Merge branch 'for-next/caches' into for-next/core

Big cleanup of our cache maintenance routines, which were confusingly
named and inconsistent in their implementations.

* for-next/caches:
  arm64: Rename arm64-internal cache maintenance functions
  arm64: Fix cache maintenance function comments
  arm64: sync_icache_aliases to take end parameter instead of size
  arm64: __clean_dcache_area_pou to take end parameter instead of size
  arm64: __clean_dcache_area_pop to take end parameter instead of size
  arm64: __clean_dcache_area_poc to take end parameter instead of size
  arm64: __flush_dcache_area to take end parameter instead of size
  arm64: dcache_by_line_op to take end parameter instead of size
  arm64: __inval_dcache_area to take end parameter instead of size
  arm64: Fix comments to refer to correct function __flush_icache_range
  arm64: Move documentation of dcache_by_line_op
  arm64: assembler: remove user_alt
  arm64: Downgrade flush_icache_range to invalidate
  arm64: Do not enable uaccess for invalidate_icache_range
  arm64: Do not enable uaccess for flush_icache_range
  arm64: Apply errata to swsusp_arch_suspend_exit
  arm64: assembler: add conditional cache fixups
  arm64: assembler: replace `kaddr` with `addr`

13 files changed, 66 insertions, 45 deletions

diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index c906d20c7b52..3fb79b76e9d9 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -181,7 +181,7 @@ static void __nocfi __apply_alternatives(struct alt_region *region, bool is_modu
 	 */
 	if (!is_module) {
 		dsb(ish);
-		__flush_icache_all();
+		icache_inval_all_pou();
 		isb();
 
 		/* Ignore ARM64_CB bit from feature mask */
diff --git a/arch/arm64/kernel/efi-entry.S b/arch/arm64/kernel/efi-entry.S
index 0073b24b5d25..61a87fa1c305 100644
--- a/arch/arm64/kernel/efi-entry.S
+++ b/arch/arm64/kernel/efi-entry.S
@@ -28,7 +28,8 @@ SYM_CODE_START(efi_enter_kernel)
 	 * stale icache entries from before relocation.
 	 */
 	ldr	w1, =kernel_size
-	bl	__clean_dcache_area_poc
+	add	x1, x0, x1
+	bl	dcache_clean_poc
 	ic	ialluis
 
 	/*
@@ -36,8 +37,8 @@ SYM_CODE_START(efi_enter_kernel)
 	 * so that we can safely disable the MMU and caches.
 	 */
 	adr	x0, 0f
-	ldr	w1, 3f
-	bl	__clean_dcache_area_poc
+	adr	x1, 3f
+	bl	dcache_clean_poc
 0:
 	/* Turn off Dcache and MMU */
 	mrs	x0, CurrentEL
@@ -64,5 +65,5 @@ SYM_CODE_START(efi_enter_kernel)
 	mov	x2, xzr
 	mov	x3, xzr
 	br	x19
+3:
 SYM_CODE_END(efi_enter_kernel)
-3:	.long	. - 0b
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 6a700526b117..a6ccd6557d19 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -118,8 +118,8 @@ SYM_CODE_START_LOCAL(preserve_boot_args)
 	dmb	sy				// needed before dc ivac with
 						// MMU off
 
-	mov	x1, #0x20			// 4 x 8 bytes
-	b	__inval_dcache_area		// tail call
+	add	x1, x0, #0x20			// 4 x 8 bytes
+	b	dcache_inval_poc		// tail call
 SYM_CODE_END(preserve_boot_args)
 
 /*
@@ -269,8 +269,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	 */
 	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	/*
 	 * Clear the init page tables.
@@ -383,13 +382,11 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 
 	adrp	x0, idmap_pg_dir
 	adrp	x1, idmap_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	adrp	x0, init_pg_dir
 	adrp	x1, init_pg_end
-	sub	x1, x1, x0
-	bl	__inval_dcache_area
+	bl	dcache_inval_poc
 
 	ret	x28
 SYM_FUNC_END(__create_page_tables)
diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S
index 8ccca660034e..81c0186a5e32 100644
--- a/arch/arm64/kernel/hibernate-asm.S
+++ b/arch/arm64/kernel/hibernate-asm.S
@@ -45,7 +45,7 @@
  * Because this code has to be copied to a 'safe' page, it can't call out to
  * other functions by PC-relative address. Also remember that it may be
  * mid-way through over-writing other functions. For this reason it contains
- * code from flush_icache_range() and uses the copy_page() macro.
+ * code from caches_clean_inval_pou() and uses the copy_page() macro.
  *
  * This 'safe' page is mapped via ttbr0, and executed from there. This function
  * switches to a copy of the linear map in ttbr1, performs the restore, then
@@ -87,11 +87,12 @@ SYM_CODE_START(swsusp_arch_suspend_exit)
 	copy_page	x0, x1, x2, x3, x4, x5, x6, x7, x8, x9
 
 	add	x1, x10, #PAGE_SIZE
-	/* Clean the copied page to PoU - based on flush_icache_range() */
+	/* Clean the copied page to PoU - based on caches_clean_inval_pou() */
 	raw_dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x10, x3
-2:	dc	cvau, x4	/* clean D line / unified line */
+2:	/* clean D line / unified line */
+alternative_insn "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	add	x4, x4, x2
 	cmp	x4, x1
 	b.lo	2b
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index b1cef371df2b..46a0b4d6e251 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -210,7 +210,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
 		return -ENOMEM;
 
 	memcpy(page, src_start, length);
-	__flush_icache_range((unsigned long)page, (unsigned long)page + length);
+	caches_clean_inval_pou((unsigned long)page, (unsigned long)page + length);
 	rc = trans_pgd_idmap_page(&trans_info, &trans_ttbr0, &t0sz, page);
 	if (rc)
 		return rc;
@@ -240,8 +240,6 @@ static int create_safe_exec_page(void *src_start, size_t length,
 	return 0;
 }
 
-#define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
-
 #ifdef CONFIG_ARM64_MTE
 
 static DEFINE_XARRAY(mte_pages);
@@ -383,13 +381,18 @@ int swsusp_arch_suspend(void)
 		ret = swsusp_save();
 	} else {
 		/* Clean kernel core startup/idle code to PoC*/
-		dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
-		dcache_clean_range(__idmap_text_start, __idmap_text_end);
+		dcache_clean_inval_poc((unsigned long)__mmuoff_data_start,
+				    (unsigned long)__mmuoff_data_end);
+		dcache_clean_inval_poc((unsigned long)__idmap_text_start,
+				    (unsigned long)__idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
 		if (el2_reset_needed()) {
-			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
-			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+			dcache_clean_inval_poc(
+				(unsigned long)__hyp_idmap_text_start,
+				(unsigned long)__hyp_idmap_text_end);
+			dcache_clean_inval_poc((unsigned long)__hyp_text_start,
+					    (unsigned long)__hyp_text_end);
 		}
 
 		swsusp_mte_restore_tags();
@@ -474,7 +477,8 @@ int swsusp_arch_resume(void)
 	 * The hibernate exit text contains a set of el2 vectors, that will
 	 * be executed at el2 with the mmu off in order to reload hyp-stub.
 	 */
-	__flush_dcache_area(hibernate_exit, exit_size);
+	dcache_clean_inval_poc((unsigned long)hibernate_exit,
+			    (unsigned long)hibernate_exit + exit_size);
 
 	/*
 	 * KASLR will cause the el2 vectors to be in a different location in
diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c
index e628c8ce1ffe..53a381a7f65d 100644
--- a/arch/arm64/kernel/idreg-override.c
+++ b/arch/arm64/kernel/idreg-override.c
@@ -237,7 +237,8 @@ asmlinkage void __init init_feature_override(void)
 
 	for (i = 0; i < ARRAY_SIZE(regs); i++) {
 		if (regs[i]->override)
-			__flush_dcache_area(regs[i]->override,
+			dcache_clean_inval_poc((unsigned long)regs[i]->override,
+					    (unsigned long)regs[i]->override +
 					    sizeof(*regs[i]->override));
 	}
 }
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index bcf3c2755370..c96a9a0043bf 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -35,7 +35,7 @@ __efistub_strnlen		= __pi_strnlen;
 __efistub_strcmp		= __pi_strcmp;
 __efistub_strncmp		= __pi_strncmp;
 __efistub_strrchr		= __pi_strrchr;
-__efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc;
+__efistub_dcache_clean_poc = __pi_dcache_clean_poc;
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 __efistub___memcpy		= __pi_memcpy;
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 6c0de2f60ea9..51cb8dc98d00 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -198,7 +198,7 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 
 	ret = aarch64_insn_write(tp, insn);
 	if (ret == 0)
-		__flush_icache_range((uintptr_t)tp,
+		caches_clean_inval_pou((uintptr_t)tp,
 				     (uintptr_t)tp + AARCH64_INSN_SIZE);
 
 	return ret;
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 341342b207f6..cfa2cfde3019 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -72,7 +72,9 @@ u64 __init kaslr_early_init(void)
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
-	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	dcache_clean_inval_poc((unsigned long)&module_alloc_base,
+			    (unsigned long)&module_alloc_base +
+				    sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -170,8 +172,12 @@ u64 __init kaslr_early_init(void)
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
-	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
-	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+	dcache_clean_inval_poc((unsigned long)&module_alloc_base,
+			    (unsigned long)&module_alloc_base +
+				    sizeof(module_alloc_base));
+	dcache_clean_inval_poc((unsigned long)&memstart_offset_seed,
+			    (unsigned long)&memstart_offset_seed +
+				    sizeof(memstart_offset_seed));
 
 	return offset;
 }
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 90a335c74442..03ceabe4d912 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -68,10 +68,16 @@ int machine_kexec_post_load(struct kimage *kimage)
 	kimage->arch.kern_reloc = __pa(reloc_code);
 	kexec_image_info(kimage);
 
-	/* Flush the reloc_code in preparation for its execution. */
-	__flush_dcache_area(reloc_code, arm64_relocate_new_kernel_size);
-	flush_icache_range((uintptr_t)reloc_code, (uintptr_t)reloc_code +
-			   arm64_relocate_new_kernel_size);
+	/*
+	 * For execution with the MMU off, reloc_code needs to be cleaned to the
+	 * PoC and invalidated from the I-cache.
+	 */
+	dcache_clean_inval_poc((unsigned long)reloc_code,
+			    (unsigned long)reloc_code +
+				    arm64_relocate_new_kernel_size);
+	icache_inval_pou((uintptr_t)reloc_code,
+				(uintptr_t)reloc_code +
+					arm64_relocate_new_kernel_size);
 
 	return 0;
 }
@@ -102,16 +108,18 @@ static void kexec_list_flush(struct kimage *kimage)
 
 	for (entry = &kimage->head; ; entry++) {
 		unsigned int flag;
-		void *addr;
+		unsigned long addr;
 
 		/* flush the list entries. */
-		__flush_dcache_area(entry, sizeof(kimage_entry_t));
+		dcache_clean_inval_poc((unsigned long)entry,
+				    (unsigned long)entry +
+					    sizeof(kimage_entry_t));
 
 		flag = *entry & IND_FLAGS;
 		if (flag == IND_DONE)
 			break;
 
-		addr = phys_to_virt(*entry & PAGE_MASK);
+		addr = (unsigned long)phys_to_virt(*entry & PAGE_MASK);
 
 		switch (flag) {
 		case IND_INDIRECTION:
@@ -120,7 +128,7 @@ static void kexec_list_flush(struct kimage *kimage)
 			break;
 		case IND_SOURCE:
 			/* flush the source pages. */
-			__flush_dcache_area(addr, PAGE_SIZE);
+			dcache_clean_inval_poc(addr, addr + PAGE_SIZE);
 			break;
 		case IND_DESTINATION:
 			break;
@@ -147,8 +155,10 @@ static void kexec_segment_flush(const struct kimage *kimage)
 			kimage->segment[i].memsz,
 			kimage->segment[i].memsz /  PAGE_SIZE);
 
-		__flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
-			kimage->segment[i].memsz);
+		dcache_clean_inval_poc(
+			(unsigned long)phys_to_virt(kimage->segment[i].mem),
+			(unsigned long)phys_to_virt(kimage->segment[i].mem) +
+				kimage->segment[i].memsz);
 	}
 }
 
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 2c247634552b..9be668f3f034 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -21,7 +21,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 	memcpy(dst, src, len);
 
 	/* flush caches (dcache/icache) */
-	sync_icache_aliases(dst, len);
+	sync_icache_aliases((unsigned long)dst, (unsigned long)dst + len);
 
 	kunmap_atomic(xol_page_kaddr);
 }
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index c45a83512805..7e1624ecab3c 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -36,7 +36,7 @@ static void write_pen_release(u64 val)
 	unsigned long size = sizeof(secondary_holding_pen_release);
 
 	secondary_holding_pen_release = val;
-	__flush_dcache_area(start, size);
+	dcache_clean_inval_poc((unsigned long)start, (unsigned long)start + size);
 }
 
 
@@ -90,8 +90,9 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
 	 * the boot protocol.
 	 */
 	writeq_relaxed(pa_holding_pen, release_addr);
-	__flush_dcache_area((__force void *)release_addr,
-			    sizeof(*release_addr));
+	dcache_clean_inval_poc((__force unsigned long)release_addr,
+			    (__force unsigned long)release_addr +
+				    sizeof(*release_addr));
 
 	/*
 	 * Send an event to wake up the secondary CPU.
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 265fe3eb1069..db5159a3055f 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -41,7 +41,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
 			dsb(ish);
 		}
 
-		ret = __flush_cache_user_range(start, start + chunk);
+		ret = caches_clean_inval_user_pou(start, start + chunk);
 		if (ret)
 			return ret;