Merge tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 fixes from Will Deacon:
 "Minor fixes all over, ranging from typos to tests to errata
  workarounds:

   - Fix possible memory hotplug failure with KASLR

   - Fix FFR value in SVE kselftest

   - Fix backtraces reported in /proc/$pid/stack

   - Disable broken CnP implementation on NVIDIA Carmel

   - Typo fixes and ACPI documentation clarification

   - Fix some W=1 warnings"

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: kernel: disable CNP on Carmel
  arm64/process.c: fix Wmissing-prototypes build warnings
  kselftest/arm64: sve: Do not use non-canonical FFR register value
  arm64: mm: correct the inside linear map range during hotplug check
  arm64: kdump: update ppos when reading elfcorehdr
  arm64: cpuinfo: Fix a typo
  Documentation: arm64/acpi : clarify arm64 support of IBFT
  arm64: stacktrace: don't trace arch_stack_walk()
  arm64: csum: cast to the proper type
diff --git a/Documentation/arm64/acpi_object_usage.rst b/Documentation/arm64/acpi_object_usage.rst
index 377e9d2..0609da7 100644
--- a/Documentation/arm64/acpi_object_usage.rst
+++ b/Documentation/arm64/acpi_object_usage.rst
@@ -17,12 +17,12 @@
 
        -  Recommended: BERT, EINJ, ERST, HEST, PCCT, SSDT
 
-       -  Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IORT,
-          MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, STAO,
-	  TCPA, TPM2, UEFI, XENV
+       -  Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IBFT,
+          IORT, MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT,
+          STAO, TCPA, TPM2, UEFI, XENV
 
-       -  Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, LPIT,
-          MSDM, OEMx, PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
+       -  Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IVRS, LPIT, MSDM, OEMx,
+          PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
 
 ====== ========================================================================
 Table  Usage for ARMv8 Linux
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index 7195102..d410a47 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -130,6 +130,9 @@
 | Marvell        | ARM-MMU-500     | #582743         | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | Carmel Core     | N/A             | NVIDIA_CARMEL_CNP_ERRATUM   |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5656e7a..e4e1b65 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -810,6 +810,16 @@
 
 	  If unsure, say Y.
 
+config NVIDIA_CARMEL_CNP_ERRATUM
+	bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores"
+	default y
+	help
+	  If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not
+	  invalidate shared TLB entries installed by a different core, as it would
+	  on standard ARM cores.
+
+	  If unsure, say Y.
+
 config SOCIONEXT_SYNQUACER_PREITS
 	bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
 	default y
diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 93a161b..dc52b73 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -37,7 +37,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	} while (--n > 0);
 
 	sum += ((sum >> 32) | (sum << 32));
-	return csum_fold((__force u32)(sum >> 32));
+	return csum_fold((__force __wsum)(sum >> 32));
 }
 #define ip_fast_csum ip_fast_csum
 
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index b77d997..c40f249 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -66,7 +66,8 @@
 #define ARM64_WORKAROUND_1508412		58
 #define ARM64_HAS_LDAPR				59
 #define ARM64_KVM_PROTECTED_MODE		60
+#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP	61
 
-#define ARM64_NCAPS				61
+#define ARM64_NCAPS				62
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index ca2cd75..efc10e9 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -251,6 +251,8 @@ unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);
 
+asmlinkage void arm64_preempt_schedule_irq(void);
+
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 9f4e3b2..6623c99 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -55,6 +55,8 @@ void arch_setup_new_exec(void);
 #define arch_setup_new_exec     arch_setup_new_exec
 
 void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst,
+				struct task_struct *src);
 
 #endif
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 506a1cd..e2c20c0 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -526,6 +526,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 				  1, 0),
 	},
 #endif
+#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM
+	{
+		/* NVIDIA Carmel */
+		.desc = "NVIDIA Carmel CNP erratum",
+		.capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+	},
+#endif
 	{
 	}
 };
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0660307..2a5d9854 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1321,7 +1321,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
 	 * may share TLB entries with a CPU stuck in the crashed
 	 * kernel.
 	 */
-	 if (is_kdump_kernel())
+	if (is_kdump_kernel())
+		return false;
+
+	if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP))
 		return false;
 
 	return has_cpuid_feature(entry, scope);
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 77605ae..51fcf99 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -353,7 +353,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	 * with the CLIDR_EL1 fields to avoid triggering false warnings
 	 * when there is a mismatch across the CPUs. Keep track of the
 	 * effective value of the CTR_EL0 in our internal records for
-	 * acurate sanity check and feature enablement.
+	 * accurate sanity check and feature enablement.
 	 */
 	info->reg_ctr = read_cpuid_effective_cachetype();
 	info->reg_dczid = read_cpuid(DCZID_EL0);
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
index e6e2842..58303a9 100644
--- a/arch/arm64/kernel/crash_dump.c
+++ b/arch/arm64/kernel/crash_dump.c
@@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
 ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
 {
 	memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+	*ppos += count;
+
 	return count;
 }
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 325c83b..6e60aa3 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -57,6 +57,8 @@
 #include <asm/processor.h>
 #include <asm/pointer_auth.h>
 #include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/system_misc.h>
 
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index ad20981..d55bdfb 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -194,8 +194,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 
 #ifdef CONFIG_STACKTRACE
 
-void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
-		     struct task_struct *task, struct pt_regs *regs)
+noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+			      void *cookie, struct task_struct *task,
+			      struct pt_regs *regs)
 {
 	struct stackframe frame;
 
@@ -203,8 +204,8 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 		start_backtrace(&frame, regs->regs[29], regs->pc);
 	else if (task == current)
 		start_backtrace(&frame,
-				(unsigned long)__builtin_frame_address(0),
-				(unsigned long)arch_stack_walk);
+				(unsigned long)__builtin_frame_address(1),
+				(unsigned long)__builtin_return_address(0));
 	else
 		start_backtrace(&frame, thread_saved_fp(task),
 				thread_saved_pc(task));
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 7484ea4..5d9550f 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1448,6 +1448,22 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
 struct range arch_get_mappable_range(void)
 {
 	struct range mhp_range;
+	u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+	u64 end_linear_pa = __pa(PAGE_END - 1);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		/*
+		 * Check for a wrap, it is possible because of randomized linear
+		 * mapping the start physical address is actually bigger than
+		 * the end physical address. In this case set start to zero
+		 * because [0, end_linear_pa] range must still be able to cover
+		 * all addressable physical addresses.
+		 */
+		if (start_linear_pa > end_linear_pa)
+			start_linear_pa = 0;
+	}
+
+	WARN_ON(start_linear_pa > end_linear_pa);
 
 	/*
 	 * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
@@ -1455,8 +1471,9 @@ struct range arch_get_mappable_range(void)
 	 * range which can be mapped inside this linear mapping range, must
 	 * also be derived from its end points.
 	 */
-	mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual));
-	mhp_range.end =  __pa(PAGE_END - 1);
+	mhp_range.start = start_linear_pa;
+	mhp_range.end =  end_linear_pa;
+
 	return mhp_range;
 }
 
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index 9210691..e3e08d9 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -284,16 +284,28 @@
 // Set up test pattern in the FFR
 // x0: pid
 // x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
 // Beware: corrupts P0.
 function setup_ffr
 	mov	x4, x30
 
-	bl	pattern
+	and	w0, w0, #0x3
+	bfi	w0, w2, #2, #2
+	mov	w1, #1
+	lsl	w1, w1, w0
+	sub	w1, w1, #1
+
 	ldr	x0, =ffrref
-	ldr	x1, =scratch
-	rdvl	x2, #1
-	lsr	x2, x2, #3
-	bl	memcpy
+	strh	w1, [x0], 2
+	rdvl	x1, #1
+	lsr	x1, x1, #3
+	sub	x1, x1, #2
+	bl	memclr
 
 	mov	x0, #0
 	ldr	x1, =ffrref