riscv: Only flush the mm icache when setting an exec pte

We used to emit a flush_icache_all() whenever a dirty executable
mapping is set in the page table but we can instead call
flush_icache_mm() which will only send IPIs to cores that currently run
this mm and add a deferred icache flush to the others.

The number of calls to sbi_remote_fence_i() (tested without IPI
support):

With a simple buildroot rootfs:
* Before: ~5k
* After :  4 (!)

Tested on HW, the boot to login is ~4.5% faster.

With an ubuntu rootfs:
* Before: ~24k
* After : ~13k

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Link: https://lore.kernel.org/r/20240202124711.256146-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
index 55a34f2020a85..bc61ee5975e41 100644
--- a/arch/riscv/mm/cacheflush.c
+++ b/arch/riscv/mm/cacheflush.c
@@ -82,12 +82,12 @@ void flush_icache_mm(struct mm_struct *mm, bool local)
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_MMU
-void flush_icache_pte(pte_t pte)
+void flush_icache_pte(struct mm_struct *mm, pte_t pte)
 {
 	struct folio *folio = page_folio(pte_page(pte));
 
 	if (!test_bit(PG_dcache_clean, &folio->flags)) {
-		flush_icache_all();
+		flush_icache_mm(mm, false);
 		set_bit(PG_dcache_clean, &folio->flags);
 	}
 }