From 1eef5d2f1b461c120bcd82077edee5ec706ac53b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 19 Aug 2015 21:23:48 +0100
Subject: [PATCH 01/17] ARM: domains: switch to keeping domain value in
 register

Rather than modifying both the domain access control register and our
per-thread copy, modify only the domain access control register, and
use the per-thread copy to save and restore the register over context
switches.  We can also avoid the explicit initialisation of the
init thread_info structure.

This allows us to avoid needing to gain access to the thread information
at the uaccess control sites.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h      | 20 +++++++++++++++-----
 arch/arm/include/asm/thread_info.h |  3 ---
 arch/arm/kernel/entry-armv.S       |  2 ++
 arch/arm/kernel/process.c          | 13 ++++++++++---
 4 files changed, 27 insertions(+), 11 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 6ddbe446425e..7f2941905714 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -59,6 +59,17 @@
 
 #ifndef __ASSEMBLY__
 
+static inline unsigned int get_domain(void)
+{
+	unsigned int domain;
+
+	asm(
+	"mrc	p15, 0, %0, c3, c0	@ get domain"
+	 : "=r" (domain));
+
+	return domain;
+}
+
 #ifdef CONFIG_CPU_USE_DOMAINS
 static inline void set_domain(unsigned val)
 {
@@ -70,11 +81,10 @@ static inline void set_domain(unsigned val)
 
 #define modify_domain(dom,type)					\
 	do {							\
-	struct thread_info *thread = current_thread_info();	\
-	unsigned int domain = thread->cpu_domain;		\
-	domain &= ~domain_val(dom, DOMAIN_MANAGER);		\
-	thread->cpu_domain = domain | domain_val(dom, type);	\
-	set_domain(thread->cpu_domain);				\
+		unsigned int domain = get_domain();		\
+		domain &= ~domain_val(dom, DOMAIN_MANAGER);	\
+		domain = domain | domain_val(dom, type);	\
+		set_domain(domain);				\
 	} while (0)
 
 #else
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index bd32eded3e50..0a0aec410d8c 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -74,9 +74,6 @@ struct thread_info {
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7dac3086e361..d19adcf6c580 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -770,6 +770,8 @@ ENTRY(__switch_to)
 	ldr	r4, [r2, #TI_TP_VALUE]
 	ldr	r5, [r2, #TI_TP_VALUE + 4]
 #ifdef CONFIG_CPU_USE_DOMAINS
+	mrc	p15, 0, r6, c3, c0, 0		@ Get domain register
+	str	r6, [r1, #TI_CPU_DOMAIN]	@ Save old domain register
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	switch_tls r1, r4, r5, r3, r7
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index f192a2a41719..e722f9b3c9b1 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -146,10 +146,9 @@ void __show_regs(struct pt_regs *regs)
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac;
+			unsigned int transbase, dac = get_domain();
 			asm("mrc p15, 0, %0, c2, c0\n\t"
-			    "mrc p15, 0, %1, c3, c0\n"
-			    : "=r" (transbase), "=r" (dac));
+			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
 			  	transbase, dac);
 		}
@@ -210,6 +209,14 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+	/*
+	 * Copy the initial value of the domain access control register
+	 * from the current thread: thread->addr_limit will have been
+	 * copied from the current thread via setup_thread_stack() in
+	 * kernel/fork.c
+	 */
+	thread->cpu_domain = get_domain();
+
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
 		childregs->ARM_r0 = 0;

From 8e798706f7e9cd7f096aa194de90269dde83773e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 19 Aug 2015 22:36:24 +0100
Subject: [PATCH 02/17] ARM: domains: provide domain_mask()

Provide a macro to generate the mask for a domain, rather than using
domain_val(, DOMAIN_MANAGER) which won't work when CPU_USE_DOMAINS
is turned off.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 7f2941905714..045b9b453bcd 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -55,7 +55,8 @@
 #define DOMAIN_MANAGER	1
 #endif
 
-#define domain_val(dom,type)	((type) << (2*(dom)))
+#define domain_mask(dom)	((3) << (2 * (dom)))
+#define domain_val(dom,type)	((type) << (2 * (dom)))
 
 #ifndef __ASSEMBLY__
 
@@ -82,7 +83,7 @@ static inline void set_domain(unsigned val)
 #define modify_domain(dom,type)					\
 	do {							\
 		unsigned int domain = get_domain();		\
-		domain &= ~domain_val(dom, DOMAIN_MANAGER);	\
+		domain &= ~domain_mask(dom);			\
 		domain = domain | domain_val(dom, type);	\
 		set_domain(domain);				\
 	} while (0)

From 0171356a7708af01ad3224702b7f0aaa5b7a1399 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 21 Aug 2015 09:23:26 +0100
Subject: [PATCH 03/17] ARM: domains: move initial domain setting value to
 asm/domains.h

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h | 6 ++++++
 arch/arm/kernel/head.S        | 5 +----
 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 045b9b453bcd..4218f88e8f7e 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -58,6 +58,12 @@
 #define domain_mask(dom)	((3) << (2 * (dom)))
 #define domain_val(dom,type)	((type) << (2 * (dom)))
 
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+
 #ifndef __ASSEMBLY__
 
 static inline unsigned int get_domain(void)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index bd755d97e459..d56e5e9a9e1e 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -461,10 +461,7 @@ __enable_mmu:
 #ifdef CONFIG_ARM_LPAE
 	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
 #else
-	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-		      domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	mov	r5, #DACR_INIT
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 #endif

From 3c2aed5b28819564e1a07b4686bd89802bcc4d6b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 21 Aug 2015 09:30:16 +0100
Subject: [PATCH 04/17] ARM: domains: get rid of manager mode for user domain

Since we switched to early trap initialisation in 94e5a85b3be0
("ARM: earlier initialization of vectors page") we haven't been writing
directly to the vectors page, and so there's no need for this domain
to be in manager mode.  Switch it to client mode.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h | 2 +-
 arch/arm/kernel/traps.c       | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 4218f88e8f7e..08b601e69ddc 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -59,7 +59,7 @@
 #define domain_val(dom,type)	((type) << (2 * (dom)))
 
 #define DACR_INIT \
-	(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
+	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 	 domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
 	 domain_val(DOMAIN_IO, DOMAIN_CLIENT))
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index d358226236f2..969f9d9e665f 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -870,7 +870,6 @@ void __init early_trap_init(void *vectors_base)
 	kuser_init(vectors_base);
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE * 2);
-	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
 #else /* ifndef CONFIG_CPU_V7M */
 	/*
 	 * on V7-M there is no need to copy the vector table to a dedicated

From a02d8dfd54cdf3b1b0464ccc2c1c4afe2c003a35 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 21 Aug 2015 09:38:31 +0100
Subject: [PATCH 05/17] ARM: domains: keep vectors in separate domain

Keep the machine vectors in its own domain to avoid software based
user access control from making the vector code inaccessible, and
thereby deadlocking the machine.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h               |  4 +++-
 arch/arm/include/asm/pgtable-2level-hwdef.h |  1 +
 arch/arm/mm/mmu.c                           |  4 ++--
 arch/arm/mm/pgd.c                           | 10 ++++++++++
 4 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 08b601e69ddc..396a12e486fe 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -43,6 +43,7 @@
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
+#define DOMAIN_VECTORS	3
 
 /*
  * Domain types
@@ -62,7 +63,8 @@
 	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 	 domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
-	 domain_val(DOMAIN_IO, DOMAIN_CLIENT))
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/arm/include/asm/pgtable-2level-hwdef.h b/arch/arm/include/asm/pgtable-2level-hwdef.h
index 5e68278e953e..d0131ee6f6af 100644
--- a/arch/arm/include/asm/pgtable-2level-hwdef.h
+++ b/arch/arm/include/asm/pgtable-2level-hwdef.h
@@ -23,6 +23,7 @@
 #define PMD_PXNTABLE		(_AT(pmdval_t, 1) << 2)     /* v7 */
 #define PMD_BIT4		(_AT(pmdval_t, 1) << 4)
 #define PMD_DOMAIN(x)		(_AT(pmdval_t, (x)) << 5)
+#define PMD_DOMAIN_MASK		PMD_DOMAIN(0x0f)
 #define PMD_PROTECTION		(_AT(pmdval_t, 1) << 9)		/* v5 */
 /*
  *   - section
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6ca7d9aa896f..a016de248034 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -291,13 +291,13 @@ static struct mem_type mem_types[] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_HIGH_VECTORS] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
 				L_PTE_USER | L_PTE_RDONLY,
 		.prot_l1   = PMD_TYPE_TABLE,
-		.domain    = DOMAIN_USER,
+		.domain    = DOMAIN_VECTORS,
 	},
 	[MT_MEMORY_RWX] = {
 		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY,
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a3681f11dd9f..e683db1b90a3 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -84,6 +84,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		if (!new_pte)
 			goto no_pte;
 
+#ifndef CONFIG_ARM_LPAE
+		/*
+		 * Modify the PTE pointer to have the correct domain.  This
+		 * needs to be the vectors domain to avoid the low vectors
+		 * being unmapped.
+		 */
+		pmd_val(*new_pmd) &= ~PMD_DOMAIN_MASK;
+		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
+#endif
+
 		init_pud = pud_offset(init_pgd, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);

From 1fb6755f16872ad256c18cce2830f9087502dffd Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 21 Aug 2015 09:42:10 +0100
Subject: [PATCH 06/17] ARM: domains: remove DOMAIN_TABLE

DOMAIN_TABLE is not used; in any case, it aliases to the kernel domain.
Remove this definition.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 396a12e486fe..2be929549938 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -34,12 +34,10 @@
  */
 #ifndef CONFIG_IO_36
 #define DOMAIN_KERNEL	0
-#define DOMAIN_TABLE	0
 #define DOMAIN_USER	1
 #define DOMAIN_IO	2
 #else
 #define DOMAIN_KERNEL	2
-#define DOMAIN_TABLE	2
 #define DOMAIN_USER	1
 #define DOMAIN_IO	0
 #endif
@@ -62,7 +60,6 @@
 #define DACR_INIT \
 	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
-	 domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
 	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
 

From 08446b129bbde34665c423d882f857a45b8c3aed Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Tue, 25 Aug 2015 14:59:15 +0100
Subject: [PATCH 07/17] ARM: mm: improve do_ldrd_abort macro

Improve the do_ldrd_abort macro code - firstly, it inefficiently checks
for the LDRD encoding by doing a multi-stage test of various bits.  This
can be simplified by generating a mask, bitmasking the instruction and
then comparing the result.

Secondly, we want to be able to test the result rather than branching
to do_DataAbort, so remove the branch at the end and rename the macro
to 'teq_ldrd' to reflect it's new usage.  teq_ldrd macro returns 'eq'
if the instruction was a LDRD.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mm/abort-ev5t.S  |  3 ++-
 arch/arm/mm/abort-ev5tj.S |  3 ++-
 arch/arm/mm/abort-ev6.S   |  3 ++-
 arch/arm/mm/abort-macro.S | 13 +++++--------
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index a0908d4653a3..c913031b79cc 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -22,7 +22,8 @@ ENTRY(v5t_early_abort)
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ check write
 	orreq	r1, r1, #1 << 11
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index 4006b7a61264..1b80d71adb0f 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -24,7 +24,8 @@ ENTRY(v5tj_early_abort)
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 8c48c5c22a33..113704f30e9f 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -34,7 +34,8 @@ ENTRY(v6_early_abort)
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
-	do_ldrd_abort tmp=ip, insn=r3
+	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
+	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 2cbf68ef0e83..50d6c0a900b1 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -29,12 +29,9 @@ not_thumb:
  *   [7:4] == 1101
  *    [20] == 0
  */
-	.macro	do_ldrd_abort, tmp, insn
-	tst	\insn, #0x0e100000		@ [27:25,20] == 0
-	bne	not_ldrd
-	and	\tmp, \insn, #0x000000f0	@ [7:4] == 1101
-	cmp	\tmp, #0x000000d0
-	beq	do_DataAbort
-not_ldrd:
+	.macro	teq_ldrd, tmp, insn
+	mov	\tmp, #0x0e100000
+	orr	\tmp, #0x000000f0
+	and	\tmp, \insn, \tmp
+	teq	\tmp, #0x000000d0
 	.endm
-

From 3fba7e23f754a9a6e639b640fa2a393712ffe1b8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 19 Aug 2015 11:02:28 +0100
Subject: [PATCH 08/17] ARM: uaccess: provide uaccess_save_and_enable() and
 uaccess_restore()

Provide uaccess_save_and_enable() and uaccess_restore() to permit
control of userspace visibility to the kernel, and hook these into
the appropriate places in the kernel where we need to access
userspace.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/futex.h       | 19 +++++++-
 arch/arm/include/asm/uaccess.h     | 71 +++++++++++++++++++++++++++---
 arch/arm/kernel/armksyms.c         |  6 +--
 arch/arm/lib/clear_user.S          |  6 +--
 arch/arm/lib/copy_from_user.S      |  6 +--
 arch/arm/lib/copy_to_user.S        |  6 +--
 arch/arm/lib/uaccess_with_memcpy.c |  4 +-
 7 files changed, 97 insertions(+), 21 deletions(-)

diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 5eed82809d82..6795368ad023 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -22,8 +22,11 @@
 #ifdef CONFIG_SMP
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags;				\
 	smp_mb();						\
 	prefetchw(uaddr);					\
+	__ua_flags = uaccess_save_and_enable();			\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -34,12 +37,15 @@
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret;
 	u32 val;
 
@@ -49,6 +55,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	smp_mb();
 	/* Prefetching cannot fault */
 	prefetchw(uaddr);
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -61,6 +68,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "=&r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 	smp_mb();
 
 	*uval = val;
@@ -73,6 +81,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
+({								\
+	unsigned int __ua_flags = uaccess_save_and_enable();	\
 	__asm__ __volatile__(					\
 	"1:	" TUSER(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
@@ -81,12 +91,15 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	__futex_atomic_ex_table("%5")				\
 	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
-	: "cc", "memory")
+	: "cc", "memory");					\
+	uaccess_restore(__ua_flags);				\
+})
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 			      u32 oldval, u32 newval)
 {
+	unsigned int __ua_flags;
 	int ret = 0;
 	u32 val;
 
@@ -94,6 +107,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	preempt_disable();
+	__ua_flags = uaccess_save_and_enable();
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	" TUSER(ldr) "	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -103,6 +117,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	: "+r" (ret), "=&r" (val)
 	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
 	: "cc", "memory");
+	uaccess_restore(__ua_flags);
 
 	*uval = val;
 	preempt_enable();
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 74b17d09ef7a..82880132f941 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -49,6 +49,21 @@ struct exception_table_entry
 
 extern int fixup_exception(struct pt_regs *regs);
 
+/*
+ * These two functions allow hooking accesses to userspace to increase
+ * system integrity by ensuring that the kernel can not inadvertantly
+ * perform such accesses (eg, via list poison values) which could then
+ * be exploited for priviledge escalation.
+ */
+static inline unsigned int uaccess_save_and_enable(void)
+{
+	return 0;
+}
+
+static inline void uaccess_restore(unsigned int flags)
+{
+}
+
 /*
  * These two are intentionally not defined anywhere - if the kernel
  * code generates any references to them, that's a bug.
@@ -165,6 +180,7 @@ extern int __get_user_64t_4(void *);
 		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			if (sizeof((x)) >= 8)				\
@@ -192,6 +208,7 @@ extern int __get_user_64t_4(void *);
 			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		x = (typeof(*(p))) __r2;				\
 		__e;							\
 	})
@@ -224,6 +241,7 @@ extern int __put_user_8(void *, unsigned long long);
 		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
+		unsigned int __ua_flags = uaccess_save_and_enable();	\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
 			__put_user_x(__r2, __p, __e, __l, 1);		\
@@ -239,6 +257,7 @@ extern int __put_user_8(void *, unsigned long long);
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
+		uaccess_restore(__ua_flags);				\
 		__e;							\
 	})
 
@@ -300,14 +319,17 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
 	unsigned long __gu_val;						\
+	unsigned int __ua_flags;					\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1:	__get_user_asm_byte(__gu_val, __gu_addr, err);	break;	\
 	case 2:	__get_user_asm_half(__gu_val, __gu_addr, err);	break;	\
 	case 4:	__get_user_asm_word(__gu_val, __gu_addr, err);	break;	\
 	default: (__gu_val) = __get_user_bad();				\
 	}								\
+	uaccess_restore(__ua_flags);					\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
@@ -381,9 +403,11 @@ do {									\
 #define __put_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __pu_addr = (unsigned long)(ptr);			\
+	unsigned int __ua_flags;					\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
 	might_fault();							\
+	__ua_flags = uaccess_save_and_enable();				\
 	switch (sizeof(*(ptr))) {					\
 	case 1: __put_user_asm_byte(__pu_val, __pu_addr, err);	break;	\
 	case 2: __put_user_asm_half(__pu_val, __pu_addr, err);	break;	\
@@ -391,6 +415,7 @@ do {									\
 	case 8:	__put_user_asm_dword(__pu_val, __pu_addr, err);	break;	\
 	default: __put_user_bad();					\
 	}								\
+	uaccess_restore(__ua_flags);					\
 } while (0)
 
 #define __put_user_asm_byte(x, __pu_addr, err)			\
@@ -474,11 +499,46 @@ do {									\
 
 
 #ifdef CONFIG_MMU
-extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_to_user_std(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+arm_copy_from_user(void *to, const void __user *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_from_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_copy_to_user(void __user *to, const void *from, unsigned long n);
+extern unsigned long __must_check
+__copy_to_user_std(void __user *to, const void *from, unsigned long n);
+
+static inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_copy_to_user(to, from, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
+extern unsigned long __must_check
+arm_clear_user(void __user *addr, unsigned long n);
+extern unsigned long __must_check
+__clear_user_std(void __user *addr, unsigned long n);
+
+static inline unsigned long __must_check
+__clear_user(void __user *addr, unsigned long n)
+{
+	unsigned int __ua_flags = uaccess_save_and_enable();
+	n = arm_clear_user(addr, n);
+	uaccess_restore(__ua_flags);
+	return n;
+}
+
 #else
 #define __copy_from_user(to, from, n)	(memcpy(to, (void __force *)from, n), 0)
 #define __copy_to_user(to, from, n)	(memcpy((void __force *)to, from, n), 0)
@@ -511,6 +571,7 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
+/* These are from lib/ code, and use __get_user() and friends */
 extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
 extern __must_check long strlen_user(const char __user *str);
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index a88671cfe1ff..a35d72d30b56 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -91,9 +91,9 @@ EXPORT_SYMBOL(__memzero);
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
-EXPORT_SYMBOL(__copy_from_user);
-EXPORT_SYMBOL(__copy_to_user);
-EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(arm_copy_from_user);
+EXPORT_SYMBOL(arm_copy_to_user);
+EXPORT_SYMBOL(arm_clear_user);
 
 EXPORT_SYMBOL(__get_user_1);
 EXPORT_SYMBOL(__get_user_2);
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 1710fd7db2d5..970d6c043774 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -12,14 +12,14 @@
 
 		.text
 
-/* Prototype: int __clear_user(void *addr, size_t sz)
+/* Prototype: unsigned long arm_clear_user(void *addr, size_t sz)
  * Purpose  : clear some user memory
  * Params   : addr - user memory address to clear
  *          : sz   - number of bytes to clear
  * Returns  : number of bytes NOT cleared
  */
 ENTRY(__clear_user_std)
-WEAK(__clear_user)
+WEAK(arm_clear_user)
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,7 +44,7 @@ WEAK(__clear_user)
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
-ENDPROC(__clear_user)
+ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
 		.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a235b9952be..1512bebfbf1b 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_from_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_from_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -89,11 +89,11 @@
 
 	.text
 
-ENTRY(__copy_from_user)
+ENTRY(arm_copy_from_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_from_user)
+ENDPROC(arm_copy_from_user)
 
 	.pushsection .fixup,"ax"
 	.align 0
diff --git a/arch/arm/lib/copy_to_user.S b/arch/arm/lib/copy_to_user.S
index 9648b0675a3e..caf5019d8161 100644
--- a/arch/arm/lib/copy_to_user.S
+++ b/arch/arm/lib/copy_to_user.S
@@ -17,7 +17,7 @@
 /*
  * Prototype:
  *
- *	size_t __copy_to_user(void *to, const void *from, size_t n)
+ *	size_t arm_copy_to_user(void *to, const void *from, size_t n)
  *
  * Purpose:
  *
@@ -93,11 +93,11 @@
 	.text
 
 ENTRY(__copy_to_user_std)
-WEAK(__copy_to_user)
+WEAK(arm_copy_to_user)
 
 #include "copy_template.S"
 
-ENDPROC(__copy_to_user)
+ENDPROC(arm_copy_to_user)
 ENDPROC(__copy_to_user_std)
 
 	.pushsection .text.fixup,"ax"
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 3e58d710013c..77f020e75ccd 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -136,7 +136,7 @@ out:
 }
 
 unsigned long
-__copy_to_user(void __user *to, const void *from, unsigned long n)
+arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	/*
 	 * This test is stubbed out of the main function above to keep
@@ -190,7 +190,7 @@ out:
 	return n;
 }
 
-unsigned long __clear_user(void __user *addr, unsigned long n)
+unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
 	if (n < 64)

From aa06e5c1f9c2b466712be904cc5b56a813e24cfd Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 26 Aug 2015 20:07:25 +0100
Subject: [PATCH 09/17] ARM: entry: get rid of multiple macro definitions

The following structure is just asking for trouble:

 #ifdef CONFIG_symbol
	.macro foo
	...
	.endm
	.macro bar
	...
	.endm
	.macro baz
	...
	.endm
 #else
	.macro foo
	...
	.endm
	.macro bar
	...
	.endm
 #ifdef CONFIG_symbol2
	.macro baz
	...
	.endm
 #else
	.macro baz
	...
	.endm
 #endif
 #endif

such as one defintion being updated, but the other definitions miss out.
Where the contents of a macro needs to be conditional, the hint is in
the first clause of this very sentence.  "contents" "conditional".  Not
multiple separate definitions, especially not when much of the macro
is the same between different configs.

This patch fixes this bad style, which had caused the Thumb2 code to
miss-out on the uaccess updates.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/entry-header.S | 109 +++++++++++++--------------------
 1 file changed, 44 insertions(+), 65 deletions(-)

diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1a0045abead7..d47b5161b029 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -196,7 +196,7 @@
 	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
 	.endm
 
-#ifndef CONFIG_THUMB2_KERNEL
+
 	.macro	svc_exit, rpsr, irq = 0
 	.if	\irq != 0
 	@ IRQs already off
@@ -215,6 +215,9 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
 	msr	spsr_cxsf, \rpsr
 #if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
 	@ We must avoid clrex due to Cortex-A15 erratum #830321
@@ -222,6 +225,20 @@
 	strex	r1, r2, [r0]			@ clear the exclusive monitor
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
 	.endm
 
 	@
@@ -241,6 +258,8 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r0, sp
 	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
 				@ clobber state restored below)
@@ -250,9 +269,26 @@
 	msr	spsr_cxsf, r9
 	ldr	r0, [r0, #S_R0]
 	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
 	.endm
 
+
 	.macro	restore_user_regs, fast = 0, offset = 0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
 	mov	r2, sp
 	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
@@ -270,72 +306,16 @@
 						@ after ldm {}^
 	add	sp, sp, #\offset + S_FRAME_SIZE
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-
-#else	/* CONFIG_THUMB2_KERNEL */
-	.macro	svc_exit, rpsr, irq = 0
-	.if	\irq != 0
-	@ IRQs already off
-#ifdef CONFIG_TRACE_IRQFLAGS
-	@ The parent context IRQs must have been enabled to get here in
-	@ the first place, so there's no point checking the PSR I bit.
-	bl	trace_hardirqs_on
-#endif
-	.else
-	@ IRQs off again before pulling preserved data off the stack
-	disable_irq_notrace
-#ifdef CONFIG_TRACE_IRQFLAGS
-	tst	\rpsr, #PSR_I_BIT
-	bleq	trace_hardirqs_on
-	tst	\rpsr, #PSR_I_BIT
-	blne	trace_hardirqs_off
-#endif
-	.endif
-	ldr	lr, [sp, #S_SP]			@ top of the stack
-	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
-
-	@ We must avoid clrex due to Cortex-A15 erratum #830321
-	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
-
-	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
-	ldmia	sp, {r0 - r12}
-	mov	sp, lr
-	ldr	lr, [sp], #4
-	rfeia	sp!
-	.endm
-
-	@
-	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
-	@
-	@ For full details see non-Thumb implementation above.
-	@
-	.macro  svc_exit_via_fiq
-	add	r0, sp, #S_R2
-	ldr	lr, [sp, #S_LR]
-	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
-			        @ clobber state restored below)
-	ldmia	r0, {r2 - r12}
-	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
-	msr	cpsr_c, r1
-	sub	r0, #S_R2
-	add	r8, r0, #S_PC
-	ldmia	r0, {r0 - r1}
-	rfeia	r8
-	.endm
-
-#ifdef CONFIG_CPU_V7M
-	/*
-	 * Note we don't need to do clrex here as clearing the local monitor is
-	 * part of each exception entry and exit sequence.
-	 */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
 	.if	\offset
 	add	sp, #\offset
 	.endif
 	v7m_exception_slow_exit ret_r0 = \fast
-	.endm
-#else	/* ifdef CONFIG_CPU_V7M */
-	.macro	restore_user_regs, fast = 0, offset = 0
+#else
+	@ Thumb mode restore
 	mov	r2, sp
 	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
@@ -353,9 +333,8 @@
 	.endif
 	add	sp, sp, #S_FRAME_SIZE - S_SP
 	movs	pc, lr				@ return & move spsr_svc into cpsr
-	.endm
-#endif	/* ifdef CONFIG_CPU_V7M / else */
 #endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
 
 /*
  * Context tracking subsystem.  Used to instrument transitions

From 2190fed67ba6f3e8129513929f2395843645e928 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Thu, 20 Aug 2015 10:32:02 +0100
Subject: [PATCH 10/17] ARM: entry: provide uaccess assembly macro hooks

Provide hooks into the kernel entry and exit paths to permit control
of userspace visibility to the kernel.  The intended use is:

- on entry to kernel from user, uaccess_disable will be called to
  disable userspace visibility
- on exit from kernel to user, uaccess_enable will be called to
  enable userspace visibility
- on entry from a kernel exception, uaccess_save_and_disable will be
  called to save the current userspace visibility setting, and disable
  access
- on exit from a kernel exception, uaccess_restore will be called to
  restore the userspace visibility as it was before the exception
  occurred.

These hooks allows us to keep userspace visibility disabled for the
vast majority of the kernel, except for localised regions where we
want to explicitly access userspace.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/assembler.h | 17 +++++++++++++++++
 arch/arm/kernel/entry-armv.S     | 30 ++++++++++++++++++++++--------
 arch/arm/kernel/entry-common.S   |  2 ++
 arch/arm/kernel/entry-header.S   |  3 +++
 arch/arm/mm/abort-ev4.S          |  1 +
 arch/arm/mm/abort-ev5t.S         |  1 +
 arch/arm/mm/abort-ev5tj.S        |  1 +
 arch/arm/mm/abort-ev6.S          |  7 ++++---
 arch/arm/mm/abort-ev7.S          |  1 +
 arch/arm/mm/abort-lv4t.S         |  2 ++
 arch/arm/mm/abort-macro.S        |  1 +
 11 files changed, 55 insertions(+), 11 deletions(-)

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 4abe57279c66..a91177043467 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -445,6 +445,23 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
+	.macro	uaccess_disable, tmp, isb=1
+	.endm
+
+	.macro	uaccess_enable, tmp, isb=1
+	.endm
+
+	.macro	uaccess_save, tmp
+	.endm
+
+	.macro	uaccess_restore
+	.endm
+
+	.macro	uaccess_save_and_disable, tmp
+	uaccess_save \tmp
+	uaccess_disable \tmp
+	.endm
+
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d19adcf6c580..61f00a3f3047 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -149,10 +149,10 @@ ENDPROC(__und_invalid)
 #define SPFIX(code...)
 #endif
 
-	.macro	svc_entry, stack_hole=0, trace=1
+	.macro	svc_entry, stack_hole=0, trace=1, uaccess=1
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	sub	sp, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
 #ifdef CONFIG_THUMB2_KERNEL
  SPFIX(	str	r0, [sp]	)	@ temporarily saved
  SPFIX(	mov	r0, sp		)
@@ -167,7 +167,7 @@ ENDPROC(__und_invalid)
 	ldmia	r0, {r3 - r5}
 	add	r7, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r6, #-1			@  ""  ""      ""       ""
-	add	r2, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+	add	r2, sp, #(S_FRAME_SIZE + 8 + \stack_hole - 4)
  SPFIX(	addeq	r2, r2, #4	)
 	str	r3, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
@@ -185,6 +185,11 @@ ENDPROC(__und_invalid)
 	@
 	stmia	r7, {r2 - r6}
 
+	uaccess_save r0
+	.if \uaccess
+	uaccess_disable r0
+	.endif
+
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
@@ -194,7 +199,7 @@ ENDPROC(__und_invalid)
 
 	.align	5
 __dabt_svc:
-	svc_entry
+	svc_entry uaccess=0
 	mov	r2, sp
 	dabt_helper
  THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
@@ -368,7 +373,7 @@ ENDPROC(__fiq_abt)
 #error "sizeof(struct pt_regs) must be a multiple of 8"
 #endif
 
-	.macro	usr_entry, trace=1
+	.macro	usr_entry, trace=1, uaccess=1
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
@@ -400,6 +405,10 @@ ENDPROC(__fiq_abt)
  ARM(	stmdb	r0, {sp, lr}^			)
  THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
+	.if \uaccess
+	uaccess_disable ip
+	.endif
+
 	@ Enable the alignment trap while in kernel mode
  ATRAP(	teq	r8, r7)
  ATRAP( mcrne	p15, 0, r8, c1, c0, 0)
@@ -435,7 +444,7 @@ ENDPROC(__fiq_abt)
 
 	.align	5
 __dabt_usr:
-	usr_entry
+	usr_entry uaccess=0
 	kuser_cmpxchg_check
 	mov	r2, sp
 	dabt_helper
@@ -458,7 +467,7 @@ ENDPROC(__irq_usr)
 
 	.align	5
 __und_usr:
-	usr_entry
+	usr_entry uaccess=0
 
 	mov	r2, r4
 	mov	r3, r5
@@ -484,6 +493,8 @@ __und_usr:
 1:	ldrt	r0, [r4]
  ARM_BE8(rev	r0, r0)				@ little endian instruction
 
+	uaccess_disable ip
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
@@ -518,9 +529,10 @@ __und_usr_thumb:
 2:	ldrht	r5, [r4]
 ARM_BE8(rev16	r5, r5)				@ little endian instruction
 	cmp	r5, #0xe800			@ 32bit instruction if xx != 0
-	blo	__und_usr_fault_16		@ 16bit undefined instruction
+	blo	__und_usr_fault_16_pan		@ 16bit undefined instruction
 3:	ldrht	r0, [r2]
 ARM_BE8(rev16	r0, r0)				@ little endian instruction
+	uaccess_disable ip
 	add	r2, r2, #2			@ r2 is PC + 2, make it PC + 4
 	str	r2, [sp, #S_PC]			@ it's a 2x16bit instr, update
 	orr	r0, r0, r5, lsl #16
@@ -715,6 +727,8 @@ ENDPROC(no_fp)
 __und_usr_fault_32:
 	mov	r1, #4
 	b	1f
+__und_usr_fault_16_pan:
+	uaccess_disable ip
 __und_usr_fault_16:
 	mov	r1, #2
 1:	mov	r0, sp
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 92828a1dec80..189154980703 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -173,6 +173,8 @@ ENTRY(vector_swi)
  USER(	ldr	scno, [lr, #-4]		)	@ get SWI instruction
 #endif
 
+	uaccess_disable tbl
+
 	adr	tbl, sys_call_table		@ load syscall table pointer
 
 #if defined(CONFIG_OABI_COMPAT)
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index d47b5161b029..0d22ad206d52 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -215,6 +215,7 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
+	uaccess_restore
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -258,6 +259,7 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
+	uaccess_restore
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
@@ -287,6 +289,7 @@
 
 
 	.macro	restore_user_regs, fast = 0, offset = 0
+	uaccess_enable r1, isb=0
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r2, sp
diff --git a/arch/arm/mm/abort-ev4.S b/arch/arm/mm/abort-ev4.S
index 54473cd4aba9..b3b31e30cadd 100644
--- a/arch/arm/mm/abort-ev4.S
+++ b/arch/arm/mm/abort-ev4.S
@@ -19,6 +19,7 @@ ENTRY(v4_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	ldr	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
 	tst	r3, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/abort-ev5t.S b/arch/arm/mm/abort-ev5t.S
index c913031b79cc..a6a381a6caa5 100644
--- a/arch/arm/mm/abort-ev5t.S
+++ b/arch/arm/mm/abort-ev5t.S
@@ -21,6 +21,7 @@ ENTRY(v5t_early_abort)
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable user access
 	bic	r1, r1, #1 << 11		@ clear bits 11 of FSR
 	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
 	beq	do_DataAbort			@ yes
diff --git a/arch/arm/mm/abort-ev5tj.S b/arch/arm/mm/abort-ev5tj.S
index 1b80d71adb0f..00ab011bef58 100644
--- a/arch/arm/mm/abort-ev5tj.S
+++ b/arch/arm/mm/abort-ev5tj.S
@@ -24,6 +24,7 @@ ENTRY(v5tj_early_abort)
 	bne	do_DataAbort
 	do_thumb_abort fsr=r1, pc=r4, psr=r5, tmp=r3
 	ldreq	r3, [r4]			@ read aborted ARM instruction
+	uaccess_disable ip			@ disable userspace access
 	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
 	beq	do_DataAbort			@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 113704f30e9f..8801a15aa105 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -26,17 +26,18 @@ ENTRY(v6_early_abort)
 	ldr	ip, =0x4107b36
 	mrc	p15, 0, r3, c0, c0, 0		@ get processor id
 	teq	ip, r3, lsr #4			@ r0 ARM1136?
-	bne	do_DataAbort
+	bne	1f
 	tst	r5, #PSR_J_BIT			@ Java?
 	tsteq	r5, #PSR_T_BIT			@ Thumb?
-	bne	do_DataAbort
+	bne	1f
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
  ARM_BE8(rev	r3, r3)
 
 	teq_ldrd tmp=ip, insn=r3		@ insn was LDRD?
-	beq	do_DataAbort			@ yes
+	beq	1f				@ yes
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
 #endif
+1:	uaccess_disable ip			@ disable userspace access
 	b	do_DataAbort
diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S
index 4812ad054214..e8d0e08c227f 100644
--- a/arch/arm/mm/abort-ev7.S
+++ b/arch/arm/mm/abort-ev7.S
@@ -15,6 +15,7 @@
 ENTRY(v7_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
+	uaccess_disable ip			@ disable userspace access
 
 	/*
 	 * V6 code adjusts the returned DFSR.
diff --git a/arch/arm/mm/abort-lv4t.S b/arch/arm/mm/abort-lv4t.S
index f3982580c273..6d8e8e3365d1 100644
--- a/arch/arm/mm/abort-lv4t.S
+++ b/arch/arm/mm/abort-lv4t.S
@@ -26,6 +26,7 @@ ENTRY(v4t_late_abort)
 #endif
 	bne	.data_thumb_abort
 	ldr	r8, [r4]			@ read arm instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 20			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 11		@ yes.
 	and	r7, r8, #15 << 24
@@ -155,6 +156,7 @@ ENTRY(v4t_late_abort)
 
 .data_thumb_abort:
 	ldrh	r8, [r4]			@ read instruction
+	uaccess_disable ip			@ disable userspace access
 	tst	r8, #1 << 11			@ L = 1 -> write?
 	orreq	r1, r1, #1 << 8			@ yes
 	and	r7, r8, #15 << 12
diff --git a/arch/arm/mm/abort-macro.S b/arch/arm/mm/abort-macro.S
index 50d6c0a900b1..4509bee4e081 100644
--- a/arch/arm/mm/abort-macro.S
+++ b/arch/arm/mm/abort-macro.S
@@ -13,6 +13,7 @@
 	tst	\psr, #PSR_T_BIT
 	beq	not_thumb
 	ldrh	\tmp, [\pc]			@ Read aborted Thumb instruction
+	uaccess_disable ip			@ disable userspace access
 	and	\tmp, \tmp, # 0xfe00		@ Mask opcode field
 	cmp	\tmp, # 0x5600			@ Is it ldrsb?
 	orreq	\tmp, \tmp, #1 << 11		@ Set L-bit if yes

From a5e090acbf545c0a3b04080f8a488b17ec41fe02 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 19 Aug 2015 20:40:41 +0100
Subject: [PATCH 11/17] ARM: software-based priviledged-no-access support

Provide a software-based implementation of the priviledged no access
support found in ARMv8.1.

Userspace pages are mapped using a different domain number from the
kernel and IO mappings.  If we switch the user domain to "no access"
when we enter the kernel, we can prevent the kernel from touching
userspace.

However, the kernel needs to be able to access userspace via the
various user accessor functions.  With the wrapping in the previous
patch, we can temporarily enable access when the kernel needs user
access, and re-disable it afterwards.

This allows us to trap non-intended accesses to userspace, eg, caused
by an inadvertent dereference of the LIST_POISON* values, which, with
appropriate user mappings setup, can be made to succeed.  This in turn
can allow use-after-free bugs to be further exploited than would
otherwise be possible.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/Kconfig                   | 15 +++++++++++++
 arch/arm/include/asm/assembler.h   | 30 +++++++++++++++++++++++++
 arch/arm/include/asm/domain.h      | 21 +++++++++++++++--
 arch/arm/include/asm/uaccess.h     | 14 ++++++++++++
 arch/arm/kernel/process.c          | 36 +++++++++++++++++++++++++-----
 arch/arm/kernel/swp_emulate.c      |  3 +++
 arch/arm/lib/csumpartialcopyuser.S | 14 ++++++++++++
 7 files changed, 125 insertions(+), 8 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a750c1425c3a..e15d5ed4d5f1 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1694,6 +1694,21 @@ config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem"
 	depends on HIGHMEM
 
+config CPU_SW_DOMAIN_PAN
+	bool "Enable use of CPU domains to implement privileged no-access"
+	depends on MMU && !ARM_LPAE
+	default y
+	help
+	  Increase kernel security by ensuring that normal kernel accesses
+	  are unable to access userspace addresses.  This can help prevent
+	  use-after-free bugs becoming an exploitable privilege escalation
+	  by ensuring that magic values (such as LIST_POISON) will always
+	  fault when dereferenced.
+
+	  CPUs with low-vector mappings use a best-efforts implementation.
+	  Their lower 1MB needs to remain accessible for the vectors, but
+	  the remainder of userspace will become appropriately inaccessible.
+
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
 	depends on PERF_EVENTS
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index a91177043467..3ae0eda5e64f 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -446,15 +446,45 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.endm
 
 	.macro	uaccess_disable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_DISABLE
+	mcr	p15, 0, \tmp, c3, c0, 0		@ Set domain register
+	.if	\isb
+	instr_sync
+	.endif
+#endif
 	.endm
 
 	.macro	uaccess_enable, tmp, isb=1
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Whenever we re-enter userspace, the domains should always be
+	 * set appropriately.
+	 */
+	mov	\tmp, #DACR_UACCESS_ENABLE
+	mcr	p15, 0, \tmp, c3, c0, 0
+	.if	\isb
+	instr_sync
+	.endif
+#endif
 	.endm
 
 	.macro	uaccess_save, tmp
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	mrc	p15, 0, \tmp, c3, c0, 0
+	str	\tmp, [sp, #S_FRAME_SIZE]
+#endif
 	.endm
 
 	.macro	uaccess_restore
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	ldr	r0, [sp, #S_FRAME_SIZE]
+	mcr	p15, 0, r0, c3, c0, 0
+#endif
 	.endm
 
 	.macro	uaccess_save_and_disable, tmp
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 2be929549938..e878129f2fee 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -57,11 +57,29 @@
 #define domain_mask(dom)	((3) << (2 * (dom)))
 #define domain_val(dom,type)	((type) << (2 * (dom)))
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+#define DACR_INIT \
+	(domain_val(DOMAIN_USER, DOMAIN_NOACCESS) | \
+	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
+	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#else
 #define DACR_INIT \
 	(domain_val(DOMAIN_USER, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 	 domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
 	 domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT))
+#endif
+
+#define __DACR_DEFAULT \
+	domain_val(DOMAIN_KERNEL, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_IO, DOMAIN_CLIENT) | \
+	domain_val(DOMAIN_VECTORS, DOMAIN_CLIENT)
+
+#define DACR_UACCESS_DISABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+#define DACR_UACCESS_ENABLE	\
+	(__DACR_DEFAULT | domain_val(DOMAIN_USER, DOMAIN_CLIENT))
 
 #ifndef __ASSEMBLY__
 
@@ -76,7 +94,6 @@ static inline unsigned int get_domain(void)
 	return domain;
 }
 
-#ifdef CONFIG_CPU_USE_DOMAINS
 static inline void set_domain(unsigned val)
 {
 	asm volatile(
@@ -85,6 +102,7 @@ static inline void set_domain(unsigned val)
 	isb();
 }
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define modify_domain(dom,type)					\
 	do {							\
 		unsigned int domain = get_domain();		\
@@ -94,7 +112,6 @@ static inline void set_domain(unsigned val)
 	} while (0)
 
 #else
-static inline void set_domain(unsigned val) { }
 static inline void modify_domain(unsigned dom, unsigned type)	{ }
 #endif
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 82880132f941..01bae13b2cea 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -57,11 +57,25 @@ extern int fixup_exception(struct pt_regs *regs);
  */
 static inline unsigned int uaccess_save_and_enable(void)
 {
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	unsigned int old_domain = get_domain();
+
+	/* Set the current domain access to permit user accesses */
+	set_domain((old_domain & ~domain_mask(DOMAIN_USER)) |
+		   domain_val(DOMAIN_USER, DOMAIN_CLIENT));
+
+	return old_domain;
+#else
 	return 0;
+#endif
 }
 
 static inline void uaccess_restore(unsigned int flags)
 {
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/* Restore the user access mask */
+	set_domain(flags);
+#endif
 }
 
 /*
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index e722f9b3c9b1..3f18098dfd08 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -129,12 +129,36 @@ void __show_regs(struct pt_regs *regs)
 	buf[4] = '\0';
 
 #ifndef CONFIG_CPU_V7M
-	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
-		buf, interrupts_enabled(regs) ? "n" : "ff",
-		fast_interrupts_enabled(regs) ? "n" : "ff",
-		processor_modes[processor_mode(regs)],
-		isa_modes[isa_mode(regs)],
-		get_fs() == get_ds() ? "kernel" : "user");
+	{
+		unsigned int domain = get_domain();
+		const char *segment;
+
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		/*
+		 * Get the domain register for the parent context. In user
+		 * mode, we don't save the DACR, so lets use what it should
+		 * be. For other modes, we place it after the pt_regs struct.
+		 */
+		if (user_mode(regs))
+			domain = DACR_UACCESS_ENABLE;
+		else
+			domain = *(unsigned int *)(regs + 1);
+#endif
+
+		if ((domain & domain_mask(DOMAIN_USER)) ==
+		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
+			segment = "none";
+		else if (get_fs() == get_ds())
+			segment = "kernel";
+		else
+			segment = "user";
+
+		printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
+			buf, interrupts_enabled(regs) ? "n" : "ff",
+			fast_interrupts_enabled(regs) ? "n" : "ff",
+			processor_modes[processor_mode(regs)],
+			isa_modes[isa_mode(regs)], segment);
+	}
 #else
 	printk("xPSR: %08lx\n", regs->ARM_cpsr);
 #endif
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
index 1361756782c7..5b26e7efa9ea 100644
--- a/arch/arm/kernel/swp_emulate.c
+++ b/arch/arm/kernel/swp_emulate.c
@@ -141,11 +141,14 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 
 	while (1) {
 		unsigned long temp;
+		unsigned int __ua_flags;
 
+		__ua_flags = uaccess_save_and_enable();
 		if (type == TYPE_SWPB)
 			__user_swpb_asm(*data, address, res, temp);
 		else
 			__user_swp_asm(*data, address, res, temp);
+		uaccess_restore(__ua_flags);
 
 		if (likely(res != -EAGAIN) || signal_pending(current))
 			break;
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 1d0957e61f89..1712f132b80d 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -17,6 +17,19 @@
 
 		.text
 
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		.macro	save_regs
+		mrc	p15, 0, ip, c3, c0, 0
+		stmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		uaccess_enable ip
+		.endm
+
+		.macro	load_regs
+		ldmfd	sp!, {r1, r2, r4 - r8, ip, lr}
+		mcr	p15, 0, ip, c3, c0, 0
+		ret	lr
+		.endm
+#else
 		.macro	save_regs
 		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
@@ -24,6 +37,7 @@
 		.macro	load_regs
 		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
+#endif
 
 		.macro	load1b,	reg1
 		ldrusr	\reg1, r0, 1

From 39dc53deff30d9b239ac36cfeb0ef2022d03a449 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 7 Sep 2015 00:29:15 +0100
Subject: [PATCH 12/17] ARM: swpan: fix nwfpe for uaccess changes

NWFPE needs to access userspace to check whether the next instruction
is another FP instruction.  Allow userspace access for this read.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/nwfpe/entry.S | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/nwfpe/entry.S b/arch/arm/nwfpe/entry.S
index 71df43547659..39c20afad7ed 100644
--- a/arch/arm/nwfpe/entry.S
+++ b/arch/arm/nwfpe/entry.S
@@ -95,9 +95,10 @@ emulate:
 	reteq	r4			@ no, return failure
 
 next:
+	uaccess_enable r3
 .Lx1:	ldrt	r6, [r5], #4		@ get the next instruction and
 					@ increment PC
-
+	uaccess_disable r3
 	and	r2, r6, #0x0F000000	@ test for FP insns
 	teq	r2, #0x0C000000
 	teqne	r2, #0x0D000000

From 296254f3223d201f2aa53f5f717eedfdc63f3db8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Mon, 7 Sep 2015 00:30:06 +0100
Subject: [PATCH 13/17] ARM: uaccess: remove unneeded uaccess_save_and_disable
 macro

This macro is never referenced, remove it.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/assembler.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 3ae0eda5e64f..9007c518d1d8 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -487,11 +487,6 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 #endif
 	.endm
 
-	.macro	uaccess_save_and_disable, tmp
-	uaccess_save \tmp
-	uaccess_disable \tmp
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6

From af4cb25df93d2e7a97d65db2bfacaa4400988dea Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Wed, 9 Sep 2015 21:19:49 +0100
Subject: [PATCH 14/17] ARM: uaccess: fix undefined instruction on ARMv7M/noMMU

The use of get_domain() in copy_thread() results in an oops on
ARMv7M/noMMU systems.  The thread cpu_domain value is only used when
CONFIG_CPU_USE_DOMAINS is enabled, so there's no need to save the
value in copy_thread() except when this is enabled, and this option
will never be enabled on these platforms.

Unhandled exception: IPSR = 00000006 LR = fffffff1
CPU: 0 PID: 0 Comm: swapper Not tainted 4.2.0-next-20150909-00001-gb8ec5ad #41
Hardware name: NXP LPC18xx/43xx (Device Tree)
task: 2823fbe0 ti: 2823c000 task.ti: 2823c000
PC is at copy_thread+0x18/0x92
LR is at copy_thread+0x19/0x92
pc : [<2800a46e>]    lr : [<2800a46f>]    psr: 4100000b
sp : 2823df00  ip : 00000000  fp : 287c81c0
r10: 00000000  r9 : 00800300  r8 : 287c8000
r7 : 287c8000  r6 : 2818908d  r5 : 00000000  r4 : 287ca000
r3 : 00000000  r2 : 00000000  r1 : fffffff0  r0 : 287ca048
xPSR: 4100000b

Reported-by: Ariel D'Alessandro <ariel@vanguardiasur.com.ar>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/kernel/process.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 3f18098dfd08..e550a4541f48 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -233,6 +233,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 	/*
 	 * Copy the initial value of the domain access control register
 	 * from the current thread: thread->addr_limit will have been
@@ -240,6 +241,7 @@ copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	 * kernel/fork.c
 	 */
 	thread->cpu_domain = get_domain();
+#endif
 
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();

From 716ff1921a86c637b8875c7bb312fc6755fa9300 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 11 Sep 2015 08:17:39 +0100
Subject: [PATCH 15/17] ARM: domains: thread_info.h no longer needs
 asm/domains.h

As of 1eef5d2f1b46 ("ARM: domains: switch to keeping domain value in
register") we no longer need to include asm/domains.h into
asm/thread_info.h.  Remove it.

Tested-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/thread_info.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 0a0aec410d8c..ae02e68b61fc 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -25,7 +25,6 @@
 struct task_struct;
 
 #include <asm/types.h>
-#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 

From 6e8f580d1fcc18e290713984c379cb97131c015a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@arm.linux.org.uk>
Date: Fri, 11 Sep 2015 08:34:52 +0100
Subject: [PATCH 16/17] ARM: domains: add memory dependencies to
 get_domain/set_domain

We need to have memory dependencies on get_domain/set_domain to avoid
the compiler over-optimising these inline assembly instructions.

Loads/stores must not be reordered across a set_domain(), so introduce
a compiler barrier for that assembly.

The value of get_domain() must not be cached across a set_domain(), but
we still want to allow the compiler to optimise it away.  Introduce a
dependency on current_thread_info()->cpu_domain to avoid this; the new
memory clobber in set_domain() should therefore cause the compiler to
re-load this.  The other advantage of using this is we should have its
address in the register set already, or very soon after at most call
sites.

Tested-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/include/asm/domain.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index e878129f2fee..fc8ba1663601 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -12,6 +12,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/barrier.h>
+#include <asm/thread_info.h>
 #endif
 
 /*
@@ -89,7 +90,8 @@ static inline unsigned int get_domain(void)
 
 	asm(
 	"mrc	p15, 0, %0, c3, c0	@ get domain"
-	 : "=r" (domain));
+	 : "=r" (domain)
+	 : "m" (current_thread_info()->cpu_domain));
 
 	return domain;
 }
@@ -98,7 +100,7 @@ static inline void set_domain(unsigned val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
-	  : : "r" (val));
+	  : : "r" (val) : "memory");
 	isb();
 }
 

From 0b61f2c0f37983c98ed4207f3f5e265938371b68 Mon Sep 17 00:00:00 2001
From: Julien Grall <julien.grall@citrix.com>
Date: Fri, 11 Sep 2015 17:25:59 +0100
Subject: [PATCH 17/17] arm/xen: Enable user access to the kernel before
 issuing a privcmd call

When Xen is copying data to/from the guest it will check if the kernel
has the right to do the access. If not, the hypercall will return an
error.

After the commit a5e090acbf545c0a3b04080f8a488b17ec41fe02 "ARM:
software-based privileged-no-access support", the kernel can't access
any longer the user space by default. This will result to fail on every
hypercall made by the userspace (i.e via privcmd).

We have to enable the userspace access and then restore the correct
permission every time the privcmd is used to made an hypercall.

I didn't find generic helpers to do a these operations, so the change
is only arm32 specific.

Reported-by: Riku Voipio <riku.voipio@linaro.org>
Signed-off-by: Julien Grall <julien.grall@citrix.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/xen/hypercall.S | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index f00e08075938..10fd99c568c6 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -98,8 +98,23 @@ ENTRY(privcmd_call)
 	mov r1, r2
 	mov r2, r3
 	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
 	ldr r4, [sp, #4]
 	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS)/set_fs(get_ds()) is
+	 * called before.
+	 */
+	uaccess_disable r4
+
 	ldm sp!, {r4}
 	ret lr
 ENDPROC(privcmd_call);