From 6fc31d54443bdc25a8166be15e3920a7e39d195d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 12 Jan 2011 17:50:42 +0000
Subject: ARM: Defer lookup of machine_type to setup.c

Since the debug macros no longer depend on the machine type information,
the machine type lookup can be deferred to setup_arch() in setup.c which
simplifies the code somewhat.

We also move the __error_a functionality into setup.c for displaying a
message when a bad machine ID is passed to the kernel via the LL debug
code.  We also log this into the kernel ring buffer which makes it
possible to retrieve the message via a debugger.

Original idea from Grant Likely.

Acked-by: Grant Likely <grant.likely@secretlab.ca>
Tested-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/head-common.S | 90 -------------------------------------------
 arch/arm/kernel/head-nommu.S  |  3 --
 arch/arm/kernel/head.S        |  9 +----
 arch/arm/kernel/setup.c       | 39 ++++++++++++++++++-
 4 files changed, 40 insertions(+), 101 deletions(-)

diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8f57515bbdb0..c84b57d27d07 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -25,83 +25,6 @@
  * machine ID for example).
  */
 	__HEAD
-__error_a:
-#ifdef CONFIG_DEBUG_LL
-	mov	r4, r1				@ preserve machine ID
-	adr	r0, str_a1
-	bl	printascii
-	mov	r0, r4
-	bl	printhex8
-	adr	r0, str_a2
-	bl	printascii
-	adr	r3, __lookup_machine_type_data
-	ldmia	r3, {r4, r5, r6}		@ get machine desc list
-	sub	r4, r3, r4			@ get offset between virt&phys
-	add	r5, r5, r4			@ convert virt addresses to
-	add	r6, r6, r4			@ physical address space
-1:	ldr	r0, [r5, #MACHINFO_TYPE]	@ get machine type
-	bl	printhex8
-	mov	r0, #'\t'
-	bl	printch
-	ldr     r0, [r5, #MACHINFO_NAME]	@ get machine name
-	add	r0, r0, r4
-	bl	printascii
-	mov	r0, #'\n'
-	bl	printch
-	add	r5, r5, #SIZEOF_MACHINE_DESC	@ next machine_desc
-	cmp	r5, r6
-	blo	1b
-	adr	r0, str_a3
-	bl	printascii
-	b	__error
-ENDPROC(__error_a)
-
-str_a1:	.asciz	"\nError: unrecognized/unsupported machine ID (r1 = 0x"
-str_a2:	.asciz	").\n\nAvailable machine support:\n\nID (hex)\tNAME\n"
-str_a3:	.asciz	"\nPlease check your kernel config and/or bootloader.\n"
-	.align
-#else
-	b	__error
-#endif
-
-/*
- * Lookup machine architecture in the linker-build list of architectures.
- * Note that we can't use the absolute addresses for the __arch_info
- * lists since we aren't running with the MMU on (and therefore, we are
- * not in the correct address space).  We have to calculate the offset.
- *
- *  r1 = machine architecture number
- * Returns:
- *  r3, r4, r6 corrupted
- *  r5 = mach_info pointer in physical address space
- */
-__lookup_machine_type:
-	adr	r3, __lookup_machine_type_data
-	ldmia	r3, {r4, r5, r6}
-	sub	r3, r3, r4			@ get offset between virt&phys
-	add	r5, r5, r3			@ convert virt addresses to
-	add	r6, r6, r3			@ physical address space
-1:	ldr	r3, [r5, #MACHINFO_TYPE]	@ get machine type
-	teq	r3, r1				@ matches loader number?
-	beq	2f				@ found
-	add	r5, r5, #SIZEOF_MACHINE_DESC	@ next machine_desc
-	cmp	r5, r6
-	blo	1b
-	mov	r5, #0				@ unknown machine
-2:	mov	pc, lr
-ENDPROC(__lookup_machine_type)
-
-/*
- * Look in arch/arm/kernel/arch.[ch] for information about the
- * __arch_info structures.
- */
-	.align	2
-	.type	__lookup_machine_type_data, %object
-__lookup_machine_type_data:
-	.long	.
-	.long	__arch_info_begin
-	.long	__arch_info_end
-	.size	__lookup_machine_type_data, . - __lookup_machine_type_data
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
@@ -109,8 +32,6 @@ __lookup_machine_type_data:
  * of this function may be more lenient with the physical address and
  * may also be able to move the ATAGS block if necessary.
  *
- * r8  = machinfo
- *
  * Returns:
  *  r2 either valid atags pointer, or zero
  *  r5, r6 corrupted
@@ -184,17 +105,6 @@ __mmap_switched_data:
 	.long	init_thread_union + THREAD_START_SP @ sp
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
-/*
- * This provides a C-API version of __lookup_machine_type
- */
-ENTRY(lookup_machine_type)
-	stmfd	sp!, {r4 - r6, lr}
-	mov	r1, r0
-	bl	__lookup_machine_type
-	mov	r0, r5
-	ldmfd	sp!, {r4 - r6, pc}
-ENDPROC(lookup_machine_type)
-
 /*
  * This provides a C-API version of __lookup_processor_type
  */
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index 814ce1a73270..6b1e0ad9ec3b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -44,9 +44,6 @@ ENTRY(stext)
 	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
 	movs	r10, r5				@ invalid processor (r5=0)?
 	beq	__error_p				@ yes, error 'p'
-	bl	__lookup_machine_type		@ r5=machinfo
-	movs	r8, r5				@ invalid machine (r5=0)?
-	beq	__error_a			@ yes, error 'a'
 
 	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
  ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index c0225da3fb21..8a154b940fef 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -87,14 +87,10 @@ ENTRY(stext)
 	movs	r10, r5				@ invalid processor (r5=0)?
  THUMB( it	eq )		@ force fixup-able long branch encoding
 	beq	__error_p			@ yes, error 'p'
-	bl	__lookup_machine_type		@ r5=machinfo
-	movs	r8, r5				@ invalid machine (r5=0)?
- THUMB( it	eq )		@ force fixup-able long branch encoding
-	beq	__error_a			@ yes, error 'a'
 
 	/*
 	 * r1 = machine no, r2 = atags,
-	 * r8 = machinfo, r9 = cpuid, r10 = procinfo
+	 * r9 = cpuid, r10 = procinfo
 	 */
 	bl	__vet_atags
 #ifdef CONFIG_SMP_ON_UP
@@ -105,7 +101,7 @@ ENTRY(stext)
 	/*
 	 * The following calls CPU specific code in a position independent
 	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
-	 * xxx_proc_info structure selected by __lookup_machine_type
+	 * xxx_proc_info structure selected by __lookup_processor_type
 	 * above.  On return, the CPU will be ready for the MMU to be
 	 * turned on, and r0 will hold the CPU control register value.
 	 */
@@ -124,7 +120,6 @@ ENDPROC(stext)
  * amount which are required to get the kernel running, which
  * generally means mapping in the kernel code.
  *
- * r8  = machinfo
  * r9  = cpuid
  * r10 = procinfo
  *
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 420b8d6485d6..78678b07901c 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -308,7 +308,44 @@ static void __init cacheid_init(void)
  * already provide the required functionality.
  */
 extern struct proc_info_list *lookup_processor_type(unsigned int);
-extern struct machine_desc *lookup_machine_type(unsigned int);
+
+static void __init early_print(const char *str, ...)
+{
+	extern void printascii(const char *);
+	char buf[256];
+	va_list ap;
+
+	va_start(ap, str);
+	vsnprintf(buf, sizeof(buf), str, ap);
+	va_end(ap);
+
+#ifdef CONFIG_DEBUG_LL
+	printascii(buf);
+#endif
+	printk("%s", buf);
+}
+
+static struct machine_desc * __init lookup_machine_type(unsigned int type)
+{
+	extern struct machine_desc __arch_info_begin[], __arch_info_end[];
+	struct machine_desc *p;
+
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+		if (type == p->nr)
+			return p;
+
+	early_print("\n"
+		"Error: unrecognized/unsupported machine ID (r1 = 0x%08x).\n\n"
+		"Available machine support:\n\nID (hex)\tNAME\n", type);
+
+	for (p = __arch_info_begin; p < __arch_info_end; p++)
+		early_print("%08x\t%s\n", p->nr, p->name);
+
+	early_print("\nPlease check your kernel config and/or bootloader.\n");
+
+	while (true)
+		/* can't use cpu_relax() here as it may require MMU setup */;
+}
 
 static void __init feat_v6_fixup(void)
 {
-- 
cgit v1.2.3


From 459c1517f9873b198af7dcded8d8cc84749bbb69 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sat, 8 Jan 2011 11:49:20 +0000
Subject: ARM: DMA: top-down allocation in DMA coherent region

Achieve better usage of the DMA coherent region by doing top-down
allocation rather than bottom up.  If we ask for a 128kB allocation,
this will be aligned to 128kB and satisfied from the very bottom
address.  If we then ask for a 600kB allocation, this will be aligned
to 1MB, and we will have a 896kB hole.

Performing top-down allocation resolves this by allocating the 128kB
at the very top, and then the 600kB can come in below it without any
unnecessary wastage.

This problem was reported by Janusz Krzysztofik, who had 2 x 128kB +
1 x 640kB allocations which wouldn't fit into 1MB.

Tested-by: Janusz Krzysztofik <jkrzyszt@tis.icnet.pl>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mm/vmregion.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm/mm/vmregion.c b/arch/arm/mm/vmregion.c
index 935993e1b1ef..036fdbfdd62f 100644
--- a/arch/arm/mm/vmregion.c
+++ b/arch/arm/mm/vmregion.c
@@ -38,7 +38,7 @@ struct arm_vmregion *
 arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 		   size_t size, gfp_t gfp)
 {
-	unsigned long addr = head->vm_start, end = head->vm_end - size;
+	unsigned long start = head->vm_start, addr = head->vm_end;
 	unsigned long flags;
 	struct arm_vmregion *c, *new;
 
@@ -54,21 +54,20 @@ arm_vmregion_alloc(struct arm_vmregion_head *head, size_t align,
 
 	spin_lock_irqsave(&head->vm_lock, flags);
 
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if ((addr + size) < addr)
-			goto nospc;
-		if ((addr + size) <= c->vm_start)
+	addr = rounddown(addr - size, align);
+	list_for_each_entry_reverse(c, &head->vm_list, vm_list) {
+		if (addr >= c->vm_end)
 			goto found;
-		addr = ALIGN(c->vm_end, align);
-		if (addr > end)
+		addr = rounddown(c->vm_start - size, align);
+		if (addr < start)
 			goto nospc;
 	}
 
  found:
 	/*
-	 * Insert this entry _before_ the one we found.
+	 * Insert this entry after the one we found.
 	 */
-	list_add_tail(&new->vm_list, &c->vm_list);
+	list_add(&new->vm_list, &c->vm_list);
 	new->vm_start = addr;
 	new->vm_end = addr + size;
 	new->vm_active = 1;
-- 
cgit v1.2.3


From 2bbd7e9b74271b2d6a14b4840fc44afbea83774d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sat, 8 Jan 2011 12:05:09 +0000
Subject: ARM: fix some sparse errors in generic ARM code

arch/arm/kernel/return_address.c:37:6: warning: symbol 'return_address' was not declared. Should it be static?
arch/arm/kernel/setup.c:76:14: warning: symbol 'processor_id' was not declared. Should it be static?
arch/arm/kernel/traps.c:259:1: warning: symbol 'die_lock' was not declared. Should it be static?
arch/arm/vfp/vfpmodule.c:156:6: warning: symbol 'vfp_raise_sigfpe' was not declared. Should it be static?

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/cputype.h   | 3 ++-
 arch/arm/kernel/return_address.c | 1 +
 arch/arm/kernel/traps.c          | 2 +-
 arch/arm/vfp/vfpmodule.c         | 2 +-
 4 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 20ae96cc0020..ed5bc9e05a4e 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -23,6 +23,8 @@
 #define CPUID_EXT_ISAR4	"c2, 4"
 #define CPUID_EXT_ISAR5	"c2, 5"
 
+extern unsigned int processor_id;
+
 #ifdef CONFIG_CPU_CP15
 #define read_cpuid(reg)							\
 	({								\
@@ -43,7 +45,6 @@
 		__val;							\
 	})
 #else
-extern unsigned int processor_id;
 #define read_cpuid(reg) (processor_id)
 #define read_cpuid_ext(reg) 0
 #endif
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index df246da4ceca..0b13a72f855d 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -9,6 +9,7 @@
  * the Free Software Foundation.
  */
 #include <linux/module.h>
+#include <linux/ftrace.h>
 
 #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 #include <linux/sched.h>
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index ee57640ba2bb..7f53c3651c58 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -256,7 +256,7 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 	return ret;
 }
 
-DEFINE_SPINLOCK(die_lock);
+static DEFINE_SPINLOCK(die_lock);
 
 /*
  * This function is protected against re-entrancy.
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 0797cb528b46..25b89d817105 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -153,7 +153,7 @@ static struct notifier_block vfp_notifier_block = {
  * Raise a SIGFPE for the current process.
  * sicode describes the signal being raised.
  */
-void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
+static void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
 {
 	siginfo_t info;
 
-- 
cgit v1.2.3


From a65d29225ed884456f3d34dcefd3a18df24af03b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sat, 8 Jan 2011 16:18:51 +0000
Subject: ARM: add 'uinstall' target for installing uboot kernels

We have 'install' and 'zinstall' for installing Image and zImage
kernels, so add 'uinstall' to complete the set.

This allows developers to have a ~/bin/installkernel script which (eg)
copies the kernel to the tftp server automatically once the kernel
has built, resulting in a better workflow.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/Makefile      | 3 ++-
 arch/arm/boot/Makefile | 4 ++++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index c22c1adfedd6..da525bc96145 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -280,7 +280,7 @@ bzImage: zImage
 zImage Image xipImage bootpImage uImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
-zinstall install: vmlinux
+zinstall uinstall install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $@
 
 # We use MRPROPER_FILES and CLEAN_FILES now
@@ -301,6 +301,7 @@ define archhelp
   echo  '                  (supply initrd image via make variable INITRD=<path>)'
   echo  '  install       - Install uncompressed kernel'
   echo  '  zinstall      - Install compressed kernel'
+  echo  '  uinstall      - Install U-Boot wrapped compressed kernel'
   echo  '                  Install using (your) ~/bin/$(INSTALLKERNEL) or'
   echo  '                  (distribution) /sbin/$(INSTALLKERNEL) or'
   echo  '                  install to $$(INSTALL_PATH) and run lilo'
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 4d26f2c52a75..9128fddf1109 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -99,6 +99,10 @@ zinstall: $(obj)/zImage
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
 
+uinstall: $(obj)/uImage
+	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
+	$(obj)/uImage System.map "$(INSTALL_PATH)"
+
 zi:
 	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
 	$(obj)/zImage System.map "$(INSTALL_PATH)"
-- 
cgit v1.2.3


From 68e6fad488ef21335529c65ca6c88c38be50cd3a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Tue, 11 Jan 2011 19:57:14 +0000
Subject: ARM: improve module relocation fixup diagnostics

Current diagnostics are rather poor when things go wrong:
  ipv6: relocation out of range, section 2 reloc 0 sym 'snmp_mib_free'

Let's include a little more information about the problem:
  ipv6: section 2 reloc 0 sym 'snmp_mib_free': relocation 28 out of range (0xbf0000a4 -> 0xc11b4858)

so that we show exactly what the problem is - not only what type of
relocation but also the offending address range too.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/module.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index 2cfe8161b478..980fe20a376e 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -75,6 +75,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 	for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) {
 		unsigned long loc;
 		Elf32_Sym *sym;
+		const char *symname;
 		s32 offset;
 #ifdef CONFIG_THUMB2_KERNEL
 		u32 upper, lower, sign, j1, j2;
@@ -82,18 +83,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
 		offset = ELF32_R_SYM(rel->r_info);
 		if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
-			printk(KERN_ERR "%s: bad relocation, section %d reloc %d\n",
+			pr_err("%s: section %u reloc %u: bad relocation sym offset\n",
 				module->name, relindex, i);
 			return -ENOEXEC;
 		}
 
 		sym = ((Elf32_Sym *)symsec->sh_addr) + offset;
+		symname = strtab + sym->st_name;
 
 		if (rel->r_offset < 0 || rel->r_offset > dstsec->sh_size - sizeof(u32)) {
-			printk(KERN_ERR "%s: out of bounds relocation, "
-				"section %d reloc %d offset %d size %d\n",
-				module->name, relindex, i, rel->r_offset,
-				dstsec->sh_size);
+			pr_err("%s: section %u reloc %u sym '%s': out of bounds relocation, offset %d size %u\n",
+			       module->name, relindex, i, symname,
+			       rel->r_offset, dstsec->sh_size);
 			return -ENOEXEC;
 		}
 
@@ -119,10 +120,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (offset & 3 ||
 			    offset <= (s32)0xfe000000 ||
 			    offset >= (s32)0x02000000) {
-				printk(KERN_ERR
-				       "%s: relocation out of range, section "
-				       "%d reloc %d sym '%s'\n", module->name,
-				       relindex, i, strtab + sym->st_name);
+				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+				       module->name, relindex, i, symname,
+				       ELF32_R_TYPE(rel->r_info), loc,
+				       sym->st_value);
 				return -ENOEXEC;
 			}
 
@@ -195,10 +196,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (!(offset & 1) ||
 			    offset <= (s32)0xff000000 ||
 			    offset >= (s32)0x01000000) {
-				printk(KERN_ERR
-				       "%s: relocation out of range, section "
-				       "%d reloc %d sym '%s'\n", module->name,
-				       relindex, i, strtab + sym->st_name);
+				pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n",
+				       module->name, relindex, i, symname,
+				       ELF32_R_TYPE(rel->r_info), loc,
+				       sym->st_value);
 				return -ENOEXEC;
 			}
 
-- 
cgit v1.2.3


From a9f43c113d7435441fb024d265aecacc4f623f5e Mon Sep 17 00:00:00 2001
From: Colin Tuckley <colin.tuckley@arm.com>
Date: Thu, 6 Jan 2011 11:16:49 +0100
Subject: ARM: 6608/1: enable bridges in pci_common_init.

Add a missing call to pci_enable_bridges() so that devices behind
bridges get found by the pci bus scan.

Signed-off-by: Chris Partington <chris.partington@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/bios32.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c
index c6273a3bfc25..d86fcd44b220 100644
--- a/arch/arm/kernel/bios32.c
+++ b/arch/arm/kernel/bios32.c
@@ -583,6 +583,11 @@ void __init pci_common_init(struct hw_pci *hw)
 			 * Assign resources.
 			 */
 			pci_bus_assign_resources(bus);
+
+			/*
+			 * Enable bridges
+			 */
+			pci_enable_bridges(bus);
 		}
 
 		/*
-- 
cgit v1.2.3


From 1dbfa187dad57d3e17207328ec8bd2d90b4177d2 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sun, 23 Jan 2011 12:08:16 +0000
Subject: ARM: irq migration: force migration off CPU going down

The force argument to irq_set_affinity really should be 'true' as
moving IRQs off a CPU which is going down isn't optional.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 28536e352deb..2f19aa5f3391 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -185,7 +185,7 @@ static void route_irq(struct irq_desc *desc, unsigned int irq, unsigned int cpu)
 
 	raw_spin_lock_irq(&desc->lock);
 	desc->irq_data.chip->irq_set_affinity(&desc->irq_data,
-					      cpumask_of(cpu), false);
+					      cpumask_of(cpu), true);
 	raw_spin_unlock_irq(&desc->lock);
 }
 
-- 
cgit v1.2.3


From 617912440bf20497d23d01ab58076998aced3f15 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sun, 23 Jan 2011 12:09:36 +0000
Subject: ARM: irq migration: ensure migration is handled safely

Ensure appropriate locks are taken to ensure that IRQ migration off
the current CPU is race-free.  We may have a concurrent set_affinity
via procfs running on another CPU in parallel with the IRQ migration,
resulting in unpredictable results.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/irq.c | 50 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 2f19aa5f3391..3535d3793e65 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -179,14 +179,21 @@ int __init arch_probe_nr_irqs(void)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static void route_irq(struct irq_desc *desc, unsigned int irq, unsigned int cpu)
+static bool migrate_one_irq(struct irq_data *d)
 {
-	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", irq, desc->irq_data.node, cpu);
+	unsigned int cpu = cpumask_any_and(d->affinity, cpu_online_mask);
+	bool ret = false;
 
-	raw_spin_lock_irq(&desc->lock);
-	desc->irq_data.chip->irq_set_affinity(&desc->irq_data,
-					      cpumask_of(cpu), true);
-	raw_spin_unlock_irq(&desc->lock);
+	if (cpu >= nr_cpu_ids) {
+		cpu = cpumask_any(cpu_online_mask);
+		ret = true;
+	}
+
+	pr_debug("IRQ%u: moving from cpu%u to cpu%u\n", d->irq, d->node, cpu);
+
+	d->chip->irq_set_affinity(d, cpumask_of(cpu), true);
+
+	return ret;
 }
 
 /*
@@ -198,25 +205,30 @@ void migrate_irqs(void)
 {
 	unsigned int i, cpu = smp_processor_id();
 	struct irq_desc *desc;
+	unsigned long flags;
+
+	local_irq_save(flags);
 
 	for_each_irq_desc(i, desc) {
 		struct irq_data *d = &desc->irq_data;
+		bool affinity_broken = false;
 
-		if (d->node == cpu) {
-			unsigned int newcpu = cpumask_any_and(d->affinity,
-							      cpu_online_mask);
-			if (newcpu >= nr_cpu_ids) {
-				if (printk_ratelimit())
-					printk(KERN_INFO "IRQ%u no longer affine to CPU%u\n",
-					       i, cpu);
+		raw_spin_lock(&desc->lock);
+		do {
+			if (desc->action == NULL)
+				break;
 
-				cpumask_setall(d->affinity);
-				newcpu = cpumask_any_and(d->affinity,
-							 cpu_online_mask);
-			}
+			if (d->node != cpu)
+				break;
 
-			route_irq(desc, i, newcpu);
-		}
+			affinity_broken = migrate_one_irq(d);
+		} while (0);
+		raw_spin_unlock(&desc->lock);
+
+		if (affinity_broken && printk_ratelimit())
+			pr_warning("IRQ%u no longer affine to CPU%u\n", i, cpu);
 	}
+
+	local_irq_restore(flags);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
-- 
cgit v1.2.3


From c191789c787f488fdb74de0ee55258f71a427704 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Sun, 23 Jan 2011 12:12:01 +0000
Subject: ARM: irq migration: update GIC migration code

This cleans up after the conversion to irq_data.  Rename the function
to match the method, and remove the now useless lookup of the irq
descriptor which is never used.  Move the bitmask calculation out of
the irq_controller_lock region.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/common/gic.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 224377211151..e21c1f4218d3 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -142,25 +142,24 @@ static int gic_set_type(struct irq_data *d, unsigned int type)
 }
 
 #ifdef CONFIG_SMP
-static int
-gic_set_cpu(struct irq_data *d, const struct cpumask *mask_val, bool force)
+static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
+			    bool force)
 {
 	void __iomem *reg = gic_dist_base(d) + GIC_DIST_TARGET + (gic_irq(d) & ~3);
 	unsigned int shift = (d->irq % 4) * 8;
 	unsigned int cpu = cpumask_first(mask_val);
-	u32 val;
-	struct irq_desc *desc;
+	u32 val, mask, bit;
 
-	spin_lock(&irq_controller_lock);
-	desc = irq_to_desc(d->irq);
-	if (desc == NULL) {
-		spin_unlock(&irq_controller_lock);
+	if (cpu >= 8)
 		return -EINVAL;
-	}
+
+	mask = 0xff << shift;
+	bit = 1 << (cpu + shift);
+
+	spin_lock(&irq_controller_lock);
 	d->node = cpu;
-	val = readl(reg) & ~(0xff << shift);
-	val |= 1 << (cpu + shift);
-	writel(val, reg);
+	val = readl(reg) & ~mask;
+	writel(val | bit, reg);
 	spin_unlock(&irq_controller_lock);
 
 	return 0;
@@ -203,7 +202,7 @@ static struct irq_chip gic_chip = {
 	.irq_unmask		= gic_unmask_irq,
 	.irq_set_type		= gic_set_type,
 #ifdef CONFIG_SMP
-	.irq_set_affinity	= gic_set_cpu,
+	.irq_set_affinity	= gic_set_affinity,
 #endif
 };
 
-- 
cgit v1.2.3


From aaa50048f6ce44af66ce0389d4cc6a8348333271 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@fluxnic.net>
Date: Tue, 25 Jan 2011 21:35:38 +0100
Subject: ARM: 6639/1: allow highmem on SMP platforms without h/w TLB ops
 broadcast

In commit e616c591405c168f6dc3dfd1221e105adfe49b8d, highmem support was
deactivated for SMP platforms without hardware TLB ops broadcast because
usage of kmap_high_get() requires that IRQs be disabled when kmap_lock
is locked which is incompatible with the IPI mechanism used by the
software TLB ops broadcast invoked through flush_all_zero_pkmaps().

The reason for kmap_high_get() is to ensure that the currently kmap'd
page usage count does not decrease to zero while we're using its
existing virtual mapping in an atomic context.  With a VIVT cache this
is essential to do due to cache coherency issues, but with a VIPT cache
this is only an optimization so not to pay the price of establishing a
second mapping if an existing one can be used.  However, on VIPT
platforms without hardware TLB maintenance we can give up on that
optimization in order to be able to use highmem.

From ARMv7 onwards the TLB ops are broadcasted in hardware, so let's
disable ARCH_NEEDS_KMAP_HIGH_GET only when CONFIG_SMP and
CONFIG_CPU_TLB_V6 are defined.

Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Tested-by: Saeed Bishara <saeed.bishara@gmail.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/highmem.h | 29 +++++++++++++++++++++++++++--
 arch/arm/mm/mmu.c              | 10 ----------
 2 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 7080e2c8fa62..a4edd19dd3d6 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -19,11 +19,36 @@
 
 extern pte_t *pkmap_page_table;
 
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
+
+/*
+ * The reason for kmap_high_get() is to ensure that the currently kmap'd
+ * page usage count does not decrease to zero while we're using its
+ * existing virtual mapping in an atomic context.  With a VIVT cache this
+ * is essential to do, but with a VIPT cache this is only an optimization
+ * so not to pay the price of establishing a second mapping if an existing
+ * one can be used.  However, on platforms without hardware TLB maintenance
+ * broadcast, we simply cannot use ARCH_NEEDS_KMAP_HIGH_GET at all since
+ * the locking involved must also disable IRQs which is incompatible with
+ * the IPI mechanism used by global TLB operations.
+ */
 #define ARCH_NEEDS_KMAP_HIGH_GET
+#if defined(CONFIG_SMP) && defined(CONFIG_CPU_TLB_V6)
+#undef ARCH_NEEDS_KMAP_HIGH_GET
+#if defined(CONFIG_HIGHMEM) && defined(CONFIG_CPU_CACHE_VIVT)
+#error "The sum of features in your kernel config cannot be supported together"
+#endif
+#endif
 
-extern void *kmap_high(struct page *page);
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
 extern void *kmap_high_get(struct page *page);
-extern void kunmap_high(struct page *page);
+#else
+static inline void *kmap_high_get(struct page *page)
+{
+	return NULL;
+}
+#endif
 
 /*
  * The following functions are already defined by <linux/highmem.h>
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 3c67e92f7d59..ff7b43b5885a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -827,16 +827,6 @@ static void __init sanity_check_meminfo(void)
 			 * rather difficult.
 			 */
 			reason = "with VIPT aliasing cache";
-		} else if (is_smp() && tlb_ops_need_broadcast()) {
-			/*
-			 * kmap_high needs to occasionally flush TLB entries,
-			 * however, if the TLB entries need to be broadcast
-			 * we may deadlock:
-			 *  kmap_high(irqs off)->flush_all_zero_pkmaps->
-			 *  flush_tlb_kernel_range->smp_call_function_many
-			 *   (must not be called with irqs off)
-			 */
-			reason = "without hardware TLB ops broadcasting";
 		}
 		if (reason) {
 			printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
-- 
cgit v1.2.3


From 74c25beeb30fa32badf575a908902cbdef4d4eb4 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 31 Jan 2011 14:43:25 +0000
Subject: ARM: vfp: improve commentry for hotplug events

Improve the documentation for the VFP hotplug notifier handler, so
that people better understand what's going on there and what has
been done for them.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/vfp/vfpmodule.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 25b89d817105..bbf3da012afd 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -489,8 +489,11 @@ void vfp_flush_hwstate(struct thread_info *thread)
 
 /*
  * VFP hardware can lose all context when a CPU goes offline.
- * Safely clear our held state when a CPU has been killed, and
- * re-enable access to VFP when the CPU comes back online.
+ * As we will be running in SMP mode with CPU hotplug, we will save the
+ * hardware state at every thread switch.  We clear our held state when
+ * a CPU has been killed, indicating that the VFP hardware doesn't contain
+ * a threads VFP state.  When a CPU starts up, we re-enable access to the
+ * VFP hardware.
  *
  * Both CPU_DYING and CPU_STARTING are called on the CPU which
  * is being offlined/onlined.
-- 
cgit v1.2.3


From b11fe38883d1de76f2f847943e085a808f83f189 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@fluxnic.net>
Date: Sat, 12 Feb 2011 22:25:27 +0100
Subject: ARM: 6663/1: make Thumb2 kernel entry point more similar to the ARM
 one

Some installers would binary patch the kernel zImage to replace the
first few nops with custom instructions.  This breaks the Thumb2 kernel
as the mode switch is right at the beginning.  Let's move it towards the
end of the nop sequence instead.

Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/boot/compressed/head.S | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 7193884ed8b0..920f4dbd4883 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -128,14 +128,14 @@ wait:		mrc	p14, 0, pc, c0, c1, 0
 		.arm				@ Always enter in ARM state
 start:
 		.type	start,#function
- THUMB(		adr	r12, BSYM(1f)	)
- THUMB(		bx	r12		)
- THUMB(		.rept	6		)
- ARM(		.rept	8		)
+		.rept	7
 		mov	r0, r0
 		.endr
+   ARM(		mov	r0, r0		)
+   ARM(		b	1f		)
+ THUMB(		adr	r12, BSYM(1f)	)
+ THUMB(		bx	r12		)
 
-		b	1f
 		.word	0x016f2818		@ Magic numbers to help the loader
 		.word	start			@ absolute load/run zImage address
 		.word	_edata			@ zImage end address
-- 
cgit v1.2.3


From 5637a126482026b37d426d76e1b18f748f309aaa Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 14 Feb 2011 15:55:45 +0000
Subject: ARM: move L1_CACHE_SHIFT_6 to mm/Kconfig

Move L1_CACHE_SHIFT related options together, rather than spreading them
across two separate Kconfig files.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/Kconfig    | 5 -----
 arch/arm/mm/Kconfig | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5cff165b7eb0..65ea7bb57c4d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -178,11 +178,6 @@ config FIQ
 config ARCH_MTD_XIP
 	bool
 
-config ARM_L1_CACHE_SHIFT_6
-	bool
-	help
-	  Setting ARM L1 cache line size to 64 Bytes.
-
 config VECTORS_BASE
 	hex
 	default 0xffff0000 if MMU || CPU_HIGH_VECTOR
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9d30c6f804b9..a51661be1412 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -845,6 +845,11 @@ config CACHE_XSC3L2
 	help
 	  This option enables the L2 cache on XScale3.
 
+config ARM_L1_CACHE_SHIFT_6
+	bool
+	help
+	  Setting ARM L1 cache line size to 64 Bytes.
+
 config ARM_L1_CACHE_SHIFT
 	int
 	default 6 if ARM_L1_CACHE_SHIFT_6
-- 
cgit v1.2.3


From 425fc47adb5bb69f76285be77a09a3341a30799e Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 14 Feb 2011 14:31:09 +0100
Subject: ARM: 6668/1: ptrace: remove single-step emulation code

PTRACE_SINGLESTEP is a ptrace request designed to offer single-stepping
support to userspace when the underlying architecture has hardware
support for this operation.

On ARM, we set arch_has_single_step() to 1 and attempt to emulate hardware
single-stepping by disassembling the current instruction to determine the
next pc and placing a software breakpoint on that location.

Unfortunately this has the following problems:

1.) Only a subset of ARMv7 instructions are supported
2.) Thumb-2 is unsupported
3.) The code is not SMP safe

We could try to fix this code, but it turns out that because of the above
issues it is rarely used in practice.  GDB, for example, uses PTRACE_POKETEXT
and PTRACE_PEEKTEXT to manage breakpoints itself and does not require any
kernel assistance.

This patch removes the single-step emulation code from ptrace meaning that
the PTRACE_SINGLESTEP request will return -EIO on ARM. Portable code must
check the return value from a ptrace call and handle the failure gracefully.

Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/processor.h |  12 --
 arch/arm/include/asm/ptrace.h    |   2 -
 arch/arm/include/asm/traps.h     |   1 +
 arch/arm/kernel/ptrace.c         | 383 +--------------------------------------
 arch/arm/kernel/ptrace.h         |  37 ----
 arch/arm/kernel/signal.c         |   9 -
 arch/arm/kernel/traps.c          |   2 +-
 7 files changed, 3 insertions(+), 443 deletions(-)
 delete mode 100644 arch/arm/kernel/ptrace.h

diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 67357baaeeeb..b439b41aeac1 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -29,19 +29,7 @@
 #define STACK_TOP_MAX	TASK_SIZE
 #endif
 
-union debug_insn {
-	u32	arm;
-	u16	thumb;
-};
-
-struct debug_entry {
-	u32			address;
-	union debug_insn	insn;
-};
-
 struct debug_info {
-	int			nsaved;
-	struct debug_entry	bp[2];
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	struct perf_event	*hbp[ARM_MAX_HBP_SLOTS];
 #endif
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 783d50f32618..a8ff22b2a391 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -130,8 +130,6 @@ struct pt_regs {
 
 #ifdef __KERNEL__
 
-#define arch_has_single_step()	(1)
-
 #define user_mode(regs)	\
 	(((regs)->ARM_cpsr & 0xf) == 0)
 
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 1b960d5ef6a5..f90756dc16dc 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -45,6 +45,7 @@ static inline int in_exception_text(unsigned long ptr)
 
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
+extern void ptrace_break(struct task_struct *tsk, struct pt_regs *regs);
 
 extern void *vectors_page;
 
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 19c6816db61e..eace844511f1 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -26,8 +26,6 @@
 #include <asm/system.h>
 #include <asm/traps.h>
 
-#include "ptrace.h"
-
 #define REG_PC	15
 #define REG_PSR	16
 /*
@@ -184,389 +182,12 @@ put_user_reg(struct task_struct *task, int offset, long data)
 	return ret;
 }
 
-static inline int
-read_u32(struct task_struct *task, unsigned long addr, u32 *res)
-{
-	int ret;
-
-	ret = access_process_vm(task, addr, res, sizeof(*res), 0);
-
-	return ret == sizeof(*res) ? 0 : -EIO;
-}
-
-static inline int
-read_instr(struct task_struct *task, unsigned long addr, u32 *res)
-{
-	int ret;
-
-	if (addr & 1) {
-		u16 val;
-		ret = access_process_vm(task, addr & ~1, &val, sizeof(val), 0);
-		ret = ret == sizeof(val) ? 0 : -EIO;
-		*res = val;
-	} else {
-		u32 val;
-		ret = access_process_vm(task, addr & ~3, &val, sizeof(val), 0);
-		ret = ret == sizeof(val) ? 0 : -EIO;
-		*res = val;
-	}
-	return ret;
-}
-
-/*
- * Get value of register `rn' (in the instruction)
- */
-static unsigned long
-ptrace_getrn(struct task_struct *child, unsigned long insn)
-{
-	unsigned int reg = (insn >> 16) & 15;
-	unsigned long val;
-
-	val = get_user_reg(child, reg);
-	if (reg == 15)
-		val += 8;
-
-	return val;
-}
-
-/*
- * Get value of operand 2 (in an ALU instruction)
- */
-static unsigned long
-ptrace_getaluop2(struct task_struct *child, unsigned long insn)
-{
-	unsigned long val;
-	int shift;
-	int type;
-
-	if (insn & 1 << 25) {
-		val = insn & 255;
-		shift = (insn >> 8) & 15;
-		type = 3;
-	} else {
-		val = get_user_reg (child, insn & 15);
-
-		if (insn & (1 << 4))
-			shift = (int)get_user_reg (child, (insn >> 8) & 15);
-		else
-			shift = (insn >> 7) & 31;
-
-		type = (insn >> 5) & 3;
-	}
-
-	switch (type) {
-	case 0:	val <<= shift;	break;
-	case 1:	val >>= shift;	break;
-	case 2:
-		val = (((signed long)val) >> shift);
-		break;
-	case 3:
- 		val = (val >> shift) | (val << (32 - shift));
-		break;
-	}
-	return val;
-}
-
-/*
- * Get value of operand 2 (in a LDR instruction)
- */
-static unsigned long
-ptrace_getldrop2(struct task_struct *child, unsigned long insn)
-{
-	unsigned long val;
-	int shift;
-	int type;
-
-	val = get_user_reg(child, insn & 15);
-	shift = (insn >> 7) & 31;
-	type = (insn >> 5) & 3;
-
-	switch (type) {
-	case 0:	val <<= shift;	break;
-	case 1:	val >>= shift;	break;
-	case 2:
-		val = (((signed long)val) >> shift);
-		break;
-	case 3:
- 		val = (val >> shift) | (val << (32 - shift));
-		break;
-	}
-	return val;
-}
-
-#define OP_MASK	0x01e00000
-#define OP_AND	0x00000000
-#define OP_EOR	0x00200000
-#define OP_SUB	0x00400000
-#define OP_RSB	0x00600000
-#define OP_ADD	0x00800000
-#define OP_ADC	0x00a00000
-#define OP_SBC	0x00c00000
-#define OP_RSC	0x00e00000
-#define OP_ORR	0x01800000
-#define OP_MOV	0x01a00000
-#define OP_BIC	0x01c00000
-#define OP_MVN	0x01e00000
-
-static unsigned long
-get_branch_address(struct task_struct *child, unsigned long pc, unsigned long insn)
-{
-	u32 alt = 0;
-
-	switch (insn & 0x0e000000) {
-	case 0x00000000:
-	case 0x02000000: {
-		/*
-		 * data processing
-		 */
-		long aluop1, aluop2, ccbit;
-
-	        if ((insn & 0x0fffffd0) == 0x012fff10) {
-		        /*
-			 * bx or blx
-			 */
-			alt = get_user_reg(child, insn & 15);
-			break;
-		}
-
-
-		if ((insn & 0xf000) != 0xf000)
-			break;
-
-		aluop1 = ptrace_getrn(child, insn);
-		aluop2 = ptrace_getaluop2(child, insn);
-		ccbit  = get_user_reg(child, REG_PSR) & PSR_C_BIT ? 1 : 0;
-
-		switch (insn & OP_MASK) {
-		case OP_AND: alt = aluop1 & aluop2;		break;
-		case OP_EOR: alt = aluop1 ^ aluop2;		break;
-		case OP_SUB: alt = aluop1 - aluop2;		break;
-		case OP_RSB: alt = aluop2 - aluop1;		break;
-		case OP_ADD: alt = aluop1 + aluop2;		break;
-		case OP_ADC: alt = aluop1 + aluop2 + ccbit;	break;
-		case OP_SBC: alt = aluop1 - aluop2 + ccbit;	break;
-		case OP_RSC: alt = aluop2 - aluop1 + ccbit;	break;
-		case OP_ORR: alt = aluop1 | aluop2;		break;
-		case OP_MOV: alt = aluop2;			break;
-		case OP_BIC: alt = aluop1 & ~aluop2;		break;
-		case OP_MVN: alt = ~aluop2;			break;
-		}
-		break;
-	}
-
-	case 0x04000000:
-	case 0x06000000:
-		/*
-		 * ldr
-		 */
-		if ((insn & 0x0010f000) == 0x0010f000) {
-			unsigned long base;
-
-			base = ptrace_getrn(child, insn);
-			if (insn & 1 << 24) {
-				long aluop2;
-
-				if (insn & 0x02000000)
-					aluop2 = ptrace_getldrop2(child, insn);
-				else
-					aluop2 = insn & 0xfff;
-
-				if (insn & 1 << 23)
-					base += aluop2;
-				else
-					base -= aluop2;
-			}
-			read_u32(child, base, &alt);
-		}
-		break;
-
-	case 0x08000000:
-		/*
-		 * ldm
-		 */
-		if ((insn & 0x00108000) == 0x00108000) {
-			unsigned long base;
-			unsigned int nr_regs;
-
-			if (insn & (1 << 23)) {
-				nr_regs = hweight16(insn & 65535) << 2;
-
-				if (!(insn & (1 << 24)))
-					nr_regs -= 4;
-			} else {
-				if (insn & (1 << 24))
-					nr_regs = -4;
-				else
-					nr_regs = 0;
-			}
-
-			base = ptrace_getrn(child, insn);
-
-			read_u32(child, base + nr_regs, &alt);
-			break;
-		}
-		break;
-
-	case 0x0a000000: {
-		/*
-		 * bl or b
-		 */
-		signed long displ;
-		/* It's a branch/branch link: instead of trying to
-		 * figure out whether the branch will be taken or not,
-		 * we'll put a breakpoint at both locations.  This is
-		 * simpler, more reliable, and probably not a whole lot
-		 * slower than the alternative approach of emulating the
-		 * branch.
-		 */
-		displ = (insn & 0x00ffffff) << 8;
-		displ = (displ >> 6) + 8;
-		if (displ != 0 && displ != 4)
-			alt = pc + displ;
-	    }
-	    break;
-	}
-
-	return alt;
-}
-
-static int
-swap_insn(struct task_struct *task, unsigned long addr,
-	  void *old_insn, void *new_insn, int size)
-{
-	int ret;
-
-	ret = access_process_vm(task, addr, old_insn, size, 0);
-	if (ret == size)
-		ret = access_process_vm(task, addr, new_insn, size, 1);
-	return ret;
-}
-
-static void
-add_breakpoint(struct task_struct *task, struct debug_info *dbg, unsigned long addr)
-{
-	int nr = dbg->nsaved;
-
-	if (nr < 2) {
-		u32 new_insn = BREAKINST_ARM;
-		int res;
-
-		res = swap_insn(task, addr, &dbg->bp[nr].insn, &new_insn, 4);
-
-		if (res == 4) {
-			dbg->bp[nr].address = addr;
-			dbg->nsaved += 1;
-		}
-	} else
-		printk(KERN_ERR "ptrace: too many breakpoints\n");
-}
-
-/*
- * Clear one breakpoint in the user program.  We copy what the hardware
- * does and use bit 0 of the address to indicate whether this is a Thumb
- * breakpoint or an ARM breakpoint.
- */
-static void clear_breakpoint(struct task_struct *task, struct debug_entry *bp)
-{
-	unsigned long addr = bp->address;
-	union debug_insn old_insn;
-	int ret;
-
-	if (addr & 1) {
-		ret = swap_insn(task, addr & ~1, &old_insn.thumb,
-				&bp->insn.thumb, 2);
-
-		if (ret != 2 || old_insn.thumb != BREAKINST_THUMB)
-			printk(KERN_ERR "%s:%d: corrupted Thumb breakpoint at "
-				"0x%08lx (0x%04x)\n", task->comm,
-				task_pid_nr(task), addr, old_insn.thumb);
-	} else {
-		ret = swap_insn(task, addr & ~3, &old_insn.arm,
-				&bp->insn.arm, 4);
-
-		if (ret != 4 || old_insn.arm != BREAKINST_ARM)
-			printk(KERN_ERR "%s:%d: corrupted ARM breakpoint at "
-				"0x%08lx (0x%08x)\n", task->comm,
-				task_pid_nr(task), addr, old_insn.arm);
-	}
-}
-
-void ptrace_set_bpt(struct task_struct *child)
-{
-	struct pt_regs *regs;
-	unsigned long pc;
-	u32 insn;
-	int res;
-
-	regs = task_pt_regs(child);
-	pc = instruction_pointer(regs);
-
-	if (thumb_mode(regs)) {
-		printk(KERN_WARNING "ptrace: can't handle thumb mode\n");
-		return;
-	}
-
-	res = read_instr(child, pc, &insn);
-	if (!res) {
-		struct debug_info *dbg = &child->thread.debug;
-		unsigned long alt;
-
-		dbg->nsaved = 0;
-
-		alt = get_branch_address(child, pc, insn);
-		if (alt)
-			add_breakpoint(child, dbg, alt);
-
-		/*
-		 * Note that we ignore the result of setting the above
-		 * breakpoint since it may fail.  When it does, this is
-		 * not so much an error, but a forewarning that we may
-		 * be receiving a prefetch abort shortly.
-		 *
-		 * If we don't set this breakpoint here, then we can
-		 * lose control of the thread during single stepping.
-		 */
-		if (!alt || predicate(insn) != PREDICATE_ALWAYS)
-			add_breakpoint(child, dbg, pc + 4);
-	}
-}
-
-/*
- * Ensure no single-step breakpoint is pending.  Returns non-zero
- * value if child was being single-stepped.
- */
-void ptrace_cancel_bpt(struct task_struct *child)
-{
-	int i, nsaved = child->thread.debug.nsaved;
-
-	child->thread.debug.nsaved = 0;
-
-	if (nsaved > 2) {
-		printk("ptrace_cancel_bpt: bogus nsaved: %d!\n", nsaved);
-		nsaved = 2;
-	}
-
-	for (i = 0; i < nsaved; i++)
-		clear_breakpoint(child, &child->thread.debug.bp[i]);
-}
-
-void user_disable_single_step(struct task_struct *task)
-{
-	task->ptrace &= ~PT_SINGLESTEP;
-	ptrace_cancel_bpt(task);
-}
-
-void user_enable_single_step(struct task_struct *task)
-{
-	task->ptrace |= PT_SINGLESTEP;
-}
-
 /*
  * Called by kernel/ptrace.c when detaching..
  */
 void ptrace_disable(struct task_struct *child)
 {
-	user_disable_single_step(child);
+	/* Nothing to do. */
 }
 
 /*
@@ -576,8 +197,6 @@ void ptrace_break(struct task_struct *tsk, struct pt_regs *regs)
 {
 	siginfo_t info;
 
-	ptrace_cancel_bpt(tsk);
-
 	info.si_signo = SIGTRAP;
 	info.si_errno = 0;
 	info.si_code  = TRAP_BRKPT;
diff --git a/arch/arm/kernel/ptrace.h b/arch/arm/kernel/ptrace.h
deleted file mode 100644
index 3926605b82ea..000000000000
--- a/arch/arm/kernel/ptrace.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- *  linux/arch/arm/kernel/ptrace.h
- *
- *  Copyright (C) 2000-2003 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/ptrace.h>
-
-extern void ptrace_cancel_bpt(struct task_struct *);
-extern void ptrace_set_bpt(struct task_struct *);
-extern void ptrace_break(struct task_struct *, struct pt_regs *);
-
-/*
- * Send SIGTRAP if we're single-stepping
- */
-static inline void single_step_trap(struct task_struct *task)
-{
-	if (task->ptrace & PT_SINGLESTEP) {
-		ptrace_cancel_bpt(task);
-		send_sig(SIGTRAP, task, 1);
-	}
-}
-
-static inline void single_step_clear(struct task_struct *task)
-{
-	if (task->ptrace & PT_SINGLESTEP)
-		ptrace_cancel_bpt(task);
-}
-
-static inline void single_step_set(struct task_struct *task)
-{
-	if (task->ptrace & PT_SINGLESTEP)
-		ptrace_set_bpt(task);
-}
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 907d5a620bca..7709668c4842 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -20,7 +20,6 @@
 #include <asm/unistd.h>
 #include <asm/vfp.h>
 
-#include "ptrace.h"
 #include "signal.h"
 
 #define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
@@ -348,8 +347,6 @@ asmlinkage int sys_sigreturn(struct pt_regs *regs)
 	if (restore_sigframe(regs, frame))
 		goto badframe;
 
-	single_step_trap(current);
-
 	return regs->ARM_r0;
 
 badframe:
@@ -383,8 +380,6 @@ asmlinkage int sys_rt_sigreturn(struct pt_regs *regs)
 	if (do_sigaltstack(&frame->sig.uc.uc_stack, NULL, regs->ARM_sp) == -EFAULT)
 		goto badframe;
 
-	single_step_trap(current);
-
 	return regs->ARM_r0;
 
 badframe:
@@ -704,8 +699,6 @@ static void do_signal(struct pt_regs *regs, int syscall)
 	if (try_to_freeze())
 		goto no_signal;
 
-	single_step_clear(current);
-
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 	if (signr > 0) {
 		sigset_t *oldset;
@@ -724,7 +717,6 @@ static void do_signal(struct pt_regs *regs, int syscall)
 			if (test_thread_flag(TIF_RESTORE_SIGMASK))
 				clear_thread_flag(TIF_RESTORE_SIGMASK);
 		}
-		single_step_set(current);
 		return;
 	}
 
@@ -770,7 +762,6 @@ static void do_signal(struct pt_regs *regs, int syscall)
 			sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
 		}
 	}
-	single_step_set(current);
 }
 
 asmlinkage void
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 7f53c3651c58..21ac43f1c2d0 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -23,6 +23,7 @@
 #include <linux/kexec.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
@@ -32,7 +33,6 @@
 #include <asm/unwind.h>
 #include <asm/tls.h>
 
-#include "ptrace.h"
 #include "signal.h"
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
-- 
cgit v1.2.3


From 6d7d0ae51574943bf571d269da3243257a2d15db Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Mon, 21 Feb 2011 07:06:45 +0100
Subject: ARM: 6750/1: improvements to compressed/head.S

In the case of a conflict between the memory used by the compressed
kernel with its decompressor code and the memory used for the
decompressed kernel, we currently store the later after the former and
relocate it afterwards.

This would be more efficient to do this the other way around i.e.
relocate the compressed data up front instead, resulting in a smaller
copy.  That also has the advantage of making the code smaller and more
straight forward.

Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/boot/compressed/head.S | 239 ++++++++++++++++++----------------------
 1 file changed, 110 insertions(+), 129 deletions(-)

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 920f4dbd4883..39859216af00 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -174,9 +174,7 @@ not_angel:
 		 */
 
 		.text
-		adr	r0, LC0
-		ldmia	r0, {r1, r2, r3, r5, r6, r11, ip}
-		ldr	sp, [r0, #28]
+
 #ifdef CONFIG_AUTO_ZRELADDR
 		@ determine final kernel image address
 		mov	r4, pc
@@ -185,35 +183,108 @@ not_angel:
 #else
 		ldr	r4, =zreladdr
 #endif
-		subs	r0, r0, r1		@ calculate the delta offset
 
-						@ if delta is zero, we are
-		beq	not_relocated		@ running at the address we
-						@ were linked at.
+		bl	cache_on
+
+restart:	adr	r0, LC0
+		ldmia	r0, {r1, r2, r3, r5, r6, r9, r11, r12}
+		ldr	sp, [r0, #32]
+
+		/*
+		 * We might be running at a different address.  We need
+		 * to fix up various pointers.
+		 */
+		sub	r0, r0, r1		@ calculate the delta offset
+		add	r5, r5, r0		@ _start
+		add	r6, r6, r0		@ _edata
 
+#ifndef CONFIG_ZBOOT_ROM
+		/* malloc space is above the relocated stack (64k max) */
+		add	sp, sp, r0
+		add	r10, sp, #0x10000
+#else
 		/*
-		 * We're running at a different address.  We need to fix
-		 * up various pointers:
-		 *   r5 - zImage base address (_start)
-		 *   r6 - size of decompressed image
-		 *   r11 - GOT start
-		 *   ip - GOT end
+		 * With ZBOOT_ROM the bss/stack is non relocatable,
+		 * but someone could still run this code from RAM,
+		 * in which case our reference is _edata.
 		 */
-		add	r5, r5, r0
+		mov	r10, r6
+#endif
+
+/*
+ * Check to see if we will overwrite ourselves.
+ *   r4  = final kernel address
+ *   r5  = start of this image
+ *   r9  = size of decompressed image
+ *   r10 = end of this image, including  bss/stack/malloc space if non XIP
+ * We basically want:
+ *   r4 >= r10 -> OK
+ *   r4 + image length <= r5 -> OK
+ */
+		cmp	r4, r10
+		bhs	wont_overwrite
+		add	r10, r4, r9
+		cmp	r10, r5
+		bls	wont_overwrite
+
+/*
+ * Relocate ourselves past the end of the decompressed kernel.
+ *   r5  = start of this image
+ *   r6  = _edata
+ *   r10 = end of the decompressed kernel
+ * Because we always copy ahead, we need to do it from the end and go
+ * backward in case the source and destination overlap.
+ */
+		/* Round up to next 256-byte boundary. */
+		add	r10, r10, #256
+		bic	r10, r10, #255
+
+		sub	r9, r6, r5		@ size to copy
+		add	r9, r9, #31		@ rounded up to a multiple
+		bic	r9, r9, #31		@ ... of 32 bytes
+		add	r6, r9, r5
+		add	r9, r9, r10
+
+1:		ldmdb	r6!, {r0 - r3, r10 - r12, lr}
+		cmp	r6, r5
+		stmdb	r9!, {r0 - r3, r10 - r12, lr}
+		bhi	1b
+
+		/* Preserve offset to relocated code. */
+		sub	r6, r9, r6
+
+		bl	cache_clean_flush
+
+		adr	r0, BSYM(restart)
+		add	r0, r0, r6
+		mov	pc, r0
+
+wont_overwrite:
+/*
+ * If delta is zero, we are running at the address we were linked at.
+ *   r0  = delta
+ *   r2  = BSS start
+ *   r3  = BSS end
+ *   r4  = kernel execution address
+ *   r7  = architecture ID
+ *   r8  = atags pointer
+ *   r11 = GOT start
+ *   r12 = GOT end
+ *   sp  = stack pointer
+ */
+		teq	r0, #0
+		beq	not_relocated
 		add	r11, r11, r0
-		add	ip, ip, r0
+		add	r12, r12, r0
 
 #ifndef CONFIG_ZBOOT_ROM
 		/*
 		 * If we're running fully PIC === CONFIG_ZBOOT_ROM = n,
 		 * we need to fix up pointers into the BSS region.
-		 *   r2 - BSS start
-		 *   r3 - BSS end
-		 *   sp - stack pointer
+		 * Note that the stack pointer has already been fixed up.
 		 */
 		add	r2, r2, r0
 		add	r3, r3, r0
-		add	sp, sp, r0
 
 		/*
 		 * Relocate all entries in the GOT table.
@@ -221,7 +292,7 @@ not_angel:
 1:		ldr	r1, [r11, #0]		@ relocate entries in the GOT
 		add	r1, r1, r0		@ table.  This fixes up the
 		str	r1, [r11], #4		@ C references.
-		cmp	r11, ip
+		cmp	r11, r12
 		blo	1b
 #else
 
@@ -234,7 +305,7 @@ not_angel:
 		cmphs	r3, r1			@ _end < entry
 		addlo	r1, r1, r0		@ table.  This fixes up the
 		str	r1, [r11], #4		@ C references.
-		cmp	r11, ip
+		cmp	r11, r12
 		blo	1b
 #endif
 
@@ -246,76 +317,24 @@ not_relocated:	mov	r0, #0
 		cmp	r2, r3
 		blo	1b
 
-		/*
-		 * The C runtime environment should now be setup
-		 * sufficiently.  Turn the cache on, set up some
-		 * pointers, and start decompressing.
-		 */
-		bl	cache_on
-
-		mov	r1, sp			@ malloc space above stack
-		add	r2, sp, #0x10000	@ 64k max
-
 /*
- * Check to see if we will overwrite ourselves.
- *   r4 = final kernel address
- *   r5 = start of this image
- *   r6 = size of decompressed image
- *   r2 = end of malloc space (and therefore this image)
- * We basically want:
- *   r4 >= r2 -> OK
- *   r4 + image length <= r5 -> OK
+ * The C runtime environment should now be setup sufficiently.
+ * Set up some pointers, and start decompressing.
+ *   r4  = kernel execution address
+ *   r7  = architecture ID
+ *   r8  = atags pointer
  */
-		cmp	r4, r2
-		bhs	wont_overwrite
-		add	r0, r4, r6
-		cmp	r0, r5
-		bls	wont_overwrite
-
-		mov	r5, r2			@ decompress after malloc space
-		mov	r0, r5
+		mov	r0, r4
+		mov	r1, sp			@ malloc space above stack
+		add	r2, sp, #0x10000	@ 64k max
 		mov	r3, r7
 		bl	decompress_kernel
-
-		add	r0, r0, #127 + 128	@ alignment + stack
-		bic	r0, r0, #127		@ align the kernel length
-/*
- * r0     = decompressed kernel length
- * r1-r3  = unused
- * r4     = kernel execution address
- * r5     = decompressed kernel start
- * r7     = architecture ID
- * r8     = atags pointer
- * r9-r12,r14 = corrupted
- */
-		add	r1, r5, r0		@ end of decompressed kernel
-		adr	r2, reloc_start
-		ldr	r3, LC1
-		add	r3, r2, r3
-1:		ldmia	r2!, {r9 - r12, r14}	@ copy relocation code
-		stmia	r1!, {r9 - r12, r14}
-		ldmia	r2!, {r9 - r12, r14}
-		stmia	r1!, {r9 - r12, r14}
-		cmp	r2, r3
-		blo	1b
-		mov	sp, r1
-		add	sp, sp, #128		@ relocate the stack
-
 		bl	cache_clean_flush
- ARM(		add	pc, r5, r0		) @ call relocation code
- THUMB(		add	r12, r5, r0		)
- THUMB(		mov	pc, r12			) @ call relocation code
-
-/*
- * We're not in danger of overwriting ourselves.  Do this the simple way.
- *
- * r4     = kernel execution address
- * r7     = architecture ID
- */
-wont_overwrite:	mov	r0, r4
-		mov	r3, r7
-		bl	decompress_kernel
-		b	call_kernel
+		bl	cache_off
+		mov	r0, #0			@ must be zero
+		mov	r1, r7			@ restore architecture number
+		mov	r2, r8			@ restore atags pointer
+		mov	pc, r4			@ call kernel
 
 		.align	2
 		.type	LC0, #object
@@ -323,11 +342,11 @@ LC0:		.word	LC0			@ r1
 		.word	__bss_start		@ r2
 		.word	_end			@ r3
 		.word	_start			@ r5
-		.word	_image_size		@ r6
+		.word	_edata			@ r6
+		.word	_image_size		@ r9
 		.word	_got_start		@ r11
 		.word	_got_end		@ ip
 		.word	user_stack_end		@ sp
-LC1:		.word	reloc_end - reloc_start
 		.size	LC0, . - LC0
 
 #ifdef CONFIG_ARCH_RPC
@@ -353,7 +372,7 @@ params:		ldr	r0, =0x10000100		@ params_phys for RPC
  * On exit,
  *  r0, r1, r2, r3, r9, r10, r12 corrupted
  * This routine must preserve:
- *  r4, r5, r6, r7, r8
+ *  r4, r7, r8
  */
 		.align	5
 cache_on:	mov	r3, #8			@ cache_on function
@@ -550,43 +569,6 @@ __common_mmu_cache_on:
 		sub	pc, lr, r0, lsr #32	@ properly flush pipeline
 #endif
 
-/*
- * All code following this line is relocatable.  It is relocated by
- * the above code to the end of the decompressed kernel image and
- * executed there.  During this time, we have no stacks.
- *
- * r0     = decompressed kernel length
- * r1-r3  = unused
- * r4     = kernel execution address
- * r5     = decompressed kernel start
- * r7     = architecture ID
- * r8     = atags pointer
- * r9-r12,r14 = corrupted
- */
-		.align	5
-reloc_start:	add	r9, r5, r0
-		sub	r9, r9, #128		@ do not copy the stack
-		debug_reloc_start
-		mov	r1, r4
-1:
-		.rept	4
-		ldmia	r5!, {r0, r2, r3, r10 - r12, r14}	@ relocate kernel
-		stmia	r1!, {r0, r2, r3, r10 - r12, r14}
-		.endr
-
-		cmp	r5, r9
-		blo	1b
-		mov	sp, r1
-		add	sp, sp, #128		@ relocate the stack
-		debug_reloc_end
-
-call_kernel:	bl	cache_clean_flush
-		bl	cache_off
-		mov	r0, #0			@ must be zero
-		mov	r1, r7			@ restore architecture number
-		mov	r2, r8			@ restore atags pointer
-		mov	pc, r4			@ call kernel
-
 /*
  * Here follow the relocatable cache support functions for the
  * various processors.  This is a generic hook for locating an
@@ -791,7 +773,7 @@ proc_types:
  * On exit,
  *  r0, r1, r2, r3, r9, r12 corrupted
  * This routine must preserve:
- *  r4, r6, r7
+ *  r4, r7, r8
  */
 		.align	5
 cache_off:	mov	r3, #12			@ cache_off function
@@ -866,7 +848,7 @@ __armv3_mmu_cache_off:
  * On exit,
  *  r1, r2, r3, r9, r10, r11, r12 corrupted
  * This routine must preserve:
- *  r0, r4, r5, r6, r7
+ *  r4, r6, r7, r8
  */
 		.align	5
 cache_clean_flush:
@@ -1088,7 +1070,6 @@ memdump:	mov	r12, r0
 #endif
 
 		.ltorg
-reloc_end:
 
 		.align
 		.section ".stack", "aw", %nobits
-- 
cgit v1.2.3


From d239b1dc093d551046a909920b5310c1d1e308c1 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Mon, 21 Feb 2011 04:57:38 +0100
Subject: ARM: 6746/1: remove the 4x expansion presumption while decompressing
 the kernel

We currently presume a 4x expansion to guess the decompressed kernel size
in order to determine if the decompressed kernel is in conflict with
the location where zImage is loaded.  This guess may cause many issues
by overestimating the final kernel image size:

- This may force a needless relocation if the location of zImage was
  fine, wasting some precious microseconds of boot time.

- The relocation may be located way too far, possibly overwriting the
  initrd image in RAM.

- If the kernel image includes a large already-compressed initramfs image
  then the problem is even more exacerbated.

And if by some strange means the 4x guess is too low then we may overwrite
ourselves with the decompressed image.

So let's use the exact decompressed kernel image size instead.  For that
we need to rely on the stat command, but this is hardly a new build
dependency as the kernel already depends on many external commands
to be built provided by the coreutils package where stat is found.

Signed-off-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/boot/compressed/Makefile       | 4 +++-
 arch/arm/boot/compressed/vmlinux.lds.in | 3 ---
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 0a8f748e506a..9d328be6e5e3 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -83,9 +83,11 @@ endif
 EXTRA_CFLAGS  := -fpic -fno-builtin
 EXTRA_AFLAGS  := -Wa,-march=all
 
+# Provide size of uncompressed kernel to the decompressor via a linker symbol.
+LDFLAGS_vmlinux := --defsym _image_size=$(shell stat -c "%s" $(obj)/../Image)
 # Supply ZRELADDR to the decompressor via a linker symbol.
 ifneq ($(CONFIG_AUTO_ZRELADDR),y)
-LDFLAGS_vmlinux := --defsym zreladdr=$(ZRELADDR)
+LDFLAGS_vmlinux += --defsym zreladdr=$(ZRELADDR)
 endif
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux += --be8
diff --git a/arch/arm/boot/compressed/vmlinux.lds.in b/arch/arm/boot/compressed/vmlinux.lds.in
index 366a924019ac..5309909d7282 100644
--- a/arch/arm/boot/compressed/vmlinux.lds.in
+++ b/arch/arm/boot/compressed/vmlinux.lds.in
@@ -43,9 +43,6 @@ SECTIONS
 
   _etext = .;
 
-  /* Assume size of decompressed image is 4x the compressed image */
-  _image_size = (_etext - _text) * 4;
-
   _got_start = .;
   .got			: { *(.got) }
   _got_end = .;
-- 
cgit v1.2.3


From 2839e06c95d12ada034cf9b63da60334c7c6358b Mon Sep 17 00:00:00 2001
From: Santosh Shilimkar <santosh.shilimkar@ti.com>
Date: Tue, 8 Mar 2011 06:59:54 +0100
Subject: ARM: 6795/1: l2x0: Errata fix for flush by Way operation can cause
 data corrupti

PL310 implements the Clean & Invalidate by Way L2 cache maintenance
operation (offset 0x7FC). This operation runs in background so that
PL310 can handle normal accesses while it is in progress. Under very
rare circumstances, due to this erratum, write data can be lost when
PL310 treats a cacheable write transaction during a Clean & Invalidate
by Way operation.

Workaround:
Disable Write-Back and Cache Linefill (Debug Control Register)
Clean & Invalidate by Way (0x7FC)
Re-enable Write-Back and Cache Linefill (Debug Control Register)

This patch also removes any OMAP dependency on PL310 Errata's

Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/Kconfig                  | 15 ++++++++++++---
 arch/arm/include/asm/outercache.h |  1 +
 arch/arm/mm/cache-l2x0.c          | 32 ++++++++++++++++++--------------
 3 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 65ea7bb57c4d..ef41f7e39f69 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1135,7 +1135,7 @@ config ARM_ERRATA_742231
 
 config PL310_ERRATA_588369
 	bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
-	depends on CACHE_L2X0 && ARCH_OMAP4
+	depends on CACHE_L2X0
 	help
 	   The PL310 L2 cache controller implements three types of Clean &
 	   Invalidate maintenance operations: by Physical Address
@@ -1144,8 +1144,7 @@ config PL310_ERRATA_588369
 	   clean operation followed immediately by an invalidate operation,
 	   both performing to the same memory location. This functionality
 	   is not correctly implemented in PL310 as clean lines are not
-	   invalidated as a result of these operations. Note that this errata
-	   uses Texas Instrument's secure monitor api.
+	   invalidated as a result of these operations.
 
 config ARM_ERRATA_720789
 	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
@@ -1172,6 +1171,16 @@ config ARM_ERRATA_743622
 	  visible impact on the overall performance or power consumption of the
 	  processor.
 
+config PL310_ERRATA_727915
+	bool "Background Clean & Invalidate by Way operation can cause data corruption"
+	depends on CACHE_L2X0
+	help
+	  PL310 implements the Clean & Invalidate by Way L2 cache maintenance
+	  operation (offset 0x7FC). This operation runs in background so that
+	  PL310 can handle normal accesses while it is in progress. Under very
+	  rare circumstances, due to this erratum, write data can be lost when
+	  PL310 treats a cacheable write transaction during a Clean &
+	  Invalidate by Way operation.
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index fc1900925275..348d513afa92 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -31,6 +31,7 @@ struct outer_cache_fns {
 #ifdef CONFIG_OUTER_CACHE_SYNC
 	void (*sync)(void);
 #endif
+	void (*set_debug)(unsigned long);
 };
 
 #ifdef CONFIG_OUTER_CACHE
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 170c9bb95866..803bce8845a7 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -67,18 +67,24 @@ static inline void l2x0_inv_line(unsigned long addr)
 	writel_relaxed(addr, base + L2X0_INV_LINE_PA);
 }
 
-#ifdef CONFIG_PL31