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

* for-next/tlbi:
  : Support for TTL (translation table level) hint in the TLB operations
  arm64: tlb: Use the TLBI RANGE feature in arm64
  arm64: enable tlbi range instructions
  arm64: tlb: Detect the ARMv8.4 TLBI RANGE feature
  arm64: tlb: don't set the ttl value in flush_tlb_page_nosync
  arm64: Shift the __tlbi_level() indentation left
  arm64: tlb: Set the TTL field in flush_*_tlb_range
  arm64: tlb: Set the TTL field in flush_tlb_range
  tlb: mmu_gather: add tlb_flush_*_range APIs
  arm64: Add tlbi_user_level TLB invalidation helper
  arm64: Add level-hinted TLB invalidation helper
  arm64: Document SW reserved PTE/PMD bits in Stage-2 descriptors
  arm64: Detect the ARMv8.4 TTL feature

arch/arm64/Kconfig

@@ -1601,6 +1601,20 @@ config ARM64_AMU_EXTN
 	  correctly reflect reality. Most commonly, the value read will be 0,
 	  indicating that the counter is not enabled.
 
+config AS_HAS_ARMV8_4
+	def_bool $(cc-option,-Wa$(comma)-march=armv8.4-a)
+
+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.
+
 endmenu
 
 menu "ARMv8.5 architectural features"

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

arch/arm64/include/asm/cpucaps.h

@@ -62,7 +62,9 @@
 #define ARM64_HAS_GENERIC_AUTH			52
 #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				55
+#define ARM64_NCAPS				57
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -692,6 +692,12 @@ static inline bool system_supports_bti(void)
 	return IS_ENABLED(CONFIG_ARM64_BTI) && cpus_have_const_cap(ARM64_BTI);
 }
 
+static inline bool system_supports_tlb_range(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_TLB_RANGE) &&
+		cpus_have_const_cap(ARM64_HAS_TLB_RANGE);
+}
+
 #define ARM64_BP_HARDEN_UNKNOWN		-1
 #define ARM64_BP_HARDEN_WA_NEEDED	0
 #define ARM64_BP_HARDEN_NOT_REQUIRED	1

arch/arm64/include/asm/pgtable-hwdef.h

@@ -178,10 +178,12 @@
 #define PTE_S2_RDONLY		(_AT(pteval_t, 1) << 6)   /* HAP[2:1] */
 #define PTE_S2_RDWR		(_AT(pteval_t, 3) << 6)   /* HAP[2:1] */
 #define PTE_S2_XN		(_AT(pteval_t, 2) << 53)  /* XN[1:0] */
+#define PTE_S2_SW_RESVD		(_AT(pteval_t, 15) << 55) /* Reserved for SW */
 
 #define PMD_S2_RDONLY		(_AT(pmdval_t, 1) << 6)   /* HAP[2:1] */
 #define PMD_S2_RDWR		(_AT(pmdval_t, 3) << 6)   /* HAP[2:1] */
 #define PMD_S2_XN		(_AT(pmdval_t, 2) << 53)  /* XN[1:0] */
+#define PMD_S2_SW_RESVD		(_AT(pmdval_t, 15) << 55) /* Reserved for SW */
 
 #define PUD_S2_RDONLY		(_AT(pudval_t, 1) << 6)   /* HAP[2:1] */
 #define PUD_S2_RDWR		(_AT(pudval_t, 3) << 6)   /* HAP[2:1] */

arch/arm64/include/asm/pgtable.h

@@ -40,6 +40,16 @@ extern void __pmd_error(const char *file, int line, unsigned long val);
 extern void __pud_error(const char *file, int line, unsigned long val);
 extern void __pgd_error(const char *file, int line, unsigned long val);
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+
+/* Set stride and tlb_level in flush_*_tlb_range */
+#define flush_pmd_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2)
+#define flush_pud_tlb_range(vma, addr, end)	\
+	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..

arch/arm64/include/asm/stage2_pgtable.h

@@ -256,4 +256,13 @@ stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
+/*
+ * Level values for the ARMv8.4-TTL extension, mapping PUD/PMD/PTE and
+ * the architectural page-table level.
+ */
+#define S2_NO_LEVEL_HINT	0
+#define S2_PUD_LEVEL		1
+#define S2_PMD_LEVEL		2
+#define S2_PTE_LEVEL		3
+
 #endif	/* __ARM64_S2_PGTABLE_H_ */

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

arch/arm64/include/asm/tlb.h

@@ -21,11 +21,37 @@ static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
 
+/*
+ * get the tlbi levels in arm64.  Default value is 0 if more than one
+ * of cleared_* is set or neither is set.
+ * Arm64 doesn't support p4ds now.
+ */
+static inline int tlb_get_level(struct mmu_gather *tlb)
+{
+	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 3;
+
+	if (tlb->cleared_pmds && !(tlb->cleared_ptes ||
+				   tlb->cleared_puds ||
+				   tlb->cleared_p4ds))
+		return 2;
+
+	if (tlb->cleared_puds && !(tlb->cleared_ptes ||
+				   tlb->cleared_pmds ||
+				   tlb->cleared_p4ds))
+		return 1;
+
+	return 0;
+}
+
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
 	struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
 	bool last_level = !tlb->freed_tables;
 	unsigned long stride = tlb_get_unmap_size(tlb);
+	int tlb_level = tlb_get_level(tlb);
 
 	/*
 	 * If we're tearing down the address space then we only care about
@@ -38,7 +64,8 @@ static inline void tlb_flush(struct mmu_gather *tlb)
 		return;
 	}
 
-	__flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level);
+	__flush_tlb_range(&vma, tlb->start, tlb->end, stride,
+			  last_level, tlb_level);
 }
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,

arch/arm64/include/asm/tlbflush.h

@@ -10,6 +10,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bitfield.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
 #include <asm/cputype.h>
@@ -59,6 +60,102 @@
 		__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.
+ *
+ * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
+ * the level at which the invalidation must take place. If the level is
+ * wrong, no invalidation may take place. In the case where the level
+ * cannot be easily determined, a 0 value for the level parameter will
+ * perform a non-hinted invalidation.
+ *
+ * For Stage-2 invalidation, use the level values provided to that effect
+ * in asm/stage2_pgtable.h.
+ */
+#define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
+
+#define __tlbi_level(op, addr, level) do {				\
+	u64 arg = addr;							\
+									\
+	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
+	    level) {							\
+		u64 ttl = level & 3;					\
+		ttl |= get_trans_granule() << 2;			\
+		arg &= ~TLBI_TTL_MASK;					\
+		arg |= FIELD_PREP(TLBI_TTL_MASK, ttl);			\
+	}								\
+									\
+	__tlbi(op, arg);						\
+} while(0)
+
+#define __tlbi_user_level(op, arg, level) do {				\
+	if (arm64_kernel_unmapped_at_el0())				\
+		__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
  *	================
@@ -179,34 +276,83 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 
 static inline void __flush_tlb_range(struct vm_area_struct *vma,
 				     unsigned long start, unsigned long end,
-				     unsigned long stride, bool last_level)
+				     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 ((!system_supports_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 (!system_supports_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) {
+		num = __TLBI_RANGE_NUM(pages, scale);
+		if (num >= 0) {
+			addr = __TLBI_VADDR_RANGE(start, asid, scale,
+						  num, tlb_level);
 			if (last_level) {
-			__tlbi(vale1is, addr);
-			__tlbi_user(vale1is, addr);
+				__tlbi(rvale1is, addr);
+				__tlbi_user(rvale1is, addr);
 			} else {
-			__tlbi(vae1is, addr);
-			__tlbi_user(vae1is, addr);
+				__tlbi(rvae1is, addr);
+				__tlbi_user(rvae1is, addr);
+			}
+			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT;
+			pages -= __TLBI_RANGE_PAGES(num, scale);
 		}
+		scale++;
 	}
 	dsb(ish);
 }
@@ -217,8 +363,9 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 	/*
 	 * We cannot use leaf-only invalidation here, since we may be invalidating
 	 * table entries as part of collapsing hugepages or moving page tables.
+	 * Set the tlb_level to 0 because we can not get enough information here.
 	 */
-	__flush_tlb_range(vma, start, end, PAGE_SIZE, false);
+	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
 }
 
 static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)

arch/arm64/kernel/cpufeature.c

@@ -1925,6 +1925,26 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = cpu_has_fwb,
 	},
+	{
+		.desc = "ARMv8.4 Translation Table Level",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_HAS_ARMv8_4_TTL,
+		.sys_reg = SYS_ID_AA64MMFR2_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64MMFR2_TTL_SHIFT,
+		.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
 	{
 		/*

include/asm-generic/tlb.h

@@ -512,6 +512,38 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 }
 #endif
 
+/*
+ * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
+ * and set corresponding cleared_*.
+ */
+static inline void tlb_flush_pte_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_ptes = 1;
+}
+
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_pmds = 1;
+}
+
+static inline void tlb_flush_pud_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_puds = 1;
+}
+
+static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_p4ds = 1;
+}
+
 #ifndef __tlb_remove_tlb_entry
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #endif
@@ -525,19 +557,17 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->cleared_ptes = 1;				\
+		tlb_flush_pte_range(tlb, address, PAGE_SIZE);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		__tlb_adjust_range(tlb, address, _sz);		\
 		if (_sz == PMD_SIZE)				\
-			tlb->cleared_pmds = 1;			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
 		else if (_sz == PUD_SIZE)			\
-			tlb->cleared_puds = 1;			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -551,8 +581,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
-		tlb->cleared_pmds = 1;					\
+		tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE);	\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -566,8 +595,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
-		tlb->cleared_puds = 1;					\
+		tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE);	\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -592,9 +620,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pmd_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -602,9 +629,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pud_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -612,9 +638,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_p4d_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif