* [PATCH 1/2] mm/sparsemem: Enable vmem_altmap support in vmemmap_populate_basepages()
2020-01-23 5:56 [PATCH 0/2] arm64: Enable vmemmap mapping from device memory Anshuman Khandual
@ 2020-01-23 5:56 ` Anshuman Khandual
2020-01-23 5:56 ` [PATCH 2/2] arm64/mm: Enable vmem_altmap support for vmemmap mappings Anshuman Khandual
1 sibling, 0 replies; 3+ messages in thread
From: Anshuman Khandual @ 2020-01-23 5:56 UTC (permalink / raw)
To: linux-mm
Cc: Anshuman Khandual, Catalin Marinas, Will Deacon, Mark Rutland,
Paul Walmsley, Palmer Dabbelt, Tony Luck, Fenghua Yu,
Dave Hansen, Andy Lutomirski, Peter Zijlstra, Thomas Gleixner,
Ingo Molnar, David Hildenbrand, Mike Rapoport, Michal Hocko,
Matthew Wilcox (Oracle),
Kirill A. Shutemov, Andrew Morton, Dan Williams, Pavel Tatashin,
linux-arm-kernel, linux-ia64, linux-riscv, x86, linux-kernel
vmemmap_populate_basepages() is used across platforms to allocate backing
memory for vmemmap mapping. This is used as a standard default choice or
as a fallback when intended huge pages allocation fails. This just creates
entire vmemmap mapping with base pages (PAGE_SIZE).
On arm64 platforms, vmemmap_populate_basepages() is called instead of the
platform specific vmemmap_populate() when ARM64_SWAPPER_USES_SECTION_MAPS
is not enabled as in case for ARM64_16K_PAGES and ARM64_64K_PAGES configs.
At present vmemmap_populate_basepages() does not support allocating from
driver defined struct vmem_altmap while trying to create vmemmap mapping
for a device memory range. It prevents ARM64_16K_PAGES and ARM64_64K_PAGES
configs on arm64 from supporting device memory with vmemap_altmap request.
This enables vmem_altmap support in vmemmap_populate_basepages() unlocking
device memory allocation for vmemap mapping on arm64 platforms with 16K or
64K base page configs.
Each architecture should evaluate and decide on subscribing device memory
based base page allocation through vmemmap_populate_basepages(). Hence lets
keep it disabled on all archs in order to preserve the existing semantics.
A subsequent patch enables it on arm64.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-riscv@lists.infradead.org
Cc: x86@kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
arch/arm64/mm/mmu.c | 2 +-
arch/ia64/mm/discontig.c | 2 +-
arch/riscv/mm/init.c | 2 +-
arch/x86/mm/init_64.c | 6 +++---
include/linux/mm.h | 5 +++--
mm/sparse-vmemmap.c | 16 +++++++++++-----
6 files changed, 20 insertions(+), 13 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8dcafe1a3527..882698a716fb 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -999,7 +999,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node);
+ return vmemmap_populate_basepages(start, end, node, NULL);
}
#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 4f33f6e7e206..20409f3afea8 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -656,7 +656,7 @@ void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node);
+ return vmemmap_populate_basepages(start, end, node, NULL);
}
void vmemmap_free(unsigned long start, unsigned long end,
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 965a8cf4829c..1d7451c91982 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -501,6 +501,6 @@ void __init paging_init(void)
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node);
+ return vmemmap_populate_basepages(start, end, node, NULL);
}
#endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bcfede46fe02..cffeb3fd9de4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1507,7 +1507,7 @@ static int __meminit vmemmap_populate_hugepages(unsigned long start,
vmemmap_verify((pte_t *)pmd, node, addr, next);
continue;
}
- if (vmemmap_populate_basepages(addr, next, node))
+ if (vmemmap_populate_basepages(addr, next, node, NULL))
return -ENOMEM;
}
return 0;
@@ -1519,7 +1519,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
int err;
if (end - start < PAGES_PER_SECTION * sizeof(struct page))
- err = vmemmap_populate_basepages(start, end, node);
+ err = vmemmap_populate_basepages(start, end, node, NULL);
else if (boot_cpu_has(X86_FEATURE_PSE))
err = vmemmap_populate_hugepages(start, end, node, altmap);
else if (altmap) {
@@ -1527,7 +1527,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
__func__);
err = -ENOMEM;
} else
- err = vmemmap_populate_basepages(start, end, node);
+ err = vmemmap_populate_basepages(start, end, node, NULL);
if (!err)
sync_global_pgds(start, end - 1);
return err;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cfaa8feecfe8..6832df2b80b7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2752,14 +2752,15 @@ pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
-pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
+pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+ struct vmem_altmap *altmap);
void *vmemmap_alloc_block(unsigned long size, int node);
struct vmem_altmap;
void *vmemmap_alloc_block_buf(unsigned long size, int node);
void *altmap_alloc_block_buf(unsigned long size, struct vmem_altmap *altmap);
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
int vmemmap_populate_basepages(unsigned long start, unsigned long end,
- int node);
+ int node, struct vmem_altmap *altmap);
int vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap);
void vmemmap_populate_print_last(void);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 200aef686722..a407abc9b46c 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -140,12 +140,18 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
start, end - 1);
}
-pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node)
+pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
+ struct vmem_altmap *altmap)
{
pte_t *pte = pte_offset_kernel(pmd, addr);
if (pte_none(*pte)) {
pte_t entry;
- void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
+ void *p;
+
+ if (altmap)
+ p = altmap_alloc_block_buf(PAGE_SIZE, altmap);
+ else
+ p = vmemmap_alloc_block_buf(PAGE_SIZE, node);
if (!p)
return NULL;
entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
@@ -213,8 +219,8 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
return pgd;
}
-int __meminit vmemmap_populate_basepages(unsigned long start,
- unsigned long end, int node)
+int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
+ int node, struct vmem_altmap *altmap)
{
unsigned long addr = start;
pgd_t *pgd;
@@ -236,7 +242,7 @@ int __meminit vmemmap_populate_basepages(unsigned long start,
pmd = vmemmap_pmd_populate(pud, addr, node);
if (!pmd)
return -ENOMEM;
- pte = vmemmap_pte_populate(pmd, addr, node);
+ pte = vmemmap_pte_populate(pmd, addr, node, altmap);
if (!pte)
return -ENOMEM;
vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
--
2.20.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* [PATCH 2/2] arm64/mm: Enable vmem_altmap support for vmemmap mappings
2020-01-23 5:56 [PATCH 0/2] arm64: Enable vmemmap mapping from device memory Anshuman Khandual
2020-01-23 5:56 ` [PATCH 1/2] mm/sparsemem: Enable vmem_altmap support in vmemmap_populate_basepages() Anshuman Khandual
@ 2020-01-23 5:56 ` Anshuman Khandual
1 sibling, 0 replies; 3+ messages in thread
From: Anshuman Khandual @ 2020-01-23 5:56 UTC (permalink / raw)
To: linux-mm
Cc: Anshuman Khandual, Catalin Marinas, Will Deacon, Mark Rutland,
Steve Capper, David Hildenbrand, Yu Zhao, Hsin-Yi Wang,
Thomas Gleixner, Andrew Morton, linux-arm-kernel, linux-kernel
Device memory ranges when getting hot added into ZONE_DEVICE, might require
their vmemmap mapping's backing memory to be allocated from their own range
instead of consuming system memory. This prevents large system memory usage
for potentially large device memory ranges. Device driver communicates this
request via vmem_altmap structure. Architecture needs to take this request
into account while creating and tearing down vemmmap mappings.
This enables vmem_altmap support in vmemmap_populate() and vmemmap_free()
which includes vmemmap_populate_basepages() used for ARM64_16K_PAGES and
ARM64_64K_PAGES configs.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Steve Capper <steve.capper@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Hsin-Yi Wang <hsinyi@chromium.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
---
arch/arm64/mm/mmu.c | 65 ++++++++++++++++++++++++++++++++-------------
1 file changed, 47 insertions(+), 18 deletions(-)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 882698a716fb..ff69349ea5ec 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -727,15 +727,30 @@ int kern_addr_valid(unsigned long addr)
}
#ifdef CONFIG_MEMORY_HOTPLUG
-static void free_hotplug_page_range(struct page *page, size_t size)
+static void free_hotplug_page_range(struct page *page, size_t size,
+ struct vmem_altmap *altmap)
{
- WARN_ON(PageReserved(page));
- free_pages((unsigned long)page_address(page), get_order(size));
+ if (altmap) {
+ /*
+ * Though unmap_hotplug_range() will tear down altmap based
+ * vmemmap mappings at all page table levels, these mappings
+ * should only have been created either at PTE or PMD level
+ * with vmemmap_populate_basepages() or vmemmap_populate()
+ * respectively. Unmapping requests at any other level will
+ * be problematic. Drop these warnings when vmemmap mapping
+ * is supported at PUD level.
+ */
+ WARN_ON((size != PAGE_SIZE) && (size != PMD_SIZE));
+ vmem_altmap_free(altmap, size >> PAGE_SHIFT);
+ } else {
+ WARN_ON(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);
+ free_hotplug_page_range(page, PAGE_SIZE, NULL);
}
static bool pgtable_range_aligned(unsigned long start, unsigned long end,
@@ -758,7 +773,8 @@ static bool pgtable_range_aligned(unsigned long start, unsigned long end,
}
static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
- unsigned long end, bool free_mapped)
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
{
pte_t *ptep, pte;
@@ -772,12 +788,14 @@ static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
pte_clear(&init_mm, addr, ptep);
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
- free_hotplug_page_range(pte_page(pte), PAGE_SIZE);
+ free_hotplug_page_range(pte_page(pte),
+ PAGE_SIZE, altmap);
} while (addr += PAGE_SIZE, addr < end);
}
static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
- unsigned long end, bool free_mapped)
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
{
unsigned long next;
pmd_t *pmdp, pmd;
@@ -800,16 +818,17 @@ static void unmap_hotplug_pmd_range(pud_t *pudp, unsigned long addr,
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
free_hotplug_page_range(pmd_page(pmd),
- PMD_SIZE);
+ PMD_SIZE, altmap);
continue;
}
WARN_ON(!pmd_table(pmd));
- unmap_hotplug_pte_range(pmdp, addr, next, free_mapped);
+ unmap_hotplug_pte_range(pmdp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void unmap_hotplug_pud_range(pgd_t *pgdp, unsigned long addr,
- unsigned long end, bool free_mapped)
+ unsigned long end, bool free_mapped,
+ struct vmem_altmap *altmap)
{
unsigned long next;
pud_t *pudp, pud;
@@ -832,20 +851,27 @@ static void unmap_hotplug_pud_range(pgd_t *pgdp, unsigned long addr,
flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
if (free_mapped)
free_hotplug_page_range(pud_page(pud),
- PUD_SIZE);
+ PUD_SIZE, altmap);
continue;
}
WARN_ON(!pud_table(pud));
- unmap_hotplug_pmd_range(pudp, addr, next, free_mapped);
+ unmap_hotplug_pmd_range(pudp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
static void unmap_hotplug_range(unsigned long addr, unsigned long end,
- bool free_mapped)
+ bool free_mapped, struct vmem_altmap *altmap)
{
unsigned long next;
pgd_t *pgdp, pgd;
+ /*
+ * vmem_altmap can only be used as backing memory in a given
+ * page table mapping. In case backing memory itself is not
+ * being freed, then altmap is irrelevant. Warn about this
+ * inconsistency when encountered.
+ */
+ WARN_ON(!free_mapped && altmap);
do {
next = pgd_addr_end(addr, end);
pgdp = pgd_offset_k(addr);
@@ -854,7 +880,7 @@ static void unmap_hotplug_range(unsigned long addr, unsigned long end,
continue;
WARN_ON(!pgd_present(pgd));
- unmap_hotplug_pud_range(pgdp, addr, next, free_mapped);
+ unmap_hotplug_pud_range(pgdp, addr, next, free_mapped, altmap);
} while (addr = next, addr < end);
}
@@ -999,7 +1025,7 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
struct vmem_altmap *altmap)
{
- return vmemmap_populate_basepages(start, end, node, NULL);
+ return vmemmap_populate_basepages(start, end, node, altmap);
}
#else /* !ARM64_SWAPPER_USES_SECTION_MAPS */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
@@ -1026,7 +1052,10 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
if (pmd_none(READ_ONCE(*pmdp))) {
void *p = NULL;
- p = vmemmap_alloc_block_buf(PMD_SIZE, node);
+ if (altmap)
+ p = altmap_alloc_block_buf(PMD_SIZE, altmap);
+ else
+ p = vmemmap_alloc_block_buf(PMD_SIZE, node);
if (!p)
return -ENOMEM;
@@ -1044,7 +1073,7 @@ void vmemmap_free(unsigned long start, unsigned long end,
#ifdef CONFIG_MEMORY_HOTPLUG
WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
- unmap_hotplug_range(start, end, true);
+ unmap_hotplug_range(start, end, true, altmap);
free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END);
#endif
}
@@ -1332,7 +1361,7 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
WARN_ON(pgdir != init_mm.pgd);
WARN_ON((start < PAGE_OFFSET) || (end > PAGE_END));
- unmap_hotplug_range(start, end, false);
+ unmap_hotplug_range(start, end, false, NULL);
free_empty_tables(start, end, PAGE_OFFSET, PAGE_END);
}
--
2.20.1
^ permalink raw reply related [flat|nested] 3+ messages in thread