arm64: mm: Batch dsb and isb when populating pgtables

After removing uneccessary TLBIs, the next bottleneck when creating the
page tables for the linear map is DSB and ISB, which were previously
issued per-pte in __set_pte(). Since we are writing multiple ptes in a
given pte table, we can elide these barriers and insert them once we
have finished writing to the table.

Execution time of map_mem(), which creates the kernel linear map page
tables, was measured on different machines with different RAM configs:

               | Apple M2 VM | Ampere Altra| Ampere Altra| Ampere Altra
               | VM, 16G     | VM, 64G     | VM, 256G    | Metal, 512G
---------------|-------------|-------------|-------------|-------------
               |   ms    (%) |   ms    (%) |   ms    (%) |    ms    (%)
---------------|-------------|-------------|-------------|-------------
before         |   78   (0%) |  435   (0%) | 1723   (0%) |  3779   (0%)
after          |   11 (-86%) |  161 (-63%) |  656 (-62%) |  1654 (-56%)
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Itaru Kitayama <itaru.kitayama@fujitsu.com>
Tested-by: Eric Chanudet <echanude@redhat.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20240412131908.433043-3-ryan.roberts@arm.comSigned-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/pgtable.h

@@ -271,9 +271,14 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
 }
 
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 {
 	WRITE_ONCE(*ptep, pte);
+}
+
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+	__set_pte_nosync(ptep, pte);
 
 	/*
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance

arch/arm64/mm/mmu.c

@@ -178,7 +178,11 @@ static void init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
 	do {
 		pte_t old_pte = __ptep_get(ptep);
 
-		__set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		/*
+		 * Required barriers to make this visible to the table walker
+		 * are deferred to the end of alloc_init_cont_pte().
+		 */
+		__set_pte_nosync(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
@@ -232,6 +236,11 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		phys += next - addr;
 	} while (addr = next, addr != end);
 
+	/*
+	 * Note: barriers and maintenance necessary to clear the fixmap slot
+	 * ensure that all previous pgtable writes are visible to the table
+	 * walker.
+	 */
 	pte_clear_fixmap();
 }