arm64 fixes:

- Zero buffers allocated with FORCE_CONTIGUOUS explicitly until the CMA
   code honours __GFP_ZERO
 
 - notrace annotation for secondary_start_kernel()
 
 - Use early_param() instead of __setup() for "kpti=" as it is needed for
   the cpufeature callback remapping swapper to non-global mappings
 
 - Ensure writes to swapper are ordered wrt subsequent cache maintenance
   in the kpti non-global remapping code
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE5RElWfyWxS+3PLO2a9axLQDIXvEFAlstMpYACgkQa9axLQDI
 XvGI0w//RK77TVab1nLePDuG8Ky001nOuE1jvJWOSZ5eNSUO4wHIN1Hy7mHN/T44
 9ngV/lG+KFLhbRp24YPCaXNHNPeqb6EpaLZyyq9/CV0o74xWKkU85X2M963NO1dQ
 5Hc9/yNNdbzWlRvhn6rYL2sknmN0Hf6huJDkGaYjFiIxsQtOd4Xw/qy1jFGPSKFP
 Feih3O/GElsMw35kEj5haNpVpfMukNsURL5FgpvEBPJ1S7NZGlFw976R37QePl3P
 8QVBiL0IgbET22TFNPDGFQJXvYHy+V4VG/4a17ODuVf96mwNS1A/D4mH3alNV9G/
 CX6Anf2nLcTCKlfTGVz+LHP31Jq0gxeVY8OZD653kYgOzdx9zNyETkM6D/P2VM2o
 40rwwiZ3gUZAzC4muEM6Zpe4+mJnaGGjsiD5tcMtg3E8ijmjc/sNmtH7fvq1Ggxo
 VsgcSpE+DP0nTcWf8NPoYHESGwHKXHjX7RyOiJF8hjivSxN/CcwGyRmXJcjSP5sC
 VcZDFz/AhKWdCGkDq/kCoccq9WYSeMClAk0hewU6fKX1+pKzvSstVi5yhDxa+aGl
 S5X7oYMgkUYRxGGbejh+4s0w1P4tW6ZkBymMmLISVCYdYbS29xbN+flLNe9Enopp
 G/xch1VcybESGyUpVDr33rcHuxpPEQvzpAQ4+XhYOfATtwgxFhE=
 =cTII
 -----END PGP SIGNATURE-----

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

Pull arm64 fixes from Catalin Marinas:

 - clear buffers allocated with FORCE_CONTIGUOUS explicitly until the
   CMA code honours __GFP_ZERO

 - notrace annotation for secondary_start_kernel()

 - use early_param() instead of __setup() for "kpti=" as it is needed
   for the cpufeature callback remapping swapper to non-global mappings

 - ensure writes to swapper are ordered wrt subsequent cache maintenance
   in the kpti non-global remapping code

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: mm: Ensure writes to swapper are ordered wrt subsequent cache maintenance
  arm64: kpti: Use early_param for kpti= command-line option
  arm64: make secondary_start_kernel() notrace
  arm64: dma-mapping: clear buffers allocated with FORCE_CONTIGUOUS flag

arch/arm64/kernel/cpufeature.c

@@ -937,7 +937,7 @@ static int __init parse_kpti(char *str)
 	__kpti_forced = enabled ? 1 : -1;
 	return 0;
 }
-__setup("kpti=", parse_kpti);
+early_param("kpti", parse_kpti);
 #endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM

arch/arm64/kernel/smp.c

@@ -179,7 +179,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
  */
-asmlinkage void secondary_start_kernel(void)
+asmlinkage notrace void secondary_start_kernel(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;

arch/arm64/mm/dma-mapping.c

@@ -583,13 +583,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 						    size >> PAGE_SHIFT);
 			return NULL;
 		}
-		if (!coherent)
-			__dma_flush_area(page_to_virt(page), iosize);
-
 		addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
 						   prot,
 						   __builtin_return_address(0));
-		if (!addr) {
+		if (addr) {
+			memset(addr, 0, size);
+			if (!coherent)
+				__dma_flush_area(page_to_virt(page), iosize);
+		} else {
 			iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
 			dma_release_from_contiguous(dev, page,
 						    size >> PAGE_SHIFT);

arch/arm64/mm/proc.S

@@ -217,8 +217,9 @@ ENDPROC(idmap_cpu_replace_ttbr1)
 
 	.macro __idmap_kpti_put_pgtable_ent_ng, type
 	orr	\type, \type, #PTE_NG		// Same bit for blocks and pages
-	str	\type, [cur_\()\type\()p]	// Update the entry and ensure it
-	dc	civac, cur_\()\type\()p		// is visible to all CPUs.
+	str	\type, [cur_\()\type\()p]	// Update the entry and ensure
+	dmb	sy				// that it is visible to all
+	dc	civac, cur_\()\type\()p		// CPUs.
 	.endm
 
 /*