qsnet-suse-2.6.patch

非常经典的一个分布式系统

+	ioproc_update_page
+
+
+==== FUNCTION
+	do_swap_page
+
+CALLED FROM
+	handle_pte_fault
+
+PTE MODIFICATION
+	set_pte
+
+ADDED HOOKS
+	ioproc_update_page
+
+
+==== FUNCTION
+	do_anonymous_page
+
+CALLED FROM
+	do_no_page
+
+PTE MODIFICATION
+	set_pte
+
+ADDED HOOKS
+	ioproc_update_page
+
+
+==== FUNCTION
+	do_no_page
+
+CALLED FROM
+	do_file_page, handle_pte_fault
+
+PTE MODIFICATION
+	set_pte
+
+ADDED HOOKS
+	ioproc_update_page
+
+
+++++ FILE
+	mm/mmap.c
+
+==== FUNCTION
+	unmap_region
+
+CALLED FROM
+	do_munmap
+
+PTE MODIFICATION
+	set_pte (unmap_vmas)
+
+ADDED HOOKS
+	ioproc_invalidate_range
+
+
+==== FUNCTION
+	exit_mmap
+
+CALLED FROM
+	mmput
+
+PTE MODIFICATION
+	set_pte (unmap_vmas)
+
+ADDED HOOKS
+	ioproc_release
+
+
+++++ FILE
+	mm/mprotect.c
+
+==== FUNCTION
+	change_protection
+
+CALLED FROM
+	mprotect_fixup
+
+PTE MODIFICATION
+	set_pte (change_pte_range)
+
+ADDED HOOKS
+	ioproc_change_protection
+
+
+++++ FILE
+	mm/mremap.c
+
+==== FUNCTION
+	move_page_tables
+
+CALLED FROM
+	move_vma
+
+PTE MODIFICATION
+	ptep_clear_flush (move_one_page)
+
+ADDED HOOKS
+	ioproc_invalidate_range
+	ioproc_invalidate_range
+
+
+++++ FILE
+	mm/rmap.c
+
+==== FUNCTION
+	try_to_unmap_one
+
+CALLED FROM
+	try_to_unmap_anon, try_to_unmap_file
+
+PTE MODIFICATION
+	ptep_clear_flush
+
+ADDED HOOKS
+	ioproc_invalidate_page
+
+
+==== FUNCTION
+	try_to_unmap_cluster
+
+CALLED FROM
+	try_to_unmap_file
+
+PTE MODIFICATION
+	ptep_clear_flush
+
+ADDED HOOKS
+	ioproc_invalidate_page
+
+
+
+++++ FILE 
+	mm/msync.c
+
+==== FUNCTION
+	filemap_sync
+
+CALLED FROM
+	msync_interval
+
+PTE MODIFICATION
+	ptep_clear_flush_dirty (filemap_sync_pte)
+
+ADDED HOOKS
+	ioproc_sync_range
+
+
+++++ FILE
+	mm/hugetlb.c
+
+==== FUNCTION
+	zap_hugepage_range
+
+CALLED FROM
+	hugetlb_vmtruncate_list
+
+PTE MODIFICATION
+	ptep_get_and_clear (unmap_hugepage_range)
+
+ADDED HOOK
+	ioproc_invalidate_range
+
+
+-- Last update DavidAddison - 17 Aug 2004
Index: LINUX-SRC-TREE/fs/exec.c
===================================================================
--- LINUX-SRC-TREE.orig/fs/exec.c
+++ LINUX-SRC-TREE/fs/exec.c
@@ -65,6 +65,8 @@ EXPORT_SYMBOL(coredump_notifier_list);
 #include <linux/kmod.h>
 #endif
 
+#include <linux/ptrack.h>
+
 int core_uses_pid;
 char core_pattern[65] = "core";
 int suid_dumpable = 0;
@@ -1213,6 +1215,9 @@ int do_execve(char * filename,
 	if (retval < 0)
 		goto out;
 
+	/* notify any ptrack callbacks of the process exec */
+	ptrack_call_callbacks(PTRACK_PHASE_EXEC, NULL);
+
 	retval = search_binary_handler(&bprm,regs);
 	if (retval >= 0) {
 		TRIG_EVENT(exec_hook, file->f_dentry->d_name.len,
Index: LINUX-SRC-TREE/fs/read_write.c
===================================================================
--- LINUX-SRC-TREE.orig/fs/read_write.c
+++ LINUX-SRC-TREE/fs/read_write.c
@@ -339,6 +339,7 @@ asmlinkage ssize_t sys_write(unsigned in
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(sys_write);
 
 asmlinkage ssize_t sys_pread64(unsigned int fd, char __user *buf,
 			     size_t count, loff_t pos)
Index: LINUX-SRC-TREE/fs/select.c
===================================================================
--- LINUX-SRC-TREE.orig/fs/select.c
+++ LINUX-SRC-TREE/fs/select.c
@@ -649,3 +649,4 @@ ssize_t generic_aio_poll(struct kiocb *i
 	}
 	return -EIOCBRETRY;
 }
+EXPORT_SYMBOL_GPL(sys_poll);
Index: LINUX-SRC-TREE/include/linux/init_task.h
===================================================================
--- LINUX-SRC-TREE.orig/include/linux/init_task.h
+++ LINUX-SRC-TREE/include/linux/init_task.h
@@ -3,6 +3,7 @@
 
 #include <linux/file.h>
 #include <linux/pagg.h>
+#include <linux/ptrack.h>
 
 #define INIT_FILES \
 { 							\
@@ -116,6 +117,7 @@ extern struct group_info init_groups;
 	.map_base	= __TASK_UNMAPPED_BASE,				\
 	.io_wait	= NULL,						\
 	INIT_TASK_PAGG(tsk)						\
+	INIT_TASK_PTRACK(tsk)						\
 }
 
 
Index: LINUX-SRC-TREE/include/linux/ioproc.h
===================================================================
--- /dev/null
+++ LINUX-SRC-TREE/include/linux/ioproc.h
@@ -0,0 +1,271 @@
+/* -*- linux-c -*-
+ *
+ *    Copyright (C) 2002-2004 Quadrics Ltd.
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ *
+ */
+
+/*
+ * Callbacks for IO processor page table updates.
+ */
+
+#ifndef __LINUX_IOPROC_H__
+#define __LINUX_IOPROC_H__
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+
+typedef struct ioproc_ops {
+	struct ioproc_ops *next;
+	void *arg;
+
+	void (*release)(void *arg, struct mm_struct *mm);
+	void (*sync_range)(void *arg, struct vm_area_struct *vma, unsigned long start, unsigned long end);
+	void (*invalidate_range)(void *arg, struct vm_area_struct *vma, unsigned long start, unsigned long end);
+	void (*update_range)(void *arg, struct vm_area_struct *vma, unsigned long start, unsigned long end);
+
+	void (*change_protection)(void *arg, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot);
+
+	void (*sync_page)(void *arg, struct vm_area_struct *vma, unsigned long address);
+	void (*invalidate_page)(void *arg, struct vm_area_struct *vma, unsigned long address);
+	void (*update_page)(void *arg, struct vm_area_struct *vma, unsigned long address);
+
+} ioproc_ops_t;
+
+/* IOPROC Registration
+ * 
+ * Called by the IOPROC device driver to register its interest in page table
+ * changes for the process associated with the supplied mm_struct
+ *
+ * The caller should first allocate and fill out an ioproc_ops structure with 
+ * the function pointers initialised to the device driver specific code for
+ * each callback. If the device driver doesn't have code for a particular 
+ * callback then it should set the function pointer to be NULL.
+ * The ioproc_ops arg parameter will be passed unchanged as the first argument
+ * to each callback function invocation.
+ *
+ * The ioproc registration is not inherited across fork() and should be called
+ * once for each process that the IOPROC device driver is interested in.
+ *
+ * Must be called holding the mm->page_table_lock
+ */
+extern int ioproc_register_ops(struct mm_struct *mm, struct ioproc_ops *ip);
+
+
+/* IOPROC De-registration
+ * 
+ * Called by the IOPROC device driver when it is no longer interested in page 
+ * table changes for the process associated with the supplied mm_struct
+ *
+ * Normally this is not needed to be called as the ioproc_release() code will
+ * automatically unlink the ioproc_ops struct from the mm_struct as the
+ * process exits
+ *
+ * Must be called holding the mm->page_table_lock
+ */
+extern int ioproc_unregister_ops(struct mm_struct *mm, struct ioproc_ops *ip);
+
+#ifdef CONFIG_IOPROC
+
+/* IOPROC Release
+ *
+ * Called during exit_mmap() as all vmas are torn down and unmapped.
+ *
+ * Also unlinks the ioproc_ops structure from the mm list as it goes.
+ *
+ * No need for locks as the mm can no longer be accessed at this point
+ *
+ */
+static inline void 
+ioproc_release(struct mm_struct *mm)
+{
+	struct ioproc_ops *cp;
+
+	while ((cp = mm->ioproc_ops) != NULL) {
+		mm->ioproc_ops = cp->next;
+        
+		if (cp->release)
+			cp->release(cp->arg, mm);
+	}
+}
+
+/* IOPROC SYNC RANGE
+ *
+ * Called when a memory map is synchronised with its disk image i.e. when the 
+ * msync() syscall is invoked. Any future read or write to the associated 
+ * pages by the IOPROC should cause the page to be marked as referenced or 
+ * modified.
+ *
+ * Called holding the mm->page_table_lock
+ */
+static inline void 
+ioproc_sync_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	struct ioproc_ops *cp;
+
+	for (cp = vma->vm_mm->ioproc_ops; cp; cp = cp->next)
+		if (cp->sync_range)
+			cp->sync_range(cp->arg, vma, start, end);
+}
+
+/* IOPROC INVALIDATE RANGE
+ *
+ * Called whenever a valid PTE is unloaded e.g. when a page is unmapped by the
+ * user or paged out by the kernel. 
+ *
+ * After this call the IOPROC must not access the physical memory again unless
+ * a new translation is loaded.
+ *
+ * Called holding the mm->page_table_lock
+ */
+static inline void 
+ioproc_invalidate_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	struct ioproc_ops *cp;
+	
+	for (cp = vma->vm_mm->ioproc_ops; cp; cp = cp->next)
+		if (cp->invalidate_range)
+			cp->invalidate_range(cp->arg, vma, start, end);
+}
+
+/* IOPROC UPDATE RANGE
+ *
+ * Called whenever a valid PTE is loaded e.g. mmaping memory, moving the brk 
+ * up, when breaking COW or faulting in an anonymous page of memory.
+ *
+ * These give the IOPROC device driver the opportunity to load translations 
+ * speculatively, which can improve performance by avoiding device translation
+ * faults.
+ *
+ * Called holding the mm->page_table_lock
+ */
+static inline void 
+ioproc_update_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	struct ioproc_ops *cp;
+
+	for (cp = vma->vm_mm->ioproc_ops; cp; cp = cp->next)
+		if (cp->update_range)
+			cp->update_range(cp->arg, vma, start, end);
+}
+
+
+/* IOPROC CHANGE PROTECTION
+ *
+ * Called when the protection on a region of memory is changed i.e. when the 
+ * mprotect() syscall is invoked.
+ *
+ * The IOPROC must not be able to write to a read-only page, so if the 
+ * permissions are downgraded then it must honour them. If they are upgraded 
+ * it can treat this in the same way as the ioproc_update_[range|sync]() calls
+ *
+ * Called holding the mm->page_table_lock
+ */
+static inline void 
+ioproc_change_protection(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot)
+{
+	struct ioproc_ops *cp;
+
+	for (cp = vma->vm_mm->ioproc_ops; cp; cp = cp->next)
+		if (cp->change_protection)
+			cp->change_protection(cp->arg, vma, start, end, newprot);
+}
+