From: Björn Töpel <[email protected]>
The RISC-V port requires that kernel PGD entries are to be
synchronized between MMs. This is done via the vmalloc_fault()
function, that simply copies the PGD entries from init_mm to the
faulting one.
Historically, faulting in PGD entries have been a source for both bugs
[1], and poor performance.
One way to get rid of vmalloc faults is by pre-allocating the PGD
entries. Pre-allocating the entries potientially wastes 64 * 4K (65 on
SV39). The pre-allocation function is pulled from Jörg Rödel's x86
work, with the addition of 3-level page tables (PMD allocations).
The pmd_alloc() function needs the ptlock cache to be initialized
(when split page locks is enabled), so the pre-allocation is done in a
RISC-V specific pgtable_cache_init() implementation.
Pre-allocate the kernel PGD entries for the vmalloc/modules area, but
only for 64b platforms.
Link: https://lore.kernel.org/lkml/[email protected]/ # [1]
Signed-off-by: Björn Töpel <[email protected]>
---
v1->v2: Fixed broken !MMU build.
---
arch/riscv/mm/fault.c | 16 ++----------
arch/riscv/mm/init.c | 58 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 60 insertions(+), 14 deletions(-)
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 8685f85a7474..b023fb311e28 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -238,24 +238,12 @@ void handle_page_fault(struct pt_regs *regs)
* only copy the information from the master page table,
* nothing more.
*/
- if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
+ if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
+ unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
vmalloc_fault(regs, code, addr);
return;
}
-#ifdef CONFIG_64BIT
- /*
- * Modules in 64bit kernels lie in their own virtual region which is not
- * in the vmalloc region, but dealing with page faults in this region
- * or the vmalloc region amounts to doing the same thing: checking that
- * the mapping exists in init_mm.pgd and updating user page table, so
- * just use vmalloc_fault.
- */
- if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) {
- vmalloc_fault(regs, code, addr);
- return;
- }
-#endif
/* Enable interrupts if they were enabled in the parent context. */
if (!regs_irqs_disabled(regs))
local_irq_enable();
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 747e5b1ef02d..45ceaff5679e 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1363,3 +1363,61 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
return vmemmap_populate_basepages(start, end, node, NULL);
}
#endif
+
+#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
+/*
+ * Pre-allocates page-table pages for a specific area in the kernel
+ * page-table. Only the level which needs to be synchronized between
+ * all page-tables is allocated because the synchronization can be
+ * expensive.
+ */
+static void __init preallocate_pgd_pages_range(unsigned long start, unsigned long end,
+ const char *area)
+{
+ unsigned long addr;
+ const char *lvl;
+
+ for (addr = start; addr < end && addr >= start; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
+ pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ lvl = "p4d";
+ p4d = p4d_alloc(&init_mm, pgd, addr);
+ if (!p4d)
+ goto failed;
+
+ if (pgtable_l5_enabled)
+ continue;
+
+ lvl = "pud";
+ pud = pud_alloc(&init_mm, p4d, addr);
+ if (!pud)
+ goto failed;
+
+ if (pgtable_l4_enabled)
+ continue;
+
+ lvl = "pmd";
+ pmd = pmd_alloc(&init_mm, pud, addr);
+ if (!pmd)
+ goto failed;
+ }
+ return;
+
+failed:
+ /*
+ * The pages have to be there now or they will be missing in
+ * process page-tables later.
+ */
+ panic("Failed to pre-allocate %s pages for %s area\n", lvl, area);
+}
+
+void __init pgtable_cache_init(void)
+{
+ preallocate_pgd_pages_range(VMALLOC_START, VMALLOC_END, "vmalloc");
+ if (IS_ENABLED(CONFIG_MODULES))
+ preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules");
+}
+#endif
base-commit: ac9a78681b921877518763ba0e89202254349d1b
--
2.39.2
Hi Björn,
On 31/05/2023 11:38, Björn Töpel wrote:
> From: Björn Töpel <[email protected]>
>
> The RISC-V port requires that kernel PGD entries are to be
> synchronized between MMs. This is done via the vmalloc_fault()
> function, that simply copies the PGD entries from init_mm to the
> faulting one.
>
> Historically, faulting in PGD entries have been a source for both bugs
> [1], and poor performance.
>
> One way to get rid of vmalloc faults is by pre-allocating the PGD
> entries. Pre-allocating the entries potientially wastes 64 * 4K (65 on
> SV39). The pre-allocation function is pulled from Jörg Rödel's x86
> work, with the addition of 3-level page tables (PMD allocations).
>
> The pmd_alloc() function needs the ptlock cache to be initialized
> (when split page locks is enabled), so the pre-allocation is done in a
> RISC-V specific pgtable_cache_init() implementation.
>
> Pre-allocate the kernel PGD entries for the vmalloc/modules area, but
> only for 64b platforms.
>
> Link: https://lore.kernel.org/lkml/[email protected]/ # [1]
> Signed-off-by: Björn Töpel <[email protected]>
> ---
> v1->v2: Fixed broken !MMU build.
> ---
> arch/riscv/mm/fault.c | 16 ++----------
> arch/riscv/mm/init.c | 58 +++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 60 insertions(+), 14 deletions(-)
>
> diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
> index 8685f85a7474..b023fb311e28 100644
> --- a/arch/riscv/mm/fault.c
> +++ b/arch/riscv/mm/fault.c
> @@ -238,24 +238,12 @@ void handle_page_fault(struct pt_regs *regs)
> * only copy the information from the master page table,
> * nothing more.
> */
> - if (unlikely((addr >= VMALLOC_START) && (addr < VMALLOC_END))) {
> + if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) &&
> + unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) {
> vmalloc_fault(regs, code, addr);
> return;
> }
>
> -#ifdef CONFIG_64BIT
> - /*
> - * Modules in 64bit kernels lie in their own virtual region which is not
> - * in the vmalloc region, but dealing with page faults in this region
> - * or the vmalloc region amounts to doing the same thing: checking that
> - * the mapping exists in init_mm.pgd and updating user page table, so
> - * just use vmalloc_fault.
> - */
> - if (unlikely(addr >= MODULES_VADDR && addr < MODULES_END)) {
> - vmalloc_fault(regs, code, addr);
> - return;
> - }
> -#endif
> /* Enable interrupts if they were enabled in the parent context. */
> if (!regs_irqs_disabled(regs))
> local_irq_enable();
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index 747e5b1ef02d..45ceaff5679e 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -1363,3 +1363,61 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
> return vmemmap_populate_basepages(start, end, node, NULL);
> }
> #endif
> +
> +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
> +/*
> + * Pre-allocates page-table pages for a specific area in the kernel
> + * page-table. Only the level which needs to be synchronized between
> + * all page-tables is allocated because the synchronization can be
> + * expensive.
> + */
> +static void __init preallocate_pgd_pages_range(unsigned long start, unsigned long end,
> + const char *area)
> +{
> + unsigned long addr;
> + const char *lvl;
> +
> + for (addr = start; addr < end && addr >= start; addr = ALIGN(addr + 1, PGDIR_SIZE)) {
> + pgd_t *pgd = pgd_offset_k(addr);
> + p4d_t *p4d;
> + pud_t *pud;
> + pmd_t *pmd;
> +
> + lvl = "p4d";
> + p4d = p4d_alloc(&init_mm, pgd, addr);
> + if (!p4d)
> + goto failed;
> +
> + if (pgtable_l5_enabled)
> + continue;
> +
> + lvl = "pud";
> + pud = pud_alloc(&init_mm, p4d, addr);
> + if (!pud)
> + goto failed;
> +
> + if (pgtable_l4_enabled)
> + continue;
> +
> + lvl = "pmd";
> + pmd = pmd_alloc(&init_mm, pud, addr);
> + if (!pmd)
> + goto failed;
> + }
> + return;
> +
> +failed:
> + /*
> + * The pages have to be there now or they will be missing in
> + * process page-tables later.
> + */
> + panic("Failed to pre-allocate %s pages for %s area\n", lvl, area);
> +}
> +
> +void __init pgtable_cache_init(void)
> +{
> + preallocate_pgd_pages_range(VMALLOC_START, VMALLOC_END, "vmalloc");
> + if (IS_ENABLED(CONFIG_MODULES))
> + preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules");
> +}
> +#endif
>
> base-commit: ac9a78681b921877518763ba0e89202254349d1b
You can add:
Reviewed-by: Alexandre Ghiti <[email protected]>
Thanks!
Alex
Hello:
This patch was applied to riscv/linux.git (for-next)
by Palmer Dabbelt <[email protected]>:
On Wed, 31 May 2023 11:38:17 +0200 you wrote:
> From: Björn Töpel <[email protected]>
>
> The RISC-V port requires that kernel PGD entries are to be
> synchronized between MMs. This is done via the vmalloc_fault()
> function, that simply copies the PGD entries from init_mm to the
> faulting one.
>
> [...]
Here is the summary with links:
- [v2] riscv: mm: Pre-allocate PGD entries for vmalloc/modules area
https://git.kernel.org/riscv/c/7d3332be011e
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html