Back-merge tag 'v4.7-rc5' into drm-next

Linux 4.7-rc5

The fsl-dcu pull needs -rc3 so go to -rc5 for now.

14 files changed, 148 insertions, 40 deletions

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7085e32..648a32c 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,7 +95,7 @@ boot := arch/arm64/boot
 Image: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-Image.%: vmlinux
+Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zinstall install:
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2..fbafa24 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
 		#size-cells = <1>;
 		#interrupts-cells = <3>;
 
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		interrupt-parent = <&gic>;
 		ranges;
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a..d7f8e06 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
 	};
 
 	amba {
-		compatible = "arm,amba-bus";
+		compatible = "simple-bus";
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges;
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c..da84645 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
 #endif /* !__ASSEMBLY__ */
 
 /*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
  *
  * General purpose regs:
  *     r0-r30: 64 bit
  *     sp,pc : 64 bit
- *     pstate  : 64 bit
- *     Total: 34
+ *     pstate  : 32 bit
+ *     Total: 33 + 1
  * FPU regs:
  *     f0-f31: 128 bit
- *     Total: 32
- * Extra regs
  *     fpsr & fpcr: 32 bit
- *     Total: 2
+ *     Total: 32 + 2
  *
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
  */
 
-#define _GP_REGS		34
+#define _GP_REGS		33
 #define _FP_REGS		32
-#define _EXTRA_REGS		2
+#define _EXTRA_REGS		3
 /*
  * general purpose registers size in bytes.
  * pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585..d25f4f1 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
 
 #define check_pgt_cache()		do { } while (0)
 
-#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
 #define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
 
 #if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e504..0226447 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
 	cpu_park_loop();
 }
 
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682b..e875a5a 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 {
 	unsigned int tmp;
 	arch_spinlock_t lockval;
+	u32 owner;
+
+	/*
+	 * Ensure prior spin_lock operations to other locks have completed
+	 * on this CPU before we test whether "lock" is locked.
+	 */
+	smp_mb();
+	owner = READ_ONCE(lock->owner) << 16;
 
 	asm volatile(
 "	sevl\n"
 "1:	wfe\n"
 "2:	ldaxr	%w0, %2\n"
+	/* Is the lock free? */
 "	eor	%w1, %w0, %w0, ror #16\n"
-"	cbnz	%w1, 1b\n"
+"	cbz	%w1, 3f\n"
+	/* Lock taken -- has there been a subsequent unlock->lock transition? */
+"	eor	%w1, %w3, %w0, lsl #16\n"
+"	cbz	%w1, 1b\n"
+	/*
+	 * The owner has been updated, so there was an unlock->lock
+	 * transition that we missed. That means we can rely on the
+	 * store-release of the unlock operation paired with the
+	 * load-acquire of the lock operation to publish any of our
+	 * previous stores to the new lock owner and therefore don't
+	 * need to bother with the writeback below.
+	 */
+"	b	4f\n"
+"3:\n"
+	/*
+	 * Serialise against any concurrent lockers by writing back the
+	 * unlocked lock value
+	 */
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 2b\n", /* Serialise against any concurrent lockers */
-	/* LSE atomics */
 "	nop\n"
-"	nop\n")
+"	nop\n",
+	/* LSE atomics */
+"	mov	%w1, %w0\n"
+"	cas	%w0, %w0, %2\n"
+"	eor	%w1, %w1, %w0\n")
+	/* Somebody else wrote to the lock, GOTO 10 and reload the value */
+"	cbnz	%w1, 2b\n"
+"4:"
 	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	:
+	: "r" (owner)
 	: "memory");
 }
 
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
+	smp_mb(); /* See arch_spin_unlock_wait */
 	return !arch_spin_value_unlocked(READ_ONCE(*lock));
 }
 
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d..21ab5df 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
+#include <asm/smp.h>
 #include <asm/suspend.h>
 #include <asm/virt.h>
 
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
 	unsigned long flags;
 	struct sleep_stack_data state;
 
+	if (cpus_are_stuck_in_kernel()) {
+		pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+		return -EBUSY;
+	}
+
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a..b5f063e 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
 	{ "x30", 8, offsetof(struct pt_regs, regs[30])},
 	{ "sp", 8, offsetof(struct pt_regs, sp)},
 	{ "pc", 8, offsetof(struct pt_regs, pc)},
-	{ "pstate", 8, offsetof(struct pt_regs, pstate)},
+	/*
+	 * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+	 * protocol disagrees. Therefore we must extract only the lower
+	 * 32-bits. Look for the big comment in asm/kgdb.h for more
+	 * detail.
+	 */
+	{ "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+							+ 4
+#endif
+	},
 	{ "v0", 16, -1 },
 	{ "v1", 16, -1 },
 	{ "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 	memset((char *)gdb_regs, 0, NUMREGBYTES);
 	thread_regs = task_pt_regs(task);
 	memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+	/* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+	dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e084..62ff3c0 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -909,3 +909,21 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	int any_cpu = raw_smp_processor_id();
+
+	if (cpu_ops[any_cpu]->cpu_die)
+		return true;
+#endif
+	return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+	return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f7cf463..2a43012 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
 
 	/*
 	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
+	 * to safely read from kernel space.
 	 */
 	fs = get_fs();
 	set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
 	print_ip_sym(where);
 }
 
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
 {
 	unsigned long addr = instruction_pointer(regs);
-	mm_segment_t fs;
 	char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
 	int i;
 
-	/*
-	 * We need to switch to kernel mode so that we can use __get_user
-	 * to safely read from kernel space.  Note that we now dump the
-	 * code first, just in case the backtrace kills us.
-	 */
-	fs = get_fs();
-	set_fs(KERNEL_DS);
-
 	for (i = -4; i < 1; i++) {
 		unsigned int val, bad;
 
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 		}
 	}
 	printk("%sCode: %s\n", lvl, str);
+}
 
-	set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+	if (!user_mode(regs)) {
+		mm_segment_t fs = get_fs();
+		set_fs(KERNEL_DS);
+		__dump_instr(lvl, regs);
+		set_fs(fs);
+	} else {
+		__dump_instr(lvl, regs);
+	}
 }
 
 static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b3978..efcf1f7 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 						 &asid_generation);
 	flush_context(cpu);
 
-	/* We have at least 1 ASID per CPU, so this will always succeed */
+	/* We have more ASIDs than CPUs, so this will always succeed */
 	asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
 
 set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
 static int asids_init(void)
 {
 	asid_bits = get_cpu_asid_bits();
-	/* If we end up with more CPUs than ASIDs, expect things to crash */
-	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+	/*
+	 * Expect allocation after rollover to fail if we don't have at least
+	 * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+	 */
+	WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);
 	asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
 			   GFP_KERNEL);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881..013e2cb 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	 * PTE_RDONLY is cleared by default in the asm below, so set it in
 	 * back if necessary (read-only or clean PTE).
 	 */
-	if (!pte_write(entry) || !dirty)
+	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
@@ -441,7 +441,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
-static struct fault_info {
+static const struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
 	int	sig;
 	int	code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea..43a76b0 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
 {
 	struct page *page = pte_page(pte);
 
-	/* no flushing needed for anonymous pages */
-	if (!page_mapping(page))
-		return;
-
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));