mm/vmalloc: cleanup after hugepage series
Subsystems (9)
Nicholas Piggin
reviewercover mm/vmalloc: cleanup after hugepage series
Christoph pointed out some overdue cleanups required after the huge page series, and I had some other comment and warning changes.
Thanks,
Nick
Nicholas Piggin (5):
mm/vmalloc: remove map_kernel_range kernel/dma: remove unnecessary unmap_kernel_range powerpc/xive: remove unnecessary unmap_kernel_range mm/vmalloc: remove unmap_kernel_range mm/vmalloc: improve allocation failure error messages
Documentation/core-api/cachetlb.rst | 4 +- arch/arm64/mm/init.c | 2 +- arch/powerpc/kernel/isa-bridge.c | 4 +- arch/powerpc/kernel/pci_64.c | 2 +- arch/powerpc/mm/ioremap.c | 2 +- arch/powerpc/sysdev/xive/common.c | 4 - drivers/pci/pci.c | 2 +- include/linux/vmalloc.h | 19 +--- kernel/dma/remap.c | 1 - mm/internal.h | 7 ++ mm/percpu-vm.c | 7 +- mm/vmalloc.c | 164 ++++++++++++++-------------- 12 files changed, 104 insertions(+), 114 deletions(-)
Signature · 1 line
2.23.0
Nicholas Piggin
reviewerPATCH 1/5 mm/vmalloc: remove map_kernel_range
This is a shim around vmap_pages_range, get rid of it.
Move the main API comment from the _noflush variant to the normal variant, and make _noflush internal to mm/.
--- Documentation/core-api/cachetlb.rst | 2 +- include/linux/vmalloc.h | 11 ----- mm/internal.h | 6 +++ mm/percpu-vm.c | 5 ++- mm/vmalloc.c | 65 +++++++++++++---------------- 5 files changed, 38 insertions(+), 51 deletions(-)
Documentation/core-api/cachetlb.rst +1 -1
@@ -213,7 +213,7 @@ Here are the routines, one by one: there will be no entries in the cache for the kernel address space for virtual addresses in the range 'start' to 'end-1'. - The first of these two routines is invoked after map_kernel_range() + The first of these two routines is invoked after vmap_range() has installed the page table entries. The second is invoked before unmap_kernel_range() deletes the page table entries.
include/linux/vmalloc.h +0 -11
@@ -217,10 +217,6 @@ static inline bool is_vm_area_hugepages(const void *addr)int vmap_range (unsigned long addr,unsigned long end,phys_addr_t phys_addr,pgprot_t prot,unsigned int max_page_shift); -extern int map_kernel_range_noflush (unsigned long start,unsigned long size, -pgprot_t prot,struct page **pages); -int map_kernel_range (unsigned long start,unsigned long size,pgprot_t prot, -struct page **pages);extern void unmap_kernel_range_noflush (unsigned long addr,unsigned long size);extern void unmap_kernel_range (unsigned long addr,unsigned long size);static inline void set_vm_flush_reset_perms (void *addr)
@@ -232,13 +228,6 @@ static inline void set_vm_flush_reset_perms(void *addr) }#else -static inline int -map_kernel_range_noflush (unsigned long start,unsigned long size, -pgprot_t prot,struct page **pages) -{ -return size >>PAGE_SHIFT ; -} -#define map_kernel_range map_kernel_range_noflushstatic inline void unmap_kernel_range_noflush (unsigned long addr,unsigned long size) {
mm/internal.h +6 -0
@@ -623,4 +623,10 @@ struct migration_target_control { gfp_t gfp_mask; }; +/* +* mm/vmalloc.c +*/ +int vmap_pages_range_noflush (unsigned long addr,unsigned long end, +pgprot_t prot,struct page **pages,unsigned int page_shift); +#endif /* __MM_INTERNAL_H */
mm/percpu-vm.c +3 -2
@@ -8,6 +8,7 @@* Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ +#include "internal.h" static struct page *pcpu_chunk_page (struct pcpu_chunk *chunk,unsigned int cpu,int page_idx)
@@ -192,8 +193,8 @@ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,static int __pcpu_map_pages (unsigned long addr,struct page **pages,int nr_pages) { -return map_kernel_range_noflush (addr, nr_pages <<PAGE_SHIFT , -PAGE_KERNEL , pages); +return vmap_pages_range_noflush (addr, addr + (nr_pages <<PAGE_SHIFT ), +PAGE_KERNEL , pages,PAGE_SHIFT ); }/**
mm/vmalloc.c +28 -37
107 lines not on this page · raw message
Signature · 1 line
2.23.0
Re: [PATCH 1/5] mm/vmalloc: remove map_kernel_range
Looks good,
Nicholas Piggin
reviewerPATCH 2/5 kernel/dma: remove unnecessary unmap_kernel_range
In reply to Nicholas Pigginvunmap will remove ptes.
--- kernel/dma/remap.c | 1 - 1 file changed, 1 deletion(-)
kernel/dma/remap.c +0 -1
@@ -66,6 +66,5 @@ void dma_common_free_remap(void *cpu_addr, size_t size)return ; } -unmap_kernel_range ((unsigned long )cpu_addr,PAGE_ALIGN (size));vunmap (cpu_addr); }
Signature · 1 line
2.23.0
Re: [PATCH 2/5] kernel/dma: remove unnecessary unmap_kernel_range
Quoted 1 line · Nicholas Piggin
vunmap will remove ptes.
Looks good,
Re: [PATCH 2/5] kernel/dma: remove unnecessary unmap_kernel_range
In reply to Nicholas PigginQuoted 1 line · Nicholas Piggin
vunmap will remove ptes.
Should there be some ASSERT after the vunmap to make sure that is the case?
Quoted 28 lines
Cc Christoph Hellwig <[email protected]>Cc Marek Szyprowski <[email protected]>Cc Robin Murphy <[email protected]>Signed-off-by Nicholas Piggin <[email protected]>--- kernel/dma/remap.c | 1 - 1 file changed, 1 deletion(-)kernel/dma/remap.c +0
-1@@ -66,6 +66,5 @@ void dma_common_free_remap(void *cpu_addr, size_t size)return ; } -unmap_kernel_range ((unsigned long )cpu_addr,PAGE_ALIGN (size));vunmap (cpu_addr); }Signature · 6 lines
2.23.0 _______________________________________________ iommu mailing list [email protected] https://lists.linuxfoundation.org/mailman/listinfo/iommu
Re: [PATCH 2/5] kernel/dma: remove unnecessary unmap_kernel_range
Quoted 5 lines · Konrad Rzeszutek Wilk
Quoted 1 line · Nicholas Piggin
vunmap will remove ptes.
Should there be some ASSERT after the vunmap to make sure that is the case?
Not really. removing the PTEs is the whole point of vunmap. Everything else is just house keeping.
Nicholas Piggin
reviewerRe: [PATCH 2/5] kernel/dma: remove unnecessary unmap_kernel_range
Excerpts from Christoph Hellwig's message of January 27, 2021 5:10 pm:
Quoted 9 lines · Konrad Rzeszutek Wilk
Quoted 5 lines · Nicholas Piggin
Quoted 1 line
vunmap will remove ptes.
Should there be some ASSERT after the vunmap to make sure that is the case?
Not really. removing the PTEs is the whole point of vunmap. Everything else is just house keeping.
Agree. I did double check this and wrote a quick test to check ptes were there before the vunmap and cleared after, just to make sure I didn't make a silly mistake with the patch. But in general drivers should be able to trust code behind the API call will do the right thing. Such assertions should go in the vunmap() implementation as appropriate.
Thanks,
Nick
Nicholas Piggin
reviewerPATCH 3/5 powerpc/xive: remove unnecessary unmap_kernel_range
In reply to Nicholas Pigginiounmap will remove ptes.
--- arch/powerpc/sysdev/xive/common.c | 4 ---- 1 file changed, 4 deletions(-)
arch/powerpc/sysdev/xive/common.c +0 -4
@@ -959,16 +959,12 @@ EXPORT_SYMBOL_GPL(is_xive_irq);void xive_cleanup_irq_data (struct xive_irq_data *xd) {if (xd->eoi_mmio) { -unmap_kernel_range ((unsigned long )xd->eoi_mmio, -1u << xd->esb_shift);iounmap (xd->eoi_mmio);if (xd->eoi_mmio == xd->trig_mmio) xd->trig_mmio =NULL ; xd->eoi_mmio =NULL ; }if (xd->trig_mmio) { -unmap_kernel_range ((unsigned long )xd->trig_mmio, -1u << xd->esb_shift);iounmap (xd->trig_mmio); xd->trig_mmio =NULL ; }
Signature · 1 line
2.23.0
Re: [PATCH 3/5] powerpc/xive: remove unnecessary unmap_kernel_range
Quoted 1 line · Nicholas Piggin
iounmap will remove ptes.
Looks good,
Re: [PATCH 3/5] powerpc/xive: remove unnecessary unmap_kernel_range
In reply to Nicholas PigginQuoted 5 lines · Nicholas Piggin
iounmap will remove ptes.
Cc "Cédric Le Goater" <[email protected]>Signed-off-by Nicholas Piggin <[email protected]>
Looks good.
Thanks,
C.
Quoted 26 lines
--- arch/powerpc/sysdev/xive/common.c | 4 ---- 1 file changed, 4 deletions(-)arch/powerpc/sysdev/xive/common.c +0
-4@@ -959,16 +959,12 @@ EXPORT_SYMBOL_GPL(is_xive_irq);void xive_cleanup_irq_data (struct xive_irq_data *xd) {if (xd->eoi_mmio) { -unmap_kernel_range ((unsigned long )xd->eoi_mmio, -1u << xd->esb_shift);iounmap (xd->eoi_mmio);if (xd->eoi_mmio == xd->trig_mmio) xd->trig_mmio =NULL ; xd->eoi_mmio =NULL ; }if (xd->trig_mmio) { -unmap_kernel_range ((unsigned long )xd->trig_mmio, -1u << xd->esb_shift);iounmap (xd->trig_mmio); xd->trig_mmio =NULL ; }
Nicholas Piggin
reviewerPATCH 4/5 mm/vmalloc: remove unmap_kernel_range
In reply to Nicholas PigginThis is a shim around vunmap_range, get rid of it.
Move the main API comment from the _noflush variant to the normal variant, and make _noflush internal to mm/.
--- Documentation/core-api/cachetlb.rst | 2 +- arch/arm64/mm/init.c | 2 +- arch/powerpc/kernel/isa-bridge.c | 4 +- arch/powerpc/kernel/pci_64.c | 2 +- arch/powerpc/mm/ioremap.c | 2 +- drivers/pci/pci.c | 2 +- include/linux/vmalloc.h | 8 +--- mm/internal.h | 1 + mm/percpu-vm.c | 2 +- mm/vmalloc.c | 59 ++++++++++++++--------------- 10 files changed, 38 insertions(+), 46 deletions(-)
Documentation/core-api/cachetlb.rst +1 -1
@@ -215,7 +215,7 @@ Here are the routines, one by one: The first of these two routines is invoked after vmap_range() has installed the page table entries. The second is invoked - before unmap_kernel_range() deletes the page table entries. + before vunmap_range() deletes the page table entries. There exists another whole class of cpu cache issues which currently require a whole different set of interfaces to handle properly.
arch/arm64/mm/init.c +1 -1
@@ -498,7 +498,7 @@ void free_initmem(void)* prevents the region from being reused for kernel modules, which * is not supported by kallsyms. */ -unmap_kernel_range ((u64 )__init_begin, (u64)(__init_end - __init_begin)); +vunmap_range ((u64 )__init_begin, (u64 )__init_end); }void dump_mem_limit (void )
arch/powerpc/kernel/isa-bridge.c +2 -2
@@ -48,7 +48,7 @@ static void remap_isa_base(phys_addr_t pa, unsigned long size)if (slab_is_available ()) {if (ioremap_page_range (ISA_IO_BASE ,ISA_IO_BASE + size, pa,pgprot_noncached (PAGE_KERNEL ))) -unmap_kernel_range (ISA_IO_BASE , size); +vunmap_range (ISA_IO_BASE ,ISA_IO_BASE + size); }else {early_ioremap_range (ISA_IO_BASE , pa, size,pgprot_noncached (PAGE_KERNEL ));
@@ -311,7 +311,7 @@ static void isa_bridge_remove(void) isa_bridge_pcidev =NULL ;/* Unmap the ISA area */ -unmap_kernel_range (ISA_IO_BASE ,0x10000 ); +vunmap_range (ISA_IO_BASE ,ISA_IO_BASE +0x10000 ); }/**
arch/powerpc/kernel/pci_64.c +1 -1
@@ -140,7 +140,7 @@ void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size) addr = (unsigned long )area->addr;if (ioremap_page_range (addr, addr + size, paddr,pgprot_noncached (PAGE_KERNEL ))) { -unmap_kernel_range (addr, size); +vunmap_range (addr, addr + size);return NULL ; }
arch/powerpc/mm/ioremap.c +1 -1
@@ -93,7 +93,7 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,if (!ret)return (void __iomem *)area->addr + offset; -unmap_kernel_range (va, size); +vunmap_range (va, va + size);free_vm_area (area);return NULL ;
drivers/pci/pci.c +1 -1
@@ -4107,7 +4107,7 @@ void pci_unmap_iospace(struct resource *res)#if defined(PCI_IOBASE ) && defined(CONFIG_MMU )unsigned long vaddr = (unsigned long )PCI_IOBASE + res->start; -unmap_kernel_range (vaddr,resource_size (res)); +vunmap_range (vaddr, vaddr +resource_size (res));#endif }EXPORT_SYMBOL (pci_unmap_iospace);
include/linux/vmalloc.h +1 -7
@@ -217,8 +217,7 @@ static inline bool is_vm_area_hugepages(const void *addr)int vmap_range (unsigned long addr,unsigned long end,phys_addr_t phys_addr,pgprot_t prot,unsigned int max_page_shift); -extern void unmap_kernel_range_noflush (unsigned long addr,unsigned long size); -extern void unmap_kernel_range (unsigned long addr,unsigned long size); +void vunmap_range (unsigned long addr,unsigned long end);static inline void set_vm_flush_reset_perms (void *addr) {struct vm_struct *vm =find_vm_area (addr);
@@ -228,11 +227,6 @@ static inline void set_vm_flush_reset_perms(void *addr) }#else -static inline void -unmap_kernel_range_noflush (unsigned long addr,unsigned long size) -{ -} -#define unmap_kernel_range unmap_kernel_range_noflushstatic inline void set_vm_flush_reset_perms (void *addr) { }
mm/internal.h +1 -0
@@ -628,5 +628,6 @@ struct migration_target_control {*/ int vmap_pages_range_noflush (unsigned long addr,unsigned long end,pgprot_t prot,struct page **pages,unsigned int page_shift); +void vunmap_range_noflush (unsigned long start,unsigned long end);#endif /* __MM_INTERNAL_H */
mm/percpu-vm.c +1 -1
@@ -134,7 +134,7 @@ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,static void __pcpu_unmap_pages (unsigned long addr,int nr_pages) { -unmap_kernel_range_noflush (addr, nr_pages <<PAGE_SHIFT ); +vunmap_range_noflush (addr, addr + (nr_pages <<PAGE_SHIFT )); }/**
mm/vmalloc.c +28 -31
93 lines not on this page · raw message
Signature · 1 line
2.23.0
Re: [PATCH 4/5] mm/vmalloc: remove unmap_kernel_range
Quoted 4 lines · Nicholas Piggin
This is a shim around
vunmap_range, get rid of it.Move the main API comment from the
_noflushvariant to the normal variant, and make_noflushinternal tomm/.
Looks good,
Nicholas Piggin
reviewerPATCH 5/5 mm/vmalloc: improve allocation failure error messages
In reply to Nicholas PigginThere are several reasons why a vmalloc can fail, virtual space exhausted, page array allocation failure, page allocation failure, and kernel page table allocation failure.
Add distinct warning messages for the main causes of failure, with some added information like page order or allocation size where applicable.
--- mm/vmalloc.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-)
mm/vmalloc.c +28 -12
@@ -2790,6 +2790,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,if (!pages) {free_vm_area (area); +warn_alloc (gfp_mask,NULL , +"vmalloc size %lu allocation failure: " +"page array size %lu allocation failed" , + area->nr_pages *PAGE_SIZE , array_size);return NULL ; }
@@ -2813,6 +2817,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,/* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i;atomic_long_add (area->nr_pages, &nr_vmalloc_pages); +warn_alloc (gfp_mask,NULL , +"vmalloc size %lu allocation failure: " +"page order %u allocation failed" , + area->nr_pages *PAGE_SIZE , page_order); goto fail; }
@@ -2824,15 +2832,17 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, }atomic_long_add (area->nr_pages, &nr_vmalloc_pages); -if (vmap_pages_range (addr, addr + size, prot, pages, page_shift) <0 ) +if (vmap_pages_range (addr, addr + size, prot, pages, page_shift) <0 ) { +warn_alloc (gfp_mask,NULL , +"vmalloc size %lu allocation failure: " +"failed to map pages" , + area->nr_pages *PAGE_SIZE ); goto fail; + }return area->addr; fail: -warn_alloc (gfp_mask,NULL , -"vmalloc: allocation failure, allocated %ld of %ld bytes" , - (area->nr_pages*PAGE_SIZE ), size);__vfree (area->addr);return NULL ; }
@@ -2866,8 +2876,15 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,unsigned long real_align = align;unsigned int shift =PAGE_SHIFT ; -if (!size || (size >>PAGE_SHIFT ) >totalram_pages ()) - goto fail; +if (WARN_ON_ONCE (!size)) +return NULL ; + +if ((size >>PAGE_SHIFT ) >totalram_pages ()) { +warn_alloc (gfp_mask,NULL , +"vmalloc size %lu allocation failure: " +"exceeds total pages" , real_size); +return NULL ; + }if (vmap_allow_huge && !(vm_flags &VM_NO_HUGE_VMAP ) &&arch_vmap_pmd_supported (prot)) {
@@ -2894,8 +2911,12 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, size =PAGE_ALIGN (size); area =__get_vm_area_node (size, align,VM_ALLOC |VM_UNINITIALIZED | vm_flags, start, end, node, gfp_mask, caller); -if (!area) +if (!area) { +warn_alloc (gfp_mask,NULL , +"vmalloc size %lu allocation failure: " +"vm_struct allocation failed" , real_size); goto fail; + } addr =__vmalloc_area_node (area, gfp_mask, prot, shift, node);if (!addr)
@@ -2920,11 +2941,6 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, goto again; } -if (!area) { -/* Warn for area allocation, page allocations already warn */ -warn_alloc (gfp_mask,NULL , -"vmalloc: allocation failure: %lu bytes" , real_size); - }return NULL ; }
Signature · 1 line
2.23.0
Re: [PATCH 5/5] mm/vmalloc: improve allocation failure error messages
Quoted 9 lines · Nicholas Piggin
There are several reasons why a vmalloc can fail, virtual space exhausted, page array allocation failure, page allocation failure, and kernel page table allocation failure.
Add distinct warning messages for the main causes of failure, with some added information like page order or allocation size where applicable.
Signed-off-by Nicholas Piggin <[email protected]>
Looks good,