Merge branch 'for-next/stage1-lpa2' into for-next/core

* for-next/stage1-lpa2: (48 commits)
  : Add support for LPA2 and WXN and stage 1
  arm64/mm: Avoid ID mapping of kpti flag if it is no longer needed
  arm64/mm: Use generic __pud_free() helper in pud_free() implementation
  arm64: gitignore: ignore relacheck
  arm64: Use Signed/Unsigned enums for TGRAN{4,16,64} and VARange
  arm64: mm: Make PUD folding check in set_pud() a runtime check
  arm64: mm: add support for WXN memory translation attribute
  mm: add arch hook to validate mmap() prot flags
  arm64: defconfig: Enable LPA2 support
  arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs
  arm64: kvm: avoid CONFIG_PGTABLE_LEVELS for runtime levels
  arm64: ptdump: Deal with translation levels folded at runtime
  arm64: ptdump: Disregard unaddressable VA space
  arm64: mm: Add support for folding PUDs at runtime
  arm64: kasan: Reduce minimum shadow alignment and enable 5 level paging
  arm64: mm: Add 5 level paging support to fixmap and swapper handling
  arm64: Enable LPA2 at boot if supported by the system
  arm64: mm: add LPA2 and 5 level paging support to G-to-nG conversion
  arm64: mm: Add definitions to support 5 levels of paging
  arm64: mm: Add LPA2 support to phys<->pte conversion routines
  arm64: mm: Wire up TCR.DS bit to PTE shareability fields
  ...

1 files changed, 19 insertions, 36 deletions

diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 96b18a707507..ab8b396428da 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -342,20 +342,6 @@ alternative_cb_end
 	.endm
 
 /*
- * idmap_get_t0sz - get the T0SZ value needed to cover the ID map
- *
- * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the
- * entire ID map region can be mapped. As T0SZ == (64 - #bits used),
- * this number conveniently equals the number of leading zeroes in
- * the physical address of _end.
- */
-	.macro	idmap_get_t0sz, reg
-	adrp	\reg, _end
-	orr	\reg, \reg, #(1 << VA_BITS_MIN) - 1
-	clz	\reg, \reg
-	.endm
-
-/*
  * tcr_compute_pa_size - set TCR.(I)PS to the highest supported
  * ID_AA64MMFR0_EL1.PARange value
  *
@@ -586,18 +572,27 @@ alternative_endif
 	.endm
 
 /*
- * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD.
+ * If the kernel is built for 52-bit virtual addressing but the hardware only
+ * supports 48 bits, we cannot program the pgdir address into TTBR1 directly,
+ * but we have to add an offset so that the TTBR1 address corresponds with the
+ * pgdir entry that covers the lowest 48-bit addressable VA.
+ *
+ * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an
+ * additional paging level, and on LPA2/16k pages, we would end up with a root
+ * level table with only 2 entries, which is suboptimal in terms of TLB
+ * utilization, so there we fall back to 47 bits of translation if LPA2 is not
+ * supported.
+ *
  * orr is used as it can cover the immediate value (and is idempotent).
- * In future this may be nop'ed out when dealing with 52-bit kernel VAs.
  * 	ttbr: Value of ttbr to set, modified.
  */
 	.macro	offset_ttbr1, ttbr, tmp
-#ifdef CONFIG_ARM64_VA_BITS_52
-	mrs_s	\tmp, SYS_ID_AA64MMFR2_EL1
-	and	\tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT)
-	cbnz	\tmp, .Lskipoffs_\@
-	orr	\ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET
-.Lskipoffs_\@ :
+#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2)
+	mrs	\tmp, tcr_el1
+	and	\tmp, \tmp, #TCR_T1SZ_MASK
+	cmp	\tmp, #TCR_T1SZ(VA_BITS_MIN)
+	orr	\tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET
+	csel	\ttbr, \tmp, \ttbr, eq
 #endif
 	.endm
 
@@ -619,25 +614,13 @@ alternative_endif
 
 	.macro	phys_to_pte, pte, phys
 #ifdef CONFIG_ARM64_PA_BITS_52
-	/*
-	 * We assume \phys is 64K aligned and this is guaranteed by only
-	 * supporting this configuration with 64K pages.
-	 */
-	orr	\pte, \phys, \phys, lsr #36
-	and	\pte, \pte, #PTE_ADDR_MASK
+	orr	\pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT
+	and	\pte, \pte, #PHYS_TO_PTE_ADDR_MASK
 #else
 	mov	\pte, \phys
 #endif
 	.endm
 
-	.macro	pte_to_phys, phys, pte
-	and	\phys, \pte, #PTE_ADDR_MASK
-#ifdef CONFIG_ARM64_PA_BITS_52
-	orr	\phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT
-	and	\phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT)
-#endif
-	.endm
-
 /*
  * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU.
  */