WARNING - OLD ARCHIVES

This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

[Xen-devel] [RFC PATCH 30/35] Add apply_to_page_range() function

To: linux-kernel@xxxxxxxxxxxxxxx
Subject: [Xen-devel] [RFC PATCH 30/35] Add apply_to_page_range() function
From: Chris Wright <chrisw@xxxxxxxxxxxx>
Date: Tue, 09 May 2006 00:00:30 -0700
Cc: virtualization@xxxxxxxxxxxxxx, Christian Limpach <Christian.Limpach@xxxxxxxxxxxx>, xen-devel@xxxxxxxxxxxxxxxxxxx, Ian Pratt <ian.pratt@xxxxxxxxxxxxx>
Delivery-date: Tue, 09 May 2006 01:54:17 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
References: <20060509084945.373541000@xxxxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Add a new mm function apply_to_page_range() which applies a given
function to every pte in a given virtual address range in a given mm
structure. This is a generic alternative to cut-and-pasting the Linux
idiomatic pagetable walking code in every place that a sequence of
PTEs must be accessed.

Although this interface is intended to be useful in a wide range of
situations, it is currently used specifically by several Xen
subsystems, for example: to ensure that pagetables have been allocated
for a virtual address range, and to construct batched special
pagetable update requests to map I/O memory (in ioremap()).

Signed-off-by: Ian Pratt <ian.pratt@xxxxxxxxxxxxx>
Signed-off-by: Christian Limpach <Christian.Limpach@xxxxxxxxxxxx>
Signed-off-by: Chris Wright <chrisw@xxxxxxxxxxxx>
---
 include/linux/mm.h |    5 ++
 mm/memory.c        |   94 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)

--- linus-2.6.orig/include/linux/mm.h
+++ linus-2.6/include/linux/mm.h
@@ -1014,6 +1014,11 @@ struct page *follow_page(struct vm_area_
 #define FOLL_GET       0x04    /* do get_page on page */
 #define FOLL_ANON      0x08    /* give ZERO_PAGE if no pgtable */
 
+typedef int (*pte_fn_t)(pte_t *pte, struct page *pmd_page, unsigned long addr,
+                       void *data);
+extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
+                              unsigned long size, pte_fn_t fn, void *data);
+
 #ifdef CONFIG_PROC_FS
 void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
 #else
--- linus-2.6.orig/mm/memory.c
+++ linus-2.6/mm/memory.c
@@ -1356,6 +1356,100 @@ int remap_pfn_range(struct vm_area_struc
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+static inline int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
+                                    unsigned long addr, unsigned long end,
+                                    pte_fn_t fn, void *data)
+{
+       pte_t *pte;
+       int err;
+       struct page *pmd_page;
+       spinlock_t *ptl;
+
+       pte = (mm == &init_mm) ?
+               pte_alloc_kernel(pmd, addr) :
+               pte_alloc_map_lock(mm, pmd, addr, &ptl);
+       if (!pte)
+               return -ENOMEM;
+
+       BUG_ON(pmd_huge(*pmd));
+
+       pmd_page = pmd_page(*pmd);
+
+       do {
+               err = fn(pte, pmd_page, addr, data);
+               if (err)
+                       break;
+       } while (pte++, addr += PAGE_SIZE, addr != end);
+
+       if (mm != &init_mm)
+               pte_unmap_unlock(pte-1, ptl);
+       return err;
+}
+
+static inline int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
+                                    unsigned long addr, unsigned long end,
+                                    pte_fn_t fn, void *data)
+{
+       pmd_t *pmd;
+       unsigned long next;
+       int err;
+
+       pmd = pmd_alloc(mm, pud, addr);
+       if (!pmd)
+               return -ENOMEM;
+       do {
+               next = pmd_addr_end(addr, end);
+               err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
+               if (err)
+                       break;
+       } while (pmd++, addr = next, addr != end);
+       return err;
+}
+
+static inline int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+                                    unsigned long addr, unsigned long end,
+                                    pte_fn_t fn, void *data)
+{
+       pud_t *pud;
+       unsigned long next;
+       int err;
+
+       pud = pud_alloc(mm, pgd, addr);
+       if (!pud)
+               return -ENOMEM;
+       do {
+               next = pud_addr_end(addr, end);
+               err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
+               if (err)
+                       break;
+       } while (pud++, addr = next, addr != end);
+       return err;
+}
+
+/*
+ * Scan a region of virtual memory, filling in page tables as necessary
+ * and calling a provided function on each leaf page table.
+ */
+int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+                       unsigned long size, pte_fn_t fn, void *data)
+{
+       pgd_t *pgd;
+       unsigned long next;
+       unsigned long end = addr + size;
+       int err;
+
+       BUG_ON(addr >= end);
+       pgd = pgd_offset(mm, addr);
+       do {
+               next = pgd_addr_end(addr, end);
+               err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+               if (err)
+                       break;
+       } while (pgd++, addr = next, addr != end);
+       return err;
+}
+EXPORT_SYMBOL_GPL(apply_to_page_range);
+
 /*
  * handle_pte_fault chooses page fault handler according to an entry
  * which was read non-atomically.  Before making any commitment, on

--

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

<Prev in Thread] Current Thread [Next in Thread>