[PATCH v3 0/3] arm64: tlb: add support for TLBI RANGE instructions

[PATCH v3 0/3] arm64: tlb: add support for TLBI RANGE instructions

[Zhenyu Ye]

NOTICE: this series are based on the arm64 for-next/tlbi branch:
git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/tlbi

ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
range of input addresses. This series add support for this feature.

--
ChangeList:
v3:
- add check on whether binutils supports ARMv8.4-a instructions.
- pass -march=armv8.4-a to KBUILD_CFLAGS.
- make __TLBI_RANGE_PAGES to be 'unsigned long' explicitly.

v2:
- remove the __tlbi_last_level() macro.
- add check for parameters in __TLBI_VADDR_RANGE macro.

RFC patches:
- Link: https://lore.kernel.org/linux-arm-kernel/20200708124031.1414-1-yezhenyu2@huawei.com/


Zhenyu Ye (3):
  arm64: tlb: Detect the ARMv8.4 TLBI RANGE feature
  arm64: enable tlbi range instructions
  arm64: tlb: Use the TLBI RANGE feature in arm64

 arch/arm64/Kconfig                |  14 +++
 arch/arm64/Makefile               |   7 ++
 arch/arm64/include/asm/cpucaps.h  |   3 +-
 arch/arm64/include/asm/sysreg.h   |   3 +
 arch/arm64/include/asm/tlbflush.h | 156 ++++++++++++++++++++++++------
 arch/arm64/kernel/cpufeature.c    |  10 ++
 6 files changed, 163 insertions(+), 30 deletions(-)

-- 
2.19.1

[PATCH v3 1/3] arm64: tlb: Detect the ARMv8.4 TLBI RANGE feature

[Zhenyu Ye]

ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
range of input addresses. This patch detect this feature.

Signed-off-by: Zhenyu Ye <yezhenyu2@huawei.com>
Link: https://lore.kernel.org/r/20200710094420.517-2-yezhenyu2@huawei.com
[catalin.marinas@arm.com: some renaming for consistency]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/cpucaps.h |  3 ++-
 arch/arm64/include/asm/sysreg.h  |  3 +++
 arch/arm64/kernel/cpufeature.c   | 10 ++++++++++
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index d44ba903d11d..07b643a70710 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -63,7 +63,8 @@
 #define ARM64_HAS_32BIT_EL1			53
 #define ARM64_BTI				54
 #define ARM64_HAS_ARMv8_4_TTL			55
+#define ARM64_HAS_TLB_RANGE			56
 
-#define ARM64_NCAPS				56
+#define ARM64_NCAPS				57
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 8c209aa17273..551f30ace4db 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -617,6 +617,9 @@
 #define ID_AA64ISAR0_SHA1_SHIFT		8
 #define ID_AA64ISAR0_AES_SHIFT		4
 
+#define ID_AA64ISAR0_TLB_RANGE_NI	0x0
+#define ID_AA64ISAR0_TLB_RANGE		0x2
+
 /* id_aa64isar1 */
 #define ID_AA64ISAR1_I8MM_SHIFT		52
 #define ID_AA64ISAR1_DGH_SHIFT		48
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index e877f56ff1ab..2f5adefef34d 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1893,6 +1893,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.min_field_value = 1,
 		.matches = has_cpuid_feature,
 	},
+	{
+		.desc = "TLB range maintenance instructions",
+		.capability = ARM64_HAS_TLB_RANGE,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR0_EL1,
+		.field_pos = ID_AA64ISAR0_TLB_SHIFT,
+		.sign = FTR_UNSIGNED,
+		.min_field_value = ID_AA64ISAR0_TLB_RANGE,
+	},
 #ifdef CONFIG_ARM64_HW_AFDBM
 	{
 		/*
-- 
2.19.1

[PATCH v3 2/3] arm64: enable tlbi range instructions

[Zhenyu Ye]

TLBI RANGE feature instoduces new assembly instructions and only
support by binutils >= 2.30.  Add necessary Kconfig logic to allow
this to be enabled and pass '-march=armv8.4-a' to KBUILD_CFLAGS.

Signed-off-by: Zhenyu Ye <yezhenyu2@huawei.com>
---
 arch/arm64/Kconfig  | 14 ++++++++++++++
 arch/arm64/Makefile |  7 +++++++
 2 files changed, 21 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 66dc41fd49f2..e385361f8137 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1596,6 +1596,20 @@ config ARM64_AMU_EXTN
 	  correctly reflect reality. Most commonly, the value read will be 0,
 	  indicating that the counter is not enabled.
 
+config ARM64_TLB_RANGE
+	bool "Enable support for tlbi range feature"
+	default y
+	depends on AS_HAS_ARMV8_4
+	help
+	  ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
+	  range of input addresses.
+
+	  The feature introduces new assembly instructions, and they were
+	  support when binutils >= 2.30.
+
+config AS_HAS_ARMV8_4
+	def_bool $(cc-option, -Wa$(comma)-march=armv8.4-a)
+
 endmenu
 
 menu "ARMv8.5 architectural features"
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index a0d94d063fa8..4e823b97c92e 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -82,11 +82,18 @@ endif
 # compiler to generate them and consequently to break the single image contract
 # we pass it only to the assembler. This option is utilized only in case of non
 # integrated assemblers.
+ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
 branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
 endif
+endif
 
 KBUILD_CFLAGS += $(branch-prot-flags-y)
 
+ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
+# make sure to pass the newest target architecture to -march.
+KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
+endif
+
 ifeq ($(CONFIG_SHADOW_CALL_STACK), y)
 KBUILD_CFLAGS	+= -ffixed-x18
 endif
-- 
2.19.1

[PATCH v3 3/3] arm64: tlb: Use the TLBI RANGE feature in arm64

[Zhenyu Ye]

Add __TLBI_VADDR_RANGE macro and rewrite __flush_tlb_range().

When cpu supports TLBI feature, the minimum range granularity is
decided by 'scale', so we can not flush all pages by one instruction
in some cases.

For example, when the pages = 0xe81a, let's start 'scale' from
maximum, and find right 'num' for each 'scale':

1. scale = 3, we can flush no pages because the minimum range is
   2^(5*3 + 1) = 0x10000.
2. scale = 2, the minimum range is 2^(5*2 + 1) = 0x800, we can
   flush 0xe800 pages this time, the num = 0xe800/0x800 - 1 = 0x1c.
   Remaining pages is 0x1a;
3. scale = 1, the minimum range is 2^(5*1 + 1) = 0x40, no page
   can be flushed.
4. scale = 0, we flush the remaining 0x1a pages, the num =
   0x1a/0x2 - 1 = 0xd.

However, in most scenarios, the pages = 1 when flush_tlb_range() is
called. Start from scale = 3 or other proper value (such as scale =
ilog2(pages)), will incur extra overhead.
So increase 'scale' from 0 to maximum, the flush order is exactly
opposite to the example.

Signed-off-by: Zhenyu Ye <yezhenyu2@huawei.com>
Link: https://lore.kernel.org/r/20200710094420.517-3-yezhenyu2@huawei.com
[catalin.marinas@arm.com: removed unnecessary masks in __TLBI_VADDR_RANGE]
[catalin.marinas@arm.com: __TLB_RANGE_NUM subtracts 1]
[catalin.marinas@arm.com: minor adjustments to the comments]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/tlbflush.h | 156 ++++++++++++++++++++++++------
 1 file changed, 127 insertions(+), 29 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 2cb275efcea3..4a21d8dc0312 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -60,6 +60,31 @@
 		__ta;						\
 	})
 
+/*
+ * Get translation granule of the system, which is decided by
+ * PAGE_SIZE.  Used by TTL.
+ *  - 4KB	: 1
+ *  - 16KB	: 2
+ *  - 64KB	: 3
+ */
+#define TLBI_TTL_TG_4K		1
+#define TLBI_TTL_TG_16K		2
+#define TLBI_TTL_TG_64K		3
+
+static inline unsigned long get_trans_granule(void)
+{
+	switch (PAGE_SIZE) {
+	case SZ_4K:
+		return TLBI_TTL_TG_4K;
+	case SZ_16K:
+		return TLBI_TTL_TG_16K;
+	case SZ_64K:
+		return TLBI_TTL_TG_64K;
+	default:
+		return 0;
+	}
+}
+
 /*
  * Level-based TLBI operations.
  *
@@ -73,9 +98,6 @@
  * in asm/stage2_pgtable.h.
  */
 #define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
-#define TLBI_TTL_TG_4K		1
-#define TLBI_TTL_TG_16K		2
-#define TLBI_TTL_TG_64K		3
 
 #define __tlbi_level(op, addr, level) do {				\
 	u64 arg = addr;							\
@@ -83,19 +105,7 @@
 	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
 	    level) {							\
 		u64 ttl = level & 3;					\
-									\
-		switch (PAGE_SIZE) {					\
-		case SZ_4K:						\
-			ttl |= TLBI_TTL_TG_4K << 2;			\
-			break;						\
-		case SZ_16K:						\
-			ttl |= TLBI_TTL_TG_16K << 2;			\
-			break;						\
-		case SZ_64K:						\
-			ttl |= TLBI_TTL_TG_64K << 2;			\
-			break;						\
-		}							\
-									\
+		ttl |= get_trans_granule() << 2;			\
 		arg &= ~TLBI_TTL_MASK;					\
 		arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);			\
 	}								\
@@ -108,6 +118,44 @@
 		__tlbi_level(op, (arg | USER_ASID_FLAG), level);	\
 } while (0)
 
+/*
+ * This macro creates a properly formatted VA operand for the TLB RANGE.
+ * The value bit assignments are:
+ *
+ * +----------+------+-------+-------+-------+----------------------+
+ * |   ASID   |  TG  | SCALE |  NUM  |  TTL  |        BADDR         |
+ * +-----------------+-------+-------+-------+----------------------+
+ * |63      48|47  46|45   44|43   39|38   37|36                   0|
+ *
+ * The address range is determined by below formula:
+ * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
+ *
+ */
+#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
+	({							\
+		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
+		__ta &= GENMASK_ULL(36, 0);			\
+		__ta |= (unsigned long)(ttl) << 37;		\
+		__ta |= (unsigned long)(num) << 39;		\
+		__ta |= (unsigned long)(scale) << 44;		\
+		__ta |= get_trans_granule() << 46;		\
+		__ta |= (unsigned long)(asid) << 48;		\
+		__ta;						\
+	})
+
+/* These macros are used by the TLBI RANGE feature. */
+#define __TLBI_RANGE_PAGES(num, scale)	\
+	((unsigned long)((num) + 1) << (5 * (scale) + 1))
+#define MAX_TLBI_RANGE_PAGES		__TLBI_RANGE_PAGES(31, 3)
+
+/*
+ * Generate 'num' values from -1 to 30 with -1 rejected by the
+ * __flush_tlb_range() loop below.
+ */
+#define TLBI_RANGE_MASK			GENMASK_ULL(4, 0)
+#define __TLBI_RANGE_NUM(pages, scale)	\
+	((((pages) >> (5 * (scale) + 1)) & TLBI_RANGE_MASK) - 1)
+
 /*
  *	TLB Invalidation
  *	================
@@ -231,32 +279,82 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long stride, bool last_level,
 				     int tlb_level)
 {
+	int num = 0;
+	int scale = 0;
 	unsigned long asid = ASID(vma->vm_mm);
 	unsigned long addr;
+	unsigned long pages;
 
 	start = round_down(start, stride);
 	end = round_up(end, stride);
+	pages = (end - start) >> PAGE_SHIFT;
 
-	if ((end - start) >= (MAX_TLBI_OPS * stride)) {
+	/*
+	 * When not uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_OPS - 1) pages;
+	 * When uses TLB range ops, we can handle up to
+	 * (MAX_TLBI_RANGE_PAGES - 1) pages.
+	 */
+	if ((!(cpus_have_const_cap(ARM64_HAS_TLB_RANGE) &&
+	       IS_ENABLED(CONFIG_ARM64_TLB_RANGE)) &&
+	     (end - start) >= (MAX_TLBI_OPS * stride)) ||
+	    pages >= MAX_TLBI_RANGE_PAGES) {
 		flush_tlb_mm(vma->vm_mm);
 		return;
 	}
 
-	/* Convert the stride into units of 4k */
-	stride >>= 12;
+	dsb(ishst);
 
-	start = __TLBI_VADDR(start, asid);
-	end = __TLBI_VADDR(end, asid);
+	/*
+	 * When the CPU does not support TLB range operations, flush the TLB
+	 * entries one by one at the granularity of 'stride'. If the the TLB
+	 * range ops are supported, then:
+	 *
+	 * 1. If 'pages' is odd, flush the first page through non-range
+	 *    operations;
+	 *
+	 * 2. For remaining pages: the minimum range granularity is decided
+	 *    by 'scale', so multiple range TLBI operations may be required.
+	 *    Start from scale = 0, flush the corresponding number of pages
+	 *    ((num+1)*2^(5*scale+1) starting from 'addr'), then increase it
+	 *    until no pages left.
+	 *
+	 * Note that certain ranges can be represented by either num = 31 and
+	 * scale or num = 0 and scale + 1. The loop below favours the latter
+	 * since num is limited to 30 by the __TLBI_RANGE_NUM() macro.
+	 */
+	while (pages > 0) {
+		if (!IS_ENABLED(CONFIG_ARM64_TLB_RANGE) ||
+		    !cpus_have_const_cap(ARM64_HAS_TLB_RANGE) ||
+		    pages % 2 == 1) {
+			addr = __TLBI_VADDR(start, asid);
+			if (last_level) {
+				__tlbi_level(vale1is, addr, tlb_level);
+				__tlbi_user_level(vale1is, addr, tlb_level);
+			} else {
+				__tlbi_level(vae1is, addr, tlb_level);
+				__tlbi_user_level(vae1is, addr, tlb_level);
+			}
+			start += stride;
+			pages -= stride >> PAGE_SHIFT;
+			continue;
+		}
 
-	dsb(ishst);
-	for (addr = start; addr < end; addr += stride) {
-		if (last_level) {
-			__tlbi_level(vale1is, addr, tlb_level);
-			__tlbi_user_level(vale1is, addr, tlb_level);
-		} else {
-			__tlbi_level(vae1is, addr, tlb_level);
-			__tlbi_user_level(vae1is, addr, tlb_level);
+		num = __TLBI_RANGE_NUM(pages, scale);
+		if (num >= 0) {
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,
+						  num, tlb_level);
+			if (last_level) {
+				__tlbi(rvale1is, addr);
+				__tlbi_user(rvale1is, addr);
+			} else {
+				__tlbi(rvae1is, addr);
+				__tlbi_user(rvae1is, addr);
+			}
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
+			pages -= __TLBI_RANGE_PAGES(num, scale);
 		}
+		scale++;
 	}
 	dsb(ish);
 }
-- 
2.19.1

Re: [PATCH v3 2/3] arm64: enable tlbi range instructions

[Catalin Marinas]

On Wed, Jul 15, 2020 at 03:19:44PM +0800, Zhenyu Ye wrote:
> diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
> index a0d94d063fa8..4e823b97c92e 100644
> --- a/arch/arm64/Makefile
> +++ b/arch/arm64/Makefile
> @@ -82,11 +82,18 @@ endif
>  # compiler to generate them and consequently to break the single image contract
>  # we pass it only to the assembler. This option is utilized only in case of non
>  # integrated assemblers.
> +ifneq ($(CONFIG_AS_HAS_ARMV8_4), y)
>  branch-prot-flags-$(CONFIG_AS_HAS_PAC) += -Wa,-march=armv8.3-a
>  endif
> +endif

I couldn't find a clear statement in the gas documentation on what
happens if multiple -march options are passed. I think it's safer to
avoid this here.

>  KBUILD_CFLAGS += $(branch-prot-flags-y)
>  
> +ifeq ($(CONFIG_AS_HAS_ARMV8_4), y)
> +# make sure to pass the newest target architecture to -march.
> +KBUILD_CFLAGS	+= -Wa,-march=armv8.4-a
> +endif

I have a suspicion both of these options will break the LLVM integrated
assembler but we don't officially support it on arm64 yet (-Wa, doesn't
seem to get passed to the integrated asm).

Thanks for the re-spin.

-- 
Catalin

Re: [PATCH v3 0/3] arm64: tlb: add support for TLBI RANGE instructions

[Catalin Marinas]

On Wed, 15 Jul 2020 15:19:42 +0800, Zhenyu Ye wrote:
> NOTICE: this series are based on the arm64 for-next/tlbi branch:
> git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/tlbi
> 
> ARMv8.4-TLBI provides TLBI invalidation instruction that apply to a
> range of input addresses. This series add support for this feature.
> 
> --
> ChangeList:
> v3:
> - add check on whether binutils supports ARMv8.4-a instructions.
> - pass -march=armv8.4-a to KBUILD_CFLAGS.
> - make __TLBI_RANGE_PAGES to be 'unsigned long' explicitly.
> 
> [...]

Applied to arm64 (for-next/tlbi), thanks!

[1/3] arm64: tlb: Detect the ARMv8.4 TLBI RANGE feature
      https://git.kernel.org/arm64/c/b620ba54547c
[2/3] arm64: enable tlbi range instructions
      https://git.kernel.org/arm64/c/7c78f67e9bd9
[3/3] arm64: tlb: Use the TLBI RANGE feature in arm64
      https://git.kernel.org/arm64/c/d1d3aa98b1d4

(I introduced a system_supports_tlb_range() to avoid the IS_ENABLED
twice)

-- 
Catalin