github/kata-containers
1
0
Fork 1
mirror of https://github.com/kata-containers/kata-containers.git synced 2025-06-22 05:28:25 +00:00
Code Issues Projects Releases Wiki Activity

kernel: enable virtio-fs for arm64.

Browse Source 
This patch add patch file for virtio-fs-v0.3 kernel to enable memory hot
remove to let virtio-fs available on arm64. Also, kernel config file for
virtio-fs-v0.3x for arm64 is offered.

Fixes: #973
Signed-off-by: Jianyong Wu <jianyong.wu@arm.com>
This commit is contained in:
Jianyong Wu 2020-03-09 16:57:15 +08:00
parent 60de5bc2f8
commit 9b8f20cac8
3 changed files with 3217 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2763
kernel/configs/arm64_kata_kvm_virtio-fs-v0.3.x Normal file
View File

File diff suppressed because it is too large Load Diff

2
kernel/kata_config_version
View File

@ -1 +1 @@
69
70

453
kernel/patches/virtio-fs-v0.3.x/0001-arm64-mm-Enable-memory-hot-remove.patch Normal file
View File

@ -0,0 +1,453 @@
From: Anshuman Khandual <anshuman.khandual@arm.com>
Date: Mon, 15 Jul 2019 11:47:50 +0530
Subject: [PATCH] arm64/mm: Enable memory hot remove
The arch code for hot-remove must tear down portions of the linear map and
vmemmap corresponding to memory being removed. In both cases the page
tables mapping these regions must be freed, and when sparse vmemmap is in
use the memory backing the vmemmap must also be freed.
This patch adds a new remove_pagetable() helper which can be used to tear
down either region, and calls it from vmemmap_free() and
___remove_pgd_mapping(). The sparse_vmap argument determines whether the
backing memory will be freed.
remove_pagetable() makes two distinct passes over the kernel page table.
In the first pass it unmaps, invalidates applicable TLB cache and frees
backing memory if required (vmemmap) for each mapped leaf entry. In the
second pass it looks for empty page table sections whose page table page
can be unmapped, TLB invalidated and freed.
While freeing intermediate level page table pages bail out if any of its
entries are still valid. This can happen for partially filled kernel page
table either from a previously attempted failed memory hot add or while
removing an address range which does not span the entire page table page
range.
The vmemmap region may share levels of table with the vmalloc region.
There can be conflicts between hot remove freeing page table pages with
a concurrent vmalloc() walking the kernel page table. This conflict can
not just be solved by taking the init_mm ptl because of existing locking
scheme in vmalloc(). Hence unlike linear mapping, skip freeing page table
pages while tearing down vmemmap mapping.
While here update arch_add_memory() to handle __add_pages() failures by
just unmapping recently added kernel linear mapping. Now enable memory hot
remove on arm64 platforms by default with ARCH_ENABLE_MEMORY_HOTREMOVE.
This implementation is overall inspired from kernel page table tear down
procedure on X86 architecture.
Acked-by: Steve Capper <steve.capper@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
arch/arm64/Kconfig | 3 +
arch/arm64/include/asm/pgtable.h | 7 +-
arch/arm64/mm/mmu.c | 290 ++++++++++++++++++++++++++++++-
include/linux/mmzone.h | 1 +
mm/Kconfig | 2 +-
5 files changed, 291 insertions(+), 12 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3adcec05b1f6..5a1231b8b8cf 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -273,6 +273,9 @@ config ZONE_DMA32
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+ def_bool y
+
config SMP
def_bool y
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 5fdcfe237338..e09760ece844 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -209,7 +209,7 @@ static inline pmd_t pmd_mkcont(pmd_t pmd)
static inline pte_t pte_mkdevmap(pte_t pte)
{
- return set_pte_bit(pte, __pgprot(PTE_DEVMAP));
+ return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
}
static inline void set_pte(pte_t *ptep, pte_t pte)
@@ -396,7 +396,10 @@ static inline int pmd_protnone(pmd_t pmd)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd))
#endif
-#define pmd_mkdevmap(pmd) pte_pmd(pte_mkdevmap(pmd_pte(pmd)))
+static inline pmd_t pmd_mkdevmap(pmd_t pmd)
+{
+ return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
+}
#define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd))
#define __phys_to_pmd_val(phys) __phys_to_pte_val(phys)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 750a69dde39b..282a4b26218c 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -722,6 +722,250 @@ int kern_addr_valid(unsigned long addr)
return pfn_valid(pte_pfn(pte));
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static void free_hotplug_page_range(struct page *page, size_t size)
+{
+ WARN_ON(!page || PageReserved(page));
+ free_pages((unsigned long)page_address(page), get_order(size));
+}
+
+static void free_hotplug_pgtable_page(struct page *page)
+{
+ free_hotplug_page_range(page, PAGE_SIZE);
+}
+
+static void free_pte_table(pmd_t *pmdp, unsigned long addr)
+{
+ struct page *page;
+ pte_t *ptep;
+ int i;
+
+ ptep = pte_offset_kernel(pmdp, 0UL);
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ if (!pte_none(READ_ONCE(ptep[i])))
+ return;
+ }
+
+ page = pmd_page(READ_ONCE(*pmdp));
+ pmd_clear(pmdp);
+ __flush_tlb_kernel_pgtable(addr);
+ free_hotplug_pgtable_page(page);
+}
+
+static void free_pmd_table(pud_t *pudp, unsigned long addr)
+{
+ struct page *page;
+ pmd_t *pmdp;
+ int i;
+
+ if (CONFIG_PGTABLE_LEVELS <= 2)
+ return;
+
+ pmdp = pmd_offset(pudp, 0UL);
+ for (i = 0; i < PTRS_PER_PMD; i++) {
+ if (!pmd_none(READ_ONCE(pmdp[i])))
+ return;
+ }
+
+ page = pud_page(READ_ONCE(*pudp));
+ pud_clear(pudp);
+ __flush_tlb_kernel_pgtable(addr);
+ free_hotplug_pgtable_page(page);
+}
+
+static void free_pud_table(pgd_t *pgdp, unsigned long addr)
+{
+ struct page *page;
+ pud_t *pudp;
+ int i;
+
+ if (CONFIG_PGTABLE_LEVELS <= 3)
+ return;
+
+ pudp = pud_offset(pgdp, 0UL);
+ for (i = 0; i < PTRS_PER_PUD; i++) {
+ if (!pud_none(READ_ONCE(pudp[i])))
+ return;
+ }
+
+ page = pgd_page(READ_ONCE(*pgdp));
+ pgd_clear(pgdp);
+ __flush_tlb_kernel_pgtable(addr);
+ free_hotplug_pgtable_page(page);
+}
+
+static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, bool sparse_vmap)
+{
+ struct page *page;
+ pte_t *ptep, pte;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ if (pte_none(pte))
+ continue;
+
+ WARN_ON(!pte_present(pte));
+ page = sparse_vmap ? pte_page(pte) : NULL;
+ pte_clear(&init_mm, addr, ptep);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+ if (sparse_vmap)
+ free_hotplug_page_range(page, PAGE_SIZE);
+ } while (addr += PAGE_SIZE, addr < end);
+}
+
+static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
+ unsigned long end, bool sparse_vmap)
+{
+ unsigned long next;
+ struct page *page;
+ pmd_t *pmdp, pmd;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd));
+ if (pmd_sect(pmd)) {
+ page = sparse_vmap ? pmd_page(pmd) : NULL;
+ pmd_clear(pmdp);
+ flush_tlb_kernel_range(addr, next);
+ if (sparse_vmap)
+ free_hotplug_page_range(page, PMD_SIZE);
+ continue;
+ }
+ WARN_ON(!pmd_table(pmd));
+ unmap_hotplug_pte_range(pmdp, addr, next, sparse_vmap);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_pud_range(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, bool sparse_vmap)
+{
+ unsigned long next;
+ struct page *page;
+ pud_t *pudp, pud;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud));
+ if (pud_sect(pud)) {
+ page = sparse_vmap ? pud_page(pud) : NULL;
+ pud_clear(pudp);
+ flush_tlb_kernel_range(addr, next);
+ if (sparse_vmap)
+ free_hotplug_page_range(page, PUD_SIZE);
+ continue;
+ }
+ WARN_ON(!pud_table(pud));
+ unmap_hotplug_pmd_range(pudp, addr, next, sparse_vmap);
+ } while (addr = next, addr < end);
+}
+
+static void unmap_hotplug_range(unsigned long addr, unsigned long end,
+ bool sparse_vmap)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ unmap_hotplug_pud_range(pgdp, addr, next, sparse_vmap);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
+ unsigned long end)
+{
+ pte_t *ptep, pte;
+
+ do {
+ ptep = pte_offset_kernel(pmdp, addr);
+ pte = READ_ONCE(*ptep);
+ WARN_ON(!pte_none(pte));
+ } while (addr += PAGE_SIZE, addr < end);
+}
+
+static void free_empty_pmd_table(pud_t *pudp, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+ pmd_t *pmdp, pmd;
+
+ do {
+ next = pmd_addr_end(addr, end);
+ pmdp = pmd_offset(pudp, addr);
+ pmd = READ_ONCE(*pmdp);
+ if (pmd_none(pmd))
+ continue;
+
+ WARN_ON(!pmd_present(pmd) || !pmd_table(pmd) || pmd_sect(pmd));
+ free_empty_pte_table(pmdp, addr, next);
+ free_pte_table(pmdp, addr);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_pud_table(pgd_t *pgdp, unsigned long addr,
+ unsigned long end)
+{
+ unsigned long next;
+ pud_t *pudp, pud;
+
+ do {
+ next = pud_addr_end(addr, end);
+ pudp = pud_offset(pgdp, addr);
+ pud = READ_ONCE(*pudp);
+ if (pud_none(pud))
+ continue;
+
+ WARN_ON(!pud_present(pud) || !pud_table(pud) || pud_sect(pud));
+ free_empty_pmd_table(pudp, addr, next);
+ free_pmd_table(pudp, addr);
+ } while (addr = next, addr < end);
+}
+
+static void free_empty_tables(unsigned long addr, unsigned long end)
+{
+ unsigned long next;
+ pgd_t *pgdp, pgd;
+
+ do {
+ next = pgd_addr_end(addr, end);
+ pgdp = pgd_offset_k(addr);
+ pgd = READ_ONCE(*pgdp);
+ if (pgd_none(pgd))
+ continue;
+
+ WARN_ON(!pgd_present(pgd));
+ free_empty_pud_table(pgdp, addr, next);
+ free_pud_table(pgdp, addr);
+ } while (addr = next, addr < end);
+}
+
+static void remove_pagetable(unsigned long start, unsigned long end,
+ bool sparse_vmap)
+{
+ unmap_hotplug_range(start, end, sparse_vmap);
+ free_empty_tables(start, end);
+}
+#endif
+
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#if !ARM64_SWAPPER_USES_SECTION_MAPS
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -769,6 +1013,27 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
void vmemmap_free(unsigned long start, unsigned long end,
struct vmem_altmap *altmap)
{
+#ifdef CONFIG_MEMORY_HOTPLUG
+ /*
+ * FIXME: We should have called remove_pagetable(start, end, true).
+ * vmemmap and vmalloc virtual range might share intermediate kernel
+ * page table entries. Removing vmemmap range page table pages here
+ * can potentially conflict with a concurrent vmalloc() allocation.
+ *
+ * This is primarily because vmalloc() does not take init_mm ptl for
+ * the entire page table walk and it's modification. Instead it just
+ * takes the lock while allocating and installing page table pages
+ * via [p4d|pud|pmd|pte]_alloc(). A concurrently vanishing page table
+ * entry via memory hot remove can cause vmalloc() kernel page table
+ * walk pointers to be invalid on the fly which can cause corruption
+ * or worst, a crash.
+ *
+ * To avoid this problem, lets not free empty page table pages for
+ * given vmemmap range being hot-removed. Just unmap and free the
+ * range instead.
+ */
+ unmap_hotplug_range(start, end, true);
+#endif
}
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
@@ -1060,10 +1325,18 @@ int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
}
#ifdef CONFIG_MEMORY_HOTPLUG
+static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
+{
+ unsigned long end = start + size;
+
+ WARN_ON(pgdir != init_mm.pgd);
+ remove_pagetable(start, end, false);
+}
+
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_restrictions *restrictions)
{
- int flags = 0;
+ int ret, flags = 0;
if (rodata_full || debug_pagealloc_enabled())
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
@@ -1071,9 +1344,14 @@ int arch_add_memory(int nid, u64 start, u64 size,
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
- return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
+ ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
restrictions);
+ if (ret)
+ __remove_pgd_mapping(swapper_pg_dir,
+ __phys_to_virt(start), size);
+ return ret;
}
+
void arch_remove_memory(int nid, u64 start, u64 size,
struct vmem_altmap *altmap)
{
@@ -1081,14 +1359,8 @@ void arch_remove_memory(int nid, u64 start, u64 size,
unsigned long nr_pages = size >> PAGE_SHIFT;
struct zone *zone;
- /*
- * FIXME: Cleanup page tables (also in arch_add_memory() in case
- * adding fails). Until then, this function should only be used
- * during memory hotplug (adding memory), not for memory
- * unplug. ARCH_ENABLE_MEMORY_HOTREMOVE must not be
- * unlocked yet.
- */
zone = page_zone(pfn_to_page(start_pfn));
__remove_pages(zone, start_pfn, nr_pages, altmap);
+ __remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
}
#endif
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d77d717c620c..47230ebdcb01 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1122,6 +1122,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
* PFN_SECTION_SHIFT pfn to/from section number
*/
#define PA_SECTION_SHIFT (SECTION_SIZE_BITS)
+#define PA_SECTION_SIZE (1UL << PA_SECTION_SHIFT)
#define PFN_SECTION_SHIFT (SECTION_SIZE_BITS - PAGE_SHIFT)
#define NR_MEM_SECTIONS (1UL << SECTIONS_SHIFT)
diff --git a/mm/Kconfig b/mm/Kconfig
index 56cec636a1fc..7c980f483a7d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -677,7 +677,7 @@ config DEV_PAGEMAP_OPS
config HMM_MIRROR
bool "HMM mirror CPU page table into a device page table"
- depends on (X86_64 || PPC64)
+ depends on (X86_64 || PPC64 || ARM64)
depends on MMU && 64BIT
select MMU_NOTIFIER
help
--
2.17.1