uml-2.6.10-fc3.patch

非常经典的一个分布式系统

Index: linux-2.6.10/lib/Kconfig.debug
===================================================================
--- linux-2.6.10.orig/lib/Kconfig.debug	2004-12-25 05:35:24.000000000 +0800
+++ linux-2.6.10/lib/Kconfig.debug	2005-04-07 22:05:29.475761192 +0800
@@ -23,7 +23,6 @@
 config MAGIC_SYSRQ
 	bool "Magic SysRq key"
 	depends on DEBUG_KERNEL && (H8300 || M68KNOMMU || V850)
-	depends (USERMODE && MCONSOLE)
 	help
 	  Enables console device to interpret special characters as
 	  commands to dump state information.
Index: linux-2.6.10/mm/mprotect.c
===================================================================
--- linux-2.6.10.orig/mm/mprotect.c	2004-12-25 05:35:50.000000000 +0800
+++ linux-2.6.10/mm/mprotect.c	2005-04-07 22:05:29.475761192 +0800
@@ -93,19 +93,20 @@
 {
 	pgd_t *dir;
 	unsigned long beg = start;
+	struct mm_struct * mm = vma->vm_mm;
 
-	dir = pgd_offset(current->mm, start);
+	dir = pgd_offset(mm, start);
 	flush_cache_range(vma, beg, end);
 	if (start >= end)
 		BUG();
-	spin_lock(&current->mm->page_table_lock);
+	spin_lock(&mm->page_table_lock);
 	do {
 		change_pmd_range(dir, start, end - start, newprot);
 		start = (start + PGDIR_SIZE) & PGDIR_MASK;
 		dir++;
 	} while (start && (start < end));
 	flush_tlb_range(vma, beg, end);
-	spin_unlock(&current->mm->page_table_lock);
+	spin_unlock(&mm->page_table_lock);
 	return;
 }
 
@@ -190,8 +191,9 @@
 	return error;
 }
 
-asmlinkage long
-sys_mprotect(unsigned long start, size_t len, unsigned long prot)
+long
+do_mprotect(struct mm_struct *mm, unsigned long start, size_t len,
+	     unsigned long prot)
 {
 	unsigned long vm_flags, nstart, end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -220,9 +222,9 @@
 
 	vm_flags = calc_vm_prot_bits(prot);
 
-	down_write(&current->mm->mmap_sem);
+	down_write(&mm->mmap_sem);
 
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma_prev(mm, start, &prev);
 	error = -ENOMEM;
 	if (!vma)
 		goto out;
@@ -288,6 +290,11 @@
 		}
 	}
 out:
-	up_write(&current->mm->mmap_sem);
+	up_write(&mm->mmap_sem);
 	return error;
 }
+
+asmlinkage long sys_mprotect(unsigned long start, size_t len, unsigned long prot)
+{
+        return(do_mprotect(current->mm, start, len, prot));
+}
Index: linux-2.6.10/mm/mmap.c
===================================================================
--- linux-2.6.10.orig/mm/mmap.c	2005-04-06 23:38:33.000000000 +0800
+++ linux-2.6.10/mm/mmap.c	2005-04-07 22:05:29.476761040 +0800
@@ -759,11 +759,11 @@
  * The caller must hold down_write(current->mm->mmap_sem).
  */
 
-unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
-			unsigned long len, unsigned long prot,
-			unsigned long flags, unsigned long pgoff)
+unsigned long __do_mmap_pgoff(struct mm_struct *mm, struct file * file,
+			    unsigned long addr, unsigned long len,
+			    unsigned long prot, unsigned long flags,
+			    unsigned long pgoff)
 {
-	struct mm_struct * mm = current->mm;
 	struct vm_area_struct * vma, * prev;
 	struct inode *inode;
 	unsigned int vm_flags;
@@ -1037,7 +1037,7 @@
 	return error;
 }
 
-EXPORT_SYMBOL(do_mmap_pgoff);
+EXPORT_SYMBOL(__do_mmap_pgoff);
 
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
Index: linux-2.6.10/mm/proc_mm.c
===================================================================
--- linux-2.6.10.orig/mm/proc_mm.c	2005-04-07 19:34:21.197950744 +0800
+++ linux-2.6.10/mm/proc_mm.c	2005-04-07 22:05:29.476761040 +0800
@@ -0,0 +1,181 @@
+/*
+ * Copyright (C) 2002 Jeff Dike ([e-mail])
+ * Licensed under the GPL
+ */
+
+#include "linux/mm.h"
+#include "linux/init.h"
+#include "linux/proc_fs.h"
+#include "linux/proc_mm.h"
+#include "linux/file.h"
+#include "linux/mman.h"
+#include "asm/uaccess.h"
+#include "asm/mmu_context.h"
+
+static struct file_operations proc_mm_fops;
+
+struct mm_struct *proc_mm_get_mm(int fd)
+{
+	struct mm_struct *ret = ERR_PTR(-EBADF);
+	struct file *file;
+
+	file = fget(fd);
+	if (!file)
+		goto out;
+
+	ret = ERR_PTR(-EINVAL);
+	if(file->f_op != &proc_mm_fops)
+		goto out_fput;
+
+	ret = file->private_data;
+ out_fput:
+	fput(file);
+ out:
+	return(ret);
+}
+
+extern long do_mmap2(struct mm_struct *mm, unsigned long addr,
+		     unsigned long len, unsigned long prot,
+		     unsigned long flags, unsigned long fd,
+		     unsigned long pgoff);
+
+static ssize_t write_proc_mm(struct file *file, const char *buffer,
+			     size_t count, loff_t *ppos)
+{
+	struct mm_struct *mm = file->private_data;
+	struct proc_mm_op req;
+	int n, ret;
+
+	if(count > sizeof(req))
+		return(-EINVAL);
+
+	n = copy_from_user(&req, buffer, count);
+	if(n != 0)
+		return(-EFAULT);
+
+	ret = count;
+	switch(req.op){
+	case MM_MMAP: {
+		struct mm_mmap *map = &req.u.mmap;
+
+		/* Nobody ever noticed it, but do_mmap_pgoff() calls
+		 * get_unmapped_area() which checks current->mm, if
+		 * MAP_FIXED is not set, so mmap() could replace
+		 * an old mapping.
+		 */
+		if (! (map->flags & MAP_FIXED))
+			return(-EINVAL);
+
+		ret = do_mmap2(mm, map->addr, map->len, map->prot,
+			       map->flags, map->fd, map->offset >> PAGE_SHIFT);
+		if((ret & ~PAGE_MASK) == 0)
+			ret = count;
+
+		break;
+	}
+	case MM_MUNMAP: {
+		struct mm_munmap *unmap = &req.u.munmap;
+
+		down_write(&mm->mmap_sem);
+		ret = do_munmap(mm, unmap->addr, unmap->len);
+		up_write(&mm->mmap_sem);
+
+		if(ret == 0)
+			ret = count;
+		break;
+	}
+	case MM_MPROTECT: {
+		struct mm_mprotect *protect = &req.u.mprotect;
+
+		ret = do_mprotect(mm, protect->addr, protect->len,
+				  protect->prot);
+		if(ret == 0)
+			ret = count;
+		break;
+	}
+
+	case MM_COPY_SEGMENTS: {
+		struct mm_struct *from = proc_mm_get_mm(req.u.copy_segments);
+
+		if(IS_ERR(from)){
+			ret = PTR_ERR(from);
+			break;
+		}
+
+		ret = copy_context(mm, from);
+		if(ret == 0)
+			ret = count;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return(ret);
+}
+
+static int open_proc_mm(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = mm_alloc();
+	int ret;
+
+	ret = -ENOMEM;
+	if(mm == NULL)
+		goto out_mem;
+
+	init_new_empty_context(mm);
+	arch_pick_mmap_layout(mm);
+
+	spin_lock(&mmlist_lock);
+	list_add(&mm->mmlist, &current->mm->mmlist);
+	spin_unlock(&mmlist_lock);
+
+	file->private_data = mm;
+
+	return(0);
+
+ out_mem:
+	return(ret);
+}
+
+static int release_proc_mm(struct inode *inode, struct file *file)
+{
+	struct mm_struct *mm = file->private_data;
+
+	mmput(mm);
+	return(0);
+}
+
+static struct file_operations proc_mm_fops = {
+	.open		= open_proc_mm,
+	.release	= release_proc_mm,
+	.write		= write_proc_mm,
+};
+
+static int make_proc_mm(void)
+{
+	struct proc_dir_entry *ent;
+
+	ent = create_proc_entry("mm", 0222, &proc_root);
+	if(ent == NULL){
+		printk("make_proc_mm : Failed to register /proc/mm\n");
+		return(0);
+	}
+	ent->proc_fops = &proc_mm_fops;
+
+	return(0);
+}
+
+__initcall(make_proc_mm);
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
Index: linux-2.6.10/mm/Makefile
===================================================================
--- linux-2.6.10.orig/mm/Makefile	2004-12-25 05:35:00.000000000 +0800
+++ linux-2.6.10/mm/Makefile	2005-04-07 22:05:29.477760888 +0800
@@ -18,3 +18,4 @@
 obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 
+obj-$(CONFIG_PROC_MM)	+= proc_mm.o
Index: linux-2.6.10/arch/um/drivers/mconsole_kern.c
===================================================================
--- linux-2.6.10.orig/arch/um/drivers/mconsole_kern.c	2004-12-25 05:33:49.000000000 +0800
+++ linux-2.6.10/arch/um/drivers/mconsole_kern.c	2005-04-07 22:05:29.477760888 +0800
@@ -204,6 +204,68 @@
 }
 #endif
 
+/* This is a more convoluted version of mconsole_proc, which has some stability
+ * problems; however, we need it fixed, because it is expected that UML users
+ * mount HPPFS instead of procfs on /proc. And we want mconsole_proc to still
+ * show the real procfs content, not the ones from hppfs.*/
+#if 0
+void mconsole_proc(struct mc_request *req)
+{
+	char path[64];
+	char *buf;
+	int len;
+	int fd;
+	int first_chunk = 1;
+	char *ptr = req->request.data;
+
+	ptr += strlen("proc");
+	while(isspace(*ptr)) ptr++;
+	snprintf(path, sizeof(path), "/proc/%s", ptr);
+
+	fd = sys_open(path, 0, 0);
+	if (fd < 0) {
+		mconsole_reply(req, "Failed to open file", 1, 0);
+		printk("open %s: %d\n",path,fd);
+		goto out;
+	}
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if(buf == NULL){
+		mconsole_reply(req, "Failed to allocate buffer", 1, 0);
+		goto out_close;
+	}
+
+	for (;;) {
+		len = sys_read(fd, buf, PAGE_SIZE-1);
+		if (len < 0) {
+			mconsole_reply(req, "Read of file failed", 1, 0);
+			goto out_free;
+		}
+		/*Begin the file content on his own line.*/
+		if (first_chunk) {
+			mconsole_reply(req, "\n", 0, 1);
+			first_chunk = 0;
+		}
+		if (len == PAGE_SIZE-1) {
+			buf[len] = '\0';
+			mconsole_reply(req, buf, 0, 1);
+		} else {
+			buf[len] = '\0';
+			mconsole_reply(req, buf, 0, 0);
+			break;
+		}
+	}
+	/*END*/
+
+ out_free:
+	kfree(buf);
+ out_close:
+	sys_close(fd);
+ out:
+	/* nothing */;
+}
+#endif
+
 void mconsole_proc(struct mc_request *req)
 {
 	char path[64];
Index: linux-2.6.10/arch/um/drivers/net_kern.c
===================================================================
--- linux-2.6.10.orig/arch/um/drivers/net_kern.c	2004-12-25 05:34:44.000000000 +0800
+++ linux-2.6.10/arch/um/drivers/net_kern.c	2005-04-07 22:05:29.478760736 +0800
@@ -126,10 +126,6 @@
 	lp->tl.data = (unsigned long) &lp->user;
 	netif_start_queue(dev);
 
-	spin_lock(&opened_lock);
-	list_add(&lp->list, &opened);
-	spin_unlock(&opened_lock);
-
 	/* clear buffer - it can happen that the host side of the interface
 	 * is full when we get here.  In this case, new data is never queued,
 	 * SIGIOs never arrive, and the net never works.
@@ -152,9 +148,6 @@
 	free_irq(dev->irq, dev);
 	if(lp->close != NULL) (*lp->close)(lp->fd, &lp->user);
 	lp->fd = -1;
-	spin_lock(&opened_lock);
-	list_del(&lp->list);
-	spin_unlock(&opened_lock);
 
 	spin_unlock(&lp->lock);
 	return 0;
@@ -397,6 +390,11 @@
 
 	if (device->have_mac)
 		set_ether_mac(dev, device->mac);
+
+	spin_lock(&opened_lock);
+	list_add(&lp->list, &opened);
+	spin_unlock(&opened_lock);
+
 	return(0);
 }
 
@@ -705,7 +703,7 @@
 static void close_devices(void)
 {
 	struct list_head *ele;
-	struct uml_net_private *lp;	
+	struct uml_net_private *lp;
 
 	list_for_each(ele, &opened){
 		lp = list_entry(ele, struct uml_net_private, list);
Index: linux-2.6.10/arch/um/drivers/net_user.c
===================================================================
--- linux-2.6.10.orig/arch/um/drivers/net_user.c	2004-12-25 05:34:26.000000000 +0800
+++ linux-2.6.10/arch/um/drivers/net_user.c	2005-04-07 22:05:29.478760736 +0800
@@ -173,10 +173,12 @@