A batch of MIPS fixes for 5.0, nothing too scary.

- A workaround for a Loongson 3 CPU bug is the biggest change, but
    still fairly straightforward. It adds extra memory barriers (sync
    instructions) around atomics to avoid a CPU bug that can break
    atomicity.
 
  - Loongson64 also sees a fix for powering off some systems which would
    incorrectly reboot rather than waiting for the power down sequence to
    complete.
 
  - We have DT fixes for the Ingenic JZ4740 SoC & the JZ4780-based Ci20
    board, and a DT warning fix for the Nexsys4/MIPSfpga board.
 
  - The Cavium Octeon platform sees a further fix to the behaviour of the
    pcie_disable command line argument that was introduced in v3.3.
 
  - The VDSO, introduced in v4.4, sees build fixes for configurations of
    GCC that were built using the --with-fp-32= flag to specify a default
    32-bit floating point ABI.
 
  - get_frame_info() sees a fix for configurations with
    CONFIG_KALLSYMS=n, for which it previously always returned an error.
 
  - If the MIPS Coherence Manager (CM) reports an error then we'll now
    clear that error correctly so that the GCR_ERROR_CAUSE register will
    be updated with information about any future errors.
 -----BEGIN PGP SIGNATURE-----
 
 iIsEABYIADMWIQRgLjeFAZEXQzy86/s+p5+stXUA3QUCXF8rDhUccGF1bC5idXJ0
 b25AbWlwcy5jb20ACgkQPqefrLV1AN0PngEAyEGqu+OyUjLGZApcM49LDMcr5RHq
 V6ED2HApfNbxsAYBAN+Uv6fm4H1LAbU+sIoHUp7DGQ1f1oFsbij4V/bqP4IA
 =nv8r
 -----END PGP SIGNATURE-----

Merge tag 'mips_fixes_5.0_3' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux

Pull MIPS fixes from Paul Burton:
 "A batch of MIPS fixes for 5.0, nothing too scary.

   - A workaround for a Loongson 3 CPU bug is the biggest change, but
     still fairly straightforward. It adds extra memory barriers (sync
     instructions) around atomics to avoid a CPU bug that can break
     atomicity.

   - Loongson64 also sees a fix for powering off some systems which
     would incorrectly reboot rather than waiting for the power down
     sequence to complete.

   - We have DT fixes for the Ingenic JZ4740 SoC & the JZ4780-based Ci20
     board, and a DT warning fix for the Nexsys4/MIPSfpga board.

   - The Cavium Octeon platform sees a further fix to the behaviour of
     the pcie_disable command line argument that was introduced in v3.3.

   - The VDSO, introduced in v4.4, sees build fixes for configurations
     of GCC that were built using the --with-fp-32= flag to specify a
     default 32-bit floating point ABI.

   - get_frame_info() sees a fix for configurations with
     CONFIG_KALLSYMS=n, for which it previously always returned an
     error.

   - If the MIPS Coherence Manager (CM) reports an error then we'll now
     clear that error correctly so that the GCR_ERROR_CAUSE register
     will be updated with information about any future errors"

* tag 'mips_fixes_5.0_3' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux:
  mips: cm: reprime error cause
  mips: loongson64: remove unreachable(), fix loongson_poweroff().
  MIPS: Remove function size check in get_frame_info()
  MIPS: Use lower case for addresses in nexys4ddr.dts
  MIPS: Loongson: Introduce and use loongson_llsc_mb()
  MIPS: VDSO: Include $(ccflags-vdso) in o32,n32 .lds builds
  MIPS: VDSO: Use same -m%-float cflag as the kernel proper
  MIPS: OCTEON: don't set octeon_dma_bar_type if PCI is disabled
  DTS: CI20: Fix bugs in ci20's device tree.
  MIPS: DTS: jz4740: Correct interrupt number of DMA core

arch/mips/Kconfig

@@ -1403,6 +1403,21 @@ config LOONGSON3_ENHANCEMENT
 	  please say 'N' here. If you want a high-performance kernel to run on
 	  new Loongson 3 machines only, please say 'Y' here.
 
+config CPU_LOONGSON3_WORKAROUNDS
+	bool "Old Loongson 3 LLSC Workarounds"
+	default y if SMP
+	depends on CPU_LOONGSON3
+	help
+	  Loongson 3 processors have the llsc issues which require workarounds.
+	  Without workarounds the system may hang unexpectedly.
+
+	  Newer Loongson 3 will fix these issues and no workarounds are needed.
+	  The workarounds have no significant side effect on them but may
+	  decrease the performance of the system so this option should be
+	  disabled unless the kernel is intended to be run on old systems.
+
+	  If unsure, please say Y.
+
 config CPU_LOONGSON2E
 	bool "Loongson 2E"
 	depends on SYS_HAS_CPU_LOONGSON2E

arch/mips/boot/dts/ingenic/ci20.dts

@@ -76,7 +76,7 @@
 	status = "okay";
 
 	pinctrl-names = "default";
-	pinctrl-0 = <&pins_uart2>;
+	pinctrl-0 = <&pins_uart3>;
 };
 
 &uart4 {
@@ -196,9 +196,9 @@
 		bias-disable;
 	};
 
-	pins_uart2: uart2 {
+	pins_uart3: uart3 {
-		function = "uart2";
+		function = "uart3";
-		groups = "uart2-data", "uart2-hwflow";
+		groups = "uart3-data", "uart3-hwflow";
 		bias-disable;
 	};
 

arch/mips/boot/dts/ingenic/jz4740.dtsi

@@ -161,7 +161,7 @@
 		#dma-cells = <2>;
 
 		interrupt-parent = <&intc>;
-		interrupts = <29>;
+		interrupts = <20>;
 
 		clocks = <&cgu JZ4740_CLK_DMA>;
 

arch/mips/boot/dts/xilfpga/nexys4ddr.dts

@@ -90,11 +90,11 @@
 		interrupts = <0>;
 	};
 
-	axi_i2c: i2c@10A00000 {
+	axi_i2c: i2c@10a00000 {
 	    compatible = "xlnx,xps-iic-2.00.a";
 	    interrupt-parent = <&axi_intc>;
 	    interrupts = <4>;
-	    reg = < 0x10A00000 0x10000 >;
+	    reg = < 0x10a00000 0x10000 >;
 	    clocks = <&ext>;
 	    xlnx,clk-freq = <0x5f5e100>;
 	    xlnx,family = "Artix7";
@@ -106,9 +106,9 @@
 	    #address-cells = <1>;
 	    #size-cells = <0>;
 
-	    ad7420@4B {
+	    ad7420@4b {
 		compatible = "adi,adt7420";
-		reg = <0x4B>;
+		reg = <0x4b>;
 	    };
 	} ;
 };

arch/mips/include/asm/atomic.h

@@ -58,6 +58,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -85,6 +86,7 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -118,6 +120,7 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
 	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -256,6 +259,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -283,6 +287,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \
@@ -316,6 +321,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
 	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
+		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
 		"	.set	push					\n"   \
 		"	.set	"MIPS_ISA_LEVEL"			\n"   \

arch/mips/include/asm/barrier.h

@@ -222,6 +222,42 @@
 #define __smp_mb__before_atomic()	__smp_mb__before_llsc()
 #define __smp_mb__after_atomic()	smp_llsc_mb()
 
+/*
+ * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load,
+ * store or pref) in between an ll & sc can cause the sc instruction to
+ * erroneously succeed, breaking atomicity. Whilst it's unusual to write code
+ * containing such sequences, this bug bites harder than we might otherwise
+ * expect due to reordering & speculation:
+ *
+ * 1) A memory access appearing prior to the ll in program order may actually
+ *    be executed after the ll - this is the reordering case.
+ *
+ *    In order to avoid this we need to place a memory barrier (ie. a sync
+ *    instruction) prior to every ll instruction, in between it & any earlier
+ *    memory access instructions. Many of these cases are already covered by
+ *    smp_mb__before_llsc() but for the remaining cases, typically ones in
+ *    which multiple CPUs may operate on a memory location but ordering is not
+ *    usually guaranteed, we use loongson_llsc_mb() below.
+ *
+ *    This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later.
+ *
+ * 2) If a conditional branch exists between an ll & sc with a target outside
+ *    of the ll-sc loop, for example an exit upon value mismatch in cmpxchg()
+ *    or similar, then misprediction of the branch may allow speculative
+ *    execution of memory accesses from outside of the ll-sc loop.
+ *
+ *    In order to avoid this we need a memory barrier (ie. a sync instruction)
+ *    at each affected branch target, for which we also use loongson_llsc_mb()
+ *    defined below.
+ *
+ *    This case affects all current Loongson 3 CPUs.
+ */
+#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */
+#define loongson_llsc_mb()	__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
+#else
+#define loongson_llsc_mb()	do { } while (0)
+#endif
+
 #include <asm-generic/barrier.h>
 
 #endif /* __ASM_BARRIER_H */

arch/mips/include/asm/bitops.h

@@ -69,6 +69,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		: "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m));
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# set_bit	\n"
@@ -79,6 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"
@@ -123,6 +125,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		: "ir" (~(1UL << bit)));
 #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6)
 	} else if (kernel_uses_llsc && __builtin_constant_p(bit)) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	" __LL "%0, %1		# clear_bit	\n"
@@ -133,6 +136,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
 		} while (unlikely(!temp));
 #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */
 	} else if (kernel_uses_llsc) {
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"
@@ -193,6 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 		unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG);
 		unsigned long temp;
 
+		loongson_llsc_mb();
 		do {
 			__asm__ __volatile__(
 			"	.set	push				\n"

arch/mips/include/asm/futex.h

@@ -50,6 +50,7 @@
 		  "i" (-EFAULT)						\
 		: "memory");						\
 	} else if (cpu_has_llsc) {					\
+		loongson_llsc_mb();					\
 		__asm__ __volatile__(					\
 		"	.set	push				\n"	\
 		"	.set	noat				\n"	\
@@ -163,6 +164,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		  "i" (-EFAULT)
 		: "memory");
 	} else if (cpu_has_llsc) {
+		loongson_llsc_mb();
 		__asm__ __volatile__(
 		"# futex_atomic_cmpxchg_inatomic			\n"
 		"	.set	push					\n"
@@ -192,6 +194,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		: GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
 		  "i" (-EFAULT)
 		: "memory");
+		loongson_llsc_mb();
 	} else
 		return -ENOSYS;
 

arch/mips/include/asm/pgtable.h

@@ -228,6 +228,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 			: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
 			: [global] "r" (page_global));
 		} else if (kernel_uses_llsc) {
+			loongson_llsc_mb();
 			__asm__ __volatile__ (
 			"	.set	push				\n"
 			"	.set	"MIPS_ISA_ARCH_LEVEL"		\n"
@@ -242,6 +243,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 			"	.set	pop				\n"
 			: [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
 			: [global] "r" (page_global));
+			loongson_llsc_mb();
 		}
 #else /* !CONFIG_SMP */
 		if (pte_none(*buddy))

arch/mips/kernel/mips-cm.c

@@ -457,5 +457,5 @@ void mips_cm_error_report(void)
 	}
 
 	/* reprime cause register */
-	write_gcr_error_cause(0);
+	write_gcr_error_cause(cm_error);
 }

arch/mips/kernel/process.c

@@ -371,7 +371,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size)
 static int get_frame_info(struct mips_frame_info *info)
 {
 	bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
-	union mips_instruction insn, *ip, *ip_end;
+	union mips_instruction insn, *ip;
 	const unsigned int max_insns = 128;
 	unsigned int last_insn_size = 0;
 	unsigned int i;
@@ -384,10 +384,9 @@ static int get_frame_info(struct mips_frame_info *info)
 	if (!ip)
 		goto err;
 
-	ip_end = (void *)ip + info->func_size;
+	for (i = 0; i < max_insns; i++) {
-
-	for (i = 0; i < max_insns && ip < ip_end; i++) {
 		ip = (void *)ip + last_insn_size;
+
 		if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
 			insn.word = ip->halfword[0] << 16;
 			last_insn_size = 2;

arch/mips/loongson64/Platform

@@ -23,6 +23,29 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS
 endif
 
 cflags-$(CONFIG_CPU_LOONGSON3)	+= -Wa,--trap
+
+#
+# Some versions of binutils, not currently mainline as of 2019/02/04, support
+# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction
+# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a
+# description).
+#
+# We disable this in order to prevent the assembler meddling with the
+# instruction that labels refer to, ie. if we label an ll instruction:
+#
+# 1: ll v0, 0(a0)
+#
+# ...then with the assembler fix applied the label may actually point at a sync
+# instruction inserted by the assembler, and if we were using the label in an
+# exception table the table would no longer contain the address of the ll
+# instruction.
+#
+# Avoid this by explicitly disabling that assembler behaviour. If upstream
+# binutils does not merge support for the flag then we can revisit & remove
+# this later - for now it ensures vendor toolchains don't cause problems.
+#
+cflags-$(CONFIG_CPU_LOONGSON3)	+= $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,)
+
 #
 # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a
 # as MIPS64 R2; older versions as just R1.  This leaves the possibility open

arch/mips/loongson64/common/reset.c

@@ -59,7 +59,12 @@ static void loongson_poweroff(void)
 {
 #ifndef CONFIG_LEFI_FIRMWARE_INTERFACE
 	mach_prepare_shutdown();
-	unreachable();
+
+	/*
+	 * It needs a wait loop here, but mips/kernel/reset.c already calls
+	 * a generic delay loop, machine_hang(), so simply return.
+	 */
+	return;
 #else
 	void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr;
 

arch/mips/mm/tlbex.c

@@ -932,6 +932,8 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		 * to mimic that here by taking a load/istream page
 		 * fault.
 		 */
+		if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS))
+			uasm_i_sync(p, 0);
 		UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0);
 		uasm_i_jr(p, ptr);
 
@@ -1646,6 +1648,8 @@ static void
 iPTE_LW(u32 **p, unsigned int pte, unsigned int ptr)
 {
 #ifdef CONFIG_SMP
+	if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS))
+		uasm_i_sync(p, 0);
 # ifdef CONFIG_PHYS_ADDR_T_64BIT
 	if (cpu_has_64bits)
 		uasm_i_lld(p, pte, 0, ptr);
@@ -2259,6 +2263,8 @@ static void build_r4000_tlb_load_handler(void)
 #endif
 
 	uasm_l_nopage_tlbl(&l, p);
+	if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS))
+		uasm_i_sync(&p, 0);
 	build_restore_work_registers(&p);
 #ifdef CONFIG_CPU_MICROMIPS
 	if ((unsigned long)tlb_do_page_fault_0 & 1) {
@@ -2313,6 +2319,8 @@ static void build_r4000_tlb_store_handler(void)
 #endif
 
 	uasm_l_nopage_tlbs(&l, p);
+	if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS))
+		uasm_i_sync(&p, 0);
 	build_restore_work_registers(&p);
 #ifdef CONFIG_CPU_MICROMIPS
 	if ((unsigned long)tlb_do_page_fault_1 & 1) {
@@ -2368,6 +2376,8 @@ static void build_r4000_tlb_modify_handler(void)
 #endif
 
 	uasm_l_nopage_tlbm(&l, p);
+	if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS))
+		uasm_i_sync(&p, 0);
 	build_restore_work_registers(&p);
 #ifdef CONFIG_CPU_MICROMIPS
 	if ((unsigned long)tlb_do_page_fault_1 & 1) {

arch/mips/pci/pci-octeon.c

@@ -568,6 +568,11 @@ static int __init octeon_pci_setup(void)
 	if (octeon_has_feature(OCTEON_FEATURE_PCIE))
 		return 0;
 
+	if (!octeon_is_pci_host()) {
+		pr_notice("Not in host mode, PCI Controller not initialized\n");
+		return 0;
+	}
+
 	/* Point pcibios_map_irq() to the PCI version of it */
 	octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq;
 
@@ -579,11 +584,6 @@ static int __init octeon_pci_setup(void)
 	else
 		octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG;
 
-	if (!octeon_is_pci_host()) {
-		pr_notice("Not in host mode, PCI Controller not initialized\n");
-		return 0;
-	}
-
 	/* PCI I/O and PCI MEM values */
 	set_io_port_base(OCTEON_PCI_IOSPACE_BASE);
 	ioport_resource.start = 0;

arch/mips/vdso/Makefile

@@ -8,6 +8,7 @@ ccflags-vdso := \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS)) \
+	$(filter -m%-float,$(KBUILD_CFLAGS)) \
 	-D__VDSO__
 
 ifdef CONFIG_CC_IS_CLANG
@@ -129,7 +130,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32
+$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32
 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)
 
@@ -169,7 +170,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE
 	$(call cmd,force_checksrc)
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32
+$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32
 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE
 	$(call if_changed_dep,cpp_lds_S)