Merge branch arm64/for-next/caches into kvmarm-master/next

arm64 cache management function cleanup from Fuad Tabba,
shared with the arm64 tree.

* arm64/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`

Signed-off-by: Marc Zyngier <maz@kernel.org>

Author: Marc Zyngier

arch/arm64/include/asm/alternative-macros.h

@@ -197,11 +197,6 @@ alternative_endif
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 
-.macro user_alt, label, oldinstr, newinstr, cond
-9999:	alternative_insn "\oldinstr", "\newinstr", \cond
-	_asm_extable 9999b, \label
-.endm
-
 #endif  /*  __ASSEMBLY__  */
 
 /*

arch/arm64/include/asm/arch_gicv3.h

@@ -124,7 +124,8 @@ static inline u32 gic_read_rpr(void)
 #define gic_read_lpir(c)		readq_relaxed(c)
 #define gic_write_lpir(v, c)		writeq_relaxed(v, c)
 
-#define gic_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+#define gic_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
 
 #define gits_read_baser(c)		readq_relaxed(c)
 #define gits_write_baser(v, c)		writeq_relaxed(v, c)

arch/arm64/include/asm/assembler.h

@@ -130,15 +130,27 @@ alternative_endif
 	.endm
 
 /*
- * Emit an entry into the exception table
+ * Create an exception table entry for `insn`, which will branch to `fixup`
+ * when an unhandled fault is taken.
  */
-	.macro		_asm_extable, from, to
+	.macro		_asm_extable, insn, fixup
 	.pushsection	__ex_table, "a"
 	.align		3
-	.long		(\from - .), (\to - .)
+	.long		(\insn - .), (\fixup - .)
 	.popsection
 	.endm
 
+/*
+ * Create an exception table entry for `insn` if `fixup` is provided. Otherwise
+ * do nothing.
+ */
+	.macro		_cond_extable, insn, fixup
+	.ifnc		\fixup,
+	_asm_extable	\insn, \fixup
+	.endif
+	.endm
+
+
 #define USER(l, x...)				\
 9999:	x;					\
 	_asm_extable	9999b, l
@@ -375,72 +387,76 @@ alternative_cb_end
 	bfi	\tcr, \tmp0, \pos, #3
 	.endm
 
+	.macro __dcache_op_workaround_clean_cache, op, addr
+alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
+	dc	\op, \addr
+alternative_else
+	dc	civac, \addr
+alternative_endif
+	.endm
+
 /*
  * Macro to perform a data cache maintenance for the interval
- * [kaddr, kaddr + size)
+ * [start, end)
  *
  * 	op:		operation passed to dc instruction
  * 	domain:		domain used in dsb instruciton
- * 	kaddr:		starting virtual address of the region
- * 	size:		size of the region
- * 	Corrupts:	kaddr, size, tmp1, tmp2
+ * 	start:          starting virtual address of the region
+ * 	end:            end virtual address of the region
+ * 	fixup:		optional label to branch to on user fault
+ * 	Corrupts:       start, end, tmp1, tmp2
  */
-	.macro __dcache_op_workaround_clean_cache, op, kaddr
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
-	dc	\op, \kaddr
-alternative_else
-	dc	civac, \kaddr
-alternative_endif
-	.endm
-
-	.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
+	.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
 	dcache_line_size \tmp1, \tmp2
-	add	\size, \kaddr, \size
 	sub	\tmp2, \tmp1, #1
-	bic	\kaddr, \kaddr, \tmp2
-9998:
+	bic	\start, \start, \tmp2
+.Ldcache_op\@:
 	.ifc	\op, cvau
-	__dcache_op_workaround_clean_cache \op, \kaddr
+	__dcache_op_workaround_clean_cache \op, \start
 	.else
 	.ifc	\op, cvac
-	__dcache_op_workaround_clean_cache \op, \kaddr
+	__dcache_op_workaround_clean_cache \op, \start
 	.else
 	.ifc	\op, cvap
-	sys	3, c7, c12, 1, \kaddr	// dc cvap
+	sys	3, c7, c12, 1, \start	// dc cvap
 	.else
 	.ifc	\op, cvadp
-	sys	3, c7, c13, 1, \kaddr	// dc cvadp
+	sys	3, c7, c13, 1, \start	// dc cvadp
 	.else
-	dc	\op, \kaddr
+	dc	\op, \start
 	.endif
 	.endif
 	.endif
 	.endif
-	add	\kaddr, \kaddr, \tmp1
-	cmp	\kaddr, \size
-	b.lo	9998b
+	add	\start, \start, \tmp1
+	cmp	\start, \end
+	b.lo	.Ldcache_op\@
 	dsb	\domain
+
+	_cond_extable .Ldcache_op\@, \fixup
 	.endm
 
 /*
  * Macro to perform an instruction cache maintenance for the interval
  * [start, end)
  *
  * 	start, end:	virtual addresses describing the region
- *	label:		A label to branch to on user fault.
+ *	fixup:		optional label to branch to on user fault
  * 	Corrupts:	tmp1, tmp2
  */
-	.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
+	.macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup
 	icache_line_size \tmp1, \tmp2
 	sub	\tmp2, \tmp1, #1
 	bic	\tmp2, \start, \tmp2
-9997:
-USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
+.Licache_op\@:
+	ic	ivau, \tmp2			// invalidate I line PoU
 	add	\tmp2, \tmp2, \tmp1
 	cmp	\tmp2, \end
-	b.lo	9997b
+	b.lo	.Licache_op\@
 	dsb	ish
 	isb
+
+	_cond_extable .Licache_op\@, \fixup
 	.endm
 
 /*

arch/arm64/include/asm/cacheflush.h

@@ -30,45 +30,58 @@
  *	the implementation assumes non-aliasing VIPT D-cache and (aliasing)
  *	VIPT I-cache.
  *
- *	flush_icache_range(start, end)
+ *	All functions below apply to the interval [start, end)
+ *		- start  - virtual start address (inclusive)
+ *		- end    - virtual end address (exclusive)
  *
- *		Ensure coherency between the I-cache and the D-cache in the
- *		region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	caches_clean_inval_pou(start, end)
  *
- *	invalidate_icache_range(start, end)
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
  *
- *		Invalidate the I-cache in the region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	caches_clean_inval_user_pou(start, end)
  *
- *	__flush_cache_user_range(start, end)
+ *		Ensure coherency between the I-cache and the D-cache region to
+ *		the Point of Unification.
+ *		Use only if the region might access user memory.
  *
- *		Ensure coherency between the I-cache and the D-cache in the
- *		region described by start, end.
- *		- start  - virtual start address
- *		- end    - virtual end address
+ *	icache_inval_pou(start, end)
  *
- *	__flush_dcache_area(kaddr, size)
+ *		Invalidate I-cache region to the Point of Unification.
  *
- *		Ensure that the data held in page is written back.
- *		- kaddr  - page address
- *		- size   - region size
+ *	dcache_clean_inval_poc(start, end)
+ *
+ *		Clean and invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_inval_poc(start, end)
+ *
+ *		Invalidate D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_poc(start, end)
+ *
+ *		Clean D-cache region to the Point of Coherency.
+ *
+ *	dcache_clean_pop(start, end)
+ *
+ *		Clean D-cache region to the Point of Persistence.
+ *
+ *	dcache_clean_pou(start, end)
+ *
+ *		Clean D-cache region to the Point of Unification.
  */
-extern void __flush_icache_range(unsigned long start, unsigned long end);
-extern int  invalidate_icache_range(unsigned long start, unsigned long end);
-extern void __flush_dcache_area(void *addr, size_t len);
-extern void __inval_dcache_area(void *addr, size_t len);
-extern void __clean_dcache_area_poc(void *addr, size_t len);
-extern void __clean_dcache_area_pop(void *addr, size_t len);
-extern void __clean_dcache_area_pou(void *addr, size_t len);
-extern long __flush_cache_user_range(unsigned long start, unsigned long end);
-extern void sync_icache_aliases(void *kaddr, unsigned long len);
+extern void caches_clean_inval_pou(unsigned long start, unsigned long end);
+extern void icache_inval_pou(unsigned long start, unsigned long end);
+extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_inval_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_poc(unsigned long start, unsigned long end);
+extern void dcache_clean_pop(unsigned long start, unsigned long end);
+extern void dcache_clean_pou(unsigned long start, unsigned long end);
+extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end);
+extern void sync_icache_aliases(unsigned long start, unsigned long end);
 
 static inline void flush_icache_range(unsigned long start, unsigned long end)
 {
-	__flush_icache_range(start, end);
+	caches_clean_inval_pou(start, end);
 
 	/*
 	 * IPI all online CPUs so that they undergo a context synchronization
@@ -122,7 +135,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-static __always_inline void __flush_icache_all(void)
+static __always_inline void icache_inval_all_pou(void)
 {
 	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
 		return;

arch/arm64/include/asm/efi.h

@@ -137,7 +137,7 @@ void efi_virtmap_unload(void);
 
 static inline void efi_capsule_flush_cache_range(void *addr, int size)
 {
-	__flush_dcache_area(addr, size);
+	dcache_clean_inval_poc((unsigned long)addr, (unsigned long)addr + size);
 }
 
 #endif /* _ASM_EFI_H */

arch/arm64/include/asm/kvm_mmu.h

@@ -180,7 +180,8 @@ static inline void *__kvm_vector_slot2addr(void *base,
 
 struct kvm;
 
-#define kvm_flush_dcache_to_poc(a,l)	__flush_dcache_area((a), (l))
+#define kvm_flush_dcache_to_poc(a,l)	\
+	dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
 
 static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 {
@@ -205,11 +206,10 @@ static inline void __invalidate_icache_guest_page(void *va, size_t size)
 {
 	if (icache_is_aliasing()) {
 		/* any kind of VIPT cache */
-		__flush_icache_all();
+		icache_inval_all_pou();
 	} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
 		/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
-		invalidate_icache_range((unsigned long)va,
-					(unsigned long)va + size);
+		icache_inval_pou((unsigned long)va, (unsigned long)va + size);
 	}
 }
 

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 */

arch/arm64/kernel/efi-entry.S

@@ -28,16 +28,17 @@ 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
 
 	/*
 	 * Clean the remainder of this routine to the PoC
 	 * 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

arch/arm64/kernel/head.S

@@ -117,8 +117,8 @@ 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)
 
 /*
@@ -268,8 +268,7 @@ 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.
@@ -382,13 +381,11 @@ 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)

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