linux/include/asm-x86/pgalloc_64.h

134 lines
3.3 KiB
C
Raw Normal View History

#ifndef _X86_64_PGALLOC_H
#define _X86_64_PGALLOC_H
#include <asm/pda.h>
#include <linux/threads.h>
#include <linux/mm.h>
#define pmd_populate_kernel(mm, pmd, pte) \
set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte)))
#define pud_populate(mm, pud, pmd) \
set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)))
#define pgd_populate(mm, pgd, pud) \
set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)))
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 12:22:04 +00:00
#define pmd_pgtable(pmd) pmd_page(pmd)
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
{
set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)));
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
{
BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
free_page((unsigned long)pmd);
}
static inline pmd_t *pmd_alloc_one (struct mm_struct *mm, unsigned long addr)
{
return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
}
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
}
static inline void pud_free(struct mm_struct *mm, pud_t *pud)
{
BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
free_page((unsigned long)pud);
}
static inline void pgd_list_add(pgd_t *pgd)
{
struct page *page = virt_to_page(pgd);
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
unsigned long flags;
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
spin_lock_irqsave(&pgd_lock, flags);
list_add(&page->lru, &pgd_list);
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
spin_unlock_irqrestore(&pgd_lock, flags);
}
static inline void pgd_list_del(pgd_t *pgd)
{
struct page *page = virt_to_page(pgd);
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
unsigned long flags;
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
spin_lock_irqsave(&pgd_lock, flags);
list_del(&page->lru);
x86: fix deadlock, make pgd_lock irq-safe lockdep just caught this one: ================================= [ INFO: inconsistent lock state ] 2.6.24 #38 --------------------------------- inconsistent {in-softirq-W} -> {softirq-on-W} usage. swapper/1 [HC0[0]:SC0[0]:HE1:SE1] takes: (pgd_lock){-+..}, at: [<ffffffff8022a9ea>] mm_init+0x1da/0x250 {in-softirq-W} state was registered at: [<ffffffffffffffff>] 0xffffffffffffffff irq event stamp: 394559 hardirqs last enabled at (394559): [<ffffffff80267f0a>] get_page_from_freelist+0x30a/0x4c0 hardirqs last disabled at (394558): [<ffffffff80267d25>] get_page_from_freelist+0x125/0x4c0 softirqs last enabled at (393952): [<ffffffff80232f8e>] __do_softirq+0xce/0xe0 softirqs last disabled at (393945): [<ffffffff8020c57c>] call_softirq+0x1c/0x30 other info that might help us debug this: no locks held by swapper/1. stack backtrace: Pid: 1, comm: swapper Not tainted 2.6.24 #38 Call Trace: [<ffffffff8024e1fb>] print_usage_bug+0x18b/0x190 [<ffffffff8024f55d>] mark_lock+0x53d/0x560 [<ffffffff8024fffa>] __lock_acquire+0x3ca/0xed0 [<ffffffff80250ba8>] lock_acquire+0xa8/0xe0 [<ffffffff8022a9ea>] ? mm_init+0x1da/0x250 [<ffffffff809bcd10>] _spin_lock+0x30/0x70 [<ffffffff8022a9ea>] mm_init+0x1da/0x250 [<ffffffff8022aa99>] mm_alloc+0x39/0x50 [<ffffffff8028b95a>] bprm_mm_init+0x2a/0x1a0 [<ffffffff8028d12b>] do_execve+0x7b/0x220 [<ffffffff80209776>] sys_execve+0x46/0x70 [<ffffffff8020c214>] kernel_execve+0x64/0xd0 [<ffffffff8020901e>] ? _stext+0x1e/0x20 [<ffffffff802090ba>] init_post+0x9a/0xf0 [<ffffffff809bc5f6>] ? trace_hardirqs_on_thunk+0x35/0x3a [<ffffffff8024f75a>] ? trace_hardirqs_on+0xba/0xd0 [<ffffffff8020c1a8>] ? child_rip+0xa/0x12 [<ffffffff8020bcbc>] ? restore_args+0x0/0x44 [<ffffffff8020c19e>] ? child_rip+0x0/0x12 turns out that pgd_lock has been used on 64-bit x86 in an irq-unsafe way for almost two years, since commit 8c914cb704a11460e. Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-02-06 21:39:45 +00:00
spin_unlock_irqrestore(&pgd_lock, flags);
}
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
unsigned boundary;
pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
if (!pgd)
return NULL;
pgd_list_add(pgd);
/*
* Copy kernel pointers in from init.
* Could keep a freelist or slab cache of those because the kernel
* part never changes.
*/
boundary = pgd_index(__PAGE_OFFSET);
memset(pgd, 0, boundary * sizeof(pgd_t));
memcpy(pgd + boundary,
init_level4_pgt + boundary,
(PTRS_PER_PGD - boundary) * sizeof(pgd_t));
return pgd;
}
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
pgd_list_del(pgd);
free_page((unsigned long)pgd);
}
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
return (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
}
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 12:22:04 +00:00
static inline pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
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 12:22:04 +00:00
struct page *page;
void *p;
p = (void *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
if (!p)
return 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 12:22:04 +00:00
page = virt_to_page(p);
pgtable_page_ctor(page);
return page;
}
/* Should really implement gc for free page table pages. This could be
done with a reference count in struct page. */
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
free_page((unsigned long)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 12:22:04 +00:00
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 12:22:04 +00:00
pgtable_page_dtor(pte);
__free_page(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 12:22:04 +00:00
#define __pte_free_tlb(tlb,pte) \
do { \
pgtable_page_dtor((pte)); \
tlb_remove_page((tlb), (pte)); \
} while (0)
#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x))
#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x))
#endif /* _X86_64_PGALLOC_H */