[RFC PATCH] arch: arm64: introduce RODATA_FULL_USE_PTE_CONT

[Huangzhaoyang]

From: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>

Kernel linear mapping will be split to the smallest granularity when
RODATA_FULL applied, which could lead to TLB pressure. Introduce a method
to apply PTE_CONT on pte.

Signed-off-by: Zhaoyang Huang <zhaoyang.huang@xxxxxxxxxx>
---
 arch/arm64/Kconfig       |  9 +++++++++
 arch/arm64/mm/mmu.c      | 10 ++++++++--
 arch/arm64/mm/pageattr.c |  9 +++++++++
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fee914c..3f8fbf0 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1198,6 +1198,15 @@ config RODATA_FULL_DEFAULT_ENABLED
 	  This requires the linear region to be mapped down to pages,
 	  which may adversely affect performance in some cases.
 
+config RODATA_FULL_USE_PTE_CONT
+       bool "Apply PTE_CONT when RODATA_FULL_DEFAULT_ENABLED enabled"
+       depends on RODATA_FULL_DEFAULT_ENABLED
+       default y
+       help
+         Apply PTE_CONT on linear mapping as much as we can when
+         RODATA_FULL_DEFAULT_ENABLED enabled which could decrease the
+         impaction on performance by small pte granularity.
+
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	help
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index cfd9deb..8017b17 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -124,15 +124,21 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
 	 * The following mapping attributes may be updated in live
 	 * kernel mappings without the need for break-before-make.
 	 */
+#ifndef CONFIG_RODATA_FULL_USE_PTE_CONT
 	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG;
+#else
+	pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG | PTE_CONT;
+#endif
 
 	/* creating or taking down mappings is always safe */
 	if (old == 0 || new == 0)
 		return true;
 
 	/* live contiguous mappings may not be manipulated at all */
-	if ((old | new) & PTE_CONT)
+#ifndef CONFIG_RODATA_FULL_USE_PTE_CONT
+	if (old | new) & PTE_CONT)
 		return false;
+#endif
 
 	/* Transitioning from Non-Global to Global is unsafe */
 	if (old & ~new & PTE_NG)
@@ -206,7 +212,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 		/* use a contiguous mapping if the range is suitably aligned */
 		if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
-		    (flags & NO_CONT_MAPPINGS) == 0)
+		    (IS_ENABLED(CONFIG_RODATA_FULL_USE_PTE_CONT) || (flags & NO_CONT_MAPPINGS) == 0))
 			__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
 
 		init_pte(pmdp, addr, next, phys, __prot);
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index a3bacd7..88a87eb 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -99,6 +99,15 @@ static int change_memory_common(unsigned long addr, int numpages,
 	if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY ||
 			    pgprot_val(clear_mask) == PTE_RDONLY)) {
 		for (i = 0; i < area->nr_pages; i++) {
+#ifdef CONFIG_RODATA_FULL_USE_PTE_CONT
+			unsigned long cont_pte_low_bound;
+			unsigned long addr;
+
+			addr = (u64)page_address(area->pages[i]);
+			cont_pte_low_bound = addr & CONT_PTE_MASK;
+			__change_memory_common(cont_pte_low_bound,
+					       (~CONT_PTE_MASK + 1), __pgprot(0) , __pgprot(PTE_CONT));
+#endif
 			__change_memory_common((u64)page_address(area->pages[i]),
 					       PAGE_SIZE, set_mask, clear_mask);
 		}
-- 
1.9.1