diff mbox series

[4/7] RISC-V: Update page tables to cover the whole linear mapping

Message ID 20190327213643.23789-5-logang@deltatee.com (mailing list archive)
State New, archived
Headers show
Series RISC-V: Sparsmem, Memory Hotplug and pte_devmap for P2P | expand

Commit Message

Logan Gunthorpe March 27, 2019, 9:36 p.m. UTC
With the new virtual address changes in an earlier patch, we want the
page tables to cover more of the linear mapping region. Instead of
only mapping from PAGE_OFFSET and up, we instead map starting
from an aligned version of va_pa_offset such that all of the physical
address space will be mapped.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Anup Patel <anup.patel@wdc.com>
Cc: Atish Patra <atish.patra@wdc.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Zong Li <zongbox@gmail.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
---
 arch/riscv/kernel/setup.c |  1 -
 arch/riscv/mm/init.c      | 27 +++++++++++++++------------
 2 files changed, 15 insertions(+), 13 deletions(-)

Comments

Anup Patel March 28, 2019, 10:03 a.m. UTC | #1
On Thu, Mar 28, 2019 at 3:06 AM Logan Gunthorpe <logang@deltatee.com> wrote:
>
> With the new virtual address changes in an earlier patch, we want the
> page tables to cover more of the linear mapping region. Instead of
> only mapping from PAGE_OFFSET and up, we instead map starting
> from an aligned version of va_pa_offset such that all of the physical
> address space will be mapped.
>
> Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
> Cc: Palmer Dabbelt <palmer@sifive.com>
> Cc: Albert Ou <aou@eecs.berkeley.edu>
> Cc: Anup Patel <anup.patel@wdc.com>
> Cc: Atish Patra <atish.patra@wdc.com>
> Cc: Paul Walmsley <paul.walmsley@sifive.com>
> Cc: Zong Li <zongbox@gmail.com>
> Cc: Mike Rapoport <rppt@linux.ibm.com>
> ---
>  arch/riscv/kernel/setup.c |  1 -
>  arch/riscv/mm/init.c      | 27 +++++++++++++++------------
>  2 files changed, 15 insertions(+), 13 deletions(-)
>
> diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
> index ecb654f6a79e..8286df8be31a 100644
> --- a/arch/riscv/kernel/setup.c
> +++ b/arch/riscv/kernel/setup.c
> @@ -59,7 +59,6 @@ EXPORT_SYMBOL(empty_zero_page);
>  /* The lucky hart to first increment this variable will boot the other cores */
>  atomic_t hart_lottery;
>  unsigned long boot_cpu_hartid;
> -
>  void __init parse_dtb(unsigned int hartid, void *dtb)
>  {
>         if (early_init_dt_scan(__va(dtb)))
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index b9d50031e78f..315194557c3d 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -150,8 +150,8 @@ pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
>  pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
>
>  #ifndef __PAGETABLE_PMD_FOLDED
> -#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
> -pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
> +#define NUM_SWAPPER_PMDS ((uintptr_t)-VMALLOC_END >> PGDIR_SHIFT)
> +pmd_t swapper_pmd[PTRS_PER_PMD*((-VMALLOC_END)/PGDIR_SIZE)] __page_aligned_bss;
>  pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
>  pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
>  #endif
> @@ -180,13 +180,18 @@ asmlinkage void __init setup_vm(void)
>         extern char _start;
>         uintptr_t i;
>         uintptr_t pa = (uintptr_t) &_start;
> +       uintptr_t linear_start;
> +       uintptr_t off;
>         pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
>
>         va_pa_offset = PAGE_OFFSET - pa;
>         pfn_base = PFN_DOWN(pa);
>
> +       linear_start = ALIGN_DOWN(va_pa_offset, PGDIR_SIZE);
> +       off = linear_start - va_pa_offset;
> +
>         /* Sanity check alignment and size */
> -       BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
> +       BUG_ON(linear_start <= VMALLOC_END);
>         BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
>
>  #ifndef __PAGETABLE_PMD_FOLDED
> @@ -195,15 +200,14 @@ asmlinkage void __init setup_vm(void)
>                         __pgprot(_PAGE_TABLE));
>         trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
>
> -       for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
> -               size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
> -
> +       for (i = 0; i < (-linear_start)/PGDIR_SIZE; ++i) {
> +               size_t o = (linear_start >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
>                 swapper_pg_dir[o] =
>                         pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
>                                 __pgprot(_PAGE_TABLE));
>         }
>         for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
> -               swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
> +               swapper_pmd[i] = pfn_pmd(PFN_DOWN(off + i * PMD_SIZE), prot);
>
>         swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
>                 pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pmd),
> @@ -215,11 +219,10 @@ asmlinkage void __init setup_vm(void)
>         trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
>                 pfn_pgd(PFN_DOWN(pa), prot);
>
> -       for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
> -               size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
> -
> -               swapper_pg_dir[o] =
> -                       pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
> +       for (i = 0; i < (-linear_start)/PGDIR_SIZE; ++i) {
> +               size_t o = (linear_start >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
> +               swapper_pg_dir[o] = pfn_pgd(PFN_DOWN(off + i * PGDIR_SIZE),
> +                                           prot);
>         }
>
>         swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
> --
> 2.20.1
>

I understand that this patch is inline with your virtual memory layout cleanup
but the way we map virtual memory in swapper_pg_dir is bound to change.

We should not be mapping complete virtual memory in swapper_pd_dir()
rather we should only map based on amount of RAM available.

Refer, https://www.lkml.org/lkml/2019/3/24/3

The setup_vm() should only map vmlinux_start to vmlinux_end plus the
FDT. Complete virtual memory mapping should be done after we have
done early parsing of FDT when we know available memory banks in
setup_vm_final() (called from paging_init())

Regards,
Anup
Logan Gunthorpe March 28, 2019, 6:24 p.m. UTC | #2
On 2019-03-28 4:03 a.m., Anup Patel wrote:
> I understand that this patch is inline with your virtual memory layout cleanup
> but the way we map virtual memory in swapper_pg_dir is bound to change.
> 
> We should not be mapping complete virtual memory in swapper_pd_dir()
> rather we should only map based on amount of RAM available.
> 
> Refer, https://www.lkml.org/lkml/2019/3/24/3
> 
> The setup_vm() should only map vmlinux_start to vmlinux_end plus the
> FDT. Complete virtual memory mapping should be done after we have
> done early parsing of FDT when we know available memory banks in
> setup_vm_final() (called from paging_init())

That makes sense, but I think a lot of it sounds a out of the scope of
what I'm doing in this patch set.

I could attempt to update my patchset so instead of expanding the linear
region on boot, we add the page tables in arch_add_memory. That would
make more sense when considering the direction you want to head with
setup_vm.

Logan
diff mbox series

Patch

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index ecb654f6a79e..8286df8be31a 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -59,7 +59,6 @@  EXPORT_SYMBOL(empty_zero_page);
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
 unsigned long boot_cpu_hartid;
-
 void __init parse_dtb(unsigned int hartid, void *dtb)
 {
 	if (early_init_dt_scan(__va(dtb)))
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b9d50031e78f..315194557c3d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -150,8 +150,8 @@  pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 
 #ifndef __PAGETABLE_PMD_FOLDED
-#define NUM_SWAPPER_PMDS ((uintptr_t)-PAGE_OFFSET >> PGDIR_SHIFT)
-pmd_t swapper_pmd[PTRS_PER_PMD*((-PAGE_OFFSET)/PGDIR_SIZE)] __page_aligned_bss;
+#define NUM_SWAPPER_PMDS ((uintptr_t)-VMALLOC_END >> PGDIR_SHIFT)
+pmd_t swapper_pmd[PTRS_PER_PMD*((-VMALLOC_END)/PGDIR_SIZE)] __page_aligned_bss;
 pmd_t trampoline_pmd[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
 #endif
@@ -180,13 +180,18 @@  asmlinkage void __init setup_vm(void)
 	extern char _start;
 	uintptr_t i;
 	uintptr_t pa = (uintptr_t) &_start;
+	uintptr_t linear_start;
+	uintptr_t off;
 	pgprot_t prot = __pgprot(pgprot_val(PAGE_KERNEL) | _PAGE_EXEC);
 
 	va_pa_offset = PAGE_OFFSET - pa;
 	pfn_base = PFN_DOWN(pa);
 
+	linear_start = ALIGN_DOWN(va_pa_offset, PGDIR_SIZE);
+	off = linear_start - va_pa_offset;
+
 	/* Sanity check alignment and size */
-	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
+	BUG_ON(linear_start <= VMALLOC_END);
 	BUG_ON((pa % (PAGE_SIZE * PTRS_PER_PTE)) != 0);
 
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -195,15 +200,14 @@  asmlinkage void __init setup_vm(void)
 			__pgprot(_PAGE_TABLE));
 	trampoline_pmd[0] = pfn_pmd(PFN_DOWN(pa), prot);
 
-	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
-		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
-
+	for (i = 0; i < (-linear_start)/PGDIR_SIZE; ++i) {
+		size_t o = (linear_start >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
 		swapper_pg_dir[o] =
 			pfn_pgd(PFN_DOWN((uintptr_t)swapper_pmd) + i,
 				__pgprot(_PAGE_TABLE));
 	}
 	for (i = 0; i < ARRAY_SIZE(swapper_pmd); i++)
-		swapper_pmd[i] = pfn_pmd(PFN_DOWN(pa + i * PMD_SIZE), prot);
+		swapper_pmd[i] = pfn_pmd(PFN_DOWN(off + i * PMD_SIZE), prot);
 
 	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =
 		pfn_pgd(PFN_DOWN((uintptr_t)fixmap_pmd),
@@ -215,11 +219,10 @@  asmlinkage void __init setup_vm(void)
 	trampoline_pg_dir[(PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD] =
 		pfn_pgd(PFN_DOWN(pa), prot);
 
-	for (i = 0; i < (-PAGE_OFFSET)/PGDIR_SIZE; ++i) {
-		size_t o = (PAGE_OFFSET >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
-
-		swapper_pg_dir[o] =
-			pfn_pgd(PFN_DOWN(pa + i * PGDIR_SIZE), prot);
+	for (i = 0; i < (-linear_start)/PGDIR_SIZE; ++i) {
+		size_t o = (linear_start >> PGDIR_SHIFT) % PTRS_PER_PGD + i;
+		swapper_pg_dir[o] = pfn_pgd(PFN_DOWN(off + i * PGDIR_SIZE),
+					    prot);
 	}
 
 	swapper_pg_dir[(FIXADDR_START >> PGDIR_SHIFT) % PTRS_PER_PGD] =