Re: [PATCH v4 06/11] riscv: mm: Add memory hotplugging support
On Wed, Jun 5, 2024 at 1:41 PM Björn Töpel wrote:
>
> From: Björn Töpel
>
> For an architecture to support memory hotplugging, a couple of
> callbacks needs to be implemented:
>
> arch_add_memory()
> This callback is responsible for adding the physical memory into the
> direct map, and call into the memory hotplugging generic code via
> __add_pages() that adds the corresponding struct page entries, and
> updates the vmemmap mapping.
>
> arch_remove_memory()
> This is the inverse of the callback above.
>
> vmemmap_free()
> This function tears down the vmemmap mappings (if
> CONFIG_SPARSEMEM_VMEMMAP is enabled), and also deallocates the
> backing vmemmap pages. Note that for persistent memory, an
> alternative allocator for the backing pages can be used; The
> vmem_altmap. This means that when the backing pages are cleared,
> extra care is needed so that the correct deallocation method is
> used.
>
> arch_get_mappable_range()
> This functions returns the PA range that the direct map can map.
> Used by the MHP internals for sanity checks.
>
> The page table unmap/teardown functions are heavily based on code from
> the x86 tree. The same remove_pgd_mapping() function is used in both
> vmemmap_free() and arch_remove_memory(), but in the latter function
> the backing pages are not removed.
>
> Signed-off-by: Björn Töpel
> ---
> arch/riscv/mm/init.c | 267 +++
> 1 file changed, 267 insertions(+)
>
> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
> index 1f7e7c223bec..bfa2dea95354 100644
> --- a/arch/riscv/mm/init.c
> +++ b/arch/riscv/mm/init.c
> @@ -1534,3 +1534,270 @@ struct execmem_info __init *execmem_arch_setup(void)
> }
> #endif /* CONFIG_MMU */
> #endif /* CONFIG_EXECMEM */
> +
> +#ifdef CONFIG_MEMORY_HOTPLUG
> +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
> +{
> + struct page *page = pmd_page(*pmd);
> + struct ptdesc *ptdesc = page_ptdesc(page);
> + pte_t *pte;
> + int i;
> +
> + for (i = 0; i < PTRS_PER_PTE; i++) {
> + pte = pte_start + i;
> + if (!pte_none(*pte))
> + return;
> + }
> +
> + pagetable_pte_dtor(ptdesc);
> + if (PageReserved(page))
> + free_reserved_page(page);
> + else
> + pagetable_free(ptdesc);
> + pmd_clear(pmd);
> +}
> +
> +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
> +{
> + struct page *page = pud_page(*pud);
> + struct ptdesc *ptdesc = page_ptdesc(page);
> + pmd_t *pmd;
> + int i;
> +
> + for (i = 0; i < PTRS_PER_PMD; i++) {
> + pmd = pmd_start + i;
> + if (!pmd_none(*pmd))
> + return;
> + }
> +
> + pagetable_pmd_dtor(ptdesc);
> + if (PageReserved(page))
> + free_reserved_page(page);
> + else
> + pagetable_free(ptdesc);
> + pud_clear(pud);
> +}
> +
> +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
> +{
> + struct page *page = p4d_page(*p4d);
> + pud_t *pud;
> + int i;
> +
> + for (i = 0; i < PTRS_PER_PUD; i++) {
> + pud = pud_start + i;
> + if (!pud_none(*pud))
> + return;
> + }
> +
> + if (PageReserved(page))
> + free_reserved_page(page);
> + else
> + free_pages((unsigned long)page_address(page), 0);
> + p4d_clear(p4d);
> +}
> +
> +static void __meminit free_vmemmap_storage(struct page *page, size_t size,
> + struct vmem_altmap *altmap)
> +{
> + int order = get_order(size);
> +
> + if (altmap) {
> + vmem_altmap_free(altmap, size >> PAGE_SHIFT);
> + return;
> + }
> +
> + if (PageReserved(page)) {
> + unsigned int nr_pages = 1 << order;
> +
> + while (nr_pages--)
> + free_reserved_page(page++);
> + return;
> + }
> +
> + free_pages((unsigned long)page_address(page), order);
> +}
> +
> +static void __meminit remove_pte_mapping(pte_t *pte_base, unsigned long
> addr, unsigned long end,
> +bool is_vmemmap, struct vmem_altmap
> *altmap)
> +{
> + unsigned long next;
> + pte_t *ptep, pte;
> +
> + for (; addr < end; addr = next) {
> + next = (addr + PAGE_SIZE) & PAGE_MASK;
> + if (next > end)
> + next = end;
> +
> + ptep = pte_base + pte_index(addr);
> + pte = ptep_get(ptep);
> + if (!pte_present(*ptep))
> + continue;
> +
> + pte_clear(_mm, addr, ptep);
> + if (is_vmemmap)
> + free_vmemmap_storage(pte_page(pte), PAGE_SIZE,
> altmap);
> + }
> +}
> +
>
[PATCH v4 06/11] riscv: mm: Add memory hotplugging support
From: Björn Töpel
For an architecture to support memory hotplugging, a couple of
callbacks needs to be implemented:
arch_add_memory()
This callback is responsible for adding the physical memory into the
direct map, and call into the memory hotplugging generic code via
__add_pages() that adds the corresponding struct page entries, and
updates the vmemmap mapping.
arch_remove_memory()
This is the inverse of the callback above.
vmemmap_free()
This function tears down the vmemmap mappings (if
CONFIG_SPARSEMEM_VMEMMAP is enabled), and also deallocates the
backing vmemmap pages. Note that for persistent memory, an
alternative allocator for the backing pages can be used; The
vmem_altmap. This means that when the backing pages are cleared,
extra care is needed so that the correct deallocation method is
used.
arch_get_mappable_range()
This functions returns the PA range that the direct map can map.
Used by the MHP internals for sanity checks.
The page table unmap/teardown functions are heavily based on code from
the x86 tree. The same remove_pgd_mapping() function is used in both
vmemmap_free() and arch_remove_memory(), but in the latter function
the backing pages are not removed.
Signed-off-by: Björn Töpel
---
arch/riscv/mm/init.c | 267 +++
1 file changed, 267 insertions(+)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1f7e7c223bec..bfa2dea95354 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1534,3 +1534,270 @@ struct execmem_info __init *execmem_arch_setup(void)
}
#endif /* CONFIG_MMU */
#endif /* CONFIG_EXECMEM */
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+ struct page *page = pmd_page(*pmd);
+ struct ptdesc *ptdesc = page_ptdesc(page);
+ pte_t *pte;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ pte = pte_start + i;
+ if (!pte_none(*pte))
+ return;
+ }
+
+ pagetable_pte_dtor(ptdesc);
+ if (PageReserved(page))
+ free_reserved_page(page);
+ else
+ pagetable_free(ptdesc);
+ pmd_clear(pmd);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+ struct page *page = pud_page(*pud);
+ struct ptdesc *ptdesc = page_ptdesc(page);
+ pmd_t *pmd;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ pmd = pmd_start + i;
+ if (!pmd_none(*pmd))
+ return;
+ }
+
+ pagetable_pmd_dtor(ptdesc);
+ if (PageReserved(page))
+ free_reserved_page(page);
+ else
+ pagetable_free(ptdesc);
+ pud_clear(pud);
+}
+
+static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d)
+{
+ struct page *page = p4d_page(*p4d);
+ pud_t *pud;
+ int i;
+
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ pud = pud_start + i;
+ if (!pud_none(*pud))
+ return;
+ }
+
+ if (PageReserved(page))
+ free_reserved_page(page);
+ else
+ free_pages((unsigned long)page_address(page), 0);
+ p4d_clear(p4d);
+}
+
+static void __meminit free_vmemmap_storage(struct page *page, size_t size,
+ struct vmem_altmap *altmap)
+{
+ int order = get_order(size);
+
+ if (altmap) {
+ vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+ return;
+ }
+
+ if (PageReserved(page)) {
+ unsigned int nr_pages = 1 << order;
+
+ while (nr_pages--)
+ free_reserved_page(page++);
+ return;
+ }
+
+ free_pages((unsigned long)page_address(page), order);
+}
+
+static void __meminit remove_pte_mapping(pte_t *pte_base, unsigned long addr,
unsigned long end,
+bool is_vmemmap, struct vmem_altmap
*altmap)
+{
+ unsigned long next;
+ pte_t *ptep, pte;
+
+ for (; addr < end; addr = next) {
+ next = (addr + PAGE_SIZE) & PAGE_MASK;
+ if (next > end)
+ next = end;
+
+ ptep = pte_base + pte_index(addr);
+ pte = ptep_get(ptep);
+ if (!pte_present(*ptep))
+ continue;
+
+ pte_clear(_mm, addr, ptep);
+ if (is_vmemmap)
+ free_vmemmap_storage(pte_page(pte), PAGE_SIZE, altmap);
+ }
+}
+
+static void __meminit remove_pmd_mapping(pmd_t *pmd_base, unsigned long addr,
unsigned long end,
+bool is_vmemmap, struct vmem_altmap
*altmap)
+{
+ unsigned long next;
+ pte_t *pte_base;
+ pmd_t *pmdp, pmd;
+
+ for (; addr < end; addr = next) {
+ next = pmd_addr_end(addr, end);
+
