diff mbox series

[v4,2/4] mm: support Svnapot in physical page linear-mapping

Message ID 20220822153413.4038052-3-panqinglin2020@iscas.ac.cn (mailing list archive)
State Superseded
Headers show
Series riscv, mm: detect svnapot cpu support at runtime | expand

Commit Message

Qinglin Pan Aug. 22, 2022, 3:34 p.m. UTC
From: Qinglin Pan <panqinglin2020@iscas.ac.cn>

Svnapot is powerful when a physical region is going to mapped to a
virtual region. Kernel will do like this when mapping all allocable
physical pages to kernel vm space. This commit modifies the
create_pte_mapping function used in linear-mapping procedure, so the
kernel can be able to use Svnapot when both address and length of
physical region are 64KB align. Code here will be executed only when
other size huge page is not suitable, so it can be an addition of
PMD_SIZE and PUD_SIZE mapping.

This commit also modifies the best_map_size function to give map_size
many times instead of only once, so a memory region can be mapped by
both PMD_SIZE and 64KB napot size.

It is tested by setting qemu's memory to a 262272k region, and the
kernel can boot successfully.

Signed-off-by: Qinglin Pan <panqinglin2020@iscas.ac.cn>

Comments

Conor Dooley Aug. 22, 2022, 9:03 p.m. UTC | #1
Hey, 
Couple questions about some things that caught my eye.
Mostly beyond my pay grade here though...

On 22/08/2022 16:34, panqinglin2020@iscas.ac.cn wrote:
> EXTERNAL EMAIL: Do not click links or open attachments unless you know the content is safe
> 
> From: Qinglin Pan <panqinglin2020@iscas.ac.cn>
> 
> Svnapot is powerful when a physical region is going to mapped to a
> virtual region. Kernel will do like this when mapping all allocable
> physical pages to kernel vm space. This commit modifies the
> create_pte_mapping function used in linear-mapping procedure, so the
> kernel can be able to use Svnapot when both address and length of
> physical region are 64KB align. Code here will be executed only when
> other size huge page is not suitable, so it can be an addition of
> PMD_SIZE and PUD_SIZE mapping.
> 
> This commit also modifies the best_map_size function to give map_size
> many times instead of only once, so a memory region can be mapped by
> both PMD_SIZE and 64KB napot size.
> 
> It is tested by setting qemu's memory to a 262272k region, and the
> kernel can boot successfully.
> 
> Signed-off-by: Qinglin Pan <panqinglin2020@iscas.ac.cn>
> 
> diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
> index cedcf8ea3c76..395fdc922e9e 100644
> --- a/arch/riscv/include/asm/mmu.h
> +++ b/arch/riscv/include/asm/mmu.h
> @@ -25,6 +25,7 @@ typedef struct {
> 
>  void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,
>                                phys_addr_t sz, pgprot_t prot);
> +void __init create_linear_mapping(void);
>  #endif /* __ASSEMBLY__ */
> 
>  #endif /* _ASM_RISCV_MMU_H */
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index 95ef6e2bf45c..37e6f7044ef1 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -292,13 +292,16 @@ void __init setup_arch(char **cmdline_p)
>         kasan_init();
>  #endif
> 
> -#ifdef CONFIG_SMP
> -       setup_smp();
> -#endif
> -
>         riscv_fill_hwcap();
>         riscv_init_cbom_blocksize();
>         apply_boot_alternatives();
> +
> +       if (has_svnapot())
> +               create_linear_mapping();

Does this now get called twice if has_svnapot()?
Once here and once in paging_init().

> +
> +#ifdef CONFIG_SMP
> +       setup_smp();
> +#endif

Are there any side effects to moving this down?

>  }
> 
>  static int __init topology_init(void)
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index b56a0a75533f..f54c3991f9ab 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -373,9 +373,21 @@ static void __init create_pte_mapping(pte_t *ptep,
>                                       phys_addr_t sz, pgprot_t prot)
>  {
>         uintptr_t pte_idx = pte_index(va);
> +#ifdef CONFIG_SVNAPOT
> +       pte_t pte;
> +
> +       if (has_svnapot() && sz == NAPOT_CONT64KB_SIZE) {
> +               do {
> +                       pte = pfn_pte(PFN_DOWN(pa), prot);
> +                       ptep[pte_idx] = pte_mknapot(pte, NAPOT_CONT64KB_ORDER);
> +                       pte_idx++;
> +                       sz -= PAGE_SIZE;
> +               } while (sz > 0);
> +               return;
> +       }
> +#endif
> 
>         BUG_ON(sz != PAGE_SIZE);
> -
>         if (pte_none(ptep[pte_idx]))
>                 ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
>  }
> @@ -673,10 +685,18 @@ void __init create_pgd_mapping(pgd_t *pgdp,
>  static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
>  {
>         /* Upgrade to PMD_SIZE mappings whenever possible */
> -       if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
> +       base &= PMD_SIZE - 1;
> +       if (!base && size >= PMD_SIZE)
> +               return PMD_SIZE;
> +
> +       if (!has_svnapot())
>                 return PAGE_SIZE;
> 
> -       return PMD_SIZE;
> +       base &= NAPOT_CONT64KB_SIZE - 1;
> +       if (!base && size >= NAPOT_CONT64KB_SIZE)
> +               return NAPOT_CONT64KB_SIZE;
> +
> +       return PAGE_SIZE;
>  }
> 
>  #ifdef CONFIG_XIP_KERNEL
> @@ -1090,18 +1110,12 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
>         pt_ops_set_fixmap();
>  }
> 
> -static void __init setup_vm_final(void)
> +void __init create_linear_mapping(void)
>  {
>         uintptr_t va, map_size;
>         phys_addr_t pa, start, end;
>         u64 i;
> 
> -       /* Setup swapper PGD for fixmap */
> -       create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
> -                          __pa_symbol(fixmap_pgd_next),
> -                          PGDIR_SIZE, PAGE_TABLE);
> -
> -       /* Map all memory banks in the linear mapping */
>         for_each_mem_range(i, &start, &end) {
>                 if (start >= end)
>                         break;
> @@ -1111,14 +1125,25 @@ static void __init setup_vm_final(void)
>                 if (end >= __pa(PAGE_OFFSET) + memory_limit)
>                         end = __pa(PAGE_OFFSET) + memory_limit;
> 
> -               map_size = best_map_size(start, end - start);
>                 for (pa = start; pa < end; pa += map_size) {
>                         va = (uintptr_t)__va(pa);
> +                       map_size = best_map_size(pa, end - pa);
> 
>                         create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
>                                            pgprot_from_va(va));
>                 }
>         }
> +}
> +
> +static void __init setup_vm_final(void)
> +{
> +       /* Setup swapper PGD for fixmap */
> +       create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
> +                          __pa_symbol(fixmap_pgd_next),
> +                          PGDIR_SIZE, PAGE_TABLE);
> +
> +       /* Map all memory banks in the linear mapping */
> +       create_linear_mapping();
> 
>         /* Map the kernel */
>         if (IS_ENABLED(CONFIG_64BIT))
> --
> 2.35.1
> 
> 
> _______________________________________________
> linux-riscv mailing list
> linux-riscv@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/linux-riscv
diff mbox series

Patch

diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h
index cedcf8ea3c76..395fdc922e9e 100644
--- a/arch/riscv/include/asm/mmu.h
+++ b/arch/riscv/include/asm/mmu.h
@@ -25,6 +25,7 @@  typedef struct {
 
 void __init create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa,
 			       phys_addr_t sz, pgprot_t prot);
+void __init create_linear_mapping(void);
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_RISCV_MMU_H */
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 95ef6e2bf45c..37e6f7044ef1 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -292,13 +292,16 @@  void __init setup_arch(char **cmdline_p)
 	kasan_init();
 #endif
 
-#ifdef CONFIG_SMP
-	setup_smp();
-#endif
-
 	riscv_fill_hwcap();
 	riscv_init_cbom_blocksize();
 	apply_boot_alternatives();
+
+	if (has_svnapot())
+		create_linear_mapping();
+
+#ifdef CONFIG_SMP
+	setup_smp();
+#endif
 }
 
 static int __init topology_init(void)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b56a0a75533f..f54c3991f9ab 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -373,9 +373,21 @@  static void __init create_pte_mapping(pte_t *ptep,
 				      phys_addr_t sz, pgprot_t prot)
 {
 	uintptr_t pte_idx = pte_index(va);
+#ifdef CONFIG_SVNAPOT
+	pte_t pte;
+
+	if (has_svnapot() && sz == NAPOT_CONT64KB_SIZE) {
+		do {
+			pte = pfn_pte(PFN_DOWN(pa), prot);
+			ptep[pte_idx] = pte_mknapot(pte, NAPOT_CONT64KB_ORDER);
+			pte_idx++;
+			sz -= PAGE_SIZE;
+		} while (sz > 0);
+		return;
+	}
+#endif
 
 	BUG_ON(sz != PAGE_SIZE);
-
 	if (pte_none(ptep[pte_idx]))
 		ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
 }
@@ -673,10 +685,18 @@  void __init create_pgd_mapping(pgd_t *pgdp,
 static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
 {
 	/* Upgrade to PMD_SIZE mappings whenever possible */
-	if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
+	base &= PMD_SIZE - 1;
+	if (!base && size >= PMD_SIZE)
+		return PMD_SIZE;
+
+	if (!has_svnapot())
 		return PAGE_SIZE;
 
-	return PMD_SIZE;
+	base &= NAPOT_CONT64KB_SIZE - 1;
+	if (!base && size >= NAPOT_CONT64KB_SIZE)
+		return NAPOT_CONT64KB_SIZE;
+
+	return PAGE_SIZE;
 }
 
 #ifdef CONFIG_XIP_KERNEL
@@ -1090,18 +1110,12 @@  asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 	pt_ops_set_fixmap();
 }
 
-static void __init setup_vm_final(void)
+void __init create_linear_mapping(void)
 {
 	uintptr_t va, map_size;
 	phys_addr_t pa, start, end;
 	u64 i;
 
-	/* Setup swapper PGD for fixmap */
-	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
-			   __pa_symbol(fixmap_pgd_next),
-			   PGDIR_SIZE, PAGE_TABLE);
-
-	/* Map all memory banks in the linear mapping */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
 			break;
@@ -1111,14 +1125,25 @@  static void __init setup_vm_final(void)
 		if (end >= __pa(PAGE_OFFSET) + memory_limit)
 			end = __pa(PAGE_OFFSET) + memory_limit;
 
-		map_size = best_map_size(start, end - start);
 		for (pa = start; pa < end; pa += map_size) {
 			va = (uintptr_t)__va(pa);
+			map_size = best_map_size(pa, end - pa);
 
 			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
 					   pgprot_from_va(va));
 		}
 	}
+}
+
+static void __init setup_vm_final(void)
+{
+	/* Setup swapper PGD for fixmap */
+	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
+			   __pa_symbol(fixmap_pgd_next),
+			   PGDIR_SIZE, PAGE_TABLE);
+
+	/* Map all memory banks in the linear mapping */
+	create_linear_mapping();
 
 	/* Map the kernel */
 	if (IS_ENABLED(CONFIG_64BIT))