decruft the vmalloc API v2
Subsystems (49)
Hi all,
Peter noticed that with some dumb luck you can toast the kernel address space with exported vmalloc symbols.
I used this as an opportunity to decruft the vmalloc.c API and make it much more systematic. This also removes any chance to create vmalloc mappings outside the designated areas or using executable permissions from modules. Besides that it removes more than 300 lines of code.
A git tree is also available here:
git://git.infradead.org/users/hch/misc.git sanitize-vmalloc-api.2
Gitweb:
http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/sanitize-vmalloc-api.2
Changes since v1:
- implement pgprot_nx for arm64 (Mark Rutland)
- fix a patch description
- properly pass pgprot to vmap in ion
- add a new patch to fix vmap() API misuse
- fix a vmap argument in x86
- two more vmalloc cleanups
- cleanup use of the unmap_kernel_range API
- rename ioremap_pbh to ioremap_phb
PATCH 1/29 x86/hyperv: use vmalloc_exec for the hypercall page
Use the designated helper for allocating executable kernel memory, and remove the now unused PAGE_KERNEL_RX define.
--- arch/x86/hyperv/hv_init.c | 2 +- arch/x86/include/asm/pgtable_types.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-)
arch/x86/hyperv/hv_init.c +1 -1
@@ -355,7 +355,7 @@ void __init hyperv_init(void) guest_id =generate_guest_id (0 ,LINUX_VERSION_CODE ,0 );wrmsrl (HV_X64_MSR_GUEST_OS_ID , guest_id); - hv_hypercall_pg =__vmalloc (PAGE_SIZE ,GFP_KERNEL ,PAGE_KERNEL_RX ); + hv_hypercall_pg =vmalloc_exec (PAGE_SIZE );if (hv_hypercall_pg ==NULL ) {wrmsrl (HV_X64_MSR_GUEST_OS_ID ,0 ); goto remove_cpuhp_state;
arch/x86/include/asm/pgtable_types.h +0 -2
@@ -194,7 +194,6 @@ enum page_cache_mode {#define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0)#define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC)#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) -#define __PAGE_KERNEL_RX (__PP| 0| 0|___A| 0|___D| 0|___G)#define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC)#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G)#define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G)
@@ -220,7 +219,6 @@ enum page_cache_mode {#define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC)#define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC)#define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) -#define PAGE_KERNEL_RX __pgprot_mask(__PAGE_KERNEL_RX | _ENC)#define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC)#define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC)#define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
Signature · 1 line
2.25.1
PATCH 2/29 x86: fix vmap arguments in map_irq_stack
In reply to Christoph Hellwigvmap does not take a gfp_t, the flags argument is for VM_* flags.
--- arch/x86/kernel/irq_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/irq_64.c +1 -1
@@ -43,7 +43,7 @@ static int map_irq_stack(unsigned int cpu) pages[i] =pfn_to_page (pa >>PAGE_SHIFT ); } - va =vmap (pages,IRQ_STACK_SIZE /PAGE_SIZE ,GFP_KERNEL ,PAGE_KERNEL ); + va =vmap (pages,IRQ_STACK_SIZE /PAGE_SIZE ,VM_MAP ,PAGE_KERNEL );if (!va)return -ENOMEM ;
Signature · 1 line
2.25.1
PATCH 3/29 staging: android: ion: use vmap instead of vm_map_ram
In reply to Christoph Hellwigvm_map_ram can keep mappings around after the vm_unmap_ram. Using that with non-PAGE_KERNEL mappings can lead to all kinds of aliasing issues.
--- drivers/staging/android/ion/ion_heap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/staging/android/ion/ion_heap.c +2 -2
@@ -99,12 +99,12 @@ int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,static int ion_heap_clear_pages (struct page **pages,int num,pgprot_t pgprot) { -void *addr =vm_map_ram (pages, num,-1 , pgprot); +void *addr =vmap (pages, num,VM_MAP , pgprot);if (!addr)return -ENOMEM ;memset (addr,0 ,PAGE_SIZE * num); -vm_unmap_ram (addr, num); +vunmap (addr);return 0 ; }
Signature · 1 line
2.25.1
PATCH 4/29 staging: media: ipu3: use vmap instead of reimplementing it
In reply to Christoph HellwigJust use vmap instead of messing with vmalloc internals.
--- drivers/staging/media/ipu3/ipu3-css-pool.h | 4 +-- drivers/staging/media/ipu3/ipu3-dmamap.c | 30 ++++++---------------- 2 files changed, 9 insertions(+), 25 deletions(-)
drivers/staging/media/ipu3/ipu3-css-pool.h +1 -3
@@ -15,14 +15,12 @@ struct imgu_device;* @size: size of the buffer in bytes. * @vaddr: kernel virtual address. * @daddr: iova dma address to access IPU3. -* @vma: private, a pointer to &struct vm_struct, -* used for imgu_dmamap_free. */ struct imgu_css_map {size_t size;void *vaddr;dma_addr_t daddr; -struct vm_struct *vma; +struct page **pages; };/**
drivers/staging/media/ipu3/ipu3-dmamap.c +8 -22
@@ -96,6 +96,7 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map,unsigned long shift =iova_shift (&imgu->iova_domain);struct device *dev = &imgu->pci_dev->dev;size_t size =PAGE_ALIGN (len); +int count = size >>PAGE_SHIFT ;struct page **pages;dma_addr_t iovaddr;struct iova *iova;
@@ -114,7 +115,7 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map,/* Call IOMMU driver to setup pgt */ iovaddr =iova_dma_addr (&imgu->iova_domain, iova); -for (i =0 ; i < size /PAGE_SIZE ; ++i) { +for (i =0 ; i < count; ++i) { rval =imgu_mmu_map (imgu->mmu, iovaddr,page_to_phys (pages[i]),PAGE_SIZE );if (rval)
@@ -123,33 +124,23 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map, iovaddr +=PAGE_SIZE ; } -/* Now grab a virtual region */ - map->vma =__get_vm_area (size,VM_USERMAP ,VMALLOC_START ,VMALLOC_END ); -if (!map->vma) + map->vaddr =vmap (pages, count,VM_USERMAP ,PAGE_KERNEL ); +if (!map->vaddr) goto out_unmap; - map->vma->pages = pages; -/* And map it in KVA */ -if (map_vm_area (map->vma,PAGE_KERNEL , pages)) - goto out_vunmap; - + map->pages = pages; map->size = size; map->daddr =iova_dma_addr (&imgu->iova_domain, iova); - map->vaddr = map->vma->addr;dev_dbg (dev,"%s: allocated %zu @ IOVA %pad @ VA %p\n" , __func__, - size, &map->daddr, map->vma->addr); - -return map->vma->addr; + size, &map->daddr, map->vaddr); -out_vunmap: -vunmap (map->vma->addr); +return map->vaddr; out_unmap:imgu_dmamap_free_buffer (pages, size);imgu_mmu_unmap (imgu->mmu,iova_dma_addr (&imgu->iova_domain, iova), i *PAGE_SIZE ); - map->vma =NULL ; out_free_iova:__free_iova (&imgu->iova_domain, iova);
@@ -177,8 +168,6 @@ void imgu_dmamap_unmap(struct imgu_device *imgu, struct imgu_css_map *map)*/ void imgu_dmamap_free (struct imgu_device *imgu,struct imgu_css_map *map) { -struct vm_struct *area = map->vma; -dev_dbg (&imgu->pci_dev->dev,"%s: freeing %zu @ IOVA %pad @ VA %p\n" , __func__, map->size, &map->daddr, map->vaddr);
@@ -187,11 +176,8 @@ void imgu_dmamap_free(struct imgu_device *imgu, struct imgu_css_map *map)imgu_dmamap_unmap (imgu, map); -if (WARN_ON (!area) ||WARN_ON (!area->pages)) -return ; - -imgu_dmamap_free_buffer (area->pages, map->size);vunmap (map->vaddr); +imgu_dmamap_free_buffer (map->pages, map->size); map->vaddr =NULL ; }
Signature · 1 line
2.25.1
Re: [PATCH 04/29] staging: media: ipu3: use vmap instead of reimplementing it
Quoted 4 lines · Christoph Hellwig
Just use vmap instead of messing with vmalloc internals.
Signed-off-by Christoph Hellwig <[email protected]>
Thanks!
Signature · 1 line
Sakari Ailus
PATCH 5/29 dma-mapping: use vmap insted of reimplementing it
In reply to Christoph HellwigReplace the open coded instance of vmap with the actual function. In the non-contiguous (IOMMU) case this requires an extra find_vm_area, but given that this isn't a fast path function that is a small price to pay.
--- kernel/dma/remap.c | 48 ++++++++++++---------------------------------- 1 file changed, 12 insertions(+), 36 deletions(-)
kernel/dma/remap.c +12 -36
@@ -20,23 +20,6 @@ struct page **dma_common_find_pages(void *cpu_addr)return area->pages; } -static struct vm_struct *__dma_common_pages_remap (struct page **pages, -size_t size,pgprot_t prot,const void *caller) -{ -struct vm_struct *area; - - area =get_vm_area_caller (size,VM_DMA_COHERENT , caller); -if (!area) -return NULL ; - -if (map_vm_area (area, prot, pages)) { -vunmap (area->addr); -return NULL ; - } - -return area; -} -/* * Remaps an array of PAGE_SIZE pages into another vm_area. * Cannot be used in non-sleeping contexts
@@ -44,15 +27,12 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages,void *dma_common_pages_remap (struct page **pages,size_t size,pgprot_t prot,const void *caller) { -struct vm_struct *area; +void *vaddr; - area =__dma_common_pages_remap (pages, size, prot, caller); -if (!area) -return NULL ; - - area->pages = pages; - -return area->addr; + vaddr =vmap (pages, size >>PAGE_SHIFT ,VM_DMA_COHERENT , prot); +if (vaddr) +find_vm_area (vaddr)->pages = pages; +return vaddr; }/*
@@ -62,24 +42,20 @@ void *dma_common_pages_remap(struct page **pages, size_t size,void *dma_common_contiguous_remap (struct page *page,size_t size,pgprot_t prot,const void *caller) { -int i; +int count = size >>PAGE_SHIFT ;struct page **pages; -struct vm_struct *area; +void *vaddr; +int i; - pages =kmalloc (sizeof (struct page *) <<get_order (size),GFP_KERNEL ); + pages =kmalloc_array (count,sizeof (struct page *),GFP_KERNEL );if (!pages)return NULL ; - -for (i =0 ; i < (size >>PAGE_SHIFT ); i++) +for (i =0 ; i < count; i++) pages[i] =nth_page (page, i); - - area =__dma_common_pages_remap (pages, size, prot, caller); - + vaddr =vmap (pages, count,VM_DMA_COHERENT , prot);kfree (pages); -if (!area) -return NULL ; -return area->addr; +return vaddr; }/*
Signature · 1 line
2.25.1
PATCH 6/29 powerpc: add an ioremap_phb helper
In reply to Christoph HellwigFactor code shared between pci_64 and electra_cf into a ioremap_pbh helper that follows the normal ioremap semantics, and returns a useful __iomem pointer. Note that it opencodes __ioremap_at as we know from the callers the slab is available. Switch pci_64 to also store the result as __iomem pointer, and unmap the result using iounmap instead of force casting and using vmalloc APIs.
--- arch/powerpc/include/asm/io.h | 2 + arch/powerpc/include/asm/pci-bridge.h | 2 +- arch/powerpc/kernel/pci_64.c | 53 ++++++++++++++++++--------- drivers/pcmcia/electra_cf.c | 45 ++++++++--------------- 4 files changed, 54 insertions(+), 48 deletions(-)
arch/powerpc/include/asm/io.h +2 -0
@@ -719,6 +719,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);extern void iounmap (volatile void __iomem *addr); +void __iomem *ioremap_phb (phys_addr_t paddr,unsigned long size); +int early_ioremap_range (unsigned long ea,phys_addr_t pa,unsigned long size,pgprot_t prot); void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
arch/powerpc/include/asm/pci-bridge.h +1 -1
@@ -66,7 +66,7 @@ struct pci_controller {void __iomem *io_base_virt;#ifdef CONFIG_PPC64 -void *io_base_alloc; +void __iomem *io_base_alloc;#endif resource_size_t io_base_phys;resource_size_t pci_io_size;
arch/powerpc/kernel/pci_64.c +35 -18
81 lines not on this page · raw message
drivers/pcmcia/electra_cf.c +16 -29
77 lines not on this page · raw message
Signature · 1 line
2.25.1
PATCH 7/29 powerpc: remove __ioremap_at and __iounmap_at
In reply to Christoph HellwigThese helpers are only used for remapping the ISA I/O base. Replace the mapping side with a remap_isa_range helper in isa-bridge.c that hard codes all the known arguments, and just remove __iounmap_at in favour of open coding it in the only caller.
--- arch/powerpc/include/asm/io.h | 8 ----- arch/powerpc/kernel/isa-bridge.c | 28 +++++++++++++----- arch/powerpc/mm/ioremap_64.c | 50 -------------------------------- 3 files changed, 21 insertions(+), 65 deletions(-)
arch/powerpc/include/asm/io.h +0 -8
@@ -699,10 +699,6 @@ static inline void iosync(void)* * * iounmap undoes such a mapping and can be hooked * -* * __ioremap_at (and the pending __iounmap_at) are low level functions to -* create hand-made mappings for use only by the PCI code and cannot -* currently be hooked. Must be page aligned. -* * * __ioremap_caller is the same as above but takes an explicit caller * reference rather than using __builtin_return_address(0) *
@@ -729,10 +725,6 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,extern void __iomem *__ioremap_caller (phys_addr_t ,unsigned long size,pgprot_t prot,void *caller); -extern void __iomem *__ioremap_at (phys_addr_t pa,void *ea, -unsigned long size,pgprot_t prot); -extern void __iounmap_at (void *ea,unsigned long size); -/* * When CONFIG_PPC_INDIRECT_PIO is set, we use the generic iomap implementation * which needs some additional definitions here. They basically allow PIO
arch/powerpc/kernel/isa-bridge.c +21 -7
@@ -18,6 +18,7 @@#include <linux/init.h> #include <linux/mm.h> #include <linux/notifier.h> +#include <linux/vmalloc.h> #include <asm/processor.h> #include <asm/io.h>
@@ -38,6 +39,22 @@ EXPORT_SYMBOL_GPL(isa_bridge_pcidev);#define ISA_SPACE_MASK 0x1#define ISA_SPACE_IO 0x1 +static void remap_isa_base (phys_addr_t pa,unsigned long size) +{ +WARN_ON_ONCE (ISA_IO_BASE & ~PAGE_MASK ); +WARN_ON_ONCE (pa & ~PAGE_MASK ); +WARN_ON_ONCE (size & ~PAGE_MASK ); + +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); + }else { +early_ioremap_range (ISA_IO_BASE , pa, size, +pgprot_noncached (PAGE_KERNEL )); + } +} +static void pci_process_ISA_OF_ranges (struct device_node *isa_node,unsigned long phb_io_base_phys) {
@@ -105,15 +122,13 @@ static void pci_process_ISA_OF_ranges(struct device_node *isa_node,if (size >0x10000 ) size =0x10000 ; -__ioremap_at (phb_io_base_phys, (void *)ISA_IO_BASE , - size,pgprot_noncached (PAGE_KERNEL )); +remap_isa_base (phb_io_base_phys, size);return ; inval_range:printk (KERN_ERR "no ISA IO ranges or unexpected isa range, " "mapping 64k\n" ); -__ioremap_at (phb_io_base_phys, (void *)ISA_IO_BASE , -0x10000 ,pgprot_noncached (PAGE_KERNEL )); +remap_isa_base (phb_io_base_phys,0x10000 ); }
@@ -248,8 +263,7 @@ void __init isa_bridge_init_non_pci(struct device_node *np)* and map it */ isa_io_base =ISA_IO_BASE ; -__ioremap_at (pbase, (void *)ISA_IO_BASE , - size,pgprot_noncached (PAGE_KERNEL )); +remap_isa_base (pbase, size);pr_debug ("ISA: Non-PCI bridge is %pOF\n" , np); }
@@ -297,7 +311,7 @@ static void isa_bridge_remove(void) isa_bridge_pcidev =NULL ;/* Unmap the ISA area */ -__iounmap_at ((void *)ISA_IO_BASE ,0x10000 ); +unmap_kernel_range (ISA_IO_BASE ,0x10000 ); }/**
arch/powerpc/mm/ioremap_64.c +0 -50
56 lines not on this page · raw message
Signature · 1 line
2.25.1
PATCH 8/29 mm: remove __get_vm_area
In reply to Christoph HellwigSwitch the two remaining callers to use __get_vm_area_caller instead.
--- arch/powerpc/kernel/pci_64.c | 3 ++- arch/sh/kernel/cpu/sh4/sq.c | 3 ++- include/linux/vmalloc.h | 2 -- mm/vmalloc.c | 8 -------- 4 files changed, 4 insertions(+), 12 deletions(-)
arch/powerpc/kernel/pci_64.c +2 -1
@@ -132,7 +132,8 @@ void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)* address decoding but I'd rather not deal with those outside of the * reserved 64K legacy region. */ - area =__get_vm_area (size,0 ,PHB_IO_BASE ,PHB_IO_END ); + area =__get_vm_area_caller (size,0 ,PHB_IO_BASE ,PHB_IO_END , +__builtin_return_address (0 ));if (!area)return NULL ;
arch/sh/kernel/cpu/sh4/sq.c +2 -1
@@ -103,7 +103,8 @@ static int __sq_remap(struct sq_mapping *map, pgprot_t prot)#if defined(CONFIG_MMU )struct vm_struct *vma; - vma =__get_vm_area (map->size,VM_ALLOC , map->sq_addr,SQ_ADDRMAX ); + vma =__get_vm_area_caller (map->size,VM_ALLOC , map->sq_addr, +SQ_ADDRMAX ,__builtin_return_address (0 ));if (!vma)return -ENOMEM ;
include/linux/vmalloc.h +0 -2
@@ -161,8 +161,6 @@ static inline size_t get_vm_area_size(const struct vm_struct *area)extern struct vm_struct *get_vm_area (unsigned long size,unsigned long flags);extern struct vm_struct *get_vm_area_caller (unsigned long size,unsigned long flags,const void *caller); -extern struct vm_struct *__get_vm_area (unsigned long size,unsigned long flags, -unsigned long start,unsigned long end); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end,
mm/vmalloc.c +0 -8
@@ -2127,14 +2127,6 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,return area; } -struct vm_struct *__get_vm_area (unsigned long size,unsigned long flags, -unsigned long start,unsigned long end) -{ -return __get_vm_area_node (size,1 , flags, start, end,NUMA_NO_NODE , -GFP_KERNEL ,__builtin_return_address (0 )); -} -EXPORT_SYMBOL_GPL (__get_vm_area); -struct vm_struct *__get_vm_area_caller (unsigned long size,unsigned long flags,unsigned long start,unsigned long end,const void *caller)
Signature · 1 line
2.25.1
PATCH 9/29 mm: unexport unmap_kernel_range_noflush
In reply to Christoph HellwigThere are no modular users of this function.
--- mm/vmalloc.c | 1 - 1 file changed, 1 deletion(-)
mm/vmalloc.c +0 -1
@@ -2029,7 +2029,6 @@ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size) {vunmap_page_range (addr, addr + size); } -EXPORT_SYMBOL_GPL (unmap_kernel_range_noflush);/** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
Signature · 1 line
2.25.1
PATCH 10/29 mm: rename CONFIG_PGTABLE_MAPPING to CONFIG_ZSMALLOC_PGTABLE_MAPPING
In reply to Christoph HellwigRename the Kconfig variable to clarify the scope.
--- arch/arm/configs/omap2plus_defconfig | 2 +- include/linux/zsmalloc.h | 2 +- mm/Kconfig | 2 +- mm/zsmalloc.c | 8 ++++---- 4 files changed, 7 insertions(+), 7 deletions(-)
arch/arm/configs/omap2plus_defconfig +1 -1
@@ -81,7 +81,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_BINFMT_MISC=y CONFIG_CMA=y CONFIG_ZSMALLOC=m -CONFIG_PGTABLE_MAPPING=y +CONFIG_ZSMALLOC_PGTABLE_MAPPING=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y
include/linux/zsmalloc.h +1 -1
@@ -20,7 +20,7 @@* zsmalloc mapping modes * * NOTE: These only make a difference when a mapped object spans pages. -* They also have no effect when PGTABLE_MAPPING is selected. +* They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected. */ enum zs_mapmode {ZS_MM_RW ,/* normal read-write mapping */
mm/Kconfig +1 -1
@@ -705,7 +705,7 @@ config ZSMALLOC returned by an alloc(). This handle must be mapped in order to access the allocated space. -config PGTABLE_MAPPING +config ZSMALLOC_PGTABLE_MAPPING bool "Use page table mapping to access object in zsmalloc" depends on ZSMALLOC help
mm/zsmalloc.c +4 -4
@@ -293,7 +293,7 @@ struct zspage { };struct mapping_area { -#ifdef CONFIG_PGTABLE_MAPPING +#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING struct vm_struct *vm;/* vm area for mapping object that span pages */ #else char *vm_buf;/* copy buffer for objects that span pages */
@@ -1113,7 +1113,7 @@ static struct zspage *find_get_zspage(struct size_class *class)return zspage; } -#ifdef CONFIG_PGTABLE_MAPPING +#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING static inline int __zs_cpu_up (struct mapping_area *area) {/*
@@ -1151,7 +1151,7 @@ static inline void __zs_unmap_object(struct mapping_area *area, unmap_kernel_range(addr, PAGE_SIZE * 2); } -#else /* CONFIG_PGTABLE_MAPPING */ +#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ static inline int __zs_cpu_up (struct mapping_area *area) {
@@ -1233,7 +1233,7 @@ static void __zs_unmap_object(struct mapping_area *area, pagefault_enable(); } -#endif /* CONFIG_PGTABLE_MAPPING */ +#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */ static int zs_cpu_prepare (unsigned int cpu) {
Signature · 1 line
2.25.1
PATCH 11/29 mm: only allow page table mappings for built-in zsmalloc
In reply to Christoph HellwigThis allows to unexport map_vm_area and unmap_kernel_range, which are rather deep internal and should not be available to modules, as they for example allow fine grained control of mapping permissions, and also allow splitting the setup of a vmalloc area and the actual mapping and thus expose vmalloc internals.
zsmalloc is typically built-in and continues to work (just like the percpu-vm code using a similar patter), while modular zsmalloc also continues to work, but must use copies.
--- mm/Kconfig | 2 +- mm/vmalloc.c | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-)
mm/Kconfig +1 -1
@@ -707,7 +707,7 @@ config ZSMALLOC config ZSMALLOC_PGTABLE_MAPPING bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC + depends on ZSMALLOC=y help By default, zsmalloc uses a copy-based object mapping method to access allocations that span two pages. However, if a particular
mm/vmalloc.c +0 -2
@@ -2046,7 +2046,6 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)vunmap_page_range (addr, end);flush_tlb_kernel_range (addr, end); } -EXPORT_SYMBOL_GPL (unmap_kernel_range);int map_vm_area (struct vm_struct *area,pgprot_t prot,struct page **pages) {
@@ -2058,7 +2057,6 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)return err >0 ?0 : err; } -EXPORT_SYMBOL_GPL (map_vm_area);static inline void setup_vmalloc_vm_locked (struct vm_struct *vm,struct vmap_area *va,unsigned long flags,const void *caller)
Signature · 1 line
2.25.1
Re: [PATCH 11/29] mm: only allow page table mappings for built-in zsmalloc
Quoted 6 lines · Christoph Hellwig
This allows to unexport
map_vm_areaandunmap_kernel_range, which are rather deep internal and should not be available to modules, as they for example allow fine grained control of mapping permissions, and also allow splitting the setup of a vmalloc area and the actual mapping and thus expose vmalloc internals.
Quoted 6 lines
zsmalloc is typically built-in and continues to work (just like the percpu-vm code using a similar patter), while modular zsmalloc also continues to work, but must use copies.
Signed-off-by Christoph Hellwig <[email protected]>
Thanks!
PATCH 12/29 mm: pass addr as unsigned long to vb_free
In reply to Christoph HellwigEver use of addr in vb_free casts to unsigned long first, and the caller has an unsigned long version of the address available anyway. Just pass that and avoid all the casts.
--- mm/vmalloc.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-)
mm/vmalloc.c +7 -9
@@ -1664,7 +1664,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)return vaddr; } -static void vb_free (const void *addr,unsigned long size) +static void vb_free (unsigned long addr,unsigned long size) {unsigned long offset;unsigned long vb_idx;
@@ -1674,24 +1674,22 @@ static void vb_free(const void *addr, unsigned long size)BUG_ON (offset_in_page (size));BUG_ON (size >PAGE_SIZE *VMAP_MAX_ALLOC ); -flush_cache_vunmap ((unsigned long )addr, (unsigned long )addr + size); +flush_cache_vunmap (addr, addr + size); order =get_order (size); - offset = (unsigned long )addr & (VMAP_BLOCK_SIZE -1 ); - offset >>=PAGE_SHIFT ; + offset = (addr & (VMAP_BLOCK_SIZE -1 )) >>PAGE_SHIFT ; - vb_idx =addr_to_vb_idx ((unsigned long )addr); + vb_idx =addr_to_vb_idx (addr);rcu_read_lock (); vb =radix_tree_lookup (&vmap_block_tree, vb_idx);rcu_read_unlock ();BUG_ON (!vb); -vunmap_page_range ((unsigned long )addr, (unsigned long )addr + size); +vunmap_page_range (addr, addr + size);if (debug_pagealloc_enabled_static ()) -flush_tlb_kernel_range ((unsigned long )addr, - (unsigned long )addr + size); +flush_tlb_kernel_range (addr, addr + size);spin_lock (&vb->lock);
@@ -1791,7 +1789,7 @@ void vm_unmap_ram(const void *mem, unsigned int count)if (likely (count <=VMAP_MAX_ALLOC )) {debug_check_no_locks_freed (mem, size); -vb_free (mem, size); +vb_free (addr, size);return ; }
Signature · 1 line
2.25.1
PATCH 13/29 mm: remove vmap_page_range_noflush and vunmap_page_range
In reply to Christoph HellwigThese have non-static aliases called map_kernel_range_noflush and unmap_kernel_range_noflush that just differ slightly in the calling conventions that pass addr + size instead of an end.
--- mm/vmalloc.c | 98 +++++++++++++++++++++------------------------------- 1 file changed, 40 insertions(+), 58 deletions(-)
mm/vmalloc.c +40 -58
@@ -127,10 +127,24 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) }while (p4d++, addr = next, addr != end); } -static void vunmap_page_range (unsigned long addr,unsigned long end) +/** +* unmap_kernel_range_noflush - unmap kernel VM area +* @addr: start of the VM area to unmap +* @size: size of the VM area to unmap +* +* Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size specify +* should have been allocated using get_vm_area() and its friends. +* +* NOTE: +* This function does NOT do any cache flushing. The caller is responsible +* for calling flush_cache_vunmap() on to-be-mapped areas before calling this +* function and flush_tlb_kernel_range() after. +*/ +void unmap_kernel_range_noflush (unsigned long addr,unsigned long size) { -pgd_t *pgd; +unsigned long end = addr + size;unsigned long next; +pgd_t *pgd;BUG_ON (addr >= end); pgd =pgd_offset_k (addr);
@@ -219,18 +233,30 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,return 0 ; } -/* -* Set up page tables in kva (addr, end). The ptes shall have prot "prot", and -* will have pfns corresponding to the "pages" array. +/** +* map_kernel_range_noflush - map kernel VM area with the specified pages +* @addr: start of the VM area to map +* @size: size of the VM area to map +* @prot: page protection flags to use +* @pages: pages to map * -* Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N] +* Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should +* have been allocated using get_vm_area() and its friends. +* +* NOTE: +* This function does NOT do any cache flushing. The caller is responsible for +* calling flush_cache_vmap() on to-be-mapped areas before calling this +* function. +* +* RETURNS: +* The number of pages mapped on success, -errno on failure. */ -static int vmap_page_range_noflush (unsigned long start,unsigned long end, -pgprot_t prot,struct page **pages) +int map_kernel_range_noflush (unsigned long addr,unsigned long size, +pgprot_t prot,struct page **pages) { -pgd_t *pgd; +unsigned long end = addr + size;unsigned long next; -unsigned long addr = start; +pgd_t *pgd;int err =0 ;int nr =0 ;
@@ -251,7 +277,7 @@ static int vmap_page_range(unsigned long start, unsigned long end, {int ret; - ret =vmap_page_range_noflush (start, end, prot, pages); + ret =map_kernel_range_noflush (start, end - start, prot, pages);flush_cache_vmap (start, end);return ret; }
@@ -1226,7 +1252,7 @@ EXPORT_SYMBOL_GPL(unregister_vmap_purge_notifier);*/ static void unmap_vmap_area (struct vmap_area *va) { -vunmap_page_range (va->va_start, va->va_end); +unmap_kernel_range_noflush (va->va_start, va->va_end - va->va_start); }/*
@@ -1686,7 +1712,7 @@ static void vb_free(unsigned long addr, unsigned long size)rcu_read_unlock ();BUG_ON (!vb); -vunmap_page_range (addr, addr + size); +unmap_kernel_range_noflush (addr, size);if (debug_pagealloc_enabled_static ())flush_tlb_kernel_range (addr, addr + size);
@@ -1984,50 +2010,6 @@ void __init vmalloc_init(void) vmap_initialized = true; } -/** -* map_kernel_range_noflush - map kernel VM area with the specified pages -* @addr: start of the VM area to map -* @size: size of the VM area to map -* @prot: page protection flags to use -* @pages: pages to map -* -* Map PFN_UP(@size) pages at @addr. The VM area @addr and @size -* specify should have been allocated using get_vm_area() and its -* friends. -* -* NOTE: -* This function does NOT do any cache flushing. The caller is -* responsible for calling flush_cache_vmap() on to-be-mapped areas -* before calling this function. -* -* RETURNS: -* The number of pages mapped on success, -errno on failure. -*/ -int map_kernel_range_noflush (unsigned long addr,unsigned long size, -pgprot_t prot,struct page **pages) -{ -return vmap_page_range_noflush (addr, addr + size, prot, pages); -} - -/** -* unmap_kernel_range_noflush - unmap kernel VM area -* @addr: start of the VM area to unmap -* @size: size of the VM area to unmap -* -* Unmap PFN_UP(@size) pages at @addr. The VM area @addr and @size -* specify should have been allocated using get_vm_area() and its -* friends. -* -* NOTE: -* This function does NOT do any cache flushing. The caller is -* responsible for calling flush_cache_vunmap() on to-be-mapped areas -* before calling this function and flush_tlb_kernel_range() after. -*/ -void unmap_kernel_range_noflush (unsigned long addr,unsigned long size) -{ -vunmap_page_range (addr, addr + size); -} -/** * unmap_kernel_range - unmap kernel VM area and flush cache and TLB * @addr: start of the VM area to unmap
@@ -2041,7 +2023,7 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)unsigned long end = addr + size;flush_cache_vunmap (addr, end); -vunmap_page_range (addr, end); +unmap_kernel_range_noflush (addr, size);flush_tlb_kernel_range (addr, end); }
Signature · 1 line
2.25.1
PATCH 14/29 mm: rename vmap_page_range to map_kernel_range
In reply to Christoph HellwigThis matches the map_kernel_range_noflush API. Also change to pass a size instead of the end, similar to the noflush version.
--- mm/vmalloc.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)
mm/vmalloc.c +5 -6
@@ -272,13 +272,13 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,return nr; } -static int vmap_page_range (unsigned long start,unsigned long end, +static int map_kernel_range (unsigned long start,unsigned long size,pgprot_t prot,struct page **pages) {int ret; - ret =map_kernel_range_noflush (start, end - start, prot, pages); -flush_cache_vmap (start, end); + ret =map_kernel_range_noflush (start, size, prot, pages); +flush_cache_vmap (start, start + size);return ret; }
@@ -1866,7 +1866,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prokasan_unpoison_vmalloc (mem, size); -if (vmap_page_range (addr, addr + size, prot, pages) <0 ) { +if (map_kernel_range (addr, size, prot, pages) <0 ) {vm_unmap_ram (mem, count);return NULL ; }
@@ -2030,10 +2030,9 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)int map_vm_area (struct vm_struct *area,pgprot_t prot,struct page **pages) {unsigned long addr = (unsigned long )area->addr; -unsigned long end = addr +get_vm_area_size (area);int err; - err =vmap_page_range (addr, end, prot, pages); + err =map_kernel_range (addr,get_vm_area_size (area), prot, pages);return err >0 ?0 : err; }
Signature · 1 line
2.25.1
PATCH 15/29 mm: don't return the number of pages from map_kernel_range{,_noflush}
In reply to Christoph HellwigNone of the callers needs the number of pages, and a 0 / -errno return value is a lot more intuitive.
--- mm/vmalloc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
mm/vmalloc.c +2 -2
@@ -249,7 +249,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,* function. * * RETURNS: -* The number of pages mapped on success, -errno on failure. +* 0 on success, -errno on failure. */ int map_kernel_range_noflush (unsigned long addr,unsigned long size,pgprot_t prot,struct page **pages)
@@ -269,7 +269,7 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,return err; }while (pgd++, addr = next, addr != end); -return nr; +return 0 ; } static int map_kernel_range(unsigned long start, unsigned long size,
Signature · 1 line
2.25.1
PATCH 16/29 mm: remove map_vm_range
In reply to Christoph HellwigSwitch all callers to map_kernel_range, which symmetric to the unmap side (as well as the _noflush versions).
--- Documentation/core-api/cachetlb.rst | 2 +- include/linux/vmalloc.h | 10 ++++------ mm/vmalloc.c | 21 +++++++-------------- mm/zsmalloc.c | 4 +++- net/ceph/ceph_common.c | 3 +-- 5 files changed, 16 insertions(+), 24 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_vm_area() + The first of these two routines is invoked after map_kernel_range() has installed the page table entries. The second is invoked before unmap_kernel_range() deletes the page table entries.
include/linux/vmalloc.h +4 -6
@@ -168,11 +168,11 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,extern struct vm_struct *remove_vm_area (const void *addr);extern struct vm_struct *find_vm_area (const void *addr); -extern int map_vm_area (struct vm_struct *area,pgprot_t prot, -struct page **pages);#ifdef CONFIG_MMU 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)
@@ -189,14 +189,12 @@ map_kernel_range_noflush(unsigned long start, unsigned long size, {return size >>PAGE_SHIFT ; } +#define map_kernel_range map_kernel_range_noflushstatic inline void unmap_kernel_range_noflush (unsigned long addr,unsigned long size) { } -static inline void -unmap_kernel_range (unsigned long addr,unsigned long size) -{ -} +#define unmap_kernel_range unmap_kernel_range_noflushstatic inline void set_vm_flush_reset_perms (void *addr) { }
mm/vmalloc.c +7 -14
@@ -272,8 +272,8 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,return 0 ; } -static int map_kernel_range (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) {int ret;
@@ -2027,16 +2027,6 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)flush_tlb_kernel_range (addr, end); } -int map_vm_area (struct vm_struct *area,pgprot_t prot,struct page **pages) -{ -unsigned long addr = (unsigned long )area->addr; -int err; - - err =map_kernel_range (addr,get_vm_area_size (area), prot, pages); - -return err >0 ?0 : err; -} -static inline void setup_vmalloc_vm_locked (struct vm_struct *vm,struct vmap_area *va,unsigned long flags,const void *caller) {
@@ -2408,7 +2398,8 @@ void *vmap(struct page **pages, unsigned int count,if (!area)return NULL ; -if (map_vm_area (area, prot, pages)) { +if (map_kernel_range ((unsigned long )area->addr, size, prot, + pages) <0 ) {vunmap (area->addr);return NULL ; }
@@ -2471,8 +2462,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, }atomic_long_add (area->nr_pages, &nr_vmalloc_pages); -if (map_vm_area (area, prot, pages)) +if (map_kernel_range ((unsigned long )area->addr,get_vm_area_size (area), + prot, pages) <0 ) goto fail; +return area->addr; fail:
mm/zsmalloc.c +3 -1
@@ -1138,7 +1138,9 @@ static inline void __zs_cpu_down(struct mapping_area *area)static inline void *__zs_map_object (struct mapping_area *area,struct page *pages[2 ],int off,int size) { -BUG_ON (map_vm_area (area->vm,PAGE_KERNEL , pages)); +unsigned long addr = (unsigned long )area->vm->addr; + +BUG_ON (map_kernel_range (addr,PAGE_SIZE *2 ,PAGE_KERNEL , pages) <0 ); area->vm_addr = area->vm->addr;return area->vm_addr + off; }
net/ceph/ceph_common.c +1 -2
@@ -190,8 +190,7 @@ EXPORT_SYMBOL(ceph_compare_options);* kvmalloc() doesn't fall back to the vmalloc allocator unless flags are * compatible with (a superset of) GFP_KERNEL. This is because while the * actual pages are allocated with the specified flags, the page table pages -* are always allocated with GFP_KERNEL. map_vm_area() doesn't even take -* flags because GFP_KERNEL is hard-coded in {p4d,pud,pmd,pte}_alloc(). +* are always allocated with GFP_KERNEL. * * ceph_kvmalloc() may be called with GFP_KERNEL, GFP_NOFS or GFP_NOIO. */
Signature · 1 line
2.25.1
PATCH 17/29 mm: remove unmap_vmap_area
In reply to Christoph HellwigThis function just has a single caller, open code it there.
--- mm/vmalloc.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)
mm/vmalloc.c +1 -9
@@ -1247,14 +1247,6 @@ int unregister_vmap_purge_notifier(struct notifier_block *nb) }EXPORT_SYMBOL_GPL (unregister_vmap_purge_notifier); -/* -* Clear the pagetable entries of a given vmap_area -*/ -static void unmap_vmap_area (struct vmap_area *va) -{ -unmap_kernel_range_noflush (va->va_start, va->va_end - va->va_start); -} -/* * lazy_max_pages is the maximum amount of virtual address space we gather up * before attempting to purge with a TLB flush.
@@ -1416,7 +1408,7 @@ static void free_vmap_area_noflush(struct vmap_area *va)static void free_unmap_vmap_area (struct vmap_area *va) {flush_cache_vunmap (va->va_start, va->va_end); -unmap_vmap_area (va); +unmap_kernel_range_noflush (va->va_start, va->va_end - va->va_start);if (debug_pagealloc_enabled_static ())flush_tlb_kernel_range (va->va_start, va->va_end);
Signature · 1 line
2.25.1
PATCH 18/29 mm: remove the prot argument from vm_map_ram
In reply to Christoph HellwigThis is always PAGE_KERNEL - for long term mappings with other properties vmap should be used.
--- drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c | 2 +- drivers/media/common/videobuf2/videobuf2-dma-sg.c | 3 +-- drivers/media/common/videobuf2/videobuf2-vmalloc.c | 3 +-- fs/erofs/decompressor.c | 2 +- fs/xfs/xfs_buf.c | 2 +- include/linux/vmalloc.h | 3 +-- mm/nommu.c | 2 +- mm/vmalloc.c | 4 ++-- 8 files changed, 9 insertions(+), 12 deletions(-)
drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +1 -1
@@ -66,7 +66,7 @@ static void *mock_dmabuf_vmap(struct dma_buf *dma_buf) {struct mock_dmabuf *mock =to_mock (dma_buf); -return vm_map_ram (mock->pages, mock->npages,0 ,PAGE_KERNEL ); +return vm_map_ram (mock->pages, mock->npages,0 ); }static void mock_dmabuf_vunmap (struct dma_buf *dma_buf,void *vaddr)
drivers/media/common/videobuf2/videobuf2-dma-sg.c +1 -2
@@ -309,8 +309,7 @@ static void *vb2_dma_sg_vaddr(void *buf_priv)if (buf->db_attach) buf->vaddr =dma_buf_vmap (buf->db_attach->dmabuf);else - buf->vaddr =vm_map_ram (buf->pages, - buf->num_pages,-1 ,PAGE_KERNEL ); + buf->vaddr =vm_map_ram (buf->pages, buf->num_pages,-1 ); }/* add offset in case userptr is not page-aligned */
drivers/media/common/videobuf2/videobuf2-vmalloc.c +1 -2
@@ -107,8 +107,7 @@ static void *vb2_vmalloc_get_userptr(struct device *dev, unsigned long vaddr, buf->vaddr = (__force void *)ioremap (__pfn_to_phys (nums[0 ]), size + offset); }else { - buf->vaddr =vm_map_ram (frame_vector_pages (vec), n_pages,-1 , -PAGE_KERNEL ); + buf->vaddr =vm_map_ram (frame_vector_pages (vec), n_pages,-1 ); }if (!buf->vaddr)
fs/erofs/decompressor.c +1 -1
@@ -274,7 +274,7 @@ static int z_erofs_decompress_generic(struct z_erofs_decompress_req *rq, i =0 ;while (1 ) { - dst =vm_map_ram (rq->out, nrpages_out,-1 ,PAGE_KERNEL ); + dst =vm_map_ram (rq->out, nrpages_out,-1 );/* retry two more times (totally 3 times) */ if (dst || ++i >=3 )
fs/xfs/xfs_buf.c +1 -1
@@ -477,7 +477,7 @@ _xfs_buf_map_pages( nofs_flag =memalloc_nofs_save (); do { bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count, - -1, PAGE_KERNEL); + -1); if (bp->b_addr) break; vm_unmap_aliases();
include/linux/vmalloc.h +1 -2
@@ -88,8 +88,7 @@ struct vmap_area {* Highlevel APIs for driver use */ extern void vm_unmap_ram (const void *mem,unsigned int count); -extern void *vm_map_ram (struct page **pages,unsigned int count, -int node,pgprot_t prot); +extern void *vm_map_ram (struct page **pages,unsigned int count,int node);extern void vm_unmap_aliases (void );#ifdef CONFIG_MMU
mm/nommu.c +1 -1
@@ -351,7 +351,7 @@ void vunmap(const void *addr) }EXPORT_SYMBOL (vunmap); -void *vm_map_ram (struct page **pages,unsigned int count,int node,pgprot_t prot) +void *vm_map_ram (struct page **pages,unsigned int count,int node) {BUG ();return NULL ;
mm/vmalloc.c +2 -2
@@ -1834,7 +1834,7 @@ EXPORT_SYMBOL(vm_unmap_ram);* * Returns: a pointer to the address that has been mapped, or %NULL on failure */ -void *vm_map_ram (struct page **pages,unsigned int count,int node,pgprot_t prot) +void *vm_map_ram (struct page **pages,unsigned int count,int node) {unsigned long size = (unsigned long )count <<PAGE_SHIFT ;unsigned long addr;
@@ -1858,7 +1858,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prokasan_unpoison_vmalloc (mem, size); -if (map_kernel_range (addr, size, prot, pages) <0 ) { +if (map_kernel_range (addr, size,PAGE_KERNEL , pages) <0 ) {vm_unmap_ram (mem, count);return NULL ; }
Signature · 1 line
2.25.1
PATCH 19/29 mm: enforce that vmap can't map pages executable
In reply to Christoph HellwigTo help enforcing the W^X protection don't allow remapping existing pages as executable.
x86 bits from Peter Zijlstra <[email protected]>, arm64 bits from Mark Rutland <[email protected]>.
--- arch/arm64/include/asm/pgtable.h | 3 +++ arch/x86/include/asm/pgtable_types.h | 6 ++++++ include/asm-generic/pgtable.h | 4 ++++ mm/vmalloc.c | 2 +- 4 files changed, 14 insertions(+), 1 deletion(-)
arch/arm64/include/asm/pgtable.h +3 -0
@@ -407,6 +407,9 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)#define __pgprot_modify (prot,mask,bits) \ __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) +#define pgprot_nx (prot) \ + __pgprot_modify(prot, 0, PTE_PXN) +/* * Mark the prot value as uncacheable and unbufferable. */
arch/x86/include/asm/pgtable_types.h +6 -0
@@ -282,6 +282,12 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;typedef struct {pgdval_t pgd; }pgd_t ; +static inline pgprot_t pgprot_nx (pgprot_t prot) +{ +return __pgprot (pgprot_val (prot) | _PAGE_NX); +} +#define pgprot_nx pgprot_nx +#ifdef CONFIG_X86_PAE /*
include/asm-generic/pgtable.h +4 -0
@@ -491,6 +491,10 @@ static inline int arch_unmap_one(struct mm_struct *mm,#define flush_tlb_fix_spurious_fault (vma, address) flush_tlb_page(vma, address)#endif +#ifndef pgprot_nx +#define pgprot_nx (prot) (prot) +#endif +#ifndef pgprot_noncached#define pgprot_noncached (prot) (prot)#endif
mm/vmalloc.c +1 -1
@@ -2390,7 +2390,7 @@ void *vmap(struct page **pages, unsigned int count,if (!area)return NULL ; -if (map_kernel_range ((unsigned long )area->addr, size, prot, +if (map_kernel_range ((unsigned long )area->addr, size,pgprot_nx (prot), pages) <0 ) {vunmap (area->addr);return NULL ;
Signature · 1 line
2.25.1
PATCH 20/29 gpu/drm: remove the powerpc hack in drm_legacy_sg_alloc
In reply to Christoph HellwigThe non-cached vmalloc mapping was initially added as a hack for the first-gen amigaone platform (6xx/book32s), isn't fully supported upstream, and which used the legacy radeon driver together with non-coherent DMA. However this only ever worked reliably for DRI .
Remove the hack as it is the last user of __vmalloc passing a page protection flag other than PAGE_KERNEL and didn't do anything for other platforms with non-coherent DMA.
--- drivers/gpu/drm/drm_scatter.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-)
drivers/gpu/drm/drm_scatter.c +1 -10
@@ -43,15 +43,6 @@#define DEBUG_SCATTER 0 -static inline void *drm_vmalloc_dma (unsigned long size) -{ -#if defined(__powerpc__) && defined(CONFIG_NOT_COHERENT_CACHE ) -return __vmalloc (size,GFP_KERNEL ,pgprot_noncached_wc (PAGE_KERNEL )); -#else -return vmalloc_32 (size); -#endif -} -static void drm_sg_cleanup (struct drm_sg_mem * entry) {struct page *page;
@@ -126,7 +117,7 @@ int drm_legacy_sg_alloc(struct drm_device *dev, void *data,return -ENOMEM ; } - entry->virtual =drm_vmalloc_dma (pages <<PAGE_SHIFT ); + entry->virtual =vmalloc_32 (pages <<PAGE_SHIFT );if (!entry->virtual) {kfree (entry->busaddr);kfree (entry->pagelist);
Signature · 1 line
2.25.1
PATCH 21/29 mm: remove the pgprot argument to __vmalloc
In reply to Christoph HellwigThe pgprot argument to __vmalloc is always PROT_KERNEL now, so remove it.
--- arch/x86/hyperv/hv_init.c | 3 +-- arch/x86/include/asm/kvm_host.h | 3 +-- arch/x86/kvm/svm/sev.c | 3 +-- drivers/block/drbd/drbd_bitmap.c | 4 +--- drivers/gpu/drm/etnaviv/etnaviv_dump.c | 4 ++-- drivers/lightnvm/pblk-init.c | 5 ++--- drivers/md/dm-bufio.c | 4 ++-- drivers/mtd/ubi/io.c | 4 ++-- drivers/scsi/sd_zbc.c | 3 +-- fs/gfs2/dir.c | 9 ++++----- fs/gfs2/quota.c | 2 +- fs/nfs/blocklayout/extent_tree.c | 2 +- fs/ntfs/malloc.h | 2 +- fs/ubifs/debug.c | 2 +- fs/ubifs/lprops.c | 2 +- fs/ubifs/lpt_commit.c | 4 ++-- fs/ubifs/orphan.c | 2 +- fs/xfs/kmem.c | 2 +- include/linux/vmalloc.h | 2 +- kernel/bpf/core.c | 6 +++--- kernel/groups.c | 2 +- kernel/module.c | 3 +-- mm/nommu.c | 15 +++++++-------- mm/page_alloc.c | 2 +- mm/percpu.c | 2 +- mm/vmalloc.c | 4 ++-- net/bridge/netfilter/ebtables.c | 6 ++---- sound/core/memalloc.c | 2 +- sound/core/pcm_memory.c | 2 +- 29 files changed, 47 insertions(+), 59 deletions(-)
arch/x86/hyperv/hv_init.c +1 -2
@@ -95,8 +95,7 @@ static int hv_cpu_init(unsigned int cpu)* not be stopped in the case of CPU offlining and the VM will hang. */ if (!*hvp) { - *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL ); + *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO); }if (*hvp) {
arch/x86/include/asm/kvm_host.h +1 -2
@@ -1280,8 +1280,7 @@ extern struct kmem_cache *x86_fpu_cache;#define __KVM_HAVE_ARCH_VM_ALLOCstatic inline struct kvm *kvm_arch_alloc_vm (void ) { -return __vmalloc (kvm_x86_ops.vm_size, -GFP_KERNEL_ACCOUNT | __GFP_ZERO,PAGE_KERNEL ); +return __vmalloc (kvm_x86_ops.vm_size,GFP_KERNEL_ACCOUNT | __GFP_ZERO); }void kvm_arch_free_vm (struct kvm *kvm);
arch/x86/kvm/svm/sev.c +1 -2
@@ -335,8 +335,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,/* Avoid using vmalloc for smaller buffers. */ size = npages *sizeof (struct page *);if (size >PAGE_SIZE ) - pages =__vmalloc (size,GFP_KERNEL_ACCOUNT | __GFP_ZERO, -PAGE_KERNEL ); + pages =__vmalloc (size,GFP_KERNEL_ACCOUNT | __GFP_ZERO);else pages =kmalloc (size,GFP_KERNEL_ACCOUNT );
drivers/block/drbd/drbd_bitmap.c +1 -3
@@ -396,9 +396,7 @@ static struct page **bm_realloc_pages(struct drbd_bitmap *b, unsigned long want) bytes =sizeof (struct page *)*want; new_pages =kzalloc (bytes,GFP_NOIO | __GFP_NOWARN);if (!new_pages) { - new_pages =__vmalloc (bytes, -GFP_NOIO | __GFP_ZERO, -PAGE_KERNEL ); + new_pages =__vmalloc (bytes,GFP_NOIO | __GFP_ZERO);if (!new_pages)return NULL ; }
drivers/gpu/drm/etnaviv/etnaviv_dump.c +2 -2
@@ -154,8 +154,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit) file_size +=sizeof (*iter.hdr) * n_obj;/* Allocate the file in vmalloc memory, it's likely to be big */ - iter.start =__vmalloc (file_size,GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, -PAGE_KERNEL ); + iter.start =__vmalloc (file_size,GFP_KERNEL | __GFP_NOWARN | + __GFP_NORETRY);if (!iter.start) {mutex_unlock (&gpu->mmu_context->lock);dev_warn (gpu->dev,"failed to allocate devcoredump file\n" );
drivers/lightnvm/pblk-init.c +2 -3
@@ -145,9 +145,8 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)int ret =0 ; map_size =pblk_trans_map_size (pblk); - pblk->trans_map =__vmalloc (map_size,GFP_KERNEL | __GFP_NOWARN - | __GFP_RETRY_MAYFAIL | __GFP_HIGHMEM, -PAGE_KERNEL ); + pblk->trans_map =__vmalloc (map_size,GFP_KERNEL | __GFP_NOWARN | + __GFP_RETRY_MAYFAIL | __GFP_HIGHMEM);if (!pblk->trans_map) {pblk_err (pblk,"failed to allocate L2P (need %zu of memory)\n" , map_size);
drivers/md/dm-bufio.c +2 -2
@@ -400,13 +400,13 @@ static void *alloc_buffer_data(struct dm_bufio_client *c, gfp_t gfp_mask,*/ if (gfp_mask & __GFP_NORETRY) {unsigned noio_flag =memalloc_noio_save (); -void *ptr =__vmalloc (c->block_size, gfp_mask,PAGE_KERNEL ); +void *ptr =__vmalloc (c->block_size, gfp_mask);memalloc_noio_restore (noio_flag);return ptr; } -return __vmalloc (c->block_size, gfp_mask,PAGE_KERNEL ); +return __vmalloc (c->block_size, gfp_mask); }/*
drivers/mtd/ubi/io.c +2 -2
@@ -1297,7 +1297,7 @@ static int self_check_write(struct ubi_device *ubi, const void *buf, int pnum,if (!ubi_dbg_chk_io (ubi))return 0 ; - buf1 =__vmalloc (len,GFP_NOFS ,PAGE_KERNEL ); + buf1 =__vmalloc (len,GFP_NOFS );if (!buf1) {ubi_err (ubi,"cannot allocate memory to check writes" );return 0 ;
@@ -1361,7 +1361,7 @@ int ubi_self_check_all_ff(struct ubi_device *ubi, int pnum, int offset, int len)if (!ubi_dbg_chk_io (ubi))return 0 ; - buf =__vmalloc (len,GFP_NOFS ,PAGE_KERNEL ); + buf =__vmalloc (len,GFP_NOFS );if (!buf) {ubi_err (ubi,"cannot allocate memory to check for 0xFFs" );return 0 ;
drivers/scsi/sd_zbc.c +1 -2
@@ -136,8 +136,7 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,while (bufsize >=SECTOR_SIZE ) { buf =__vmalloc (bufsize, -GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY, -PAGE_KERNEL ); +GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY);if (buf) { *buflen = bufsize;return buf;
fs/gfs2/dir.c +4 -5
@@ -354,7 +354,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip) hc =kmalloc (hsize,GFP_NOFS | __GFP_NOWARN);if (hc ==NULL ) - hc =__vmalloc (hsize,GFP_NOFS ,PAGE_KERNEL ); + hc =__vmalloc (hsize,GFP_NOFS );if (hc ==NULL )return ERR_PTR (-ENOMEM );
@@ -1166,7 +1166,7 @@ static int dir_double_exhash(struct gfs2_inode *dip) hc2 =kmalloc_array (hsize_bytes,2 ,GFP_NOFS | __GFP_NOWARN);if (hc2 ==NULL ) - hc2 =__vmalloc (hsize_bytes *2 ,GFP_NOFS ,PAGE_KERNEL ); + hc2 =__vmalloc (hsize_bytes *2 ,GFP_NOFS );if (!hc2)return -ENOMEM ;
@@ -1327,7 +1327,7 @@ static void *gfs2_alloc_sort_buffer(unsigned size)if (size <KMALLOC_MAX_SIZE ) ptr =kmalloc (size,GFP_NOFS | __GFP_NOWARN);if (!ptr) - ptr =__vmalloc (size,GFP_NOFS ,PAGE_KERNEL ); + ptr =__vmalloc (size,GFP_NOFS );return ptr; }
@@ -1987,8 +1987,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len, ht =kzalloc (size,GFP_NOFS | __GFP_NOWARN);if (ht ==NULL ) - ht =__vmalloc (size,GFP_NOFS | __GFP_NOWARN | __GFP_ZERO, -PAGE_KERNEL ); + ht =__vmalloc (size,GFP_NOFS | __GFP_NOWARN | __GFP_ZERO);if (!ht)return -ENOMEM ;
fs/gfs2/quota.c +1 -1
@@ -1368,7 +1368,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) sdp->sd_quota_bitmap =kzalloc (bm_size,GFP_NOFS | __GFP_NOWARN);if (sdp->sd_quota_bitmap ==NULL ) sdp->sd_quota_bitmap =__vmalloc (bm_size,GFP_NOFS | - __GFP_ZERO,PAGE_KERNEL ); + __GFP_ZERO);if (!sdp->sd_quota_bitmap)return error;
fs/nfs/blocklayout/extent_tree.c +1 -1
@@ -582,7 +582,7 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)if (!arg->layoutupdate_pages)return -ENOMEM ; - start_p =__vmalloc (buffer_size,GFP_NOFS ,PAGE_KERNEL ); + start_p =__vmalloc (buffer_size,GFP_NOFS );if (!start_p) {kfree (arg->layoutupdate_pages);return -ENOMEM ;
fs/ntfs/malloc.h +1 -1
@@ -34,7 +34,7 @@ static inline void *__ntfs_malloc(unsigned long size, gfp_t gfp_mask)/* return (void *)__get_free_page(gfp_mask); */ }if (likely ((size >>PAGE_SHIFT ) <totalram_pages ())) -return __vmalloc (size, gfp_mask,PAGE_KERNEL ); +return __vmalloc (size, gfp_mask);return NULL ; }
fs/ubifs/debug.c +1 -1
@@ -815,7 +815,7 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum)pr_err ("(pid %d) start dumping LEB %d\n" , current->pid, lnum); - buf =__vmalloc (c->leb_size,GFP_NOFS ,PAGE_KERNEL ); + buf =__vmalloc (c->leb_size,GFP_NOFS );if (!buf) {ubifs_err (c,"cannot allocate memory for dumping LEB %d" , lnum);return ;
fs/ubifs/lprops.c +1 -1
@@ -1095,7 +1095,7 @@ static int scan_check_cb(struct ubifs_info *c,return LPT_SCAN_CONTINUE ; } - buf =__vmalloc (c->leb_size,GFP_NOFS ,PAGE_KERNEL ); + buf =__vmalloc (c->leb_size,GFP_NOFS );if (!buf)return -ENOMEM ;
fs/ubifs/lpt_commit.c +2 -2
@@ -1596,7 +1596,7 @@ static int dbg_check_ltab_lnum(struct ubifs_info *c, int lnum)if (!dbg_is_chk_lprops (c))return 0 ; - buf = p =__vmalloc (c->leb_size,GFP_NOFS ,PAGE_KERNEL ); + buf = p =__vmalloc (c->leb_size,GFP_NOFS );if (!buf) {ubifs_err (c,"cannot allocate memory for ltab checking" );return 0 ;
@@ -1845,7 +1845,7 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum)void *buf, *p;pr_err ("(pid %d) start dumping LEB %d\n" , current->pid, lnum); - buf = p =__vmalloc (c->leb_size,GFP_NOFS ,PAGE_KERNEL ); + buf = p =__vmalloc (c->leb_size,GFP_NOFS );if (!buf) {ubifs_err (c,"cannot allocate memory to dump LPT" );return ;
fs/ubifs/orphan.c +1 -1
@@ -977,7 +977,7 @@ static int dbg_scan_orphans(struct ubifs_info *c, struct check_info *ci)if (c->no_orphs)return 0 ; - buf =__vmalloc (c->leb_size,GFP_NOFS ,PAGE_KERNEL ); + buf =__vmalloc (c->leb_size,GFP_NOFS );if (!buf) {ubifs_err (c,"cannot allocate memory to check orphans" );return 0 ;
fs/xfs/kmem.c +1 -1
@@ -48,7 +48,7 @@ __kmem_vmalloc(size_t size, xfs_km_flags_t flags)if (flags &KM_NOFS ) nofs_flag =memalloc_nofs_save (); - ptr =__vmalloc (size, lflags,PAGE_KERNEL ); + ptr =__vmalloc (size, lflags);if (flags &KM_NOFS )memalloc_nofs_restore (nofs_flag);
include/linux/vmalloc.h +1 -1
@@ -110,7 +110,7 @@ extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags);extern void *vmalloc_exec (unsigned long size);extern void *vmalloc_32 (unsigned long size);extern void *vmalloc_32_user (unsigned long size); -extern void *__vmalloc (unsigned long size,gfp_t gfp_mask,pgprot_t prot); +extern void *__vmalloc (unsigned long size,gfp_t gfp_mask); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node,
kernel/bpf/core.c +3 -3
@@ -82,7 +82,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flagstruct bpf_prog *fp; size =round_up (size,PAGE_SIZE ); - fp =__vmalloc (size, gfp_flags,PAGE_KERNEL ); + fp =__vmalloc (size, gfp_flags);if (fp ==NULL )return NULL ;
@@ -232,7 +232,7 @@ struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,if (ret)return NULL ; - fp =__vmalloc (size, gfp_flags,PAGE_KERNEL ); + fp =__vmalloc (size, gfp_flags);if (fp ==NULL ) {__bpf_prog_uncharge (fp_old->aux->user, delta); }else {
@@ -1089,7 +1089,7 @@ static struct bpf_prog *bpf_prog_clone_create(struct bpf_prog *fp_other,gfp_t gfp_flags =GFP_KERNEL | __GFP_ZERO | gfp_extra_flags;struct bpf_prog *fp; - fp =__vmalloc (fp_other->pages *PAGE_SIZE , gfp_flags,PAGE_KERNEL ); + fp =__vmalloc (fp_other->pages *PAGE_SIZE , gfp_flags);if (fp !=NULL ) {/* aux->prog still points to the fp_other one, so * when promoting the clone to the real program,
kernel/groups.c +1 -1
@@ -20,7 +20,7 @@ struct group_info *groups_alloc(int gidsetsize) len =sizeof (struct group_info ) +sizeof (kgid_t) * gidsetsize; gi =kmalloc (len,GFP_KERNEL_ACCOUNT |__GFP_NOWARN|__GFP_NORETRY);if (!gi) - gi =__vmalloc (len,GFP_KERNEL_ACCOUNT ,PAGE_KERNEL ); + gi =__vmalloc (len,GFP_KERNEL_ACCOUNT );if (!gi)return NULL ;
kernel/module.c +1 -2
@@ -2946,8 +2946,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,return err;/* Suck in entire file: we'll want most of it. */ - info->hdr =__vmalloc (info->len, -GFP_KERNEL | __GFP_NOWARN,PAGE_KERNEL ); + info->hdr =__vmalloc (info->len,GFP_KERNEL | __GFP_NOWARN);if (!info->hdr)return -ENOMEM ;
mm/nommu.c +7 -8
@@ -140,7 +140,7 @@ void vfree(const void *addr) }EXPORT_SYMBOL (vfree); -void *__vmalloc (unsigned long size,gfp_t gfp_mask,pgprot_t prot) +void *__vmalloc (unsigned long size,gfp_t gfp_mask) {/* * You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
@@ -152,14 +152,14 @@ EXPORT_SYMBOL(__vmalloc);void *__vmalloc_node_flags (unsigned long size,int node,gfp_t flags) { -return __vmalloc (size, flags,PAGE_KERNEL ); +return __vmalloc (size, flags); }static void *__vmalloc_user_flags (unsigned long size,gfp_t flags) {void *ret; - ret =__vmalloc (size, flags,PAGE_KERNEL ); + ret =__vmalloc (size, flags);if (ret) {struct vm_area_struct *vma;
@@ -230,7 +230,7 @@ long vwrite(char *buf, char *addr, unsigned long count)*/ void *vmalloc (unsigned long size) { -return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM,PAGE_KERNEL ); +return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM); }EXPORT_SYMBOL (vmalloc);
@@ -248,8 +248,7 @@ EXPORT_SYMBOL(vmalloc);*/ void *vzalloc (unsigned long size) { -return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, -PAGE_KERNEL ); +return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO); }EXPORT_SYMBOL (vzalloc);
@@ -302,7 +301,7 @@ EXPORT_SYMBOL(vzalloc_node);void *vmalloc_exec (unsigned long size) { -return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM,PAGE_KERNEL_EXEC ); +return __vmalloc (size,GFP_KERNEL | __GFP_HIGHMEM); }/**
@@ -314,7 +313,7 @@ void *vmalloc_exec(unsigned long size)*/ void *vmalloc_32 (unsigned long size) { -return __vmalloc (size,GFP_KERNEL ,PAGE_KERNEL ); +return __vmalloc (size,GFP_KERNEL ); }EXPORT_SYMBOL (vmalloc_32);
mm/page_alloc.c +1 -1
@@ -8238,7 +8238,7 @@ void *__init alloc_large_system_hash(const char *tablename, table =memblock_alloc_raw (size,SMP_CACHE_BYTES ); }else if (get_order (size) >=MAX_ORDER || hashdist) { - table =__vmalloc (size, gfp_flags,PAGE_KERNEL ); + table =__vmalloc (size, gfp_flags); virt = true; }else {/*
mm/percpu.c +1 -1
@@ -481,7 +481,7 @@ static void *pcpu_mem_zalloc(size_t size, gfp_t gfp)if (size <=PAGE_SIZE )return kzalloc (size, gfp);else -return __vmalloc (size, gfp | __GFP_ZERO,PAGE_KERNEL ); +return __vmalloc (size, gfp | __GFP_ZERO); }/**
mm/vmalloc.c +2 -2
@@ -2563,9 +2563,9 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, gfp_mask, prot, 0, node, caller); } -void *__vmalloc (unsigned long size,gfp_t gfp_mask,pgprot_t prot) +void *__vmalloc (unsigned long size,gfp_t gfp_mask) { -return __vmalloc_node (size,1 , gfp_mask, prot,NUMA_NO_NODE , +return __vmalloc_node (size,1 , gfp_mask,PAGE_KERNEL ,NUMA_NO_NODE ,__builtin_return_address (0 )); }EXPORT_SYMBOL (__vmalloc);
net/bridge/netfilter/ebtables.c +2 -4
@@ -1095,16 +1095,14 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof (tmp.name) -1 ] =0 ; countersize =COUNTER_OFFSET (tmp.nentries) * nr_cpu_ids; - newinfo =__vmalloc (sizeof (*newinfo) + countersize,GFP_KERNEL_ACCOUNT , -PAGE_KERNEL ); + newinfo =__vmalloc (sizeof (*newinfo) + countersize,GFP_KERNEL_ACCOUNT );if (!newinfo)return -ENOMEM ;if (countersize)memset (newinfo->counters,0 , countersize); - newinfo->entries =__vmalloc (tmp.entries_size,GFP_KERNEL_ACCOUNT , -PAGE_KERNEL ); + newinfo->entries =__vmalloc (tmp.entries_size,GFP_KERNEL_ACCOUNT );if (!newinfo->entries) { ret = -ENOMEM ; goto free_newinfo;
sound/core/memalloc.c +1 -1
@@ -143,7 +143,7 @@ int snd_dma_alloc_pages(int type, struct device *device, size_t size,break ;case SNDRV_DMA_TYPE_VMALLOC : gfp =snd_mem_get_gfp_flags (device,GFP_KERNEL | __GFP_HIGHMEM); - dmab->area =__vmalloc (size, gfp,PAGE_KERNEL ); + dmab->area =__vmalloc (size, gfp); dmab->addr =0 ;break ;#ifdef CONFIG_HAS_DMA
sound/core/pcm_memory.c +1 -1
@@ -460,7 +460,7 @@ int _snd_pcm_lib_alloc_vmalloc_buffer(struct snd_pcm_substream *substream,return 0 ;/* already large enough */ vfree (runtime->dma_area); } - runtime->dma_area =__vmalloc (size, gfp_flags,PAGE_KERNEL ); + runtime->dma_area =__vmalloc (size, gfp_flags);if (!runtime->dma_area)return -ENOMEM ; runtime->dma_bytes = size;
Signature · 1 line
2.25.1
Re: [PATCH 21/29] mm: remove the pgprot argument to __vmalloc
Quoted 9 lines · Christoph Hellwig
The pgprot argument to
__vmallocis alwaysPROT_KERNELnow, so remove it.Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Michael Kelley <[email protected]> [hyperv]--- arch/x86/hyperv/hv_init.c | 3 +--
[...]
arch/x86/hyperv/hv_init.c static int hv_cpu_init(unsigned int cpu) · line 99
Quoted 13 lines
arch/x86/hyperv/hv_init.c +1
-2@@ -95,8 +95,7 @@ static int hv_cpu_init(unsigned int cpu)* not be stopped in the case of CPU offlining and the VM will hang. */ if (!*hvp) { - *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL ); + *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO); }
Re: [PATCH 21/29] mm: remove the pgprot argument to __vmalloc
Greetings;
I recently noticed this change via the linux-next tree.
It may not be possible to edit at this late date, but the change description refers to PROT_KERNEL, which is a symbol which does not appear to exist; perhaps PAGE_KERNEL was meant? The mismatch caused me and a couple other folks some confusion briefly until we decided it was supposed to be PAGE_KERNEL; if it's not too late, editing the description to clarify so would be nice.
Many thanks.
John Dorminy
Quoted 29 lines · Wei Liu
Quoted 9 lines · Christoph Hellwig
The pgprot argument to
__vmallocis alwaysPROT_KERNELnow, so remove it.Signed-off-by Christoph Hellwig <[email protected]>Reviewed-by Michael Kelley <[email protected]> [hyperv]--- arch/x86/hyperv/hv_init.c | 3 +--[...]
arch/x86/hyperv/hv_init.c static int hv_cpu_init(unsigned int cpu) · line 95
Quoted 7 lines
arch/x86/hyperv/hv_init.c +0
-0@@ -95,8 +95,7 @@ static int hv_cpu_init(unsigned int cpu)* not be stopped in the case of CPU offlining and the VM will hang.
arch/x86/hyperv/hv_init.c static int hv_cpu_init(unsigned int cpu) · line 99
Quoted 6 lines
arch/x86/hyperv/hv_init.c +1
-2*/ if (!*hvp) { - *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL ); + *hvp =__vmalloc (PAGE_SIZE ,GFP_KERNEL | __GFP_ZERO); }Acked-by Wei Liu <[email protected]>
Re: [PATCH 21/29] mm: remove the pgprot argument to __vmalloc
Quoted 3 lines
Quoted 3 lines · Christoph Hellwig
Quoted 2 lines
The pgprot argument to
__vmallocis alwaysPROT_KERNELnow, so remove it.
Greetings;
I recently noticed this change via the linux-next tree.
It may not be possible to edit at this late date, but the change description refers to PROT_KERNEL, which is a symbol which does not appear to exist; perhaps PAGE_KERNEL was meant? The mismatch caused me and a couple other folks some confusion briefly until we decided it was supposed to be PAGE_KERNEL; if it's not too late, editing the description to clarify so would be nice.
Many thanks.
John Dorminy
Andrew Morton
maintainerRe: [PATCH 21/29] mm: remove the pgprot argument to __vmalloc
Quoted 3 lines · On Thu, 30 Apr 2020 22:38:10 -0400 John Dorminy <[email protected]> wrote:
the change
description refers toPROT_KERNEL, which is a symbol which does not appear to exist; perhapsPAGE_KERNELwas meant?
Yes, thanks, fixed.
PATCH 22/29 mm: remove the prot argument to __vmalloc_node
In reply to Christoph HellwigThis is always PAGE_KERNEL now.
--- mm/vmalloc.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-)
mm/vmalloc.c +14 -21
@@ -2401,8 +2401,7 @@ void *vmap(struct page **pages, unsigned int count,EXPORT_SYMBOL (vmap);static void *__vmalloc_node (unsigned long size,unsigned long align, -gfp_t gfp_mask,pgprot_t prot, -int node,const void *caller); +gfp_t gfp_mask,int node,const void *caller);static void *__vmalloc_area_node (struct vm_struct *area,gfp_t gfp_mask,pgprot_t prot,int node) {
@@ -2420,7 +2419,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,/* Please note that the recursion is strictly bounded. */ if (array_size >PAGE_SIZE ) { pages =__vmalloc_node (array_size,1 , nested_gfp|highmem_mask, -PAGE_KERNEL , node, area->caller); + node, area->caller); }else { pages =kmalloc_node (array_size, nested_gfp, node); }
@@ -2539,13 +2538,11 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_range);* @size: allocation size * @align: desired alignment * @gfp_mask: flags for the page level allocator -* @prot: protection mask for the allocated pages * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * -* Allocate enough pages to cover @size from the page level -* allocator with @gfp_mask flags. Map them into contiguous -* kernel virtual space, using a pagetable protection of @prot. +* Allocate enough pages to cover @size from the page level allocator with +* @gfp_mask flags. Map them into contiguous kernel virtual space. * * Reclaim modifiers in @gfp_mask - __GFP_NORETRY, __GFP_RETRY_MAYFAIL * and __GFP_NOFAIL are not supported
@@ -2556,16 +2553,15 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_range);* Return: pointer to the allocated memory or %NULL on error */ static void *__vmalloc_node (unsigned long size,unsigned long align, -gfp_t gfp_mask,pgprot_t prot, -int node,const void *caller) +gfp_t gfp_mask,int node,const void *caller) {return __vmalloc_node_range (size, align,VMALLOC_START ,VMALLOC_END , - gfp_mask, prot,0 , node, caller); + gfp_mask,PAGE_KERNEL ,0 , node, caller); }void *__vmalloc (unsigned long size,gfp_t gfp_mask) { -return __vmalloc_node (size,1 , gfp_mask,PAGE_KERNEL ,NUMA_NO_NODE , +return __vmalloc_node (size,1 , gfp_mask,NUMA_NO_NODE ,__builtin_return_address (0 )); }EXPORT_SYMBOL (__vmalloc);
@@ -2573,15 +2569,15 @@ EXPORT_SYMBOL(__vmalloc);static inline void *__vmalloc_node_flags (unsigned long size,int node,gfp_t flags) { -return __vmalloc_node (size,1 , flags,PAGE_KERNEL , - node,__builtin_return_address (0 )); +return __vmalloc_node (size,1 , flags, node, +__builtin_return_address (0 )); }void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags,void *caller) { -return __vmalloc_node (size,1 , flags,PAGE_KERNEL , node, caller); +return __vmalloc_node (size,1 , flags, node, caller); }/**
@@ -2656,8 +2652,8 @@ EXPORT_SYMBOL(vmalloc_user);*/ void *vmalloc_node (unsigned long size,int node) { -return __vmalloc_node (size,1 ,GFP_KERNEL ,PAGE_KERNEL , - node,__builtin_return_address (0 )); +return __vmalloc_node (size,1 ,GFP_KERNEL , node, +__builtin_return_address (0 )); }EXPORT_SYMBOL (vmalloc_node);
@@ -2670,9 +2666,6 @@ EXPORT_SYMBOL(vmalloc_node);* allocator and map them into contiguous kernel virtual space. * The memory allocated is set to zero. * -* For tight control over page level allocator and protection flags -* use __vmalloc_node() instead. -* * Return: pointer to the allocated memory or %NULL on error */ void *vzalloc_node (unsigned long size,int node)
@@ -2745,8 +2738,8 @@ void *vmalloc_exec(unsigned long size)*/ void *vmalloc_32 (unsigned long size) { -return __vmalloc_node (size,1 ,GFP_VMALLOC32 ,PAGE_KERNEL , -NUMA_NO_NODE ,__builtin_return_address (0 )); +return __vmalloc_node (size,1 ,GFP_VMALLOC32 ,NUMA_NO_NODE , +__builtin_return_address (0 )); }EXPORT_SYMBOL (vmalloc_32);
Signature · 1 line
2.25.1
PATCH 23/29 mm: remove both instances of __vmalloc_node_flags
In reply to Christoph HellwigThe real version just had a few callers that can open code it and remove one layer of indirection. The nommu stub was public but only had a single caller, so remove it and avoid a CONFIG_MMU ifdef in vmalloc.h.
--- include/linux/vmalloc.h | 9 --------- mm/nommu.c | 3 ++- mm/vmalloc.c | 20 ++++++-------------- 3 files changed, 8 insertions(+), 24 deletions(-)
include/linux/vmalloc.h +0 -9
@@ -115,17 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -#ifndef CONFIG_MMU -extern void *__vmalloc_node_flags (unsigned long size,int node,gfp_t flags); -static inline void *__vmalloc_node_flags_caller (unsigned long size,int node, -gfp_t flags,void *caller) -{ -return __vmalloc_node_flags (size, node, flags); -} -#else extern void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags,void *caller); -#endif extern void vfree (const void *addr);extern void vfree_atomic (const void *addr);
mm/nommu.c +2 -1
@@ -150,7 +150,8 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); -void *__vmalloc_node_flags (unsigned long size,int node,gfp_t flags) +void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags, +void *caller) {return __vmalloc (size, flags); }
mm/vmalloc.c +6 -14
@@ -2566,14 +2566,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); -static inline void *__vmalloc_node_flags (unsigned long size, -int node,gfp_t flags) -{ -return __vmalloc_node (size,1 , flags, node, -__builtin_return_address (0 )); -} - -void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags,void *caller) {
@@ -2594,8 +2586,8 @@ void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags,*/ void *vmalloc (unsigned long size) { -return __vmalloc_node_flags (size,NUMA_NO_NODE , -GFP_KERNEL ); +return __vmalloc_node (size,1 ,GFP_KERNEL ,NUMA_NO_NODE , +__builtin_return_address (0 )); }EXPORT_SYMBOL (vmalloc);
@@ -2614,8 +2606,8 @@ EXPORT_SYMBOL(vmalloc);*/ void *vzalloc (unsigned long size) { -return __vmalloc_node_flags (size,NUMA_NO_NODE , -GFP_KERNEL | __GFP_ZERO); +return __vmalloc_node (size,1 ,GFP_KERNEL | __GFP_ZERO,NUMA_NO_NODE , +__builtin_return_address (0 )); }EXPORT_SYMBOL (vzalloc);
@@ -2670,8 +2662,8 @@ EXPORT_SYMBOL(vmalloc_node);*/ void *vzalloc_node (unsigned long size,int node) { -return __vmalloc_node_flags (size, node, -GFP_KERNEL | __GFP_ZERO); +return __vmalloc_node (size,1 ,GFP_KERNEL | __GFP_ZERO, node, +__builtin_return_address (0 )); }EXPORT_SYMBOL (vzalloc_node);
Signature · 1 line
2.25.1
PATCH 24/29 mm: remove __vmalloc_node_flags_caller
In reply to Christoph HellwigJust use __vmalloc_node instead which gets and extra argument. To be able to to use __vmalloc_node in all caller make it available outside of vmalloc and implement it in nommu.c.
--- include/linux/vmalloc.h | 4 ++-- kernel/bpf/syscall.c | 5 ++--- mm/nommu.c | 4 ++-- mm/util.c | 2 +- mm/vmalloc.c | 10 +--------- 5 files changed, 8 insertions(+), 17 deletions(-)
include/linux/vmalloc.h +2 -2
@@ -115,8 +115,8 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller); -extern void *__vmalloc_node_flags_caller (unsigned long size, -int node,gfp_t flags,void *caller); +void *__vmalloc_node (unsigned long size,unsigned long align,gfp_t gfp_mask, +int node,const void *caller);extern void vfree (const void *addr);extern void vfree_atomic (const void *addr);
kernel/bpf/syscall.c +2 -3
@@ -299,9 +299,8 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)return vmalloc_user_node_flags (size, numa_node,GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags); } -return __vmalloc_node_flags_caller (size, numa_node, -GFP_KERNEL | __GFP_RETRY_MAYFAIL | - flags,__builtin_return_address (0 )); +return __vmalloc_node (size,1 ,GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, + numa_node,__builtin_return_address (0 )); }void *bpf_map_area_alloc (u64 size,int numa_node)
mm/nommu.c +2 -2
@@ -150,8 +150,8 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); -void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags, -void *caller) +void *__vmalloc_node (unsigned long size,unsigned long align,gfp_t gfp_mask, +int node,const void *caller) {return __vmalloc (size, flags); }
mm/util.c +1 -1
@@ -580,7 +580,7 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)if (ret || size <=PAGE_SIZE )return ret; -return __vmalloc_node_flags_caller (size, node, flags, +return __vmalloc_node (size,1 , flags, node,__builtin_return_address (0 )); }EXPORT_SYMBOL (kvmalloc_node);
mm/vmalloc.c +1 -9
@@ -2400,8 +2400,6 @@ void *vmap(struct page **pages, unsigned int count, }EXPORT_SYMBOL (vmap); -static void *__vmalloc_node (unsigned long size,unsigned long align, -gfp_t gfp_mask,int node,const void *caller);static void *__vmalloc_area_node (struct vm_struct *area,gfp_t gfp_mask,pgprot_t prot,int node) {
@@ -2552,7 +2550,7 @@ EXPORT_SYMBOL_GPL(__vmalloc_node_range);* * Return: pointer to the allocated memory or %NULL on error */ -static void *__vmalloc_node (unsigned long size,unsigned long align, +void *__vmalloc_node (unsigned long size,unsigned long align,gfp_t gfp_mask,int node,const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
@@ -2566,12 +2564,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); -void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags, -void *caller) -{ -return __vmalloc_node (size,1 , flags, node, caller); -} -/** * vmalloc - allocate virtually contiguous memory * @size: allocation size
Signature · 1 line
2.25.1
Re: [PATCH 24/29] mm: remove __vmalloc_node_flags_caller
Hi Christoph,
Quoted 6 lines · Christoph Hellwig
Just use
__vmalloc_nodeinstead which gets and extra argument. To be able to to use__vmalloc_nodein all caller make it available outside of vmalloc and implement it innommu.c.Signed-off-by Christoph Hellwig <[email protected]>
One more nommu failure below...
Quoted 12 lines
mm/nommu.c +2
-2@@ -150,8 +150,8 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); -void *__vmalloc_node_flags_caller (unsigned long size,int node,gfp_t flags, -void *caller) +void *__vmalloc_node (unsigned long size,unsigned long align,gfp_t gfp_mask, +int node,const void *caller) {return __vmalloc (size, flags);
Quoted 5 lines · On Mon, Apr 20, 2020 at 10:39 AM <[email protected]> wrote:
FAILED linux-next/m5272c3_defconfig/m68k-gcc8 Mon Apr 20, 18:38
http://kisskb.ellerman.id.au/kisskb/buildresult/14213623/
mm/nommu.c:164:25: error: 'flags' undeclared (first use in this function); did you mean 'class'?
"return __vmalloc(size, gfp_mask);"
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]
In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
PATCH 25/29 mm: switch the test_vmalloc module to use __vmalloc_node
In reply to Christoph HellwigNo need to export the very low-level __vmalloc_node_range when the test module can use a slightly higher level variant.
--- lib/test_vmalloc.c | 26 +++++++------------------- mm/vmalloc.c | 17 ++++++++--------- 2 files changed, 15 insertions(+), 28 deletions(-)
lib/test_vmalloc.c +7 -19
@@ -91,12 +91,8 @@ static int random_size_align_alloc_test(void)*/ size = ((rnd %10 ) +1 ) *PAGE_SIZE ; - ptr =__vmalloc_node_range (size, align, -VMALLOC_START ,VMALLOC_END , -GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL , -0 ,0 ,__builtin_return_address (0 )); - + ptr =__vmalloc_node (size, align,GFP_KERNEL | __GFP_ZERO, +__builtin_return_address (0 ));if (!ptr)return -1 ;
@@ -118,12 +114,8 @@ static int align_shift_alloc_test(void)for (i =0 ; i <BITS_PER_LONG ; i++) { align = ((unsigned long )1 ) << i; - ptr =__vmalloc_node_range (PAGE_SIZE , align, -VMALLOC_START ,VMALLOC_END , -GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL , -0 ,0 ,__builtin_return_address (0 )); - + ptr =__vmalloc_node (PAGE_SIZE , align,GFP_KERNEL | __GFP_ZERO, +__builtin_return_address (0 ));if (!ptr)return -1 ;
@@ -139,13 +131,9 @@ static int fix_align_alloc_test(void)int i;for (i =0 ; i < test_loop_count; i++) { - ptr =__vmalloc_node_range (5 *PAGE_SIZE , -THREAD_ALIGN <<1 , -VMALLOC_START ,VMALLOC_END , -GFP_KERNEL | __GFP_ZERO, -PAGE_KERNEL , -0 ,0 ,__builtin_return_address (0 )); - + ptr =__vmalloc_node (5 *PAGE_SIZE ,THREAD_ALIGN <<1 , +GFP_KERNEL | __GFP_ZERO, +__builtin_return_address (0 ));if (!ptr)return -1 ;
mm/vmalloc.c +8 -9
@@ -2522,15 +2522,6 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,return NULL ; } -/* -* This is only for performance analysis of vmalloc and stress purpose. -* It is required by vmalloc test module, therefore do not use it other -* than that. -*/ -#ifdef CONFIG_TEST_VMALLOC_MODULE -EXPORT_SYMBOL_GPL (__vmalloc_node_range); -#endif -/** * __vmalloc_node - allocate virtually contiguous memory * @size: allocation size
@@ -2556,6 +2547,14 @@ void *__vmalloc_node(unsigned long size, unsigned long align,return __vmalloc_node_range (size, align,VMALLOC_START ,VMALLOC_END , gfp_mask,PAGE_KERNEL ,0 , node, caller); } +/* +* This is only for performance analysis of vmalloc and stress purpose. +* It is required by vmalloc test module, therefore do not use it other +* than that. +*/ +#ifdef CONFIG_TEST_VMALLOC_MODULE +EXPORT_SYMBOL_GPL (__vmalloc_node); +#endif void *__vmalloc (unsigned long size,gfp_t gfp_mask) {
Signature · 1 line
2.25.1
PATCH 26/29 mm: remove vmalloc_user_node_flags
In reply to Christoph HellwigOpen code it in __bpf_map_area_alloc, which is the only caller. Also clean up __bpf_map_area_alloc to have a single vmalloc call with slightly different flags instead of the current two different calls.
For this to compile for the nommu case add a __vmalloc_node_range stub to nommu.c.
--- include/linux/vmalloc.h | 1 - kernel/bpf/syscall.c | 24 ++++++++++++++---------- mm/nommu.c | 14 ++++++++------ mm/vmalloc.c | 20 -------------------- 4 files changed, 22 insertions(+), 37 deletions(-)
include/linux/vmalloc.h +0 -1
@@ -106,7 +106,6 @@ extern void *vzalloc(unsigned long size);extern void *vmalloc_user (unsigned long size);extern void *vmalloc_node (unsigned long size,int node);extern void *vzalloc_node (unsigned long size,int node); -extern void *vmalloc_user_node_flags (unsigned long size,int node,gfp_t flags);extern void *vmalloc_exec (unsigned long size);extern void *vmalloc_32 (unsigned long size);extern void *vmalloc_32_user (unsigned long size);
kernel/bpf/syscall.c +14 -10
@@ -25,6 +25,7 @@#include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> +#include <asm/pgtable.h> #include <linux/bpf_lsm.h> #define IS_FD_ARRAY (map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -281,26 +282,29 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable)* __GFP_RETRY_MAYFAIL to avoid such situations. */ -const gfp_t flags = __GFP_NOWARN | __GFP_ZERO; +const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; +unsigned int flags =0 ; +unsigned long align =1 ;void *area;if (size >=SIZE_MAX )return NULL ;/* kmalloc()'ed memory can't be mmap()'ed */ -if (!mmapable && size <= (PAGE_SIZE <<PAGE_ALLOC_COSTLY_ORDER )) { - area =kmalloc_node (size,GFP_USER | __GFP_NORETRY | flags, +if (mmapable) { +BUG_ON (!PAGE_ALIGNED (size)); + align =SHMLBA ; + flags =VM_USERMAP ; + }else if (size <= (PAGE_SIZE <<PAGE_ALLOC_COSTLY_ORDER )) { + area =kmalloc_node (size, gfp |GFP_USER | __GFP_NORETRY, numa_node);if (area !=NULL )return area; } -if (mmapable) { -BUG_ON (!PAGE_ALIGNED (size)); -return vmalloc_user_node_flags (size, numa_node,GFP_KERNEL | - __GFP_RETRY_MAYFAIL | flags); - } -return __vmalloc_node (size,1 ,GFP_KERNEL | __GFP_RETRY_MAYFAIL | flags, - numa_node,__builtin_return_address (0 )); + +return __vmalloc_node_range (size, align,VMALLOC_START ,VMALLOC_END , + gfp |GFP_KERNEL | __GFP_RETRY_MAYFAIL,PAGE_KERNEL , + flags, numa_node,__builtin_return_address (0 )); }void *bpf_map_area_alloc (u64 size,int numa_node)
mm/nommu.c +8 -6
@@ -150,6 +150,14 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); +void *__vmalloc_node_range (unsigned long size,unsigned long align, +unsigned long start,unsigned long end,gfp_t gfp_mask, +pgprot_t prot,unsigned long vm_flags,int node, +const void *caller) +{ +return __vmalloc (size, flags); +} +void *__vmalloc_node (unsigned long size,unsigned long align,gfp_t gfp_mask,int node,const void *caller) {
@@ -180,12 +188,6 @@ void *vmalloc_user(unsigned long size) }EXPORT_SYMBOL (vmalloc_user); -void *vmalloc_user_node_flags (unsigned long size,int node,gfp_t flags) -{ -return __vmalloc_user_flags (size, flags | __GFP_ZERO); -} -EXPORT_SYMBOL (vmalloc_user_node_flags); -struct page *vmalloc_to_page (const void *addr) {return virt_to_page (addr);
mm/vmalloc.c +0 -20
@@ -2658,26 +2658,6 @@ void *vzalloc_node(unsigned long size, int node) }EXPORT_SYMBOL (vzalloc_node); -/** -* vmalloc_user_node_flags - allocate memory for userspace on a specific node -* @size: allocation size -* @node: numa node -* @flags: flags for the page level allocator -* -* The resulting memory area is zeroed so it can be mapped to userspace -* without leaking data. -* -* Return: pointer to the allocated memory or %NULL on error -*/ -void *vmalloc_user_node_flags (unsigned long size,int node,gfp_t flags) -{ -return __vmalloc_node_range (size,SHMLBA ,VMALLOC_START ,VMALLOC_END , - flags | __GFP_ZERO,PAGE_KERNEL , -VM_USERMAP , node, -__builtin_return_address (0 )); -} -EXPORT_SYMBOL (vmalloc_user_node_flags); -/** * vmalloc_exec - allocate virtually contiguous, executable memory * @size: allocation size
Signature · 1 line
2.25.1
Re: [PATCH 26/29] mm: remove vmalloc_user_node_flags
Hi Christoph,
Quoted 6 lines · Christoph Hellwig
Open code it in
__bpf_map_area_alloc, which is the only caller. Also clean up__bpf_map_area_allocto have a single vmalloc call with slightly different flags instead of the current two different calls.For this to compile for the nommu case add a
__vmalloc_node_rangestub tonommu.c.
Apparently your nommu-cross-compilers are in quarantaine? ;-)
Quoted 16 lines
Signed-off-by Christoph Hellwig <[email protected]>Acked-by Johannes Weiner <[email protected]>mm/nommu.c +6
-0@@ -150,6 +150,14 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask) }EXPORT_SYMBOL (__vmalloc); +void *__vmalloc_node_range (unsigned long size,unsigned long align, +unsigned long start,unsigned long end,gfp_t gfp_mask, +pgprot_t prot,unsigned long vm_flags,int node, +const void *caller) +{ +return __vmalloc (size, flags);
Quoted 5 lines · On Mon, Apr 20, 2020 at 10:39 AM <[email protected]> wrote:
FAILED linux-next/m5272c3_defconfig/m68k-gcc8 Mon Apr 20, 18:38
http://kisskb.ellerman.id.au/kisskb/buildresult/14213623/
mm/nommu.c:158:25: error: 'flags' undeclared (first use in this function); did you mean 'class'?
"return __vmalloc(size, gfp_mask);", I assume?
Gr{oetje,eeting}s,
Geert
--
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- [email protected]
In personal conversations with technical people, I call myself a hacker. But when I'm talking to journalists I just say "programmer" or something like that.
-- Linus Torvalds
PATCH 27/29 arm64: use __vmalloc_node in arch_alloc_vmap_stack
In reply to Christoph Hellwigarch_alloc_vmap_stack can use a slightly higher level vmalloc function.
--- arch/arm64/include/asm/vmap_stack.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)
arch/arm64/include/asm/vmap_stack.h +2 -4
@@ -19,10 +19,8 @@ static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node) {BUILD_BUG_ON (!IS_ENABLED (CONFIG_VMAP_STACK )); -return __vmalloc_node_range (stack_size,THREAD_ALIGN , -VMALLOC_START ,VMALLOC_END , -THREADINFO_GFP ,PAGE_KERNEL ,0 , node, -__builtin_return_address (0 )); +return __vmalloc_node (stack_size,THREAD_ALIGN ,THREADINFO_GFP , node, +__builtin_return_address (0 )); }#endif /* __ASM_VMAP_STACK_H */
Signature · 1 line
2.25.1
PATCH 28/29 powerpc: use __vmalloc_node in alloc_vm_stack
In reply to Christoph Hellwigalloc_vm_stack can use a slightly higher level vmalloc function.
--- arch/powerpc/kernel/irq.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
arch/powerpc/kernel/irq.c +2 -3
@@ -748,9 +748,8 @@ void do_IRQ(struct pt_regs *regs)static void *__init alloc_vm_stack (void ) { -return __vmalloc_node_range (THREAD_SIZE ,THREAD_ALIGN ,VMALLOC_START , -VMALLOC_END ,THREADINFO_GFP ,PAGE_KERNEL , -0 ,NUMA_NO_NODE , (void *)_RET_IP_); +return __vmalloc_node (THREAD_SIZE ,THREAD_ALIGN ,THREADINFO_GFP , +NUMA_NO_NODE , (void *)_RET_IP_); }static void __init vmap_irqstack_init (void )
Signature · 1 line
2.25.1
PATCH 29/29 s390: use __vmalloc_node in stack_alloc
In reply to Christoph Hellwigstack_alloc can use a slightly higher level vmalloc function.
--- arch/s390/kernel/setup.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-)
arch/s390/kernel/setup.c +3 -6
@@ -305,12 +305,9 @@ void *restart_stack __section(.data);unsigned long stack_alloc (void ) {#ifdef CONFIG_VMAP_STACK -return (unsigned long ) -__vmalloc_node_range (THREAD_SIZE ,THREAD_SIZE , -VMALLOC_START ,VMALLOC_END , -THREADINFO_GFP , -PAGE_KERNEL ,0 ,NUMA_NO_NODE , -__builtin_return_address (0 )); +return (unsigned long )__vmalloc_node (THREAD_SIZE ,THREAD_SIZE , +THREADINFO_GFP ,NUMA_NO_NODE , +__builtin_return_address (0 ));#else return __get_free_pages (GFP_KERNEL ,THREAD_SIZE_ORDER );#endif
Signature · 1 line
2.25.1