Merge tag 'arc-v4.2-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC fixes from Vineet Gupta:
 - Makefile changes (top-level+ARC) reinstates -O3 builds (regression
   since 3.16)
 - IDU intc related fixes, IRQ affinity
 - patch to make bitops safer for ARC
 - perf fix from Alexey to remove signed PC braino
 - Futex backend gets llock/scond support

* tag 'arc-v4.2-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARCv2: support HS38 releases
  ARC: make sure instruction_pointer() returns unsigned value
  ARC: slightly refactor macros for boot logging
  ARC: Add llock/scond to futex backend
  arc:irqchip: prepare for drivers/irqchip/irqchip.h removal
  ARC: Make ARC bitops "safer" (add anti-optimization)
  ARCv2: [axs103] bump CPU frequency from 75 to 90 MHZ
  ARCv2: intc: IDU: Fix potential race in installing a chained IRQ handler
  ARCv2: intc: IDU: support irq affinity
  ARC: fix unused var wanring
  ARC: Don't memzero twice in dma_alloc_coherent for __GFP_ZERO
  ARC: Override toplevel default -O2 with -O3
  kbuild: Allow arch Makefiles to override {cpp,ld,c}flags
  ARCv2: guard SLC DMA ops with spinlock
  ARC: Kconfig: better way to disable ARC_HAS_LLSC for ARC_CPU_750D

16 files changed, 112 insertions, 57 deletions

diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index e63b446d973c..13f888a02a3d 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -952,6 +952,14 @@ When kbuild executes, the following steps are followed (roughly):
 	$(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic
 	mode) if this option is supported by $(AR).
 
+    ARCH_CPPFLAGS, ARCH_AFLAGS, ARCH_CFLAGS   Overrides the kbuild defaults
+
+	These variables are appended to the KBUILD_CPPFLAGS,
+	KBUILD_AFLAGS, and KBUILD_CFLAGS, respectively, after the
+	top-level Makefile has set any other flags. This provides a
+	means for an architecture to override the defaults.
+
+
 --- 6.2 Add prerequisites to archheaders:
 
 	The archheaders: rule is used to generate header files that
diff --git a/Makefile b/Makefile
index 257ef5892ab7..2f49d89eccfa 100644
--- a/Makefile
+++ b/Makefile
@@ -780,10 +780,11 @@ endif
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 
-# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
-KBUILD_CPPFLAGS += $(KCPPFLAGS)
-KBUILD_AFLAGS += $(KAFLAGS)
-KBUILD_CFLAGS += $(KCFLAGS)
+# Add any arch overrides and user supplied CPPFLAGS, AFLAGS and CFLAGS as the
+# last assignments
+KBUILD_CPPFLAGS += $(ARCH_CPPFLAGS) $(KCPPFLAGS)
+KBUILD_AFLAGS   += $(ARCH_AFLAGS)   $(KAFLAGS)
+KBUILD_CFLAGS   += $(ARCH_CFLAGS)   $(KCFLAGS)
 
 # Use --build-id when available.
 LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e7cee0a5c56d..91cf4055acab 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -115,6 +115,7 @@ if ISA_ARCOMPACT
 
 config ARC_CPU_750D
 	bool "ARC750D"
+	select ARC_CANT_LLSC
 	help
 	  Support for ARC750 core
 
@@ -362,7 +363,7 @@ config ARC_CANT_LLSC
 config ARC_HAS_LLSC
 	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
 	default y
-	depends on !ARC_CPU_750D && !ARC_CANT_LLSC
+	depends on !ARC_CANT_LLSC
 
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 6107062c0111..46d87310220d 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -49,7 +49,8 @@ endif
 
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
-cflags-y  += -O3
+# Note: No need to add to cflags-y as that happens anyways
+ARCH_CFLAGS += -O3
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 15c8d6226c9d..1cd5e82f5dc2 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 199d42820eca..2f0b33257db2 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 99fe118d3730..57c1f33844d4 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -50,8 +50,7 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	 * done for const @nr, but no code is generated due to gcc	\
 	 * const prop.							\
 	 */								\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock       %0, [%1]		\n"			\
@@ -82,8 +81,7 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 									\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -129,16 +127,13 @@ static inline void op##_bit(unsigned long nr, volatile unsigned long *m)\
 	unsigned long temp, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	/*								\
 	 * spin lock/unlock provide the needed smp_mb() before/after	\
 	 */								\
 	bitops_lock(flags);						\
 									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));					\
 									\
 	bitops_unlock(flags);						\
 }
@@ -149,17 +144,14 @@ static inline int test_and_##op##_bit(unsigned long nr, volatile unsigned long *
 	unsigned long old, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	bitops_lock(flags);						\
 									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
 	bitops_unlock(flags);						\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #endif /* CONFIG_ARC_HAS_LLSC */
@@ -174,11 +166,8 @@ static inline void __##op##_bit(unsigned long nr, volatile unsigned long *m)	\
 	unsigned long temp;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));				\
 }
 
 #define __TEST_N_BIT_OP(op, c_op, asm_op)				\
@@ -187,13 +176,10 @@ static inline int __test_and_##op##_bit(unsigned long nr, volatile unsigned long
 	unsigned long old;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #define BIT_OPS(op, c_op, asm_op)					\
@@ -224,10 +210,7 @@ test_bit(unsigned int nr, const volatile unsigned long *addr)
 
 	addr += nr >> 5;
 
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	mask = 1 << nr;
+	mask = 1UL << (nr & 0x1f);
 
 	return ((mask & *addr) != 0);
 }
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 05b5aaf5b0f9..70cfe16b742d 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -16,12 +16,40 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	__asm__ __volatile__(				\
+	"1:	llock	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	b   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory")
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
 							\
 	__asm__ __volatile__(				\
-	"1:	ld  %1, [%2]			\n"	\
+	"1:	ld	%1, [%2]		\n"	\
 		insn				"\n"	\
-	"2:	st  %0, [%2]			\n"	\
+	"2:	st	%0, [%2]		\n"	\
 	"	mov %0, 0			\n"	\
 	"3:					\n"	\
 	"	.section .fixup,\"ax\"		\n"	\
@@ -39,6 +67,8 @@
 	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
 	: "cc", "memory")
 
+#endif
+
 static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
@@ -123,11 +153,17 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval,
 
 	pagefault_disable();
 
-	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
-	"1:	ld    %0, [%3]	\n"
-	"	brne  %0, %1, 3f	\n"
-	"2:	st    %2, [%3]	\n"
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	scond	%2, [%3]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	st	%2, [%3]		\n"
+#endif
 	"3:	\n"
 	"	.section .fixup,\"ax\"	\n"
 	"4:	mov %0, %4	\n"
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 91755972b9a2..91694ec1ce95 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -106,7 +106,7 @@ struct callee_regs {
 	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
-#define instruction_pointer(regs)	((regs)->ret)
+#define instruction_pointer(regs)	(unsigned long)((regs)->ret)
 #define profile_pc(regs)		instruction_pointer(regs)
 
 /* return 1 if user mode or 0 if kernel mode */
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6208c630abed..26c156827479 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index fcdddb631766..039fac30b5c1 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 30284e8de6ff..2fb86589054d 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -175,7 +175,6 @@ void mcip_init_early_smp(void)
 #include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include "../../drivers/irqchip/irqchip.h"
 
 /*
  * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
@@ -218,11 +217,28 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
+#ifdef CONFIG_SMP
 static int
-idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f)
+idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
+		     bool force)
 {
+	unsigned long flags;
+	cpumask_t online;
+
+	/* errout if no online cpu per @cpumask */
+	if (!cpumask_and(&online, cpumask, cpu_online_mask))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
+	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
 	return IRQ_SET_MASK_OK;
 }
+#endif
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
@@ -330,8 +346,7 @@ idu_of_init(struct device_node *intc, struct device_node *parent)
 		if (!i)
 			idu_first_irq = irq;
 
-		irq_set_handler_data(irq, domain);
-		irq_set_chained_handler(irq, idu_cascade_isr);
+		irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
 	}
 
 	__mcip_cmd(CMD_IDU_ENABLE, 0);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a3d186211ed3..18cc01591c96 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -142,17 +142,22 @@ static void read_arc_build_cfg_regs(void)
 }
 
 static const struct cpuinfo_data arc_cpu_tbl[] = {
+#ifdef CONFIG_ISA_ARCOMPACT
 	{ {0x20, "ARC 600"      }, 0x2F},
 	{ {0x30, "ARC 700"      }, 0x33},
 	{ {0x34, "ARC 700 R4.10"}, 0x34},
 	{ {0x35, "ARC 700 R4.11"}, 0x35},
-	{ {0x50, "ARC HS38"	}, 0x51},
+#else
+	{ {0x50, "ARC HS38 R2.0"}, 0x51},
+	{ {0x52, "ARC HS38 R2.1"}, 0x52},
+#endif
 	{ {0x00, NULL		} }
 };
 
-#define IS_AVAIL1(v, str)	((v) ? str : "")
-#define IS_USED(cfg)		(IS_ENABLED(cfg) ? "" : "(not used) ")
-#define IS_AVAIL2(v, str, cfg)  IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg))
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#define IS_USED_RUN(v)		((v) ? "" : "(not used) ")
+#define IS_USED_CFG(cfg)	IS_USED_RUN(IS_ENABLED(cfg))
+#define IS_AVAIL2(v, s, cfg)	IS_AVAIL1(v, s), IS_AVAIL1(v, IS_USED_CFG(cfg))
 
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
@@ -226,7 +231,7 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
 		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED(CONFIG_ARC_HAS_HW_MPY));
+			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 807f7d61d7a7..a6f91e88ce36 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -58,7 +58,6 @@ static void show_callee_regs(struct callee_regs *cregs)
 
 static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 {
-	struct path path;
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index b29d62ed4f7e..1cd6695b6ab5 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -468,10 +468,18 @@ static void __ic_line_inv_vaddr(unsigned long paddr, unsigned long vaddr,
 noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 {
 #ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&lock, flags);
 
 	/*
 	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
@@ -504,7 +512,7 @@ noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&lock, flags);
 #endif
 }
 
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 74a637a1cfc4..57706a9c6948 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -60,8 +60,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
-	if (kvaddr != NULL)
-		memset(kvaddr, 0, size);
+	if (kvaddr == NULL)
+		return NULL;
 
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;