Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

95 files changed, 845 insertions, 410 deletions

diff --git a/Documentation/scsi/cxgb3i.txt b/Documentation/scsi/cxgb3i.txt
index 8141fa0..7ac8032 100644
--- a/Documentation/scsi/cxgb3i.txt
+++ b/Documentation/scsi/cxgb3i.txt
@@ -4,7 +4,7 @@ Introduction
 ============
 
 The Chelsio T3 ASIC based Adapters (S310, S320, S302, S304, Mezz cards, etc.
-series of products) supports iSCSI acceleration and iSCSI Direct Data Placement
+series of products) support iSCSI acceleration and iSCSI Direct Data Placement
 (DDP) where the hardware handles the expensive byte touching operations, such
 as CRC computation and verification, and direct DMA to the final host memory
 destination:
@@ -31,9 +31,9 @@ destination:
 	  the TCP segments onto the wire. It handles TCP retransmission if
 	  needed.
 
-	  On receving, S3 h/w recovers the iSCSI PDU by reassembling TCP
+	  On receiving, S3 h/w recovers the iSCSI PDU by reassembling TCP
 	  segments, separating the header and data, calculating and verifying
-	  the digests, then forwards the header to the host. The payload data,
+	  the digests, then forwarding the header to the host. The payload data,
 	  if possible, will be directly placed into the pre-posted host DDP
 	  buffer. Otherwise, the payload data will be sent to the host too.
 
@@ -68,9 +68,8 @@ The following steps need to be taken to accelerates the open-iscsi initiator:
 	sure the ip address is unique in the network.
 
 3. edit /etc/iscsi/iscsid.conf
-   The default setting for MaxRecvDataSegmentLength (131072) is too big,
-   replace "node.conn[0].iscsi.MaxRecvDataSegmentLength" to be a value no
-   bigger than 15360 (for example 8192):
+   The default setting for MaxRecvDataSegmentLength (131072) is too big;
+   replace with a value no bigger than 15360 (for example 8192):
 
 	node.conn[0].iscsi.MaxRecvDataSegmentLength = 8192
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 59fd2d1..1c2ca1d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2464,7 +2464,7 @@ S:	Maintained
 
 ISDN SUBSYSTEM
 P:	Karsten Keil
-M:	kkeil@suse.de
+M:	isdn@linux-pingi.de
 L:	isdn4linux@listserv.isdn4linux.de (subscribers-only)
 W:	http://www.isdn4linux.de
 T:	git kernel.org:/pub/scm/linux/kernel/kkeil/isdn-2.6.git
diff --git a/Makefile b/Makefile
index df6ce3e..d04ee0a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 29
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Erotic Pickled Herring
 
 # *DOCUMENTATION*
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7049815..68d6494 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -233,12 +233,13 @@ static void __init cacheid_init(void)
 	unsigned int cachetype = read_cpuid_cachetype();
 	unsigned int arch = cpu_architecture();
 
-	if (arch >= CPU_ARCH_ARMv7) {
-		cacheid = CACHEID_VIPT_NONALIASING;
-		if ((cachetype & (3 << 14)) == 1 << 14)
-			cacheid |= CACHEID_ASID_TAGGED;
-	} else if (arch >= CPU_ARCH_ARMv6) {
-		if (cachetype & (1 << 23))
+	if (arch >= CPU_ARCH_ARMv6) {
+		if ((cachetype & (7 << 29)) == 4 << 29) {
+			/* ARMv7 register format */
+			cacheid = CACHEID_VIPT_NONALIASING;
+			if ((cachetype & (3 << 14)) == 1 << 14)
+				cacheid |= CACHEID_ASID_TAGGED;
+		} else if (cachetype & (1 << 23))
 			cacheid = CACHEID_VIPT_ALIASING;
 		else
 			cacheid = CACHEID_VIPT_NONALIASING;
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 9bb4f04..7ac812d 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -332,7 +332,6 @@ static int at91_pm_enter(suspend_state_t state)
 			at91_sys_read(AT91_AIC_IPR) & at91_sys_read(AT91_AIC_IMR));
 
 error:
-	sdram_selfrefresh_disable();
 	target_state = PM_SUSPEND_ON;
 	at91_irq_resume();
 	at91_gpio_resume();
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8a7f65b..94077fb 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -23,7 +23,8 @@ ENTRY(v6_early_abort)
 #ifdef CONFIG_CPU_32v6K
 	clrex
 #else
-	strex	r0, r1, [sp]			@ Clear the exclusive monitor
+	sub	r1, sp, #4			@ Get unused stack location
+	strex	r0, r1, [r1]			@ Clear the exclusive monitor
 #endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
diff --git a/arch/arm/plat-s3c64xx/irq-eint.c b/arch/arm/plat-s3c64xx/irq-eint.c
index 1f7cc00..ebb305c 100644
--- a/arch/arm/plat-s3c64xx/irq-eint.c
+++ b/arch/arm/plat-s3c64xx/irq-eint.c
@@ -55,7 +55,7 @@ static void s3c_irq_eint_unmask(unsigned int irq)
 	u32 mask;
 
 	mask = __raw_readl(S3C64XX_EINT0MASK);
-	mask |= eint_irq_to_bit(irq);
+	mask &= ~eint_irq_to_bit(irq);
 	__raw_writel(mask, S3C64XX_EINT0MASK);
 }
 
diff --git a/arch/mips/include/asm/seccomp.h b/arch/mips/include/asm/seccomp.h
index 36ed440..a6772e9 100644
--- a/arch/mips/include/asm/seccomp.h
+++ b/arch/mips/include/asm/seccomp.h
@@ -1,6 +1,5 @@
 #ifndef __ASM_SECCOMP_H
 
-#include <linux/thread_info.h>
 #include <linux/unistd.h>
 
 #define __NR_seccomp_read __NR_read
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index d811a8c..4774c2f 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -210,5 +210,10 @@ struct compat_shmid64_ds {
 	compat_ulong_t __unused6;
 };
 
+static inline int is_compat_task(void)
+{
+	return test_thread_flag(TIF_32BIT);
+}
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_COMPAT_H */
diff --git a/arch/powerpc/include/asm/seccomp.h b/arch/powerpc/include/asm/seccomp.h
index 853765e..00c1d91 100644
--- a/arch/powerpc/include/asm/seccomp.h
+++ b/arch/powerpc/include/asm/seccomp.h
@@ -1,10 +1,6 @@
 #ifndef _ASM_POWERPC_SECCOMP_H
 #define _ASM_POWERPC_SECCOMP_H
 
-#ifdef __KERNEL__
-#include <linux/thread_info.h>
-#endif
-
 #include <linux/unistd.h>
 
 #define __NR_seccomp_read __NR_read
diff --git a/arch/powerpc/platforms/86xx/gef_sbc610.c b/arch/powerpc/platforms/86xx/gef_sbc610.c
index fb371f5..d6b772b 100644
--- a/arch/powerpc/platforms/86xx/gef_sbc610.c
+++ b/arch/powerpc/platforms/86xx/gef_sbc610.c
@@ -142,6 +142,10 @@ static void __init gef_sbc610_nec_fixup(struct pci_dev *pdev)
 {
 	unsigned int val;
 
+	/* Do not do the fixup on other platforms! */
+	if (!machine_is(gef_sbc610))
+		return;
+
 	printk(KERN_INFO "Running NEC uPD720101 Fixup\n");
 
 	/* Ensure ports 1, 2, 3, 4 & 5 are enabled */
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index c42cd89..6118890 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -556,7 +556,7 @@ static void __exit aes_s390_fini(void)
 module_init(aes_s390_init);
 module_exit(aes_s390_fini);
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS("aes-all");
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
 MODULE_LICENSE("GPL");
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index f260b58..0e70625 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -240,4 +240,9 @@ struct compat_shmid64_ds {
 	unsigned int	__unused2;
 };
 
+static inline int is_compat_task(void)
+{
+	return test_thread_flag(TIF_32BIT);
+}
+
 #endif /* _ASM_SPARC64_COMPAT_H */
diff --git a/arch/sparc/include/asm/seccomp.h b/arch/sparc/include/asm/seccomp.h
index 7fcd996..adca1bc 100644
--- a/arch/sparc/include/asm/seccomp.h
+++ b/arch/sparc/include/asm/seccomp.h
@@ -1,11 +1,5 @@
 #ifndef _ASM_SECCOMP_H
 
-#include <linux/thread_info.h> /* already defines TIF_32BIT */
-
-#ifndef TIF_32BIT
-#error "unexpected TIF_32BIT on sparc64"
-#endif
-
 #include <linux/unistd.h>
 
 #define __NR_seccomp_read __NR_read
diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h
index a6ad87b..b811d6f 100644
--- a/arch/x86/include/asm/seccomp_32.h
+++ b/arch/x86/include/asm/seccomp_32.h
@@ -1,12 +1,6 @@
 #ifndef _ASM_X86_SECCOMP_32_H
 #define _ASM_X86_SECCOMP_32_H
 
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on i386"
-#endif
-
 #include <linux/unistd.h>
 
 #define __NR_seccomp_read __NR_read
diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h
index 4171bb7..84ec1bd 100644
--- a/arch/x86/include/asm/seccomp_64.h
+++ b/arch/x86/include/asm/seccomp_64.h
@@ -1,14 +1,6 @@
 #ifndef _ASM_X86_SECCOMP_64_H
 #define _ASM_X86_SECCOMP_64_H
 
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on x86_64"
-#else
-#define TIF_32BIT TIF_IA32
-#endif
-
 #include <linux/unistd.h>
 #include <asm/ia32_unistd.h>
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 5a4c23d..06ca07f 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1388,7 +1388,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 #ifdef CONFIG_X86_32
 # define IS_IA32	1
 #elif defined CONFIG_IA32_EMULATION
-# define IS_IA32	test_thread_flag(TIF_IA32)
+# define IS_IA32	is_compat_task()
 #else
 # define IS_IA32	0
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e6d36b4..b135225 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -714,6 +714,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	pos = start_pfn << PAGE_SHIFT;
 	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
 			<< (PMD_SHIFT - PAGE_SHIFT);
+	if (end_pfn > (end >> PAGE_SHIFT))
+		end_pfn = end >> PAGE_SHIFT;
 	if (start_pfn < end_pfn) {
 		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 		pos = end_pfn << PAGE_SHIFT;
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 6c2b1af..04102d4 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -20,23 +20,16 @@
 #include <asm/pat.h>
 #include <linux/module.h>
 
-#ifdef CONFIG_X86_PAE
-int
-is_io_mapping_possible(resource_size_t base, unsigned long size)
-{
-	return 1;
-}
-#else
-int
-is_io_mapping_possible(resource_size_t base, unsigned long size)
+int is_io_mapping_possible(resource_size_t base, unsigned long size)
 {
+#ifndef CONFIG_X86_PAE
 	/* There is no way to map greater than 1 << 32 address without PAE */
 	if (base + size > 0x100000000ULL)
 		return 0;
-
+#endif
 	return 1;
 }
-#endif
+EXPORT_SYMBOL_GPL(is_io_mapping_possible);
 
 /* Map 'pfn' using fixed map 'type' and protections 'prot'
  */
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 93d82038..9f20503 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -32,11 +32,14 @@ struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
 	unsigned long page; /* location of the fault page */
+	bool old_presence; /* page presence prior to arming */
+	bool armed;
 
 	/*
 	 * Number of times this page has been registered as a part
 	 * of a probe. If zero, page is disarmed and this may be freed.
-	 * Used only by writers (RCU).
+	 * Used only by writers (RCU) and post_kmmio_handler().
+	 * Protected by kmmio_lock, when linked into kmmio_page_table.
 	 */
 	int count;
 };
@@ -105,57 +108,85 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
 	return NULL;
 }
 
-static void set_page_present(unsigned long addr, bool present,
-							unsigned int *pglevel)
+static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+{
+	pmdval_t v = pmd_val(*pmd);
+	*old = !!(v & _PAGE_PRESENT);
+	v &= ~_PAGE_PRESENT;
+	if (present)
+		v |= _PAGE_PRESENT;
+	set_pmd(pmd, __pmd(v));
+}
+
+static void set_pte_presence(pte_t *pte, bool present, bool *old)
+{
+	pteval_t v = pte_val(*pte);
+	*old = !!(v & _PAGE_PRESENT);
+	v &= ~_PAGE_PRESENT;
+	if (present)
+		v |= _PAGE_PRESENT;
+	set_pte_atomic(pte, __pte(v));
+}
+
+static int set_page_presence(unsigned long addr, bool present, bool *old)
 {
-	pteval_t pteval;
-	pmdval_t pmdval;
 	unsigned int level;
-	pmd_t *pmd;
 	pte_t *pte = lookup_address(addr, &level);
 
 	if (!pte) {
 		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
-		return;
+		return -1;
 	}
 
-	if (pglevel)
-		*pglevel = level;
-
 	switch (level) {
 	case PG_LEVEL_2M:
-		pmd = (pmd_t *)pte;
-		pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT;
-		if (present)
-			pmdval |= _PAGE_PRESENT;
-		set_pmd(pmd, __pmd(pmdval));
+		set_pmd_presence((pmd_t *)pte, present, old);
 		break;
-
 	case PG_LEVEL_4K:
-		pteval = pte_val(*pte) & ~_PAGE_PRESENT;
-		if (present)
-			pteval |= _PAGE_PRESENT;
-		set_pte_atomic(pte, __pte(pteval));
+		set_pte_presence(pte, present, old);
 		break;
-
 	default:
 		pr_err("kmmio: unexpected page level 0x%x.\n", level);
-		return;
+		return -1;
 	}
 
 	__flush_tlb_one(addr);
+	return 0;
 }
 
-/** Mark the given page as not present. Access to it will trigger a fault. */
-static void arm_kmmio_fault_page(unsigned long page, unsigned int *pglevel)
+/*
+ * Mark the given page as not present. Access to it will trigger a fault.
+ *
+ * Struct kmmio_fault_page is protected by RCU and kmmio_lock, but the
+ * protection is ignored here. RCU read lock is assumed held, so the struct
+ * will not disappear unexpectedly. Furthermore, the caller must guarantee,
+ * that double arming the same virtual address (page) cannot occur.
+ *
+ * Double disarming on the other hand is allowed, and may occur when a fault
+ * and mmiotrace shutdown happen simultaneously.
+ */
+static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	set_page_present(page & PAGE_MASK, false, pglevel);
+	int ret;
+	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
+	if (f->armed) {
+		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
+					f->page, f->count, f->old_presence);
+	}
+	ret = set_page_presence(f->page, false, &f->old_presence);
+	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
+	f->armed = true;
+	return ret;
 }
 
-/** Mark the given page as present. */
-static void disarm_kmmio_fault_page(unsigned long page, unsigned int *pglevel)
+/** Restore the given page to saved presence state. */
+static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	set_page_present(page & PAGE_MASK, true, pglevel);
+	bool tmp;
+	int ret = set_page_presence(f->page, f->old_presence, &tmp);
+	WARN_ONCE(ret < 0,
+			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+	f->armed = false;
 }
 
 /*
@@ -202,28 +233,32 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 
 	ctx = &get_cpu_var(kmmio_ctx);
 	if (ctx->active) {
-		disarm_kmmio_fault_page(faultpage->page, NULL);
 		if (addr == ctx->addr) {
 			/*
-			 * On SMP we sometimes get recursive probe hits on the
-			 * same address. Context is already saved, fall out.
+			 * A second fault on the same page means some other
+			 * condition needs handling by do_page_fault(), the
+			 * page really not being present is the most common.
 			 */
-			pr_debug("kmmio: duplicate probe hit on CPU %d, for "
-						"address 0x%08lx.\n",
-						smp_processor_id(), addr);
-			ret = 1;
-			goto no_kmmio_ctx;
-		}
-		/*
-		 * Prevent overwriting already in-flight context.
-		 * This should not happen, let's hope disarming at least
-		 * prevents a panic.
-		 */
-		pr_emerg("kmmio: recursive probe hit on CPU %d, "
+			pr_debug("kmmio: secondary hit for 0x%08lx CPU %d.\n",
+					addr, smp_processor_id());
+
+			if (!faultpage->old_presence)
+				pr_info("kmmio: unexpected secondary hit for "
+					"address 0x%08lx on CPU %d.\n", addr,
+					smp_processor_id());
+		} else {
+			/*
+			 * Prevent overwriting already in-flight context.
+			 * This should not happen, let's hope disarming at
+			 * least prevents a panic.
+			 */
+			pr_emerg("kmmio: recursive probe hit on CPU %d, "
 					"for address 0x%08lx. Ignoring.\n",
 					smp_processor_id(), addr);
-		pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
-					ctx->addr);
+			pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
+						ctx->addr);
+			disarm_kmmio_fault_page(faultpage);
+		}
 		goto no_kmmio_ctx;
 	}
 	ctx->active++;
@@ -244,7 +279,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	regs->flags &= ~X86_EFLAGS_IF;
 
 	/* Now we set present bit in PTE and single step. */
-	disarm_kmmio_fault_page(ctx->fpage->page, NULL);
+	disarm_kmmio_fault_page(ctx->fpage);
 
 	/*
 	 * If another cpu accesses the same page while we are stepping,
@@ -275,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
 
 	if (!ctx->active) {
-		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+		pr_warning("kmmio: spurious debug trap on CPU %d.\n",
 							smp_processor_id());
 		goto out;
 	}
@@ -283,7 +318,11 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	if (ctx->probe && ctx->probe->post_handler)
 		ctx->probe->post_handler(ctx->probe, condition, regs);
 
-	arm_kmmio_fault_page(ctx->fpage->page, NULL);
+	/* Prevent racing against release_kmmio_fault_page(). */
+	spin_lock(&kmmio_lock);
+	if (ctx->fpage->count)
+		arm_kmmio_fault_page(ctx->fpage);
+	spin_unlock(&kmmio_lock);
 
 	regs->flags &= ~X86_EFLAGS_TF;
 	regs->flags |= ctx->saved_flags;
@@ -315,20 +354,24 @@ static int add_kmmio_fault_page(unsigned long page)
 	f = get_kmmio_fault_page(page);
 	if (f) {
 		if (!f->count)
-			arm_kmmio_fault_page(f->page, NULL);
+			arm_kmmio_fault_page(f);
 		f->count++;
 		return 0;
 	}
 
-	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
 	if (!f)
 		return -1;
 
 	f->count = 1;
 	f->page = page;
-	list_add_rcu(&f->list, kmmio_page_list(f->page));
 
-	arm_kmmio_fault_page(f->page, NULL);
+	if (arm_kmmio_fault_page(f)) {
+		kfree(f);
+		return -1;
+	}
+
+	list_add_rcu(&f->list, kmmio_page_list(f->page));
 
 	return 0;
 }
@@ -347,7 +390,7 @@ static void release_kmmio_fault_page(unsigned long page,
 	f->count--;
 	BUG_ON(f->count < 0);
 	if (!f->count) {
-		disarm_kmmio_fault_page(f->page, NULL);
+		disarm_kmmio_fault_page(f);
 		f->release_next = *release_list;
 		*release_list = f;
 	}
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index aebbf67..e0ab173 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -11,6 +11,7 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
@@ -868,6 +869,7 @@ pgprot_t pgprot_writecombine(pgprot_t prot)
 	else
 		return pgprot_noncached(prot);
 }
+EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index ab50a8d..427fd1b 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -1,5 +1,5 @@
 /*
- * Written by Pekka Paalanen, 2008 <pq@iki.fi>
+ * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi>
  */
 #include <linux/module.h>
 #include <linux/io.h>
@@ -9,35 +9,74 @@
 
 static unsigned long mmio_address;
 module_param(mmio_address, ulong, 0);
-MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
+MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
+				"(or 8 MB if read_far is non-zero).");
+
+static unsigned long read_far = 0x400100;
+module_param(read_far, ulong, 0);
+MODULE_PARM_DESC(read_far, " Offset of a 32-bit read within 8 MB "
+				"(default: 0x400100).");
+
+static unsigned v16(unsigned i)
+{
+	return i * 12 + 7;
+}
+
+static unsigned v32(unsigned i)
+{
+	return i * 212371 + 13;
+}
 
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
+	pr_info(MODULE_NAME ": write test.\n");
 	mmiotrace_printk("Write test.\n");
+
 	for (i = 0; i < 256; i++)
 		iowrite8(i, p + i);
+
 	for (i = 1024; i < (5 * 1024); i += 2)
-		iowrite16(i * 12 + 7, p + i);
+		iowrite16(v16(i), p + i);
+
 	for (i = (5 * 1024); i < (16 * 1024); i += 4)
-		iowrite32(i * 212371 + 13, p + i);
+		iowrite32(v32(i), p + i);
 }
 
 static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
+	unsigned errs[3] = { 0 };
+	pr_info(MODULE_NAME ": read test.\n");
 	mmiotrace_printk("Read test.\n");
+
 	for (i = 0; i < 256; i++)
-		ioread8(p + i);
+		if (ioread8(p + i) != i)
+			++errs[0];
+
 	for (i = 1024; i < (5 * 1024); i += 2)
-		ioread16(p + i);
+		if (ioread16(p + i) != v16(i))
+			++errs[1];
+
 	for (i = (5 * 1024); i < (16 * 1024); i += 4)
-		ioread32(p + i);
+		if (ioread32(p + i) != v32(i))
+			++errs[2];
+
+	mmiotrace_printk("Read errors: 8-bit %d, 16-bit %d, 32-bit %d.\n",
+						errs[0], errs[1], errs[2]);
 }
 
-static void do_test(void)
+static void do_read_far_test(void __iomem *p)
 {
-	void __iomem *p = ioremap_nocache(mmio_address, 0x4000);
+	pr_info(MODULE_NAME ": read far test.\n");
+	mmiotrace_printk("Read far test.\n");
+
+	ioread32(p + read_far);
+}
+
+static void do_test(unsigned long size)
+{
+	void __iomem *p = ioremap_nocache(mmio_address, size);
 	if (!p) {
 		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
 		return;
@@ -45,11 +84,15 @@ static void do_test(void)
 	mmiotrace_printk("ioremap returned %p.\n", p);
 	do_write_test(p);
 	do_read_test(p);
+	if (read_far && read_far < size - 4)
+		do_read_far_test(p);
 	iounmap(p);
 }
 
 static int __init init(void)
 {
+	unsigned long size = (read_far) ? (8 << 20) : (16 << 10);
+
 	if (mmio_address == 0) {
 		pr_err(MODULE_NAME ": you have to use the module argument "
 							"mmio_address.\n");
@@ -58,10 +101,11 @@ static int __init init(void)
 		return -ENXIO;
 	}
 
-	pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx "
-					"in PCI address space, and writing "
-					"rubbish in there.\n", mmio_address);
-	do_test();
+	pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI "
+		"address space, and writing 16 kB of rubbish in there.\n",
+		 size >> 10, mmio_address);
+	do_test(size);
+	pr_info(MODULE_NAME ": All done.\n");
 	return 0;
 }
 
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index e9f80c7..10131fb 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -78,8 +78,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 	if (cpu_has_arch_perfmon) {
 		union cpuid10_eax eax;
 		eax.full = cpuid_eax(0xa);
-		if (counter_width < eax.split.bit_width)
-			counter_width = eax.split.bit_width;
+
+		/*
+		 * For Core2 (family 6, model 15), don't reset the
+		 * counter width:
+		 */
+		if (!(eax.split.version_id == 0 &&
+			current_cpu_data.x86 == 6 &&
+				current_cpu_data.x86_model == 15)) {
+
+			if (counter_width < eax.split.bit_width)
+				counter_width = eax.split.bit_width;
+		}
 	}
 
 	/* clear all counters */
diff --git a/crypto/api.c b/crypto/api.c
index efe77df..38a2bc0 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -215,8 +215,19 @@ struct crypto_alg *crypto_larval_lookup(const char *name, u32 type, u32 mask)
 	mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD);
 	type &= mask;
 
-	alg = try_then_request_module(crypto_alg_lookup(name, type, mask),
-				      name);
+	alg = crypto_alg_lookup(name, type, mask);
+	if (!alg) {
+		char tmp[CRYPTO_MAX_ALG_NAME];
+
+		request_module(name);
+
+		if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask) &&
+		    snprintf(tmp, sizeof(tmp), "%s-all", name) < sizeof(tmp))
+			request_module(tmp);
+
+		alg = crypto_alg_lookup(name, type, mask);
+	}
+
 	if (alg)
 		return crypto_is_larval(alg) ? crypto_larval_wait(alg) : alg;
 
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 2d637e0..d9e751b 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -457,10 +457,12 @@ static int init_ixp_crypto(void)
 	if (!ctx_pool) {
 		goto err;
 	}
-	ret = qmgr_request_queue(SEND_QID, NPE_QLEN_TOTAL, 0, 0);
+	ret = qmgr_request_queue(SEND_QID, NPE_QLEN_TOTAL, 0, 0,
+				 "ixp_crypto:out", NULL);
 	if (ret)
 		goto err;
-	ret = qmgr_request_queue(RECV_QID, NPE_QLEN, 0, 0);
+	ret = qmgr_request_queue(RECV_QID, NPE_QLEN, 0, 0,
+				 "ixp_crypto:in", NULL);
 	if (ret) {
 		qmgr_release_queue(SEND_QID);
 		goto err;
diff --git a/drivers/crypto/padlock-aes.c b/drivers/crypto/padlock-aes.c
index 856b3cc..3f0fdd1 100644
--- a/drivers/crypto/padlock-aes.c
+++ b/drivers/crypto/padlock-aes.c
@@ -489,4 +489,4 @@ MODULE_DESCRIPTION("VIA PadLock AES algorithm support");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("aes");
+MODULE_ALIAS("aes-all");
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index a7fbade..a2c8e85 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -304,7 +304,7 @@ MODULE_DESCRIPTION("VIA PadLock SHA1/SHA256 algorithms support.");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Michal Ludvig");
 
-MODULE_ALIAS("sha1");
-MODULE_ALIAS("sha256");
+MODULE_ALIAS("sha1-all");
+MODULE_ALIAS("sha256-all");
 MODULE_ALIAS("sha1-padlock");
 MODULE_ALIAS("sha256-padlock");
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index ea5440d..647374a 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -1401,7 +1401,7 @@ MODULE_ALIAS("platform:iop-adma");
 
 static struct platform_driver iop_adma_driver = {
 	.probe		= iop_adma_probe,
-	.remove		= iop_adma_remove,
+	.remove		= __devexit_p(iop_adma_remove),
 	.driver		= {
 		.owner	= THIS_MODULE,
 		.name	= "iop-adma",
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index d35cbd1..5d5d5b3 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -1287,7 +1287,7 @@ mv_xor_conf_mbus_windows(struct mv_xor_shared_private *msp,
 
 static struct platform_driver mv_xor_driver = {
 	.probe		= mv_xor_probe,
-	.remove		= mv_xor_remove,
+	.remove		= __devexit_p(mv_xor_remove),
 	.driver		= {
 		.owner	= THIS_MODULE,
 		.name	= MV_XOR_NAME,
diff --git a/drivers/gpu/drm/drm_bufs.c b/drivers/gpu/drm/drm_bufs.c
index 72c667f..12715d3 100644
--- a/drivers/gpu/drm/drm_bufs.c
+++ b/drivers/gpu/drm/drm_bufs.c
@@ -420,7 +420,7 @@ int drm_rmmap_locked(struct drm_device *dev, drm_local_map_t *map)
 				dev->sigdata.lock = NULL;
 			master->lock.hw_lock = NULL;   /* SHM removed */
 			master->lock.file_priv = NULL;
-			wake_up_interruptible(&master->lock.lock_queue);
+			wake_up_interruptible_all(&master->lock.lock_queue);
 		}
 		break;
 	case _DRM_AGP:
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index 6c020fe..f52663e 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -484,6 +484,7 @@ int drm_release(struct inode *inode, struct file *filp)
 	mutex_lock(&dev->struct_mutex);
 
 	if (file_priv->is_master) {
+		struct drm_master *master = file_priv->master;
 		struct drm_file *temp;
 		list_for_each_entry(temp, &dev->filelist, lhead) {
 			if ((temp->master == file_priv->master) &&
@@ -491,6 +492,19 @@ int drm_release(struct inode *inode, struct file *filp)
 				temp->authenticated = 0;
 		}
 
+		/**
+		 * Since the master is disappearing, so is the
+		 * possibility to lock.
+		 */
+
+		if (master->lock.hw_lock) {
+			if (dev->sigdata.lock == master->lock.hw_lock)
+				dev->sigdata.lock = NULL;
+			master->lock.hw_lock = NULL;
+			master->lock.file_priv = NULL;
+			wake_up_interruptible_all(&master->lock.lock_queue);
+		}
+
 		if (file_priv->minor->master == file_priv->master) {
 			/* drop the reference held my the minor */
 			drm_master_put(&file_priv->minor->master);
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index 46e7b28..e2f70a5 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -80,6 +80,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		__set_current_state(TASK_INTERRUPTIBLE);
 		if (!master->lock.hw_lock) {
 			/* Device has been unregistered */
+			send_sig(SIGTERM, current, 0);
 			ret = -EINTR;
 			break;
 		}
@@ -93,7 +94,7 @@ int drm_lock(struct drm_device *dev, void *data, struct drm_file *file_priv)
 		/* Contention */
 		schedule();
 		if (signal_pending(current)) {
-			ret = -ERESTARTSYS;
+			ret = -EINTR;
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 46bb923..7c8b15b 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -146,14 +146,6 @@ static void drm_master_destroy(struct kref *kref)
 
 	drm_ht_remove(&master->magiclist);
 
-	if (master->lock.hw_lock) {
-		if (dev->sigdata.lock == master->lock.hw_lock)
-			dev->sigdata.lock = NULL;
-		master->lock.hw_lock = NULL;
-		master->lock.file_priv = NULL;
-		wake_up_interruptible(&master->lock.lock_queue);
-	}
-
 	drm_free(master, sizeof(*master), DRM_MEM_DRIVER);
 }
 
@@ -176,7 +168,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data,
 	    file_priv->minor->master != file_priv->master) {
 		mutex_lock(&dev->struct_mutex);
 		file_priv->minor->master = drm_master_get(file_priv->master);
-		mutex_lock(&dev->struct_mutex);
+		mutex_unlock(&dev->struct_mutex);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 548ff2c..87b6b60 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -383,12 +383,13 @@ int i915_irq_emit(struct drm_device *dev, void *data,
 	drm_i915_irq_emit_t *emit = data;
 	int result;
 
-	RING_LOCK_TEST_WITH_RETURN(dev, file_priv);
-
 	if (!dev_priv) {
 		DRM_ERROR("called with no initialization\n");
 		return -EINVAL;
 	}
+
+	RING_LOCK_TEST_WITH_RETURN(dev, file_priv);
+
 	mutex_lock(&dev->struct_mutex);
 	result = i915_emit_irq(dev);
 	mutex_unlock(&dev->struct_mutex);
diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c
index eeda276f..7f186bb 100644
--- a/drivers/i2c/busses/i2c-mv64xxx.c
+++ b/drivers/i2c/busses/i2c-mv64xxx.c
@@ -482,7 +482,7 @@ mv64xxx_i2c_map_regs(struct platform_device *pd,
 	return 0;
 }
 
-static void __devexit
+static void
 mv64xxx_i2c_unmap_regs(struct mv64xxx_i2c_data *drv_data)
 {
 	if (drv_data->reg_base) {
@@ -577,7 +577,7 @@ mv64xxx_i2c_remove(struct platform_device *dev)
 
 static struct platform_driver mv64xxx_i2c_driver = {
 	.probe	= mv64xxx_i2c_probe,
-	.remove	= mv64xxx_i2c_remove,
+	.remove	= __devexit_p(mv64xxx_i2c_remove),
 	.driver	= {
 		.owner	= THIS_MODULE,
 		.name	= MV64XXX_I2C_CTLR_NAME,
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index c3c8b9b..45470f1 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -839,7 +839,7 @@ static void atkbd_disconnect(struct serio *serio)
  */
 static void atkbd_dell_laptop_keymap_fixup(struct atkbd *atkbd)
 {
-	const unsigned int forced_release_keys[] = {
+	static const unsigned int forced_release_keys[] = {
 		0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8f, 0x93,
 	};
 	int i;
@@ -856,7 +856,7 @@ static void atkbd_dell_laptop_keymap_fixup(struct atkbd *atkbd)
  */
 static void atkbd_hp_keymap_fixup(struct atkbd *atkbd)
 {
-	const unsigned int forced_release_keys[] = {
+	static const unsigned int forced_release_keys[] = {
 		0x94,
 	};
 	int i;
diff --git a/drivers/input/keyboard/bf54x-keys.c b/drivers/input/keyboard/bf54x-keys.c
index 1928401..ee855c5 100644
--- a/drivers/input/keyboard/bf54x-keys.c
+++ b/drivers/input/keyboard/bf54x-keys.c
@@ -209,8 +209,8 @@ static int __devinit bfin_kpad_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	if (!pdata->debounce_time || !pdata->debounce_time > MAX_MULT ||
-	    !pdata->coldrive_time || !pdata->coldrive_time > MAX_MULT) {
+	if (!pdata->debounce_time || pdata->debounce_time > MAX_MULT ||
+	    !pdata->coldrive_time || pdata->coldrive_time > MAX_MULT) {
 		printk(KERN_ERR DRV_NAME
 			": Invalid Debounce/Columdrive Time from pdata\n");
 		bfin_write_KPAD_MSEL(0xFF0);	/* Default MSEL	*/
diff --git a/drivers/input/keyboard/corgikbd.c b/drivers/input/keyboard/corgikbd.c
index c8ed065..abb04c8 100644
--- a/drivers/input/keyboard/corgikbd.c
+++ b/drivers/input/keyboard/corgikbd.c
@@ -288,7 +288,7 @@ static int corgikbd_resume(struct platform_device *dev)
 #define corgikbd_resume		NULL
 #endif
 
-static int __init corgikbd_probe(struct platform_device *pdev)
+static int __devinit corgikbd_probe(struct platform_device *pdev)
 {
 	struct corgikbd *corgikbd;
 	struct input_dev *input_dev;
@@ -368,7 +368,7 @@ static int __init corgikbd_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int corgikbd_remove(struct platform_device *pdev)
+static int __devexit corgikbd_remove(struct platform_device *pdev)
 {
 	int i;
 	struct corgikbd *corgikbd = platform_get_drvdata(pdev);
@@ -388,7 +388,7 @@ static int corgikbd_remove(struct platform_device *pdev)
 
 static struct platform_driver corgikbd_driver = {
 	.probe		= corgikbd_probe,
-	.remove		= corgikbd_remove,
+	.remove		= __devexit_p(corgikbd_remove),
 	.suspend	= corgikbd_suspend,
 	.resume		= corgikbd_resume,
 	.driver		= {
@@ -397,7 +397,7 @@ static struct platform_driver corgikbd_driver = {
 	},
 };
 
-static int __devinit corgikbd_init(void)
+static int __init corgikbd_init(void)
 {
 	return platform_driver_register(&corgikbd_driver);
 }
diff --git a/drivers/input/keyboard/omap-keypad.c b/drivers/input/keyboard/omap-keypad.c
index 3f3d119..058fa8b 100644
--- a/drivers/input/keyboard/omap-keypad.c
+++ b/drivers/input/keyboard/omap-keypad.c
@@ -279,7 +279,7 @@ static int omap_kp_resume(struct platform_device *dev)
 #define omap_kp_resume	NULL
 #endif
 
-static int __init omap_kp_probe(struct platform_device *pdev)
+static int __devinit omap_kp_probe(struct platform_device *pdev)
 {
 	struct omap_kp *omap_kp;
 	struct input_dev *input_dev;
@@ -422,7 +422,7 @@ err1:
 	return -EINVAL;
 }
 
-static int omap_kp_remove(struct platform_device *pdev)
+static int __devexit omap_kp_remove(struct platform_device *pdev)
 {
 	struct omap_kp *omap_kp = platform_get_drvdata(pdev);
 
@@ -454,7 +454,7 @@ static int omap_kp_remove(struct platform_device *pdev)
 
 static struct platform_driver omap_kp_driver = {
 	.probe		= omap_kp_probe,
-	.remove		= omap_kp_remove,
+	.remove		= __devexit_p(omap_kp_remove),
 	.suspend	= omap_kp_suspend,
 	.resume		= omap_kp_resume,
 	.driver		= {
@@ -463,7 +463,7 @@ static struct platform_driver omap_kp_driver = {
 	},
 };
 
-static int __devinit omap_kp_init(void)
+static int __init omap_kp_init(void)
 {
 	printk(KERN_INFO "OMAP Keypad Driver\n");
 	return platform_driver_register(&omap_kp_driver);
diff --git a/drivers/input/keyboard/spitzkbd.c b/drivers/input/keyboard/spitzkbd.c
index c48b76a..9d1781a 100644
--- a/drivers/input/keyboard/spitzkbd.c
+++ b/drivers/input/keyboard/spitzkbd.c
@@ -343,7 +343,7 @@ static int spitzkbd_resume(struct platform_device *dev)
 #define spitzkbd_resume		NULL
 #endif
 
-static int __init spitzkbd_probe(struct platform_device *dev)
+static int __devinit spitzkbd_probe(struct platform_device *dev)
 {
 	struct spitzkbd *spitzkbd;
 	struct input_dev *input_dev;
@@ -444,7 +444,7 @@ static int __init spitzkbd_probe(struct platform_device *dev)
 	return err;
 }
 
-static int spitzkbd_remove(struct platform_device *dev)
+static int __devexit spitzkbd_remove(struct platform_device *dev)
 {
 	int i;
 	struct spitzkbd *spitzkbd = platform_get_drvdata(dev);
@@ -470,7 +470,7 @@ static int spitzkbd_remove(struct platform_device *dev)
 
 static struct platform_driver spitzkbd_driver = {
 	.probe		= spitzkbd_probe,
-	.remove		= spitzkbd_remove,
+	.remove		= __devexit_p(spitzkbd_remove),
 	.suspend	= spitzkbd_suspend,
 	.resume		= spitzkbd_resume,
 	.driver		= {
@@ -479,7 +479,7 @@ static struct platform_driver spitzkbd_driver = {
 	},
 };
 
-static int __devinit spitzkbd_init(void)
+static int __init spitzkbd_init(void)
 {
 	return platform_driver_register(&spitzkbd_driver);
 }
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index 093c8c1..9705f3a 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -70,7 +70,7 @@ config MOUSE_PS2_SYNAPTICS
 config MOUSE_PS2_LIFEBOOK
 	bool "Fujitsu Lifebook PS/2 mouse protocol extension" if EMBEDDED
 	default y
-	depends on MOUSE_PS2
+	depends on MOUSE_PS2 && X86
 	help
 	  Say Y here if you have a Fujitsu B-series Lifebook PS/2
 	  TouchScreen connected to your system.
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index b9a25d5..6ab0eb1a 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -542,7 +542,7 @@ int elantech_detect(struct psmouse *psmouse, int set_properties)
 	    ps2_command(ps2dev,  NULL, PSMOUSE_CMD_SETSCALE11) ||
 	    ps2_command(ps2dev,  NULL, PSMOUSE_CMD_SETSCALE11) ||
 	    ps2_command(ps2dev, param, PSMOUSE_CMD_GETINFO)) {
-		pr_err("elantech.c: sending Elantech magic knock failed.\n");
+		pr_debug("elantech.c: sending Elantech magic knock failed.\n");
 		return -1;
 	}
 
@@ -551,8 +551,27 @@ int elantech_detect(struct psmouse *psmouse, int set_properties)
 	 * set of magic numbers
 	 */
 	if (param[0] != 0x3c || param[1] != 0x03 || param[2] != 0xc8) {
-		pr_info("elantech.c: unexpected magic knock result 0x%02x, 0x%02x, 0x%02x.\n",
-			param[0], param[1], param[2]);
+		pr_debug("elantech.c: "
+			 "unexpected magic knock result 0x%02x, 0x%02x, 0x%02x.\n",
+			 param[0], param[1], param[2]);
+		return -1;
+	}
+
+	/*
+	 * Query touchpad's firmware version and see if it reports known
+	 * value to avoid mis-detection. Logitech mice are known to respond
+	 * to Elantech magic knock and there might be more.
+	 */
+	if (synaptics_send_cmd(psmouse, ETP_FW_VERSION_QUERY, param)) {
+		pr_debug("elantech.c: failed to query firmware version.\n");
+		return -1;
+	}
+
+	pr_debug("elantech.c: Elantech version query result 0x%02x, 0x%02x, 0x%02x.\n",
+		 param[0], param[1], param[2]);
+
+	if (param[0] == 0 || param[1] != 0) {
+		pr_debug("elantech.c: Probably not a real Elantech touchpad. Aborting.\n");
 		return -1;
 	}
 
@@ -600,8 +619,7 @@ int elantech_init(struct psmouse *psmouse)
 	int i, error;
 	unsigned char param[3];
 
-	etd = kzalloc(sizeof(struct elantech_data), GFP_KERNEL);
-	psmouse->private = etd;
+	psmouse->private = etd = kzalloc(sizeof(struct elantech_data), GFP_KERNEL);
 	if (!etd)
 		return -1;
 
@@ -610,14 +628,12 @@ int elantech_init(struct psmouse *psmouse)
 		etd->parity[i] = etd->parity[i & (i - 1)] ^ 1;
 
 	/*
-	 * Find out what version hardware this is
+	 * Do the version query again so we can store the result
 	 */
 	if (synaptics_send_cmd(psmouse, ETP_FW_VERSION_QUERY, param)) {
 		pr_err("elantech.c: failed to query firmware version.\n");
 		goto init_fail;
 	}
-	pr_info("elantech.c: Elantech version query result 0x%02x, 0x%02x, 0x%02x.\n",
-		param[0], param[1], param[2]);
 	etd->fw_version_maj = param[0];
 	etd->fw_version_min = param[2];
 
diff --git a/drivers/input/mouse/pxa930_trkball.c b/drivers/input/mouse/pxa930_trkball.c
index d297acc..1e827ad 100644
--- a/drivers/input/mouse/pxa930_trkball.c
+++ b/drivers/input/mouse/pxa930_trkball.c
@@ -83,7 +83,7 @@ static int write_tbcr(struct pxa930_trkball *trkball, int v)
 
 	__raw_writel(v, trkball->mmio_base + TBCR);
 
-	while (i--) {
+	while (--i) {
 		if (__raw_readl(trkball->mmio_base + TBCR) == v)
 			break;
 		msleep(1);
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 865fc69..f3e4f7b 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -182,11 +182,6 @@ static int synaptics_identify(struct psmouse *psmouse)
 
 static int synaptics_query_hardware(struct psmouse *psmouse)
 {
-	int retries = 0;
-
-	while ((retries++ < 3) && psmouse_reset(psmouse))
-		/* empty */;
-
 	if (synaptics_identify(psmouse))
 		return -1;
 	if (synaptics_model_id(psmouse))
@@ -582,6 +577,8 @@ static int synaptics_reconnect(struct psmouse *psmouse)
 	struct synaptics_data *priv = psmouse->private;
 	struct synaptics_data old_priv = *priv;
 
+	psmouse_reset(psmouse);
+
 	if (synaptics_detect(psmouse, 0))
 		return -1;
 
@@ -640,6 +637,8 @@ int synaptics_init(struct psmouse *psmouse)
 	if (!priv)
 		return -1;
 
+	psmouse_reset(psmouse);
+
 	if (synaptics_query_hardware(psmouse)) {
 		printk(KERN_ERR "Unable to query Synaptics hardware.\n");
 		goto init_fail;
diff --git a/drivers/input/serio/ambakmi.c b/drivers/input/serio/ambakmi.c
index b10ffae..e29cdc1 100644
--- a/drivers/input/serio/ambakmi.c
+++ b/drivers/input/serio/ambakmi.c
@@ -57,7 +57,7 @@ static int amba_kmi_write(struct serio *io, unsigned char val)
 	struct amba_kmi_port *kmi = io->port_data;
 	unsigned int timeleft = 10000; /* timeout in 100ms */
 
-	while ((readb(KMISTAT) & KMISTAT_TXEMPTY) == 0 && timeleft--)
+	while ((readb(KMISTAT) & KMISTAT_TXEMPTY) == 0 && --timeleft)
 		udelay(10);
 
 	if (timeleft)
@@ -129,8 +129,8 @@ static int amba_kmi_probe(struct amba_device *dev, void *id)
 	io->write	= amba_kmi_write;
 	io->open	= amba_kmi_open;
 	io->close	= amba_kmi_close;
-	strlcpy(io->name, dev->dev.bus_id, sizeof(io->name));
-	strlcpy(io->phys, dev->dev.bus_id, sizeof(io->phys));
+	strlcpy(io->name, dev_name(&dev->dev), sizeof(io->name));
+	strlcpy(io->phys, dev_name(&dev->dev), sizeof(io->phys));
 	io->port_data	= kmi;
 	io->dev.parent	= &dev->dev;
 
diff --git a/drivers/input/serio/gscps2.c b/drivers/input/serio/gscps2.c
index adc3bd6..bd0f92d 100644
--- a/drivers/input/serio/gscps2.c
+++ b/drivers/input/serio/gscps2.c
@@ -359,7 +359,7 @@ static int __init gscps2_probe(struct parisc_device *dev)
 
 	snprintf(serio->name, sizeof(serio->name), "GSC PS/2 %s",
 		 (ps2port->id == GSC_ID_KEYBOARD) ? "keyboard" : "mouse");
-	strlcpy(serio->phys, dev->dev.bus_id, sizeof(serio->phys));
+	strlcpy(serio->phys, dev_name(&dev->dev), sizeof(serio->phys));
 	serio->id.type		= SERIO_8042;
 	serio->write		= gscps2_write;
 	serio->open		= gscps2_open;
diff --git a/drivers/input/serio/sa1111ps2.c b/drivers/input/serio/sa1111ps2.c
index 2ad8878..57953c0 100644
--- a/drivers/input/serio/sa1111ps2.c
+++ b/drivers/input/serio/sa1111ps2.c
@@ -246,8 +246,8 @@ static int __devinit ps2_probe(struct sa1111_dev *dev)
 	serio->write		= ps2_write;
 	serio->open		= ps2_open;
 	serio->close		= ps2_close;
-	strlcpy(serio->name, dev->dev.bus_id, sizeof(serio->name));
-	strlcpy(serio->phys, dev->dev.bus_id, sizeof(serio->phys));
+	strlcpy(serio->name, dev_name(&dev->dev), sizeof(serio->name));
+	strlcpy(serio->phys, dev_name(&dev->dev), sizeof(serio->phys));
 	serio->port_data	= ps2if;
 	serio->dev.parent	= &dev->dev;
 	ps2if->io		= serio;
diff --git a/drivers/input/touchscreen/atmel_tsadcc.c b/drivers/input/touchscreen/atmel_tsadcc.c
index a89a6a8..055969e 100644
--- a/drivers/input/touchscreen/atmel_tsadcc.c
+++ b/drivers/input/touchscreen/atmel_tsadcc.c
@@ -236,7 +236,7 @@ static int __devinit atmel_tsadcc_probe(struct platform_device *pdev)
 	ts_dev->bufferedmeasure = 0;
 
 	snprintf(ts_dev->phys, sizeof(ts_dev->phys),
-		 "%s/input0", pdev->dev.bus_id);
+		 "%s/input0", dev_name(&pdev->dev));
 
 	input_dev->name = "atmel touch screen controller";
 	input_dev->phys = ts_dev->phys;
diff --git a/drivers/input/touchscreen/corgi_ts.c b/drivers/input/touchscreen/corgi_ts.c
index 65202c9..3fb51b5 100644
--- a/drivers/input/touchscreen/corgi_ts.c
+++ b/drivers/input/touchscreen/corgi_ts.c
@@ -268,7 +268,7 @@ static int corgits_resume(struct platform_device *dev)
 #define corgits_resume		NULL
 #endif
 
-static int __init corgits_probe(struct platform_device *pdev)
+static int __devinit corgits_probe(struct platform_device *pdev)
 {
 	struct corgi_ts *corgi_ts;
 	struct input_dev *input_dev;
@@ -343,7 +343,7 @@ static int __init corgits_probe(struct platform_device *pdev)
 	return err;
 }
 
-static int corgits_remove(struct platform_device *pdev)
+static int __devexit corgits_remove(struct platform_device *pdev)
 {
 	struct corgi_ts *corgi_ts = platform_get_drvdata(pdev);
 
@@ -352,12 +352,13 @@ static int corgits_remove(struct platform_device *pdev)
 	corgi_ts->machinfo->put_hsync();
 	input_unregister_device(corgi_ts->input);
 	kfree(corgi_ts);
+
 	return 0;
 }
 
 static struct platform_driver corgits_driver = {
 	.probe		= corgits_probe,
-	.remove		= corgits_remove,
+	.remove		= __devexit_p(corgits_remove),
 	.suspend	= corgits_suspend,
 	.resume		= corgits_resume,
 	.driver		= {
@@ -366,7 +367,7 @@ static struct platform_driver corgits_driver = {
 	},
 };
 
-static int __devinit corgits_init(void)
+static int __init corgits_init(void)
 {
 	return platform_driver_register(&corgits_driver);
 }
diff --git a/drivers/input/touchscreen/tsc2007.c b/drivers/input/touchscreen/tsc2007.c
index b75dc29..4ab0702 100644
--- a/drivers/input/touchscreen/tsc2007.c
+++ b/drivers/input/touchscreen/tsc2007.c
@@ -289,7 +289,8 @@ static int tsc2007_probe(struct i2c_client *client,
 
 	pdata->init_platform_hw();
 
-	snprintf(ts->phys, sizeof(ts->phys), "%s/input0", client->dev.bus_id);
+	snprintf(ts->phys, sizeof(ts->phys),
+		 "%s/input0", dev_name(&client->dev));
 
 	input_dev->name = "TSC2007 Touchscreen";
 	input_dev->phys = ts->phys;
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index 5080b26..fb7cb9b 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -60,6 +60,10 @@ static int swap_xy;
 module_param(swap_xy, bool, 0644);
 MODULE_PARM_DESC(swap_xy, "If set X and Y axes are swapped.");
 
+static int hwcalib_xy;
+module_param(hwcalib_xy, bool, 0644);
+MODULE_PARM_DESC(hwcalib_xy, "If set hw-calibrated X/Y are used if available");
+
 /* device specifc data/functions */
 struct usbtouch_usb;
 struct usbtouch_device_info {
@@ -118,6 +122,7 @@ enum {
 
 #define USB_DEVICE_HID_CLASS(vend, prod) \
 	.match_flags = USB_DEVICE_ID_MATCH_INT_CLASS \
+		| USB_DEVICE_ID_MATCH_INT_PROTOCOL \
 		| USB_DEVICE_ID_MATCH_DEVICE, \
 	.idVendor = (vend), \
 	.idProduct = (prod), \
@@ -260,8 +265,13 @@ static int panjit_read_data(struct usbtouch_usb *dev, unsigned char *pkt)
 
 static int mtouch_read_data(struct usbtouch_usb *dev, unsigned char *pkt)
 {
-	dev->x = (pkt[8] << 8) | pkt[7];
-	dev->y = (pkt[10] << 8) | pkt[9];
+	if (hwcalib_xy) {
+		dev->x = (pkt[4] << 8) | pkt[3];
+		dev->y = 0xffff - ((pkt[6] << 8) | pkt[5]);
+	} else {
+		dev->x = (pkt[8] << 8) | pkt[7];
+		dev->y = (pkt[10] << 8) | pkt[9];
+	}
 	dev->touch = (pkt[2] & 0x40) ? 1 : 0;
 
 	return 1;
@@ -294,6 +304,12 @@ static int mtouch_init(struct usbtouch_usb *usbtouch)
 			return ret;
 	}
 
+	/* Default min/max xy are the raw values, override if using hw-calib */
+	if (hwcalib_xy) {
+		input_set_abs_params(usbtouch->input, ABS_X, 0, 0xffff, 0, 0);
+		input_set_abs_params(usbtouch->input, ABS_Y, 0, 0xffff, 0, 0);
+	}
+
 	return 0;
 }
 #endif
diff --git a/drivers/media/video/uvc/uvc_status.c b/drivers/media/video/uvc/uvc_status.c
index c1e4ae2..c705f24 100644
--- a/drivers/media/video/uvc/uvc_status.c
+++ b/drivers/media/video/uvc/uvc_status.c
@@ -46,8 +46,8 @@ static int uvc_input_init(struct uvc_device *dev)
 	usb_to_input_id(udev, &input->id);
 	input->dev.parent = &dev->intf->dev;
 
-	set_bit(EV_KEY, input->evbit);
-	set_bit(BTN_0, input->keybit);
+	__set_bit(EV_KEY, input->evbit);
+	__set_bit(KEY_CAMERA, input->keybit);
 
 	if ((ret = input_register_device(input)) < 0)
 		goto error;
@@ -70,8 +70,10 @@ static void uvc_input_cleanup(struct uvc_device *dev)
 static void uvc_input_report_key(struct uvc_device *dev, unsigned int code,
 	int value)
 {
-	if (dev->input)
+	if (dev->input) {
 		input_report_key(dev->input, code, value);
+		input_sync(dev->input);
+	}
 }
 
 #else
@@ -96,7 +98,7 @@ static void uvc_event_streaming(struct uvc_device *dev, __u8 *data, int len)
 			return;
 		uvc_trace(UVC_TRACE_STATUS, "Button (intf %u) %s len %d\n",
 			data[1], data[3] ? "pressed" : "released", len);
-		uvc_input_report_key(dev, BTN_0, data[3]);
+		uvc_input_report_key(dev, KEY_CAMERA, data[3]);
 	} else {
 		uvc_trace(UVC_TRACE_STATUS, "Stream %u error event %02x %02x "
 			"len %d.\n", data[1], data[2], data[3], len);
diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index 96ac883..ea3aafb 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -91,9 +91,9 @@ MODULE_PARM_DESC(mpt_msi_enable_fc, " Enable MSI Support for FC \
 		controllers (default=0)");
 
 static int mpt_msi_enable_sas;
-module_param(mpt_msi_enable_sas, int, 1);
+module_param(mpt_msi_enable_sas, int, 0);
 MODULE_PARM_DESC(mpt_msi_enable_sas, " Enable MSI Support for SAS \
-		controllers (default=1)");
+		controllers (default=0)");
 
 
 static int mpt_channel_mapping;
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c
index 8cff5f5..406da9a 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci.c
@@ -107,6 +107,7 @@ static const struct sdhci_pci_fixes sdhci_ene_714 = {
 
 static const struct sdhci_pci_fixes sdhci_cafe = {
 	.quirks		= SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER |
+			  SDHCI_QUIRK_NO_BUSY_IRQ |
 			  SDHCI_QUIRK_BROKEN_TIMEOUT_VAL,
 };
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index f52f305..accb592 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1291,8 +1291,11 @@ static void sdhci_cmd_irq(struct sdhci_host *host, u32 intmask)
 		if (host->cmd->data)
 			DBG("Cannot wait for busy signal when also "
 				"doing a data transfer");
-		else
+		else if (!(host->quirks & SDHCI_QUIRK_NO_BUSY_IRQ))
 			return;
+
+		/* The controller does not support the end-of-busy IRQ,
+		 * fall through and take the SDHCI_INT_RESPONSE */
 	}
 
 	if (intmask & SDHCI_INT_RESPONSE)
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index ebb8365..43c37c6 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -208,6 +208,8 @@ struct sdhci_host {
 #define SDHCI_QUIRK_BROKEN_TIMEOUT_VAL			(1<<12)
 /* Controller has an issue with buffer bits for small transfers */
 #define SDHCI_QUIRK_BROKEN_SMALL_PIO			(1<<13)
+/* Controller does not provide transfer-complete interrupt when not busy */
+#define SDHCI_QUIRK_NO_BUSY_IRQ				(1<<14)
 
 	int			irq;		/* Device IRQ */
 	void __iomem *		ioaddr;		/* Mapped address */
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index 917cf8d..c2dfd3e 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -149,7 +149,7 @@ static int __devexit orion_nand_remove(struct platform_device *pdev)
 
 static struct platform_driver orion_nand_driver = {
 	.probe		= orion_nand_probe,
-	.remove		= orion_nand_remove,
+	.remove		= __devexit_p(orion_nand_remove),
 	.driver		= {
 		.name	= "orion_nand",
 		.owner	= THIS_MODULE,
diff --git a/drivers/net/arm/Makefile b/drivers/net/arm/Makefile
index c69c0cd..811a3cc 100644
--- a/drivers/net/arm/Makefile
+++ b/drivers/net/arm/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-$(CONFIG_ARM_AM79C961A)	+= am79c961a.o
-obj-$(CONFIG_ARM_ETHERH)	+= etherh.o ../8390.o
+obj-$(CONFIG_ARM_ETHERH)	+= etherh.o
 obj-$(CONFIG_ARM_ETHER3)	+= ether3.o
 obj-$(CONFIG_ARM_ETHER1)	+= ether1.o
 obj-$(CONFIG_ARM_AT91_ETHER)	+= at91_ether.o
diff --git a/drivers/net/arm/etherh.c b/drivers/net/arm/etherh.c
index 54b52e5..f52f668c 100644
--- a/drivers/net/arm/etherh.c
+++ b/drivers/net/arm/etherh.c
@@ -641,15 +641,15 @@ static const struct net_device_ops etherh_netdev_ops = {
 	.ndo_open		= etherh_open,
 	.ndo_stop		= etherh_close,
 	.ndo_set_config		= etherh_set_config,
-	.ndo_start_xmit		= ei_start_xmit,
-	.ndo_tx_timeout		= ei_tx_timeout,
-	.ndo_get_stats		= ei_get_stats,
-	.ndo_set_multicast_list = ei_set_multicast_list,
+	.ndo_start_xmit		= __ei_start_xmit,
+	.ndo_tx_timeout		= __ei_tx_timeout,
+	.ndo_get_stats		= __ei_get_stats,
+	.ndo_set_multicast_list = __ei_set_multicast_list,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_change_mtu		= eth_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= ei_poll,
+	.ndo_poll_controller	= __ei_poll,
 #endif
 };
 
diff --git a/drivers/scsi/cxgb3i/cxgb3i.h b/drivers/scsi/cxgb3i/cxgb3i.h
index fde6e4c..a7cf550 100644
--- a/drivers/scsi/cxgb3i/cxgb3i.h
+++ b/drivers/scsi/cxgb3i/cxgb3i.h
@@ -20,6 +20,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/scatterlist.h>
+#include <linux/skbuff.h>
 #include <scsi/libiscsi_tcp.h>
 
 /* from cxgb3 LLD */
@@ -113,6 +114,26 @@ struct cxgb3i_endpoint {
 	struct cxgb3i_conn *cconn;
 };
 
+/**
+ * struct cxgb3i_task_data - private iscsi task data
+ *
+ * @nr_frags:	# of coalesced page frags (from scsi sgl)
+ * @frags:	coalesced page frags (from scsi sgl)
+ * @skb:	tx pdu skb
+ * @offset:	data offset for the next pdu
+ * @count:	max. possible pdu payload
+ * @sgoffset:	offset to the first sg entry for a given offset
+ */
+#define MAX_PDU_FRAGS	((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512)
+struct cxgb3i_task_data {
+	unsigned short nr_frags;
+	skb_frag_t frags[MAX_PDU_FRAGS];
+	struct sk_buff *skb;
+	unsigned int offset;
+	unsigned int count;
+	unsigned int sgoffset;
+};
+
 int cxgb3i_iscsi_init(void);
 void cxgb3i_iscsi_cleanup(void);
 
diff --git a/drivers/scsi/cxgb3i/cxgb3i_ddp.c b/drivers/scsi/cxgb3i/cxgb3i_ddp.c
index 08f3a09..a83d36e 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_ddp.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_ddp.c
@@ -639,10 +639,11 @@ static int ddp_init(struct t3cdev *tdev)
 	write_unlock(&cxgb3i_ddp_rwlock);
 
 	ddp_log_info("nppods %u (0x%x ~ 0x%x), bits %u, mask 0x%x,0x%x "
-			"pkt %u,%u.\n",
+			"pkt %u/%u, %u/%u.\n",
 			ppmax, ddp->llimit, ddp->ulimit, ddp->idx_bits,
 			ddp->idx_mask, ddp->rsvd_tag_mask,
-			ddp->max_txsz, ddp->max_rxsz);
+			ddp->max_txsz, uinfo.max_txsz,
+			ddp->max_rxsz, uinfo.max_rxsz);
 	return 0;
 
 free_ddp_map:
@@ -654,8 +655,8 @@ free_ddp_map:
  * cxgb3i_adapter_ddp_init - initialize the adapter's ddp resource
  * @tdev: t3cdev adapter
  * @tformat: tag format
- * @txsz: max tx pkt size, filled in by this func.
- * @rxsz: max rx pkt size, filled in by this func.
+ * @txsz: max tx pdu payload size, filled in by this func.
+ * @rxsz: max rx pdu payload size, filled in by this func.
  * initialize the ddp pagepod manager for a given adapter if needed and
  * setup the tag format for a given iscsi entity
  */
@@ -685,10 +686,12 @@ int cxgb3i_adapter_ddp_init(struct t3cdev *tdev,
 		      tformat->sw_bits, tformat->rsvd_bits,
 		      tformat->rsvd_shift, tformat->rsvd_mask);
 
-	*txsz = ddp->max_txsz;
-	*rxsz = ddp->max_rxsz;
-	ddp_log_info("ddp max pkt size: %u, %u.\n",
-		     ddp->max_txsz, ddp->max_rxsz);
+	*txsz = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+			ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN);
+	*rxsz = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+			ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN);
+	ddp_log_info("max payload size: %u/%u, %u/%u.\n",
+		     *txsz, ddp->max_txsz, *rxsz, ddp->max_rxsz);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(cxgb3i_adapter_ddp_init);
diff --git a/drivers/scsi/cxgb3i/cxgb3i_ddp.h b/drivers/scsi/cxgb3i/cxgb3i_ddp.h
index 5c7c4d9..3faae78 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_ddp.h
+++ b/drivers/scsi/cxgb3i/cxgb3i_ddp.h
@@ -13,6 +13,8 @@
 #ifndef __CXGB3I_ULP2_DDP_H__
 #define __CXGB3I_ULP2_DDP_H__
 
+#include <linux/vmalloc.h>
+
 /**
  * struct cxgb3i_tag_format - cxgb3i ulp tag format for an iscsi entity
  *
@@ -85,8 +87,9 @@ struct cxgb3i_ddp_info {
 	struct sk_buff **gl_skb;
 };
 
+#define ISCSI_PDU_NONPAYLOAD_LEN	312 /* bhs(48) + ahs(256) + digest(8) */
 #define ULP2_MAX_PKT_SIZE	16224
-#define ULP2_MAX_PDU_PAYLOAD	(ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_MAX)
+#define ULP2_MAX_PDU_PAYLOAD	(ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN)
 #define PPOD_PAGES_MAX		4
 #define PPOD_PAGES_SHIFT	2	/* 4 pages per pod */
 
diff --git a/drivers/scsi/cxgb3i/cxgb3i_init.c b/drivers/scsi/cxgb3i/cxgb3i_init.c
index 091ecb4..1ce9f24 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_init.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_init.c
@@ -12,8 +12,8 @@
 #include "cxgb3i.h"
 
 #define DRV_MODULE_NAME         "cxgb3i"
-#define DRV_MODULE_VERSION	"1.0.0"
-#define DRV_MODULE_RELDATE	"Jun. 1, 2008"
+#define DRV_MODULE_VERSION	"1.0.1"
+#define DRV_MODULE_RELDATE	"Jan. 2009"
 
 static char version[] =
 	"Chelsio S3xx iSCSI Driver " DRV_MODULE_NAME
diff --git a/drivers/scsi/cxgb3i/cxgb3i_iscsi.c b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
index d83464b..fa2a44f 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_iscsi.c
@@ -364,7 +364,8 @@ cxgb3i_session_create(struct iscsi_endpoint *ep, u16 cmds_max, u16 qdepth,
 
 	cls_session = iscsi_session_setup(&cxgb3i_iscsi_transport, shost,
 					  cmds_max,
-					  sizeof(struct iscsi_tcp_task),
+					  sizeof(struct iscsi_tcp_task) +
+					  sizeof(struct cxgb3i_task_data),
 					  initial_cmdsn, ISCSI_MAX_TARGET);
 	if (!cls_session)
 		return NULL;
@@ -402,17 +403,15 @@ static inline int cxgb3i_conn_max_xmit_dlength(struct iscsi_conn *conn)
 {
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
 	struct cxgb3i_conn *cconn = tcp_conn->dd_data;
-	unsigned int max = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
-				 cconn->hba->snic->tx_max_size -
-				 ISCSI_PDU_NONPAYLOAD_MAX);
+	unsigned int max = max(512 * MAX_SKB_FRAGS, SKB_TX_HEADROOM);
 
+	max = min(cconn->hba->snic->tx_max_size, max);
 	if (conn->max_xmit_dlength)
-		conn->max_xmit_dlength = min_t(unsigned int,
-						conn->max_xmit_dlength, max);
+		conn->max_xmit_dlength = min(conn->max_xmit_dlength, max);
 	else
 		conn->max_xmit_dlength = max;
 	align_pdu_size(conn->max_xmit_dlength);
-	cxgb3i_log_info("conn 0x%p, max xmit %u.\n",
+	cxgb3i_api_debug("conn 0x%p, max xmit %u.\n",
 			 conn, conn->max_xmit_dlength);
 	return 0;
 }
@@ -427,9 +426,7 @@ static inline int cxgb3i_conn_max_recv_dlength(struct iscsi_conn *conn)
 {
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
 	struct cxgb3i_conn *cconn = tcp_conn->dd_data;
-	unsigned int max = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
-				 cconn->hba->snic->rx_max_size -
-				 ISCSI_PDU_NONPAYLOAD_MAX);
+	unsigned int max = cconn->hba->snic->rx_max_size;
 
 	align_pdu_size(max);
 	if (conn->max_recv_dlength) {
@@ -439,8 +436,7 @@ static inline int cxgb3i_conn_max_recv_dlength(struct iscsi_conn *conn)
 					 conn->max_recv_dlength, max);
 			return -EINVAL;
 		}
-		conn->max_recv_dlength = min_t(unsigned int,
-						conn->max_recv_dlength, max);
+		conn->max_recv_dlength = min(conn->max_recv_dlength, max);
 		align_pdu_size(conn->max_recv_dlength);
 	} else
 		conn->max_recv_dlength = max;
@@ -844,7 +840,7 @@ static struct scsi_host_template cxgb3i_host_template = {
 	.proc_name		= "cxgb3i",
 	.queuecommand		= iscsi_queuecommand,
 	.change_queue_depth	= iscsi_change_queue_depth,
-	.can_queue		= 128 * (ISCSI_DEF_XMIT_CMDS_MAX - 1),
+	.can_queue		= CXGB3I_SCSI_QDEPTH_DFLT - 1,
 	.sg_tablesize		= SG_ALL,
 	.max_sectors		= 0xFFFF,
 	.cmd_per_lun		= ISCSI_DEF_CMD_PER_LUN,
diff --git a/drivers/scsi/cxgb3i/cxgb3i_offload.c b/drivers/scsi/cxgb3i/cxgb3i_offload.c
index a865f1f..de3b3b6 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_offload.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_offload.c
@@ -23,19 +23,19 @@
 #include "cxgb3i_ddp.h"
 
 #ifdef __DEBUG_C3CN_CONN__
-#define c3cn_conn_debug         cxgb3i_log_info
+#define c3cn_conn_debug		cxgb3i_log_debug
 #else
 #define c3cn_conn_debug(fmt...)
 #endif
 
 #ifdef __DEBUG_C3CN_TX__
-#define c3cn_tx_debug         cxgb3i_log_debug
+#define c3cn_tx_debug		cxgb3i_log_debug
 #else
 #define c3cn_tx_debug(fmt...)
 #endif
 
 #ifdef __DEBUG_C3CN_RX__
-#define c3cn_rx_debug         cxgb3i_log_debug
+#define c3cn_rx_debug		cxgb3i_log_debug
 #else
 #define c3cn_rx_debug(fmt...)
 #endif
@@ -47,9 +47,9 @@ static int cxgb3_rcv_win = 256 * 1024;
 module_param(cxgb3_rcv_win, int, 0644);
 MODULE_PARM_DESC(cxgb3_rcv_win, "TCP receive window in bytes (default=256KB)");
 
-static int cxgb3_snd_win = 64 * 1024;
+static int cxgb3_snd_win = 128 * 1024;
 module_param(cxgb3_snd_win, int, 0644);
-MODULE_PARM_DESC(cxgb3_snd_win, "TCP send window in bytes (default=64KB)");
+MODULE_PARM_DESC(cxgb3_snd_win, "TCP send window in bytes (default=128KB)");
 
 static int cxgb3_rx_credit_thres = 10 * 1024;
 module_param(cxgb3_rx_credit_thres, int, 0644);
@@ -301,8 +301,8 @@ static void act_open_req_arp_failure(struct t3cdev *dev, struct sk_buff *skb)
 static void skb_entail(struct s3_conn *c3cn, struct sk_buff *skb,
 		       int flags)
 {
-	CXGB3_SKB_CB(skb)->seq = c3cn->write_seq;
-	CXGB3_SKB_CB(skb)->flags = flags;
+	skb_tcp_seq(skb) = c3cn->write_seq;
+	skb_flags(skb) = flags;
 	__skb_queue_tail(&c3cn->write_queue, skb);
 }
 
@@ -457,12 +457,9 @@ static unsigned int wrlen __read_mostly;
  * The number of WRs needed for an skb depends on the number of fragments
  * in the skb and whether it has any payload in its main body.  This maps the
  * length of the gather list represented by an skb into the # of necessary WRs.
- *
- * The max. length of an skb is controlled by the max pdu size which is ~16K.
- * Also, assume the min. fragment length is the sector size (512), then add
- * extra fragment counts for iscsi bhs and payload padding.
+ * The extra two fragments are for iscsi bhs and payload padding.
  */
-#define SKB_WR_LIST_SIZE	(16384/512 + 3)
+#define SKB_WR_LIST_SIZE	(MAX_SKB_FRAGS + 2)
 static unsigned int skb_wrs[SKB_WR_LIST_SIZE] __read_mostly;
 
 static void s3_init_wr_tab(unsigned int wr_len)
@@ -485,7 +482,7 @@ static void s3_init_wr_tab(unsigned int wr_len)
 
 static inline void reset_wr_list(struct s3_conn *c3cn)
 {
-	c3cn->wr_pending_head = NULL;
+	c3cn->wr_pending_head = c3cn->wr_pending_tail = NULL;
 }
 
 /*
@@ -496,7 +493,7 @@ static inline void reset_wr_list(struct s3_conn *c3cn)
 static inline void enqueue_wr(struct s3_conn *c3cn,
 			      struct sk_buff *skb)
 {
-	skb_wr_data(skb) = NULL;
+	skb_tx_wr_next(skb) = NULL;
 
 	/*
 	 * We want to take an extra reference since both us and the driver
@@ -509,10 +506,22 @@ static inline void enqueue_wr(struct s3_conn *c3cn,
 	if (!c3cn->wr_pending_head)
 		c3cn->wr_pending_head = skb;
 	else
-		skb_wr_data(skb) = skb;
+		skb_tx_wr_next(c3cn->wr_pending_tail) = skb;
 	c3cn->wr_pending_tail = skb;
 }
 
+static int count_pending_wrs(struct s3_conn *c3cn)
+{
+	int n = 0;
+	const struct sk_buff *skb = c3cn->wr_pending_head;
+
+	while (skb) {
+		n += skb->csum;
+		skb = skb_tx_wr_next(skb);
+	}
+	return n;
+}
+
 static inline struct sk_buff *peek_wr(const struct s3_conn *c3cn)
 {
 	return c3cn->wr_pending_head;
@@ -529,8 +538,8 @@ static inline struct sk_buff *dequeue_wr(struct s3_conn *c3cn)
 
 	if (likely(skb)) {
 		/* Don't bother clearing the tail */
-		c3cn->wr_pending_head = skb_wr_data(skb);
-		skb_wr_data(skb) = NULL;
+		c3cn->wr_pending_head = skb_tx_wr_next(skb);
+		skb_tx_wr_next(skb) = NULL;
 	}
 	return skb;
 }
@@ -543,13 +552,14 @@ static void purge_wr_queue(struct s3_conn *c3cn)
 }
 
 static inline void make_tx_data_wr(struct s3_conn *c3cn, struct sk_buff *skb,
-				   int len)
+				   int len, int req_completion)
 {
 	struct tx_data_wr *req;
 
 	skb_reset_transport_header(skb);
 	req = (struct tx_data_wr *)__skb_push(skb, sizeof(*req));
-	req->wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_TX_DATA));
+	req->wr_hi = htonl(V_WR_OP(FW_WROPCODE_OFLD_TX_DATA) |
+			(req_completion ? F_WR_COMPL : 0));
 	req->wr_lo = htonl(V_WR_TID(c3cn->tid));
 	req->sndseq = htonl(c3cn->snd_nxt);
 	/* len includes the length of any HW ULP additions */
@@ -592,7 +602,7 @@ static int c3cn_push_tx_frames(struct s3_conn *c3cn, int req_completion)
 
 	if (unlikely(c3cn->state == C3CN_STATE_CONNECTING ||
 		     c3cn->state == C3CN_STATE_CLOSE_WAIT_1 ||
-		     c3cn->state == C3CN_STATE_ABORTING)) {
+		     c3cn->state >= C3CN_STATE_ABORTING)) {
 		c3cn_tx_debug("c3cn 0x%p, in closing state %u.\n",
 			      c3cn, c3cn->state);
 		return 0;
@@ -615,7 +625,7 @@ static int c3cn_push_tx_frames(struct s3_conn *c3cn, int req_completion)
 		if (c3cn->wr_avail < wrs_needed) {
 			c3cn_tx_debug("c3cn 0x%p, skb len %u/%u, frag %u, "
 				      "wr %d < %u.\n",
-				      c3cn, skb->len, skb->datalen, frags,
+				      c3cn, skb->len, skb->data_len, frags,
 				      wrs_needed, c3cn->wr_avail);
 			break;
 		}
@@ -627,20 +637,24 @@ static int c3cn_push_tx_frames(struct s3_conn *c3cn, int req_completion)
 		c3cn->wr_unacked += wrs_needed;
 		enqueue_wr(c3cn, skb);
 
-		if (likely(CXGB3_SKB_CB(skb)->flags & C3CB_FLAG_NEED_HDR)) {
-			len += ulp_extra_len(skb);
-			make_tx_data_wr(c3cn, skb, len);
-			c3cn->snd_nxt += len;
-			if ((req_completion
-			     && c3cn->wr_unacked == wrs_needed)
-			    || (CXGB3_SKB_CB(skb)->flags & C3CB_FLAG_COMPL)
-			    || c3cn->wr_unacked >= c3cn->wr_max / 2) {
-				struct work_request_hdr *wr = cplhdr(skb);
+		c3cn_tx_debug("c3cn 0x%p, enqueue, skb len %u/%u, frag %u, "
+				"wr %d, left %u, unack %u.\n",
+				c3cn, skb->len, skb->data_len, frags,
+				wrs_needed, c3cn->wr_avail, c3cn->wr_unacked);
+
 
-				wr->wr_hi |= htonl(F_WR_COMPL);
+		if (likely(skb_flags(skb) & C3CB_FLAG_NEED_HDR)) {
+			if ((req_completion &&
+				c3cn->wr_unacked == wrs_needed) ||
+			    (skb_flags(skb) & C3CB_FLAG_COMPL) ||
+			    c3cn->wr_unacked >= c3cn->wr_max / 2) {
+				req_completion = 1;
 				c3cn->wr_unacked = 0;
 			}
-			CXGB3_SKB_CB(skb)->flags &= ~C3CB_FLAG_NEED_HDR;
+			len += ulp_extra_len(skb);
+			make_tx_data_wr(c3cn, skb, len, req_completion);
+			c3cn->snd_nxt += len;
+			skb_flags(skb) &= ~C3CB_FLAG_NEED_HDR;
 		}
 
 		total_size += skb->truesize;
@@ -735,8 +749,11 @@ static void process_act_establish(struct s3_conn *c3cn, struct sk_buff *skb)
 	if (unlikely(c3cn_flag(c3cn, C3CN_ACTIVE_CLOSE_NEEDED)))
 		/* upper layer has requested closing */
 		send_abort_req(c3cn);
-	else if (c3cn_push_tx_frames(c3cn, 1))
+	else {
+		if (skb_queue_len(&c3cn->write_queue))
+			c3cn_push_tx_frames(c3cn, 1);
 		cxgb3i_conn_tx_open(c3cn);
+	}
 }
 
 static int do_act_establish(struct t3cdev *cdev, struct sk_buff *skb,
@@ -1082,8 +1099,8 @@ static void process_rx_iscsi_hdr(struct s3_conn *c3cn, struct sk_buff *skb)
 		return;
 	}
 
-	CXGB3_SKB_CB(skb)->seq = ntohl(hdr_cpl->seq);
-	CXGB3_SKB_CB(skb)->flags = 0;
+	skb_tcp_seq(skb) = ntohl(hdr_cpl->seq);
+	skb_flags(skb) = 0;
 
 	skb_reset_transport_header(skb);
 	__skb_pull(skb, sizeof(struct cpl_iscsi_hdr));
@@ -1103,12 +1120,12 @@ static void process_rx_iscsi_hdr(struct s3_conn *c3cn, struct sk_buff *skb)
 		goto abort_conn;
 
 	skb_ulp_mode(skb) = ULP2_FLAG_DATA_READY;
-	skb_ulp_pdulen(skb) = ntohs(ddp_cpl.len);
-	skb_ulp_ddigest(skb) = ntohl(ddp_cpl.ulp_crc);
+	skb_rx_pdulen(skb) = ntohs(ddp_cpl.len);
+	skb_rx_ddigest(skb) = ntohl(ddp_cpl.ulp_crc);
 	status = ntohl(ddp_cpl.ddp_status);
 
 	c3cn_rx_debug("rx skb 0x%p, len %u, pdulen %u, ddp status 0x%x.\n",
-		      skb, skb->len, skb_ulp_pdulen(skb), status);
+		      skb, skb->len, skb_rx_pdulen(skb), status);
 
 	if (status & (1 << RX_DDP_STATUS_HCRC_SHIFT))
 		skb_ulp_mode(skb) |= ULP2_FLAG_HCRC_ERROR;
@@ -1126,7 +1143,7 @@ static void process_rx_iscsi_hdr(struct s3_conn *c3cn, struct sk_buff *skb)
 	} else if (status & (1 << RX_DDP_STATUS_DDP_SHIFT))
 		skb_ulp_mode(skb) |= ULP2_FLAG_DATA_DDPED;
 
-	c3cn->rcv_nxt = ntohl(ddp_cpl.seq) + skb_ulp_pdulen(skb);
+	c3cn->rcv_nxt = ntohl(ddp_cpl.seq) + skb_rx_pdulen(skb);
 	__pskb_trim(skb, len);
 	__skb_queue_tail(&c3cn->receive_queue, skb);
 	cxgb3i_conn_pdu_ready(c3cn);
@@ -1151,12 +1168,27 @@ static int do_iscsi_hdr(struct t3cdev *t3dev, struct sk_buff *skb, void *ctx)
  * Process an acknowledgment of WR completion.  Advance snd_una and send the
  * next batch of work requests from the write queue.
  */
+static void check_wr_invariants(struct s3_conn *c3cn)
+{
+	int pending = count_pending_wrs(c3cn);
+
+	if (unlikely(c3cn->wr_avail + pending != c3cn->wr_max))
+		cxgb3i_log_error("TID %u: credit imbalance: avail %u, "
+				"pending %u, total should be %u\n",
+				c3cn->tid, c3cn->wr_avail, pending,
+				c3cn->wr_max);
+}
+
 static void process_wr_ack(struct s3_conn *c3cn, struct sk_buff *skb)
 {
 	struct cpl_wr_ack *hdr = cplhdr(skb);
 	unsigned int credits = ntohs(hdr->credits);
 	u32 snd_una = ntohl(hdr->snd_una);
 
+	c3cn_tx_debug("%u WR credits, avail %u, unack %u, TID %u, state %u.\n",
+			credits, c3cn->wr_avail, c3cn->wr_unacked,
+			c3cn->tid, c3cn->state);
+
 	c3cn->wr_avail += credits;
 	if (c3cn->wr_unacked > c3cn->wr_max - c3cn->wr_avail)
 		c3cn->wr_unacked = c3cn->wr_max - c3cn->wr_avail;
@@ -1171,6 +1203,17 @@ static void process_wr_ack(struct s3_conn *c3cn, struct sk_buff *skb)
 			break;
 		}
 		if (unlikely(credits < p->csum)) {
+			struct tx_data_wr *w = cplhdr(p);
+			cxgb3i_log_error("TID %u got %u WR credits need %u, "
+					 "len %u, main body %u, frags %u, "
+					 "seq # %u, ACK una %u, ACK nxt %u, "
+					 "WR_AVAIL %u, WRs pending %u\n",
+					 c3cn->tid, credits, p->csum, p->len,
+					 p->len - p->data_len,
+					 skb_shinfo(p)->nr_frags,
+					 ntohl(w->sndseq), snd_una,
+					 ntohl(hdr->snd_nxt), c3cn->wr_avail,
+					 count_pending_wrs(c3cn) - credits);
 			p->csum -= credits;
 			break;
 		} else {
@@ -1180,15 +1223,24 @@ static void process_wr_ack(struct s3_conn *c3cn, struct sk_buff *skb)
 		}
 	}
 
-	if (unlikely(before(snd_una, c3cn->snd_una)))
+	check_wr_invariants(c3cn);
+
+	if (unlikely(before(snd_una, c3cn->snd_una))) {
+		cxgb3i_log_error("TID %u, unexpected sequence # %u in WR_ACK "
+				 "snd_una %u\n",
+				 c3cn->tid, snd_una, c3cn->snd_una);
 		goto out_free;
+	}
 
 	if (c3cn->snd_una != snd_una) {
 		c3cn->snd_una = snd_una;
 		dst_confirm(c3cn->dst_cache);
 	}
 
-	if (skb_queue_len(&c3cn->write_queue) && c3cn_push_tx_frames(c3cn, 0))
+	if (skb_queue_len(&c3cn->write_queue)) {
+		if (c3cn_push_tx_frames(c3cn, 0))
+			cxgb3i_conn_tx_open(c3cn);
+	} else
 		cxgb3i_conn_tx_open(c3cn);
 out_free:
 	__kfree_skb(skb);
@@ -1452,7 +1504,7 @@ static void init_offload_conn(struct s3_conn *c3cn,
 			      struct dst_entry *dst)
 {
 	BUG_ON(c3cn->cdev != cdev);
-	c3cn->wr_max = c3cn->wr_avail = T3C_DATA(cdev)->max_wrs;
+	c3cn->wr_max = c3cn->wr_avail = T3C_DATA(cdev)->max_wrs - 1;
 	c3cn->wr_unacked = 0;
 	c3cn->mss_idx = select_mss(c3cn, dst_mtu(dst));
 
@@ -1671,9 +1723,17 @@ int cxgb3i_c3cn_send_pdus(struct s3_conn *c3cn, struct sk_buff *skb)
 		goto out_err;
 	}
 
-	err = -EPIPE;
 	if (c3cn->err) {
 		c3cn_tx_debug("c3cn 0x%p, err %d.\n", c3cn, c3cn->err);
+		err = -EPIPE;
+		goto out_err;
+	}
+
+	if (c3cn->write_seq - c3cn->snd_una >= cxgb3_snd_win) {
+		c3cn_tx_debug("c3cn 0x%p, snd %u - %u > %u.\n",
+				c3cn, c3cn->write_seq, c3cn->snd_una,
+				cxgb3_snd_win);
+		err = -EAGAIN;
 		goto out_err;
 	}
 
diff --git a/drivers/scsi/cxgb3i/cxgb3i_offload.h b/drivers/scsi/cxgb3i/cxgb3i_offload.h
index d231569..6344b9e 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_offload.h
+++ b/drivers/scsi/cxgb3i/cxgb3i_offload.h
@@ -178,25 +178,33 @@ void cxgb3i_c3cn_release(struct s3_conn *);
  * @flag:	see C3CB_FLAG_* below
  * @ulp_mode:	ULP mode/submode of sk_buff
  * @seq:	tcp sequence number
- * @ddigest:	pdu data digest
- * @pdulen:	recovered pdu length
- * @wr_data:	scratch area for tx wr
  */
+struct cxgb3_skb_rx_cb {
+	__u32 ddigest;			/* data digest */
+	__u32 pdulen;			/* recovered pdu length */
+};
+
+struct cxgb3_skb_tx_cb {
+	struct sk_buff *wr_next;	/* next wr */
+};
+
 struct cxgb3_skb_cb {
 	__u8 flags;
 	__u8 ulp_mode;
 	__u32 seq;
-	__u32 ddigest;
-	__u32 pdulen;
-	struct sk_buff *wr_data;
+	union {
+		struct cxgb3_skb_rx_cb rx;
+		struct cxgb3_skb_tx_cb tx;
+	};
 };
 
 #define CXGB3_SKB_CB(skb)	((struct cxgb3_skb_cb *)&((skb)->cb[0]))
-
+#define skb_flags(skb)		(CXGB3_SKB_CB(skb)->flags)
 #define skb_ulp_mode(skb)	(CXGB3_SKB_CB(skb)->ulp_mode)
-#define skb_ulp_ddigest(skb)	(CXGB3_SKB_CB(skb)->ddigest)
-#define skb_ulp_pdulen(skb)	(CXGB3_SKB_CB(skb)->pdulen)
-#define skb_wr_data(skb)	(CXGB3_SKB_CB(skb)->wr_data)
+#define skb_tcp_seq(skb)	(CXGB3_SKB_CB(skb)->seq)
+#define skb_rx_ddigest(skb)	(CXGB3_SKB_CB(skb)->rx.ddigest)
+#define skb_rx_pdulen(skb)	(CXGB3_SKB_CB(skb)->rx.pdulen)
+#define skb_tx_wr_next(skb)	(CXGB3_SKB_CB(skb)->tx.wr_next)
 
 enum c3cb_flags {
 	C3CB_FLAG_NEED_HDR = 1 << 0,	/* packet needs a TX_DATA_WR header */
@@ -217,6 +225,7 @@ struct sge_opaque_hdr {
 /* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */
 #define TX_HEADER_LEN \
 		(sizeof(struct tx_data_wr) + sizeof(struct sge_opaque_hdr))
+#define SKB_TX_HEADROOM		SKB_MAX_HEAD(TX_HEADER_LEN)
 
 /*
  * get and set private ip for iscsi traffic
diff --git a/drivers/scsi/cxgb3i/cxgb3i_pdu.c b/drivers/scsi/cxgb3i/cxgb3i_pdu.c
index ce7ce8c..17115c2 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_pdu.c
+++ b/drivers/scsi/cxgb3i/cxgb3i_pdu.c
@@ -32,6 +32,10 @@
 #define cxgb3i_tx_debug(fmt...)
 #endif
 
+/* always allocate rooms for AHS */
+#define SKB_TX_PDU_HEADER_LEN	\
+	(sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE)
+static unsigned int skb_extra_headroom;
 static struct page *pad_page;
 
 /*
@@ -146,12 +150,13 @@ static inline void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc)
 
 void cxgb3i_conn_cleanup_task(struct iscsi_task *task)
 {
-	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = task->dd_data +
+					sizeof(struct iscsi_tcp_task);
 
 	/* never reached the xmit task callout */
-	if (tcp_task->dd_data)
-		kfree_skb(tcp_task->dd_data);
-	tcp_task->dd_data = NULL;
+	if (tdata->skb)
+		__kfree_skb(tdata->skb);
+	memset(tdata, 0, sizeof(struct cxgb3i_task_data));
 
 	/* MNC - Do we need a check in case this is called but
 	 * cxgb3i_conn_alloc_pdu has never been called on the task */
@@ -159,28 +164,102 @@ void cxgb3i_conn_cleanup_task(struct iscsi_task *task)
 	iscsi_tcp_cleanup_task(task);
 }
 
-/*
- * We do not support ahs yet
- */
+static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt,
+				unsigned int offset, unsigned int *off,
+				struct scatterlist **sgp)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sgl, sg, sgcnt, i) {
+		if (offset < sg->length) {
+			*off = offset;
+			*sgp = sg;
+			return 0;
+		}
+		offset -= sg->length;
+	}
+	return -EFAULT;
+}
+
+static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset,
+				unsigned int dlen, skb_frag_t *frags,
+				int frag_max)
+{
+	unsigned int datalen = dlen;
+	unsigned int sglen = sg->length - sgoffset;
+	struct page *page = sg_page(sg);
+	int i;
+
+	i = 0;
+	do {
+		unsigned int copy;
+
+		if (!sglen) {
+			sg = sg_next(sg);
+			if (!sg) {
+				cxgb3i_log_error("%s, sg NULL, len %u/%u.\n",
+						 __func__, datalen, dlen);
+				return -EINVAL;
+			}
+			sgoffset = 0;
+			sglen = sg->length;
+			page = sg_page(sg);
+
+		}
+		copy = min(datalen, sglen);
+		if (i && page == frags[i - 1].page &&
+		    sgoffset + sg->offset ==
+			frags[i - 1].page_offset + frags[i - 1].size) {
+			frags[i - 1].size += copy;
+		} else {
+			if (i >= frag_max) {
+				cxgb3i_log_error("%s, too many pages %u, "
+						 "dlen %u.\n", __func__,
+						 frag_max, dlen);
+				return -EINVAL;
+			}
+
+			frags[i].page = page;
+			frags[i].page_offset = sg->offset + sgoffset;
+			frags[i].size = copy;
+			i++;
+		}
+		datalen -= copy;
+		sgoffset += copy;
+		sglen -= copy;
+	} while (datalen);
+
+	return i;
+}
+
 int cxgb3i_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
 {
+	struct iscsi_conn *conn = task->conn;
 	struct iscsi_tcp_task *tcp_task = task->dd_data;
-	struct sk_buff *skb;
+	struct cxgb3i_task_data *tdata = task->dd_data + sizeof(*tcp_task);
+	struct scsi_cmnd *sc = task->sc;
+	int headroom = SKB_TX_PDU_HEADER_LEN;
 
+	tcp_task->dd_data = tdata;
 	task->hdr = NULL;
-	/* always allocate rooms for AHS */
-	skb = alloc_skb(sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE +
-			TX_HEADER_LEN,  GFP_ATOMIC);
-	if (!skb)
+
+	/* write command, need to send data pdus */
+	if (skb_extra_headroom && (opcode == ISCSI_OP_SCSI_DATA_OUT ||
+	    (opcode == ISCSI_OP_SCSI_CMD &&
+	    (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE))))
+		headroom += min(skb_extra_headroom, conn->max_xmit_dlength);
+
+	tdata->skb = alloc_skb(TX_HEADER_LEN + headroom, GFP_ATOMIC);
+	if (!tdata->skb)
 		return -ENOMEM;
+	skb_reserve(tdata->skb, TX_HEADER_LEN);
 
 	cxgb3i_tx_debug("task 0x%p, opcode 0x%x, skb 0x%p.\n",
-			task, opcode, skb);
+			task, opcode, tdata->skb);
 
-	tcp_task->dd_data = skb;
-	skb_reserve(skb, TX_HEADER_LEN);
-	task->hdr = (struct iscsi_hdr *)skb->data;
-	task->hdr_max = sizeof(struct iscsi_hdr);
+	task->hdr = (struct iscsi_hdr *)tdata->skb->data;
+	task->hdr_max = SKB_TX_PDU_HEADER_LEN;
 
 	/* data_out uses scsi_cmd's itt */
 	if (opcode != ISCSI_OP_SCSI_DATA_OUT)
@@ -192,13 +271,13 @@ int cxgb3i_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
 int cxgb3i_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
 			      unsigned int count)
 {
-	struct iscsi_tcp_task *tcp_task = task->dd_data;
-	struct sk_buff *skb = tcp_task->dd_data;
 	struct iscsi_conn *conn = task->conn;
-	struct page *pg;
+	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = tcp_task->dd_data;
+	struct sk_buff *skb = tdata->skb;
 	unsigned int datalen = count;
 	int i, padlen = iscsi_padding(count);
-	skb_frag_t *frag;
+	struct page *pg;
 
 	cxgb3i_tx_debug("task 0x%p,0x%p, offset %u, count %u, skb 0x%p.\n",
 			task, task->sc, offset, count, skb);
@@ -209,90 +288,94 @@ int cxgb3i_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
 		return 0;
 
 	if (task->sc) {
-		struct scatterlist *sg;
-		struct scsi_data_buffer *sdb;
-		unsigned int sgoffset = offset;
-		struct page *sgpg;
-		unsigned int sglen;
-
-		sdb = scsi_out(task->sc);
-		sg = sdb->table.sgl;
-
-		for_each_sg(sdb->table.sgl, sg, sdb->table.nents, i) {
-			cxgb3i_tx_debug("sg %d, page 0x%p, len %u offset %u\n",
-					i, sg_page(sg), sg->length, sg->offset);
-
-			if (sgoffset < sg->length)
-				break;
-			sgoffset -= sg->length;
+		struct scsi_data_buffer *sdb = scsi_out(task->sc);
+		struct scatterlist *sg = NULL;
+		int err;
+
+		tdata->offset = offset;
+		tdata->count = count;
+		err = sgl_seek_offset(sdb->table.sgl, sdb->table.nents,
+					tdata->offset, &tdata->sgoffset, &sg);
+		if (err < 0) {
+			cxgb3i_log_warn("tpdu, sgl %u, bad offset %u/%u.\n",
+					sdb->table.nents, tdata->offset,
+					sdb->length);
+			return err;
 		}
-		sgpg = sg_page(sg);
-		sglen = sg->length - sgoffset;
-
-		do {
-			int j = skb_shinfo(skb)->nr_frags;
-			unsigned int copy;
-
-			if (!sglen) {
-				sg = sg_next(sg);
-				sgpg = sg_page(sg);
-				sgoffset = 0;
-				sglen = sg->length;
-				++i;
+		err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count,
+					tdata->frags, MAX_PDU_FRAGS);
+		if (err < 0) {
+			cxgb3i_log_warn("tpdu, sgl %u, bad offset %u + %u.\n",
+					sdb->table.nents, tdata->offset,
+					tdata->count);
+			return err;
+		}
+		tdata->nr_frags = err;
+
+		if (tdata->nr_frags > MAX_SKB_FRAGS ||
+		    (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) {
+			char *dst = skb->data + task->hdr_len;
+			skb_frag_t *frag = tdata->frags;
+
+			/* data fits in the skb's headroom */
+			for (i = 0; i < tdata->nr_frags; i++, frag++) {
+				char *src = kmap_atomic(frag->page,
+							KM_SOFTIRQ0);
+
+				memcpy(dst, src+frag->page_offset, frag->size);
+				dst += frag->size;
+				kunmap_atomic(src, KM_SOFTIRQ0);
 			}
-			copy = min(sglen, datalen);
-			if (j && skb_can_coalesce(skb, j, sgpg,
-						  sg->offset + sgoffset)) {
-				skb_shinfo(skb)->frags[j - 1].size += copy;
-			} else {
-				get_page(sgpg);
-				skb_fill_page_desc(skb, j, sgpg,
-						   sg->offset + sgoffset, copy);
+			if (padlen) {
+				memset(dst, 0, padlen);
+				padlen = 0;
 			}
-			sgoffset += copy;
-			sglen -= copy;
-			datalen -= copy;
-		} while (datalen);
+			skb_put(skb, count + padlen);
+		} else {
+			/* data fit into frag_list */
+			for (i = 0; i < tdata->nr_frags; i++)
+				get_page(tdata->frags[i].page);
+
+			memcpy(skb_shinfo(skb)->frags, tdata->frags,
+				sizeof(skb_frag_t) * tdata->nr_frags);
+			skb_shinfo(skb)->nr_frags = tdata->nr_frags;
+			skb->len += count;
+			skb->data_len += count;
+			skb->truesize += count;
+		}
+
 	} else {
 		pg = virt_to_page(task->data);
 
-		while (datalen) {
-			i = skb_shinfo(skb)->nr_frags;
-			frag = &skb_shinfo(skb)->frags[i];
-
-			get_page(pg);
-			frag->page = pg;
-			frag->page_offset = 0;
-			frag->size = min((unsigned int)PAGE_SIZE, datalen);
-
-			skb_shinfo(skb)->nr_frags++;
-			datalen -= frag->size;
-			pg++;
-		}
+		get_page(pg);
+		skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data),
+					count);
+		skb->len += count;
+		skb->data_len += count;
+		skb->truesize += count;
 	}
 
 	if (padlen) {
 		i = skb_shinfo(skb)->nr_frags;
-		frag = &skb_shinfo(skb)->frags[i];
-		frag->page = pad_page;
-		frag->page_offset = 0;
-		frag->size = padlen;
-		skb_shinfo(skb)->nr_frags++;
+		get_page(pad_page);
+		skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, pad_page, 0,
+				 padlen);
+
+		skb->data_len += padlen;
+		skb->truesize += padlen;
+		skb->len += padlen;
 	}
 
-	datalen = count + padlen;
-	skb->data_len += datalen;
-	skb->truesize += datalen;
-	skb->len += datalen;
 	return 0;
 }
 
 int cxgb3i_conn_xmit_pdu(struct iscsi_task *task)
 {
-	struct iscsi_tcp_task *tcp_task = task->dd_data;
-	struct sk_buff *skb = tcp_task->dd_data;
 	struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
 	struct cxgb3i_conn *cconn = tcp_conn->dd_data;
+	struct iscsi_tcp_task *tcp_task = task->dd_data;
+	struct cxgb3i_task_data *tdata = tcp_task->dd_data;
+	struct sk_buff *skb = tdata->skb;
 	unsigned int datalen;
 	int err;
 
@@ -300,13 +383,14 @@ int cxgb3i_conn_xmit_pdu(struct iscsi_task *task)
 		return 0;
 
 	datalen = skb->data_len;
-	tcp_task->dd_data = NULL;
+	tdata->skb = NULL;
 	err = cxgb3i_c3cn_send_pdus(cconn->cep->c3cn, skb);
-	cxgb3i_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n",
-			task, skb, skb->len, skb->data_len, err);
 	if (err > 0) {
 		int pdulen = err;
 
+	cxgb3i_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n",
+			task, skb, skb->len, skb->data_len, err);
+
 		if (task->conn->hdrdgst_en)
 			pdulen += ISCSI_DIGEST_SIZE;
 		if (datalen && task->conn->datadgst_en)
@@ -325,12 +409,14 @@ int cxgb3i_conn_xmit_pdu(struct iscsi_task *task)
 		return err;
 	}
 	/* reset skb to send when we are called again */
-	tcp_task->dd_data = skb;
+	tdata->skb = skb;
 	return -EAGAIN;
 }
 
 int cxgb3i_pdu_init(void)
 {
+	if (SKB_TX_HEADROOM > (512 * MAX_SKB_FRAGS))
+		skb_extra_headroom = SKB_TX_HEADROOM;
 	pad_page = alloc_page(GFP_KERNEL);
 	if (!pad_page)
 		return -ENOMEM;
@@ -366,7 +452,9 @@ void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn)
 	skb = skb_peek(&c3cn->receive_queue);
 	while (!err && skb) {
 		__skb_unlink(skb, &c3cn->receive_queue);
-		read += skb_ulp_pdulen(skb);
+		read += skb_rx_pdulen(skb);
+		cxgb3i_rx_debug("conn 0x%p, cn 0x%p, rx skb 0x%p, pdulen %u.\n",
+				conn, c3cn, skb, skb_rx_pdulen(skb));
 		err = cxgb3i_conn_read_pdu_skb(conn, skb);
 		__kfree_skb(skb);
 		skb = skb_peek(&c3cn->receive_queue);
@@ -377,6 +465,11 @@ void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn)
 		cxgb3i_c3cn_rx_credits(c3cn, read);
 	}
 	conn->rxdata_octets += read;
+
+	if (err) {
+		cxgb3i_log_info("conn 0x%p rx failed err %d.\n", conn, err);
+		iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+	}
 }
 
 void cxgb3i_conn_tx_open(struct s3_conn *c3cn)
diff --git a/drivers/scsi/cxgb3i/cxgb3i_pdu.h b/drivers/scsi/cxgb3i/cxgb3i_pdu.h
index a3f685c..0770b23 100644
--- a/drivers/scsi/cxgb3i/cxgb3i_pdu.h
+++ b/drivers/scsi/cxgb3i/cxgb3i_pdu.h
@@ -53,7 +53,7 @@ struct cpl_rx_data_ddp_norss {
 #define ULP2_FLAG_DCRC_ERROR		0x20
 #define ULP2_FLAG_PAD_ERROR		0x40
 
-void cxgb3i_conn_closing(struct s3_conn *);
+void cxgb3i_conn_closing(struct s3_conn *c3cn);
 void cxgb3i_conn_pdu_ready(struct s3_conn *c3cn);
 void cxgb3i_conn_tx_open(struct s3_conn *c3cn);
 #endif
diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c
index a48e499..34be88d 100644
--- a/drivers/scsi/hptiop.c
+++ b/drivers/scsi/hptiop.c
@@ -1251,6 +1251,7 @@ static struct pci_device_id hptiop_id_table[] = {
 	{ PCI_VDEVICE(TTI, 0x3530), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x3560), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x4322), (kernel_ulong_t)&hptiop_itl_ops },
+	{ PCI_VDEVICE(TTI, 0x4321), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x4210), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x4211), (kernel_ulong_t)&hptiop_itl_ops },
 	{ PCI_VDEVICE(TTI, 0x4310), (kernel_ulong_t)&hptiop_itl_ops },
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 940dc32..b82ffd9 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1040,12 +1040,11 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				action = ACTION_FAIL;
 			break;
 		case ABORTED_COMMAND:
+			action = ACTION_FAIL;
 			if (sshdr.asc == 0x10) { /* DIF */
 				description = "Target Data Integrity Failure";
-				action = ACTION_FAIL;
 				error = -EILSEQ;
-			} else
-				action = ACTION_RETRY;
+			}
 			break;
 		case NOT_READY:
 			/* If the device is in the process of becoming
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d57566b..55310db 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -107,6 +107,7 @@ static void scsi_disk_release(struct device *cdev);
 static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *);
 static void sd_print_result(struct scsi_disk *, int);
 
+static DEFINE_SPINLOCK(sd_index_lock);
 static DEFINE_IDA(sd_index_ida);
 
 /* This semaphore is used to mediate the 0->1 reference get in the
@@ -1914,7 +1915,9 @@ static int sd_probe(struct device *dev)
 		if (!ida_pre_get(&sd_index_ida, GFP_KERNEL))
 			goto out_put;
 
+		spin_lock(&sd_index_lock);
 		error = ida_get_new(&sd_index_ida, &index);
+		spin_unlock(&sd_index_lock);
 	} while (error == -EAGAIN);
 
 	if (error)
@@ -1936,7 +1939,9 @@ static int sd_probe(struct device *dev)
 	return 0;
 
  out_free_index:
+	spin_lock(&sd_index_lock);
 	ida_remove(&sd_index_ida, index);
+	spin_unlock(&sd_index_lock);
  out_put:
 	put_disk(gd);
  out_free:
@@ -1986,7 +1991,9 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 	struct gendisk *disk = sdkp->disk;
 	
+	spin_lock(&sd_index_lock);
 	ida_remove(&sd_index_ida, sdkp->index);
+	spin_unlock(&sd_index_lock);
 
 	disk->private_data = NULL;
 	put_disk(disk);
diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c
index 48ff701..2552b9f 100644
--- a/drivers/video/pxafb.c
+++ b/drivers/video/pxafb.c
@@ -2230,7 +2230,7 @@ static int __devexit pxafb_remove(struct platform_device *dev)
 
 static struct platform_driver pxafb_driver = {
 	.probe		= pxafb_probe,
-	.remove 	= pxafb_remove,
+	.remove 	= __devexit_p(pxafb_remove),
 	.suspend	= pxafb_suspend,
 	.resume		= pxafb_resume,
 	.driver		= {
diff --git a/fs/Makefile b/fs/Makefile
index 38bc735..dc20db3 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -69,10 +69,12 @@ obj-$(CONFIG_DLM)		+= dlm/
 # Do not add any filesystems before this line
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
-obj-$(CONFIG_EXT4_FS)		+= ext4/ # Before ext2 so root fs can be ext4
+obj-$(CONFIG_EXT2_FS)		+= ext2/
+# We place ext4 after ext2 so plain ext2 root fs's are mounted using ext2
+# unless explicitly requested by rootfstype
+obj-$(CONFIG_EXT4_FS)		+= ext4/
 obj-$(CONFIG_JBD)		+= jbd/
 obj-$(CONFIG_JBD2)		+= jbd2/
-obj-$(CONFIG_EXT2_FS)		+= ext2/
 obj-$(CONFIG_CRAMFS)		+= cramfs/
 obj-$(CONFIG_SQUASHFS)		+= squashfs/
 obj-y				+= ramfs/
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 9a50b80..de9459b 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -609,7 +609,9 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
  */
 int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 {
-	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) || (*retries)++ > 3)
+	if (!ext4_has_free_blocks(EXT4_SB(sb), 1) ||
+	    (*retries)++ > 3 ||
+	    !EXT4_SB(sb)->s_journal)
 		return 0;
 
 	jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 51cdd13..c7fed5b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2544,7 +2544,7 @@ retry:
 
 		ext4_journal_stop(handle);
 
-		if (mpd.retval == -ENOSPC) {
+		if ((mpd.retval == -ENOSPC) && sbi->s_journal) {
 			/* commit the transaction which would
 			 * free blocks released in the transaction
 			 * and try again
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a5732c5..39d1993 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3091,7 +3091,6 @@ static int ext4_freeze(struct super_block *sb)
 
 		/* Journal blocked and flushed, clear needs_recovery flag. */
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
-		ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
 		error = ext4_commit_super(sb, EXT4_SB(sb)->s_es, 1);
 		if (error)
 			goto out;
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index cbc2f0c..0adb0f9 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -91,8 +91,11 @@ io_mapping_unmap_atomic(void *vaddr)
 static inline void *
 io_mapping_map_wc(struct io_mapping *mapping, unsigned long offset)
 {
+	resource_size_t phys_addr;
+
 	BUG_ON(offset >= mapping->size);
-	resource_size_t phys_addr = mapping->base + offset;
+	phys_addr = mapping->base + offset;
+
 	return ioremap_wc(phys_addr, PAGE_SIZE);
 }
 
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index f3f697d..80044a4 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -181,4 +181,10 @@ extern long rcu_batches_completed_bh(void);
 #define rcu_enter_nohz()	do { } while (0)
 #define rcu_exit_nohz()		do { } while (0)
 
+/* A context switch is a grace period for rcuclassic. */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUCLASSIC_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 921340a..528343e 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -52,6 +52,9 @@ struct rcu_head {
 	void (*func)(struct rcu_head *head);
 };
 
+/* Internal to kernel, but needed by rcupreempt.h. */
+extern int rcu_scheduler_active;
+
 #if defined(CONFIG_CLASSIC_RCU)
 #include <linux/rcuclassic.h>
 #elif defined(CONFIG_TREE_RCU)
@@ -265,6 +268,7 @@ extern void rcu_barrier_sched(void);
 
 /* Internal to kernel */
 extern void rcu_init(void);
+extern void rcu_scheduler_starting(void);
 extern int rcu_needs_cpu(int cpu);
 
 #endif /* __LINUX_RCUPDATE_H */
diff --git a/include/linux/rcupreempt.h b/include/linux/rcupreempt.h
index 3e05c09..74304b4 100644
--- a/include/linux/rcupreempt.h
+++ b/include/linux/rcupreempt.h
@@ -142,4 +142,19 @@ static inline void rcu_exit_nohz(void)
 #define rcu_exit_nohz()		do { } while (0)
 #endif /* CONFIG_NO_HZ */
 
+/*
+ * A context switch is a grace period for rcupreempt synchronize_rcu()
+ * only during early boot, before the scheduler has been initialized.
+ * So, how the heck do we get a context switch?  Well, if the caller
+ * invokes synchronize_rcu(), they are willing to accept a context
+ * switch, so we simply pretend that one happened.
+ *
+ * After boot, there might be a blocked or preempted task in an RCU
+ * read-side critical section, so we cannot then take the fastpath.
+ */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1 && !rcu_scheduler_active;
+}
+
 #endif /* __LINUX_RCUPREEMPT_H */
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index d4368b7..a722fb6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -326,4 +326,10 @@ static inline void rcu_exit_nohz(void)
 }
 #endif /* CONFIG_NO_HZ */
 
+/* A context switch is a grace period for rcutree. */
+static inline int rcu_blocking_is_gp(void)
+{
+	return num_online_cpus() == 1;
+}
+
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8981e52..8c216e0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2291,9 +2291,13 @@ extern long sched_group_rt_runtime(struct task_group *tg);
 extern int sched_group_set_rt_period(struct task_group *tg,
 				      long rt_period_us);
 extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 #endif
 #endif
 
+extern int task_can_switch_user(struct user_struct *up,
+					struct task_struct *tsk);
+
 #ifdef CONFIG_TASK_XACCT
 static inline void add_rchar(struct task_struct *tsk, ssize_t amt)
 {
diff --git a/init/main.c b/init/main.c
index 8442094..83697e1 100644
--- a/init/main.c
+++ b/init/main.c
@@ -97,7 +97,7 @@ static inline void mark_rodata_ro(void) { }
 extern void tc_init(void);
 #endif
 
-enum system_states system_state;
+enum system_states system_state __read_mostly;
 EXPORT_SYMBOL(system_state);
 
 /*
@@ -463,6 +463,7 @@ static noinline void __init_refok rest_init(void)
 	 * at least once to get things moving:
 	 */
 	init_idle_bootup_task(current);
+	rcu_scheduler_starting();
 	preempt_enable_no_resched();
 	schedule();
 	preempt_disable();
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index bd5a900..654c640 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -679,8 +679,8 @@ int rcu_needs_cpu(int cpu)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index d92a76a..cae8a05 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -44,6 +44,7 @@
 #include <linux/cpu.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/kernel_stat.h>
 
 enum rcu_barrier {
 	RCU_BARRIER_STD,
@@ -55,6 +56,7 @@ static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL};
 static atomic_t rcu_barrier_cpu_count;
 static DEFINE_MUTEX(rcu_barrier_mutex);
 static struct completion rcu_barrier_completion;
+int rcu_scheduler_active __read_mostly;
 
 /*
  * Awaken the corresponding synchronize_rcu() instance now that a
@@ -80,6 +82,10 @@ void wakeme_after_rcu(struct rcu_head  *head)
 void synchronize_rcu(void)
 {
 	struct rcu_synchronize rcu;
+
+	if (rcu_blocking_is_gp())
+		return;
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu(&rcu.head, wakeme_after_rcu);
@@ -175,3 +181,9 @@ void __init rcu_init(void)
 	__rcu_init();
 }
 
+void rcu_scheduler_starting(void)
+{
+	WARN_ON(num_online_cpus() != 1);
+	WARN_ON(nr_context_switches() > 0);
+	rcu_scheduler_active = 1;
+}
diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c
index 33cfc50..5d59e85 100644
--- a/kernel/rcupreempt.c
+++ b/kernel/rcupreempt.c
@@ -1181,6 +1181,9 @@ void __synchronize_sched(void)
 {
 	struct rcu_synchronize rcu;
 
+	if (num_online_cpus() == 1)
+		return;  /* blocking is gp if only one CPU! */
+
 	init_completion(&rcu.completion);
 	/* Will wake me after RCU finished. */
 	call_rcu_sched(&rcu.head, wakeme_after_rcu);
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index b2fd602..97ce315 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -948,8 +948,8 @@ static void rcu_do_batch(struct rcu_data *rdp)
 void rcu_check_callbacks(int cpu, int user)
 {
 	if (user ||
-	    (idle_cpu(cpu) && !in_softirq() &&
-				hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
+	    (idle_cpu(cpu) && rcu_scheduler_active &&
+	     !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) {
 
 		/*
 		 * Get here if this CPU took its interrupt from user
diff --git a/kernel/sched.c b/kernel/sched.c
index 410eec4..8e2558c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -223,7 +223,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
 {
 	ktime_t now;
 
-	if (rt_bandwidth_enabled() && rt_b->rt_runtime == RUNTIME_INF)
+	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
 		return;
 
 	if (hrtimer_active(&rt_b->rt_period_timer))
@@ -9224,6 +9224,16 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
 #else /* !CONFIG_RT_GROUP_SCHED */
 static int sched_rt_global_constraints(void)
 {
@@ -9317,8 +9327,7 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		      struct task_struct *tsk)
 {
 #ifdef CONFIG_RT_GROUP_SCHED
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0)
+	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
 		return -EINVAL;
 #else
 	/* We don't support RT-tasks being in separate groups */
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index ad64fcb..57d4b13 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -8,6 +8,7 @@
 
 #include <linux/seccomp.h>
 #include <linux/sched.h>
+#include <linux/compat.h>
 
 /* #define SECCOMP_DEBUG 1 */
 #define NR_SECCOMP_MODES 1
@@ -22,7 +23,7 @@ static int mode1_syscalls[] = {
 	0, /* null terminated */
 };
 
-#ifdef TIF_32BIT
+#ifdef CONFIG_COMPAT
 static int mode1_syscalls_32[] = {
 	__NR_seccomp_read_32, __NR_seccomp_write_32, __NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
 	0, /* null terminated */
@@ -37,8 +38,8 @@ void __secure_computing(int this_syscall)
 	switch (mode) {
 	case 1:
 		syscall = mode1_syscalls;
-#ifdef TIF_32BIT
-		if (test_thread_flag(TIF_32BIT))
+#ifdef CONFIG_COMPAT
+		if (is_compat_task())
 			syscall = mode1_syscalls_32;
 #endif
 		do {
diff --git a/kernel/sys.c b/kernel/sys.c
index f145c41..37f458e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -559,7 +559,7 @@ error:
 	abort_creds(new);
 	return retval;
 }
-  
+
 /*
  * change the user struct in a credentials set to match the new UID
  */
@@ -571,6 +571,11 @@ static int set_user(struct cred *new)
 	if (!new_user)
 		return -EAGAIN;
 
+	if (!task_can_switch_user(new_user, current)) {
+		free_uid(new_user);
+		return -EINVAL;
+	}
+
 	if (atomic_read(&new_user->processes) >=
 				current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
 			new_user != INIT_USER) {
@@ -631,10 +636,11 @@ SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
-	if (new->uid != old->uid && set_user(new) < 0)
-		goto error;
-
+	if (new->uid != old->uid) {
+		retval = set_user(new);
+		if (retval < 0)
+			goto error;
+	}
 	if (ruid != (uid_t) -1 ||
 	    (euid != (uid_t) -1 && euid != old->uid))
 		new->suid = new->euid;
@@ -680,9 +686,10 @@ SYSCALL_DEFINE1(setuid, uid_t, uid)
 	retval = -EPERM;
 	if (capable(CAP_SETUID)) {
 		new->suid = new->uid = uid;
-		if (uid != old->uid && set_user(new) < 0) {
-			retval = -EAGAIN;
-			goto error;
+		if (uid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
 		}
 	} else if (uid != old->uid && uid != new->suid) {
 		goto error;
@@ -734,11 +741,13 @@ SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid)
 			goto error;
 	}
 
-	retval = -EAGAIN;
 	if (ruid != (uid_t) -1) {
 		new->uid = ruid;
-		if (ruid != old->uid && set_user(new) < 0)
-			goto error;
+		if (ruid != old->uid) {
+			retval = set_user(new);
+			if (retval < 0)
+				goto error;
+		}
 	}
 	if (euid != (uid_t) -1)
 		new->euid = euid;
diff --git a/kernel/user.c b/kernel/user.c
index 3551ac7..6a9b696 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -362,6 +362,24 @@ static void free_user(struct user_struct *up, unsigned long flags)
 
 #endif
 
+#if defined(CONFIG_RT_GROUP_SCHED) && defined(CONFIG_USER_SCHED)
+/*
+ * We need to check if a setuid can take place. This function should be called
+ * before successfully completing the setuid.
+ */
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+
+	return sched_rt_can_attach(up->tg, tsk);
+
+}
+#else
+int task_can_switch_user(struct user_struct *up, struct task_struct *tsk)
+{
+	return 1;
+}
+#endif
+
 /*
  * Locate the user_struct for the passed UID.  If found, take a ref on it.  The
  * caller must undo that ref with free_uid().
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index 3f4b266..350794a 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -386,11 +386,12 @@ int selinux_netlbl_inode_permission(struct inode *inode, int mask)
 	if (!S_ISSOCK(inode->i_mode) ||
 	    ((mask & (MAY_WRITE | MAY_APPEND)) == 0))
 		return 0;
-
 	sock = SOCKET_I(inode);
 	sk = sock->sk;
+	if (sk == NULL)
+		return 0;
 	sksec = sk->sk_security;
-	if (sksec->nlbl_state != NLBL_REQUIRE)
+	if (sksec == NULL || sksec->nlbl_state != NLBL_REQUIRE)
 		return 0;
 
 	local_bh_disable();
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index c8d9178..5e909e0 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2095,6 +2095,8 @@ static struct snd_pci_quirk probe_mask_list[] __devinitdata = {
 	SND_PCI_QUIRK(0x1028, 0x20ac, "Dell Studio Desktop", 0x01),
 	/* including bogus ALC268 in slot#2 that conflicts with ALC888 */
 	SND_PCI_QUIRK(0x17c0, 0x4085, "Medion MD96630", 0x01),
+	/* conflict of ALC268 in slot#3 (digital I/O); a temporary fix */
+	SND_PCI_QUIRK(0x1179, 0xff00, "Toshiba laptop", 0x03),
 	{}
 };
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a680be0..6c26afc 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10557,6 +10557,7 @@ static struct snd_pci_quirk alc262_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x1309, "HP xw4*00", ALC262_HP_BPC),
 	SND_PCI_QUIRK(0x103c, 0x130a, "HP xw6*00", ALC262_HP_BPC),
 	SND_PCI_QUIRK(0x103c, 0x130b, "HP xw8*00", ALC262_HP_BPC),
+	SND_PCI_QUIRK(0x103c, 0x170b, "HP xw*", ALC262_HP_BPC),
 	SND_PCI_QUIRK(0x103c, 0x2800, "HP D7000", ALC262_HP_BPC_D7000_WL),
 	SND_PCI_QUIRK(0x103c, 0x2801, "HP D7000", ALC262_HP_BPC_D7000_WF),
 	SND_PCI_QUIRK(0x103c, 0x2802, "HP D7000", ALC262_HP_BPC_D7000_WL),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 8027edf..3bc4276 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -4989,7 +4989,7 @@ again:
 	case STAC_DELL_M4_3:
 		spec->num_dmics = 1;
 		spec->num_smuxes = 0;
-		spec->num_dmuxes = 0;
+		spec->num_dmuxes = 1;
 		break;
 	default:
 		spec->num_dmics = STAC92HD71BXX_NUM_DMICS;