Received-SPF: pass (google.com: domain of linux-kernel+bounces-131622-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Ryan Roberts <ryan.roberts@arm.com>
To: Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Ard Biesheuvel <ardb@kernel.org>,
	David Hildenbrand <david@redhat.com>,
	Donald Dutile <ddutile@redhat.com>,
	Eric Chanudet <echanude@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org,
	Itaru Kitayama <itaru.kitayama@fujitsu.com>
Subject: [PATCH v2 1/4] arm64: mm: Don't remap pgtables per-cont(pte|pmd) block
Date: Thu,  4 Apr 2024 15:33:05 +0100
Message-Id: <20240404143308.2224141-2-ryan.roberts@arm.com>
In-Reply-To: <20240404143308.2224141-1-ryan.roberts@arm.com>
References: <20240404143308.2224141-1-ryan.roberts@arm.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

A large part of the kernel boot time is creating the kernel linear map
page tables. When rodata=full, all memory is mapped by pte. And when
there is lots of physical ram, there are lots of pte tables to populate.
The primary cost associated with this is mapping and unmapping the pte
table memory in the fixmap; at unmap time, the TLB entry must be
invalidated and this is expensive.

Previously, each pmd and pte table was fixmapped/fixunmapped for each
cont(pte|pmd) block of mappings (16 entries with 4K granule). This means
we ended up issuing 32 TLBIs per (pmd|pte) table during the population
phase.

Let's fix that, and fixmap/fixunmap each page once per population, for a
saving of 31 TLBIs per (pmd|pte) table. This gives a significant boot
speedup.

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         |  153   (0%) | 2227   (0%) | 8798   (0%) | 17442   (0%)
after          |   77 (-49%) |  431 (-81%) | 1727 (-80%) |  3796 (-78%)

Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Itaru Kitayama <itaru.kitayama@fujitsu.com>
Tested-by: Eric Chanudet <echanude@redhat.com>
---
 arch/arm64/mm/mmu.c | 32 ++++++++++++++++++--------------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 495b732d5af3..fd91b5bdb514 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -172,12 +172,9 @@ bool pgattr_change_is_safe(u64 old, u64 new)
 	return ((old ^ new) & ~mask) == 0;
 }
 
-static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
-		     phys_addr_t phys, pgprot_t prot)
+static pte_t *init_pte(pte_t *ptep, unsigned long addr, unsigned long end,
+		       phys_addr_t phys, pgprot_t prot)
 {
-	pte_t *ptep;
-
-	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
 		pte_t old_pte = __ptep_get(ptep);
 
@@ -193,7 +190,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
 
-	pte_clear_fixmap();
+	return ptep;
 }
 
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
@@ -204,6 +201,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 {
 	unsigned long next;
 	pmd_t pmd = READ_ONCE(*pmdp);
+	pte_t *ptep;
 
 	BUG_ON(pmd_sect(pmd));
 	if (pmd_none(pmd)) {
@@ -219,6 +217,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 	}
 	BUG_ON(pmd_bad(pmd));
 
+	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
 		pgprot_t __prot = prot;
 
@@ -229,20 +228,20 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pte(pmdp, addr, next, phys, __prot);
+		ptep = init_pte(ptep, addr, next, phys, __prot);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	pte_clear_fixmap();
 }
 
-static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
-		     phys_addr_t phys, pgprot_t prot,
-		     phys_addr_t (*pgtable_alloc)(int), int flags)
+static pmd_t *init_pmd(pmd_t *pmdp, unsigned long addr, unsigned long end,
+		       phys_addr_t phys, pgprot_t prot,
+		       phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
-	pmd_t *pmdp;
 
-	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pmd_t old_pmd = READ_ONCE(*pmdp);
 
@@ -269,7 +268,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		phys += next - addr;
 	} while (pmdp++, addr = next, addr != end);
 
-	pmd_clear_fixmap();
+	return pmdp;
 }
 
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
@@ -279,6 +278,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
+	pmd_t *pmdp;
 
 	/*
 	 * Check for initial section mappings in the pgd/pud.
@@ -297,6 +297,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	}
 	BUG_ON(pud_bad(pud));
 
+	pmdp = pmd_set_fixmap_offset(pudp, addr);
 	do {
 		pgprot_t __prot = prot;
 
@@ -307,10 +308,13 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 		    (flags & NO_CONT_MAPPINGS) == 0)
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
-		init_pmd(pudp, addr, next, phys, __prot, pgtable_alloc, flags);
+		pmdp = init_pmd(pmdp, addr, next, phys, __prot, pgtable_alloc,
+				flags);
 
 		phys += next - addr;
 	} while (addr = next, addr != end);
+
+	pmd_clear_fixmap();
 }
 
 static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
-- 
2.25.1