[linuxsh-dev] 2.5.5

[NIIBE Y. <gn...@m1...>]

Sync up to 2.5.5 (getting changes from patch-2.5.5.bz2).
I add the change for your reference.  Please note that it's note
me who does this change, I just incorporate the change into the repository.

2002-03-20  NIIBE Yutaka  <gn...@m1...>

	Update to 2.5.5.
	* AGAINST-2.5.5: New file.
	* AGAINST-2.5.4: Removed.
	* Documentation/cachetlb.txt: Include the change.
	* Makefile: Version 2.5.4.  Merged.
	* arch/sh/config.in, drivers/Makefile: Sound driver move.
	* arch/sh/kernel/signal.c: recalc_sigpending API change.
	* drivers/net/8139too.c, drivers/net/Config.in: Update.
	* drivers/pci/pci.ids: Update.
	* include/asm-sh/pgtable.h: New API flush_icache_user_range, 
	Removed page_address API here (move to linux/mm.h).
	* include/net/inet_ecn.h: Update. 
	* kernel/ptrace.c: Use new API flush_icache_user_range. 
	* mm/memory.c: Update.

Index: Makefile
===================================================================
RCS file: /cvsroot/linuxsh/linux/Makefile,v
retrieving revision 1.9
diff -u -3 -p -r1.9 Makefile
--- Makefile	1 Mar 2002 05:08:25 -0000	1.9
+++ Makefile	20 Mar 2002 01:46:38 -0000
@@ -1,6 +1,6 @@
 VERSION = 2
 PATCHLEVEL = 5
-SUBLEVEL = 4
+SUBLEVEL = 5
 EXTRAVERSION = -sh
 
 KERNELRELEASE=$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(EXTRAVERSION)
@@ -122,7 +122,7 @@ CORE_FILES	=kernel/kernel.o mm/mm.o fs/f
 NETWORKS	=net/network.o
 
 LIBS		=$(TOPDIR)/lib/lib.a
-SUBDIRS		=kernel drivers mm fs net ipc lib
+SUBDIRS		=kernel lib drivers mm fs net ipc sound
 
 DRIVERS-n :=
 DRIVERS-y :=
@@ -156,7 +156,7 @@ ifneq ($(CONFIG_CD_NO_IDESCSI)$(CONFIG_B
 DRIVERS-y += drivers/cdrom/driver.o
 endif
 
-DRIVERS-$(CONFIG_SOUND) += drivers/sound/sounddrivers.o
+DRIVERS-$(CONFIG_SOUND) += sound/sound.o
 DRIVERS-$(CONFIG_PCI) += drivers/pci/driver.o
 DRIVERS-$(CONFIG_MTD) += drivers/mtd/mtdlink.o
 DRIVERS-$(CONFIG_PCMCIA) += drivers/pcmcia/pcmcia.o
@@ -202,7 +202,7 @@ CLEAN_FILES = \
 	drivers/char/drm/*-mod.c \
 	drivers/pci/devlist.h drivers/pci/classlist.h drivers/pci/gen-devlist \
 	drivers/zorro/devlist.h drivers/zorro/gen-devlist \
-	drivers/sound/bin2hex drivers/sound/hex2hex \
+	sound/oss/bin2hex sound/oss/hex2hex \
 	drivers/atm/fore200e_mkfirm drivers/atm/{pca,sba}*{.bin,.bin1,.bin2} \
 	drivers/scsi/aic7xxx/aicasm/aicasm_gram.c \
 	drivers/scsi/aic7xxx/aicasm/aicasm_scan.c \
@@ -223,11 +223,11 @@ MRPROPER_FILES = \
 	drivers/net/hamradio/soundmodem/sm_tbl_{hapn4800,psk4800}.h \
 	drivers/net/hamradio/soundmodem/sm_tbl_{afsk2400_7,afsk2400_8}.h \
 	drivers/net/hamradio/soundmodem/gentbl \
-	drivers/sound/*_boot.h drivers/sound/.*.boot \
-	drivers/sound/msndinit.c \
-	drivers/sound/msndperm.c \
-	drivers/sound/pndsperm.c \
-	drivers/sound/pndspini.c \
+	sound/oss/*_boot.h sound/oss/.*.boot \
+	sound/oss/msndinit.c \
+	sound/oss/msndperm.c \
+	sound/oss/pndsperm.c \
+	sound/oss/pndspini.c \
 	drivers/atm/fore200e_*_fw.c drivers/atm/.fore200e_*.fw \
 	.version .config* config.in config.old \
 	scripts/tkparse scripts/kconfig.tk scripts/kconfig.tmp \
@@ -344,7 +344,7 @@ init/main.o: init/main.c include/config/
 init/do_mounts.o: init/do_mounts.c include/config/MARKER
 	$(CC) $(CFLAGS) $(CFLAGS_KERNEL) $(PROFILING) -c -o $*.o $<
 
-fs lib mm ipc kernel drivers net: dummy
+fs lib mm ipc kernel drivers net sound: dummy
 	$(MAKE) CFLAGS="$(CFLAGS) $(CFLAGS_KERNEL)" $(subst $@, _dir_$@, $@)
 
 TAGS: dummy
Index: Documentation/cachetlb.txt
===================================================================
RCS file: /cvsroot/linuxsh/linux/Documentation/cachetlb.txt,v
retrieving revision 1.3
diff -u -3 -p -r1.3 cachetlb.txt
--- Documentation/cachetlb.txt	24 Jan 2002 11:04:15 -0000	1.3
+++ Documentation/cachetlb.txt	20 Mar 2002 01:46:38 -0000
@@ -341,6 +341,17 @@ Here is the new interface:
 	If the icache does not snoop stores then this routine will need
 	to flush it.
 
+  void flush_icache_user_range(struct vm_area_struct *vma,
+			struct page *page, unsigned long addr, int len)
+	This is called when the kernel stores into addresses that are
+	part of the address space of a user process (which may be some
+	other process than the current process).  The addr argument
+	gives the virtual address in that process's address space,
+	page is the page which is being modified, and len indicates
+	how many bytes have been modified.  The modified region must
+	not cross a page boundary.  Currently this is only called from
+	kernel/ptrace.c.
+
   void flush_icache_page(struct vm_area_struct *vma, struct page *page)
 	All the functionality of flush_icache_page can be implemented in
 	flush_dcache_page and update_mmu_cache. In 2.5 the hope is to
Index: arch/sh/config.in
===================================================================
RCS file: /cvsroot/linuxsh/linux/arch/sh/config.in,v
retrieving revision 1.5
diff -u -3 -p -r1.5 config.in
--- arch/sh/config.in	19 Mar 2002 23:48:05 -0000	1.5
+++ arch/sh/config.in	20 Mar 2002 01:46:38 -0000
@@ -356,7 +356,7 @@ comment 'Sound'
 
 tristate 'Sound card support' CONFIG_SOUND
 if [ "$CONFIG_SOUND" != "n" ]; then
-   source drivers/sound/Config.in
+   source sound/Config.in
 fi
 endmenu
 
Index: arch/sh/kernel/signal.c
===================================================================
RCS file: /cvsroot/linuxsh/linux/arch/sh/kernel/signal.c,v
retrieving revision 1.3
diff -u -3 -p -r1.3 signal.c
--- arch/sh/kernel/signal.c	1 Mar 2002 01:55:10 -0000	1.3
+++ arch/sh/kernel/signal.c	20 Mar 2002 01:46:38 -0000
@@ -83,7 +83,7 @@ sys_sigsuspend(old_sigset_t mask,
 	spin_lock_irq(&current->sigmask_lock);
 	saveset = current->blocked;
 	siginitset(&current->blocked, mask);
-	recalc_sigpending(current);
+	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 
 	regs.regs[0] = -EINTR;
@@ -112,7 +112,7 @@ sys_rt_sigsuspend(sigset_t *unewset, siz
 	spin_lock_irq(&current->sigmask_lock);
 	saveset = current->blocked;
 	current->blocked = newset;
-	recalc_sigpending(current);
+	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 
 	regs.regs[0] = -EINTR;
@@ -283,7 +283,7 @@ asmlinkage int sys_sigreturn(unsigned lo
 
 	spin_lock_irq(&current->sigmask_lock);
 	current->blocked = set;
-	recalc_sigpending(current);
+	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 
 	if (restore_sigcontext(&regs, &frame->sc, &r0))
@@ -313,7 +313,7 @@ asmlinkage int sys_rt_sigreturn(unsigned
 	sigdelsetmask(&set, ~_BLOCKABLE);
 	spin_lock_irq(&current->sigmask_lock);
 	current->blocked = set;
-	recalc_sigpending(current);
+	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 
 	if (restore_sigcontext(&regs, &frame->uc.uc_mcontext, &r0))
@@ -558,7 +558,7 @@ handle_signal(unsigned long sig, struct 
 		spin_lock_irq(&current->sigmask_lock);
 		sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask);
 		sigaddset(&current->blocked,sig);
-		recalc_sigpending(current);
+		recalc_sigpending();
 		spin_unlock_irq(&current->sigmask_lock);
 	}
 }
Index: drivers/Makefile
===================================================================
RCS file: /cvsroot/linuxsh/linux/drivers/Makefile,v
retrieving revision 1.4
diff -u -3 -p -r1.4 Makefile
--- drivers/Makefile	1 Mar 2002 01:55:10 -0000	1.4
+++ drivers/Makefile	20 Mar 2002 01:46:38 -0000
@@ -10,7 +10,7 @@ mod-subdirs :=	dio mtd sbus video macint
 		message/i2o message/fusion scsi md ieee1394 pnp isdn atm \
 		fc4 net/hamradio i2c acpi bluetooth input/serio input/gameport maple
 
-subdir-y :=	base parport char block net sound misc media cdrom hotplug
+subdir-y :=	base parport char block net misc media cdrom hotplug
 subdir-m :=	$(subdir-y)
 
 
Index: drivers/net/8139too.c
===================================================================
RCS file: /cvsroot/linuxsh/linux/drivers/net/8139too.c,v
retrieving revision 1.7
diff -u -3 -p -r1.7 8139too.c
--- drivers/net/8139too.c	1 Mar 2002 01:55:10 -0000	1.7
+++ drivers/net/8139too.c	20 Mar 2002 01:46:39 -0000
@@ -229,6 +229,7 @@ typedef enum {
 	DFE538TX,
 	DFE690TXD,
 	FE2000VX,
+	ALLIED8139,
 	SEGABBA,
 	RTL8129,
 } board_t;
@@ -248,6 +249,7 @@ static struct {
 	{ "D-Link DFE-538TX (RealTek RTL8139)", RTL8139_CAPS },
 	{ "D-Link DFE-690TXD (RealTek RTL8139)", RTL8139_CAPS },
 	{ "AboCom FE2000VX (RealTek RTL8139)", RTL8139_CAPS },
+	{ "Allied Telesyn 8139 CardBus", RTL8139_CAPS },
 	{ "SEGA Broadband Adapter", RTL8139_CAPS },
 	{ "RealTek RTL8129", RTL8129_CAPS },
 };
@@ -263,6 +265,7 @@ static struct pci_device_id rtl8139_pci_
 	{0x1186, 0x1300, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DFE538TX },
 	{0x1186, 0x1340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, DFE690TXD },
 	{0x13d1, 0xab06, PCI_ANY_ID, PCI_ANY_ID, 0, 0, FE2000VX },
+	{0x1259, 0xa117, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ALLIED8139 },
 	{0x11db, 0x1234, PCI_ANY_ID, PCI_ANY_ID, 0, 0, SEGABBA },
 
 #ifdef CONFIG_8139TOO_8129
@@ -1580,7 +1583,7 @@ static int rtl8139_thread (void *data)
 	reparent_to_init();
 	spin_lock_irq(&current->sigmask_lock);
 	sigemptyset(&current->blocked);
-	recalc_sigpending(current);
+	recalc_sigpending();
 	spin_unlock_irq(&current->sigmask_lock);
 
 	strncpy (current->comm, dev->name, sizeof(current->comm) - 1);
@@ -1669,23 +1672,24 @@ static int rtl8139_start_xmit (struct sk
 	struct rtl8139_private *tp = dev->priv;
 	void *ioaddr = tp->mmio_addr;
 	unsigned int entry;
+	unsigned int len = skb->len;
 
 	/* Calculate the next Tx descriptor entry. */
 	entry = tp->cur_tx % NUM_TX_DESC;
 
-	if (likely(skb->len < TX_BUF_SIZE)) {
+	if (likely(len < TX_BUF_SIZE)) {
 		skb_copy_and_csum_dev(skb, tp->tx_buf[entry]);
 		dev_kfree_skb(skb);
 	} else {
 		dev_kfree_skb(skb);
 		tp->stats.tx_dropped++;
 		return 0;
-  	}
+	}
 
 	/* Note: the chip doesn't have auto-pad! */
 	spin_lock_irq(&tp->lock);
 	RTL_W32_F (TxStatus0 + (entry * sizeof (u32)),
-		   tp->tx_flag | (skb->len >= ETH_ZLEN ? skb->len : ETH_ZLEN));
+		   tp->tx_flag | max(len, (unsigned int)ETH_ZLEN));
 
 	dev->trans_start = jiffies;
 
@@ -1696,8 +1700,8 @@ static int rtl8139_start_xmit (struct sk
 		netif_stop_queue (dev);
 	spin_unlock_irq(&tp->lock);
 
-	DPRINTK ("%s: Queued Tx packet at %p size %u to slot %d.\n",
-		 dev->name, skb->data, skb->len, entry);
+	DPRINTK ("%s: Queued Tx packet size %u to slot %d.\n",
+		 dev->name, len, entry);
 
 	return 0;
 }
Index: drivers/net/Config.in
===================================================================
RCS file: /cvsroot/linuxsh/linux/drivers/net/Config.in,v
retrieving revision 1.4
diff -u -3 -p -r1.4 Config.in
--- drivers/net/Config.in	1 Mar 2002 01:55:10 -0000	1.4
+++ drivers/net/Config.in	20 Mar 2002 01:46:39 -0000
@@ -37,7 +37,6 @@ if [ "$CONFIG_NET_ETHERNET" = "y" ]; the
         bool '    Use AAUI port instead of TP by default' CONFIG_MACE_AAUI_PORT
       fi
       dep_tristate '  BMAC (G3 ethernet) support' CONFIG_BMAC $CONFIG_ALL_PPC
-      dep_tristate '  GMAC (G4/iBook ethernet) support' CONFIG_GMAC $CONFIG_ALL_PPC
       tristate '  National DP83902AV (Oak ethernet) support' CONFIG_OAKNET
    fi
    if [ "$CONFIG_ZORRO" = "y" ]; then
Index: drivers/pci/pci.ids
===================================================================
RCS file: /cvsroot/linuxsh/linux/drivers/pci/pci.ids,v
retrieving revision 1.2
diff -u -3 -p -r1.2 pci.ids
--- drivers/pci/pci.ids	3 Dec 2001 22:15:34 -0000	1.2
+++ drivers/pci/pci.ids	20 Mar 2002 01:46:39 -0000
@@ -1551,9 +1551,14 @@
 	0001  i960 PCI bus interface
 	1076  VScom 800 8 port serial adaptor
 	1077  VScom 400 4 port serial adaptor
+	9030  PCI <-> IOBus Bridge (Hot Swap)
+		15ed 1002  Macrolink MCCS 8-port Serial (Hot Swap)
+		15ed 1003  Macrolink MCCS 16-port Serial (Hot Swap)
 	9036  9036
 	9050  PCI <-> IOBus Bridge
 		10b5 2273  SH-ARC SoHard ARCnet card
+		15ed 1000  Macrolink MCCS 8-port Serial
+		15ed 1001  Macrolink MCCS 16-port Serial
 		d84d 4006  EX-4006 1P
 		d84d 4008  EX-4008 1P EPP/ECP
 		d84d 4014  EX-4014 2P
@@ -3943,6 +3948,12 @@
 1413  Addonics
 1414  Microsoft Corporation
 1415  Oxford Semiconductor Ltd
+	9501  16PCI954 Function 0
+		15ed 2000  Macrolink MCCR Serial p0-3 of 8
+		15ed 2001  Macrolink MCCR Serial p0-3 of 16
+	9511  16PCI954 Function 1
+		15ed 2000  Macrolink MCCR Serial p4-7 of 8
+		15ed 2001  Macrolink MCCR Serial p4-15 of 16
 1416  Multiwave Innovation pte Ltd
 1417  Convergenet Technologies Inc
 1418  Kyushu electronics systems Inc
Index: include/asm-sh/pgtable.h
===================================================================
RCS file: /cvsroot/linuxsh/linux/include/asm-sh/pgtable.h,v
retrieving revision 1.4
diff -u -3 -p -r1.4 pgtable.h
--- include/asm-sh/pgtable.h	24 Jan 2002 11:04:15 -0000	1.4
+++ include/asm-sh/pgtable.h	20 Mar 2002 01:46:39 -0000
@@ -41,6 +41,7 @@ extern void paging_init(void);
 #define flush_dcache_page(page)			do { } while (0)
 #define flush_icache_range(start, end)		do { } while (0)
 #define flush_icache_page(vma,pg)		do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
 #define flush_cache_sigtramp(vaddr)		do { } while (0)
 
 #define p3_cache_init()				do { } while (0)
@@ -64,6 +65,7 @@ extern void flush_cache_sigtramp(unsigne
 
 #define flush_page_to_ram(page)			do { } while (0)
 #define flush_icache_page(vma,pg)		do { } while (0)
+#define flush_icache_user_range(vma,pg,adr,len)	do { } while (0)
 
 /* Initialization of P3 area for copy_user_page */
 extern void p3_cache_init(void);
@@ -206,11 +208,6 @@ extern unsigned long empty_zero_page[102
 #define pmd_clear(xp)	do { set_pmd(xp, __pmd(0)); } while (0)
 #define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
 
-/*
- * Permanent address of a page. Obviously must never be
- * called on a highmem page.
- */
-#define page_address(page)  ((page)->virtual) /* P1 address of the page */
 #define pages_to_mb(x)	((x) >> (20-PAGE_SHIFT))
 #define pte_page(x) 	phys_to_page(pte_val(x)&PTE_PHYS_MASK)
 
Index: include/net/inet_ecn.h
===================================================================
RCS file: /cvsroot/linuxsh/linux/include/net/inet_ecn.h,v
retrieving revision 1.2
diff -u -3 -p -r1.2 inet_ecn.h
--- include/net/inet_ecn.h	20 Jan 2002 07:42:26 -0000	1.2
+++ include/net/inet_ecn.h	20 Mar 2002 01:46:39 -0000
@@ -28,15 +28,15 @@ static inline __u8 INET_ECN_encapsulate(
 	return outer;
 }
 
-#define	INET_ECN_xmit(sk) do { (sk)->protinfo.af_inet.tos |= 2; } while (0)
-#define	INET_ECN_dontxmit(sk) do { (sk)->protinfo.af_inet.tos &= ~3; } while (0)
+#define	INET_ECN_xmit(sk) do { inet_sk(sk)->tos |= 2; } while (0)
+#define	INET_ECN_dontxmit(sk) do { inet_sk(sk)->tos &= ~3; } while (0)
 
 #define IP6_ECN_flow_init(label) do {	\
       (label) &= ~htonl(3<<20);		\
     } while (0)
 
 #define	IP6_ECN_flow_xmit(sk, label) do {			\
-	if (INET_ECN_is_capable((sk)->protinfo.af_inet.tos))	\
+	if (INET_ECN_is_capable(inet_sk(sk)->tos))		\
 		(label) |= __constant_htons(2 << 4);		\
     } while (0)
 
Index: kernel/ptrace.c
===================================================================
RCS file: /cvsroot/linuxsh/linux/kernel/ptrace.c,v
retrieving revision 1.4
diff -u -3 -p -r1.4 ptrace.c
--- kernel/ptrace.c	24 Jan 2002 10:28:23 -0000	1.4
+++ kernel/ptrace.c	20 Mar 2002 01:46:39 -0000
@@ -152,7 +152,7 @@ int access_process_vm(struct task_struct
 			memcpy(maddr + offset, buf, bytes);
 			flush_dcache_page(page);
 			flush_page_to_ram(page);
-			flush_icache_page(vma, page);
+			flush_icache_user_range(vma, page, addr, bytes);
 		} else {
 			memcpy(buf, maddr + offset, bytes);
 			flush_page_to_ram(page);
Index: mm/memory.c
===================================================================
RCS file: /cvsroot/linuxsh/linux/mm/memory.c,v
retrieving revision 1.6
diff -u -3 -p -r1.6 memory.c
--- mm/memory.c	24 Jan 2002 11:04:16 -0000	1.6
+++ mm/memory.c	20 Mar 2002 01:46:39 -0000
@@ -90,7 +90,7 @@ void __free_pte(pte_t pte)
  */
 static inline void free_one_pmd(pmd_t * dir)
 {
-	pte_t * pte;
+	struct page *pte;
 
 	if (pmd_none(*dir))
 		return;
@@ -99,7 +99,7 @@ static inline void free_one_pmd(pmd_t * 
 		pmd_clear(dir);
 		return;
 	}
-	pte = pte_offset(dir, 0);
+	pte = pmd_page(*dir);
 	pmd_clear(dir);
 	pte_free(pte);
 }
@@ -125,18 +125,6 @@ static inline void free_one_pgd(pgd_t * 
 	pmd_free(pmd);
 }
 
-/* Low and high watermarks for page table cache.
-   The system should try to have pgt_water[0] <= cache elements <= pgt_water[1]
- */
-int pgt_cache_water[2] = { 25, 50 };
-
-/* Returns the number of pages freed */
-int check_pgt_cache(void)
-{
-	return do_check_pgt_cache(pgt_cache_water[0], pgt_cache_water[1]);
-}
-
-
 /*
  * This function clears all user-level page tables of a process - this
  * is needed by execve(), so that old pages aren't in the way.
@@ -152,11 +140,59 @@ void clear_page_tables(struct mm_struct 
 		page_dir++;
 	} while (--nr);
 	spin_unlock(&mm->page_table_lock);
+}
 
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
+pte_t * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+	if (!pmd_present(*pmd)) {
+		struct page *new;
+
+		spin_unlock(&mm->page_table_lock);
+		new = pte_alloc_one(mm, address);
+		spin_lock(&mm->page_table_lock);
+		if (!new)
+			return NULL;
+
+		/*
+		 * Because we dropped the lock, we should re-check the
+		 * entry, as somebody else could have populated it..
+		 */
+		if (pmd_present(*pmd)) {
+			pte_free(new);
+			goto out;
+		}
+		pmd_populate(mm, pmd, new);
+	}
+out:
+	if (pmd_present(*pmd))
+		return pte_offset_map(pmd, address);
+	return NULL;
 }
 
+pte_t * pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
+{
+	if (!pmd_present(*pmd)) {
+		pte_t *new;
+
+		spin_unlock(&mm->page_table_lock);
+		new = pte_alloc_one_kernel(mm, address);
+		spin_lock(&mm->page_table_lock);
+		if (!new)
+			return NULL;
+
+		/*
+		 * Because we dropped the lock, we should re-check the
+		 * entry, as somebody else could have populated it..
+		 */
+		if (pmd_present(*pmd)) {
+			pte_free_kernel(new);
+			goto out;
+		}
+		pmd_populate_kernel(mm, pmd, new);
+	}
+out:
+	return pte_offset_kernel(pmd, address);
+}
 #define PTE_TABLE_MASK	((PTRS_PER_PTE-1) * sizeof(pte_t))
 #define PMD_TABLE_MASK	((PTRS_PER_PMD-1) * sizeof(pmd_t))
 
@@ -169,7 +205,7 @@ void clear_page_tables(struct mm_struct 
  *         variable count and make things faster. -jj
  *
  * dst->page_table_lock is held on entry and exit,
- * but may be dropped within pmd_alloc() and pte_alloc().
+ * but may be dropped within pmd_alloc() and pte_alloc_map().
  */
 int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
 			struct vm_area_struct *vma)
@@ -177,7 +213,7 @@ int copy_page_range(struct mm_struct *ds
 	pgd_t * src_pgd, * dst_pgd;
 	unsigned long address = vma->vm_start;
 	unsigned long end = vma->vm_end;
-	unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE;
+	unsigned long cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	src_pgd = pgd_offset(src, address)-1;
 	dst_pgd = pgd_offset(dst, address)-1;
@@ -221,12 +257,11 @@ skip_copy_pte_range:		address = (address
 				goto cont_copy_pmd_range;
 			}
 
-			src_pte = pte_offset(src_pmd, address);
-			dst_pte = pte_alloc(dst, dst_pmd, address);
+			dst_pte = pte_alloc_map(dst, dst_pmd, address);
 			if (!dst_pte)
 				goto nomem;
-
 			spin_lock(&src->page_table_lock);			
+			src_pte = pte_offset_map_nested(src_pmd, address);
 			do {
 				pte_t pte = *src_pte;
 				struct page *ptepage;
@@ -245,7 +280,7 @@ skip_copy_pte_range:		address = (address
 					goto cont_copy_pte_range;
 
 				/* If it's a COW mapping, write protect it both in the parent and the child */
-				if (cow) {
+				if (cow && pte_write(pte)) {
 					ptep_set_wrprotect(src_pte);
 					pte = *src_pte;
 				}
@@ -259,11 +294,16 @@ skip_copy_pte_range:		address = (address
 
 cont_copy_pte_range:		set_pte(dst_pte, pte);
 cont_copy_pte_range_noset:	address += PAGE_SIZE;
-				if (address >= end)
+				if (address >= end) {
+					pte_unmap_nested(src_pte);
+					pte_unmap(dst_pte);
 					goto out_unlock;
+				}
 				src_pte++;
 				dst_pte++;
 			} while ((unsigned long)src_pte & PTE_TABLE_MASK);
+			pte_unmap_nested(src_pte-1);
+			pte_unmap(dst_pte-1);
 			spin_unlock(&src->page_table_lock);
 		
 cont_copy_pmd_range:	src_pmd++;
@@ -292,7 +332,7 @@ static inline void forget_pte(pte_t page
 static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long address, unsigned long size)
 {
 	unsigned long offset;
-	pte_t * ptep;
+	pte_t *ptep;
 	int freed = 0;
 
 	if (pmd_none(*pmd))
@@ -302,7 +342,7 @@ static inline int zap_pte_range(mmu_gath
 		pmd_clear(pmd);
 		return 0;
 	}
-	ptep = pte_offset(pmd, address);
+	ptep = pte_offset_map(pmd, address);
 	offset = address & ~PMD_MASK;
 	if (offset + size > PMD_SIZE)
 		size = PMD_SIZE - offset;
@@ -322,6 +362,7 @@ static inline int zap_pte_range(mmu_gath
 			pte_clear(ptep);
 		}
 	}
+	pte_unmap(ptep-1);
 
 	return freed;
 }
@@ -415,11 +456,16 @@ static struct page * follow_page(struct 
 	if (pmd_none(*pmd) || pmd_bad(*pmd))
 		goto out;
 
-	ptep = pte_offset(pmd, address);
-	if (!ptep)
+	preempt_disable();
+	ptep = pte_offset_map(pmd, address);
+	if (!ptep) {
+		preempt_enable();
 		goto out;
+	}
 
 	pte = *ptep;
+	pte_unmap(ptep);
+	preempt_enable();
 	if (pte_present(pte)) {
 		if (!write ||
 		    (pte_write(pte) && pte_dirty(pte)))
@@ -446,20 +492,25 @@ static inline struct page * get_page_map
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
 		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas)
 {
-	int i = 0;
+	int i;
+	unsigned int flags;
+
+	/* 
+	 * Require read or write permissions.
+	 * If 'force' is set, we only require the "MAY" flags.
+	 */
+	flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+	flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+	i = 0;
+	
 
 	do {
 		struct vm_area_struct *	vma;
 
 		vma = find_extend_vma(mm, start);
 
-		if ( !vma ||
-		    (!force &&
-		     	((write && (!(vma->vm_flags & VM_WRITE))) ||
-		    	 (!write && (!(vma->vm_flags & VM_READ))) ) )) {
-			if (i) return i;
-			return -EFAULT;
-		}
+		if ( !vma || !(flags & vma->vm_flags) )
+			return i ? : -EFAULT;
 
 		spin_lock(&mm->page_table_lock);
 		do {
@@ -748,10 +799,11 @@ static inline int zeromap_pmd_range(stru
 	if (end > PGDIR_SIZE)
 		end = PGDIR_SIZE;
 	do {
-		pte_t * pte = pte_alloc(mm, pmd, address);
+		pte_t * pte = pte_alloc_map(mm, pmd, address);
 		if (!pte)
 			return -ENOMEM;
 		zeromap_pte_range(pte, address, end - address, prot);
+		pte_unmap(pte);
 		address = (address + PMD_SIZE) & PMD_MASK;
 		pmd++;
 	} while (address && (address < end));
@@ -828,10 +880,11 @@ static inline int remap_pmd_range(struct
 		end = PGDIR_SIZE;
 	phys_addr -= address;
 	do {
-		pte_t * pte = pte_alloc(mm, pmd, address);
+		pte_t * pte = pte_alloc_map(mm, pmd, address);
 		if (!pte)
 			return -ENOMEM;
 		remap_pte_range(pte, address, end - address, address + phys_addr, prot);
+		pte_unmap(pte);
 		address = (address + PMD_SIZE) & PMD_MASK;
 		pmd++;
 	} while (address && (address < end));
@@ -919,7 +972,7 @@ static inline void break_cow(struct vm_a
  * with the page_table_lock released.
  */
 static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
-	unsigned long address, pte_t *page_table, pte_t pte)
+	unsigned long address, pte_t *page_table, pmd_t *pmd, pte_t pte)
 {
 	struct page *old_page, *new_page;
 
@@ -935,10 +988,12 @@ static int do_wp_page(struct mm_struct *
 			flush_cache_page(vma, address);
 #endif
 			establish_pte(vma, address, page_table, pte_mkyoung(pte_mkdirty(pte_mkwrite(pte))));
+			pte_unmap(page_table);
 			spin_unlock(&mm->page_table_lock);
 			return 1;	/* Minor fault */
 		}
 	}
+	pte_unmap(page_table);
 
 	/*
 	 * Ok, we need to copy. Oh, well..
@@ -955,6 +1010,7 @@ static int do_wp_page(struct mm_struct *
 	 * Re-check the pte - we dropped the lock
 	 */
 	spin_lock(&mm->page_table_lock);
+	page_table = pte_offset_map(pmd, address);
 	if (pte_same(*page_table, pte)) {
 		if (PageReserved(old_page))
 			++mm->rss;
@@ -964,12 +1020,14 @@ static int do_wp_page(struct mm_struct *
 		/* Free the old page.. */
 		new_page = old_page;
 	}
+	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 	return 1;	/* Minor fault */
 
 bad_wp_page:
+	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 	printk("do_wp_page: bogus page at address %08lx (page 0x%lx)\n",address,(unsigned long)old_page);
 	return -1;
@@ -1052,11 +1110,8 @@ do_expand:
 	inode->i_size = offset;
 
 out_truncate:
-	if (inode->i_op && inode->i_op->truncate) {
-		lock_kernel();
+	if (inode->i_op && inode->i_op->truncate)
 		inode->i_op->truncate(inode);
-		unlock_kernel();
-	}
 out:
 	return 0;
 }
@@ -1093,13 +1148,14 @@ void swapin_readahead(swp_entry_t entry)
  */
 static int do_swap_page(struct mm_struct * mm,
 	struct vm_area_struct * vma, unsigned long address,
-	pte_t * page_table, pte_t orig_pte, int write_access)
+	pte_t *page_table, pmd_t *pmd, pte_t orig_pte, int write_access)
 {
 	struct page *page;
 	swp_entry_t entry = pte_to_swp_entry(orig_pte);
 	pte_t pte;
 	int ret = 1;
 
+	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 	page = lookup_swap_cache(entry);
 	if (!page) {
@@ -1112,7 +1168,9 @@ static int do_swap_page(struct mm_struct
 			 */
 			int retval;
 			spin_lock(&mm->page_table_lock);
+			page_table = pte_offset_map(pmd, address);
 			retval = pte_same(*page_table, orig_pte) ? -1 : 1;
+			pte_unmap(page_table);
 			spin_unlock(&mm->page_table_lock);
 			return retval;
 		}
@@ -1128,7 +1186,9 @@ static int do_swap_page(struct mm_struct
 	 * released the page table lock.
 	 */
 	spin_lock(&mm->page_table_lock);
+	page_table = pte_offset_map(pmd, address);
 	if (!pte_same(*page_table, orig_pte)) {
+		pte_unmap(page_table);
 		spin_unlock(&mm->page_table_lock);
 		unlock_page(page);
 		page_cache_release(page);
@@ -1153,6 +1213,7 @@ static int do_swap_page(struct mm_struct
 
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(vma, address, pte);
+	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 	return ret;
 }
@@ -1162,7 +1223,7 @@ static int do_swap_page(struct mm_struct
  * spinlock held to protect against concurrent faults in
  * multithreaded programs. 
  */
-static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
+static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, pmd_t *pmd, int write_access, unsigned long addr)
 {
 	pte_t entry;
 
@@ -1174,6 +1235,7 @@ static int do_anonymous_page(struct mm_s
 		struct page *page;
 
 		/* Allocate our own private page. */
+		pte_unmap(page_table);
 		spin_unlock(&mm->page_table_lock);
 
 		page = alloc_page(GFP_HIGHUSER);
@@ -1182,7 +1244,10 @@ static int do_anonymous_page(struct mm_s
 		clear_user_highpage(page, addr);
 
 		spin_lock(&mm->page_table_lock);
+		page_table = pte_offset_map(pmd, addr);
+
 		if (!pte_none(*page_table)) {
+			pte_unmap(page_table);
 			page_cache_release(page);
 			spin_unlock(&mm->page_table_lock);
 			return 1;
@@ -1194,6 +1259,7 @@ static int do_anonymous_page(struct mm_s
 	}
 
 	set_pte(page_table, entry);
+	pte_unmap(page_table);
 
 	/* No need to invalidate - it was non-present before */
 	update_mmu_cache(vma, addr, entry);
@@ -1217,13 +1283,14 @@ no_mem:
  * spinlock held. Exit with the spinlock released.
  */
 static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
-	unsigned long address, int write_access, pte_t *page_table)
+	unsigned long address, int write_access, pte_t *page_table, pmd_t *pmd)
 {
 	struct page * new_page;
 	pte_t entry;
 
 	if (!vma->vm_ops || !vma->vm_ops->nopage)
-		return do_anonymous_page(mm, vma, page_table, write_access, address);
+		return do_anonymous_page(mm, vma, page_table, pmd, write_access, address);
+	pte_unmap(page_table);
 	spin_unlock(&mm->page_table_lock);
 
 	new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
@@ -1249,6 +1316,8 @@ static int do_no_page(struct mm_struct *
 	}
 
 	spin_lock(&mm->page_table_lock);
+	page_table = pte_offset_map(pmd, address);
+
 	/*
 	 * This silly early PAGE_DIRTY setting removes a race
 	 * due to the bad i386 page protection. But it's valid
@@ -1268,8 +1337,10 @@ static int do_no_page(struct mm_struct *
 		if (write_access)
 			entry = pte_mkwrite(pte_mkdirty(entry));
 		set_pte(page_table, entry);
+		pte_unmap(page_table);
 	} else {
 		/* One of our sibling threads was faster, back out. */
+		pte_unmap(page_table);
 		page_cache_release(new_page);
 		spin_unlock(&mm->page_table_lock);
 		return 1;
@@ -1304,7 +1375,7 @@ static int do_no_page(struct mm_struct *
  */
 static inline int handle_pte_fault(struct mm_struct *mm,
 	struct vm_area_struct * vma, unsigned long address,
-	int write_access, pte_t * pte)
+	int write_access, pte_t *pte, pmd_t *pmd)
 {
 	pte_t entry;
 
@@ -1316,18 +1387,19 @@ static inline int handle_pte_fault(struc
 		 * drop the lock.
 		 */
 		if (pte_none(entry))
-			return do_no_page(mm, vma, address, write_access, pte);
-		return do_swap_page(mm, vma, address, pte, entry, write_access);
+			return do_no_page(mm, vma, address, write_access, pte, pmd);
+		return do_swap_page(mm, vma, address, pte, pmd, entry, write_access);
 	}
 
 	if (write_access) {
 		if (!pte_write(entry))
-			return do_wp_page(mm, vma, address, pte, entry);
+			return do_wp_page(mm, vma, address, pte, pmd, entry);
 
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
 	establish_pte(vma, address, pte, entry);
+	pte_unmap(pte);
 	spin_unlock(&mm->page_table_lock);
 	return 1;
 }
@@ -1352,9 +1424,9 @@ int handle_mm_fault(struct mm_struct *mm
 	pmd = pmd_alloc(mm, pgd, address);
 
 	if (pmd) {
-		pte_t * pte = pte_alloc(mm, pmd, address);
+		pte_t * pte = pte_alloc_map(mm, pmd, address);
 		if (pte)
-			return handle_pte_fault(mm, vma, address, write_access, pte);
+			return handle_pte_fault(mm, vma, address, write_access, pte, pmd);
 	}
 	spin_unlock(&mm->page_table_lock);
 	return -1;
@@ -1373,64 +1445,25 @@ pmd_t *__pmd_alloc(struct mm_struct *mm,
 {
 	pmd_t *new;
 
-	/* "fast" allocation can happen without dropping the lock.. */
-	new = pmd_alloc_one_fast(mm, address);
-	if (!new) {
-		spin_unlock(&mm->page_table_lock);
-		new = pmd_alloc_one(mm, address);
-		spin_lock(&mm->page_table_lock);
-		if (!new)
-			return NULL;
+	spin_unlock(&mm->page_table_lock);
+	new = pmd_alloc_one(mm, address);
+	spin_lock(&mm->page_table_lock);
+	if (!new)
+		return NULL;
 
-		/*
-		 * Because we dropped the lock, we should re-check the
-		 * entry, as somebody else could have populated it..
-		 */
-		if (!pgd_none(*pgd)) {
-			pmd_free(new);
-			goto out;
-		}
+	/*
+	 * Because we dropped the lock, we should re-check the
+	 * entry, as somebody else could have populated it..
+	 */
+	if (pgd_present(*pgd)) {
+		pmd_free(new);
+		goto out;
 	}
 	pgd_populate(mm, pgd, new);
 out:
 	return pmd_offset(pgd, address);
 }
 
-/*
- * Allocate the page table directory.
- *
- * We've already handled the fast-path in-line, and we own the
- * page table lock.
- */
-pte_t *pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
-{
-	if (pmd_none(*pmd)) {
-		pte_t *new;
-
-		/* "fast" allocation can happen without dropping the lock.. */
-		new = pte_alloc_one_fast(mm, address);
-		if (!new) {
-			spin_unlock(&mm->page_table_lock);
-			new = pte_alloc_one(mm, address);
-			spin_lock(&mm->page_table_lock);
-			if (!new)
-				return NULL;
-
-			/*
-			 * Because we dropped the lock, we should re-check the
-			 * entry, as somebody else could have populated it..
-			 */
-			if (!pmd_none(*pmd)) {
-				pte_free(new);
-				goto out;
-			}
-		}
-		pmd_populate(mm, pmd, new);
-	}
-out:
-	return pte_offset(pmd, address);
-}
-
 int make_pages_present(unsigned long addr, unsigned long end)
 {
 	int ret, len, write;
@@ -1446,4 +1479,29 @@ int make_pages_present(unsigned long add
 	ret = get_user_pages(current, current->mm, addr,
 			len, write, 0, NULL, NULL);
 	return ret == len ? 0 : -1;
+}
+
+/* 
+ * Map a vmalloc()-space virtual address to the physical page.
+ */
+struct page * vmalloc_to_page(unsigned long addr)
+{
+	struct page *page = NULL;
+	pgd_t *pgd = pgd_offset_k(addr);
+	pmd_t *pmd;
+	pte_t *ptep, pte;
+  
+	if (!pgd_none(*pgd)) {
+		pmd = pmd_offset(pgd, addr);
+		if (!pmd_none(*pmd)) {
+			preempt_disable();
+			ptep = pte_offset_map(pmd, addr);
+			pte = *ptep;
+			if (pte_present(pte))
+				page = pte_page(pte);
+			pte_unmap(ptep);
+			preempt_enable();
+		}
+	}
+	return page;
 }