problem). Solve this by attempting to clear out the page table, and copy any of its entries to the new one. Also, add a bug if a nonlinear condition is encountered and can't be resolved, which might save some hours of debugging if this fragile scheme ever breaks again... Once we have such logic, we can also use it to eliminate the early ioremap trickery around the page table setup for the fixmap area. This also fixes potential issues with FIX_* entries sharing the leaf page table with the early ioremap ones getting discarded by early_ioremap_clear() and not restored by early_ioremap_reset(). It at once eliminates the temporary (and configuration, namely NR_CPUS, dependent) unavailability of early fixed mappings during the time the fixmap area page tables get constructed. Finally, also replace the hard coded calculation of the initial table space needed for the fixmap area with a proper one, allowing kernels configured for large CPU counts to actually boot. Based-on: Nick Piggin <npiggin@suse.de> Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-16 11:59:33 +00:00
pte = page_table_kmap_check(one_page_table_init(pmd),
pmd, vaddr, pte);
vaddr += PMD_SIZE;
}
pmd_idx = 0;
}
}
static inline int is_kernel_text(unsigned long addr)
{
if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
return 1;
return 0;
}
/*
* This maps the physical memory to kernel virtual address space, a total
* of max_low_pfn pages, by creating page tables starting from address
* PAGE_OFFSET:
*/
static void __init kernel_physical_mapping_init(pgd_t *pgd_base,
unsigned long start_pfn,
unsigned long end_pfn,
int use_pse)
{
int pgd_idx, pmd_idx, pte_ofs;
unsigned long pfn;
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte;
unsigned pages_2m, pages_4k;
int mapping_iter;
/*
* First iteration will setup identity mapping using large/small pages
* based on use_pse, with other attributes same as set by
* the early code in head_32.S
*
* Second iteration will setup the appropriate attributes (NX, GLOBAL..)
* as desired for the kernel identity mapping.
*
* This two pass mechanism conforms to the TLB app note which says:
*
* "Software should not write to a paging-structure entry in a way
* that would change, for any linear address, both the page size
* and either the page frame or attributes."
*/
mapping_iter = 1;
if (!cpu_has_pse)
use_pse = 0;
repeat:
pages_2m = pages_4k = 0;
pfn = start_pfn;
pgd_idx = pgd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
pgd = pgd_base + pgd_idx;
for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
pmd = one_md_table_init(pgd);
if (pfn >= end_pfn)
continue;
#ifdef CONFIG_X86_PAE
pmd_idx = pmd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
pmd += pmd_idx;
#else
pmd_idx = 0;
#endif
for (; pmd_idx < PTRS_PER_PMD && pfn < end_pfn;
pmd++, pmd_idx++) {
unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET;
/*
* Map with big pages if possible, otherwise
* create normal page tables:
*/
if (use_pse) {
unsigned int addr2;
pgprot_t prot = PAGE_KERNEL_LARGE;
/*
* first pass will use the same initial
* identity mapping attribute + _PAGE_PSE.
*/
pgprot_t init_prot =
__pgprot(PTE_IDENT_ATTR |
_PAGE_PSE);
addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
PAGE_OFFSET + PAGE_SIZE-1;
if (is_kernel_text(addr) ||
is_kernel_text(addr2))
prot = PAGE_KERNEL_LARGE_EXEC;
pages_2m++;
if (mapping_iter == 1)
set_pmd(pmd, pfn_pmd(pfn, init_prot));
else
set_pmd(pmd, pfn_pmd(pfn, prot));
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
pfn += PTRS_PER_PTE;
continue;
}
pte = one_page_table_init(pmd);
pte_ofs = pte_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
pte += pte_ofs;
for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn;
pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) {
pgprot_t prot = PAGE_KERNEL;
/*
* first pass will use the same initial
* identity mapping attribute.
*/
pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR);
if (is_kernel_text(addr))
prot = PAGE_KERNEL_EXEC;
pages_4k++;
if (mapping_iter == 1)
set_pte(pte, pfn_pte(pfn, init_prot));
else
set_pte(pte, pfn_pte(pfn, prot));
}
}
}
if (mapping_iter == 1) {
/*
* update direct mapping page count only in the first
* iteration.
*/
update_page_count(PG_LEVEL_2M, pages_2m);
update_page_count(PG_LEVEL_4K, pages_4k);
/*
* local global flush tlb, which will flush the previous
* mappings present in both small and large page TLB's.
*/
__flush_tlb_all();
/*
* Second iteration will set the actual desired PTE attributes.
*/
mapping_iter = 2;
goto repeat;
}
}
/*
* devmem_is_allowed() checks to see if /dev/mem access to a certain address
* is valid. The argument is a physical page number.
*
*
* On x86, access has to be given to the first megabyte of ram because that area
* contains bios code and data regions used by X and dosemu and similar apps.
* Access has to be given to non-kernel-ram areas as well, these contain the PCI
* mmio resources as well as potential bios/acpi data regions.
*/
int devmem_is_allowed(unsigned long pagenr)
{
if (pagenr <= 256)
return 1;
if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
return 0;
if (!page_is_ram(pagenr))
return 1;
return 0;
}
pte_t *kmap_pte;
pgprot_t kmap_prot;
static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
{
return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
vaddr), vaddr), vaddr);
}
static void __init kmap_init(void)
{
unsigned long kmap_vstart;
/*
* Cache the first kmap pte:
*/
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
kmap_prot = PAGE_KERNEL;
}
#ifdef CONFIG_HIGHMEM
static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
unsigned long vaddr;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
vaddr = PKMAP_BASE;
page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);
pgd = swapper_pg_dir + pgd_index(vaddr);
pud = pud_offset(pgd, vaddr);
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pkmap_page_table = pte;
}
static void __init add_one_highpage_init(struct page *page, int pfn)
{
ClearPageReserved(page);
init_page_count(page);
__free_page(page);
totalhigh_pages++;
}
struct add_highpages_data {
unsigned long start_pfn;
unsigned long end_pfn;
};
static int __init add_highpages_work_fn(unsigned long start_pfn,
unsigned long end_pfn, void *datax)
{
int node_pfn;
struct page *page;
unsigned long final_start_pfn, final_end_pfn;
struct add_highpages_data *data;
data = (struct add_highpages_data *)datax;
final_start_pfn = max(start_pfn, data->start_pfn);
final_end_pfn = min(end_pfn, data->end_pfn);
if (final_start_pfn >= final_end_pfn)
return 0;
for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
node_pfn++) {
if (!pfn_valid(node_pfn))
continue;
page = pfn_to_page(node_pfn);
add_one_highpage_init(page, node_pfn);
}
return 0;
}
void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
unsigned long end_pfn)
{
struct add_highpages_data data;
data.start_pfn = start_pfn;
data.end_pfn = end_pfn;
work_with_active_regions(nid, add_highpages_work_fn, &data);
}
#ifndef CONFIG_NUMA
static void __init set_highmem_pages_init(void)
{
add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
totalram_pages += totalhigh_pages;
}
#endif /* !CONFIG_NUMA */
#else
static inline void permanent_kmaps_init(pgd_t *pgd_base)
{
}
static inline void set_highmem_pages_init(void)
{
}
#endif /* CONFIG_HIGHMEM */
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
void __init native_pagetable_setup_start(pgd_t *base)
{
unsigned long pfn, va;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
/*
* Remove any mappings which extend past the end of physical
* memory from the boot time page table:
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
*/
for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
pgd = base + pgd_index(va);
if (!pgd_present(*pgd))
break;
pud = pud_offset(pgd, va);
pmd = pmd_offset(pud, va);
if (!pmd_present(*pmd))
break;
pte = pte_offset_kernel(pmd, va);
if (!pte_present(*pte))
break;
pte_clear(NULL, va, pte);
}
paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
}
void __init native_pagetable_setup_done(pgd_t *base)
{
}
/*
* Build a proper pagetable for the kernel mappings. Up until this
* point, we've been running on some set of pagetables constructed by
* the boot process.
*
* If we're booting on native hardware, this will be a pagetable
* constructed in arch/x86/kernel/head_32.S. The root of the
* pagetable will be swapper_pg_dir.
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
*
* If we're booting paravirtualized under a hypervisor, then there are
* more options: we may already be running PAE, and the pagetable may
* or may not be based in swapper_pg_dir. In any case,
* paravirt_pagetable_setup_start() will set up swapper_pg_dir
* appropriately for the rest of the initialization to work.
*
* In general, pagetable_init() assumes that the pagetable may already
* be partially populated, and so it avoids stomping on any existing
* mappings.
*/
static void __init early_ioremap_page_table_range_init(pgd_t *pgd_base)
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
{
unsigned long vaddr, end;
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
/*
* Fixed mappings, only the page table structure has to be
* created - mappings will be set by set_fixmap():
*/
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
[PATCH] i386: PARAVIRT: Hooks to set up initial pagetable This patch introduces paravirt_ops hooks to control how the kernel's initial pagetable is set up. In the case of a native boot, the very early bootstrap code creates a simple non-PAE pagetable to map the kernel and physical memory. When the VM subsystem is initialized, it creates a proper pagetable which respects the PAE mode, large pages, etc. When booting under a hypervisor, there are many possibilities for what paging environment the hypervisor establishes for the guest kernel, so the constructon of the kernel's pagetable depends on the hypervisor. In the case of Xen, the hypervisor boots the kernel with a fully constructed pagetable, which is already using PAE if necessary. Also, Xen requires particular care when constructing pagetables to make sure all pagetables are always mapped read-only. In order to make this easier, kernel's initial pagetable construction has been changed to only allocate and initialize a pagetable page if there's no page already present in the pagetable. This allows the Xen paravirt backend to make a copy of the hypervisor-provided pagetable, allowing the kernel to establish any more mappings it needs while keeping the existing ones. A slightly subtle point which is worth highlighting here is that Xen requires all kernel mappings to share the same pte_t pages between all pagetables, so that updating a kernel page's mapping in one pagetable is reflected in all other pagetables. This makes it possible to allocate a page and attach it to a pagetable without having to explicitly enumerate that page's mapping in all pagetables. And: +From: "Eric W. Biederman" <ebiederm@xmission.com> If we don't set the leaf page table entries it is quite possible that will inherit and incorrect page table entry from the initial boot page table setup in head.S. So we need to redo the effort here, so we pick up PSE, PGE and the like. Hypervisors like Xen require that their page tables be read-only, which is slightly incompatible with our low identity mappings, however I discussed this with Jeremy he has modified the Xen early set_pte function to avoid problems in this area. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Jeremy Fitzhardinge <jeremy@xensource.com> Signed-off-by: Andi Kleen <ak@suse.de> Acked-by: William Irwin <bill.irwin@oracle.com> Cc: Ingo Molnar <mingo@elte.hu>
2007-05-02 17:27:13 +00:00
end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
page_table_range_init(vaddr, end, pgd_base);
early_ioremap_reset();
}
static void __init pagetable_init(void)
{
pgd_t *pgd_base = swapper_pg_dir;
permanent_kmaps_init(pgd_base);
}
#ifdef CONFIG_ACPI_SLEEP
/*
* ACPI suspend needs this for resume, because things like the intel-agp
* driver might have split up a kernel 4MB mapping.
*/
char swsusp_pg_dir[PAGE_SIZE]
__attribute__ ((aligned(PAGE_SIZE)));
static inline void save_pg_dir(void)
{
memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
}
#else /* !CONFIG_ACPI_SLEEP */
static inline void save_pg_dir(void)
{
}
#endif /* !CONFIG_ACPI_SLEEP */
void zap_low_mappings(void)
{
int i;
/*
* Zap initial low-memory mappings.
*
* Note that "pgd_clear()" doesn't do it for
* us, because pgd_clear() is a no-op on i386.
*/
for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
#ifdef CONFIG_X86_PAE
set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
}
flush_tlb_all();
}
int nx_enabled;
pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
EXPORT_SYMBOL_GPL(__supported_pte_mask);
#ifdef CONFIG_X86_PAE
static int disable_nx __initdata;
/*
* noexec = on|off
*
* Control non executable mappings.
*
* on Enable
* off Disable
*/
static int __init noexec_setup(char *str)
{
if (!str || !strcmp(str, "on")) {
if (cpu_has_nx) {
__supported_pte_mask |= _PAGE_NX;
disable_nx = 0;
}
} else {
if (!strcmp(str, "off")) {
disable_nx = 1;
__supported_pte_mask &= ~_PAGE_NX;
} else {
return -EINVAL;
}
}
return 0;
}
early_param("noexec", noexec_setup);
static void __init set_nx(void)
{
unsigned int v[4], l, h;
if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
if ((v[3] & (1 << 20)) && !disable_nx) {
rdmsr(MSR_EFER, l, h);
l |= EFER_NX;
wrmsr(MSR_EFER, l, h);
nx_enabled = 1;
__supported_pte_mask |= _PAGE_NX;
}
}
}
#endif
/* user-defined highmem size */
static unsigned int highmem_pages = -1;
/*
* highmem=size forces highmem to be exactly 'size' bytes.
* This works even on boxes that have no highmem otherwise.
* This also works to reduce highmem size on bigger boxes.
*/
static int __init parse_highmem(char *arg)
{
if (!arg)
return -EINVAL;
highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT;
return 0;
}
early_param("highmem", parse_highmem);
/*
* Determine low and high memory ranges:
*/
void __init find_low_pfn_range(void)
{
/* it could update max_pfn */
/* max_low_pfn is 0, we already have early_res support */
max_low_pfn = max_pfn;
if (max_low_pfn > MAXMEM_PFN) {
if (highmem_pages == -1)
highmem_pages = max_pfn - MAXMEM_PFN;
if (highmem_pages + MAXMEM_PFN < max_pfn)
max_pfn = MAXMEM_PFN + highmem_pages;
if (highmem_pages + MAXMEM_PFN > max_pfn) {
printk(KERN_WARNING "only %luMB highmem pages "
"available, ignoring highmem size of %uMB.\n",
pages_to_mb(max_pfn - MAXMEM_PFN),
pages_to_mb(highmem_pages));
highmem_pages = 0;
}
max_low_pfn = MAXMEM_PFN;
#ifndef CONFIG_HIGHMEM
/* Maximum memory usable is what is directly addressable */
printk(KERN_WARNING "Warning only %ldMB will be used.\n",
MAXMEM>>20);
if (max_pfn > MAX_NONPAE_PFN)
printk(KERN_WARNING
"Use a HIGHMEM64G enabled kernel.\n");
else
printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
max_pfn = MAXMEM_PFN;
#else /* !CONFIG_HIGHMEM */
#ifndef CONFIG_HIGHMEM64G
if (max_pfn > MAX_NONPAE_PFN) {
max_pfn = MAX_NONPAE_PFN;
printk(KERN_WARNING "Warning only 4GB will be used."
"Use a HIGHMEM64G enabled kernel.\n");
}
#endif /* !CONFIG_HIGHMEM64G */
#endif /* !CONFIG_HIGHMEM */
} else {
if (highmem_pages == -1)
highmem_pages = 0;
#ifdef CONFIG_HIGHMEM
if (highmem_pages >= max_pfn) {
printk(KERN_ERR "highmem size specified (%uMB) is "
"bigger than pages available (%luMB)!.\n",
pages_to_mb(highmem_pages),
pages_to_mb(max_pfn));
highmem_pages = 0;
}
if (highmem_pages) {
if (max_low_pfn - highmem_pages <
64*1024*1024/PAGE_SIZE){
printk(KERN_ERR "highmem size %uMB results in "
"smaller than 64MB lowmem, ignoring it.\n"
, pages_to_mb(highmem_pages));
highmem_pages = 0;
}
max_low_pfn -= highmem_pages;
}
#else
if (highmem_pages)
printk(KERN_ERR "ignoring highmem size on non-highmem"
" kernel!\n");
#endif
}
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init initmem_init(unsigned long start_pfn,
unsigned long end_pfn)
{
#ifdef CONFIG_HIGHMEM
highstart_pfn = highend_pfn = max_pfn;
if (max_pfn > max_low_pfn)
highstart_pfn = max_low_pfn;
memory_present(0, 0, highend_pfn);
e820_register_active_regions(0, 0, highend_pfn);
printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
pages_to_mb(highend_pfn - highstart_pfn));
num_physpages = highend_pfn;
high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
memory_present(0, 0, max_low_pfn);
e820_register_active_regions(0, 0, max_low_pfn);
num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
#ifdef CONFIG_FLATMEM
max_mapnr = num_physpages;
#endif
printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
pages_to_mb(max_low_pfn));
setup_bootmem_allocator();
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
static void __init zone_sizes_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] =
virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
#endif
free_area_init_nodes(max_zone_pfns);
}
void __init setup_bootmem_allocator(void)
{
int i;
unsigned long bootmap_size, bootmap;
/*
* Initialize the boot-time allocator (with low memory only):
*/
bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
bootmap = find_e820_area(min_low_pfn<<PAGE_SHIFT,
max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
PAGE_SIZE);
if (bootmap == -1L)
panic("Cannot find bootmem map of size %ld\n", bootmap_size);
reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP");
/* don't touch min_low_pfn */
bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT,
min_low_pfn, max_low_pfn);
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: %08lx - %08lx\n",
min_low_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT);
printk(KERN_INFO " bootmap %08lx - %08lx\n",
bootmap, bootmap + bootmap_size);
for_each_online_node(i)
free_bootmem_with_active_regions(i, max_low_pfn);
early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT);
after_init_bootmem = 1;
}
static void __init find_early_table_space(unsigned long end, int use_pse)
{
unsigned long puds, pmds, ptes, tables, start;
puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
tables = PAGE_ALIGN(puds * sizeof(pud_t));
pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
tables += PAGE_ALIGN(pmds * sizeof(pmd_t));
if (use_pse) {
unsigned long extra;
extra = end - ((end>>PMD_SHIFT) << PMD_SHIFT);
extra += PMD_SIZE;
ptes = (extra + PAGE_SIZE - 1) >> PAGE_SHIFT;
} else
ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
tables += PAGE_ALIGN(ptes * sizeof(pte_t));
/* for fixmap */
x86: fix assumed to be contiguous leaf page tables for kmap_atomic region (take 2) Debugging and original patch from Nick Piggin <npiggin@suse.de> The early fixmap pmd entry inserted at the very top of the KVA is causing the subsequent fixmap mapping code to not provide physically linear pte pages over the kmap atomic portion of the fixmap (which relies on said property to calculate pte addresses). This has caused weird boot failures in kmap_atomic much later in the boot process (initial userspace faults) on a 32-bit PAE system with a larger number of CPUs (smaller CPU counts tend not to run over into the next page so don't show up the problem). Solve this by attempting to clear out the page table, and copy any of its entries to the new one. Also, add a bug if a nonlinear condition is encountered and can't be resolved, which might save some hours of debugging if this fragile scheme ever breaks again... Once we have such logic, we can also use it to eliminate the early ioremap trickery around the page table setup for the fixmap area. This also fixes potential issues with FIX_* entries sharing the leaf page table with the early ioremap ones getting discarded by early_ioremap_clear() and not restored by early_ioremap_reset(). It at once eliminates the temporary (and configuration, namely NR_CPUS, dependent) unavailability of early fixed mappings during the time the fixmap area page tables get constructed. Finally, also replace the hard coded calculation of the initial table space needed for the fixmap area with a proper one, allowing kernels configured for large CPU counts to actually boot. Based-on: Nick Piggin <npiggin@suse.de> Signed-off-by: Jan Beulich <jbeulich@novell.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-16 11:59:33 +00:00
tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t));
/*
* RED-PEN putting page tables only on node 0 could
* cause a hotspot and fill up ZONE_DMA. The page tables
* need roughly 0.5KB per GB.
*/
start = 0x7000;
table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT,
tables, PAGE_SIZE);
if (table_start == -1UL)
panic("Cannot find space for the kernel page tables");
table_start >>= PAGE_SHIFT;
table_end = table_start;
table_top = table_start + (tables>>PAGE_SHIFT);
printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
end, table_start << PAGE_SHIFT,
(table_start << PAGE_SHIFT) + tables);
}
unsigned long __init_refok init_memory_mapping(unsigned long start,
unsigned long end)
{
pgd_t *pgd_base = swapper_pg_dir;
unsigned long start_pfn, end_pfn;
unsigned long big_page_start;
#ifdef CONFIG_DEBUG_PAGEALLOC
/*
* For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
* This will simplify cpa(), which otherwise needs to support splitting
* large pages into small in interrupt context, etc.
*/
int use_pse = 0;
#else
int use_pse = cpu_has_pse;
#endif
/*
* Find space for the kernel direct mapping tables.
*/
if (!after_init_bootmem)
find_early_table_space(end, use_pse);
#ifdef CONFIG_X86_PAE
set_nx();
if (nx_enabled)
printk(KERN_INFO "NX (Execute Disable) protection: active\n");
#endif
/* Enable PSE if available */
if (cpu_has_pse)
set_in_cr4(X86_CR4_PSE);
/* Enable PGE if available */
if (cpu_has_pge) {
set_in_cr4(X86_CR4_PGE);
__supported_pte_mask |= _PAGE_GLOBAL;
}
/*
* Don't use a large page for the first 2/4MB of memory
* because there are often fixed size MTRRs in there
* and overlapping MTRRs into large pages can cause
* slowdowns.
*/
big_page_start = PMD_SIZE;
if (start < big_page_start) {
start_pfn = start >> PAGE_SHIFT;
end_pfn = min(big_page_start>>PAGE_SHIFT, end>>PAGE_SHIFT);
} else {
/* head is not big page alignment ? */
start_pfn = start >> PAGE_SHIFT;
end_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
}
if (start_pfn < end_pfn)
kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn, 0);
/* big page range */
start_pfn = ((start + (PMD_SIZE - 1))>>PMD_SHIFT)
<< (PMD_SHIFT - PAGE_SHIFT);
if (start_pfn < (big_page_start >> PAGE_SHIFT))
start_pfn = big_page_start >> PAGE_SHIFT;
end_pfn = (end>>PMD_SHIFT) << (PMD_SHIFT - PAGE_SHIFT);
if (start_pfn < end_pfn)
kernel_physical_mapping_init(pgd_base, start_pfn, end_pfn,
use_pse);
/* tail is not big page alignment ? */
start_pfn = end_pfn;
if (start_pfn > (big_page_start>>PAGE_SHIFT)) {
end_pfn = end >> PAGE_SHIFT;
if (start_pfn < end_pfn)
kernel_physical_mapping_init(pgd_base, start_pfn,
end_pfn, 0);
}
early_ioremap_page_table_range_init(pgd_base);
load_cr3(swapper_pg_dir);
__flush_tlb_all();
if (!after_init_bootmem)
reserve_early(table_start << PAGE_SHIFT,
table_end << PAGE_SHIFT, "PGTABLE");
if (!after_init_bootmem)
early_memtest(start, end);
return end >> PAGE_SHIFT;
}
/*
* paging_init() sets up the page tables - note that the first 8MB are
* already mapped by head.S.
*
* This routines also unmaps the page at virtual kernel address 0, so
* that we can trap those pesky NULL-reference errors in the kernel.
*/
void __init paging_init(void)
{
pagetable_init();
__flush_tlb_all();
kmap_init();
/*
* NOTE: at this point the bootmem allocator is fully available.
*/
sparse_init();
zone_sizes_init();
}
/*
* Test if the WP bit works in supervisor mode. It isn't supported on 386's
* and also on some strange 486's. All 586+'s are OK. This used to involve
* black magic jumps to work around some nasty CPU bugs, but fortunately the
* switch to using exceptions got rid of all that.
*/
static void __init test_wp_bit(void)
{
printk(KERN_INFO
"Checking if this processor honours the WP bit even in supervisor mode...");
/* Any page-aligned address will do, the test is non-destructive */
__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
boot_cpu_data.wp_works_ok = do_test_wp_bit();
clear_fixmap(FIX_WP_TEST);
if (!boot_cpu_data.wp_works_ok) {
printk(KERN_CONT "No.\n");
#ifdef CONFIG_X86_WP_WORKS_OK
panic(
"This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
#endif
} else {
printk(KERN_CONT "Ok.\n");
}
}
static struct kcore_list kcore_mem, kcore_vmalloc;
void __init mem_init(void)
{
int codesize, reservedpages, datasize, initsize;
int tmp;
pci_iommu_alloc();
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();
reservedpages = 0;
for (tmp = 0; tmp < max_low_pfn; tmp++)
/*
* Only count reserved RAM pages:
*/
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;
set_highmem_pages_init();
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
VMALLOC_END-VMALLOC_START);
printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
"%dk reserved, %dk data, %dk init, %ldk highmem)\n",
(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
num_physpages << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >> 10,
initsize >> 10,
(unsigned long) (totalhigh_pages << (PAGE_SHIFT-10))
);
printk(KERN_INFO "virtual kernel memory layout:\n"
" fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#endif
" vmalloc : 0x%08lx - 0x%08lx (%4ld MB)\n"
" lowmem : 0x%08lx - 0x%08lx (%4ld MB)\n"
" .init : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .data : 0x%08lx - 0x%08lx (%4ld kB)\n"
" .text : 0x%08lx - 0x%08lx (%4ld kB)\n",
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif
VMALLOC_START, VMALLOC_END,
(VMALLOC_END - VMALLOC_START) >> 20,
(unsigned long)__va(0), (unsigned long)high_memory,
((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,
(unsigned long)&__init_begin, (unsigned long)&__init_end,
((unsigned long)&__init_end -
(unsigned long)&__init_begin) >> 10,
(unsigned long)&_etext, (unsigned long)&_edata,
((unsigned long)&_edata - (unsigned long)&_etext) >> 10,
(unsigned long)&_text, (unsigned long)&_etext,
((unsigned long)&_etext - (unsigned long)&_text) >> 10);
/*
* Check boundaries twice: Some fundamental inconsistencies can
* be detected at build time already.
*/
#define __FIXADDR_TOP (-PAGE_SIZE)
#ifdef CONFIG_HIGHMEM
BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
BUILD_BUG_ON(VMALLOC_END > PKMAP_BASE);
#endif
#define high_memory (-128UL << 20)
BUILD_BUG_ON(VMALLOC_START >= VMALLOC_END);
#undef high_memory
#undef __FIXADDR_TOP
#ifdef CONFIG_HIGHMEM
BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE > FIXADDR_START);
BUG_ON(VMALLOC_END > PKMAP_BASE);
#endif
BUG_ON(VMALLOC_START >= VMALLOC_END);
BUG_ON((unsigned long)high_memory > VMALLOC_START);
if (boot_cpu_data.wp_works_ok < 0)
test_wp_bit();
x86: fix app crashes after SMP resume After resume on a 2cpu laptop, kernel builds collapse with a sed hang, sh or make segfault (often on 20295564), real-time signal to cc1 etc. Several hurdles to jump, but a manually-assisted bisect led to -rc1's d2bcbad5f3ad38a1c09861bca7e252dde7bb8259 x86: do not zap_low_mappings in __smp_prepare_cpus. Though the low mappings were removed at bootup, they were left behind (with Global flags helping to keep them in TLB) after resume or cpu online, causing the crashes seen. Reinstate zap_low_mappings (with local __flush_tlb_all) for each cpu_up on x86_32. This used to be serialized by smp_commenced_mask: that's now gone, but a low_mappings flag will do. No need for native_smp_cpus_done to repeat the zap: let mem_init zap BSP's low mappings just like on UP. (In passing, fix error code from native_cpu_up: do_boot_cpu returns a variety of diagnostic values, Dprintk what it says but convert to -EIO. And save_pg_dir separately before zap_low_mappings: doesn't matter now, but zapping twice in succession wiped out resume's swsusp_pg_dir.) That worked well on the duo and one quad, but wouldn't boot 3rd or 4th cpu on P4 Xeon, oopsing just after unlock_ipi_call_lock. The TLB flush IPI now being sent reveals a long-standing bug: the booting cpu has its APIC readied in smp_callin at the top of start_secondary, but isn't put into the cpu_online_map until just before that unlock_ipi_call_lock. So native_smp_call_function_mask to online cpus would send_IPI_allbutself, including the cpu just coming up, though it has been excluded from the count to wait for: by the time it handles the IPI, the call data on native_smp_call_function_mask's stack may well have been overwritten. So fall back to send_IPI_mask while cpu_online_map does not match cpu_callout_map: perhaps there's a better APICological fix to be made at the start_secondary end, but I wouldn't know that. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-13 13:26:57 +00:00
save_pg_dir();
zap_low_mappings();
}
#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdata = NODE_DATA(nid);
[PATCH] reduce MAX_NR_ZONES: remove two strange uses of MAX_NR_ZONES I keep seeing zones on various platforms that are never used and wonder why we compile support for them into the kernel. Counters show up for HIGHMEM and DMA32 that are alway zero. This patch allows the removal of ZONE_DMA32 for non x86_64 architectures and it will get rid of ZONE_HIGHMEM for arches not using highmem (like 64 bit architectures). If an arch does not define CONFIG_HIGHMEM then ZONE_HIGHMEM will not be defined. Similarly if an arch does not define CONFIG_ZONE_DMA32 then ZONE_DMA32 will not be defined. No current architecture uses all the 4 zones (DMA,DMA32,NORMAL,HIGH) that we have now. The patchset will reduce the number of zones for all platforms. On many platforms that do not have DMA32 or HIGHMEM this will reduce the number of zones by 50%. F.e. ia64 only uses DMA and NORMAL. Large amounts of memory can be saved for larger systemss that may have a few hundred NUMA nodes. With ZONE_DMA32 and ZONE_HIGHMEM support optional MAX_NR_ZONES will be 2 for many non i386 platforms and even for i386 without CONFIG_HIGHMEM set. Tested on ia64, x86_64 and on i386 with and without highmem. The patchset consists of 11 patches that are following this message. One could go even further than this patchset and also make ZONE_DMA optional because some platforms do not need a separate DMA zone and can do DMA to all of memory. This could reduce MAX_NR_ZONES to 1. Such a patchset will hopefully follow soon. This patch: Fix strange uses of MAX_NR_ZONES Sometimes we use MAX_NR_ZONES - x to refer to a zone. Make that explicit. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 06:31:09 +00:00
struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
unsigned long start_pfn = start >> PAGE_SHIFT;
unsigned long nr_pages = size >> PAGE_SHIFT;
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:14 +00:00
return __add_pages(nid, zone, start_pfn, nr_pages);
}
#endif
/*
* This function cannot be __init, since exceptions don't work in that
* section. Put this after the callers, so that it cannot be inlined.
*/
static noinline int do_test_wp_bit(void)
{
char tmp_reg;
int flag;
__asm__ __volatile__(
" movb %0, %1 \n"
"1: movb %1, %0 \n"
" xorl %2, %2 \n"
"2: \n"
_ASM_EXTABLE(1b,2b)
:"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
"=q" (tmp_reg),
"=r" (flag)
:"2" (1)
:"memory");
return flag;
}
#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
unsigned long size = PFN_ALIGN(_etext) - start;
#ifndef CONFIG_DYNAMIC_FTRACE
/* Dynamic tracing modifies the kernel text section */
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
printk(KERN_INFO "Write protecting the kernel text: %luk\n",
size >> 10);
#ifdef CONFIG_CPA_DEBUG
printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
start, start+size);
set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT);
printk(KERN_INFO "Testing CPA: write protecting again\n");
set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
#endif
#endif /* CONFIG_DYNAMIC_FTRACE */
start += size;
size = (unsigned long)__end_rodata - start;
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
size >> 10);
rodata_test();
#ifdef CONFIG_CPA_DEBUG
printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size);
set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
printk(KERN_INFO "Testing CPA: write protecting again\n");
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
}
#endif
[PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann <kraxel@suse.de> Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 10:59:32 +00:00
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
#ifdef CONFIG_DEBUG_PAGEALLOC
/*
* If debugging page accesses then do not free this memory but
* mark them not present - any buggy init-section access will
* create a kernel page fault:
*/
printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
begin, PAGE_ALIGN(end));
set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
unsigned long addr;
/*
* We just marked the kernel text read only above, now that
* we are going to free part of that, we need to make that
* writeable first.
*/
set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
[PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann <kraxel@suse.de> Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 10:59:32 +00:00
for (addr = begin; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
free_page(addr);
[PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann <kraxel@suse.de> Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 10:59:32 +00:00
totalram_pages++;
}
printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
#endif
[PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann <kraxel@suse.de> Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 10:59:32 +00:00
}
void free_initmem(void)
{
free_init_pages("unused kernel memory",
(unsigned long)(&__init_begin),
(unsigned long)(&__init_end));
[PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann <kraxel@suse.de> Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-23 10:59:32 +00:00
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
free_init_pages("initrd memory", start, end);
}
#endif
int __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
int flags)
{
return reserve_bootmem(phys, len, flags);
}