arm64: Add support for new control bits CTR_EL0.DIC and CTR_EL0.IDC

The DCache clean & ICache invalidation requirements for instructions
to be data coherence are discoverable through new fields in CTR_EL0.
The following two control bits DIC and IDC were defined for this
purpose. No need to perform point of unification cache maintenance
operations from software on systems where CPU caches are transparent.

This patch optimize the three functions __flush_cache_user_range(),
clean_dcache_area_pou() and invalidate_icache_range() if the hardware
reports CTR_EL0.IDC and/or CTR_EL0.IDC. Basically it skips the two
instructions 'DC CVAU' and 'IC IVAU', and the associated loop logic
in order to avoid the unnecessary overhead.

CTR_EL0.DIC: Instruction cache invalidation requirements for
 instruction to data coherence. The meaning of this bit[29].
  0: Instruction cache invalidation to the point of unification
     is required for instruction to data coherence.
  1: Instruction cache cleaning to the point of unification is
      not required for instruction to data coherence.

CTR_EL0.IDC: Data cache clean requirements for instruction to data
 coherence. The meaning of this bit[28].
  0: Data cache clean to the point of unification is required for
     instruction to data coherence, unless CLIDR_EL1.LoC == 0b000
     or (CLIDR_EL1.LoUIS == 0b000 && CLIDR_EL1.LoUU == 0b000).
  1: Data cache clean to the point of unification is not required
     for instruction to data coherence.
Co-authored-by: Philip Elcan <pelcan@codeaurora.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Shanker Donthineni <shankerd@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/cache.h

@@ -20,8 +20,12 @@
 
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
+#define CTR_DMINLINE_SHIFT	16
+#define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
+#define CTR_IDC_SHIFT		28
+#define CTR_DIC_SHIFT		29
 
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 

arch/arm64/include/asm/cacheflush.h

@@ -133,6 +133,9 @@ extern void flush_dcache_page(struct page *);
 
 static inline void __flush_icache_all(void)
 {
+	if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+		return;
+
 	asm("ic	ialluis");
 	dsb(ish);
 }

arch/arm64/include/asm/cpucaps.h

@@ -46,7 +46,9 @@
 #define ARM64_HARDEN_BP_POST_GUEST_EXIT		25
 #define ARM64_HAS_RAS_EXTN			26
 #define ARM64_WORKAROUND_843419			27
+#define ARM64_HAS_CACHE_IDC			28
+#define ARM64_HAS_CACHE_DIC			29
 
-#define ARM64_NCAPS				28
+#define ARM64_NCAPS				30
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/kernel/cpufeature.c

@@ -200,11 +200,11 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 
 static const struct arm64_ftr_bits ftr_ctr[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, 31, 1, 1), /* RES1 */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 29, 1, 1),	/* DIC */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 28, 1, 1),	/* IDC */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, 20, 4, 0),	/* ERG */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DIC_SHIFT, 1, 1),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IDC_SHIFT, 1, 1),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_CWG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, CTR_ERG_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_DMINLINE_SHIFT, 4, 1),
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
 	 * make use of *minLine.
@@ -852,6 +852,18 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus
 					ID_AA64PFR0_FP_SHIFT) < 0;
 }
 
+static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
+			  int __unused)
+{
+	return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_IDC_SHIFT);
+}
+
+static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
+			  int __unused)
+{
+	return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_DIC_SHIFT);
+}
+
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 
@@ -1088,6 +1100,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.enable = cpu_clear_disr,
 	},
 #endif /* CONFIG_ARM64_RAS_EXTN */
+	{
+		.desc = "Data cache clean to the PoU not required for I/D coherence",
+		.capability = ARM64_HAS_CACHE_IDC,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = has_cache_idc,
+	},
+	{
+		.desc = "Instruction cache invalidation not required for I/D coherence",
+		.capability = ARM64_HAS_CACHE_DIC,
+		.def_scope = SCOPE_SYSTEM,
+		.matches = has_cache_dic,
+	},
 	{},
 };
 

arch/arm64/mm/cache.S

@@ -50,6 +50,10 @@ ENTRY(flush_icache_range)
  */
 ENTRY(__flush_cache_user_range)
 	uaccess_ttbr0_enable x2, x3, x4
+alternative_if ARM64_HAS_CACHE_IDC
+	dsb	ishst
+	b	7f
+alternative_else_nop_endif
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
@@ -60,8 +64,13 @@ user_alt 9f, "dc cvau, x4",  "dc civac, x4",  ARM64_WORKAROUND_CLEAN_CACHE
 	b.lo	1b
 	dsb	ish
 
+7:
+alternative_if ARM64_HAS_CACHE_DIC
+	isb
+	b	8f
+alternative_else_nop_endif
 	invalidate_icache_by_line x0, x1, x2, x3, 9f
-	mov	x0, #0
+8:	mov	x0, #0
 1:
 	uaccess_ttbr0_disable x1, x2
 	ret
@@ -80,6 +89,12 @@ ENDPROC(__flush_cache_user_range)
  *	- end     - virtual end address of region
  */
 ENTRY(invalidate_icache_range)
+alternative_if ARM64_HAS_CACHE_DIC
+	mov	x0, xzr
+	isb
+	ret
+alternative_else_nop_endif
+
 	uaccess_ttbr0_enable x2, x3, x4
 
 	invalidate_icache_by_line x0, x1, x2, x3, 2f
@@ -116,6 +131,10 @@ ENDPIPROC(__flush_dcache_area)
  *	- size    - size in question
  */
 ENTRY(__clean_dcache_area_pou)
+alternative_if ARM64_HAS_CACHE_IDC
+	dsb	ishst
+	ret
+alternative_else_nop_endif
 	dcache_by_line_op cvau, ish, x0, x1, x2, x3
 	ret
 ENDPROC(__clean_dcache_area_pou)