From 6aae3425aa9ca776e8201a93494a4a482353d2c3 Mon Sep 17 00:00:00 2001
From: Vineet Gupta <Vineet.Gupta1@synopsys.com>
Date: Sat, 30 Nov 2019 17:51:06 -0800
Subject: ARC: mm: remove __ARCH_USE_5LEVEL_HACK

Patch series "elide extraneous generated code for folded p4d/pud/pmd", v3.

This series came out of seemingly benign excursion into
understanding/removing __ARCH_USE_5LEVEL_HACK from ARC port showing some
extraneous code being generated despite folded p4d/pud/pmd

| bloat-o-meter2 vmlinux-[AB]*
| add/remove: 0/0 grow/shrink: 3/0 up/down: 130/0 (130)
| function                                     old     new   delta
| free_pgd_range                               548     660    +112
| p4d_clear_bad                                  2      20     +18

The patches here address that

| bloat-o-meter2 vmlinux-[BF]*
| add/remove: 0/2 grow/shrink: 0/1 up/down: 0/-386 (-386)
| function                                     old     new   delta
| pud_clear_bad                                 20       -     -20
| p4d_clear_bad                                 20       -     -20
| free_pgd_range                               660     314    -346

The code savings are not a whole lot, but still worthwhile IMHO.

This patch (of 5):

With paging code made 5-level compliant, this is no longer needed.  ARC
has software page walker with 2 lookup levels (pgd -> pte)

This was expected to be non functional change but ended with slight
code bloat due to needless inclusions of p*d_free_tlb() macros which
will be addressed in further patches.

| bloat-o-meter2 vmlinux-[AB]*
| add/remove: 0/0 grow/shrink: 2/0 up/down: 128/0 (128)
| function                                     old     new   delta
| free_pgd_range                               546     656    +110
| p4d_clear_bad                                  2      20     +18
| Total: Before=4137148, After=4137276, chg 0.000000%

Link: http://lkml.kernel.org/r/20191016162400.14796-2-vgupta@synopsys.com
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Nick Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/arc/include/asm/pgtable.h |  1 -
 arch/arc/mm/fault.c            | 10 ++++++++--
 arch/arc/mm/highmem.c          |  4 +++-
 3 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'arch/arc')

diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 7addd0301c51..b917b596f7fb 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -33,7 +33,6 @@
 #define _ASM_ARC_PGTABLE_H
 
 #include <linux/bits.h>
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopmd.h>
 #include <asm/page.h>
 #include <asm/mmu.h>	/* to propagate CONFIG_ARC_MMU_VER <n> */
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index 3861543b66a0..fb86bc3e9b35 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -30,6 +30,7 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	 * with the 'reference' page table.
 	 */
 	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -39,8 +40,13 @@ noinline static int handle_kernel_vaddr_fault(unsigned long address)
 	if (!pgd_present(*pgd_k))
 		goto bad_area;
 
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
+	p4d = p4d_offset(pgd, address);
+	p4d_k = p4d_offset(pgd_k, address);
+	if (!p4d_present(*p4d_k))
+		goto bad_area;
+
+	pud = pud_offset(p4d, address);
+	pud_k = pud_offset(p4d_k, address);
 	if (!pud_present(*pud_k))
 		goto bad_area;
 
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index a4856bfaedf3..fc8849e4f72e 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -111,12 +111,14 @@ EXPORT_SYMBOL(__kunmap_atomic);
 static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
 	pgd_t *pgd_k;
+	p4d_t *p4d_k;
 	pud_t *pud_k;
 	pmd_t *pmd_k;
 	pte_t *pte_k;
 
 	pgd_k = pgd_offset_k(kvaddr);
-	pud_k = pud_offset(pgd_k, kvaddr);
+	p4d_k = p4d_offset(pgd_k, kvaddr);
+	pud_k = pud_offset(p4d_k, kvaddr);
 	pmd_k = pmd_offset(pud_k, kvaddr);
 
 	pte_k = (pte_t *)memblock_alloc_low(PAGE_SIZE, PAGE_SIZE);
-- 
cgit v1.2.3