Merge 5.14-rc5 into usb-next

We need the usb fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

17 files changed, 126 insertions, 43 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b5b13a932561..fdcd54d39c1e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1800,11 +1800,11 @@ config RANDOMIZE_BASE
 	  If unsure, say N.
 
 config RANDOMIZE_MODULE_REGION_FULL
-	bool "Randomize the module region over a 4 GB range"
+	bool "Randomize the module region over a 2 GB range"
 	depends on RANDOMIZE_BASE
 	default y
 	help
-	  Randomizes the location of the module region inside a 4 GB window
+	  Randomizes the location of the module region inside a 2 GB window
 	  covering the core kernel. This way, it is less likely for modules
 	  to leak information about the location of core kernel data structures
 	  but it does imply that function calls between modules and the core
@@ -1812,7 +1812,10 @@ config RANDOMIZE_MODULE_REGION_FULL
 
 	  When this option is not set, the module region will be randomized over
 	  a limited range that contains the [_stext, _etext] interval of the
-	  core kernel, so branch relocations are always in range.
+	  core kernel, so branch relocations are almost always in range unless
+	  ARM64_MODULE_PLTS is enabled and the region is exhausted. In this
+	  particular case of region exhaustion, modules might be able to fall
+	  back to a larger 2GB area.
 
 config CC_HAVE_STACKPROTECTOR_SYSREG
 	def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0)
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7bc37d0a1b68..7b668db43261 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -21,19 +21,11 @@ LDFLAGS_vmlinux		+= -shared -Bsymbolic -z notext \
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
-  ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
-$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
-  else
+  ifeq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
 LDFLAGS_vmlinux	+= --fix-cortex-a53-843419
   endif
 endif
 
-ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
-  ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
-$(warning LSE atomics not supported by binutils)
-  endif
-endif
-
 cc_has_k_constraint := $(call try-run,echo				\
 	'int main(void) {						\
 		asm volatile("and w0, w0, %w0" :: "K" (4294967295));	\
@@ -176,6 +168,17 @@ vdso_install:
 
 archprepare:
 	$(Q)$(MAKE) $(build)=arch/arm64/tools kapi
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+  ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
+	@echo "warning: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum" >&2
+  endif
+endif
+ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS),y)
+  ifneq ($(CONFIG_ARM64_LSE_ATOMICS),y)
+	@echo "warning: LSE atomics not supported by binutils" >&2
+  endif
+endif
+
 
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
index dd764b720fb0..f6a79c8080d1 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
@@ -54,6 +54,7 @@
 
 &mscc_felix_port0 {
 	label = "swp0";
+	managed = "in-band-status";
 	phy-handle = <&phy0>;
 	phy-mode = "sgmii";
 	status = "okay";
@@ -61,6 +62,7 @@
 
 &mscc_felix_port1 {
 	label = "swp1";
+	managed = "in-band-status";
 	phy-handle = <&phy1>;
 	phy-mode = "sgmii";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index b2e3e5d2a108..343ecf0e8973 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -66,7 +66,7 @@
 		};
 	};
 
-	sysclk: clock-sysclk {
+	sysclk: sysclk {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <100000000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index ca38d0d6c3c4..f4eaab3ecf03 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -579,7 +579,7 @@
 			};
 
 			flexcan1: can@308c0000 {
-				compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+				compatible = "fsl,imx8mp-flexcan";
 				reg = <0x308c0000 0x10000>;
 				interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
@@ -594,7 +594,7 @@
 			};
 
 			flexcan2: can@308d0000 {
-				compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+				compatible = "fsl,imx8mp-flexcan";
 				reg = <0x308d0000 0x10000>;
 				interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index ce2bcddf396f..a05b1ab2dd12 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -19,6 +19,8 @@
 	aliases {
 		spi0 = &spi0;
 		ethernet1 = &eth1;
+		mmc0 = &sdhci0;
+		mmc1 = &sdhci1;
 	};
 
 	chosen {
@@ -119,6 +121,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <100000>;
+	/delete-property/ mrvl,i2c-fast-mode;
 	status = "okay";
 
 	rtc@6f {
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 076d5efc4c3d..5ba7a4519b95 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -1840,7 +1840,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE1R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE1W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE1>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE1 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14120000 {
@@ -1890,7 +1894,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE2AR &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE2AW &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE2>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE2 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14140000 {
@@ -1940,7 +1948,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE3R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE3W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE3>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE3 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14160000 {
@@ -1990,7 +2002,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE4>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14180000 {
@@ -2040,7 +2056,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE0>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@141a0000 {
@@ -2094,7 +2114,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE5>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@14160000 {
@@ -2127,6 +2151,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE4>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@14180000 {
@@ -2159,6 +2191,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE0>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@141a0000 {
@@ -2194,6 +2234,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE5>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	sram@40000000 {
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index e58bca832dff..41b332c054ab 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -320,7 +320,17 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
-	return regs->regs[0];
+	unsigned long val = regs->regs[0];
+
+	/*
+	 * Audit currently uses regs_return_value() instead of
+	 * syscall_get_return_value(). Apply the same sign-extension here until
+	 * audit is updated to use syscall_get_return_value().
+	 */
+	if (compat_user_mode(regs))
+		val = sign_extend64(val, 31);
+
+	return val;
 }
 
 static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 1801399204d7..8aebc00c1718 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -35,7 +35,7 @@ struct stack_info {
  * accounting information necessary for robust unwinding.
  *
  * @fp:          The fp value in the frame record (or the real fp)
- * @pc:          The fp value in the frame record (or the real lr)
+ * @pc:          The lr value in the frame record (or the real lr)
  *
  * @stacks_done: Stacks which have been entirely unwound, for which it is no
  *               longer valid to unwind to.
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index cfc0672013f6..03e20895453a 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -29,22 +29,23 @@ static inline void syscall_rollback(struct task_struct *task,
 	regs->regs[0] = regs->orig_x0;
 }
 
-
-static inline long syscall_get_error(struct task_struct *task,
-				     struct pt_regs *regs)
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
 {
-	unsigned long error = regs->regs[0];
+	unsigned long val = regs->regs[0];
 
 	if (is_compat_thread(task_thread_info(task)))
-		error = sign_extend64(error, 31);
+		val = sign_extend64(val, 31);
 
-	return IS_ERR_VALUE(error) ? error : 0;
+	return val;
 }
 
-static inline long syscall_get_return_value(struct task_struct *task,
-					    struct pt_regs *regs)
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
 {
-	return regs->regs[0];
+	unsigned long error = syscall_get_return_value(task, regs);
+
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline void syscall_set_return_value(struct task_struct *task,
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index cfa2cfde3019..418b2bba1521 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -162,7 +162,9 @@ u64 __init kaslr_early_init(void)
 		 * a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE,
 		 * _stext) . This guarantees that the resulting region still
 		 * covers [_stext, _etext], and that all relative branches can
-		 * be resolved without veneers.
+		 * be resolved without veneers unless this region is exhausted
+		 * and we fall back to a larger 2GB window in module_alloc()
+		 * when ARM64_MODULE_PLTS is enabled.
 		 */
 		module_range = MODULES_VSIZE - (u64)(_etext - _stext);
 		module_alloc_base = (u64)_etext + offset - MODULES_VSIZE;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 499b6b2f9757..b381a1ee9ea7 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1862,7 +1862,7 @@ void syscall_trace_exit(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	if (flags & _TIF_SYSCALL_TRACEPOINT)
-		trace_sys_exit(regs, regs_return_value(regs));
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
 	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f8192f4ae0b8..23036334f4dc 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -29,6 +29,7 @@
 #include <asm/unistd.h>
 #include <asm/fpsimd.h>
 #include <asm/ptrace.h>
+#include <asm/syscall.h>
 #include <asm/signal32.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -890,7 +891,7 @@ static void do_signal(struct pt_regs *regs)
 		     retval == -ERESTART_RESTARTBLOCK ||
 		     (retval == -ERESTARTSYS &&
 		      !(ksig.ka.sa.sa_flags & SA_RESTART)))) {
-			regs->regs[0] = -EINTR;
+			syscall_set_return_value(current, regs, -EINTR, 0);
 			regs->pc = continue_addr;
 		}
 
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index b83c8d911930..8982a2b78acf 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -218,7 +218,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 
 #ifdef CONFIG_STACKTRACE
 
-noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
 			      void *cookie, struct task_struct *task,
 			      struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 263d6c1a525f..50a0f1a38e84 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -54,10 +54,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
-	if (is_compat_task())
-		ret = lower_32_bits(ret);
-
-	regs->regs[0] = ret;
+	syscall_set_return_value(current, regs, 0, ret);
 
 	/*
 	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
@@ -115,7 +112,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		 * syscall. do_notify_resume() will send a signal to userspace
 		 * before the syscall is restarted.
 		 */
-		regs->regs[0] = -ERESTARTNOINTR;
+		syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0);
 		return;
 	}
 
@@ -136,7 +133,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		 * anyway.
 		 */
 		if (scno == NO_SYSCALL)
-			regs->regs[0] = -ENOSYS;
+			syscall_set_return_value(current, regs, -ENOSYS, 0);
 		scno = syscall_trace_enter(regs);
 		if (scno == NO_SYSCALL)
 			goto trace_exit;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 3155c9e778f0..0625bf2353c2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -947,7 +947,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
 
-	shared = (vma->vm_flags & VM_PFNMAP);
+	shared = (vma->vm_flags & VM_SHARED);
 
 	switch (vma_shift) {
 #ifndef __PAGETABLE_PMD_FOLDED
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index dccf98a37283..41c23f474ea6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -823,6 +823,19 @@ emit_cond_jmp:
 			return ret;
 		break;
 
+	/* speculation barrier */
+	case BPF_ST | BPF_NOSPEC:
+		/*
+		 * Nothing required here.
+		 *
+		 * In case of arm64, we rely on the firmware mitigation of
+		 * Speculative Store Bypass as controlled via the ssbd kernel
+		 * parameter. Whenever the mitigation is enabled, it works
+		 * for all of the kernel code with no need to provide any
+		 * additional instructions.
+		 */
+		break;
+
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
 	case BPF_ST | BPF_MEM | BPF_H: