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

Pull arm64 updates from Will Deacon:
 "Here are the core arm64 updates for 4.1.

  Highlights include a significant rework to head.S (allowing us to boot
  on machines with physical memory at a really high address), an AES
  performance boost on Cortex-A57 and the ability to run a 32-bit
  userspace with 64k pages (although this requires said userspace to be
  built with a recent binutils).

  The head.S rework spilt over into KVM, so there are some changes under
  arch/arm/ which have been acked by Marc Zyngier (KVM co-maintainer).
  In particular, the linker script changes caused us some issues in
  -next, so there are a few merge commits where we had to apply fixes on
  top of a stable branch.

  Other changes include:

   - AES performance boost for Cortex-A57
   - AArch32 (compat) userspace with 64k pages
   - Cortex-A53 erratum workaround for #845719
   - defconfig updates (new platforms, PCI, ...)"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (39 commits)
  arm64: fix midr range for Cortex-A57 erratum 832075
  arm64: errata: add workaround for cortex-a53 erratum #845719
  arm64: Use bool function return values of true/false not 1/0
  arm64: defconfig: updates for 4.1
  arm64: Extract feature parsing code from cpu_errata.c
  arm64: alternative: Allow immediate branch as alternative instruction
  arm64: insn: Add aarch64_insn_decode_immediate
  ARM: kvm: round HYP section to page size instead of log2 upper bound
  ARM: kvm: assert on HYP section boundaries not actual code size
  arm64: head.S: ensure idmap_t0sz is visible
  arm64: pmu: add support for interrupt-affinity property
  dt: pmu: extend ARM PMU binding to allow for explicit interrupt affinity
  arm64: head.S: ensure visibility of page tables
  arm64: KVM: use ID map with increased VA range if required
  arm64: mm: increase VA range of identity map
  ARM: kvm: implement replacement for ld's LOG2CEIL()
  arm64: proc: remove unused cpu_get_pgd macro
  arm64: enforce x1|x2|x3 == 0 upon kernel entry as per boot protocol
  arm64: remove __calc_phys_offset
  arm64: merge __enable_mmu and __turn_mmu_on
  ...

3 files changed, 47 insertions, 43 deletions

diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 4cf48c3aca13..405aa1883307 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -269,6 +269,16 @@ static inline void __kvm_flush_dcache_pud(pud_t pud)
 void kvm_set_way_flush(struct kvm_vcpu *vcpu);
 void kvm_toggle_cache(struct kvm_vcpu *vcpu, bool was_enabled);
 
+static inline bool __kvm_cpu_uses_extended_idmap(void)
+{
+	return false;
+}
+
+static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
+				       pgd_t *hyp_pgd,
+				       pgd_t *merged_hyp_pgd,
+				       unsigned long hyp_idmap_start) { }
+
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* __ARM_KVM_MMU_H__ */
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 7a301be9ac67..8b60fde5ce48 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -11,7 +11,7 @@
 #ifdef CONFIG_ARM_KERNMEM_PERMS
 #include <asm/pgtable.h>
 #endif
-	
+
 #define PROC_INFO							\
 	. = ALIGN(4);							\
 	VMLINUX_SYMBOL(__proc_info_begin) = .;				\
@@ -23,7 +23,7 @@
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
 	*(.idmap.text)							\
 	VMLINUX_SYMBOL(__idmap_text_end) = .;				\
-	. = ALIGN(32);							\
+	. = ALIGN(PAGE_SIZE);						\
 	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;			\
 	*(.hyp.idmap.text)						\
 	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
@@ -343,8 +343,11 @@ SECTIONS
  */
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+
 /*
- * The HYP init code can't be more than a page long.
+ * The HYP init code can't be more than a page long,
+ * and should not cross a page boundary.
  * The above comment applies as well.
  */
-ASSERT(((__hyp_idmap_text_end - __hyp_idmap_text_start) <= PAGE_SIZE), "HYP init code too big")
+ASSERT(__hyp_idmap_text_end - (__hyp_idmap_text_start & PAGE_MASK) <= PAGE_SIZE,
+	"HYP init code too big or misaligned")
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 15b050d46fc9..1d5accbd3dcf 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -35,9 +35,9 @@ extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
 
 static pgd_t *boot_hyp_pgd;
 static pgd_t *hyp_pgd;
+static pgd_t *merged_hyp_pgd;
 static DEFINE_MUTEX(kvm_hyp_pgd_mutex);
 
-static void *init_bounce_page;
 static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
@@ -405,9 +405,6 @@ void free_boot_hyp_pgd(void)
 	if (hyp_pgd)
 		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
-	free_page((unsigned long)init_bounce_page);
-	init_bounce_page = NULL;
-
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 }
 
@@ -438,6 +435,11 @@ void free_hyp_pgds(void)
 		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
 	}
+	if (merged_hyp_pgd) {
+		clear_page(merged_hyp_pgd);
+		free_page((unsigned long)merged_hyp_pgd);
+		merged_hyp_pgd = NULL;
+	}
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 }
@@ -1622,12 +1624,18 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
 
 phys_addr_t kvm_mmu_get_httbr(void)
 {
-	return virt_to_phys(hyp_pgd);
+	if (__kvm_cpu_uses_extended_idmap())
+		return virt_to_phys(merged_hyp_pgd);
+	else
+		return virt_to_phys(hyp_pgd);
 }
 
 phys_addr_t kvm_mmu_get_boot_httbr(void)
 {
-	return virt_to_phys(boot_hyp_pgd);
+	if (__kvm_cpu_uses_extended_idmap())
+		return virt_to_phys(merged_hyp_pgd);
+	else
+		return virt_to_phys(boot_hyp_pgd);
 }
 
 phys_addr_t kvm_get_idmap_vector(void)
@@ -1643,39 +1651,11 @@ int kvm_mmu_init(void)
 	hyp_idmap_end = kvm_virt_to_phys(__hyp_idmap_text_end);
 	hyp_idmap_vector = kvm_virt_to_phys(__kvm_hyp_init);
 
-	if ((hyp_idmap_start ^ hyp_idmap_end) & PAGE_MASK) {
-		/*
-		 * Our init code is crossing a page boundary. Allocate
-		 * a bounce page, copy the code over and use that.
-		 */
-		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
-		phys_addr_t phys_base;
-
-		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
-		if (!init_bounce_page) {
-			kvm_err("Couldn't allocate HYP init bounce page\n");
-			err = -ENOMEM;
-			goto out;
-		}
-
-		memcpy(init_bounce_page, __hyp_idmap_text_start, len);
-		/*
-		 * Warning: the code we just copied to the bounce page
-		 * must be flushed to the point of coherency.
-		 * Otherwise, the data may be sitting in L2, and HYP
-		 * mode won't be able to observe it as it runs with
-		 * caches off at that point.
-		 */
-		kvm_flush_dcache_to_poc(init_bounce_page, len);
-
-		phys_base = kvm_virt_to_phys(init_bounce_page);
-		hyp_idmap_vector += phys_base - hyp_idmap_start;
-		hyp_idmap_start = phys_base;
-		hyp_idmap_end = phys_base + len;
-
-		kvm_info("Using HYP init bounce page @%lx\n",
-			 (unsigned long)phys_base);
-	}
+	/*
+	 * We rely on the linker script to ensure at build time that the HYP
+	 * init code does not cross a page boundary.
+	 */
+	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
 	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
 	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
@@ -1698,6 +1678,17 @@ int kvm_mmu_init(void)
 		goto out;
 	}
 
+	if (__kvm_cpu_uses_extended_idmap()) {
+		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+		if (!merged_hyp_pgd) {
+			kvm_err("Failed to allocate extra HYP pgd\n");
+			goto out;
+		}
+		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
+				    hyp_idmap_start);
+		return 0;
+	}
+
 	/* Map the very same page at the trampoline VA */
 	err = 	__create_hyp_mappings(boot_hyp_pgd,
 				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,