linux/arch/ia64/include/asm/pgalloc.h

123 lines
2.7 KiB
C
Raw Normal View History

#ifndef _ASM_IA64_PGALLOC_H
#define _ASM_IA64_PGALLOC_H
/*
* This file contains the functions and defines necessary to allocate
* page tables.
*
* This hopefully works with any (fixed) ia-64 page-size, as defined
* in <asm/page.h> (currently 8192).
*
* Copyright (C) 1998-2001 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
* Copyright (C) 2000, Goutham Rao <goutham.rao@intel.com>
*/
#include <linux/compiler.h>
#include <linux/mm.h>
#include <linux/page-flags.h>
#include <linux/threads.h>
#include <linux/quicklist.h>
#include <asm/mmu_context.h>
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return quicklist_alloc(0, GFP_KERNEL, NULL);
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
quicklist_free(0, NULL, pgd);
}
#ifdef CONFIG_PGTABLE_4
static inline void
pgd_populate(struct mm_struct *mm, pgd_t * pgd_entry, pud_t * pud)
{
pgd_val(*pgd_entry) = __pa(pud);
}
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return quicklist_alloc(0, GFP_KERNEL, NULL);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
quicklist_free(0, NULL, pud);
}
#define __pud_free_tlb(tlb, pud) pud_free((tlb)->mm, pud)
#endif /* CONFIG_PGTABLE_4 */
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
static inline void
pud_populate(struct mm_struct *mm, pud_t * pud_entry, pmd_t * pmd)
{
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
pud_val(*pud_entry) = __pa(pmd);
}
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return quicklist_alloc(0, GFP_KERNEL, NULL);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
quicklist_free(0, NULL, pmd);
}
#define __pmd_free_tlb(tlb, pmd) pmd_free((tlb)->mm, pmd)
static inline void
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
pmd_populate(struct mm_struct *mm, pmd_t * pmd_entry, pgtable_t pte)
{
pmd_val(*pmd_entry) = page_to_phys(pte);
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
#define pmd_pgtable(pmd) pmd_page(pmd)
static inline void
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
pmd_populate_kernel(struct mm_struct *mm, pmd_t * pmd_entry, pte_t * pte)
{
pmd_val(*pmd_entry) = __pa(pte);
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr)
{
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
struct page *page;
void *pg;
pg = quicklist_alloc(0, GFP_KERNEL, NULL);
if (!pg)
return NULL;
page = virt_to_page(pg);
pgtable_page_ctor(page);
return page;
}
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
unsigned long addr)
{
return quicklist_alloc(0, GFP_KERNEL, NULL);
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
{
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
pgtable_page_dtor(pte);
quicklist_free_page(0, NULL, pte);
}
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
quicklist_free(0, NULL, pte);
}
static inline void check_pgt_cache(void)
{
quicklist_trim(0, NULL, 25, 16);
}
#define __pte_free_tlb(tlb, pte) pte_free((tlb)->mm, pte)
[IA64] Percpu quicklist for combined allocator for pgd/pmd/pte. This patch introduces using the quicklists for pgd, pmd, and pte levels by combining the alloc and free functions into a common set of routines. This greatly simplifies the reading of this header file. This patch is simple but necessary for large numa configurations. It simply ensures that only pages from the local node are added to a cpus quicklist. This prevents the trapping of pages on a remote nodes quicklist by starting a process, touching a large number of pages to fill pmd and pte entries, migrating to another node, and then unmapping or exiting. With those conditions, the pages get trapped and if the machine has more than 100 nodes of the same size, the calculation of the pgtable high water mark will be larger than any single node so page table cache flushing will never occur. I ran lmbench lat_proc fork and lat_proc exec on a zx1 with and without this patch and did not notice any change. On an sn2 machine, there was a slight improvement which is possibly due to pages from other nodes trapped on the test node before starting the run. I did not investigate further. This patch shrinks the quicklist based upon free memory on the node instead of the high/low water marks. I have written it to enable preemption periodically and recalculate the amount to shrink every time we have freed enough pages that the quicklist size should have grown. I rescan the nodes zones each pass because other processess may be draining node memory at the same time as we are adding. Signed-off-by: Robin Holt <holt@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
2005-04-26 04:13:16 +08:00
#endif /* _ASM_IA64_PGALLOC_H */