* [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
@ 2022-04-12 9:07 ` Guanghui Feng
0 siblings, 0 replies; 6+ messages in thread
From: Guanghui Feng @ 2022-04-12 9:07 UTC (permalink / raw)
To: catalin.marinas, will, linux-arm-kernel; +Cc: linux-kernel, baolin.wang
There are many changes and discussions:
commit 031495635b46
commit 1a8e1cef7603
commit 8424ecdde7df
commit 0a30c53573b0
commit 2687275a5843
When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
mem_map will use non block/section mapping(for crashkernel requires to shrink
the region in page granularity). But it will degrade performance when doing
larging continuous mem access in kernel(memcpy/memmove, etc).
This patch firstly do block/section mapping at mem_map, reserve crashkernel
memory. And then walking pagetable to split block/section mapping
to non block/section mapping [only] for crashkernel mem. We will accelerate
mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
conspicuously on some platform with this optimization.
Signed-off-by: Guanghui Feng <guanghuifeng@linux.alibaba.com>
---
arch/arm64/include/asm/mmu.h | 1 +
arch/arm64/mm/init.c | 8 +-
arch/arm64/mm/mmu.c | 274 +++++++++++++++++++++++++++++++++++++++----
3 files changed, 253 insertions(+), 30 deletions(-)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 48f8466..df113cc 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -63,6 +63,7 @@ static inline bool arm64_kernel_unmapped_at_el0(void)
extern void arm64_memblock_init(void);
extern void paging_init(void);
extern void bootmem_init(void);
+extern void mapping_crashkernel(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
extern void init_mem_pgprot(void);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 8ac25f1..02edd45 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -335,10 +335,6 @@ void __init arm64_memblock_init(void)
}
early_init_fdt_scan_reserved_mem();
-
- if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
- reserve_crashkernel();
-
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
}
@@ -385,8 +381,8 @@ void __init bootmem_init(void)
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
*/
- if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
- reserve_crashkernel();
+ reserve_crashkernel();
+ mapping_crashkernel();
memblock_dump_all();
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 626ec32..0672afd 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -498,6 +498,256 @@ static int __init enable_crash_mem_map(char *arg)
}
early_param("crashkernel", enable_crash_mem_map);
+#ifdef CONFIG_KEXEC_CORE
+static phys_addr_t __init early_crashkernel_pgtable_alloc(int shift)
+{
+ phys_addr_t phys;
+ void *ptr;
+
+ phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
+ MEMBLOCK_ALLOC_NOLEAKTRACE);
+ if (!phys)
+ panic("Failed to allocate page table page\n");
+
+ ptr = (void *)__phys_to_virt(phys);
+ memset(ptr, 0, PAGE_SIZE);
+ return phys;
+}
+
+static void init_crashkernel_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end,
+ phys_addr_t phys, pgprot_t prot)
+{
+ pte_t *ptep;
+ ptep = pte_offset_kernel(pmdp, addr);
+ do {
+ set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+ phys += PAGE_SIZE;
+ } while (ptep++, addr += PAGE_SIZE, addr != end);
+}
+
+static void alloc_crashkernel_cont_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ BUG_ON(pmd_sect(pmd));
+ if (pmd_none(pmd)) {
+ pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+ phys_addr_t pte_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pmdval |= PMD_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
+ __pmd_populate(pmdp, pte_phys, pmdval);
+ pmd = READ_ONCE(*pmdp);
+ }
+ BUG_ON(pmd_bad(pmd));
+
+ do {
+ pgprot_t __prot = prot;
+ next = pte_cont_addr_end(addr, end);
+ init_crashkernel_pte(pmdp, addr, next, phys, __prot);
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int), int flags)
+{
+ phys_addr_t map_offset;
+ unsigned long next;
+ pmd_t *pmdp;
+ pmdval_t pmdval;
+
+ pmdp = pmd_offset(pudp, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
+ phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
+ pmd_clear(pmdp);
+ pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+ if (flags & NO_EXEC_MAPPINGS)
+ pmdval |= PMD_TABLE_PXN;
+ __pmd_populate(pmdp, pte_phys, pmdval);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+ map_offset = addr - (addr & PMD_MASK);
+ if (map_offset)
+ alloc_init_cont_pte(pmdp, addr & PMD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+ if (next < (addr & PMD_MASK) + PMD_SIZE)
+ alloc_init_cont_pte(pmdp, next, (addr & PUD_MASK) +
+ PUD_SIZE, next - addr + phys,
+ prot, pgtable_alloc, flags);
+ }
+ alloc_crashkernel_cont_pte(pmdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pmdp++, addr = next, addr != end);
+}
+
+static void alloc_crashkernel_cont_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pud_t pud = READ_ONCE(*pudp);
+
+ /*
+ * Check for initial section mappings in the pgd/pud.
+ */
+ BUG_ON(pud_sect(pud));
+ if (pud_none(pud)) {
+ pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+ phys_addr_t pmd_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pudval |= PUD_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
+ __pud_populate(pudp, pmd_phys, pudval);
+ pud = READ_ONCE(*pudp);
+ }
+ BUG_ON(pud_bad(pud));
+
+ do {
+ pgprot_t __prot = prot;
+ next = pmd_cont_addr_end(addr, end);
+ init_crashkernel_pmd(pudp, addr, next, phys, __prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void alloc_crashkernel_pud(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ phys_addr_t map_offset;
+ unsigned long next;
+ pud_t *pudp;
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+ p4d_t p4d = READ_ONCE(*p4dp);
+ pudval_t pudval;
+
+ if (p4d_none(p4d)) {
+ p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
+ phys_addr_t pud_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ p4dval |= P4D_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pud_phys = pgtable_alloc(PUD_SHIFT);
+ __p4d_populate(p4dp, pud_phys, p4dval);
+ p4d = READ_ONCE(*p4dp);
+ }
+ BUG_ON(p4d_bad(p4d));
+
+ /*
+ * No need for locking during early boot. And it doesn't work as
+ * expected with KASLR enabled.
+ */
+ if (system_state != SYSTEM_BOOTING)
+ mutex_lock(&fixmap_lock);
+ pudp = pud_offset(p4dp, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (!pud_none(*pudp) && pud_sect(*pudp)) {
+ phys_addr_t pmd_phys = pgtable_alloc(PMD_SHIFT);
+ pud_clear(pudp);
+
+ pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+ if (flags & NO_EXEC_MAPPINGS)
+ pudval |= PUD_TABLE_PXN;
+ __pud_populate(pudp, pmd_phys, pudval);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+ map_offset = addr - (addr & PUD_MASK);
+ if (map_offset)
+ alloc_init_cont_pmd(pudp, addr & PUD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+ if (next < (addr & PUD_MASK) + PUD_SIZE)
+ alloc_init_cont_pmd(pudp, next, (addr & PUD_MASK) +
+ PUD_SIZE, next - addr + phys,
+ prot, pgtable_alloc, flags);
+ }
+ alloc_crashkernel_cont_pmd(pudp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pudp++, addr = next, addr != end);
+
+ if (system_state != SYSTEM_BOOTING)
+ mutex_unlock(&fixmap_lock);
+}
+
+static void __create_crashkernel_mapping(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long addr, end, next;
+ pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
+
+ /*
+ * If the virtual and physical address don't have the same offset
+ * within a page, we cannot map the region as the caller expects.
+ */
+ if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
+ return;
+
+ phys &= PAGE_MASK;
+ addr = virt & PAGE_MASK;
+ end = PAGE_ALIGN(virt + size);
+
+ do {
+ next = pgd_addr_end(addr, end);
+ alloc_crashkernel_pud(pgdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pgdp++, addr = next, addr != end);
+}
+
+static void __init map_crashkernel(pgd_t *pgdp, phys_addr_t start,
+ phys_addr_t end, pgprot_t prot, int flags)
+{
+ __create_crashkernel_mapping(pgdp, start, __phys_to_virt(start),
+ end - start, prot,
+ early_crashkernel_pgtable_alloc, flags);
+}
+
+void __init mapping_crashkernel(void)
+{
+ if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
+ return;
+
+ if (!crash_mem_map || !crashk_res.end)
+ return;
+
+ map_crashkernel(swapper_pg_dir, crashk_res.start,
+ crashk_res.end + 1, PAGE_KERNEL,
+ NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+}
+#else
+void __init mapping_crashkernel(void) {}
+#endif
+
static void __init map_mem(pgd_t *pgdp)
{
static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
@@ -527,17 +777,6 @@ static void __init map_mem(pgd_t *pgdp)
*/
memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
-#ifdef CONFIG_KEXEC_CORE
- if (crash_mem_map) {
- if (IS_ENABLED(CONFIG_ZONE_DMA) ||
- IS_ENABLED(CONFIG_ZONE_DMA32))
- flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
- else if (crashk_res.end)
- memblock_mark_nomap(crashk_res.start,
- resource_size(&crashk_res));
- }
-#endif
-
/* map all the memory banks */
for_each_mem_range(i, &start, &end) {
if (start >= end)
@@ -570,19 +809,6 @@ static void __init map_mem(pgd_t *pgdp)
* in page granularity and put back unused memory to buddy system
* through /sys/kernel/kexec_crash_size interface.
*/
-#ifdef CONFIG_KEXEC_CORE
- if (crash_mem_map &&
- !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
- if (crashk_res.end) {
- __map_memblock(pgdp, crashk_res.start,
- crashk_res.end + 1,
- PAGE_KERNEL,
- NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
- memblock_clear_nomap(crashk_res.start,
- resource_size(&crashk_res));
- }
- }
-#endif
}
void mark_rodata_ro(void)
--
1.8.3.1
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
@ 2022-04-12 9:07 ` Guanghui Feng
0 siblings, 0 replies; 6+ messages in thread
From: Guanghui Feng @ 2022-04-12 9:07 UTC (permalink / raw)
To: catalin.marinas, will, linux-arm-kernel; +Cc: linux-kernel, baolin.wang
There are many changes and discussions:
commit 031495635b46
commit 1a8e1cef7603
commit 8424ecdde7df
commit 0a30c53573b0
commit 2687275a5843
When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
mem_map will use non block/section mapping(for crashkernel requires to shrink
the region in page granularity). But it will degrade performance when doing
larging continuous mem access in kernel(memcpy/memmove, etc).
This patch firstly do block/section mapping at mem_map, reserve crashkernel
memory. And then walking pagetable to split block/section mapping
to non block/section mapping [only] for crashkernel mem. We will accelerate
mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
conspicuously on some platform with this optimization.
Signed-off-by: Guanghui Feng <guanghuifeng@linux.alibaba.com>
---
arch/arm64/include/asm/mmu.h | 1 +
arch/arm64/mm/init.c | 8 +-
arch/arm64/mm/mmu.c | 274 +++++++++++++++++++++++++++++++++++++++----
3 files changed, 253 insertions(+), 30 deletions(-)
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 48f8466..df113cc 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -63,6 +63,7 @@ static inline bool arm64_kernel_unmapped_at_el0(void)
extern void arm64_memblock_init(void);
extern void paging_init(void);
extern void bootmem_init(void);
+extern void mapping_crashkernel(void);
extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
extern void init_mem_pgprot(void);
extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 8ac25f1..02edd45 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -335,10 +335,6 @@ void __init arm64_memblock_init(void)
}
early_init_fdt_scan_reserved_mem();
-
- if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
- reserve_crashkernel();
-
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
}
@@ -385,8 +381,8 @@ void __init bootmem_init(void)
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
*/
- if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
- reserve_crashkernel();
+ reserve_crashkernel();
+ mapping_crashkernel();
memblock_dump_all();
}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 626ec32..0672afd 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -498,6 +498,256 @@ static int __init enable_crash_mem_map(char *arg)
}
early_param("crashkernel", enable_crash_mem_map);
+#ifdef CONFIG_KEXEC_CORE
+static phys_addr_t __init early_crashkernel_pgtable_alloc(int shift)
+{
+ phys_addr_t phys;
+ void *ptr;
+
+ phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0,
+ MEMBLOCK_ALLOC_NOLEAKTRACE);
+ if (!phys)
+ panic("Failed to allocate page table page\n");
+
+ ptr = (void *)__phys_to_virt(phys);
+ memset(ptr, 0, PAGE_SIZE);
+ return phys;
+}
+
+static void init_crashkernel_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end,
+ phys_addr_t phys, pgprot_t prot)
+{
+ pte_t *ptep;
+ ptep = pte_offset_kernel(pmdp, addr);
+ do {
+ set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+ phys += PAGE_SIZE;
+ } while (ptep++, addr += PAGE_SIZE, addr != end);
+}
+
+static void alloc_crashkernel_cont_pte(pmd_t *pmdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pmd_t pmd = READ_ONCE(*pmdp);
+
+ BUG_ON(pmd_sect(pmd));
+ if (pmd_none(pmd)) {
+ pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+ phys_addr_t pte_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pmdval |= PMD_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
+ __pmd_populate(pmdp, pte_phys, pmdval);
+ pmd = READ_ONCE(*pmdp);
+ }
+ BUG_ON(pmd_bad(pmd));
+
+ do {
+ pgprot_t __prot = prot;
+ next = pte_cont_addr_end(addr, end);
+ init_crashkernel_pte(pmdp, addr, next, phys, __prot);
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int), int flags)
+{
+ phys_addr_t map_offset;
+ unsigned long next;
+ pmd_t *pmdp;
+ pmdval_t pmdval;
+
+ pmdp = pmd_offset(pudp, addr);
+ do {
+ next = pmd_addr_end(addr, end);
+ if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
+ phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
+ pmd_clear(pmdp);
+ pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+ if (flags & NO_EXEC_MAPPINGS)
+ pmdval |= PMD_TABLE_PXN;
+ __pmd_populate(pmdp, pte_phys, pmdval);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+ map_offset = addr - (addr & PMD_MASK);
+ if (map_offset)
+ alloc_init_cont_pte(pmdp, addr & PMD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+ if (next < (addr & PMD_MASK) + PMD_SIZE)
+ alloc_init_cont_pte(pmdp, next, (addr & PUD_MASK) +
+ PUD_SIZE, next - addr + phys,
+ prot, pgtable_alloc, flags);
+ }
+ alloc_crashkernel_cont_pte(pmdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pmdp++, addr = next, addr != end);
+}
+
+static void alloc_crashkernel_cont_pmd(pud_t *pudp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long next;
+ pud_t pud = READ_ONCE(*pudp);
+
+ /*
+ * Check for initial section mappings in the pgd/pud.
+ */
+ BUG_ON(pud_sect(pud));
+ if (pud_none(pud)) {
+ pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+ phys_addr_t pmd_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pudval |= PUD_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
+ __pud_populate(pudp, pmd_phys, pudval);
+ pud = READ_ONCE(*pudp);
+ }
+ BUG_ON(pud_bad(pud));
+
+ do {
+ pgprot_t __prot = prot;
+ next = pmd_cont_addr_end(addr, end);
+ init_crashkernel_pmd(pudp, addr, next, phys, __prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void alloc_crashkernel_pud(pgd_t *pgdp, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ phys_addr_t map_offset;
+ unsigned long next;
+ pud_t *pudp;
+ p4d_t *p4dp = p4d_offset(pgdp, addr);
+ p4d_t p4d = READ_ONCE(*p4dp);
+ pudval_t pudval;
+
+ if (p4d_none(p4d)) {
+ p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
+ phys_addr_t pud_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ p4dval |= P4D_TABLE_PXN;
+ BUG_ON(!pgtable_alloc);
+ pud_phys = pgtable_alloc(PUD_SHIFT);
+ __p4d_populate(p4dp, pud_phys, p4dval);
+ p4d = READ_ONCE(*p4dp);
+ }
+ BUG_ON(p4d_bad(p4d));
+
+ /*
+ * No need for locking during early boot. And it doesn't work as
+ * expected with KASLR enabled.
+ */
+ if (system_state != SYSTEM_BOOTING)
+ mutex_lock(&fixmap_lock);
+ pudp = pud_offset(p4dp, addr);
+ do {
+ next = pud_addr_end(addr, end);
+ if (!pud_none(*pudp) && pud_sect(*pudp)) {
+ phys_addr_t pmd_phys = pgtable_alloc(PMD_SHIFT);
+ pud_clear(pudp);
+
+ pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+ if (flags & NO_EXEC_MAPPINGS)
+ pudval |= PUD_TABLE_PXN;
+ __pud_populate(pudp, pmd_phys, pudval);
+ flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
+
+ map_offset = addr - (addr & PUD_MASK);
+ if (map_offset)
+ alloc_init_cont_pmd(pudp, addr & PUD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+ if (next < (addr & PUD_MASK) + PUD_SIZE)
+ alloc_init_cont_pmd(pudp, next, (addr & PUD_MASK) +
+ PUD_SIZE, next - addr + phys,
+ prot, pgtable_alloc, flags);
+ }
+ alloc_crashkernel_cont_pmd(pudp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pudp++, addr = next, addr != end);
+
+ if (system_state != SYSTEM_BOOTING)
+ mutex_unlock(&fixmap_lock);
+}
+
+static void __create_crashkernel_mapping(pgd_t *pgdir, phys_addr_t phys,
+ unsigned long virt, phys_addr_t size,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(int),
+ int flags)
+{
+ unsigned long addr, end, next;
+ pgd_t *pgdp = pgd_offset_pgd(pgdir, virt);
+
+ /*
+ * If the virtual and physical address don't have the same offset
+ * within a page, we cannot map the region as the caller expects.
+ */
+ if (WARN_ON((phys ^ virt) & ~PAGE_MASK))
+ return;
+
+ phys &= PAGE_MASK;
+ addr = virt & PAGE_MASK;
+ end = PAGE_ALIGN(virt + size);
+
+ do {
+ next = pgd_addr_end(addr, end);
+ alloc_crashkernel_pud(pgdp, addr, next, phys, prot,
+ pgtable_alloc, flags);
+ phys += next - addr;
+ } while (pgdp++, addr = next, addr != end);
+}
+
+static void __init map_crashkernel(pgd_t *pgdp, phys_addr_t start,
+ phys_addr_t end, pgprot_t prot, int flags)
+{
+ __create_crashkernel_mapping(pgdp, start, __phys_to_virt(start),
+ end - start, prot,
+ early_crashkernel_pgtable_alloc, flags);
+}
+
+void __init mapping_crashkernel(void)
+{
+ if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
+ return;
+
+ if (!crash_mem_map || !crashk_res.end)
+ return;
+
+ map_crashkernel(swapper_pg_dir, crashk_res.start,
+ crashk_res.end + 1, PAGE_KERNEL,
+ NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+}
+#else
+void __init mapping_crashkernel(void) {}
+#endif
+
static void __init map_mem(pgd_t *pgdp)
{
static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
@@ -527,17 +777,6 @@ static void __init map_mem(pgd_t *pgdp)
*/
memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
-#ifdef CONFIG_KEXEC_CORE
- if (crash_mem_map) {
- if (IS_ENABLED(CONFIG_ZONE_DMA) ||
- IS_ENABLED(CONFIG_ZONE_DMA32))
- flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
- else if (crashk_res.end)
- memblock_mark_nomap(crashk_res.start,
- resource_size(&crashk_res));
- }
-#endif
-
/* map all the memory banks */
for_each_mem_range(i, &start, &end) {
if (start >= end)
@@ -570,19 +809,6 @@ static void __init map_mem(pgd_t *pgdp)
* in page granularity and put back unused memory to buddy system
* through /sys/kernel/kexec_crash_size interface.
*/
-#ifdef CONFIG_KEXEC_CORE
- if (crash_mem_map &&
- !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
- if (crashk_res.end) {
- __map_memblock(pgdp, crashk_res.start,
- crashk_res.end + 1,
- PAGE_KERNEL,
- NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
- memblock_clear_nomap(crashk_res.start,
- resource_size(&crashk_res));
- }
- }
-#endif
}
void mark_rodata_ro(void)
--
1.8.3.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
2022-04-12 9:07 ` Guanghui Feng
@ 2022-04-13 16:53 ` Catalin Marinas
-1 siblings, 0 replies; 6+ messages in thread
From: Catalin Marinas @ 2022-04-13 16:53 UTC (permalink / raw)
To: Guanghui Feng; +Cc: will, linux-arm-kernel, linux-kernel, baolin.wang
On Tue, Apr 12, 2022 at 05:07:56PM +0800, Guanghui Feng wrote:
> There are many changes and discussions:
> commit 031495635b46
> commit 1a8e1cef7603
> commit 8424ecdde7df
> commit 0a30c53573b0
> commit 2687275a5843
>
> When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
> mem_map will use non block/section mapping(for crashkernel requires to shrink
> the region in page granularity). But it will degrade performance when doing
> larging continuous mem access in kernel(memcpy/memmove, etc).
>
> This patch firstly do block/section mapping at mem_map, reserve crashkernel
> memory. And then walking pagetable to split block/section mapping
> to non block/section mapping [only] for crashkernel mem. We will accelerate
> mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
> conspicuously on some platform with this optimization.
Do you actually have some real world use-cases where this improvement
matters? I don't deny that large memcpy over the kernel linear map may
be slightly faster but where does this really matter?
> +static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
> + unsigned long end, phys_addr_t phys,
> + pgprot_t prot,
> + phys_addr_t (*pgtable_alloc)(int), int flags)
> +{
> + phys_addr_t map_offset;
> + unsigned long next;
> + pmd_t *pmdp;
> + pmdval_t pmdval;
> +
> + pmdp = pmd_offset(pudp, addr);
> + do {
> + next = pmd_addr_end(addr, end);
> + if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
> + phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
> + pmd_clear(pmdp);
> + pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
> + if (flags & NO_EXEC_MAPPINGS)
> + pmdval |= PMD_TABLE_PXN;
> + __pmd_populate(pmdp, pte_phys, pmdval);
> + flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
The architecture requires us to do a break-before-make here, so
pmd_clear(), TLBI, __pmd_populate() - in this order. And that's where it
gets tricky, if the kernel happens to access this pmd range while it is
unmapped, you'd get a translation fault.
--
Catalin
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
@ 2022-04-13 16:53 ` Catalin Marinas
0 siblings, 0 replies; 6+ messages in thread
From: Catalin Marinas @ 2022-04-13 16:53 UTC (permalink / raw)
To: Guanghui Feng; +Cc: will, linux-arm-kernel, linux-kernel, baolin.wang
On Tue, Apr 12, 2022 at 05:07:56PM +0800, Guanghui Feng wrote:
> There are many changes and discussions:
> commit 031495635b46
> commit 1a8e1cef7603
> commit 8424ecdde7df
> commit 0a30c53573b0
> commit 2687275a5843
>
> When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
> mem_map will use non block/section mapping(for crashkernel requires to shrink
> the region in page granularity). But it will degrade performance when doing
> larging continuous mem access in kernel(memcpy/memmove, etc).
>
> This patch firstly do block/section mapping at mem_map, reserve crashkernel
> memory. And then walking pagetable to split block/section mapping
> to non block/section mapping [only] for crashkernel mem. We will accelerate
> mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
> conspicuously on some platform with this optimization.
Do you actually have some real world use-cases where this improvement
matters? I don't deny that large memcpy over the kernel linear map may
be slightly faster but where does this really matter?
> +static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
> + unsigned long end, phys_addr_t phys,
> + pgprot_t prot,
> + phys_addr_t (*pgtable_alloc)(int), int flags)
> +{
> + phys_addr_t map_offset;
> + unsigned long next;
> + pmd_t *pmdp;
> + pmdval_t pmdval;
> +
> + pmdp = pmd_offset(pudp, addr);
> + do {
> + next = pmd_addr_end(addr, end);
> + if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
> + phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
> + pmd_clear(pmdp);
> + pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
> + if (flags & NO_EXEC_MAPPINGS)
> + pmdval |= PMD_TABLE_PXN;
> + __pmd_populate(pmdp, pte_phys, pmdval);
> + flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
The architecture requires us to do a break-before-make here, so
pmd_clear(), TLBI, __pmd_populate() - in this order. And that's where it
gets tricky, if the kernel happens to access this pmd range while it is
unmapped, you'd get a translation fault.
--
Catalin
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
2022-04-13 16:53 ` Catalin Marinas
@ 2022-04-14 3:43 ` guanghui.fgh
-1 siblings, 0 replies; 6+ messages in thread
From: guanghui.fgh @ 2022-04-14 3:43 UTC (permalink / raw)
To: Catalin Marinas; +Cc: will, linux-arm-kernel, linux-kernel, baolin.wang
Thanks for your response!
在 2022/4/14 0:53, Catalin Marinas 写道:
> On Tue, Apr 12, 2022 at 05:07:56PM +0800, Guanghui Feng wrote:
>> There are many changes and discussions:
>> commit 031495635b46
>> commit 1a8e1cef7603
>> commit 8424ecdde7df
>> commit 0a30c53573b0
>> commit 2687275a5843
>>
>> When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
>> mem_map will use non block/section mapping(for crashkernel requires to shrink
>> the region in page granularity). But it will degrade performance when doing
>> larging continuous mem access in kernel(memcpy/memmove, etc).
>>
>> This patch firstly do block/section mapping at mem_map, reserve crashkernel
>> memory. And then walking pagetable to split block/section mapping
>> to non block/section mapping [only] for crashkernel mem. We will accelerate
>> mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
>> conspicuously on some platform with this optimization.
> Do you actually have some real world use-cases where this improvement
> matters? I don't deny that large memcpy over the kernel linear map may
> be slightly faster but where does this really matter?
When doing fio test, there may be about 10-20% performance gap.
The test method:
1.prepare env with shell script
set -x
modprobe -r brd
modprobe brd rd_nr=1 rd_size=134217728
dmsetup remove_all
wipefs -a --force /dev/ram0
mkfs -t ext4 -E lazy_itable_init=0,lazy_journal_init=0 -q -F /dev/ram0
mkdir -p /fs/ram0
mount -t ext4 /dev/ram0 /fs/ram0
#sed -i s/scan_lvs = 1/scan_lvs = 1/ /etc/lvm/lvm.conf
2.prepare fio env with setting file in [x.fio]:
[global]
bs=4k
ioengine=psync
iodepth=128
size=8G
direct=1
runtime=30
invalidate=1
#fallocate=native
group_reporting
thread=1
time_based=1
rw=read
directory=/fs/ram0
#filename=/dev/ram0
numjobs=1
[task_0]
cpus_allowed=16
stonewall=1
3.running fio testcase:
sudo fio x.fio
-----------------------------------------------------
At the same time, I have test memcpy in the double envs
(block/section mapping + non block/section mapping):
1.alloc many continuous pages(src/dst: 10000 * 2^10 bytes):
alloc_pages(GFP_KERNEL, 10)
2.memcpy for src to dst
>> +static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
>> + unsigned long end, phys_addr_t phys,
>> + pgprot_t prot,
>> + phys_addr_t (*pgtable_alloc)(int), int flags)
>> +{
>> + phys_addr_t map_offset;
>> + unsigned long next;
>> + pmd_t *pmdp;
>> + pmdval_t pmdval;
>> +
>> + pmdp = pmd_offset(pudp, addr);
>> + do {
>> + next = pmd_addr_end(addr, end);
>> + if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
>> + phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
>> + pmd_clear(pmdp);
>> + pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
>> + if (flags & NO_EXEC_MAPPINGS)
>> + pmdval |= PMD_TABLE_PXN;
>> + __pmd_populate(pmdp, pte_phys, pmdval);
>> + flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> The architecture requires us to do a break-before-make here, so
> pmd_clear(), TLBI, __pmd_populate() - in this order. And that's where it
> gets tricky, if the kernel happens to access this pmd range while it is
> unmapped, you'd get a translation fault.
OK, Thanks.
+ if (map_offset)
+ alloc_init_cont_pte(pmdp, addr & PMD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+
+ map_offset = addr - (addr & PUD_MASK);
+ if (map_offset)
+ alloc_init_cont_pmd(pudp, addr & PUD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
Sorry，There is a defect. When rebuilding normal pmd/pte(out of crashkernel mem),
the flags should strip NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS on some scenes:
!(can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE)).
So we will use as many as possible block/section mapping.
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel
@ 2022-04-14 3:43 ` guanghui.fgh
0 siblings, 0 replies; 6+ messages in thread
From: guanghui.fgh @ 2022-04-14 3:43 UTC (permalink / raw)
To: Catalin Marinas; +Cc: will, linux-arm-kernel, linux-kernel, baolin.wang
Thanks for your response!
在 2022/4/14 0:53, Catalin Marinas 写道:
> On Tue, Apr 12, 2022 at 05:07:56PM +0800, Guanghui Feng wrote:
>> There are many changes and discussions:
>> commit 031495635b46
>> commit 1a8e1cef7603
>> commit 8424ecdde7df
>> commit 0a30c53573b0
>> commit 2687275a5843
>>
>> When using DMA/DMA32 zone and crashkernel, disable rodata full and kfence,
>> mem_map will use non block/section mapping(for crashkernel requires to shrink
>> the region in page granularity). But it will degrade performance when doing
>> larging continuous mem access in kernel(memcpy/memmove, etc).
>>
>> This patch firstly do block/section mapping at mem_map, reserve crashkernel
>> memory. And then walking pagetable to split block/section mapping
>> to non block/section mapping [only] for crashkernel mem. We will accelerate
>> mem access about 10-20% performance improvement, and reduce the cpu dTLB miss
>> conspicuously on some platform with this optimization.
> Do you actually have some real world use-cases where this improvement
> matters? I don't deny that large memcpy over the kernel linear map may
> be slightly faster but where does this really matter?
When doing fio test, there may be about 10-20% performance gap.
The test method:
1.prepare env with shell script
set -x
modprobe -r brd
modprobe brd rd_nr=1 rd_size=134217728
dmsetup remove_all
wipefs -a --force /dev/ram0
mkfs -t ext4 -E lazy_itable_init=0,lazy_journal_init=0 -q -F /dev/ram0
mkdir -p /fs/ram0
mount -t ext4 /dev/ram0 /fs/ram0
#sed -i s/scan_lvs = 1/scan_lvs = 1/ /etc/lvm/lvm.conf
2.prepare fio env with setting file in [x.fio]:
[global]
bs=4k
ioengine=psync
iodepth=128
size=8G
direct=1
runtime=30
invalidate=1
#fallocate=native
group_reporting
thread=1
time_based=1
rw=read
directory=/fs/ram0
#filename=/dev/ram0
numjobs=1
[task_0]
cpus_allowed=16
stonewall=1
3.running fio testcase:
sudo fio x.fio
-----------------------------------------------------
At the same time, I have test memcpy in the double envs
(block/section mapping + non block/section mapping):
1.alloc many continuous pages(src/dst: 10000 * 2^10 bytes):
alloc_pages(GFP_KERNEL, 10)
2.memcpy for src to dst
>> +static void init_crashkernel_pmd(pud_t *pudp, unsigned long addr,
>> + unsigned long end, phys_addr_t phys,
>> + pgprot_t prot,
>> + phys_addr_t (*pgtable_alloc)(int), int flags)
>> +{
>> + phys_addr_t map_offset;
>> + unsigned long next;
>> + pmd_t *pmdp;
>> + pmdval_t pmdval;
>> +
>> + pmdp = pmd_offset(pudp, addr);
>> + do {
>> + next = pmd_addr_end(addr, end);
>> + if (!pmd_none(*pmdp) && pmd_sect(*pmdp)) {
>> + phys_addr_t pte_phys = pgtable_alloc(PAGE_SHIFT);
>> + pmd_clear(pmdp);
>> + pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
>> + if (flags & NO_EXEC_MAPPINGS)
>> + pmdval |= PMD_TABLE_PXN;
>> + __pmd_populate(pmdp, pte_phys, pmdval);
>> + flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
> The architecture requires us to do a break-before-make here, so
> pmd_clear(), TLBI, __pmd_populate() - in this order. And that's where it
> gets tricky, if the kernel happens to access this pmd range while it is
> unmapped, you'd get a translation fault.
OK, Thanks.
+ if (map_offset)
+ alloc_init_cont_pte(pmdp, addr & PMD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
+
+ map_offset = addr - (addr & PUD_MASK);
+ if (map_offset)
+ alloc_init_cont_pmd(pudp, addr & PUD_MASK, addr,
+ phys - map_offset, prot,
+ pgtable_alloc, flags);
+
Sorry，There is a defect. When rebuilding normal pmd/pte(out of crashkernel mem),
the flags should strip NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS on some scenes:
!(can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE)).
So we will use as many as possible block/section mapping.
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2022-04-14 3:44 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-04-12 9:07 [PATCH RFC v1] arm64: mm: change mem_map to use block/section mapping with crashkernel Guanghui Feng
2022-04-12 9:07 ` Guanghui Feng
2022-04-13 16:53 ` Catalin Marinas
2022-04-13 16:53 ` Catalin Marinas
2022-04-14 3:43 ` guanghui.fgh
2022-04-14 3:43 ` guanghui.fgh
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.