From bdebd6a2831b6fab69eb85cee74a8ba77f1a1cc2 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Mon, 20 Apr 2020 18:14:11 -0700 Subject: vmalloc: fix remap_vmalloc_range() bounds checks remap_vmalloc_range() has had various issues with the bounds checks it promises to perform ("This function checks that addr is a valid vmalloc'ed area, and that it is big enough to cover the vma") over time, e.g.: - not detecting pgoff< Signed-off-by: Andrew Morton Cc: stable@vger.kernel.org Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Martin KaFai Lau Cc: Song Liu Cc: Yonghong Song Cc: Andrii Nakryiko Cc: John Fastabend Cc: KP Singh Link: http://lkml.kernel.org/r/20200415222312.236431-1-jannh@google.com Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0507a162ccd0..a95d3cc74d79 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -137,7 +137,7 @@ extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, - unsigned long size); + unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -- cgit v1.2.3-71-gd317 From 4926627793c0a7e7db2bc674e1d06777e86d8dab Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:50:45 -0700 Subject: mm: remove __get_vm_area Switch the two remaining callers to use __get_vm_area_caller instead. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-9-hch@lst.de Signed-off-by: Linus Torvalds --- 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(-) (limited to 'include/linux/vmalloc.h') diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c index 2a976314f169..d9ac980c398c 100644 --- a/arch/powerpc/kernel/pci_64.c +++ b/arch/powerpc/kernel/pci_64.c @@ -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; diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c index 934ff84844fa..d432164b23b7 100644 --- a/arch/sh/kernel/cpu/sh4/sq.c +++ b/arch/sh/kernel/cpu/sh4/sq.c @@ -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; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a95d3cc74d79..ff69d1e037ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9a8227afa073..6e9527f131d1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2128,14 +2128,6 @@ 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) -- cgit v1.2.3-71-gd317 From ed1f324c5fed06c91f30a36aedb66f34244ab86e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:19 -0700 Subject: mm: remove map_vm_range Switch all callers to map_kernel_range, which symmetric to the unmap side (as well as the _noflush versions). Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-17-hch@lst.de Signed-off-by: Linus Torvalds --- 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(-) (limited to 'include/linux/vmalloc.h') diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst index 93cb65d52720..a1582cc79f0f 100644 --- a/Documentation/core-api/cachetlb.rst +++ b/Documentation/core-api/cachetlb.rst @@ -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. diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index ff69d1e037ca..a1e9bdc3ad9e 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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_noflush static 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_noflush static inline void set_vm_flush_reset_perms(void *addr) { } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index aab00ddee686..49ca687d8853 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -273,8 +273,8 @@ 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; @@ -2028,16 +2028,6 @@ 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) { @@ -2409,7 +2399,8 @@ 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; } @@ -2472,8 +2463,10 @@ 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: diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index ac0524330b9b..f6dc0673e62c 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -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; } diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index a0e97f6c1072..66f22e8aa529 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -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. */ -- cgit v1.2.3-71-gd317 From d4efd79a81abc7096a418ee3103f261cfb6ab634 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:27 -0700 Subject: mm: remove the prot argument from vm_map_ram This is always PAGE_KERNEL - for long term mappings with other properties vmap should be used. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-19-hch@lst.de Signed-off-by: Linus Torvalds --- 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(-) (limited to 'include/linux/vmalloc.h') diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c index 9272bef57092..debaf7b18ab5 100644 --- a/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/mock_dmabuf.c @@ -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) diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 6db60e9d5183..92072a08af25 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -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 */ diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c index 1a4f0ca87c7c..c66fda4a65e4 100644 --- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c +++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c @@ -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) diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 5d2d81940679..7628816f2453 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -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) diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 9ec3eaf1c618..65538d18e64f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -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(); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a1e9bdc3ad9e..5488cea5ef11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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 diff --git a/mm/nommu.c b/mm/nommu.c index 318df4e236c9..4f07b7ef0297 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -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; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3b9b1366baa3..9848156a1c6a 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1835,7 +1835,7 @@ 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; @@ -1859,7 +1859,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro kasan_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; } -- cgit v1.2.3-71-gd317 From 88dca4ca5a93d2c09e5bbc6a62fbfc3af83c4fca Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:40 -0700 Subject: mm: remove the pgprot argument to __vmalloc The pgprot argument to __vmalloc is always PAGE_KERNEL now, so remove it. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Reviewed-by: Michael Kelley [hyperv] Acked-by: Gao Xiang [erofs] Acked-by: Peter Zijlstra (Intel) Acked-by: Wei Liu Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-22-hch@lst.de Signed-off-by: Linus Torvalds --- 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(-) (limited to 'include/linux/vmalloc.h') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 697ddd2afef9..e2137070386a 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -97,8 +97,7 @@ 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) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0a6b35353fc7..e94b3de564d6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1279,8 +1279,7 @@ extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static 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); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 89f7f3aebd31..5573a97f1520 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -336,8 +336,7 @@ 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); diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 15e99697234a..df53dca5d02c 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -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; } diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index 648cf0207309..706af0304ca4 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -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"); diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c index 9a967a2e83dd..6e677ff62cc9 100644 --- a/drivers/lightnvm/pblk-init.c +++ b/drivers/lightnvm/pblk-init.c @@ -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); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 2d519c223562..d1786cfd7f22 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -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); } /* diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c index b57b84fb97d0..14d890b00d2c 100644 --- a/drivers/mtd/ubi/io.c +++ b/drivers/mtd/ubi/io.c @@ -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; diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index f45c22b09726..8be27426aa66 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -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; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index c3f7732415be..c0f2875c946c 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -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; diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 8259fef3f986..4b67d47a7e00 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1365,7 +1365,7 @@ 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; diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index 7a57ff2528af..8f7cff7a4293 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -582,7 +582,7 @@ retry: 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; diff --git a/fs/ntfs/malloc.h b/fs/ntfs/malloc.h index 842b0bfc3ac9..7068425735f1 100644 --- a/fs/ntfs/malloc.h +++ b/fs/ntfs/malloc.h @@ -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; } diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 0f5a480fe264..31288d8fa2ce 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -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; diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 29826c51883a..22bfda158f7f 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -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; diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index ff5e0411cf2d..d76a19e460cd 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -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; diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c index 283f9eb48410..2c294085ffed 100644 --- a/fs/ubifs/orphan.c +++ b/fs/ubifs/orphan.c @@ -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; diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 1da94237a8cf..f1366475c389 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -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); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 5488cea5ef11..1c278e030599 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 14aa1f74dd10..cf6fe9107f5c 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -82,7 +82,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag struct 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, diff --git a/kernel/groups.c b/kernel/groups.c index daae2f2dc6d4..6ee6691f6839 100644 --- a/kernel/groups.c +++ b/kernel/groups.c @@ -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; diff --git a/kernel/module.c b/kernel/module.c index 646f1e2330d2..086618a0058f 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -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; diff --git a/mm/nommu.c b/mm/nommu.c index 4f07b7ef0297..2df549adb22b 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -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); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cc406ee17ad9..45ad73122e82 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8244,7 +8244,7 @@ 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 { /* diff --git a/mm/percpu.c b/mm/percpu.c index 7da7d7737dab..696367b18222 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -482,7 +482,7 @@ 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); } /** diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d7c7108181a..11194ae18f23 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2564,9 +2564,9 @@ 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); diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 78db58c7aec2..7e869284e052 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -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; diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index a83553fbedf0..bea46ed157a6 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -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 diff --git a/sound/core/pcm_memory.c b/sound/core/pcm_memory.c index fcab37ea6641..860935e3aea4 100644 --- a/sound/core/pcm_memory.c +++ b/sound/core/pcm_memory.c @@ -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; -- cgit v1.2.3-71-gd317 From 4d39d7285f45cc6c72b850f040d3addd626658e4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:49 -0700 Subject: mm: remove both instances of __vmalloc_node_flags The 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. Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Link: http://lkml.kernel.org/r/20200414131348.444715-24-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 9 --------- mm/nommu.c | 3 ++- mm/vmalloc.c | 20 ++++++-------------- 3 files changed, 8 insertions(+), 24 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 1c278e030599..91d143783458 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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); diff --git a/mm/nommu.c b/mm/nommu.c index 2df549adb22b..9553efa59787 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -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); } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c9343f1a7268..e9f730092c81 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2567,14 +2567,6 @@ 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) { @@ -2595,8 +2587,8 @@ 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); @@ -2615,8 +2607,8 @@ 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); @@ -2671,8 +2663,8 @@ 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); -- cgit v1.2.3-71-gd317 From 2b9059489c839e67ca9254913325e18cea11a980 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:51:53 -0700 Subject: mm: remove __vmalloc_node_flags_caller Just 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. [akpm@linux-foundation.org: fix nommu build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: Johannes Weiner Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-25-hch@lst.de Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 4 ++-- kernel/bpf/syscall.c | 5 ++--- mm/nommu.c | 6 +++--- mm/util.c | 2 +- mm/vmalloc.c | 10 +--------- 5 files changed, 9 insertions(+), 18 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 91d143783458..964d58a060ca 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e6dee19a668..9c1cf7a87fb3 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -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) diff --git a/mm/nommu.c b/mm/nommu.c index 9553efa59787..08848fc18672 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -150,10 +150,10 @@ 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); + return __vmalloc(size, gfp_mask); } static void *__vmalloc_user_flags(unsigned long size, gfp_t flags) diff --git a/mm/util.c b/mm/util.c index 988d11e6c17c..6d5868adbe18 100644 --- a/mm/util.c +++ b/mm/util.c @@ -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); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e9f730092c81..88f9971a7d6e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2401,8 +2401,6 @@ 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) { @@ -2553,7 +2551,7 @@ 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, @@ -2567,12 +2565,6 @@ 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 -- cgit v1.2.3-71-gd317 From 041de93ff86fc500aa73e5360039c95f4d31b95f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 1 Jun 2020 21:52:02 -0700 Subject: mm: remove vmalloc_user_node_flags Open 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. [akpm@linux-foundation.org: fix nommu.c build] Signed-off-by: Christoph Hellwig Signed-off-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Cc: Christian Borntraeger Cc: Christophe Leroy Cc: Daniel Vetter Cc: David Airlie Cc: Gao Xiang Cc: Greg Kroah-Hartman Cc: Haiyang Zhang Cc: "K. Y. Srinivasan" Cc: Laura Abbott Cc: Mark Rutland Cc: Michael Kelley Cc: Minchan Kim Cc: Nitin Gupta Cc: Robin Murphy Cc: Sakari Ailus Cc: Stephen Hemminger Cc: Sumit Semwal Cc: Wei Liu Cc: Benjamin Herrenschmidt Cc: Catalin Marinas Cc: Heiko Carstens Cc: Paul Mackerras Cc: Vasily Gorbik Cc: Will Deacon Cc: Stephen Rothwell Link: http://lkml.kernel.org/r/20200414131348.444715-27-hch@lst.de Signed-off-by: Linus Torvalds --- 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(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 964d58a060ca..3332926295d4 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -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); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 9c1cf7a87fb3..42c7a42fc9c8 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #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) diff --git a/mm/nommu.c b/mm/nommu.c index 08848fc18672..371697bf372d 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -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, gfp_mask); +} + 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); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 931106654d1f..410bfe26ee73 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2659,26 +2659,6 @@ 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 -- cgit v1.2.3-71-gd317 From 2ba3e6947aed9bb9575eb1603c0ac6e39185d32a Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:22 -0700 Subject: mm/vmalloc: track which page-table levels were modified Track at which levels in the page-table entries were modified by vmap/vunmap. After the page-table has been modified, use that information do decide whether the new arch_sync_kernel_mappings() needs to be called. [akpm@linux-foundation.org: map_kernel_range_noflush() needs the arch_sync_kernel_mappings() call] Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-3-joro@8bytes.org Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 16 +++++++++ mm/vmalloc.c | 95 +++++++++++++++++++++++++++++++++++-------------- 2 files changed, 85 insertions(+), 26 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 3332926295d4..0efc35dc5b25 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -133,6 +133,22 @@ extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, void vmalloc_sync_mappings(void); void vmalloc_sync_unmappings(void); +/* + * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values + * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() + * needs to be called. + */ +#ifndef ARCH_PAGE_TABLE_SYNC_MASK +#define ARCH_PAGE_TABLE_SYNC_MASK 0 +#endif + +/* + * There is no default implementation for arch_sync_kernel_mappings(). It is + * relied upon the compiler to optimize calls out if ARCH_PAGE_TABLE_SYNC_MASK + * is 0. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end); + /* * Lowlevel-APIs (not for driver use!) */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 410bfe26ee73..154e3396154c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -69,7 +69,8 @@ static void free_work(struct work_struct *w) /*** Page table manipulation functions ***/ -static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) +static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pte_t *pte; @@ -78,59 +79,81 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end) pte_t ptent = ptep_get_and_clear(&init_mm, addr, pte); WARN_ON(!pte_none(ptent) && !pte_present(ptent)); } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; } -static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) +static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; + int cleared; pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (pmd_clear_huge(pmd)) + + cleared = pmd_clear_huge(pmd); + if (cleared || pmd_bad(*pmd)) + *mask |= PGTBL_PMD_MODIFIED; + + if (cleared) continue; if (pmd_none_or_clear_bad(pmd)) continue; - vunmap_pte_range(pmd, addr, next); + vunmap_pte_range(pmd, addr, next, mask); } while (pmd++, addr = next, addr != end); } -static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end) +static void vunmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; + int cleared; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - if (pud_clear_huge(pud)) + + cleared = pud_clear_huge(pud); + if (cleared || pud_bad(*pud)) + *mask |= PGTBL_PUD_MODIFIED; + + if (cleared) continue; if (pud_none_or_clear_bad(pud)) continue; - vunmap_pmd_range(pud, addr, next); + vunmap_pmd_range(pud, addr, next, mask); } while (pud++, addr = next, addr != end); } -static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) +static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, + pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; + int cleared; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); - if (p4d_clear_huge(p4d)) + + cleared = p4d_clear_huge(p4d); + if (cleared || p4d_bad(*p4d)) + *mask |= PGTBL_P4D_MODIFIED; + + if (cleared) continue; if (p4d_none_or_clear_bad(p4d)) continue; - vunmap_pud_range(p4d, addr, next); + vunmap_pud_range(p4d, addr, next, mask); } while (p4d++, addr = next, addr != end); } /** * unmap_kernel_range_noflush - unmap kernel VM area - * @addr: start of the VM area to unmap + * @start: 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 @@ -141,24 +164,33 @@ static void vunmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end) * 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) +void unmap_kernel_range_noflush(unsigned long start, unsigned long size) { - unsigned long end = addr + size; + unsigned long end = start + size; unsigned long next; pgd_t *pgd; + unsigned long addr = start; + pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); + start = addr; pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; if (pgd_none_or_clear_bad(pgd)) continue; - vunmap_p4d_range(pgd, addr, next); + vunmap_p4d_range(pgd, addr, next, &mask); } while (pgd++, addr = next, addr != end); + + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); } static int vmap_pte_range(pmd_t *pmd, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pte_t *pte; @@ -167,7 +199,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, * callers keep track of where we're up to. */ - pte = pte_alloc_kernel(pmd, addr); + pte = pte_alloc_kernel_track(pmd, addr, mask); if (!pte) return -ENOMEM; do { @@ -180,55 +212,59 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, set_pte_at(&init_mm, addr, pte, mk_pte(page, prot)); (*nr)++; } while (pte++, addr += PAGE_SIZE, addr != end); + *mask |= PGTBL_PTE_MODIFIED; return 0; } static int vmap_pmd_range(pud_t *pud, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pmd_t *pmd; unsigned long next; - pmd = pmd_alloc(&init_mm, pud, addr); + pmd = pmd_alloc_track(&init_mm, pud, addr, mask); if (!pmd) return -ENOMEM; do { next = pmd_addr_end(addr, end); - if (vmap_pte_range(pmd, addr, next, prot, pages, nr)) + if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pmd++, addr = next, addr != end); return 0; } static int vmap_pud_range(p4d_t *p4d, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { pud_t *pud; unsigned long next; - pud = pud_alloc(&init_mm, p4d, addr); + pud = pud_alloc_track(&init_mm, p4d, addr, mask); if (!pud) return -ENOMEM; do { next = pud_addr_end(addr, end); - if (vmap_pmd_range(pud, addr, next, prot, pages, nr)) + if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (pud++, addr = next, addr != end); return 0; } static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, - unsigned long end, pgprot_t prot, struct page **pages, int *nr) + unsigned long end, pgprot_t prot, struct page **pages, int *nr, + pgtbl_mod_mask *mask) { p4d_t *p4d; unsigned long next; - p4d = p4d_alloc(&init_mm, pgd, addr); + p4d = p4d_alloc_track(&init_mm, pgd, addr, mask); if (!p4d) return -ENOMEM; do { next = p4d_addr_end(addr, end); - if (vmap_pud_range(p4d, addr, next, prot, pages, nr)) + if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask)) return -ENOMEM; } while (p4d++, addr = next, addr != end); return 0; @@ -255,21 +291,28 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, int map_kernel_range_noflush(unsigned long addr, unsigned long size, pgprot_t prot, struct page **pages) { + unsigned long start = addr; unsigned long end = addr + size; unsigned long next; pgd_t *pgd; int err = 0; int nr = 0; + pgtbl_mod_mask mask = 0; BUG_ON(addr >= end); pgd = pgd_offset_k(addr); do { next = pgd_addr_end(addr, end); - err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr); + if (pgd_bad(*pgd)) + mask |= PGTBL_PGD_MODIFIED; + err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask); if (err) return err; } while (pgd++, addr = next, addr != end); + if (mask & ARCH_PAGE_TABLE_SYNC_MASK) + arch_sync_kernel_mappings(start, end); + return 0; } -- cgit v1.2.3-71-gd317 From 73f693c3a705756032c2863bfb37570276902d7d Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 1 Jun 2020 21:52:36 -0700 Subject: mm: remove vmalloc_sync_(un)mappings() These functions are not needed anymore because the vmalloc and ioremap mappings are now synchronized when they are created or torn down. Remove all callers and function definitions. Signed-off-by: Joerg Roedel Signed-off-by: Andrew Morton Tested-by: Steven Rostedt (VMware) Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Dave Hansen Cc: "H . Peter Anvin" Cc: Ingo Molnar Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Cc: Vlastimil Babka Link: http://lkml.kernel.org/r/20200515140023.25469-7-joro@8bytes.org Signed-off-by: Linus Torvalds --- arch/x86/mm/fault.c | 37 ------------------------------------- drivers/acpi/apei/ghes.c | 6 ------ include/linux/vmalloc.h | 2 -- kernel/notifier.c | 1 - kernel/trace/trace.c | 12 ------------ mm/nommu.c | 12 ------------ mm/vmalloc.c | 21 --------------------- 7 files changed, 91 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index edeb2adaf31f..255fc631b042 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -214,26 +214,6 @@ void arch_sync_kernel_mappings(unsigned long start, unsigned long end) } } -static void vmalloc_sync(void) -{ - unsigned long address; - - if (SHARED_KERNEL_PMD) - return; - - arch_sync_kernel_mappings(VMALLOC_START, VMALLOC_END); -} - -void vmalloc_sync_mappings(void) -{ - vmalloc_sync(); -} - -void vmalloc_sync_unmappings(void) -{ - vmalloc_sync(); -} - /* * 32-bit: * @@ -336,23 +316,6 @@ out: #else /* CONFIG_X86_64: */ -void vmalloc_sync_mappings(void) -{ - /* - * 64-bit mappings might allocate new p4d/pud pages - * that need to be propagated to all tasks' PGDs. - */ - sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END); -} - -void vmalloc_sync_unmappings(void) -{ - /* - * Unmappings never allocate or free p4d/pud pages. - * No work is required here. - */ -} - /* * 64-bit: * diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 24c9642e8fc7..aabe9c5ee515 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -167,12 +167,6 @@ int ghes_estatus_pool_init(int num_ghes) if (!addr) goto err_pool_alloc; - /* - * New allocation must be visible in all pgd before it can be found by - * an NMI allocating from the pool. - */ - vmalloc_sync_mappings(); - rc = gen_pool_add(ghes_estatus_pool, addr, PAGE_ALIGN(len), -1); if (rc) goto err_pool_add; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0efc35dc5b25..48bb681e6c2a 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -130,8 +130,6 @@ extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); -void vmalloc_sync_mappings(void); -void vmalloc_sync_unmappings(void); /* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values diff --git a/kernel/notifier.c b/kernel/notifier.c index 5989bbb93039..84c987dfbe03 100644 --- a/kernel/notifier.c +++ b/kernel/notifier.c @@ -519,7 +519,6 @@ NOKPROBE_SYMBOL(notify_die); int register_die_notifier(struct notifier_block *nb) { - vmalloc_sync_mappings(); return atomic_notifier_chain_register(&die_chain, nb); } EXPORT_SYMBOL_GPL(register_die_notifier); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 29615f15a820..f12e99b387b2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8527,18 +8527,6 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) allocate_snapshot = false; #endif - /* - * Because of some magic with the way alloc_percpu() works on - * x86_64, we need to synchronize the pgd of all the tables, - * otherwise the trace events that happen in x86_64 page fault - * handlers can't cope with accessing the chance that a - * alloc_percpu()'d memory might be touched in the page fault trace - * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() - * calls in tracing, because something might get triggered within a - * page fault trace event! - */ - vmalloc_sync_mappings(); - return 0; } diff --git a/mm/nommu.c b/mm/nommu.c index 371697bf372d..dfae55f41901 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -371,18 +371,6 @@ void vm_unmap_aliases(void) } EXPORT_SYMBOL_GPL(vm_unmap_aliases); -/* - * Implement a stub for vmalloc_sync_[un]mapping() if the architecture - * chose not to have one. - */ -void __weak vmalloc_sync_mappings(void) -{ -} - -void __weak vmalloc_sync_unmappings(void) -{ -} - struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes) { BUG(); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 154e3396154c..1e94497b7388 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1353,12 +1353,6 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end) if (unlikely(valist == NULL)) return false; - /* - * First make sure the mappings are removed from all page-tables - * before they are freed. - */ - vmalloc_sync_unmappings(); - /* * TODO: to calculate a flush range without looping. * The list can be up to lazy_max_pages() elements. @@ -3089,21 +3083,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, } EXPORT_SYMBOL(remap_vmalloc_range); -/* - * Implement stubs for vmalloc_sync_[un]mappings () if the architecture chose - * not to have one. - * - * The purpose of this function is to make sure the vmalloc area - * mappings are identical in all page-tables in the system. - */ -void __weak vmalloc_sync_mappings(void) -{ -} - -void __weak vmalloc_sync_unmappings(void) -{ -} - static int f(pte_t *pte, unsigned long addr, void *data) { pte_t ***p = data; -- cgit v1.2.3-71-gd317